diff options
| author | Stephen Rothwell <sfr@canb.auug.org.au> | 2013-02-07 17:04:23 +1100 |
|---|---|---|
| committer | Stephen Rothwell <sfr@canb.auug.org.au> | 2013-02-07 17:04:23 +1100 |
| commit | 89fa7d4989785694ba720133c0fd3d7485cd059a (patch) | |
| tree | ef062d89ed62defaed0856e9e0dff6e130b54aff | |
| parent | e61c0ad53a8281dca1f392a7654e9b1f2210cb91 (diff) | |
| parent | f66cce24892aa254a556516339c8307a1a6fd165 (diff) | |
Merge branch 'akpm/master'
701 files changed, 20382 insertions, 7438 deletions
diff --git a/Documentation/ABI/testing/sysfs-class-bdi b/Documentation/ABI/testing/sysfs-class-bdi index 5f500977b42f..d773d5697cf5 100644 --- a/Documentation/ABI/testing/sysfs-class-bdi +++ b/Documentation/ABI/testing/sysfs-class-bdi @@ -48,3 +48,8 @@ max_ratio (read-write) most of the write-back cache. For example in case of an NFS mount that is prone to get stuck, or a FUSE mount which cannot be trusted to play fair. + +stable_pages_required (read-only) + + If set, the backing device requires that all pages comprising a write + request must not be changed until writeout is complete. diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-ksm b/Documentation/ABI/testing/sysfs-kernel-mm-ksm new file mode 100644 index 000000000000..73e653ee2481 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-kernel-mm-ksm @@ -0,0 +1,52 @@ +What: /sys/kernel/mm/ksm +Date: September 2009 +KernelVersion: 2.6.32 +Contact: Linux memory management mailing list <linux-mm@kvack.org> +Description: Interface for Kernel Samepage Merging (KSM) + +What: /sys/kernel/mm/ksm/full_scans +What: /sys/kernel/mm/ksm/pages_shared +What: /sys/kernel/mm/ksm/pages_sharing +What: /sys/kernel/mm/ksm/pages_to_scan +What: /sys/kernel/mm/ksm/pages_unshared +What: /sys/kernel/mm/ksm/pages_volatile +What: /sys/kernel/mm/ksm/run +What: /sys/kernel/mm/ksm/sleep_millisecs +Date: September 2009 +Contact: Linux memory management mailing list <linux-mm@kvack.org> +Description: Kernel Samepage Merging daemon sysfs interface + + full_scans: how many times all mergeable areas have been + scanned. + + pages_shared: how many shared pages are being used. + + pages_sharing: how many more sites are sharing them i.e. how + much saved. + + pages_to_scan: how many present pages to scan before ksmd goes + to sleep. + + pages_unshared: how many pages unique but repeatedly checked + for merging. + + pages_volatile: how many pages changing too fast to be placed + in a tree. + + run: write 0 to disable ksm, read 0 while ksm is disabled. + write 1 to run ksm, read 1 while ksm is running. + write 2 to disable ksm and unmerge all its pages. + + sleep_millisecs: how many milliseconds ksm should sleep between + scans. + + See Documentation/vm/ksm.txt for more information. + +What: /sys/kernel/mm/ksm/merge_across_nodes +Date: January 2013 +KernelVersion: 3.9 +Contact: Linux memory management mailing list <linux-mm@kvack.org> +Description: Control merging pages across different NUMA nodes. + + When it is set to 0 only pages from the same node are merged, + otherwise pages from all nodes can be merged together (default). diff --git a/Documentation/DMA-API-HOWTO.txt b/Documentation/DMA-API-HOWTO.txt index 4a4fb295ceef..14129f149a75 100644 --- a/Documentation/DMA-API-HOWTO.txt +++ b/Documentation/DMA-API-HOWTO.txt @@ -488,9 +488,10 @@ will invoke the generic mapping error check interface. Doing so will ensure that the mapping code will work correctly on all dma implementations without any dependency on the specifics of the underlying implementation. Using the returned address without checking for errors could result in failures ranging -from panics to silent data corruption. Couple of example of incorrect ways to -check for errors that make assumptions about the underlying dma implementation -are as follows and these are applicable to dma_map_page() as well. +from panics to silent data corruption. A couple of examples of incorrect ways +to check for errors that make assumptions about the underlying dma +implementation are as follows and these are applicable to dma_map_page() as +well. Incorrect example 1: dma_addr_t dma_handle; @@ -751,7 +752,7 @@ Example 1: dma_unmap_single(dma_handle1); map_error_handling1: -Example 2: (if buffers are allocated a loop, unmap all mapped buffers when +Example 2: (if buffers are allocated in a loop, unmap all mapped buffers when mapping error is detected in the middle) dma_addr_t dma_addr; diff --git a/Documentation/IPMI.txt b/Documentation/IPMI.txt index 16eb4c9e9233..f13c9132e9f2 100644 --- a/Documentation/IPMI.txt +++ b/Documentation/IPMI.txt @@ -348,34 +348,40 @@ You can change this at module load time (for a module) with: modprobe ipmi_si.o type=<type1>,<type2>.... ports=<port1>,<port2>... addrs=<addr1>,<addr2>... - irqs=<irq1>,<irq2>... trydefaults=[0|1] + irqs=<irq1>,<irq2>... regspacings=<sp1>,<sp2>,... regsizes=<size1>,<size2>,... regshifts=<shift1>,<shift2>,... slave_addrs=<addr1>,<addr2>,... force_kipmid=<enable1>,<enable2>,... kipmid_max_busy_us=<ustime1>,<ustime2>,... unload_when_empty=[0|1] + trydefaults=[0|1] trydmi=[0|1] tryacpi=[0|1] + tryplatform=[0|1] trypci=[0|1] -Each of these except si_trydefaults is a list, the first item for the +Each of these except try... items is a list, the first item for the first interface, second item for the second interface, etc. The si_type may be either "kcs", "smic", or "bt". If you leave it blank, it defaults to "kcs". -If you specify si_addrs as non-zero for an interface, the driver will +If you specify addrs as non-zero for an interface, the driver will use the memory address given as the address of the device. This overrides si_ports. -If you specify si_ports as non-zero for an interface, the driver will +If you specify ports as non-zero for an interface, the driver will use the I/O port given as the device address. -If you specify si_irqs as non-zero for an interface, the driver will +If you specify irqs as non-zero for an interface, the driver will attempt to use the given interrupt for the device. -si_trydefaults sets whether the standard IPMI interface at 0xca2 and +trydefaults sets whether the standard IPMI interface at 0xca2 and any interfaces specified by ACPE are tried. By default, the driver tries it, set this value to zero to turn this off. +The other try... items disable discovery by their corresponding +names. These are all enabled by default, set them to zero to disable +them. The tryplatform disables openfirmware. + The next three parameters have to do with register layout. The registers used by the interfaces may not appear at successive locations and they may not be in 8-bit registers. These parameters diff --git a/Documentation/cgroups/blkio-controller.txt b/Documentation/cgroups/blkio-controller.txt index 1b70843c574e..da272c8f44e7 100644 --- a/Documentation/cgroups/blkio-controller.txt +++ b/Documentation/cgroups/blkio-controller.txt @@ -75,7 +75,7 @@ Throttling/Upper Limit policy mount -t cgroup -o blkio none /sys/fs/cgroup/blkio - Specify a bandwidth rate on particular device for root group. The format - for policy is "<major>:<minor> <byes_per_second>". + for policy is "<major>:<minor> <bytes_per_second>". echo "8:16 1048576" > /sys/fs/cgroup/blkio/blkio.throttle.read_bps_device diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt index 8b8c28b9864c..addb1f110e9a 100644 --- a/Documentation/cgroups/memory.txt +++ b/Documentation/cgroups/memory.txt @@ -70,6 +70,7 @@ Brief summary of control files. memory.move_charge_at_immigrate # set/show controls of moving charges memory.oom_control # set/show oom controls. memory.numa_stat # show the number of memory usage per numa node + memory.dangling_memcgs # show debugging information about dangling groups memory.kmem.limit_in_bytes # set/show hard limit for kernel memory memory.kmem.usage_in_bytes # show current kernel memory allocation @@ -577,6 +578,21 @@ unevictable=<total anon pages> N0=<node 0 pages> N1=<node 1 pages> ... And we have total = file + anon + unevictable. +5.7 dangling_memcgs + +This file will only be ever present in the root cgroup, if the option +CONFIG_MEMCG_DEBUG_ASYNC_DESTROY is set. When a memcg is destroyed, the memory +consumed by it may not be immediately freed. This is because when some +extensions are used, such as swap or kernel memory, objects can outlive the +group and hold a reference to it. + +If this is the case, the dangling_memcgs file will show information about what +are the memcgs still alive, and which references are still preventing it to be +freed. There is nothing wrong with that, but it is very useful when debugging, +to know where this memory is being held. This is a developer-oriented debugging +facility only, and no guarantees of interface stability will be given. The file +is read-only, and has the sole purpose of displaying information. + 6. Hierarchy support The memory controller supports a deep hierarchy and hierarchical accounting. diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 927bf5a2eb76..634edc2f2115 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1644,6 +1644,36 @@ bytes respectively. Such letter suffixes can also be entirely omitted. that the amount of memory usable for all allocations is not too small. + movablemem_map=acpi + [KNL,X86,IA-64,PPC] This parameter is similar to + memmap except it specifies the memory map of + ZONE_MOVABLE. + This option inform the kernel to use Hot Pluggable bit + in flags from SRAT from ACPI BIOS to determine which + memory devices could be hotplugged. The corresponding + memory ranges will be set as ZONE_MOVABLE. + + movablemem_map=nn[KMG]@ss[KMG] + [KNL,X86,IA-64,PPC] This parameter is similar to + memmap except it specifies the memory map of + ZONE_MOVABLE. + If user specifies memory ranges, the info in SRAT will + be ingored. And it works like the following: + - If more ranges are all within one node, then from + lowest ss to the end of the node will be ZONE_MOVABLE. + - If a range is within a node, then from ss to the end + of the node will be ZONE_MOVABLE. + - If a range covers two or more nodes, then from ss to + the end of the 1st node will be ZONE_MOVABLE, and all + the rest nodes will only have ZONE_MOVABLE. + If memmap is specified at the same time, the + movablemem_map will be limited within the memmap + areas. If kernelcore or movablecore is also specified, + movablemem_map will have higher priority to be + satisfied. So the administrator should be careful that + the amount of movablemem_map areas are not too large. + Otherwise kernel won't have enough memory to start. + MTD_Partition= [MTD] Format: <name>,<region-number>,<size>,<offset> diff --git a/Documentation/printk-formats.txt b/Documentation/printk-formats.txt index 8ffb274367c7..e8a6aa473bab 100644 --- a/Documentation/printk-formats.txt +++ b/Documentation/printk-formats.txt @@ -53,6 +53,14 @@ Struct Resources: For printing struct resources. The 'R' and 'r' specifiers result in a printed resource with ('R') or without ('r') a decoded flags member. +Physical addresses: + + %pa 0x01234567 or 0x0123456789abcdef + + For printing a phys_addr_t type (and its derivatives, such as + resource_size_t) which can vary based on build options, regardless of + the width of the CPU data path. Passed by reference. + Raw buffer as a hex string: %*ph 00 01 02 ... 3f %*phC 00:01:02: ... :3f @@ -150,9 +158,9 @@ s64 SHOULD be printed with %lld/%llx, (long long): printk("%lld", (long long)s64_var); If <type> is dependent on a config option for its size (e.g., sector_t, -blkcnt_t, phys_addr_t, resource_size_t) or is architecture-dependent -for its size (e.g., tcflag_t), use a format specifier of its largest -possible type and explicitly cast to it. Example: +blkcnt_t) or is architecture-dependent for its size (e.g., tcflag_t), use a +format specifier of its largest possible type and explicitly cast to it. +Example: printk("test: sector number/total blocks: %llu/%llu\n", (unsigned long long)sector, (unsigned long long)blockcount); diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index 078701fdbd4d..21ad1815be8c 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -138,18 +138,39 @@ Setting this to zero disables periodic writeback altogether. drop_caches -Writing to this will cause the kernel to drop clean caches, dentries and -inodes from memory, causing that memory to become free. +Writing to this will cause the kernel to drop clean caches, as well as +reclaimable slab objects like dentries and inodes. Once dropped, their +memory becomes free. To free pagecache: echo 1 > /proc/sys/vm/drop_caches -To free dentries and inodes: +To free reclaimable slab objects (includes dentries and inodes): echo 2 > /proc/sys/vm/drop_caches -To free pagecache, dentries and inodes: +To free slab objects and pagecache: echo 3 > /proc/sys/vm/drop_caches -As this is a non-destructive operation and dirty objects are not freeable, the -user should run `sync' first. +This is a non-destructive operation and will not free any dirty objects. +To increase the number of objects freed by this operation, the user may run +`sync' prior to writing to /proc/sys/vm/drop_caches. This will minimize the +number of dirty objects on the system and create more candidates to be +dropped. + +This file is not a means to control the growth of the various kernel caches +(inodes, dentries, pagecache, etc...) These objects are automatically +reclaimed by the kernel when memory is needed elsewhere on the system. + +Use of this file can cause performance problems. Since it discards cached +objects, it may cost a significant amount of I/O and CPU to recreate the +dropped objects, especially if they were under heavy use. Because of this, +use outside of a testing or debugging environment is not recommended. + +You may see informational messages in your kernel log when this file is +used: + + cat (1234): dropped kernel caches: 3 + +These are informational only. They do not mean that anything is wrong +with your system. ============================================================== diff --git a/Documentation/vm/ksm.txt b/Documentation/vm/ksm.txt index b392e496f816..25cc89ba811b 100644 --- a/Documentation/vm/ksm.txt +++ b/Documentation/vm/ksm.txt @@ -58,6 +58,13 @@ sleep_millisecs - how many milliseconds ksmd should sleep before next scan e.g. "echo 20 > /sys/kernel/mm/ksm/sleep_millisecs" Default: 20 (chosen for demonstration purposes) +merge_across_nodes - specifies if pages from different numa nodes can be merged. + When set to 0, ksm merges only pages which physically + reside in the memory area of same NUMA node. It brings + lower latency to access to shared page. Value can be + changed only when there is no ksm shared pages in system. + Default: 1 + run - set 0 to stop ksmd from running but keep merged pages, set 1 to run ksmd e.g. "echo 1 > /sys/kernel/mm/ksm/run", set 2 to stop ksmd and unmerge all pages currently merged, diff --git a/MAINTAINERS b/MAINTAINERS index a0f3ce5a1a9f..c4cd5c10cf0d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1996,7 +1996,8 @@ F: drivers/misc/* CHECKPATCH M: Andy Whitcroft <apw@canonical.com> -S: Supported +M: Joe Perches <joe@perches.com> +S: Maintained F: scripts/checkpatch.pl CHINESE DOCUMENTATION @@ -5144,6 +5145,10 @@ L: linux-mm@kvack.org W: http://www.linux-mm.org S: Maintained F: include/linux/mm.h +F: include/linux/gfp.h +F: include/linux/mmzone.h +F: include/linux/memory_hotplug.h +F: include/linux/vmalloc.h F: mm/ MEMORY RESOURCE CONTROLLER diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index dbc1760f418b..b9e37ad6fa19 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -1300,17 +1300,15 @@ static unsigned long arch_get_unmapped_area_1(unsigned long addr, unsigned long len, unsigned long limit) { - struct vm_area_struct *vma = find_vma(current->mm, addr); - - while (1) { - /* At this point: (!vma || addr < vma->vm_end). */ - if (limit - len < addr) - return -ENOMEM; - if (!vma || addr + len <= vma->vm_start) - return addr; - addr = vma->vm_end; - vma = vma->vm_next; - } + struct vm_unmapped_area_info info; + + info.flags = 0; + info.length = len; + info.low_limit = addr; + info.high_limit = limit; + info.align_mask = 0; + info.align_offset = 0; + return vm_unmapped_area(&info); } unsigned long diff --git a/arch/arm/boot/dts/armada-370-xp.dtsi b/arch/arm/boot/dts/armada-370-xp.dtsi index 4c0abe85405f..5b2922599f0e 100644 --- a/arch/arm/boot/dts/armada-370-xp.dtsi +++ b/arch/arm/boot/dts/armada-370-xp.dtsi @@ -131,6 +131,12 @@ clocks = <&coreclk 0>; status = "disabled"; }; + + rtc@10300 { + compatible = "marvell,orion-rtc"; + reg = <0xd0010300 0x20>; + interrupts = <50>; + }; }; }; diff --git a/arch/arm/configs/mvebu_defconfig b/arch/arm/configs/mvebu_defconfig index cbd91bce1ca9..9d3922bf7372 100644 --- a/arch/arm/configs/mvebu_defconfig +++ b/arch/arm/configs/mvebu_defconfig @@ -41,6 +41,7 @@ CONFIG_GPIO_SYSFS=y # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_S35390A=y +CONFIG_RTC_DRV_MV=y CONFIG_DMADEVICES=y CONFIG_MV_XOR=y # CONFIG_IOMMU_SUPPORT is not set diff --git a/arch/arm/configs/pxa910_defconfig b/arch/arm/configs/pxa910_defconfig index 191118caa5c0..3bb7771d3c19 100644 --- a/arch/arm/configs/pxa910_defconfig +++ b/arch/arm/configs/pxa910_defconfig @@ -42,6 +42,14 @@ CONFIG_SMC91X=y # CONFIG_SERIO is not set CONFIG_SERIAL_PXA=y CONFIG_SERIAL_PXA_CONSOLE=y +CONFIG_SPI=y +CONFIG_FB=y +CONFIG_MMP_DISP=y +CONFIG_MMP_DISP_CONTROLLER=y +CONFIG_MMP_SPI=y +CONFIG_MMP_PANEL_TPOHVGA=y +CONFIG_MMP_FB=y +CONFIG_LOGO=y # CONFIG_LEGACY_PTYS is not set # CONFIG_HW_RANDOM is not set # CONFIG_HWMON is not set diff --git a/arch/arm/kernel/kprobes.c b/arch/arm/kernel/kprobes.c index 4dd41fc9e235..170e9f34003f 100644 --- a/arch/arm/kernel/kprobes.c +++ b/arch/arm/kernel/kprobes.c @@ -395,7 +395,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs) { struct kretprobe_instance *ri = NULL; struct hlist_head *head, empty_rp; - struct hlist_node *node, *tmp; + struct hlist_node *tmp; unsigned long flags, orig_ret_address = 0; unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline; @@ -415,7 +415,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs) * real return address, and all the rest will point to * kretprobe_trampoline */ - hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { + hlist_for_each_entry_safe(ri, tmp, head, hlist) { if (ri->task != current) /* another task is sharing our hash bucket */ continue; @@ -442,7 +442,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs) kretprobe_assert(ri, orig_ret_address, trampoline_address); kretprobe_hash_unlock(current, &flags); - hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) { + hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); kfree(ri); } diff --git a/arch/arm/mach-mmp/include/mach/pxa910.h b/arch/arm/mach-mmp/include/mach/pxa910.h index eff31ab6dc3b..b914afa1fcdc 100644 --- a/arch/arm/mach-mmp/include/mach/pxa910.h +++ b/arch/arm/mach-mmp/include/mach/pxa910.h @@ -8,6 +8,7 @@ extern void __init pxa910_init_irq(void); #include <linux/i2c/pxa-i2c.h> #include <mach/devices.h> #include <linux/platform_data/mtd-nand-pxa3xx.h> +#include <video/mmp_disp.h> extern struct pxa_device_desc pxa910_device_uart1; extern struct pxa_device_desc pxa910_device_uart2; @@ -21,7 +22,9 @@ extern struct pxa_device_desc pxa910_device_nand; extern struct platform_device pxa168_device_u2o; extern struct platform_device pxa168_device_u2ootg; extern struct platform_device pxa168_device_u2oehci; - +extern struct pxa_device_desc pxa910_device_disp; +extern struct pxa_device_desc pxa910_device_fb; +extern struct pxa_device_desc pxa910_device_panel; extern struct platform_device pxa910_device_gpio; extern struct platform_device pxa910_device_rtc; diff --git a/arch/arm/mach-mmp/pxa910.c b/arch/arm/mach-mmp/pxa910.c index c6a89f1eca4e..36cb321a3d70 100644 --- a/arch/arm/mach-mmp/pxa910.c +++ b/arch/arm/mach-mmp/pxa910.c @@ -134,6 +134,9 @@ PXA910_DEVICE(pwm2, "pxa910-pwm", 1, NONE, 0xd401a400, 0x10); PXA910_DEVICE(pwm3, "pxa910-pwm", 2, NONE, 0xd401a800, 0x10); PXA910_DEVICE(pwm4, "pxa910-pwm", 3, NONE, 0xd401ac00, 0x10); PXA910_DEVICE(nand, "pxa3xx-nand", -1, NAND, 0xd4283000, 0x80, 97, 99); +PXA910_DEVICE(disp, "mmp-disp", 0, LCD, 0xd420b000, 0x1ec); +PXA910_DEVICE(fb, "mmp-fb", -1, NONE, 0, 0); +PXA910_DEVICE(panel, "tpo-hvga", -1, NONE, 0, 0); struct resource pxa910_resource_gpio[] = { { diff --git a/arch/arm/mach-mmp/ttc_dkb.c b/arch/arm/mach-mmp/ttc_dkb.c index 6e474900b13e..22a9058f9f4d 100644 --- a/arch/arm/mach-mmp/ttc_dkb.c +++ b/arch/arm/mach-mmp/ttc_dkb.c @@ -19,6 +19,8 @@ #include <linux/gpio.h> #include <linux/mfd/88pm860x.h> #include <linux/platform_data/mv_usb.h> +#include <linux/spi/spi.h> +#include <linux/delay.h> #include <asm/mach-types.h> #include <asm/mach/arch.h> @@ -184,6 +186,92 @@ static struct pxa3xx_nand_platform_data dkb_nand_info = { }; #endif +#ifdef CONFIG_MMP_DISP +/* path config */ +#define CFG_IOPADMODE(iopad) (iopad) /* 0x0 ~ 0xd */ +#define SCLK_SOURCE_SELECT(x) (x << 30) /* 0x0 ~ 0x3 */ +/* link config */ +#define CFG_DUMBMODE(mode) (mode << 28) /* 0x0 ~ 0x6*/ +#define CFG_GRA_SWAPRB(x) (x << 0) /* 1: rbswap enabled */ +static struct mmp_mach_path_config dkb_disp_config[] = { + [0] = { + .name = "mmp-parallel", + .overlay_num = 2, + .output_type = PATH_OUT_PARALLEL, + .path_config = CFG_IOPADMODE(0x1) + | SCLK_SOURCE_SELECT(0x1), + .link_config = CFG_DUMBMODE(0x2) + | CFG_GRA_SWAPRB(0x1), + }, +}; + +static struct mmp_mach_plat_info dkb_disp_info = { + .name = "mmp-disp", + .clk_name = "disp0", + .path_num = 1, + .paths = dkb_disp_config, +}; + +static struct mmp_buffer_driver_mach_info dkb_fb_info = { + .name = "mmp-fb", + .path_name = "mmp-parallel", + .overlay_id = 0, + .dmafetch_id = 1, + .default_pixfmt = PIXFMT_RGB565, +}; + +static void dkb_tpo_panel_power(int on) +{ + int err; + u32 spi_reset = mfp_to_gpio(MFP_PIN_GPIO106); + + if (on) { + err = gpio_request(spi_reset, "TPO_LCD_SPI_RESET"); + if (err) { + pr_err("failed to request GPIO for TPO LCD RESET\n"); + return; + } + gpio_direction_output(spi_reset, 0); + udelay(100); + gpio_set_value(spi_reset, 1); + gpio_free(spi_reset); + } else { + err = gpio_request(spi_reset, "TPO_LCD_SPI_RESET"); + if (err) { + pr_err("failed to request LCD RESET gpio\n"); + return; + } + gpio_set_value(spi_reset, 0); + gpio_free(spi_reset); + } +} + +static struct mmp_mach_panel_info dkb_tpo_panel_info = { + .name = "tpo-hvga", + .plat_path_name = "mmp-parallel", + .plat_set_onoff = dkb_tpo_panel_power, +}; + +static struct spi_board_info spi_board_info[] __initdata = { + { + .modalias = "tpo-hvga", + .platform_data = &dkb_tpo_panel_info, + .bus_num = 5, + } +}; + +static void __init add_disp(void) +{ + pxa_register_device(&pxa910_device_disp, + &dkb_disp_info, sizeof(dkb_disp_info)); + spi_register_board_info(spi_board_info, ARRAY_SIZE(spi_board_info)); + pxa_register_device(&pxa910_device_fb, + &dkb_fb_info, sizeof(dkb_fb_info)); + pxa_register_device(&pxa910_device_panel, + &dkb_tpo_panel_info, sizeof(dkb_tpo_panel_info)); +} +#endif + static void __init ttc_dkb_init(void) { mfp_config(ARRAY_AND_SIZE(ttc_dkb_pin_config)); @@ -212,6 +300,10 @@ static void __init ttc_dkb_init(void) pxa168_device_u2ootg.dev.platform_data = &ttc_usb_pdata; platform_device_register(&pxa168_device_u2ootg); #endif + +#ifdef CONFIG_MMP_DISP + add_disp(); +#endif } MACHINE_START(TTC_DKB, "PXA910-based TTC_DKB Development Platform") diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c index 10062ceadd1c..0c6356255fe3 100644 --- a/arch/arm/mm/mmap.c +++ b/arch/arm/mm/mmap.c @@ -181,11 +181,9 @@ void arch_pick_mmap_layout(struct mm_struct *mm) if (mmap_is_legacy()) { mm->mmap_base = TASK_UNMAPPED_BASE + random_factor; mm->get_unmapped_area = arch_get_unmapped_area; - mm->unmap_area = arch_unmap_area; } else { mm->mmap_base = mmap_base(random_factor); mm->get_unmapped_area = arch_get_unmapped_area_topdown; - mm->unmap_area = arch_unmap_area_topdown; } } diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c index 7c7be7855638..8ed6cb1a900f 100644 --- a/arch/arm64/mm/mmap.c +++ b/arch/arm64/mm/mmap.c @@ -90,11 +90,9 @@ void arch_pick_mmap_layout(struct mm_struct *mm) if (mmap_is_legacy()) { mm->mmap_base = TASK_UNMAPPED_BASE; mm->get_unmapped_area = arch_get_unmapped_area; - mm->unmap_area = arch_unmap_area; } else { mm->mmap_base = mmap_base(); mm->get_unmapped_area = arch_get_unmapped_area_topdown; - mm->unmap_area = arch_unmap_area_topdown; } } EXPORT_SYMBOL_GPL(arch_pick_mmap_layout); diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index f4dd585898c5..224b44ab534e 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -434,4 +434,7 @@ int __meminit vmemmap_populate(struct page *start_page, return 0; } #endif /* CONFIG_ARM64_64K_PAGES */ +void vmemmap_free(struct page *memmap, unsigned long nr_pages) +{ +} #endif /* CONFIG_SPARSEMEM_VMEMMAP */ diff --git a/arch/cris/include/uapi/asm/posix_types.h b/arch/cris/include/uapi/asm/posix_types.h index ce4e51793151..0f22e6a67ea5 100644 --- a/arch/cris/include/uapi/asm/posix_types.h +++ b/arch/cris/include/uapi/asm/posix_types.h @@ -22,11 +22,6 @@ typedef unsigned short __kernel_uid_t; typedef unsigned short __kernel_gid_t; #define __kernel_uid_t __kernel_uid_t -typedef __SIZE_TYPE__ __kernel_size_t; -typedef long __kernel_ssize_t; -typedef int __kernel_ptrdiff_t; -#define __kernel_size_t __kernel_size_t - typedef unsigned short __kernel_old_dev_t; #define __kernel_old_dev_t __kernel_old_dev_t diff --git a/arch/frv/mm/elf-fdpic.c b/arch/frv/mm/elf-fdpic.c index 385fd30b142f..836f14707a62 100644 --- a/arch/frv/mm/elf-fdpic.c +++ b/arch/frv/mm/elf-fdpic.c @@ -60,7 +60,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi unsigned long pgoff, unsigned long flags) { struct vm_area_struct *vma; - unsigned long limit; + struct vm_unmapped_area_info info; if (len > TASK_SIZE) return -ENOMEM; @@ -79,39 +79,24 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi } /* search between the bottom of user VM and the stack grow area */ - addr = PAGE_SIZE; - limit = (current->mm->start_stack - 0x00200000); - if (addr + len <= limit) { - limit -= len; - - if (addr <= limit) { - vma = find_vma(current->mm, PAGE_SIZE); - for (; vma; vma = vma->vm_next) { - if (addr > limit) - break; - if (addr + len <= vma->vm_start) - goto success; - addr = vma->vm_end; - } - } - } + info.flags = 0; + info.length = len; + info.low_limit = PAGE_SIZE; + info.high_limit = (current->mm->start_stack - 0x00200000); + info.align_mask = 0; + info.align_offset = 0; + addr = vm_unmapped_area(&info); + if (!(addr & ~PAGE_MASK)) + goto success; + VM_BUG_ON(addr != -ENOMEM); /* search from just above the WorkRAM area to the top of memory */ - addr = PAGE_ALIGN(0x80000000); - limit = TASK_SIZE - len; - if (addr <= limit) { - vma = find_vma(current->mm, addr); - for (; vma; vma = vma->vm_next) { - if (addr > limit) - break; - if (addr + len <= vma->vm_start) - goto success; - addr = vma->vm_end; - } - - if (!vma && addr <= limit) - goto success; - } + info.low_limit = PAGE_ALIGN(0x80000000); + info.high_limit = TASK_SIZE; + addr = vm_unmapped_area(&info); + if (!(addr & ~PAGE_MASK)) + goto success; + VM_BUG_ON(addr != -ENOMEM); #if 0 printk("[area] l=%lx (ENOMEM) f='%s'\n", diff --git a/arch/ia64/include/asm/meminit.h b/arch/ia64/include/asm/meminit.h index 61c7b1750b16..925ecb55c713 100644 --- a/arch/ia64/include/asm/meminit.h +++ b/arch/ia64/include/asm/meminit.h @@ -49,6 +49,8 @@ extern int reserve_elfcorehdr(u64 *start, u64 *end); #define GRANULEROUNDDOWN(n) ((n) & ~(IA64_GRANULE_SIZE-1)) #define GRANULEROUNDUP(n) (((n)+IA64_GRANULE_SIZE-1) & ~(IA64_GRANULE_SIZE-1)) +extern u64 max_addr; + #ifdef CONFIG_NUMA extern void call_pernode_memory (unsigned long start, unsigned long len, void *func); #else diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c index f034563aeae5..f6522cbd2085 100644 --- a/arch/ia64/kernel/efi.c +++ b/arch/ia64/kernel/efi.c @@ -49,7 +49,7 @@ extern efi_status_t efi_call_phys (void *, ...); struct efi efi; EXPORT_SYMBOL(efi); static efi_runtime_services_t *runtime; -static u64 mem_limit = ~0UL, max_addr = ~0UL, min_addr = 0UL; +u64 mem_limit = ~0UL, max_addr = ~0UL, min_addr = 0UL; #define efi_call_virt(f, args...) (*(f))(args) diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c index 7026b29e277a..f8280a766a78 100644 --- a/arch/ia64/kernel/kprobes.c +++ b/arch/ia64/kernel/kprobes.c @@ -423,7 +423,7 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) { struct kretprobe_instance *ri = NULL; struct hlist_head *head, empty_rp; - struct hlist_node *node, *tmp; + struct hlist_node *tmp; unsigned long flags, orig_ret_address = 0; unsigned long trampoline_address = ((struct fnptr *)kretprobe_trampoline)->ip; @@ -444,7 +444,7 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) * real return address, and all the rest will point to * kretprobe_trampoline */ - hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { + hlist_for_each_entry_safe(ri, tmp, head, hlist) { if (ri->task != current) /* another task is sharing our hash bucket */ continue; @@ -461,7 +461,7 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) regs->cr_iip = orig_ret_address; - hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { + hlist_for_each_entry_safe(ri, tmp, head, hlist) { if (ri->task != current) /* another task is sharing our hash bucket */ continue; @@ -487,7 +487,7 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) kretprobe_hash_unlock(current, &flags); preempt_enable_no_resched(); - hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) { + hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); kfree(ri); } diff --git a/arch/ia64/kernel/sys_ia64.c b/arch/ia64/kernel/sys_ia64.c index d9439ef2f661..41e33f84c185 100644 --- a/arch/ia64/kernel/sys_ia64.c +++ b/arch/ia64/kernel/sys_ia64.c @@ -25,9 +25,9 @@ arch_get_unmapped_area (struct file *filp, unsigned long addr, unsigned long len unsigned long pgoff, unsigned long flags) { long map_shared = (flags & MAP_SHARED); - unsigned long start_addr, align_mask = PAGE_SIZE - 1; + unsigned long align_mask = 0; struct mm_struct *mm = current->mm; - struct vm_area_struct *vma; + struct vm_unmapped_area_info info; if (len > RGN_MAP_LIMIT) return -ENOMEM; @@ -44,7 +44,7 @@ arch_get_unmapped_area (struct file *filp, unsigned long addr, unsigned long len addr = 0; #endif if (!addr) - addr = mm->free_area_cache; + addr = TASK_UNMAPPED_BASE; if (map_shared && (TASK_SIZE > 0xfffffffful)) /* @@ -53,28 +53,15 @@ arch_get_unmapped_area (struct file *filp, unsigned long addr, unsigned long len * tasks, we prefer to avoid exhausting the address space too quickly by * limiting alignment to a single page. */ - align_mask = SHMLBA - 1; - - full_search: - start_addr = addr = (addr + align_mask) & ~align_mask; - - for (vma = find_vma(mm, addr); ; vma = vma->vm_next) { - /* At this point: (!vma || addr < vma->vm_end). */ - if (TASK_SIZE - len < addr || RGN_MAP_LIMIT - len < REGION_OFFSET(addr)) { - if (start_addr != TASK_UNMAPPED_BASE) { - /* Start a new search --- just in case we missed some holes. */ - addr = TASK_UNMAPPED_BASE; - goto full_search; - } - return -ENOMEM; - } - if (!vma || addr + len <= vma->vm_start) { - /* Remember the address where we stopped this search: */ - mm->free_area_cache = addr + len; - return addr; - } - addr = (vma->vm_end + align_mask) & ~align_mask; - } + align_mask = PAGE_MASK & (SHMLBA - 1); + + info.flags = 0; + info.length = len; + info.low_limit = addr; + info.high_limit = TASK_SIZE; + info.align_mask = align_mask; + info.align_offset = 0; + return vm_unmapped_area(&info); } asmlinkage long diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c index 1516d1dc11fd..80dab509dfb0 100644 --- a/arch/ia64/mm/contig.c +++ b/arch/ia64/mm/contig.c @@ -93,7 +93,7 @@ void show_mem(unsigned int filter) printk(KERN_INFO "%d pages swap cached\n", total_cached); printk(KERN_INFO "Total of %ld pages in page table cache\n", quicklist_total_size()); - printk(KERN_INFO "%d free buffer pages\n", nr_free_buffer_pages()); + printk(KERN_INFO "%ld free buffer pages\n", nr_free_buffer_pages()); } diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c index c641333cd997..c2e955ee79a8 100644 --- a/arch/ia64/mm/discontig.c +++ b/arch/ia64/mm/discontig.c @@ -666,7 +666,7 @@ void show_mem(unsigned int filter) printk(KERN_INFO "%d pages swap cached\n", total_cached); printk(KERN_INFO "Total of %ld pages in page table cache\n", quicklist_total_size()); - printk(KERN_INFO "%d free buffer pages\n", nr_free_buffer_pages()); + printk(KERN_INFO "%ld free buffer pages\n", nr_free_buffer_pages()); } /** @@ -822,4 +822,8 @@ int __meminit vmemmap_populate(struct page *start_page, { return vmemmap_populate_basepages(start_page, size, node); } + +void vmemmap_free(struct page *memmap, unsigned long nr_pages) +{ +} #endif diff --git a/arch/ia64/mm/hugetlbpage.c b/arch/ia64/mm/hugetlbpage.c index 5ca674b74737..76069c18ee42 100644 --- a/arch/ia64/mm/hugetlbpage.c +++ b/arch/ia64/mm/hugetlbpage.c @@ -148,7 +148,7 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { - struct vm_area_struct *vmm; + struct vm_unmapped_area_info info; if (len > RGN_MAP_LIMIT) return -ENOMEM; @@ -165,16 +165,14 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, u /* This code assumes that RGN_HPAGE != 0. */ if ((REGION_NUMBER(addr) != RGN_HPAGE) || (addr & (HPAGE_SIZE - 1))) addr = HPAGE_REGION_BASE; - else - addr = ALIGN(addr, HPAGE_SIZE); - for (vmm = find_vma(current->mm, addr); ; vmm = vmm->vm_next) { - /* At this point: (!vmm || addr < vmm->vm_end). */ - if (REGION_OFFSET(addr) + len > RGN_MAP_LIMIT) - return -ENOMEM; - if (!vmm || (addr + len) <= vmm->vm_start) - return addr; - addr = ALIGN(vmm->vm_end, HPAGE_SIZE); - } + + info.flags = 0; + info.length = len; + info.low_limit = addr; + info.high_limit = HPAGE_REGION_BASE + RGN_MAP_LIMIT; + info.align_mask = PAGE_MASK & (HPAGE_SIZE - 1); + info.align_offset = 0; + return vm_unmapped_area(&info); } static int __init hugetlb_setup_sz(char *str) diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index b755ea92aea7..8fe35a8c923b 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -207,6 +207,17 @@ free_initrd_mem (unsigned long start, unsigned long end) start = PAGE_ALIGN(start); end = end & PAGE_MASK; + /* + * Initrd size is fixed in boot loader, but kernel parameter max_addr + * which aligns in granules is fixed after boot loader, so initrd size + * maybe overflow. + */ + if (max_addr != ~0UL) { + end = GRANULEROUNDDOWN(end); + if (start > end) + start = end; + } + if (start < end) printk(KERN_INFO "Freeing initrd memory: %ldkB freed\n", (end - start) >> 10); @@ -688,6 +699,24 @@ int arch_add_memory(int nid, u64 start, u64 size) return ret; } + +#ifdef CONFIG_MEMORY_HOTREMOVE +int arch_remove_memory(u64 start, u64 size) +{ + unsigned long start_pfn = start >> PAGE_SHIFT; + unsigned long nr_pages = size >> PAGE_SHIFT; + struct zone *zone; + int ret; + + zone = page_zone(pfn_to_page(start_pfn)); + ret = __remove_pages(zone, start_pfn, nr_pages); + if (ret) + pr_warn("%s: Problem encountered in __remove_pages() as" + " ret=%d\n", __func__, ret); + + return ret; +} +#endif #endif /* diff --git a/arch/mips/kernel/kprobes.c b/arch/mips/kernel/kprobes.c index a14be5fa5ec8..12bc4ebdf55b 100644 --- a/arch/mips/kernel/kprobes.c +++ b/arch/mips/kernel/kprobes.c @@ -598,7 +598,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, { struct kretprobe_instance *ri = NULL; struct hlist_head *head, empty_rp; - struct hlist_node *node, *tmp; + struct hlist_node *tmp; unsigned long flags, orig_ret_address = 0; unsigned long trampoline_address = (unsigned long)kretprobe_trampoline; @@ -618,7 +618,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, * real return address, and all the rest will point to * kretprobe_trampoline */ - hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { + hlist_for_each_entry_safe(ri, tmp, head, hlist) { if (ri->task != current) /* another task is sharing our hash bucket */ continue; @@ -645,7 +645,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, kretprobe_hash_unlock(current, &flags); preempt_enable_no_resched(); - hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) { + hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); kfree(ri); } diff --git a/arch/mips/mm/mmap.c b/arch/mips/mm/mmap.c index 7e5fe2790d8a..f1baadd56e82 100644 --- a/arch/mips/mm/mmap.c +++ b/arch/mips/mm/mmap.c @@ -158,11 +158,9 @@ void arch_pick_mmap_layout(struct mm_struct *mm) if (mmap_is_legacy()) { mm->mmap_base = TASK_UNMAPPED_BASE + random_factor; mm->get_unmapped_area = arch_get_unmapped_area; - mm->unmap_area = arch_unmap_area; } else { mm->mmap_base = mmap_base(random_factor); mm->get_unmapped_area = arch_get_unmapped_area_topdown; - mm->unmap_area = arch_unmap_area_topdown; } } diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index f76c10863c62..6ab138088076 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -35,18 +35,15 @@ static unsigned long get_unshared_area(unsigned long addr, unsigned long len) { - struct vm_area_struct *vma; + struct vm_unmapped_area_info info; - addr = PAGE_ALIGN(addr); - - for (vma = find_vma(current->mm, addr); ; vma = vma->vm_next) { - /* At this point: (!vma || addr < vma->vm_end). */ - if (TASK_SIZE - len < addr) - return -ENOMEM; - if (!vma || addr + len <= vma->vm_start) - return addr; - addr = vma->vm_end; - } + info.flags = 0; + info.length = len; + info.low_limit = PAGE_ALIGN(addr); + info.high_limit = TASK_SIZE; + info.align_mask = 0; + info.align_offset = 0; + return vm_unmapped_area(&info); } #define DCACHE_ALIGN(addr) (((addr) + (SHMLBA - 1)) &~ (SHMLBA - 1)) @@ -63,30 +60,21 @@ static unsigned long get_unshared_area(unsigned long addr, unsigned long len) */ static int get_offset(struct address_space *mapping) { - int offset = (unsigned long) mapping << (PAGE_SHIFT - 8); - return offset & 0x3FF000; + return (unsigned long) mapping >> 8; } static unsigned long get_shared_area(struct address_space *mapping, unsigned long addr, unsigned long len, unsigned long pgoff) { - struct vm_area_struct *vma; - int offset = mapping ? get_offset(mapping) : 0; - - offset = (offset + (pgoff << PAGE_SHIFT)) & 0x3FF000; + struct vm_unmapped_area_info info; - addr = DCACHE_ALIGN(addr - offset) + offset; - - for (vma = find_vma(current->mm, addr); ; vma = vma->vm_next) { - /* At this point: (!vma || addr < vma->vm_end). */ - if (TASK_SIZE - len < addr) - return -ENOMEM; - if (!vma || addr + len <= vma->vm_start) - return addr; - addr = DCACHE_ALIGN(vma->vm_end - offset) + offset; - if (addr < vma->vm_end) /* handle wraparound */ - return -ENOMEM; - } + info.flags = 0; + info.length = len; + info.low_limit = PAGE_ALIGN(addr); + info.high_limit = TASK_SIZE; + info.align_mask = PAGE_MASK & (SHMLBA - 1); + info.align_offset = (get_offset(mapping) + pgoff) << PAGE_SHIFT; + return vm_unmapped_area(&info); } unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, diff --git a/arch/powerpc/include/asm/page_64.h b/arch/powerpc/include/asm/page_64.h index cd915d6b093d..88693cef4f3d 100644 --- a/arch/powerpc/include/asm/page_64.h +++ b/arch/powerpc/include/asm/page_64.h @@ -99,8 +99,7 @@ extern unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, unsigned long flags, unsigned int psize, - int topdown, - int use_cache); + int topdown); extern unsigned int get_slice_psize(struct mm_struct *mm, unsigned long addr); diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index e88c64331819..11f5b03a0b06 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -310,7 +310,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, { struct kretprobe_instance *ri = NULL; struct hlist_head *head, empty_rp; - struct hlist_node *node, *tmp; + struct hlist_node *tmp; unsigned long flags, orig_ret_address = 0; unsigned long trampoline_address =(unsigned long)&kretprobe_trampoline; @@ -330,7 +330,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, * real return address, and all the rest will point to * kretprobe_trampoline */ - hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { + hlist_for_each_entry_safe(ri, tmp, head, hlist) { if (ri->task != current) /* another task is sharing our hash bucket */ continue; @@ -357,7 +357,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, kretprobe_hash_unlock(current, &flags); preempt_enable_no_resched(); - hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) { + hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); kfree(ri); } diff --git a/arch/powerpc/kvm/book3s_mmu_hpte.c b/arch/powerpc/kvm/book3s_mmu_hpte.c index 2c86b0d63714..da8b13c4b776 100644 --- a/arch/powerpc/kvm/book3s_mmu_hpte.c +++ b/arch/powerpc/kvm/book3s_mmu_hpte.c @@ -124,7 +124,6 @@ static void kvmppc_mmu_pte_flush_all(struct kvm_vcpu *vcpu) { struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); struct hpte_cache *pte; - struct hlist_node *node; int i; rcu_read_lock(); @@ -132,7 +131,7 @@ static void kvmppc_mmu_pte_flush_all(struct kvm_vcpu *vcpu) for (i = 0; i < HPTEG_HASH_NUM_VPTE_LONG; i++) { struct hlist_head *list = &vcpu3s->hpte_hash_vpte_long[i]; - hlist_for_each_entry_rcu(pte, node, list, list_vpte_long) + hlist_for_each_entry_rcu(pte, list, list_vpte_long) invalidate_pte(vcpu, pte); } @@ -143,7 +142,6 @@ static void kvmppc_mmu_pte_flush_page(struct kvm_vcpu *vcpu, ulong guest_ea) { struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); struct hlist_head *list; - struct hlist_node *node; struct hpte_cache *pte; /* Find the list of entries in the map */ @@ -152,7 +150,7 @@ static void kvmppc_mmu_pte_flush_page(struct kvm_vcpu *vcpu, ulong guest_ea) rcu_read_lock(); /* Check the list for matching entries and invalidate */ - hlist_for_each_entry_rcu(pte, node, list, list_pte) + hlist_for_each_entry_rcu(pte, list, list_pte) if ((pte->pte.eaddr & ~0xfffUL) == guest_ea) invalidate_pte(vcpu, pte); @@ -163,7 +161,6 @@ static void kvmppc_mmu_pte_flush_long(struct kvm_vcpu *vcpu, ulong guest_ea) { struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); struct hlist_head *list; - struct hlist_node *node; struct hpte_cache *pte; /* Find the list of entries in the map */ @@ -173,7 +170,7 @@ static void kvmppc_mmu_pte_flush_long(struct kvm_vcpu *vcpu, ulong guest_ea) rcu_read_lock(); /* Check the list for matching entries and invalidate */ - hlist_for_each_entry_rcu(pte, node, list, list_pte_long) + hlist_for_each_entry_rcu(pte, list, list_pte_long) if ((pte->pte.eaddr & 0x0ffff000UL) == guest_ea) invalidate_pte(vcpu, pte); @@ -207,7 +204,6 @@ static void kvmppc_mmu_pte_vflush_short(struct kvm_vcpu *vcpu, u64 guest_vp) { struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); struct hlist_head *list; - struct hlist_node *node; struct hpte_cache *pte; u64 vp_mask = 0xfffffffffULL; @@ -216,7 +212,7 @@ static void kvmppc_mmu_pte_vflush_short(struct kvm_vcpu *vcpu, u64 guest_vp) rcu_read_lock(); /* Check the list for matching entries and invalidate */ - hlist_for_each_entry_rcu(pte, node, list, list_vpte) + hlist_for_each_entry_rcu(pte, list, list_vpte) if ((pte->pte.vpage & vp_mask) == guest_vp) invalidate_pte(vcpu, pte); @@ -228,7 +224,6 @@ static void kvmppc_mmu_pte_vflush_long(struct kvm_vcpu *vcpu, u64 guest_vp) { struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); struct hlist_head *list; - struct hlist_node *node; struct hpte_cache *pte; u64 vp_mask = 0xffffff000ULL; @@ -238,7 +233,7 @@ static void kvmppc_mmu_pte_vflush_long(struct kvm_vcpu *vcpu, u64 guest_vp) rcu_read_lock(); /* Check the list for matching entries and invalidate */ - hlist_for_each_entry_rcu(pte, node, list, list_vpte_long) + hlist_for_each_entry_rcu(pte, list, list_vpte_long) if ((pte->pte.vpage & vp_mask) == guest_vp) invalidate_pte(vcpu, pte); @@ -266,7 +261,6 @@ void kvmppc_mmu_pte_vflush(struct kvm_vcpu *vcpu, u64 guest_vp, u64 vp_mask) void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, ulong pa_start, ulong pa_end) { struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); - struct hlist_node *node; struct hpte_cache *pte; int i; @@ -277,7 +271,7 @@ void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, ulong pa_start, ulong pa_end) for (i = 0; i < HPTEG_HASH_NUM_VPTE_LONG; i++) { struct hlist_head *list = &vcpu3s->hpte_hash_vpte_long[i]; - hlist_for_each_entry_rcu(pte, node, list, list_vpte_long) + hlist_for_each_entry_rcu(pte, list, list_vpte_long) if ((pte->pte.raddr >= pa_start) && (pte->pte.raddr < pa_end)) invalidate_pte(vcpu, pte); diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 1a6de0a7d8eb..5dc52d803ed8 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -742,7 +742,7 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, struct hstate *hstate = hstate_file(file); int mmu_psize = shift_to_mmu_psize(huge_page_shift(hstate)); - return slice_get_unmapped_area(addr, len, flags, mmu_psize, 1, 0); + return slice_get_unmapped_area(addr, len, flags, mmu_psize, 1); } #endif diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 95a45293e5ac..7e2246fb2f31 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -297,5 +297,10 @@ int __meminit vmemmap_populate(struct page *start_page, return 0; } + +void vmemmap_free(struct page *memmap, unsigned long nr_pages) +{ +} + #endif /* CONFIG_SPARSEMEM_VMEMMAP */ diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 40df7c8f2096..f1f7409a4183 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -133,6 +133,18 @@ int arch_add_memory(int nid, u64 start, u64 size) return __add_pages(nid, zone, start_pfn, nr_pages); } + +#ifdef CONFIG_MEMORY_HOTREMOVE +int arch_remove_memory(u64 start, u64 size) +{ + unsigned long start_pfn = start >> PAGE_SHIFT; + unsigned long nr_pages = size >> PAGE_SHIFT; + struct zone *zone; + + zone = page_zone(pfn_to_page(start_pfn)); + return __remove_pages(zone, start_pfn, nr_pages); +} +#endif #endif /* CONFIG_MEMORY_HOTPLUG */ /* diff --git a/arch/powerpc/mm/mmap_64.c b/arch/powerpc/mm/mmap_64.c index 67a42ed0d2fc..cb8bdbe4972f 100644 --- a/arch/powerpc/mm/mmap_64.c +++ b/arch/powerpc/mm/mmap_64.c @@ -92,10 +92,8 @@ void arch_pick_mmap_layout(struct mm_struct *mm) if (mmap_is_legacy()) { mm->mmap_base = TASK_UNMAPPED_BASE; mm->get_unmapped_area = arch_get_unmapped_area; - mm->unmap_area = arch_unmap_area; } else { mm->mmap_base = mmap_base(); mm->get_unmapped_area = arch_get_unmapped_area_topdown; - mm->unmap_area = arch_unmap_area_topdown; } } diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c index cf9dada734b6..3e99c149271a 100644 --- a/arch/powerpc/mm/slice.c +++ b/arch/powerpc/mm/slice.c @@ -237,134 +237,112 @@ static void slice_convert(struct mm_struct *mm, struct slice_mask mask, int psiz #endif } +/* + * Compute which slice addr is part of; + * set *boundary_addr to the start or end boundary of that slice + * (depending on 'end' parameter); + * return boolean indicating if the slice is marked as available in the + * 'available' slice_mark. + */ +static bool slice_scan_available(unsigned long addr, + struct slice_mask available, + int end, + unsigned long *boundary_addr) +{ + unsigned long slice; + if (addr < SLICE_LOW_TOP) { + slice = GET_LOW_SLICE_INDEX(addr); + *boundary_addr = (slice + end) << SLICE_LOW_SHIFT; + return !!(available.low_slices & (1u << slice)); + } else { + slice = GET_HIGH_SLICE_INDEX(addr); + *boundary_addr = (slice + end) ? + ((slice + end) << SLICE_HIGH_SHIFT) : SLICE_LOW_TOP; + return !!(available.high_slices & (1u << slice)); + } +} + static unsigned long slice_find_area_bottomup(struct mm_struct *mm, unsigned long len, struct slice_mask available, - int psize, int use_cache) + int psize) { - struct vm_area_struct *vma; - unsigned long start_addr, addr; - struct slice_mask mask; int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT); - - if (use_cache) { - if (len <= mm->cached_hole_size) { - start_addr = addr = TASK_UNMAPPED_BASE; - mm->cached_hole_size = 0; - } else - start_addr = addr = mm->free_area_cache; - } else - start_addr = addr = TASK_UNMAPPED_BASE; - -full_search: - for (;;) { - addr = _ALIGN_UP(addr, 1ul << pshift); - if ((TASK_SIZE - len) < addr) - break; - vma = find_vma(mm, addr); - BUG_ON(vma && (addr >= vma->vm_end)); - - mask = slice_range_to_mask(addr, len); - if (!slice_check_fit(mask, available)) { - if (addr < SLICE_LOW_TOP) - addr = _ALIGN_UP(addr + 1, 1ul << SLICE_LOW_SHIFT); - else - addr = _ALIGN_UP(addr + 1, 1ul << SLICE_HIGH_SHIFT); + unsigned long addr, found, next_end; + struct vm_unmapped_area_info info; + + info.flags = 0; + info.length = len; + info.align_mask = PAGE_MASK & ((1ul << pshift) - 1); + info.align_offset = 0; + + addr = TASK_UNMAPPED_BASE; + while (addr < TASK_SIZE) { + info.low_limit = addr; + if (!slice_scan_available(addr, available, 1, &addr)) continue; + + next_slice: + /* + * At this point [info.low_limit; addr) covers + * available slices only and ends at a slice boundary. + * Check if we need to reduce the range, or if we can + * extend it to cover the next available slice. + */ + if (addr >= TASK_SIZE) + addr = TASK_SIZE; + else if (slice_scan_available(addr, available, 1, &next_end)) { + addr = next_end; + goto next_slice; } - if (!vma || addr + len <= vma->vm_start) { - /* - * Remember the place where we stopped the search: - */ - if (use_cache) - mm->free_area_cache = addr + len; - return addr; - } - if (use_cache && (addr + mm->cached_hole_size) < vma->vm_start) - mm->cached_hole_size = vma->vm_start - addr; - addr = vma->vm_end; - } + info.high_limit = addr; - /* Make sure we didn't miss any holes */ - if (use_cache && start_addr != TASK_UNMAPPED_BASE) { - start_addr = addr = TASK_UNMAPPED_BASE; - mm->cached_hole_size = 0; - goto full_search; + found = vm_unmapped_area(&info); + if (!(found & ~PAGE_MASK)) + return found; } + return -ENOMEM; } static unsigned long slice_find_area_topdown(struct mm_struct *mm, unsigned long len, struct slice_mask available, - int psize, int use_cache) + int psize) { - struct vm_area_struct *vma; - unsigned long addr; - struct slice_mask mask; int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT); + unsigned long addr, found, prev; + struct vm_unmapped_area_info info; - /* check if free_area_cache is useful for us */ - if (use_cache) { - if (len <= mm->cached_hole_size) { - mm->cached_hole_size = 0; - mm->free_area_cache = mm->mmap_base; - } - - /* either no address requested or can't fit in requested - * address hole - */ - addr = mm->free_area_cache; - - /* make sure it can fit in the remaining address space */ - if (addr > len) { - addr = _ALIGN_DOWN(addr - len, 1ul << pshift); - mask = slice_range_to_mask(addr, len); - if (slice_check_fit(mask, available) && - slice_area_is_free(mm, addr, len)) - /* remember the address as a hint for - * next time - */ - return (mm->free_area_cache = addr); - } - } + info.flags = VM_UNMAPPED_AREA_TOPDOWN; + info.length = len; + info.align_mask = PAGE_MASK & ((1ul << pshift) - 1); + info.align_offset = 0; addr = mm->mmap_base; - while (addr > len) { - /* Go down by chunk size */ - addr = _ALIGN_DOWN(addr - len, 1ul << pshift); - - /* Check for hit with different page size */ - mask = slice_range_to_mask(addr, len); - if (!slice_check_fit(mask, available)) { - if (addr < SLICE_LOW_TOP) - addr = _ALIGN_DOWN(addr, 1ul << SLICE_LOW_SHIFT); - else if (addr < (1ul << SLICE_HIGH_SHIFT)) - addr = SLICE_LOW_TOP; - else - addr = _ALIGN_DOWN(addr, 1ul << SLICE_HIGH_SHIFT); + while (addr > PAGE_SIZE) { + info.high_limit = addr; + if (!slice_scan_available(addr - 1, available, 0, &addr)) continue; - } + prev_slice: /* - * Lookup failure means no vma is above this address, - * else if new region fits below vma->vm_start, - * return with success: + * At this point [addr; info.high_limit) covers + * available slices only and starts at a slice boundary. + * Check if we need to reduce the range, or if we can + * extend it to cover the previous available slice. */ - vma = find_vma(mm, addr); - if (!vma || (addr + len) <= vma->vm_start) { - /* remember the address as a hint for next time */ - if (use_cache) - mm->free_area_cache = addr; - return addr; + if (addr < PAGE_SIZE) + addr = PAGE_SIZE; + else if (slice_scan_available(addr - 1, available, 0, &prev)) { + addr = prev; + goto prev_slice; } + info.low_limit = addr; - /* remember the largest hole we saw so far */ - if (use_cache && (addr + mm->cached_hole_size) < vma->vm_start) - mm->cached_hole_size = vma->vm_start - addr; - - /* try just below the current vma->vm_start */ - addr = vma->vm_start; + found = vm_unmapped_area(&info); + if (!(found & ~PAGE_MASK)) + return found; } /* @@ -373,28 +351,18 @@ static unsigned long slice_find_area_topdown(struct mm_struct *mm, * can happen with large stack limits and large mmap() * allocations. */ - addr = slice_find_area_bottomup(mm, len, available, psize, 0); - - /* - * Restore the topdown base: - */ - if (use_cache) { - mm->free_area_cache = mm->mmap_base; - mm->cached_hole_size = ~0UL; - } - - return addr; + return slice_find_area_bottomup(mm, len, available, psize); } static unsigned long slice_find_area(struct mm_struct *mm, unsigned long len, struct slice_mask mask, int psize, - int topdown, int use_cache) + int topdown) { if (topdown) - return slice_find_area_topdown(mm, len, mask, psize, use_cache); + return slice_find_area_topdown(mm, len, mask, psize); else - return slice_find_area_bottomup(mm, len, mask, psize, use_cache); + return slice_find_area_bottomup(mm, len, mask, psize); } #define or_mask(dst, src) do { \ @@ -415,7 +383,7 @@ static unsigned long slice_find_area(struct mm_struct *mm, unsigned long len, unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, unsigned long flags, unsigned int psize, - int topdown, int use_cache) + int topdown) { struct slice_mask mask = {0, 0}; struct slice_mask good_mask; @@ -430,8 +398,8 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, BUG_ON(mm->task_size == 0); slice_dbg("slice_get_unmapped_area(mm=%p, psize=%d...\n", mm, psize); - slice_dbg(" addr=%lx, len=%lx, flags=%lx, topdown=%d, use_cache=%d\n", - addr, len, flags, topdown, use_cache); + slice_dbg(" addr=%lx, len=%lx, flags=%lx, topdown=%d\n", + addr, len, flags, topdown); if (len > mm->task_size) return -ENOMEM; @@ -503,8 +471,7 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, /* Now let's see if we can find something in the existing * slices for that size */ - newaddr = slice_find_area(mm, len, good_mask, psize, topdown, - use_cache); + newaddr = slice_find_area(mm, len, good_mask, psize, topdown); if (newaddr != -ENOMEM) { /* Found within the good mask, we don't have to setup, * we thus return directly @@ -536,8 +503,7 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, * anywhere in the good area. */ if (addr) { - addr = slice_find_area(mm, len, good_mask, psize, topdown, - use_cache); + addr = slice_find_area(mm, len, good_mask, psize, topdown); if (addr != -ENOMEM) { slice_dbg(" found area at 0x%lx\n", addr); return addr; @@ -547,15 +513,14 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, /* Now let's see if we can find something in the existing slices * for that size plus free slices */ - addr = slice_find_area(mm, len, potential_mask, psize, topdown, - use_cache); + addr = slice_find_area(mm, len, potential_mask, psize, topdown); #ifdef CONFIG_PPC_64K_PAGES if (addr == -ENOMEM && psize == MMU_PAGE_64K) { /* retry the search with 4k-page slices included */ or_mask(potential_mask, compat_mask); addr = slice_find_area(mm, len, potential_mask, psize, - topdown, use_cache); + topdown); } #endif @@ -586,8 +551,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long flags) { return slice_get_unmapped_area(addr, len, flags, - current->mm->context.user_psize, - 0, 1); + current->mm->context.user_psize, 0); } unsigned long arch_get_unmapped_area_topdown(struct file *filp, @@ -597,8 +561,7 @@ unsigned long arch_get_unmapped_area_topdown(struct file *filp, const unsigned long flags) { return slice_get_unmapped_area(addr0, len, flags, - current->mm->context.user_psize, - 1, 1); + current->mm->context.user_psize, 1); } unsigned int get_slice_psize(struct mm_struct *mm, unsigned long addr) diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c index 0cfece4cf6ef..2eb4df2a9388 100644 --- a/arch/powerpc/platforms/cell/spufs/file.c +++ b/arch/powerpc/platforms/cell/spufs/file.c @@ -352,7 +352,7 @@ static unsigned long spufs_get_unmapped_area(struct file *file, /* Else, try to obtain a 64K pages slice */ return slice_get_unmapped_area(addr, len, flags, - MMU_PAGE_64K, 1, 0); + MMU_PAGE_64K, 1); } #endif /* CONFIG_SPU_FS_64K_LS */ diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c index 06ea69bd387a..c6c6f4394f3d 100644 --- a/arch/s390/hypfs/inode.c +++ b/arch/s390/hypfs/inode.c @@ -21,6 +21,7 @@ #include <linux/module.h> #include <linux/seq_file.h> #include <linux/mount.h> +#include <linux/aio.h> #include <asm/ebcdic.h> #include "hypfs.h" diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index d1c7214e157c..3388b2b2a07d 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -354,7 +354,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, { struct kretprobe_instance *ri; struct hlist_head *head, empty_rp; - struct hlist_node *node, *tmp; + struct hlist_node *tmp; unsigned long flags, orig_ret_address; unsigned long trampoline_address; kprobe_opcode_t *correct_ret_addr; @@ -379,7 +379,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, orig_ret_address = 0; correct_ret_addr = NULL; trampoline_address = (unsigned long) &kretprobe_trampoline; - hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { + hlist_for_each_entry_safe(ri, tmp, head, hlist) { if (ri->task != current) /* another task is sharing our hash bucket */ continue; @@ -398,7 +398,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, kretprobe_assert(ri, orig_ret_address, trampoline_address); correct_ret_addr = ri->ret_addr; - hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { + hlist_for_each_entry_safe(ri, tmp, head, hlist) { if (ri->task != current) /* another task is sharing our hash bucket */ continue; @@ -427,7 +427,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, kretprobe_hash_unlock(current, &flags); preempt_enable_no_resched(); - hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) { + hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); kfree(ri); } diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index ae672f41c464..49ce6bb2c641 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -228,4 +228,16 @@ int arch_add_memory(int nid, u64 start, u64 size) vmem_remove_mapping(start, size); return rc; } + +#ifdef CONFIG_MEMORY_HOTREMOVE +int arch_remove_memory(u64 start, u64 size) +{ + /* + * There is no hardware or firmware interface which could trigger a + * hot memory remove on s390. So there is nothing that needs to be + * implemented. + */ + return -EBUSY; +} +#endif #endif /* CONFIG_MEMORY_HOTPLUG */ diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index c59a5efa58b1..f2a462625c9e 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -91,11 +91,9 @@ void arch_pick_mmap_layout(struct mm_struct *mm) if (mmap_is_legacy()) { mm->mmap_base = TASK_UNMAPPED_BASE; mm->get_unmapped_area = arch_get_unmapped_area; - mm->unmap_area = arch_unmap_area; } else { mm->mmap_base = mmap_base(); mm->get_unmapped_area = arch_get_unmapped_area_topdown; - mm->unmap_area = arch_unmap_area_topdown; } } @@ -173,11 +171,9 @@ void arch_pick_mmap_layout(struct mm_struct *mm) if (mmap_is_legacy()) { mm->mmap_base = TASK_UNMAPPED_BASE; mm->get_unmapped_area = s390_get_unmapped_area; - mm->unmap_area = arch_unmap_area; } else { mm->mmap_base = mmap_base(); mm->get_unmapped_area = s390_get_unmapped_area_topdown; - mm->unmap_area = arch_unmap_area_topdown; } } diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index 6ed1426d27c5..fa09c2f02e64 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -272,6 +272,10 @@ out: return ret; } +void vmemmap_free(struct page *memmap, unsigned long nr_pages) +{ +} + /* * Add memory segment to the segment list if it doesn't overlap with * an already present segment. diff --git a/arch/s390/pci/pci_msi.c b/arch/s390/pci/pci_msi.c index 90fd3482b9e2..0297931335e1 100644 --- a/arch/s390/pci/pci_msi.c +++ b/arch/s390/pci/pci_msi.c @@ -25,10 +25,9 @@ static DEFINE_SPINLOCK(msi_map_lock); struct msi_desc *__irq_get_msi_desc(unsigned int irq) { - struct hlist_node *entry; struct msi_map *map; - hlist_for_each_entry_rcu(map, entry, + hlist_for_each_entry_rcu(map, &msi_hash[msi_hashfn(irq)], msi_chain) if (map->irq == irq) return map->msi; diff --git a/arch/sh/kernel/kprobes.c b/arch/sh/kernel/kprobes.c index 1208b09e95c3..42b46e61a2d5 100644 --- a/arch/sh/kernel/kprobes.c +++ b/arch/sh/kernel/kprobes.c @@ -310,7 +310,7 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) { struct kretprobe_instance *ri = NULL; struct hlist_head *head, empty_rp; - struct hlist_node *node, *tmp; + struct hlist_node *tmp; unsigned long flags, orig_ret_address = 0; unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline; @@ -330,7 +330,7 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) * real return address, and all the rest will point to * kretprobe_trampoline */ - hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { + hlist_for_each_entry_safe(ri, tmp, head, hlist) { if (ri->task != current) /* another task is sharing our hash bucket */ continue; @@ -360,7 +360,7 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) preempt_enable_no_resched(); - hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) { + hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); kfree(ri); } diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index 82cc576fab15..105794037143 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -558,4 +558,21 @@ int memory_add_physaddr_to_nid(u64 addr) EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); #endif +#ifdef CONFIG_MEMORY_HOTREMOVE +int arch_remove_memory(u64 start, u64 size) +{ + unsigned long start_pfn = start >> PAGE_SHIFT; + unsigned long nr_pages = size >> PAGE_SHIFT; + struct zone *zone; + int ret; + + zone = page_zone(pfn_to_page(start_pfn)); + ret = __remove_pages(zone, start_pfn, nr_pages); + if (unlikely(ret)) + pr_warn("%s: Failed, __remove_pages() == %d\n", __func__, + ret); + + return ret; +} +#endif #endif /* CONFIG_MEMORY_HOTPLUG */ diff --git a/arch/sparc/kernel/kprobes.c b/arch/sparc/kernel/kprobes.c index a39d1ba5a119..e72212148d2a 100644 --- a/arch/sparc/kernel/kprobes.c +++ b/arch/sparc/kernel/kprobes.c @@ -511,7 +511,7 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) { struct kretprobe_instance *ri = NULL; struct hlist_head *head, empty_rp; - struct hlist_node *node, *tmp; + struct hlist_node *tmp; unsigned long flags, orig_ret_address = 0; unsigned long trampoline_address =(unsigned long)&kretprobe_trampoline; @@ -531,7 +531,7 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) * real return address, and all the rest will point to * kretprobe_trampoline */ - hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { + hlist_for_each_entry_safe(ri, tmp, head, hlist) { if (ri->task != current) /* another task is sharing our hash bucket */ continue; @@ -559,7 +559,7 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) kretprobe_hash_unlock(current, &flags); preempt_enable_no_resched(); - hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) { + hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); kfree(ri); } diff --git a/arch/sparc/kernel/ldc.c b/arch/sparc/kernel/ldc.c index 9fcc6b4e93b3..54df554b82d9 100644 --- a/arch/sparc/kernel/ldc.c +++ b/arch/sparc/kernel/ldc.c @@ -953,9 +953,8 @@ static HLIST_HEAD(ldc_channel_list); static int __ldc_channel_exists(unsigned long id) { struct ldc_channel *lp; - struct hlist_node *n; - hlist_for_each_entry(lp, n, &ldc_channel_list, list) { + hlist_for_each_entry(lp, &ldc_channel_list, list) { if (lp->id == id) return 1; } diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c index 708bc29d36a8..f3c169f9d3a1 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -290,7 +290,6 @@ void arch_pick_mmap_layout(struct mm_struct *mm) sysctl_legacy_va_layout) { mm->mmap_base = TASK_UNMAPPED_BASE + random_factor; mm->get_unmapped_area = arch_get_unmapped_area; - mm->unmap_area = arch_unmap_area; } else { /* We know it's 32-bit */ unsigned long task_size = STACK_TOP32; @@ -302,7 +301,6 @@ void arch_pick_mmap_layout(struct mm_struct *mm) mm->mmap_base = PAGE_ALIGN(task_size - gap - random_factor); mm->get_unmapped_area = arch_get_unmapped_area_topdown; - mm->unmap_area = arch_unmap_area_topdown; } } diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c index dde85ef1c56d..48e0c030e8f5 100644 --- a/arch/sparc/mm/init_32.c +++ b/arch/sparc/mm/init_32.c @@ -57,7 +57,7 @@ void show_mem(unsigned int filter) printk("Mem-info:\n"); show_free_areas(filter); printk("Free swap: %6ldkB\n", - nr_swap_pages << (PAGE_SHIFT-10)); + get_nr_swap_pages() << (PAGE_SHIFT-10)); printk("%ld pages of RAM\n", totalram_pages); printk("%ld free pages\n", nr_free_pages()); } diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index fc5a7c4bd9e8..02598e69e533 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -2229,6 +2229,11 @@ void __meminit vmemmap_populate_print_last(void) node_start = 0; } } + +void vmemmap_free(struct page *memmap, unsigned long nr_pages) +{ +} + #endif /* CONFIG_SPARSEMEM_VMEMMAP */ static void prot_init_common(unsigned long page_none, diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig index 8620b8fa3b36..4163153b0505 100644 --- a/arch/tile/Kconfig +++ b/arch/tile/Kconfig @@ -414,12 +414,6 @@ config TILE_USB Provides USB host adapter support for the built-in EHCI and OHCI interfaces on TILE-Gx chips. -# USB OHCI needs the bounce pool since tilegx will often have more -# than 4GB of memory, but we don't currently use the IOTLB to present -# a 32-bit address to OHCI. So we need to use a bounce pool instead. -config NEED_BOUNCE_POOL - def_bool USB_OHCI_HCD - source "drivers/pci/hotplug/Kconfig" endmenu diff --git a/arch/tile/mm/elf.c b/arch/tile/mm/elf.c index 3cfa98bf9125..743c951c61b0 100644 --- a/arch/tile/mm/elf.c +++ b/arch/tile/mm/elf.c @@ -130,7 +130,6 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, if (!retval) { unsigned long addr = MEM_USER_INTRPT; addr = mmap_region(NULL, addr, INTRPT_SIZE, - MAP_FIXED|MAP_ANONYMOUS|MAP_PRIVATE, VM_READ|VM_EXEC| VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, 0); if (addr > (unsigned long) -PAGE_SIZE) diff --git a/arch/tile/mm/init.c b/arch/tile/mm/init.c index ef29d6c5e10e..2749515a0547 100644 --- a/arch/tile/mm/init.c +++ b/arch/tile/mm/init.c @@ -935,6 +935,14 @@ int remove_memory(u64 start, u64 size) { return -EINVAL; } + +#ifdef CONFIG_MEMORY_HOTREMOVE +int arch_remove_memory(u64 start, u64 size) +{ + /* TODO */ + return -EBUSY; +} +#endif #endif struct kmem_cache *pgd_cache; diff --git a/arch/tile/mm/mmap.c b/arch/tile/mm/mmap.c index f96f4cec602a..d67d91ebf63e 100644 --- a/arch/tile/mm/mmap.c +++ b/arch/tile/mm/mmap.c @@ -66,10 +66,8 @@ void arch_pick_mmap_layout(struct mm_struct *mm) if (!is_32bit || rlimit(RLIMIT_STACK) == RLIM_INFINITY) { mm->mmap_base = TASK_UNMAPPED_BASE; mm->get_unmapped_area = arch_get_unmapped_area; - mm->unmap_area = arch_unmap_area; } else { mm->mmap_base = mmap_base(mm); mm->get_unmapped_area = arch_get_unmapped_area_topdown; - mm->unmap_area = arch_unmap_area_topdown; } } diff --git a/arch/tile/mm/pgtable.c b/arch/tile/mm/pgtable.c index de0de0c0e8a1..b3b4972c2451 100644 --- a/arch/tile/mm/pgtable.c +++ b/arch/tile/mm/pgtable.c @@ -61,7 +61,7 @@ void show_mem(unsigned int filter) global_page_state(NR_PAGETABLE), global_page_state(NR_BOUNCE), global_page_state(NR_FILE_PAGES), - nr_swap_pages); + get_nr_swap_pages()); for_each_zone(zone) { unsigned long flags, order, total = 0, largest_order = -1; diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index a703af19c281..3b3558577642 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -309,8 +309,6 @@ static int load_aout_binary(struct linux_binprm *bprm) (current->mm->start_data = N_DATADDR(ex)); current->mm->brk = ex.a_bss + (current->mm->start_brk = N_BSSADDR(ex)); - current->mm->free_area_cache = TASK_UNMAPPED_BASE; - current->mm->cached_hole_size = 0; retval = setup_arg_pages(bprm, IA32_STACK_TOP, EXSTACK_DEFAULT); if (retval < 0) { diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h index cccd07fa5e3a..b8e9224f0b45 100644 --- a/arch/x86/include/asm/e820.h +++ b/arch/x86/include/asm/e820.h @@ -17,6 +17,8 @@ extern unsigned long pci_mem_start; extern int e820_any_mapped(u64 start, u64 end, unsigned type); extern int e820_all_mapped(u64 start, u64 end, unsigned type); extern void e820_add_region(u64 start, u64 size, int type); +extern void e820_add_limit_region(u64 start, u64 size, int type); +extern void e820_adjust_region(u64 *start, u64 *size); extern void e820_print_map(char *who); extern int sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, u32 *pnr_map); diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h index 52560a2038e1..1b99ee5c9f00 100644 --- a/arch/x86/include/asm/numa.h +++ b/arch/x86/include/asm/numa.h @@ -57,8 +57,8 @@ static inline int numa_cpu_node(int cpu) #endif #ifdef CONFIG_NUMA -extern void __cpuinit numa_set_node(int cpu, int node); -extern void __cpuinit numa_clear_node(int cpu); +extern void numa_set_node(int cpu, int node); +extern void numa_clear_node(int cpu); extern void __init init_cpu_to_node(void); extern void __cpuinit numa_add_cpu(int cpu); extern void __cpuinit numa_remove_cpu(int cpu); diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index e6423002c10b..567b5d0632b2 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -351,6 +351,7 @@ static inline void update_page_count(int level, unsigned long pages) { } * as a pte too. */ extern pte_t *lookup_address(unsigned long address, unsigned int *level); +extern int __split_large_page(pte_t *kpte, unsigned long address, pte_t *pbase); extern phys_addr_t slow_virt_to_phys(void *__address); #endif /* !__ASSEMBLY__ */ diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index cfc755dc1607..230c8ea878e5 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -696,6 +696,10 @@ EXPORT_SYMBOL(acpi_map_lsapic); int acpi_unmap_lsapic(int cpu) { +#ifdef CONFIG_ACPI_NUMA + set_apicid_to_node(per_cpu(x86_cpu_to_apicid, cpu), NUMA_NO_NODE); +#endif + per_cpu(x86_cpu_to_apicid, cpu) = -1; set_cpu_present(cpu, false); num_processors--; diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index d32abeabbda5..0d5bb689649a 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -47,6 +47,7 @@ unsigned long pci_mem_start = 0xaeedbabe; #ifdef CONFIG_PCI EXPORT_SYMBOL(pci_mem_start); #endif +static u64 mem_limit = ~0ULL; /* * This function checks if any part of the range <start,end> is mapped @@ -108,7 +109,7 @@ int __init e820_all_mapped(u64 start, u64 end, unsigned type) * Add a memory region to the kernel e820 map. */ static void __init __e820_add_region(struct e820map *e820x, u64 start, u64 size, - int type) + int type, bool limited) { int x = e820x->nr_map; @@ -119,6 +120,22 @@ static void __init __e820_add_region(struct e820map *e820x, u64 start, u64 size, return; } + if (limited) { + if (start >= mem_limit) { + printk(KERN_ERR "e820: ignoring [mem %#010llx-%#010llx]\n", + (unsigned long long)start, + (unsigned long long)(start + size - 1)); + return; + } + + if (mem_limit - start < size) { + printk(KERN_ERR "e820: ignoring [mem %#010llx-%#010llx]\n", + (unsigned long long)mem_limit, + (unsigned long long)(start + size - 1)); + size = mem_limit - start; + } + } + e820x->map[x].addr = start; e820x->map[x].size = size; e820x->map[x].type = type; @@ -127,7 +144,37 @@ static void __init __e820_add_region(struct e820map *e820x, u64 start, u64 size, void __init e820_add_region(u64 start, u64 size, int type) { - __e820_add_region(&e820, start, size, type); + __e820_add_region(&e820, start, size, type, false); +} + +/* + * do_add_efi_memmap() calls this function(). + * + * Note: BOOT_SERVICES_{CODE,DATA} regions on some efi machines are marked + * as E820_RAM, and they are needed to be mapped. Please use e820_add_region() + * to add BOOT_SERVICES_{CODE,DATA} regions. + */ +void __init e820_add_limit_region(u64 start, u64 size, int type) +{ + /* + * efi_init() is called after finish_e820_parsing(), so we should + * check whether [start, start + size) contains address above + * mem_limit if the type is E820_RAM. + */ + __e820_add_region(&e820, start, size, type, type == E820_RAM); +} + +void __init e820_adjust_region(u64 *start, u64 *size) +{ + if (*start >= mem_limit) { + *size = 0; + return; + } + + if (mem_limit - *start < *size) + *size = mem_limit - *start; + + return; } static void __init e820_print_type(u32 type) @@ -455,8 +502,9 @@ static u64 __init __e820_update_range(struct e820map *e820x, u64 start, /* new range is totally covered? */ if (ei->addr < start && ei_end > end) { - __e820_add_region(e820x, start, size, new_type); - __e820_add_region(e820x, end, ei_end - end, ei->type); + __e820_add_region(e820x, start, size, new_type, false); + __e820_add_region(e820x, end, ei_end - end, ei->type, + false); ei->size = start - ei->addr; real_updated_size += size; continue; @@ -469,7 +517,7 @@ static u64 __init __e820_update_range(struct e820map *e820x, u64 start, continue; __e820_add_region(e820x, final_start, final_end - final_start, - new_type); + new_type, false); real_updated_size += final_end - final_start; @@ -809,7 +857,7 @@ static int userdef __initdata; /* "mem=nopentium" disables the 4MB page tables. */ static int __init parse_memopt(char *p) { - u64 mem_size; + char *oldp; if (!p) return -EINVAL; @@ -825,11 +873,11 @@ static int __init parse_memopt(char *p) } userdef = 1; - mem_size = memparse(p, &p); + oldp = p; + mem_limit = memparse(p, &p); /* don't remove all of memory when handling "mem={invalid}" param */ - if (mem_size == 0) + if (mem_limit == 0 || p == oldp) return -EINVAL; - e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1); return 0; } @@ -895,6 +943,12 @@ early_param("memmap", parse_memmap_opt); void __init finish_e820_parsing(void) { + if (mem_limit != ~0ULL) { + userdef = 1; + e820_remove_range(mem_limit, ULLONG_MAX - mem_limit, + E820_RAM, 1); + } + if (userdef) { u32 nr = e820.nr_map; diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index e124554598ee..3f06e6149981 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -652,7 +652,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs) { struct kretprobe_instance *ri = NULL; struct hlist_head *head, empty_rp; - struct hlist_node *node, *tmp; + struct hlist_node *tmp; unsigned long flags, orig_ret_address = 0; unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline; kprobe_opcode_t *correct_ret_addr = NULL; @@ -682,7 +682,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs) * will be the real return address, and all the rest will * point to kretprobe_trampoline. */ - hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { + hlist_for_each_entry_safe(ri, tmp, head, hlist) { if (ri->task != current) /* another task is sharing our hash bucket */ continue; @@ -701,7 +701,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs) kretprobe_assert(ri, orig_ret_address, trampoline_address); correct_ret_addr = ri->ret_addr; - hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { + hlist_for_each_entry_safe(ri, tmp, head, hlist) { if (ri->task != current) /* another task is sharing our hash bucket */ continue; @@ -728,7 +728,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs) kretprobe_hash_unlock(current, &flags); - hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) { + hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); kfree(ri); } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index c64ecb5f3a85..ede1d0f35939 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1052,6 +1052,15 @@ void __init setup_arch(char **cmdline_p) setup_bios_corruption_check(); #endif + /* + * In the memory hotplug case, the kernel needs info from SRAT to + * determine which memory is hotpluggable before allocating memory + * using memblock. + */ + acpi_boot_table_init(); + early_acpi_boot_init(); + early_parse_srat(); + #ifdef CONFIG_X86_32 printk(KERN_DEBUG "initial memory mapped: [mem 0x00000000-%#010lx]\n", (max_pfn_mapped<<PAGE_SHIFT) - 1); @@ -1096,10 +1105,6 @@ void __init setup_arch(char **cmdline_p) /* * Parse the ACPI tables for possible boot-time SMP configuration. */ - acpi_boot_table_init(); - - early_acpi_boot_init(); - initmem_init(); memblock_find_dma_reserve(); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 0242a8a1b2e2..d8fa3484d248 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -1645,13 +1645,13 @@ static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, static void kvm_mmu_commit_zap_page(struct kvm *kvm, struct list_head *invalid_list); -#define for_each_gfn_sp(kvm, sp, gfn, pos) \ - hlist_for_each_entry(sp, pos, \ +#define for_each_gfn_sp(kvm, sp, gfn) \ + hlist_for_each_entry(sp, \ &(kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)], hash_link) \ if ((sp)->gfn != (gfn)) {} else -#define for_each_gfn_indirect_valid_sp(kvm, sp, gfn, pos) \ - hlist_for_each_entry(sp, pos, \ +#define for_each_gfn_indirect_valid_sp(kvm, sp, gfn) \ + hlist_for_each_entry(sp, \ &(kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)], hash_link) \ if ((sp)->gfn != (gfn) || (sp)->role.direct || \ (sp)->role.invalid) {} else @@ -1707,11 +1707,10 @@ static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, static void kvm_sync_pages(struct kvm_vcpu *vcpu, gfn_t gfn) { struct kvm_mmu_page *s; - struct hlist_node *node; LIST_HEAD(invalid_list); bool flush = false; - for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn, node) { + for_each_gfn_indirect_valid_sp (vcpu->kvm, s, gfn) { if (!s->unsync) continue; @@ -1849,7 +1848,6 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, union kvm_mmu_page_role role; unsigned quadrant; struct kvm_mmu_page *sp; - struct hlist_node *node; bool need_sync = false; role = vcpu->arch.mmu.base_role; @@ -1864,7 +1862,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1; role.quadrant = quadrant; } - for_each_gfn_sp(vcpu->kvm, sp, gfn, node) { + for_each_gfn_sp (vcpu->kvm, sp, gfn) { if (!need_sync && sp->unsync) need_sync = true; @@ -2152,16 +2150,14 @@ void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int goal_nr_mmu_pages) int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) { struct kvm_mmu_page *sp; - struct hlist_node *node; LIST_HEAD(invalid_list); int r; pgprintk("%s: looking for gfn %llx\n", __func__, gfn); r = 0; spin_lock(&kvm->mmu_lock); - for_each_gfn_indirect_valid_sp(kvm, sp, gfn, node) { - pgprintk("%s: gfn %llx role %x\n", __func__, gfn, - sp->role.word); + for_each_gfn_indirect_valid_sp (kvm, sp, gfn) { + pgprintk("%s: gfn %llx role %x\n", __func__, gfn, sp->role.word); r = 1; kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); } @@ -2289,24 +2285,22 @@ static void __kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) static void kvm_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn) { struct kvm_mmu_page *s; - struct hlist_node *node; - for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn, node) { + for_each_gfn_indirect_valid_sp (vcpu->kvm, s, gfn) { if (s->unsync) continue; - WARN_ON(s->role.level != PT_PAGE_TABLE_LEVEL); - __kvm_unsync_page(vcpu, s); - } + WARN_ON(s->role.level != PT_PAGE_TABLE_LEVEL); + __kvm_unsync_page(vcpu, s); + } } static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn, bool can_unsync) { struct kvm_mmu_page *s; - struct hlist_node *node; bool need_unsync = false; - for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn, node) { + for_each_gfn_indirect_valid_sp (vcpu->kvm, s, gfn) { if (!can_unsync) return 1; @@ -3941,7 +3935,6 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, gfn_t gfn = gpa >> PAGE_SHIFT; union kvm_mmu_page_role mask = { .word = 0 }; struct kvm_mmu_page *sp; - struct hlist_node *node; LIST_HEAD(invalid_list); u64 entry, gentry, *spte; int npte; @@ -3972,15 +3965,12 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE); mask.cr0_wp = mask.cr4_pae = mask.nxe = 1; - for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn, node) { - if (detect_write_misaligned(sp, gpa, bytes) || - detect_write_flooding(sp)) { - zap_page |= !!kvm_mmu_prepare_zap_page(vcpu->kvm, sp, - &invalid_list); + for_each_gfn_indirect_valid_sp (vcpu->kvm, sp, gfn) { + if (detect_write_misaligned(sp, gpa, bytes) || detect_write_flooding(sp)) { + zap_page |= !!kvm_mmu_prepare_zap_page(vcpu->kvm, sp, &invalid_list); ++vcpu->kvm->stat.mmu_flooded; continue; } - spte = get_written_sptes(sp, gpa, &npte); if (!spte) continue; diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 027088f2f7dd..c755cd624bf0 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -937,14 +937,8 @@ spurious_fault(unsigned long error_code, unsigned long address) if (pmd_large(*pmd)) return spurious_fault_check(error_code, (pte_t *) pmd); - /* - * Note: don't use pte_present() here, since it returns true - * if the _PAGE_PROTNONE bit is set. However, this aliases the - * _PAGE_GLOBAL bit, which for kernel pages give false positives - * when CONFIG_DEBUG_PAGEALLOC is used. - */ pte = pte_offset_kernel(pmd, address); - if (!(pte_flags(*pte) & _PAGE_PRESENT)) + if (!pte_present(*pte)) return 0; ret = spurious_fault_check(error_code, pte); diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index b299724f6e34..2d19001151d5 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -862,6 +862,18 @@ int arch_add_memory(int nid, u64 start, u64 size) return __add_pages(nid, zone, start_pfn, nr_pages); } + +#ifdef CONFIG_MEMORY_HOTREMOVE +int arch_remove_memory(u64 start, u64 size) +{ + unsigned long start_pfn = start >> PAGE_SHIFT; + unsigned long nr_pages = size >> PAGE_SHIFT; + struct zone *zone; + + zone = page_zone(pfn_to_page(start_pfn)); + return __remove_pages(zone, start_pfn, nr_pages); +} +#endif #endif /* diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 90b6a624fa18..f440080dd3f6 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -707,6 +707,343 @@ int arch_add_memory(int nid, u64 start, u64 size) } EXPORT_SYMBOL_GPL(arch_add_memory); +#define PAGE_INUSE 0xFD + +static void __meminit free_pagetable(struct page *page, int order) +{ + struct zone *zone; + bool bootmem = false; + unsigned long magic; + unsigned int nr_pages = 1 << order; + + /* bootmem page has reserved flag */ + if (PageReserved(page)) { + __ClearPageReserved(page); + bootmem = true; + + magic = (unsigned long)page->lru.next; + if (magic == SECTION_INFO || magic == MIX_SECTION_INFO) { + while (nr_pages--) + put_page_bootmem(page++); + } else + __free_pages_bootmem(page, order); + } else + free_pages((unsigned long)page_address(page), order); + + /* + * SECTION_INFO pages and MIX_SECTION_INFO pages + * are all allocated by bootmem. + */ + if (bootmem) { + zone = page_zone(page); + zone_span_writelock(zone); + zone->present_pages += nr_pages; + zone_span_writeunlock(zone); + totalram_pages += nr_pages; + } +} + +static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd) +{ + pte_t *pte; + int i; + + for (i = 0; i < PTRS_PER_PTE; i++) { + pte = pte_start + i; + if (pte_val(*pte)) + return; + } + + /* free a pte talbe */ + free_pagetable(pmd_page(*pmd), 0); + spin_lock(&init_mm.page_table_lock); + pmd_clear(pmd); + spin_unlock(&init_mm.page_table_lock); +} + +static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud) +{ + pmd_t *pmd; + int i; + + for (i = 0; i < PTRS_PER_PMD; i++) { + pmd = pmd_start + i; + if (pmd_val(*pmd)) + return; + } + + /* free a pmd talbe */ + free_pagetable(pud_page(*pud), 0); + spin_lock(&init_mm.page_table_lock); + pud_clear(pud); + spin_unlock(&init_mm.page_table_lock); +} + +/* Return true if pgd is changed, otherwise return false. */ +static bool __meminit free_pud_table(pud_t *pud_start, pgd_t *pgd) +{ + pud_t *pud; + int i; + + for (i = 0; i < PTRS_PER_PUD; i++) { + pud = pud_start + i; + if (pud_val(*pud)) + return false; + } + + /* free a pud table */ + free_pagetable(pgd_page(*pgd), 0); + spin_lock(&init_mm.page_table_lock); + pgd_clear(pgd); + spin_unlock(&init_mm.page_table_lock); + + return true; +} + +static void __meminit +remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end, + bool direct) +{ + unsigned long next, pages = 0; + pte_t *pte; + void *page_addr; + phys_addr_t phys_addr; + + pte = pte_start + pte_index(addr); + for (; addr < end; addr = next, pte++) { + next = (addr + PAGE_SIZE) & PAGE_MASK; + if (next > end) + next = end; + + if (!pte_present(*pte)) + continue; + + /* + * We mapped [0,1G) memory as identity mapping when + * initializing, in arch/x86/kernel/head_64.S. These + * pagetables cannot be removed. + */ + phys_addr = pte_val(*pte) + (addr & PAGE_MASK); + if (phys_addr < (phys_addr_t)0x40000000) + return; + + if (IS_ALIGNED(addr, PAGE_SIZE) && + IS_ALIGNED(next, PAGE_SIZE)) { + /* + * Do not free direct mapping pages since they were + * freed when offlining, or simplely not in use. + */ + if (!direct) + free_pagetable(pte_page(*pte), 0); + + spin_lock(&init_mm.page_table_lock); + pte_clear(&init_mm, addr, pte); + spin_unlock(&init_mm.page_table_lock); + + /* For non-direct mapping, pages means nothing. */ + pages++; + } else { + /* + * If we are here, we are freeing vmemmap pages since + * direct mapped memory ranges to be freed are aligned. + * + * If we are not removing the whole page, it means + * other page structs in this page are being used and + * we canot remove them. So fill the unused page_structs + * with 0xFD, and remove the page when it is wholly + * filled with 0xFD. + */ + memset((void *)addr, PAGE_INUSE, next - addr); + + page_addr = page_address(pte_page(*pte)); + if (!memchr_inv(page_addr, PAGE_INUSE, PAGE_SIZE)) { + free_pagetable(pte_page(*pte), 0); + + spin_lock(&init_mm.page_table_lock); + pte_clear(&init_mm, addr, pte); + spin_unlock(&init_mm.page_table_lock); + } + } + } + + /* Call free_pte_table() in remove_pmd_table(). */ + flush_tlb_all(); + if (direct) + update_page_count(PG_LEVEL_4K, -pages); +} + +static void __meminit +remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end, + bool direct) +{ + unsigned long next, pages = 0; + pte_t *pte_base; + pmd_t *pmd; + void *page_addr; + + pmd = pmd_start + pmd_index(addr); + for (; addr < end; addr = next, pmd++) { + next = pmd_addr_end(addr, end); + + if (!pmd_present(*pmd)) + continue; + + if (pmd_large(*pmd)) { + if (IS_ALIGNED(addr, PMD_SIZE) && + IS_ALIGNED(next, PMD_SIZE)) { + if (!direct) + free_pagetable(pmd_page(*pmd), + get_order(PMD_SIZE)); + + spin_lock(&init_mm.page_table_lock); + pmd_clear(pmd); + spin_unlock(&init_mm.page_table_lock); + pages++; + } else { + /* If here, we are freeing vmemmap pages. */ + memset((void *)addr, PAGE_INUSE, next - addr); + + page_addr = page_address(pmd_page(*pmd)); + if (!memchr_inv(page_addr, PAGE_INUSE, + PMD_SIZE)) { + free_pagetable(pmd_page(*pmd), + get_order(PMD_SIZE)); + + spin_lock(&init_mm.page_table_lock); + pmd_clear(pmd); + spin_unlock(&init_mm.page_table_lock); + } + } + + continue; + } + + pte_base = (pte_t *)pmd_page_vaddr(*pmd); + remove_pte_table(pte_base, addr, next, direct); + free_pte_table(pte_base, pmd); + } + + /* Call free_pmd_table() in remove_pud_table(). */ + if (direct) + update_page_count(PG_LEVEL_2M, -pages); +} + +static void __meminit +remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end, + bool direct) +{ + unsigned long next, pages = 0; + pmd_t *pmd_base; + pud_t *pud; + void *page_addr; + + pud = pud_start + pud_index(addr); + for (; addr < end; addr = next, pud++) { + next = pud_addr_end(addr, end); + + if (!pud_present(*pud)) + continue; + + if (pud_large(*pud)) { + if (IS_ALIGNED(addr, PUD_SIZE) && + IS_ALIGNED(next, PUD_SIZE)) { + if (!direct) + free_pagetable(pud_page(*pud), + get_order(PUD_SIZE)); + + spin_lock(&init_mm.page_table_lock); + pud_clear(pud); + spin_unlock(&init_mm.page_table_lock); + pages++; + } else { + /* If here, we are freeing vmemmap pages. */ + memset((void *)addr, PAGE_INUSE, next - addr); + + page_addr = page_address(pud_page(*pud)); + if (!memchr_inv(page_addr, PAGE_INUSE, + PUD_SIZE)) { + free_pagetable(pud_page(*pud), + get_order(PUD_SIZE)); + + spin_lock(&init_mm.page_table_lock); + pud_clear(pud); + spin_unlock(&init_mm.page_table_lock); + } + } + + continue; + } + + pmd_base = (pmd_t *)pud_page_vaddr(*pud); + remove_pmd_table(pmd_base, addr, next, direct); + free_pmd_table(pmd_base, pud); + } + + if (direct) + update_page_count(PG_LEVEL_1G, -pages); +} + +/* start and end are both virtual address. */ +static void __meminit +remove_pagetable(unsigned long start, unsigned long end, bool direct) +{ + unsigned long next; + pgd_t *pgd; + pud_t *pud; + bool pgd_changed = false; + + for (; start < end; start = next) { + next = pgd_addr_end(start, end); + + pgd = pgd_offset_k(start); + if (!pgd_present(*pgd)) + continue; + + pud = (pud_t *)pgd_page_vaddr(*pgd); + remove_pud_table(pud, start, next, direct); + if (free_pud_table(pud, pgd)) + pgd_changed = true; + } + + if (pgd_changed) + sync_global_pgds(start, end - 1); + + flush_tlb_all(); +} + +void __ref vmemmap_free(struct page *memmap, unsigned long nr_pages) +{ + unsigned long start = (unsigned long)memmap; + unsigned long end = (unsigned long)(memmap + nr_pages); + + remove_pagetable(start, end, false); +} + +static void __meminit +kernel_physical_mapping_remove(unsigned long start, unsigned long end) +{ + start = (unsigned long)__va(start); + end = (unsigned long)__va(end); + + remove_pagetable(start, end, true); +} + +#ifdef CONFIG_MEMORY_HOTREMOVE +int __ref arch_remove_memory(u64 start, u64 size) +{ + unsigned long start_pfn = start >> PAGE_SHIFT; + unsigned long nr_pages = size >> PAGE_SHIFT; + struct zone *zone; + int ret; + + zone = page_zone(pfn_to_page(start_pfn)); + kernel_physical_mapping_remove(start, start + size); + ret = __remove_pages(zone, start_pfn, nr_pages); + WARN_ON_ONCE(ret); + + return ret; +} +#endif #endif /* CONFIG_MEMORY_HOTPLUG */ static struct kcore_list kcore_vsyscall; @@ -1016,6 +1353,66 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node) return 0; } +#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_HAVE_BOOTMEM_INFO_NODE) +void register_page_bootmem_memmap(unsigned long section_nr, + struct page *start_page, unsigned long size) +{ + unsigned long addr = (unsigned long)start_page; + unsigned long end = (unsigned long)(start_page + size); + unsigned long next; + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + unsigned int nr_pages; + struct page *page; + + for (; addr < end; addr = next) { + pte_t *pte = NULL; + + pgd = pgd_offset_k(addr); + if (pgd_none(*pgd)) { + next = (addr + PAGE_SIZE) & PAGE_MASK; + continue; + } + get_page_bootmem(section_nr, pgd_page(*pgd), MIX_SECTION_INFO); + + pud = pud_offset(pgd, addr); + if (pud_none(*pud)) { + next = (addr + PAGE_SIZE) & PAGE_MASK; + continue; + } + get_page_bootmem(section_nr, pud_page(*pud), MIX_SECTION_INFO); + + if (!cpu_has_pse) { + next = (addr + PAGE_SIZE) & PAGE_MASK; + pmd = pmd_offset(pud, addr); + if (pmd_none(*pmd)) + continue; + get_page_bootmem(section_nr, pmd_page(*pmd), + MIX_SECTION_INFO); + + pte = pte_offset_kernel(pmd, addr); + if (pte_none(*pte)) + continue; + get_page_bootmem(section_nr, pte_page(*pte), + SECTION_INFO); + } else { + next = pmd_addr_end(addr, end); + + pmd = pmd_offset(pud, addr); + if (pmd_none(*pmd)) + continue; + + nr_pages = 1 << (get_order(PMD_SIZE)); + page = pmd_page(*pmd); + while (nr_pages--) + get_page_bootmem(section_nr, page++, + SECTION_INFO); + } + } +} +#endif + void __meminit vmemmap_populate_print_last(void) { if (p_start) { diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 845df6835f9f..62c29a5bfe26 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -115,10 +115,8 @@ void arch_pick_mmap_layout(struct mm_struct *mm) if (mmap_is_legacy()) { mm->mmap_base = mmap_legacy_base(); mm->get_unmapped_area = arch_get_unmapped_area; - mm->unmap_area = arch_unmap_area; } else { mm->mmap_base = mmap_base(); mm->get_unmapped_area = arch_get_unmapped_area_topdown; - mm->unmap_area = arch_unmap_area_topdown; } } diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 8504f3698753..3545585207c7 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -56,7 +56,7 @@ early_param("numa", numa_setup); /* * apicid, cpu, node mappings */ -s16 __apicid_to_node[MAX_LOCAL_APIC] __cpuinitdata = { +s16 __apicid_to_node[MAX_LOCAL_APIC] = { [0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE }; @@ -78,7 +78,7 @@ EXPORT_SYMBOL(node_to_cpumask_map); DEFINE_EARLY_PER_CPU(int, x86_cpu_to_node_map, NUMA_NO_NODE); EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map); -void __cpuinit numa_set_node(int cpu, int node) +void numa_set_node(int cpu, int node) { int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map); @@ -97,11 +97,10 @@ void __cpuinit numa_set_node(int cpu, int node) #endif per_cpu(x86_cpu_to_node_map, cpu) = node; - if (node != NUMA_NO_NODE) - set_cpu_numa_node(cpu, node); + set_cpu_numa_node(cpu, node); } -void __cpuinit numa_clear_node(int cpu) +void numa_clear_node(int cpu) { numa_set_node(cpu, NUMA_NO_NODE); } @@ -213,10 +212,9 @@ static void __init setup_node_data(int nid, u64 start, u64 end) * Allocate node data. Try node-local memory and then any node. * Never allocate in DMA zone. */ - nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid); + nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid); if (!nd_pa) { - pr_err("Cannot find %zu bytes in node %d\n", - nd_size, nid); + pr_err("Cannot find %zu bytes in any node\n", nd_size); return; } nd = __va(nd_pa); @@ -561,7 +559,7 @@ static int __init numa_init(int (*init_func)(void)) for (i = 0; i < MAX_LOCAL_APIC; i++) set_apicid_to_node(i, NUMA_NO_NODE); - nodes_clear(numa_nodes_parsed); + /* Do not clear numa_nodes_parsed because SRAT was parsed earlier. */ nodes_clear(node_possible_map); nodes_clear(node_online_map); memset(&numa_meminfo, 0, sizeof(numa_meminfo)); diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index a1b1c88f9caf..091934e1d0d9 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -473,6 +473,19 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, pgprot_val(req_prot) |= pgprot_val(cpa->mask_set); /* + * Set the PSE and GLOBAL flags only if the PRESENT flag is + * set otherwise pmd_present/pmd_huge will return true even on + * a non present pmd. The canon_pgprot will clear _PAGE_GLOBAL + * for the ancient hardware that doesn't support it. + */ + if (pgprot_val(new_prot) & _PAGE_PRESENT) + pgprot_val(new_prot) |= _PAGE_PSE | _PAGE_GLOBAL; + else + pgprot_val(new_prot) &= ~(_PAGE_PSE | _PAGE_GLOBAL); + + new_prot = canon_pgprot(new_prot); + + /* * old_pte points to the large page base address. So we need * to add the offset of the virtual address: */ @@ -517,7 +530,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, * The address is aligned and the number of pages * covers the full page. */ - new_pte = pfn_pte(pte_pfn(old_pte), canon_pgprot(new_prot)); + new_pte = pfn_pte(pte_pfn(old_pte), new_prot); __set_pmd_pte(kpte, address, new_pte); cpa->flags |= CPA_FLUSHTLB; do_split = 0; @@ -529,21 +542,13 @@ out_unlock: return do_split; } -static int split_large_page(pte_t *kpte, unsigned long address) +int __split_large_page(pte_t *kpte, unsigned long address, pte_t *pbase) { unsigned long pfn, pfninc = 1; unsigned int i, level; - pte_t *pbase, *tmp; + pte_t *tmp; pgprot_t ref_prot; - struct page *base; - - if (!debug_pagealloc) - spin_unlock(&cpa_lock); - base = alloc_pages(GFP_KERNEL | __GFP_NOTRACK, 0); - if (!debug_pagealloc) - spin_lock(&cpa_lock); - if (!base) - return -ENOMEM; + struct page *base = virt_to_page(pbase); spin_lock(&pgd_lock); /* @@ -551,10 +556,11 @@ static int split_large_page(pte_t *kpte, unsigned long address) * up for us already: */ tmp = lookup_address(address, &level); - if (tmp != kpte) - goto out_unlock; + if (tmp != kpte) { + spin_unlock(&pgd_lock); + return 1; + } - pbase = (pte_t *)page_address(base); paravirt_alloc_pte(&init_mm, page_to_pfn(base)); ref_prot = pte_pgprot(pte_clrhuge(*kpte)); /* @@ -568,16 +574,35 @@ static int split_large_page(pte_t *kpte, unsigned long address) #ifdef CONFIG_X86_64 if (level == PG_LEVEL_1G) { pfninc = PMD_PAGE_SIZE >> PAGE_SHIFT; - pgprot_val(ref_prot) |= _PAGE_PSE; + /* + * Set the PSE flags only if the PRESENT flag is set + * otherwise pmd_present/pmd_huge will return true + * even on a non present pmd. + */ + if (pgprot_val(ref_prot) & _PAGE_PRESENT) + pgprot_val(ref_prot) |= _PAGE_PSE; + else + pgprot_val(ref_prot) &= ~_PAGE_PSE; } #endif /* + * Set the GLOBAL flags only if the PRESENT flag is set + * otherwise pmd/pte_present will return true even on a non + * present pmd/pte. The canon_pgprot will clear _PAGE_GLOBAL + * for the ancient hardware that doesn't support it. + */ + if (pgprot_val(ref_prot) & _PAGE_PRESENT) + pgprot_val(ref_prot) |= _PAGE_GLOBAL; + else + pgprot_val(ref_prot) &= ~_PAGE_GLOBAL; + + /* * Get the target pfn from the original entry: */ pfn = pte_pfn(*kpte); for (i = 0; i < PTRS_PER_PTE; i++, pfn += pfninc) - set_pte(&pbase[i], pfn_pte(pfn, ref_prot)); + set_pte(&pbase[i], pfn_pte(pfn, canon_pgprot(ref_prot))); if (pfn_range_is_mapped(PFN_DOWN(__pa(address)), PFN_DOWN(__pa(address)) + 1)) @@ -601,17 +626,27 @@ static int split_large_page(pte_t *kpte, unsigned long address) * going on. */ __flush_tlb_all(); + spin_unlock(&pgd_lock); - base = NULL; + return 0; +} -out_unlock: - /* - * If we dropped out via the lookup_address check under - * pgd_lock then stick the page back into the pool: - */ - if (base) +static int split_large_page(pte_t *kpte, unsigned long address) +{ + pte_t *pbase; + struct page *base; + + if (!debug_pagealloc) + spin_unlock(&cpa_lock); + base = alloc_pages(GFP_KERNEL | __GFP_NOTRACK, 0); + if (!debug_pagealloc) + spin_lock(&cpa_lock); + if (!base) + return -ENOMEM; + + pbase = (pte_t *)page_address(base); + if (__split_large_page(kpte, address, pbase)) __free_page(base); - spin_unlock(&pgd_lock); return 0; } @@ -682,6 +717,18 @@ repeat: new_prot = static_protections(new_prot, address, pfn); /* + * Set the GLOBAL flags only if the PRESENT flag is + * set otherwise pte_present will return true even on + * a non present pte. The canon_pgprot will clear + * _PAGE_GLOBAL for the ancient hardware that doesn't + * support it. + */ + if (pgprot_val(new_prot) & _PAGE_PRESENT) + pgprot_val(new_prot) |= _PAGE_GLOBAL; + else + pgprot_val(new_prot) &= ~_PAGE_GLOBAL; + + /* * We need to keep the pfn from the existing PTE, * after all we're only going to change it's attributes * not the memory it points to diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c index cdd0da9dd530..b20b5b7ac7e1 100644 --- a/arch/x86/mm/srat.c +++ b/arch/x86/mm/srat.c @@ -141,11 +141,87 @@ static inline int save_add_info(void) {return 1;} static inline int save_add_info(void) {return 0;} #endif +#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP +static void __init +handle_movablemem(int node, u64 start, u64 end, u32 hotpluggable) +{ + int overlap; + unsigned long start_pfn, end_pfn; + + start_pfn = PFN_DOWN(start); + end_pfn = PFN_UP(end); + + /* + * For movablemem_map=acpi: + * + * SRAT: |_____| |_____| |_________| |_________| ...... + * node id: 0 1 1 2 + * hotpluggable: n y y n + * movablemem_map: |_____| |_________| + * + * Using movablemem_map, we can prevent memblock from allocating memory + * on ZONE_MOVABLE at boot time. + */ + if (hotpluggable && movablemem_map.acpi) { + insert_movablemem_map(start_pfn, end_pfn); + goto out; + } + + /* + * For movablemem_map=nn[KMG]@ss[KMG]: + * + * SRAT: |_____| |_____| |_________| |_________| ...... + * node id: 0 1 1 2 + * user specified: |__| |___| + * movablemem_map: |___| |_________| |______| ...... + * + * Using movablemem_map, we can prevent memblock from allocating memory + * on ZONE_MOVABLE at boot time. + * + * NOTE: In this case, SRAT info will be ingored. + */ + overlap = movablemem_map_overlap(start_pfn, end_pfn); + if (overlap >= 0) { + /* + * If part of this range is in movablemem_map, we need to + * add the range after it to extend the range to the end + * of the node, because from the min address specified to + * the end of the node will be ZONE_MOVABLE. + */ + start_pfn = max(start_pfn, + movablemem_map.map[overlap].start_pfn); + insert_movablemem_map(start_pfn, end_pfn); + + /* + * Set the nodemask, so that if the address range on one node + * is not continuse, we can add the subsequent ranges on the + * same node into movablemem_map. + */ + node_set(node, movablemem_map.numa_nodes_hotplug); + } else { + if (node_isset(node, movablemem_map.numa_nodes_hotplug)) + /* + * Insert the range if we already have movable ranges + * on the same node. + */ + insert_movablemem_map(start_pfn, end_pfn); + } +out: + return; +} +#else /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ +static inline void +handle_movablemem(int node, u64 start, u64 end, u32 hotpluggable) +{ +} +#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ + /* Callback for parsing of the Proximity Domain <-> Memory Area mappings */ int __init acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) { u64 start, end; + u32 hotpluggable; int node, pxm; if (srat_disabled()) @@ -154,7 +230,8 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) goto out_err_bad_srat; if ((ma->flags & ACPI_SRAT_MEM_ENABLED) == 0) goto out_err; - if ((ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) && !save_add_info()) + hotpluggable = ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE; + if (hotpluggable && !save_add_info()) goto out_err; start = ma->base_address; @@ -174,9 +251,12 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) node_set(node, numa_nodes_parsed); - printk(KERN_INFO "SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]\n", + printk(KERN_INFO "SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx] %s\n", node, pxm, - (unsigned long long) start, (unsigned long long) end - 1); + (unsigned long long) start, (unsigned long long) end - 1, + hotpluggable ? "Hot Pluggable": ""); + + handle_movablemem(node, start, end, hotpluggable); return 0; out_err_bad_srat: diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 9b9054b98187..fe59054afc1d 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -320,10 +320,17 @@ static void __init do_add_efi_memmap(void) int e820_type; switch (md->type) { - case EFI_LOADER_CODE: - case EFI_LOADER_DATA: case EFI_BOOT_SERVICES_CODE: case EFI_BOOT_SERVICES_DATA: + /* EFI_BOOT_SERVICES_{CODE,DATA} needs to be mapped */ + if (md->attribute & EFI_MEMORY_WB) + e820_type = E820_RAM; + else + e820_type = E820_RESERVED; + e820_add_region(start, size, e820_type); + continue; + case EFI_LOADER_CODE: + case EFI_LOADER_DATA: case EFI_CONVENTIONAL_MEMORY: if (md->attribute & EFI_MEMORY_WB) e820_type = E820_RAM; @@ -348,7 +355,7 @@ static void __init do_add_efi_memmap(void) e820_type = E820_RESERVED; break; } - e820_add_region(start, size, e820_type); + e820_add_limit_region(start, size, e820_type); } sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); } @@ -455,6 +462,8 @@ void __init efi_free_boot_services(void) md->type != EFI_BOOT_SERVICES_DATA) continue; + e820_adjust_region(&start, &size); + /* Could not reserve boot area */ if (!size) continue; diff --git a/block/Kconfig b/block/Kconfig index 4a85ccf8d4cf..a7e40a7c8214 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -4,7 +4,6 @@ menuconfig BLOCK bool "Enable the block layer" if EXPERT default y - select PERCPU_RWSEM help Provide block layer support for the kernel. diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 87ea95d1f533..b2b9837f9dd3 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -459,7 +459,6 @@ static int blkcg_reset_stats(struct cgroup *cgroup, struct cftype *cftype, { struct blkcg *blkcg = cgroup_to_blkcg(cgroup); struct blkcg_gq *blkg; - struct hlist_node *n; int i; mutex_lock(&blkcg_pol_mutex); @@ -470,7 +469,7 @@ static int blkcg_reset_stats(struct cgroup *cgroup, struct cftype *cftype, * stat updates. This is a debug feature which shouldn't exist * anyway. If you get hit by a race, retry. */ - hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) { + hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) { for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; @@ -518,11 +517,10 @@ void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg, bool show_total) { struct blkcg_gq *blkg; - struct hlist_node *n; u64 total = 0; rcu_read_lock(); - hlist_for_each_entry_rcu(blkg, n, &blkcg->blkg_list, blkcg_node) { + hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) { spin_lock_irq(blkg->q->queue_lock); if (blkcg_policy_enabled(blkg->q, pol)) total += prfill(sf, blkg->pd[pol->plid], data); diff --git a/block/blk-core.c b/block/blk-core.c index 66d31687cf6b..186603b36c44 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -151,7 +151,8 @@ void blk_rq_init(struct request_queue *q, struct request *rq) EXPORT_SYMBOL(blk_rq_init); static void req_bio_endio(struct request *rq, struct bio *bio, - unsigned int nbytes, int error) + unsigned int nbytes, int error, + struct batch_complete *batch) { if (error) clear_bit(BIO_UPTODATE, &bio->bi_flags); @@ -175,7 +176,7 @@ static void req_bio_endio(struct request *rq, struct bio *bio, /* don't actually finish bio if it's part of flush sequence */ if (bio->bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ)) - bio_endio(bio, error); + bio_endio_batch(bio, error, batch); } void blk_dump_rq_flags(struct request *rq, char *msg) @@ -1473,6 +1474,11 @@ void blk_queue_bio(struct request_queue *q, struct bio *bio) */ blk_queue_bounce(q, &bio); + if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) { + bio_endio(bio, -EIO); + return; + } + if (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) { spin_lock_irq(q->queue_lock); where = ELEVATOR_INSERT_FLUSH; @@ -1706,9 +1712,6 @@ generic_make_request_checks(struct bio *bio) */ blk_partition_remap(bio); - if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) - goto end_io; - if (bio_check_eod(bio, nr_sectors)) goto end_io; @@ -2248,7 +2251,8 @@ EXPORT_SYMBOL(blk_fetch_request); * %false - this request doesn't have any more data * %true - this request has more data **/ -bool blk_update_request(struct request *req, int error, unsigned int nr_bytes) +bool blk_update_request(struct request *req, int error, unsigned int nr_bytes, + struct batch_complete *batch) { int total_bytes, bio_nbytes, next_idx = 0; struct bio *bio; @@ -2304,7 +2308,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes) if (nr_bytes >= bio->bi_size) { req->bio = bio->bi_next; nbytes = bio->bi_size; - req_bio_endio(req, bio, nbytes, error); + req_bio_endio(req, bio, nbytes, error, batch); next_idx = 0; bio_nbytes = 0; } else { @@ -2366,7 +2370,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes) * if the request wasn't completed, update state */ if (bio_nbytes) { - req_bio_endio(req, bio, bio_nbytes, error); + req_bio_endio(req, bio, bio_nbytes, error, batch); bio->bi_idx += next_idx; bio_iovec(bio)->bv_offset += nr_bytes; bio_iovec(bio)->bv_len -= nr_bytes; @@ -2403,14 +2407,15 @@ EXPORT_SYMBOL_GPL(blk_update_request); static bool blk_update_bidi_request(struct request *rq, int error, unsigned int nr_bytes, - unsigned int bidi_bytes) + unsigned int bidi_bytes, + struct batch_complete *batch) { - if (blk_update_request(rq, error, nr_bytes)) + if (blk_update_request(rq, error, nr_bytes, batch)) return true; /* Bidi request must be completed as a whole */ if (unlikely(blk_bidi_rq(rq)) && - blk_update_request(rq->next_rq, error, bidi_bytes)) + blk_update_request(rq->next_rq, error, bidi_bytes, batch)) return true; if (blk_queue_add_random(rq->q)) @@ -2493,7 +2498,7 @@ static bool blk_end_bidi_request(struct request *rq, int error, struct request_queue *q = rq->q; unsigned long flags; - if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes)) + if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes, NULL)) return true; spin_lock_irqsave(q->queue_lock, flags); @@ -2519,9 +2524,10 @@ static bool blk_end_bidi_request(struct request *rq, int error, * %true - still buffers pending for this request **/ bool __blk_end_bidi_request(struct request *rq, int error, - unsigned int nr_bytes, unsigned int bidi_bytes) + unsigned int nr_bytes, unsigned int bidi_bytes, + struct batch_complete *batch) { - if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes)) + if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes, batch)) return true; blk_finish_request(rq, error); @@ -2622,7 +2628,7 @@ EXPORT_SYMBOL_GPL(blk_end_request_err); **/ bool __blk_end_request(struct request *rq, int error, unsigned int nr_bytes) { - return __blk_end_bidi_request(rq, error, nr_bytes, 0); + return __blk_end_bidi_request(rq, error, nr_bytes, 0, NULL); } EXPORT_SYMBOL(__blk_end_request); @@ -2634,7 +2640,7 @@ EXPORT_SYMBOL(__blk_end_request); * Description: * Completely finish @rq. Must be called with queue lock held. */ -void __blk_end_request_all(struct request *rq, int error) +void blk_end_request_all_batch(struct request *rq, int error, struct batch_complete *batch) { bool pending; unsigned int bidi_bytes = 0; @@ -2642,10 +2648,10 @@ void __blk_end_request_all(struct request *rq, int error) if (unlikely(blk_bidi_rq(rq))) bidi_bytes = blk_rq_bytes(rq->next_rq); - pending = __blk_end_bidi_request(rq, error, blk_rq_bytes(rq), bidi_bytes); + pending = __blk_end_bidi_request(rq, error, blk_rq_bytes(rq), bidi_bytes, batch); BUG_ON(pending); } -EXPORT_SYMBOL(__blk_end_request_all); +EXPORT_SYMBOL(blk_end_request_all_batch); /** * __blk_end_request_cur - Helper function to finish the current request chunk. diff --git a/block/blk-flush.c b/block/blk-flush.c index 720ad607ff91..ab8e21170bf8 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -316,7 +316,7 @@ void blk_insert_flush(struct request *rq) * complete the request. */ if (!policy) { - __blk_end_bidi_request(rq, 0, 0, 0); + __blk_end_bidi_request(rq, 0, 0, 0, NULL); return; } diff --git a/block/blk-integrity.c b/block/blk-integrity.c index da2a818c3a92..dabd221857e1 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -420,6 +420,8 @@ int blk_integrity_register(struct gendisk *disk, struct blk_integrity *template) } else bi->name = bi_unsupported_name; + disk->queue->backing_dev_info.capabilities |= BDI_CAP_STABLE_WRITES; + return 0; } EXPORT_SYMBOL(blk_integrity_register); @@ -438,6 +440,8 @@ void blk_integrity_unregister(struct gendisk *disk) if (!disk || !disk->integrity) return; + disk->queue->backing_dev_info.capabilities &= ~BDI_CAP_STABLE_WRITES; + bi = disk->integrity; kobject_uevent(&bi->kobj, KOBJ_REMOVE); diff --git a/block/blk-ioc.c b/block/blk-ioc.c index fab4cdd3f7bb..9c4bb8266bc8 100644 --- a/block/blk-ioc.c +++ b/block/blk-ioc.c @@ -164,7 +164,6 @@ EXPORT_SYMBOL(put_io_context); */ void put_io_context_active(struct io_context *ioc) { - struct hlist_node *n; unsigned long flags; struct io_cq *icq; @@ -180,7 +179,7 @@ void put_io_context_active(struct io_context *ioc) */ retry: spin_lock_irqsave_nested(&ioc->lock, flags, 1); - hlist_for_each_entry(icq, n, &ioc->icq_list, ioc_node) { + hlist_for_each_entry(icq, &ioc->icq_list, ioc_node) { if (icq->flags & ICQ_EXITED) continue; if (spin_trylock(icq->q->queue_lock)) { diff --git a/block/blk.h b/block/blk.h index e837b8f619b7..dc8fee6d41d6 100644 --- a/block/blk.h +++ b/block/blk.h @@ -31,7 +31,8 @@ void blk_queue_bypass_end(struct request_queue *q); void blk_dequeue_request(struct request *rq); void __blk_queue_free_tags(struct request_queue *q); bool __blk_end_bidi_request(struct request *rq, int error, - unsigned int nr_bytes, unsigned int bidi_bytes); + unsigned int nr_bytes, unsigned int bidi_bytes, + struct batch_complete *batch); void blk_rq_timed_out_timer(unsigned long data); void blk_delete_timer(struct request *); diff --git a/block/bsg.c b/block/bsg.c index ff64ae3bacee..420a5a9f1b23 100644 --- a/block/bsg.c +++ b/block/bsg.c @@ -800,11 +800,10 @@ static struct bsg_device *bsg_add_device(struct inode *inode, static struct bsg_device *__bsg_get_device(int minor, struct request_queue *q) { struct bsg_device *bd; - struct hlist_node *entry; mutex_lock(&bsg_mutex); - hlist_for_each_entry(bd, entry, bsg_dev_idx_hash(minor), dev_list) { + hlist_for_each_entry(bd, bsg_dev_idx_hash(minor), dev_list) { if (bd->queue == q) { atomic_inc(&bd->ref_count); goto found; @@ -997,7 +996,7 @@ int bsg_register_queue(struct request_queue *q, struct device *parent, { struct bsg_class_device *bcd; dev_t dev; - int ret, minor; + int ret; struct device *class_dev = NULL; const char *devname; @@ -1017,23 +1016,16 @@ int bsg_register_queue(struct request_queue *q, struct device *parent, mutex_lock(&bsg_mutex); - ret = idr_pre_get(&bsg_minor_idr, GFP_KERNEL); - if (!ret) { - ret = -ENOMEM; - goto unlock; - } - - ret = idr_get_new(&bsg_minor_idr, bcd, &minor); - if (ret < 0) + ret = idr_alloc(&bsg_minor_idr, bcd, 0, BSG_MAX_DEVS, GFP_KERNEL); + if (ret < 0) { + if (ret == -ENOSPC) { + printk(KERN_ERR "bsg: too many bsg devices\n"); + ret = -EINVAL; + } goto unlock; - - if (minor >= BSG_MAX_DEVS) { - printk(KERN_ERR "bsg: too many bsg devices\n"); - ret = -EINVAL; - goto remove_idr; } - bcd->minor = minor; + bcd->minor = ret; bcd->queue = q; bcd->parent = get_device(parent); bcd->release = release; @@ -1059,8 +1051,7 @@ unregister_class_dev: device_unregister(class_dev); put_dev: put_device(parent); -remove_idr: - idr_remove(&bsg_minor_idr, minor); + idr_remove(&bsg_minor_idr, bcd->minor); unlock: mutex_unlock(&bsg_mutex); return ret; diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index b66365b6ba77..4f0ade74cfd0 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -1697,7 +1697,6 @@ static int __cfq_set_weight(struct cgroup *cgrp, struct cftype *cft, u64 val, { struct blkcg *blkcg = cgroup_to_blkcg(cgrp); struct blkcg_gq *blkg; - struct hlist_node *n; if (val < CFQ_WEIGHT_MIN || val > CFQ_WEIGHT_MAX) return -EINVAL; @@ -1709,7 +1708,7 @@ static int __cfq_set_weight(struct cgroup *cgrp, struct cftype *cft, u64 val, else blkcg->cfq_leaf_weight = val; - hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) { + hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) { struct cfq_group *cfqg = blkg_to_cfqg(blkg); if (!cfqg) @@ -3594,6 +3593,8 @@ retry: spin_lock_irq(cfqd->queue->queue_lock); if (new_cfqq) goto retry; + else + return &cfqd->oom_cfqq; } else { cfqq = kmem_cache_alloc_node(cfq_pool, gfp_mask | __GFP_ZERO, diff --git a/block/elevator.c b/block/elevator.c index 62be2a243b39..a0ffdd943c98 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -273,10 +273,10 @@ static void elv_rqhash_reposition(struct request_queue *q, struct request *rq) static struct request *elv_rqhash_find(struct request_queue *q, sector_t offset) { struct elevator_queue *e = q->elevator; - struct hlist_node *entry, *next; + struct hlist_node *next; struct request *rq; - hash_for_each_possible_safe(e->hash, rq, entry, next, hash, offset) { + hash_for_each_possible_safe(e->hash, rq, next, hash, offset) { BUG_ON(!ELV_ON_HASH(rq)); if (unlikely(!rq_mergeable(rq))) { diff --git a/block/genhd.c b/block/genhd.c index 3993ebf4135f..a1ed52af5290 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -18,6 +18,7 @@ #include <linux/mutex.h> #include <linux/idr.h> #include <linux/log2.h> +#include <linux/pm_runtime.h> #include "blk.h" @@ -25,7 +26,7 @@ static DEFINE_MUTEX(block_class_lock); struct kobject *block_depr; /* for extended dynamic devt allocation, currently only one major is used */ -#define MAX_EXT_DEVT (1 << MINORBITS) +#define NR_EXT_DEVT (1 << MINORBITS) /* For extended devt allocation. ext_devt_mutex prevents look up * results from going away underneath its user. @@ -410,7 +411,7 @@ static int blk_mangle_minor(int minor) int blk_alloc_devt(struct hd_struct *part, dev_t *devt) { struct gendisk *disk = part_to_disk(part); - int idx, rc; + int idx; /* in consecutive minor range? */ if (part->partno < disk->minors) { @@ -419,19 +420,11 @@ int blk_alloc_devt(struct hd_struct *part, dev_t *devt) } /* allocate ext devt */ - do { - if (!idr_pre_get(&ext_devt_idr, GFP_KERNEL)) - return -ENOMEM; - rc = idr_get_new(&ext_devt_idr, part, &idx); - } while (rc == -EAGAIN); - - if (rc) - return rc; - - if (idx > MAX_EXT_DEVT) { - idr_remove(&ext_devt_idr, idx); - return -EBUSY; - } + mutex_lock(&ext_devt_mutex); + idx = idr_alloc(&ext_devt_idr, part, 0, NR_EXT_DEVT, GFP_KERNEL); + mutex_unlock(&ext_devt_mutex); + if (idx < 0) + return idx == -ENOSPC ? -EBUSY : idx; *devt = MKDEV(BLOCK_EXT_MAJOR, blk_mangle_minor(idx)); return 0; @@ -534,6 +527,14 @@ static void register_disk(struct gendisk *disk) return; } } + + /* + * avoid probable deadlock caused by allocating memory with + * GFP_KERNEL in runtime_resume callback of its all ancestor + * devices + */ + pm_runtime_set_memalloc_noio(ddev, true); + disk->part0.holder_dir = kobject_create_and_add("holders", &ddev->kobj); disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj); @@ -646,7 +647,6 @@ void del_gendisk(struct gendisk *disk) disk_part_iter_exit(&piter); invalidate_partition(disk, 0); - blk_free_devt(disk_to_dev(disk)->devt); set_capacity(disk, 0); disk->flags &= ~GENHD_FL_UP; @@ -663,7 +663,9 @@ void del_gendisk(struct gendisk *disk) disk->driverfs_dev = NULL; if (!sysfs_deprecated) sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk))); + pm_runtime_set_memalloc_noio(disk_to_dev(disk), false); device_del(disk_to_dev(disk)); + blk_free_devt(disk_to_dev(disk)->devt); } EXPORT_SYMBOL(del_gendisk); @@ -847,7 +849,7 @@ static int show_partition(struct seq_file *seqf, void *v) char buf[BDEVNAME_SIZE]; /* Don't show non-partitionable removeable devices or empty devices */ - if (!get_capacity(sgp) || (!disk_max_parts(sgp) && + if (!get_capacity(sgp) || (!(disk_max_parts(sgp) > 1) && (sgp->flags & GENHD_FL_REMOVABLE))) return 0; if (sgp->flags & GENHD_FL_SUPPRESS_PARTITION_INFO) diff --git a/block/partition-generic.c b/block/partition-generic.c index f1d14519cc04..1cb4deca1324 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -249,11 +249,11 @@ void delete_partition(struct gendisk *disk, int partno) if (!part) return; - blk_free_devt(part_devt(part)); rcu_assign_pointer(ptbl->part[partno], NULL); rcu_assign_pointer(ptbl->last_lookup, NULL); kobject_put(part->holder_dir); device_del(part_to_dev(part)); + blk_free_devt(part_devt(part)); hd_struct_put(part); } diff --git a/block/partitions/msdos.c b/block/partitions/msdos.c index 8752a5d26565..7681cd295ab8 100644 --- a/block/partitions/msdos.c +++ b/block/partitions/msdos.c @@ -455,14 +455,19 @@ int msdos_partition(struct parsed_partitions *state) data = read_part_sector(state, 0, §); if (!data) return -1; - if (!msdos_magic_present(data + 510)) { + + /* + * Note order! (some AIX disks, e.g. unbootable kind, + * have no MSDOS 55aa) + */ + if (aix_magic_present(state, data)) { put_dev_sector(sect); + strlcat(state->pp_buf, " [AIX]", PAGE_SIZE); return 0; } - if (aix_magic_present(state, data)) { + if (!msdos_magic_present(data + 510)) { put_dev_sector(sect); - strlcat(state->pp_buf, " [AIX]", PAGE_SIZE); return 0; } diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c index 9a87daa6f4fb..a5ffcc988f0b 100644 --- a/block/scsi_ioctl.c +++ b/block/scsi_ioctl.c @@ -27,6 +27,7 @@ #include <linux/ratelimit.h> #include <linux/slab.h> #include <linux/times.h> +#include <linux/uio.h> #include <asm/uaccess.h> #include <scsi/scsi.h> diff --git a/crypto/algapi.c b/crypto/algapi.c index 08c57c8aec95..6149a6e09643 100644 --- a/crypto/algapi.c +++ b/crypto/algapi.c @@ -447,7 +447,7 @@ EXPORT_SYMBOL_GPL(crypto_register_template); void crypto_unregister_template(struct crypto_template *tmpl) { struct crypto_instance *inst; - struct hlist_node *p, *n; + struct hlist_node *n; struct hlist_head *list; LIST_HEAD(users); @@ -457,7 +457,7 @@ void crypto_unregister_template(struct crypto_template *tmpl) list_del_init(&tmpl->list); list = &tmpl->instances; - hlist_for_each_entry(inst, p, list, list) { + hlist_for_each_entry(inst, list, list) { int err = crypto_remove_alg(&inst->alg, &users); BUG_ON(err); } @@ -466,7 +466,7 @@ void crypto_unregister_template(struct crypto_template *tmpl) up_write(&crypto_alg_sem); - hlist_for_each_entry_safe(inst, p, n, list, list) { + hlist_for_each_entry_safe(inst, n, list, list) { BUG_ON(atomic_read(&inst->alg.cra_refcnt) != 1); tmpl->free(inst); } diff --git a/drivers/acpi/acpi_memhotplug.c b/drivers/acpi/acpi_memhotplug.c index 94c823b25138..7d0d62c8a4e6 100644 --- a/drivers/acpi/acpi_memhotplug.c +++ b/drivers/acpi/acpi_memhotplug.c @@ -273,9 +273,11 @@ static int acpi_memory_enable_device(struct acpi_memory_device *mem_device) static int acpi_memory_remove_memory(struct acpi_memory_device *mem_device) { - int result = 0; + int result = 0, nid; struct acpi_memory_info *info, *n; + nid = acpi_get_node(mem_device->device->handle); + list_for_each_entry_safe(info, n, &mem_device->res_list, list) { if (info->failed) /* The kernel does not use this memory block */ @@ -288,7 +290,9 @@ static int acpi_memory_remove_memory(struct acpi_memory_device *mem_device) */ return -EBUSY; - result = remove_memory(info->start_addr, info->length); + if (nid < 0) + nid = memory_add_physaddr_to_nid(info->start_addr); + result = remove_memory(nid, info->start_addr, info->length); if (result) return result; diff --git a/drivers/acpi/numa.c b/drivers/acpi/numa.c index 33e609f63585..59844ee149be 100644 --- a/drivers/acpi/numa.c +++ b/drivers/acpi/numa.c @@ -282,10 +282,10 @@ acpi_table_parse_srat(enum acpi_srat_type id, handler, max_entries); } -int __init acpi_numa_init(void) -{ - int cnt = 0; +static int srat_mem_cnt; +void __init early_parse_srat(void) +{ /* * Should not limit number with cpu num that is from NR_CPUS or nr_cpus= * SRAT cpu entries could have different order with that in MADT. @@ -295,21 +295,24 @@ int __init acpi_numa_init(void) /* SRAT: Static Resource Affinity Table */ if (!acpi_table_parse(ACPI_SIG_SRAT, acpi_parse_srat)) { acpi_table_parse_srat(ACPI_SRAT_TYPE_X2APIC_CPU_AFFINITY, - acpi_parse_x2apic_affinity, 0); + acpi_parse_x2apic_affinity, 0); acpi_table_parse_srat(ACPI_SRAT_TYPE_CPU_AFFINITY, - acpi_parse_processor_affinity, 0); - cnt = acpi_table_parse_srat(ACPI_SRAT_TYPE_MEMORY_AFFINITY, - acpi_parse_memory_affinity, - NR_NODE_MEMBLKS); + acpi_parse_processor_affinity, 0); + srat_mem_cnt = acpi_table_parse_srat(ACPI_SRAT_TYPE_MEMORY_AFFINITY, + acpi_parse_memory_affinity, + NR_NODE_MEMBLKS); } +} +int __init acpi_numa_init(void) +{ /* SLIT: System Locality Information Table */ acpi_table_parse(ACPI_SIG_SLIT, acpi_parse_slit); acpi_numa_arch_fixup(); - if (cnt < 0) - return cnt; + if (srat_mem_cnt < 0) + return srat_mem_cnt; else if (!parsed_numa_memblks) return -ENOENT; return 0; diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c index c5d2fd85dbe0..d57e32c5c5dc 100644 --- a/drivers/acpi/processor_driver.c +++ b/drivers/acpi/processor_driver.c @@ -45,6 +45,7 @@ #include <linux/cpuidle.h> #include <linux/slab.h> #include <linux/acpi.h> +#include <linux/memory_hotplug.h> #include <asm/io.h> #include <asm/cpu.h> @@ -641,6 +642,7 @@ static int acpi_processor_remove(struct acpi_device *device) per_cpu(processors, pr->id) = NULL; per_cpu(processor_device_array, pr->id) = NULL; + try_offline_node(cpu_to_node(pr->id)); free: free_cpumask_var(pr->throttling.shared_cpu_map); diff --git a/drivers/atm/atmtcp.c b/drivers/atm/atmtcp.c index b22d71cac54c..738be42d6fc5 100644 --- a/drivers/atm/atmtcp.c +++ b/drivers/atm/atmtcp.c @@ -157,7 +157,6 @@ static int atmtcp_v_ioctl(struct atm_dev *dev,unsigned int cmd,void __user *arg) { struct atm_cirange ci; struct atm_vcc *vcc; - struct hlist_node *node; struct sock *s; int i; @@ -171,7 +170,7 @@ static int atmtcp_v_ioctl(struct atm_dev *dev,unsigned int cmd,void __user *arg) for(i = 0; i < VCC_HTABLE_SIZE; ++i) { struct hlist_head *head = &vcc_hash[i]; - sk_for_each(s, node, head) { + sk_for_each(s, head) { vcc = atm_sk(s); if (vcc->dev != dev) continue; @@ -264,12 +263,11 @@ static struct atm_vcc *find_vcc(struct atm_dev *dev, short vpi, int vci) { struct hlist_head *head; struct atm_vcc *vcc; - struct hlist_node *node; struct sock *s; head = &vcc_hash[vci & (VCC_HTABLE_SIZE -1)]; - sk_for_each(s, node, head) { + sk_for_each(s, head) { vcc = atm_sk(s); if (vcc->dev == dev && vcc->vci == vci && vcc->vpi == vpi && diff --git a/drivers/atm/eni.c b/drivers/atm/eni.c index c1eb6fa8ac35..b1955ba40d63 100644 --- a/drivers/atm/eni.c +++ b/drivers/atm/eni.c @@ -2093,7 +2093,6 @@ static unsigned char eni_phy_get(struct atm_dev *dev,unsigned long addr) static int eni_proc_read(struct atm_dev *dev,loff_t *pos,char *page) { - struct hlist_node *node; struct sock *s; static const char *signal[] = { "LOST","unknown","okay" }; struct eni_dev *eni_dev = ENI_DEV(dev); @@ -2171,7 +2170,7 @@ static int eni_proc_read(struct atm_dev *dev,loff_t *pos,char *page) for(i = 0; i < VCC_HTABLE_SIZE; ++i) { struct hlist_head *head = &vcc_hash[i]; - sk_for_each(s, node, head) { + sk_for_each(s, head) { struct eni_vcc *eni_vcc; int length; diff --git a/drivers/atm/he.c b/drivers/atm/he.c index 72b6960fa95f..d6891267f5bb 100644 --- a/drivers/atm/he.c +++ b/drivers/atm/he.c @@ -329,7 +329,6 @@ __find_vcc(struct he_dev *he_dev, unsigned cid) { struct hlist_head *head; struct atm_vcc *vcc; - struct hlist_node *node; struct sock *s; short vpi; int vci; @@ -338,7 +337,7 @@ __find_vcc(struct he_dev *he_dev, unsigned cid) vci = cid & ((1 << he_dev->vcibits) - 1); head = &vcc_hash[vci & (VCC_HTABLE_SIZE -1)]; - sk_for_each(s, node, head) { + sk_for_each(s, head) { vcc = atm_sk(s); if (vcc->dev == he_dev->atm_dev && vcc->vci == vci && vcc->vpi == vpi && diff --git a/drivers/atm/nicstar.c b/drivers/atm/nicstar.c index ed1d2b7f923b..6587dc295eb0 100644 --- a/drivers/atm/nicstar.c +++ b/drivers/atm/nicstar.c @@ -251,7 +251,6 @@ static void nicstar_remove_one(struct pci_dev *pcidev) if (card->scd2vc[j] != NULL) free_scq(card, card->scd2vc[j]->scq, card->scd2vc[j]->tx_vcc); } - idr_remove_all(&card->idr); idr_destroy(&card->idr); pci_free_consistent(card->pcidev, NS_RSQSIZE + NS_RSQ_ALIGNMENT, card->rsq.org, card->rsq.dma); @@ -950,11 +949,10 @@ static void free_scq(ns_dev *card, scq_info *scq, struct atm_vcc *vcc) static void push_rxbufs(ns_dev * card, struct sk_buff *skb) { struct sk_buff *handle1, *handle2; - u32 id1 = 0, id2 = 0; + int id1, id2; u32 addr1, addr2; u32 stat; unsigned long flags; - int err; /* *BARF* */ handle2 = NULL; @@ -1027,23 +1025,12 @@ static void push_rxbufs(ns_dev * card, struct sk_buff *skb) card->lbfqc += 2; } - do { - if (!idr_pre_get(&card->idr, GFP_ATOMIC)) { - printk(KERN_ERR - "nicstar%d: no free memory for idr\n", - card->index); - goto out; - } - - if (!id1) - err = idr_get_new_above(&card->idr, handle1, 0, &id1); - - if (!id2 && err == 0) - err = idr_get_new_above(&card->idr, handle2, 0, &id2); - - } while (err == -EAGAIN); + id1 = idr_alloc(&card->idr, handle1, 0, 0, GFP_ATOMIC); + if (id1 < 0) + goto out; - if (err) + id2 = idr_alloc(&card->idr, handle2, 0, 0, GFP_ATOMIC); + if (id2 < 0) goto out; spin_lock_irqsave(&card->res_lock, flags); diff --git a/drivers/atm/solos-pci.c b/drivers/atm/solos-pci.c index 0474a89170b9..32784d18d1f7 100644 --- a/drivers/atm/solos-pci.c +++ b/drivers/atm/solos-pci.c @@ -896,12 +896,11 @@ static struct atm_vcc *find_vcc(struct atm_dev *dev, short vpi, int vci) { struct hlist_head *head; struct atm_vcc *vcc = NULL; - struct hlist_node *node; struct sock *s; read_lock(&vcc_sklist_lock); head = &vcc_hash[vci & (VCC_HTABLE_SIZE -1)]; - sk_for_each(s, node, head) { + sk_for_each(s, head) { vcc = atm_sk(s); if (vcc->dev == dev && vcc->vci == vci && vcc->vpi == vpi && vcc->qos.rxtp.traffic_class != ATM_NONE && diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 987604d56c83..8300a1864c33 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -693,6 +693,12 @@ int offline_memory_block(struct memory_block *mem) return ret; } +/* return true if the memory block is offlined, otherwise, return false */ +bool is_memblock_offlined(struct memory_block *mem) +{ + return mem->state == MEM_OFFLINE; +} + /* * Initialize the sysfs support for memory devices... */ diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 3148b10dc2e5..1244930e3d7a 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -124,6 +124,76 @@ unsigned long pm_runtime_autosuspend_expiration(struct device *dev) } EXPORT_SYMBOL_GPL(pm_runtime_autosuspend_expiration); +static int dev_memalloc_noio(struct device *dev, void *data) +{ + return dev->power.memalloc_noio; +} + +/* + * pm_runtime_set_memalloc_noio - Set a device's memalloc_noio flag. + * @dev: Device to handle. + * @enable: True for setting the flag and False for clearing the flag. + * + * Set the flag for all devices in the path from the device to the + * root device in the device tree if @enable is true, otherwise clear + * the flag for devices in the path whose siblings don't set the flag. + * + * The function should only be called by block device, or network + * device driver for solving the deadlock problem during runtime + * resume/suspend: + * + * If memory allocation with GFP_KERNEL is called inside runtime + * resume/suspend callback of any one of its ancestors(or the + * block device itself), the deadlock may be triggered inside the + * memory allocation since it might not complete until the block + * device becomes active and the involed page I/O finishes. The + * situation is pointed out first by Alan Stern. Network device + * are involved in iSCSI kind of situation. + * + * The lock of dev_hotplug_mutex is held in the function for handling + * hotplug race because pm_runtime_set_memalloc_noio() may be called + * in async probe(). + * + * The function should be called between device_add() and device_del() + * on the affected device(block/network device). + */ +void pm_runtime_set_memalloc_noio(struct device *dev, bool enable) +{ + static DEFINE_MUTEX(dev_hotplug_mutex); + + mutex_lock(&dev_hotplug_mutex); + for (;;) { + bool enabled; + + /* hold power lock since bitfield is not SMP-safe. */ + spin_lock_irq(&dev->power.lock); + enabled = dev->power.memalloc_noio; + dev->power.memalloc_noio = enable; + spin_unlock_irq(&dev->power.lock); + + /* + * not need to enable ancestors any more if the device + * has been enabled. + */ + if (enabled && enable) + break; + + dev = dev->parent; + + /* + * clear flag of the parent device only if all the + * children don't set the flag because ancestor's + * flag was set by any one of the descendants. + */ + if (!dev || (!enable && + device_for_each_child(dev, NULL, + dev_memalloc_noio))) + break; + } + mutex_unlock(&dev_hotplug_mutex); +} +EXPORT_SYMBOL_GPL(pm_runtime_set_memalloc_noio); + /** * rpm_check_suspend_allowed - Test whether a device may be suspended. * @dev: Device to test. @@ -278,7 +348,24 @@ static int rpm_callback(int (*cb)(struct device *), struct device *dev) if (!cb) return -ENOSYS; - retval = __rpm_callback(cb, dev); + if (dev->power.memalloc_noio) { + unsigned int noio_flag; + + /* + * Deadlock might be caused if memory allocation with + * GFP_KERNEL happens inside runtime_suspend and + * runtime_resume callbacks of one block device's + * ancestor or the block device itself. Network + * device might be thought as part of iSCSI block + * device, so network device and its ancestor should + * be marked as memalloc_noio too. + */ + noio_flag = memalloc_noio_save(); + retval = __rpm_callback(cb, dev); + memalloc_noio_restore(noio_flag); + } else { + retval = __rpm_callback(cb, dev); + } dev->power.runtime_error = retval; return retval != -EACCES ? retval : -EIO; diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 8c13eeb83c53..e98da675f0c1 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -2660,25 +2660,24 @@ enum drbd_ret_code conn_new_minor(struct drbd_tconn *tconn, unsigned int minor, mdev->read_requests = RB_ROOT; mdev->write_requests = RB_ROOT; - if (!idr_pre_get(&minors, GFP_KERNEL)) - goto out_no_minor_idr; - if (idr_get_new_above(&minors, mdev, minor, &minor_got)) + minor_got = idr_alloc(&minors, mdev, minor, minor + 1, GFP_KERNEL); + if (minor_got < 0) { + if (minor_got == -ENOSPC) { + err = ERR_MINOR_EXISTS; + drbd_msg_put_info("requested minor exists already"); + } goto out_no_minor_idr; - if (minor_got != minor) { - err = ERR_MINOR_EXISTS; - drbd_msg_put_info("requested minor exists already"); - goto out_idr_remove_minor; } - if (!idr_pre_get(&tconn->volumes, GFP_KERNEL)) - goto out_idr_remove_minor; - if (idr_get_new_above(&tconn->volumes, mdev, vnr, &vnr_got)) + vnr_got = idr_alloc(&tconn->volumes, mdev, vnr, vnr + 1, GFP_KERNEL); + if (vnr_got < 0) { + if (vnr_got == -ENOSPC) { + err = ERR_INVALID_REQUEST; + drbd_msg_put_info("requested volume exists already"); + } goto out_idr_remove_minor; - if (vnr_got != vnr) { - err = ERR_INVALID_REQUEST; - drbd_msg_put_info("requested volume exists already"); - goto out_idr_remove_vol; } + add_disk(disk); kref_init(&mdev->kref); /* one ref for both idrs and the the add_disk */ @@ -2689,8 +2688,6 @@ enum drbd_ret_code conn_new_minor(struct drbd_tconn *tconn, unsigned int minor, return NO_ERROR; -out_idr_remove_vol: - idr_remove(&tconn->volumes, vnr_got); out_idr_remove_minor: idr_remove(&minors, minor_got); synchronize_rcu(); diff --git a/drivers/block/loop.c b/drivers/block/loop.c index ae1251270624..56a3963f8a57 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -162,12 +162,13 @@ static struct loop_func_table *xfer_funcs[MAX_LO_CRYPT] = { static loff_t get_size(loff_t offset, loff_t sizelimit, struct file *file) { - loff_t size, loopsize; + loff_t loopsize; /* Compute loopsize in bytes */ - size = i_size_read(file->f_mapping->host); - loopsize = size - offset; - /* offset is beyond i_size, wierd but possible */ + loopsize = i_size_read(file->f_mapping->host); + if (offset > 0) + loopsize -= offset; + /* offset is beyond i_size, weird but possible */ if (loopsize < 0) return 0; @@ -190,6 +191,7 @@ figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit) { loff_t size = get_size(offset, sizelimit, lo->lo_backing_file); sector_t x = (sector_t)size; + struct block_device *bdev = lo->lo_device; if (unlikely((loff_t)x != size)) return -EFBIG; @@ -198,6 +200,9 @@ figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit) if (lo->lo_sizelimit != sizelimit) lo->lo_sizelimit = sizelimit; set_capacity(lo->lo_disk, x); + bd_set_size(bdev, (loff_t)get_capacity(bdev->bd_disk) << 9); + /* let user-space know about the new size */ + kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE); return 0; } @@ -1091,10 +1096,10 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) return err; if (lo->lo_offset != info->lo_offset || - lo->lo_sizelimit != info->lo_sizelimit) { + lo->lo_sizelimit != info->lo_sizelimit) if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit)) return -EFBIG; - } + loop_config_discard(lo); memcpy(lo->lo_file_name, info->lo_file_name, LO_NAME_SIZE); @@ -1271,28 +1276,10 @@ loop_get_status64(struct loop_device *lo, struct loop_info64 __user *arg) { static int loop_set_capacity(struct loop_device *lo, struct block_device *bdev) { - int err; - sector_t sec; - loff_t sz; - - err = -ENXIO; if (unlikely(lo->lo_state != Lo_bound)) - goto out; - err = figure_loop_size(lo, lo->lo_offset, lo->lo_sizelimit); - if (unlikely(err)) - goto out; - sec = get_capacity(lo->lo_disk); - /* the width of sector_t may be narrow for bit-shift */ - sz = sec; - sz <<= 9; - mutex_lock(&bdev->bd_mutex); - bd_set_size(bdev, sz); - /* let user-space know about the new size */ - kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE); - mutex_unlock(&bdev->bd_mutex); + return -ENXIO; - out: - return err; + return figure_loop_size(lo, lo->lo_offset, lo->lo_sizelimit); } static int lo_ioctl(struct block_device *bdev, fmode_t mode, @@ -1624,30 +1611,17 @@ static int loop_add(struct loop_device **l, int i) if (!lo) goto out; - if (!idr_pre_get(&loop_index_idr, GFP_KERNEL)) - goto out_free_dev; - + /* allocate id, if @id >= 0, we're requesting that specific id */ if (i >= 0) { - int m; - - /* create specific i in the index */ - err = idr_get_new_above(&loop_index_idr, lo, i, &m); - if (err >= 0 && i != m) { - idr_remove(&loop_index_idr, m); + err = idr_alloc(&loop_index_idr, lo, i, i + 1, GFP_KERNEL); + if (err == -ENOSPC) err = -EEXIST; - } - } else if (i == -1) { - int m; - - /* get next free nr */ - err = idr_get_new(&loop_index_idr, lo, &m); - if (err >= 0) - i = m; } else { - err = -EINVAL; + err = idr_alloc(&loop_index_idr, lo, 0, 0, GFP_KERNEL); } if (err < 0) goto out_free_dev; + i = err; lo->lo_queue = blk_alloc_queue(GFP_KERNEL); if (!lo->lo_queue) @@ -1858,11 +1832,15 @@ static int __init loop_init(void) max_part = (1UL << part_shift) - 1; } - if ((1UL << part_shift) > DISK_MAX_PARTS) - return -EINVAL; + if ((1UL << part_shift) > DISK_MAX_PARTS) { + err = -EINVAL; + goto misc_out; + } - if (max_loop > 1UL << (MINORBITS - part_shift)) - return -EINVAL; + if (max_loop > 1UL << (MINORBITS - part_shift)) { + err = -EINVAL; + goto misc_out; + } /* * If max_loop is specified, create that many devices upfront. @@ -1880,8 +1858,10 @@ static int __init loop_init(void) range = 1UL << MINORBITS; } - if (register_blkdev(LOOP_MAJOR, "loop")) - return -EIO; + if (register_blkdev(LOOP_MAJOR, "loop")) { + err = -EIO; + goto misc_out; + } blk_register_region(MKDEV(LOOP_MAJOR, 0), range, THIS_MODULE, loop_probe, NULL, NULL); @@ -1894,6 +1874,10 @@ static int __init loop_init(void) printk(KERN_INFO "loop: module loaded\n"); return 0; + +misc_out: + misc_deregister(&loop_misc); + return err; } static int loop_exit_cb(int id, void *ptr, void *data) @@ -1911,7 +1895,6 @@ static void __exit loop_exit(void) range = max_loop ? max_loop << part_shift : 1UL << MINORBITS; idr_for_each(&loop_index_idr, &loop_exit_cb, NULL); - idr_remove_all(&loop_index_idr); idr_destroy(&loop_index_idr); blk_unregister_region(MKDEV(LOOP_MAJOR, 0), range); diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index 11cc9522cdd4..8bedaf46792f 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -161,11 +161,9 @@ static void mtip_command_cleanup(struct driver_data *dd) command = &port->commands[commandindex]; if (atomic_read(&command->active) - && (command->async_callback)) { - command->async_callback(command->async_data, - -ENODEV); - command->async_callback = NULL; - command->async_data = NULL; + && (command->bio)) { + bio_endio(command->bio, -ENODEV); + command->bio = NULL; } dma_unmap_sg(&port->dd->pdev->dev, @@ -606,11 +604,9 @@ static void mtip_timeout_function(unsigned long int data) writel(1 << bit, port->completed[group]); /* Call the async completion callback. */ - if (likely(command->async_callback)) - command->async_callback(command->async_data, - -EIO); - command->async_callback = NULL; - command->comp_func = NULL; + if (likely(command->bio)) + bio_endio(command->bio, -EIO); + command->bio = NULL; /* Unmap the DMA scatter list entries */ dma_unmap_sg(&port->dd->pdev->dev, @@ -679,7 +675,8 @@ static void mtip_timeout_function(unsigned long int data) static void mtip_async_complete(struct mtip_port *port, int tag, void *data, - int status) + int status, + struct batch_complete *batch) { struct mtip_cmd *command; struct driver_data *dd = data; @@ -696,11 +693,10 @@ static void mtip_async_complete(struct mtip_port *port, } /* Upper layer callback */ - if (likely(command->async_callback)) - command->async_callback(command->async_data, cb_status); + if (likely(command->bio)) + bio_endio_batch(command->bio, cb_status, batch); - command->async_callback = NULL; - command->comp_func = NULL; + command->bio = NULL; /* Unmap the DMA scatter list entries */ dma_unmap_sg(&dd->pdev->dev, @@ -733,24 +729,22 @@ static void mtip_async_complete(struct mtip_port *port, static void mtip_completion(struct mtip_port *port, int tag, void *data, - int status) + int status, + struct batch_complete *batch) { - struct mtip_cmd *command = &port->commands[tag]; struct completion *waiting = data; if (unlikely(status == PORT_IRQ_TF_ERR)) dev_warn(&port->dd->pdev->dev, "Internal command %d completed with TFE\n", tag); - command->async_callback = NULL; - command->comp_func = NULL; - complete(waiting); } static void mtip_null_completion(struct mtip_port *port, int tag, void *data, - int status) + int status, + struct batch_complete *batch) { return; } @@ -796,7 +790,7 @@ static void mtip_handle_tfe(struct driver_data *dd) atomic_inc(&cmd->active); /* active > 1 indicates error */ if (cmd->comp_data && cmd->comp_func) { cmd->comp_func(port, MTIP_TAG_INTERNAL, - cmd->comp_data, PORT_IRQ_TF_ERR); + cmd->comp_data, PORT_IRQ_TF_ERR, NULL); } goto handle_tfe_exit; } @@ -829,7 +823,7 @@ static void mtip_handle_tfe(struct driver_data *dd) cmd->comp_func(port, tag, cmd->comp_data, - 0); + 0, NULL); } else { dev_err(&port->dd->pdev->dev, "Missing completion func for tag %d", @@ -916,7 +910,7 @@ static void mtip_handle_tfe(struct driver_data *dd) if (cmd->comp_func) { cmd->comp_func(port, tag, cmd->comp_data, - -ENODATA); + -ENODATA, NULL); } continue; } @@ -946,7 +940,7 @@ static void mtip_handle_tfe(struct driver_data *dd) port, tag, cmd->comp_data, - PORT_IRQ_TF_ERR); + PORT_IRQ_TF_ERR, NULL); else dev_warn(&port->dd->pdev->dev, "Bad completion for tag %d\n", @@ -973,6 +967,9 @@ static inline void mtip_workq_sdbfx(struct mtip_port *port, int group, struct driver_data *dd = port->dd; int tag, bit; struct mtip_cmd *command; + struct batch_complete batch; + + batch_complete_init(&batch); if (!completed) { WARN_ON_ONCE(!completed); @@ -997,7 +994,8 @@ static inline void mtip_workq_sdbfx(struct mtip_port *port, int group, port, tag, command->comp_data, - 0); + 0, + &batch); } else { dev_warn(&dd->pdev->dev, "Null completion " @@ -1034,7 +1032,7 @@ static inline void mtip_process_legacy(struct driver_data *dd, u32 port_stat) cmd->comp_func(port, MTIP_TAG_INTERNAL, cmd->comp_data, - 0); + 0, NULL); return; } } @@ -2554,8 +2552,8 @@ static int mtip_hw_ioctl(struct driver_data *dd, unsigned int cmd, * None */ static void mtip_hw_submit_io(struct driver_data *dd, sector_t sector, - int nsect, int nents, int tag, void *callback, - void *data, int dir) + int nsect, int nents, int tag, + struct bio *bio, int dir) { struct host_to_dev_fis *fis; struct mtip_port *port = dd->port; @@ -2610,12 +2608,7 @@ static void mtip_hw_submit_io(struct driver_data *dd, sector_t sector, command->comp_func = mtip_async_complete; command->direction = dma_dir; - /* - * Set the completion function and data for the command passed - * from the upper layer. - */ - command->async_data = data; - command->async_callback = callback; + command->bio = bio; /* * To prevent this command from being issued @@ -3795,7 +3788,6 @@ static void mtip_make_request(struct request_queue *queue, struct bio *bio) bio_sectors(bio), nents, tag, - bio_endio, bio, bio_data_dir(bio)); } else diff --git a/drivers/block/mtip32xx/mtip32xx.h b/drivers/block/mtip32xx/mtip32xx.h index 3bffff5f670c..af8c6f79a8d8 100644 --- a/drivers/block/mtip32xx/mtip32xx.h +++ b/drivers/block/mtip32xx/mtip32xx.h @@ -325,11 +325,9 @@ struct mtip_cmd { void (*comp_func)(struct mtip_port *port, int tag, void *data, - int status); - /* Additional callback function that may be called by comp_func() */ - void (*async_callback)(void *data, int status); - - void *async_data; /* Addl. data passed to async_callback() */ + int status, + struct batch_complete *batch); + struct bio *bio; int scatter_ents; /* Number of scatter list entries used */ diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c index 57763c54363a..deb722d63d68 100644 --- a/drivers/block/swim3.c +++ b/drivers/block/swim3.c @@ -775,7 +775,7 @@ static irqreturn_t swim3_interrupt(int irq, void *dev_id) if (intr & ERROR_INTR) { n = fs->scount - 1 - resid / 512; if (n > 0) { - blk_update_request(req, 0, n << 9); + blk_update_request(req, 0, n << 9, NULL); fs->req_sector += n; } if (fs->retries < 5) { @@ -1090,10 +1090,13 @@ static const struct block_device_operations floppy_fops = { static void swim3_mb_event(struct macio_dev* mdev, int mb_state) { struct floppy_state *fs = macio_get_drvdata(mdev); - struct swim3 __iomem *sw = fs->swim3; + struct swim3 __iomem *sw; if (!fs) return; + + sw = fs->swim3; + if (mb_state != MB_FD) return; diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 8ad21a25bc0d..5a9e04a6a6d7 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -210,7 +210,8 @@ static void virtblk_bio_send_flush_work(struct work_struct *work) virtblk_bio_send_flush(vbr); } -static inline void virtblk_request_done(struct virtblk_req *vbr) +static inline void virtblk_request_done(struct virtblk_req *vbr, + struct batch_complete *batch) { struct virtio_blk *vblk = vbr->vblk; struct request *req = vbr->req; @@ -224,11 +225,12 @@ static inline void virtblk_request_done(struct virtblk_req *vbr) req->errors = (error != 0); } - __blk_end_request_all(req, error); + blk_end_request_all_batch(req, error, batch); mempool_free(vbr, vblk->pool); } -static inline void virtblk_bio_flush_done(struct virtblk_req *vbr) +static inline void virtblk_bio_flush_done(struct virtblk_req *vbr, + struct batch_complete *batch) { struct virtio_blk *vblk = vbr->vblk; @@ -237,12 +239,13 @@ static inline void virtblk_bio_flush_done(struct virtblk_req *vbr) INIT_WORK(&vbr->work, virtblk_bio_send_data_work); queue_work(virtblk_wq, &vbr->work); } else { - bio_endio(vbr->bio, virtblk_result(vbr)); + bio_endio_batch(vbr->bio, virtblk_result(vbr), batch); mempool_free(vbr, vblk->pool); } } -static inline void virtblk_bio_data_done(struct virtblk_req *vbr) +static inline void virtblk_bio_data_done(struct virtblk_req *vbr, + struct batch_complete *batch) { struct virtio_blk *vblk = vbr->vblk; @@ -252,17 +255,18 @@ static inline void virtblk_bio_data_done(struct virtblk_req *vbr) INIT_WORK(&vbr->work, virtblk_bio_send_flush_work); queue_work(virtblk_wq, &vbr->work); } else { - bio_endio(vbr->bio, virtblk_result(vbr)); + bio_endio_batch(vbr->bio, virtblk_result(vbr), batch); mempool_free(vbr, vblk->pool); } } -static inline void virtblk_bio_done(struct virtblk_req *vbr) +static inline void virtblk_bio_done(struct virtblk_req *vbr, + struct batch_complete *batch) { if (unlikely(vbr->flags & VBLK_IS_FLUSH)) - virtblk_bio_flush_done(vbr); + virtblk_bio_flush_done(vbr, batch); else - virtblk_bio_data_done(vbr); + virtblk_bio_data_done(vbr, batch); } static void virtblk_done(struct virtqueue *vq) @@ -272,16 +276,19 @@ static void virtblk_done(struct virtqueue *vq) struct virtblk_req *vbr; unsigned long flags; unsigned int len; + struct batch_complete batch; + + batch_complete_init(&batch); spin_lock_irqsave(vblk->disk->queue->queue_lock, flags); do { virtqueue_disable_cb(vq); while ((vbr = virtqueue_get_buf(vblk->vq, &len)) != NULL) { if (vbr->bio) { - virtblk_bio_done(vbr); + virtblk_bio_done(vbr, &batch); bio_done = true; } else { - virtblk_request_done(vbr); + virtblk_request_done(vbr, &batch); req_done = true; } } @@ -291,6 +298,8 @@ static void virtblk_done(struct virtqueue *vq) blk_start_queue(vblk->disk->queue); spin_unlock_irqrestore(vblk->disk->queue->queue_lock, flags); + batch_complete(&batch); + if (bio_done) wake_up(&vblk->queue_wait); } diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c index 1c7fdcd22a98..0ac9b45a585e 100644 --- a/drivers/char/ipmi/ipmi_si_intf.c +++ b/drivers/char/ipmi/ipmi_si_intf.c @@ -1208,6 +1208,16 @@ static int smi_num; /* Used to sequence the SMIs */ #define DEFAULT_REGSPACING 1 #define DEFAULT_REGSIZE 1 +#ifdef CONFIG_ACPI +static bool si_tryacpi = 1; +#endif +#ifdef CONFIG_DMI +static bool si_trydmi = 1; +#endif +static bool si_tryplatform = 1; +#ifdef CONFIG_PCI +static bool si_trypci = 1; +#endif static bool si_trydefaults = 1; static char *si_type[SI_MAX_PARMS]; #define MAX_SI_TYPE_STR 30 @@ -1238,6 +1248,25 @@ MODULE_PARM_DESC(hotmod, "Add and remove interfaces. See" " Documentation/IPMI.txt in the kernel sources for the" " gory details."); +#ifdef CONFIG_ACPI +module_param_named(tryacpi, si_tryacpi, bool, 0); +MODULE_PARM_DESC(tryacpi, "Setting this to zero will disable the" + " default scan of the interfaces identified via ACPI"); +#endif +#ifdef CONFIG_DMI +module_param_named(trydmi, si_trydmi, bool, 0); +MODULE_PARM_DESC(trydmi, "Setting this to zero will disable the" + " default scan of the interfaces identified via DMI"); +#endif +module_param_named(tryplatform, si_tryplatform, bool, 0); +MODULE_PARM_DESC(tryacpi, "Setting this to zero will disable the" + " default scan of the interfaces identified via platform" + " interfaces like openfirmware"); +#ifdef CONFIG_PCI +module_param_named(trypci, si_trypci, bool, 0); +MODULE_PARM_DESC(tryacpi, "Setting this to zero will disable the" + " default scan of the interfaces identified via pci"); +#endif module_param_named(trydefaults, si_trydefaults, bool, 0); MODULE_PARM_DESC(trydefaults, "Setting this to 'false' will disable the" " default scan of the KCS and SMIC interface at the standard" @@ -3371,13 +3400,15 @@ static int init_ipmi_si(void) return 0; initialized = 1; - rv = platform_driver_register(&ipmi_driver); - if (rv) { - printk(KERN_ERR PFX "Unable to register driver: %d\n", rv); - return rv; + if (si_tryplatform) { + rv = platform_driver_register(&ipmi_driver); + if (rv) { + printk(KERN_ERR PFX "Unable to register " + "driver: %d\n", rv); + return rv; + } } - /* Parse out the si_type string into its components. */ str = si_type_str; if (*str != '\0') { @@ -3400,24 +3431,31 @@ static int init_ipmi_si(void) return 0; #ifdef CONFIG_PCI - rv = pci_register_driver(&ipmi_pci_driver); - if (rv) - printk(KERN_ERR PFX "Unable to register PCI driver: %d\n", rv); - else - pci_registered = 1; + if (si_trypci) { + rv = pci_register_driver(&ipmi_pci_driver); + if (rv) + printk(KERN_ERR PFX "Unable to register " + "PCI driver: %d\n", rv); + else + pci_registered = 1; + } #endif #ifdef CONFIG_ACPI - pnp_register_driver(&ipmi_pnp_driver); - pnp_registered = 1; + if (si_tryacpi) { + pnp_register_driver(&ipmi_pnp_driver); + pnp_registered = 1; + } #endif #ifdef CONFIG_DMI - dmi_find_bmc(); + if (si_trydmi) + dmi_find_bmc(); #endif #ifdef CONFIG_ACPI - spmi_find_bmc(); + if (si_tryacpi) + spmi_find_bmc(); #endif /* We prefer devices with interrupts, but in the case of a machine diff --git a/drivers/char/mem.c b/drivers/char/mem.c index 6f6e92a3102d..3b9f28961f78 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -28,6 +28,7 @@ #include <linux/pfn.h> #include <linux/export.h> #include <linux/io.h> +#include <linux/aio.h> #include <asm/uaccess.h> @@ -627,6 +628,18 @@ static ssize_t write_null(struct file *file, const char __user *buf, return count; } +static ssize_t aio_read_null(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) +{ + return 0; +} + +static ssize_t aio_write_null(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) +{ + return iov_length(iov, nr_segs); +} + static int pipe_to_null(struct pipe_inode_info *info, struct pipe_buffer *buf, struct splice_desc *sd) { @@ -670,6 +683,24 @@ static ssize_t read_zero(struct file *file, char __user *buf, return written ? written : -EFAULT; } +static ssize_t aio_read_zero(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) +{ + size_t written = 0; + unsigned long i; + ssize_t ret; + + for (i = 0; i < nr_segs; i++) { + ret = read_zero(iocb->ki_filp, iov[i].iov_base, iov[i].iov_len, + &pos); + if (ret < 0) + break; + written += ret; + } + + return written ? written : -EFAULT; +} + static int mmap_zero(struct file *file, struct vm_area_struct *vma) { #ifndef CONFIG_MMU @@ -738,6 +769,7 @@ static int open_port(struct inode *inode, struct file *filp) #define full_lseek null_lseek #define write_zero write_null #define read_full read_zero +#define aio_write_zero aio_write_null #define open_mem open_port #define open_kmem open_mem #define open_oldmem open_mem @@ -766,6 +798,8 @@ static const struct file_operations null_fops = { .llseek = null_lseek, .read = read_null, .write = write_null, + .aio_read = aio_read_null, + .aio_write = aio_write_null, .splice_write = splice_write_null, }; @@ -782,6 +816,8 @@ static const struct file_operations zero_fops = { .llseek = zero_lseek, .read = read_zero, .write = write_zero, + .aio_read = aio_read_zero, + .aio_write = aio_write_zero, .mmap = mmap_zero, }; diff --git a/drivers/char/misc.c b/drivers/char/misc.c index 522136d40843..190d4423653f 100644 --- a/drivers/char/misc.c +++ b/drivers/char/misc.c @@ -183,19 +183,12 @@ static const struct file_operations misc_fops = { int misc_register(struct miscdevice * misc) { - struct miscdevice *c; dev_t dev; int err = 0; INIT_LIST_HEAD(&misc->list); mutex_lock(&misc_mtx); - list_for_each_entry(c, &misc_list, list) { - if (c->minor == misc->minor) { - mutex_unlock(&misc_mtx); - return -EBUSY; - } - } if (misc->minor == MISC_DYNAMIC_MINOR) { int i = find_first_zero_bit(misc_minors, DYNAMIC_MINORS); @@ -205,6 +198,15 @@ int misc_register(struct miscdevice * misc) } misc->minor = DYNAMIC_MINORS - i - 1; set_bit(i, misc_minors); + } else { + struct miscdevice *c; + + list_for_each_entry(c, &misc_list, list) { + if (c->minor == misc->minor) { + mutex_unlock(&misc_mtx); + return -EBUSY; + } + } } dev = MKDEV(MISC_MAJOR, misc->minor); diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index fabbfe1a9253..ed87b2405806 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -52,31 +52,29 @@ static void clk_summary_show_subtree(struct seq_file *s, struct clk *c, int level) { struct clk *child; - struct hlist_node *tmp; if (!c) return; clk_summary_show_one(s, c, level); - hlist_for_each_entry(child, tmp, &c->children, child_node) + hlist_for_each_entry(child, &c->children, child_node) clk_summary_show_subtree(s, child, level + 1); } static int clk_summary_show(struct seq_file *s, void *data) { struct clk *c; - struct hlist_node *tmp; seq_printf(s, " clock enable_cnt prepare_cnt rate\n"); seq_printf(s, "---------------------------------------------------------------------\n"); mutex_lock(&prepare_lock); - hlist_for_each_entry(c, tmp, &clk_root_list, child_node) + hlist_for_each_entry(c, &clk_root_list, child_node) clk_summary_show_subtree(s, c, 0); - hlist_for_each_entry(c, tmp, &clk_orphan_list, child_node) + hlist_for_each_entry(c, &clk_orphan_list, child_node) clk_summary_show_subtree(s, c, 0); mutex_unlock(&prepare_lock); @@ -111,14 +109,13 @@ static void clk_dump_one(struct seq_file *s, struct clk *c, int level) static void clk_dump_subtree(struct seq_file *s, struct clk *c, int level) { struct clk *child; - struct hlist_node *tmp; if (!c) return; clk_dump_one(s, c, level); - hlist_for_each_entry(child, tmp, &c->children, child_node) { + hlist_for_each_entry(child, &c->children, child_node) { seq_printf(s, ","); clk_dump_subtree(s, child, level + 1); } @@ -129,21 +126,20 @@ static void clk_dump_subtree(struct seq_file *s, struct clk *c, int level) static int clk_dump(struct seq_file *s, void *data) { struct clk *c; - struct hlist_node *tmp; bool first_node = true; seq_printf(s, "{"); mutex_lock(&prepare_lock); - hlist_for_each_entry(c, tmp, &clk_root_list, child_node) { + hlist_for_each_entry(c, &clk_root_list, child_node) { if (!first_node) seq_printf(s, ","); first_node = false; clk_dump_subtree(s, c, 0); } - hlist_for_each_entry(c, tmp, &clk_orphan_list, child_node) { + hlist_for_each_entry(c, &clk_orphan_list, child_node) { seq_printf(s, ","); clk_dump_subtree(s, c, 0); } @@ -222,7 +218,6 @@ out: static int clk_debug_create_subtree(struct clk *clk, struct dentry *pdentry) { struct clk *child; - struct hlist_node *tmp; int ret = -EINVAL;; if (!clk || !pdentry) @@ -233,7 +228,7 @@ static int clk_debug_create_subtree(struct clk *clk, struct dentry *pdentry) if (ret) goto out; - hlist_for_each_entry(child, tmp, &clk->children, child_node) + hlist_for_each_entry(child, &clk->children, child_node) clk_debug_create_subtree(child, clk->dentry); ret = 0; @@ -299,7 +294,6 @@ out: static int __init clk_debug_init(void) { struct clk *clk; - struct hlist_node *tmp; struct dentry *d; rootdir = debugfs_create_dir("clk", NULL); @@ -324,10 +318,10 @@ static int __init clk_debug_init(void) mutex_lock(&prepare_lock); - hlist_for_each_entry(clk, tmp, &clk_root_list, child_node) + hlist_for_each_entry(clk, &clk_root_list, child_node) clk_debug_create_subtree(clk, rootdir); - hlist_for_each_entry(clk, tmp, &clk_orphan_list, child_node) + hlist_for_each_entry(clk, &clk_orphan_list, child_node) clk_debug_create_subtree(clk, orphandir); inited = 1; @@ -345,13 +339,12 @@ static inline int clk_debug_register(struct clk *clk) { return 0; } static void clk_disable_unused_subtree(struct clk *clk) { struct clk *child; - struct hlist_node *tmp; unsigned long flags; if (!clk) goto out; - hlist_for_each_entry(child, tmp, &clk->children, child_node) + hlist_for_each_entry(child, &clk->children, child_node) clk_disable_unused_subtree(child); spin_lock_irqsave(&enable_lock, flags); @@ -384,14 +377,13 @@ out: static int clk_disable_unused(void) { struct clk *clk; - struct hlist_node *tmp; mutex_lock(&prepare_lock); - hlist_for_each_entry(clk, tmp, &clk_root_list, child_node) + hlist_for_each_entry(clk, &clk_root_list, child_node) clk_disable_unused_subtree(clk); - hlist_for_each_entry(clk, tmp, &clk_orphan_list, child_node) + hlist_for_each_entry(clk, &clk_orphan_list, child_node) clk_disable_unused_subtree(clk); mutex_unlock(&prepare_lock); @@ -484,12 +476,11 @@ static struct clk *__clk_lookup_subtree(const char *name, struct clk *clk) { struct clk *child; struct clk *ret; - struct hlist_node *tmp; if (!strcmp(clk->name, name)) return clk; - hlist_for_each_entry(child, tmp, &clk->children, child_node) { + hlist_for_each_entry(child, &clk->children, child_node) { ret = __clk_lookup_subtree(name, child); if (ret) return ret; @@ -502,20 +493,19 @@ struct clk *__clk_lookup(const char *name) { struct clk *root_clk; struct clk *ret; - struct hlist_node *tmp; if (!name) return NULL; /* search the 'proper' clk tree first */ - hlist_for_each_entry(root_clk, tmp, &clk_root_list, child_node) { + hlist_for_each_entry(root_clk, &clk_root_list, child_node) { ret = __clk_lookup_subtree(name, root_clk); if (ret) return ret; } /* if not found, then search the orphan tree */ - hlist_for_each_entry(root_clk, tmp, &clk_orphan_list, child_node) { + hlist_for_each_entry(root_clk, &clk_orphan_list, child_node) { ret = __clk_lookup_subtree(name, root_clk); if (ret) return ret; @@ -812,7 +802,6 @@ static void __clk_recalc_rates(struct clk *clk, unsigned long msg) { unsigned long old_rate; unsigned long parent_rate = 0; - struct hlist_node *tmp; struct clk *child; old_rate = clk->rate; @@ -832,7 +821,7 @@ static void __clk_recalc_rates(struct clk *clk, unsigned long msg) if (clk->notifier_count && msg) __clk_notify(clk, msg, old_rate, clk->rate); - hlist_for_each_entry(child, tmp, &clk->children, child_node) + hlist_for_each_entry(child, &clk->children, child_node) __clk_recalc_rates(child, msg); } @@ -878,7 +867,6 @@ EXPORT_SYMBOL_GPL(clk_get_rate); */ static int __clk_speculate_rates(struct clk *clk, unsigned long parent_rate) { - struct hlist_node *tmp; struct clk *child; unsigned long new_rate; int ret = NOTIFY_DONE; @@ -895,7 +883,7 @@ static int __clk_speculate_rates(struct clk *clk, unsigned long parent_rate) if (ret == NOTIFY_BAD) goto out; - hlist_for_each_entry(child, tmp, &clk->children, child_node) { + hlist_for_each_entry(child, &clk->children, child_node) { ret = __clk_speculate_rates(child, new_rate); if (ret == NOTIFY_BAD) break; @@ -908,11 +896,10 @@ out: static void clk_calc_subtree(struct clk *clk, unsigned long new_rate) { struct clk *child; - struct hlist_node *tmp; clk->new_rate = new_rate; - hlist_for_each_entry(child, tmp, &clk->children, child_node) { + hlist_for_each_entry(child, &clk->children, child_node) { if (child->ops->recalc_rate) child->new_rate = child->ops->recalc_rate(child->hw, new_rate); else @@ -983,7 +970,6 @@ out: */ static struct clk *clk_propagate_rate_change(struct clk *clk, unsigned long event) { - struct hlist_node *tmp; struct clk *child, *fail_clk = NULL; int ret = NOTIFY_DONE; @@ -996,7 +982,7 @@ static struct clk *clk_propagate_rate_change(struct clk *clk, unsigned long even fail_clk = clk; } - hlist_for_each_entry(child, tmp, &clk->children, child_node) { + hlist_for_each_entry(child, &clk->children, child_node) { clk = clk_propagate_rate_change(child, event); if (clk) fail_clk = clk; @@ -1014,7 +1000,6 @@ static void clk_change_rate(struct clk *clk) struct clk *child; unsigned long old_rate; unsigned long best_parent_rate = 0; - struct hlist_node *tmp; old_rate = clk->rate; @@ -1032,7 +1017,7 @@ static void clk_change_rate(struct clk *clk) if (clk->notifier_count && old_rate != clk->rate) __clk_notify(clk, POST_RATE_CHANGE, old_rate, clk->rate); - hlist_for_each_entry(child, tmp, &clk->children, child_node) + hlist_for_each_entry(child, &clk->children, child_node) clk_change_rate(child); } @@ -1348,7 +1333,7 @@ int __clk_init(struct device *dev, struct clk *clk) { int i, ret = 0; struct clk *orphan; - struct hlist_node *tmp, *tmp2; + struct hlist_node *tmp2; if (!clk) return -EINVAL; @@ -1448,7 +1433,7 @@ int __clk_init(struct device *dev, struct clk *clk) * walk the list of orphan clocks and reparent any that are children of * this clock */ - hlist_for_each_entry_safe(orphan, tmp, tmp2, &clk_orphan_list, child_node) { + hlist_for_each_entry_safe(orphan, tmp2, &clk_orphan_list, child_node) { if (orphan->ops->get_parent) { i = orphan->ops->get_parent(orphan->hw); if (!strcmp(clk->name, orphan->parent_names[i])) diff --git a/drivers/dca/dca-sysfs.c b/drivers/dca/dca-sysfs.c index 591b6597c00a..126cf295b198 100644 --- a/drivers/dca/dca-sysfs.c +++ b/drivers/dca/dca-sysfs.c @@ -53,22 +53,19 @@ void dca_sysfs_remove_req(struct dca_provider *dca, int slot) int dca_sysfs_add_provider(struct dca_provider *dca, struct device *dev) { struct device *cd; - int err = 0; + int ret; -idr_try_again: - if (!idr_pre_get(&dca_idr, GFP_KERNEL)) - return -ENOMEM; + idr_preload(GFP_KERNEL); spin_lock(&dca_idr_lock); - err = idr_get_new(&dca_idr, dca, &dca->id); + + ret = idr_alloc(&dca_idr, dca, 0, 0, GFP_NOWAIT); + if (ret >= 0) + dca->id = ret; + spin_unlock(&dca_idr_lock); - switch (err) { - case 0: - break; - case -EAGAIN: - goto idr_try_again; - default: - return err; - } + idr_preload_end(); + if (ret < 0) + return ret; cd = device_create(dca_class, dev, MKDEV(0, 0), NULL, "dca%d", dca->id); if (IS_ERR(cd)) { diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index 242b8c0a3de8..b2728d6ba2fd 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -686,18 +686,14 @@ static int get_dma_id(struct dma_device *device) { int rc; - idr_retry: - if (!idr_pre_get(&dma_idr, GFP_KERNEL)) - return -ENOMEM; mutex_lock(&dma_list_mutex); - rc = idr_get_new(&dma_idr, NULL, &device->dev_id); - mutex_unlock(&dma_list_mutex); - if (rc == -EAGAIN) - goto idr_retry; - else if (rc != 0) - return rc; - return 0; + rc = idr_alloc(&dma_idr, NULL, 0, 0, GFP_KERNEL); + if (rc >= 0) + device->dev_id = rc; + + mutex_unlock(&dma_list_mutex); + return rc < 0 ? rc : 0; } /** diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c index f8d22872d753..27ac423ab25e 100644 --- a/drivers/firewire/core-cdev.c +++ b/drivers/firewire/core-cdev.c @@ -487,27 +487,28 @@ static int ioctl_get_info(struct client *client, union ioctl_arg *arg) static int add_client_resource(struct client *client, struct client_resource *resource, gfp_t gfp_mask) { + bool preload = gfp_mask & __GFP_WAIT; unsigned long flags; int ret; - retry: - if (idr_pre_get(&client->resource_idr, gfp_mask) == 0) - return -ENOMEM; - + if (preload) + idr_preload(gfp_mask); spin_lock_irqsave(&client->lock, flags); + if (client->in_shutdown) ret = -ECANCELED; else - ret = idr_get_new(&client->resource_idr, resource, - &resource->handle); + ret = idr_alloc(&client->resource_idr, resource, 0, 0, + GFP_NOWAIT); if (ret >= 0) { + resource->handle = ret; client_get(client); schedule_if_iso_resource(resource); } - spin_unlock_irqrestore(&client->lock, flags); - if (ret == -EAGAIN) - goto retry; + spin_unlock_irqrestore(&client->lock, flags); + if (preload) + idr_preload_end(); return ret < 0 ? ret : 0; } @@ -1779,7 +1780,6 @@ static int fw_device_op_release(struct inode *inode, struct file *file) wait_event(client->tx_flush_wait, !has_outbound_transactions(client)); idr_for_each(&client->resource_idr, shutdown_resource, client); - idr_remove_all(&client->resource_idr); idr_destroy(&client->resource_idr); list_for_each_entry_safe(event, next_event, &client->event_list, link) diff --git a/drivers/firewire/core-device.c b/drivers/firewire/core-device.c index 3873d535b28d..b946330b02c3 100644 --- a/drivers/firewire/core-device.c +++ b/drivers/firewire/core-device.c @@ -1017,9 +1017,7 @@ static void fw_device_init(struct work_struct *work) fw_device_get(device); down_write(&fw_device_rwsem); - ret = idr_pre_get(&fw_device_idr, GFP_KERNEL) ? - idr_get_new(&fw_device_idr, device, &minor) : - -ENOMEM; + ret = idr_alloc(&fw_device_idr, device, 0, 1 << MINORBITS, GFP_KERNEL); up_write(&fw_device_rwsem); if (ret < 0) diff --git a/drivers/firmware/memmap.c b/drivers/firmware/memmap.c index 90723e65b081..0b5b5f619c75 100644 --- a/drivers/firmware/memmap.c +++ b/drivers/firmware/memmap.c @@ -21,6 +21,7 @@ #include <linux/types.h> #include <linux/bootmem.h> #include <linux/slab.h> +#include <linux/mm.h> /* * Data types ------------------------------------------------------------------ @@ -52,6 +53,9 @@ static ssize_t start_show(struct firmware_map_entry *entry, char *buf); static ssize_t end_show(struct firmware_map_entry *entry, char *buf); static ssize_t type_show(struct firmware_map_entry *entry, char *buf); +static struct firmware_map_entry * __meminit +firmware_map_find_entry(u64 start, u64 end, const char *type); + /* * Static data ----------------------------------------------------------------- */ @@ -79,7 +83,52 @@ static const struct sysfs_ops memmap_attr_ops = { .show = memmap_attr_show, }; -static struct kobj_type memmap_ktype = { +/* Firmware memory map entries. */ +static LIST_HEAD(map_entries); +static DEFINE_SPINLOCK(map_entries_lock); + +/* + * For memory hotplug, there is no way to free memory map entries allocated + * by boot mem after the system is up. So when we hot-remove memory whose + * map entry is allocated by bootmem, we need to remember the storage and + * reuse it when the memory is hot-added again. + */ +static LIST_HEAD(map_entries_bootmem); +static DEFINE_SPINLOCK(map_entries_bootmem_lock); + + +static inline struct firmware_map_entry * +to_memmap_entry(struct kobject *kobj) +{ + return container_of(kobj, struct firmware_map_entry, kobj); +} + +static void __meminit release_firmware_map_entry(struct kobject *kobj) +{ + struct firmware_map_entry *entry = to_memmap_entry(kobj); + + if (PageReserved(virt_to_page(entry))) { + /* + * Remember the storage allocated by bootmem, and reuse it when + * the memory is hot-added again. The entry will be added to + * map_entries_bootmem here, and deleted from &map_entries in + * firmware_map_remove_entry(). + */ + if (firmware_map_find_entry(entry->start, entry->end, + entry->type)) { + spin_lock(&map_entries_bootmem_lock); + list_add(&entry->list, &map_entries_bootmem); + spin_unlock(&map_entries_bootmem_lock); + } + + return; + } + + kfree(entry); +} + +static struct kobj_type __refdata memmap_ktype = { + .release = release_firmware_map_entry, .sysfs_ops = &memmap_attr_ops, .default_attrs = def_attrs, }; @@ -88,13 +137,6 @@ static struct kobj_type memmap_ktype = { * Registration functions ------------------------------------------------------ */ -/* - * Firmware memory map entries. No locking is needed because the - * firmware_map_add() and firmware_map_add_early() functions are called - * in firmware initialisation code in one single thread of execution. - */ -static LIST_HEAD(map_entries); - /** * firmware_map_add_entry() - Does the real work to add a firmware memmap entry. * @start: Start of the memory range. @@ -118,11 +160,25 @@ static int firmware_map_add_entry(u64 start, u64 end, INIT_LIST_HEAD(&entry->list); kobject_init(&entry->kobj, &memmap_ktype); + spin_lock(&map_entries_lock); list_add_tail(&entry->list, &map_entries); + spin_unlock(&map_entries_lock); return 0; } +/** + * firmware_map_remove_entry() - Does the real work to remove a firmware + * memmap entry. + * @entry: removed entry. + * + * The caller must hold map_entries_lock, and release it properly. + **/ +static inline void firmware_map_remove_entry(struct firmware_map_entry *entry) +{ + list_del(&entry->list); +} + /* * Add memmap entry on sysfs */ @@ -144,6 +200,78 @@ static int add_sysfs_fw_map_entry(struct firmware_map_entry *entry) return 0; } +/* + * Remove memmap entry on sysfs + */ +static inline void remove_sysfs_fw_map_entry(struct firmware_map_entry *entry) +{ + kobject_put(&entry->kobj); +} + +/* + * firmware_map_find_entry_in_list() - Search memmap entry in a given list. + * @start: Start of the memory range. + * @end: End of the memory range (exclusive). + * @type: Type of the memory range. + * @list: In which to find the entry. + * + * This function is to find the memmap entey of a given memory range in a + * given list. The caller must hold map_entries_lock, and must not release + * the lock until the processing of the returned entry has completed. + * + * Return: Pointer to the entry to be found on success, or NULL on failure. + */ +static struct firmware_map_entry * __meminit +firmware_map_find_entry_in_list(u64 start, u64 end, const char *type, + struct list_head *list) +{ + struct firmware_map_entry *entry; + + list_for_each_entry(entry, list, list) + if ((entry->start == start) && (entry->end == end) && + (!strcmp(entry->type, type))) { + return entry; + } + + return NULL; +} + +/* + * firmware_map_find_entry() - Search memmap entry in map_entries. + * @start: Start of the memory range. + * @end: End of the memory range (exclusive). + * @type: Type of the memory range. + * + * This function is to find the memmap entey of a given memory range. + * The caller must hold map_entries_lock, and must not release the lock + * until the processing of the returned entry has completed. + * + * Return: Pointer to the entry to be found on success, or NULL on failure. + */ +static struct firmware_map_entry * __meminit +firmware_map_find_entry(u64 start, u64 end, const char *type) +{ + return firmware_map_find_entry_in_list(start, end, type, &map_entries); +} + +/* + * firmware_map_find_entry_bootmem() - Search memmap entry in map_entries_bootmem. + * @start: Start of the memory range. + * @end: End of the memory range (exclusive). + * @type: Type of the memory range. + * + * This function is similar to firmware_map_find_entry except that it find the + * given entry in map_entries_bootmem. + * + * Return: Pointer to the entry to be found on success, or NULL on failure. + */ +static struct firmware_map_entry * __meminit +firmware_map_find_entry_bootmem(u64 start, u64 end, const char *type) +{ + return firmware_map_find_entry_in_list(start, end, type, + &map_entries_bootmem); +} + /** * firmware_map_add_hotplug() - Adds a firmware mapping entry when we do * memory hotplug. @@ -161,9 +289,19 @@ int __meminit firmware_map_add_hotplug(u64 start, u64 end, const char *type) { struct firmware_map_entry *entry; - entry = kzalloc(sizeof(struct firmware_map_entry), GFP_ATOMIC); - if (!entry) - return -ENOMEM; + entry = firmware_map_find_entry_bootmem(start, end, type); + if (!entry) { + entry = kzalloc(sizeof(struct firmware_map_entry), GFP_ATOMIC); + if (!entry) + return -ENOMEM; + } else { + /* Reuse storage allocated by bootmem. */ + spin_lock(&map_entries_bootmem_lock); + list_del(&entry->list); + spin_unlock(&map_entries_bootmem_lock); + + memset(entry, 0, sizeof(*entry)); + } firmware_map_add_entry(start, end, type, entry); /* create the memmap entry */ @@ -196,6 +334,36 @@ int __init firmware_map_add_early(u64 start, u64 end, const char *type) return firmware_map_add_entry(start, end, type, entry); } +/** + * firmware_map_remove() - remove a firmware mapping entry + * @start: Start of the memory range. + * @end: End of the memory range. + * @type: Type of the memory range. + * + * removes a firmware mapping entry. + * + * Returns 0 on success, or -EINVAL if no entry. + **/ +int __meminit firmware_map_remove(u64 start, u64 end, const char *type) +{ + struct firmware_map_entry *entry; + + spin_lock(&map_entries_lock); + entry = firmware_map_find_entry(start, end - 1, type); + if (!entry) { + spin_unlock(&map_entries_lock); + return -EINVAL; + } + + firmware_map_remove_entry(entry); + spin_unlock(&map_entries_lock); + + /* remove the memmap entry */ + remove_sysfs_fw_map_entry(entry); + + return 0; +} + /* * Sysfs functions ------------------------------------------------------------- */ @@ -217,8 +385,10 @@ static ssize_t type_show(struct firmware_map_entry *entry, char *buf) return snprintf(buf, PAGE_SIZE, "%s\n", entry->type); } -#define to_memmap_attr(_attr) container_of(_attr, struct memmap_attribute, attr) -#define to_memmap_entry(obj) container_of(obj, struct firmware_map_entry, kobj) +static inline struct memmap_attribute *to_memmap_attr(struct attribute *attr) +{ + return container_of(attr, struct memmap_attribute, attr); +} static ssize_t memmap_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index e14eb88bbe8d..9b37b90480c2 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -358,15 +358,10 @@ static int gpio_setup_irq(struct gpio_desc *desc, struct device *dev, goto err_out; } - do { - ret = -ENOMEM; - if (idr_pre_get(&dirent_idr, GFP_KERNEL)) - ret = idr_get_new_above(&dirent_idr, value_sd, - 1, &id); - } while (ret == -EAGAIN); - - if (ret) + ret = idr_alloc(&dirent_idr, value_sd, 1, 0, GFP_KERNEL); + if (ret < 0) goto free_sd; + id = ret; desc->flags &= GPIO_FLAGS_MASK; desc->flags |= (unsigned long)id << ID_SHIFT; diff --git a/drivers/gpu/drm/drm_context.c b/drivers/gpu/drm/drm_context.c index 45adf97e678f..725968d38976 100644 --- a/drivers/gpu/drm/drm_context.c +++ b/drivers/gpu/drm/drm_context.c @@ -74,24 +74,13 @@ void drm_ctxbitmap_free(struct drm_device * dev, int ctx_handle) */ static int drm_ctxbitmap_next(struct drm_device * dev) { - int new_id; int ret; -again: - if (idr_pre_get(&dev->ctx_idr, GFP_KERNEL) == 0) { - DRM_ERROR("Out of memory expanding drawable idr\n"); - return -ENOMEM; - } mutex_lock(&dev->struct_mutex); - ret = idr_get_new_above(&dev->ctx_idr, NULL, - DRM_RESERVED_CONTEXTS, &new_id); + ret = idr_alloc(&dev->ctx_idr, NULL, DRM_RESERVED_CONTEXTS, 0, + GFP_KERNEL); mutex_unlock(&dev->struct_mutex); - if (ret == -EAGAIN) - goto again; - else if (ret) - return ret; - - return new_id; + return ret; } /** @@ -118,7 +107,7 @@ int drm_ctxbitmap_init(struct drm_device * dev) void drm_ctxbitmap_cleanup(struct drm_device * dev) { mutex_lock(&dev->struct_mutex); - idr_remove_all(&dev->ctx_idr); + idr_destroy(&dev->ctx_idr); mutex_unlock(&dev->struct_mutex); } diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index 9c797f6fea75..838c9b655e04 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -252,32 +252,21 @@ char *drm_get_connector_status_name(enum drm_connector_status status) static int drm_mode_object_get(struct drm_device *dev, struct drm_mode_object *obj, uint32_t obj_type) { - int new_id = 0; int ret; -again: - if (idr_pre_get(&dev->mode_config.crtc_idr, GFP_KERNEL) == 0) { - DRM_ERROR("Ran out memory getting a mode number\n"); - return -ENOMEM; - } - mutex_lock(&dev->mode_config.idr_mutex); - ret = idr_get_new_above(&dev->mode_config.crtc_idr, obj, 1, &new_id); - - if (!ret) { + ret = idr_alloc(&dev->mode_config.crtc_idr, obj, 1, 0, GFP_KERNEL); + if (ret >= 0) { /* * Set up the object linking under the protection of the idr * lock so that other users can't see inconsistent state. */ - obj->id = new_id; + obj->id = ret; obj->type = obj_type; } mutex_unlock(&dev->mode_config.idr_mutex); - if (ret == -EAGAIN) - goto again; - - return ret; + return ret < 0 ? ret : 0; } /** @@ -1258,7 +1247,6 @@ void drm_mode_config_cleanup(struct drm_device *dev) crtc->funcs->destroy(crtc); } - idr_remove_all(&dev->mode_config.crtc_idr); idr_destroy(&dev->mode_config.crtc_idr); } EXPORT_SYMBOL(drm_mode_config_cleanup); diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c index be174cab105a..25f91cd23e60 100644 --- a/drivers/gpu/drm/drm_drv.c +++ b/drivers/gpu/drm/drm_drv.c @@ -297,7 +297,6 @@ static void __exit drm_core_exit(void) unregister_chrdev(DRM_MAJOR, "drm"); - idr_remove_all(&drm_minors_idr); idr_destroy(&drm_minors_idr); } diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 0c6e25e979dd..79ed61822c30 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -353,6 +353,14 @@ static void drm_fb_helper_dpms(struct fb_info *info, int dpms_mode) int i, j; /* + * fbdev->blank can be called from irq context in case of a panic. + * Since we already have our own special panic handler which will + * restore the fbdev console mode completely, just bail out early. + */ + if (oops_in_progress) + return; + + /* * For each CRTC in this fb, turn the connectors on/off. */ drm_modeset_lock_all(dev); diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 24efae464e2c..6577514941be 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -270,21 +270,19 @@ drm_gem_handle_create(struct drm_file *file_priv, int ret; /* - * Get the user-visible handle using idr. + * Get the user-visible handle using idr. Preload and perform + * allocation under our spinlock. */ -again: - /* ensure there is space available to allocate a handle */ - if (idr_pre_get(&file_priv->object_idr, GFP_KERNEL) == 0) - return -ENOMEM; - - /* do the allocation under our spinlock */ + idr_preload(GFP_KERNEL); spin_lock(&file_priv->table_lock); - ret = idr_get_new_above(&file_priv->object_idr, obj, 1, (int *)handlep); + + ret = idr_alloc(&file_priv->object_idr, obj, 1, 0, GFP_NOWAIT); + spin_unlock(&file_priv->table_lock); - if (ret == -EAGAIN) - goto again; - else if (ret) + idr_preload_end(); + if (ret < 0) return ret; + *handlep = ret; drm_gem_object_handle_reference(obj); @@ -451,22 +449,15 @@ drm_gem_flink_ioctl(struct drm_device *dev, void *data, if (obj == NULL) return -ENOENT; -again: - if (idr_pre_get(&dev->object_name_idr, GFP_KERNEL) == 0) { - ret = -ENOMEM; - goto err; - } - + idr_preload(GFP_KERNEL); spin_lock(&dev->object_name_lock); if (!obj->name) { - ret = idr_get_new_above(&dev->object_name_idr, obj, 1, - &obj->name); + ret = idr_alloc(&dev->object_name_idr, obj, 1, 0, GFP_NOWAIT); + obj->name = ret; args->name = (uint64_t) obj->name; spin_unlock(&dev->object_name_lock); - if (ret == -EAGAIN) - goto again; - else if (ret) + if (ret < 0) goto err; /* Allocate a reference for the name table. */ @@ -561,8 +552,6 @@ drm_gem_release(struct drm_device *dev, struct drm_file *file_private) { idr_for_each(&file_private->object_idr, &drm_gem_object_release_handle, file_private); - - idr_remove_all(&file_private->object_idr); idr_destroy(&file_private->object_idr); } diff --git a/drivers/gpu/drm/drm_hashtab.c b/drivers/gpu/drm/drm_hashtab.c index 80254547a3f8..7e4bae760e27 100644 --- a/drivers/gpu/drm/drm_hashtab.c +++ b/drivers/gpu/drm/drm_hashtab.c @@ -60,14 +60,13 @@ void drm_ht_verbose_list(struct drm_open_hash *ht, unsigned long key) { struct drm_hash_item *entry; struct hlist_head *h_list; - struct hlist_node *list; unsigned int hashed_key; int count = 0; hashed_key = hash_long(key, ht->order); DRM_DEBUG("Key is 0x%08lx, Hashed key is 0x%08x\n", key, hashed_key); h_list = &ht->table[hashed_key]; - hlist_for_each_entry(entry, list, h_list, head) + hlist_for_each_entry(entry, h_list, head) DRM_DEBUG("count %d, key: 0x%08lx\n", count++, entry->key); } @@ -76,14 +75,13 @@ static struct hlist_node *drm_ht_find_key(struct drm_open_hash *ht, { struct drm_hash_item *entry; struct hlist_head *h_list; - struct hlist_node *list; unsigned int hashed_key; hashed_key = hash_long(key, ht->order); h_list = &ht->table[hashed_key]; - hlist_for_each_entry(entry, list, h_list, head) { + hlist_for_each_entry(entry, h_list, head) { if (entry->key == key) - return list; + return &entry->head; if (entry->key > key) break; } @@ -95,14 +93,13 @@ static struct hlist_node *drm_ht_find_key_rcu(struct drm_open_hash *ht, { struct drm_hash_item *entry; struct hlist_head *h_list; - struct hlist_node *list; unsigned int hashed_key; hashed_key = hash_long(key, ht->order); h_list = &ht->table[hashed_key]; - hlist_for_each_entry_rcu(entry, list, h_list, head) { + hlist_for_each_entry_rcu(entry, h_list, head) { if (entry->key == key) - return list; + return &entry->head; if (entry->key > key) break; } @@ -113,19 +110,19 @@ int drm_ht_insert_item(struct drm_open_hash *ht, struct drm_hash_item *item) { struct drm_hash_item *entry; struct hlist_head *h_list; - struct hlist_node *list, *parent; + struct hlist_node *parent; unsigned int hashed_key; unsigned long key = item->key; hashed_key = hash_long(key, ht->order); h_list = &ht->table[hashed_key]; parent = NULL; - hlist_for_each_entry(entry, list, h_list, head) { + hlist_for_each_entry(entry, h_list, head) { if (entry->key == key) return -EINVAL; if (entry->key > key) break; - parent = list; + parent = &entry->head; } if (parent) { hlist_add_after_rcu(parent, &item->head); diff --git a/drivers/gpu/drm/drm_stub.c b/drivers/gpu/drm/drm_stub.c index 200e104f1fa0..7d30802a018f 100644 --- a/drivers/gpu/drm/drm_stub.c +++ b/drivers/gpu/drm/drm_stub.c @@ -109,7 +109,6 @@ EXPORT_SYMBOL(drm_ut_debug_printk); static int drm_minor_get_id(struct drm_device *dev, int type) { - int new_id; int ret; int base = 0, limit = 63; @@ -121,25 +120,11 @@ static int drm_minor_get_id(struct drm_device *dev, int type) limit = base + 255; } -again: - if (idr_pre_get(&drm_minors_idr, GFP_KERNEL) == 0) { - DRM_ERROR("Out of memory expanding drawable idr\n"); - return -ENOMEM; - } mutex_lock(&dev->struct_mutex); - ret = idr_get_new_above(&drm_minors_idr, NULL, - base, &new_id); + ret = idr_alloc(&drm_minors_idr, NULL, base, limit, GFP_KERNEL); mutex_unlock(&dev->struct_mutex); - if (ret == -EAGAIN) - goto again; - else if (ret) - return ret; - if (new_id >= limit) { - idr_remove(&drm_minors_idr, new_id); - return -EINVAL; - } - return new_id; + return ret == -ENOSPC ? -EINVAL : ret; } struct drm_master *drm_master_create(struct drm_minor *minor) diff --git a/drivers/gpu/drm/exynos/exynos_drm_ipp.c b/drivers/gpu/drm/exynos/exynos_drm_ipp.c index 1a556354e92f..1adce07ecb5b 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_ipp.c +++ b/drivers/gpu/drm/exynos/exynos_drm_ipp.c @@ -137,21 +137,15 @@ static int ipp_create_id(struct idr *id_idr, struct mutex *lock, void *obj, DRM_DEBUG_KMS("%s\n", __func__); -again: - /* ensure there is space available to allocate a handle */ - if (idr_pre_get(id_idr, GFP_KERNEL) == 0) { - DRM_ERROR("failed to get idr.\n"); - return -ENOMEM; - } - /* do the allocation under our mutexlock */ mutex_lock(lock); - ret = idr_get_new_above(id_idr, obj, 1, (int *)idp); + ret = idr_alloc(id_idr, obj, 1, 0, GFP_KERNEL); mutex_unlock(lock); - if (ret == -EAGAIN) - goto again; + if (ret < 0) + return ret; - return ret; + *idp = ret; + return 0; } static void *ipp_find_obj(struct idr *id_idr, struct mutex *lock, u32 id) @@ -1786,8 +1780,6 @@ err_iommu: drm_iommu_detach_device(drm_dev, ippdrv->dev); err_idr: - idr_remove_all(&ctx->ipp_idr); - idr_remove_all(&ctx->prop_idr); idr_destroy(&ctx->ipp_idr); idr_destroy(&ctx->prop_idr); return ret; @@ -1965,8 +1957,6 @@ static int ipp_remove(struct platform_device *pdev) exynos_drm_subdrv_unregister(&ctx->subdrv); /* remove,destroy ipp idr */ - idr_remove_all(&ctx->ipp_idr); - idr_remove_all(&ctx->prop_idr); idr_destroy(&ctx->ipp_idr); idr_destroy(&ctx->prop_idr); diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c index a3f06bcad551..27e586ad6b30 100644 --- a/drivers/gpu/drm/i915/i915_gem_context.c +++ b/drivers/gpu/drm/i915/i915_gem_context.c @@ -144,7 +144,7 @@ create_hw_context(struct drm_device *dev, { struct drm_i915_private *dev_priv = dev->dev_private; struct i915_hw_context *ctx; - int ret, id; + int ret; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (ctx == NULL) @@ -169,22 +169,11 @@ create_hw_context(struct drm_device *dev, ctx->file_priv = file_priv; -again: - if (idr_pre_get(&file_priv->context_idr, GFP_KERNEL) == 0) { - ret = -ENOMEM; - DRM_DEBUG_DRIVER("idr allocation failed\n"); - goto err_out; - } - - ret = idr_get_new_above(&file_priv->context_idr, ctx, - DEFAULT_CONTEXT_ID + 1, &id); - if (ret == 0) - ctx->id = id; - - if (ret == -EAGAIN) - goto again; - else if (ret) + ret = idr_alloc(&file_priv->context_idr, ctx, DEFAULT_CONTEXT_ID + 1, 0, + GFP_KERNEL); + if (ret < 0) goto err_out; + ctx->id = ret; return ctx; diff --git a/drivers/gpu/drm/sis/sis_drv.c b/drivers/gpu/drm/sis/sis_drv.c index 841065b998a1..5a5325e6b759 100644 --- a/drivers/gpu/drm/sis/sis_drv.c +++ b/drivers/gpu/drm/sis/sis_drv.c @@ -58,7 +58,6 @@ static int sis_driver_unload(struct drm_device *dev) { drm_sis_private_t *dev_priv = dev->dev_private; - idr_remove_all(&dev_priv->object_idr); idr_destroy(&dev_priv->object_idr); kfree(dev_priv); diff --git a/drivers/gpu/drm/sis/sis_mm.c b/drivers/gpu/drm/sis/sis_mm.c index 2b2f78c428af..9a43d98e5003 100644 --- a/drivers/gpu/drm/sis/sis_mm.c +++ b/drivers/gpu/drm/sis/sis_mm.c @@ -128,17 +128,10 @@ static int sis_drm_alloc(struct drm_device *dev, struct drm_file *file, if (retval) goto fail_alloc; -again: - if (idr_pre_get(&dev_priv->object_idr, GFP_KERNEL) == 0) { - retval = -ENOMEM; - goto fail_idr; - } - - retval = idr_get_new_above(&dev_priv->object_idr, item, 1, &user_key); - if (retval == -EAGAIN) - goto again; - if (retval) + retval = idr_alloc(&dev_priv->object_idr, item, 1, 0, GFP_KERNEL); + if (retval < 0) goto fail_idr; + user_key = retval; list_add(&item->owner_list, &file_priv->obj_list); mutex_unlock(&dev->struct_mutex); diff --git a/drivers/gpu/drm/via/via_map.c b/drivers/gpu/drm/via/via_map.c index c0f1cc7f5ca9..d0ab3fb32acd 100644 --- a/drivers/gpu/drm/via/via_map.c +++ b/drivers/gpu/drm/via/via_map.c @@ -120,7 +120,6 @@ int via_driver_unload(struct drm_device *dev) { drm_via_private_t *dev_priv = dev->dev_private; - idr_remove_all(&dev_priv->object_idr); idr_destroy(&dev_priv->object_idr); kfree(dev_priv); diff --git a/drivers/gpu/drm/via/via_mm.c b/drivers/gpu/drm/via/via_mm.c index 0d55432e02a2..0ab93ff09873 100644 --- a/drivers/gpu/drm/via/via_mm.c +++ b/drivers/gpu/drm/via/via_mm.c @@ -148,17 +148,10 @@ int via_mem_alloc(struct drm_device *dev, void *data, if (retval) goto fail_alloc; -again: - if (idr_pre_get(&dev_priv->object_idr, GFP_KERNEL) == 0) { - retval = -ENOMEM; - goto fail_idr; - } - - retval = idr_get_new_above(&dev_priv->object_idr, item, 1, &user_key); - if (retval == -EAGAIN) - goto again; - if (retval) + retval = idr_alloc(&dev_priv->object_idr, item, 1, 0, GFP_KERNEL); + if (retval < 0) goto fail_idr; + user_key = retval; list_add(&item->owner_list, &file_priv->obj_list); mutex_unlock(&dev->struct_mutex); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c index e01a17b407b2..c9d067643f01 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c @@ -177,17 +177,16 @@ int vmw_resource_alloc_id(struct vmw_resource *res) BUG_ON(res->id != -1); - do { - if (unlikely(idr_pre_get(idr, GFP_KERNEL) == 0)) - return -ENOMEM; - - write_lock(&dev_priv->resource_lock); - ret = idr_get_new_above(idr, res, 1, &res->id); - write_unlock(&dev_priv->resource_lock); + idr_preload(GFP_KERNEL); + write_lock(&dev_priv->resource_lock); - } while (ret == -EAGAIN); + ret = idr_alloc(idr, res, 1, 0, GFP_NOWAIT); + if (ret >= 0) + res->id = ret; - return ret; + write_unlock(&dev_priv->resource_lock); + idr_preload_end(); + return ret < 0 ? ret : 0; } /** diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c index 66a30f7ac882..795c916cf42a 100644 --- a/drivers/i2c/i2c-core.c +++ b/drivers/i2c/i2c-core.c @@ -935,25 +935,16 @@ out_list: */ int i2c_add_adapter(struct i2c_adapter *adapter) { - int id, res = 0; - -retry: - if (idr_pre_get(&i2c_adapter_idr, GFP_KERNEL) == 0) - return -ENOMEM; + int res; mutex_lock(&core_lock); - /* "above" here means "above or equal to", sigh */ - res = idr_get_new_above(&i2c_adapter_idr, adapter, - __i2c_first_dynamic_bus_num, &id); + res = idr_alloc(&i2c_adapter_idr, adapter, + __i2c_first_dynamic_bus_num, 0, GFP_KERNEL); mutex_unlock(&core_lock); - - if (res < 0) { - if (res == -EAGAIN) - goto retry; + if (res < 0) return res; - } - adapter->nr = id; + adapter->nr = res; return i2c_register_adapter(adapter); } EXPORT_SYMBOL(i2c_add_adapter); @@ -984,33 +975,17 @@ EXPORT_SYMBOL(i2c_add_adapter); int i2c_add_numbered_adapter(struct i2c_adapter *adap) { int id; - int status; if (adap->nr == -1) /* -1 means dynamically assign bus id */ return i2c_add_adapter(adap); - if (adap->nr & ~MAX_IDR_MASK) - return -EINVAL; - -retry: - if (idr_pre_get(&i2c_adapter_idr, GFP_KERNEL) == 0) - return -ENOMEM; mutex_lock(&core_lock); - /* "above" here means "above or equal to", sigh; - * we need the "equal to" result to force the result - */ - status = idr_get_new_above(&i2c_adapter_idr, adap, adap->nr, &id); - if (status == 0 && id != adap->nr) { - status = -EBUSY; - idr_remove(&i2c_adapter_idr, id); - } + id = idr_alloc(&i2c_adapter_idr, adap, adap->nr, adap->nr + 1, + GFP_KERNEL); mutex_unlock(&core_lock); - if (status == -EAGAIN) - goto retry; - - if (status == 0) - status = i2c_register_adapter(adap); - return status; + if (id < 0) + return id == -ENOSPC ? -EBUSY : id; + return 0; } EXPORT_SYMBOL_GPL(i2c_add_numbered_adapter); diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index 394fea2ba1bc..98281fe5ea4b 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -382,20 +382,21 @@ static int cm_init_av_by_path(struct ib_sa_path_rec *path, struct cm_av *av) static int cm_alloc_id(struct cm_id_private *cm_id_priv) { unsigned long flags; - int ret, id; + int id; static int next_id; - do { - spin_lock_irqsave(&cm.lock, flags); - ret = idr_get_new_above(&cm.local_id_table, cm_id_priv, - next_id, &id); - if (!ret) - next_id = ((unsigned) id + 1) & MAX_IDR_MASK; - spin_unlock_irqrestore(&cm.lock, flags); - } while( (ret == -EAGAIN) && idr_pre_get(&cm.local_id_table, GFP_KERNEL) ); + idr_preload(GFP_KERNEL); + spin_lock_irqsave(&cm.lock, flags); + + id = idr_alloc(&cm.local_id_table, cm_id_priv, next_id, 0, GFP_NOWAIT); + if (id >= 0) + next_id = ((unsigned) id + 1) & MAX_IDR_MASK; + + spin_unlock_irqrestore(&cm.lock, flags); + idr_preload_end(); cm_id_priv->id.local_id = (__force __be32)id ^ cm.random_id_operand; - return ret; + return id < 0 ? id : 0; } static void cm_free_id(__be32 local_id) @@ -3844,7 +3845,6 @@ static int __init ib_cm_init(void) cm.remote_sidr_table = RB_ROOT; idr_init(&cm.local_id_table); get_random_bytes(&cm.random_id_operand, sizeof cm.random_id_operand); - idr_pre_get(&cm.local_id_table, GFP_KERNEL); INIT_LIST_HEAD(&cm.timewait_list); ret = class_register(&cm_class); diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index d789eea32168..71c2c7116802 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -2143,33 +2143,23 @@ static int cma_alloc_port(struct idr *ps, struct rdma_id_private *id_priv, unsigned short snum) { struct rdma_bind_list *bind_list; - int port, ret; + int ret; bind_list = kzalloc(sizeof *bind_list, GFP_KERNEL); if (!bind_list) return -ENOMEM; - do { - ret = idr_get_new_above(ps, bind_list, snum, &port); - } while ((ret == -EAGAIN) && idr_pre_get(ps, GFP_KERNEL)); - - if (ret) - goto err1; - - if (port != snum) { - ret = -EADDRNOTAVAIL; - goto err2; - } + ret = idr_alloc(ps, bind_list, snum, snum + 1, GFP_KERNEL); + if (ret < 0) + goto err; bind_list->ps = ps; - bind_list->port = (unsigned short) port; + bind_list->port = (unsigned short)ret; cma_bind_port(bind_list, id_priv); return 0; -err2: - idr_remove(ps, port); -err1: +err: kfree(bind_list); - return ret; + return ret == -ENOSPC ? -EADDRNOTAVAIL : ret; } static int cma_alloc_any_port(struct idr *ps, struct rdma_id_private *id_priv) @@ -2214,10 +2204,9 @@ static int cma_check_port(struct rdma_bind_list *bind_list, { struct rdma_id_private *cur_id; struct sockaddr *addr, *cur_addr; - struct hlist_node *node; addr = (struct sockaddr *) &id_priv->id.route.addr.src_addr; - hlist_for_each_entry(cur_id, node, &bind_list->owners, node) { + hlist_for_each_entry(cur_id, &bind_list->owners, node) { if (id_priv == cur_id) continue; diff --git a/drivers/infiniband/core/fmr_pool.c b/drivers/infiniband/core/fmr_pool.c index 176c8f90f2bb..9f5ad7cc33c8 100644 --- a/drivers/infiniband/core/fmr_pool.c +++ b/drivers/infiniband/core/fmr_pool.c @@ -118,14 +118,13 @@ static inline struct ib_pool_fmr *ib_fmr_cache_lookup(struct ib_fmr_pool *pool, { struct hlist_head *bucket; struct ib_pool_fmr *fmr; - struct hlist_node *pos; if (!pool->cache_bucket) return NULL; bucket = pool->cache_bucket + ib_fmr_hash(*page_list); - hlist_for_each_entry(fmr, pos, bucket, cache_node) + hlist_for_each_entry(fmr, bucket, cache_node) if (io_virtual_address == fmr->io_virtual_address && page_list_len == fmr->page_list_len && !memcmp(page_list, fmr->page_list, diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c index a8905abc56e4..934f45e79e5e 100644 --- a/drivers/infiniband/core/sa_query.c +++ b/drivers/infiniband/core/sa_query.c @@ -611,19 +611,21 @@ static void init_mad(struct ib_sa_mad *mad, struct ib_mad_agent *agent) static int send_mad(struct ib_sa_query *query, int timeout_ms, gfp_t gfp_mask) { + bool preload = gfp_mask & __GFP_WAIT; unsigned long flags; int ret, id; -retry: - if (!idr_pre_get(&query_idr, gfp_mask)) - return -ENOMEM; + if (preload) + idr_preload(gfp_mask); spin_lock_irqsave(&idr_lock, flags); - ret = idr_get_new(&query_idr, query, &id); + + id = idr_alloc(&query_idr, query, 0, 0, GFP_NOWAIT); + spin_unlock_irqrestore(&idr_lock, flags); - if (ret == -EAGAIN) - goto retry; - if (ret) - return ret; + if (preload) + idr_preload_end(); + if (id < 0) + return id; query->mad_buf->timeout_ms = timeout_ms; query->mad_buf->context[0] = query; diff --git a/drivers/infiniband/core/ucm.c b/drivers/infiniband/core/ucm.c index 49b15ac1987e..f2f63933e8a9 100644 --- a/drivers/infiniband/core/ucm.c +++ b/drivers/infiniband/core/ucm.c @@ -176,7 +176,6 @@ static void ib_ucm_cleanup_events(struct ib_ucm_context *ctx) static struct ib_ucm_context *ib_ucm_ctx_alloc(struct ib_ucm_file *file) { struct ib_ucm_context *ctx; - int result; ctx = kzalloc(sizeof *ctx, GFP_KERNEL); if (!ctx) @@ -187,17 +186,10 @@ static struct ib_ucm_context *ib_ucm_ctx_alloc(struct ib_ucm_file *file) ctx->file = file; INIT_LIST_HEAD(&ctx->events); - do { - result = idr_pre_get(&ctx_id_table, GFP_KERNEL); - if (!result) - goto error; - - mutex_lock(&ctx_id_mutex); - result = idr_get_new(&ctx_id_table, ctx, &ctx->id); - mutex_unlock(&ctx_id_mutex); - } while (result == -EAGAIN); - - if (result) + mutex_lock(&ctx_id_mutex); + ctx->id = idr_alloc(&ctx_id_table, ctx, 0, 0, GFP_KERNEL); + mutex_unlock(&ctx_id_mutex); + if (ctx->id < 0) goto error; list_add_tail(&ctx->file_list, &file->ctxs); diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index 2709ff581392..5ca44cd9b00c 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -145,7 +145,6 @@ static void ucma_put_ctx(struct ucma_context *ctx) static struct ucma_context *ucma_alloc_ctx(struct ucma_file *file) { struct ucma_context *ctx; - int ret; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) @@ -156,17 +155,10 @@ static struct ucma_context *ucma_alloc_ctx(struct ucma_file *file) INIT_LIST_HEAD(&ctx->mc_list); ctx->file = file; - do { - ret = idr_pre_get(&ctx_idr, GFP_KERNEL); - if (!ret) - goto error; - - mutex_lock(&mut); - ret = idr_get_new(&ctx_idr, ctx, &ctx->id); - mutex_unlock(&mut); - } while (ret == -EAGAIN); - - if (ret) + mutex_lock(&mut); + ctx->id = idr_alloc(&ctx_idr, ctx, 0, 0, GFP_KERNEL); + mutex_unlock(&mut); + if (ctx->id < 0) goto error; list_add_tail(&ctx->list, &file->ctx_list); @@ -180,23 +172,15 @@ error: static struct ucma_multicast* ucma_alloc_multicast(struct ucma_context *ctx) { struct ucma_multicast *mc; - int ret; mc = kzalloc(sizeof(*mc), GFP_KERNEL); if (!mc) return NULL; - do { - ret = idr_pre_get(&multicast_idr, GFP_KERNEL); - if (!ret) - goto error; - - mutex_lock(&mut); - ret = idr_get_new(&multicast_idr, mc, &mc->id); - mutex_unlock(&mut); - } while (ret == -EAGAIN); - - if (ret) + mutex_lock(&mut); + mc->id = idr_alloc(&multicast_idr, mc, 0, 0, GFP_KERNEL); + mutex_unlock(&mut); + if (mc->id < 0) goto error; mc->ctx = ctx; diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index 0cb0007724a2..83bc309cea5c 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -124,18 +124,17 @@ static int idr_add_uobj(struct idr *idr, struct ib_uobject *uobj) { int ret; -retry: - if (!idr_pre_get(idr, GFP_KERNEL)) - return -ENOMEM; - + idr_preload(GFP_KERNEL); spin_lock(&ib_uverbs_idr_lock); - ret = idr_get_new(idr, uobj, &uobj->id); - spin_unlock(&ib_uverbs_idr_lock); - if (ret == -EAGAIN) - goto retry; + ret = idr_alloc(idr, uobj, 0, 0, GFP_NOWAIT); + if (ret >= 0) + uobj->id = ret; - return ret; + spin_unlock(&ib_uverbs_idr_lock); + idr_preload_end(); + + return ret < 0 ? ret : 0; } void idr_remove_uobj(struct idr *idr, struct ib_uobject *uobj) diff --git a/drivers/infiniband/hw/amso1100/c2_qp.c b/drivers/infiniband/hw/amso1100/c2_qp.c index 28cd5cb51859..0ab826b280b2 100644 --- a/drivers/infiniband/hw/amso1100/c2_qp.c +++ b/drivers/infiniband/hw/amso1100/c2_qp.c @@ -382,14 +382,17 @@ static int c2_alloc_qpn(struct c2_dev *c2dev, struct c2_qp *qp) { int ret; - do { - spin_lock_irq(&c2dev->qp_table.lock); - ret = idr_get_new_above(&c2dev->qp_table.idr, qp, - c2dev->qp_table.last++, &qp->qpn); - spin_unlock_irq(&c2dev->qp_table.lock); - } while ((ret == -EAGAIN) && - idr_pre_get(&c2dev->qp_table.idr, GFP_KERNEL)); - return ret; + idr_preload(GFP_KERNEL); + spin_lock_irq(&c2dev->qp_table.lock); + + ret = idr_alloc(&c2dev->qp_table.idr, qp, c2dev->qp_table.last++, 0, + GFP_NOWAIT); + if (ret >= 0) + qp->qpn = ret; + + spin_unlock_irq(&c2dev->qp_table.lock); + idr_preload_end(); + return ret < 0 ? ret : 0; } static void c2_free_qpn(struct c2_dev *c2dev, int qpn) diff --git a/drivers/infiniband/hw/cxgb3/iwch.h b/drivers/infiniband/hw/cxgb3/iwch.h index a1c44578e039..837862287a29 100644 --- a/drivers/infiniband/hw/cxgb3/iwch.h +++ b/drivers/infiniband/hw/cxgb3/iwch.h @@ -153,19 +153,17 @@ static inline int insert_handle(struct iwch_dev *rhp, struct idr *idr, void *handle, u32 id) { int ret; - int newid; - - do { - if (!idr_pre_get(idr, GFP_KERNEL)) { - return -ENOMEM; - } - spin_lock_irq(&rhp->lock); - ret = idr_get_new_above(idr, handle, id, &newid); - BUG_ON(newid != id); - spin_unlock_irq(&rhp->lock); - } while (ret == -EAGAIN); - - return ret; + + idr_preload(GFP_KERNEL); + spin_lock_irq(&rhp->lock); + + ret = idr_alloc(idr, handle, id, id + 1, GFP_NOWAIT); + + spin_unlock_irq(&rhp->lock); + idr_preload_end(); + + BUG_ON(ret == -ENOSPC); + return ret < 0 ? ret : 0; } static inline void remove_handle(struct iwch_dev *rhp, struct idr *idr, u32 id) diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h index 9c1644fb0259..7f862da54e8e 100644 --- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h +++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h @@ -260,20 +260,21 @@ static inline int _insert_handle(struct c4iw_dev *rhp, struct idr *idr, void *handle, u32 id, int lock) { int ret; - int newid; - do { - if (!idr_pre_get(idr, lock ? GFP_KERNEL : GFP_ATOMIC)) - return -ENOMEM; - if (lock) - spin_lock_irq(&rhp->lock); - ret = idr_get_new_above(idr, handle, id, &newid); - BUG_ON(!ret && newid != id); - if (lock) - spin_unlock_irq(&rhp->lock); - } while (ret == -EAGAIN); - - return ret; + if (lock) { + idr_preload(GFP_KERNEL); + spin_lock_irq(&rhp->lock); + } + + ret = idr_alloc(idr, handle, id, id + 1, GFP_ATOMIC); + + if (lock) { + spin_unlock_irq(&rhp->lock); + idr_preload_end(); + } + + BUG_ON(ret == -ENOSPC); + return ret < 0 ? ret : 0; } static inline int insert_handle(struct c4iw_dev *rhp, struct idr *idr, diff --git a/drivers/infiniband/hw/ehca/ehca_cq.c b/drivers/infiniband/hw/ehca/ehca_cq.c index 8f5290147e8a..212150c25ea0 100644 --- a/drivers/infiniband/hw/ehca/ehca_cq.c +++ b/drivers/infiniband/hw/ehca/ehca_cq.c @@ -128,7 +128,7 @@ struct ib_cq *ehca_create_cq(struct ib_device *device, int cqe, int comp_vector, void *vpage; u32 counter; u64 rpage, cqx_fec, h_ret; - int ipz_rc, ret, i; + int ipz_rc, i; unsigned long flags; if (cqe >= 0xFFFFFFFF - 64 - additional_cqe) @@ -163,32 +163,19 @@ struct ib_cq *ehca_create_cq(struct ib_device *device, int cqe, int comp_vector, adapter_handle = shca->ipz_hca_handle; param.eq_handle = shca->eq.ipz_eq_handle; - do { - if (!idr_pre_get(&ehca_cq_idr, GFP_KERNEL)) { - cq = ERR_PTR(-ENOMEM); - ehca_err(device, "Can't reserve idr nr. device=%p", - device); - goto create_cq_exit1; - } - - write_lock_irqsave(&ehca_cq_idr_lock, flags); - ret = idr_get_new(&ehca_cq_idr, my_cq, &my_cq->token); - write_unlock_irqrestore(&ehca_cq_idr_lock, flags); - } while (ret == -EAGAIN); + idr_preload(GFP_KERNEL); + write_lock_irqsave(&ehca_cq_idr_lock, flags); + my_cq->token = idr_alloc(&ehca_cq_idr, my_cq, 0, 0x2000000, GFP_NOWAIT); + write_unlock_irqrestore(&ehca_cq_idr_lock, flags); + idr_preload_end(); - if (ret) { + if (my_cq->token < 0) { cq = ERR_PTR(-ENOMEM); ehca_err(device, "Can't allocate new idr entry. device=%p", device); goto create_cq_exit1; } - if (my_cq->token > 0x1FFFFFF) { - cq = ERR_PTR(-ENOMEM); - ehca_err(device, "Invalid number of cq. device=%p", device); - goto create_cq_exit2; - } - /* * CQs maximum depth is 4GB-64, but we need additional 20 as buffer * for receiving errors CQEs. diff --git a/drivers/infiniband/hw/ehca/ehca_qp.c b/drivers/infiniband/hw/ehca/ehca_qp.c index 149393915ae5..00d6861a6a18 100644 --- a/drivers/infiniband/hw/ehca/ehca_qp.c +++ b/drivers/infiniband/hw/ehca/ehca_qp.c @@ -636,30 +636,26 @@ static struct ehca_qp *internal_create_qp( my_qp->send_cq = container_of(init_attr->send_cq, struct ehca_cq, ib_cq); - do { - if (!idr_pre_get(&ehca_qp_idr, GFP_KERNEL)) { - ret = -ENOMEM; - ehca_err(pd->device, "Can't reserve idr resources."); - goto create_qp_exit0; - } + idr_preload(GFP_KERNEL); + write_lock_irqsave(&ehca_qp_idr_lock, flags); - write_lock_irqsave(&ehca_qp_idr_lock, flags); - ret = idr_get_new(&ehca_qp_idr, my_qp, &my_qp->token); - write_unlock_irqrestore(&ehca_qp_idr_lock, flags); - } while (ret == -EAGAIN); + ret = idr_alloc(&ehca_qp_idr, my_qp, 0, 0x2000000, GFP_NOWAIT); + if (ret >= 0) + my_qp->token = ret; - if (ret) { - ret = -ENOMEM; - ehca_err(pd->device, "Can't allocate new idr entry."); + write_unlock_irqrestore(&ehca_qp_idr_lock, flags); + idr_preload_end(); + if (ret < 0) { + if (ret == -ENOSPC) { + ret = -EINVAL; + ehca_err(pd->device, "Invalid number of qp"); + } else { + ret = -ENOMEM; + ehca_err(pd->device, "Can't allocate new idr entry."); + } goto create_qp_exit0; } - if (my_qp->token > 0x1FFFFFF) { - ret = -EINVAL; - ehca_err(pd->device, "Invalid number of qp"); - goto create_qp_exit1; - } - if (has_srq) parms.srq_token = my_qp->token; diff --git a/drivers/infiniband/hw/ipath/ipath_driver.c b/drivers/infiniband/hw/ipath/ipath_driver.c index 7b371f545ece..fcdaeea9f7de 100644 --- a/drivers/infiniband/hw/ipath/ipath_driver.c +++ b/drivers/infiniband/hw/ipath/ipath_driver.c @@ -194,11 +194,6 @@ static struct ipath_devdata *ipath_alloc_devdata(struct pci_dev *pdev) struct ipath_devdata *dd; int ret; - if (!idr_pre_get(&unit_table, GFP_KERNEL)) { - dd = ERR_PTR(-ENOMEM); - goto bail; - } - dd = vzalloc(sizeof(*dd)); if (!dd) { dd = ERR_PTR(-ENOMEM); @@ -206,9 +201,10 @@ static struct ipath_devdata *ipath_alloc_devdata(struct pci_dev *pdev) } dd->ipath_unit = -1; + idr_preload(GFP_KERNEL); spin_lock_irqsave(&ipath_devs_lock, flags); - ret = idr_get_new(&unit_table, dd, &dd->ipath_unit); + ret = idr_alloc(&unit_table, dd, 0, 0, GFP_KERNEL); if (ret < 0) { printk(KERN_ERR IPATH_DRV_NAME ": Could not allocate unit ID: error %d\n", -ret); @@ -216,6 +212,7 @@ static struct ipath_devdata *ipath_alloc_devdata(struct pci_dev *pdev) dd = ERR_PTR(ret); goto bail_unlock; } + dd->ipath_unit = ret; dd->pcidev = pdev; pci_set_drvdata(pdev, dd); @@ -224,7 +221,7 @@ static struct ipath_devdata *ipath_alloc_devdata(struct pci_dev *pdev) bail_unlock: spin_unlock_irqrestore(&ipath_devs_lock, flags); - + idr_preload_end(); bail: return dd; } @@ -2503,11 +2500,6 @@ static int __init infinipath_init(void) * the PCI subsystem. */ idr_init(&unit_table); - if (!idr_pre_get(&unit_table, GFP_KERNEL)) { - printk(KERN_ERR IPATH_DRV_NAME ": idr_pre_get() failed\n"); - ret = -ENOMEM; - goto bail; - } ret = pci_register_driver(&ipath_driver); if (ret < 0) { diff --git a/drivers/infiniband/hw/ipath/ipath_file_ops.c b/drivers/infiniband/hw/ipath/ipath_file_ops.c index 3eb7e454849b..62edc414e162 100644 --- a/drivers/infiniband/hw/ipath/ipath_file_ops.c +++ b/drivers/infiniband/hw/ipath/ipath_file_ops.c @@ -40,6 +40,7 @@ #include <linux/slab.h> #include <linux/highmem.h> #include <linux/io.h> +#include <linux/aio.h> #include <linux/jiffies.h> #include <linux/cpu.h> #include <asm/pgtable.h> diff --git a/drivers/infiniband/hw/mlx4/cm.c b/drivers/infiniband/hw/mlx4/cm.c index dbc99d41605c..80e59ed864b3 100644 --- a/drivers/infiniband/hw/mlx4/cm.c +++ b/drivers/infiniband/hw/mlx4/cm.c @@ -203,7 +203,7 @@ static void sl_id_map_add(struct ib_device *ibdev, struct id_map_entry *new) static struct id_map_entry * id_map_alloc(struct ib_device *ibdev, int slave_id, u32 sl_cm_id) { - int ret, id; + int ret; static int next_id; struct id_map_entry *ent; struct mlx4_ib_sriov *sriov = &to_mdev(ibdev)->sriov; @@ -220,25 +220,23 @@ id_map_alloc(struct ib_device *ibdev, int slave_id, u32 sl_cm_id) ent->dev = to_mdev(ibdev); INIT_DELAYED_WORK(&ent->timeout, id_map_ent_timeout); - do { - spin_lock(&to_mdev(ibdev)->sriov.id_map_lock); - ret = idr_get_new_above(&sriov->pv_id_table, ent, - next_id, &id); - if (!ret) { - next_id = ((unsigned) id + 1) & MAX_IDR_MASK; - ent->pv_cm_id = (u32)id; - sl_id_map_add(ibdev, ent); - } + idr_preload(GFP_KERNEL); + spin_lock(&to_mdev(ibdev)->sriov.id_map_lock); - spin_unlock(&sriov->id_map_lock); - } while (ret == -EAGAIN && idr_pre_get(&sriov->pv_id_table, GFP_KERNEL)); - /*the function idr_get_new_above can return -ENOSPC, so don't insert in that case.*/ - if (!ret) { - spin_lock(&sriov->id_map_lock); + ret = idr_alloc(&sriov->pv_id_table, ent, next_id, 0, GFP_NOWAIT); + if (ret >= 0) { + next_id = ((unsigned)ret + 1) & MAX_IDR_MASK; + ent->pv_cm_id = (u32)ret; + sl_id_map_add(ibdev, ent); list_add_tail(&ent->list, &sriov->cm_list); - spin_unlock(&sriov->id_map_lock); - return ent; } + + spin_unlock(&sriov->id_map_lock); + idr_preload_end(); + + if (ret >= 0) + return ent; + /*error flow*/ kfree(ent); mlx4_ib_warn(ibdev, "No more space in the idr (err:0x%x)\n", ret); diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c index c4e0131f1b57..48928c8e7774 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c @@ -51,18 +51,6 @@ static DEFINE_IDR(ocrdma_dev_id); static union ib_gid ocrdma_zero_sgid; -static int ocrdma_get_instance(void) -{ - int instance = 0; - - /* Assign an unused number */ - if (!idr_pre_get(&ocrdma_dev_id, GFP_KERNEL)) - return -1; - if (idr_get_new(&ocrdma_dev_id, NULL, &instance)) - return -1; - return instance; -} - void ocrdma_get_guid(struct ocrdma_dev *dev, u8 *guid) { u8 mac_addr[6]; @@ -416,7 +404,7 @@ static struct ocrdma_dev *ocrdma_add(struct be_dev_info *dev_info) goto idr_err; memcpy(&dev->nic_info, dev_info, sizeof(*dev_info)); - dev->id = ocrdma_get_instance(); + dev->id = idr_alloc(&ocrdma_dev_id, NULL, 0, 0, GFP_KERNEL); if (dev->id < 0) goto idr_err; diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c index 959a5c4ff812..488300c3c330 100644 --- a/drivers/infiniband/hw/qib/qib_file_ops.c +++ b/drivers/infiniband/hw/qib/qib_file_ops.c @@ -39,7 +39,7 @@ #include <linux/vmalloc.h> #include <linux/highmem.h> #include <linux/io.h> -#include <linux/uio.h> +#include <linux/aio.h> #include <linux/jiffies.h> #include <asm/pgtable.h> #include <linux/delay.h> diff --git a/drivers/infiniband/hw/qib/qib_init.c b/drivers/infiniband/hw/qib/qib_init.c index ddf066d9abb6..50e33aa0b4e3 100644 --- a/drivers/infiniband/hw/qib/qib_init.c +++ b/drivers/infiniband/hw/qib/qib_init.c @@ -1060,22 +1060,23 @@ struct qib_devdata *qib_alloc_devdata(struct pci_dev *pdev, size_t extra) struct qib_devdata *dd; int ret; - if (!idr_pre_get(&qib_unit_table, GFP_KERNEL)) { - dd = ERR_PTR(-ENOMEM); - goto bail; - } - dd = (struct qib_devdata *) ib_alloc_device(sizeof(*dd) + extra); if (!dd) { dd = ERR_PTR(-ENOMEM); goto bail; } + idr_preload(GFP_KERNEL); spin_lock_irqsave(&qib_devs_lock, flags); - ret = idr_get_new(&qib_unit_table, dd, &dd->unit); - if (ret >= 0) + + ret = idr_alloc(&qib_unit_table, dd, 0, 0, GFP_NOWAIT); + if (ret >= 0) { + dd->unit = ret; list_add(&dd->list, &qib_dev_list); + } + spin_unlock_irqrestore(&qib_devs_lock, flags); + idr_preload_end(); if (ret < 0) { qib_early_err(&pdev->dev, @@ -1180,11 +1181,6 @@ static int __init qlogic_ib_init(void) * the PCI subsystem. */ idr_init(&qib_unit_table); - if (!idr_pre_get(&qib_unit_table, GFP_KERNEL)) { - pr_err("idr_pre_get() failed\n"); - ret = -ENOMEM; - goto bail_cq_wq; - } ret = pci_register_driver(&qib_driver); if (ret < 0) { @@ -1199,7 +1195,6 @@ static int __init qlogic_ib_init(void) bail_unit: idr_destroy(&qib_unit_table); -bail_cq_wq: destroy_workqueue(qib_cq_wq); bail_dev: qib_dev_cleanup(); diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c index abe2d699b6f3..8b07f83d48ad 100644 --- a/drivers/isdn/mISDN/socket.c +++ b/drivers/isdn/mISDN/socket.c @@ -483,7 +483,6 @@ data_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_len) { struct sockaddr_mISDN *maddr = (struct sockaddr_mISDN *) addr; struct sock *sk = sock->sk; - struct hlist_node *node; struct sock *csk; int err = 0; @@ -508,7 +507,7 @@ data_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_len) if (sk->sk_protocol < ISDN_P_B_START) { read_lock_bh(&data_sockets.lock); - sk_for_each(csk, node, &data_sockets.head) { + sk_for_each(csk, &data_sockets.head) { if (sk == csk) continue; if (_pms(csk)->dev != _pms(sk)->dev) diff --git a/drivers/isdn/mISDN/stack.c b/drivers/isdn/mISDN/stack.c index deda591f70b9..9cb4b621fbc3 100644 --- a/drivers/isdn/mISDN/stack.c +++ b/drivers/isdn/mISDN/stack.c @@ -64,12 +64,11 @@ unlock: static void send_socklist(struct mISDN_sock_list *sl, struct sk_buff *skb) { - struct hlist_node *node; struct sock *sk; struct sk_buff *cskb = NULL; read_lock(&sl->lock); - sk_for_each(sk, node, &sl->head) { + sk_for_each(sk, &sl->head) { if (sk->sk_state != MISDN_BOUND) continue; if (!cskb) diff --git a/drivers/leds/leds-ot200.c b/drivers/leds/leds-ot200.c index ee14662ed5ce..98cae529373f 100644 --- a/drivers/leds/leds-ot200.c +++ b/drivers/leds/leds-ot200.c @@ -47,37 +47,37 @@ static struct ot200_led leds[] = { { .name = "led_1", .port = 0x49, - .mask = BIT(7), + .mask = BIT(6), }, { .name = "led_2", .port = 0x49, - .mask = BIT(6), + .mask = BIT(5), }, { .name = "led_3", .port = 0x49, - .mask = BIT(5), + .mask = BIT(4), }, { .name = "led_4", .port = 0x49, - .mask = BIT(4), + .mask = BIT(3), }, { .name = "led_5", .port = 0x49, - .mask = BIT(3), + .mask = BIT(2), }, { .name = "led_6", .port = 0x49, - .mask = BIT(2), + .mask = BIT(1), }, { .name = "led_7", .port = 0x49, - .mask = BIT(1), + .mask = BIT(0), } }; diff --git a/drivers/md/dm-bio-prison.c b/drivers/md/dm-bio-prison.c index 4d670bbe963c..144067c95aba 100644 --- a/drivers/md/dm-bio-prison.c +++ b/drivers/md/dm-bio-prison.c @@ -111,9 +111,8 @@ static struct dm_bio_prison_cell *__search_bucket(struct hlist_head *bucket, struct dm_cell_key *key) { struct dm_bio_prison_cell *cell; - struct hlist_node *tmp; - hlist_for_each_entry(cell, tmp, bucket, list) + hlist_for_each_entry(cell, bucket, list) if (keys_equal(&cell->key, key)) return cell; diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index f12fdbcc4f76..3c955e10a618 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -859,9 +859,8 @@ static void __check_watermark(struct dm_bufio_client *c) static struct dm_buffer *__find(struct dm_bufio_client *c, sector_t block) { struct dm_buffer *b; - struct hlist_node *hn; - hlist_for_each_entry(b, hn, &c->cache_hash[DM_BUFIO_HASH(block)], + hlist_for_each_entry(b, &c->cache_hash[DM_BUFIO_HASH(block)], hash_list) { dm_bufio_cond_resched(); if (b->block == block) diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index dcbd4f6957ce..c3678650a607 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -227,12 +227,11 @@ static void stop_tracking_chunk(struct dm_snapshot *s, struct bio *bio) static int __chunk_is_tracked(struct dm_snapshot *s, chunk_t chunk) { struct dm_snap_tracked_chunk *c; - struct hlist_node *hn; int found = 0; spin_lock_irq(&s->tracked_chunk_lock); - hlist_for_each_entry(c, hn, + hlist_for_each_entry(c, &s->tracked_chunk_hash[DM_TRACKED_CHUNK_HASH(chunk)], node) { if (c->chunk == chunk) { found = 1; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 5b7bc58a5ea3..ac74b81bf1d4 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -318,7 +318,6 @@ static void __exit dm_exit(void) /* * Should be empty by this point. */ - idr_remove_all(&_minor_idr); idr_destroy(&_minor_idr); } @@ -711,7 +710,7 @@ static void end_clone_bio(struct bio *clone, int error) * Do not use blk_end_request() here, because it may complete * the original request before the clone, and break the ordering. */ - blk_update_request(tio->orig, 0, nr_bytes); + blk_update_request(tio->orig, 0, nr_bytes, NULL); } /* @@ -1802,62 +1801,38 @@ static void free_minor(int minor) */ static int specific_minor(int minor) { - int r, m; + int r; if (minor >= (1 << MINORBITS)) return -EINVAL; - r = idr_pre_get(&_minor_idr, GFP_KERNEL); - if (!r) - return -ENOMEM; - + idr_preload(GFP_KERNEL); spin_lock(&_minor_lock); - if (idr_find(&_minor_idr, minor)) { - r = -EBUSY; - goto out; - } - - r = idr_get_new_above(&_minor_idr, MINOR_ALLOCED, minor, &m); - if (r) - goto out; + r = idr_alloc(&_minor_idr, MINOR_ALLOCED, minor, minor + 1, GFP_NOWAIT); - if (m != minor) { - idr_remove(&_minor_idr, m); - r = -EBUSY; - goto out; - } - -out: spin_unlock(&_minor_lock); - return r; + idr_preload_end(); + if (r < 0) + return r == -ENOSPC ? -EBUSY : r; + return 0; } static int next_free_minor(int *minor) { - int r, m; - - r = idr_pre_get(&_minor_idr, GFP_KERNEL); - if (!r) - return -ENOMEM; + int r; + idr_preload(GFP_KERNEL); spin_lock(&_minor_lock); - r = idr_get_new(&_minor_idr, MINOR_ALLOCED, &m); - if (r) - goto out; - - if (m >= (1 << MINORBITS)) { - idr_remove(&_minor_idr, m); - r = -ENOSPC; - goto out; - } - - *minor = m; + r = idr_alloc(&_minor_idr, MINOR_ALLOCED, 0, 1 << MINORBITS, GFP_NOWAIT); -out: spin_unlock(&_minor_lock); - return r; + idr_preload_end(); + if (r < 0) + return r; + *minor = r; + return 0; } static const struct block_device_operations dm_blk_dops; diff --git a/drivers/md/persistent-data/dm-transaction-manager.c b/drivers/md/persistent-data/dm-transaction-manager.c index d247a35da3c6..81da1a26042e 100644 --- a/drivers/md/persistent-data/dm-transaction-manager.c +++ b/drivers/md/persistent-data/dm-transaction-manager.c @@ -25,8 +25,8 @@ struct shadow_info { /* * It would be nice if we scaled with the size of transaction. */ -#define HASH_SIZE 256 -#define HASH_MASK (HASH_SIZE - 1) +#define DM_HASH_SIZE 256 +#define DM_HASH_MASK (DM_HASH_SIZE - 1) struct dm_transaction_manager { int is_clone; @@ -36,7 +36,7 @@ struct dm_transaction_manager { struct dm_space_map *sm; spinlock_t lock; - struct hlist_head buckets[HASH_SIZE]; + struct hlist_head buckets[DM_HASH_SIZE]; }; /*----------------------------------------------------------------*/ @@ -44,12 +44,11 @@ struct dm_transaction_manager { static int is_shadow(struct dm_transaction_manager *tm, dm_block_t b) { int r = 0; - unsigned bucket = dm_hash_block(b, HASH_MASK); + unsigned bucket = dm_hash_block(b, DM_HASH_MASK); struct shadow_info *si; - struct hlist_node *n; spin_lock(&tm->lock); - hlist_for_each_entry(si, n, tm->buckets + bucket, hlist) + hlist_for_each_entry(si, tm->buckets + bucket, hlist) if (si->where == b) { r = 1; break; @@ -71,7 +70,7 @@ static void insert_shadow(struct dm_transaction_manager *tm, dm_block_t b) si = kmalloc(sizeof(*si), GFP_NOIO); if (si) { si->where = b; - bucket = dm_hash_block(b, HASH_MASK); + bucket = dm_hash_block(b, DM_HASH_MASK); spin_lock(&tm->lock); hlist_add_head(&si->hlist, tm->buckets + bucket); spin_unlock(&tm->lock); @@ -81,14 +80,14 @@ static void insert_shadow(struct dm_transaction_manager *tm, dm_block_t b) static void wipe_shadow_table(struct dm_transaction_manager *tm) { struct shadow_info *si; - struct hlist_node *n, *tmp; + struct hlist_node *tmp; struct hlist_head *bucket; int i; spin_lock(&tm->lock); - for (i = 0; i < HASH_SIZE; i++) { + for (i = 0; i < DM_HASH_SIZE; i++) { bucket = tm->buckets + i; - hlist_for_each_entry_safe(si, n, tmp, bucket, hlist) + hlist_for_each_entry_safe(si, tmp, bucket, hlist) kfree(si); INIT_HLIST_HEAD(bucket); @@ -115,7 +114,7 @@ static struct dm_transaction_manager *dm_tm_create(struct dm_block_manager *bm, tm->sm = sm; spin_lock_init(&tm->lock); - for (i = 0; i < HASH_SIZE; i++) + for (i = 0; i < DM_HASH_SIZE; i++) INIT_HLIST_HEAD(tm->buckets + i); return tm; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 77c4a585fb82..96ea6200b301 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -389,10 +389,9 @@ static struct stripe_head *__find_stripe(struct r5conf *conf, sector_t sector, short generation) { struct stripe_head *sh; - struct hlist_node *hn; pr_debug("__find_stripe, sector %llu\n", (unsigned long long)sector); - hlist_for_each_entry(sh, hn, stripe_hash(conf, sector), hash) + hlist_for_each_entry(sh, stripe_hash(conf, sector), hash) if (sh->sector == sector && sh->generation == generation) return sh; pr_debug("__stripe %llu not in cache\n", (unsigned long long)sector); diff --git a/drivers/memstick/core/memstick.c b/drivers/memstick/core/memstick.c index 56ff19cdc2ad..ffcb10ac4341 100644 --- a/drivers/memstick/core/memstick.c +++ b/drivers/memstick/core/memstick.c @@ -512,18 +512,17 @@ int memstick_add_host(struct memstick_host *host) { int rc; - while (1) { - if (!idr_pre_get(&memstick_host_idr, GFP_KERNEL)) - return -ENOMEM; + idr_preload(GFP_KERNEL); + spin_lock(&memstick_host_lock); - spin_lock(&memstick_host_lock); - rc = idr_get_new(&memstick_host_idr, host, &host->id); - spin_unlock(&memstick_host_lock); - if (!rc) - break; - else if (rc != -EAGAIN) - return rc; - } + rc = idr_alloc(&memstick_host_idr, host, 0, 0, GFP_NOWAIT); + if (rc >= 0) + host->id = rc; + + spin_unlock(&memstick_host_lock); + idr_preload_end(); + if (rc < 0) + return rc; dev_set_name(&host->dev, "memstick%u", host->id); diff --git a/drivers/memstick/core/mspro_block.c b/drivers/memstick/core/mspro_block.c index 9729b92fbfdd..f12b78dbce04 100644 --- a/drivers/memstick/core/mspro_block.c +++ b/drivers/memstick/core/mspro_block.c @@ -1213,21 +1213,10 @@ static int mspro_block_init_disk(struct memstick_dev *card) msb->page_size = be16_to_cpu(sys_info->unit_size); mutex_lock(&mspro_block_disk_lock); - if (!idr_pre_get(&mspro_block_disk_idr, GFP_KERNEL)) { - mutex_unlock(&mspro_block_disk_lock); - return -ENOMEM; - } - - rc = idr_get_new(&mspro_block_disk_idr, card, &disk_id); + disk_id = idr_alloc(&mspro_block_disk_idr, card, 0, 256, GFP_KERNEL); mutex_unlock(&mspro_block_disk_lock); - - if (rc) - return rc; - - if ((disk_id << MSPRO_BLOCK_PART_SHIFT) > 255) { - rc = -ENOSPC; - goto out_release_id; - } + if (disk_id < 0) + return disk_id; msb->disk = alloc_disk(1 << MSPRO_BLOCK_PART_SHIFT); if (!msb->disk) { diff --git a/drivers/mfd/rtsx_pcr.c b/drivers/mfd/rtsx_pcr.c index 822237e322ba..45e97b443cd4 100644 --- a/drivers/mfd/rtsx_pcr.c +++ b/drivers/mfd/rtsx_pcr.c @@ -1061,15 +1061,14 @@ static int rtsx_pci_probe(struct pci_dev *pcidev, } handle->pcr = pcr; - if (!idr_pre_get(&rtsx_pci_idr, GFP_KERNEL)) { - ret = -ENOMEM; - goto free_handle; - } - + idr_preload(GFP_KERNEL); spin_lock(&rtsx_pci_lock); - ret = idr_get_new(&rtsx_pci_idr, pcr, &pcr->id); + ret = idr_alloc(&rtsx_pci_idr, pcr, 0, 0, GFP_NOWAIT); + if (ret >= 0) + pcr->id = ret; spin_unlock(&rtsx_pci_lock); - if (ret) + idr_preload_end(); + if (ret < 0) goto free_handle; pcr->pci = pcidev; diff --git a/drivers/misc/c2port/core.c b/drivers/misc/c2port/core.c index f428d86bfc10..f32550a74bdd 100644 --- a/drivers/misc/c2port/core.c +++ b/drivers/misc/c2port/core.c @@ -885,7 +885,7 @@ struct c2port_device *c2port_device_register(char *name, struct c2port_ops *ops, void *devdata) { struct c2port_device *c2dev; - int id, ret; + int ret; if (unlikely(!ops) || unlikely(!ops->access) || \ unlikely(!ops->c2d_dir) || unlikely(!ops->c2ck_set) || \ @@ -897,22 +897,18 @@ struct c2port_device *c2port_device_register(char *name, if (unlikely(!c2dev)) return ERR_PTR(-ENOMEM); - ret = idr_pre_get(&c2port_idr, GFP_KERNEL); - if (!ret) { - ret = -ENOMEM; - goto error_idr_get_new; - } - + idr_preload(GFP_KERNEL); spin_lock_irq(&c2port_idr_lock); - ret = idr_get_new(&c2port_idr, c2dev, &id); + ret = idr_alloc(&c2port_idr, c2dev, 0, 0, GFP_NOWAIT); spin_unlock_irq(&c2port_idr_lock); + idr_preload_end(); if (ret < 0) - goto error_idr_get_new; - c2dev->id = id; + goto error_idr_alloc; + c2dev->id = ret; c2dev->dev = device_create(c2port_class, NULL, 0, c2dev, - "c2port%d", id); + "c2port%d", c2dev->id); if (unlikely(IS_ERR(c2dev->dev))) { ret = PTR_ERR(c2dev->dev); goto error_device_create; @@ -946,10 +942,10 @@ error_device_create_bin_file: error_device_create: spin_lock_irq(&c2port_idr_lock); - idr_remove(&c2port_idr, id); + idr_remove(&c2port_idr, c2dev->id); spin_unlock_irq(&c2port_idr_lock); -error_idr_get_new: +error_idr_alloc: kfree(c2dev); return ERR_PTR(ret); diff --git a/drivers/misc/sgi-gru/grutlbpurge.c b/drivers/misc/sgi-gru/grutlbpurge.c index 240a6d361665..2129274ef7ab 100644 --- a/drivers/misc/sgi-gru/grutlbpurge.c +++ b/drivers/misc/sgi-gru/grutlbpurge.c @@ -280,11 +280,10 @@ static struct mmu_notifier *mmu_find_ops(struct mm_struct *mm, const struct mmu_notifier_ops *ops) { struct mmu_notifier *mn, *gru_mn = NULL; - struct hlist_node *n; if (mm->mmu_notifier_mm) { rcu_read_lock(); - hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, + hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) if (mn->ops == ops) { gru_mn = mn; diff --git a/drivers/misc/tifm_core.c b/drivers/misc/tifm_core.c index 0bd5349b0422..0ab7c922212c 100644 --- a/drivers/misc/tifm_core.c +++ b/drivers/misc/tifm_core.c @@ -196,13 +196,14 @@ int tifm_add_adapter(struct tifm_adapter *fm) { int rc; - if (!idr_pre_get(&tifm_adapter_idr, GFP_KERNEL)) - return -ENOMEM; - + idr_preload(GFP_KERNEL); spin_lock(&tifm_adapter_lock); - rc = idr_get_new(&tifm_adapter_idr, fm, &fm->id); + rc = idr_alloc(&tifm_adapter_idr, fm, 0, 0, GFP_NOWAIT); + if (rc >= 0) + fm->id = rc; spin_unlock(&tifm_adapter_lock); - if (rc) + idr_preload_end(); + if (rc < 0) return rc; dev_set_name(&fm->dev, "tifm%u", fm->id); diff --git a/drivers/misc/vmw_vmci/vmci_doorbell.c b/drivers/misc/vmw_vmci/vmci_doorbell.c index c3e8397f62ed..a8cee33ae8d2 100644 --- a/drivers/misc/vmw_vmci/vmci_doorbell.c +++ b/drivers/misc/vmw_vmci/vmci_doorbell.c @@ -127,9 +127,8 @@ static struct dbell_entry *dbell_index_table_find(u32 idx) { u32 bucket = VMCI_DOORBELL_HASH(idx); struct dbell_entry *dbell; - struct hlist_node *node; - hlist_for_each_entry(dbell, node, &vmci_doorbell_it.entries[bucket], + hlist_for_each_entry(dbell, &vmci_doorbell_it.entries[bucket], node) { if (idx == dbell->idx) return dbell; @@ -359,12 +358,10 @@ static void dbell_fire_entries(u32 notify_idx) { u32 bucket = VMCI_DOORBELL_HASH(notify_idx); struct dbell_entry *dbell; - struct hlist_node *node; spin_lock_bh(&vmci_doorbell_it.lock); - hlist_for_each_entry(dbell, node, - &vmci_doorbell_it.entries[bucket], node) { + hlist_for_each_entry(dbell, &vmci_doorbell_it.entries[bucket], node) { if (dbell->idx == notify_idx && atomic_read(&dbell->active) == 1) { if (dbell->run_delayed) { diff --git a/drivers/misc/vmw_vmci/vmci_resource.c b/drivers/misc/vmw_vmci/vmci_resource.c index a196f84a4fd2..9a53a30de445 100644 --- a/drivers/misc/vmw_vmci/vmci_resource.c +++ b/drivers/misc/vmw_vmci/vmci_resource.c @@ -46,11 +46,10 @@ static struct vmci_resource *vmci_resource_lookup(struct vmci_handle handle, enum vmci_resource_type type) { struct vmci_resource *r, *resource = NULL; - struct hlist_node *node; unsigned int idx = vmci_resource_hash(handle); rcu_read_lock(); - hlist_for_each_entry_rcu(r, node, + hlist_for_each_entry_rcu(r, &vmci_resource_table.entries[idx], node) { u32 cid = r->handle.context; u32 rid = r->handle.resource; @@ -146,12 +145,11 @@ void vmci_resource_remove(struct vmci_resource *resource) struct vmci_handle handle = resource->handle; unsigned int idx = vmci_resource_hash(handle); struct vmci_resource *r; - struct hlist_node *node; /* Remove resource from hash table. */ spin_lock(&vmci_resource_table.lock); - hlist_for_each_entry(r, node, &vmci_resource_table.entries[idx], node) { + hlist_for_each_entry(r, &vmci_resource_table.entries[idx], node) { if (vmci_handle_is_equal(r->handle, resource->handle)) { hlist_del_init_rcu(&r->node); break; diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c index ee2e16b17017..1117de7c3410 100644 --- a/drivers/mmc/core/host.c +++ b/drivers/mmc/core/host.c @@ -306,19 +306,20 @@ struct mmc_host *mmc_alloc_host(int extra, struct device *dev) int err; struct mmc_host *host; - if (!idr_pre_get(&mmc_host_idr, GFP_KERNEL)) - return NULL; - host = kzalloc(sizeof(struct mmc_host) + extra, GFP_KERNEL); if (!host) return NULL; /* scanning will be enabled when we're ready */ host->rescan_disable = 1; + idr_preload(GFP_KERNEL); spin_lock(&mmc_host_lock); - err = idr_get_new(&mmc_host_idr, host, &host->index); + err = idr_alloc(&mmc_host_idr, host, 0, 0, GFP_NOWAIT); + if (err >= 0) + host->index = err; spin_unlock(&mmc_host_lock); - if (err) + idr_preload_end(); + if (err < 0) goto free; dev_set_name(&host->class_dev, "mmc%d", host->index); diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c index ec794a72975d..61d5f56473e1 100644 --- a/drivers/mtd/mtdcore.c +++ b/drivers/mtd/mtdcore.c @@ -349,13 +349,8 @@ int add_mtd_device(struct mtd_info *mtd) BUG_ON(mtd->writesize == 0); mutex_lock(&mtd_table_mutex); - do { - if (!idr_pre_get(&mtd_idr, GFP_KERNEL)) - goto fail_locked; - error = idr_get_new(&mtd_idr, mtd, &i); - } while (error == -EAGAIN); - - if (error) + i = idr_alloc(&mtd_idr, mtd, 0, 0, GFP_KERNEL); + if (i < 0) goto fail_locked; mtd->index = i; diff --git a/drivers/mtd/tests/mtd_nandecctest.c b/drivers/mtd/tests/mtd_nandecctest.c index 5015d10591d9..70106607c247 100644 --- a/drivers/mtd/tests/mtd_nandecctest.c +++ b/drivers/mtd/tests/mtd_nandecctest.c @@ -256,7 +256,7 @@ static int nand_ecc_test_run(const size_t size) goto error; } - get_random_bytes(correct_data, size); + prandom_bytes(correct_data, size); __nand_calculate_ecc(correct_data, size, correct_ecc); for (i = 0; i < ARRAY_SIZE(nand_ecc_test); i++) { diff --git a/drivers/mtd/tests/mtd_oobtest.c b/drivers/mtd/tests/mtd_oobtest.c index e827fa8cd844..3e24b379ffa4 100644 --- a/drivers/mtd/tests/mtd_oobtest.c +++ b/drivers/mtd/tests/mtd_oobtest.c @@ -29,6 +29,7 @@ #include <linux/mtd/mtd.h> #include <linux/slab.h> #include <linux/sched.h> +#include <linux/random.h> static int dev = -EINVAL; module_param(dev, int, S_IRUGO); @@ -46,26 +47,7 @@ static int use_offset; static int use_len; static int use_len_max; static int vary_offset; -static unsigned long next = 1; - -static inline unsigned int simple_rand(void) -{ - next = next * 1103515245 + 12345; - return (unsigned int)((next / 65536) % 32768); -} - -static inline void simple_srand(unsigned long seed) -{ - next = seed; -} - -static void set_random_data(unsigned char *buf, size_t len) -{ - size_t i; - - for (i = 0; i < len; ++i) - buf[i] = simple_rand(); -} +static struct rnd_state rnd_state; static int erase_eraseblock(int ebnum) { @@ -129,7 +111,7 @@ static int write_eraseblock(int ebnum) loff_t addr = ebnum * mtd->erasesize; for (i = 0; i < pgcnt; ++i, addr += mtd->writesize) { - set_random_data(writebuf, use_len); + prandom_bytes_state(&rnd_state, writebuf, use_len); ops.mode = MTD_OPS_AUTO_OOB; ops.len = 0; ops.retlen = 0; @@ -182,7 +164,7 @@ static int verify_eraseblock(int ebnum) loff_t addr = ebnum * mtd->erasesize; for (i = 0; i < pgcnt; ++i, addr += mtd->writesize) { - set_random_data(writebuf, use_len); + prandom_bytes_state(&rnd_state, writebuf, use_len); ops.mode = MTD_OPS_AUTO_OOB; ops.len = 0; ops.retlen = 0; @@ -273,7 +255,7 @@ static int verify_eraseblock_in_one_go(int ebnum) loff_t addr = ebnum * mtd->erasesize; size_t len = mtd->ecclayout->oobavail * pgcnt; - set_random_data(writebuf, len); + prandom_bytes_state(&rnd_state, writebuf, len); ops.mode = MTD_OPS_AUTO_OOB; ops.len = 0; ops.retlen = 0; @@ -424,12 +406,12 @@ static int __init mtd_oobtest_init(void) if (err) goto out; - simple_srand(1); + prandom_seed_state(&rnd_state, 1); err = write_whole_device(); if (err) goto out; - simple_srand(1); + prandom_seed_state(&rnd_state, 1); err = verify_all_eraseblocks(); if (err) goto out; @@ -444,13 +426,13 @@ static int __init mtd_oobtest_init(void) if (err) goto out; - simple_srand(3); + prandom_seed_state(&rnd_state, 3); err = write_whole_device(); if (err) goto out; /* Check all eraseblocks */ - simple_srand(3); + prandom_seed_state(&rnd_state, 3); pr_info("verifying all eraseblocks\n"); for (i = 0; i < ebcnt; ++i) { if (bbt[i]) @@ -479,7 +461,7 @@ static int __init mtd_oobtest_init(void) use_len = mtd->ecclayout->oobavail; use_len_max = mtd->ecclayout->oobavail; vary_offset = 1; - simple_srand(5); + prandom_seed_state(&rnd_state, 5); err = write_whole_device(); if (err) @@ -490,7 +472,7 @@ static int __init mtd_oobtest_init(void) use_len = mtd->ecclayout->oobavail; use_len_max = mtd->ecclayout->oobavail; vary_offset = 1; - simple_srand(5); + prandom_seed_state(&rnd_state, 5); err = verify_all_eraseblocks(); if (err) goto out; @@ -649,7 +631,7 @@ static int __init mtd_oobtest_init(void) goto out; /* Write all eraseblocks */ - simple_srand(11); + prandom_seed_state(&rnd_state, 11); pr_info("writing OOBs of whole device\n"); for (i = 0; i < ebcnt - 1; ++i) { int cnt = 2; @@ -659,7 +641,7 @@ static int __init mtd_oobtest_init(void) continue; addr = (i + 1) * mtd->erasesize - mtd->writesize; for (pg = 0; pg < cnt; ++pg) { - set_random_data(writebuf, sz); + prandom_bytes_state(&rnd_state, writebuf, sz); ops.mode = MTD_OPS_AUTO_OOB; ops.len = 0; ops.retlen = 0; @@ -680,12 +662,13 @@ static int __init mtd_oobtest_init(void) pr_info("written %u eraseblocks\n", i); /* Check all eraseblocks */ - simple_srand(11); + prandom_seed_state(&rnd_state, 11); pr_info("verifying all eraseblocks\n"); for (i = 0; i < ebcnt - 1; ++i) { if (bbt[i] || bbt[i + 1]) continue; - set_random_data(writebuf, mtd->ecclayout->oobavail * 2); + prandom_bytes_state(&rnd_state, writebuf, + mtd->ecclayout->oobavail * 2); addr = (i + 1) * mtd->erasesize - mtd->writesize; ops.mode = MTD_OPS_AUTO_OOB; ops.len = 0; diff --git a/drivers/mtd/tests/mtd_pagetest.c b/drivers/mtd/tests/mtd_pagetest.c index f93a76f88113..0c1140b6c286 100644 --- a/drivers/mtd/tests/mtd_pagetest.c +++ b/drivers/mtd/tests/mtd_pagetest.c @@ -29,6 +29,7 @@ #include <linux/mtd/mtd.h> #include <linux/slab.h> #include <linux/sched.h> +#include <linux/random.h> static int dev = -EINVAL; module_param(dev, int, S_IRUGO); @@ -45,26 +46,7 @@ static int bufsize; static int ebcnt; static int pgcnt; static int errcnt; -static unsigned long next = 1; - -static inline unsigned int simple_rand(void) -{ - next = next * 1103515245 + 12345; - return (unsigned int)((next / 65536) % 32768); -} - -static inline void simple_srand(unsigned long seed) -{ - next = seed; -} - -static void set_random_data(unsigned char *buf, size_t len) -{ - size_t i; - - for (i = 0; i < len; ++i) - buf[i] = simple_rand(); -} +static struct rnd_state rnd_state; static int erase_eraseblock(int ebnum) { @@ -98,7 +80,7 @@ static int write_eraseblock(int ebnum) size_t written; loff_t addr = ebnum * mtd->erasesize; - set_random_data(writebuf, mtd->erasesize); + prandom_bytes_state(&rnd_state, writebuf, mtd->erasesize); cond_resched(); err = mtd_write(mtd, addr, mtd->erasesize, &written, writebuf); if (err || written != mtd->erasesize) @@ -124,7 +106,7 @@ static int verify_eraseblock(int ebnum) for (i = 0; i < ebcnt && bbt[ebcnt - i - 1]; ++i) addrn -= mtd->erasesize; - set_random_data(writebuf, mtd->erasesize); + prandom_bytes_state(&rnd_state, writebuf, mtd->erasesize); for (j = 0; j < pgcnt - 1; ++j, addr += pgsize) { /* Do a read to set the internal dataRAMs to different data */ err = mtd_read(mtd, addr0, bufsize, &read, twopages); @@ -160,7 +142,8 @@ static int verify_eraseblock(int ebnum) } /* Check boundary between eraseblocks */ if (addr <= addrn - pgsize - pgsize && !bbt[ebnum + 1]) { - unsigned long oldnext = next; + struct rnd_state old_state = rnd_state; + /* Do a read to set the internal dataRAMs to different data */ err = mtd_read(mtd, addr0, bufsize, &read, twopages); if (mtd_is_bitflip(err)) @@ -188,13 +171,13 @@ static int verify_eraseblock(int ebnum) return err; } memcpy(boundary, writebuf + mtd->erasesize - pgsize, pgsize); - set_random_data(boundary + pgsize, pgsize); + prandom_bytes_state(&rnd_state, boundary + pgsize, pgsize); if (memcmp(twopages, boundary, bufsize)) { pr_err("error: verify failed at %#llx\n", (long long)addr); errcnt += 1; } - next = oldnext; + rnd_state = old_state; } return err; } @@ -326,7 +309,7 @@ static int erasecrosstest(void) return err; pr_info("writing 1st page of block %d\n", ebnum); - set_random_data(writebuf, pgsize); + prandom_bytes_state(&rnd_state, writebuf, pgsize); strcpy(writebuf, "There is no data like this!"); err = mtd_write(mtd, addr0, pgsize, &written, writebuf); if (err || written != pgsize) { @@ -359,7 +342,7 @@ static int erasecrosstest(void) return err; pr_info("writing 1st page of block %d\n", ebnum); - set_random_data(writebuf, pgsize); + prandom_bytes_state(&rnd_state, writebuf, pgsize); strcpy(writebuf, "There is no data like this!"); err = mtd_write(mtd, addr0, pgsize, &written, writebuf); if (err || written != pgsize) { @@ -417,7 +400,7 @@ static int erasetest(void) return err; pr_info("writing 1st page of block %d\n", ebnum); - set_random_data(writebuf, pgsize); + prandom_bytes_state(&rnd_state, writebuf, pgsize); err = mtd_write(mtd, addr0, pgsize, &written, writebuf); if (err || written != pgsize) { pr_err("error: write failed at %#llx\n", @@ -565,7 +548,7 @@ static int __init mtd_pagetest_init(void) pr_info("erased %u eraseblocks\n", i); /* Write all eraseblocks */ - simple_srand(1); + prandom_seed_state(&rnd_state, 1); pr_info("writing whole device\n"); for (i = 0; i < ebcnt; ++i) { if (bbt[i]) @@ -580,7 +563,7 @@ static int __init mtd_pagetest_init(void) pr_info("written %u eraseblocks\n", i); /* Check all eraseblocks */ - simple_srand(1); + prandom_seed_state(&rnd_state, 1); pr_info("verifying all eraseblocks\n"); for (i = 0; i < ebcnt; ++i) { if (bbt[i]) diff --git a/drivers/mtd/tests/mtd_speedtest.c b/drivers/mtd/tests/mtd_speedtest.c index 596cbea8df4c..a6ce9c1fa6c5 100644 --- a/drivers/mtd/tests/mtd_speedtest.c +++ b/drivers/mtd/tests/mtd_speedtest.c @@ -49,13 +49,6 @@ static int pgcnt; static int goodebcnt; static struct timeval start, finish; -static void set_random_data(unsigned char *buf, size_t len) -{ - size_t i; - - for (i = 0; i < len; ++i) - buf[i] = random32(); -} static int erase_eraseblock(int ebnum) { @@ -396,7 +389,7 @@ static int __init mtd_speedtest_init(void) goto out; } - set_random_data(iobuf, mtd->erasesize); + prandom_bytes(iobuf, mtd->erasesize); err = scan_for_bad_eraseblocks(); if (err) diff --git a/drivers/mtd/tests/mtd_stresstest.c b/drivers/mtd/tests/mtd_stresstest.c index 1d29739db916..787f539d16ca 100644 --- a/drivers/mtd/tests/mtd_stresstest.c +++ b/drivers/mtd/tests/mtd_stresstest.c @@ -282,8 +282,7 @@ static int __init mtd_stresstest_init(void) } for (i = 0; i < ebcnt; i++) offsets[i] = mtd->erasesize; - for (i = 0; i < bufsize; i++) - writebuf[i] = random32(); + prandom_bytes(writebuf, bufsize); err = scan_for_bad_eraseblocks(); if (err) diff --git a/drivers/mtd/tests/mtd_subpagetest.c b/drivers/mtd/tests/mtd_subpagetest.c index c880c2229c59..aade56f27945 100644 --- a/drivers/mtd/tests/mtd_subpagetest.c +++ b/drivers/mtd/tests/mtd_subpagetest.c @@ -28,6 +28,7 @@ #include <linux/mtd/mtd.h> #include <linux/slab.h> #include <linux/sched.h> +#include <linux/random.h> static int dev = -EINVAL; module_param(dev, int, S_IRUGO); @@ -43,26 +44,7 @@ static int bufsize; static int ebcnt; static int pgcnt; static int errcnt; -static unsigned long next = 1; - -static inline unsigned int simple_rand(void) -{ - next = next * 1103515245 + 12345; - return (unsigned int)((next / 65536) % 32768); -} - -static inline void simple_srand(unsigned long seed) -{ - next = seed; -} - -static void set_random_data(unsigned char *buf, size_t len) -{ - size_t i; - - for (i = 0; i < len; ++i) - buf[i] = simple_rand(); -} +static struct rnd_state rnd_state; static inline void clear_data(unsigned char *buf, size_t len) { @@ -119,7 +101,7 @@ static int write_eraseblock(int ebnum) int err = 0; loff_t addr = ebnum * mtd->erasesize; - set_random_data(writebuf, subpgsize); + prandom_bytes_state(&rnd_state, writebuf, subpgsize); err = mtd_write(mtd, addr, subpgsize, &written, writebuf); if (unlikely(err || written != subpgsize)) { pr_err("error: write failed at %#llx\n", @@ -133,7 +115,7 @@ static int write_eraseblock(int ebnum) addr += subpgsize; - set_random_data(writebuf, subpgsize); + prandom_bytes_state(&rnd_state, writebuf, subpgsize); err = mtd_write(mtd, addr, subpgsize, &written, writebuf); if (unlikely(err || written != subpgsize)) { pr_err("error: write failed at %#llx\n", @@ -157,7 +139,7 @@ static int write_eraseblock2(int ebnum) for (k = 1; k < 33; ++k) { if (addr + (subpgsize * k) > (ebnum + 1) * mtd->erasesize) break; - set_random_data(writebuf, subpgsize * k); + prandom_bytes_state(&rnd_state, writebuf, subpgsize * k); err = mtd_write(mtd, addr, subpgsize * k, &written, writebuf); if (unlikely(err || written != subpgsize * k)) { pr_err("error: write failed at %#llx\n", @@ -193,7 +175,7 @@ static int verify_eraseblock(int ebnum) int err = 0; loff_t addr = ebnum * mtd->erasesize; - set_random_data(writebuf, subpgsize); + prandom_bytes_state(&rnd_state, writebuf, subpgsize); clear_data(readbuf, subpgsize); err = mtd_read(mtd, addr, subpgsize, &read, readbuf); if (unlikely(err || read != subpgsize)) { @@ -220,7 +202,7 @@ static int verify_eraseblock(int ebnum) addr += subpgsize; - set_random_data(writebuf, subpgsize); + prandom_bytes_state(&rnd_state, writebuf, subpgsize); clear_data(readbuf, subpgsize); err = mtd_read(mtd, addr, subpgsize, &read, readbuf); if (unlikely(err || read != subpgsize)) { @@ -257,7 +239,7 @@ static int verify_eraseblock2(int ebnum) for (k = 1; k < 33; ++k) { if (addr + (subpgsize * k) > (ebnum + 1) * mtd->erasesize) break; - set_random_data(writebuf, subpgsize * k); + prandom_bytes_state(&rnd_state, writebuf, subpgsize * k); clear_data(readbuf, subpgsize * k); err = mtd_read(mtd, addr, subpgsize * k, &read, readbuf); if (unlikely(err || read != subpgsize * k)) { @@ -430,7 +412,7 @@ static int __init mtd_subpagetest_init(void) goto out; pr_info("writing whole device\n"); - simple_srand(1); + prandom_seed_state(&rnd_state, 1); for (i = 0; i < ebcnt; ++i) { if (bbt[i]) continue; @@ -443,7 +425,7 @@ static int __init mtd_subpagetest_init(void) } pr_info("written %u eraseblocks\n", i); - simple_srand(1); + prandom_seed_state(&rnd_state, 1); pr_info("verifying all eraseblocks\n"); for (i = 0; i < ebcnt; ++i) { if (bbt[i]) @@ -466,7 +448,7 @@ static int __init mtd_subpagetest_init(void) goto out; /* Write all eraseblocks */ - simple_srand(3); + prandom_seed_state(&rnd_state, 3); pr_info("writing whole device\n"); for (i = 0; i < ebcnt; ++i) { if (bbt[i]) @@ -481,7 +463,7 @@ static int __init mtd_subpagetest_init(void) pr_info("written %u eraseblocks\n", i); /* Check all eraseblocks */ - simple_srand(3); + prandom_seed_state(&rnd_state, 3); pr_info("verifying all eraseblocks\n"); for (i = 0; i < ebcnt; ++i) { if (bbt[i]) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index db6735931d66..9b90d20ae56b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -2175,13 +2175,13 @@ static int ixgbe_get_ethtool_fdir_entry(struct ixgbe_adapter *adapter, union ixgbe_atr_input *mask = &adapter->fdir_mask; struct ethtool_rx_flow_spec *fsp = (struct ethtool_rx_flow_spec *)&cmd->fs; - struct hlist_node *node, *node2; + struct hlist_node *node2; struct ixgbe_fdir_filter *rule = NULL; /* report total rule count */ cmd->data = (1024 << adapter->fdir_pballoc) - 2; - hlist_for_each_entry_safe(rule, node, node2, + hlist_for_each_entry_safe(rule, node2, &adapter->fdir_filter_list, fdir_node) { if (fsp->location <= rule->sw_idx) break; @@ -2242,14 +2242,14 @@ static int ixgbe_get_ethtool_fdir_all(struct ixgbe_adapter *adapter, struct ethtool_rxnfc *cmd, u32 *rule_locs) { - struct hlist_node *node, *node2; + struct hlist_node *node2; struct ixgbe_fdir_filter *rule; int cnt = 0; /* report total rule count */ cmd->data = (1024 << adapter->fdir_pballoc) - 2; - hlist_for_each_entry_safe(rule, node, node2, + hlist_for_each_entry_safe(rule, node2, &adapter->fdir_filter_list, fdir_node) { if (cnt == cmd->rule_cnt) return -EMSGSIZE; @@ -2336,19 +2336,19 @@ static int ixgbe_update_ethtool_fdir_entry(struct ixgbe_adapter *adapter, u16 sw_idx) { struct ixgbe_hw *hw = &adapter->hw; - struct hlist_node *node, *node2, *parent; - struct ixgbe_fdir_filter *rule; + struct hlist_node *node2; + struct ixgbe_fdir_filter *rule, *parent; int err = -EINVAL; parent = NULL; rule = NULL; - hlist_for_each_entry_safe(rule, node, node2, + hlist_for_each_entry_safe(rule, node2, &adapter->fdir_filter_list, fdir_node) { /* hash found, or no matching entry */ if (rule->sw_idx >= sw_idx) break; - parent = node; + parent = rule; } /* if there is an old rule occupying our place remove it */ @@ -2377,7 +2377,7 @@ static int ixgbe_update_ethtool_fdir_entry(struct ixgbe_adapter *adapter, /* add filter to the list */ if (parent) - hlist_add_after(parent, &input->fdir_node); + hlist_add_after(&parent->fdir_node, &input->fdir_node); else hlist_add_head(&input->fdir_node, &adapter->fdir_filter_list); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 396e280c4373..be828a02aee5 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -3874,7 +3874,7 @@ static void ixgbe_configure_pb(struct ixgbe_adapter *adapter) static void ixgbe_fdir_filter_restore(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; - struct hlist_node *node, *node2; + struct hlist_node *node2; struct ixgbe_fdir_filter *filter; spin_lock(&adapter->fdir_perfect_lock); @@ -3882,7 +3882,7 @@ static void ixgbe_fdir_filter_restore(struct ixgbe_adapter *adapter) if (!hlist_empty(&adapter->fdir_filter_list)) ixgbe_fdir_set_input_mask_82599(hw, &adapter->fdir_mask); - hlist_for_each_entry_safe(filter, node, node2, + hlist_for_each_entry_safe(filter, node2, &adapter->fdir_filter_list, fdir_node) { ixgbe_fdir_write_perfect_filter_82599(hw, &filter->filter, @@ -4339,12 +4339,12 @@ static void ixgbe_clean_all_tx_rings(struct ixgbe_adapter *adapter) static void ixgbe_fdir_filter_exit(struct ixgbe_adapter *adapter) { - struct hlist_node *node, *node2; + struct hlist_node *node2; struct ixgbe_fdir_filter *filter; spin_lock(&adapter->fdir_perfect_lock); - hlist_for_each_entry_safe(filter, node, node2, + hlist_for_each_entry_safe(filter, node2, &adapter->fdir_filter_list, fdir_node) { hlist_del(&filter->fdir_node); kfree(filter); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index ac1c14f7424a..656e1ddf1015 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -228,11 +228,10 @@ static inline struct mlx4_en_filter * mlx4_en_filter_find(struct mlx4_en_priv *priv, __be32 src_ip, __be32 dst_ip, __be16 src_port, __be16 dst_port) { - struct hlist_node *elem; struct mlx4_en_filter *filter; struct mlx4_en_filter *ret = NULL; - hlist_for_each_entry(filter, elem, + hlist_for_each_entry(filter, filter_hash_bucket(priv, src_ip, dst_ip, src_port, dst_port), filter_chain) { diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c index 51716ab8739a..eec7c101a097 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c @@ -576,14 +576,14 @@ void qlcnic_free_mac_list(struct qlcnic_adapter *adapter) void qlcnic_prune_lb_filters(struct qlcnic_adapter *adapter) { struct qlcnic_filter *tmp_fil; - struct hlist_node *tmp_hnode, *n; + struct hlist_node *n; struct hlist_head *head; int i, time; u8 cmd; for (i = 0; i < adapter->fhash.fbucket_size; i++) { head = &(adapter->fhash.fhead[i]); - hlist_for_each_entry_safe(tmp_fil, tmp_hnode, n, head, fnode) { + hlist_for_each_entry_safe(tmp_fil, n, head, fnode) { cmd = tmp_fil->vlan_id ? QLCNIC_MAC_VLAN_DEL : QLCNIC_MAC_DEL; time = tmp_fil->ftime; @@ -605,14 +605,14 @@ void qlcnic_prune_lb_filters(struct qlcnic_adapter *adapter) void qlcnic_delete_lb_filters(struct qlcnic_adapter *adapter) { struct qlcnic_filter *tmp_fil; - struct hlist_node *tmp_hnode, *n; + struct hlist_node *n; struct hlist_head *head; int i; u8 cmd; for (i = 0; i < adapter->fhash.fbucket_size; i++) { head = &(adapter->fhash.fhead[i]); - hlist_for_each_entry_safe(tmp_fil, tmp_hnode, n, head, fnode) { + hlist_for_each_entry_safe(tmp_fil, n, head, fnode) { cmd = tmp_fil->vlan_id ? QLCNIC_MAC_VLAN_DEL : QLCNIC_MAC_DEL; qlcnic_sre_macaddr_change(adapter, diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c index bb4311e9aea9..afd31d3b5958 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c @@ -187,7 +187,7 @@ static void qlcnic_send_filter(struct qlcnic_adapter *adapter, struct sk_buff *skb) { struct qlcnic_filter *fil, *tmp_fil; - struct hlist_node *tmp_hnode, *n; + struct hlist_node *n; struct hlist_head *head; struct net_device *netdev = adapter->netdev; struct ethhdr *phdr = (struct ethhdr *)(skb->data); @@ -212,7 +212,7 @@ static void qlcnic_send_filter(struct qlcnic_adapter *adapter, hindex = qlcnic_mac_hash(src_addr) & (adapter->fhash.fbucket_size - 1); head = &(adapter->fhash.fhead[hindex]); - hlist_for_each_entry_safe(tmp_fil, tmp_hnode, n, head, fnode) { + hlist_for_each_entry_safe(tmp_fil, n, head, fnode) { if (!memcmp(tmp_fil->faddr, &src_addr, ETH_ALEN) && tmp_fil->vlan_id == vlan_id) { if (jiffies > (QLCNIC_READD_AGE * HZ + tmp_fil->ftime)) diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c index 289b4eefb42f..1df0ff3839e8 100644 --- a/drivers/net/ethernet/sun/sunvnet.c +++ b/drivers/net/ethernet/sun/sunvnet.c @@ -614,10 +614,9 @@ struct vnet_port *__tx_port_find(struct vnet *vp, struct sk_buff *skb) { unsigned int hash = vnet_hashfn(skb->data); struct hlist_head *hp = &vp->port_hash[hash]; - struct hlist_node *n; struct vnet_port *port; - hlist_for_each_entry(port, n, hp, hash) { + hlist_for_each_entry(port, hp, hash) { if (ether_addr_equal(port->raddr, skb->data)) return port; } diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index f494da82c33f..bbe533f31ee4 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -55,9 +55,8 @@ static struct macvlan_dev *macvlan_hash_lookup(const struct macvlan_port *port, const unsigned char *addr) { struct macvlan_dev *vlan; - struct hlist_node *n; - hlist_for_each_entry_rcu(vlan, n, &port->vlan_hash[addr[5]], hlist) { + hlist_for_each_entry_rcu(vlan, &port->vlan_hash[addr[5]], hlist) { if (ether_addr_equal_64bits(vlan->dev->dev_addr, addr)) return vlan; } @@ -141,7 +140,6 @@ static void macvlan_broadcast(struct sk_buff *skb, { const struct ethhdr *eth = eth_hdr(skb); const struct macvlan_dev *vlan; - struct hlist_node *n; struct sk_buff *nskb; unsigned int i; int err; @@ -151,7 +149,7 @@ static void macvlan_broadcast(struct sk_buff *skb, return; for (i = 0; i < MACVLAN_HASH_SIZE; i++) { - hlist_for_each_entry_rcu(vlan, n, &port->vlan_hash[i], hlist) { + hlist_for_each_entry_rcu(vlan, &port->vlan_hash[i], hlist) { if (vlan->dev == src || !(vlan->mode & mode)) continue; diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index b181dfb3d6d6..1814cfe86e8e 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -279,28 +279,17 @@ static int macvtap_receive(struct sk_buff *skb) static int macvtap_get_minor(struct macvlan_dev *vlan) { int retval = -ENOMEM; - int id; mutex_lock(&minor_lock); - if (idr_pre_get(&minor_idr, GFP_KERNEL) == 0) - goto exit; - - retval = idr_get_new_above(&minor_idr, vlan, 1, &id); - if (retval < 0) { - if (retval == -EAGAIN) - retval = -ENOMEM; - goto exit; - } - if (id < MACVTAP_NUM_DEVS) { - vlan->minor = id; - } else { + retval = idr_alloc(&minor_idr, vlan, 1, MACVTAP_NUM_DEVS, GFP_KERNEL); + if (retval >= 0) { + vlan->minor = retval; + } else if (retval == -ENOSPC) { printk(KERN_ERR "too many macvtap devices\n"); retval = -EINVAL; - idr_remove(&minor_idr, id); } -exit: mutex_unlock(&minor_lock); - return retval; + return retval < 0 ? retval : 0; } static void macvtap_free_minor(struct macvlan_dev *vlan) diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 0b2706abe3e3..7efdb9149e68 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -2946,46 +2946,21 @@ static void __exit ppp_cleanup(void) * by holding all_ppp_mutex */ -static int __unit_alloc(struct idr *p, void *ptr, int n) -{ - int unit, err; - -again: - if (!idr_pre_get(p, GFP_KERNEL)) { - pr_err("PPP: No free memory for idr\n"); - return -ENOMEM; - } - - err = idr_get_new_above(p, ptr, n, &unit); - if (err < 0) { - if (err == -EAGAIN) - goto again; - return err; - } - - return unit; -} - /* associate pointer with specified number */ static int unit_set(struct idr *p, void *ptr, int n) { int unit; - unit = __unit_alloc(p, ptr, n); - if (unit < 0) - return unit; - else if (unit != n) { - idr_remove(p, unit); - return -EINVAL; - } - + unit = idr_alloc(p, ptr, n, n + 1, GFP_KERNEL); + if (unit == -ENOSPC) + unit = -EINVAL; return unit; } /* get new free unit number and associate pointer with it */ static int unit_get(struct idr *p, void *ptr) { - return __unit_alloc(p, ptr, 0); + return idr_alloc(p, ptr, 0, 0, GFP_KERNEL); } /* put unit number back to a pool */ diff --git a/drivers/net/tun.c b/drivers/net/tun.c index b1038c0e2240..d52d1b148ce7 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -197,9 +197,8 @@ static inline u32 tun_hashfn(u32 rxhash) static struct tun_flow_entry *tun_flow_find(struct hlist_head *head, u32 rxhash) { struct tun_flow_entry *e; - struct hlist_node *n; - hlist_for_each_entry_rcu(e, n, head, hash_link) { + hlist_for_each_entry_rcu(e, head, hash_link) { if (e->rxhash == rxhash) return e; } @@ -241,9 +240,9 @@ static void tun_flow_flush(struct tun_struct *tun) spin_lock_bh(&tun->lock); for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) { struct tun_flow_entry *e; - struct hlist_node *h, *n; + struct hlist_node *n; - hlist_for_each_entry_safe(e, h, n, &tun->flows[i], hash_link) + hlist_for_each_entry_safe(e, n, &tun->flows[i], hash_link) tun_flow_delete(tun, e); } spin_unlock_bh(&tun->lock); @@ -256,9 +255,9 @@ static void tun_flow_delete_by_queue(struct tun_struct *tun, u16 queue_index) spin_lock_bh(&tun->lock); for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) { struct tun_flow_entry *e; - struct hlist_node *h, *n; + struct hlist_node *n; - hlist_for_each_entry_safe(e, h, n, &tun->flows[i], hash_link) { + hlist_for_each_entry_safe(e, n, &tun->flows[i], hash_link) { if (e->queue_index == queue_index) tun_flow_delete(tun, e); } @@ -279,9 +278,9 @@ static void tun_flow_cleanup(unsigned long data) spin_lock_bh(&tun->lock); for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) { struct tun_flow_entry *e; - struct hlist_node *h, *n; + struct hlist_node *n; - hlist_for_each_entry_safe(e, h, n, &tun->flows[i], hash_link) { + hlist_for_each_entry_safe(e, n, &tun->flows[i], hash_link) { unsigned long this_timer; count++; this_timer = e->updated + delay; diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 72485b9b9005..6b573406a6f9 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -144,9 +144,8 @@ static inline struct hlist_head *vni_head(struct net *net, u32 id) static struct vxlan_dev *vxlan_find_vni(struct net *net, u32 id) { struct vxlan_dev *vxlan; - struct hlist_node *node; - hlist_for_each_entry_rcu(vxlan, node, vni_head(net, id), hlist) { + hlist_for_each_entry_rcu(vxlan, vni_head(net, id), hlist) { if (vxlan->vni == id) return vxlan; } @@ -291,9 +290,8 @@ static struct vxlan_fdb *vxlan_find_mac(struct vxlan_dev *vxlan, { struct hlist_head *head = vxlan_fdb_head(vxlan, mac); struct vxlan_fdb *f; - struct hlist_node *node; - hlist_for_each_entry_rcu(f, node, head, hlist) { + hlist_for_each_entry_rcu(f, head, hlist) { if (compare_ether_addr(mac, f->eth_addr) == 0) return f; } @@ -420,10 +418,9 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, for (h = 0; h < FDB_HASH_SIZE; ++h) { struct vxlan_fdb *f; - struct hlist_node *n; int err; - hlist_for_each_entry_rcu(f, n, &vxlan->fdb_head[h], hlist) { + hlist_for_each_entry_rcu(f, &vxlan->fdb_head[h], hlist) { if (idx < cb->args[0]) goto skip; @@ -481,11 +478,10 @@ static bool vxlan_group_used(struct vxlan_net *vn, const struct vxlan_dev *this) { const struct vxlan_dev *vxlan; - struct hlist_node *node; unsigned h; for (h = 0; h < VNI_HASH_SIZE; ++h) - hlist_for_each_entry(vxlan, node, &vn->vni_list[h], hlist) { + hlist_for_each_entry(vxlan, &vn->vni_list[h], hlist) { if (vxlan == this) continue; diff --git a/drivers/net/wireless/zd1201.c b/drivers/net/wireless/zd1201.c index 48273dd05b63..4941f201d6c8 100644 --- a/drivers/net/wireless/zd1201.c +++ b/drivers/net/wireless/zd1201.c @@ -309,7 +309,6 @@ static void zd1201_usbrx(struct urb *urb) if (data[urb->actual_length-1] == ZD1201_PACKET_RXDATA) { int datalen = urb->actual_length-1; unsigned short len, fc, seq; - struct hlist_node *node; len = ntohs(*(__be16 *)&data[datalen-2]); if (len>datalen) @@ -362,7 +361,7 @@ static void zd1201_usbrx(struct urb *urb) hlist_add_head(&frag->fnode, &zd->fraglist); goto resubmit; } - hlist_for_each_entry(frag, node, &zd->fraglist, fnode) + hlist_for_each_entry(frag, &zd->fraglist, fnode) if (frag->seq == (seq&IEEE80211_SCTL_SEQ)) break; if (!frag) @@ -1831,14 +1830,14 @@ err_zd: static void zd1201_disconnect(struct usb_interface *interface) { struct zd1201 *zd = usb_get_intfdata(interface); - struct hlist_node *node, *node2; + struct hlist_node *node2; struct zd1201_frag *frag; if (!zd) return; usb_set_intfdata(interface, NULL); - hlist_for_each_entry_safe(frag, node, node2, &zd->fraglist, fnode) { + hlist_for_each_entry_safe(frag, node2, &zd->fraglist, fnode) { hlist_del_init(&frag->fnode); kfree_skb(frag->skb); kfree(frag); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 393cf095a0c4..816039fdd305 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -842,9 +842,8 @@ static struct pci_cap_saved_state *pci_find_saved_cap( struct pci_dev *pci_dev, char cap) { struct pci_cap_saved_state *tmp; - struct hlist_node *pos; - hlist_for_each_entry(tmp, pos, &pci_dev->saved_cap_space, next) { + hlist_for_each_entry(tmp, &pci_dev->saved_cap_space, next) { if (tmp->cap.cap_nr == cap) return tmp; } @@ -1041,7 +1040,6 @@ struct pci_saved_state *pci_store_saved_state(struct pci_dev *dev) struct pci_saved_state *state; struct pci_cap_saved_state *tmp; struct pci_cap_saved_data *cap; - struct hlist_node *pos; size_t size; if (!dev->state_saved) @@ -1049,7 +1047,7 @@ struct pci_saved_state *pci_store_saved_state(struct pci_dev *dev) size = sizeof(*state) + sizeof(struct pci_cap_saved_data); - hlist_for_each_entry(tmp, pos, &dev->saved_cap_space, next) + hlist_for_each_entry(tmp, &dev->saved_cap_space, next) size += sizeof(struct pci_cap_saved_data) + tmp->cap.size; state = kzalloc(size, GFP_KERNEL); @@ -1060,7 +1058,7 @@ struct pci_saved_state *pci_store_saved_state(struct pci_dev *dev) sizeof(state->config_space)); cap = state->cap; - hlist_for_each_entry(tmp, pos, &dev->saved_cap_space, next) { + hlist_for_each_entry(tmp, &dev->saved_cap_space, next) { size_t len = sizeof(struct pci_cap_saved_data) + tmp->cap.size; memcpy(cap, &tmp->cap, len); cap = (struct pci_cap_saved_data *)((u8 *)cap + len); @@ -2035,9 +2033,9 @@ void pci_allocate_cap_save_buffers(struct pci_dev *dev) void pci_free_cap_save_buffers(struct pci_dev *dev) { struct pci_cap_saved_state *tmp; - struct hlist_node *pos, *n; + struct hlist_node *n; - hlist_for_each_entry_safe(tmp, pos, n, &dev->saved_cap_space, next) + hlist_for_each_entry_safe(tmp, n, &dev->saved_cap_space, next) kfree(tmp); } diff --git a/drivers/pcmcia/cs.c b/drivers/pcmcia/cs.c index 673c14ea11e3..5292db69c426 100644 --- a/drivers/pcmcia/cs.c +++ b/drivers/pcmcia/cs.c @@ -484,7 +484,7 @@ static int socket_early_resume(struct pcmcia_socket *skt) static int socket_late_resume(struct pcmcia_socket *skt) { - int ret; + int ret = 0; mutex_lock(&skt->ops_mutex); skt->state &= ~SOCKET_SUSPEND; @@ -511,19 +511,31 @@ static int socket_late_resume(struct pcmcia_socket *skt) return socket_insert(skt); } + if (!(skt->state & SOCKET_CARDBUS) && (skt->callback)) + ret = skt->callback->early_resume(skt); + return ret; +} + +/* + * Finalize the resume. In case of a cardbus socket, we have + * to rebind the devices as we can't be certain that it has been + * replaced, or not. + */ +static int socket_complete_resume(struct pcmcia_socket *skt) +{ + int ret = 0; #ifdef CONFIG_CARDBUS if (skt->state & SOCKET_CARDBUS) { /* We can't be sure the CardBus card is the same * as the one previously inserted. Therefore, remove * and re-add... */ cb_free(skt); - cb_alloc(skt); - return 0; + ret = cb_alloc(skt); + if (ret) + cb_free(skt); } #endif - if (!(skt->state & SOCKET_CARDBUS) && (skt->callback)) - skt->callback->early_resume(skt); - return 0; + return ret; } /* @@ -533,11 +545,15 @@ static int socket_late_resume(struct pcmcia_socket *skt) */ static int socket_resume(struct pcmcia_socket *skt) { + int err; if (!(skt->state & SOCKET_SUSPEND)) return -EBUSY; socket_early_resume(skt); - return socket_late_resume(skt); + err = socket_late_resume(skt); + if (!err) + err = socket_complete_resume(skt); + return err; } static void socket_remove(struct pcmcia_socket *skt) @@ -848,6 +864,12 @@ static int __used pcmcia_socket_dev_resume(struct device *dev) return __pcmcia_pm_op(dev, socket_late_resume); } +static void __used pcmcia_socket_dev_complete(struct device *dev) +{ + WARN(__pcmcia_pm_op(dev, socket_complete_resume), + "failed to complete resume"); +} + static const struct dev_pm_ops pcmcia_socket_pm_ops = { /* dev_resume may be called with IRQs enabled */ SET_SYSTEM_SLEEP_PM_OPS(NULL, @@ -862,6 +884,7 @@ static const struct dev_pm_ops pcmcia_socket_pm_ops = { .resume_noirq = pcmcia_socket_dev_resume_noirq, .thaw_noirq = pcmcia_socket_dev_resume_noirq, .restore_noirq = pcmcia_socket_dev_resume_noirq, + .complete = pcmcia_socket_dev_complete, }; #define PCMCIA_SOCKET_CLASS_PM_OPS (&pcmcia_socket_pm_ops) diff --git a/drivers/power/bq2415x_charger.c b/drivers/power/bq2415x_charger.c index ca70365e9410..3f00568635e8 100644 --- a/drivers/power/bq2415x_charger.c +++ b/drivers/power/bq2415x_charger.c @@ -1504,16 +1504,11 @@ static int bq2415x_probe(struct i2c_client *client, } /* Get new ID for the new device */ - ret = idr_pre_get(&bq2415x_id, GFP_KERNEL); - if (ret == 0) - return -ENOMEM; - mutex_lock(&bq2415x_id_mutex); - ret = idr_get_new(&bq2415x_id, client, &num); + num = idr_alloc(&bq2415x_id, client, 0, 0, GFP_KERNEL); mutex_unlock(&bq2415x_id_mutex); - - if (ret < 0) - return ret; + if (num < 0) + return num; name = kasprintf(GFP_KERNEL, "%s-%d", id->name, num); if (!name) { diff --git a/drivers/power/bq27x00_battery.c b/drivers/power/bq27x00_battery.c index 8ccf5d7d0add..26037ca7efb4 100644 --- a/drivers/power/bq27x00_battery.c +++ b/drivers/power/bq27x00_battery.c @@ -791,14 +791,11 @@ static int bq27x00_battery_probe(struct i2c_client *client, int retval = 0; /* Get new ID for the new battery device */ - retval = idr_pre_get(&battery_id, GFP_KERNEL); - if (retval == 0) - return -ENOMEM; mutex_lock(&battery_mutex); - retval = idr_get_new(&battery_id, client, &num); + num = idr_alloc(&battery_id, client, 0, 0, GFP_KERNEL); mutex_unlock(&battery_mutex); - if (retval < 0) - return retval; + if (num < 0) + return num; name = kasprintf(GFP_KERNEL, "%s-%d", id->name, num); if (!name) { diff --git a/drivers/power/ds2782_battery.c b/drivers/power/ds2782_battery.c index e7301b3ed623..c09e7726c96c 100644 --- a/drivers/power/ds2782_battery.c +++ b/drivers/power/ds2782_battery.c @@ -395,17 +395,12 @@ static int ds278x_battery_probe(struct i2c_client *client, } /* Get an ID for this battery */ - ret = idr_pre_get(&battery_id, GFP_KERNEL); - if (ret == 0) { - ret = -ENOMEM; - goto fail_id; - } - mutex_lock(&battery_lock); - ret = idr_get_new(&battery_id, client, &num); + ret = idr_alloc(&battery_id, client, 0, 0, GFP_KERNEL); mutex_unlock(&battery_lock); if (ret < 0) goto fail_id; + num = ret; info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) { diff --git a/drivers/pps/kapi.c b/drivers/pps/kapi.c index f197e8ea185c..cdad4d95b20e 100644 --- a/drivers/pps/kapi.c +++ b/drivers/pps/kapi.c @@ -102,7 +102,7 @@ struct pps_device *pps_register_source(struct pps_source_info *info, goto pps_register_source_exit; } - /* These initializations must be done before calling idr_get_new() + /* These initializations must be done before calling idr_alloc() * in order to avoid reces into pps_event(). */ pps->params.api_version = PPS_API_VERS; diff --git a/drivers/pps/pps.c b/drivers/pps/pps.c index 2420d5af0583..de8e663ee137 100644 --- a/drivers/pps/pps.c +++ b/drivers/pps/pps.c @@ -290,29 +290,21 @@ int pps_register_cdev(struct pps_device *pps) dev_t devt; mutex_lock(&pps_idr_lock); - /* Get new ID for the new PPS source */ - if (idr_pre_get(&pps_idr, GFP_KERNEL) == 0) { - mutex_unlock(&pps_idr_lock); - return -ENOMEM; - } - - /* Now really allocate the PPS source. - * After idr_get_new() calling the new source will be freely available - * into the kernel. + /* + * Get new ID for the new PPS source. After idr_alloc() calling + * the new source will be freely available into the kernel. */ - err = idr_get_new(&pps_idr, pps, &pps->id); - mutex_unlock(&pps_idr_lock); - - if (err < 0) - return err; - - pps->id &= MAX_IDR_MASK; - if (pps->id >= PPS_MAX_SOURCES) { - pr_err("%s: too many PPS sources in the system\n", - pps->info.name); - err = -EBUSY; - goto free_idr; + err = idr_alloc(&pps_idr, pps, 0, PPS_MAX_SOURCES, GFP_KERNEL); + if (err < 0) { + if (err == -ENOSPC) { + pr_err("%s: too many PPS sources in the system\n", + pps->info.name); + err = -EBUSY; + } + goto out_unlock; } + pps->id = err; + mutex_unlock(&pps_idr_lock); devt = MKDEV(MAJOR(pps_devt), pps->id); @@ -345,8 +337,8 @@ del_cdev: free_idr: mutex_lock(&pps_idr_lock); idr_remove(&pps_idr, pps->id); +out_unlock: mutex_unlock(&pps_idr_lock); - return err; } diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index dd3bfaf1ad40..29387df4bfc9 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -199,11 +199,6 @@ int rproc_alloc_vring(struct rproc_vdev *rvdev, int i) /* actual size of vring (in bytes) */ size = PAGE_ALIGN(vring_size(rvring->len, rvring->align)); - if (!idr_pre_get(&rproc->notifyids, GFP_KERNEL)) { - dev_err(dev, "idr_pre_get failed\n"); - return -ENOMEM; - } - /* * Allocate non-cacheable memory for the vring. In the future * this call will also configure the IOMMU for us @@ -221,12 +216,13 @@ int rproc_alloc_vring(struct rproc_vdev *rvdev, int i) * TODO: let the rproc know the notifyid of this vring * TODO: support predefined notifyids (via resource table) */ - ret = idr_get_new(&rproc->notifyids, rvring, ¬ifyid); + ret = idr_alloc(&rproc->notifyids, rvring, 0, 0, GFP_KERNEL); if (ret) { - dev_err(dev, "idr_get_new failed: %d\n", ret); + dev_err(dev, "idr_alloc failed: %d\n", ret); dma_free_coherent(dev->parent, size, va, dma); return ret; } + notifyid = ret; /* Store largest notifyid */ rproc->max_notifyid = max(rproc->max_notifyid, notifyid); @@ -1180,7 +1176,6 @@ static void rproc_type_release(struct device *dev) rproc_delete_debug_dir(rproc); - idr_remove_all(&rproc->notifyids); idr_destroy(&rproc->notifyids); if (rproc->index >= 0) diff --git a/drivers/rpmsg/virtio_rpmsg_bus.c b/drivers/rpmsg/virtio_rpmsg_bus.c index d85446021ddb..a59684b5fc68 100644 --- a/drivers/rpmsg/virtio_rpmsg_bus.c +++ b/drivers/rpmsg/virtio_rpmsg_bus.c @@ -213,13 +213,10 @@ static struct rpmsg_endpoint *__rpmsg_create_ept(struct virtproc_info *vrp, struct rpmsg_channel *rpdev, rpmsg_rx_cb_t cb, void *priv, u32 addr) { - int err, tmpaddr, request; + int id_min, id_max, id; struct rpmsg_endpoint *ept; struct device *dev = rpdev ? &rpdev->dev : &vrp->vdev->dev; - if (!idr_pre_get(&vrp->endpoints, GFP_KERNEL)) - return NULL; - ept = kzalloc(sizeof(*ept), GFP_KERNEL); if (!ept) { dev_err(dev, "failed to kzalloc a new ept\n"); @@ -234,31 +231,28 @@ static struct rpmsg_endpoint *__rpmsg_create_ept(struct virtproc_info *vrp, ept->priv = priv; /* do we need to allocate a local address ? */ - request = addr == RPMSG_ADDR_ANY ? RPMSG_RESERVED_ADDRESSES : addr; + if (addr == RPMSG_ADDR_ANY) { + id_min = RPMSG_RESERVED_ADDRESSES; + id_max = 0; + } else { + id_min = addr; + id_max = addr + 1; + } mutex_lock(&vrp->endpoints_lock); /* bind the endpoint to an rpmsg address (and allocate one if needed) */ - err = idr_get_new_above(&vrp->endpoints, ept, request, &tmpaddr); - if (err) { - dev_err(dev, "idr_get_new_above failed: %d\n", err); + id = idr_alloc(&vrp->endpoints, ept, id_min, id_max, GFP_KERNEL); + if (id < 0) { + dev_err(dev, "idr_alloc failed: %d\n", id); goto free_ept; } - - /* make sure the user's address request is fulfilled, if relevant */ - if (addr != RPMSG_ADDR_ANY && tmpaddr != addr) { - dev_err(dev, "address 0x%x already in use\n", addr); - goto rem_idr; - } - - ept->addr = tmpaddr; + ept->addr = id; mutex_unlock(&vrp->endpoints_lock); return ept; -rem_idr: - idr_remove(&vrp->endpoints, request); free_ept: mutex_unlock(&vrp->endpoints_lock); kref_put(&ept->refcount, __ept_release); @@ -1036,7 +1030,6 @@ static void rpmsg_remove(struct virtio_device *vdev) if (vrp->ns_ept) __rpmsg_destroy_ept(vrp, vrp->ns_ept); - idr_remove_all(&vrp->endpoints); idr_destroy(&vrp->endpoints); vdev->config->del_vqs(vrp->vdev); diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig index 3847515500b1..8d1f108b1975 100644 --- a/drivers/rtc/Kconfig +++ b/drivers/rtc/Kconfig @@ -204,6 +204,12 @@ config RTC_DRV_DS3232 This driver can also be built as a module. If so, the module will be called rtc-ds3232. +config RTC_DRV_LP8788 + tristate "TI LP8788 RTC driver" + depends on MFD_LP8788 + help + Say Y to enable support for the LP8788 RTC/ALARM driver. + config RTC_DRV_MAX6900 tristate "Maxim MAX6900" help @@ -243,6 +249,16 @@ config RTC_DRV_MAX8998 This driver can also be built as a module. If so, the module will be called rtc-max8998. +config RTC_DRV_MAX77686 + tristate "Maxim MAX77686" + depends on MFD_MAX77686 + help + If you say yes here you will get support for the + RTC of Maxim MAX77686 PMIC. + + This driver can also be built as a module. If so, the module + will be called rtc-max77686. + config RTC_DRV_RS5C372 tristate "Ricoh R2025S/D, RS5C372A/B, RV5C386, RV5C387A" help @@ -390,6 +406,14 @@ config RTC_DRV_TPS65910 This driver can also be built as a module. If so, the module will be called rtc-tps65910. +config RTC_DRV_TPS80031 + tristate "TI TPS80031/TPS80032 RTC driver" + depends on MFD_TPS80031 + help + TI Power Managment IC TPS80031 supports RTC functionality + along with alarm. This driver supports the RTC driver for + the TPS80031 RTC module. + config RTC_DRV_RC5T583 tristate "RICOH 5T583 RTC driver" depends on MFD_RC5T583 @@ -547,6 +571,14 @@ config RTC_DRV_PCF2123 This driver can also be built as a module. If so, the module will be called rtc-pcf2123. +config RTC_DRV_RX4581 + tristate "Epson RX-4581" + help + If you say yes here you will get support for the Epson RX-4581. + + This driver can also be built as a module. If so the module + will be called rtc-rx4581. + endif # SPI_MASTER comment "Platform RTC drivers" diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile index 805603897ee5..e864b1eb6533 100644 --- a/drivers/rtc/Makefile +++ b/drivers/rtc/Makefile @@ -58,6 +58,7 @@ obj-$(CONFIG_RTC_DRV_IMXDI) += rtc-imxdi.o obj-$(CONFIG_RTC_DRV_ISL1208) += rtc-isl1208.o obj-$(CONFIG_RTC_DRV_ISL12022) += rtc-isl12022.o obj-$(CONFIG_RTC_DRV_JZ4740) += rtc-jz4740.o +obj-$(CONFIG_RTC_DRV_LP8788) += rtc-lp8788.o obj-$(CONFIG_RTC_DRV_LPC32XX) += rtc-lpc32xx.o obj-$(CONFIG_RTC_DRV_LOONGSON1) += rtc-ls1x.o obj-$(CONFIG_RTC_DRV_M41T80) += rtc-m41t80.o @@ -72,6 +73,7 @@ obj-$(CONFIG_RTC_DRV_MAX8907) += rtc-max8907.o obj-$(CONFIG_RTC_DRV_MAX8925) += rtc-max8925.o obj-$(CONFIG_RTC_DRV_MAX8998) += rtc-max8998.o obj-$(CONFIG_RTC_DRV_MAX6902) += rtc-max6902.o +obj-$(CONFIG_RTC_DRV_MAX77686) += rtc-max77686.o obj-$(CONFIG_RTC_DRV_MC13XXX) += rtc-mc13xxx.o obj-$(CONFIG_RTC_DRV_MSM6242) += rtc-msm6242.o obj-$(CONFIG_RTC_DRV_MPC5121) += rtc-mpc5121.o @@ -98,6 +100,7 @@ obj-$(CONFIG_RTC_DRV_RS5C313) += rtc-rs5c313.o obj-$(CONFIG_RTC_DRV_RS5C348) += rtc-rs5c348.o obj-$(CONFIG_RTC_DRV_RS5C372) += rtc-rs5c372.o obj-$(CONFIG_RTC_DRV_RV3029C2) += rtc-rv3029c2.o +obj-$(CONFIG_RTC_DRV_RX4581) += rtc-rx4581.o obj-$(CONFIG_RTC_DRV_RX8025) += rtc-rx8025.o obj-$(CONFIG_RTC_DRV_RX8581) += rtc-rx8581.o obj-$(CONFIG_RTC_DRV_S35390A) += rtc-s35390a.o @@ -116,6 +119,7 @@ obj-$(CONFIG_RTC_DRV_TILE) += rtc-tile.o obj-$(CONFIG_RTC_DRV_TWL4030) += rtc-twl.o obj-$(CONFIG_RTC_DRV_TPS6586X) += rtc-tps6586x.o obj-$(CONFIG_RTC_DRV_TPS65910) += rtc-tps65910.o +obj-$(CONFIG_RTC_DRV_TPS80031) += rtc-tps80031.o obj-$(CONFIG_RTC_DRV_TX4939) += rtc-tx4939.o obj-$(CONFIG_RTC_DRV_V3020) += rtc-v3020.o obj-$(CONFIG_RTC_DRV_VR41XX) += rtc-vr41xx.o diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c index 16630aa87f45..9deb9e47a67c 100644 --- a/drivers/rtc/rtc-cmos.c +++ b/drivers/rtc/rtc-cmos.c @@ -1098,7 +1098,6 @@ static __init void cmos_of_init(struct platform_device *pdev) } #else static inline void cmos_of_init(struct platform_device *pdev) {} -#define of_cmos_match NULL #endif /*----------------------------------------------------------------*/ @@ -1140,7 +1139,7 @@ static struct platform_driver cmos_platform_driver = { #ifdef CONFIG_PM .pm = &cmos_pm_ops, #endif - .of_match_table = of_cmos_match, + .of_match_table = of_match_ptr(of_cmos_match), } }; diff --git a/drivers/rtc/rtc-ds1305.c b/drivers/rtc/rtc-ds1305.c index d578773f5ce2..b05a6dc96405 100644 --- a/drivers/rtc/rtc-ds1305.c +++ b/drivers/rtc/rtc-ds1305.c @@ -635,9 +635,7 @@ static int ds1305_probe(struct spi_device *spi) goto fail0; } - dev_dbg(&spi->dev, "ctrl %s: %02x %02x %02x\n", - "read", ds1305->ctrl[0], - ds1305->ctrl[1], ds1305->ctrl[2]); + dev_dbg(&spi->dev, "ctrl %s: %3ph\n", "read", ds1305->ctrl); /* Sanity check register values ... partially compensating for the * fact that SPI has no device handshake. A pullup on MISO would @@ -723,9 +721,7 @@ static int ds1305_probe(struct spi_device *spi) goto fail0; } - dev_dbg(&spi->dev, "ctrl %s: %02x %02x %02x\n", - "write", ds1305->ctrl[0], - ds1305->ctrl[1], ds1305->ctrl[2]); + dev_dbg(&spi->dev, "ctrl %s: %3ph\n", "write", ds1305->ctrl); } /* see if non-Linux software set up AM/PM mode */ diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c index e0d0ba4de03f..a65621c42170 100644 --- a/drivers/rtc/rtc-ds1307.c +++ b/drivers/rtc/rtc-ds1307.c @@ -4,6 +4,7 @@ * Copyright (C) 2005 James Chapman (ds1337 core) * Copyright (C) 2006 David Brownell * Copyright (C) 2009 Matthias Fuchs (rx8025 support) + * Copyright (C) 2012 Bertrand Achard (nvram access fixes) * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -196,7 +197,7 @@ static s32 ds1307_read_block_data_once(const struct i2c_client *client, static s32 ds1307_read_block_data(const struct i2c_client *client, u8 command, u8 length, u8 *values) { - u8 oldvalues[I2C_SMBUS_BLOCK_MAX]; + u8 oldvalues[255]; s32 ret; int tries = 0; @@ -222,7 +223,7 @@ static s32 ds1307_read_block_data(const struct i2c_client *client, u8 command, static s32 ds1307_write_block_data(const struct i2c_client *client, u8 command, u8 length, const u8 *values) { - u8 currvalues[I2C_SMBUS_BLOCK_MAX]; + u8 currvalues[255]; int tries = 0; dev_dbg(&client->dev, "ds1307_write_block_data (length=%d)\n", length); @@ -250,6 +251,57 @@ static s32 ds1307_write_block_data(const struct i2c_client *client, u8 command, /*----------------------------------------------------------------------*/ +/* These RTC devices are not designed to be connected to a SMbus adapter. + SMbus limits block operations length to 32 bytes, whereas it's not + limited on I2C buses. As a result, accesses may exceed 32 bytes; + in that case, split them into smaller blocks */ + +static s32 ds1307_native_smbus_write_block_data(const struct i2c_client *client, + u8 command, u8 length, const u8 *values) +{ + u8 suboffset = 0; + + if (length <= I2C_SMBUS_BLOCK_MAX) + return i2c_smbus_write_i2c_block_data(client, + command, length, values); + + while (suboffset < length) { + s32 retval = i2c_smbus_write_i2c_block_data(client, + command + suboffset, + min(I2C_SMBUS_BLOCK_MAX, length - suboffset), + values + suboffset); + if (retval < 0) + return retval; + + suboffset += I2C_SMBUS_BLOCK_MAX; + } + return length; +} + +static s32 ds1307_native_smbus_read_block_data(const struct i2c_client *client, + u8 command, u8 length, u8 *values) +{ + u8 suboffset = 0; + + if (length <= I2C_SMBUS_BLOCK_MAX) + return i2c_smbus_read_i2c_block_data(client, + command, length, values); + + while (suboffset < length) { + s32 retval = i2c_smbus_read_i2c_block_data(client, + command + suboffset, + min(I2C_SMBUS_BLOCK_MAX, length - suboffset), + values + suboffset); + if (retval < 0) + return retval; + + suboffset += I2C_SMBUS_BLOCK_MAX; + } + return length; +} + +/*----------------------------------------------------------------------*/ + /* * The IRQ logic includes a "real" handler running in IRQ context just * long enough to schedule this workqueue entry. We need a task context @@ -322,12 +374,7 @@ static int ds1307_get_time(struct device *dev, struct rtc_time *t) return -EIO; } - dev_dbg(dev, "%s: %02x %02x %02x %02x %02x %02x %02x\n", - "read", - ds1307->regs[0], ds1307->regs[1], - ds1307->regs[2], ds1307->regs[3], - ds1307->regs[4], ds1307->regs[5], - ds1307->regs[6]); + dev_dbg(dev, "%s: %7ph\n", "read", ds1307->regs); t->tm_sec = bcd2bin(ds1307->regs[DS1307_REG_SECS] & 0x7f); t->tm_min = bcd2bin(ds1307->regs[DS1307_REG_MIN] & 0x7f); @@ -398,9 +445,7 @@ static int ds1307_set_time(struct device *dev, struct rtc_time *t) break; } - dev_dbg(dev, "%s: %02x %02x %02x %02x %02x %02x %02x\n", - "write", buf[0], buf[1], buf[2], buf[3], - buf[4], buf[5], buf[6]); + dev_dbg(dev, "%s: %7ph\n", "write", buf); result = ds1307->write_block_data(ds1307->client, ds1307->offset, 7, buf); @@ -653,8 +698,8 @@ static int ds1307_probe(struct i2c_client *client, buf = ds1307->regs; if (i2c_check_functionality(adapter, I2C_FUNC_SMBUS_I2C_BLOCK)) { - ds1307->read_block_data = i2c_smbus_read_i2c_block_data; - ds1307->write_block_data = i2c_smbus_write_i2c_block_data; + ds1307->read_block_data = ds1307_native_smbus_read_block_data; + ds1307->write_block_data = ds1307_native_smbus_write_block_data; } else { ds1307->read_block_data = ds1307_read_block_data; ds1307->write_block_data = ds1307_write_block_data; diff --git a/drivers/rtc/rtc-ds2404.c b/drivers/rtc/rtc-ds2404.c index 5ea9df7c8c31..4539e37c2238 100644 --- a/drivers/rtc/rtc-ds2404.c +++ b/drivers/rtc/rtc-ds2404.c @@ -283,19 +283,7 @@ static struct platform_driver rtc_device_driver = { .owner = THIS_MODULE, }, }; - -static __init int ds2404_init(void) -{ - return platform_driver_register(&rtc_device_driver); -} - -static __exit void ds2404_exit(void) -{ - platform_driver_unregister(&rtc_device_driver); -} - -module_init(ds2404_init); -module_exit(ds2404_exit); +module_platform_driver(rtc_device_driver); MODULE_DESCRIPTION("DS2404 RTC"); MODULE_AUTHOR("Sven Schnelle"); diff --git a/drivers/rtc/rtc-fm3130.c b/drivers/rtc/rtc-fm3130.c index 04e93c6597f8..bff3cdc5140e 100644 --- a/drivers/rtc/rtc-fm3130.c +++ b/drivers/rtc/rtc-fm3130.c @@ -116,17 +116,7 @@ static int fm3130_get_time(struct device *dev, struct rtc_time *t) fm3130_rtc_mode(dev, FM3130_MODE_NORMAL); - dev_dbg(dev, "%s: %02x %02x %02x %02x %02x %02x %02x %02x" - "%02x %02x %02x %02x %02x %02x %02x\n", - "read", - fm3130->regs[0], fm3130->regs[1], - fm3130->regs[2], fm3130->regs[3], - fm3130->regs[4], fm3130->regs[5], - fm3130->regs[6], fm3130->regs[7], - fm3130->regs[8], fm3130->regs[9], - fm3130->regs[0xa], fm3130->regs[0xb], - fm3130->regs[0xc], fm3130->regs[0xd], - fm3130->regs[0xe]); + dev_dbg(dev, "%s: %15ph\n", "read", fm3130->regs); t->tm_sec = bcd2bin(fm3130->regs[FM3130_RTC_SECONDS] & 0x7f); t->tm_min = bcd2bin(fm3130->regs[FM3130_RTC_MINUTES] & 0x7f); @@ -175,12 +165,7 @@ static int fm3130_set_time(struct device *dev, struct rtc_time *t) tmp = t->tm_year - 100; buf[FM3130_RTC_YEARS] = bin2bcd(tmp); - dev_dbg(dev, "%s: %02x %02x %02x %02x %02x %02x %02x" - "%02x %02x %02x %02x %02x %02x %02x %02x\n", - "write", buf[0], buf[1], buf[2], buf[3], - buf[4], buf[5], buf[6], buf[7], - buf[8], buf[9], buf[0xa], buf[0xb], - buf[0xc], buf[0xd], buf[0xe]); + dev_dbg(dev, "%s: %15ph\n", "write", buf); fm3130_rtc_mode(dev, FM3130_MODE_WRITE); @@ -517,18 +502,8 @@ bad_alarm: bad_clock: if (!fm3130->data_valid || !fm3130->alarm_valid) - dev_dbg(&client->dev, - "%s: %02x %02x %02x %02x %02x %02x %02x %02x" - "%02x %02x %02x %02x %02x %02x %02x\n", - "bogus registers", - fm3130->regs[0], fm3130->regs[1], - fm3130->regs[2], fm3130->regs[3], - fm3130->regs[4], fm3130->regs[5], - fm3130->regs[6], fm3130->regs[7], - fm3130->regs[8], fm3130->regs[9], - fm3130->regs[0xa], fm3130->regs[0xb], - fm3130->regs[0xc], fm3130->regs[0xd], - fm3130->regs[0xe]); + dev_dbg(&client->dev, "%s: %15ph\n", "bogus registers", + fm3130->regs); /* We won't bail out here because we just got invalid data. Time setting from u-boot doesn't work anyway */ diff --git a/drivers/rtc/rtc-isl12022.c b/drivers/rtc/rtc-isl12022.c index 1850104705c0..6b4298ea683d 100644 --- a/drivers/rtc/rtc-isl12022.c +++ b/drivers/rtc/rtc-isl12022.c @@ -227,7 +227,7 @@ static int isl12022_set_datetime(struct i2c_client *client, struct rtc_time *tm) buf[ISL12022_REG_SC + i]); if (ret) return -EIO; - }; + } return 0; } diff --git a/drivers/rtc/rtc-lp8788.c b/drivers/rtc/rtc-lp8788.c new file mode 100644 index 000000000000..4a4e78e2231c --- /dev/null +++ b/drivers/rtc/rtc-lp8788.c @@ -0,0 +1,344 @@ +/* + * TI LP8788 MFD - rtc driver + * + * Copyright 2012 Texas Instruments + * + * Author: Milo(Woogyom) Kim <milo.kim@ti.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include <linux/err.h> +#include <linux/irqdomain.h> +#include <linux/mfd/lp8788.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/rtc.h> +#include <linux/slab.h> + +/* register address */ +#define LP8788_INTEN_3 0x05 +#define LP8788_RTC_UNLOCK 0x64 +#define LP8788_RTC_SEC 0x70 +#define LP8788_ALM1_SEC 0x77 +#define LP8788_ALM1_EN 0x7D +#define LP8788_ALM2_SEC 0x7E +#define LP8788_ALM2_EN 0x84 + +/* mask/shift bits */ +#define LP8788_INT_RTC_ALM1_M BIT(1) /* Addr 05h */ +#define LP8788_INT_RTC_ALM1_S 1 +#define LP8788_INT_RTC_ALM2_M BIT(2) /* Addr 05h */ +#define LP8788_INT_RTC_ALM2_S 2 +#define LP8788_ALM_EN_M BIT(7) /* Addr 7Dh or 84h */ +#define LP8788_ALM_EN_S 7 + +#define DEFAULT_ALARM_SEL LP8788_ALARM_1 +#define LP8788_MONTH_OFFSET 1 +#define LP8788_BASE_YEAR 2000 +#define MAX_WDAY_BITS 7 +#define LP8788_WDAY_SET 1 +#define RTC_UNLOCK 0x1 +#define RTC_LATCH 0x2 +#define ALARM_IRQ_FLAG (RTC_IRQF | RTC_AF) + +enum lp8788_time { + LPTIME_SEC, + LPTIME_MIN, + LPTIME_HOUR, + LPTIME_MDAY, + LPTIME_MON, + LPTIME_YEAR, + LPTIME_WDAY, + LPTIME_MAX, +}; + +struct lp8788_rtc { + struct lp8788 *lp; + struct rtc_device *rdev; + enum lp8788_alarm_sel alarm; + int irq; +}; + +static const u8 addr_alarm_sec[LP8788_ALARM_MAX] = { + LP8788_ALM1_SEC, + LP8788_ALM2_SEC, +}; + +static const u8 addr_alarm_en[LP8788_ALARM_MAX] = { + LP8788_ALM1_EN, + LP8788_ALM2_EN, +}; + +static const u8 mask_alarm_en[LP8788_ALARM_MAX] = { + LP8788_INT_RTC_ALM1_M, + LP8788_INT_RTC_ALM2_M, +}; + +static const u8 shift_alarm_en[LP8788_ALARM_MAX] = { + LP8788_INT_RTC_ALM1_S, + LP8788_INT_RTC_ALM2_S, +}; + +static int _to_tm_wday(u8 lp8788_wday) +{ + int i; + + if (lp8788_wday == 0) + return 0; + + /* lookup defined weekday from read register value */ + for (i = 0; i < MAX_WDAY_BITS; i++) { + if ((lp8788_wday >> i) == LP8788_WDAY_SET) + break; + } + + return i + 1; +} + +static inline int _to_lp8788_wday(int tm_wday) +{ + return LP8788_WDAY_SET << (tm_wday - 1); +} + +static void lp8788_rtc_unlock(struct lp8788 *lp) +{ + lp8788_write_byte(lp, LP8788_RTC_UNLOCK, RTC_UNLOCK); + lp8788_write_byte(lp, LP8788_RTC_UNLOCK, RTC_LATCH); +} + +static int lp8788_rtc_read_time(struct device *dev, struct rtc_time *tm) +{ + struct lp8788_rtc *rtc = dev_get_drvdata(dev); + struct lp8788 *lp = rtc->lp; + u8 data[LPTIME_MAX]; + int ret; + + lp8788_rtc_unlock(lp); + + ret = lp8788_read_multi_bytes(lp, LP8788_RTC_SEC, data, LPTIME_MAX); + if (ret) + return ret; + + tm->tm_sec = data[LPTIME_SEC]; + tm->tm_min = data[LPTIME_MIN]; + tm->tm_hour = data[LPTIME_HOUR]; + tm->tm_mday = data[LPTIME_MDAY]; + tm->tm_mon = data[LPTIME_MON] - LP8788_MONTH_OFFSET; + tm->tm_year = data[LPTIME_YEAR] + LP8788_BASE_YEAR - 1900; + tm->tm_wday = _to_tm_wday(data[LPTIME_WDAY]); + + return 0; +} + +static int lp8788_rtc_set_time(struct device *dev, struct rtc_time *tm) +{ + struct lp8788_rtc *rtc = dev_get_drvdata(dev); + struct lp8788 *lp = rtc->lp; + u8 data[LPTIME_MAX - 1]; + int ret, i, year; + + year = tm->tm_year + 1900 - LP8788_BASE_YEAR; + if (year < 0) { + dev_err(lp->dev, "invalid year: %d\n", year); + return -EINVAL; + } + + /* because rtc weekday is a readonly register, do not update */ + data[LPTIME_SEC] = tm->tm_sec; + data[LPTIME_MIN] = tm->tm_min; + data[LPTIME_HOUR] = tm->tm_hour; + data[LPTIME_MDAY] = tm->tm_mday; + data[LPTIME_MON] = tm->tm_mon + LP8788_MONTH_OFFSET; + data[LPTIME_YEAR] = year; + + for (i = 0; i < ARRAY_SIZE(data); i++) { + ret = lp8788_write_byte(lp, LP8788_RTC_SEC + i, data[i]); + if (ret) + return ret; + } + + return 0; +} + +static int lp8788_read_alarm(struct device *dev, struct rtc_wkalrm *alarm) +{ + struct lp8788_rtc *rtc = dev_get_drvdata(dev); + struct lp8788 *lp = rtc->lp; + struct rtc_time *tm = &alarm->time; + u8 addr, data[LPTIME_MAX]; + int ret; + + addr = addr_alarm_sec[rtc->alarm]; + ret = lp8788_read_multi_bytes(lp, addr, data, LPTIME_MAX); + if (ret) + return ret; + + tm->tm_sec = data[LPTIME_SEC]; + tm->tm_min = data[LPTIME_MIN]; + tm->tm_hour = data[LPTIME_HOUR]; + tm->tm_mday = data[LPTIME_MDAY]; + tm->tm_mon = data[LPTIME_MON] - LP8788_MONTH_OFFSET; + tm->tm_year = data[LPTIME_YEAR] + LP8788_BASE_YEAR - 1900; + tm->tm_wday = _to_tm_wday(data[LPTIME_WDAY]); + alarm->enabled = data[LPTIME_WDAY] & LP8788_ALM_EN_M; + + return 0; +} + +static int lp8788_set_alarm(struct device *dev, struct rtc_wkalrm *alarm) +{ + struct lp8788_rtc *rtc = dev_get_drvdata(dev); + struct lp8788 *lp = rtc->lp; + struct rtc_time *tm = &alarm->time; + u8 addr, data[LPTIME_MAX]; + int ret, i, year; + + year = tm->tm_year + 1900 - LP8788_BASE_YEAR; + if (year < 0) { + dev_err(lp->dev, "invalid year: %d\n", year); + return -EINVAL; + } + + data[LPTIME_SEC] = tm->tm_sec; + data[LPTIME_MIN] = tm->tm_min; + data[LPTIME_HOUR] = tm->tm_hour; + data[LPTIME_MDAY] = tm->tm_mday; + data[LPTIME_MON] = tm->tm_mon + LP8788_MONTH_OFFSET; + data[LPTIME_YEAR] = year; + data[LPTIME_WDAY] = _to_lp8788_wday(tm->tm_wday); + + for (i = 0; i < ARRAY_SIZE(data); i++) { + addr = addr_alarm_sec[rtc->alarm] + i; + ret = lp8788_write_byte(lp, addr, data[i]); + if (ret) + return ret; + } + + alarm->enabled = 1; + addr = addr_alarm_en[rtc->alarm]; + + return lp8788_update_bits(lp, addr, LP8788_ALM_EN_M, + alarm->enabled << LP8788_ALM_EN_S); +} + +static int lp8788_alarm_irq_enable(struct device *dev, unsigned int enable) +{ + struct lp8788_rtc *rtc = dev_get_drvdata(dev); + struct lp8788 *lp = rtc->lp; + u8 mask, shift; + + if (!rtc->irq) + return -EIO; + + mask = mask_alarm_en[rtc->alarm]; + shift = shift_alarm_en[rtc->alarm]; + + return lp8788_update_bits(lp, LP8788_INTEN_3, mask, enable << shift); +} + +static const struct rtc_class_ops lp8788_rtc_ops = { + .read_time = lp8788_rtc_read_time, + .set_time = lp8788_rtc_set_time, + .read_alarm = lp8788_read_alarm, + .set_alarm = lp8788_set_alarm, + .alarm_irq_enable = lp8788_alarm_irq_enable, +}; + +static irqreturn_t lp8788_alarm_irq_handler(int irq, void *ptr) +{ + struct lp8788_rtc *rtc = ptr; + + rtc_update_irq(rtc->rdev, 1, ALARM_IRQ_FLAG); + return IRQ_HANDLED; +} + +static int lp8788_alarm_irq_register(struct platform_device *pdev, + struct lp8788_rtc *rtc) +{ + struct resource *r; + struct lp8788 *lp = rtc->lp; + struct irq_domain *irqdm = lp->irqdm; + int irq; + + rtc->irq = 0; + + /* even the alarm IRQ number is not specified, rtc time should work */ + r = platform_get_resource_byname(pdev, IORESOURCE_IRQ, LP8788_ALM_IRQ); + if (!r) + return 0; + + if (rtc->alarm == LP8788_ALARM_1) + irq = r->start; + else + irq = r->end; + + rtc->irq = irq_create_mapping(irqdm, irq); + + return request_threaded_irq(rtc->irq, NULL, lp8788_alarm_irq_handler, + 0, LP8788_ALM_IRQ, rtc); +} + +static void lp8788_alarm_irq_unregister(struct lp8788_rtc *rtc) +{ + if (rtc->irq) + free_irq(rtc->irq, rtc); +} + +static int lp8788_rtc_probe(struct platform_device *pdev) +{ + struct lp8788 *lp = dev_get_drvdata(pdev->dev.parent); + struct lp8788_rtc *rtc; + struct device *dev = &pdev->dev; + + rtc = devm_kzalloc(dev, sizeof(struct lp8788_rtc), GFP_KERNEL); + if (!rtc) + return -ENOMEM; + + rtc->lp = lp; + rtc->alarm = lp->pdata ? lp->pdata->alarm_sel : DEFAULT_ALARM_SEL; + platform_set_drvdata(pdev, rtc); + + device_init_wakeup(dev, 1); + + rtc->rdev = rtc_device_register("lp8788_rtc", dev, + &lp8788_rtc_ops, THIS_MODULE); + if (IS_ERR(rtc->rdev)) { + dev_err(dev, "can not register rtc device\n"); + return PTR_ERR(rtc->rdev); + } + + if (lp8788_alarm_irq_register(pdev, rtc)) + dev_warn(lp->dev, "no rtc irq handler\n"); + + return 0; +} + +static int lp8788_rtc_remove(struct platform_device *pdev) +{ + struct lp8788_rtc *rtc = platform_get_drvdata(pdev); + + lp8788_alarm_irq_unregister(rtc); + rtc_device_unregister(rtc->rdev); + platform_set_drvdata(pdev, NULL); + + return 0; +} + +static struct platform_driver lp8788_rtc_driver = { + .probe = lp8788_rtc_probe, + .remove = lp8788_rtc_remove, + .driver = { + .name = LP8788_DEV_RTC, + .owner = THIS_MODULE, + }, +}; +module_platform_driver(lp8788_rtc_driver); + +MODULE_DESCRIPTION("Texas Instruments LP8788 RTC Driver"); +MODULE_AUTHOR("Milo Kim"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:lp8788-rtc"); diff --git a/drivers/rtc/rtc-max77686.c b/drivers/rtc/rtc-max77686.c new file mode 100644 index 000000000000..2da0855b742f --- /dev/null +++ b/drivers/rtc/rtc-max77686.c @@ -0,0 +1,645 @@ +/* + * RTC driver for Maxim MAX77686 + * + * Copyright (C) 2012 Samsung Electronics Co.Ltd + * + * based on rtc-max8997.c + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + */ + +#include <linux/slab.h> +#include <linux/rtc.h> +#include <linux/delay.h> +#include <linux/mutex.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/mfd/max77686-private.h> +#include <linux/irqdomain.h> +#include <linux/regmap.h> + +/* RTC Control Register */ +#define BCD_EN_SHIFT 0 +#define BCD_EN_MASK (1 << BCD_EN_SHIFT) +#define MODEL24_SHIFT 1 +#define MODEL24_MASK (1 << MODEL24_SHIFT) +/* RTC Update Register1 */ +#define RTC_UDR_SHIFT 0 +#define RTC_UDR_MASK (1 << RTC_UDR_SHIFT) +#define RTC_RBUDR_SHIFT 4 +#define RTC_RBUDR_MASK (1 << RTC_RBUDR_SHIFT) +/* WTSR and SMPL Register */ +#define WTSRT_SHIFT 0 +#define SMPLT_SHIFT 2 +#define WTSR_EN_SHIFT 6 +#define SMPL_EN_SHIFT 7 +#define WTSRT_MASK (3 << WTSRT_SHIFT) +#define SMPLT_MASK (3 << SMPLT_SHIFT) +#define WTSR_EN_MASK (1 << WTSR_EN_SHIFT) +#define SMPL_EN_MASK (1 << SMPL_EN_SHIFT) +/* RTC Hour register */ +#define HOUR_PM_SHIFT 6 +#define HOUR_PM_MASK (1 << HOUR_PM_SHIFT) +/* RTC Alarm Enable */ +#define ALARM_ENABLE_SHIFT 7 +#define ALARM_ENABLE_MASK (1 << ALARM_ENABLE_SHIFT) + +#define MAX77686_RTC_UPDATE_DELAY 16 +#undef MAX77686_RTC_WTSR_SMPL + +enum { + RTC_SEC = 0, + RTC_MIN, + RTC_HOUR, + RTC_WEEKDAY, + RTC_MONTH, + RTC_YEAR, + RTC_DATE, + RTC_NR_TIME +}; + +struct max77686_rtc_info { + struct device *dev; + struct max77686_dev *max77686; + struct i2c_client *rtc; + struct rtc_device *rtc_dev; + struct mutex lock; + + struct regmap *regmap; + + int virq; + int rtc_24hr_mode; +}; + +enum MAX77686_RTC_OP { + MAX77686_RTC_WRITE, + MAX77686_RTC_READ, +}; + +static inline int max77686_rtc_calculate_wday(u8 shifted) +{ + int counter = -1; + while (shifted) { + shifted >>= 1; + counter++; + } + return counter; +} + +static void max77686_rtc_data_to_tm(u8 *data, struct rtc_time *tm, + int rtc_24hr_mode) +{ + tm->tm_sec = data[RTC_SEC] & 0x7f; + tm->tm_min = data[RTC_MIN] & 0x7f; + if (rtc_24hr_mode) + tm->tm_hour = data[RTC_HOUR] & 0x1f; + else { + tm->tm_hour = data[RTC_HOUR] & 0x0f; + if (data[RTC_HOUR] & HOUR_PM_MASK) + tm->tm_hour += 12; + } + + tm->tm_wday = max77686_rtc_calculate_wday(data[RTC_WEEKDAY] & 0x7f); + tm->tm_mday = data[RTC_DATE] & 0x1f; + tm->tm_mon = (data[RTC_MONTH] & 0x0f) - 1; + tm->tm_year = (data[RTC_YEAR] & 0x7f) + 100; + tm->tm_yday = 0; + tm->tm_isdst = 0; +} + +static int max77686_rtc_tm_to_data(struct rtc_time *tm, u8 *data) +{ + data[RTC_SEC] = tm->tm_sec; + data[RTC_MIN] = tm->tm_min; + data[RTC_HOUR] = tm->tm_hour; + data[RTC_WEEKDAY] = 1 << tm->tm_wday; + data[RTC_DATE] = tm->tm_mday; + data[RTC_MONTH] = tm->tm_mon + 1; + data[RTC_YEAR] = tm->tm_year > 100 ? (tm->tm_year - 100) : 0 ; + + if (tm->tm_year < 100) { + pr_warn("%s: MAX77686 RTC cannot handle the year %d." + "Assume it's 2000.\n", __func__, 1900 + tm->tm_year); + return -EINVAL; + } + return 0; +} + +static int max77686_rtc_update(struct max77686_rtc_info *info, + enum MAX77686_RTC_OP op) +{ + int ret; + unsigned int data; + + switch (op) { + case MAX77686_RTC_WRITE: + data = 1 << RTC_UDR_SHIFT; + break; + case MAX77686_RTC_READ: + data = 1 << RTC_RBUDR_SHIFT; + break; + } + + ret = regmap_update_bits(info->max77686->rtc_regmap, + MAX77686_RTC_UPDATE0, data, data); + if (ret < 0) + dev_err(info->dev, "%s: fail to write update reg(ret=%d, data=0x%x)\n", + __func__, ret, data); + else { + /* Minimum 16ms delay required before RTC update. */ + msleep(MAX77686_RTC_UPDATE_DELAY); + } + + return ret; +} + +static int max77686_rtc_read_time(struct device *dev, struct rtc_time *tm) +{ + struct max77686_rtc_info *info = dev_get_drvdata(dev); + u8 data[RTC_NR_TIME]; + int ret; + + mutex_lock(&info->lock); + + ret = max77686_rtc_update(info, MAX77686_RTC_READ); + if (ret < 0) + goto out; + + ret = regmap_bulk_read(info->max77686->rtc_regmap, + MAX77686_RTC_SEC, data, RTC_NR_TIME); + if (ret < 0) { + dev_err(info->dev, "%s: fail to read time reg(%d)\n", __func__, ret); + goto out; + } + + max77686_rtc_data_to_tm(data, tm, info->rtc_24hr_mode); + + ret = rtc_valid_tm(tm); + +out: + mutex_unlock(&info->lock); + return ret; +} + +static int max77686_rtc_set_time(struct device *dev, struct rtc_time *tm) +{ + struct max77686_rtc_info *info = dev_get_drvdata(dev); + u8 data[RTC_NR_TIME]; + int ret; + + ret = max77686_rtc_tm_to_data(tm, data); + if (ret < 0) + return ret; + + mutex_lock(&info->lock); + + ret = regmap_bulk_write(info->max77686->rtc_regmap, + MAX77686_RTC_SEC, data, RTC_NR_TIME); + if (ret < 0) { + dev_err(info->dev, "%s: fail to write time reg(%d)\n", __func__, + ret); + goto out; + } + + ret = max77686_rtc_update(info, MAX77686_RTC_WRITE); + +out: + mutex_unlock(&info->lock); + return ret; +} + +static int max77686_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm) +{ + struct max77686_rtc_info *info = dev_get_drvdata(dev); + u8 data[RTC_NR_TIME]; + unsigned int val; + int i, ret; + + mutex_lock(&info->lock); + + ret = max77686_rtc_update(info, MAX77686_RTC_READ); + if (ret < 0) + goto out; + + ret = regmap_bulk_read(info->max77686->rtc_regmap, + MAX77686_ALARM1_SEC, data, RTC_NR_TIME); + if (ret < 0) { + dev_err(info->dev, "%s:%d fail to read alarm reg(%d)\n", + __func__, __LINE__, ret); + goto out; + } + + max77686_rtc_data_to_tm(data, &alrm->time, info->rtc_24hr_mode); + + alrm->enabled = 0; + for (i = 0; i < RTC_NR_TIME; i++) { + if (data[i] & ALARM_ENABLE_MASK) { + alrm->enabled = 1; + break; + } + } + + alrm->pending = 0; + ret = regmap_read(info->max77686->regmap, MAX77686_REG_STATUS1, &val); + if (ret < 0) { + dev_err(info->dev, "%s:%d fail to read status1 reg(%d)\n", + __func__, __LINE__, ret); + goto out; + } + + if (val & (1 << 4)) /* RTCA1 */ + alrm->pending = 1; + +out: + mutex_unlock(&info->lock); + return 0; +} + +static int max77686_rtc_stop_alarm(struct max77686_rtc_info *info) +{ + u8 data[RTC_NR_TIME]; + int ret, i; + struct rtc_time tm; + + if (!mutex_is_locked(&info->lock)) + dev_warn(info->dev, "%s: should have mutex locked\n", __func__); + + ret = max77686_rtc_update(info, MAX77686_RTC_READ); + if (ret < 0) + goto out; + + ret = regmap_bulk_read(info->max77686->rtc_regmap, + MAX77686_ALARM1_SEC, data, RTC_NR_TIME); + if (ret < 0) { + dev_err(info->dev, "%s: fail to read alarm reg(%d)\n", + __func__, ret); + goto out; + } + + max77686_rtc_data_to_tm(data, &tm, info->rtc_24hr_mode); + + for (i = 0; i < RTC_NR_TIME; i++) + data[i] &= ~ALARM_ENABLE_MASK; + + ret = regmap_bulk_write(info->max77686->rtc_regmap, + MAX77686_ALARM1_SEC, data, RTC_NR_TIME); + if (ret < 0) { + dev_err(info->dev, "%s: fail to write alarm reg(%d)\n", + __func__, ret); + goto out; + } + + ret = max77686_rtc_update(info, MAX77686_RTC_WRITE); +out: + return ret; +} + +static int max77686_rtc_start_alarm(struct max77686_rtc_info *info) +{ + u8 data[RTC_NR_TIME]; + int ret; + struct rtc_time tm; + + if (!mutex_is_locked(&info->lock)) + dev_warn(info->dev, "%s: should have mutex locked\n", __func__); + + ret = max77686_rtc_update(info, MAX77686_RTC_READ); + if (ret < 0) + goto out; + + ret = regmap_bulk_read(info->max77686->rtc_regmap, + MAX77686_ALARM1_SEC, data, RTC_NR_TIME); + if (ret < 0) { + dev_err(info->dev, "%s: fail to read alarm reg(%d)\n", + __func__, ret); + goto out; + } + + max77686_rtc_data_to_tm(data, &tm, info->rtc_24hr_mode); + + data[RTC_SEC] |= (1 << ALARM_ENABLE_SHIFT); + data[RTC_MIN] |= (1 << ALARM_ENABLE_SHIFT); + data[RTC_HOUR] |= (1 << ALARM_ENABLE_SHIFT); + data[RTC_WEEKDAY] &= ~ALARM_ENABLE_MASK; + if (data[RTC_MONTH] & 0xf) + data[RTC_MONTH] |= (1 << ALARM_ENABLE_SHIFT); + if (data[RTC_YEAR] & 0x7f) + data[RTC_YEAR] |= (1 << ALARM_ENABLE_SHIFT); + if (data[RTC_DATE] & 0x1f) + data[RTC_DATE] |= (1 << ALARM_ENABLE_SHIFT); + + ret = regmap_bulk_write(info->max77686->rtc_regmap, + MAX77686_ALARM1_SEC, data, RTC_NR_TIME); + if (ret < 0) { + dev_err(info->dev, "%s: fail to write alarm reg(%d)\n", + __func__, ret); + goto out; + } + + ret = max77686_rtc_update(info, MAX77686_RTC_WRITE); +out: + return ret; +} + +static int max77686_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm) +{ + struct max77686_rtc_info *info = dev_get_drvdata(dev); + u8 data[RTC_NR_TIME]; + int ret; + + ret = max77686_rtc_tm_to_data(&alrm->time, data); + if (ret < 0) + return ret; + + mutex_lock(&info->lock); + + ret = max77686_rtc_stop_alarm(info); + if (ret < 0) + goto out; + + ret = regmap_bulk_write(info->max77686->rtc_regmap, + MAX77686_ALARM1_SEC, data, RTC_NR_TIME); + + if (ret < 0) { + dev_err(info->dev, "%s: fail to write alarm reg(%d)\n", + __func__, ret); + goto out; + } + + ret = max77686_rtc_update(info, MAX77686_RTC_WRITE); + if (ret < 0) + goto out; + + if (alrm->enabled) + ret = max77686_rtc_start_alarm(info); +out: + mutex_unlock(&info->lock); + return ret; +} + +static int max77686_rtc_alarm_irq_enable(struct device *dev, + unsigned int enabled) +{ + struct max77686_rtc_info *info = dev_get_drvdata(dev); + int ret; + + mutex_lock(&info->lock); + if (enabled) + ret = max77686_rtc_start_alarm(info); + else + ret = max77686_rtc_stop_alarm(info); + mutex_unlock(&info->lock); + + return ret; +} + +static irqreturn_t max77686_rtc_alarm_irq(int irq, void *data) +{ + struct max77686_rtc_info *info = data; + + dev_info(info->dev, "%s:irq(%d)\n", __func__, irq); + + rtc_update_irq(info->rtc_dev, 1, RTC_IRQF | RTC_AF); + + return IRQ_HANDLED; +} + +static const struct rtc_class_ops max77686_rtc_ops = { + .read_time = max77686_rtc_read_time, + .set_time = max77686_rtc_set_time, + .read_alarm = max77686_rtc_read_alarm, + .set_alarm = max77686_rtc_set_alarm, + .alarm_irq_enable = max77686_rtc_alarm_irq_enable, +}; + +#ifdef MAX77686_RTC_WTSR_SMPL +static void max77686_rtc_enable_wtsr(struct max77686_rtc_info *info, bool enable) +{ + int ret; + unsigned int val, mask; + + if (enable) + val = (1 << WTSR_EN_SHIFT) | (3 << WTSRT_SHIFT); + else + val = 0; + + mask = WTSR_EN_MASK | WTSRT_MASK; + + dev_info(info->dev, "%s: %s WTSR\n", __func__, + enable ? "enable" : "disable"); + + ret = regmap_update_bits(info->max77686->rtc_regmap, + MAX77686_WTSR_SMPL_CNTL, mask, val); + if (ret < 0) { + dev_err(info->dev, "%s: fail to update WTSR reg(%d)\n", + __func__, ret); + return; + } + + max77686_rtc_update(info, MAX77686_RTC_WRITE); +} + +static void max77686_rtc_enable_smpl(struct max77686_rtc_info *info, bool enable) +{ + int ret; + unsigned int val, mask; + + if (enable) + val = (1 << SMPL_EN_SHIFT) | (0 << SMPLT_SHIFT); + else + val = 0; + + mask = SMPL_EN_MASK | SMPLT_MASK; + + dev_info(info->dev, "%s: %s SMPL\n", __func__, + enable ? "enable" : "disable"); + + ret = regmap_update_bits(info->max77686->rtc_regmap, + MAX77686_WTSR_SMPL_CNTL, mask, val); + if (ret < 0) { + dev_err(info->dev, "%s: fail to update SMPL reg(%d)\n", + __func__, ret); + return; + } + + max77686_rtc_update(info, MAX77686_RTC_WRITE); + + val = 0; + regmap_read(info->max77686->rtc_regmap, MAX77686_WTSR_SMPL_CNTL, &val); + pr_info("%s: WTSR_SMPL(0x%02x)\n", __func__, val); +} +#endif /* MAX77686_RTC_WTSR_SMPL */ + +static int max77686_rtc_init_reg(struct max77686_rtc_info *info) +{ + u8 data[2]; + int ret; + + /* Set RTC control register : Binary mode, 24hour mdoe */ + data[0] = (1 << BCD_EN_SHIFT) | (1 << MODEL24_SHIFT); + data[1] = (0 << BCD_EN_SHIFT) | (1 << MODEL24_SHIFT); + + info->rtc_24hr_mode = 1; + + ret = regmap_bulk_write(info->max77686->rtc_regmap, MAX77686_RTC_CONTROLM, data, 2); + if (ret < 0) { + dev_err(info->dev, "%s: fail to write controlm reg(%d)\n", + __func__, ret); + return ret; + } + + ret = max77686_rtc_update(info, MAX77686_RTC_WRITE); + return ret; +} + +static struct regmap_config max77686_rtc_regmap_config = { + .reg_bits = 8, + .val_bits = 8, +}; + +static int max77686_rtc_probe(struct platform_device *pdev) +{ + struct max77686_dev *max77686 = dev_get_drvdata(pdev->dev.parent); + struct max77686_rtc_info *info; + int ret, virq; + + printk(KERN_INFO "%s\n", __func__); + + info = kzalloc(sizeof(struct max77686_rtc_info), GFP_KERNEL); + if (!info) + return -ENOMEM; + + mutex_init(&info->lock); + info->dev = &pdev->dev; + info->max77686 = max77686; + info->rtc = max77686->rtc; + info->max77686->rtc_regmap = regmap_init_i2c(info->max77686->rtc, + &max77686_rtc_regmap_config); + if (IS_ERR(info->max77686->rtc_regmap)) { + ret = PTR_ERR(info->max77686->rtc_regmap); + dev_err(info->max77686->dev, "Failed to allocate register map: %d\n", + ret); + kfree(info); + return ret; + } + platform_set_drvdata(pdev, info); + + ret = max77686_rtc_init_reg(info); + + if (ret < 0) { + dev_err(&pdev->dev, "Failed to initialize RTC reg:%d\n", ret); + goto err_rtc; + } + +#ifdef MAX77686_RTC_WTSR_SMPL + max77686_rtc_enable_wtsr(info, true); + max77686_rtc_enable_smpl(info, true); +#endif + + device_init_wakeup(&pdev->dev, 1); + + info->rtc_dev = rtc_device_register("max77686-rtc", &pdev->dev, + &max77686_rtc_ops, THIS_MODULE); + + if (IS_ERR(info->rtc_dev)) { + printk(KERN_INFO "%s: fail\n", __func__); + + ret = PTR_ERR(info->rtc_dev); + dev_err(&pdev->dev, "Failed to register RTC device: %d\n", ret); + if (ret == 0) + ret = -EINVAL; + goto err_rtc; + } + virq = irq_create_mapping(max77686->irq_domain, MAX77686_RTCIRQ_RTCA1); + if (!virq) + goto err_rtc; + info->virq = virq; + + ret = request_threaded_irq(virq, NULL, max77686_rtc_alarm_irq, 0, + "rtc-alarm0", info); + if (ret < 0) { + dev_err(&pdev->dev, "Failed to request alarm IRQ: %d: %d\n", + info->virq, ret); + goto err_rtc; + } + + goto out; +err_rtc: + kfree(info); + return ret; +out: + return ret; +} + +static int max77686_rtc_remove(struct platform_device *pdev) +{ + struct max77686_rtc_info *info = platform_get_drvdata(pdev); + + if (info) { + free_irq(info->virq, info); + rtc_device_unregister(info->rtc_dev); + kfree(info); + } + + return 0; +} + +static void max77686_rtc_shutdown(struct platform_device *pdev) +{ +#ifdef MAX77686_RTC_WTSR_SMPL + struct max77686_rtc_info *info = platform_get_drvdata(pdev); + int i; + u8 val = 0; + + for (i = 0; i < 3; i++) { + max77686_rtc_enable_wtsr(info, false); + regmap_read(info->max77686->rtc_regmap, MAX77686_WTSR_SMPL_CNTL, &val); + pr_info("%s: WTSR_SMPL reg(0x%02x)\n", __func__, val); + if (val & WTSR_EN_MASK) + pr_emerg("%s: fail to disable WTSR\n", __func__); + else { + pr_info("%s: success to disable WTSR\n", __func__); + break; + } + } + + /* Disable SMPL when power off */ + max77686_rtc_enable_smpl(info, false); +#endif /* MAX77686_RTC_WTSR_SMPL */ +} + +static const struct platform_device_id rtc_id[] = { + { "max77686-rtc", 0 }, + {}, +}; + +static struct platform_driver max77686_rtc_driver = { + .driver = { + .name = "max77686-rtc", + .owner = THIS_MODULE, + }, + .probe = max77686_rtc_probe, + .remove = max77686_rtc_remove, + .shutdown = max77686_rtc_shutdown, + .id_table = rtc_id, +}; + +static int __init max77686_rtc_init(void) +{ + return platform_driver_register(&max77686_rtc_driver); +} +module_init(max77686_rtc_init); + +static void __exit max77686_rtc_exit(void) +{ + platform_driver_unregister(&max77686_rtc_driver); +} +module_exit(max77686_rtc_exit); + +MODULE_DESCRIPTION("Maxim MAX77686 RTC driver"); +MODULE_AUTHOR("<woong.byun@samsung.com>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/rtc/rtc-mpc5121.c b/drivers/rtc/rtc-mpc5121.c index bec10be96f84..bdcc60830aec 100644 --- a/drivers/rtc/rtc-mpc5121.c +++ b/drivers/rtc/rtc-mpc5121.c @@ -13,6 +13,7 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/rtc.h> +#include <linux/of.h> #include <linux/of_device.h> #include <linux/of_platform.h> #include <linux/io.h> @@ -403,17 +404,19 @@ static int mpc5121_rtc_remove(struct platform_device *op) return 0; } +#ifdef CONFIG_OF static struct of_device_id mpc5121_rtc_match[] = { { .compatible = "fsl,mpc5121-rtc", }, { .compatible = "fsl,mpc5200-rtc", }, {}, }; +#endif static struct platform_driver mpc5121_rtc_driver = { .driver = { .name = "mpc5121-rtc", .owner = THIS_MODULE, - .of_match_table = mpc5121_rtc_match, + .of_match_table = of_match_ptr(mpc5121_rtc_match), }, .probe = mpc5121_rtc_probe, .remove = mpc5121_rtc_remove, diff --git a/drivers/rtc/rtc-pcf8523.c b/drivers/rtc/rtc-pcf8523.c index be05a645f99e..889e3160e701 100644 --- a/drivers/rtc/rtc-pcf8523.c +++ b/drivers/rtc/rtc-pcf8523.c @@ -23,6 +23,7 @@ #define REG_CONTROL3_PM_VDD (1 << 6) /* switch-over disabled */ #define REG_CONTROL3_PM_DSM (1 << 5) /* direct switching mode */ #define REG_CONTROL3_PM_MASK 0xe0 +#define REG_CONTROL3_BLF (1 << 2) /* battery low bit, read-only */ #define REG_SECONDS 0x03 #define REG_SECONDS_OS (1 << 7) @@ -250,9 +251,39 @@ static int pcf8523_rtc_set_time(struct device *dev, struct rtc_time *tm) return pcf8523_start_rtc(client); } +#ifdef CONFIG_RTC_INTF_DEV +static int pcf8523_rtc_ioctl(struct device *dev, unsigned int cmd, + unsigned long arg) +{ + struct i2c_client *client = to_i2c_client(dev); + u8 value; + int ret = 0, err; + + switch (cmd) { + case RTC_VL_READ: + err = pcf8523_read(client, REG_CONTROL3, &value); + if (err < 0) + return err; + + if (value & REG_CONTROL3_BLF) + ret = 1; + + if (copy_to_user((void __user *)arg, &ret, sizeof(int))) + return -EFAULT; + + return 0; + default: + return -ENOIOCTLCMD; + } +} +#else +#define pcf8523_rtc_ioctl NULL +#endif + static const struct rtc_class_ops pcf8523_rtc_ops = { .read_time = pcf8523_rtc_read_time, .set_time = pcf8523_rtc_set_time, + .ioctl = pcf8523_rtc_ioctl, }; static int pcf8523_probe(struct i2c_client *client, diff --git a/drivers/rtc/rtc-pcf8563.c b/drivers/rtc/rtc-pcf8563.c index 7098ee89bd29..f7daf18a112e 100644 --- a/drivers/rtc/rtc-pcf8563.c +++ b/drivers/rtc/rtc-pcf8563.c @@ -181,7 +181,7 @@ static int pcf8563_set_datetime(struct i2c_client *client, struct rtc_time *tm) __func__, err, data[0], data[1]); return -EIO; } - }; + } return 0; } diff --git a/drivers/rtc/rtc-pl031.c b/drivers/rtc/rtc-pl031.c index 81c5077feff3..8900ea784817 100644 --- a/drivers/rtc/rtc-pl031.c +++ b/drivers/rtc/rtc-pl031.c @@ -384,6 +384,8 @@ static int pl031_probe(struct amba_device *adev, const struct amba_id *id) goto out_no_irq; } + device_init_wakeup(&adev->dev, 1); + return 0; out_no_irq: diff --git a/drivers/rtc/rtc-pxa.c b/drivers/rtc/rtc-pxa.c index f771b2ee4b18..b7e462978609 100644 --- a/drivers/rtc/rtc-pxa.c +++ b/drivers/rtc/rtc-pxa.c @@ -19,6 +19,7 @@ * */ +#include <linux/delay.h> #include <linux/init.h> #include <linux/platform_device.h> #include <linux/module.h> @@ -62,6 +63,10 @@ #define RYxR_MONTH_S 5 #define RYxR_MONTH_MASK (0xf << RYxR_MONTH_S) #define RYxR_DAY_MASK 0x1f +#define RDxR_WOM_S 20 +#define RDxR_WOM_MASK (0x7 << RDxR_WOM_S) +#define RDxR_DOW_S 17 +#define RDxR_DOW_MASK (0x7 << RDxR_DOW_S) #define RDxR_HOUR_S 12 #define RDxR_HOUR_MASK (0x1f << RDxR_HOUR_S) #define RDxR_MIN_S 6 @@ -76,21 +81,29 @@ #define RYAR1 0x1c #define RTCPICR 0x34 #define PIAR 0x38 +#define PSBR_RTC 0x00 #define rtc_readl(pxa_rtc, reg) \ __raw_readl((pxa_rtc)->base + (reg)) #define rtc_writel(pxa_rtc, reg, value) \ __raw_writel((value), (pxa_rtc)->base + (reg)) +#define rtc_readl_psbr(pxa_rtc, reg) \ + __raw_readl((pxa_rtc)->base_psbr + (reg)) +#define rtc_writel_psbr(pxa_rtc, reg, value) \ + __raw_writel((value), (pxa_rtc)->base_psbr + (reg)) struct pxa_rtc { struct resource *ress; + struct resource *ress_psbr; void __iomem *base; + void __iomem *base_psbr; int irq_1Hz; int irq_Alrm; struct rtc_device *rtc; spinlock_t lock; /* Protects this structure */ }; +static struct pxa_rtc *rtc_info; static u32 ryxr_calc(struct rtc_time *tm) { return ((tm->tm_year + 1900) << RYxR_YEAR_S) @@ -100,7 +113,10 @@ static u32 ryxr_calc(struct rtc_time *tm) static u32 rdxr_calc(struct rtc_time *tm) { - return (tm->tm_hour << RDxR_HOUR_S) | (tm->tm_min << RDxR_MIN_S) + return ((((tm->tm_mday + 6) / 7) << RDxR_WOM_S) & RDxR_WOM_MASK) + | (((tm->tm_wday + 1) << RDxR_DOW_S) & RDxR_DOW_MASK) + | (tm->tm_hour << RDxR_HOUR_S) + | (tm->tm_min << RDxR_MIN_S) | tm->tm_sec; } @@ -109,6 +125,7 @@ static void tm_calc(u32 rycr, u32 rdcr, struct rtc_time *tm) tm->tm_year = ((rycr & RYxR_YEAR_MASK) >> RYxR_YEAR_S) - 1900; tm->tm_mon = (((rycr & RYxR_MONTH_MASK) >> RYxR_MONTH_S)) - 1; tm->tm_mday = (rycr & RYxR_DAY_MASK); + tm->tm_wday = ((rdcr & RDxR_DOW_MASK) >> RDxR_DOW_S) - 1; tm->tm_hour = (rdcr & RDxR_HOUR_MASK) >> RDxR_HOUR_S; tm->tm_min = (rdcr & RDxR_MIN_MASK) >> RDxR_MIN_S; tm->tm_sec = rdcr & RDxR_SEC_MASK; @@ -166,7 +183,6 @@ static irqreturn_t pxa_rtc_irq(int irq, void *dev_id) /* enable back rtc interrupts */ rtc_writel(pxa_rtc, RTSR, rtsr & ~RTSR_TRIG_MASK); - spin_unlock(&pxa_rtc->lock); return IRQ_HANDLED; } @@ -241,12 +257,45 @@ static int pxa_rtc_read_time(struct device *dev, struct rtc_time *tm) static int pxa_rtc_set_time(struct device *dev, struct rtc_time *tm) { struct pxa_rtc *pxa_rtc = dev_get_drvdata(dev); - + /* sequence to wirte pxa rtc register RCNR RDCR RYCR is + *1. set PSBR[RWE] bit, take 2x32-khz to complete + *2. write to RTC register,take 2x32-khz to complete + *3. clear PSBR[RWE] bit,take 2x32-khz to complete + */ + if ((tm->tm_year < 70) || (tm->tm_year > 138)) + return -EINVAL; + rtc_writel_psbr(rtc_info, PSBR_RTC, 0x01); + udelay(100); rtc_writel(pxa_rtc, RYCR, ryxr_calc(tm)); rtc_writel(pxa_rtc, RDCR, rdxr_calc(tm)); + udelay(100); + rtc_writel_psbr(rtc_info, PSBR_RTC, 0x00); + udelay(100); + pxa_rtc_read_time(dev, tm); + dev_info(dev, "tm.year = %d, tm.month = %d, tm.day = %d\n", + tm->tm_year + 1900, tm->tm_mon, tm->tm_mday); + return 0; +} +int pxa_rtc_sync_time(unsigned int ticks) +{ + /* sequence to wirte pxa rtc register RCNR RDCR RYCR is + *1. set PSBR[RWE] bit, take 2x32-khz to complete + *2. write to RTC register,take 2x32-khz to complete + *3. clear PSBR[RWE] bit,take 2x32-khz to complete + */ + struct rtc_time tm; + rtc_time_to_tm(ticks, &tm); + rtc_writel_psbr(rtc_info, PSBR_RTC, 0x01); + udelay(100); + rtc_writel(rtc_info, RYCR, ryxr_calc(&tm)); + rtc_writel(rtc_info, RDCR, rdxr_calc(&tm)); + udelay(100); + rtc_writel_psbr(rtc_info, PSBR_RTC, 0x00); + udelay(100); return 0; } +EXPORT_SYMBOL(pxa_rtc_sync_time); static int pxa_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm) { @@ -300,8 +349,6 @@ static int pxa_rtc_proc(struct device *dev, struct seq_file *seq) } static const struct rtc_class_ops pxa_rtc_ops = { - .open = pxa_rtc_open, - .release = pxa_rtc_release, .read_time = pxa_rtc_read_time, .set_time = pxa_rtc_set_time, .read_alarm = pxa_rtc_read_alarm, @@ -320,7 +367,7 @@ static int __init pxa_rtc_probe(struct platform_device *pdev) pxa_rtc = kzalloc(sizeof(struct pxa_rtc), GFP_KERNEL); if (!pxa_rtc) return -ENOMEM; - + rtc_info = pxa_rtc; spin_lock_init(&pxa_rtc->lock); platform_set_drvdata(pdev, pxa_rtc); @@ -330,6 +377,11 @@ static int __init pxa_rtc_probe(struct platform_device *pdev) dev_err(dev, "No I/O memory resource defined\n"); goto err_ress; } + pxa_rtc->ress_psbr = platform_get_resource(pdev, IORESOURCE_MEM, 1); + if (!pxa_rtc->ress_psbr) { + dev_err(dev, "No I/O memory resource defined\n"); + goto err_ress; + } pxa_rtc->irq_1Hz = platform_get_irq(pdev, 0); if (pxa_rtc->irq_1Hz < 0) { @@ -341,7 +393,6 @@ static int __init pxa_rtc_probe(struct platform_device *pdev) dev_err(dev, "No alarm IRQ resource defined\n"); goto err_ress; } - ret = -ENOMEM; pxa_rtc->base = ioremap(pxa_rtc->ress->start, resource_size(pxa_rtc->ress)); @@ -350,6 +401,12 @@ static int __init pxa_rtc_probe(struct platform_device *pdev) goto err_map; } + pxa_rtc->base_psbr = ioremap(pxa_rtc->ress_psbr->start, + resource_size(pxa_rtc->ress_psbr)); + if (!pxa_rtc->base_psbr) { + dev_err(&pdev->dev, "Unable to map pxa RTC PSBR I/O memory\n"); + goto err_map; + } /* * If the clock divider is uninitialized then reset it to the * default value to get the 1Hz clock. @@ -372,7 +429,7 @@ static int __init pxa_rtc_probe(struct platform_device *pdev) } device_init_wakeup(dev, 1); - + pxa_rtc_open(dev); return 0; err_rtc_reg: @@ -387,6 +444,9 @@ static int __exit pxa_rtc_remove(struct platform_device *pdev) { struct pxa_rtc *pxa_rtc = platform_get_drvdata(pdev); + struct device *dev = &pdev->dev; + pxa_rtc_release(dev); + rtc_device_unregister(pxa_rtc->rtc); spin_lock_irq(&pxa_rtc->lock); @@ -444,10 +504,7 @@ static struct platform_driver pxa_rtc_driver = { static int __init pxa_rtc_init(void) { - if (cpu_is_pxa27x() || cpu_is_pxa3xx()) - return platform_driver_probe(&pxa_rtc_driver, pxa_rtc_probe); - - return -ENODEV; + return platform_driver_probe(&pxa_rtc_driver, pxa_rtc_probe); } static void __exit pxa_rtc_exit(void) diff --git a/drivers/rtc/rtc-rx4581.c b/drivers/rtc/rtc-rx4581.c new file mode 100644 index 000000000000..599ec73ec886 --- /dev/null +++ b/drivers/rtc/rtc-rx4581.c @@ -0,0 +1,314 @@ +/* drivers/rtc/rtc-rx4581.c + * + * written by Torben Hohn <torbenh@linutronix.de> + * + * Based on: + * drivers/rtc/rtc-max6902.c + * + * Copyright (C) 2006 8D Technologies inc. + * Copyright (C) 2004 Compulab Ltd. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Driver for MAX6902 spi RTC + * + * and based on: + * drivers/rtc/rtc-rx8581.c + * + * An I2C driver for the Epson RX8581 RTC + * + * Author: Martyn Welch <martyn.welch@ge.com> + * Copyright 2008 GE Intelligent Platforms Embedded Systems, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Based on: rtc-pcf8563.c (An I2C driver for the Philips PCF8563 RTC) + * Copyright 2005-06 Tower Technologies + * + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/platform_device.h> +#include <linux/init.h> +#include <linux/rtc.h> +#include <linux/spi/spi.h> +#include <linux/bcd.h> + +#define RX4581_REG_SC 0x00 /* Second in BCD */ +#define RX4581_REG_MN 0x01 /* Minute in BCD */ +#define RX4581_REG_HR 0x02 /* Hour in BCD */ +#define RX4581_REG_DW 0x03 /* Day of Week */ +#define RX4581_REG_DM 0x04 /* Day of Month in BCD */ +#define RX4581_REG_MO 0x05 /* Month in BCD */ +#define RX4581_REG_YR 0x06 /* Year in BCD */ +#define RX4581_REG_RAM 0x07 /* RAM */ +#define RX4581_REG_AMN 0x08 /* Alarm Min in BCD*/ +#define RX4581_REG_AHR 0x09 /* Alarm Hour in BCD */ +#define RX4581_REG_ADM 0x0A +#define RX4581_REG_ADW 0x0A +#define RX4581_REG_TMR0 0x0B +#define RX4581_REG_TMR1 0x0C +#define RX4581_REG_EXT 0x0D /* Extension Register */ +#define RX4581_REG_FLAG 0x0E /* Flag Register */ +#define RX4581_REG_CTRL 0x0F /* Control Register */ + + +/* Flag Register bit definitions */ +#define RX4581_FLAG_UF 0x20 /* Update */ +#define RX4581_FLAG_TF 0x10 /* Timer */ +#define RX4581_FLAG_AF 0x08 /* Alarm */ +#define RX4581_FLAG_VLF 0x02 /* Voltage Low */ + +/* Control Register bit definitions */ +#define RX4581_CTRL_UIE 0x20 /* Update Interrupt Enable */ +#define RX4581_CTRL_TIE 0x10 /* Timer Interrupt Enable */ +#define RX4581_CTRL_AIE 0x08 /* Alarm Interrupt Enable */ +#define RX4581_CTRL_STOP 0x02 /* STOP bit */ +#define RX4581_CTRL_RESET 0x01 /* RESET bit */ + +static int rx4581_set_reg(struct device *dev, unsigned char address, + unsigned char data) +{ + struct spi_device *spi = to_spi_device(dev); + unsigned char buf[2]; + + /* high nibble must be '0' to write */ + buf[0] = address & 0x0f; + buf[1] = data; + + return spi_write_then_read(spi, buf, 2, NULL, 0); +} + +static int rx4581_get_reg(struct device *dev, unsigned char address, + unsigned char *data) +{ + struct spi_device *spi = to_spi_device(dev); + + /* Set MSB to indicate read */ + *data = address | 0x80; + + return spi_write_then_read(spi, data, 1, data, 1); +} + +/* + * In the routines that deal directly with the rx8581 hardware, we use + * rtc_time -- month 0-11, hour 0-23, yr = calendar year-epoch. + */ +static int rx4581_get_datetime(struct device *dev, struct rtc_time *tm) +{ + struct spi_device *spi = to_spi_device(dev); + unsigned char date[7]; + unsigned char data; + int err; + + /* First we ensure that the "update flag" is not set, we read the + * time and date then re-read the "update flag". If the update flag + * has been set, we know that the time has changed during the read so + * we repeat the whole process again. + */ + err = rx4581_get_reg(dev, RX4581_REG_FLAG, &data); + if (err != 0) { + dev_err(dev, "Unable to read device flags\n"); + return -EIO; + } + + do { + /* If update flag set, clear it */ + if (data & RX4581_FLAG_UF) { + err = rx4581_set_reg(dev, + RX4581_REG_FLAG, (data & ~RX4581_FLAG_UF)); + if (err != 0) { + dev_err(dev, "Unable to write device " + "flags\n"); + return -EIO; + } + } + + /* Now read time and date */ + date[0] = 0x80; + err = spi_write_then_read(spi, date, 1, date, 7); + if (err < 0) { + dev_err(dev, "Unable to read date\n"); + return -EIO; + } + + /* Check flag register */ + err = rx4581_get_reg(dev, RX4581_REG_FLAG, &data); + if (err != 0) { + dev_err(dev, "Unable to read device flags\n"); + return -EIO; + } + } while (data & RX4581_FLAG_UF); + + if (data & RX4581_FLAG_VLF) + dev_info(dev, + "low voltage detected, date/time is not reliable.\n"); + + dev_dbg(dev, + "%s: raw data is sec=%02x, min=%02x, hr=%02x, " + "wday=%02x, mday=%02x, mon=%02x, year=%02x\n", + __func__, + date[0], date[1], date[2], date[3], date[4], date[5], date[6]); + + tm->tm_sec = bcd2bin(date[RX4581_REG_SC] & 0x7F); + tm->tm_min = bcd2bin(date[RX4581_REG_MN] & 0x7F); + tm->tm_hour = bcd2bin(date[RX4581_REG_HR] & 0x3F); /* rtc hr 0-23 */ + tm->tm_wday = ilog2(date[RX4581_REG_DW] & 0x7F); + tm->tm_mday = bcd2bin(date[RX4581_REG_DM] & 0x3F); + tm->tm_mon = bcd2bin(date[RX4581_REG_MO] & 0x1F) - 1; /* rtc mn 1-12 */ + tm->tm_year = bcd2bin(date[RX4581_REG_YR]); + if (tm->tm_year < 70) + tm->tm_year += 100; /* assume we are in 1970...2069 */ + + + dev_dbg(dev, "%s: tm is secs=%d, mins=%d, hours=%d, " + "mday=%d, mon=%d, year=%d, wday=%d\n", + __func__, + tm->tm_sec, tm->tm_min, tm->tm_hour, + tm->tm_mday, tm->tm_mon, tm->tm_year, tm->tm_wday); + + err = rtc_valid_tm(tm); + if (err < 0) + dev_err(dev, "retrieved date/time is not valid.\n"); + + return err; +} + +static int rx4581_set_datetime(struct device *dev, struct rtc_time *tm) +{ + struct spi_device *spi = to_spi_device(dev); + int err; + unsigned char buf[8], data; + + dev_dbg(dev, "%s: secs=%d, mins=%d, hours=%d, " + "mday=%d, mon=%d, year=%d, wday=%d\n", + __func__, + tm->tm_sec, tm->tm_min, tm->tm_hour, + tm->tm_mday, tm->tm_mon, tm->tm_year, tm->tm_wday); + + buf[0] = 0x00; + /* hours, minutes and seconds */ + buf[RX4581_REG_SC+1] = bin2bcd(tm->tm_sec); + buf[RX4581_REG_MN+1] = bin2bcd(tm->tm_min); + buf[RX4581_REG_HR+1] = bin2bcd(tm->tm_hour); + + buf[RX4581_REG_DM+1] = bin2bcd(tm->tm_mday); + + /* month, 1 - 12 */ + buf[RX4581_REG_MO+1] = bin2bcd(tm->tm_mon + 1); + + /* year and century */ + buf[RX4581_REG_YR+1] = bin2bcd(tm->tm_year % 100); + buf[RX4581_REG_DW+1] = (0x1 << tm->tm_wday); + + /* Stop the clock */ + err = rx4581_get_reg(dev, RX4581_REG_CTRL, &data); + if (err != 0) { + dev_err(dev, "Unable to read control register\n"); + return -EIO; + } + + err = rx4581_set_reg(dev, RX4581_REG_CTRL, + (data | RX4581_CTRL_STOP)); + if (err != 0) { + dev_err(dev, "Unable to write control register\n"); + return -EIO; + } + + /* write register's data */ + err = spi_write_then_read(spi, buf, 8, NULL, 0); + if (err != 0) { + dev_err(dev, "Unable to write to date registers\n"); + return -EIO; + } + + /* get VLF and clear it */ + err = rx4581_get_reg(dev, RX4581_REG_FLAG, &data); + if (err != 0) { + dev_err(dev, "Unable to read flag register\n"); + return -EIO; + } + + err = rx4581_set_reg(dev, RX4581_REG_FLAG, + (data & ~(RX4581_FLAG_VLF))); + if (err != 0) { + dev_err(dev, "Unable to write flag register\n"); + return -EIO; + } + + /* Restart the clock */ + err = rx4581_get_reg(dev, RX4581_REG_CTRL, &data); + if (err != 0) { + dev_err(dev, "Unable to read control register\n"); + return -EIO; + } + + err = rx4581_set_reg(dev, RX4581_REG_CTRL, + (data & ~(RX4581_CTRL_STOP))); + if (err != 0) { + dev_err(dev, "Unable to write control register\n"); + return -EIO; + } + + return 0; +} + +static const struct rtc_class_ops rx4581_rtc_ops = { + .read_time = rx4581_get_datetime, + .set_time = rx4581_set_datetime, +}; + +static int rx4581_probe(struct spi_device *spi) +{ + struct rtc_device *rtc; + unsigned char tmp; + int res; + + res = rx4581_get_reg(&spi->dev, RX4581_REG_SC, &tmp); + if (res != 0) + return res; + + rtc = rtc_device_register("rx4581", + &spi->dev, &rx4581_rtc_ops, THIS_MODULE); + if (IS_ERR(rtc)) + return PTR_ERR(rtc); + + dev_set_drvdata(&spi->dev, rtc); + return 0; +} + +static int rx4581_remove(struct spi_device *spi) +{ + struct rtc_device *rtc = dev_get_drvdata(&spi->dev); + + rtc_device_unregister(rtc); + return 0; +} + +static const struct spi_device_id rx4581_id[] = { + { "rx4581", 0 }, + { } +}; +MODULE_DEVICE_TABLE(spi, rx4581_id); + +static struct spi_driver rx4581_driver = { + .driver = { + .name = "rtc-rx4581", + .owner = THIS_MODULE, + }, + .probe = rx4581_probe, + .remove = rx4581_remove, + .id_table = rx4581_id, +}; + +module_spi_driver(rx4581_driver); + +MODULE_DESCRIPTION("rx4581 spi RTC driver"); +MODULE_AUTHOR("Torben Hohn"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("spi:rtc-rx4581"); diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c index 0c397ac3b132..fb994e9ddc15 100644 --- a/drivers/rtc/rtc-s3c.c +++ b/drivers/rtc/rtc-s3c.c @@ -115,7 +115,7 @@ static int s3c_rtc_setaie(struct device *dev, unsigned int enabled) { unsigned int tmp; - pr_debug("%s: aie=%d\n", __func__, enabled); + dev_dbg(dev, "%s: aie=%d\n", __func__, enabled); clk_enable(rtc_clk); tmp = readb(s3c_rtc_base + S3C2410_RTCALM) & ~S3C2410_RTCALM_ALMEN; @@ -203,7 +203,7 @@ static int s3c_rtc_gettime(struct device *dev, struct rtc_time *rtc_tm) rtc_tm->tm_year += 100; - pr_debug("read time %04d.%02d.%02d %02d:%02d:%02d\n", + dev_dbg(dev, "read time %04d.%02d.%02d %02d:%02d:%02d\n", 1900 + rtc_tm->tm_year, rtc_tm->tm_mon, rtc_tm->tm_mday, rtc_tm->tm_hour, rtc_tm->tm_min, rtc_tm->tm_sec); @@ -218,7 +218,7 @@ static int s3c_rtc_settime(struct device *dev, struct rtc_time *tm) void __iomem *base = s3c_rtc_base; int year = tm->tm_year - 100; - pr_debug("set time %04d.%02d.%02d %02d:%02d:%02d\n", + dev_dbg(dev, "set time %04d.%02d.%02d %02d:%02d:%02d\n", 1900 + tm->tm_year, tm->tm_mon, tm->tm_mday, tm->tm_hour, tm->tm_min, tm->tm_sec); @@ -259,7 +259,7 @@ static int s3c_rtc_getalarm(struct device *dev, struct rtc_wkalrm *alrm) alrm->enabled = (alm_en & S3C2410_RTCALM_ALMEN) ? 1 : 0; - pr_debug("read alarm %d, %04d.%02d.%02d %02d:%02d:%02d\n", + dev_dbg(dev, "read alarm %d, %04d.%02d.%02d %02d:%02d:%02d\n", alm_en, 1900 + alm_tm->tm_year, alm_tm->tm_mon, alm_tm->tm_mday, alm_tm->tm_hour, alm_tm->tm_min, alm_tm->tm_sec); @@ -310,7 +310,7 @@ static int s3c_rtc_setalarm(struct device *dev, struct rtc_wkalrm *alrm) unsigned int alrm_en; clk_enable(rtc_clk); - pr_debug("s3c_rtc_setalarm: %d, %04d.%02d.%02d %02d:%02d:%02d\n", + dev_dbg(dev, "s3c_rtc_setalarm: %d, %04d.%02d.%02d %02d:%02d:%02d\n", alrm->enabled, 1900 + tm->tm_year, tm->tm_mon + 1, tm->tm_mday, tm->tm_hour, tm->tm_min, tm->tm_sec); @@ -333,7 +333,7 @@ static int s3c_rtc_setalarm(struct device *dev, struct rtc_wkalrm *alrm) writeb(bin2bcd(tm->tm_hour), base + S3C2410_ALMHOUR); } - pr_debug("setting S3C2410_RTCALM to %08x\n", alrm_en); + dev_dbg(dev, "setting S3C2410_RTCALM to %08x\n", alrm_en); writeb(alrm_en, base + S3C2410_RTCALM); @@ -459,7 +459,7 @@ static int s3c_rtc_probe(struct platform_device *pdev) int ret; int tmp; - pr_debug("%s: probe=%p\n", __func__, pdev); + dev_dbg(&pdev->dev, "%s: probe=%p\n", __func__, pdev); /* find the IRQs */ @@ -475,7 +475,7 @@ static int s3c_rtc_probe(struct platform_device *pdev) return s3c_rtc_alarmno; } - pr_debug("s3c2410_rtc: tick irq %d, alarm irq %d\n", + dev_dbg(&pdev->dev, "s3c2410_rtc: tick irq %d, alarm irq %d\n", s3c_rtc_tickno, s3c_rtc_alarmno); /* get the memory region */ @@ -504,7 +504,7 @@ static int s3c_rtc_probe(struct platform_device *pdev) s3c_rtc_enable(pdev, 1); - pr_debug("s3c2410_rtc: RTCCON=%02x\n", + dev_dbg(&pdev->dev, "s3c2410_rtc: RTCCON=%02x\n", readw(s3c_rtc_base + S3C2410_RTCCON)); device_init_wakeup(&pdev->dev, 1); diff --git a/drivers/rtc/rtc-sa1100.c b/drivers/rtc/rtc-sa1100.c index 50a5c4adee48..df9180e80e3a 100644 --- a/drivers/rtc/rtc-sa1100.c +++ b/drivers/rtc/rtc-sa1100.c @@ -349,12 +349,14 @@ static const struct dev_pm_ops sa1100_rtc_pm_ops = { }; #endif +#ifdef CONFIG_OF static struct of_device_id sa1100_rtc_dt_ids[] = { { .compatible = "mrvl,sa1100-rtc", }, { .compatible = "mrvl,mmp-rtc", }, {} }; MODULE_DEVICE_TABLE(of, sa1100_rtc_dt_ids); +#endif static struct platform_driver sa1100_rtc_driver = { .probe = sa1100_rtc_probe, @@ -364,7 +366,7 @@ static struct platform_driver sa1100_rtc_driver = { #ifdef CONFIG_PM .pm = &sa1100_rtc_pm_ops, #endif - .of_match_table = sa1100_rtc_dt_ids, + .of_match_table = of_match_ptr(sa1100_rtc_dt_ids), }, }; diff --git a/drivers/rtc/rtc-snvs.c b/drivers/rtc/rtc-snvs.c index 40662e9dc0ab..f7d90703db5e 100644 --- a/drivers/rtc/rtc-snvs.c +++ b/drivers/rtc/rtc-snvs.c @@ -338,7 +338,7 @@ static struct platform_driver snvs_rtc_driver = { .name = "snvs_rtc", .owner = THIS_MODULE, .pm = &snvs_rtc_pm_ops, - .of_match_table = snvs_dt_ids, + .of_match_table = of_match_ptr(snvs_dt_ids), }, .probe = snvs_rtc_probe, .remove = snvs_rtc_remove, diff --git a/drivers/rtc/rtc-stmp3xxx.c b/drivers/rtc/rtc-stmp3xxx.c index cc9a9b652b13..98f0d3c30738 100644 --- a/drivers/rtc/rtc-stmp3xxx.c +++ b/drivers/rtc/rtc-stmp3xxx.c @@ -26,6 +26,7 @@ #include <linux/rtc.h> #include <linux/slab.h> #include <linux/of_device.h> +#include <linux/of.h> #include <linux/stmp_device.h> #include <linux/stmp3xxx_rtc_wdt.h> @@ -344,7 +345,7 @@ static struct platform_driver stmp3xxx_rtcdrv = { .driver = { .name = "stmp3xxx-rtc", .owner = THIS_MODULE, - .of_match_table = rtc_dt_ids, + .of_match_table = of_match_ptr(rtc_dt_ids), }, }; diff --git a/drivers/rtc/rtc-tps65910.c b/drivers/rtc/rtc-tps65910.c index e5fef141a0e2..8bd8115329b5 100644 --- a/drivers/rtc/rtc-tps65910.c +++ b/drivers/rtc/rtc-tps65910.c @@ -22,13 +22,13 @@ #include <linux/rtc.h> #include <linux/bcd.h> #include <linux/platform_device.h> +#include <linux/pm_runtime.h> #include <linux/interrupt.h> #include <linux/mfd/tps65910.h> struct tps65910_rtc { struct rtc_device *rtc; - /* To store the list of enabled interrupts */ - u32 irqstat; + int irq; }; /* Total number of RTC registers needed to set time*/ @@ -267,13 +267,14 @@ static int tps65910_rtc_probe(struct platform_device *pdev) } ret = devm_request_threaded_irq(&pdev->dev, irq, NULL, - tps65910_rtc_interrupt, IRQF_TRIGGER_LOW, + tps65910_rtc_interrupt, IRQF_TRIGGER_LOW | IRQF_EARLY_RESUME, dev_name(&pdev->dev), &pdev->dev); if (ret < 0) { dev_err(&pdev->dev, "IRQ is not free.\n"); return ret; } - device_init_wakeup(&pdev->dev, 1); + tps_rtc->irq = irq; + device_set_wakeup_capable(&pdev->dev, 1); tps_rtc->rtc = rtc_device_register(pdev->name, &pdev->dev, &tps65910_rtc_ops, THIS_MODULE); @@ -304,49 +305,36 @@ static int tps65910_rtc_remove(struct platform_device *pdev) } #ifdef CONFIG_PM_SLEEP - static int tps65910_rtc_suspend(struct device *dev) { - struct tps65910 *tps = dev_get_drvdata(dev->parent); - u8 alarm = TPS65910_RTC_INTERRUPTS_IT_ALARM; - int ret; - - /* Store current list of enabled interrupts*/ - ret = regmap_read(tps->regmap, TPS65910_RTC_INTERRUPTS, - &tps->rtc->irqstat); - if (ret < 0) - return ret; + struct tps65910_rtc *tps_rtc = dev_get_drvdata(dev); - /* Enable RTC ALARM interrupt only */ - return regmap_write(tps->regmap, TPS65910_RTC_INTERRUPTS, alarm); + if (device_may_wakeup(dev)) + enable_irq_wake(tps_rtc->irq); + return 0; } static int tps65910_rtc_resume(struct device *dev) { - struct tps65910 *tps = dev_get_drvdata(dev->parent); + struct tps65910_rtc *tps_rtc = dev_get_drvdata(dev); - /* Restore list of enabled interrupts before suspend */ - return regmap_write(tps->regmap, TPS65910_RTC_INTERRUPTS, - tps->rtc->irqstat); + if (device_may_wakeup(dev)) + disable_irq_wake(tps_rtc->irq); + return 0; } +#endif static const struct dev_pm_ops tps65910_rtc_pm_ops = { - .suspend = tps65910_rtc_suspend, - .resume = tps65910_rtc_resume, + SET_SYSTEM_SLEEP_PM_OPS(tps65910_rtc_suspend, tps65910_rtc_resume) }; -#define DEV_PM_OPS (&tps65910_rtc_pm_ops) -#else -#define DEV_PM_OPS NULL -#endif - static struct platform_driver tps65910_rtc_driver = { .probe = tps65910_rtc_probe, .remove = tps65910_rtc_remove, .driver = { .owner = THIS_MODULE, .name = "tps65910-rtc", - .pm = DEV_PM_OPS, + .pm = &tps65910_rtc_pm_ops, }, }; diff --git a/drivers/rtc/rtc-tps80031.c b/drivers/rtc/rtc-tps80031.c new file mode 100644 index 000000000000..97406411d58c --- /dev/null +++ b/drivers/rtc/rtc-tps80031.c @@ -0,0 +1,349 @@ +/* + * rtc-tps80031.c -- TI TPS80031/TPS80032 RTC driver + * + * RTC driver for TI TPS80031/TPS80032 Fully Integrated + * Power Management with Power Path and Battery Charger + * + * Copyright (c) 2012, NVIDIA Corporation. + * + * Author: Laxman Dewangan <ldewangan@nvidia.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation version 2. + * + * This program is distributed "as is" WITHOUT ANY WARRANTY of any kind, + * whether express or implied; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA + * 02111-1307, USA + */ + +#include <linux/bcd.h> +#include <linux/device.h> +#include <linux/err.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/mfd/tps80031.h> +#include <linux/platform_device.h> +#include <linux/pm.h> +#include <linux/rtc.h> +#include <linux/slab.h> + +#define ENABLE_ALARM_INT 0x08 +#define ALARM_INT_STATUS 0x40 + +/** + * Setting bit to 1 in STOP_RTC will run the RTC and + * setting this bit to 0 will freeze RTC. + */ +#define STOP_RTC 0x1 + +/* Power on reset Values of RTC registers */ +#define TPS80031_RTC_POR_YEAR 0 +#define TPS80031_RTC_POR_MONTH 1 +#define TPS80031_RTC_POR_DAY 1 + +/* Numbers of registers for time and alarms */ +#define TPS80031_RTC_TIME_NUM_REGS 7 +#define TPS80031_RTC_ALARM_NUM_REGS 6 + +/** + * PMU RTC have only 2 nibbles to store year information, so using an + * offset of 100 to set the base year as 2000 for our driver. + */ +#define RTC_YEAR_OFFSET 100 + +struct tps80031_rtc { + struct rtc_device *rtc; + int irq; +}; + +static int tps80031_rtc_read_time(struct device *dev, struct rtc_time *tm) +{ + u8 buff[TPS80031_RTC_TIME_NUM_REGS]; + int ret; + + ret = tps80031_reads(dev->parent, TPS80031_SLAVE_ID1, + TPS80031_SECONDS_REG, TPS80031_RTC_TIME_NUM_REGS, buff); + if (ret < 0) { + dev_err(dev, "reading RTC_SECONDS_REG failed, err = %d\n", ret); + return ret; + } + + tm->tm_sec = bcd2bin(buff[0]); + tm->tm_min = bcd2bin(buff[1]); + tm->tm_hour = bcd2bin(buff[2]); + tm->tm_mday = bcd2bin(buff[3]); + tm->tm_mon = bcd2bin(buff[4]) - 1; + tm->tm_year = bcd2bin(buff[5]) + RTC_YEAR_OFFSET; + tm->tm_wday = bcd2bin(buff[6]); + return 0; +} + +static int tps80031_rtc_set_time(struct device *dev, struct rtc_time *tm) +{ + u8 buff[7]; + int ret; + + buff[0] = bin2bcd(tm->tm_sec); + buff[1] = bin2bcd(tm->tm_min); + buff[2] = bin2bcd(tm->tm_hour); + buff[3] = bin2bcd(tm->tm_mday); + buff[4] = bin2bcd(tm->tm_mon + 1); + buff[5] = bin2bcd(tm->tm_year % RTC_YEAR_OFFSET); + buff[6] = bin2bcd(tm->tm_wday); + + /* Stop RTC while updating the RTC time registers */ + ret = tps80031_clr_bits(dev->parent, TPS80031_SLAVE_ID1, + TPS80031_RTC_CTRL_REG, STOP_RTC); + if (ret < 0) { + dev_err(dev->parent, "Stop RTC failed, err = %d\n", ret); + return ret; + } + + ret = tps80031_writes(dev->parent, TPS80031_SLAVE_ID1, + TPS80031_SECONDS_REG, + TPS80031_RTC_TIME_NUM_REGS, buff); + if (ret < 0) { + dev_err(dev, "writing RTC_SECONDS_REG failed, err %d\n", ret); + return ret; + } + + ret = tps80031_set_bits(dev->parent, TPS80031_SLAVE_ID1, + TPS80031_RTC_CTRL_REG, STOP_RTC); + if (ret < 0) + dev_err(dev->parent, "Start RTC failed, err = %d\n", ret); + return ret; +} + +static int tps80031_rtc_alarm_irq_enable(struct device *dev, + unsigned int enable) +{ + int ret; + + if (enable) + ret = tps80031_set_bits(dev->parent, TPS80031_SLAVE_ID1, + TPS80031_RTC_INTERRUPTS_REG, ENABLE_ALARM_INT); + else + ret = tps80031_clr_bits(dev->parent, TPS80031_SLAVE_ID1, + TPS80031_RTC_INTERRUPTS_REG, ENABLE_ALARM_INT); + if (ret < 0) { + dev_err(dev, "Update on RTC_INT failed, err = %d\n", ret); + return ret; + } + return 0; +} + +static int tps80031_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm) +{ + u8 buff[TPS80031_RTC_ALARM_NUM_REGS]; + int ret; + + buff[0] = bin2bcd(alrm->time.tm_sec); + buff[1] = bin2bcd(alrm->time.tm_min); + buff[2] = bin2bcd(alrm->time.tm_hour); + buff[3] = bin2bcd(alrm->time.tm_mday); + buff[4] = bin2bcd(alrm->time.tm_mon + 1); + buff[5] = bin2bcd(alrm->time.tm_year % RTC_YEAR_OFFSET); + ret = tps80031_writes(dev->parent, TPS80031_SLAVE_ID1, + TPS80031_ALARM_SECONDS_REG, + TPS80031_RTC_ALARM_NUM_REGS, buff); + if (ret < 0) { + dev_err(dev, "Writing RTC_ALARM failed, err %d\n", ret); + return ret; + } + return tps80031_rtc_alarm_irq_enable(dev, alrm->enabled); +} + +static int tps80031_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm) +{ + u8 buff[6]; + int ret; + + ret = tps80031_reads(dev->parent, TPS80031_SLAVE_ID1, + TPS80031_ALARM_SECONDS_REG, + TPS80031_RTC_ALARM_NUM_REGS, buff); + if (ret < 0) { + dev_err(dev->parent, + "reading RTC_ALARM failed, err = %d\n", ret); + return ret; + } + + alrm->time.tm_sec = bcd2bin(buff[0]); + alrm->time.tm_min = bcd2bin(buff[1]); + alrm->time.tm_hour = bcd2bin(buff[2]); + alrm->time.tm_mday = bcd2bin(buff[3]); + alrm->time.tm_mon = bcd2bin(buff[4]) - 1; + alrm->time.tm_year = bcd2bin(buff[5]) + RTC_YEAR_OFFSET; + return 0; +} + +static int clear_alarm_int_status(struct device *dev, struct tps80031_rtc *rtc) +{ + int ret; + u8 buf; + + /** + * As per datasheet, A dummy read of this RTC_STATUS_REG register + * is necessary before each I2C read in order to update the status + * register value. + */ + ret = tps80031_read(dev->parent, TPS80031_SLAVE_ID1, + TPS80031_RTC_STATUS_REG, &buf); + if (ret < 0) { + dev_err(dev, "reading RTC_STATUS failed. err = %d\n", ret); + return ret; + } + + /* clear Alarm status bits.*/ + ret = tps80031_set_bits(dev->parent, TPS80031_SLAVE_ID1, + TPS80031_RTC_STATUS_REG, ALARM_INT_STATUS); + if (ret < 0) { + dev_err(dev, "clear Alarm INT failed, err = %d\n", ret); + return ret; + } + return 0; +} + +static irqreturn_t tps80031_rtc_irq(int irq, void *data) +{ + struct device *dev = data; + struct tps80031_rtc *rtc = dev_get_drvdata(dev); + int ret; + + ret = clear_alarm_int_status(dev, rtc); + if (ret < 0) + return ret; + + rtc_update_irq(rtc->rtc, 1, RTC_IRQF | RTC_AF); + return IRQ_HANDLED; +} + +static const struct rtc_class_ops tps80031_rtc_ops = { + .read_time = tps80031_rtc_read_time, + .set_time = tps80031_rtc_set_time, + .set_alarm = tps80031_rtc_set_alarm, + .read_alarm = tps80031_rtc_read_alarm, + .alarm_irq_enable = tps80031_rtc_alarm_irq_enable, +}; + +static int tps80031_rtc_probe(struct platform_device *pdev) +{ + struct tps80031_rtc *rtc; + struct rtc_time tm; + int ret; + + rtc = devm_kzalloc(&pdev->dev, sizeof(*rtc), GFP_KERNEL); + if (!rtc) + return -ENOMEM; + + rtc->irq = platform_get_irq(pdev, 0); + platform_set_drvdata(pdev, rtc); + + /* Start RTC */ + ret = tps80031_set_bits(pdev->dev.parent, TPS80031_SLAVE_ID1, + TPS80031_RTC_CTRL_REG, STOP_RTC); + if (ret < 0) { + dev_err(&pdev->dev, "failed to start RTC. err = %d\n", ret); + return ret; + } + + /* If RTC have POR values, set time 01:01:2000 */ + tps80031_rtc_read_time(&pdev->dev, &tm); + if ((tm.tm_year == RTC_YEAR_OFFSET + TPS80031_RTC_POR_YEAR) && + (tm.tm_mon == (TPS80031_RTC_POR_MONTH - 1)) && + (tm.tm_mday == TPS80031_RTC_POR_DAY)) { + tm.tm_year = 2000; + tm.tm_mday = 1; + tm.tm_mon = 1; + ret = tps80031_rtc_set_time(&pdev->dev, &tm); + if (ret < 0) { + dev_err(&pdev->dev, + "RTC set time failed, err = %d\n", ret); + return ret; + } + } + + /* Clear alarm intretupt status if it is there */ + ret = clear_alarm_int_status(&pdev->dev, rtc); + if (ret < 0) { + dev_err(&pdev->dev, "Clear alarm int failed, err = %d\n", ret); + return ret; + } + + rtc->rtc = rtc_device_register(pdev->name, &pdev->dev, + &tps80031_rtc_ops, THIS_MODULE); + if (IS_ERR(rtc->rtc)) { + ret = PTR_ERR(rtc->rtc); + dev_err(&pdev->dev, "RTC registration failed, err %d\n", ret); + return ret; + } + + ret = request_threaded_irq(rtc->irq, NULL, tps80031_rtc_irq, + IRQF_ONESHOT | IRQF_EARLY_RESUME, + dev_name(&pdev->dev), rtc); + if (ret < 0) { + dev_err(&pdev->dev, "request IRQ:%d failed, err = %d\n", + rtc->irq, ret); + rtc_device_unregister(rtc->rtc); + return ret; + } + device_set_wakeup_capable(&pdev->dev, 1); + return 0; +} + +static int tps80031_rtc_remove(struct platform_device *pdev) +{ + struct tps80031_rtc *rtc = platform_get_drvdata(pdev); + + free_irq(rtc->irq, rtc); + rtc_device_unregister(rtc->rtc); + return 0; +} + +#ifdef CONFIG_PM_SLEEP +static int tps80031_rtc_suspend(struct device *dev) +{ + struct tps80031_rtc *rtc = dev_get_drvdata(dev); + + if (device_may_wakeup(dev)) + enable_irq_wake(rtc->irq); + return 0; +} + +static int tps80031_rtc_resume(struct device *dev) +{ + struct tps80031_rtc *rtc = dev_get_drvdata(dev); + + if (device_may_wakeup(dev)) + disable_irq_wake(rtc->irq); + return 0; +}; +#endif + +static const struct dev_pm_ops tps80031_pm_ops = { + SET_SYSTEM_SLEEP_PM_OPS(tps80031_rtc_suspend, tps80031_rtc_resume) +}; + +static struct platform_driver tps80031_rtc_driver = { + .driver = { + .name = "tps80031-rtc", + .owner = THIS_MODULE, + .pm = &tps80031_pm_ops, + }, + .probe = tps80031_rtc_probe, + .remove = tps80031_rtc_remove, +}; + +module_platform_driver(tps80031_rtc_driver); + +MODULE_ALIAS("platform:tps80031-rtc"); +MODULE_DESCRIPTION("TI TPS80031/TPS80032 RTC driver"); +MODULE_AUTHOR("Laxman Dewangan <ldewangan@nvidia.com>"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/rtc/rtc-twl.c b/drivers/rtc/rtc-twl.c index ccd4ad370b32..8bc6c80b184c 100644 --- a/drivers/rtc/rtc-twl.c +++ b/drivers/rtc/rtc-twl.c @@ -27,6 +27,7 @@ #include <linux/bcd.h> #include <linux/platform_device.h> #include <linux/interrupt.h> +#include <linux/of.h> #include <linux/i2c/twl.h> @@ -588,11 +589,14 @@ static int twl_rtc_resume(struct platform_device *pdev) #define twl_rtc_resume NULL #endif +#ifdef CONFIG_OF static const struct of_device_id twl_rtc_of_match[] = { {.compatible = "ti,twl4030-rtc", }, { }, }; MODULE_DEVICE_TABLE(of, twl_rtc_of_match); +#endif + MODULE_ALIAS("platform:twl_rtc"); static struct platform_driver twl4030rtc_driver = { @@ -604,7 +608,7 @@ static struct platform_driver twl4030rtc_driver = { .driver = { .owner = THIS_MODULE, .name = "twl_rtc", - .of_match_table = twl_rtc_of_match, + .of_match_table = of_match_ptr(twl_rtc_of_match), }, }; diff --git a/drivers/scsi/bfa/bfad_im.c b/drivers/scsi/bfa/bfad_im.c index 8f92732655c7..5864f987f206 100644 --- a/drivers/scsi/bfa/bfad_im.c +++ b/drivers/scsi/bfa/bfad_im.c @@ -523,20 +523,13 @@ bfad_im_scsi_host_alloc(struct bfad_s *bfad, struct bfad_im_port_s *im_port, int error = 1; mutex_lock(&bfad_mutex); - if (!idr_pre_get(&bfad_im_port_index, GFP_KERNEL)) { + error = idr_alloc(&bfad_im_port_index, im_port, 0, 0, GFP_KERNEL); + if (error < 0) { mutex_unlock(&bfad_mutex); - printk(KERN_WARNING "idr_pre_get failure\n"); + printk(KERN_WARNING "idr_alloc failure\n"); goto out; } - - error = idr_get_new(&bfad_im_port_index, im_port, - &im_port->idr_id); - if (error) { - mutex_unlock(&bfad_mutex); - printk(KERN_WARNING "idr_get_new failure\n"); - goto out; - } - + im_port->idr_id = error; mutex_unlock(&bfad_mutex); im_port->shost = bfad_scsi_host_alloc(im_port, bfad); diff --git a/drivers/scsi/ch.c b/drivers/scsi/ch.c index a15474eef5f7..2a323742ce04 100644 --- a/drivers/scsi/ch.c +++ b/drivers/scsi/ch.c @@ -895,7 +895,7 @@ static int ch_probe(struct device *dev) { struct scsi_device *sd = to_scsi_device(dev); struct device *class_dev; - int minor, ret = -ENOMEM; + int ret; scsi_changer *ch; if (sd->type != TYPE_MEDIUM_CHANGER) @@ -905,22 +905,19 @@ static int ch_probe(struct device *dev) if (NULL == ch) return -ENOMEM; - if (!idr_pre_get(&ch_index_idr, GFP_KERNEL)) - goto free_ch; - + idr_preload(GFP_KERNEL); spin_lock(&ch_index_lock); - ret = idr_get_new(&ch_index_idr, ch, &minor); + ret = idr_alloc(&ch_index_idr, ch, 0, CH_MAX_DEVS + 1, GFP_NOWAIT); spin_unlock(&ch_index_lock); + idr_preload_end(); - if (ret) + if (ret < 0) { + if (ret == -ENOSPC) + ret = -ENODEV; goto free_ch; - - if (minor > CH_MAX_DEVS) { - ret = -ENODEV; - goto remove_idr; } - ch->minor = minor; + ch->minor = ret; sprintf(ch->name,"ch%d",ch->minor); class_dev = device_create(ch_sysfs_class, dev, @@ -944,7 +941,7 @@ static int ch_probe(struct device *dev) return 0; remove_idr: - idr_remove(&ch_index_idr, minor); + idr_remove(&ch_index_idr, ch->minor); free_ch: kfree(ch); return ret; diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 26ca2efa976e..314b4f61b9e3 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -3165,14 +3165,10 @@ destroy_port(struct lpfc_vport *vport) int lpfc_get_instance(void) { - int instance = 0; - - /* Assign an unused number */ - if (!idr_pre_get(&lpfc_hba_index, GFP_KERNEL)) - return -1; - if (idr_get_new(&lpfc_hba_index, NULL, &instance)) - return -1; - return instance; + int ret; + + ret = idr_alloc(&lpfc_hba_index, NULL, 0, 0, GFP_KERNEL); + return ret < 0 ? -1 : ret; } /** diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index be2c9a6561ff..df5e961484e1 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -35,6 +35,7 @@ static int sg_version_num = 30534; /* 2 digits for each component */ #include <linux/sched.h> #include <linux/string.h> #include <linux/mm.h> +#include <linux/aio.h> #include <linux/errno.h> #include <linux/mtio.h> #include <linux/ioctl.h> @@ -1391,24 +1392,23 @@ static Sg_device *sg_alloc(struct gendisk *disk, struct scsi_device *scsidp) return ERR_PTR(-ENOMEM); } - if (!idr_pre_get(&sg_index_idr, GFP_KERNEL)) { - printk(KERN_WARNING "idr expansion Sg_device failure\n"); - error = -ENOMEM; - goto out; - } - + idr_preload(GFP_KERNEL); write_lock_irqsave(&sg_index_lock, iflags); - error = idr_get_new(&sg_index_idr, sdp, &k); - if (error) { - write_unlock_irqrestore(&sg_index_lock, iflags); - printk(KERN_WARNING "idr allocation Sg_device failure: %d\n", - error); - goto out; + error = idr_alloc(&sg_index_idr, sdp, 0, SG_MAX_DEVS, GFP_NOWAIT); + if (error < 0) { + if (error == -ENOSPC) { + sdev_printk(KERN_WARNING, scsidp, + "Unable to attach sg device type=%d, minor number exceeds %d\n", + scsidp->type, SG_MAX_DEVS - 1); + error = -ENODEV; + } else { + printk(KERN_WARNING + "idr allocation Sg_device failure: %d\n", error); + } + goto out_unlock; } - - if (unlikely(k >= SG_MAX_DEVS)) - goto overflow; + k = error; SCSI_LOG_TIMEOUT(3, printk("sg_alloc: dev=%d \n", k)); sprintf(disk->disk_name, "sg%d", k); @@ -1420,25 +1420,17 @@ static Sg_device *sg_alloc(struct gendisk *disk, struct scsi_device *scsidp) sdp->sg_tablesize = queue_max_segments(q); sdp->index = k; kref_init(&sdp->d_ref); + error = 0; +out_unlock: write_unlock_irqrestore(&sg_index_lock, iflags); + idr_preload_end(); - error = 0; - out: if (error) { kfree(sdp); return ERR_PTR(error); } return sdp; - - overflow: - idr_remove(&sg_index_idr, k); - write_unlock_irqrestore(&sg_index_lock, iflags); - sdev_printk(KERN_WARNING, scsidp, - "Unable to attach sg device type=%d, minor " - "number exceeds %d\n", scsidp->type, SG_MAX_DEVS - 1); - error = -ENODEV; - goto out; } static int diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c index 98156a97c472..7c6edcaf880f 100644 --- a/drivers/scsi/st.c +++ b/drivers/scsi/st.c @@ -4076,7 +4076,7 @@ static int st_probe(struct device *dev) struct st_modedef *STm; struct st_partstat *STps; struct st_buffer *buffer; - int i, dev_num, error; + int i, error; char *stp; if (SDp->type != TYPE_TAPE) @@ -4178,27 +4178,17 @@ static int st_probe(struct device *dev) tpnt->blksize_changed = 0; mutex_init(&tpnt->lock); - if (!idr_pre_get(&st_index_idr, GFP_KERNEL)) { - pr_warn("st: idr expansion failed\n"); - error = -ENOMEM; - goto out_put_disk; - } - + idr_preload(GFP_KERNEL); spin_lock(&st_index_lock); - error = idr_get_new(&st_index_idr, tpnt, &dev_num); + error = idr_alloc(&st_index_idr, tpnt, 0, ST_MAX_TAPES + 1, GFP_NOWAIT); spin_unlock(&st_index_lock); - if (error) { + idr_preload_end(); + if (error < 0) { pr_warn("st: idr allocation failed: %d\n", error); goto out_put_disk; } - - if (dev_num > ST_MAX_TAPES) { - pr_err("st: Too many tape devices (max. %d).\n", ST_MAX_TAPES); - goto out_put_index; - } - - tpnt->index = dev_num; - sprintf(disk->disk_name, "st%d", dev_num); + tpnt->index = error; + sprintf(disk->disk_name, "st%d", tpnt->index); dev_set_drvdata(dev, tpnt); @@ -4218,9 +4208,8 @@ static int st_probe(struct device *dev) out_remove_devs: remove_cdevs(tpnt); -out_put_index: spin_lock(&st_index_lock); - idr_remove(&st_index_idr, dev_num); + idr_remove(&st_index_idr, tpnt->index); spin_unlock(&st_index_lock); out_put_disk: put_disk(disk); diff --git a/drivers/staging/android/binder.c b/drivers/staging/android/binder.c index 538ebe213129..24456a0de6b2 100644 --- a/drivers/staging/android/binder.c +++ b/drivers/staging/android/binder.c @@ -2880,7 +2880,6 @@ static int binder_release(struct inode *nodp, struct file *filp) static void binder_deferred_release(struct binder_proc *proc) { - struct hlist_node *pos; struct binder_transaction *t; struct rb_node *n; int threads, nodes, incoming_refs, outgoing_refs, buffers, active_transactions, page_count; @@ -2924,7 +2923,7 @@ static void binder_deferred_release(struct binder_proc *proc) node->local_weak_refs = 0; hlist_add_head(&node->dead_node, &binder_dead_nodes); - hlist_for_each_entry(ref, pos, &node->refs, node_entry) { + hlist_for_each_entry(ref, &node->refs, node_entry) { incoming_refs++; if (ref->death) { death++; @@ -3156,12 +3155,11 @@ static void print_binder_thread(struct seq_file *m, static void print_binder_node(struct seq_file *m, struct binder_node *node) { struct binder_ref *ref; - struct hlist_node *pos; struct binder_work *w; int count; count = 0; - hlist_for_each_entry(ref, pos, &node->refs, node_entry) + hlist_for_each_entry(ref, &node->refs, node_entry) count++; seq_printf(m, " node %d: u%p c%p hs %d hw %d ls %d lw %d is %d iw %d", @@ -3171,7 +3169,7 @@ static void print_binder_node(struct seq_file *m, struct binder_node *node) node->internal_strong_refs, count); if (count) { seq_puts(m, " proc"); - hlist_for_each_entry(ref, pos, &node->refs, node_entry) + hlist_for_each_entry(ref, &node->refs, node_entry) seq_printf(m, " %d", ref->proc->pid); } seq_puts(m, "\n"); @@ -3369,7 +3367,6 @@ static void print_binder_proc_stats(struct seq_file *m, static int binder_state_show(struct seq_file *m, void *unused) { struct binder_proc *proc; - struct hlist_node *pos; struct binder_node *node; int do_lock = !binder_debug_no_lock; @@ -3380,10 +3377,10 @@ static int binder_state_show(struct seq_file *m, void *unused) if (!hlist_empty(&binder_dead_nodes)) seq_puts(m, "dead nodes:\n"); - hlist_for_each_entry(node, pos, &binder_dead_nodes, dead_node) + hlist_for_each_entry(node, &binder_dead_nodes, dead_node) print_binder_node(m, node); - hlist_for_each_entry(proc, pos, &binder_procs, proc_node) + hlist_for_each_entry(proc, &binder_procs, proc_node) print_binder_proc(m, proc, 1); if (do_lock) binder_unlock(__func__); @@ -3393,7 +3390,6 @@ static int binder_state_show(struct seq_file *m, void *unused) static int binder_stats_show(struct seq_file *m, void *unused) { struct binder_proc *proc; - struct hlist_node *pos; int do_lock = !binder_debug_no_lock; if (do_lock) @@ -3403,7 +3399,7 @@ static int binder_stats_show(struct seq_file *m, void *unused) print_binder_stats(m, "", &binder_stats); - hlist_for_each_entry(proc, pos, &binder_procs, proc_node) + hlist_for_each_entry(proc, &binder_procs, proc_node) print_binder_proc_stats(m, proc); if (do_lock) binder_unlock(__func__); @@ -3413,14 +3409,13 @@ static int binder_stats_show(struct seq_file *m, void *unused) static int binder_transactions_show(struct seq_file *m, void *unused) { struct binder_proc *proc; - struct hlist_node *pos; int do_lock = !binder_debug_no_lock; if (do_lock) binder_lock(__func__); seq_puts(m, "binder transactions:\n"); - hlist_for_each_entry(proc, pos, &binder_procs, proc_node) + hlist_for_each_entry(proc, &binder_procs, proc_node) print_binder_proc(m, proc, 0); if (do_lock) binder_unlock(__func__); diff --git a/drivers/staging/android/logger.c b/drivers/staging/android/logger.c index dbc63cbb4d3a..b4a313cdbed5 100644 --- a/drivers/staging/android/logger.c +++ b/drivers/staging/android/logger.c @@ -28,6 +28,7 @@ #include <linux/slab.h> #include <linux/time.h> #include <linux/vmalloc.h> +#include <linux/aio.h> #include "logger.h" #include <asm/ioctls.h> diff --git a/drivers/staging/zcache/zbud.c b/drivers/staging/zcache/zbud.c index 6835fab5d116..79ae9bd00676 100644 --- a/drivers/staging/zcache/zbud.c +++ b/drivers/staging/zcache/zbud.c @@ -404,7 +404,7 @@ static inline struct page *zbud_unuse_zbudpage(struct zbudpage *zbudpage, else zbud_pers_pageframes--; zbudpage_spin_unlock(zbudpage); - reset_page_mapcount(page); + page_mapcount_reset(page); init_page_count(page); page->index = 0; return page; diff --git a/drivers/staging/zsmalloc/zsmalloc-main.c b/drivers/staging/zsmalloc/zsmalloc-main.c index 06f73a93a44d..e78d262c5249 100644 --- a/drivers/staging/zsmalloc/zsmalloc-main.c +++ b/drivers/staging/zsmalloc/zsmalloc-main.c @@ -472,7 +472,7 @@ static void reset_page(struct page *page) set_page_private(page, 0); page->mapping = NULL; page->freelist = NULL; - reset_page_mapcount(page); + page_mapcount_reset(page); } static void free_zspage(struct page *first_page) diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 339f97f7085b..f1fdf4f4341c 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -144,23 +144,24 @@ struct iscsi_tiqn *iscsit_add_tiqn(unsigned char *buf) spin_lock_init(&tiqn->login_stats.lock); spin_lock_init(&tiqn->logout_stats.lock); - if (!idr_pre_get(&tiqn_idr, GFP_KERNEL)) { - pr_err("idr_pre_get() for tiqn_idr failed\n"); - kfree(tiqn); - return ERR_PTR(-ENOMEM); - } tiqn->tiqn_state = TIQN_STATE_ACTIVE; + idr_preload(GFP_KERNEL); spin_lock(&tiqn_lock); - ret = idr_get_new(&tiqn_idr, NULL, &tiqn->tiqn_index); + + ret = idr_alloc(&tiqn_idr, NULL, 0, 0, GFP_NOWAIT); if (ret < 0) { - pr_err("idr_get_new() failed for tiqn->tiqn_index\n"); + pr_err("idr_alloc() failed for tiqn->tiqn_index\n"); spin_unlock(&tiqn_lock); + idr_preload_end(); kfree(tiqn); return ERR_PTR(ret); } + tiqn->tiqn_index = ret; list_add_tail(&tiqn->tiqn_list, &g_tiqn_list); + spin_unlock(&tiqn_lock); + idr_preload_end(); pr_debug("CORE[0] - Added iSCSI Target IQN: %s\n", tiqn->tiqn); diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index fdb632f0ab85..2535d4d46c0e 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -247,19 +247,16 @@ static int iscsi_login_zero_tsih_s1( spin_lock_init(&sess->session_usage_lock); spin_lock_init(&sess->ttt_lock); - if (!idr_pre_get(&sess_idr, GFP_KERNEL)) { - pr_err("idr_pre_get() for sess_idr failed\n"); - iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR, - ISCSI_LOGIN_STATUS_NO_RESOURCES); - kfree(sess); - return -ENOMEM; - } + idr_preload(GFP_KERNEL); spin_lock_bh(&sess_idr_lock); - ret = idr_get_new(&sess_idr, NULL, &sess->session_index); + ret = idr_alloc(&sess_idr, NULL, 0, 0, GFP_NOWAIT); + if (ret >= 0) + sess->session_index = ret; spin_unlock_bh(&sess_idr_lock); + idr_preload_end(); if (ret < 0) { - pr_err("idr_get_new() for sess_idr failed\n"); + pr_err("idr_alloc() for sess_idr failed\n"); iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR, ISCSI_LOGIN_STATUS_NO_RESOURCES); kfree(sess); diff --git a/drivers/target/tcm_fc/tfc_sess.c b/drivers/target/tcm_fc/tfc_sess.c index 6659dd36e806..113f33598b9f 100644 --- a/drivers/target/tcm_fc/tfc_sess.c +++ b/drivers/target/tcm_fc/tfc_sess.c @@ -169,7 +169,6 @@ static struct ft_sess *ft_sess_get(struct fc_lport *lport, u32 port_id) { struct ft_tport *tport; struct hlist_head *head; - struct hlist_node *pos; struct ft_sess *sess; rcu_read_lock(); @@ -178,7 +177,7 @@ static struct ft_sess *ft_sess_get(struct fc_lport *lport, u32 port_id) goto out; head = &tport->hash[ft_sess_hash(port_id)]; - hlist_for_each_entry_rcu(sess, pos, head, hash) { + hlist_for_each_entry_rcu(sess, head, hash) { if (sess->port_id == port_id) { kref_get(&sess->kref); rcu_read_unlock(); @@ -201,10 +200,9 @@ static struct ft_sess *ft_sess_create(struct ft_tport *tport, u32 port_id, { struct ft_sess *sess; struct hlist_head *head; - struct hlist_node *pos; head = &tport->hash[ft_sess_hash(port_id)]; - hlist_for_each_entry_rcu(sess, pos, head, hash) + hlist_for_each_entry_rcu(sess, head, hash) if (sess->port_id == port_id) return sess; @@ -253,11 +251,10 @@ static void ft_sess_unhash(struct ft_sess *sess) static struct ft_sess *ft_sess_delete(struct ft_tport *tport, u32 port_id) { struct hlist_head *head; - struct hlist_node *pos; struct ft_sess *sess; head = &tport->hash[ft_sess_hash(port_id)]; - hlist_for_each_entry_rcu(sess, pos, head, hash) { + hlist_for_each_entry_rcu(sess, head, hash) { if (sess->port_id == port_id) { ft_sess_unhash(sess); return sess; @@ -273,12 +270,11 @@ static struct ft_sess *ft_sess_delete(struct ft_tport *tport, u32 port_id) static void ft_sess_delete_all(struct ft_tport *tport) { struct hlist_head *head; - struct hlist_node *pos; struct ft_sess *sess; for (head = tport->hash; head < &tport->hash[FT_SESS_HASH_SIZE]; head++) { - hlist_for_each_entry_rcu(sess, pos, head, hash) { + hlist_for_each_entry_rcu(sess, head, hash) { ft_sess_unhash(sess); transport_deregister_session_configfs(sess->se_sess); ft_sess_put(sess); /* release from table */ diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c index 455c77a961de..8dc44cbb3e09 100644 --- a/drivers/thermal/cpu_cooling.c +++ b/drivers/thermal/cpu_cooling.c @@ -73,21 +73,14 @@ static struct cpufreq_cooling_device *notify_device; */ static int get_idr(struct idr *idr, int *id) { - int err; -again: - if (unlikely(idr_pre_get(idr, GFP_KERNEL) == 0)) - return -ENOMEM; + int ret; mutex_lock(&cooling_cpufreq_lock); - err = idr_get_new(idr, NULL, id); + ret = idr_alloc(idr, NULL, 0, 0, GFP_KERNEL); mutex_unlock(&cooling_cpufreq_lock); - - if (unlikely(err == -EAGAIN)) - goto again; - else if (unlikely(err)) - return err; - - *id = *id & MAX_IDR_MASK; + if (unlikely(ret < 0)) + return ret; + *id = ret; return 0; } diff --git a/drivers/thermal/thermal_sys.c b/drivers/thermal/thermal_sys.c index 6472e7e9f969..2eaaaa60fb09 100644 --- a/drivers/thermal/thermal_sys.c +++ b/drivers/thermal/thermal_sys.c @@ -131,23 +131,16 @@ EXPORT_SYMBOL_GPL(thermal_unregister_governor); static int get_idr(struct idr *idr, struct mutex *lock, int *id) { - int err; - -again: - if (unlikely(idr_pre_get(idr, GFP_KERNEL) == 0)) - return -ENOMEM; + int ret; if (lock) mutex_lock(lock); - err = idr_get_new(idr, NULL, id); + ret = idr_alloc(idr, NULL, 0, 0, GFP_KERNEL); if (lock) mutex_unlock(lock); - if (unlikely(err == -EAGAIN)) - goto again; - else if (unlikely(err)) - return err; - - *id = *id & MAX_IDR_MASK; + if (unlikely(ret < 0)) + return ret; + *id = ret; return 0; } diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c index 5110f367f1f1..c8b926291e28 100644 --- a/drivers/uio/uio.c +++ b/drivers/uio/uio.c @@ -369,26 +369,15 @@ static void uio_dev_del_attributes(struct uio_device *idev) static int uio_get_minor(struct uio_device *idev) { int retval = -ENOMEM; - int id; mutex_lock(&minor_lock); - if (idr_pre_get(&uio_idr, GFP_KERNEL) == 0) - goto exit; - - retval = idr_get_new(&uio_idr, idev, &id); - if (retval < 0) { - if (retval == -EAGAIN) - retval = -ENOMEM; - goto exit; - } - if (id < UIO_MAX_DEVICES) { - idev->minor = id; - } else { + retval = idr_alloc(&uio_idr, idev, 0, UIO_MAX_DEVICES, GFP_KERNEL); + if (retval >= 0) { + idev->minor = retval; + } else if (retval == -ENOSPC) { dev_err(idev->dev, "too many uio devices\n"); retval = -EINVAL; - idr_remove(&uio_idr, id); } -exit: mutex_unlock(&minor_lock); return retval; } diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 1775ad471edd..5480352f984d 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -5177,6 +5177,7 @@ int usb_reset_device(struct usb_device *udev) { int ret; int i; + unsigned int noio_flag; struct usb_host_config *config = udev->actconfig; if (udev->state == USB_STATE_NOTATTACHED || @@ -5186,6 +5187,17 @@ int usb_reset_device(struct usb_device *udev) return -EINVAL; } + /* + * Don't allocate memory with GFP_KERNEL in current + * context to avoid possible deadlock if usb mass + * storage interface or usbnet interface(iSCSI case) + * is included in current configuration. The easist + * approach is to do it for every device reset, + * because the device 'memalloc_noio' flag may have + * not been set before reseting the usb device. + */ + noio_flag = memalloc_noio_save(); + /* Prevent autosuspend during the reset */ usb_autoresume_device(udev); @@ -5230,6 +5242,7 @@ int usb_reset_device(struct usb_device *udev) } usb_autosuspend_device(udev); + memalloc_noio_restore(noio_flag); return ret; } EXPORT_SYMBOL_GPL(usb_reset_device); diff --git a/drivers/usb/gadget/amd5536udc.c b/drivers/usb/gadget/amd5536udc.c index 75973f33a4c8..142616a42f45 100644 --- a/drivers/usb/gadget/amd5536udc.c +++ b/drivers/usb/gadget/amd5536udc.c @@ -3102,7 +3102,7 @@ static int init_dma_pools(struct udc *dev) } /* DMA setup */ - dev->data_requests = dma_pool_create("data_requests", NULL, + dev->data_requests = dma_pool_create("data_requests", &dev->pdev->dev, sizeof(struct udc_data_dma), 0, 0); if (!dev->data_requests) { DBG(dev, "can't get request data pool\n"); @@ -3114,7 +3114,7 @@ static int init_dma_pools(struct udc *dev) dev->ep[UDC_EP0IN_IX].dma = &dev->regs->ctl; /* dma desc for setup data */ - dev->stp_requests = dma_pool_create("setup requests", NULL, + dev->stp_requests = dma_pool_create("setup requests", &dev->pdev->dev, sizeof(struct udc_stp_dma), 0, 0); if (!dev->stp_requests) { DBG(dev, "can't get stp request pool\n"); @@ -3235,6 +3235,12 @@ static int udc_pci_probe( pci_set_master(pdev); pci_try_set_mwi(pdev); + dev->phys_addr = resource; + dev->irq = pdev->irq; + dev->pdev = pdev; + dev->gadget.dev.parent = &pdev->dev; + dev->gadget.dev.dma_mask = pdev->dev.dma_mask; + /* init dma pools */ if (use_dma) { retval = init_dma_pools(dev); @@ -3242,12 +3248,6 @@ static int udc_pci_probe( goto finished; } - dev->phys_addr = resource; - dev->irq = pdev->irq; - dev->pdev = pdev; - dev->gadget.dev.parent = &pdev->dev; - dev->gadget.dev.dma_mask = pdev->dev.dma_mask; - /* general probing */ if (udc_probe(dev) == 0) return 0; diff --git a/drivers/usb/gadget/inode.c b/drivers/usb/gadget/inode.c index 8ac840f25ba9..f4bbc7d39ae9 100644 --- a/drivers/usb/gadget/inode.c +++ b/drivers/usb/gadget/inode.c @@ -24,6 +24,8 @@ #include <linux/sched.h> #include <linux/slab.h> #include <linux/poll.h> +#include <linux/mmu_context.h> +#include <linux/aio.h> #include <linux/device.h> #include <linux/moduleparam.h> @@ -513,6 +515,9 @@ static long ep_ioctl(struct file *fd, unsigned code, unsigned long value) struct kiocb_priv { struct usb_request *req; struct ep_data *epdata; + struct kiocb *iocb; + struct mm_struct *mm; + struct work_struct work; void *buf; const struct iovec *iv; unsigned long nr_segs; @@ -528,7 +533,6 @@ static int ep_aio_cancel(struct kiocb *iocb, struct io_event *e) local_irq_disable(); epdata = priv->epdata; // spin_lock(&epdata->dev->lock); - kiocbSetCancelled(iocb); if (likely(epdata && epdata->ep && priv->req)) value = usb_ep_dequeue (epdata->ep, priv->req); else @@ -540,15 +544,12 @@ static int ep_aio_cancel(struct kiocb *iocb, struct io_event *e) return value; } -static ssize_t ep_aio_read_retry(struct kiocb *iocb) +static ssize_t ep_copy_to_user(struct kiocb_priv *priv) { - struct kiocb_priv *priv = iocb->private; ssize_t len, total; void *to_copy; int i; - /* we "retry" to get the right mm context for this: */ - /* copy stuff into user buffers */ total = priv->actual; len = 0; @@ -568,9 +569,26 @@ static ssize_t ep_aio_read_retry(struct kiocb *iocb) if (total == 0) break; } + + return len; +} + +static void ep_user_copy_worker(struct work_struct *work) +{ + struct kiocb_priv *priv = container_of(work, struct kiocb_priv, work); + struct mm_struct *mm = priv->mm; + struct kiocb *iocb = priv->iocb; + size_t ret; + + use_mm(mm); + ret = ep_copy_to_user(priv); + unuse_mm(mm); + + /* completing the iocb can drop the ctx and mm, don't touch mm after */ + aio_complete(iocb, ret, ret); + kfree(priv->buf); kfree(priv); - return len; } static void ep_aio_complete(struct usb_ep *ep, struct usb_request *req) @@ -596,14 +614,14 @@ static void ep_aio_complete(struct usb_ep *ep, struct usb_request *req) aio_complete(iocb, req->actual ? req->actual : req->status, req->status); } else { - /* retry() won't report both; so we hide some faults */ + /* ep_copy_to_user() won't report both; we hide some faults */ if (unlikely(0 != req->status)) DBG(epdata->dev, "%s fault %d len %d\n", ep->name, req->status, req->actual); priv->buf = req->buf; priv->actual = req->actual; - kick_iocb(iocb); + schedule_work(&priv->work); } spin_unlock(&epdata->dev->lock); @@ -633,8 +651,10 @@ fail: return value; } iocb->private = priv; + priv->iocb = iocb; priv->iv = iv; priv->nr_segs = nr_segs; + INIT_WORK(&priv->work, ep_user_copy_worker); value = get_ready_ep(iocb->ki_filp->f_flags, epdata); if (unlikely(value < 0)) { @@ -642,10 +662,11 @@ fail: goto fail; } - iocb->ki_cancel = ep_aio_cancel; + kiocb_set_cancel_fn(iocb, ep_aio_cancel); get_ep(epdata); priv->epdata = epdata; priv->actual = 0; + priv->mm = current->mm; /* mm teardown waits for iocbs in exit_aio() */ /* each kiocb is coupled to one usb_request, but we can't * allocate or submit those if the host disconnected. @@ -674,7 +695,7 @@ fail: kfree(priv); put_ep(epdata); } else - value = (iv ? -EIOCBRETRY : -EIOCBQUEUED); + value = -EIOCBQUEUED; return value; } @@ -692,7 +713,6 @@ ep_aio_read(struct kiocb *iocb, const struct iovec *iov, if (unlikely(!buf)) return -ENOMEM; - iocb->ki_retry = ep_aio_read_retry; return ep_aio_rwtail(iocb, buf, iocb->ki_left, epdata, iov, nr_segs); } diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 12c264d3b058..7f61abfa4563 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -139,23 +139,8 @@ EXPORT_SYMBOL_GPL(vfio_unregister_iommu_driver); */ static int vfio_alloc_group_minor(struct vfio_group *group) { - int ret, minor; - -again: - if (unlikely(idr_pre_get(&vfio.group_idr, GFP_KERNEL) == 0)) - return -ENOMEM; - /* index 0 is used by /dev/vfio/vfio */ - ret = idr_get_new_above(&vfio.group_idr, group, 1, &minor); - if (ret == -EAGAIN) - goto again; - if (ret || minor > MINORMASK) { - if (minor > MINORMASK) - idr_remove(&vfio.group_idr, minor); - return -ENOSPC; - } - - return minor; + return idr_alloc(&vfio.group_idr, group, 1, MINORMASK + 1, GFP_KERNEL); } static void vfio_free_group_minor(int minor) diff --git a/drivers/video/Kconfig b/drivers/video/Kconfig index e4e1765b82f2..55a66a60bb32 100644 --- a/drivers/video/Kconfig +++ b/drivers/video/Kconfig @@ -364,7 +364,7 @@ config FB_SA1100 Y here. config FB_IMX - tristate "Freescale i.MX LCD support" + tristate "Freescale i.MX1/21/25/27 LCD support" depends on FB && IMX_HAVE_PLATFORM_IMX_FB select FB_CFB_FILLRECT select FB_CFB_COPYAREA @@ -2183,6 +2183,15 @@ config FB_XILINX framebuffer. ML300 carries a 640*480 LCD display on the board, ML403 uses a standard DB15 VGA connector. +config FB_GOLDFISH + tristate "Goldfish Framebuffer" + depends on FB + select FB_CFB_FILLRECT + select FB_CFB_COPYAREA + select FB_CFB_IMAGEBLIT + ---help--- + Framebuffer driver for Goldfish Virtual Platform + config FB_COBALT tristate "Cobalt server LCD frame buffer support" depends on FB && (MIPS_COBALT || MIPS_SEAD3) @@ -2422,6 +2431,7 @@ config FB_PUV3_UNIGFX source "drivers/video/omap/Kconfig" source "drivers/video/omap2/Kconfig" source "drivers/video/exynos/Kconfig" +source "drivers/video/mmp/Kconfig" source "drivers/video/backlight/Kconfig" if VT diff --git a/drivers/video/Makefile b/drivers/video/Makefile index 768a137a1bac..0577f834fdcd 100644 --- a/drivers/video/Makefile +++ b/drivers/video/Makefile @@ -98,6 +98,7 @@ obj-$(CONFIG_FB_ATMEL) += atmel_lcdfb.o obj-$(CONFIG_FB_PVR2) += pvr2fb.o obj-$(CONFIG_FB_VOODOO1) += sstfb.o obj-$(CONFIG_FB_ARMCLCD) += amba-clcd.o +obj-$(CONFIG_FB_GOLDFISH) += goldfishfb.o obj-$(CONFIG_FB_68328) += 68328fb.o obj-$(CONFIG_FB_GBE) += gbefb.o obj-$(CONFIG_FB_CIRRUS) += cirrusfb.o @@ -105,6 +106,7 @@ obj-$(CONFIG_FB_ASILIANT) += asiliantfb.o obj-$(CONFIG_FB_PXA) += pxafb.o obj-$(CONFIG_FB_PXA168) += pxa168fb.o obj-$(CONFIG_PXA3XX_GCU) += pxa3xx-gcu.o +obj-$(CONFIG_MMP_DISP) += mmp/ obj-$(CONFIG_FB_W100) += w100fb.o obj-$(CONFIG_FB_TMIO) += tmiofb.o obj-$(CONFIG_FB_AU1100) += au1100fb.o diff --git a/drivers/video/backlight/88pm860x_bl.c b/drivers/video/backlight/88pm860x_bl.c index c072ed9aea36..2cd63507ed74 100644 --- a/drivers/video/backlight/88pm860x_bl.c +++ b/drivers/video/backlight/88pm860x_bl.c @@ -165,8 +165,10 @@ static int pm860x_backlight_dt_init(struct platform_device *pdev, struct pm860x_backlight_data *data, char *name) { - struct device_node *nproot = pdev->dev.parent->of_node, *np; + struct device_node *nproot, *np; int iset = 0; + + nproot = of_node_get(pdev->dev.parent->of_node); if (!nproot) return -ENODEV; nproot = of_find_node_by_name(nproot, "backlights"); @@ -184,6 +186,7 @@ static int pm860x_backlight_dt_init(struct platform_device *pdev, break; } } + of_node_put(nproot); return 0; } #else diff --git a/drivers/video/backlight/Kconfig b/drivers/video/backlight/Kconfig index 765a945f8ea1..e2fc9f50bbea 100644 --- a/drivers/video/backlight/Kconfig +++ b/drivers/video/backlight/Kconfig @@ -126,6 +126,21 @@ config LCD_AMS369FG06 If you have an AMS369FG06 AMOLED Panel, say Y to enable its LCD control driver. +config LCD_LMS501KF03 + tristate "LMS501KF03 LCD Driver" + depends on SPI + default n + help + If you have an LMS501KF03 LCD Panel, say Y to enable its + LCD control driver. + +config LCD_HX8357 + tristate "Himax HX-8357 LCD Driver" + depends on SPI + help + If you have a HX-8357 LCD panel, say Y to enable its LCD control + driver. + endif # LCD_CLASS_DEVICE # @@ -369,6 +384,12 @@ config BACKLIGHT_LP855X This supports TI LP8550, LP8551, LP8552, LP8553 and LP8556 backlight driver. +config BACKLIGHT_LP8788 + tristate "Backlight driver for TI LP8788 MFD" + depends on BACKLIGHT_CLASS_DEVICE && MFD_LP8788 + help + This supports TI LP8788 backlight driver. + config BACKLIGHT_OT200 tristate "Backlight driver for ot200 visualisation device" depends on BACKLIGHT_CLASS_DEVICE && CS5535_MFGPT && GPIO_CS5535 @@ -390,6 +411,13 @@ config BACKLIGHT_TPS65217 If you have a Texas Instruments TPS65217 say Y to enable the backlight driver. +config BACKLIGHT_AS3711 + tristate "AS3711 Backlight" + depends on BACKLIGHT_CLASS_DEVICE && MFD_AS3711 + help + If you have an Austrian Microsystems AS3711 say Y to enable the + backlight driver. + endif # BACKLIGHT_CLASS_DEVICE endif # BACKLIGHT_LCD_SUPPORT diff --git a/drivers/video/backlight/Makefile b/drivers/video/backlight/Makefile index e7ce7291635d..96c4d620c5ce 100644 --- a/drivers/video/backlight/Makefile +++ b/drivers/video/backlight/Makefile @@ -1,47 +1,51 @@ # Backlight & LCD drivers -obj-$(CONFIG_LCD_CLASS_DEVICE) += lcd.o -obj-$(CONFIG_LCD_CORGI) += corgi_lcd.o -obj-$(CONFIG_LCD_HP700) += jornada720_lcd.o -obj-$(CONFIG_LCD_L4F00242T03) += l4f00242t03.o -obj-$(CONFIG_LCD_LMS283GF05) += lms283gf05.o -obj-$(CONFIG_LCD_LTV350QV) += ltv350qv.o -obj-$(CONFIG_LCD_ILI9320) += ili9320.o -obj-$(CONFIG_LCD_PLATFORM) += platform_lcd.o -obj-$(CONFIG_LCD_VGG2432A4) += vgg2432a4.o -obj-$(CONFIG_LCD_TDO24M) += tdo24m.o -obj-$(CONFIG_LCD_TOSA) += tosa_lcd.o -obj-$(CONFIG_LCD_S6E63M0) += s6e63m0.o -obj-$(CONFIG_LCD_LD9040) += ld9040.o -obj-$(CONFIG_LCD_AMS369FG06) += ams369fg06.o +obj-$(CONFIG_LCD_AMS369FG06) += ams369fg06.o +obj-$(CONFIG_LCD_CLASS_DEVICE) += lcd.o +obj-$(CONFIG_LCD_CORGI) += corgi_lcd.o +obj-$(CONFIG_LCD_HP700) += jornada720_lcd.o +obj-$(CONFIG_LCD_HX8357) += hx8357.o +obj-$(CONFIG_LCD_ILI9320) += ili9320.o +obj-$(CONFIG_LCD_L4F00242T03) += l4f00242t03.o +obj-$(CONFIG_LCD_LD9040) += ld9040.o +obj-$(CONFIG_LCD_LMS283GF05) += lms283gf05.o +obj-$(CONFIG_LCD_LMS501KF03) += lms501kf03.o +obj-$(CONFIG_LCD_LTV350QV) += ltv350qv.o +obj-$(CONFIG_LCD_PLATFORM) += platform_lcd.o +obj-$(CONFIG_LCD_S6E63M0) += s6e63m0.o +obj-$(CONFIG_LCD_TDO24M) += tdo24m.o +obj-$(CONFIG_LCD_TOSA) += tosa_lcd.o +obj-$(CONFIG_LCD_VGG2432A4) += vgg2432a4.o -obj-$(CONFIG_BACKLIGHT_CLASS_DEVICE) += backlight.o -obj-$(CONFIG_BACKLIGHT_ATMEL_PWM) += atmel-pwm-bl.o -obj-$(CONFIG_BACKLIGHT_EP93XX) += ep93xx_bl.o -obj-$(CONFIG_BACKLIGHT_GENERIC) += generic_bl.o -obj-$(CONFIG_BACKLIGHT_HP700) += jornada720_bl.o -obj-$(CONFIG_BACKLIGHT_HP680) += hp680_bl.o -obj-$(CONFIG_BACKLIGHT_LM3533) += lm3533_bl.o -obj-$(CONFIG_BACKLIGHT_LOCOMO) += locomolcd.o -obj-$(CONFIG_BACKLIGHT_LM3630) += lm3630_bl.o -obj-$(CONFIG_BACKLIGHT_LM3639) += lm3639_bl.o -obj-$(CONFIG_BACKLIGHT_LP855X) += lp855x_bl.o -obj-$(CONFIG_BACKLIGHT_OMAP1) += omap1_bl.o -obj-$(CONFIG_BACKLIGHT_PANDORA) += pandora_bl.o -obj-$(CONFIG_BACKLIGHT_CARILLO_RANCH) += cr_bllcd.o -obj-$(CONFIG_BACKLIGHT_PWM) += pwm_bl.o -obj-$(CONFIG_BACKLIGHT_DA903X) += da903x_bl.o -obj-$(CONFIG_BACKLIGHT_DA9052) += da9052_bl.o -obj-$(CONFIG_BACKLIGHT_MAX8925) += max8925_bl.o -obj-$(CONFIG_BACKLIGHT_APPLE) += apple_bl.o -obj-$(CONFIG_BACKLIGHT_TOSA) += tosa_bl.o -obj-$(CONFIG_BACKLIGHT_SAHARA) += kb3886_bl.o -obj-$(CONFIG_BACKLIGHT_WM831X) += wm831x_bl.o -obj-$(CONFIG_BACKLIGHT_ADP5520) += adp5520_bl.o -obj-$(CONFIG_BACKLIGHT_ADP8860) += adp8860_bl.o -obj-$(CONFIG_BACKLIGHT_ADP8870) += adp8870_bl.o -obj-$(CONFIG_BACKLIGHT_88PM860X) += 88pm860x_bl.o +obj-$(CONFIG_BACKLIGHT_88PM860X) += 88pm860x_bl.o +obj-$(CONFIG_BACKLIGHT_AAT2870) += aat2870_bl.o +obj-$(CONFIG_BACKLIGHT_ADP5520) += adp5520_bl.o +obj-$(CONFIG_BACKLIGHT_ADP8860) += adp8860_bl.o +obj-$(CONFIG_BACKLIGHT_ADP8870) += adp8870_bl.o +obj-$(CONFIG_BACKLIGHT_APPLE) += apple_bl.o +obj-$(CONFIG_BACKLIGHT_AS3711) += as3711_bl.o +obj-$(CONFIG_BACKLIGHT_ATMEL_PWM) += atmel-pwm-bl.o +obj-$(CONFIG_BACKLIGHT_CARILLO_RANCH) += cr_bllcd.o +obj-$(CONFIG_BACKLIGHT_CLASS_DEVICE) += backlight.o +obj-$(CONFIG_BACKLIGHT_DA903X) += da903x_bl.o +obj-$(CONFIG_BACKLIGHT_DA9052) += da9052_bl.o +obj-$(CONFIG_BACKLIGHT_EP93XX) += ep93xx_bl.o +obj-$(CONFIG_BACKLIGHT_GENERIC) += generic_bl.o +obj-$(CONFIG_BACKLIGHT_HP680) += hp680_bl.o +obj-$(CONFIG_BACKLIGHT_HP700) += jornada720_bl.o +obj-$(CONFIG_BACKLIGHT_LM3533) += lm3533_bl.o +obj-$(CONFIG_BACKLIGHT_LM3630) += lm3630_bl.o +obj-$(CONFIG_BACKLIGHT_LM3639) += lm3639_bl.o +obj-$(CONFIG_BACKLIGHT_LOCOMO) += locomolcd.o +obj-$(CONFIG_BACKLIGHT_LP855X) += lp855x_bl.o +obj-$(CONFIG_BACKLIGHT_LP8788) += lp8788_bl.o +obj-$(CONFIG_BACKLIGHT_MAX8925) += max8925_bl.o +obj-$(CONFIG_BACKLIGHT_OMAP1) += omap1_bl.o +obj-$(CONFIG_BACKLIGHT_OT200) += ot200_bl.o +obj-$(CONFIG_BACKLIGHT_PANDORA) += pandora_bl.o obj-$(CONFIG_BACKLIGHT_PCF50633) += pcf50633-backlight.o -obj-$(CONFIG_BACKLIGHT_AAT2870) += aat2870_bl.o -obj-$(CONFIG_BACKLIGHT_OT200) += ot200_bl.o -obj-$(CONFIG_BACKLIGHT_TPS65217) += tps65217_bl.o +obj-$(CONFIG_BACKLIGHT_PWM) += pwm_bl.o +obj-$(CONFIG_BACKLIGHT_SAHARA) += kb3886_bl.o +obj-$(CONFIG_BACKLIGHT_TOSA) += tosa_bl.o +obj-$(CONFIG_BACKLIGHT_TPS65217) += tps65217_bl.o +obj-$(CONFIG_BACKLIGHT_WM831X) += wm831x_bl.o diff --git a/drivers/video/backlight/aat2870_bl.c b/drivers/video/backlight/aat2870_bl.c index 7ff752288b92..c6fc668d6236 100644 --- a/drivers/video/backlight/aat2870_bl.c +++ b/drivers/video/backlight/aat2870_bl.c @@ -74,7 +74,7 @@ static int aat2870_bl_get_brightness(struct backlight_device *bd) static int aat2870_bl_update_status(struct backlight_device *bd) { - struct aat2870_bl_driver_data *aat2870_bl = dev_get_drvdata(&bd->dev); + struct aat2870_bl_driver_data *aat2870_bl = bl_get_data(bd); struct aat2870_data *aat2870 = dev_get_drvdata(aat2870_bl->pdev->dev.parent); int brightness = bd->props.brightness; diff --git a/drivers/video/backlight/ams369fg06.c b/drivers/video/backlight/ams369fg06.c index f57e1905236a..d29e49443f29 100644 --- a/drivers/video/backlight/ams369fg06.c +++ b/drivers/video/backlight/ams369fg06.c @@ -10,25 +10,16 @@ * under the terms of the GNU General Public License as published by the * Free Software Foundation; either version 2 of the License, or (at your * option) any later version. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */ -#include <linux/wait.h> -#include <linux/module.h> -#include <linux/fb.h> +#include <linux/backlight.h> #include <linux/delay.h> +#include <linux/fb.h> #include <linux/gpio.h> -#include <linux/spi/spi.h> #include <linux/lcd.h> -#include <linux/backlight.h> +#include <linux/module.h> +#include <linux/spi/spi.h> +#include <linux/wait.h> #define SLEEPMSEC 0x1000 #define ENDDEF 0x2000 @@ -210,8 +201,9 @@ static int ams369fg06_panel_send_sequence(struct ams369fg06 *lcd, ret = ams369fg06_spi_write(lcd, wbuf[i], wbuf[i+1]); if (ret) break; - } else - mdelay(wbuf[i+1]); + } else { + msleep(wbuf[i+1]); + } i += 2; } @@ -313,41 +305,32 @@ static int ams369fg06_ldi_disable(struct ams369fg06 *lcd) static int ams369fg06_power_is_on(int power) { - return ((power) <= FB_BLANK_NORMAL); + return power <= FB_BLANK_NORMAL; } static int ams369fg06_power_on(struct ams369fg06 *lcd) { int ret = 0; - struct lcd_platform_data *pd = NULL; - struct backlight_device *bd = NULL; + struct lcd_platform_data *pd; + struct backlight_device *bd; pd = lcd->lcd_pd; - if (!pd) { - dev_err(lcd->dev, "platform data is NULL.\n"); - return -EFAULT; - } - bd = lcd->bd; - if (!bd) { - dev_err(lcd->dev, "backlight device is NULL.\n"); - return -EFAULT; - } if (!pd->power_on) { dev_err(lcd->dev, "power_on is NULL.\n"); - return -EFAULT; + return -EINVAL; } else { pd->power_on(lcd->ld, 1); - mdelay(pd->power_on_delay); + msleep(pd->power_on_delay); } if (!pd->reset) { dev_err(lcd->dev, "reset is NULL.\n"); - return -EFAULT; + return -EINVAL; } else { pd->reset(lcd->ld); - mdelay(pd->reset_delay); + msleep(pd->reset_delay); } ret = ams369fg06_ldi_init(lcd); @@ -374,14 +357,10 @@ static int ams369fg06_power_on(struct ams369fg06 *lcd) static int ams369fg06_power_off(struct ams369fg06 *lcd) { - int ret = 0; - struct lcd_platform_data *pd = NULL; + int ret; + struct lcd_platform_data *pd; pd = lcd->lcd_pd; - if (!pd) { - dev_err(lcd->dev, "platform data is NULL\n"); - return -EFAULT; - } ret = ams369fg06_ldi_disable(lcd); if (ret) { @@ -389,13 +368,9 @@ static int ams369fg06_power_off(struct ams369fg06 *lcd) return -EIO; } - mdelay(pd->power_off_delay); + msleep(pd->power_off_delay); - if (!pd->power_on) { - dev_err(lcd->dev, "power_on is NULL.\n"); - return -EFAULT; - } else - pd->power_on(lcd->ld, 0); + pd->power_on(lcd->ld, 0); return 0; } @@ -446,7 +421,7 @@ static int ams369fg06_set_brightness(struct backlight_device *bd) { int ret = 0; int brightness = bd->props.brightness; - struct ams369fg06 *lcd = dev_get_drvdata(&bd->dev); + struct ams369fg06 *lcd = bl_get_data(bd); if (brightness < MIN_BRIGHTNESS || brightness > bd->props.max_brightness) { @@ -501,7 +476,7 @@ static int ams369fg06_probe(struct spi_device *spi) lcd->lcd_pd = spi->dev.platform_data; if (!lcd->lcd_pd) { dev_err(&spi->dev, "platform data is NULL\n"); - return -EFAULT; + return -EINVAL; } ld = lcd_device_register("ams369fg06", &spi->dev, lcd, @@ -534,10 +509,11 @@ static int ams369fg06_probe(struct spi_device *spi) lcd->power = FB_BLANK_POWERDOWN; ams369fg06_power(lcd, FB_BLANK_UNBLANK); - } else + } else { lcd->power = FB_BLANK_UNBLANK; + } - dev_set_drvdata(&spi->dev, lcd); + spi_set_drvdata(spi, lcd); dev_info(&spi->dev, "ams369fg06 panel driver has been probed.\n"); @@ -550,7 +526,7 @@ out_lcd_unregister: static int ams369fg06_remove(struct spi_device *spi) { - struct ams369fg06 *lcd = dev_get_drvdata(&spi->dev); + struct ams369fg06 *lcd = spi_get_drvdata(spi); ams369fg06_power(lcd, FB_BLANK_POWERDOWN); backlight_device_unregister(lcd->bd); @@ -560,44 +536,26 @@ static int ams369fg06_remove(struct spi_device *spi) } #if defined(CONFIG_PM) -static unsigned int before_power; - static int ams369fg06_suspend(struct spi_device *spi, pm_message_t mesg) { - int ret = 0; - struct ams369fg06 *lcd = dev_get_drvdata(&spi->dev); + struct ams369fg06 *lcd = spi_get_drvdata(spi); dev_dbg(&spi->dev, "lcd->power = %d\n", lcd->power); - before_power = lcd->power; - /* * when lcd panel is suspend, lcd panel becomes off * regardless of status. */ - ret = ams369fg06_power(lcd, FB_BLANK_POWERDOWN); - - return ret; + return ams369fg06_power(lcd, FB_BLANK_POWERDOWN); } static int ams369fg06_resume(struct spi_device *spi) { - int ret = 0; - struct ams369fg06 *lcd = dev_get_drvdata(&spi->dev); + struct ams369fg06 *lcd = spi_get_drvdata(spi); - /* - * after suspended, if lcd panel status is FB_BLANK_UNBLANK - * (at that time, before_power is FB_BLANK_UNBLANK) then - * it changes that status to FB_BLANK_POWERDOWN to get lcd on. - */ - if (before_power == FB_BLANK_UNBLANK) - lcd->power = FB_BLANK_POWERDOWN; - - dev_dbg(&spi->dev, "before_power = %d\n", before_power); + lcd->power = FB_BLANK_POWERDOWN; - ret = ams369fg06_power(lcd, before_power); - - return ret; + return ams369fg06_power(lcd, FB_BLANK_UNBLANK); } #else #define ams369fg06_suspend NULL @@ -606,7 +564,7 @@ static int ams369fg06_resume(struct spi_device *spi) static void ams369fg06_shutdown(struct spi_device *spi) { - struct ams369fg06 *lcd = dev_get_drvdata(&spi->dev); + struct ams369fg06 *lcd = spi_get_drvdata(spi); ams369fg06_power(lcd, FB_BLANK_POWERDOWN); } diff --git a/drivers/video/backlight/as3711_bl.c b/drivers/video/backlight/as3711_bl.c new file mode 100644 index 000000000000..41d52fe52543 --- /dev/null +++ b/drivers/video/backlight/as3711_bl.c @@ -0,0 +1,380 @@ +/* + * AS3711 PMIC backlight driver, using DCDC Step Up Converters + * + * Copyright (C) 2012 Renesas Electronics Corporation + * Author: Guennadi Liakhovetski, <g.liakhovetski@gmx.de> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the version 2 of the GNU General Public License as + * published by the Free Software Foundation + */ + +#include <linux/backlight.h> +#include <linux/delay.h> +#include <linux/device.h> +#include <linux/err.h> +#include <linux/fb.h> +#include <linux/kernel.h> +#include <linux/mfd/as3711.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/regmap.h> +#include <linux/slab.h> + +enum as3711_bl_type { + AS3711_BL_SU1, + AS3711_BL_SU2, +}; + +struct as3711_bl_data { + bool powered; + const char *fb_name; + struct device *fb_dev; + enum as3711_bl_type type; + int brightness; + struct backlight_device *bl; +}; + +struct as3711_bl_supply { + struct as3711_bl_data su1; + struct as3711_bl_data su2; + const struct as3711_bl_pdata *pdata; + struct as3711 *as3711; +}; + +static struct as3711_bl_supply *to_supply(struct as3711_bl_data *su) +{ + switch (su->type) { + case AS3711_BL_SU1: + return container_of(su, struct as3711_bl_supply, su1); + case AS3711_BL_SU2: + return container_of(su, struct as3711_bl_supply, su2); + } + return NULL; +} + +static int as3711_set_brightness_auto_i(struct as3711_bl_data *data, + unsigned int brightness) +{ + struct as3711_bl_supply *supply = to_supply(data); + struct as3711 *as3711 = supply->as3711; + const struct as3711_bl_pdata *pdata = supply->pdata; + int ret = 0; + + /* Only all equal current values are supported */ + if (pdata->su2_auto_curr1) + ret = regmap_write(as3711->regmap, AS3711_CURR1_VALUE, + brightness); + if (!ret && pdata->su2_auto_curr2) + ret = regmap_write(as3711->regmap, AS3711_CURR2_VALUE, + brightness); + if (!ret && pdata->su2_auto_curr3) + ret = regmap_write(as3711->regmap, AS3711_CURR3_VALUE, + brightness); + + return ret; +} + +static int as3711_set_brightness_v(struct as3711 *as3711, + unsigned int brightness, + unsigned int reg) +{ + if (brightness > 31) + return -EINVAL; + + return regmap_update_bits(as3711->regmap, reg, 0xf0, + brightness << 4); +} + +static int as3711_bl_su2_reset(struct as3711_bl_supply *supply) +{ + struct as3711 *as3711 = supply->as3711; + int ret = regmap_update_bits(as3711->regmap, AS3711_STEPUP_CONTROL_5, + 3, supply->pdata->su2_fbprot); + if (!ret) + ret = regmap_update_bits(as3711->regmap, + AS3711_STEPUP_CONTROL_2, 1, 0); + if (!ret) + ret = regmap_update_bits(as3711->regmap, + AS3711_STEPUP_CONTROL_2, 1, 1); + return ret; +} + +/* + * Someone with less fragile or less expensive hardware could try to simplify + * the brightness adjustment procedure. + */ +static int as3711_bl_update_status(struct backlight_device *bl) +{ + struct as3711_bl_data *data = bl_get_data(bl); + struct as3711_bl_supply *supply = to_supply(data); + struct as3711 *as3711 = supply->as3711; + int brightness = bl->props.brightness; + int ret = 0; + + dev_dbg(&bl->dev, "%s(): brightness %u, pwr %x, blank %x, state %x\n", + __func__, bl->props.brightness, bl->props.power, + bl->props.fb_blank, bl->props.state); + + if (bl->props.power != FB_BLANK_UNBLANK || + bl->props.fb_blank != FB_BLANK_UNBLANK || + bl->props.state & (BL_CORE_SUSPENDED | BL_CORE_FBBLANK)) + brightness = 0; + + if (data->type == AS3711_BL_SU1) { + ret = as3711_set_brightness_v(as3711, brightness, + AS3711_STEPUP_CONTROL_1); + } else { + const struct as3711_bl_pdata *pdata = supply->pdata; + + switch (pdata->su2_feedback) { + case AS3711_SU2_VOLTAGE: + ret = as3711_set_brightness_v(as3711, brightness, + AS3711_STEPUP_CONTROL_2); + break; + case AS3711_SU2_CURR_AUTO: + ret = as3711_set_brightness_auto_i(data, brightness / 4); + if (ret < 0) + return ret; + if (brightness) { + ret = as3711_bl_su2_reset(supply); + if (ret < 0) + return ret; + udelay(500); + ret = as3711_set_brightness_auto_i(data, brightness); + } else { + ret = regmap_update_bits(as3711->regmap, + AS3711_STEPUP_CONTROL_2, 1, 0); + } + break; + /* Manual one current feedback pin below */ + case AS3711_SU2_CURR1: + ret = regmap_write(as3711->regmap, AS3711_CURR1_VALUE, + brightness); + break; + case AS3711_SU2_CURR2: + ret = regmap_write(as3711->regmap, AS3711_CURR2_VALUE, + brightness); + break; + case AS3711_SU2_CURR3: + ret = regmap_write(as3711->regmap, AS3711_CURR3_VALUE, + brightness); + break; + default: + ret = -EINVAL; + } + } + if (!ret) + data->brightness = brightness; + + return ret; +} + +static int as3711_bl_get_brightness(struct backlight_device *bl) +{ + struct as3711_bl_data *data = bl_get_data(bl); + + return data->brightness; +} + +static const struct backlight_ops as3711_bl_ops = { + .update_status = as3711_bl_update_status, + .get_brightness = as3711_bl_get_brightness, +}; + +static int as3711_bl_init_su2(struct as3711_bl_supply *supply) +{ + struct as3711 *as3711 = supply->as3711; + const struct as3711_bl_pdata *pdata = supply->pdata; + u8 ctl = 0; + int ret; + + dev_dbg(as3711->dev, "%s(): use %u\n", __func__, pdata->su2_feedback); + + /* Turn SU2 off */ + ret = regmap_write(as3711->regmap, AS3711_STEPUP_CONTROL_2, 0); + if (ret < 0) + return ret; + + switch (pdata->su2_feedback) { + case AS3711_SU2_VOLTAGE: + ret = regmap_update_bits(as3711->regmap, AS3711_STEPUP_CONTROL_4, 3, 0); + break; + case AS3711_SU2_CURR1: + ctl = 1; + ret = regmap_update_bits(as3711->regmap, AS3711_STEPUP_CONTROL_4, 3, 1); + break; + case AS3711_SU2_CURR2: + ctl = 4; + ret = regmap_update_bits(as3711->regmap, AS3711_STEPUP_CONTROL_4, 3, 2); + break; + case AS3711_SU2_CURR3: + ctl = 0x10; + ret = regmap_update_bits(as3711->regmap, AS3711_STEPUP_CONTROL_4, 3, 3); + break; + case AS3711_SU2_CURR_AUTO: + if (pdata->su2_auto_curr1) + ctl = 2; + if (pdata->su2_auto_curr2) + ctl |= 8; + if (pdata->su2_auto_curr3) + ctl |= 0x20; + ret = 0; + break; + default: + return -EINVAL; + } + + if (!ret) + ret = regmap_write(as3711->regmap, AS3711_CURR_CONTROL, ctl); + + return ret; +} + +static int as3711_bl_register(struct platform_device *pdev, + unsigned int max_brightness, struct as3711_bl_data *su) +{ + struct backlight_properties props = {.type = BACKLIGHT_RAW,}; + struct backlight_device *bl; + + /* max tuning I = 31uA for voltage- and 38250uA for current-feedback */ + props.max_brightness = max_brightness; + + bl = backlight_device_register(su->type == AS3711_BL_SU1 ? + "as3711-su1" : "as3711-su2", + &pdev->dev, su, + &as3711_bl_ops, &props); + if (IS_ERR(bl)) { + dev_err(&pdev->dev, "failed to register backlight\n"); + return PTR_ERR(bl); + } + + bl->props.brightness = props.max_brightness; + + backlight_update_status(bl); + + su->bl = bl; + + return 0; +} + +static int as3711_backlight_probe(struct platform_device *pdev) +{ + struct as3711_bl_pdata *pdata = dev_get_platdata(&pdev->dev); + struct as3711 *as3711 = dev_get_drvdata(pdev->dev.parent); + struct as3711_bl_supply *supply; + struct as3711_bl_data *su; + unsigned int max_brightness; + int ret; + + if (!pdata || (!pdata->su1_fb && !pdata->su2_fb)) { + dev_err(&pdev->dev, "No platform data, exiting...\n"); + return -ENODEV; + } + + /* + * Due to possible hardware damage I chose to block all modes, + * unsupported on my hardware. Anyone, wishing to use any of those modes + * will have to first review the code, then activate and test it. + */ + if (pdata->su1_fb || + pdata->su2_fbprot != AS3711_SU2_GPIO4 || + pdata->su2_feedback != AS3711_SU2_CURR_AUTO) { + dev_warn(&pdev->dev, + "Attention! An untested mode has been chosen!\n" + "Please, review the code, enable, test, and report success:-)\n"); + return -EINVAL; + } + + supply = devm_kzalloc(&pdev->dev, sizeof(*supply), GFP_KERNEL); + if (!supply) + return -ENOMEM; + + supply->as3711 = as3711; + supply->pdata = pdata; + + if (pdata->su1_fb) { + su = &supply->su1; + su->fb_name = pdata->su1_fb; + su->type = AS3711_BL_SU1; + + max_brightness = min(pdata->su1_max_uA, 31); + ret = as3711_bl_register(pdev, max_brightness, su); + if (ret < 0) + return ret; + } + + if (pdata->su2_fb) { + su = &supply->su2; + su->fb_name = pdata->su2_fb; + su->type = AS3711_BL_SU2; + + switch (pdata->su2_fbprot) { + case AS3711_SU2_GPIO2: + case AS3711_SU2_GPIO3: + case AS3711_SU2_GPIO4: + case AS3711_SU2_LX_SD4: + break; + default: + ret = -EINVAL; + goto esu2; + } + + switch (pdata->su2_feedback) { + case AS3711_SU2_VOLTAGE: + max_brightness = min(pdata->su2_max_uA, 31); + break; + case AS3711_SU2_CURR1: + case AS3711_SU2_CURR2: + case AS3711_SU2_CURR3: + case AS3711_SU2_CURR_AUTO: + max_brightness = min(pdata->su2_max_uA / 150, 255); + break; + default: + ret = -EINVAL; + goto esu2; + } + + ret = as3711_bl_init_su2(supply); + if (ret < 0) + return ret; + + ret = as3711_bl_register(pdev, max_brightness, su); + if (ret < 0) + goto esu2; + } + + platform_set_drvdata(pdev, supply); + + return 0; + +esu2: + backlight_device_unregister(supply->su1.bl); + return ret; +} + +static int as3711_backlight_remove(struct platform_device *pdev) +{ + struct as3711_bl_supply *supply = platform_get_drvdata(pdev); + + backlight_device_unregister(supply->su1.bl); + backlight_device_unregister(supply->su2.bl); + + return 0; +} + +static struct platform_driver as3711_backlight_driver = { + .driver = { + .name = "as3711-backlight", + .owner = THIS_MODULE, + }, + .probe = as3711_backlight_probe, + .remove = as3711_backlight_remove, +}; + +module_platform_driver(as3711_backlight_driver); + +MODULE_DESCRIPTION("Backlight Driver for AS3711 PMICs"); +MODULE_AUTHOR("Guennadi Liakhovetski <g.liakhovetski@gmx.de"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:as3711-backlight"); diff --git a/drivers/video/backlight/corgi_lcd.c b/drivers/video/backlight/corgi_lcd.c index e323fcbe884e..aa782f302983 100644 --- a/drivers/video/backlight/corgi_lcd.c +++ b/drivers/video/backlight/corgi_lcd.c @@ -337,7 +337,7 @@ static void corgi_lcd_power_off(struct corgi_lcd *lcd) static int corgi_lcd_set_mode(struct lcd_device *ld, struct fb_videomode *m) { - struct corgi_lcd *lcd = dev_get_drvdata(&ld->dev); + struct corgi_lcd *lcd = lcd_get_data(ld); int mode = CORGI_LCD_MODE_QVGA; if (m->xres == 640 || m->xres == 480) @@ -364,7 +364,7 @@ static int corgi_lcd_set_mode(struct lcd_device *ld, struct fb_videomode *m) static int corgi_lcd_set_power(struct lcd_device *ld, int power) { - struct corgi_lcd *lcd = dev_get_drvdata(&ld->dev); + struct corgi_lcd *lcd = lcd_get_data(ld); if (POWER_IS_ON(power) && !POWER_IS_ON(lcd->power)) corgi_lcd_power_on(lcd); @@ -378,7 +378,7 @@ static int corgi_lcd_set_power(struct lcd_device *ld, int power) static int corgi_lcd_get_power(struct lcd_device *ld) { - struct corgi_lcd *lcd = dev_get_drvdata(&ld->dev); + struct corgi_lcd *lcd = lcd_get_data(ld); return lcd->power; } @@ -391,7 +391,7 @@ static struct lcd_ops corgi_lcd_ops = { static int corgi_bl_get_intensity(struct backlight_device *bd) { - struct corgi_lcd *lcd = dev_get_drvdata(&bd->dev); + struct corgi_lcd *lcd = bl_get_data(bd); return lcd->intensity; } @@ -423,7 +423,7 @@ static int corgi_bl_set_intensity(struct corgi_lcd *lcd, int intensity) static int corgi_bl_update_status(struct backlight_device *bd) { - struct corgi_lcd *lcd = dev_get_drvdata(&bd->dev); + struct corgi_lcd *lcd = bl_get_data(bd); int intensity = bd->props.brightness; if (bd->props.power != FB_BLANK_UNBLANK) @@ -460,7 +460,7 @@ static const struct backlight_ops corgi_bl_ops = { #ifdef CONFIG_PM static int corgi_lcd_suspend(struct spi_device *spi, pm_message_t state) { - struct corgi_lcd *lcd = dev_get_drvdata(&spi->dev); + struct corgi_lcd *lcd = spi_get_drvdata(spi); corgibl_flags |= CORGIBL_SUSPENDED; corgi_bl_set_intensity(lcd, 0); @@ -470,7 +470,7 @@ static int corgi_lcd_suspend(struct spi_device *spi, pm_message_t state) static int corgi_lcd_resume(struct spi_device *spi) { - struct corgi_lcd *lcd = dev_get_drvdata(&spi->dev); + struct corgi_lcd *lcd = spi_get_drvdata(spi); corgibl_flags &= ~CORGIBL_SUSPENDED; corgi_lcd_set_power(lcd->lcd_dev, FB_BLANK_UNBLANK); @@ -577,7 +577,7 @@ static int corgi_lcd_probe(struct spi_device *spi) lcd->kick_battery = pdata->kick_battery; - dev_set_drvdata(&spi->dev, lcd); + spi_set_drvdata(spi, lcd); corgi_lcd_set_power(lcd->lcd_dev, FB_BLANK_UNBLANK); backlight_update_status(lcd->bl_dev); @@ -594,7 +594,7 @@ err_unregister_lcd: static int corgi_lcd_remove(struct spi_device *spi) { - struct corgi_lcd *lcd = dev_get_drvdata(&spi->dev); + struct corgi_lcd *lcd = spi_get_drvdata(spi); lcd->bl_dev->props.power = FB_BLANK_UNBLANK; lcd->bl_dev->props.brightness = 0; diff --git a/drivers/video/backlight/hx8357.c b/drivers/video/backlight/hx8357.c new file mode 100644 index 000000000000..00925c0a79b9 --- /dev/null +++ b/drivers/video/backlight/hx8357.c @@ -0,0 +1,482 @@ +/* + * Driver for the Himax HX-8357 LCD Controller + * + * Copyright 2012 Free Electrons + * + * Licensed under the GPLv2 or later. + */ + +#include <linux/delay.h> +#include <linux/lcd.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/of_gpio.h> +#include <linux/spi/spi.h> + +#define HX8357_NUM_IM_PINS 3 + +#define HX8357_SWRESET 0x01 +#define HX8357_GET_RED_CHANNEL 0x06 +#define HX8357_GET_GREEN_CHANNEL 0x07 +#define HX8357_GET_BLUE_CHANNEL 0x08 +#define HX8357_GET_POWER_MODE 0x0a +#define HX8357_GET_MADCTL 0x0b +#define HX8357_GET_PIXEL_FORMAT 0x0c +#define HX8357_GET_DISPLAY_MODE 0x0d +#define HX8357_GET_SIGNAL_MODE 0x0e +#define HX8357_GET_DIAGNOSTIC_RESULT 0x0f +#define HX8357_ENTER_SLEEP_MODE 0x10 +#define HX8357_EXIT_SLEEP_MODE 0x11 +#define HX8357_ENTER_PARTIAL_MODE 0x12 +#define HX8357_ENTER_NORMAL_MODE 0x13 +#define HX8357_EXIT_INVERSION_MODE 0x20 +#define HX8357_ENTER_INVERSION_MODE 0x21 +#define HX8357_SET_DISPLAY_OFF 0x28 +#define HX8357_SET_DISPLAY_ON 0x29 +#define HX8357_SET_COLUMN_ADDRESS 0x2a +#define HX8357_SET_PAGE_ADDRESS 0x2b +#define HX8357_WRITE_MEMORY_START 0x2c +#define HX8357_READ_MEMORY_START 0x2e +#define HX8357_SET_PARTIAL_AREA 0x30 +#define HX8357_SET_SCROLL_AREA 0x33 +#define HX8357_SET_TEAR_OFF 0x34 +#define HX8357_SET_TEAR_ON 0x35 +#define HX8357_SET_ADDRESS_MODE 0x36 +#define HX8357_SET_SCROLL_START 0x37 +#define HX8357_EXIT_IDLE_MODE 0x38 +#define HX8357_ENTER_IDLE_MODE 0x39 +#define HX8357_SET_PIXEL_FORMAT 0x3a +#define HX8357_SET_PIXEL_FORMAT_DBI_3BIT (0x1) +#define HX8357_SET_PIXEL_FORMAT_DBI_16BIT (0x5) +#define HX8357_SET_PIXEL_FORMAT_DBI_18BIT (0x6) +#define HX8357_SET_PIXEL_FORMAT_DPI_3BIT (0x1 << 4) +#define HX8357_SET_PIXEL_FORMAT_DPI_16BIT (0x5 << 4) +#define HX8357_SET_PIXEL_FORMAT_DPI_18BIT (0x6 << 4) +#define HX8357_WRITE_MEMORY_CONTINUE 0x3c +#define HX8357_READ_MEMORY_CONTINUE 0x3e +#define HX8357_SET_TEAR_SCAN_LINES 0x44 +#define HX8357_GET_SCAN_LINES 0x45 +#define HX8357_READ_DDB_START 0xa1 +#define HX8357_SET_DISPLAY_MODE 0xb4 +#define HX8357_SET_DISPLAY_MODE_RGB_THROUGH (0x3) +#define HX8357_SET_DISPLAY_MODE_RGB_INTERFACE (1 << 4) +#define HX8357_SET_PANEL_DRIVING 0xc0 +#define HX8357_SET_DISPLAY_FRAME 0xc5 +#define HX8357_SET_RGB 0xc6 +#define HX8357_SET_RGB_ENABLE_HIGH (1 << 1) +#define HX8357_SET_GAMMA 0xc8 +#define HX8357_SET_POWER 0xd0 +#define HX8357_SET_VCOM 0xd1 +#define HX8357_SET_POWER_NORMAL 0xd2 +#define HX8357_SET_PANEL_RELATED 0xe9 + +struct hx8357_data { + unsigned im_pins[HX8357_NUM_IM_PINS]; + unsigned reset; + struct spi_device *spi; + int state; +}; + +static int hx8357_spi_write_then_read(struct lcd_device *lcdev, + void *txbuf, u16 txlen, + void *rxbuf, u16 rxlen) +{ + struct hx8357_data *lcd = lcd_get_data(lcdev); + struct spi_message msg; + struct spi_transfer xfer[2]; + u16 *local_txbuf = NULL; + int ret = 0; + + memset(xfer, 0, sizeof(xfer)); + spi_message_init(&msg); + + if (txlen) { + int i; + + local_txbuf = kcalloc(sizeof(*local_txbuf), txlen, GFP_KERNEL); + + if (!local_txbuf) { + dev_err(&lcdev->dev, "Couldn't allocate data buffer.\n"); + return -ENOMEM; + } + + for (i = 0; i < txlen; i++) { + local_txbuf[i] = ((u8 *)txbuf)[i]; + if (i > 0) + local_txbuf[i] |= 1 << 8; + } + + xfer[0].len = 2 * txlen; + xfer[0].bits_per_word = 9; + xfer[0].tx_buf = local_txbuf; + spi_message_add_tail(&xfer[0], &msg); + } + + if (rxlen) { + xfer[1].len = rxlen; + xfer[1].bits_per_word = 8; + xfer[1].rx_buf = rxbuf; + spi_message_add_tail(&xfer[1], &msg); + } + + ret = spi_sync(lcd->spi, &msg); + if (ret < 0) + dev_err(&lcdev->dev, "Couldn't send SPI data.\n"); + + if (txlen) + kfree(local_txbuf); + + return ret; +} + +static inline int hx8357_spi_write_array(struct lcd_device *lcdev, + u8 *value, u8 len) +{ + return hx8357_spi_write_then_read(lcdev, value, len, NULL, 0); +} + +static inline int hx8357_spi_write_byte(struct lcd_device *lcdev, + u8 value) +{ + return hx8357_spi_write_then_read(lcdev, &value, 1, NULL, 0); +} + +static int hx8357_enter_standby(struct lcd_device *lcdev) +{ + int ret; + + ret = hx8357_spi_write_byte(lcdev, HX8357_SET_DISPLAY_OFF); + if (ret < 0) + return ret; + + usleep_range(10000, 12000); + + ret = hx8357_spi_write_byte(lcdev, HX8357_ENTER_SLEEP_MODE); + if (ret < 0) + return ret; + + msleep(120); + + return 0; +} + +static int hx8357_exit_standby(struct lcd_device *lcdev) +{ + int ret; + + ret = hx8357_spi_write_byte(lcdev, HX8357_EXIT_SLEEP_MODE); + if (ret < 0) + return ret; + + msleep(120); + + ret = hx8357_spi_write_byte(lcdev, HX8357_SET_DISPLAY_ON); + if (ret < 0) + return ret; + + return 0; +} + +static int hx8357_lcd_init(struct lcd_device *lcdev) +{ + struct hx8357_data *lcd = lcd_get_data(lcdev); + u8 buf[16]; + int ret; + + /* + * Set the interface selection pins to SPI mode, with three + * wires + */ + gpio_set_value_cansleep(lcd->im_pins[0], 1); + gpio_set_value_cansleep(lcd->im_pins[1], 0); + gpio_set_value_cansleep(lcd->im_pins[2], 1); + + /* Reset the screen */ + gpio_set_value(lcd->reset, 1); + usleep_range(10000, 12000); + gpio_set_value(lcd->reset, 0); + usleep_range(10000, 12000); + gpio_set_value(lcd->reset, 1); + msleep(120); + + buf[0] = HX8357_SET_POWER; + buf[1] = 0x44; + buf[2] = 0x41; + buf[3] = 0x06; + ret = hx8357_spi_write_array(lcdev, buf, 4); + if (ret < 0) + return ret; + + buf[0] = HX8357_SET_VCOM; + buf[1] = 0x40; + buf[2] = 0x10; + ret = hx8357_spi_write_array(lcdev, buf, 3); + if (ret < 0) + return ret; + + buf[0] = HX8357_SET_POWER_NORMAL; + buf[1] = 0x05; + buf[2] = 0x12; + ret = hx8357_spi_write_array(lcdev, buf, 3); + if (ret < 0) + return ret; + + buf[0] = HX8357_SET_PANEL_DRIVING; + buf[1] = 0x14; + buf[2] = 0x3b; + buf[3] = 0x00; + buf[4] = 0x02; + buf[5] = 0x11; + ret = hx8357_spi_write_array(lcdev, buf, 6); + if (ret < 0) + return ret; + + buf[0] = HX8357_SET_DISPLAY_FRAME; + buf[1] = 0x0c; + ret = hx8357_spi_write_array(lcdev, buf, 2); + if (ret < 0) + return ret; + + buf[0] = HX8357_SET_PANEL_RELATED; + buf[1] = 0x01; + ret = hx8357_spi_write_array(lcdev, buf, 2); + if (ret < 0) + return ret; + + buf[0] = 0xea; + buf[1] = 0x03; + buf[2] = 0x00; + buf[3] = 0x00; + ret = hx8357_spi_write_array(lcdev, buf, 4); + if (ret < 0) + return ret; + + buf[0] = 0xeb; + buf[1] = 0x40; + buf[2] = 0x54; + buf[3] = 0x26; + buf[4] = 0xdb; + ret = hx8357_spi_write_array(lcdev, buf, 5); + if (ret < 0) + return ret; + + buf[0] = HX8357_SET_GAMMA; + buf[1] = 0x00; + buf[2] = 0x15; + buf[3] = 0x00; + buf[4] = 0x22; + buf[5] = 0x00; + buf[6] = 0x08; + buf[7] = 0x77; + buf[8] = 0x26; + buf[9] = 0x77; + buf[10] = 0x22; + buf[11] = 0x04; + buf[12] = 0x00; + ret = hx8357_spi_write_array(lcdev, buf, 13); + if (ret < 0) + return ret; + + buf[0] = HX8357_SET_ADDRESS_MODE; + buf[1] = 0xc0; + ret = hx8357_spi_write_array(lcdev, buf, 2); + if (ret < 0) + return ret; + + buf[0] = HX8357_SET_PIXEL_FORMAT; + buf[1] = HX8357_SET_PIXEL_FORMAT_DPI_18BIT | + HX8357_SET_PIXEL_FORMAT_DBI_18BIT; + ret = hx8357_spi_write_array(lcdev, buf, 2); + if (ret < 0) + return ret; + + buf[0] = HX8357_SET_COLUMN_ADDRESS; + buf[1] = 0x00; + buf[2] = 0x00; + buf[3] = 0x01; + buf[4] = 0x3f; + ret = hx8357_spi_write_array(lcdev, buf, 5); + if (ret < 0) + return ret; + + buf[0] = HX8357_SET_PAGE_ADDRESS; + buf[1] = 0x00; + buf[2] = 0x00; + buf[3] = 0x01; + buf[4] = 0xdf; + ret = hx8357_spi_write_array(lcdev, buf, 5); + if (ret < 0) + return ret; + + buf[0] = HX8357_SET_RGB; + buf[1] = 0x02; + ret = hx8357_spi_write_array(lcdev, buf, 2); + if (ret < 0) + return ret; + + buf[0] = HX8357_SET_DISPLAY_MODE; + buf[1] = HX8357_SET_DISPLAY_MODE_RGB_THROUGH | + HX8357_SET_DISPLAY_MODE_RGB_INTERFACE; + ret = hx8357_spi_write_array(lcdev, buf, 2); + if (ret < 0) + return ret; + + ret = hx8357_spi_write_byte(lcdev, HX8357_EXIT_SLEEP_MODE); + if (ret < 0) + return ret; + + msleep(120); + + ret = hx8357_spi_write_byte(lcdev, HX8357_SET_DISPLAY_ON); + if (ret < 0) + return ret; + + usleep_range(5000, 7000); + + ret = hx8357_spi_write_byte(lcdev, HX8357_WRITE_MEMORY_START); + if (ret < 0) + return ret; + + return 0; +} + +#define POWER_IS_ON(pwr) ((pwr) <= FB_BLANK_NORMAL) + +static int hx8357_set_power(struct lcd_device *lcdev, int power) +{ + struct hx8357_data *lcd = lcd_get_data(lcdev); + int ret = 0; + + if (POWER_IS_ON(power) && !POWER_IS_ON(lcd->state)) + ret = hx8357_exit_standby(lcdev); + else if (!POWER_IS_ON(power) && POWER_IS_ON(lcd->state)) + ret = hx8357_enter_standby(lcdev); + + if (ret == 0) + lcd->state = power; + else + dev_warn(&lcdev->dev, "failed to set power mode %d\n", power); + + return ret; +} + +static int hx8357_get_power(struct lcd_device *lcdev) +{ + struct hx8357_data *lcd = lcd_get_data(lcdev); + + return lcd->state; +} + +static struct lcd_ops hx8357_ops = { + .set_power = hx8357_set_power, + .get_power = hx8357_get_power, +}; + +static int hx8357_probe(struct spi_device *spi) +{ + struct lcd_device *lcdev; + struct hx8357_data *lcd; + int i, ret; + + lcd = devm_kzalloc(&spi->dev, sizeof(*lcd), GFP_KERNEL); + if (!lcd) { + dev_err(&spi->dev, "Couldn't allocate lcd internal structure!\n"); + return -ENOMEM; + } + + ret = spi_setup(spi); + if (ret < 0) { + dev_err(&spi->dev, "SPI setup failed.\n"); + return ret; + } + + lcd->spi = spi; + + lcd->reset = of_get_named_gpio(spi->dev.of_node, "gpios-reset", 0); + if (!gpio_is_valid(lcd->reset)) { + dev_err(&spi->dev, "Missing dt property: gpios-reset\n"); + return -EINVAL; + } + + ret = devm_gpio_request_one(&spi->dev, lcd->reset, + GPIOF_OUT_INIT_HIGH, + "hx8357-reset"); + if (ret) { + dev_err(&spi->dev, + "failed to request gpio %d: %d\n", + lcd->reset, ret); + return -EINVAL; + } + + for (i = 0; i < HX8357_NUM_IM_PINS; i++) { + lcd->im_pins[i] = of_get_named_gpio(spi->dev.of_node, + "im-gpios", i); + if (lcd->im_pins[i] == -EPROBE_DEFER) { + dev_info(&spi->dev, "GPIO requested is not here yet, deferring the probe\n"); + return -EPROBE_DEFER; + } + if (!gpio_is_valid(lcd->im_pins[i])) { + dev_err(&spi->dev, "Missing dt property: im-gpios\n"); + return -EINVAL; + } + + ret = devm_gpio_request_one(&spi->dev, lcd->im_pins[i], + GPIOF_OUT_INIT_LOW, "im_pins"); + if (ret) { + dev_err(&spi->dev, "failed to request gpio %d: %d\n", + lcd->im_pins[i], ret); + return -EINVAL; + } + } + + lcdev = lcd_device_register("mxsfb", &spi->dev, lcd, &hx8357_ops); + if (IS_ERR(lcdev)) { + ret = PTR_ERR(lcdev); + return ret; + } + spi_set_drvdata(spi, lcdev); + + ret = hx8357_lcd_init(lcdev); + if (ret) { + dev_err(&spi->dev, "Couldn't initialize panel\n"); + goto init_error; + } + + dev_info(&spi->dev, "Panel probed\n"); + + return 0; + +init_error: + lcd_device_unregister(lcdev); + return ret; +} + +static int hx8357_remove(struct spi_device *spi) +{ + struct lcd_device *lcdev = spi_get_drvdata(spi); + + lcd_device_unregister(lcdev); + return 0; +} + +static const struct of_device_id hx8357_dt_ids[] = { + { .compatible = "himax,hx8357" }, + {}, +}; +MODULE_DEVICE_TABLE(of, hx8357_dt_ids); + +static struct spi_driver hx8357_driver = { + .probe = hx8357_probe, + .remove = hx8357_remove, + .driver = { + .name = "hx8357", + .of_match_table = of_match_ptr(hx8357_dt_ids), + }, +}; + +module_spi_driver(hx8357_driver); + +MODULE_AUTHOR("Maxime Ripard <maxime.ripard@free-electrons.com>"); +MODULE_DESCRIPTION("Himax HX-8357 LCD Driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/video/backlight/l4f00242t03.c b/drivers/video/backlight/l4f00242t03.c index 9a35196d12d7..fb6155771326 100644 --- a/drivers/video/backlight/l4f00242t03.c +++ b/drivers/video/backlight/l4f00242t03.c @@ -49,7 +49,7 @@ static void l4f00242t03_reset(unsigned int gpio) static void l4f00242t03_lcd_init(struct spi_device *spi) { struct l4f00242t03_pdata *pdata = spi->dev.platform_data; - struct l4f00242t03_priv *priv = dev_get_drvdata(&spi->dev); + struct l4f00242t03_priv *priv = spi_get_drvdata(spi); const u16 cmd[] = { 0x36, param(0), 0x3A, param(0x60) }; dev_dbg(&spi->dev, "initializing LCD\n"); @@ -70,7 +70,7 @@ static void l4f00242t03_lcd_init(struct spi_device *spi) static void l4f00242t03_lcd_powerdown(struct spi_device *spi) { struct l4f00242t03_pdata *pdata = spi->dev.platform_data; - struct l4f00242t03_priv *priv = dev_get_drvdata(&spi->dev); + struct l4f00242t03_priv *priv = spi_get_drvdata(spi); dev_dbg(&spi->dev, "Powering down LCD\n"); @@ -168,7 +168,7 @@ static int l4f00242t03_probe(struct spi_device *spi) return -ENOMEM; } - dev_set_drvdata(&spi->dev, priv); + spi_set_drvdata(spi, priv); spi->bits_per_word = 9; spi_setup(spi); @@ -190,27 +190,24 @@ static int l4f00242t03_probe(struct spi_device *spi) return ret; } - priv->io_reg = regulator_get(&spi->dev, "vdd"); + priv->io_reg = devm_regulator_get(&spi->dev, "vdd"); if (IS_ERR(priv->io_reg)) { dev_err(&spi->dev, "%s: Unable to get the IO regulator\n", __func__); return PTR_ERR(priv->io_reg); } - priv->core_reg = regulator_get(&spi->dev, "vcore"); + priv->core_reg = devm_regulator_get(&spi->dev, "vcore"); if (IS_ERR(priv->core_reg)) { - ret = PTR_ERR(priv->core_reg); dev_err(&spi->dev, "%s: Unable to get the core regulator\n", __func__); - goto err1; + return PTR_ERR(priv->core_reg); } priv->ld = lcd_device_register("l4f00242t03", &spi->dev, priv, &l4f_ops); - if (IS_ERR(priv->ld)) { - ret = PTR_ERR(priv->ld); - goto err2; - } + if (IS_ERR(priv->ld)) + return PTR_ERR(priv->ld); /* Init the LCD */ l4f00242t03_lcd_init(spi); @@ -220,33 +217,22 @@ static int l4f00242t03_probe(struct spi_device *spi) dev_info(&spi->dev, "Epson l4f00242t03 lcd probed.\n"); return 0; - -err2: - regulator_put(priv->core_reg); -err1: - regulator_put(priv->io_reg); - - return ret; } static int l4f00242t03_remove(struct spi_device *spi) { - struct l4f00242t03_priv *priv = dev_get_drvdata(&spi->dev); + struct l4f00242t03_priv *priv = spi_get_drvdata(spi); l4f00242t03_lcd_power_set(priv->ld, FB_BLANK_POWERDOWN); lcd_device_unregister(priv->ld); - - dev_set_drvdata(&spi->dev, NULL); - - regulator_put(priv->io_reg); - regulator_put(priv->core_reg); + spi_set_drvdata(spi, NULL); return 0; } static void l4f00242t03_shutdown(struct spi_device *spi) { - struct l4f00242t03_priv *priv = dev_get_drvdata(&spi->dev); + struct l4f00242t03_priv *priv = spi_get_drvdata(spi); if (priv) l4f00242t03_lcd_power_set(priv->ld, FB_BLANK_POWERDOWN); diff --git a/drivers/video/backlight/ld9040.c b/drivers/video/backlight/ld9040.c index 1cb352418513..1b642f5f381a 100644 --- a/drivers/video/backlight/ld9040.c +++ b/drivers/video/backlight/ld9040.c @@ -9,29 +9,20 @@ * under the terms of the GNU General Public License as published by the * Free Software Foundation; either version 2 of the License, or (at your * option) any later version. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */ -#include <linux/wait.h> -#include <linux/fb.h> +#include <linux/backlight.h> #include <linux/delay.h> +#include <linux/fb.h> #include <linux/gpio.h> -#include <linux/spi/spi.h> -#include <linux/irq.h> #include <linux/interrupt.h> +#include <linux/irq.h> #include <linux/kernel.h> #include <linux/lcd.h> -#include <linux/backlight.h> #include <linux/module.h> #include <linux/regulator/consumer.h> +#include <linux/spi/spi.h> +#include <linux/wait.h> #include "ld9040_gamma.h" @@ -43,7 +34,6 @@ #define MIN_BRIGHTNESS 0 #define MAX_BRIGHTNESS 24 -#define power_is_on(pwr) ((pwr) <= FB_BLANK_NORMAL) struct ld9040 { struct device *dev; @@ -78,7 +68,7 @@ static void ld9040_regulator_enable(struct ld9040 *lcd) lcd->enabled = true; } - mdelay(pd->power_on_delay); + msleep(pd->power_on_delay); out: mutex_unlock(&lcd->lock); } @@ -474,8 +464,9 @@ static int ld9040_panel_send_sequence(struct ld9040 *lcd, ret = ld9040_spi_write(lcd, wbuf[i], wbuf[i+1]); if (ret) break; - } else - udelay(wbuf[i+1]*1000); + } else { + msleep(wbuf[i+1]); + } i += 2; } @@ -513,14 +504,9 @@ gamma_err: static int ld9040_gamma_ctl(struct ld9040 *lcd, int gamma) { - int ret = 0; - - ret = _ld9040_gamma_ctl(lcd, gamma_table.gamma_22_table[gamma]); - - return ret; + return _ld9040_gamma_ctl(lcd, gamma_table.gamma_22_table[gamma]); } - static int ld9040_ldi_init(struct ld9040 *lcd) { int ret, i; @@ -539,7 +525,7 @@ static int ld9040_ldi_init(struct ld9040 *lcd) for (i = 0; i < ARRAY_SIZE(init_seq); i++) { ret = ld9040_panel_send_sequence(lcd, init_seq[i]); /* workaround: minimum delay time for transferring CMD */ - udelay(300); + usleep_range(300, 310); if (ret) break; } @@ -549,11 +535,7 @@ static int ld9040_ldi_init(struct ld9040 *lcd) static int ld9040_ldi_enable(struct ld9040 *lcd) { - int ret = 0; - - ret = ld9040_panel_send_sequence(lcd, seq_display_on); - - return ret; + return ld9040_panel_send_sequence(lcd, seq_display_on); } static int ld9040_ldi_disable(struct ld9040 *lcd) @@ -566,25 +548,27 @@ static int ld9040_ldi_disable(struct ld9040 *lcd) return ret; } +static int ld9040_power_is_on(int power) +{ + return power <= FB_BLANK_NORMAL; +} + static int ld9040_power_on(struct ld9040 *lcd) { int ret = 0; - struct lcd_platform_data *pd = NULL; + struct lcd_platform_data *pd; + pd = lcd->lcd_pd; - if (!pd) { - dev_err(lcd->dev, "platform data is NULL.\n"); - return -EFAULT; - } /* lcd power on */ ld9040_regulator_enable(lcd); if (!pd->reset) { dev_err(lcd->dev, "reset is NULL.\n"); - return -EFAULT; + return -EINVAL; } else { pd->reset(lcd->ld); - mdelay(pd->reset_delay); + msleep(pd->reset_delay); } ret = ld9040_ldi_init(lcd); @@ -604,14 +588,10 @@ static int ld9040_power_on(struct ld9040 *lcd) static int ld9040_power_off(struct ld9040 *lcd) { - int ret = 0; - struct lcd_platform_data *pd = NULL; + int ret; + struct lcd_platform_data *pd; pd = lcd->lcd_pd; - if (!pd) { - dev_err(lcd->dev, "platform data is NULL.\n"); - return -EFAULT; - } ret = ld9040_ldi_disable(lcd); if (ret) { @@ -619,7 +599,7 @@ static int ld9040_power_off(struct ld9040 *lcd) return -EIO; } - mdelay(pd->power_off_delay); + msleep(pd->power_off_delay); /* lcd power off */ ld9040_regulator_disable(lcd); @@ -631,9 +611,9 @@ static int ld9040_power(struct ld9040 *lcd, int power) { int ret = 0; - if (power_is_on(power) && !power_is_on(lcd->power)) + if (ld9040_power_is_on(power) && !ld9040_power_is_on(lcd->power)) ret = ld9040_power_on(lcd); - else if (!power_is_on(power) && power_is_on(lcd->power)) + else if (!ld9040_power_is_on(power) && ld9040_power_is_on(lcd->power)) ret = ld9040_power_off(lcd); if (!ret) @@ -698,7 +678,6 @@ static const struct backlight_ops ld9040_backlight_ops = { .update_status = ld9040_set_brightness, }; - static int ld9040_probe(struct spi_device *spi) { int ret = 0; @@ -726,22 +705,20 @@ static int ld9040_probe(struct spi_device *spi) lcd->lcd_pd = spi->dev.platform_data; if (!lcd->lcd_pd) { dev_err(&spi->dev, "platform data is NULL.\n"); - return -EFAULT; + return -EINVAL; } mutex_init(&lcd->lock); - ret = regulator_bulk_get(lcd->dev, ARRAY_SIZE(supplies), supplies); + ret = devm_regulator_bulk_get(lcd->dev, ARRAY_SIZE(supplies), supplies); if (ret) { dev_err(lcd->dev, "Failed to get regulators: %d\n", ret); return ret; } ld = lcd_device_register("ld9040", &spi->dev, lcd, &ld9040_lcd_ops); - if (IS_ERR(ld)) { - ret = PTR_ERR(ld); - goto out_free_regulator; - } + if (IS_ERR(ld)) + return PTR_ERR(ld); lcd->ld = ld; @@ -772,30 +749,28 @@ static int ld9040_probe(struct spi_device *spi) lcd->power = FB_BLANK_POWERDOWN; ld9040_power(lcd, FB_BLANK_UNBLANK); - } else + } else { lcd->power = FB_BLANK_UNBLANK; + } - dev_set_drvdata(&spi->dev, lcd); + spi_set_drvdata(spi, lcd); dev_info(&spi->dev, "ld9040 panel driver has been probed.\n"); return 0; out_unregister_lcd: lcd_device_unregister(lcd->ld); -out_free_regulator: - regulator_bulk_free(ARRAY_SIZE(supplies), supplies); return ret; } static int ld9040_remove(struct spi_device *spi) { - struct ld9040 *lcd = dev_get_drvdata(&spi->dev); + struct ld9040 *lcd = spi_get_drvdata(spi); ld9040_power(lcd, FB_BLANK_POWERDOWN); backlight_device_unregister(lcd->bd); lcd_device_unregister(lcd->ld); - regulator_bulk_free(ARRAY_SIZE(supplies), supplies); return 0; } @@ -803,8 +778,7 @@ static int ld9040_remove(struct spi_device *spi) #if defined(CONFIG_PM) static int ld9040_suspend(struct spi_device *spi, pm_message_t mesg) { - int ret = 0; - struct ld9040 *lcd = dev_get_drvdata(&spi->dev); + struct ld9040 *lcd = spi_get_drvdata(spi); dev_dbg(&spi->dev, "lcd->power = %d\n", lcd->power); @@ -812,21 +786,16 @@ static int ld9040_suspend(struct spi_device *spi, pm_message_t mesg) * when lcd panel is suspend, lcd panel becomes off * regardless of status. */ - ret = ld9040_power(lcd, FB_BLANK_POWERDOWN); - - return ret; + return ld9040_power(lcd, FB_BLANK_POWERDOWN); } static int ld9040_resume(struct spi_device *spi) { - int ret = 0; - struct ld9040 *lcd = dev_get_drvdata(&spi->dev); + struct ld9040 *lcd = spi_get_drvdata(spi); lcd->power = FB_BLANK_POWERDOWN; - ret = ld9040_power(lcd, FB_BLANK_UNBLANK); - - return ret; + return ld9040_power(lcd, FB_BLANK_UNBLANK); } #else #define ld9040_suspend NULL @@ -836,7 +805,7 @@ static int ld9040_resume(struct spi_device *spi) /* Power down all displays on reboot, poweroff or halt. */ static void ld9040_shutdown(struct spi_device *spi) { - struct ld9040 *lcd = dev_get_drvdata(&spi->dev); + struct ld9040 *lcd = spi_get_drvdata(spi); ld9040_power(lcd, FB_BLANK_POWERDOWN); } diff --git a/drivers/video/backlight/lm3630_bl.c b/drivers/video/backlight/lm3630_bl.c index a6d637b5c68f..76a62e978fc3 100644 --- a/drivers/video/backlight/lm3630_bl.c +++ b/drivers/video/backlight/lm3630_bl.c @@ -320,7 +320,7 @@ static int lm3630_backlight_register(struct lm3630_chip_data *pchip, backlight_device_register(name, pchip->dev, pchip, &lm3630_bank_a_ops, &props); if (IS_ERR(pchip->bled1)) - return -EIO; + return PTR_ERR(pchip->bled1); break; case BLED_2: props.brightness = pdata->init_brt_led2; @@ -329,7 +329,7 @@ static int lm3630_backlight_register(struct lm3630_chip_data *pchip, backlight_device_register(name, pchip->dev, pchip, &lm3630_bank_b_ops, &props); if (IS_ERR(pchip->bled2)) - return -EIO; + return PTR_ERR(pchip->bled2); break; } return 0; diff --git a/drivers/video/backlight/lm3639_bl.c b/drivers/video/backlight/lm3639_bl.c index 7ab2d2a04e41..053964da8dd3 100644 --- a/drivers/video/backlight/lm3639_bl.c +++ b/drivers/video/backlight/lm3639_bl.c @@ -350,14 +350,13 @@ static int lm3639_probe(struct i2c_client *client, &lm3639_bled_ops, &props); if (IS_ERR(pchip->bled)) { dev_err(&client->dev, "fail : backlight register\n"); - ret = -EIO; + ret = PTR_ERR(pchip->bled); goto err_out; } ret = device_create_file(&(pchip->bled->dev), &dev_attr_bled_mode); if (ret < 0) { dev_err(&client->dev, "failed : add sysfs entries\n"); - ret = -EIO; goto err_bled_mode; } @@ -369,7 +368,6 @@ static int lm3639_probe(struct i2c_client *client, &client->dev, &pchip->cdev_flash); if (ret < 0) { dev_err(&client->dev, "fail : flash register\n"); - ret = -EIO; goto err_flash; } @@ -381,7 +379,6 @@ static int lm3639_probe(struct i2c_client *client, &client->dev, &pchip->cdev_torch); if (ret < 0) { dev_err(&client->dev, "fail : torch register\n"); - ret = -EIO; goto err_torch; } diff --git a/drivers/video/backlight/lms283gf05.c b/drivers/video/backlight/lms283gf05.c index 55819b384701..4eec47261cd3 100644 --- a/drivers/video/backlight/lms283gf05.c +++ b/drivers/video/backlight/lms283gf05.c @@ -180,7 +180,7 @@ static int lms283gf05_probe(struct spi_device *spi) st->spi = spi; st->ld = ld; - dev_set_drvdata(&spi->dev, st); + spi_set_drvdata(spi, st); /* kick in the LCD */ if (pdata) @@ -192,7 +192,7 @@ static int lms283gf05_probe(struct spi_device *spi) static int lms283gf05_remove(struct spi_device *spi) { - struct lms283gf05_state *st = dev_get_drvdata(&spi->dev); + struct lms283gf05_state *st = spi_get_drvdata(spi); lcd_device_unregister(st->ld); diff --git a/drivers/video/backlight/lms501kf03.c b/drivers/video/backlight/lms501kf03.c new file mode 100644 index 000000000000..b43882abefaf --- /dev/null +++ b/drivers/video/backlight/lms501kf03.c @@ -0,0 +1,441 @@ +/* + * lms501kf03 TFT LCD panel driver. + * + * Copyright (c) 2012 Samsung Electronics Co., Ltd. + * Author: Jingoo Han <jg1.han@samsung.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include <linux/backlight.h> +#include <linux/delay.h> +#include <linux/fb.h> +#include <linux/gpio.h> +#include <linux/lcd.h> +#include <linux/module.h> +#include <linux/spi/spi.h> +#include <linux/wait.h> + +#define COMMAND_ONLY 0x00 +#define DATA_ONLY 0x01 + +struct lms501kf03 { + struct device *dev; + struct spi_device *spi; + unsigned int power; + struct lcd_device *ld; + struct lcd_platform_data *lcd_pd; +}; + +static const unsigned char seq_password[] = { + 0xb9, 0xff, 0x83, 0x69, +}; + +static const unsigned char seq_power[] = { + 0xb1, 0x01, 0x00, 0x34, 0x06, 0x00, 0x14, 0x14, 0x20, 0x28, + 0x12, 0x12, 0x17, 0x0a, 0x01, 0xe6, 0xe6, 0xe6, 0xe6, 0xe6, +}; + +static const unsigned char seq_display[] = { + 0xb2, 0x00, 0x2b, 0x03, 0x03, 0x70, 0x00, 0xff, 0x00, 0x00, + 0x00, 0x00, 0x03, 0x03, 0x00, 0x01, +}; + +static const unsigned char seq_rgb_if[] = { + 0xb3, 0x09, +}; + +static const unsigned char seq_display_inv[] = { + 0xb4, 0x01, 0x08, 0x77, 0x0e, 0x06, +}; + +static const unsigned char seq_vcom[] = { + 0xb6, 0x4c, 0x2e, +}; + +static const unsigned char seq_gate[] = { + 0xd5, 0x00, 0x05, 0x03, 0x29, 0x01, 0x07, 0x17, 0x68, 0x13, + 0x37, 0x20, 0x31, 0x8a, 0x46, 0x9b, 0x57, 0x13, 0x02, 0x75, + 0xb9, 0x64, 0xa8, 0x07, 0x0f, 0x04, 0x07, +}; + +static const unsigned char seq_panel[] = { + 0xcc, 0x02, +}; + +static const unsigned char seq_col_mod[] = { + 0x3a, 0x77, +}; + +static const unsigned char seq_w_gamma[] = { + 0xe0, 0x00, 0x04, 0x09, 0x0f, 0x1f, 0x3f, 0x1f, 0x2f, 0x0a, + 0x0f, 0x10, 0x16, 0x18, 0x16, 0x17, 0x0d, 0x15, 0x00, 0x04, + 0x09, 0x0f, 0x38, 0x3f, 0x20, 0x39, 0x0a, 0x0f, 0x10, 0x16, + 0x18, 0x16, 0x17, 0x0d, 0x15, +}; + +static const unsigned char seq_rgb_gamma[] = { + 0xc1, 0x01, 0x03, 0x07, 0x0f, 0x1a, 0x22, 0x2c, 0x33, 0x3c, + 0x46, 0x4f, 0x58, 0x60, 0x69, 0x71, 0x79, 0x82, 0x89, 0x92, + 0x9a, 0xa1, 0xa9, 0xb1, 0xb9, 0xc1, 0xc9, 0xcf, 0xd6, 0xde, + 0xe5, 0xec, 0xf3, 0xf9, 0xff, 0xdd, 0x39, 0x07, 0x1c, 0xcb, + 0xab, 0x5f, 0x49, 0x80, 0x03, 0x07, 0x0f, 0x19, 0x20, 0x2a, + 0x31, 0x39, 0x42, 0x4b, 0x53, 0x5b, 0x63, 0x6b, 0x73, 0x7b, + 0x83, 0x8a, 0x92, 0x9b, 0xa2, 0xaa, 0xb2, 0xba, 0xc2, 0xca, + 0xd0, 0xd8, 0xe1, 0xe8, 0xf0, 0xf8, 0xff, 0xf7, 0xd8, 0xbe, + 0xa7, 0x39, 0x40, 0x85, 0x8c, 0xc0, 0x04, 0x07, 0x0c, 0x17, + 0x1c, 0x23, 0x2b, 0x34, 0x3b, 0x43, 0x4c, 0x54, 0x5b, 0x63, + 0x6a, 0x73, 0x7a, 0x82, 0x8a, 0x91, 0x98, 0xa1, 0xa8, 0xb0, + 0xb7, 0xc1, 0xc9, 0xcf, 0xd9, 0xe3, 0xea, 0xf4, 0xff, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +}; + +static const unsigned char seq_up_dn[] = { + 0x36, 0x10, +}; + +static const unsigned char seq_sleep_in[] = { + 0x10, +}; + +static const unsigned char seq_sleep_out[] = { + 0x11, +}; + +static const unsigned char seq_display_on[] = { + 0x29, +}; + +static const unsigned char seq_display_off[] = { + 0x10, +}; + +static int lms501kf03_spi_write_byte(struct lms501kf03 *lcd, int addr, int data) +{ + u16 buf[1]; + struct spi_message msg; + + struct spi_transfer xfer = { + .len = 2, + .tx_buf = buf, + }; + + buf[0] = (addr << 8) | data; + + spi_message_init(&msg); + spi_message_add_tail(&xfer, &msg); + + return spi_sync(lcd->spi, &msg); +} + +static int lms501kf03_spi_write(struct lms501kf03 *lcd, unsigned char address, + unsigned char command) +{ + return lms501kf03_spi_write_byte(lcd, address, command); +} + +static int lms501kf03_panel_send_sequence(struct lms501kf03 *lcd, + const unsigned char *wbuf, + unsigned int len) +{ + int ret = 0, i = 0; + + while (i < len) { + if (i == 0) + ret = lms501kf03_spi_write(lcd, COMMAND_ONLY, wbuf[i]); + else + ret = lms501kf03_spi_write(lcd, DATA_ONLY, wbuf[i]); + if (ret) + break; + i += 1; + } + + return ret; +} + +static int lms501kf03_ldi_init(struct lms501kf03 *lcd) +{ + int ret, i; + static const unsigned char *init_seq[] = { + seq_password, + seq_power, + seq_display, + seq_rgb_if, + seq_display_inv, + seq_vcom, + seq_gate, + seq_panel, + seq_col_mod, + seq_w_gamma, + seq_rgb_gamma, + seq_sleep_out, + }; + + static const unsigned int size_seq[] = { + ARRAY_SIZE(seq_password), + ARRAY_SIZE(seq_power), + ARRAY_SIZE(seq_display), + ARRAY_SIZE(seq_rgb_if), + ARRAY_SIZE(seq_display_inv), + ARRAY_SIZE(seq_vcom), + ARRAY_SIZE(seq_gate), + ARRAY_SIZE(seq_panel), + ARRAY_SIZE(seq_col_mod), + ARRAY_SIZE(seq_w_gamma), + ARRAY_SIZE(seq_rgb_gamma), + ARRAY_SIZE(seq_sleep_out), + }; + + for (i = 0; i < ARRAY_SIZE(init_seq); i++) { + ret = lms501kf03_panel_send_sequence(lcd, init_seq[i], + size_seq[i]); + if (ret) + break; + } + /* + * According to the datasheet, 120ms delay time is required. + * After sleep out sequence, command is blocked for 120ms. + * Thus, LDI should wait for 120ms. + */ + msleep(120); + + return ret; +} + +static int lms501kf03_ldi_enable(struct lms501kf03 *lcd) +{ + return lms501kf03_panel_send_sequence(lcd, seq_display_on, + ARRAY_SIZE(seq_display_on)); +} + +static int lms501kf03_ldi_disable(struct lms501kf03 *lcd) +{ + return lms501kf03_panel_send_sequence(lcd, seq_display_off, + ARRAY_SIZE(seq_display_off)); +} + +static int lms501kf03_power_is_on(int power) +{ + return (power) <= FB_BLANK_NORMAL; +} + +static int lms501kf03_power_on(struct lms501kf03 *lcd) +{ + int ret = 0; + struct lcd_platform_data *pd; + + pd = lcd->lcd_pd; + + if (!pd->power_on) { + dev_err(lcd->dev, "power_on is NULL.\n"); + return -EINVAL; + } else { + pd->power_on(lcd->ld, 1); + msleep(pd->power_on_delay); + } + + if (!pd->reset) { + dev_err(lcd->dev, "reset is NULL.\n"); + return -EINVAL; + } else { + pd->reset(lcd->ld); + msleep(pd->reset_delay); + } + + ret = lms501kf03_ldi_init(lcd); + if (ret) { + dev_err(lcd->dev, "failed to initialize ldi.\n"); + return ret; + } + + ret = lms501kf03_ldi_enable(lcd); + if (ret) { + dev_err(lcd->dev, "failed to enable ldi.\n"); + return ret; + } + + return 0; +} + +static int lms501kf03_power_off(struct lms501kf03 *lcd) +{ + int ret = 0; + struct lcd_platform_data *pd; + + pd = lcd->lcd_pd; + + ret = lms501kf03_ldi_disable(lcd); + if (ret) { + dev_err(lcd->dev, "lcd setting failed.\n"); + return -EIO; + } + + msleep(pd->power_off_delay); + + pd->power_on(lcd->ld, 0); + + return 0; +} + +static int lms501kf03_power(struct lms501kf03 *lcd, int power) +{ + int ret = 0; + + if (lms501kf03_power_is_on(power) && + !lms501kf03_power_is_on(lcd->power)) + ret = lms501kf03_power_on(lcd); + else if (!lms501kf03_power_is_on(power) && + lms501kf03_power_is_on(lcd->power)) + ret = lms501kf03_power_off(lcd); + + if (!ret) + lcd->power = power; + + return ret; +} + +static int lms501kf03_get_power(struct lcd_device *ld) +{ + struct lms501kf03 *lcd = lcd_get_data(ld); + + return lcd->power; +} + +static int lms501kf03_set_power(struct lcd_device *ld, int power) +{ + struct lms501kf03 *lcd = lcd_get_data(ld); + + if (power != FB_BLANK_UNBLANK && power != FB_BLANK_POWERDOWN && + power != FB_BLANK_NORMAL) { + dev_err(lcd->dev, "power value should be 0, 1 or 4.\n"); + return -EINVAL; + } + + return lms501kf03_power(lcd, power); +} + +static struct lcd_ops lms501kf03_lcd_ops = { + .get_power = lms501kf03_get_power, + .set_power = lms501kf03_set_power, +}; + +static int lms501kf03_probe(struct spi_device *spi) +{ + struct lms501kf03 *lcd = NULL; + struct lcd_device *ld = NULL; + int ret = 0; + + lcd = devm_kzalloc(&spi->dev, sizeof(struct lms501kf03), GFP_KERNEL); + if (!lcd) + return -ENOMEM; + + /* lms501kf03 lcd panel uses 3-wire 9-bit SPI Mode. */ + spi->bits_per_word = 9; + + ret = spi_setup(spi); + if (ret < 0) { + dev_err(&spi->dev, "spi setup failed.\n"); + return ret; + } + + lcd->spi = spi; + lcd->dev = &spi->dev; + + lcd->lcd_pd = spi->dev.platform_data; + if (!lcd->lcd_pd) { + dev_err(&spi->dev, "platform data is NULL\n"); + return -EINVAL; + } + + ld = lcd_device_register("lms501kf03", &spi->dev, lcd, + &lms501kf03_lcd_ops); + if (IS_ERR(ld)) + return PTR_ERR(ld); + + lcd->ld = ld; + + if (!lcd->lcd_pd->lcd_enabled) { + /* + * if lcd panel was off from bootloader then + * current lcd status is powerdown and then + * it enables lcd panel. + */ + lcd->power = FB_BLANK_POWERDOWN; + + lms501kf03_power(lcd, FB_BLANK_UNBLANK); + } else { + lcd->power = FB_BLANK_UNBLANK; + } + + spi_set_drvdata(spi, lcd); + + dev_info(&spi->dev, "lms501kf03 panel driver has been probed.\n"); + + return 0; +} + +static int lms501kf03_remove(struct spi_device *spi) +{ + struct lms501kf03 *lcd = spi_get_drvdata(spi); + + lms501kf03_power(lcd, FB_BLANK_POWERDOWN); + lcd_device_unregister(lcd->ld); + + return 0; +} + +#if defined(CONFIG_PM) + +static int lms501kf03_suspend(struct spi_device *spi, pm_message_t mesg) +{ + struct lms501kf03 *lcd = spi_get_drvdata(spi); + + dev_dbg(&spi->dev, "lcd->power = %d\n", lcd->power); + + /* + * when lcd panel is suspend, lcd panel becomes off + * regardless of status. + */ + return lms501kf03_power(lcd, FB_BLANK_POWERDOWN); +} + +static int lms501kf03_resume(struct spi_device *spi) +{ + struct lms501kf03 *lcd = spi_get_drvdata(spi); + + lcd->power = FB_BLANK_POWERDOWN; + + return lms501kf03_power(lcd, FB_BLANK_UNBLANK); +} +#else +#define lms501kf03_suspend NULL +#define lms501kf03_resume NULL +#endif + +static void lms501kf03_shutdown(struct spi_device *spi) +{ + struct lms501kf03 *lcd = spi_get_drvdata(spi); + + lms501kf03_power(lcd, FB_BLANK_POWERDOWN); +} + +static struct spi_driver lms501kf03_driver = { + .driver = { + .name = "lms501kf03", + .owner = THIS_MODULE, + }, + .probe = lms501kf03_probe, + .remove = lms501kf03_remove, + .shutdown = lms501kf03_shutdown, + .suspend = lms501kf03_suspend, + .resume = lms501kf03_resume, +}; + +module_spi_driver(lms501kf03_driver); + +MODULE_AUTHOR("Jingoo Han <jg1.han@samsung.com>"); +MODULE_DESCRIPTION("lms501kf03 LCD Driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/video/backlight/lp8788_bl.c b/drivers/video/backlight/lp8788_bl.c new file mode 100644 index 000000000000..fbf17bcd855c --- /dev/null +++ b/drivers/video/backlight/lp8788_bl.c @@ -0,0 +1,350 @@ +/* + * TI LP8788 MFD - backlight driver + * + * Copyright 2012 Texas Instruments + * + * Author: Milo(Woogyom) Kim <milo.kim@ti.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include <linux/backlight.h> +#include <linux/err.h> +#include <linux/mfd/lp8788.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/pwm.h> +#include <linux/slab.h> + +/* register address */ +#define LP8788_BL_CONFIG 0x96 +#define LP8788_BL_BRIGHTNESS 0x97 +#define LP8788_BL_RAMP 0x98 + +/* mask/shift bits */ +#define LP8788_BL_EN BIT(0) /* Addr 96h */ +#define LP8788_BL_PWM_EN BIT(5) +#define LP8788_BL_FULLSCALE_S 2 +#define LP8788_BL_DIM_MODE_S 1 +#define LP8788_BL_PWM_POLARITY_S 6 +#define LP8788_BL_RAMP_RISE_S 4 /* Addr 98h */ + +#define BUF_SIZE 20 +#define MAX_BRIGHTNESS 127 +#define DEFAULT_BL_NAME "lcd-backlight" + +struct lp8788_bl_config { + enum lp8788_bl_ctrl_mode bl_mode; + enum lp8788_bl_dim_mode dim_mode; + enum lp8788_bl_full_scale_current full_scale; + enum lp8788_bl_ramp_step rise_time; + enum lp8788_bl_ramp_step fall_time; + enum lp8788_bl_pwm_polarity pwm_pol; +}; + +struct lp8788_bl { + struct lp8788 *lp; + struct backlight_device *bl_dev; + struct lp8788_backlight_platform_data *pdata; + enum lp8788_bl_ctrl_mode mode; + struct pwm_device *pwm; +}; + +struct lp8788_bl_config default_bl_config = { + .bl_mode = LP8788_BL_REGISTER_ONLY, + .dim_mode = LP8788_DIM_EXPONENTIAL, + .full_scale = LP8788_FULLSCALE_1900uA, + .rise_time = LP8788_RAMP_8192us, + .fall_time = LP8788_RAMP_8192us, + .pwm_pol = LP8788_PWM_ACTIVE_HIGH, +}; + +static inline bool is_brightness_ctrl_by_pwm(enum lp8788_bl_ctrl_mode mode) +{ + return (mode == LP8788_BL_COMB_PWM_BASED); +} + +static inline bool is_brightness_ctrl_by_register(enum lp8788_bl_ctrl_mode mode) +{ + return (mode == LP8788_BL_REGISTER_ONLY || + mode == LP8788_BL_COMB_REGISTER_BASED); +} + +static int lp8788_backlight_configure(struct lp8788_bl *bl) +{ + struct lp8788_backlight_platform_data *pdata = bl->pdata; + struct lp8788_bl_config *cfg = &default_bl_config; + int ret; + u8 val; + + /* update chip configuration if platform data exists, + otherwise use the default settings */ + if (pdata) { + cfg->bl_mode = pdata->bl_mode; + cfg->dim_mode = pdata->dim_mode; + cfg->full_scale = pdata->full_scale; + cfg->rise_time = pdata->rise_time; + cfg->fall_time = pdata->fall_time; + cfg->pwm_pol = pdata->pwm_pol; + } + + /* brightness ramp up/down */ + val = (cfg->rise_time << LP8788_BL_RAMP_RISE_S) | cfg->fall_time; + ret = lp8788_write_byte(bl->lp, LP8788_BL_RAMP, val); + if (ret) { + /* no I2C needed in case of pwm control mode */ + if (is_brightness_ctrl_by_pwm(cfg->bl_mode)) + goto no_err; + else + return ret; + } + + /* fullscale current setting */ + val = (cfg->full_scale << LP8788_BL_FULLSCALE_S) | + (cfg->dim_mode << LP8788_BL_DIM_MODE_S); + + /* brightness control mode */ + switch (cfg->bl_mode) { + case LP8788_BL_REGISTER_ONLY: + val |= LP8788_BL_EN; + break; + case LP8788_BL_COMB_PWM_BASED: + case LP8788_BL_COMB_REGISTER_BASED: + val |= LP8788_BL_EN | LP8788_BL_PWM_EN | + (cfg->pwm_pol << LP8788_BL_PWM_POLARITY_S); + break; + default: + dev_err(bl->lp->dev, "invalid mode: %d\n", cfg->bl_mode); + return -EINVAL; + } + + bl->mode = cfg->bl_mode; + + return lp8788_write_byte(bl->lp, LP8788_BL_CONFIG, val); + +no_err: + return 0; +} + +static void lp8788_pwm_ctrl(struct lp8788_bl *bl, int br, int max_br) +{ + unsigned int period; + unsigned int duty; + struct device *dev; + struct pwm_device *pwm; + + if (!bl->pdata) + return; + + period = bl->pdata->period_ns; + duty = br * period / max_br; + dev = bl->lp->dev; + + /* request pwm device with the consumer name */ + if (!bl->pwm) { + pwm = devm_pwm_get(dev, LP8788_DEV_BACKLIGHT); + if (IS_ERR(pwm)) { + dev_err(dev, "can not get pwm device\n"); + return; + } + + bl->pwm = pwm; + } + + pwm_config(bl->pwm, duty, period); + if (duty) + pwm_enable(bl->pwm); + else + pwm_disable(bl->pwm); +} + +static int lp8788_bl_update_status(struct backlight_device *bl_dev) +{ + struct lp8788_bl *bl = bl_get_data(bl_dev); + enum lp8788_bl_ctrl_mode mode = bl->mode; + + if (bl_dev->props.state & BL_CORE_SUSPENDED) + bl_dev->props.brightness = 0; + + if (is_brightness_ctrl_by_pwm(mode)) { + int brt = bl_dev->props.brightness; + int max = bl_dev->props.max_brightness; + + lp8788_pwm_ctrl(bl, brt, max); + } else if (is_brightness_ctrl_by_register(mode)) { + u8 brt = bl_dev->props.brightness; + + lp8788_write_byte(bl->lp, LP8788_BL_BRIGHTNESS, brt); + } + + return 0; +} + +static int lp8788_bl_get_brightness(struct backlight_device *bl_dev) +{ + struct lp8788_bl *bl = bl_get_data(bl_dev); + enum lp8788_bl_ctrl_mode mode = bl->mode; + + if (is_brightness_ctrl_by_register(mode)) { + u8 val = 0; + + lp8788_read_byte(bl->lp, LP8788_BL_BRIGHTNESS, &val); + bl_dev->props.brightness = val; + } + + return bl_dev->props.brightness; +} + +static const struct backlight_ops lp8788_bl_ops = { + .options = BL_CORE_SUSPENDRESUME, + .update_status = lp8788_bl_update_status, + .get_brightness = lp8788_bl_get_brightness, +}; + +static int lp8788_backlight_register(struct lp8788_bl *bl) +{ + struct backlight_device *bl_dev; + struct backlight_properties props; + struct lp8788_backlight_platform_data *pdata = bl->pdata; + int init_brt; + char *name; + + props.type = BACKLIGHT_PLATFORM; + props.max_brightness = MAX_BRIGHTNESS; + + /* initial brightness */ + if (pdata) + init_brt = min_t(int, pdata->initial_brightness, + props.max_brightness); + else + init_brt = 0; + + props.brightness = init_brt; + + /* backlight device name */ + if (!pdata || !pdata->name) + name = DEFAULT_BL_NAME; + else + name = pdata->name; + + bl_dev = backlight_device_register(name, bl->lp->dev, bl, + &lp8788_bl_ops, &props); + if (IS_ERR(bl_dev)) + return PTR_ERR(bl_dev); + + bl->bl_dev = bl_dev; + + return 0; +} + +static void lp8788_backlight_unregister(struct lp8788_bl *bl) +{ + struct backlight_device *bl_dev = bl->bl_dev; + + if (bl_dev) + backlight_device_unregister(bl_dev); +} + +static ssize_t lp8788_get_bl_ctl_mode(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct lp8788_bl *bl = dev_get_drvdata(dev); + enum lp8788_bl_ctrl_mode mode = bl->mode; + char *strmode; + + if (is_brightness_ctrl_by_pwm(mode)) + strmode = "pwm based"; + else if (is_brightness_ctrl_by_register(mode)) + strmode = "register based"; + else + strmode = "invalid mode"; + + return scnprintf(buf, BUF_SIZE, "%s\n", strmode); +} + +static DEVICE_ATTR(bl_ctl_mode, S_IRUGO, lp8788_get_bl_ctl_mode, NULL); + +static struct attribute *lp8788_attributes[] = { + &dev_attr_bl_ctl_mode.attr, + NULL, +}; + +static const struct attribute_group lp8788_attr_group = { + .attrs = lp8788_attributes, +}; + +static int lp8788_backlight_probe(struct platform_device *pdev) +{ + struct lp8788 *lp = dev_get_drvdata(pdev->dev.parent); + struct lp8788_bl *bl; + int ret; + + bl = devm_kzalloc(lp->dev, sizeof(struct lp8788_bl), GFP_KERNEL); + if (!bl) + return -ENOMEM; + + bl->lp = lp; + if (lp->pdata) + bl->pdata = lp->pdata->bl_pdata; + + platform_set_drvdata(pdev, bl); + + ret = lp8788_backlight_configure(bl); + if (ret) { + dev_err(lp->dev, "backlight config err: %d\n", ret); + goto err_dev; + } + + ret = lp8788_backlight_register(bl); + if (ret) { + dev_err(lp->dev, "register backlight err: %d\n", ret); + goto err_dev; + } + + ret = sysfs_create_group(&pdev->dev.kobj, &lp8788_attr_group); + if (ret) { + dev_err(lp->dev, "register sysfs err: %d\n", ret); + goto err_sysfs; + } + + backlight_update_status(bl->bl_dev); + + return 0; + +err_sysfs: + lp8788_backlight_unregister(bl); +err_dev: + return ret; +} + +static int lp8788_backlight_remove(struct platform_device *pdev) +{ + struct lp8788_bl *bl = platform_get_drvdata(pdev); + struct backlight_device *bl_dev = bl->bl_dev; + + bl_dev->props.brightness = 0; + backlight_update_status(bl_dev); + sysfs_remove_group(&pdev->dev.kobj, &lp8788_attr_group); + lp8788_backlight_unregister(bl); + platform_set_drvdata(pdev, NULL); + + return 0; +} + +static struct platform_driver lp8788_bl_driver = { + .probe = lp8788_backlight_probe, + .remove = lp8788_backlight_remove, + .driver = { + .name = LP8788_DEV_BACKLIGHT, + .owner = THIS_MODULE, + }, +}; +module_platform_driver(lp8788_bl_driver); + +MODULE_DESCRIPTION("Texas Instruments LP8788 Backlight Driver"); +MODULE_AUTHOR("Milo Kim"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:lp8788-backlight"); diff --git a/drivers/video/backlight/ltv350qv.c b/drivers/video/backlight/ltv350qv.c index 226d813edf01..c0b4b8f2de98 100644 --- a/drivers/video/backlight/ltv350qv.c +++ b/drivers/video/backlight/ltv350qv.c @@ -252,7 +252,7 @@ static int ltv350qv_probe(struct spi_device *spi) if (ret) goto out_unregister; - dev_set_drvdata(&spi->dev, lcd); + spi_set_drvdata(spi, lcd); return 0; @@ -263,7 +263,7 @@ out_unregister: static int ltv350qv_remove(struct spi_device *spi) { - struct ltv350qv *lcd = dev_get_drvdata(&spi->dev); + struct ltv350qv *lcd = spi_get_drvdata(spi); ltv350qv_power(lcd, FB_BLANK_POWERDOWN); lcd_device_unregister(lcd->ld); @@ -274,14 +274,14 @@ static int ltv350qv_remove(struct spi_device *spi) #ifdef CONFIG_PM static int ltv350qv_suspend(struct spi_device *spi, pm_message_t state) { - struct ltv350qv *lcd = dev_get_drvdata(&spi->dev); + struct ltv350qv *lcd = spi_get_drvdata(spi); return ltv350qv_power(lcd, FB_BLANK_POWERDOWN); } static int ltv350qv_resume(struct spi_device *spi) { - struct ltv350qv *lcd = dev_get_drvdata(&spi->dev); + struct ltv350qv *lcd = spi_get_drvdata(spi); return ltv350qv_power(lcd, FB_BLANK_UNBLANK); } @@ -293,7 +293,7 @@ static int ltv350qv_resume(struct spi_device *spi) /* Power down all displays on reboot, poweroff or halt */ static void ltv350qv_shutdown(struct spi_device *spi) { - struct ltv350qv *lcd = dev_get_drvdata(&spi->dev); + struct ltv350qv *lcd = spi_get_drvdata(spi); ltv350qv_power(lcd, FB_BLANK_POWERDOWN); } diff --git a/drivers/video/backlight/omap1_bl.c b/drivers/video/backlight/omap1_bl.c index af31c269baa6..627110163067 100644 --- a/drivers/video/backlight/omap1_bl.c +++ b/drivers/video/backlight/omap1_bl.c @@ -77,7 +77,7 @@ static void omapbl_blank(struct omap_backlight *bl, int mode) static int omapbl_suspend(struct platform_device *pdev, pm_message_t state) { struct backlight_device *dev = platform_get_drvdata(pdev); - struct omap_backlight *bl = dev_get_drvdata(&dev->dev); + struct omap_backlight *bl = bl_get_data(dev); omapbl_blank(bl, FB_BLANK_POWERDOWN); return 0; @@ -86,7 +86,7 @@ static int omapbl_suspend(struct platform_device *pdev, pm_message_t state) static int omapbl_resume(struct platform_device *pdev) { struct backlight_device *dev = platform_get_drvdata(pdev); - struct omap_backlight *bl = dev_get_drvdata(&dev->dev); + struct omap_backlight *bl = bl_get_data(dev); omapbl_blank(bl, bl->powermode); return 0; @@ -98,7 +98,7 @@ static int omapbl_resume(struct platform_device *pdev) static int omapbl_set_power(struct backlight_device *dev, int state) { - struct omap_backlight *bl = dev_get_drvdata(&dev->dev); + struct omap_backlight *bl = bl_get_data(dev); omapbl_blank(bl, state); bl->powermode = state; @@ -108,7 +108,7 @@ static int omapbl_set_power(struct backlight_device *dev, int state) static int omapbl_update_status(struct backlight_device *dev) { - struct omap_backlight *bl = dev_get_drvdata(&dev->dev); + struct omap_backlight *bl = bl_get_data(dev); if (bl->current_intensity != dev->props.brightness) { if (bl->powermode == FB_BLANK_UNBLANK) @@ -124,7 +124,7 @@ static int omapbl_update_status(struct backlight_device *dev) static int omapbl_get_intensity(struct backlight_device *dev) { - struct omap_backlight *bl = dev_get_drvdata(&dev->dev); + struct omap_backlight *bl = bl_get_data(dev); return bl->current_intensity; } diff --git a/drivers/video/backlight/pwm_bl.c b/drivers/video/backlight/pwm_bl.c index a71ef4a79ec4..fa00304a63d8 100644 --- a/drivers/video/backlight/pwm_bl.c +++ b/drivers/video/backlight/pwm_bl.c @@ -37,7 +37,7 @@ struct pwm_bl_data { static int pwm_backlight_update_status(struct backlight_device *bl) { - struct pwm_bl_data *pb = dev_get_drvdata(&bl->dev); + struct pwm_bl_data *pb = bl_get_data(bl); int brightness = bl->props.brightness; int max = bl->props.max_brightness; @@ -82,7 +82,7 @@ static int pwm_backlight_get_brightness(struct backlight_device *bl) static int pwm_backlight_check_fb(struct backlight_device *bl, struct fb_info *info) { - struct pwm_bl_data *pb = dev_get_drvdata(&bl->dev); + struct pwm_bl_data *pb = bl_get_data(bl); return !pb->check_fb || pb->check_fb(pb->dev, info); } @@ -264,7 +264,7 @@ err_alloc: static int pwm_backlight_remove(struct platform_device *pdev) { struct backlight_device *bl = platform_get_drvdata(pdev); - struct pwm_bl_data *pb = dev_get_drvdata(&bl->dev); + struct pwm_bl_data *pb = bl_get_data(bl); backlight_device_unregister(bl); pwm_config(pb->pwm, 0, pb->period); @@ -278,7 +278,7 @@ static int pwm_backlight_remove(struct platform_device *pdev) static int pwm_backlight_suspend(struct device *dev) { struct backlight_device *bl = dev_get_drvdata(dev); - struct pwm_bl_data *pb = dev_get_drvdata(&bl->dev); + struct pwm_bl_data *pb = bl_get_data(bl); if (pb->notify) pb->notify(pb->dev, 0); diff --git a/drivers/video/backlight/s6e63m0.c b/drivers/video/backlight/s6e63m0.c index 3e1c1135f6df..9c2677f0ef7d 100644 --- a/drivers/video/backlight/s6e63m0.c +++ b/drivers/video/backlight/s6e63m0.c @@ -9,28 +9,19 @@ * under the terms of the GNU General Public License as published by the * Free Software Foundation; either version 2 of the License, or (at your * option) any later version. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */ -#include <linux/wait.h> -#include <linux/fb.h> +#include <linux/backlight.h> #include <linux/delay.h> +#include <linux/fb.h> #include <linux/gpio.h> -#include <linux/spi/spi.h> -#include <linux/irq.h> #include <linux/interrupt.h> +#include <linux/irq.h> #include <linux/kernel.h> #include <linux/lcd.h> -#include <linux/backlight.h> #include <linux/module.h> +#include <linux/spi/spi.h> +#include <linux/wait.h> #include "s6e63m0_gamma.h" @@ -43,8 +34,6 @@ #define MIN_BRIGHTNESS 0 #define MAX_BRIGHTNESS 10 -#define POWER_IS_ON(pwr) ((pwr) <= FB_BLANK_NORMAL) - struct s6e63m0 { struct device *dev; struct spi_device *spi; @@ -57,7 +46,7 @@ struct s6e63m0 { struct lcd_platform_data *lcd_pd; }; -static const unsigned short SEQ_PANEL_CONDITION_SET[] = { +static const unsigned short seq_panel_condition_set[] = { 0xF8, 0x01, DATA_ONLY, 0x27, DATA_ONLY, 0x27, @@ -76,7 +65,7 @@ static const unsigned short SEQ_PANEL_CONDITION_SET[] = { ENDDEF, 0x0000 }; -static const unsigned short SEQ_DISPLAY_CONDITION_SET[] = { +static const unsigned short seq_display_condition_set[] = { 0xf2, 0x02, DATA_ONLY, 0x03, DATA_ONLY, 0x1c, @@ -90,7 +79,7 @@ static const unsigned short SEQ_DISPLAY_CONDITION_SET[] = { ENDDEF, 0x0000 }; -static const unsigned short SEQ_GAMMA_SETTING[] = { +static const unsigned short seq_gamma_setting[] = { 0xfa, 0x00, DATA_ONLY, 0x18, DATA_ONLY, 0x08, @@ -119,7 +108,7 @@ static const unsigned short SEQ_GAMMA_SETTING[] = { ENDDEF, 0x0000 }; -static const unsigned short SEQ_ETC_CONDITION_SET[] = { +static const unsigned short seq_etc_condition_set[] = { 0xf6, 0x00, DATA_ONLY, 0x8c, DATA_ONLY, 0x07, @@ -318,47 +307,47 @@ static const unsigned short SEQ_ETC_CONDITION_SET[] = { ENDDEF, 0x0000 }; -static const unsigned short SEQ_ACL_ON[] = { +static const unsigned short seq_acl_on[] = { /* ACL on */ 0xc0, 0x01, ENDDEF, 0x0000 }; -static const unsigned short SEQ_ACL_OFF[] = { +static const unsigned short seq_acl_off[] = { /* ACL off */ 0xc0, 0x00, ENDDEF, 0x0000 }; -static const unsigned short SEQ_ELVSS_ON[] = { +static const unsigned short seq_elvss_on[] = { /* ELVSS on */ 0xb1, 0x0b, ENDDEF, 0x0000 }; -static const unsigned short SEQ_ELVSS_OFF[] = { +static const unsigned short seq_elvss_off[] = { /* ELVSS off */ 0xb1, 0x0a, ENDDEF, 0x0000 }; -static const unsigned short SEQ_STAND_BY_OFF[] = { +static const unsigned short seq_stand_by_off[] = { 0x11, COMMAND_ONLY, ENDDEF, 0x0000 }; -static const unsigned short SEQ_STAND_BY_ON[] = { +static const unsigned short seq_stand_by_on[] = { 0x10, COMMAND_ONLY, ENDDEF, 0x0000 }; -static const unsigned short SEQ_DISPLAY_ON[] = { +static const unsigned short seq_display_on[] = { 0x29, COMMAND_ONLY, ENDDEF, 0x0000 @@ -406,8 +395,9 @@ static int s6e63m0_panel_send_sequence(struct s6e63m0 *lcd, ret = s6e63m0_spi_write(lcd, wbuf[i], wbuf[i+1]); if (ret) break; - } else - udelay(wbuf[i+1]*1000); + } else { + msleep(wbuf[i+1]); + } i += 2; } @@ -457,12 +447,12 @@ static int s6e63m0_ldi_init(struct s6e63m0 *lcd) { int ret, i; const unsigned short *init_seq[] = { - SEQ_PANEL_CONDITION_SET, - SEQ_DISPLAY_CONDITION_SET, - SEQ_GAMMA_SETTING, - SEQ_ETC_CONDITION_SET, - SEQ_ACL_ON, - SEQ_ELVSS_ON, + seq_panel_condition_set, + seq_display_condition_set, + seq_gamma_setting, + seq_etc_condition_set, + seq_acl_on, + seq_elvss_on, }; for (i = 0; i < ARRAY_SIZE(init_seq); i++) { @@ -478,8 +468,8 @@ static int s6e63m0_ldi_enable(struct s6e63m0 *lcd) { int ret = 0, i; const unsigned short *enable_seq[] = { - SEQ_STAND_BY_OFF, - SEQ_DISPLAY_ON, + seq_stand_by_off, + seq_display_on, }; for (i = 0; i < ARRAY_SIZE(enable_seq); i++) { @@ -495,43 +485,39 @@ static int s6e63m0_ldi_disable(struct s6e63m0 *lcd) { int ret; - ret = s6e63m0_panel_send_sequence(lcd, SEQ_STAND_BY_ON); + ret = s6e63m0_panel_send_sequence(lcd, seq_stand_by_on); return ret; } +static int s6e63m0_power_is_on(int power) +{ + return power <= FB_BLANK_NORMAL; +} + static int s6e63m0_power_on(struct s6e63m0 *lcd) { int ret = 0; - struct lcd_platform_data *pd = NULL; - struct backlight_device *bd = NULL; + struct lcd_platform_data *pd; + struct backlight_device *bd; pd = lcd->lcd_pd; - if (!pd) { - dev_err(lcd->dev, "platform data is NULL.\n"); - return -EFAULT; - } - bd = lcd->bd; - if (!bd) { - dev_err(lcd->dev, "backlight device is NULL.\n"); - return -EFAULT; - } if (!pd->power_on) { dev_err(lcd->dev, "power_on is NULL.\n"); - return -EFAULT; + return -EINVAL; } else { pd->power_on(lcd->ld, 1); - mdelay(pd->power_on_delay); + msleep(pd->power_on_delay); } if (!pd->reset) { dev_err(lcd->dev, "reset is NULL.\n"); - return -EFAULT; + return -EINVAL; } else { pd->reset(lcd->ld); - mdelay(pd->reset_delay); + msleep(pd->reset_delay); } ret = s6e63m0_ldi_init(lcd); @@ -558,14 +544,10 @@ static int s6e63m0_power_on(struct s6e63m0 *lcd) static int s6e63m0_power_off(struct s6e63m0 *lcd) { - int ret = 0; - struct lcd_platform_data *pd = NULL; + int ret; + struct lcd_platform_data *pd; pd = lcd->lcd_pd; - if (!pd) { - dev_err(lcd->dev, "platform data is NULL.\n"); - return -EFAULT; - } ret = s6e63m0_ldi_disable(lcd); if (ret) { @@ -573,13 +555,9 @@ static int s6e63m0_power_off(struct s6e63m0 *lcd) return -EIO; } - mdelay(pd->power_off_delay); + msleep(pd->power_off_delay); - if (!pd->power_on) { - dev_err(lcd->dev, "power_on is NULL.\n"); - return -EFAULT; - } else - pd->power_on(lcd->ld, 0); + pd->power_on(lcd->ld, 0); return 0; } @@ -588,9 +566,9 @@ static int s6e63m0_power(struct s6e63m0 *lcd, int power) { int ret = 0; - if (POWER_IS_ON(power) && !POWER_IS_ON(lcd->power)) + if (s6e63m0_power_is_on(power) && !s6e63m0_power_is_on(lcd->power)) ret = s6e63m0_power_on(lcd); - else if (!POWER_IS_ON(power) && POWER_IS_ON(lcd->power)) + else if (!s6e63m0_power_is_on(power) && s6e63m0_power_is_on(lcd->power)) ret = s6e63m0_power_off(lcd); if (!ret) @@ -760,7 +738,7 @@ static int s6e63m0_probe(struct spi_device *spi) lcd->lcd_pd = spi->dev.platform_data; if (!lcd->lcd_pd) { dev_err(&spi->dev, "platform data is NULL.\n"); - return -EFAULT; + return -EINVAL; } ld = lcd_device_register("s6e63m0", &spi->dev, lcd, &s6e63m0_lcd_ops); @@ -788,7 +766,7 @@ static int s6e63m0_probe(struct spi_device *spi) * know that. */ lcd->gamma_table_count = - sizeof(gamma_table) / (MAX_GAMMA_LEVEL * sizeof(int)); + sizeof(gamma_table) / (MAX_GAMMA_LEVEL * sizeof(int *)); ret = device_create_file(&(spi->dev), &dev_attr_gamma_mode); if (ret < 0) @@ -811,10 +789,11 @@ static int s6e63m0_probe(struct spi_device *spi) lcd->power = FB_BLANK_POWERDOWN; s6e63m0_power(lcd, FB_BLANK_UNBLANK); - } else + } else { lcd->power = FB_BLANK_UNBLANK; + } - dev_set_drvdata(&spi->dev, lcd); + spi_set_drvdata(spi, lcd); dev_info(&spi->dev, "s6e63m0 panel driver has been probed.\n"); @@ -827,7 +806,7 @@ out_lcd_unregister: static int s6e63m0_remove(struct spi_device *spi) { - struct s6e63m0 *lcd = dev_get_drvdata(&spi->dev); + struct s6e63m0 *lcd = spi_get_drvdata(spi); s6e63m0_power(lcd, FB_BLANK_POWERDOWN); device_remove_file(&spi->dev, &dev_attr_gamma_table); @@ -839,44 +818,26 @@ static int s6e63m0_remove(struct spi_device *spi) } #if defined(CONFIG_PM) -static unsigned int before_power; - static int s6e63m0_suspend(struct spi_device *spi, pm_message_t mesg) { - int ret = 0; - struct s6e63m0 *lcd = dev_get_drvdata(&spi->dev); + struct s6e63m0 *lcd = spi_get_drvdata(spi); dev_dbg(&spi->dev, "lcd->power = %d\n", lcd->power); - before_power = lcd->power; - /* * when lcd panel is suspend, lcd panel becomes off * regardless of status. */ - ret = s6e63m0_power(lcd, FB_BLANK_POWERDOWN); - - return ret; + return s6e63m0_power(lcd, FB_BLANK_POWERDOWN); } static int s6e63m0_resume(struct spi_device *spi) { - int ret = 0; - struct s6e63m0 *lcd = dev_get_drvdata(&spi->dev); - - /* - * after suspended, if lcd panel status is FB_BLANK_UNBLANK - * (at that time, before_power is FB_BLANK_UNBLANK) then - * it changes that status to FB_BLANK_POWERDOWN to get lcd on. - */ - if (before_power == FB_BLANK_UNBLANK) - lcd->power = FB_BLANK_POWERDOWN; + struct s6e63m0 *lcd = spi_get_drvdata(spi); - dev_dbg(&spi->dev, "before_power = %d\n", before_power); + lcd->power = FB_BLANK_POWERDOWN; - ret = s6e63m0_power(lcd, before_power); - - return ret; + return s6e63m0_power(lcd, FB_BLANK_UNBLANK); } #else #define s6e63m0_suspend NULL @@ -886,7 +847,7 @@ static int s6e63m0_resume(struct spi_device *spi) /* Power down all displays on reboot, poweroff or halt. */ static void s6e63m0_shutdown(struct spi_device *spi) { - struct s6e63m0 *lcd = dev_get_drvdata(&spi->dev); + struct s6e63m0 *lcd = spi_get_drvdata(spi); s6e63m0_power(lcd, FB_BLANK_POWERDOWN); } diff --git a/drivers/video/backlight/tdo24m.c b/drivers/video/backlight/tdo24m.c index ad2325f3d652..00162085eec0 100644 --- a/drivers/video/backlight/tdo24m.c +++ b/drivers/video/backlight/tdo24m.c @@ -390,7 +390,7 @@ static int tdo24m_probe(struct spi_device *spi) if (IS_ERR(lcd->lcd_dev)) return PTR_ERR(lcd->lcd_dev); - dev_set_drvdata(&spi->dev, lcd); + spi_set_drvdata(spi, lcd); err = tdo24m_power(lcd, FB_BLANK_UNBLANK); if (err) goto out_unregister; @@ -404,7 +404,7 @@ out_unregister: static int tdo24m_remove(struct spi_device *spi) { - struct tdo24m *lcd = dev_get_drvdata(&spi->dev); + struct tdo24m *lcd = spi_get_drvdata(spi); tdo24m_power(lcd, FB_BLANK_POWERDOWN); lcd_device_unregister(lcd->lcd_dev); @@ -415,14 +415,14 @@ static int tdo24m_remove(struct spi_device *spi) #ifdef CONFIG_PM static int tdo24m_suspend(struct spi_device *spi, pm_message_t state) { - struct tdo24m *lcd = dev_get_drvdata(&spi->dev); + struct tdo24m *lcd = spi_get_drvdata(spi); return tdo24m_power(lcd, FB_BLANK_POWERDOWN); } static int tdo24m_resume(struct spi_device *spi) { - struct tdo24m *lcd = dev_get_drvdata(&spi->dev); + struct tdo24m *lcd = spi_get_drvdata(spi); return tdo24m_power(lcd, FB_BLANK_UNBLANK); } @@ -434,7 +434,7 @@ static int tdo24m_resume(struct spi_device *spi) /* Power down all displays on reboot, poweroff or halt */ static void tdo24m_shutdown(struct spi_device *spi) { - struct tdo24m *lcd = dev_get_drvdata(&spi->dev); + struct tdo24m *lcd = spi_get_drvdata(spi); tdo24m_power(lcd, FB_BLANK_POWERDOWN); } diff --git a/drivers/video/backlight/tosa_bl.c b/drivers/video/backlight/tosa_bl.c index 588682cc1614..2326fa810c59 100644 --- a/drivers/video/backlight/tosa_bl.c +++ b/drivers/video/backlight/tosa_bl.c @@ -54,7 +54,7 @@ static void tosa_bl_set_backlight(struct tosa_bl_data *data, int brightness) static int tosa_bl_update_status(struct backlight_device *dev) { struct backlight_properties *props = &dev->props; - struct tosa_bl_data *data = dev_get_drvdata(&dev->dev); + struct tosa_bl_data *data = bl_get_data(dev); int power = max(props->power, props->fb_blank); int brightness = props->brightness; diff --git a/drivers/video/backlight/tosa_lcd.c b/drivers/video/backlight/tosa_lcd.c index 96bae941585a..666fe2593ea4 100644 --- a/drivers/video/backlight/tosa_lcd.c +++ b/drivers/video/backlight/tosa_lcd.c @@ -193,7 +193,7 @@ static int tosa_lcd_probe(struct spi_device *spi) return ret; data->spi = spi; - dev_set_drvdata(&spi->dev, data); + spi_set_drvdata(spi, data); ret = devm_gpio_request_one(&spi->dev, TOSA_GPIO_TG_ON, GPIOF_OUT_INIT_LOW, "tg #pwr"); @@ -220,13 +220,13 @@ static int tosa_lcd_probe(struct spi_device *spi) err_register: tosa_lcd_tg_off(data); err_gpio_tg: - dev_set_drvdata(&spi->dev, NULL); + spi_set_drvdata(spi, NULL); return ret; } static int tosa_lcd_remove(struct spi_device *spi) { - struct tosa_lcd_data *data = dev_get_drvdata(&spi->dev); + struct tosa_lcd_data *data = spi_get_drvdata(spi); lcd_device_unregister(data->lcd); @@ -235,7 +235,7 @@ static int tosa_lcd_remove(struct spi_device *spi) tosa_lcd_tg_off(data); - dev_set_drvdata(&spi->dev, NULL); + spi_set_drvdata(spi, NULL); return 0; } @@ -243,7 +243,7 @@ static int tosa_lcd_remove(struct spi_device *spi) #ifdef CONFIG_PM static int tosa_lcd_suspend(struct spi_device *spi, pm_message_t state) { - struct tosa_lcd_data *data = dev_get_drvdata(&spi->dev); + struct tosa_lcd_data *data = spi_get_drvdata(spi); tosa_lcd_tg_off(data); @@ -252,7 +252,7 @@ static int tosa_lcd_suspend(struct spi_device *spi, pm_message_t state) static int tosa_lcd_resume(struct spi_device *spi) { - struct tosa_lcd_data *data = dev_get_drvdata(&spi->dev); + struct tosa_lcd_data *data = spi_get_drvdata(spi); tosa_lcd_tg_init(data); if (POWER_IS_ON(data->lcd_power)) diff --git a/drivers/video/backlight/vgg2432a4.c b/drivers/video/backlight/vgg2432a4.c index 45e81b4cf8b4..84d582f591dc 100644 --- a/drivers/video/backlight/vgg2432a4.c +++ b/drivers/video/backlight/vgg2432a4.c @@ -208,12 +208,11 @@ static int vgg2432a4_lcd_init(struct ili9320 *lcd, #ifdef CONFIG_PM static int vgg2432a4_suspend(struct spi_device *spi, pm_message_t state) { - return ili9320_suspend(dev_get_drvdata(&spi->dev), state); + return ili9320_suspend(spi_get_drvdata(spi), state); } - static int vgg2432a4_resume(struct spi_device *spi) { - return ili9320_resume(dev_get_drvdata(&spi->dev)); + return ili9320_resume(spi_get_drvdata(spi)); } #else #define vgg2432a4_suspend NULL @@ -242,12 +241,12 @@ static int vgg2432a4_probe(struct spi_device *spi) static int vgg2432a4_remove(struct spi_device *spi) { - return ili9320_remove(dev_get_drvdata(&spi->dev)); + return ili9320_remove(spi_get_drvdata(spi)); } static void vgg2432a4_shutdown(struct spi_device *spi) { - ili9320_shutdown(dev_get_drvdata(&spi->dev)); + ili9320_shutdown(spi_get_drvdata(spi)); } static struct spi_driver vgg2432a4_driver = { diff --git a/drivers/video/console/fbcon.c b/drivers/video/console/fbcon.c index 2aef9cac4d18..7d97d3fe9e89 100644 --- a/drivers/video/console/fbcon.c +++ b/drivers/video/console/fbcon.c @@ -1269,8 +1269,16 @@ static void fbcon_clear(struct vc_data *vc, int sy, int sx, int height, if (!height || !width) return; - if (sy < vc->vc_top && vc->vc_top == logo_lines) + if (sy < vc->vc_top && vc->vc_top == logo_lines) { vc->vc_top = 0; + /* + * If the font dimensions are not an integral of the display + * dimensions then the ops->clear below won't end up clearing + * the margins. Call clear_margins here in case the logo + * bitmap stretched into the margin area. + */ + fbcon_clear_margins(vc, 0); + } /* Split blits that cross physical y_wrap boundary */ diff --git a/drivers/video/cyber2000fb.c b/drivers/video/cyber2000fb.c index 57886787ead0..e78d9f2233b8 100644 --- a/drivers/video/cyber2000fb.c +++ b/drivers/video/cyber2000fb.c @@ -518,6 +518,9 @@ static void cyber2000fb_set_timing(struct cfb_info *cfb, struct par_info *hw) cyber2000_grphw(0xb9, 0x00, cfb); spin_unlock(&cfb->reg_b0_lock); + /* wait (for the PLL?) to avoid palette corruption at higher clocks */ + msleep(1000); + cfb->ramdac_ctrl = hw->ramdac; cyber2000fb_write_ramdac_ctrl(cfb); diff --git a/drivers/video/goldfishfb.c b/drivers/video/goldfishfb.c new file mode 100644 index 000000000000..f7f5c296e104 --- /dev/null +++ b/drivers/video/goldfishfb.c @@ -0,0 +1,316 @@ +/* + * Copyright (C) 2007 Google, Inc. + * Copyright (C) 2012 Intel, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/dma-mapping.h> +#include <linux/errno.h> +#include <linux/string.h> +#include <linux/slab.h> +#include <linux/delay.h> +#include <linux/mm.h> +#include <linux/fb.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/ioport.h> +#include <linux/platform_device.h> + +enum { + FB_GET_WIDTH = 0x00, + FB_GET_HEIGHT = 0x04, + FB_INT_STATUS = 0x08, + FB_INT_ENABLE = 0x0c, + FB_SET_BASE = 0x10, + FB_SET_ROTATION = 0x14, + FB_SET_BLANK = 0x18, + FB_GET_PHYS_WIDTH = 0x1c, + FB_GET_PHYS_HEIGHT = 0x20, + + FB_INT_VSYNC = 1U << 0, + FB_INT_BASE_UPDATE_DONE = 1U << 1 +}; + +struct goldfish_fb { + void __iomem *reg_base; + int irq; + spinlock_t lock; + wait_queue_head_t wait; + int base_update_count; + int rotation; + struct fb_info fb; + u32 cmap[16]; +}; + +static irqreturn_t goldfish_fb_interrupt(int irq, void *dev_id) +{ + unsigned long irq_flags; + struct goldfish_fb *fb = dev_id; + u32 status; + + spin_lock_irqsave(&fb->lock, irq_flags); + status = readl(fb->reg_base + FB_INT_STATUS); + if (status & FB_INT_BASE_UPDATE_DONE) { + fb->base_update_count++; + wake_up(&fb->wait); + } + spin_unlock_irqrestore(&fb->lock, irq_flags); + return status ? IRQ_HANDLED : IRQ_NONE; +} + +static inline u32 convert_bitfield(int val, struct fb_bitfield *bf) +{ + unsigned int mask = (1 << bf->length) - 1; + + return (val >> (16 - bf->length) & mask) << bf->offset; +} + +static int +goldfish_fb_setcolreg(unsigned int regno, unsigned int red, unsigned int green, + unsigned int blue, unsigned int transp, struct fb_info *info) +{ + struct goldfish_fb *fb = container_of(info, struct goldfish_fb, fb); + + if (regno < 16) { + fb->cmap[regno] = convert_bitfield(transp, &fb->fb.var.transp) | + convert_bitfield(blue, &fb->fb.var.blue) | + convert_bitfield(green, &fb->fb.var.green) | + convert_bitfield(red, &fb->fb.var.red); + return 0; + } else { + return 1; + } +} + +static int goldfish_fb_check_var(struct fb_var_screeninfo *var, + struct fb_info *info) +{ + if ((var->rotate & 1) != (info->var.rotate & 1)) { + if ((var->xres != info->var.yres) || + (var->yres != info->var.xres) || + (var->xres_virtual != info->var.yres) || + (var->yres_virtual > info->var.xres * 2) || + (var->yres_virtual < info->var.xres)) { + return -EINVAL; + } + } else { + if ((var->xres != info->var.xres) || + (var->yres != info->var.yres) || + (var->xres_virtual != info->var.xres) || + (var->yres_virtual > info->var.yres * 2) || + (var->yres_virtual < info->var.yres)) { + return -EINVAL; + } + } + if ((var->xoffset != info->var.xoffset) || + (var->bits_per_pixel != info->var.bits_per_pixel) || + (var->grayscale != info->var.grayscale)) { + return -EINVAL; + } + return 0; +} + +static int goldfish_fb_set_par(struct fb_info *info) +{ + struct goldfish_fb *fb = container_of(info, struct goldfish_fb, fb); + if (fb->rotation != fb->fb.var.rotate) { + info->fix.line_length = info->var.xres * 2; + fb->rotation = fb->fb.var.rotate; + writel(fb->rotation, fb->reg_base + FB_SET_ROTATION); + } + return 0; +} + + +static int goldfish_fb_pan_display(struct fb_var_screeninfo *var, + struct fb_info *info) +{ + unsigned long irq_flags; + int base_update_count; + struct goldfish_fb *fb = container_of(info, struct goldfish_fb, fb); + + spin_lock_irqsave(&fb->lock, irq_flags); + base_update_count = fb->base_update_count; + writel(fb->fb.fix.smem_start + fb->fb.var.xres * 2 * var->yoffset, + fb->reg_base + FB_SET_BASE); + spin_unlock_irqrestore(&fb->lock, irq_flags); + wait_event_timeout(fb->wait, + fb->base_update_count != base_update_count, HZ / 15); + if (fb->base_update_count == base_update_count) + pr_err("goldfish_fb_pan_display: timeout wating for base update\n"); + return 0; +} + +static int goldfish_fb_blank(int blank, struct fb_info *info) +{ + struct goldfish_fb *fb = container_of(info, struct goldfish_fb, fb); + switch (blank) { + case FB_BLANK_NORMAL: + writel(1, fb->reg_base + FB_SET_BLANK); + break; + case FB_BLANK_UNBLANK: + writel(0, fb->reg_base + FB_SET_BLANK); + break; + } + return 0; +} + +static struct fb_ops goldfish_fb_ops = { + .owner = THIS_MODULE, + .fb_check_var = goldfish_fb_check_var, + .fb_set_par = goldfish_fb_set_par, + .fb_setcolreg = goldfish_fb_setcolreg, + .fb_pan_display = goldfish_fb_pan_display, + .fb_blank = goldfish_fb_blank, + .fb_fillrect = cfb_fillrect, + .fb_copyarea = cfb_copyarea, + .fb_imageblit = cfb_imageblit, +}; + + +static int goldfish_fb_probe(struct platform_device *pdev) +{ + int ret; + struct resource *r; + struct goldfish_fb *fb; + size_t framesize; + u32 width, height; + dma_addr_t fbpaddr; + + fb = kzalloc(sizeof(*fb), GFP_KERNEL); + if (fb == NULL) { + ret = -ENOMEM; + goto err_fb_alloc_failed; + } + spin_lock_init(&fb->lock); + init_waitqueue_head(&fb->wait); + platform_set_drvdata(pdev, fb); + + r = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (r == NULL) { + ret = -ENODEV; + goto err_no_io_base; + } + fb->reg_base = ioremap(r->start, PAGE_SIZE); + if (fb->reg_base == NULL) { + ret = -ENOMEM; + goto err_no_io_base; + } + + fb->irq = platform_get_irq(pdev, 0); + if (fb->irq <= 0) { + ret = -ENODEV; + goto err_no_irq; + } + + width = readl(fb->reg_base + FB_GET_WIDTH); + height = readl(fb->reg_base + FB_GET_HEIGHT); + + fb->fb.fbops = &goldfish_fb_ops; + fb->fb.flags = FBINFO_FLAG_DEFAULT; + fb->fb.pseudo_palette = fb->cmap; + fb->fb.fix.type = FB_TYPE_PACKED_PIXELS; + fb->fb.fix.visual = FB_VISUAL_TRUECOLOR; + fb->fb.fix.line_length = width * 2; + fb->fb.fix.accel = FB_ACCEL_NONE; + fb->fb.fix.ypanstep = 1; + + fb->fb.var.xres = width; + fb->fb.var.yres = height; + fb->fb.var.xres_virtual = width; + fb->fb.var.yres_virtual = height * 2; + fb->fb.var.bits_per_pixel = 16; + fb->fb.var.activate = FB_ACTIVATE_NOW; + fb->fb.var.height = readl(fb->reg_base + FB_GET_PHYS_HEIGHT); + fb->fb.var.width = readl(fb->reg_base + FB_GET_PHYS_WIDTH); + fb->fb.var.pixclock = 10000; + + fb->fb.var.red.offset = 11; + fb->fb.var.red.length = 5; + fb->fb.var.green.offset = 5; + fb->fb.var.green.length = 6; + fb->fb.var.blue.offset = 0; + fb->fb.var.blue.length = 5; + + framesize = width * height * 2 * 2; + fb->fb.screen_base = dma_alloc_coherent(&pdev->dev, framesize, + &fbpaddr, GFP_KERNEL); + pr_debug("allocating frame buffer %d * %d, got %p\n", + width, height, fb->fb.screen_base); + if (fb->fb.screen_base == 0) { + ret = -ENOMEM; + goto err_alloc_screen_base_failed; + } + fb->fb.fix.smem_start = fbpaddr; + fb->fb.fix.smem_len = framesize; + + ret = fb_set_var(&fb->fb, &fb->fb.var); + if (ret) + goto err_fb_set_var_failed; + + ret = request_irq(fb->irq, goldfish_fb_interrupt, IRQF_SHARED, + pdev->name, fb); + if (ret) + goto err_request_irq_failed; + + writel(FB_INT_BASE_UPDATE_DONE, fb->reg_base + FB_INT_ENABLE); + goldfish_fb_pan_display(&fb->fb.var, &fb->fb); /* updates base */ + + ret = register_framebuffer(&fb->fb); + if (ret) + goto err_register_framebuffer_failed; + return 0; + +err_register_framebuffer_failed: + free_irq(fb->irq, fb); +err_request_irq_failed: +err_fb_set_var_failed: + dma_free_coherent(&pdev->dev, framesize, + fb->fb.screen_base, fb->fb.fix.smem_start); +err_alloc_screen_base_failed: +err_no_irq: + iounmap(fb->reg_base); +err_no_io_base: + kfree(fb); +err_fb_alloc_failed: + return ret; +} + +static int goldfish_fb_remove(struct platform_device *pdev) +{ + size_t framesize; + struct goldfish_fb *fb = platform_get_drvdata(pdev); + + framesize = fb->fb.var.xres_virtual * fb->fb.var.yres_virtual * 2; + unregister_framebuffer(&fb->fb); + free_irq(fb->irq, fb); + + dma_free_coherent(&pdev->dev, framesize, fb->fb.screen_base, + fb->fb.fix.smem_start); + iounmap(fb->reg_base); + return 0; +} + + +static struct platform_driver goldfish_fb_driver = { + .probe = goldfish_fb_probe, + .remove = goldfish_fb_remove, + .driver = { + .name = "goldfish_fb" + } +}; + +module_platform_driver(goldfish_fb_driver); + +MODULE_LICENSE("GPL v2"); diff --git a/drivers/video/mmp/Kconfig b/drivers/video/mmp/Kconfig new file mode 100644 index 000000000000..e9ea39e13722 --- /dev/null +++ b/drivers/video/mmp/Kconfig @@ -0,0 +1,11 @@ +menuconfig MMP_DISP + tristate "Marvell MMP Display Subsystem support" + depends on CPU_PXA910 || CPU_MMP2 || CPU_MMP3 || CPU_PXA988 + help + Marvell Display Subsystem support. + +if MMP_DISP +source "drivers/video/mmp/hw/Kconfig" +source "drivers/video/mmp/panel/Kconfig" +source "drivers/video/mmp/fb/Kconfig" +endif diff --git a/drivers/video/mmp/Makefile b/drivers/video/mmp/Makefile new file mode 100644 index 000000000000..a014cb358bf8 --- /dev/null +++ b/drivers/video/mmp/Makefile @@ -0,0 +1 @@ +obj-y += core.o hw/ panel/ fb/ diff --git a/drivers/video/mmp/core.c b/drivers/video/mmp/core.c new file mode 100644 index 000000000000..9ed83419038b --- /dev/null +++ b/drivers/video/mmp/core.c @@ -0,0 +1,258 @@ +/* + * linux/drivers/video/mmp/common.c + * This driver is a common framework for Marvell Display Controller + * + * Copyright (C) 2012 Marvell Technology Group Ltd. + * Authors: Zhou Zhu <zzhu3@marvell.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + * + */ + +#include <linux/slab.h> +#include <linux/dma-mapping.h> +#include <linux/export.h> +#include <video/mmp_disp.h> + +static struct mmp_overlay *path_get_overlay(struct mmp_path *path, + int overlay_id) +{ + if (path && overlay_id < path->overlay_num) + return &path->overlays[overlay_id]; + return 0; +} + +static int path_check_status(struct mmp_path *path) +{ + int i; + for (i = 0; i < path->overlay_num; i++) + if (path->overlays[i].status) + return 1; + + return 0; +} + +/* + * Get modelist write pointer of modelist. + * It also returns modelist number + * this function fetches modelist from phy/panel: + * for HDMI/parallel or dsi to hdmi cases, get from phy + * or get from panel + */ +static int path_get_modelist(struct mmp_path *path, + struct mmp_mode **modelist) +{ + BUG_ON(!path || !modelist); + + if (path->panel && path->panel->get_modelist) + return path->panel->get_modelist(path->panel, modelist); + + return 0; +} + +/* + * panel list is used to pair panel/path when path/panel registered + * path list is used for both buffer driver and platdriver + * plat driver do path register/unregister + * panel driver do panel register/unregister + * buffer driver get registered path + */ +static LIST_HEAD(panel_list); +static LIST_HEAD(path_list); +static DEFINE_MUTEX(disp_lock); + +/* + * mmp_register_panel - register panel to panel_list and connect to path + * @p: panel to be registered + * + * this function provides interface for panel drivers to register panel + * to panel_list and connect to path which matchs panel->plat_path_name. + * no error returns when no matching path is found as path register after + * panel register is permitted. + */ +void mmp_register_panel(struct mmp_panel *panel) +{ + struct mmp_path *path; + + mutex_lock(&disp_lock); + + /* add */ + list_add_tail(&panel->node, &panel_list); + + /* try to register to path */ + list_for_each_entry(path, &path_list, node) { + if (!strcmp(panel->plat_path_name, path->name)) { + dev_info(panel->dev, "connect to path %s\n", + path->name); + path->panel = panel; + break; + } + } + + mutex_unlock(&disp_lock); +} +EXPORT_SYMBOL_GPL(mmp_register_panel); + +/* + * mmp_unregister_panel - unregister panel from panel_list and disconnect + * @p: panel to be unregistered + * + * this function provides interface for panel drivers to unregister panel + * from panel_list and disconnect from path. + */ +void mmp_unregister_panel(struct mmp_panel *panel) +{ + struct mmp_path *path; + + mutex_lock(&disp_lock); + list_del(&panel->node); + + list_for_each_entry(path, &path_list, node) { + if (path->panel && path->panel == panel) { + dev_info(panel->dev, "disconnect from path %s\n", + path->name); + path->panel = NULL; + break; + } + } + mutex_unlock(&disp_lock); +} +EXPORT_SYMBOL_GPL(mmp_unregister_panel); + +/* + * mmp_get_path - get path by name + * @p: path name + * + * this function checks path name in path_list and return matching path + * return NULL if no matching path + */ +struct mmp_path *mmp_get_path(const char *name) +{ + struct mmp_path *path; + int found = 0; + + mutex_lock(&disp_lock); + list_for_each_entry(path, &path_list, node) { + if (!strcmp(name, path->name)) { + found = 1; + break; + } + } + mutex_unlock(&disp_lock); + + return found ? path : NULL; +} +EXPORT_SYMBOL_GPL(mmp_get_path); + +/* + * mmp_register_path - init and register path by path_info + * @p: path info provided by display controller + * + * this function init by path info and register path to path_list + * this function also try to connect path with panel by name + */ +struct mmp_path *mmp_register_path(struct mmp_path_info *info) +{ + int i; + size_t size; + struct mmp_path *path = NULL; + struct mmp_panel *panel; + + size = sizeof(struct mmp_path) + + sizeof(struct mmp_overlay) * info->overlay_num; + path = kzalloc(size, GFP_KERNEL); + if (!path) + goto failed; + + /* path set */ + mutex_init(&path->access_ok); + path->dev = info->dev; + path->id = info->id; + path->name = info->name; + path->output_type = info->output_type; + path->overlay_num = info->overlay_num; + path->plat_data = info->plat_data; + path->ops.set_mode = info->set_mode; + + mutex_lock(&disp_lock); + /* get panel */ + list_for_each_entry(panel, &panel_list, node) { + if (!strcmp(info->name, panel->plat_path_name)) { + dev_info(path->dev, "get panel %s\n", panel->name); + path->panel = panel; + break; + } + } + + dev_info(path->dev, "register %s, overlay_num %d\n", + path->name, path->overlay_num); + + /* default op set: if already set by driver, never cover it */ + if (!path->ops.check_status) + path->ops.check_status = path_check_status; + if (!path->ops.get_overlay) + path->ops.get_overlay = path_get_overlay; + if (!path->ops.get_modelist) + path->ops.get_modelist = path_get_modelist; + + /* step3: init overlays */ + for (i = 0; i < path->overlay_num; i++) { + path->overlays[i].path = path; + path->overlays[i].id = i; + mutex_init(&path->overlays[i].access_ok); + path->overlays[i].ops = info->overlay_ops; + } + + /* add to pathlist */ + list_add_tail(&path->node, &path_list); + + mutex_unlock(&disp_lock); + return path; + +failed: + kfree(path); + mutex_unlock(&disp_lock); + return NULL; +} +EXPORT_SYMBOL_GPL(mmp_register_path); + +/* + * mmp_unregister_path - unregister and destory path + * @p: path to be destoried. + * + * this function registers path and destorys it. + */ +void mmp_unregister_path(struct mmp_path *path) +{ + int i; + + if (!path) + return; + + mutex_lock(&disp_lock); + /* del from pathlist */ + list_del(&path->node); + + /* deinit overlays */ + for (i = 0; i < path->overlay_num; i++) + mutex_destroy(&path->overlays[i].access_ok); + + mutex_destroy(&path->access_ok); + + kfree(path); + mutex_unlock(&disp_lock); + + dev_info(path->dev, "de-register %s\n", path->name); +} +EXPORT_SYMBOL_GPL(mmp_unregister_path); diff --git a/drivers/video/mmp/fb/Kconfig b/drivers/video/mmp/fb/Kconfig new file mode 100644 index 000000000000..9b0141f105f5 --- /dev/null +++ b/drivers/video/mmp/fb/Kconfig @@ -0,0 +1,13 @@ +if MMP_DISP + +config MMP_FB + bool "fb driver for Marvell MMP Display Subsystem" + depends on FB + select FB_CFB_FILLRECT + select FB_CFB_COPYAREA + select FB_CFB_IMAGEBLIT + default y + help + fb driver for Marvell MMP Display Subsystem + +endif diff --git a/drivers/video/mmp/fb/Makefile b/drivers/video/mmp/fb/Makefile new file mode 100644 index 000000000000..709fd1f76abe --- /dev/null +++ b/drivers/video/mmp/fb/Makefile @@ -0,0 +1 @@ +obj-$(CONFIG_MMP_FB) += mmpfb.o diff --git a/drivers/video/mmp/fb/mmpfb.c b/drivers/video/mmp/fb/mmpfb.c new file mode 100644 index 000000000000..f34a3a907f1b --- /dev/null +++ b/drivers/video/mmp/fb/mmpfb.c @@ -0,0 +1,684 @@ +/* + * linux/drivers/video/mmp/fb/mmpfb.c + * Framebuffer driver for Marvell Display controller. + * + * Copyright (C) 2012 Marvell Technology Group Ltd. + * Authors: Zhou Zhu <zzhu3@marvell.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + * + */ +#include <linux/module.h> +#include <linux/dma-mapping.h> +#include "mmpfb.h" + +static int var_to_pixfmt(struct fb_var_screeninfo *var) +{ + /* + * Pseudocolor mode? + */ + if (var->bits_per_pixel == 8) + return PIXFMT_PSEUDOCOLOR; + + /* + * Check for YUV422PLANAR. + */ + if (var->bits_per_pixel == 16 && var->red.length == 8 && + var->green.length == 4 && var->blue.length == 4) { + if (var->green.offset >= var->blue.offset) + return PIXFMT_YUV422P; + else + return PIXFMT_YVU422P; + } + + /* + * Check for YUV420PLANAR. + */ + if (var->bits_per_pixel == 12 && var->red.length == 8 && + var->green.length == 2 && var->blue.length == 2) { + if (var->green.offset >= var->blue.offset) + return PIXFMT_YUV420P; + else + return PIXFMT_YVU420P; + } + + /* + * Check for YUV422PACK. + */ + if (var->bits_per_pixel == 16 && var->red.length == 16 && + var->green.length == 16 && var->blue.length == 16) { + if (var->red.offset == 0) + return PIXFMT_YUYV; + else if (var->green.offset >= var->blue.offset) + return PIXFMT_UYVY; + else + return PIXFMT_VYUY; + } + + /* + * Check for 565/1555. + */ + if (var->bits_per_pixel == 16 && var->red.length <= 5 && + var->green.length <= 6 && var->blue.length <= 5) { + if (var->transp.length == 0) { + if (var->red.offset >= var->blue.offset) + return PIXFMT_RGB565; + else + return PIXFMT_BGR565; + } + } + + /* + * Check for 888/A888. + */ + if (var->bits_per_pixel <= 32 && var->red.length <= 8 && + var->green.length <= 8 && var->blue.length <= 8) { + if (var->bits_per_pixel == 24 && var->transp.length == 0) { + if (var->red.offset >= var->blue.offset) + return PIXFMT_RGB888PACK; + else + return PIXFMT_BGR888PACK; + } + + if (var->bits_per_pixel == 32 && var->transp.offset == 24) { + if (var->red.offset >= var->blue.offset) + return PIXFMT_RGBA888; + else + return PIXFMT_BGRA888; + } else { + if (var->red.offset >= var->blue.offset) + return PIXFMT_RGB888UNPACK; + else + return PIXFMT_BGR888UNPACK; + } + + /* fall through */ + } + + return -EINVAL; +} + +static void pixfmt_to_var(struct fb_var_screeninfo *var, int pix_fmt) +{ + switch (pix_fmt) { + case PIXFMT_RGB565: + var->bits_per_pixel = 16; + var->red.offset = 11; var->red.length = 5; + var->green.offset = 5; var->green.length = 6; + var->blue.offset = 0; var->blue.length = 5; + var->transp.offset = 0; var->transp.length = 0; + break; + case PIXFMT_BGR565: + var->bits_per_pixel = 16; + var->red.offset = 0; var->red.length = 5; + var->green.offset = 5; var->green.length = 6; + var->blue.offset = 11; var->blue.length = 5; + var->transp.offset = 0; var->transp.length = 0; + break; + case PIXFMT_RGB888UNPACK: + var->bits_per_pixel = 32; + var->red.offset = 16; var->red.length = 8; + var->green.offset = 8; var->green.length = 8; + var->blue.offset = 0; var->blue.length = 8; + var->transp.offset = 0; var->transp.length = 0; + break; + case PIXFMT_BGR888UNPACK: + var->bits_per_pixel = 32; + var->red.offset = 0; var->red.length = 8; + var->green.offset = 8; var->green.length = 8; + var->blue.offset = 16; var->blue.length = 8; + var->transp.offset = 0; var->transp.length = 0; + break; + case PIXFMT_RGBA888: + var->bits_per_pixel = 32; + var->red.offset = 16; var->red.length = 8; + var->green.offset = 8; var->green.length = 8; + var->blue.offset = 0; var->blue.length = 8; + var->transp.offset = 24; var->transp.length = 8; + break; + case PIXFMT_BGRA888: + var->bits_per_pixel = 32; + var->red.offset = 0; var->red.length = 8; + var->green.offset = 8; var->green.length = 8; + var->blue.offset = 16; var->blue.length = 8; + var->transp.offset = 24; var->transp.length = 8; + break; + case PIXFMT_RGB888PACK: + var->bits_per_pixel = 24; + var->red.offset = 16; var->red.length = 8; + var->green.offset = 8; var->green.length = 8; + var->blue.offset = 0; var->blue.length = 8; + var->transp.offset = 0; var->transp.length = 0; + break; + case PIXFMT_BGR888PACK: + var->bits_per_pixel = 24; + var->red.offset = 0; var->red.length = 8; + var->green.offset = 8; var->green.length = 8; + var->blue.offset = 16; var->blue.length = 8; + var->transp.offset = 0; var->transp.length = 0; + break; + case PIXFMT_YUV420P: + var->bits_per_pixel = 12; + var->red.offset = 4; var->red.length = 8; + var->green.offset = 2; var->green.length = 2; + var->blue.offset = 0; var->blue.length = 2; + var->transp.offset = 0; var->transp.length = 0; + break; + case PIXFMT_YVU420P: + var->bits_per_pixel = 12; + var->red.offset = 4; var->red.length = 8; + var->green.offset = 0; var->green.length = 2; + var->blue.offset = 2; var->blue.length = 2; + var->transp.offset = 0; var->transp.length = 0; + break; + case PIXFMT_YUV422P: + var->bits_per_pixel = 16; + var->red.offset = 8; var->red.length = 8; + var->green.offset = 4; var->green.length = 4; + var->blue.offset = 0; var->blue.length = 4; + var->transp.offset = 0; var->transp.length = 0; + break; + case PIXFMT_YVU422P: + var->bits_per_pixel = 16; + var->red.offset = 8; var->red.length = 8; + var->green.offset = 0; var->green.length = 4; + var->blue.offset = 4; var->blue.length = 4; + var->transp.offset = 0; var->transp.length = 0; + break; + case PIXFMT_UYVY: + var->bits_per_pixel = 16; + var->red.offset = 8; var->red.length = 16; + var->green.offset = 4; var->green.length = 16; + var->blue.offset = 0; var->blue.length = 16; + var->transp.offset = 0; var->transp.length = 0; + break; + case PIXFMT_VYUY: + var->bits_per_pixel = 16; + var->red.offset = 8; var->red.length = 16; + var->green.offset = 0; var->green.length = 16; + var->blue.offset = 4; var->blue.length = 16; + var->transp.offset = 0; var->transp.length = 0; + break; + case PIXFMT_YUYV: + var->bits_per_pixel = 16; + var->red.offset = 0; var->red.length = 16; + var->green.offset = 4; var->green.length = 16; + var->blue.offset = 8; var->blue.length = 16; + var->transp.offset = 0; var->transp.length = 0; + break; + case PIXFMT_PSEUDOCOLOR: + var->bits_per_pixel = 8; + var->red.offset = 0; var->red.length = 8; + var->green.offset = 0; var->green.length = 8; + var->blue.offset = 0; var->blue.length = 8; + var->transp.offset = 0; var->transp.length = 0; + break; + } +} + +/* + * fb framework has its limitation: + * 1. input color/output color is not seprated + * 2. fb_videomode not include output color + * so for fb usage, we keep a output format which is not changed + * then it's added for mmpmode + */ +static void fbmode_to_mmpmode(struct mmp_mode *mode, + struct fb_videomode *videomode, int output_fmt) +{ + u64 div_result = 1000000000000ll; + mode->name = videomode->name; + mode->refresh = videomode->refresh; + mode->xres = videomode->xres; + mode->yres = videomode->yres; + + do_div(div_result, videomode->pixclock); + mode->pixclock_freq = (u32)div_result; + + mode->left_margin = videomode->left_margin; + mode->right_margin = videomode->right_margin; + mode->upper_margin = videomode->upper_margin; + mode->lower_margin = videomode->lower_margin; + mode->hsync_len = videomode->hsync_len; + mode->vsync_len = videomode->vsync_len; + mode->hsync_invert = !!(videomode->sync & FB_SYNC_HOR_HIGH_ACT); + mode->vsync_invert = !!(videomode->sync & FB_SYNC_VERT_HIGH_ACT); + /* no defined flag in fb, use vmode>>3*/ + mode->invert_pixclock = !!(videomode->vmode & 8); + mode->pix_fmt_out = output_fmt; +} + +static void mmpmode_to_fbmode(struct fb_videomode *videomode, + struct mmp_mode *mode) +{ + u64 div_result = 1000000000000ll; + + videomode->name = mode->name; + videomode->refresh = mode->refresh; + videomode->xres = mode->xres; + videomode->yres = mode->yres; + + do_div(div_result, mode->pixclock_freq); + videomode->pixclock = (u32)div_result; + + videomode->left_margin = mode->left_margin; + videomode->right_margin = mode->right_margin; + videomode->upper_margin = mode->upper_margin; + videomode->lower_margin = mode->lower_margin; + videomode->hsync_len = mode->hsync_len; + videomode->vsync_len = mode->vsync_len; + videomode->sync = (mode->hsync_invert ? FB_SYNC_HOR_HIGH_ACT : 0) + | (mode->vsync_invert ? FB_SYNC_VERT_HIGH_ACT : 0); + videomode->vmode = mode->invert_pixclock ? 8 : 0; +} + +static int mmpfb_check_var(struct fb_var_screeninfo *var, + struct fb_info *info) +{ + struct mmpfb_info *fbi = info->par; + + if (var->bits_per_pixel == 8) + return -EINVAL; + /* + * Basic geometry sanity checks. + */ + if (var->xoffset + var->xres > var->xres_virtual) + return -EINVAL; + if (var->yoffset + var->yres > var->yres_virtual) + return -EINVAL; + + /* + * Check size of framebuffer. + */ + if (var->xres_virtual * var->yres_virtual * + (var->bits_per_pixel >> 3) > fbi->fb_size) + return -EINVAL; + + return 0; +} + +static unsigned int chan_to_field(unsigned int chan, struct fb_bitfield *bf) +{ + return ((chan & 0xffff) >> (16 - bf->length)) << bf->offset; +} + +static u32 to_rgb(u16 red, u16 green, u16 blue) +{ + red >>= 8; + green >>= 8; + blue >>= 8; + + return (red << 16) | (green << 8) | blue; +} + +static int mmpfb_setcolreg(unsigned int regno, unsigned int red, + unsigned int green, unsigned int blue, + unsigned int trans, struct fb_info *info) +{ + struct mmpfb_info *fbi = info->par; + u32 val; + + if (info->fix.visual == FB_VISUAL_TRUECOLOR && regno < 16) { + val = chan_to_field(red, &info->var.red); + val |= chan_to_field(green, &info->var.green); + val |= chan_to_field(blue , &info->var.blue); + fbi->pseudo_palette[regno] = val; + } + + if (info->fix.visual == FB_VISUAL_PSEUDOCOLOR && regno < 256) { + val = to_rgb(red, green, blue); + /* TODO */ + } + + return 0; +} + +static int mmpfb_pan_display(struct fb_var_screeninfo *var, + struct fb_info *info) +{ + struct mmpfb_info *fbi = info->par; + struct mmp_addr addr; + + memset(&addr, 0, sizeof(addr)); + addr.phys[0] = (var->yoffset * var->xres_virtual + var->xoffset) + * var->bits_per_pixel / 8 + fbi->fb_start_dma; + mmp_overlay_set_addr(fbi->overlay, &addr); + + return 0; +} + +static int var_update(struct fb_info *info) +{ + struct mmpfb_info *fbi = info->par; + struct fb_var_screeninfo *var = &info->var; + struct fb_videomode *m; + int pix_fmt; + + /* set pix_fmt */ + pix_fmt = var_to_pixfmt(var); + if (pix_fmt < 0) + return -EINVAL; + pixfmt_to_var(var, pix_fmt); + fbi->pix_fmt = pix_fmt; + + /* set var according to best video mode*/ + m = (struct fb_videomode *)fb_match_mode(var, &info->modelist); + if (!m) { + dev_err(fbi->dev, "set par: no match mode, use best mode\n"); + m = (struct fb_videomode *)fb_find_best_mode(var, + &info->modelist); + fb_videomode_to_var(var, m); + } + memcpy(&fbi->mode, m, sizeof(struct fb_videomode)); + + /* fix to 2* yres */ + var->yres_virtual = var->yres * 2; + info->fix.visual = (pix_fmt == PIXFMT_PSEUDOCOLOR) ? + FB_VISUAL_PSEUDOCOLOR : FB_VISUAL_TRUECOLOR; + info->fix.line_length = var->xres_virtual * var->bits_per_pixel / 8; + info->fix.ypanstep = var->yres; + return 0; +} + +static int mmpfb_set_par(struct fb_info *info) +{ + struct mmpfb_info *fbi = info->par; + struct fb_var_screeninfo *var = &info->var; + struct mmp_addr addr; + struct mmp_win win; + struct mmp_mode mode; + int ret; + + ret = var_update(info); + if (ret != 0) + return ret; + + /* set window/path according to new videomode */ + fbmode_to_mmpmode(&mode, &fbi->mode, fbi->output_fmt); + mmp_path_set_mode(fbi->path, &mode); + + memset(&win, 0, sizeof(win)); + win.xsrc = win.xdst = fbi->mode.xres; + win.ysrc = win.ydst = fbi->mode.yres; + win.pix_fmt = fbi->pix_fmt; + mmp_overlay_set_win(fbi->overlay, &win); + + /* set address always */ + memset(&addr, 0, sizeof(addr)); + addr.phys[0] = (var->yoffset * var->xres_virtual + var->xoffset) + * var->bits_per_pixel / 8 + fbi->fb_start_dma; + mmp_overlay_set_addr(fbi->overlay, &addr); + + return 0; +} + +static void mmpfb_power(struct mmpfb_info *fbi, int power) +{ + struct mmp_addr addr; + struct mmp_win win; + struct fb_var_screeninfo *var = &fbi->fb_info->var; + + /* for power on, always set address/window again */ + if (power) { + memset(&win, 0, sizeof(win)); + win.xsrc = win.xdst = fbi->mode.xres; + win.ysrc = win.ydst = fbi->mode.yres; + win.pix_fmt = fbi->pix_fmt; + mmp_overlay_set_win(fbi->overlay, &win); + + /* set address always */ + memset(&addr, 0, sizeof(addr)); + addr.phys[0] = fbi->fb_start_dma + + (var->yoffset * var->xres_virtual + var->xoffset) + * var->bits_per_pixel / 8; + mmp_overlay_set_addr(fbi->overlay, &addr); + } + mmp_overlay_set_onoff(fbi->overlay, power); +} + +static int mmpfb_blank(int blank, struct fb_info *info) +{ + struct mmpfb_info *fbi = info->par; + + mmpfb_power(fbi, (blank == FB_BLANK_UNBLANK)); + + return 0; +} + +static struct fb_ops mmpfb_ops = { + .owner = THIS_MODULE, + .fb_blank = mmpfb_blank, + .fb_check_var = mmpfb_check_var, + .fb_set_par = mmpfb_set_par, + .fb_setcolreg = mmpfb_setcolreg, + .fb_pan_display = mmpfb_pan_display, + .fb_fillrect = cfb_fillrect, + .fb_copyarea = cfb_copyarea, + .fb_imageblit = cfb_imageblit, +}; + +static int modes_setup(struct mmpfb_info *fbi) +{ + struct fb_videomode *videomodes; + struct mmp_mode *mmp_modes; + struct fb_info *info = fbi->fb_info; + int videomode_num, i; + + /* get videomodes from path */ + videomode_num = mmp_path_get_modelist(fbi->path, &mmp_modes); + if (!videomode_num) { + dev_warn(fbi->dev, "can't get videomode num\n"); + return 0; + } + /* put videomode list to info structure */ + videomodes = kzalloc(sizeof(struct fb_videomode) * videomode_num, + GFP_KERNEL); + if (!videomodes) { + dev_err(fbi->dev, "can't malloc video modes\n"); + return -ENOMEM; + } + for (i = 0; i < videomode_num; i++) + mmpmode_to_fbmode(&videomodes[i], &mmp_modes[i]); + fb_videomode_to_modelist(videomodes, videomode_num, &info->modelist); + + /* set videomode[0] as default mode */ + memcpy(&fbi->mode, &videomodes[0], sizeof(struct fb_videomode)); + fbi->output_fmt = mmp_modes[0].pix_fmt_out; + fb_videomode_to_var(&info->var, &fbi->mode); + mmp_path_set_mode(fbi->path, &mmp_modes[0]); + + kfree(videomodes); + return videomode_num; +} + +static int fb_info_setup(struct fb_info *info, + struct mmpfb_info *fbi) +{ + int ret = 0; + /* Initialise static fb parameters.*/ + info->flags = FBINFO_DEFAULT | FBINFO_PARTIAL_PAN_OK | + FBINFO_HWACCEL_XPAN | FBINFO_HWACCEL_YPAN; + info->node = -1; + strcpy(info->fix.id, fbi->name); + info->fix.type = FB_TYPE_PACKED_PIXELS; + info->fix.type_aux = 0; + info->fix.xpanstep = 0; + info->fix.ypanstep = info->var.yres; + info->fix.ywrapstep = 0; + info->fix.accel = FB_ACCEL_NONE; + info->fix.smem_start = fbi->fb_start_dma; + info->fix.smem_len = fbi->fb_size; + info->fix.visual = (fbi->pix_fmt == PIXFMT_PSEUDOCOLOR) ? + FB_VISUAL_PSEUDOCOLOR : FB_VISUAL_TRUECOLOR; + info->fix.line_length = info->var.xres_virtual * + info->var.bits_per_pixel / 8; + info->fbops = &mmpfb_ops; + info->pseudo_palette = fbi->pseudo_palette; + info->screen_base = fbi->fb_start; + info->screen_size = fbi->fb_size; + + /* For FB framework: Allocate color map and Register framebuffer*/ + if (fb_alloc_cmap(&info->cmap, 256, 0) < 0) + ret = -ENOMEM; + + return ret; +} + +static void fb_info_clear(struct fb_info *info) +{ + fb_dealloc_cmap(&info->cmap); +} + +static int mmpfb_probe(struct platform_device *pdev) +{ + struct mmp_buffer_driver_mach_info *mi; + struct fb_info *info = 0; + struct mmpfb_info *fbi = 0; + int ret, modes_num; + + mi = pdev->dev.platform_data; + if (mi == NULL) { + dev_err(&pdev->dev, "no platform data defined\n"); + return -EINVAL; + } + + /* initialize fb */ + info = framebuffer_alloc(sizeof(struct mmpfb_info), &pdev->dev); + if (info == NULL) + return -ENOMEM; + fbi = info->par; + if (!fbi) { + ret = -EINVAL; + goto failed; + } + + /* init fb */ + fbi->fb_info = info; + platform_set_drvdata(pdev, fbi); + fbi->dev = &pdev->dev; + fbi->name = mi->name; + fbi->pix_fmt = mi->default_pixfmt; + pixfmt_to_var(&info->var, fbi->pix_fmt); + mutex_init(&fbi->access_ok); + + /* get display path by name */ + fbi->path = mmp_get_path(mi->path_name); + if (!fbi->path) { + dev_err(&pdev->dev, "can't get the path %s\n", mi->path_name); + ret = -EINVAL; + goto failed_destroy_mutex; + } + + dev_info(fbi->dev, "path %s get\n", fbi->path->name); + + /* get overlay */ + fbi->overlay = mmp_path_get_overlay(fbi->path, mi->overlay_id); + if (!fbi->overlay) { + ret = -EINVAL; + goto failed_destroy_mutex; + } + /* set fetch used */ + mmp_overlay_set_fetch(fbi->overlay, mi->dmafetch_id); + + modes_num = modes_setup(fbi); + if (modes_num < 0) { + ret = modes_num; + goto failed_destroy_mutex; + } + + /* + * if get modes success, means not hotplug panels, use caculated buffer + * or use default size + */ + if (modes_num > 0) { + /* fix to 2* yres */ + info->var.yres_virtual = info->var.yres * 2; + + /* Allocate framebuffer memory: size = modes xy *4 */ + fbi->fb_size = info->var.xres_virtual * info->var.yres_virtual + * info->var.bits_per_pixel / 8; + } else { + fbi->fb_size = MMPFB_DEFAULT_SIZE; + } + + fbi->fb_start = dma_alloc_coherent(&pdev->dev, PAGE_ALIGN(fbi->fb_size), + &fbi->fb_start_dma, GFP_KERNEL); + if (fbi->fb_start == NULL) { + dev_err(&pdev->dev, "can't alloc framebuffer\n"); + ret = -ENOMEM; + goto failed_destroy_mutex; + } + memset(fbi->fb_start, 0, fbi->fb_size); + dev_info(fbi->dev, "fb %dk allocated\n", fbi->fb_size/1024); + + /* fb power on */ + if (modes_num > 0) + mmpfb_power(fbi, 1); + + ret = fb_info_setup(info, fbi); + if (ret < 0) + goto failed_free_buff; + + ret = register_framebuffer(info); + if (ret < 0) { + dev_err(&pdev->dev, "Failed to register fb: %d\n", ret); + ret = -ENXIO; + goto failed_clear_info; + } + + dev_info(fbi->dev, "loaded to /dev/fb%d <%s>.\n", + info->node, info->fix.id); + +#ifdef CONFIG_LOGO + if (fbi->fb_start) { + fb_prepare_logo(info, 0); + fb_show_logo(info, 0); + } +#endif + + return 0; + +failed_clear_info: + fb_info_clear(info); +failed_free_buff: + dma_free_coherent(&pdev->dev, PAGE_ALIGN(fbi->fb_size), fbi->fb_start, + fbi->fb_start_dma); +failed_destroy_mutex: + mutex_destroy(&fbi->access_ok); +failed: + dev_err(fbi->dev, "mmp-fb: frame buffer device init failed\n"); + platform_set_drvdata(pdev, NULL); + + framebuffer_release(info); + + return ret; +} + +static struct platform_driver mmpfb_driver = { + .driver = { + .name = "mmp-fb", + .owner = THIS_MODULE, + }, + .probe = mmpfb_probe, +}; + +static int mmpfb_init(void) +{ + return platform_driver_register(&mmpfb_driver); +} +module_init(mmpfb_init); + +MODULE_AUTHOR("Zhou Zhu <zhou.zhu@marvell.com>"); +MODULE_DESCRIPTION("Framebuffer driver for Marvell displays"); +MODULE_LICENSE("GPL"); diff --git a/drivers/video/mmp/fb/mmpfb.h b/drivers/video/mmp/fb/mmpfb.h new file mode 100644 index 000000000000..88c23c10a9ec --- /dev/null +++ b/drivers/video/mmp/fb/mmpfb.h @@ -0,0 +1,54 @@ +/* + * linux/drivers/video/mmp/fb/mmpfb.h + * Framebuffer driver for Marvell Display controller. + * + * Copyright (C) 2012 Marvell Technology Group Ltd. + * Authors: Zhou Zhu <zzhu3@marvell.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + * + */ + +#ifndef _MMP_FB_H_ +#define _MMP_FB_H_ + +#include <video/mmp_disp.h> +#include <linux/fb.h> + +/* LCD controller private state. */ +struct mmpfb_info { + struct device *dev; + int id; + const char *name; + + struct fb_info *fb_info; + /* basicaly videomode is for output */ + struct fb_videomode mode; + int pix_fmt; + + void *fb_start; + int fb_size; + dma_addr_t fb_start_dma; + + struct mmp_overlay *overlay; + struct mmp_path *path; + + struct mutex access_ok; + + unsigned int pseudo_palette[16]; + int output_fmt; +}; + +#define MMPFB_DEFAULT_SIZE (PAGE_ALIGN(1920 * 1080 * 4 * 2)) +#endif /* _MMP_FB_H_ */ diff --git a/drivers/video/mmp/hw/Kconfig b/drivers/video/mmp/hw/Kconfig new file mode 100644 index 000000000000..02f109a20cd0 --- /dev/null +++ b/drivers/video/mmp/hw/Kconfig @@ -0,0 +1,20 @@ +if MMP_DISP + +config MMP_DISP_CONTROLLER + bool "mmp display controller hw support" + depends on CPU_PXA910 || CPU_MMP2 || CPU_MMP3 || CPU_PXA988 + default n + help + Marvell MMP display hw controller support + this controller is used on Marvell PXA910, + MMP2, MMP3, PXA988 chips + +config MMP_DISP_SPI + bool "mmp display controller spi port" + depends on MMP_DISP_CONTROLLER && SPI_MASTER + default y + help + Marvell MMP display hw controller spi port support + will register as a spi master for panel usage + +endif diff --git a/drivers/video/mmp/hw/Makefile b/drivers/video/mmp/hw/Makefile new file mode 100644 index 000000000000..0000a714fedf --- /dev/null +++ b/drivers/video/mmp/hw/Makefile @@ -0,0 +1,2 @@ +obj-$(CONFIG_MMP_DISP_CONTROLLER) += mmp_ctrl.o +obj-$(CONFIG_MMP_DISP_SPI) += mmp_spi.o diff --git a/drivers/video/mmp/hw/mmp_ctrl.c b/drivers/video/mmp/hw/mmp_ctrl.c new file mode 100644 index 000000000000..4bd31b2af398 --- /dev/null +++ b/drivers/video/mmp/hw/mmp_ctrl.c @@ -0,0 +1,591 @@ +/* + * linux/drivers/video/mmp/hw/mmp_ctrl.c + * Marvell MMP series Display Controller support + * + * Copyright (C) 2012 Marvell Technology Group Ltd. + * Authors: Guoqing Li <ligq@marvell.com> + * Lisa Du <cldu@marvell.com> + * Zhou Zhu <zzhu3@marvell.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + * + */ +#include <linux/module.h> +#include <linux/moduleparam.h> +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/string.h> +#include <linux/interrupt.h> +#include <linux/slab.h> +#include <linux/delay.h> +#include <linux/platform_device.h> +#include <linux/dma-mapping.h> +#include <linux/clk.h> +#include <linux/err.h> +#include <linux/vmalloc.h> +#include <linux/uaccess.h> +#include <linux/kthread.h> +#include <linux/io.h> + +#include "mmp_ctrl.h" + +static irqreturn_t ctrl_handle_irq(int irq, void *dev_id) +{ + struct mmphw_ctrl *ctrl = (struct mmphw_ctrl *)dev_id; + u32 isr, imask, tmp; + + isr = readl_relaxed(ctrl->reg_base + SPU_IRQ_ISR); + imask = readl_relaxed(ctrl->reg_base + SPU_IRQ_ENA); + + do { + /* clear clock only */ + tmp = readl_relaxed(ctrl->reg_base + SPU_IRQ_ISR); + if (tmp & isr) + writel_relaxed(~isr, ctrl->reg_base + SPU_IRQ_ISR); + } while ((isr = readl(ctrl->reg_base + SPU_IRQ_ISR)) & imask); + + return IRQ_HANDLED; +} + +static u32 fmt_to_reg(struct mmp_overlay *overlay, int pix_fmt) +{ + u32 link_config = path_to_path_plat(overlay->path)->link_config; + u32 rbswap, uvswap = 0, yuvswap = 0, + csc_en = 0, val = 0, + vid = overlay_is_vid(overlay); + + switch (pix_fmt) { + case PIXFMT_RGB565: + case PIXFMT_RGB1555: + case PIXFMT_RGB888PACK: + case PIXFMT_RGB888UNPACK: + case PIXFMT_RGBA888: + rbswap = !(link_config & 0x1); + break; + case PIXFMT_VYUY: + case PIXFMT_YVU422P: + case PIXFMT_YVU420P: + rbswap = link_config & 0x1; + uvswap = 1; + break; + case PIXFMT_YUYV: + rbswap = link_config & 0x1; + yuvswap = 1; + break; + default: + rbswap = link_config & 0x1; + break; + } + + switch (pix_fmt) { + case PIXFMT_RGB565: + case PIXFMT_BGR565: + val = 0; + break; + case PIXFMT_RGB1555: + case PIXFMT_BGR1555: + val = 0x1; + break; + case PIXFMT_RGB888PACK: + case PIXFMT_BGR888PACK: + val = 0x2; + break; + case PIXFMT_RGB888UNPACK: + case PIXFMT_BGR888UNPACK: + val = 0x3; + break; + case PIXFMT_RGBA888: + case PIXFMT_BGRA888: + val = 0x4; + break; + case PIXFMT_UYVY: + case PIXFMT_VYUY: + case PIXFMT_YUYV: + val = 0x5; + csc_en = 1; + break; + case PIXFMT_YUV422P: + case PIXFMT_YVU422P: + val = 0x6; + csc_en = 1; + break; + case PIXFMT_YUV420P: + case PIXFMT_YVU420P: + val = 0x7; + csc_en = 1; + break; + default: + break; + } + + return (dma_palette(0) | dma_fmt(vid, val) | + dma_swaprb(vid, rbswap) | dma_swapuv(vid, uvswap) | + dma_swapyuv(vid, yuvswap) | dma_csc(vid, csc_en)); +} + +static void dmafetch_set_fmt(struct mmp_overlay *overlay) +{ + u32 tmp; + struct mmp_path *path = overlay->path; + tmp = readl_relaxed(ctrl_regs(path) + dma_ctrl(0, path->id)); + tmp &= ~dma_mask(overlay_is_vid(overlay)); + tmp |= fmt_to_reg(overlay, overlay->win.pix_fmt); + writel_relaxed(tmp, ctrl_regs(path) + dma_ctrl(0, path->id)); +} + +static void overlay_set_win(struct mmp_overlay *overlay, struct mmp_win *win) +{ + struct lcd_regs *regs = path_regs(overlay->path); + u32 pitch; + + /* assert win supported */ + memcpy(&overlay->win, win, sizeof(struct mmp_win)); + + mutex_lock(&overlay->access_ok); + pitch = win->xsrc * pixfmt_to_stride(win->pix_fmt); + writel_relaxed(pitch, ®s->g_pitch); + writel_relaxed((win->ysrc << 16) | win->xsrc, ®s->g_size); + writel_relaxed((win->ydst << 16) | win->xdst, ®s->g_size_z); + writel_relaxed(0, ®s->g_start); + + dmafetch_set_fmt(overlay); + mutex_unlock(&overlay->access_ok); +} + +static void dmafetch_onoff(struct mmp_overlay *overlay, int on) +{ + u32 mask = overlay_is_vid(overlay) ? CFG_GRA_ENA_MASK : + CFG_DMA_ENA_MASK; + u32 enable = overlay_is_vid(overlay) ? CFG_GRA_ENA(1) : CFG_DMA_ENA(1); + u32 tmp; + struct mmp_path *path = overlay->path; + + mutex_lock(&overlay->access_ok); + tmp = readl_relaxed(ctrl_regs(path) + dma_ctrl(0, path->id)); + tmp &= ~mask; + tmp |= (on ? enable : 0); + writel(tmp, ctrl_regs(path) + dma_ctrl(0, path->id)); + mutex_unlock(&overlay->access_ok); +} + +static void path_enabledisable(struct mmp_path *path, int on) +{ + u32 tmp; + mutex_lock(&path->access_ok); + tmp = readl_relaxed(ctrl_regs(path) + LCD_SCLK(path)); + if (on) + tmp &= ~SCLK_DISABLE; + else + tmp |= SCLK_DISABLE; + writel_relaxed(tmp, ctrl_regs(path) + LCD_SCLK(path)); + mutex_unlock(&path->access_ok); +} + +static void path_onoff(struct mmp_path *path, int on) +{ + if (path->status == on) { + dev_info(path->dev, "path %s is already %s\n", + path->name, stat_name(path->status)); + return; + } + + if (on) { + path_enabledisable(path, 1); + + if (path->panel && path->panel->set_onoff) + path->panel->set_onoff(path->panel, 1); + } else { + if (path->panel && path->panel->set_onoff) + path->panel->set_onoff(path->panel, 0); + + path_enabledisable(path, 0); + } + path->status = on; +} + +static void overlay_set_onoff(struct mmp_overlay *overlay, int on) +{ + if (overlay->status == on) { + dev_info(overlay_to_ctrl(overlay)->dev, "overlay %s is already %s\n", + overlay->path->name, stat_name(overlay->status)); + return; + } + overlay->status = on; + dmafetch_onoff(overlay, on); + if (overlay->path->ops.check_status(overlay->path) + != overlay->path->status) + path_onoff(overlay->path, on); +} + +static void overlay_set_fetch(struct mmp_overlay *overlay, int fetch_id) +{ + overlay->dmafetch_id = fetch_id; +} + +static int overlay_set_addr(struct mmp_overlay *overlay, struct mmp_addr *addr) +{ + struct lcd_regs *regs = path_regs(overlay->path); + + /* FIXME: assert addr supported */ + memcpy(&overlay->addr, addr, sizeof(struct mmp_win)); + writel(addr->phys[0], ®s->g_0); + + return overlay->addr.phys[0]; +} + +static void path_set_mode(struct mmp_path *path, struct mmp_mode *mode) +{ + struct lcd_regs *regs = path_regs(path); + u32 total_x, total_y, vsync_ctrl, tmp, sclk_src, sclk_div, + link_config = path_to_path_plat(path)->link_config; + + /* FIXME: assert videomode supported */ + memcpy(&path->mode, mode, sizeof(struct mmp_mode)); + + mutex_lock(&path->access_ok); + + /* polarity of timing signals */ + tmp = readl_relaxed(ctrl_regs(path) + intf_ctrl(path->id)) & 0x1; + tmp |= mode->vsync_invert ? 0 : 0x8; + tmp |= mode->hsync_invert ? 0 : 0x4; + tmp |= link_config & CFG_DUMBMODE_MASK; + tmp |= CFG_DUMB_ENA(1); + writel_relaxed(tmp, ctrl_regs(path) + intf_ctrl(path->id)); + + writel_relaxed((mode->yres << 16) | mode->xres, ®s->screen_active); + writel_relaxed((mode->left_margin << 16) | mode->right_margin, + ®s->screen_h_porch); + writel_relaxed((mode->upper_margin << 16) | mode->lower_margin, + ®s->screen_v_porch); + total_x = mode->xres + mode->left_margin + mode->right_margin + + mode->hsync_len; + total_y = mode->yres + mode->upper_margin + mode->lower_margin + + mode->vsync_len; + writel_relaxed((total_y << 16) | total_x, ®s->screen_size); + + /* vsync ctrl */ + if (path->output_type == PATH_OUT_DSI) + vsync_ctrl = 0x01330133; + else + vsync_ctrl = ((mode->xres + mode->right_margin) << 16) + | (mode->xres + mode->right_margin); + writel_relaxed(vsync_ctrl, ®s->vsync_ctrl); + + /* set pixclock div */ + sclk_src = clk_get_rate(path_to_ctrl(path)->clk); + sclk_div = sclk_src / mode->pixclock_freq; + if (sclk_div * mode->pixclock_freq < sclk_src) + sclk_div++; + + dev_info(path->dev, "%s sclk_src %d sclk_div 0x%x pclk %d\n", + __func__, sclk_src, sclk_div, mode->pixclock_freq); + + tmp = readl_relaxed(ctrl_regs(path) + LCD_SCLK(path)); + tmp &= ~CLK_INT_DIV_MASK; + tmp |= sclk_div; + writel_relaxed(tmp, ctrl_regs(path) + LCD_SCLK(path)); + + mutex_unlock(&path->access_ok); +} + +static struct mmp_overlay_ops mmphw_overlay_ops = { + .set_fetch = overlay_set_fetch, + .set_onoff = overlay_set_onoff, + .set_win = overlay_set_win, + .set_addr = overlay_set_addr, +}; + +static void ctrl_set_default(struct mmphw_ctrl *ctrl) +{ + u32 tmp, irq_mask; + + /* + * LCD Global control(LCD_TOP_CTRL) should be configed before + * any other LCD registers read/write, or there maybe issues. + */ + tmp = readl_relaxed(ctrl->reg_base + LCD_TOP_CTRL); + tmp |= 0xfff0; + writel_relaxed(tmp, ctrl->reg_base + LCD_TOP_CTRL); + + + /* disable all interrupts */ + irq_mask = path_imasks(0) | err_imask(0) | + path_imasks(1) | err_imask(1); + tmp = readl_relaxed(ctrl->reg_base + SPU_IRQ_ENA); + tmp &= ~irq_mask; + tmp |= irq_mask; + writel_relaxed(tmp, ctrl->reg_base + SPU_IRQ_ENA); +} + +static void path_set_default(struct mmp_path *path) +{ + struct lcd_regs *regs = path_regs(path); + u32 dma_ctrl1, mask, tmp, path_config; + + path_config = path_to_path_plat(path)->path_config; + + /* Configure IOPAD: should be parallel only */ + if (PATH_OUT_PARALLEL == path->output_type) { + mask = CFG_IOPADMODE_MASK | CFG_BURST_MASK | CFG_BOUNDARY_MASK; + tmp = readl_relaxed(ctrl_regs(path) + SPU_IOPAD_CONTROL); + tmp &= ~mask; + tmp |= path_config; + writel_relaxed(tmp, ctrl_regs(path) + SPU_IOPAD_CONTROL); + } + + /* Select path clock source */ + tmp = readl_relaxed(ctrl_regs(path) + LCD_SCLK(path)); + tmp &= ~SCLK_SRC_SEL_MASK; + tmp |= path_config; + writel_relaxed(tmp, ctrl_regs(path) + LCD_SCLK(path)); + + /* + * Configure default bits: vsync triggers DMA, + * power save enable, configure alpha registers to + * display 100% graphics, and set pixel command. + */ + dma_ctrl1 = 0x2032ff81; + + dma_ctrl1 |= CFG_VSYNC_INV_MASK; + writel_relaxed(dma_ctrl1, ctrl_regs(path) + dma_ctrl(1, path->id)); + + /* Configure default register values */ + writel_relaxed(0x00000000, ®s->blank_color); + writel_relaxed(0x00000000, ®s->g_1); + writel_relaxed(0x00000000, ®s->g_start); + + /* + * 1.enable multiple burst request in DMA AXI + * bus arbiter for faster read if not tv path; + * 2.enable horizontal smooth filter; + */ + if (PATH_PN == path->id) { + mask = CFG_GRA_HSMOOTH_MASK | CFG_DMA_HSMOOTH_MASK + | CFG_ARBFAST_ENA(1); + tmp = readl_relaxed(ctrl_regs(path) + dma_ctrl(0, path->id)); + tmp |= mask; + writel_relaxed(tmp, ctrl_regs(path) + dma_ctrl(0, path->id)); + } else if (PATH_TV == path->id) { + mask = CFG_GRA_HSMOOTH_MASK | CFG_DMA_HSMOOTH_MASK + | CFG_ARBFAST_ENA(1); + tmp = readl_relaxed(ctrl_regs(path) + dma_ctrl(0, path->id)); + tmp &= ~mask; + tmp |= CFG_GRA_HSMOOTH_MASK | CFG_DMA_HSMOOTH_MASK; + writel_relaxed(tmp, ctrl_regs(path) + dma_ctrl(0, path->id)); + } +} + +static int path_init(struct mmphw_path_plat *path_plat, + struct mmp_mach_path_config *config) +{ + struct mmphw_ctrl *ctrl = path_plat->ctrl; + struct mmp_path_info *path_info; + struct mmp_path *path = NULL; + + dev_info(ctrl->dev, "%s: %s\n", __func__, config->name); + + /* init driver data */ + path_info = kzalloc(sizeof(struct mmp_path_info), GFP_KERNEL); + if (!path_info) { + dev_err(ctrl->dev, "%s: unable to alloc path_info for %s\n", + __func__, config->name); + return 0; + } + path_info->name = config->name; + path_info->id = path_plat->id; + path_info->dev = ctrl->dev; + path_info->overlay_num = config->overlay_num; + path_info->overlay_ops = &mmphw_overlay_ops; + path_info->set_mode = path_set_mode; + path_info->plat_data = path_plat; + + /* create/register platform device */ + path = mmp_register_path(path_info); + if (!path) { + kfree(path_info); + return 0; + } + path_plat->path = path; + path_plat->path_config = config->path_config; + path_plat->link_config = config->link_config; + path_set_default(path); + + kfree(path_info); + return 1; +} + +static void path_deinit(struct mmphw_path_plat *path_plat) +{ + if (!path_plat) + return; + + if (path_plat->path) + mmp_unregister_path(path_plat->path); +} + +static int mmphw_probe(struct platform_device *pdev) +{ + struct mmp_mach_plat_info *mi; + struct resource *res; + int ret, i, size, irq; + struct mmphw_path_plat *path_plat; + struct mmphw_ctrl *ctrl = NULL; + + /* get resources from platform data */ + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (res == NULL) { + dev_err(&pdev->dev, "%s: no IO memory defined\n", __func__); + ret = -ENOENT; + goto failed; + } + + irq = platform_get_irq(pdev, 0); + if (irq < 0) { + dev_err(&pdev->dev, "%s: no IRQ defined\n", __func__); + ret = -ENOENT; + goto failed; + } + + /* get configs from platform data */ + mi = pdev->dev.platform_data; + if (mi == NULL || !mi->path_num || !mi->paths) { + dev_err(&pdev->dev, "%s: no platform data defined\n", __func__); + ret = -EINVAL; + goto failed; + } + + /* allocate */ + size = sizeof(struct mmphw_ctrl) + sizeof(struct mmphw_path_plat) * + mi->path_num; + ctrl = devm_kzalloc(&pdev->dev, size, GFP_KERNEL); + if (!ctrl) { + ret = -ENOMEM; + goto failed; + } + + ctrl->name = mi->name; + ctrl->path_num = mi->path_num; + ctrl->dev = &pdev->dev; + ctrl->irq = irq; + platform_set_drvdata(pdev, ctrl); + mutex_init(&ctrl->access_ok); + + /* map registers.*/ + if (!devm_request_mem_region(ctrl->dev, res->start, + resource_size(res), ctrl->name)) { + dev_err(ctrl->dev, + "can't request region for resource %pR\n", res); + ret = -EINVAL; + goto failed; + } + + ctrl->reg_base = devm_ioremap_nocache(ctrl->dev, + res->start, resource_size(res)); + if (ctrl->reg_base == NULL) { + dev_err(ctrl->dev, "%s: res %x - %x map failed\n", __func__, + res->start, res->end); + ret = -ENOMEM; + goto failed; + } + + /* request irq */ + ret = devm_request_irq(ctrl->dev, ctrl->irq, ctrl_handle_irq, + IRQF_SHARED, "lcd_controller", ctrl); + if (ret < 0) { + dev_err(ctrl->dev, "%s unable to request IRQ %d\n", + __func__, ctrl->irq); + ret = -ENXIO; + goto failed; + } + + /* get clock */ + ctrl->clk = devm_clk_get(ctrl->dev, mi->clk_name); + if (IS_ERR(ctrl->clk)) { + dev_err(ctrl->dev, "unable to get clk %s\n", mi->clk_name); + ret = -ENOENT; + goto failed_get_clk; + } + clk_prepare_enable(ctrl->clk); + + /* init global regs */ + ctrl_set_default(ctrl); + + /* init pathes from machine info and register them */ + for (i = 0; i < ctrl->path_num; i++) { + /* get from config and machine info */ + path_plat = &ctrl->path_plats[i]; + path_plat->id = i; + path_plat->ctrl = ctrl; + + /* path init */ + if (!path_init(path_plat, &mi->paths[i])) { + ret = -EINVAL; + goto failed_path_init; + } + } + +#ifdef CONFIG_MMP_DISP_SPI + ret = lcd_spi_register(ctrl); + if (ret < 0) + goto failed_path_init; +#endif + + dev_info(ctrl->dev, "device init done\n"); + + return 0; + +failed_path_init: + for (i = 0; i < ctrl->path_num; i++) { + path_plat = &ctrl->path_plats[i]; + path_deinit(path_plat); + } + + if (ctrl->clk) { + devm_clk_put(ctrl->dev, ctrl->clk); + clk_disable_unprepare(ctrl->clk); + } +failed_get_clk: + devm_free_irq(ctrl->dev, ctrl->irq, ctrl); +failed: + if (ctrl) { + if (ctrl->reg_base) + devm_iounmap(ctrl->dev, ctrl->reg_base); + devm_release_mem_region(ctrl->dev, res->start, + resource_size(res)); + devm_kfree(ctrl->dev, ctrl); + } + + platform_set_drvdata(pdev, NULL); + dev_err(&pdev->dev, "device init failed\n"); + + return ret; +} + +static struct platform_driver mmphw_driver = { + .driver = { + .name = "mmp-disp", + .owner = THIS_MODULE, + }, + .probe = mmphw_probe, +}; + +static int mmphw_init(void) +{ + return platform_driver_register(&mmphw_driver); +} +module_init(mmphw_init); + +MODULE_AUTHOR("Li Guoqing<ligq@marvell.com>"); +MODULE_DESCRIPTION("Framebuffer driver for mmp"); +MODULE_LICENSE("GPL"); diff --git a/drivers/video/mmp/hw/mmp_ctrl.h b/drivers/video/mmp/hw/mmp_ctrl.h new file mode 100644 index 000000000000..6408d8ef3abb --- /dev/null +++ b/drivers/video/mmp/hw/mmp_ctrl.h @@ -0,0 +1,1974 @@ +/* + * drivers/video/mmp/hw/mmp_ctrl.h + * + * + * Copyright (C) 2012 Marvell Technology Group Ltd. + * Authors: Guoqing Li <ligq@marvell.com> + * Lisa Du <cldu@marvell.com> + * Zhou Zhu <zzhu3@marvell.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + * + */ + +#ifndef _MMP_CTRL_H_ +#define _MMP_CTRL_H_ + +#include <video/mmp_disp.h> + +/* ------------< LCD register >------------ */ +struct lcd_regs { +/* TV patch register for MMP2 */ +/* 32 bit TV Video Frame0 Y Starting Address */ +#define LCD_TVD_START_ADDR_Y0 (0x0000) +/* 32 bit TV Video Frame0 U Starting Address */ +#define LCD_TVD_START_ADDR_U0 (0x0004) +/* 32 bit TV Video Frame0 V Starting Address */ +#define LCD_TVD_START_ADDR_V0 (0x0008) +/* 32 bit TV Video Frame0 Command Starting Address */ +#define LCD_TVD_START_ADDR_C0 (0x000C) +/* 32 bit TV Video Frame1 Y Starting Address Register*/ +#define LCD_TVD_START_ADDR_Y1 (0x0010) +/* 32 bit TV Video Frame1 U Starting Address Register*/ +#define LCD_TVD_START_ADDR_U1 (0x0014) +/* 32 bit TV Video Frame1 V Starting Address Register*/ +#define LCD_TVD_START_ADDR_V1 (0x0018) +/* 32 bit TV Video Frame1 Command Starting Address Register*/ +#define LCD_TVD_START_ADDR_C1 (0x001C) +/* 32 bit TV Video Y andC Line Length(Pitch)Register*/ +#define LCD_TVD_PITCH_YC (0x0020) +/* 32 bit TV Video U andV Line Length(Pitch)Register*/ +#define LCD_TVD_PITCH_UV (0x0024) +/* 32 bit TV Video Starting Point on Screen Register*/ +#define LCD_TVD_OVSA_HPXL_VLN (0x0028) +/* 32 bit TV Video Source Size Register*/ +#define LCD_TVD_HPXL_VLN (0x002C) +/* 32 bit TV Video Destination Size (After Zooming)Register*/ +#define LCD_TVDZM_HPXL_VLN (0x0030) + u32 v_y0; + u32 v_u0; + u32 v_v0; + u32 v_c0; + u32 v_y1; + u32 v_u1; + u32 v_v1; + u32 v_c1; + u32 v_pitch_yc; /* Video Y and C Line Length (Pitch) */ + u32 v_pitch_uv; /* Video U and V Line Length (Pitch) */ + u32 v_start; /* Video Starting Point on Screen */ + u32 v_size; /* Video Source Size */ + u32 v_size_z; /* Video Destination Size (After Zooming) */ + +/* 32 bit TV Graphic Frame 0 Starting Address Register*/ +#define LCD_TVG_START_ADDR0 (0x0034) +/* 32 bit TV Graphic Frame 1 Starting Address Register*/ +#define LCD_TVG_START_ADDR1 (0x0038) +/* 32 bit TV Graphic Line Length(Pitch)Register*/ +#define LCD_TVG_PITCH (0x003C) +/* 32 bit TV Graphic Starting Point on Screen Register*/ +#define LCD_TVG_OVSA_HPXL_VLN (0x0040) +/* 32 bit TV Graphic Source Size Register*/ +#define LCD_TVG_HPXL_VLN (0x0044) +/* 32 bit TV Graphic Destination size (after Zooming)Register*/ +#define LCD_TVGZM_HPXL_VLN (0x0048) + u32 g_0; /* Graphic Frame 0/1 Starting Address */ + u32 g_1; + u32 g_pitch; /* Graphic Line Length (Pitch) */ + u32 g_start; /* Graphic Starting Point on Screen */ + u32 g_size; /* Graphic Source Size */ + u32 g_size_z; /* Graphic Destination Size (After Zooming) */ + +/* 32 bit TV Hardware Cursor Starting Point on screen Register*/ +#define LCD_TVC_OVSA_HPXL_VLN (0x004C) +/* 32 bit TV Hardware Cursor Size Register */ +#define LCD_TVC_HPXL_VLN (0x0050) + u32 hc_start; /* Hardware Cursor */ + u32 hc_size; /* Hardware Cursor */ + +/* 32 bit TV Total Screen Size Register*/ +#define LCD_TV_V_H_TOTAL (0x0054) +/* 32 bit TV Screen Active Size Register*/ +#define LCD_TV_V_H_ACTIVE (0x0058) +/* 32 bit TV Screen Horizontal Porch Register*/ +#define LCD_TV_H_PORCH (0x005C) +/* 32 bit TV Screen Vertical Porch Register*/ +#define LCD_TV_V_PORCH (0x0060) + u32 screen_size; /* Screen Total Size */ + u32 screen_active; /* Screen Active Size */ + u32 screen_h_porch; /* Screen Horizontal Porch */ + u32 screen_v_porch; /* Screen Vertical Porch */ + +/* 32 bit TV Screen Blank Color Register*/ +#define LCD_TV_BLANKCOLOR (0x0064) +/* 32 bit TV Hardware Cursor Color1 Register*/ +#define LCD_TV_ALPHA_COLOR1 (0x0068) +/* 32 bit TV Hardware Cursor Color2 Register*/ +#define LCD_TV_ALPHA_COLOR2 (0x006C) + u32 blank_color; /* Screen Blank Color */ + u32 hc_Alpha_color1; /* Hardware Cursor Color1 */ + u32 hc_Alpha_color2; /* Hardware Cursor Color2 */ + +/* 32 bit TV Video Y Color Key Control*/ +#define LCD_TV_COLORKEY_Y (0x0070) +/* 32 bit TV Video U Color Key Control*/ +#define LCD_TV_COLORKEY_U (0x0074) +/* 32 bit TV Video V Color Key Control*/ +#define LCD_TV_COLORKEY_V (0x0078) + u32 v_colorkey_y; /* Video Y Color Key Control */ + u32 v_colorkey_u; /* Video U Color Key Control */ + u32 v_colorkey_v; /* Video V Color Key Control */ + +/* 32 bit TV VSYNC PulsePixel Edge Control Register*/ +#define LCD_TV_SEPXLCNT (0x007C) + u32 vsync_ctrl; /* VSYNC PulsePixel Edge Control */ +}; + +#define intf_ctrl(id) ((id) ? (((id) & 1) ? LCD_TVIF_CTRL : \ + LCD_DUMB2_CTRL) : LCD_SPU_DUMB_CTRL) +#define dma_ctrl0(id) ((id) ? (((id) & 1) ? LCD_TV_CTRL0 : \ + LCD_PN2_CTRL0) : LCD_SPU_DMA_CTRL0) +#define dma_ctrl1(id) ((id) ? (((id) & 1) ? LCD_TV_CTRL1 : \ + LCD_PN2_CTRL1) : LCD_SPU_DMA_CTRL1) +#define dma_ctrl(ctrl1, id) (ctrl1 ? dma_ctrl1(id) : dma_ctrl0(id)) + +/* 32 bit TV Path DMA Control 0*/ +#define LCD_TV_CTRL0 (0x0080) +/* 32 bit TV Path DMA Control 1*/ +#define LCD_TV_CTRL1 (0x0084) +/* 32 bit TV Path Video Contrast*/ +#define LCD_TV_CONTRAST (0x0088) +/* 32 bit TV Path Video Saturation*/ +#define LCD_TV_SATURATION (0x008C) +/* 32 bit TV Path Video Hue Adjust*/ +#define LCD_TV_CBSH_HUE (0x0090) +/* 32 bit TV Path TVIF Control Register */ +#define LCD_TVIF_CTRL (0x0094) +#define TV_VBLNK_VALID_EN (1 << 12) + +/* 32 bit TV Path I/O Pad Control*/ +#define LCD_TVIOPAD_CTRL (0x0098) +/* 32 bit TV Path Cloc Divider */ +#define LCD_TCLK_DIV (0x009C) + +#define LCD_SCLK(path) ((PATH_PN == path->id) ? LCD_CFG_SCLK_DIV :\ + ((PATH_TV == path->id) ? LCD_TCLK_DIV : LCD_PN2_SCLK_DIV)) + +/* dither configure */ +#ifdef CONFIG_CPU_PXA988 +#define LCD_DITHER_CTRL (0x01EC) +#else +#define LCD_DITHER_CTRL (0x00A0) +#endif + +#define DITHER_TBL_INDEX_SEL(s) ((s) << 16) +#define DITHER_MODE2(m) ((m) << 12) +#define DITHER_MODE2_SHIFT (12) +#define DITHER_4X8_EN2 (1 << 9) +#define DITHER_4X8_EN2_SHIFT (9) +#define DITHER_EN2 (1 << 8) +#define DITHER_MODE1(m) ((m) << 4) +#define DITHER_MODE1_SHIFT (4) +#define DITHER_4X8_EN1 (1 << 1) +#define DITHER_4X8_EN1_SHIFT (1) +#define DITHER_EN1 (1) + +/* dither table data was fixed by video bpp of input and output*/ +#ifdef CONFIG_CPU_PXA988 +#define DITHER_TB_4X4_INDEX0 (0x6e4ca280) +#define DITHER_TB_4X4_INDEX1 (0x5d7f91b3) +#define DITHER_TB_4X8_INDEX0 (0xb391a280) +#define DITHER_TB_4X8_INDEX1 (0x7f5d6e4c) +#define DITHER_TB_4X8_INDEX2 (0x80a291b3) +#define DITHER_TB_4X8_INDEX3 (0x4c6e5d7f) +#define LCD_DITHER_TBL_DATA (0x01F0) +#else +#define DITHER_TB_4X4_INDEX0 (0x3b19f7d5) +#define DITHER_TB_4X4_INDEX1 (0x082ac4e6) +#define DITHER_TB_4X8_INDEX0 (0xf7d508e6) +#define DITHER_TB_4X8_INDEX1 (0x3b194c2a) +#define DITHER_TB_4X8_INDEX2 (0xc4e6d5f7) +#define DITHER_TB_4X8_INDEX3 (0x082a193b) +#define LCD_DITHER_TBL_DATA (0x00A4) +#endif + +/* Video Frame 0&1 start address registers */ +#define LCD_SPU_DMA_START_ADDR_Y0 0x00C0 +#define LCD_SPU_DMA_START_ADDR_U0 0x00C4 +#define LCD_SPU_DMA_START_ADDR_V0 0x00C8 +#define LCD_CFG_DMA_START_ADDR_0 0x00CC /* Cmd address */ +#define LCD_SPU_DMA_START_ADDR_Y1 0x00D0 +#define LCD_SPU_DMA_START_ADDR_U1 0x00D4 +#define LCD_SPU_DMA_START_ADDR_V1 0x00D8 +#define LCD_CFG_DMA_START_ADDR_1 0x00DC /* Cmd address */ + +/* YC & UV Pitch */ +#define LCD_SPU_DMA_PITCH_YC 0x00E0 +#define SPU_DMA_PITCH_C(c) ((c)<<16) +#define SPU_DMA_PITCH_Y(y) (y) +#define LCD_SPU_DMA_PITCH_UV 0x00E4 +#define SPU_DMA_PITCH_V(v) ((v)<<16) +#define SPU_DMA_PITCH_U(u) (u) + +/* Video Starting Point on Screen Register */ +#define LCD_SPUT_DMA_OVSA_HPXL_VLN 0x00E8 +#define CFG_DMA_OVSA_VLN(y) ((y)<<16) /* 0~0xfff */ +#define CFG_DMA_OVSA_HPXL(x) (x) /* 0~0xfff */ + +/* Video Size Register */ +#define LCD_SPU_DMA_HPXL_VLN 0x00EC +#define CFG_DMA_VLN(y) ((y)<<16) +#define CFG_DMA_HPXL(x) (x) + +/* Video Size After zooming Register */ +#define LCD_SPU_DZM_HPXL_VLN 0x00F0 +#define CFG_DZM_VLN(y) ((y)<<16) +#define CFG_DZM_HPXL(x) (x) + +/* Graphic Frame 0&1 Starting Address Register */ +#define LCD_CFG_GRA_START_ADDR0 0x00F4 +#define LCD_CFG_GRA_START_ADDR1 0x00F8 + +/* Graphic Frame Pitch */ +#define LCD_CFG_GRA_PITCH 0x00FC + +/* Graphic Starting Point on Screen Register */ +#define LCD_SPU_GRA_OVSA_HPXL_VLN 0x0100 +#define CFG_GRA_OVSA_VLN(y) ((y)<<16) +#define CFG_GRA_OVSA_HPXL(x) (x) + +/* Graphic Size Register */ +#define LCD_SPU_GRA_HPXL_VLN 0x0104 +#define CFG_GRA_VLN(y) ((y)<<16) +#define CFG_GRA_HPXL(x) (x) + +/* Graphic Size after Zooming Register */ +#define LCD_SPU_GZM_HPXL_VLN 0x0108 +#define CFG_GZM_VLN(y) ((y)<<16) +#define CFG_GZM_HPXL(x) (x) + +/* HW Cursor Starting Point on Screen Register */ +#define LCD_SPU_HWC_OVSA_HPXL_VLN 0x010C +#define CFG_HWC_OVSA_VLN(y) ((y)<<16) +#define CFG_HWC_OVSA_HPXL(x) (x) + +/* HW Cursor Size */ +#define LCD_SPU_HWC_HPXL_VLN 0x0110 +#define CFG_HWC_VLN(y) ((y)<<16) +#define CFG_HWC_HPXL(x) (x) + +/* Total Screen Size Register */ +#define LCD_SPUT_V_H_TOTAL 0x0114 +#define CFG_V_TOTAL(y) ((y)<<16) +#define CFG_H_TOTAL(x) (x) + +/* Total Screen Active Size Register */ +#define LCD_SPU_V_H_ACTIVE 0x0118 +#define CFG_V_ACTIVE(y) ((y)<<16) +#define CFG_H_ACTIVE(x) (x) + +/* Screen H&V Porch Register */ +#define LCD_SPU_H_PORCH 0x011C +#define CFG_H_BACK_PORCH(b) ((b)<<16) +#define CFG_H_FRONT_PORCH(f) (f) +#define LCD_SPU_V_PORCH 0x0120 +#define CFG_V_BACK_PORCH(b) ((b)<<16) +#define CFG_V_FRONT_PORCH(f) (f) + +/* Screen Blank Color Register */ +#define LCD_SPU_BLANKCOLOR 0x0124 +#define CFG_BLANKCOLOR_MASK 0x00FFFFFF +#define CFG_BLANKCOLOR_R_MASK 0x000000FF +#define CFG_BLANKCOLOR_G_MASK 0x0000FF00 +#define CFG_BLANKCOLOR_B_MASK 0x00FF0000 + +/* HW Cursor Color 1&2 Register */ +#define LCD_SPU_ALPHA_COLOR1 0x0128 +#define CFG_HWC_COLOR1 0x00FFFFFF +#define CFG_HWC_COLOR1_R(red) ((red)<<16) +#define CFG_HWC_COLOR1_G(green) ((green)<<8) +#define CFG_HWC_COLOR1_B(blue) (blue) +#define CFG_HWC_COLOR1_R_MASK 0x000000FF +#define CFG_HWC_COLOR1_G_MASK 0x0000FF00 +#define CFG_HWC_COLOR1_B_MASK 0x00FF0000 +#define LCD_SPU_ALPHA_COLOR2 0x012C +#define CFG_HWC_COLOR2 0x00FFFFFF +#define CFG_HWC_COLOR2_R_MASK 0x000000FF +#define CFG_HWC_COLOR2_G_MASK 0x0000FF00 +#define CFG_HWC_COLOR2_B_MASK 0x00FF0000 + +/* Video YUV Color Key Control */ +#define LCD_SPU_COLORKEY_Y 0x0130 +#define CFG_CKEY_Y2(y2) ((y2)<<24) +#define CFG_CKEY_Y2_MASK 0xFF000000 +#define CFG_CKEY_Y1(y1) ((y1)<<16) +#define CFG_CKEY_Y1_MASK 0x00FF0000 +#define CFG_CKEY_Y(y) ((y)<<8) +#define CFG_CKEY_Y_MASK 0x0000FF00 +#define CFG_ALPHA_Y(y) (y) +#define CFG_ALPHA_Y_MASK 0x000000FF +#define LCD_SPU_COLORKEY_U 0x0134 +#define CFG_CKEY_U2(u2) ((u2)<<24) +#define CFG_CKEY_U2_MASK 0xFF000000 +#define CFG_CKEY_U1(u1) ((u1)<<16) +#define CFG_CKEY_U1_MASK 0x00FF0000 +#define CFG_CKEY_U(u) ((u)<<8) +#define CFG_CKEY_U_MASK 0x0000FF00 +#define CFG_ALPHA_U(u) (u) +#define CFG_ALPHA_U_MASK 0x000000FF +#define LCD_SPU_COLORKEY_V 0x0138 +#define CFG_CKEY_V2(v2) ((v2)<<24) +#define CFG_CKEY_V2_MASK 0xFF000000 +#define CFG_CKEY_V1(v1) ((v1)<<16) +#define CFG_CKEY_V1_MASK 0x00FF0000 +#define CFG_CKEY_V(v) ((v)<<8) +#define CFG_CKEY_V_MASK 0x0000FF00 +#define CFG_ALPHA_V(v) (v) +#define CFG_ALPHA_V_MASK 0x000000FF + +/* Graphics/Video DMA color key enable bits in LCD_TV_CTRL1 */ +#define CFG_CKEY_GRA 0x2 +#define CFG_CKEY_DMA 0x1 + +/* Interlace mode enable bits in LCD_TV_CTRL1 */ +#define CFG_TV_INTERLACE_EN (1 << 22) +#define CFG_TV_NIB (1 << 0) + +#define LCD_PN_SEPXLCNT 0x013c /* MMP2 */ + +/* SPI Read Data Register */ +#define LCD_SPU_SPI_RXDATA 0x0140 + +/* Smart Panel Read Data Register */ +#define LCD_SPU_ISA_RSDATA 0x0144 +#define ISA_RXDATA_16BIT_1_DATA_MASK 0x000000FF +#define ISA_RXDATA_16BIT_2_DATA_MASK 0x0000FF00 +#define ISA_RXDATA_16BIT_3_DATA_MASK 0x00FF0000 +#define ISA_RXDATA_16BIT_4_DATA_MASK 0xFF000000 +#define ISA_RXDATA_32BIT_1_DATA_MASK 0x00FFFFFF + +#define LCD_SPU_DBG_ISA (0x0148) /* TTC */ +#define LCD_SPU_DMAVLD_YC (0x014C) +#define LCD_SPU_DMAVLD_UV (0x0150) +#define LCD_SPU_DMAVLD_UVSPU_GRAVLD (0x0154) + +#define LCD_READ_IOPAD (0x0148) /* MMP2*/ +#define LCD_DMAVLD_YC (0x014C) +#define LCD_DMAVLD_UV (0x0150) +#define LCD_TVGGRAVLD_HLEN (0x0154) + +/* HWC SRAM Read Data Register */ +#define LCD_SPU_HWC_RDDAT 0x0158 + +/* Gamma Table SRAM Read Data Register */ +#define LCD_SPU_GAMMA_RDDAT 0x015c +#define CFG_GAMMA_RDDAT_MASK 0x000000FF + +/* Palette Table SRAM Read Data Register */ +#define LCD_SPU_PALETTE_RDDAT 0x0160 +#define CFG_PALETTE_RDDAT_MASK 0x00FFFFFF + +#define LCD_SPU_DBG_DMATOP (0x0164) /* TTC */ +#define LCD_SPU_DBG_GRATOP (0x0168) +#define LCD_SPU_DBG_TXCTRL (0x016C) +#define LCD_SPU_DBG_SLVTOP (0x0170) +#define LCD_SPU_DBG_MUXTOP (0x0174) + +#define LCD_SLV_DBG (0x0164) /* MMP2 */ +#define LCD_TVDVLD_YC (0x0168) +#define LCD_TVDVLD_UV (0x016C) +#define LCD_TVC_RDDAT (0x0170) +#define LCD_TV_GAMMA_RDDAT (0x0174) + +/* I/O Pads Input Read Only Register */ +#define LCD_SPU_IOPAD_IN 0x0178 +#define CFG_IOPAD_IN_MASK 0x0FFFFFFF + +#define LCD_TV_PALETTE_RDDAT (0x0178) /* MMP2 */ + +/* Reserved Read Only Registers */ +#define LCD_CFG_RDREG5F 0x017C +#define IRE_FRAME_CNT_MASK 0x000000C0 +#define IPE_FRAME_CNT_MASK 0x00000030 +#define GRA_FRAME_CNT_MASK 0x0000000C /* Graphic */ +#define DMA_FRAME_CNT_MASK 0x00000003 /* Video */ + +#define LCD_FRAME_CNT (0x017C) /* MMP2 */ + +/* SPI Control Register. */ +#define LCD_SPU_SPI_CTRL 0x0180 +#define CFG_SCLKCNT(div) ((div)<<24) /* 0xFF~0x2 */ +#define CFG_SCLKCNT_MASK 0xFF000000 +#define CFG_RXBITS(rx) (((rx) - 1)<<16) /* 0x1F~0x1 */ +#define CFG_RXBITS_MASK 0x00FF0000 +#define CFG_TXBITS(tx) (((tx) - 1)<<8) /* 0x1F~0x1 */ +#define CFG_TXBITS_MASK 0x0000FF00 +#define CFG_CLKINV(clk) ((clk)<<7) +#define CFG_CLKINV_MASK 0x00000080 +#define CFG_KEEPXFER(transfer) ((transfer)<<6) +#define CFG_KEEPXFER_MASK 0x00000040 +#define CFG_RXBITSTO0(rx) ((rx)<<5) +#define CFG_RXBITSTO0_MASK 0x00000020 +#define CFG_TXBITSTO0(tx) ((tx)<<4) +#define CFG_TXBITSTO0_MASK 0x00000010 +#define CFG_SPI_ENA(spi) ((spi)<<3) +#define CFG_SPI_ENA_MASK 0x00000008 +#define CFG_SPI_SEL(spi) ((spi)<<2) +#define CFG_SPI_SEL_MASK 0x00000004 +#define CFG_SPI_3W4WB(wire) ((wire)<<1) +#define CFG_SPI_3W4WB_MASK 0x00000002 +#define CFG_SPI_START(start) (start) +#define CFG_SPI_START_MASK 0x00000001 + +/* SPI Tx Data Register */ +#define LCD_SPU_SPI_TXDATA 0x0184 + +/* + 1. Smart Pannel 8-bit Bus Control Register. + 2. AHB Slave Path Data Port Register +*/ +#define LCD_SPU_SMPN_CTRL 0x0188 + +/* DMA Control 0 Register */ +#define LCD_SPU_DMA_CTRL0 0x0190 +#define CFG_NOBLENDING(nb) ((nb)<<31) +#define CFG_NOBLENDING_MASK 0x80000000 +#define CFG_GAMMA_ENA(gn) ((gn)<<30) +#define CFG_GAMMA_ENA_MASK 0x40000000 +#define CFG_CBSH_ENA(cn) ((cn)<<29) +#define CFG_CBSH_ENA_MASK 0x20000000 +#define CFG_PALETTE_ENA(pn) ((pn)<<28) +#define CFG_PALETTE_ENA_MASK 0x10000000 +#define CFG_ARBFAST_ENA(an) ((an)<<27) +#define CFG_ARBFAST_ENA_MASK 0x08000000 +#define CFG_HWC_1BITMOD(mode) ((mode)<<26) +#define CFG_HWC_1BITMOD_MASK 0x04000000 +#define CFG_HWC_1BITENA(mn) ((mn)<<25) +#define CFG_HWC_1BITENA_MASK 0x02000000 +#define CFG_HWC_ENA(cn) ((cn)<<24) +#define CFG_HWC_ENA_MASK 0x01000000 +#define CFG_DMAFORMAT(dmaformat) ((dmaformat)<<20) +#define CFG_DMAFORMAT_MASK 0x00F00000 +#define CFG_GRAFORMAT(graformat) ((graformat)<<16) +#define CFG_GRAFORMAT_MASK 0x000F0000 +/* for graphic part */ +#define CFG_GRA_FTOGGLE(toggle) ((toggle)<<15) +#define CFG_GRA_FTOGGLE_MASK 0x00008000 +#define CFG_GRA_HSMOOTH(smooth) ((smooth)<<14) +#define CFG_GRA_HSMOOTH_MASK 0x00004000 +#define CFG_GRA_TSTMODE(test) ((test)<<13) +#define CFG_GRA_TSTMODE_MASK 0x00002000 +#define CFG_GRA_SWAPRB(swap) ((swap)<<12) +#define CFG_GRA_SWAPRB_MASK 0x00001000 +#define CFG_GRA_SWAPUV(swap) ((swap)<<11) +#define CFG_GRA_SWAPUV_MASK 0x00000800 +#define CFG_GRA_SWAPYU(swap) ((swap)<<10) +#define CFG_GRA_SWAPYU_MASK 0x00000400 +#define CFG_GRA_SWAP_MASK 0x00001C00 +#define CFG_YUV2RGB_GRA(cvrt) ((cvrt)<<9) +#define CFG_YUV2RGB_GRA_MASK 0x00000200 +#define CFG_GRA_ENA(gra) ((gra)<<8) +#define CFG_GRA_ENA_MASK 0x00000100 +#define dma0_gfx_masks (CFG_GRAFORMAT_MASK | CFG_GRA_FTOGGLE_MASK | \ + CFG_GRA_HSMOOTH_MASK | CFG_GRA_TSTMODE_MASK | CFG_GRA_SWAP_MASK | \ + CFG_YUV2RGB_GRA_MASK | CFG_GRA_ENA_MASK) +/* for video part */ +#define CFG_DMA_FTOGGLE(toggle) ((toggle)<<7) +#define CFG_DMA_FTOGGLE_MASK 0x00000080 +#define CFG_DMA_HSMOOTH(smooth) ((smooth)<<6) +#define CFG_DMA_HSMOOTH_MASK 0x00000040 +#define CFG_DMA_TSTMODE(test) ((test)<<5) +#define CFG_DMA_TSTMODE_MASK 0x00000020 +#define CFG_DMA_SWAPRB(swap) ((swap)<<4) +#define CFG_DMA_SWAPRB_MASK 0x00000010 +#define CFG_DMA_SWAPUV(swap) ((swap)<<3) +#define CFG_DMA_SWAPUV_MASK 0x00000008 +#define CFG_DMA_SWAPYU(swap) ((swap)<<2) +#define CFG_DMA_SWAPYU_MASK 0x00000004 +#define CFG_DMA_SWAP_MASK 0x0000001C +#define CFG_YUV2RGB_DMA(cvrt) ((cvrt)<<1) +#define CFG_YUV2RGB_DMA_MASK 0x00000002 +#define CFG_DMA_ENA(video) (video) +#define CFG_DMA_ENA_MASK 0x00000001 +#define dma0_vid_masks (CFG_DMAFORMAT_MASK | CFG_DMA_FTOGGLE_MASK | \ + CFG_DMA_HSMOOTH_MASK | CFG_DMA_TSTMODE_MASK | CFG_DMA_SWAP_MASK | \ + CFG_YUV2RGB_DMA_MASK | CFG_DMA_ENA_MASK) +#define dma_palette(val) ((val ? 1 : 0) << 28) +#define dma_fmt(vid, val) ((val & 0xf) << ((vid) ? 20 : 16)) +#define dma_swaprb(vid, val) ((val ? 1 : 0) << ((vid) ? 4 : 12)) +#define dma_swapuv(vid, val) ((val ? 1 : 0) << ((vid) ? 3 : 11)) +#define dma_swapyuv(vid, val) ((val ? 1 : 0) << ((vid) ? 2 : 10)) +#define dma_csc(vid, val) ((val ? 1 : 0) << ((vid) ? 1 : 9)) +#define dma_hsmooth(vid, val) ((val ? 1 : 0) << ((vid) ? 6 : 14)) +#define dma_mask(vid) (dma_palette(1) | dma_fmt(vid, 0xf) | dma_csc(vid, 1) \ + | dma_swaprb(vid, 1) | dma_swapuv(vid, 1) | dma_swapyuv(vid, 1)) + +/* DMA Control 1 Register */ +#define LCD_SPU_DMA_CTRL1 0x0194 +#define CFG_FRAME_TRIG(trig) ((trig)<<31) +#define CFG_FRAME_TRIG_MASK 0x80000000 +#define CFG_VSYNC_TRIG(trig) ((trig)<<28) +#define CFG_VSYNC_TRIG_MASK 0x70000000 +#define CFG_VSYNC_INV(inv) ((inv)<<27) +#define CFG_VSYNC_INV_MASK 0x08000000 +#define CFG_COLOR_KEY_MODE(cmode) ((cmode)<<24) +#define CFG_COLOR_KEY_MASK 0x07000000 +#define CFG_CARRY(carry) ((carry)<<23) +#define CFG_CARRY_MASK 0x00800000 +#define CFG_LNBUF_ENA(lnbuf) ((lnbuf)<<22) +#define CFG_LNBUF_ENA_MASK 0x00400000 +#define CFG_GATED_ENA(gated) ((gated)<<21) +#define CFG_GATED_ENA_MASK 0x00200000 +#define CFG_PWRDN_ENA(power) ((power)<<20) +#define CFG_PWRDN_ENA_MASK 0x00100000 +#define CFG_DSCALE(dscale) ((dscale)<<18) +#define CFG_DSCALE_MASK 0x000C0000 +#define CFG_ALPHA_MODE(amode) ((amode)<<16) +#define CFG_ALPHA_MODE_MASK 0x00030000 +#define CFG_ALPHA(alpha) ((alpha)<<8) +#define CFG_ALPHA_MASK 0x0000FF00 +#define CFG_PXLCMD(pxlcmd) (pxlcmd) +#define CFG_PXLCMD_MASK 0x000000FF + +/* SRAM Control Register */ +#define LCD_SPU_SRAM_CTRL 0x0198 +#define CFG_SRAM_INIT_WR_RD(mode) ((mode)<<14) +#define CFG_SRAM_INIT_WR_RD_MASK 0x0000C000 +#define CFG_SRAM_ADDR_LCDID(id) ((id)<<8) +#define CFG_SRAM_ADDR_LCDID_MASK 0x00000F00 +#define CFG_SRAM_ADDR(addr) (addr) +#define CFG_SRAM_ADDR_MASK 0x000000FF + +/* SRAM Write Data Register */ +#define LCD_SPU_SRAM_WRDAT 0x019C + +/* SRAM RTC/WTC Control Register */ +#define LCD_SPU_SRAM_PARA0 0x01A0 + +/* SRAM Power Down Control Register */ +#define LCD_SPU_SRAM_PARA1 0x01A4 +#define CFG_CSB_256x32(hwc) ((hwc)<<15) /* HWC */ +#define CFG_CSB_256x32_MASK 0x00008000 +#define CFG_CSB_256x24(palette) ((palette)<<14) /* Palette */ +#define CFG_CSB_256x24_MASK 0x00004000 +#define CFG_CSB_256x8(gamma) ((gamma)<<13) /* Gamma */ +#define CFG_CSB_256x8_MASK 0x00002000 +#define CFG_PDWN256x32(pdwn) ((pdwn)<<7) /* HWC */ +#define CFG_PDWN256x32_MASK 0x00000080 +#define CFG_PDWN256x24(pdwn) ((pdwn)<<6) /* Palette */ +#define CFG_PDWN256x24_MASK 0x00000040 +#define CFG_PDWN256x8(pdwn) ((pdwn)<<5) /* Gamma */ +#define CFG_PDWN256x8_MASK 0x00000020 +#define CFG_PDWN32x32(pdwn) ((pdwn)<<3) +#define CFG_PDWN32x32_MASK 0x00000008 +#define CFG_PDWN16x66(pdwn) ((pdwn)<<2) +#define CFG_PDWN16x66_MASK 0x00000004 +#define CFG_PDWN32x66(pdwn) ((pdwn)<<1) +#define CFG_PDWN32x66_MASK 0x00000002 +#define CFG_PDWN64x66(pdwn) (pdwn) +#define CFG_PDWN64x66_MASK 0x00000001 + +/* Smart or Dumb Panel Clock Divider */ +#define LCD_CFG_SCLK_DIV 0x01A8 +#define SCLK_SRC_SEL(src) ((src)<<31) +#define SCLK_SRC_SEL_MASK 0x80000000 +#define SCLK_DISABLE (1<<28) +#define CLK_FRACDIV(frac) ((frac)<<16) +#define CLK_FRACDIV_MASK 0x0FFF0000 +#define DSI1_BITCLK_DIV(div) (div<<8) +#define DSI1_BITCLK_DIV_MASK 0x00000F00 +#define CLK_INT_DIV(div) (div) +#define CLK_INT_DIV_MASK 0x000000FF + +/* Video Contrast Register */ +#define LCD_SPU_CONTRAST 0x01AC +#define CFG_BRIGHTNESS(bright) ((bright)<<16) +#define CFG_BRIGHTNESS_MASK 0xFFFF0000 +#define CFG_CONTRAST(contrast) (contrast) +#define CFG_CONTRAST_MASK 0x0000FFFF + +/* Video Saturation Register */ +#define LCD_SPU_SATURATION 0x01B0 +#define CFG_C_MULTS(mult) ((mult)<<16) +#define CFG_C_MULTS_MASK 0xFFFF0000 +#define CFG_SATURATION(sat) (sat) +#define CFG_SATURATION_MASK 0x0000FFFF + +/* Video Hue Adjust Register */ +#define LCD_SPU_CBSH_HUE 0x01B4 +#define CFG_SIN0(sin0) ((sin0)<<16) +#define CFG_SIN0_MASK 0xFFFF0000 +#define CFG_COS0(con0) (con0) +#define CFG_COS0_MASK 0x0000FFFF + +/* Dump LCD Panel Control Register */ +#define LCD_SPU_DUMB_CTRL 0x01B8 +#define CFG_DUMBMODE(mode) ((mode)<<28) +#define CFG_DUMBMODE_MASK 0xF0000000 +#define CFG_LCDGPIO_O(data) ((data)<<20) +#define CFG_LCDGPIO_O_MASK 0x0FF00000 +#define CFG_LCDGPIO_ENA(gpio) ((gpio)<<12) +#define CFG_LCDGPIO_ENA_MASK 0x000FF000 +#define CFG_BIAS_OUT(bias) ((bias)<<8) +#define CFG_BIAS_OUT_MASK 0x00000100 +#define CFG_REVERSE_RGB(RGB) ((RGB)<<7) +#define CFG_REVERSE_RGB_MASK 0x00000080 +#define CFG_INV_COMPBLANK(blank) ((blank)<<6) +#define CFG_INV_COMPBLANK_MASK 0x00000040 +#define CFG_INV_COMPSYNC(sync) ((sync)<<5) +#define CFG_INV_COMPSYNC_MASK 0x00000020 +#define CFG_INV_HENA(hena) ((hena)<<4) +#define CFG_INV_HENA_MASK 0x00000010 +#define CFG_INV_VSYNC(vsync) ((vsync)<<3) +#define CFG_INV_VSYNC_MASK 0x00000008 +#define CFG_INV_HSYNC(hsync) ((hsync)<<2) +#define CFG_INV_HSYNC_MASK 0x00000004 +#define CFG_INV_PCLK(pclk) ((pclk)<<1) +#define CFG_INV_PCLK_MASK 0x00000002 +#define CFG_DUMB_ENA(dumb) (dumb) +#define CFG_DUMB_ENA_MASK 0x00000001 + +/* LCD I/O Pads Control Register */ +#define SPU_IOPAD_CONTROL 0x01BC +#define CFG_GRA_VM_ENA(vm) ((vm)<<15) +#define CFG_GRA_VM_ENA_MASK 0x00008000 +#define CFG_DMA_VM_ENA(vm) ((vm)<<13) +#define CFG_DMA_VM_ENA_MASK 0x00002000 +#define CFG_CMD_VM_ENA(vm) ((vm)<<12) +#define CFG_CMD_VM_ENA_MASK 0x00001000 +#define CFG_CSC(csc) ((csc)<<8) +#define CFG_CSC_MASK 0x00000300 +#define CFG_BOUNDARY(size) ((size)<<5) +#define CFG_BOUNDARY_MASK 0x00000020 +#define CFG_BURST(len) ((len)<<4) +#define CFG_BURST_MASK 0x00000010 +#define CFG_IOPADMODE(iopad) (iopad) +#define CFG_IOPADMODE_MASK 0x0000000F + +/* LCD Interrupt Control Register */ +#define SPU_IRQ_ENA 0x01C0 +#define DMA_FRAME_IRQ0_ENA(irq) ((irq)<<31) +#define DMA_FRAME_IRQ0_ENA_MASK 0x80000000 +#define DMA_FRAME_IRQ1_ENA(irq) ((irq)<<30) +#define DMA_FRAME_IRQ1_ENA_MASK 0x40000000 +#define DMA_FF_UNDERFLOW_ENA(ff) ((ff)<<29) +#define DMA_FF_UNDERFLOW_ENA_MASK 0x20000000 +#define AXI_BUS_ERROR_IRQ_ENA(irq) ((irq)<<28) +#define AXI_BUS_ERROR_IRQ_ENA_MASK 0x10000000 +#define GRA_FRAME_IRQ0_ENA(irq) ((irq)<<27) +#define GRA_FRAME_IRQ0_ENA_MASK 0x08000000 +#define GRA_FRAME_IRQ1_ENA(irq) ((irq)<<26) +#define GRA_FRAME_IRQ1_ENA_MASK 0x04000000 +#define GRA_FF_UNDERFLOW_ENA(ff) ((ff)<<25) +#define GRA_FF_UNDERFLOW_ENA_MASK 0x02000000 +#define VSYNC_IRQ_ENA(vsync_irq) ((vsync_irq)<<23) +#define VSYNC_IRQ_ENA_MASK 0x00800000 +#define DUMB_FRAMEDONE_ENA(fdone) ((fdone)<<22) +#define DUMB_FRAMEDONE_ENA_MASK 0x00400000 +#define TWC_FRAMEDONE_ENA(fdone) ((fdone)<<21) +#define TWC_FRAMEDONE_ENA_MASK 0x00200000 +#define HWC_FRAMEDONE_ENA(fdone) ((fdone)<<20) +#define HWC_FRAMEDONE_ENA_MASK 0x00100000 +#define SLV_IRQ_ENA(irq) ((irq)<<19) +#define SLV_IRQ_ENA_MASK 0x00080000 +#define SPI_IRQ_ENA(irq) ((irq)<<18) +#define SPI_IRQ_ENA_MASK 0x00040000 +#define PWRDN_IRQ_ENA(irq) ((irq)<<17) +#define PWRDN_IRQ_ENA_MASK 0x00020000 +#define AXI_LATENCY_TOO_LONG_IRQ_ENA(irq) ((irq)<<16) +#define AXI_LATENCY_TOO_LONG_IRQ_ENA_MASK 0x00010000 +#define CLEAN_SPU_IRQ_ISR(irq) (irq) +#define CLEAN_SPU_IRQ_ISR_MASK 0x0000FFFF +#define TV_DMA_FRAME_IRQ0_ENA(irq) ((irq)<<15) +#define TV_DMA_FRAME_IRQ0_ENA_MASK 0x00008000 +#define TV_DMA_FRAME_IRQ1_ENA(irq) ((irq)<<14) +#define TV_DMA_FRAME_IRQ1_ENA_MASK 0x00004000 +#define TV_DMA_FF_UNDERFLOW_ENA(unerrun) ((unerrun)<<13) +#define TV_DMA_FF_UNDERFLOW_ENA_MASK 0x00002000 +#define TVSYNC_IRQ_ENA(irq) ((irq)<<12) +#define TVSYNC_IRQ_ENA_MASK 0x00001000 +#define TV_FRAME_IRQ0_ENA(irq) ((irq)<<11) +#define TV_FRAME_IRQ0_ENA_MASK 0x00000800 +#define TV_FRAME_IRQ1_ENA(irq) ((irq)<<10) +#define TV_FRAME_IRQ1_ENA_MASK 0x00000400 +#define TV_GRA_FF_UNDERFLOW_ENA(unerrun) ((unerrun)<<9) +#define TV_GRA_FF_UNDERFLOW_ENA_MASK 0x00000200 +#define TV_FRAMEDONE_ENA(irq) ((irq)<<8) +#define TV_FRAMEDONE_ENA_MASK 0x00000100 + +/* FIXME - JUST GUESS */ +#define PN2_DMA_FRAME_IRQ0_ENA(irq) ((irq)<<7) +#define PN2_DMA_FRAME_IRQ0_ENA_MASK 0x00000080 +#define PN2_DMA_FRAME_IRQ1_ENA(irq) ((irq)<<6) +#define PN2_DMA_FRAME_IRQ1_ENA_MASK 0x00000040 +#define PN2_DMA_FF_UNDERFLOW_ENA(ff) ((ff)<<5) +#define PN2_DMA_FF_UNDERFLOW_ENA_MASK 0x00000020 +#define PN2_GRA_FRAME_IRQ0_ENA(irq) ((irq)<<3) +#define PN2_GRA_FRAME_IRQ0_ENA_MASK 0x00000008 +#define PN2_GRA_FRAME_IRQ1_ENA(irq) ((irq)<<2) +#define PN2_GRA_FRAME_IRQ1_ENA_MASK 0x04000004 +#define PN2_GRA_FF_UNDERFLOW_ENA(ff) ((ff)<<1) +#define PN2_GRA_FF_UNDERFLOW_ENA_MASK 0x00000002 +#define PN2_VSYNC_IRQ_ENA(irq) ((irq)<<0) +#define PN2_SYNC_IRQ_ENA_MASK 0x00000001 + +#define gf0_imask(id) ((id) ? (((id) & 1) ? TV_FRAME_IRQ0_ENA_MASK \ + : PN2_GRA_FRAME_IRQ0_ENA_MASK) : GRA_FRAME_IRQ0_ENA_MASK) +#define gf1_imask(id) ((id) ? (((id) & 1) ? TV_FRAME_IRQ1_ENA_MASK \ + : PN2_GRA_FRAME_IRQ1_ENA_MASK) : GRA_FRAME_IRQ1_ENA_MASK) +#define vsync_imask(id) ((id) ? (((id) & 1) ? TVSYNC_IRQ_ENA_MASK \ + : PN2_SYNC_IRQ_ENA_MASK) : VSYNC_IRQ_ENA_MASK) +#define vsync_imasks (vsync_imask(0) | vsync_imask(1)) + +#define display_done_imask(id) ((id) ? (((id) & 1) ? TV_FRAMEDONE_ENA_MASK\ + : (PN2_DMA_FRAME_IRQ0_ENA_MASK | PN2_DMA_FRAME_IRQ1_ENA_MASK))\ + : DUMB_FRAMEDONE_ENA_MASK) + +#define display_done_imasks (display_done_imask(0) | display_done_imask(1)) + +#define vf0_imask(id) ((id) ? (((id) & 1) ? TV_DMA_FRAME_IRQ0_ENA_MASK \ + : PN2_DMA_FRAME_IRQ0_ENA_MASK) : DMA_FRAME_IRQ0_ENA_MASK) +#define vf1_imask(id) ((id) ? (((id) & 1) ? TV_DMA_FRAME_IRQ1_ENA_MASK \ + : PN2_DMA_FRAME_IRQ1_ENA_MASK) : DMA_FRAME_IRQ1_ENA_MASK) + +#define gfx_imasks (gf0_imask(0) | gf1_imask(0) | gf0_imask(1) | \ + gf1_imask(1)) +#define vid_imasks (vf0_imask(0) | vf1_imask(0) | vf0_imask(1) | \ + vf1_imask(1)) +#define vid_imask(id) (display_done_imask(id)) + +#define pn1_imasks (gf0_imask(0) | gf1_imask(0) | vsync_imask(0) | \ + display_done_imask(0) | vf0_imask(0) | vf1_imask(0)) +#define tv_imasks (gf0_imask(1) | gf1_imask(1) | vsync_imask(1) | \ + display_done_imask(1) | vf0_imask(1) | vf1_imask(1)) +#define path_imasks(id) ((id) ? (tv_imasks) : (pn1_imasks)) + +/* error indications */ +#define vid_udflow_imask(id) ((id) ? (((id) & 1) ? \ + (TV_DMA_FF_UNDERFLOW_ENA_MASK) : (PN2_DMA_FF_UNDERFLOW_ENA_MASK)) : \ + (DMA_FF_UNDERFLOW_ENA_MASK)) +#define gfx_udflow_imask(id) ((id) ? (((id) & 1) ? \ + (TV_GRA_FF_UNDERFLOW_ENA_MASK) : (PN2_GRA_FF_UNDERFLOW_ENA_MASK)) : \ + (GRA_FF_UNDERFLOW_ENA_MASK)) + +#define err_imask(id) (vid_udflow_imask(id) | gfx_udflow_imask(id) | \ + AXI_BUS_ERROR_IRQ_ENA_MASK | AXI_LATENCY_TOO_LONG_IRQ_ENA_MASK) +#define err_imasks (err_imask(0) | err_imask(1) | err_imask(2)) +/* LCD Interrupt Status Register */ +#define SPU_IRQ_ISR 0x01C4 +#define DMA_FRAME_IRQ0(irq) ((irq)<<31) +#define DMA_FRAME_IRQ0_MASK 0x80000000 +#define DMA_FRAME_IRQ1(irq) ((irq)<<30) +#define DMA_FRAME_IRQ1_MASK 0x40000000 +#define DMA_FF_UNDERFLOW(ff) ((ff)<<29) +#define DMA_FF_UNDERFLOW_MASK 0x20000000 +#define AXI_BUS_ERROR_IRQ(irq) ((irq)<<28) +#define AXI_BUS_ERROR_IRQ_MASK 0x10000000 +#define GRA_FRAME_IRQ0(irq) ((irq)<<27) +#define GRA_FRAME_IRQ0_MASK 0x08000000 +#define GRA_FRAME_IRQ1(irq) ((irq)<<26) +#define GRA_FRAME_IRQ1_MASK 0x04000000 +#define GRA_FF_UNDERFLOW(ff) ((ff)<<25) +#define GRA_FF_UNDERFLOW_MASK 0x02000000 +#define VSYNC_IRQ(vsync_irq) ((vsync_irq)<<23) +#define VSYNC_IRQ_MASK 0x00800000 +#define DUMB_FRAMEDONE(fdone) ((fdone)<<22) +#define DUMB_FRAMEDONE_MASK 0x00400000 +#define TWC_FRAMEDONE(fdone) ((fdone)<<21) +#define TWC_FRAMEDONE_MASK 0x00200000 +#define HWC_FRAMEDONE(fdone) ((fdone)<<20) +#define HWC_FRAMEDONE_MASK 0x00100000 +#define SLV_IRQ(irq) ((irq)<<19) +#define SLV_IRQ_MASK 0x00080000 +#define SPI_IRQ(irq) ((irq)<<18) +#define SPI_IRQ_MASK 0x00040000 +#define PWRDN_IRQ(irq) ((irq)<<17) +#define PWRDN_IRQ_MASK 0x00020000 +#define AXI_LATENCY_TOO_LONGR_IRQ(irq) ((irq)<<16) +#define AXI_LATENCY_TOO_LONGR_IRQ_MASK 0x00010000 +#define TV_DMA_FRAME_IRQ0(irq) ((irq)<<15) +#define TV_DMA_FRAME_IRQ0_MASK 0x00008000 +#define TV_DMA_FRAME_IRQ1(irq) ((irq)<<14) +#define TV_DMA_FRAME_IRQ1_MASK 0x00004000 +#define TV_DMA_FF_UNDERFLOW(unerrun) ((unerrun)<<13) +#define TV_DMA_FF_UNDERFLOW_MASK 0x00002000 +#define TVSYNC_IRQ(irq) ((irq)<<12) +#define TVSYNC_IRQ_MASK 0x00001000 +#define TV_FRAME_IRQ0(irq) ((irq)<<11) +#define TV_FRAME_IRQ0_MASK 0x00000800 +#define TV_FRAME_IRQ1(irq) ((irq)<<10) +#define TV_FRAME_IRQ1_MASK 0x00000400 +#define TV_GRA_FF_UNDERFLOW(unerrun) ((unerrun)<<9) +#define TV_GRA_FF_UNDERFLOW_MASK 0x00000200 +#define PN2_DMA_FRAME_IRQ0(irq) ((irq)<<7) +#define PN2_DMA_FRAME_IRQ0_MASK 0x00000080 +#define PN2_DMA_FRAME_IRQ1(irq) ((irq)<<6) +#define PN2_DMA_FRAME_IRQ1_MASK 0x00000040 +#define PN2_DMA_FF_UNDERFLOW(ff) ((ff)<<5) +#define PN2_DMA_FF_UNDERFLOW_MASK 0x00000020 +#define PN2_GRA_FRAME_IRQ0(irq) ((irq)<<3) +#define PN2_GRA_FRAME_IRQ0_MASK 0x00000008 +#define PN2_GRA_FRAME_IRQ1(irq) ((irq)<<2) +#define PN2_GRA_FRAME_IRQ1_MASK 0x04000004 +#define PN2_GRA_FF_UNDERFLOW(ff) ((ff)<<1) +#define PN2_GRA_FF_UNDERFLOW_MASK 0x00000002 +#define PN2_VSYNC_IRQ(irq) ((irq)<<0) +#define PN2_SYNC_IRQ_MASK 0x00000001 + +/* LCD FIFO Depth register */ +#define LCD_FIFO_DEPTH 0x01c8 +#define VIDEO_FIFO(fi) ((fi) << 0) +#define VIDEO_FIFO_MASK 0x00000003 +#define GRAPHIC_FIFO(fi) ((fi) << 2) +#define GRAPHIC_FIFO_MASK 0x0000000c + +/* read-only */ +#define DMA_FRAME_IRQ0_LEVEL_MASK 0x00008000 +#define DMA_FRAME_IRQ1_LEVEL_MASK 0x00004000 +#define DMA_FRAME_CNT_ISR_MASK 0x00003000 +#define GRA_FRAME_IRQ0_LEVEL_MASK 0x00000800 +#define GRA_FRAME_IRQ1_LEVEL_MASK 0x00000400 +#define GRA_FRAME_CNT_ISR_MASK 0x00000300 +#define VSYNC_IRQ_LEVEL_MASK 0x00000080 +#define DUMB_FRAMEDONE_LEVEL_MASK 0x00000040 +#define TWC_FRAMEDONE_LEVEL_MASK 0x00000020 +#define HWC_FRAMEDONE_LEVEL_MASK 0x00000010 +#define SLV_FF_EMPTY_MASK 0x00000008 +#define DMA_FF_ALLEMPTY_MASK 0x00000004 +#define GRA_FF_ALLEMPTY_MASK 0x00000002 +#define PWRDN_IRQ_LEVEL_MASK 0x00000001 + +/* 32 bit LCD Interrupt Reset Status*/ +#define SPU_IRQ_RSR (0x01C8) +/* 32 bit Panel Path Graphic Partial Display Horizontal Control Register*/ +#define LCD_GRA_CUTHPXL (0x01CC) +/* 32 bit Panel Path Graphic Partial Display Vertical Control Register*/ +#define LCD_GRA_CUTVLN (0x01D0) +/* 32 bit TV Path Graphic Partial Display Horizontal Control Register*/ +#define LCD_TVG_CUTHPXL (0x01D4) +/* 32 bit TV Path Graphic Partial Display Vertical Control Register*/ +#define LCD_TVG_CUTVLN (0x01D8) +/* 32 bit LCD Global Control Register*/ +#define LCD_TOP_CTRL (0x01DC) +/* 32 bit LCD SQU Line Buffer Control Register 1*/ +#define LCD_SQULN1_CTRL (0x01E0) +/* 32 bit LCD SQU Line Buffer Control Register 2*/ +#define LCD_SQULN2_CTRL (0x01E4) +#define squln_ctrl(id) ((id) ? (((id) & 1) ? LCD_SQULN2_CTRL : \ + LCD_PN2_SQULN1_CTRL) : LCD_SQULN1_CTRL) + +/* 32 bit LCD Mixed Overlay Control Register */ +#define LCD_AFA_ALL2ONE (0x01E8) + +#define LCD_PN2_SCLK_DIV (0x01EC) +#define LCD_PN2_TCLK_DIV (0x01F0) +#define LCD_LVDS_SCLK_DIV_WR (0x01F4) +#define LCD_LVDS_SCLK_DIV_RD (0x01FC) +#define PN2_LCD_DMA_START_ADDR_Y0 (0x0200) +#define PN2_LCD_DMA_START_ADDR_U0 (0x0204) +#define PN2_LCD_DMA_START_ADDR_V0 (0x0208) +#define PN2_LCD_DMA_START_ADDR_C0 (0x020C) +#define PN2_LCD_DMA_START_ADDR_Y1 (0x0210) +#define PN2_LCD_DMA_START_ADDR_U1 (0x0214) +#define PN2_LCD_DMA_START_ADDR_V1 (0x0218) +#define PN2_LCD_DMA_START_ADDR_C1 (0x021C) +#define PN2_LCD_DMA_PITCH_YC (0x0220) +#define PN2_LCD_DMA_PITCH_UV (0x0224) +#define PN2_LCD_DMA_OVSA_HPXL_VLN (0x0228) +#define PN2_LCD_DMA_HPXL_VLN (0x022C) +#define PN2_LCD_DMAZM_HPXL_VLN (0x0230) +#define PN2_LCD_GRA_START_ADDR0 (0x0234) +#define PN2_LCD_GRA_START_ADDR1 (0x0238) +#define PN2_LCD_GRA_PITCH (0x023C) +#define PN2_LCD_GRA_OVSA_HPXL_VLN (0x0240) +#define PN2_LCD_GRA_HPXL_VLN (0x0244) +#define PN2_LCD_GRAZM_HPXL_VLN (0x0248) +#define PN2_LCD_HWC_OVSA_HPXL_VLN (0x024C) +#define PN2_LCD_HWC_HPXL_VLN (0x0250) +#define LCD_PN2_V_H_TOTAL (0x0254) +#define LCD_PN2_V_H_ACTIVE (0x0258) +#define LCD_PN2_H_PORCH (0x025C) +#define LCD_PN2_V_PORCH (0x0260) +#define LCD_PN2_BLANKCOLOR (0x0264) +#define LCD_PN2_ALPHA_COLOR1 (0x0268) +#define LCD_PN2_ALPHA_COLOR2 (0x026C) +#define LCD_PN2_COLORKEY_Y (0x0270) +#define LCD_PN2_COLORKEY_U (0x0274) +#define LCD_PN2_COLORKEY_V (0x0278) +#define LCD_PN2_SEPXLCNT (0x027C) +#define LCD_TV_V_H_TOTAL_FLD (0x0280) +#define LCD_TV_V_PORCH_FLD (0x0284) +#define LCD_TV_SEPXLCNT_FLD (0x0288) + +#define LCD_2ND_ALPHA (0x0294) +#define LCD_PN2_CONTRAST (0x0298) +#define LCD_PN2_SATURATION (0x029c) +#define LCD_PN2_CBSH_HUE (0x02a0) +#define LCD_TIMING_EXT (0x02C0) +#define LCD_PN2_LAYER_ALPHA_SEL1 (0x02c4) +#define LCD_PN2_CTRL0 (0x02C8) +#define TV_LAYER_ALPHA_SEL1 (0x02cc) +#define LCD_SMPN2_CTRL (0x02D0) +#define LCD_IO_OVERL_MAP_CTRL (0x02D4) +#define LCD_DUMB2_CTRL (0x02d8) +#define LCD_PN2_CTRL1 (0x02DC) +#define PN2_IOPAD_CONTROL (0x02E0) +#define LCD_PN2_SQULN1_CTRL (0x02E4) +#define PN2_LCD_GRA_CUTHPXL (0x02e8) +#define PN2_LCD_GRA_CUTVLN (0x02ec) +#define LCD_PN2_SQULN2_CTRL (0x02F0) +#define ALL_LAYER_ALPHA_SEL (0x02F4) + +/* pxa988 has different MASTER_CTRL from MMP3/MMP2 */ +#ifdef CONFIG_CPU_PXA988 +#define TIMING_MASTER_CONTROL (0x01F4) +#define MASTER_ENH(id) (1 << ((id) + 5)) +#define MASTER_ENV(id) (1 << ((id) + 6)) +#else +#define TIMING_MASTER_CONTROL (0x02F8) +#define MASTER_ENH(id) (1 << (id)) +#define MASTER_ENV(id) (1 << ((id) + 4)) +#endif + +#define DSI_START_SEL_SHIFT(id) (((id) << 1) + 8) +#define timing_master_config(path, dsi_id, lcd_id) \ + (MASTER_ENH(path) | MASTER_ENV(path) | \ + (((lcd_id) + ((dsi_id) << 1)) << DSI_START_SEL_SHIFT(path))) + +#define LCD_2ND_BLD_CTL (0x02Fc) +#define LVDS_SRC_MASK (3 << 30) +#define LVDS_SRC_SHIFT (30) +#define LVDS_FMT_MASK (1 << 28) +#define LVDS_FMT_SHIFT (28) + +#define CLK_SCLK (1 << 0) +#define CLK_LVDS_RD (1 << 1) +#define CLK_LVDS_WR (1 << 2) + +#define gra_partdisp_ctrl_hor(id) ((id) ? (((id) & 1) ? \ + LCD_TVG_CUTHPXL : PN2_LCD_GRA_CUTHPXL) : LCD_GRA_CUTHPXL) +#define gra_partdisp_ctrl_ver(id) ((id) ? (((id) & 1) ? \ + LCD_TVG_CUTVLN : PN2_LCD_GRA_CUTVLN) : LCD_GRA_CUTVLN) + +/* + * defined Video Memory Color format for DMA control 0 register + * DMA0 bit[23:20] + */ +#define VMODE_RGB565 0x0 +#define VMODE_RGB1555 0x1 +#define VMODE_RGB888PACKED 0x2 +#define VMODE_RGB888UNPACKED 0x3 +#define VMODE_RGBA888 0x4 +#define VMODE_YUV422PACKED 0x5 +#define VMODE_YUV422PLANAR 0x6 +#define VMODE_YUV420PLANAR 0x7 +#define VMODE_SMPNCMD 0x8 +#define VMODE_PALETTE4BIT 0x9 +#define VMODE_PALETTE8BIT 0xa +#define VMODE_RESERVED 0xb + +/* + * defined Graphic Memory Color format for DMA control 0 register + * DMA0 bit[19:16] + */ +#define GMODE_RGB565 0x0 +#define GMODE_RGB1555 0x1 +#define GMODE_RGB888PACKED 0x2 +#define GMODE_RGB888UNPACKED 0x3 +#define GMODE_RGBA888 0x4 +#define GMODE_YUV422PACKED 0x5 +#define GMODE_YUV422PLANAR 0x6 +#define GMODE_YUV420PLANAR 0x7 +#define GMODE_SMPNCMD 0x8 +#define GMODE_PALETTE4BIT 0x9 +#define GMODE_PALETTE8BIT 0xa +#define GMODE_RESERVED 0xb + +/* + * define for DMA control 1 register + */ +#define DMA1_FRAME_TRIG 31 /* bit location */ +#define DMA1_VSYNC_MODE 28 +#define DMA1_VSYNC_INV 27 +#define DMA1_CKEY 24 +#define DMA1_CARRY 23 +#define DMA1_LNBUF_ENA 22 +#define DMA1_GATED_ENA 21 +#define DMA1_PWRDN_ENA 20 +#define DMA1_DSCALE 18 +#define DMA1_ALPHA_MODE 16 +#define DMA1_ALPHA 08 +#define DMA1_PXLCMD 00 + +/* + * defined for Configure Dumb Mode + * DUMB LCD Panel bit[31:28] + */ +#define DUMB16_RGB565_0 0x0 +#define DUMB16_RGB565_1 0x1 +#define DUMB18_RGB666_0 0x2 +#define DUMB18_RGB666_1 0x3 +#define DUMB12_RGB444_0 0x4 +#define DUMB12_RGB444_1 0x5 +#define DUMB24_RGB888_0 0x6 +#define DUMB_BLANK 0x7 + +/* + * defined for Configure I/O Pin Allocation Mode + * LCD LCD I/O Pads control register bit[3:0] + */ +#define IOPAD_DUMB24 0x0 +#define IOPAD_DUMB18SPI 0x1 +#define IOPAD_DUMB18GPIO 0x2 +#define IOPAD_DUMB16SPI 0x3 +#define IOPAD_DUMB16GPIO 0x4 +#define IOPAD_DUMB12 0x5 +#define IOPAD_SMART18SPI 0x6 +#define IOPAD_SMART16SPI 0x7 +#define IOPAD_SMART8BOTH 0x8 +#define IOPAD_DUMB18_SMART8 0x9 +#define IOPAD_DUMB16_SMART8SPI 0xa +#define IOPAD_DUMB16_SMART8GPIO 0xb +#define IOPAD_DUMB16_DUMB16 0xc +#define IOPAD_SMART8_SMART8 0xc + +/* + *defined for indicating boundary and cycle burst length + */ +#define CFG_BOUNDARY_1KB (1<<5) +#define CFG_BOUNDARY_4KB (0<<5) +#define CFG_CYC_BURST_LEN16 (1<<4) +#define CFG_CYC_BURST_LEN8 (0<<4) + +/* + * defined Dumb Panel Clock Divider register + * SCLK_Source bit[31] + */ + /* 0: PLL clock select*/ +#define AXI_BUS_SEL 0x80000000 +#define CCD_CLK_SEL 0x40000000 +#define DCON_CLK_SEL 0x20000000 +#define ENA_CLK_INT_DIV CONFIG_FB_DOVE_CLCD_SCLK_DIV +#define IDLE_CLK_INT_DIV 0x1 /* idle Integer Divider */ +#define DIS_CLK_INT_DIV 0x0 /* Disable Integer Divider */ + +/* SRAM ID */ +#define SRAMID_GAMMA_YR 0x0 +#define SRAMID_GAMMA_UG 0x1 +#define SRAMID_GAMMA_VB 0x2 +#define SRAMID_PALATTE 0x3 +#define SRAMID_HWC 0xf + +/* SRAM INIT Read/Write */ +#define SRAMID_INIT_READ 0x0 +#define SRAMID_INIT_WRITE 0x2 +#define SRAMID_INIT_DEFAULT 0x3 + +/* + * defined VSYNC selection mode for DMA control 1 register + * DMA1 bit[30:28] + */ +#define VMODE_SMPN 0x0 +#define VMODE_SMPNIRQ 0x1 +#define VMODE_DUMB 0x2 +#define VMODE_IPE 0x3 +#define VMODE_IRE 0x4 + +/* + * defined Configure Alpha and Alpha mode for DMA control 1 register + * DMA1 bit[15:08](alpha) / bit[17:16](alpha mode) + */ +/* ALPHA mode */ +#define MODE_ALPHA_DMA 0x0 +#define MODE_ALPHA_GRA 0x1 +#define MODE_ALPHA_CFG 0x2 + +/* alpha value */ +#define ALPHA_NOGRAPHIC 0xFF /* all video, no graphic */ +#define ALPHA_NOVIDEO 0x00 /* all graphic, no video */ +#define ALPHA_GRAPHNVIDEO 0x0F /* Selects graphic & video */ + +/* + * defined Pixel Command for DMA control 1 register + * DMA1 bit[07:00] + */ +#define PIXEL_CMD 0x81 + +/* DSI */ +/* DSI1 - 4 Lane Controller base */ +#define DSI1_REGS_PHYSICAL_BASE 0xD420B800 +/* DSI2 - 3 Lane Controller base */ +#define DSI2_REGS_PHYSICAL_BASE 0xD420BA00 + +/* DSI Controller Registers */ +struct dsi_lcd_regs { +#define DSI_LCD1_CTRL_0 0x100 /* DSI Active Panel 1 Control register 0 */ +#define DSI_LCD1_CTRL_1 0x104 /* DSI Active Panel 1 Control register 1 */ + u32 ctrl0; + u32 ctrl1; + u32 reserved1[2]; + +#define DSI_LCD1_TIMING_0 0x110 /* Timing register 0 */ +#define DSI_LCD1_TIMING_1 0x114 /* Timing register 1 */ +#define DSI_LCD1_TIMING_2 0x118 /* Timing register 2 */ +#define DSI_LCD1_TIMING_3 0x11C /* Timing register 3 */ +#define DSI_LCD1_WC_0 0x120 /* Word Count register 0 */ +#define DSI_LCD1_WC_1 0x124 /* Word Count register 1 */ +#define DSI_LCD1_WC_2 0x128 /* Word Count register 2 */ + u32 timing0; + u32 timing1; + u32 timing2; + u32 timing3; + u32 wc0; + u32 wc1; + u32 wc2; + u32 reserved2[1]; + u32 slot_cnt0; + u32 slot_cnt1; + u32 reserved3[2]; + u32 status_0; + u32 status_1; + u32 status_2; + u32 status_3; + u32 status_4; +}; + +struct dsi_regs { +#define DSI_CTRL_0 0x000 /* DSI control register 0 */ +#define DSI_CTRL_1 0x004 /* DSI control register 1 */ + u32 ctrl0; + u32 ctrl1; + u32 reserved1[2]; + u32 irq_status; + u32 irq_mask; + u32 reserved2[2]; + +#define DSI_CPU_CMD_0 0x020 /* DSI CPU packet command register 0 */ +#define DSI_CPU_CMD_1 0x024 /* DSU CPU Packet Command Register 1 */ +#define DSI_CPU_CMD_3 0x02C /* DSU CPU Packet Command Register 3 */ +#define DSI_CPU_WDAT_0 0x030 /* DSI CUP */ + u32 cmd0; + u32 cmd1; + u32 cmd2; + u32 cmd3; + u32 dat0; + u32 status0; + u32 status1; + u32 status2; + u32 status3; + u32 status4; + u32 reserved3[2]; + + u32 smt_cmd; + u32 smt_ctrl0; + u32 smt_ctrl1; + u32 reserved4[1]; + + u32 rx0_status; + +/* Rx Packet Header - data from slave device */ +#define DSI_RX_PKT_HDR_0 0x064 + u32 rx0_header; + u32 rx1_status; + u32 rx1_header; + u32 rx_ctrl; + u32 rx_ctrl1; + u32 rx2_status; + u32 rx2_header; + u32 reserved5[1]; + + u32 phy_ctrl1; +#define DSI_PHY_CTRL_2 0x088 /* DSI DPHI Control Register 2 */ +#define DSI_PHY_CTRL_3 0x08C /* DPHY Control Register 3 */ + u32 phy_ctrl2; + u32 phy_ctrl3; + u32 phy_status0; + u32 phy_status1; + u32 reserved6[5]; + u32 phy_status2; + +#define DSI_PHY_RCOMP_0 0x0B0 /* DPHY Rcomp Control Register */ + u32 phy_rcomp0; + u32 reserved7[3]; +#define DSI_PHY_TIME_0 0x0C0 /* DPHY Timing Control Register 0 */ +#define DSI_PHY_TIME_1 0x0C4 /* DPHY Timing Control Register 1 */ +#define DSI_PHY_TIME_2 0x0C8 /* DPHY Timing Control Register 2 */ +#define DSI_PHY_TIME_3 0x0CC /* DPHY Timing Control Register 3 */ +#define DSI_PHY_TIME_4 0x0D0 /* DPHY Timing Control Register 4 */ +#define DSI_PHY_TIME_5 0x0D4 /* DPHY Timing Control Register 5 */ + u32 phy_timing0; + u32 phy_timing1; + u32 phy_timing2; + u32 phy_timing3; + u32 phy_code_0; + u32 phy_code_1; + u32 reserved8[2]; + u32 mem_ctrl; + u32 tx_timer; + u32 rx_timer; + u32 turn_timer; + u32 reserved9[4]; + +#define DSI_LCD1_CTRL_0 0x100 /* DSI Active Panel 1 Control register 0 */ +#define DSI_LCD1_CTRL_1 0x104 /* DSI Active Panel 1 Control register 1 */ +#define DSI_LCD1_TIMING_0 0x110 /* Timing register 0 */ +#define DSI_LCD1_TIMING_1 0x114 /* Timing register 1 */ +#define DSI_LCD1_TIMING_2 0x118 /* Timing register 2 */ +#define DSI_LCD1_TIMING_3 0x11C /* Timing register 3 */ +#define DSI_LCD1_WC_0 0x120 /* Word Count register 0 */ +#define DSI_LCD1_WC_1 0x124 /* Word Count register 1 */ +#define DSI_LCD1_WC_2 0x128 /* Word Count register 2 */ + struct dsi_lcd_regs lcd1; + u32 reserved10[11]; + struct dsi_lcd_regs lcd2; +}; + +#define DSI_LCD2_CTRL_0 0x180 /* DSI Active Panel 2 Control register 0 */ +#define DSI_LCD2_CTRL_1 0x184 /* DSI Active Panel 2 Control register 1 */ +#define DSI_LCD2_TIMING_0 0x190 /* Timing register 0 */ +#define DSI_LCD2_TIMING_1 0x194 /* Timing register 1 */ +#define DSI_LCD2_TIMING_2 0x198 /* Timing register 2 */ +#define DSI_LCD2_TIMING_3 0x19C /* Timing register 3 */ +#define DSI_LCD2_WC_0 0x1A0 /* Word Count register 0 */ +#define DSI_LCD2_WC_1 0x1A4 /* Word Count register 1 */ +#define DSI_LCD2_WC_2 0x1A8 /* Word Count register 2 */ + +/* DSI_CTRL_0 0x0000 DSI Control Register 0 */ +#define DSI_CTRL_0_CFG_SOFT_RST (1<<31) +#define DSI_CTRL_0_CFG_SOFT_RST_REG (1<<30) +#define DSI_CTRL_0_CFG_LCD1_TX_EN (1<<8) +#define DSI_CTRL_0_CFG_LCD1_SLV (1<<4) +#define DSI_CTRL_0_CFG_LCD1_EN (1<<0) + +/* DSI_CTRL_1 0x0004 DSI Control Register 1 */ +#define DSI_CTRL_1_CFG_EOTP (1<<8) +#define DSI_CTRL_1_CFG_RSVD (2<<4) +#define DSI_CTRL_1_CFG_LCD2_VCH_NO_MASK (3<<2) +#define DSI_CTRL_1_CFG_LCD2_VCH_NO_SHIFT 2 +#define DSI_CTRL_1_CFG_LCD1_VCH_NO_MASK (3<<0) +#define DSI_CTRL_1_CFG_LCD1_VCH_NO_SHIFT 0 + +/* DSI_LCD1_CTRL_1 0x0104 DSI Active Panel 1 Control Register 1 */ +/* LCD 1 Vsync Reset Enable */ +#define DSI_LCD1_CTRL_1_CFG_L1_VSYNC_RST_EN (1<<31) +/* LCD 1 2K Pixel Buffer Mode Enable */ +#define DSI_LCD1_CTRL_1_CFG_L1_M2K_EN (1<<30) +/* Bit(s) DSI_LCD1_CTRL_1_RSRV_29_23 reserved */ +/* Long Blanking Packet Enable */ +#define DSI_LCD1_CTRL_1_CFG_L1_HLP_PKT_EN (1<<22) +/* Extra Long Blanking Packet Enable */ +#define DSI_LCD1_CTRL_1_CFG_L1_HEX_PKT_EN (1<<21) +/* Front Porch Packet Enable */ +#define DSI_LCD1_CTRL_1_CFG_L1_HFP_PKT_EN (1<<20) +/* hact Packet Enable */ +#define DSI_LCD1_CTRL_1_CFG_L1_HACT_PKT_EN (1<<19) +/* Back Porch Packet Enable */ +#define DSI_LCD1_CTRL_1_CFG_L1_HBP_PKT_EN (1<<18) +/* hse Packet Enable */ +#define DSI_LCD1_CTRL_1_CFG_L1_HSE_PKT_EN (1<<17) +/* hsa Packet Enable */ +#define DSI_LCD1_CTRL_1_CFG_L1_HSA_PKT_EN (1<<16) +/* All Item Enable after Pixel Data */ +#define DSI_LCD1_CTRL_1_CFG_L1_ALL_SLOT_EN (1<<15) +/* Extra Long Packet Enable after Pixel Data */ +#define DSI_LCD1_CTRL_1_CFG_L1_HEX_SLOT_EN (1<<14) +/* Bit(s) DSI_LCD1_CTRL_1_RSRV_13_11 reserved */ +/* Turn Around Bus at Last h Line */ +#define DSI_LCD1_CTRL_1_CFG_L1_LAST_LINE_TURN (1<<10) +/* Go to Low Power Every Frame */ +#define DSI_LCD1_CTRL_1_CFG_L1_LPM_FRAME_EN (1<<9) +/* Go to Low Power Every Line */ +#define DSI_LCD1_CTRL_1_CFG_L1_LPM_LINE_EN (1<<8) +/* Bit(s) DSI_LCD1_CTRL_1_RSRV_7_4 reserved */ +/* DSI Transmission Mode for LCD 1 */ +#define DSI_LCD1_CTRL_1_CFG_L1_BURST_MODE_SHIFT 2 +#define DSI_LCD1_CTRL_1_CFG_L1_BURST_MODE_MASK (3<<2) +/* LCD 1 Input Data RGB Mode for LCD 1 */ +#define DSI_LCD2_CTRL_1_CFG_L1_RGB_TYPE_SHIFT 0 +#define DSI_LCD2_CTRL_1_CFG_L1_RGB_TYPE_MASK (3<<2) + +/* DSI_PHY_CTRL_2 0x0088 DPHY Control Register 2 */ +/* Bit(s) DSI_PHY_CTRL_2_RSRV_31_12 reserved */ +/* DPHY LP Receiver Enable */ +#define DSI_PHY_CTRL_2_CFG_CSR_LANE_RESC_EN_MASK (0xf<<8) +#define DSI_PHY_CTRL_2_CFG_CSR_LANE_RESC_EN_SHIFT 8 +/* DPHY Data Lane Enable */ +#define DSI_PHY_CTRL_2_CFG_CSR_LANE_EN_MASK (0xf<<4) +#define DSI_PHY_CTRL_2_CFG_CSR_LANE_EN_SHIFT 4 +/* DPHY Bus Turn Around */ +#define DSI_PHY_CTRL_2_CFG_CSR_LANE_TURN_MASK (0xf) +#define DSI_PHY_CTRL_2_CFG_CSR_LANE_TURN_SHIFT 0 + +/* DSI_CPU_CMD_1 0x0024 DSI CPU Packet Command Register 1 */ +/* Bit(s) DSI_CPU_CMD_1_RSRV_31_24 reserved */ +/* LPDT TX Enable */ +#define DSI_CPU_CMD_1_CFG_TXLP_LPDT_MASK (0xf<<20) +#define DSI_CPU_CMD_1_CFG_TXLP_LPDT_SHIFT 20 +/* ULPS TX Enable */ +#define DSI_CPU_CMD_1_CFG_TXLP_ULPS_MASK (0xf<<16) +#define DSI_CPU_CMD_1_CFG_TXLP_ULPS_SHIFT 16 +/* Low Power TX Trigger Code */ +#define DSI_CPU_CMD_1_CFG_TXLP_TRIGGER_CODE_MASK (0xffff) +#define DSI_CPU_CMD_1_CFG_TXLP_TRIGGER_CODE_SHIFT 0 + +/* DSI_PHY_TIME_0 0x00c0 DPHY Timing Control Register 0 */ +/* Length of HS Exit Period in tx_clk_esc Cycles */ +#define DSI_PHY_TIME_0_CFG_CSR_TIME_HS_EXIT_MASK (0xff<<24) +#define DSI_PHY_TIME_0_CFG_CSR_TIME_HS_EXIT_SHIFT 24 +/* DPHY HS Trail Period Length */ +#define DSI_PHY_TIME_0_CFG_CSR_TIME_HS_TRAIL_MASK (0xff<<16) +#define DSI_PHY_TIME_0_CFG_CSR_TIME_HS_TRAIL_SHIFT 16 +/* DPHY HS Zero State Length */ +#define DSI_PHY_TIME_0_CDG_CSR_TIME_HS_ZERO_MASK (0xff<<8) +#define DSI_PHY_TIME_0_CDG_CSR_TIME_HS_ZERO_SHIFT 8 +/* DPHY HS Prepare State Length */ +#define DSI_PHY_TIME_0_CFG_CSR_TIME_HS_PREP_MASK (0xff) +#define DSI_PHY_TIME_0_CFG_CSR_TIME_HS_PREP_SHIFT 0 + +/* DSI_PHY_TIME_1 0x00c4 DPHY Timing Control Register 1 */ +/* Time to Drive LP-00 by New Transmitter */ +#define DSI_PHY_TIME_1_CFG_CSR_TIME_TA_GET_MASK (0xff<<24) +#define DSI_PHY_TIME_1_CFG_CSR_TIME_TA_GET_SHIFT 24 +/* Time to Drive LP-00 after Turn Request */ +#define DSI_PHY_TIME_1_CFG_CSR_TIME_TA_GO_MASK (0xff<<16) +#define DSI_PHY_TIME_1_CFG_CSR_TIME_TA_GO_SHIFT 16 +/* DPHY HS Wakeup Period Length */ +#define DSI_PHY_TIME_1_CFG_CSR_TIME_WAKEUP_MASK (0xffff) +#define DSI_PHY_TIME_1_CFG_CSR_TIME_WAKEUP_SHIFT 0 + +/* DSI_PHY_TIME_2 0x00c8 DPHY Timing Control Register 2 */ +/* DPHY CLK Exit Period Length */ +#define DSI_PHY_TIME_2_CFG_CSR_TIME_CK_EXIT_MASK (0xff<<24) +#define DSI_PHY_TIME_2_CFG_CSR_TIME_CK_EXIT_SHIFT 24 +/* DPHY CLK Trail Period Length */ +#define DSI_PHY_TIME_2_CFG_CSR_TIME_CK_TRAIL_MASK (0xff<<16) +#define DSI_PHY_TIME_2_CFG_CSR_TIME_CK_TRAIL_SHIFT 16 +/* DPHY CLK Zero State Length */ +#define DSI_PHY_TIME_2_CFG_CSR_TIME_CK_ZERO_MASK (0xff<<8) +#define DSI_PHY_TIME_2_CFG_CSR_TIME_CK_ZERO_SHIFT 8 +/* DPHY CLK LP Length */ +#define DSI_PHY_TIME_2_CFG_CSR_TIME_CK_LPX_MASK (0xff) +#define DSI_PHY_TIME_2_CFG_CSR_TIME_CK_LPX_SHIFT 0 + +/* DSI_PHY_TIME_3 0x00cc DPHY Timing Control Register 3 */ +/* Bit(s) DSI_PHY_TIME_3_RSRV_31_16 reserved */ +/* DPHY LP Length */ +#define DSI_PHY_TIME_3_CFG_CSR_TIME_LPX_MASK (0xff<<8) +#define DSI_PHY_TIME_3_CFG_CSR_TIME_LPX_SHIFT 8 +/* DPHY HS req to rdy Length */ +#define DSI_PHY_TIME_3_CFG_CSR_TIME_REQRDY_MASK (0xff) +#define DSI_PHY_TIME_3_CFG_CSR_TIME_REQRDY_SHIFT 0 + +/* + * DSI timings + * PXA988 has diffrent ESC CLK with MMP2/MMP3 + * it will be used in dsi_set_dphy() in pxa688_phy.c + * as low power mode clock. + */ +#ifdef CONFIG_CPU_PXA988 +#define DSI_ESC_CLK 52 /* Unit: Mhz */ +#define DSI_ESC_CLK_T 19 /* Unit: ns */ +#else +#define DSI_ESC_CLK 66 /* Unit: Mhz */ +#define DSI_ESC_CLK_T 15 /* Unit: ns */ +#endif + +/* LVDS */ +/* LVDS_PHY_CTRL */ +#define LVDS_PHY_CTL 0x2A4 +#define LVDS_PLL_LOCK (1 << 31) +#define LVDS_PHY_EXT_MASK (7 << 28) +#define LVDS_PHY_EXT_SHIFT (28) +#define LVDS_CLK_PHASE_MASK (0x7f << 16) +#define LVDS_CLK_PHASE_SHIFT (16) +#define LVDS_SSC_RESET_EXT (1 << 13) +#define LVDS_SSC_MODE_DOWN_SPREAD (1 << 12) +#define LVDS_SSC_EN (1 << 11) +#define LVDS_PU_PLL (1 << 10) +#define LVDS_PU_TX (1 << 9) +#define LVDS_PU_IVREF (1 << 8) +#define LVDS_CLK_SEL (1 << 7) +#define LVDS_CLK_SEL_LVDS_PCLK (1 << 7) +#define LVDS_PD_CH_MASK (0x3f << 1) +#define LVDS_PD_CH(ch) ((ch) << 1) +#define LVDS_RST (1 << 0) + +#define LVDS_PHY_CTL_EXT 0x2A8 + +/* LVDS_PHY_CTRL_EXT1 */ +#define LVDS_SSC_RNGE_MASK (0x7ff << 16) +#define LVDS_SSC_RNGE_SHIFT (16) +#define LVDS_RESERVE_IN_MASK (0xf << 12) +#define LVDS_RESERVE_IN_SHIFT (12) +#define LVDS_TEST_MON_MASK (0x7 << 8) +#define LVDS_TEST_MON_SHIFT (8) +#define LVDS_POL_SWAP_MASK (0x3f << 0) +#define LVDS_POL_SWAP_SHIFT (0) + +/* LVDS_PHY_CTRL_EXT2 */ +#define LVDS_TX_DIF_AMP_MASK (0xf << 24) +#define LVDS_TX_DIF_AMP_SHIFT (24) +#define LVDS_TX_DIF_CM_MASK (0x3 << 22) +#define LVDS_TX_DIF_CM_SHIFT (22) +#define LVDS_SELLV_TXCLK_MASK (0x1f << 16) +#define LVDS_SELLV_TXCLK_SHIFT (16) +#define LVDS_TX_CMFB_EN (0x1 << 15) +#define LVDS_TX_TERM_EN (0x1 << 14) +#define LVDS_SELLV_TXDATA_MASK (0x1f << 8) +#define LVDS_SELLV_TXDATA_SHIFT (8) +#define LVDS_SELLV_OP7_MASK (0x3 << 6) +#define LVDS_SELLV_OP7_SHIFT (6) +#define LVDS_SELLV_OP6_MASK (0x3 << 4) +#define LVDS_SELLV_OP6_SHIFT (4) +#define LVDS_SELLV_OP9_MASK (0x3 << 2) +#define LVDS_SELLV_OP9_SHIFT (2) +#define LVDS_STRESSTST_EN (0x1 << 0) + +/* LVDS_PHY_CTRL_EXT3 */ +#define LVDS_KVCO_MASK (0xf << 28) +#define LVDS_KVCO_SHIFT (28) +#define LVDS_CTUNE_MASK (0x3 << 26) +#define LVDS_CTUNE_SHIFT (26) +#define LVDS_VREG_IVREF_MASK (0x3 << 24) +#define LVDS_VREG_IVREF_SHIFT (24) +#define LVDS_VDDL_MASK (0xf << 20) +#define LVDS_VDDL_SHIFT (20) +#define LVDS_VDDM_MASK (0x3 << 18) +#define LVDS_VDDM_SHIFT (18) +#define LVDS_FBDIV_MASK (0xf << 8) +#define LVDS_FBDIV_SHIFT (8) +#define LVDS_REFDIV_MASK (0x7f << 0) +#define LVDS_REFDIV_SHIFT (0) + +/* LVDS_PHY_CTRL_EXT4 */ +#define LVDS_SSC_FREQ_DIV_MASK (0xffff << 16) +#define LVDS_SSC_FREQ_DIV_SHIFT (16) +#define LVDS_INTPI_MASK (0xf << 12) +#define LVDS_INTPI_SHIFT (12) +#define LVDS_VCODIV_SEL_SE_MASK (0xf << 8) +#define LVDS_VCODIV_SEL_SE_SHIFT (8) +#define LVDS_RESET_INTP_EXT (0x1 << 7) +#define LVDS_VCO_VRNG_MASK (0x7 << 4) +#define LVDS_VCO_VRNG_SHIFT (4) +#define LVDS_PI_EN (0x1 << 3) +#define LVDS_ICP_MASK (0x7 << 0) +#define LVDS_ICP_SHIFT (0) + +/* LVDS_PHY_CTRL_EXT5 */ +#define LVDS_FREQ_OFFSET_MASK (0x1ffff << 15) +#define LVDS_FREQ_OFFSET_SHIFT (15) +#define LVDS_FREQ_OFFSET_VALID (0x1 << 2) +#define LVDS_FREQ_OFFSET_MODE_CK_DIV4_OUT (0x1 << 1) +#define LVDS_FREQ_OFFSET_MODE_EN (0x1 << 0) + +/* VDMA */ +struct vdma_ch_regs { +#define VDMA_DC_SADDR_1 0x320 +#define VDMA_DC_SADDR_2 0x3A0 +#define VDMA_DC_SZ_1 0x324 +#define VDMA_DC_SZ_2 0x3A4 +#define VDMA_CTRL_1 0x328 +#define VDMA_CTRL_2 0x3A8 +#define VDMA_SRC_SZ_1 0x32C +#define VDMA_SRC_SZ_2 0x3AC +#define VDMA_SA_1 0x330 +#define VDMA_SA_2 0x3B0 +#define VDMA_DA_1 0x334 +#define VDMA_DA_2 0x3B4 +#define VDMA_SZ_1 0x338 +#define VDMA_SZ_2 0x3B8 + u32 dc_saddr; + u32 dc_size; + u32 ctrl; + u32 src_size; + u32 src_addr; + u32 dst_addr; + u32 dst_size; +#define VDMA_PITCH_1 0x33C +#define VDMA_PITCH_2 0x3BC +#define VDMA_ROT_CTRL_1 0x340 +#define VDMA_ROT_CTRL_2 0x3C0 +#define VDMA_RAM_CTRL0_1 0x344 +#define VDMA_RAM_CTRL0_2 0x3C4 +#define VDMA_RAM_CTRL1_1 0x348 +#define VDMA_RAM_CTRL1_2 0x3C8 + u32 pitch; + u32 rot_ctrl; + u32 ram_ctrl0; + u32 ram_ctrl1; + +}; +struct vdma_regs { +#define VDMA_ARBR_CTRL 0x300 +#define VDMA_IRQR 0x304 +#define VDMA_IRQM 0x308 +#define VDMA_IRQS 0x30C +#define VDMA_MDMA_ARBR_CTRL 0x310 + u32 arbr_ctr; + u32 irq_raw; + u32 irq_mask; + u32 irq_status; + u32 mdma_arbr_ctrl; + u32 reserved[3]; + + struct vdma_ch_regs ch1; + u32 reserved2[21]; + struct vdma_ch_regs ch2; +}; + +/* CMU */ +#define CMU_PIP_DE_H_CFG 0x0008 +#define CMU_PRI1_H_CFG 0x000C +#define CMU_PRI2_H_CFG 0x0010 +#define CMU_ACE_MAIN_DE1_H_CFG 0x0014 +#define CMU_ACE_MAIN_DE2_H_CFG 0x0018 +#define CMU_ACE_PIP_DE1_H_CFG 0x001C +#define CMU_ACE_PIP_DE2_H_CFG 0x0020 +#define CMU_PIP_DE_V_CFG 0x0024 +#define CMU_PRI_V_CFG 0x0028 +#define CMU_ACE_MAIN_DE_V_CFG 0x002C +#define CMU_ACE_PIP_DE_V_CFG 0x0030 +#define CMU_BAR_0_CFG 0x0034 +#define CMU_BAR_1_CFG 0x0038 +#define CMU_BAR_2_CFG 0x003C +#define CMU_BAR_3_CFG 0x0040 +#define CMU_BAR_4_CFG 0x0044 +#define CMU_BAR_5_CFG 0x0048 +#define CMU_BAR_6_CFG 0x004C +#define CMU_BAR_7_CFG 0x0050 +#define CMU_BAR_8_CFG 0x0054 +#define CMU_BAR_9_CFG 0x0058 +#define CMU_BAR_10_CFG 0x005C +#define CMU_BAR_11_CFG 0x0060 +#define CMU_BAR_12_CFG 0x0064 +#define CMU_BAR_13_CFG 0x0068 +#define CMU_BAR_14_CFG 0x006C +#define CMU_BAR_15_CFG 0x0070 +#define CMU_BAR_CTRL 0x0074 +#define PATTERN_TOTAL 0x0078 +#define PATTERN_ACTIVE 0x007C +#define PATTERN_FRONT_PORCH 0x0080 +#define PATTERN_BACK_PORCH 0x0084 +#define CMU_CLK_CTRL 0x0088 + +#define CMU_ICSC_M_C0_L 0x0900 +#define CMU_ICSC_M_C0_H 0x0901 +#define CMU_ICSC_M_C1_L 0x0902 +#define CMU_ICSC_M_C1_H 0x0903 +#define CMU_ICSC_M_C2_L 0x0904 +#define CMU_ICSC_M_C2_H 0x0905 +#define CMU_ICSC_M_C3_L 0x0906 +#define CMU_ICSC_M_C3_H 0x0907 +#define CMU_ICSC_M_C4_L 0x0908 +#define CMU_ICSC_M_C4_H 0x0909 +#define CMU_ICSC_M_C5_L 0x090A +#define CMU_ICSC_M_C5_H 0x090B +#define CMU_ICSC_M_C6_L 0x090C +#define CMU_ICSC_M_C6_H 0x090D +#define CMU_ICSC_M_C7_L 0x090E +#define CMU_ICSC_M_C7_H 0x090F +#define CMU_ICSC_M_C8_L 0x0910 +#define CMU_ICSC_M_C8_H 0x0911 +#define CMU_ICSC_M_O1_0 0x0914 +#define CMU_ICSC_M_O1_1 0x0915 +#define CMU_ICSC_M_O1_2 0x0916 +#define CMU_ICSC_M_O2_0 0x0918 +#define CMU_ICSC_M_O2_1 0x0919 +#define CMU_ICSC_M_O2_2 0x091A +#define CMU_ICSC_M_O3_0 0x091C +#define CMU_ICSC_M_O3_1 0x091D +#define CMU_ICSC_M_O3_2 0x091E +#define CMU_ICSC_P_C0_L 0x0920 +#define CMU_ICSC_P_C0_H 0x0921 +#define CMU_ICSC_P_C1_L 0x0922 +#define CMU_ICSC_P_C1_H 0x0923 +#define CMU_ICSC_P_C2_L 0x0924 +#define CMU_ICSC_P_C2_H 0x0925 +#define CMU_ICSC_P_C3_L 0x0926 +#define CMU_ICSC_P_C3_H 0x0927 +#define CMU_ICSC_P_C4_L 0x0928 +#define CMU_ICSC_P_C4_H 0x0929 +#define CMU_ICSC_P_C5_L 0x092A +#define CMU_ICSC_P_C5_H 0x092B +#define CMU_ICSC_P_C6_L 0x092C +#define CMU_ICSC_P_C6_H 0x092D +#define CMU_ICSC_P_C7_L 0x092E +#define CMU_ICSC_P_C7_H 0x092F +#define CMU_ICSC_P_C8_L 0x0930 +#define CMU_ICSC_P_C8_H 0x0931 +#define CMU_ICSC_P_O1_0 0x0934 +#define CMU_ICSC_P_O1_1 0x0935 +#define CMU_ICSC_P_O1_2 0x0936 +#define CMU_ICSC_P_O2_0 0x0938 +#define CMU_ICSC_P_O2_1 0x0939 +#define CMU_ICSC_P_O2_2 0x093A +#define CMU_ICSC_P_O3_0 0x093C +#define CMU_ICSC_P_O3_1 0x093D +#define CMU_ICSC_P_O3_2 0x093E +#define CMU_BR_M_EN 0x0940 +#define CMU_BR_M_TH1_L 0x0942 +#define CMU_BR_M_TH1_H 0x0943 +#define CMU_BR_M_TH2_L 0x0944 +#define CMU_BR_M_TH2_H 0x0945 +#define CMU_ACE_M_EN 0x0950 +#define CMU_ACE_M_WFG1 0x0951 +#define CMU_ACE_M_WFG2 0x0952 +#define CMU_ACE_M_WFG3 0x0953 +#define CMU_ACE_M_TH0 0x0954 +#define CMU_ACE_M_TH1 0x0955 +#define CMU_ACE_M_TH2 0x0956 +#define CMU_ACE_M_TH3 0x0957 +#define CMU_ACE_M_TH4 0x0958 +#define CMU_ACE_M_TH5 0x0959 +#define CMU_ACE_M_OP0_L 0x095A +#define CMU_ACE_M_OP0_H 0x095B +#define CMU_ACE_M_OP5_L 0x095C +#define CMU_ACE_M_OP5_H 0x095D +#define CMU_ACE_M_GB2 0x095E +#define CMU_ACE_M_GB3 0x095F +#define CMU_ACE_M_MS1 0x0960 +#define CMU_ACE_M_MS2 0x0961 +#define CMU_ACE_M_MS3 0x0962 +#define CMU_BR_P_EN 0x0970 +#define CMU_BR_P_TH1_L 0x0972 +#define CMU_BR_P_TH1_H 0x0973 +#define CMU_BR_P_TH2_L 0x0974 +#define CMU_BR_P_TH2_H 0x0975 +#define CMU_ACE_P_EN 0x0980 +#define CMU_ACE_P_WFG1 0x0981 +#define CMU_ACE_P_WFG2 0x0982 +#define CMU_ACE_P_WFG3 0x0983 +#define CMU_ACE_P_TH0 0x0984 +#define CMU_ACE_P_TH1 0x0985 +#define CMU_ACE_P_TH2 0x0986 +#define CMU_ACE_P_TH3 0x0987 +#define CMU_ACE_P_TH4 0x0988 +#define CMU_ACE_P_TH5 0x0989 +#define CMU_ACE_P_OP0_L 0x098A +#define CMU_ACE_P_OP0_H 0x098B +#define CMU_ACE_P_OP5_L 0x098C +#define CMU_ACE_P_OP5_H 0x098D +#define CMU_ACE_P_GB2 0x098E +#define CMU_ACE_P_GB3 0x098F +#define CMU_ACE_P_MS1 0x0990 +#define CMU_ACE_P_MS2 0x0991 +#define CMU_ACE_P_MS3 0x0992 +#define CMU_FTDC_M_EN 0x09A0 +#define CMU_FTDC_P_EN 0x09A1 +#define CMU_FTDC_INLOW_L 0x09A2 +#define CMU_FTDC_INLOW_H 0x09A3 +#define CMU_FTDC_INHIGH_L 0x09A4 +#define CMU_FTDC_INHIGH_H 0x09A5 +#define CMU_FTDC_OUTLOW_L 0x09A6 +#define CMU_FTDC_OUTLOW_H 0x09A7 +#define CMU_FTDC_OUTHIGH_L 0x09A8 +#define CMU_FTDC_OUTHIGH_H 0x09A9 +#define CMU_FTDC_YLOW 0x09AA +#define CMU_FTDC_YHIGH 0x09AB +#define CMU_FTDC_CH1 0x09AC +#define CMU_FTDC_CH2_L 0x09AE +#define CMU_FTDC_CH2_H 0x09AF +#define CMU_FTDC_CH3_L 0x09B0 +#define CMU_FTDC_CH3_H 0x09B1 +#define CMU_FTDC_1_C00_6 0x09B2 +#define CMU_FTDC_1_C01_6 0x09B8 +#define CMU_FTDC_1_C11_6 0x09BE +#define CMU_FTDC_1_C10_6 0x09C4 +#define CMU_FTDC_1_OFF00_6 0x09CA +#define CMU_FTDC_1_OFF10_6 0x09D0 +#define CMU_HS_M_EN 0x0A00 +#define CMU_HS_M_AX1_L 0x0A02 +#define CMU_HS_M_AX1_H 0x0A03 +#define CMU_HS_M_AX2_L 0x0A04 +#define CMU_HS_M_AX2_H 0x0A05 +#define CMU_HS_M_AX3_L 0x0A06 +#define CMU_HS_M_AX3_H 0x0A07 +#define CMU_HS_M_AX4_L 0x0A08 +#define CMU_HS_M_AX4_H 0x0A09 +#define CMU_HS_M_AX5_L 0x0A0A +#define CMU_HS_M_AX5_H 0x0A0B +#define CMU_HS_M_AX6_L 0x0A0C +#define CMU_HS_M_AX6_H 0x0A0D +#define CMU_HS_M_AX7_L 0x0A0E +#define CMU_HS_M_AX7_H 0x0A0F +#define CMU_HS_M_AX8_L 0x0A10 +#define CMU_HS_M_AX8_H 0x0A11 +#define CMU_HS_M_AX9_L 0x0A12 +#define CMU_HS_M_AX9_H 0x0A13 +#define CMU_HS_M_AX10_L 0x0A14 +#define CMU_HS_M_AX10_H 0x0A15 +#define CMU_HS_M_AX11_L 0x0A16 +#define CMU_HS_M_AX11_H 0x0A17 +#define CMU_HS_M_AX12_L 0x0A18 +#define CMU_HS_M_AX12_H 0x0A19 +#define CMU_HS_M_AX13_L 0x0A1A +#define CMU_HS_M_AX13_H 0x0A1B +#define CMU_HS_M_AX14_L 0x0A1C +#define CMU_HS_M_AX14_H 0x0A1D +#define CMU_HS_M_H1_H14 0x0A1E +#define CMU_HS_M_S1_S14 0x0A2C +#define CMU_HS_M_GL 0x0A3A +#define CMU_HS_M_MAXSAT_RGB_Y_L 0x0A3C +#define CMU_HS_M_MAXSAT_RGB_Y_H 0x0A3D +#define CMU_HS_M_MAXSAT_RCR_L 0x0A3E +#define CMU_HS_M_MAXSAT_RCR_H 0x0A3F +#define CMU_HS_M_MAXSAT_RCB_L 0x0A40 +#define CMU_HS_M_MAXSAT_RCB_H 0x0A41 +#define CMU_HS_M_MAXSAT_GCR_L 0x0A42 +#define CMU_HS_M_MAXSAT_GCR_H 0x0A43 +#define CMU_HS_M_MAXSAT_GCB_L 0x0A44 +#define CMU_HS_M_MAXSAT_GCB_H 0x0A45 +#define CMU_HS_M_MAXSAT_BCR_L 0x0A46 +#define CMU_HS_M_MAXSAT_BCR_H 0x0A47 +#define CMU_HS_M_MAXSAT_BCB_L 0x0A48 +#define CMU_HS_M_MAXSAT_BCB_H 0x0A49 +#define CMU_HS_M_ROFF_L 0x0A4A +#define CMU_HS_M_ROFF_H 0x0A4B +#define CMU_HS_M_GOFF_L 0x0A4C +#define CMU_HS_M_GOFF_H 0x0A4D +#define CMU_HS_M_BOFF_L 0x0A4E +#define CMU_HS_M_BOFF_H 0x0A4F +#define CMU_HS_P_EN 0x0A50 +#define CMU_HS_P_AX1_L 0x0A52 +#define CMU_HS_P_AX1_H 0x0A53 +#define CMU_HS_P_AX2_L 0x0A54 +#define CMU_HS_P_AX2_H 0x0A55 +#define CMU_HS_P_AX3_L 0x0A56 +#define CMU_HS_P_AX3_H 0x0A57 +#define CMU_HS_P_AX4_L 0x0A58 +#define CMU_HS_P_AX4_H 0x0A59 +#define CMU_HS_P_AX5_L 0x0A5A +#define CMU_HS_P_AX5_H 0x0A5B +#define CMU_HS_P_AX6_L 0x0A5C +#define CMU_HS_P_AX6_H 0x0A5D +#define CMU_HS_P_AX7_L 0x0A5E +#define CMU_HS_P_AX7_H 0x0A5F +#define CMU_HS_P_AX8_L 0x0A60 +#define CMU_HS_P_AX8_H 0x0A61 +#define CMU_HS_P_AX9_L 0x0A62 +#define CMU_HS_P_AX9_H 0x0A63 +#define CMU_HS_P_AX10_L 0x0A64 +#define CMU_HS_P_AX10_H 0x0A65 +#define CMU_HS_P_AX11_L 0x0A66 +#define CMU_HS_P_AX11_H 0x0A67 +#define CMU_HS_P_AX12_L 0x0A68 +#define CMU_HS_P_AX12_H 0x0A69 +#define CMU_HS_P_AX13_L 0x0A6A +#define CMU_HS_P_AX13_H 0x0A6B +#define CMU_HS_P_AX14_L 0x0A6C +#define CMU_HS_P_AX14_H 0x0A6D +#define CMU_HS_P_H1_H14 0x0A6E +#define CMU_HS_P_S1_S14 0x0A7C +#define CMU_HS_P_GL 0x0A8A +#define CMU_HS_P_MAXSAT_RGB_Y_L 0x0A8C +#define CMU_HS_P_MAXSAT_RGB_Y_H 0x0A8D +#define CMU_HS_P_MAXSAT_RCR_L 0x0A8E +#define CMU_HS_P_MAXSAT_RCR_H 0x0A8F +#define CMU_HS_P_MAXSAT_RCB_L 0x0A90 +#define CMU_HS_P_MAXSAT_RCB_H 0x0A91 +#define CMU_HS_P_MAXSAT_GCR_L 0x0A92 +#define CMU_HS_P_MAXSAT_GCR_H 0x0A93 +#define CMU_HS_P_MAXSAT_GCB_L 0x0A94 +#define CMU_HS_P_MAXSAT_GCB_H 0x0A95 +#define CMU_HS_P_MAXSAT_BCR_L 0x0A96 +#define CMU_HS_P_MAXSAT_BCR_H 0x0A97 +#define CMU_HS_P_MAXSAT_BCB_L 0x0A98 +#define CMU_HS_P_MAXSAT_BCB_H 0x0A99 +#define CMU_HS_P_ROFF_L 0x0A9A +#define CMU_HS_P_ROFF_H 0x0A9B +#define CMU_HS_P_GOFF_L 0x0A9C +#define CMU_HS_P_GOFF_H 0x0A9D +#define CMU_HS_P_BOFF_L 0x0A9E +#define CMU_HS_P_BOFF_H 0x0A9F +#define CMU_GLCSC_M_C0_L 0x0AA0 +#define CMU_GLCSC_M_C0_H 0x0AA1 +#define CMU_GLCSC_M_C1_L 0x0AA2 +#define CMU_GLCSC_M_C1_H 0x0AA3 +#define CMU_GLCSC_M_C2_L 0x0AA4 +#define CMU_GLCSC_M_C2_H 0x0AA5 +#define CMU_GLCSC_M_C3_L 0x0AA6 +#define CMU_GLCSC_M_C3_H 0x0AA7 +#define CMU_GLCSC_M_C4_L 0x0AA8 +#define CMU_GLCSC_M_C4_H 0x0AA9 +#define CMU_GLCSC_M_C5_L 0x0AAA +#define CMU_GLCSC_M_C5_H 0x0AAB +#define CMU_GLCSC_M_C6_L 0x0AAC +#define CMU_GLCSC_M_C6_H 0x0AAD +#define CMU_GLCSC_M_C7_L 0x0AAE +#define CMU_GLCSC_M_C7_H 0x0AAF +#define CMU_GLCSC_M_C8_L 0x0AB0 +#define CMU_GLCSC_M_C8_H 0x0AB1 +#define CMU_GLCSC_M_O1_1 0x0AB4 +#define CMU_GLCSC_M_O1_2 0x0AB5 +#define CMU_GLCSC_M_O1_3 0x0AB6 +#define CMU_GLCSC_M_O2_1 0x0AB8 +#define CMU_GLCSC_M_O2_2 0x0AB9 +#define CMU_GLCSC_M_O2_3 0x0ABA +#define CMU_GLCSC_M_O3_1 0x0ABC +#define CMU_GLCSC_M_O3_2 0x0ABD +#define CMU_GLCSC_M_O3_3 0x0ABE +#define CMU_GLCSC_P_C0_L 0x0AC0 +#define CMU_GLCSC_P_C0_H 0x0AC1 +#define CMU_GLCSC_P_C1_L 0x0AC2 +#define CMU_GLCSC_P_C1_H 0x0AC3 +#define CMU_GLCSC_P_C2_L 0x0AC4 +#define CMU_GLCSC_P_C2_H 0x0AC5 +#define CMU_GLCSC_P_C3_L 0x0AC6 +#define CMU_GLCSC_P_C3_H 0x0AC7 +#define CMU_GLCSC_P_C4_L 0x0AC8 +#define CMU_GLCSC_P_C4_H 0x0AC9 +#define CMU_GLCSC_P_C5_L 0x0ACA +#define CMU_GLCSC_P_C5_H 0x0ACB +#define CMU_GLCSC_P_C6_L 0x0ACC +#define CMU_GLCSC_P_C6_H 0x0ACD +#define CMU_GLCSC_P_C7_L 0x0ACE +#define CMU_GLCSC_P_C7_H 0x0ACF +#define CMU_GLCSC_P_C8_L 0x0AD0 +#define CMU_GLCSC_P_C8_H 0x0AD1 +#define CMU_GLCSC_P_O1_1 0x0AD4 +#define CMU_GLCSC_P_O1_2 0x0AD5 +#define CMU_GLCSC_P_O1_3 0x0AD6 +#define CMU_GLCSC_P_O2_1 0x0AD8 +#define CMU_GLCSC_P_O2_2 0x0AD9 +#define CMU_GLCSC_P_O2_3 0x0ADA +#define CMU_GLCSC_P_O3_1 0x0ADC +#define CMU_GLCSC_P_O3_2 0x0ADD +#define CMU_GLCSC_P_O3_3 0x0ADE +#define CMU_PIXVAL_M_EN 0x0AE0 +#define CMU_PIXVAL_P_EN 0x0AE1 + +#define CMU_CLK_CTRL_TCLK 0x0 +#define CMU_CLK_CTRL_SCLK 0x2 +#define CMU_CLK_CTRL_MSK 0x2 +#define CMU_CLK_CTRL_ENABLE 0x1 + +#define LCD_TOP_CTRL_TV 0x2 +#define LCD_TOP_CTRL_PN 0x0 +#define LCD_TOP_CTRL_SEL_MSK 0x2 +#define LCD_IO_CMU_IN_SEL_MSK (0x3 << 20) +#define LCD_IO_CMU_IN_SEL_TV 0 +#define LCD_IO_CMU_IN_SEL_PN 1 +#define LCD_IO_CMU_IN_SEL_PN2 2 +#define LCD_IO_TV_OUT_SEL_MSK (0x3 << 26) +#define LCD_IO_PN_OUT_SEL_MSK (0x3 << 24) +#define LCD_IO_PN2_OUT_SEL_MSK (0x3 << 28) +#define LCD_IO_TV_OUT_SEL_NON 3 +#define LCD_IO_PN_OUT_SEL_NON 3 +#define LCD_IO_PN2_OUT_SEL_NON 3 +#define LCD_TOP_CTRL_CMU_ENABLE 0x1 +#define LCD_IO_OVERL_MSK 0xC00000 +#define LCD_IO_OVERL_TV 0x0 +#define LCD_IO_OVERL_LCD1 0x400000 +#define LCD_IO_OVERL_LCD2 0xC00000 +#define HINVERT_MSK 0x4 +#define VINVERT_MSK 0x8 +#define HINVERT_LEN 0x2 +#define VINVERT_LEN 0x3 + +#define CMU_CTRL 0x88 +#define CMU_CTRL_A0_MSK 0x6 +#define CMU_CTRL_A0_TV 0x0 +#define CMU_CTRL_A0_LCD1 0x1 +#define CMU_CTRL_A0_LCD2 0x2 +#define CMU_CTRL_A0_HDMI 0x3 + +#define ICR_DRV_ROUTE_OFF 0x0 +#define ICR_DRV_ROUTE_TV 0x1 +#define ICR_DRV_ROUTE_LCD1 0x2 +#define ICR_DRV_ROUTE_LCD2 0x3 + +enum { + PATH_PN = 0, + PATH_TV, + PATH_P2, +}; + +/* + * mmp path describes part of mmp path related info: + * which is hiden in display driver and not exported to buffer driver + */ +struct mmphw_ctrl; +struct mmphw_path_plat { + int id; + struct mmphw_ctrl *ctrl; + struct mmp_path *path; + u32 path_config; + u32 link_config; +}; + +/* mmp ctrl describes mmp controller related info */ +struct mmphw_ctrl { + /* platform related, get from config */ + const char *name; + int irq; + void *reg_base; + struct clk *clk; + + /* sys info */ + struct device *dev; + + /* state */ + int open_count; + int status; + struct mutex access_ok; + + /*pathes*/ + int path_num; + struct mmphw_path_plat path_plats[0]; +}; + +static inline int overlay_is_vid(struct mmp_overlay *overlay) +{ + return overlay->dmafetch_id & 1; +} + +static inline struct mmphw_path_plat *path_to_path_plat(struct mmp_path *path) +{ + return (struct mmphw_path_plat *)path->plat_data; +} + +static inline struct mmphw_ctrl *path_to_ctrl(struct mmp_path *path) +{ + return path_to_path_plat(path)->ctrl; +} + +static inline struct mmphw_ctrl *overlay_to_ctrl(struct mmp_overlay *overlay) +{ + return path_to_ctrl(overlay->path); +} + +static inline void *ctrl_regs(struct mmp_path *path) +{ + return path_to_ctrl(path)->reg_base; +} + +/* path regs, for regs symmetrical for both pathes */ +static inline struct lcd_regs *path_regs(struct mmp_path *path) +{ + if (path->id == PATH_PN) + return (struct lcd_regs *)(ctrl_regs(path) + 0xc0); + else if (path->id == PATH_TV) + return (struct lcd_regs *)ctrl_regs(path); + else if (path->id == PATH_P2) + return (struct lcd_regs *)(ctrl_regs(path) + 0x200); + else { + dev_err(path->dev, "path id %d invalid\n", path->id); + BUG_ON(1); + return NULL; + } +} + +#ifdef CONFIG_MMP_DISP_SPI +extern int lcd_spi_register(struct mmphw_ctrl *ctrl); +#endif +#endif /* _MMP_CTRL_H_ */ diff --git a/drivers/video/mmp/hw/mmp_spi.c b/drivers/video/mmp/hw/mmp_spi.c new file mode 100644 index 000000000000..e62ca7bf0d5e --- /dev/null +++ b/drivers/video/mmp/hw/mmp_spi.c @@ -0,0 +1,180 @@ +/* + * linux/drivers/video/mmp/hw/mmp_spi.c + * using the spi in LCD controler for commands send + * + * Copyright (C) 2012 Marvell Technology Group Ltd. + * Authors: Guoqing Li <ligq@marvell.com> + * Lisa Du <cldu@marvell.com> + * Zhou Zhu <zzhu3@marvell.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + * + */ +#include <linux/errno.h> +#include <linux/delay.h> +#include <linux/err.h> +#include <linux/io.h> +#include <linux/spi/spi.h> +#include "mmp_ctrl.h" + +/** + * spi_write - write command to the SPI port + * @data: can be 8/16/32-bit, MSB justified data to write. + * @len: data length. + * + * Wait bus transfer complete IRQ. + * The caller is expected to perform the necessary locking. + * + * Returns: + * %-ETIMEDOUT timeout occurred + * 0 success + */ +static inline int lcd_spi_write(struct spi_device *spi, u32 data) +{ + int timeout = 100000, isr, ret = 0; + u32 tmp; + void *reg_base = + *(void **)spi_master_get_devdata(spi->master); + + /* clear ISR */ + writel_relaxed(~SPI_IRQ_MASK, reg_base + SPU_IRQ_ISR); + + switch (spi->bits_per_word) { + case 8: + writel_relaxed((u8)data, reg_base + LCD_SPU_SPI_TXDATA); + break; + case 16: + writel_relaxed((u16)data, reg_base + LCD_SPU_SPI_TXDATA); + break; + case 32: + writel_relaxed((u32)data, reg_base + LCD_SPU_SPI_TXDATA); + break; + default: + dev_err(&spi->dev, "Wrong spi bit length\n"); + } + + /* SPI start to send command */ + tmp = readl_relaxed(reg_base + LCD_SPU_SPI_CTRL); + tmp &= ~CFG_SPI_START_MASK; + tmp |= CFG_SPI_START(1); + writel(tmp, reg_base + LCD_SPU_SPI_CTRL); + + isr = readl_relaxed(reg_base + SPU_IRQ_ISR); + while (!(isr & SPI_IRQ_ENA_MASK)) { + udelay(100); + isr = readl_relaxed(reg_base + SPU_IRQ_ISR); + if (!--timeout) { + ret = -ETIMEDOUT; + dev_err(&spi->dev, "spi cmd send time out\n"); + break; + } + } + + tmp = readl_relaxed(reg_base + LCD_SPU_SPI_CTRL); + tmp &= ~CFG_SPI_START_MASK; + tmp |= CFG_SPI_START(0); + writel_relaxed(tmp, reg_base + LCD_SPU_SPI_CTRL); + + writel_relaxed(~SPI_IRQ_MASK, reg_base + SPU_IRQ_ISR); + + return ret; +} + +static int lcd_spi_setup(struct spi_device *spi) +{ + void *reg_base = + *(void **)spi_master_get_devdata(spi->master); + u32 tmp; + + tmp = CFG_SCLKCNT(16) | + CFG_TXBITS(spi->bits_per_word) | + CFG_SPI_SEL(1) | CFG_SPI_ENA(1) | + CFG_SPI_3W4WB(1); + writel(tmp, reg_base + LCD_SPU_SPI_CTRL); + + /* + * After set mode it need a time to pull up the spi singals, + * or it would cause the wrong waveform when send spi command, + * especially on pxa910h + */ + tmp = readl_relaxed(reg_base + SPU_IOPAD_CONTROL); + if ((tmp & CFG_IOPADMODE_MASK) != IOPAD_DUMB18SPI) + writel_relaxed(IOPAD_DUMB18SPI | + (tmp & ~CFG_IOPADMODE_MASK), + reg_base + SPU_IOPAD_CONTROL); + udelay(20); + return 0; +} + +static int lcd_spi_one_transfer(struct spi_device *spi, struct spi_message *m) +{ + struct spi_transfer *t; + int i; + + list_for_each_entry(t, &m->transfers, transfer_list) { + switch (spi->bits_per_word) { + case 8: + for (i = 0; i < t->len; i++) + lcd_spi_write(spi, ((u8 *)t->tx_buf)[i]); + break; + case 16: + for (i = 0; i < t->len/2; i++) + lcd_spi_write(spi, ((u16 *)t->tx_buf)[i]); + break; + case 32: + for (i = 0; i < t->len/4; i++) + lcd_spi_write(spi, ((u32 *)t->tx_buf)[i]); + break; + default: + dev_err(&spi->dev, "Wrong spi bit length\n"); + } + } + + m->status = 0; + if (m->complete) + m->complete(m->context); + return 0; +} + +int lcd_spi_register(struct mmphw_ctrl *ctrl) +{ + struct spi_master *master; + void **p_regbase; + int err; + + master = spi_alloc_master(ctrl->dev, sizeof(void *)); + if (!master) { + dev_err(ctrl->dev, "unable to allocate SPI master\n"); + return -ENOMEM; + } + p_regbase = spi_master_get_devdata(master); + *p_regbase = ctrl->reg_base; + + /* set bus num to 5 to avoid conflict with other spi hosts */ + master->bus_num = 5; + master->num_chipselect = 1; + master->setup = lcd_spi_setup; + master->transfer = lcd_spi_one_transfer; + + err = spi_register_master(master); + if (err < 0) { + dev_err(ctrl->dev, "unable to register SPI master\n"); + spi_master_put(master); + return err; + } + + dev_info(&master->dev, "registered\n"); + + return 0; +} diff --git a/drivers/video/mmp/panel/Kconfig b/drivers/video/mmp/panel/Kconfig new file mode 100644 index 000000000000..4b2c4f457b11 --- /dev/null +++ b/drivers/video/mmp/panel/Kconfig @@ -0,0 +1,6 @@ +config MMP_PANEL_TPOHVGA + bool "tpohvga panel TJ032MD01BW support" + depends on SPI_MASTER + default n + help + tpohvga panel support diff --git a/drivers/video/mmp/panel/Makefile b/drivers/video/mmp/panel/Makefile new file mode 100644 index 000000000000..2f91611c7e5e --- /dev/null +++ b/drivers/video/mmp/panel/Makefile @@ -0,0 +1 @@ +obj-$(CONFIG_MMP_PANEL_TPOHVGA) += tpo_tj032md01bw.o diff --git a/drivers/video/mmp/panel/tpo_tj032md01bw.c b/drivers/video/mmp/panel/tpo_tj032md01bw.c new file mode 100644 index 000000000000..998978b08f5e --- /dev/null +++ b/drivers/video/mmp/panel/tpo_tj032md01bw.c @@ -0,0 +1,186 @@ +/* + * linux/drivers/video/mmp/panel/tpo_tj032md01bw.c + * active panel using spi interface to do init + * + * Copyright (C) 2012 Marvell Technology Group Ltd. + * Authors: Guoqing Li <ligq@marvell.com> + * Lisa Du <cldu@marvell.com> + * Zhou Zhu <zzhu3@marvell.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + * + */ + +#include <linux/module.h> +#include <linux/moduleparam.h> +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/string.h> +#include <linux/delay.h> +#include <linux/platform_device.h> +#include <linux/err.h> +#include <linux/spi/spi.h> +#include <video/mmp_disp.h> + +static u16 init[] = { + 0x0801, + 0x0800, + 0x0200, + 0x0304, + 0x040e, + 0x0903, + 0x0b18, + 0x0c53, + 0x0d01, + 0x0ee0, + 0x0f01, + 0x1058, + 0x201e, + 0x210a, + 0x220a, + 0x231e, + 0x2400, + 0x2532, + 0x2600, + 0x27ac, + 0x2904, + 0x2aa2, + 0x2b45, + 0x2c45, + 0x2d15, + 0x2e5a, + 0x2fff, + 0x306b, + 0x310d, + 0x3248, + 0x3382, + 0x34bd, + 0x35e7, + 0x3618, + 0x3794, + 0x3801, + 0x395d, + 0x3aae, + 0x3bff, + 0x07c9, +}; + +static u16 poweroff[] = { + 0x07d9, +}; + +struct tpohvga_plat_data { + void (*plat_onoff)(int status); + struct spi_device *spi; +}; + +static void tpohvga_onoff(struct mmp_panel *panel, int status) +{ + struct tpohvga_plat_data *plat = panel->plat_data; + int ret; + + if (status) { + plat->plat_onoff(1); + + ret = spi_write(plat->spi, init, sizeof(init)); + if (ret < 0) + dev_warn(panel->dev, "init cmd failed(%d)\n", ret); + } else { + ret = spi_write(plat->spi, poweroff, sizeof(poweroff)); + if (ret < 0) + dev_warn(panel->dev, "poweroff cmd failed(%d)\n", ret); + + plat->plat_onoff(0); + } +} + +static struct mmp_mode mmp_modes_tpohvga[] = { + [0] = { + .pixclock_freq = 10394400, + .refresh = 60, + .xres = 320, + .yres = 480, + .hsync_len = 10, + .left_margin = 15, + .right_margin = 10, + .vsync_len = 2, + .upper_margin = 4, + .lower_margin = 2, + .invert_pixclock = 1, + .pix_fmt_out = PIXFMT_RGB565, + }, +}; + +static int tpohvga_get_modelist(struct mmp_panel *panel, + struct mmp_mode **modelist) +{ + *modelist = mmp_modes_tpohvga; + return 1; +} + +static struct mmp_panel panel_tpohvga = { + .name = "tpohvga", + .panel_type = PANELTYPE_ACTIVE, + .get_modelist = tpohvga_get_modelist, + .set_onoff = tpohvga_onoff, +}; + +static int tpohvga_probe(struct spi_device *spi) +{ + struct mmp_mach_panel_info *mi; + int ret; + struct tpohvga_plat_data *plat_data; + + /* get configs from platform data */ + mi = spi->dev.platform_data; + if (mi == NULL) { + dev_err(&spi->dev, "%s: no platform data defined\n", __func__); + return -EINVAL; + } + + /* setup spi related info */ + spi->bits_per_word = 16; + ret = spi_setup(spi); + if (ret < 0) { + dev_err(&spi->dev, "spi setup failed %d", ret); + return ret; + } + + plat_data = kzalloc(sizeof(*plat_data), GFP_KERNEL); + if (plat_data == NULL) + return -ENOMEM; + + plat_data->spi = spi; + plat_data->plat_onoff = mi->plat_set_onoff; + panel_tpohvga.plat_data = plat_data; + panel_tpohvga.plat_path_name = mi->plat_path_name; + panel_tpohvga.dev = &spi->dev; + + mmp_register_panel(&panel_tpohvga); + + return 0; +} + +static struct spi_driver panel_tpohvga_driver = { + .driver = { + .name = "tpo-hvga", + .owner = THIS_MODULE, + }, + .probe = tpohvga_probe, +}; +module_spi_driver(panel_tpohvga_driver); + +MODULE_AUTHOR("Lisa Du<cldu@marvell.com>"); +MODULE_DESCRIPTION("Panel driver for tpohvga"); +MODULE_LICENSE("GPL"); diff --git a/drivers/w1/slaves/Kconfig b/drivers/w1/slaves/Kconfig index 67526690acbc..762561fbabbf 100644 --- a/drivers/w1/slaves/Kconfig +++ b/drivers/w1/slaves/Kconfig @@ -17,11 +17,16 @@ config W1_SLAVE_SMEM simple 64bit memory rom(ds2401/ds2411/ds1990*) to your wire. config W1_SLAVE_DS2408 - tristate "8-Channel Addressable Switch (IO Expander) 0x29 family support (DS2408)" - help - Say Y here if you want to use a 1-wire + tristate "8-Channel Addressable Switch (IO Expander) 0x29 family support (DS2408)" + help + Say Y here if you want to use a 1-wire + DS2408 8-Channel Addressable Switch device support - DS2408 8-Channel Addressable Switch device support +config W1_SLAVE_DS2413 + tristate "Dual Channel Addressable Switch 0x3a family support (DS2413)" + help + Say Y here if you want to use a 1-wire + DS2413 Dual Channel Addressable Switch device support config W1_SLAVE_DS2423 tristate "Counter 1-wire device (DS2423)" diff --git a/drivers/w1/slaves/Makefile b/drivers/w1/slaves/Makefile index 05188f6aab5a..06529f3157ab 100644 --- a/drivers/w1/slaves/Makefile +++ b/drivers/w1/slaves/Makefile @@ -4,7 +4,8 @@ obj-$(CONFIG_W1_SLAVE_THERM) += w1_therm.o obj-$(CONFIG_W1_SLAVE_SMEM) += w1_smem.o -obj-$(CONFIG_W1_SLAVE_DS2408) += w1_ds2408.o +obj-$(CONFIG_W1_SLAVE_DS2408) += w1_ds2408.o +obj-$(CONFIG_W1_SLAVE_DS2413) += w1_ds2413.o obj-$(CONFIG_W1_SLAVE_DS2423) += w1_ds2423.o obj-$(CONFIG_W1_SLAVE_DS2431) += w1_ds2431.o obj-$(CONFIG_W1_SLAVE_DS2433) += w1_ds2433.o diff --git a/drivers/w1/slaves/w1_ds2413.c b/drivers/w1/slaves/w1_ds2413.c new file mode 100644 index 000000000000..829786252c6b --- /dev/null +++ b/drivers/w1/slaves/w1_ds2413.c @@ -0,0 +1,177 @@ +/* + * w1_ds2413.c - w1 family 3a (DS2413) driver + * based on w1_ds2408.c by Jean-Francois Dagenais <dagenaisj@sonatest.com> + * + * Copyright (c) 2013 Mariusz Bialonczyk <manio@skyboo.net> + * + * This source code is licensed under the GNU General Public License, + * Version 2. See the file COPYING for more details. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/moduleparam.h> +#include <linux/device.h> +#include <linux/types.h> +#include <linux/delay.h> +#include <linux/slab.h> + +#include "../w1.h" +#include "../w1_int.h" +#include "../w1_family.h" + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Mariusz Bialonczyk <manio@skyboo.net>"); +MODULE_DESCRIPTION("w1 family 3a driver for DS2413 2 Pin IO"); + +#define W1_F3A_RETRIES 3 +#define W1_F3A_FUNC_PIO_ACCESS_READ 0xF5 +#define W1_F3A_FUNC_PIO_ACCESS_WRITE 0x5A +#define W1_F3A_SUCCESS_CONFIRM_BYTE 0xAA + +static ssize_t w1_f3a_read_state( + struct file *filp, struct kobject *kobj, + struct bin_attribute *bin_attr, + char *buf, loff_t off, size_t count) +{ + struct w1_slave *sl = kobj_to_w1_slave(kobj); + dev_dbg(&sl->dev, + "Reading %s kobj: %p, off: %0#10x, count: %zu, buff addr: %p", + bin_attr->attr.name, kobj, (unsigned int)off, count, buf); + + if (off != 0) + return 0; + if (!buf) + return -EINVAL; + + mutex_lock(&sl->master->bus_mutex); + dev_dbg(&sl->dev, "mutex locked"); + + if (w1_reset_select_slave(sl)) { + mutex_unlock(&sl->master->bus_mutex); + return -EIO; + } + + w1_write_8(sl->master, W1_F3A_FUNC_PIO_ACCESS_READ); + *buf = w1_read_8(sl->master); + + mutex_unlock(&sl->master->bus_mutex); + dev_dbg(&sl->dev, "mutex unlocked"); + + /* check for correct complement */ + if ((*buf & 0x0F) != ((~*buf >> 4) & 0x0F)) + return -EIO; + else + return 1; +} + +static ssize_t w1_f3a_write_output( + struct file *filp, struct kobject *kobj, + struct bin_attribute *bin_attr, + char *buf, loff_t off, size_t count) +{ + struct w1_slave *sl = kobj_to_w1_slave(kobj); + u8 w1_buf[3]; + unsigned int retries = W1_F3A_RETRIES; + + if (count != 1 || off != 0) + return -EFAULT; + + dev_dbg(&sl->dev, "locking mutex for write_output"); + mutex_lock(&sl->master->bus_mutex); + dev_dbg(&sl->dev, "mutex locked"); + + if (w1_reset_select_slave(sl)) + goto error; + + /* according to the DS2413 datasheet the most significant 6 bits + should be set to "1"s, so do it now */ + *buf = *buf | 0xFC; + + while (retries--) { + w1_buf[0] = W1_F3A_FUNC_PIO_ACCESS_WRITE; + w1_buf[1] = *buf; + w1_buf[2] = ~(*buf); + w1_write_block(sl->master, w1_buf, 3); + + if (w1_read_8(sl->master) == W1_F3A_SUCCESS_CONFIRM_BYTE) { + mutex_unlock(&sl->master->bus_mutex); + dev_dbg(&sl->dev, "mutex unlocked, retries:%d", retries); + return 1; + } + if (w1_reset_resume_command(sl->master)) + goto error; + } + +error: + mutex_unlock(&sl->master->bus_mutex); + dev_dbg(&sl->dev, "mutex unlocked in error, retries:%d", retries); + return -EIO; +} + +#define NB_SYSFS_BIN_FILES 2 +static struct bin_attribute w1_f3a_sysfs_bin_files[NB_SYSFS_BIN_FILES] = { + { + .attr = { + .name = "state", + .mode = S_IRUGO, + }, + .size = 1, + .read = w1_f3a_read_state, + }, + { + .attr = { + .name = "output", + .mode = S_IRUGO | S_IWUSR | S_IWGRP, + }, + .size = 1, + .write = w1_f3a_write_output, + } +}; + +static int w1_f3a_add_slave(struct w1_slave *sl) +{ + int err = 0; + int i; + + for (i = 0; i < NB_SYSFS_BIN_FILES && !err; ++i) + err = sysfs_create_bin_file( + &sl->dev.kobj, + &(w1_f3a_sysfs_bin_files[i])); + if (err) + while (--i >= 0) + sysfs_remove_bin_file(&sl->dev.kobj, + &(w1_f3a_sysfs_bin_files[i])); + return err; +} + +static void w1_f3a_remove_slave(struct w1_slave *sl) +{ + int i; + for (i = NB_SYSFS_BIN_FILES - 1; i >= 0; --i) + sysfs_remove_bin_file(&sl->dev.kobj, + &(w1_f3a_sysfs_bin_files[i])); +} + +static struct w1_family_ops w1_f3a_fops = { + .add_slave = w1_f3a_add_slave, + .remove_slave = w1_f3a_remove_slave, +}; + +static struct w1_family w1_family_3a = { + .fid = W1_FAMILY_DS2413, + .fops = &w1_f3a_fops, +}; + +static int __init w1_f3a_init(void) +{ + return w1_register_family(&w1_family_3a); +} + +static void __exit w1_f3a_exit(void) +{ + w1_unregister_family(&w1_family_3a); +} + +module_init(w1_f3a_init); +module_exit(w1_f3a_exit); diff --git a/drivers/w1/w1_family.h b/drivers/w1/w1_family.h index a1f0ce151d53..625dd08f775f 100644 --- a/drivers/w1/w1_family.h +++ b/drivers/w1/w1_family.h @@ -39,6 +39,7 @@ #define W1_EEPROM_DS2431 0x2D #define W1_FAMILY_DS2760 0x30 #define W1_FAMILY_DS2780 0x32 +#define W1_FAMILY_DS2413 0x3A #define W1_THERM_DS1825 0x3B #define W1_FAMILY_DS2781 0x3D #define W1_THERM_DS28EA00 0x42 diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index 0ad61c6a65a5..055562c580b4 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -33,6 +33,7 @@ #include <linux/pagemap.h> #include <linux/idr.h> #include <linux/sched.h> +#include <linux/aio.h> #include <net/9p/9p.h> #include <net/9p/client.h> diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index c2483e97beee..357260be9244 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -620,6 +620,7 @@ v9fs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) lock_page(page); if (page->mapping != inode->i_mapping) goto out_unlock; + wait_for_stable_page(page); return VM_FAULT_LOCKED; out_unlock: diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c index eb82ee53ee0b..d9a43674cb94 100644 --- a/fs/affs/amigaffs.c +++ b/fs/affs/amigaffs.c @@ -125,9 +125,8 @@ static void affs_fix_dcache(struct inode *inode, u32 entry_ino) { struct dentry *dentry; - struct hlist_node *p; spin_lock(&inode->i_lock); - hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) { if (entry_ino == (u32)(long)dentry->d_fsdata) { dentry->d_fsdata = (void *)inode->i_ino; break; diff --git a/fs/afs/write.c b/fs/afs/write.c index 9aa52d93c73c..5151ea381c08 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -14,6 +14,7 @@ #include <linux/pagemap.h> #include <linux/writeback.h> #include <linux/pagevec.h> +#include <linux/aio.h> #include "internal.h" static int afs_write_back_from_locked_page(struct afs_writeback *wb, @@ -8,6 +8,8 @@ * * See ../COPYING for licensing terms. */ +#define pr_fmt(fmt) "%s: " fmt, __func__ + #include <linux/kernel.h> #include <linux/init.h> #include <linux/errno.h> @@ -18,14 +20,14 @@ #include <linux/backing-dev.h> #include <linux/uio.h> -#define DEBUG 0 - #include <linux/sched.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/mman.h> +#include <linux/bio.h> #include <linux/mmu_context.h> +#include <linux/percpu.h> #include <linux/slab.h> #include <linux/timer.h> #include <linux/aio.h> @@ -35,15 +37,94 @@ #include <linux/eventfd.h> #include <linux/blkdev.h> #include <linux/compat.h> +#include <linux/percpu-refcount.h> #include <asm/kmap_types.h> #include <asm/uaccess.h> -#if DEBUG > 1 -#define dprintk printk -#else -#define dprintk(x...) do { ; } while (0) -#endif +#define AIO_RING_MAGIC 0xa10a10a1 +#define AIO_RING_COMPAT_FEATURES 1 +#define AIO_RING_INCOMPAT_FEATURES 0 +struct aio_ring { + unsigned id; /* kernel internal index number */ + unsigned nr; /* number of io_events */ + unsigned head; + unsigned tail; + + unsigned magic; + unsigned compat_features; + unsigned incompat_features; + unsigned header_length; /* size of aio_ring */ + + + struct io_event io_events[0]; +}; /* 128 bytes + ring size */ + +#define AIO_RING_PAGES 8 + +struct kioctx_cpu { + unsigned reqs_available; +}; + +struct kioctx { + struct percpu_ref users; + + /* This needs improving */ + unsigned long user_id; + struct hlist_node list; + + struct __percpu kioctx_cpu *cpu; + + unsigned req_batch; + + unsigned nr; + + /* sys_io_setup currently limits this to an unsigned int */ + unsigned max_reqs; + + unsigned long mmap_base; + unsigned long mmap_size; + + struct page **ring_pages; + long nr_pages; + + struct rcu_head rcu_head; + struct work_struct rcu_work; + + struct { + atomic_t reqs_available; + } ____cacheline_aligned_in_smp; + + struct { + spinlock_t ctx_lock; + struct list_head active_reqs; /* used for cancellation */ + } ____cacheline_aligned_in_smp; + + struct { + struct mutex ring_lock; + wait_queue_head_t wait; + + /* + * Copy of the real tail, that aio_complete uses - to reduce + * cacheline bouncing. The real tail will tend to be much more + * contended - since typically events are delivered one at a + * time, and then aio_read_events() slurps them up a bunch at a + * time - so it's helpful if aio_read_events() isn't also + * contending for the tail. So, aio_complete() updates + * shadow_tail whenever it updates tail. + * + * Also needed because tail is used as a hacky lock and isn't + * always the real tail. + */ + unsigned shadow_tail; + } ____cacheline_aligned_in_smp; + + struct { + unsigned tail; + } ____cacheline_aligned_in_smp; + + struct page *internal_pages[AIO_RING_PAGES]; +}; /*------ sysctl variables----*/ static DEFINE_SPINLOCK(aio_nr_lock); @@ -54,11 +135,6 @@ unsigned long aio_max_nr = 0x10000; /* system wide maximum number of aio request static struct kmem_cache *kiocb_cachep; static struct kmem_cache *kioctx_cachep; -static struct workqueue_struct *aio_wq; - -static void aio_kick_handler(struct work_struct *); -static void aio_queue_work(struct kioctx *); - /* aio_setup * Creates the slab caches used by the aio routines, panic on * failure as this is done early during the boot sequence. @@ -68,10 +144,7 @@ static int __init aio_setup(void) kiocb_cachep = KMEM_CACHE(kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC); kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC); - aio_wq = alloc_workqueue("aio", 0, 1); /* used to limit concurrency */ - BUG_ON(!aio_wq); - - pr_debug("aio_setup: sizeof(struct page) = %d\n", (int)sizeof(struct page)); + pr_debug("sizeof(struct page) = %zu\n", sizeof(struct page)); return 0; } @@ -79,31 +152,29 @@ __initcall(aio_setup); static void aio_free_ring(struct kioctx *ctx) { - struct aio_ring_info *info = &ctx->ring_info; long i; - for (i=0; i<info->nr_pages; i++) - put_page(info->ring_pages[i]); + for (i = 0; i < ctx->nr_pages; i++) + put_page(ctx->ring_pages[i]); - if (info->mmap_size) { - BUG_ON(ctx->mm != current->mm); - vm_munmap(info->mmap_base, info->mmap_size); - } + if (ctx->mmap_size) + vm_munmap(ctx->mmap_base, ctx->mmap_size); - if (info->ring_pages && info->ring_pages != info->internal_pages) - kfree(info->ring_pages); - info->ring_pages = NULL; - info->nr = 0; + if (ctx->ring_pages && ctx->ring_pages != ctx->internal_pages) + kfree(ctx->ring_pages); } static int aio_setup_ring(struct kioctx *ctx) { struct aio_ring *ring; - struct aio_ring_info *info = &ctx->ring_info; unsigned nr_events = ctx->max_reqs; - unsigned long size; + struct mm_struct *mm = current->mm; + unsigned long size, populate; int nr_pages; + nr_events = max(nr_events, num_possible_cpus() * 4); + nr_events *= 2; + /* Compensate for the ring buffer's head/tail overlap entry */ nr_events += 2; /* 1 is required, 2 for good luck */ @@ -116,43 +187,44 @@ static int aio_setup_ring(struct kioctx *ctx) nr_events = (PAGE_SIZE * nr_pages - sizeof(struct aio_ring)) / sizeof(struct io_event); - info->nr = 0; - info->ring_pages = info->internal_pages; + ctx->nr = 0; + ctx->ring_pages = ctx->internal_pages; if (nr_pages > AIO_RING_PAGES) { - info->ring_pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL); - if (!info->ring_pages) + ctx->ring_pages = kcalloc(nr_pages, sizeof(struct page *), + GFP_KERNEL); + if (!ctx->ring_pages) return -ENOMEM; } - info->mmap_size = nr_pages * PAGE_SIZE; - dprintk("attempting mmap of %lu bytes\n", info->mmap_size); - down_write(&ctx->mm->mmap_sem); - info->mmap_base = do_mmap_pgoff(NULL, 0, info->mmap_size, - PROT_READ|PROT_WRITE, - MAP_ANONYMOUS|MAP_PRIVATE, 0); - if (IS_ERR((void *)info->mmap_base)) { - up_write(&ctx->mm->mmap_sem); - info->mmap_size = 0; + ctx->mmap_size = nr_pages * PAGE_SIZE; + pr_debug("attempting mmap of %lu bytes\n", ctx->mmap_size); + down_write(&mm->mmap_sem); + ctx->mmap_base = do_mmap_pgoff(NULL, 0, ctx->mmap_size, + PROT_READ|PROT_WRITE, + MAP_ANONYMOUS|MAP_PRIVATE, 0, &populate); + if (IS_ERR((void *)ctx->mmap_base)) { + up_write(&mm->mmap_sem); + ctx->mmap_size = 0; aio_free_ring(ctx); return -EAGAIN; } - dprintk("mmap address: 0x%08lx\n", info->mmap_base); - info->nr_pages = get_user_pages(current, ctx->mm, - info->mmap_base, nr_pages, - 1, 0, info->ring_pages, NULL); - up_write(&ctx->mm->mmap_sem); + pr_debug("mmap address: 0x%08lx\n", ctx->mmap_base); + ctx->nr_pages = get_user_pages(current, mm, ctx->mmap_base, nr_pages, + 1, 0, ctx->ring_pages, NULL); + up_write(&mm->mmap_sem); - if (unlikely(info->nr_pages != nr_pages)) { + if (unlikely(ctx->nr_pages != nr_pages)) { aio_free_ring(ctx); return -EAGAIN; } + if (populate) + mm_populate(ctx->mmap_base, populate); - ctx->user_id = info->mmap_base; + ctx->user_id = ctx->mmap_base; + ctx->nr = nr_events; /* trusted copy */ - info->nr = nr_events; /* trusted copy */ - - ring = kmap_atomic(info->ring_pages[0]); + ring = kmap_atomic(ctx->ring_pages[0]); ring->nr = nr_events; /* user copy */ ring->id = ctx->user_id; ring->head = ring->tail = 0; @@ -161,72 +233,142 @@ static int aio_setup_ring(struct kioctx *ctx) ring->incompat_features = AIO_RING_INCOMPAT_FEATURES; ring->header_length = sizeof(struct aio_ring); kunmap_atomic(ring); + flush_dcache_page(ctx->ring_pages[0]); return 0; } - -/* aio_ring_event: returns a pointer to the event at the given index from - * kmap_atomic(). Release the pointer with put_aio_ring_event(); - */ #define AIO_EVENTS_PER_PAGE (PAGE_SIZE / sizeof(struct io_event)) #define AIO_EVENTS_FIRST_PAGE ((PAGE_SIZE - sizeof(struct aio_ring)) / sizeof(struct io_event)) #define AIO_EVENTS_OFFSET (AIO_EVENTS_PER_PAGE - AIO_EVENTS_FIRST_PAGE) -#define aio_ring_event(info, nr) ({ \ - unsigned pos = (nr) + AIO_EVENTS_OFFSET; \ - struct io_event *__event; \ - __event = kmap_atomic( \ - (info)->ring_pages[pos / AIO_EVENTS_PER_PAGE]); \ - __event += pos % AIO_EVENTS_PER_PAGE; \ - __event; \ -}) - -#define put_aio_ring_event(event) do { \ - struct io_event *__event = (event); \ - (void)__event; \ - kunmap_atomic((void *)((unsigned long)__event & PAGE_MASK)); \ -} while(0) - -static void ctx_rcu_free(struct rcu_head *head) +void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel) +{ + struct kioctx *ctx = req->ki_ctx; + unsigned long flags; + + spin_lock_irqsave(&ctx->ctx_lock, flags); + + if (!req->ki_list.next) + list_add(&req->ki_list, &ctx->active_reqs); + + req->ki_cancel = cancel; + + spin_unlock_irqrestore(&ctx->ctx_lock, flags); +} +EXPORT_SYMBOL(kiocb_set_cancel_fn); + +static int kiocb_cancel(struct kioctx *ctx, struct kiocb *kiocb, + struct io_event *res) +{ + kiocb_cancel_fn *old, *cancel; + int ret = -EINVAL; + + /* + * Don't want to set kiocb->ki_cancel = KIOCB_CANCELLED unless it + * actually has a cancel function, hence the cmpxchg() + */ + + cancel = ACCESS_ONCE(kiocb->ki_cancel); + do { + if (!cancel || cancel == KIOCB_CANCELLED) + return ret; + + old = cancel; + cancel = cmpxchg(&kiocb->ki_cancel, old, KIOCB_CANCELLED); + } while (cancel != old); + + atomic_inc(&kiocb->ki_users); + spin_unlock_irq(&ctx->ctx_lock); + + memset(res, 0, sizeof(*res)); + res->obj = (u64)(unsigned long)kiocb->ki_obj.user; + res->data = kiocb->ki_user_data; + ret = cancel(kiocb, res); + + spin_lock_irq(&ctx->ctx_lock); + + return ret; +} + +static void free_ioctx_rcu(struct rcu_head *head) { struct kioctx *ctx = container_of(head, struct kioctx, rcu_head); + + free_percpu(ctx->cpu); kmem_cache_free(kioctx_cachep, ctx); } -/* __put_ioctx - * Called when the last user of an aio context has gone away, - * and the struct needs to be freed. +/* + * When this function runs, the kioctx has been removed from the "hash table" + * and ctx->users has dropped to 0, so we know no more kiocbs can be submitted - + * now it's safe to cancel any that need to be. */ -static void __put_ioctx(struct kioctx *ctx) +static void free_ioctx(struct kioctx *ctx) { - unsigned nr_events = ctx->max_reqs; - BUG_ON(ctx->reqs_active); + struct aio_ring *ring; + struct io_event res; + struct kiocb *req; + unsigned cpu, head, avail; - cancel_delayed_work_sync(&ctx->wq); - aio_free_ring(ctx); - mmdrop(ctx->mm); - ctx->mm = NULL; - if (nr_events) { - spin_lock(&aio_nr_lock); - BUG_ON(aio_nr - nr_events > aio_nr); - aio_nr -= nr_events; - spin_unlock(&aio_nr_lock); + spin_lock_irq(&ctx->ctx_lock); + + while (!list_empty(&ctx->active_reqs)) { + req = list_first_entry(&ctx->active_reqs, + struct kiocb, ki_list); + + list_del_init(&req->ki_list); + kiocb_cancel(ctx, req, &res); } - pr_debug("__put_ioctx: freeing %p\n", ctx); - call_rcu(&ctx->rcu_head, ctx_rcu_free); -} -static inline int try_get_ioctx(struct kioctx *kioctx) -{ - return atomic_inc_not_zero(&kioctx->users); + spin_unlock_irq(&ctx->ctx_lock); + + for_each_possible_cpu(cpu) { + struct kioctx_cpu *kcpu = per_cpu_ptr(ctx->cpu, cpu); + + atomic_add(kcpu->reqs_available, &ctx->reqs_available); + kcpu->reqs_available = 0; + } + + ring = kmap_atomic(ctx->ring_pages[0]); + head = ring->head; + kunmap_atomic(ring); + + while (atomic_read(&ctx->reqs_available) < ctx->nr) { + wait_event(ctx->wait, head != ctx->shadow_tail); + + avail = (head < ctx->shadow_tail ? ctx->shadow_tail : ctx->nr) - head; + + atomic_add(avail, &ctx->reqs_available); + head += avail; + head %= ctx->nr; + } + + WARN_ON(atomic_read(&ctx->reqs_available) > ctx->nr); + + aio_free_ring(ctx); + + spin_lock(&aio_nr_lock); + BUG_ON(aio_nr - ctx->max_reqs > aio_nr); + aio_nr -= ctx->max_reqs; + spin_unlock(&aio_nr_lock); + + pr_debug("freeing %p\n", ctx); + + /* + * Here the call_rcu() is between the wait_event() for reqs_active to + * hit 0, and freeing the ioctx. + * + * aio_complete() decrements reqs_active, but it has to touch the ioctx + * after to issue a wakeup so we use rcu. + */ + call_rcu(&ctx->rcu_head, free_ioctx_rcu); } -static inline void put_ioctx(struct kioctx *kioctx) +static void put_ioctx(struct kioctx *ctx) { - BUG_ON(atomic_read(&kioctx->users) <= 0); - if (unlikely(atomic_dec_and_test(&kioctx->users))) - __put_ioctx(kioctx); + if (percpu_ref_put(&ctx->users)) + free_ioctx(ctx); } /* ioctx_alloc @@ -234,7 +376,7 @@ static inline void put_ioctx(struct kioctx *kioctx) */ static struct kioctx *ioctx_alloc(unsigned nr_events) { - struct mm_struct *mm; + struct mm_struct *mm = current->mm; struct kioctx *ctx; int err = -ENOMEM; @@ -253,21 +395,29 @@ static struct kioctx *ioctx_alloc(unsigned nr_events) return ERR_PTR(-ENOMEM); ctx->max_reqs = nr_events; - mm = ctx->mm = current->mm; - atomic_inc(&mm->mm_count); - atomic_set(&ctx->users, 2); + percpu_ref_init(&ctx->users); + rcu_read_lock(); + percpu_ref_get(&ctx->users); + rcu_read_unlock(); + spin_lock_init(&ctx->ctx_lock); - spin_lock_init(&ctx->ring_info.ring_lock); + mutex_init(&ctx->ring_lock); init_waitqueue_head(&ctx->wait); INIT_LIST_HEAD(&ctx->active_reqs); - INIT_LIST_HEAD(&ctx->run_list); - INIT_DELAYED_WORK(&ctx->wq, aio_kick_handler); - if (aio_setup_ring(ctx) < 0) + ctx->cpu = alloc_percpu(struct kioctx_cpu); + if (!ctx->cpu) goto out_freectx; + if (aio_setup_ring(ctx) < 0) + goto out_freepcpu; + + atomic_set(&ctx->reqs_available, ctx->nr); + ctx->req_batch = ctx->nr / (num_possible_cpus() * 4); + BUG_ON(!ctx->req_batch); + /* limit the number of system wide aios */ spin_lock(&aio_nr_lock); if (aio_nr + nr_events > aio_max_nr || @@ -283,64 +433,58 @@ static struct kioctx *ioctx_alloc(unsigned nr_events) hlist_add_head_rcu(&ctx->list, &mm->ioctx_list); spin_unlock(&mm->ioctx_lock); - dprintk("aio: allocated ioctx %p[%ld]: mm=%p mask=0x%x\n", - ctx, ctx->user_id, current->mm, ctx->ring_info.nr); + pr_debug("allocated ioctx %p[%ld]: mm=%p mask=0x%x\n", + ctx, ctx->user_id, mm, ctx->nr); return ctx; out_cleanup: err = -EAGAIN; aio_free_ring(ctx); +out_freepcpu: + free_percpu(ctx->cpu); out_freectx: - mmdrop(mm); kmem_cache_free(kioctx_cachep, ctx); - dprintk("aio: error allocating ioctx %d\n", err); + pr_debug("error allocating ioctx %d\n", err); return ERR_PTR(err); } -/* kill_ctx - * Cancels all outstanding aio requests on an aio context. Used - * when the processes owning a context have all exited to encourage - * the rapid destruction of the kioctx. - */ -static void kill_ctx(struct kioctx *ctx) +static void kill_ioctx_work(struct work_struct *work) { - int (*cancel)(struct kiocb *, struct io_event *); - struct task_struct *tsk = current; - DECLARE_WAITQUEUE(wait, tsk); - struct io_event res; + struct kioctx *ctx = container_of(work, struct kioctx, rcu_work); - spin_lock_irq(&ctx->ctx_lock); - ctx->dead = 1; - while (!list_empty(&ctx->active_reqs)) { - struct list_head *pos = ctx->active_reqs.next; - struct kiocb *iocb = list_kiocb(pos); - list_del_init(&iocb->ki_list); - cancel = iocb->ki_cancel; - kiocbSetCancelled(iocb); - if (cancel) { - iocb->ki_users++; - spin_unlock_irq(&ctx->ctx_lock); - cancel(iocb, &res); - spin_lock_irq(&ctx->ctx_lock); - } - } + wake_up_all(&ctx->wait); + put_ioctx(ctx); +} - if (!ctx->reqs_active) - goto out; +static void kill_ioctx_rcu(struct rcu_head *head) +{ + struct kioctx *ctx = container_of(head, struct kioctx, rcu_head); - add_wait_queue(&ctx->wait, &wait); - set_task_state(tsk, TASK_UNINTERRUPTIBLE); - while (ctx->reqs_active) { - spin_unlock_irq(&ctx->ctx_lock); - io_schedule(); - set_task_state(tsk, TASK_UNINTERRUPTIBLE); - spin_lock_irq(&ctx->ctx_lock); - } - __set_task_state(tsk, TASK_RUNNING); - remove_wait_queue(&ctx->wait, &wait); + INIT_WORK(&ctx->rcu_work, kill_ioctx_work); + schedule_work(&ctx->rcu_work); +} -out: - spin_unlock_irq(&ctx->ctx_lock); +/* kill_ioctx + * Cancels all outstanding aio requests on an aio context. Used + * when the processes owning a context have all exited to encourage + * the rapid destruction of the kioctx. + */ +static void kill_ioctx(struct kioctx *ctx) +{ + if (percpu_ref_kill(&ctx->users)) { + hlist_del_rcu(&ctx->list); + /* Between hlist_del_rcu() and dropping the initial ref */ + synchronize_rcu(); + + /* + * We can't punt to workqueue here because put_ioctx() -> + * free_ioctx() will unmap the ringbuffer, and that has to be + * done in the original process's context. kill_ioctx_rcu/work() + * exist for exit_aio(), as in that path free_ioctx() won't do + * the unmap. + */ + kill_ioctx_work(&ctx->rcu_work); + } } /* wait_on_sync_kiocb: @@ -348,9 +492,9 @@ out: */ ssize_t wait_on_sync_kiocb(struct kiocb *iocb) { - while (iocb->ki_users) { + while (atomic_read(&iocb->ki_users)) { set_current_state(TASK_UNINTERRUPTIBLE); - if (!iocb->ki_users) + if (!atomic_read(&iocb->ki_users)) break; io_schedule(); } @@ -359,28 +503,20 @@ ssize_t wait_on_sync_kiocb(struct kiocb *iocb) } EXPORT_SYMBOL(wait_on_sync_kiocb); -/* exit_aio: called when the last user of mm goes away. At this point, - * there is no way for any new requests to be submited or any of the - * io_* syscalls to be called on the context. However, there may be - * outstanding requests which hold references to the context; as they - * go away, they will call put_ioctx and release any pinned memory - * associated with the request (held via struct page * references). +/* + * exit_aio: called when the last user of mm goes away. At this point, there is + * no way for any new requests to be submited or any of the io_* syscalls to be + * called on the context. + * + * There may be outstanding kiocbs, but free_ioctx() will explicitly wait on + * them. */ void exit_aio(struct mm_struct *mm) { struct kioctx *ctx; + struct hlist_node *n; - while (!hlist_empty(&mm->ioctx_list)) { - ctx = hlist_entry(mm->ioctx_list.first, struct kioctx, list); - hlist_del_rcu(&ctx->list); - - kill_ctx(ctx); - - if (1 != atomic_read(&ctx->users)) - printk(KERN_DEBUG - "exit_aio:ioctx still alive: %d %d %d\n", - atomic_read(&ctx->users), ctx->dead, - ctx->reqs_active); + hlist_for_each_entry_safe(ctx, n, &mm->ioctx_list, list) { /* * We don't need to bother with munmap() here - * exit_mmap(mm) is coming and it'll unmap everything. @@ -388,150 +524,95 @@ void exit_aio(struct mm_struct *mm) * as indicator that it needs to unmap the area, * just set it to 0; aio_free_ring() is the only * place that uses ->mmap_size, so it's safe. - * That way we get all munmap done to current->mm - - * all other callers have ctx->mm == current->mm. */ - ctx->ring_info.mmap_size = 0; - put_ioctx(ctx); + ctx->mmap_size = 0; + + if (percpu_ref_kill(&ctx->users)) { + hlist_del_rcu(&ctx->list); + call_rcu(&ctx->rcu_head, kill_ioctx_rcu); + } } } -/* aio_get_req - * Allocate a slot for an aio request. Increments the users count - * of the kioctx so that the kioctx stays around until all requests are - * complete. Returns NULL if no requests are free. - * - * Returns with kiocb->users set to 2. The io submit code path holds - * an extra reference while submitting the i/o. - * This prevents races between the aio code path referencing the - * req (after submitting it) and aio_complete() freeing the req. - */ -static struct kiocb *__aio_get_req(struct kioctx *ctx) +static void put_reqs_available(struct kioctx *ctx, unsigned nr) { - struct kiocb *req = NULL; - - req = kmem_cache_alloc(kiocb_cachep, GFP_KERNEL); - if (unlikely(!req)) - return NULL; + struct kioctx_cpu *kcpu; - req->ki_flags = 0; - req->ki_users = 2; - req->ki_key = 0; - req->ki_ctx = ctx; - req->ki_cancel = NULL; - req->ki_retry = NULL; - req->ki_dtor = NULL; - req->private = NULL; - req->ki_iovec = NULL; - INIT_LIST_HEAD(&req->ki_run_list); - req->ki_eventfd = NULL; - - return req; -} + preempt_disable(); + kcpu = this_cpu_ptr(ctx->cpu); -/* - * struct kiocb's are allocated in batches to reduce the number of - * times the ctx lock is acquired and released. - */ -#define KIOCB_BATCH_SIZE 32L -struct kiocb_batch { - struct list_head head; - long count; /* number of requests left to allocate */ -}; + kcpu->reqs_available += nr; + while (kcpu->reqs_available >= ctx->req_batch * 2) { + kcpu->reqs_available -= ctx->req_batch; + atomic_add(ctx->req_batch, &ctx->reqs_available); + } -static void kiocb_batch_init(struct kiocb_batch *batch, long total) -{ - INIT_LIST_HEAD(&batch->head); - batch->count = total; + preempt_enable(); } -static void kiocb_batch_free(struct kioctx *ctx, struct kiocb_batch *batch) +static bool get_reqs_available(struct kioctx *ctx) { - struct kiocb *req, *n; + struct kioctx_cpu *kcpu; + bool ret = false; - if (list_empty(&batch->head)) - return; + preempt_disable(); + kcpu = this_cpu_ptr(ctx->cpu); - spin_lock_irq(&ctx->ctx_lock); - list_for_each_entry_safe(req, n, &batch->head, ki_batch) { - list_del(&req->ki_batch); - list_del(&req->ki_list); - kmem_cache_free(kiocb_cachep, req); - ctx->reqs_active--; - } - if (unlikely(!ctx->reqs_active && ctx->dead)) - wake_up_all(&ctx->wait); - spin_unlock_irq(&ctx->ctx_lock); -} - -/* - * Allocate a batch of kiocbs. This avoids taking and dropping the - * context lock a lot during setup. - */ -static int kiocb_batch_refill(struct kioctx *ctx, struct kiocb_batch *batch) -{ - unsigned short allocated, to_alloc; - long avail; - struct kiocb *req, *n; - struct aio_ring *ring; + if (!kcpu->reqs_available) { + int old, avail = atomic_read(&ctx->reqs_available); - to_alloc = min(batch->count, KIOCB_BATCH_SIZE); - for (allocated = 0; allocated < to_alloc; allocated++) { - req = __aio_get_req(ctx); - if (!req) - /* allocation failed, go with what we've got */ - break; - list_add(&req->ki_batch, &batch->head); - } + do { + if (avail < ctx->req_batch) + goto out; - if (allocated == 0) - goto out; + old = avail; + avail = atomic_cmpxchg(&ctx->reqs_available, + avail, avail - ctx->req_batch); + } while (avail != old); - spin_lock_irq(&ctx->ctx_lock); - ring = kmap_atomic(ctx->ring_info.ring_pages[0]); - - avail = aio_ring_avail(&ctx->ring_info, ring) - ctx->reqs_active; - BUG_ON(avail < 0); - if (avail < allocated) { - /* Trim back the number of requests. */ - list_for_each_entry_safe(req, n, &batch->head, ki_batch) { - list_del(&req->ki_batch); - kmem_cache_free(kiocb_cachep, req); - if (--allocated <= avail) - break; - } + kcpu->reqs_available += ctx->req_batch; } - batch->count -= allocated; - list_for_each_entry(req, &batch->head, ki_batch) { - list_add(&req->ki_list, &ctx->active_reqs); - ctx->reqs_active++; - } - - kunmap_atomic(ring); - spin_unlock_irq(&ctx->ctx_lock); - + ret = true; + kcpu->reqs_available--; out: - return allocated; + preempt_enable(); + return ret; } -static inline struct kiocb *aio_get_req(struct kioctx *ctx, - struct kiocb_batch *batch) +/* aio_get_req + * Allocate a slot for an aio request. Increments the ki_users count + * of the kioctx so that the kioctx stays around until all requests are + * complete. Returns NULL if no requests are free. + * + * Returns with kiocb->ki_users set to 2. The io submit code path holds + * an extra reference while submitting the i/o. + * This prevents races between the aio code path referencing the + * req (after submitting it) and aio_complete() freeing the req. + */ +static inline struct kiocb *aio_get_req(struct kioctx *ctx) { struct kiocb *req; - if (list_empty(&batch->head)) - if (kiocb_batch_refill(ctx, batch) == 0) - return NULL; - req = list_first_entry(&batch->head, struct kiocb, ki_batch); - list_del(&req->ki_batch); + if (!get_reqs_available(ctx)) + return NULL; + + req = kmem_cache_alloc(kiocb_cachep, GFP_KERNEL|__GFP_ZERO); + if (unlikely(!req)) + goto out_put; + + atomic_set(&req->ki_users, 2); + req->ki_ctx = ctx; return req; +out_put: + put_reqs_available(ctx, 1); + return NULL; } -static inline void really_put_req(struct kioctx *ctx, struct kiocb *req) +static void kiocb_free(struct kiocb *req) { - assert_spin_locked(&ctx->ctx_lock); - + if (req->ki_filp) + fput(req->ki_filp); if (req->ki_eventfd != NULL) eventfd_ctx_put(req->ki_eventfd); if (req->ki_dtor) @@ -539,48 +620,12 @@ static inline void really_put_req(struct kioctx *ctx, struct kiocb *req) if (req->ki_iovec != &req->ki_inline_vec) kfree(req->ki_iovec); kmem_cache_free(kiocb_cachep, req); - ctx->reqs_active--; - - if (unlikely(!ctx->reqs_active && ctx->dead)) - wake_up_all(&ctx->wait); } -/* __aio_put_req - * Returns true if this put was the last user of the request. - */ -static int __aio_put_req(struct kioctx *ctx, struct kiocb *req) +void aio_put_req(struct kiocb *req) { - dprintk(KERN_DEBUG "aio_put(%p): f_count=%ld\n", - req, atomic_long_read(&req->ki_filp->f_count)); - - assert_spin_locked(&ctx->ctx_lock); - - req->ki_users--; - BUG_ON(req->ki_users < 0); - if (likely(req->ki_users)) - return 0; - list_del(&req->ki_list); /* remove from active_reqs */ - req->ki_cancel = NULL; - req->ki_retry = NULL; - - fput(req->ki_filp); - req->ki_filp = NULL; - really_put_req(ctx, req); - return 1; -} - -/* aio_put_req - * Returns true if this put was the last user of the kiocb, - * false if the request is still in use. - */ -int aio_put_req(struct kiocb *req) -{ - struct kioctx *ctx = req->ki_ctx; - int ret; - spin_lock_irq(&ctx->ctx_lock); - ret = __aio_put_req(ctx, req); - spin_unlock_irq(&ctx->ctx_lock); - return ret; + if (atomic_dec_and_test(&req->ki_users)) + kiocb_free(req); } EXPORT_SYMBOL(aio_put_req); @@ -588,631 +633,355 @@ static struct kioctx *lookup_ioctx(unsigned long ctx_id) { struct mm_struct *mm = current->mm; struct kioctx *ctx, *ret = NULL; - struct hlist_node *n; rcu_read_lock(); - hlist_for_each_entry_rcu(ctx, n, &mm->ioctx_list, list) { - /* - * RCU protects us against accessing freed memory but - * we have to be careful not to get a reference when the - * reference count already dropped to 0 (ctx->dead test - * is unreliable because of races). - */ - if (ctx->user_id == ctx_id && !ctx->dead && try_get_ioctx(ctx)){ + hlist_for_each_entry_rcu(ctx, &mm->ioctx_list, list) + if (ctx->user_id == ctx_id){ + percpu_ref_get(&ctx->users); ret = ctx; break; } - } rcu_read_unlock(); return ret; } -/* - * Queue up a kiocb to be retried. Assumes that the kiocb - * has already been marked as kicked, and places it on - * the retry run list for the corresponding ioctx, if it - * isn't already queued. Returns 1 if it actually queued - * the kiocb (to tell the caller to activate the work - * queue to process it), or 0, if it found that it was - * already queued. - */ -static inline int __queue_kicked_iocb(struct kiocb *iocb) +static inline unsigned kioctx_ring_put(struct kioctx *ctx, struct kiocb *req, + unsigned tail) { - struct kioctx *ctx = iocb->ki_ctx; - - assert_spin_locked(&ctx->ctx_lock); + struct io_event *ev_page, *event; + unsigned pos = tail + AIO_EVENTS_OFFSET; - if (list_empty(&iocb->ki_run_list)) { - list_add_tail(&iocb->ki_run_list, - &ctx->run_list); - return 1; - } - return 0; -} + if (++tail >= ctx->nr) + tail = 0; -/* aio_run_iocb - * This is the core aio execution routine. It is - * invoked both for initial i/o submission and - * subsequent retries via the aio_kick_handler. - * Expects to be invoked with iocb->ki_ctx->lock - * already held. The lock is released and reacquired - * as needed during processing. - * - * Calls the iocb retry method (already setup for the - * iocb on initial submission) for operation specific - * handling, but takes care of most of common retry - * execution details for a given iocb. The retry method - * needs to be non-blocking as far as possible, to avoid - * holding up other iocbs waiting to be serviced by the - * retry kernel thread. - * - * The trickier parts in this code have to do with - * ensuring that only one retry instance is in progress - * for a given iocb at any time. Providing that guarantee - * simplifies the coding of individual aio operations as - * it avoids various potential races. - */ -static ssize_t aio_run_iocb(struct kiocb *iocb) -{ - struct kioctx *ctx = iocb->ki_ctx; - ssize_t (*retry)(struct kiocb *); - ssize_t ret; + ev_page = kmap_atomic(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]); + event = ev_page + pos % AIO_EVENTS_PER_PAGE; - if (!(retry = iocb->ki_retry)) { - printk("aio_run_iocb: iocb->ki_retry = NULL\n"); - return 0; - } + event->obj = (u64)(unsigned long)req->ki_obj.user; + event->data = req->ki_user_data; + event->res = req->ki_res; + event->res2 = req->ki_res2; - /* - * We don't want the next retry iteration for this - * operation to start until this one has returned and - * updated the iocb state. However, wait_queue functions - * can trigger a kick_iocb from interrupt context in the - * meantime, indicating that data is available for the next - * iteration. We want to remember that and enable the - * next retry iteration _after_ we are through with - * this one. - * - * So, in order to be able to register a "kick", but - * prevent it from being queued now, we clear the kick - * flag, but make the kick code *think* that the iocb is - * still on the run list until we are actually done. - * When we are done with this iteration, we check if - * the iocb was kicked in the meantime and if so, queue - * it up afresh. - */ + kunmap_atomic(ev_page); + flush_dcache_page(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]); - kiocbClearKicked(iocb); + pr_debug("%p[%u]: %p: %p %Lx %lx %lx\n", + ctx, tail, req, req->ki_obj.user, req->ki_user_data, + req->ki_res, req->ki_res2); - /* - * This is so that aio_complete knows it doesn't need to - * pull the iocb off the run list (We can't just call - * INIT_LIST_HEAD because we don't want a kick_iocb to - * queue this on the run list yet) - */ - iocb->ki_run_list.next = iocb->ki_run_list.prev = NULL; - spin_unlock_irq(&ctx->ctx_lock); + return tail; +} - /* Quit retrying if the i/o has been cancelled */ - if (kiocbIsCancelled(iocb)) { - ret = -EINTR; - aio_complete(iocb, ret, 0); - /* must not access the iocb after this */ - goto out; - } +static inline unsigned kioctx_ring_lock(struct kioctx *ctx) +{ + unsigned tail; /* - * Now we are all set to call the retry method in async - * context. + * ctx->tail is both our lock and the canonical version of the tail + * pointer. */ - ret = retry(iocb); - - if (ret != -EIOCBRETRY && ret != -EIOCBQUEUED) { - /* - * There's no easy way to restart the syscall since other AIO's - * may be already running. Just fail this IO with EINTR. - */ - if (unlikely(ret == -ERESTARTSYS || ret == -ERESTARTNOINTR || - ret == -ERESTARTNOHAND || ret == -ERESTART_RESTARTBLOCK)) - ret = -EINTR; - aio_complete(iocb, ret, 0); - } -out: - spin_lock_irq(&ctx->ctx_lock); - - if (-EIOCBRETRY == ret) { - /* - * OK, now that we are done with this iteration - * and know that there is more left to go, - * this is where we let go so that a subsequent - * "kick" can start the next iteration - */ - - /* will make __queue_kicked_iocb succeed from here on */ - INIT_LIST_HEAD(&iocb->ki_run_list); - /* we must queue the next iteration ourselves, if it - * has already been kicked */ - if (kiocbIsKicked(iocb)) { - __queue_kicked_iocb(iocb); + while ((tail = xchg(&ctx->tail, UINT_MAX)) == UINT_MAX) + cpu_relax(); - /* - * __queue_kicked_iocb will always return 1 here, because - * iocb->ki_run_list is empty at this point so it should - * be safe to unconditionally queue the context into the - * work queue. - */ - aio_queue_work(ctx); - } - } - return ret; + return tail; } -/* - * __aio_run_iocbs: - * Process all pending retries queued on the ioctx - * run list. - * Assumes it is operating within the aio issuer's mm - * context. - */ -static int __aio_run_iocbs(struct kioctx *ctx) +static inline void kioctx_ring_unlock(struct kioctx *ctx, unsigned tail) { - struct kiocb *iocb; - struct list_head run_list; + struct aio_ring *ring; - assert_spin_locked(&ctx->ctx_lock); + if (!ctx) + return; - list_replace_init(&ctx->run_list, &run_list); - while (!list_empty(&run_list)) { - iocb = list_entry(run_list.next, struct kiocb, - ki_run_list); - list_del(&iocb->ki_run_list); - /* - * Hold an extra reference while retrying i/o. - */ - iocb->ki_users++; /* grab extra reference */ - aio_run_iocb(iocb); - __aio_put_req(ctx, iocb); - } - if (!list_empty(&ctx->run_list)) - return 1; - return 0; -} + smp_wmb(); + /* make event visible before updating tail */ -static void aio_queue_work(struct kioctx * ctx) -{ - unsigned long timeout; - /* - * if someone is waiting, get the work started right - * away, otherwise, use a longer delay - */ - smp_mb(); - if (waitqueue_active(&ctx->wait)) - timeout = 1; - else - timeout = HZ/10; - queue_delayed_work(aio_wq, &ctx->wq, timeout); -} + ctx->shadow_tail = tail; -/* - * aio_run_all_iocbs: - * Process all pending retries queued on the ioctx - * run list, and keep running them until the list - * stays empty. - * Assumes it is operating within the aio issuer's mm context. - */ -static inline void aio_run_all_iocbs(struct kioctx *ctx) -{ - spin_lock_irq(&ctx->ctx_lock); - while (__aio_run_iocbs(ctx)) - ; - spin_unlock_irq(&ctx->ctx_lock); -} + ring = kmap_atomic(ctx->ring_pages[0]); + ring->tail = tail; + kunmap_atomic(ring); + flush_dcache_page(ctx->ring_pages[0]); -/* - * aio_kick_handler: - * Work queue handler triggered to process pending - * retries on an ioctx. Takes on the aio issuer's - * mm context before running the iocbs, so that - * copy_xxx_user operates on the issuer's address - * space. - * Run on aiod's context. - */ -static void aio_kick_handler(struct work_struct *work) -{ - struct kioctx *ctx = container_of(work, struct kioctx, wq.work); - mm_segment_t oldfs = get_fs(); - struct mm_struct *mm; - int requeue; + /* unlock, make new tail visible before checking waitlist */ + smp_mb(); - set_fs(USER_DS); - use_mm(ctx->mm); - spin_lock_irq(&ctx->ctx_lock); - requeue =__aio_run_iocbs(ctx); - mm = ctx->mm; - spin_unlock_irq(&ctx->ctx_lock); - unuse_mm(mm); - set_fs(oldfs); - /* - * we're in a worker thread already; no point using non-zero delay - */ - if (requeue) - queue_delayed_work(aio_wq, &ctx->wq, 0); -} + ctx->tail = tail; + if (waitqueue_active(&ctx->wait)) + wake_up(&ctx->wait); +} -/* - * Called by kick_iocb to queue the kiocb for retry - * and if required activate the aio work queue to process - * it - */ -static void try_queue_kicked_iocb(struct kiocb *iocb) +void batch_complete_aio(struct batch_complete *batch) { - struct kioctx *ctx = iocb->ki_ctx; + struct kioctx *ctx = NULL; + struct eventfd_ctx *eventfd = NULL; + struct rb_node *n; unsigned long flags; - int run = 0; - - spin_lock_irqsave(&ctx->ctx_lock, flags); - /* set this inside the lock so that we can't race with aio_run_iocb() - * testing it and putting the iocb on the run list under the lock */ - if (!kiocbTryKick(iocb)) - run = __queue_kicked_iocb(iocb); - spin_unlock_irqrestore(&ctx->ctx_lock, flags); - if (run) - aio_queue_work(ctx); -} + unsigned tail = 0; -/* - * kick_iocb: - * Called typically from a wait queue callback context - * to trigger a retry of the iocb. - * The retry is usually executed by aio workqueue - * threads (See aio_kick_handler). - */ -void kick_iocb(struct kiocb *iocb) -{ - /* sync iocbs are easy: they can only ever be executing from a - * single context. */ - if (is_sync_kiocb(iocb)) { - kiocbSetKicked(iocb); - wake_up_process(iocb->ki_obj.tsk); + if (RB_EMPTY_ROOT(&batch->kiocb)) return; - } - - try_queue_kicked_iocb(iocb); -} -EXPORT_SYMBOL(kick_iocb); - -/* aio_complete - * Called when the io request on the given iocb is complete. - * Returns true if this is the last user of the request. The - * only other user of the request can be the cancellation code. - */ -int aio_complete(struct kiocb *iocb, long res, long res2) -{ - struct kioctx *ctx = iocb->ki_ctx; - struct aio_ring_info *info; - struct aio_ring *ring; - struct io_event *event; - unsigned long flags; - unsigned long tail; - int ret; /* - * Special case handling for sync iocbs: - * - events go directly into the iocb for fast handling - * - the sync task with the iocb in its stack holds the single iocb - * ref, no other paths have a way to get another ref - * - the sync task helpfully left a reference to itself in the iocb + * Take rcu_read_lock() in case the kioctx is being destroyed, as we + * need to issue a wakeup after incrementing reqs_available. */ - if (is_sync_kiocb(iocb)) { - BUG_ON(iocb->ki_users != 1); - iocb->ki_user_data = res; - iocb->ki_users = 0; - wake_up_process(iocb->ki_obj.tsk); - return 1; - } - - info = &ctx->ring_info; + rcu_read_lock(); + local_irq_save(flags); - /* add a completion event to the ring buffer. - * must be done holding ctx->ctx_lock to prevent - * other code from messing with the tail - * pointer since we might be called from irq - * context. - */ - spin_lock_irqsave(&ctx->ctx_lock, flags); + n = rb_first(&batch->kiocb); + while (n) { + struct kiocb *req = container_of(n, struct kiocb, ki_node); - if (iocb->ki_run_list.prev && !list_empty(&iocb->ki_run_list)) - list_del_init(&iocb->ki_run_list); + if (n->rb_right) { + n->rb_right->__rb_parent_color = n->__rb_parent_color; + n = n->rb_right; - /* - * cancelled requests don't get events, userland was given one - * when the event got cancelled. - */ - if (kiocbIsCancelled(iocb)) - goto put_rq; + while (n->rb_left) + n = n->rb_left; + } else { + n = rb_parent(n); + } - ring = kmap_atomic(info->ring_pages[0]); + if (unlikely(xchg(&req->ki_cancel, + KIOCB_CANCELLED) == KIOCB_CANCELLED)) { + /* + * Can't use the percpu reqs_available here - could race + * with free_ioctx() + */ + atomic_inc(&req->ki_ctx->reqs_available); + aio_put_req(req); + continue; + } - tail = info->tail; - event = aio_ring_event(info, tail); - if (++tail >= info->nr) - tail = 0; + if (unlikely(req->ki_eventfd != eventfd)) { + if (eventfd) { + /* Make event visible */ + kioctx_ring_unlock(ctx, tail); + ctx = NULL; - event->obj = (u64)(unsigned long)iocb->ki_obj.user; - event->data = iocb->ki_user_data; - event->res = res; - event->res2 = res2; + eventfd_signal(eventfd, 1); + eventfd_ctx_put(eventfd); + } - dprintk("aio_complete: %p[%lu]: %p: %p %Lx %lx %lx\n", - ctx, tail, iocb, iocb->ki_obj.user, iocb->ki_user_data, - res, res2); + eventfd = req->ki_eventfd; + req->ki_eventfd = NULL; + } - /* after flagging the request as done, we - * must never even look at it again - */ - smp_wmb(); /* make event visible before updating tail */ + if (unlikely(req->ki_ctx != ctx)) { + kioctx_ring_unlock(ctx, tail); - info->tail = tail; - ring->tail = tail; + ctx = req->ki_ctx; + tail = kioctx_ring_lock(ctx); + } - put_aio_ring_event(event); - kunmap_atomic(ring); + tail = kioctx_ring_put(ctx, req, tail); + aio_put_req(req); + } - pr_debug("added to ring %p at [%lu]\n", iocb, tail); + kioctx_ring_unlock(ctx, tail); + local_irq_restore(flags); + rcu_read_unlock(); /* * Check if the user asked us to deliver the result through an * eventfd. The eventfd_signal() function is safe to be called * from IRQ context. */ - if (iocb->ki_eventfd != NULL) - eventfd_signal(iocb->ki_eventfd, 1); + if (eventfd) { + eventfd_signal(eventfd, 1); + eventfd_ctx_put(eventfd); + } +} +EXPORT_SYMBOL(batch_complete_aio); + +/* aio_complete_batch + * Called when the io request on the given iocb is complete; @batch may be + * NULL. + */ +void aio_complete_batch(struct kiocb *req, long res, long res2, + struct batch_complete *batch) +{ + req->ki_res = res; + req->ki_res2 = res2; -put_rq: - /* everything turned out well, dispose of the aiocb. */ - ret = __aio_put_req(ctx, iocb); + if (req->ki_list.next) { + struct kioctx *ctx = req->ki_ctx; + unsigned long flags; + + spin_lock_irqsave(&ctx->ctx_lock, flags); + list_del(&req->ki_list); + spin_unlock_irqrestore(&ctx->ctx_lock, flags); + } /* - * We have to order our ring_info tail store above and test - * of the wait list below outside the wait lock. This is - * like in wake_up_bit() where clearing a bit has to be - * ordered with the unlocked test. + * Special case handling for sync iocbs: + * - events go directly into the iocb for fast handling + * - the sync task with the iocb in its stack holds the single iocb + * ref, no other paths have a way to get another ref + * - the sync task helpfully left a reference to itself in the iocb */ - smp_mb(); + if (is_sync_kiocb(req)) { + BUG_ON(atomic_read(&req->ki_users) != 1); + req->ki_user_data = req->ki_res; + atomic_set(&req->ki_users, 0); + wake_up_process(req->ki_obj.tsk); + } else if (batch) { + int res; + struct kiocb *t; + struct rb_node **n = &batch->kiocb.rb_node, *parent = NULL; + + while (*n) { + parent = *n; + t = container_of(*n, struct kiocb, ki_node); + + res = req->ki_ctx != t->ki_ctx + ? req->ki_ctx < t->ki_ctx + : req->ki_eventfd != t->ki_eventfd + ? req->ki_eventfd < t->ki_eventfd + : req < t; + + n = res ? &(*n)->rb_left : &(*n)->rb_right; + } - if (waitqueue_active(&ctx->wait)) - wake_up(&ctx->wait); + rb_link_node(&req->ki_node, parent, n); + rb_insert_color(&req->ki_node, &batch->kiocb); + } else { + struct batch_complete batch_stack; - spin_unlock_irqrestore(&ctx->ctx_lock, flags); - return ret; + memset(&req->ki_node, 0, sizeof(req->ki_node)); + batch_stack.kiocb.rb_node = &req->ki_node; + + batch_complete_aio(&batch_stack); + } } -EXPORT_SYMBOL(aio_complete); +EXPORT_SYMBOL(aio_complete_batch); -/* aio_read_evt - * Pull an event off of the ioctx's event ring. Returns the number of - * events fetched (0 or 1 ;-) - * FIXME: make this use cmpxchg. - * TODO: make the ringbuffer user mmap()able (requires FIXME). +/* aio_read_events + * Pull an event off of the ioctx's event ring. Returns the number of + * events fetched */ -static int aio_read_evt(struct kioctx *ioctx, struct io_event *ent) +static long aio_read_events_ring(struct kioctx *ctx, + struct io_event __user *event, long nr) { - struct aio_ring_info *info = &ioctx->ring_info; struct aio_ring *ring; - unsigned long head; - int ret = 0; - - ring = kmap_atomic(info->ring_pages[0]); - dprintk("in aio_read_evt h%lu t%lu m%lu\n", - (unsigned long)ring->head, (unsigned long)ring->tail, - (unsigned long)ring->nr); + unsigned head, pos; + long ret = 0; + int copy_ret; - if (ring->head == ring->tail) - goto out; + mutex_lock(&ctx->ring_lock); - spin_lock(&info->ring_lock); - - head = ring->head % info->nr; - if (head != ring->tail) { - struct io_event *evp = aio_ring_event(info, head); - *ent = *evp; - head = (head + 1) % info->nr; - smp_mb(); /* finish reading the event before updatng the head */ - ring->head = head; - ret = 1; - put_aio_ring_event(evp); - } - spin_unlock(&info->ring_lock); - -out: + ring = kmap_atomic(ctx->ring_pages[0]); + head = ring->head; kunmap_atomic(ring); - dprintk("leaving aio_read_evt: %d h%lu t%lu\n", ret, - (unsigned long)ring->head, (unsigned long)ring->tail); - return ret; -} -struct aio_timeout { - struct timer_list timer; - int timed_out; - struct task_struct *p; -}; - -static void timeout_func(unsigned long data) -{ - struct aio_timeout *to = (struct aio_timeout *)data; + pr_debug("h%u t%u m%u\n", head, ctx->shadow_tail, ctx->nr); - to->timed_out = 1; - wake_up_process(to->p); -} + if (head == ctx->shadow_tail) + goto out; -static inline void init_timeout(struct aio_timeout *to) -{ - setup_timer_on_stack(&to->timer, timeout_func, (unsigned long) to); - to->timed_out = 0; - to->p = current; -} + while (ret < nr) { + long avail = (head < ctx->shadow_tail + ? ctx->shadow_tail : ctx->nr) - head; + struct io_event *ev; + struct page *page; -static inline void set_timeout(long start_jiffies, struct aio_timeout *to, - const struct timespec *ts) -{ - to->timer.expires = start_jiffies + timespec_to_jiffies(ts); - if (time_after(to->timer.expires, jiffies)) - add_timer(&to->timer); - else - to->timed_out = 1; -} + if (head == ctx->shadow_tail) + break; -static inline void clear_timeout(struct aio_timeout *to) -{ - del_singleshot_timer_sync(&to->timer); -} + avail = min(avail, nr - ret); + avail = min_t(long, avail, AIO_EVENTS_PER_PAGE - + ((head + AIO_EVENTS_OFFSET) % AIO_EVENTS_PER_PAGE)); -static int read_events(struct kioctx *ctx, - long min_nr, long nr, - struct io_event __user *event, - struct timespec __user *timeout) -{ - long start_jiffies = jiffies; - struct task_struct *tsk = current; - DECLARE_WAITQUEUE(wait, tsk); - int ret; - int i = 0; - struct io_event ent; - struct aio_timeout to; - int retry = 0; - - /* needed to zero any padding within an entry (there shouldn't be - * any, but C is fun! - */ - memset(&ent, 0, sizeof(ent)); -retry: - ret = 0; - while (likely(i < nr)) { - ret = aio_read_evt(ctx, &ent); - if (unlikely(ret <= 0)) - break; + pos = head + AIO_EVENTS_OFFSET; + page = ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]; + pos %= AIO_EVENTS_PER_PAGE; - dprintk("read event: %Lx %Lx %Lx %Lx\n", - ent.data, ent.obj, ent.res, ent.res2); + ev = kmap(page); + copy_ret = copy_to_user(event + ret, ev + pos, sizeof(*ev) * avail); + kunmap(page); - /* Could we split the check in two? */ - ret = -EFAULT; - if (unlikely(copy_to_user(event, &ent, sizeof(ent)))) { - dprintk("aio: lost an event due to EFAULT.\n"); - break; + if (unlikely(copy_ret)) { + ret = -EFAULT; + goto out; } - ret = 0; - /* Good, event copied to userland, update counts. */ - event ++; - i ++; + ret += avail; + head += avail; + head %= ctx->nr; } - if (min_nr <= i) - return i; - if (ret) - return ret; - - /* End fast path */ + ring = kmap_atomic(ctx->ring_pages[0]); + ring->head = head; + kunmap_atomic(ring); + flush_dcache_page(ctx->ring_pages[0]); - /* racey check, but it gets redone */ - if (!retry && unlikely(!list_empty(&ctx->run_list))) { - retry = 1; - aio_run_all_iocbs(ctx); - goto retry; - } + pr_debug("%li h%u t%u\n", ret, head, ctx->shadow_tail); - init_timeout(&to); - if (timeout) { - struct timespec ts; - ret = -EFAULT; - if (unlikely(copy_from_user(&ts, timeout, sizeof(ts)))) - goto out; - - set_timeout(start_jiffies, &to, &ts); - } + put_reqs_available(ctx, ret); +out: + mutex_unlock(&ctx->ring_lock); - while (likely(i < nr)) { - add_wait_queue_exclusive(&ctx->wait, &wait); - do { - set_task_state(tsk, TASK_INTERRUPTIBLE); - ret = aio_read_evt(ctx, &ent); - if (ret) - break; - if (min_nr <= i) - break; - if (unlikely(ctx->dead)) { - ret = -EINVAL; - break; - } - if (to.timed_out) /* Only check after read evt */ - break; - /* Try to only show up in io wait if there are ops - * in flight */ - if (ctx->reqs_active) - io_schedule(); - else - schedule(); - if (signal_pending(tsk)) { - ret = -EINTR; - break; - } - /*ret = aio_read_evt(ctx, &ent);*/ - } while (1) ; + return ret; +} - set_task_state(tsk, TASK_RUNNING); - remove_wait_queue(&ctx->wait, &wait); +static bool aio_read_events(struct kioctx *ctx, long min_nr, long nr, + struct io_event __user *event, long *i) +{ + long ret = aio_read_events_ring(ctx, event + *i, nr - *i); - if (unlikely(ret <= 0)) - break; + if (ret > 0) + *i += ret; - ret = -EFAULT; - if (unlikely(copy_to_user(event, &ent, sizeof(ent)))) { - dprintk("aio: lost an event due to EFAULT.\n"); - break; - } + if (unlikely(percpu_ref_dead(&ctx->users))) + ret = -EINVAL; - /* Good, event copied to userland, update counts. */ - event ++; - i ++; - } + if (!*i) + *i = ret; - if (timeout) - clear_timeout(&to); -out: - destroy_timer_on_stack(&to.timer); - return i ? i : ret; + return ret < 0 || *i >= min_nr; } -/* Take an ioctx and remove it from the list of ioctx's. Protects - * against races with itself via ->dead. - */ -static void io_destroy(struct kioctx *ioctx) +static long read_events(struct kioctx *ctx, long min_nr, long nr, + struct io_event __user *event, + struct timespec __user *timeout) { - struct mm_struct *mm = current->mm; - int was_dead; + ktime_t until = { .tv64 = KTIME_MAX }; + long ret = 0; - /* delete the entry from the list is someone else hasn't already */ - spin_lock(&mm->ioctx_lock); - was_dead = ioctx->dead; - ioctx->dead = 1; - hlist_del_rcu(&ioctx->list); - spin_unlock(&mm->ioctx_lock); + if (timeout) { + struct timespec ts; - dprintk("aio_release(%p)\n", ioctx); - if (likely(!was_dead)) - put_ioctx(ioctx); /* twice for the list */ + if (unlikely(copy_from_user(&ts, timeout, sizeof(ts)))) + return -EFAULT; - kill_ctx(ioctx); + until = timespec_to_ktime(ts); + } /* - * Wake up any waiters. The setting of ctx->dead must be seen - * by other CPUs at this point. Right now, we rely on the - * locking done by the above calls to ensure this consistency. + * Note that aio_read_events() is being called as the conditional - i.e. + * we're calling it after prepare_to_wait() has set task state to + * TASK_INTERRUPTIBLE. + * + * But aio_read_events() can block, and if it blocks it's going to flip + * the task state back to TASK_RUNNING. + * + * This should be ok, provided it doesn't flip the state back to + * TASK_RUNNING and return 0 too much - that causes us to spin. That + * will only happen if the mutex_lock() call blocks, and we then find + * the ringbuffer empty. So in practice we should be ok, but it's + * something to be aware of when touching this code. */ - wake_up_all(&ioctx->wait); + wait_event_interruptible_hrtimeout(ctx->wait, + aio_read_events(ctx, min_nr, nr, event, &ret), until); + + if (!ret && signal_pending(current)) + ret = -EINTR; + + return ret; } /* sys_io_setup: @@ -1250,7 +1019,7 @@ SYSCALL_DEFINE2(io_setup, unsigned, nr_events, aio_context_t __user *, ctxp) if (!IS_ERR(ioctx)) { ret = put_user(ioctx->user_id, ctxp); if (ret) - io_destroy(ioctx); + kill_ioctx(ioctx); put_ioctx(ioctx); } @@ -1268,7 +1037,7 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx) { struct kioctx *ioctx = lookup_ioctx(ctx); if (likely(NULL != ioctx)) { - io_destroy(ioctx); + kill_ioctx(ioctx); put_ioctx(ioctx); return 0; } @@ -1299,24 +1068,15 @@ static void aio_advance_iovec(struct kiocb *iocb, ssize_t ret) BUG_ON(ret > 0 && iocb->ki_left == 0); } -static ssize_t aio_rw_vect_retry(struct kiocb *iocb) +typedef ssize_t (aio_rw_op)(struct kiocb *, const struct iovec *, + unsigned long, loff_t); + +static ssize_t aio_rw_vect_retry(struct kiocb *iocb, int rw, aio_rw_op *rw_op) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; - ssize_t (*rw_op)(struct kiocb *, const struct iovec *, - unsigned long, loff_t); ssize_t ret = 0; - unsigned short opcode; - - if ((iocb->ki_opcode == IOCB_CMD_PREADV) || - (iocb->ki_opcode == IOCB_CMD_PREAD)) { - rw_op = file->f_op->aio_read; - opcode = IOCB_CMD_PREADV; - } else { - rw_op = file->f_op->aio_write; - opcode = IOCB_CMD_PWRITEV; - } /* This matches the pread()/pwrite() logic */ if (iocb->ki_pos < 0) @@ -1332,7 +1092,7 @@ static ssize_t aio_rw_vect_retry(struct kiocb *iocb) /* retry all partial writes. retry partial reads as long as its a * regular file. */ } while (ret > 0 && iocb->ki_left > 0 && - (opcode == IOCB_CMD_PWRITEV || + (rw == WRITE || (!S_ISFIFO(inode->i_mode) && !S_ISSOCK(inode->i_mode)))); /* This means we must have transferred all that we could */ @@ -1342,81 +1102,49 @@ static ssize_t aio_rw_vect_retry(struct kiocb *iocb) /* If we managed to write some out we return that, rather than * the eventual error. */ - if (opcode == IOCB_CMD_PWRITEV - && ret < 0 && ret != -EIOCBQUEUED && ret != -EIOCBRETRY + if (rw == WRITE + && ret < 0 && ret != -EIOCBQUEUED && iocb->ki_nbytes - iocb->ki_left) ret = iocb->ki_nbytes - iocb->ki_left; return ret; } -static ssize_t aio_fdsync(struct kiocb *iocb) -{ - struct file *file = iocb->ki_filp; - ssize_t ret = -EINVAL; - - if (file->f_op->aio_fsync) - ret = file->f_op->aio_fsync(iocb, 1); - return ret; -} - -static ssize_t aio_fsync(struct kiocb *iocb) -{ - struct file *file = iocb->ki_filp; - ssize_t ret = -EINVAL; - - if (file->f_op->aio_fsync) - ret = file->f_op->aio_fsync(iocb, 0); - return ret; -} - -static ssize_t aio_setup_vectored_rw(int type, struct kiocb *kiocb, bool compat) +static ssize_t aio_setup_vectored_rw(int rw, struct kiocb *kiocb, bool compat) { ssize_t ret; + kiocb->ki_nr_segs = kiocb->ki_nbytes; + #ifdef CONFIG_COMPAT if (compat) - ret = compat_rw_copy_check_uvector(type, + ret = compat_rw_copy_check_uvector(rw, (struct compat_iovec __user *)kiocb->ki_buf, - kiocb->ki_nbytes, 1, &kiocb->ki_inline_vec, + kiocb->ki_nr_segs, 1, &kiocb->ki_inline_vec, &kiocb->ki_iovec); else #endif - ret = rw_copy_check_uvector(type, + ret = rw_copy_check_uvector(rw, (struct iovec __user *)kiocb->ki_buf, - kiocb->ki_nbytes, 1, &kiocb->ki_inline_vec, + kiocb->ki_nr_segs, 1, &kiocb->ki_inline_vec, &kiocb->ki_iovec); if (ret < 0) - goto out; - - ret = rw_verify_area(type, kiocb->ki_filp, &kiocb->ki_pos, ret); - if (ret < 0) - goto out; + return ret; - kiocb->ki_nr_segs = kiocb->ki_nbytes; - kiocb->ki_cur_seg = 0; - /* ki_nbytes/left now reflect bytes instead of segs */ + /* ki_nbytes now reflect bytes instead of segs */ kiocb->ki_nbytes = ret; - kiocb->ki_left = ret; - - ret = 0; -out: - return ret; + return 0; } -static ssize_t aio_setup_single_vector(int type, struct file * file, struct kiocb *kiocb) +static ssize_t aio_setup_single_vector(int rw, struct kiocb *kiocb) { - int bytes; - - bytes = rw_verify_area(type, file, &kiocb->ki_pos, kiocb->ki_left); - if (bytes < 0) - return bytes; + if (unlikely(!access_ok(!rw, kiocb->ki_buf, kiocb->ki_nbytes))) + return -EFAULT; kiocb->ki_iovec = &kiocb->ki_inline_vec; kiocb->ki_iovec->iov_base = kiocb->ki_buf; - kiocb->ki_iovec->iov_len = bytes; + kiocb->ki_iovec->iov_len = kiocb->ki_nbytes; kiocb->ki_nr_segs = 1; - kiocb->ki_cur_seg = 0; return 0; } @@ -1425,96 +1153,94 @@ static ssize_t aio_setup_single_vector(int type, struct file * file, struct kioc * Performs the initial checks and aio retry method * setup for the kiocb at the time of io submission. */ -static ssize_t aio_setup_iocb(struct kiocb *kiocb, bool compat) +static ssize_t aio_run_iocb(struct kiocb *req, bool compat) { - struct file *file = kiocb->ki_filp; - ssize_t ret = 0; + struct file *file = req->ki_filp; + ssize_t ret; + int rw; + fmode_t mode; + aio_rw_op *rw_op; - switch (kiocb->ki_opcode) { + switch (req->ki_opcode) { case IOCB_CMD_PREAD: - ret = -EBADF; - if (unlikely(!(file->f_mode & FMODE_READ))) - break; - ret = -EFAULT; - if (unlikely(!access_ok(VERIFY_WRITE, kiocb->ki_buf, - kiocb->ki_left))) - break; - ret = aio_setup_single_vector(READ, file, kiocb); - if (ret) - break; - ret = -EINVAL; - if (file->f_op->aio_read) - kiocb->ki_retry = aio_rw_vect_retry; - break; - case IOCB_CMD_PWRITE: - ret = -EBADF; - if (unlikely(!(file->f_mode & FMODE_WRITE))) - break; - ret = -EFAULT; - if (unlikely(!access_ok(VERIFY_READ, kiocb->ki_buf, - kiocb->ki_left))) - break; - ret = aio_setup_single_vector(WRITE, file, kiocb); - if (ret) - break; - ret = -EINVAL; - if (file->f_op->aio_write) - kiocb->ki_retry = aio_rw_vect_retry; - break; case IOCB_CMD_PREADV: - ret = -EBADF; - if (unlikely(!(file->f_mode & FMODE_READ))) - break; - ret = aio_setup_vectored_rw(READ, kiocb, compat); - if (ret) - break; - ret = -EINVAL; - if (file->f_op->aio_read) - kiocb->ki_retry = aio_rw_vect_retry; - break; + mode = FMODE_READ; + rw = READ; + rw_op = file->f_op->aio_read; + goto rw_common; + + case IOCB_CMD_PWRITE: case IOCB_CMD_PWRITEV: - ret = -EBADF; - if (unlikely(!(file->f_mode & FMODE_WRITE))) - break; - ret = aio_setup_vectored_rw(WRITE, kiocb, compat); + mode = FMODE_WRITE; + rw = WRITE; + rw_op = file->f_op->aio_write; + goto rw_common; +rw_common: + if (unlikely(!(file->f_mode & mode))) + return -EBADF; + + if (!rw_op) + return -EINVAL; + + ret = (req->ki_opcode == IOCB_CMD_PREADV || + req->ki_opcode == IOCB_CMD_PWRITEV) + ? aio_setup_vectored_rw(rw, req, compat) + : aio_setup_single_vector(rw, req); if (ret) - break; - ret = -EINVAL; - if (file->f_op->aio_write) - kiocb->ki_retry = aio_rw_vect_retry; + return ret; + + ret = rw_verify_area(rw, file, &req->ki_pos, req->ki_nbytes); + if (ret < 0) + return ret; + + req->ki_nbytes = ret; + req->ki_left = ret; + + ret = aio_rw_vect_retry(req, rw, rw_op); break; + case IOCB_CMD_FDSYNC: - ret = -EINVAL; - if (file->f_op->aio_fsync) - kiocb->ki_retry = aio_fdsync; + if (!file->f_op->aio_fsync) + return -EINVAL; + + ret = file->f_op->aio_fsync(req, 1); break; + case IOCB_CMD_FSYNC: - ret = -EINVAL; - if (file->f_op->aio_fsync) - kiocb->ki_retry = aio_fsync; + if (!file->f_op->aio_fsync) + return -EINVAL; + + ret = file->f_op->aio_fsync(req, 0); break; + default: - dprintk("EINVAL: io_submit: no operation provided\n"); - ret = -EINVAL; + pr_debug("EINVAL: no operation provided\n"); + return -EINVAL; } - if (!kiocb->ki_retry) - return ret; + if (ret != -EIOCBQUEUED) { + /* + * There's no easy way to restart the syscall since other AIO's + * may be already running. Just fail this IO with EINTR. + */ + if (unlikely(ret == -ERESTARTSYS || ret == -ERESTARTNOINTR || + ret == -ERESTARTNOHAND || ret == -ERESTART_RESTARTBLOCK)) + ret = -EINTR; + aio_complete(req, ret, 0); + } return 0; } static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, - struct iocb *iocb, struct kiocb_batch *batch, - bool compat) + struct iocb *iocb, bool compat) { struct kiocb *req; - struct file *file; ssize_t ret; /* enforce forwards compatibility on users */ if (unlikely(iocb->aio_reserved1 || iocb->aio_reserved2)) { - pr_debug("EINVAL: io_submit: reserve field set\n"); + pr_debug("EINVAL: reserve field set\n"); return -EINVAL; } @@ -1528,16 +1254,16 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, return -EINVAL; } - file = fget(iocb->aio_fildes); - if (unlikely(!file)) - return -EBADF; - - req = aio_get_req(ctx, batch); /* returns with 2 references to req */ - if (unlikely(!req)) { - fput(file); + req = aio_get_req(ctx); + if (unlikely(!req)) return -EAGAIN; + + req->ki_filp = fget(iocb->aio_fildes); + if (unlikely(!req->ki_filp)) { + ret = -EBADF; + goto out_put_req; } - req->ki_filp = file; + if (iocb->aio_flags & IOCB_FLAG_RESFD) { /* * If the IOCB_FLAG_RESFD flag of aio_flags is set, get an @@ -1553,9 +1279,9 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, } } - ret = put_user(req->ki_key, &user_iocb->aio_key); + ret = put_user(KIOCB_KEY, &user_iocb->aio_key); if (unlikely(ret)) { - dprintk("EFAULT: aio_key\n"); + pr_debug("EFAULT: aio_key\n"); goto out_put_req; } @@ -1567,41 +1293,14 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, req->ki_left = req->ki_nbytes = iocb->aio_nbytes; req->ki_opcode = iocb->aio_lio_opcode; - ret = aio_setup_iocb(req, compat); - + ret = aio_run_iocb(req, compat); if (ret) goto out_put_req; - spin_lock_irq(&ctx->ctx_lock); - /* - * We could have raced with io_destroy() and are currently holding a - * reference to ctx which should be destroyed. We cannot submit IO - * since ctx gets freed as soon as io_submit() puts its reference. The - * check here is reliable: io_destroy() sets ctx->dead before waiting - * for outstanding IO and the barrier between these two is realized by - * unlock of mm->ioctx_lock and lock of ctx->ctx_lock. Analogously we - * increment ctx->reqs_active before checking for ctx->dead and the - * barrier is realized by unlock and lock of ctx->ctx_lock. Thus if we - * don't see ctx->dead set here, io_destroy() waits for our IO to - * finish. - */ - if (ctx->dead) { - spin_unlock_irq(&ctx->ctx_lock); - ret = -EINVAL; - goto out_put_req; - } - aio_run_iocb(req); - if (!list_empty(&ctx->run_list)) { - /* drain the run list */ - while (__aio_run_iocbs(ctx)) - ; - } - spin_unlock_irq(&ctx->ctx_lock); - aio_put_req(req); /* drop extra ref to req */ return 0; - out_put_req: + put_reqs_available(ctx, 1); aio_put_req(req); /* drop extra ref to req */ aio_put_req(req); /* drop i/o ref to req */ return ret; @@ -1614,7 +1313,6 @@ long do_io_submit(aio_context_t ctx_id, long nr, long ret = 0; int i = 0; struct blk_plug plug; - struct kiocb_batch batch; if (unlikely(nr < 0)) return -EINVAL; @@ -1627,12 +1325,10 @@ long do_io_submit(aio_context_t ctx_id, long nr, ctx = lookup_ioctx(ctx_id); if (unlikely(!ctx)) { - pr_debug("EINVAL: io_submit: invalid context id\n"); + pr_debug("EINVAL: invalid context id\n"); return -EINVAL; } - kiocb_batch_init(&batch, nr); - blk_start_plug(&plug); /* @@ -1653,13 +1349,12 @@ long do_io_submit(aio_context_t ctx_id, long nr, break; } - ret = io_submit_one(ctx, user_iocb, &tmp, &batch, compat); + ret = io_submit_one(ctx, user_iocb, &tmp, compat); if (ret) break; } blk_finish_plug(&plug); - kiocb_batch_free(ctx, &batch); put_ioctx(ctx); return i ? i : ret; } @@ -1692,10 +1387,13 @@ static struct kiocb *lookup_kiocb(struct kioctx *ctx, struct iocb __user *iocb, assert_spin_locked(&ctx->ctx_lock); + if (key != KIOCB_KEY) + return NULL; + /* TODO: use a hash or array, this sucks. */ list_for_each(pos, &ctx->active_reqs) { struct kiocb *kiocb = list_kiocb(pos); - if (kiocb->ki_obj.user == iocb && kiocb->ki_key == key) + if (kiocb->ki_obj.user == iocb) return kiocb; } return NULL; @@ -1714,7 +1412,7 @@ static struct kiocb *lookup_kiocb(struct kioctx *ctx, struct iocb __user *iocb, SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, struct io_event __user *, result) { - int (*cancel)(struct kiocb *iocb, struct io_event *res); + struct io_event res; struct kioctx *ctx; struct kiocb *kiocb; u32 key; @@ -1729,32 +1427,22 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, return -EINVAL; spin_lock_irq(&ctx->ctx_lock); - ret = -EAGAIN; + kiocb = lookup_kiocb(ctx, iocb, key); - if (kiocb && kiocb->ki_cancel) { - cancel = kiocb->ki_cancel; - kiocb->ki_users ++; - kiocbSetCancelled(kiocb); - } else - cancel = NULL; + if (kiocb) + ret = kiocb_cancel(ctx, kiocb, &res); + else + ret = -EINVAL; + spin_unlock_irq(&ctx->ctx_lock); - if (NULL != cancel) { - struct io_event tmp; - pr_debug("calling cancel\n"); - memset(&tmp, 0, sizeof(tmp)); - tmp.obj = (u64)(unsigned long)kiocb->ki_obj.user; - tmp.data = kiocb->ki_user_data; - ret = cancel(kiocb, &tmp); - if (!ret) { - /* Cancellation succeeded -- copy the result - * into the user's buffer. - */ - if (copy_to_user(result, &tmp, sizeof(tmp))) - ret = -EFAULT; - } - } else - ret = -EINVAL; + if (!ret) { + /* Cancellation succeeded -- copy the result + * into the user's buffer. + */ + if (copy_to_user(result, &res, sizeof(res))) + ret = -EFAULT; + } put_ioctx(ctx); diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c index c93447604da8..847ee4dd72a4 100644 --- a/fs/autofs4/root.c +++ b/fs/autofs4/root.c @@ -587,7 +587,7 @@ static int autofs4_dir_unlink(struct inode *dir, struct dentry *dentry) /* This allows root to remove symlinks */ if (!autofs4_oz_mode(sbi) && !capable(CAP_SYS_ADMIN)) - return -EACCES; + return -EPERM; if (atomic_dec_and_test(&ino->count)) { p_ino = autofs4_dentry_ino(dentry->d_parent); diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c index 6043567b95c2..692e75ca6415 100644 --- a/fs/binfmt_aout.c +++ b/fs/binfmt_aout.c @@ -256,8 +256,6 @@ static int load_aout_binary(struct linux_binprm * bprm) (current->mm->start_data = N_DATADDR(ex)); current->mm->brk = ex.a_bss + (current->mm->start_brk = N_BSSADDR(ex)); - current->mm->free_area_cache = current->mm->mmap_base; - current->mm->cached_hole_size = 0; retval = setup_arg_pages(bprm, STACK_TOP, EXSTACK_DEFAULT); if (retval < 0) { diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index da19fc7c00b2..d1777a445841 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -140,6 +140,25 @@ static int padzero(unsigned long elf_bss) #define ELF_BASE_PLATFORM NULL #endif +/* + * Use get_random_int() to implement AT_RANDOM while avoiding depletion + * of the entropy pool. + */ +static void get_atrandom_bytes(unsigned char *buf, size_t nbytes) +{ + unsigned char *p = buf; + + while (nbytes) { + unsigned int random_variable; + size_t chunk = min(nbytes, sizeof(random_variable)); + + random_variable = get_random_int(); + memcpy(p, &random_variable, chunk); + p += chunk; + nbytes -= chunk; + } +} + static int create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec, unsigned long load_addr, unsigned long interp_load_addr) @@ -201,7 +220,7 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec, /* * Generate 16 random bytes for userspace PRNG seeding. */ - get_random_bytes(k_rand_bytes, sizeof(k_rand_bytes)); + get_atrandom_bytes(k_rand_bytes, sizeof(k_rand_bytes)); u_rand_bytes = (elf_addr_t __user *) STACK_ALLOC(p, sizeof(k_rand_bytes)); if (__copy_to_user(u_rand_bytes, k_rand_bytes, sizeof(k_rand_bytes))) @@ -735,8 +754,6 @@ static int load_elf_binary(struct linux_binprm *bprm) /* Do this so that we can load the interpreter, if need be. We will change some of these later */ - current->mm->free_area_cache = current->mm->mmap_base; - current->mm->cached_hole_size = 0; retval = setup_arg_pages(bprm, randomize_stack_top(STACK_TOP), executable_stack); if (retval < 0) { @@ -1253,7 +1270,7 @@ static int writenote(struct memelfnote *men, struct file *file, #undef DUMP_WRITE static void fill_elf_header(struct elfhdr *elf, int segs, - u16 machine, u32 flags, u8 osabi) + u16 machine, u32 flags) { memset(elf, 0, sizeof(*elf)); @@ -1638,7 +1655,7 @@ static int fill_note_info(struct elfhdr *elf, int phdrs, * Initialize the ELF file header. */ fill_elf_header(elf, phdrs, - view->e_machine, view->e_flags, view->ei_osabi); + view->e_machine, view->e_flags); /* * Allocate a structure for each thread. @@ -1878,7 +1895,7 @@ static int fill_note_info(struct elfhdr *elf, int phdrs, elf_core_copy_regs(&info->prstatus->pr_reg, regs); /* Set up header */ - fill_elf_header(elf, phdrs, ELF_ARCH, ELF_CORE_EFLAGS, ELF_OSABI); + fill_elf_header(elf, phdrs, ELF_ARCH, ELF_CORE_EFLAGS); /* * Set up the notes in similar form to SVR4 core dumps made @@ -27,6 +27,7 @@ #include <linux/mempool.h> #include <linux/workqueue.h> #include <linux/cgroup.h> +#include <linux/aio.h> #include <scsi/sg.h> /* for struct sg_iovec */ #include <trace/events/block.h> @@ -1407,33 +1408,44 @@ void bio_flush_dcache_pages(struct bio *bi) EXPORT_SYMBOL(bio_flush_dcache_pages); #endif -/** - * bio_endio - end I/O on a bio - * @bio: bio - * @error: error, if any - * - * Description: - * bio_endio() will end I/O on the whole bio. bio_endio() is the - * preferred way to end I/O on a bio, it takes care of clearing - * BIO_UPTODATE on error. @error is 0 on success, and and one of the - * established -Exxxx (-EIO, for instance) error values in case - * something went wrong. No one should call bi_end_io() directly on a - * bio unless they own it and thus know that it has an end_io - * function. - **/ -void bio_endio(struct bio *bio, int error) +static inline void __bio_endio(struct bio *bio, struct batch_complete *batch) { - if (error) + if (bio->bi_error) clear_bit(BIO_UPTODATE, &bio->bi_flags); else if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) - error = -EIO; + bio->bi_error = -EIO; + + if (bio_flagged(bio, BIO_BATCH_ENDIO)) + bio->bi_batch_end_io(bio, bio->bi_error, batch); + else if (bio->bi_end_io) + bio->bi_end_io(bio, bio->bi_error); +} + +void bio_endio_batch(struct bio *bio, int error, struct batch_complete *batch) +{ + if (error) + bio->bi_error = error; trace_block_bio_complete(bio, error); - if (bio->bi_end_io) - bio->bi_end_io(bio, error); + if (batch) + bio_list_add(&batch->bio, bio); + else + __bio_endio(bio, batch); + +} +EXPORT_SYMBOL(bio_endio_batch); + +void batch_complete(struct batch_complete *batch) +{ + struct bio *bio; + + while ((bio = bio_list_pop(&batch->bio))) + __bio_endio(bio, batch); + + batch_complete_aio(batch); } -EXPORT_SYMBOL(bio_endio); +EXPORT_SYMBOL(batch_complete); void bio_pair_release(struct bio_pair *bp) { diff --git a/fs/block_dev.c b/fs/block_dev.c index 172f8491a2bd..363ebe453455 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -27,6 +27,7 @@ #include <linux/namei.h> #include <linux/log2.h> #include <linux/cleancache.h> +#include <linux/aio.h> #include <asm/uaccess.h> #include "internal.h" @@ -616,11 +617,9 @@ void bd_forget(struct inode *inode) struct block_device *bdev = NULL; spin_lock(&bdev_lock); - if (inode->i_bdev) { - if (!sb_is_blkdev_sb(inode->i_sb)) - bdev = inode->i_bdev; - __bd_forget(inode); - } + if (!sb_is_blkdev_sb(inode->i_sb)) + bdev = inode->i_bdev; + __bd_forget(inode); spin_unlock(&bdev_lock); if (bdev) @@ -994,6 +993,7 @@ int revalidate_disk(struct gendisk *disk) mutex_lock(&bdev->bd_mutex); check_disk_size_change(disk, bdev); + bdev->bd_invalidated = 0; mutex_unlock(&bdev->bd_mutex); bdput(bdev); return ret; @@ -1032,7 +1032,9 @@ void bd_set_size(struct block_device *bdev, loff_t size) { unsigned bsize = bdev_logical_block_size(bdev); - bdev->bd_inode->i_size = size; + mutex_lock(&bdev->bd_inode->i_mutex); + i_size_write(bdev->bd_inode, size); + mutex_unlock(&bdev->bd_inode->i_mutex); while (bsize < PAGE_CACHE_SIZE) { if (size & bsize) break; @@ -1117,7 +1119,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) } } - if (!ret && !bdev->bd_openers) { + if (!ret) { bd_set_size(bdev,(loff_t)get_capacity(disk)<<9); bdi = blk_get_backing_dev_info(bdev); if (bdi == NULL) diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index f76b1fd160d4..fcb7060aa1c2 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -30,6 +30,7 @@ #include <linux/statfs.h> #include <linux/compat.h> #include <linux/slab.h> +#include <linux/aio.h> #include "ctree.h" #include "disk-io.h" #include "transaction.h" diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index cc93b23ca352..ed7ea0afe9ad 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -39,6 +39,7 @@ #include <linux/slab.h> #include <linux/ratelimit.h> #include <linux/mount.h> +#include <linux/aio.h> #include "compat.h" #include "ctree.h" #include "disk-io.h" diff --git a/fs/buffer.c b/fs/buffer.c index 5a2915f5dbc4..b095a2ac1fdb 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2369,7 +2369,7 @@ int __block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, if (unlikely(ret < 0)) goto out_unlock; set_page_dirty(page); - wait_on_page_writeback(page); + wait_for_stable_page(page); return 0; out_unlock: unlock_page(page); @@ -3237,7 +3237,7 @@ static struct kmem_cache *bh_cachep __read_mostly; * Once the number of bh's in the machine exceeds this level, we start * stripping them in writeback. */ -static int max_buffer_heads; +static unsigned long max_buffer_heads; int buffer_heads_over_limit; @@ -3353,7 +3353,7 @@ EXPORT_SYMBOL(bh_submit_read); void __init buffer_init(void) { - int nrpages; + unsigned long nrpages; bh_cachep = kmem_cache_create("buffer_head", sizeof(struct buffer_head), 0, diff --git a/fs/ceph/file.c b/fs/ceph/file.c index e51558fca3a3..3d03090c6ace 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -7,6 +7,7 @@ #include <linux/mount.h> #include <linux/namei.h> #include <linux/writeback.h> +#include <linux/aio.h> #include "super.h" #include "mds_client.h" diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index ed6208ff85a7..7a3f57f4f624 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -806,10 +806,9 @@ static bool inode_has_hashed_dentries(struct inode *inode) { struct dentry *dentry; - struct hlist_node *p; spin_lock(&inode->i_lock); - hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) { if (!d_unhashed(dentry) || IS_ROOT(dentry)) { spin_unlock(&inode->i_lock); return true; diff --git a/fs/compat.c b/fs/compat.c index fe40fde29111..ba323f8de6fc 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -48,6 +48,7 @@ #include <linux/fs_struct.h> #include <linux/slab.h> #include <linux/pagemap.h> +#include <linux/aio.h> #include <asm/uaccess.h> #include <asm/mmu_context.h> diff --git a/fs/coredump.c b/fs/coredump.c index 177493272a61..57b9bd6da233 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -501,7 +501,7 @@ void do_coredump(siginfo_t *siginfo) * so we dump it as root in mode 2, and only into a controlled * environment (pipe handler or fully qualified path). */ - if (__get_dumpable(cprm.mm_flags) == SUID_DUMPABLE_SAFE) { + if (__get_dumpable(cprm.mm_flags) == SUID_DUMP_ROOT) { /* Setuid core dump mode */ flag = O_EXCL; /* Stop rewrite attacks */ cred->fsuid = GLOBAL_ROOT_UID; /* Dump root private */ diff --git a/fs/dcache.c b/fs/dcache.c index 19153a0a810c..070b318202ec 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -675,11 +675,10 @@ EXPORT_SYMBOL(dget_parent); static struct dentry *__d_find_alias(struct inode *inode, int want_discon) { struct dentry *alias, *discon_alias; - struct hlist_node *p; again: discon_alias = NULL; - hlist_for_each_entry(alias, p, &inode->i_dentry, d_alias) { + hlist_for_each_entry(alias, &inode->i_dentry, d_alias) { spin_lock(&alias->d_lock); if (S_ISDIR(inode->i_mode) || !d_unhashed(alias)) { if (IS_ROOT(alias) && @@ -730,10 +729,9 @@ EXPORT_SYMBOL(d_find_alias); void d_prune_aliases(struct inode *inode) { struct dentry *dentry; - struct hlist_node *p; restart: spin_lock(&inode->i_lock); - hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) { spin_lock(&dentry->d_lock); if (!dentry->d_count) { __dget_dlock(dentry); @@ -1440,14 +1438,13 @@ static struct dentry *__d_instantiate_unique(struct dentry *entry, int len = entry->d_name.len; const char *name = entry->d_name.name; unsigned int hash = entry->d_name.hash; - struct hlist_node *p; if (!inode) { __d_instantiate(entry, NULL); return NULL; } - hlist_for_each_entry(alias, p, &inode->i_dentry, d_alias) { + hlist_for_each_entry(alias, &inode->i_dentry, d_alias) { /* * Don't need alias->d_lock here, because aliases with * d_parent == entry->d_parent are not subject to name or diff --git a/fs/direct-io.c b/fs/direct-io.c index cf5b44b10c67..55683f36a2f1 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -37,6 +37,7 @@ #include <linux/uio.h> #include <linux/atomic.h> #include <linux/prefetch.h> +#include <linux/aio.h> /* * How many user pages to map in one call to get_user_pages(). This determines @@ -229,7 +230,8 @@ static inline struct page *dio_get_page(struct dio *dio, * filesystems can use it to hold additional state between get_block calls and * dio_complete. */ -static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret, bool is_async) +static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret, bool is_async, + struct batch_complete *batch) { ssize_t transferred = 0; @@ -261,9 +263,9 @@ static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret, bool is dio->end_io(dio->iocb, offset, transferred, dio->private, ret, is_async); } else { - if (is_async) - aio_complete(dio->iocb, ret, 0); inode_dio_done(dio->inode); + if (is_async) + aio_complete_batch(dio->iocb, ret, 0, batch); } return ret; @@ -273,7 +275,7 @@ static int dio_bio_complete(struct dio *dio, struct bio *bio); /* * Asynchronous IO callback. */ -static void dio_bio_end_aio(struct bio *bio, int error) +static void dio_bio_end_aio(struct bio *bio, int error, struct batch_complete *batch) { struct dio *dio = bio->bi_private; unsigned long remaining; @@ -289,7 +291,7 @@ static void dio_bio_end_aio(struct bio *bio, int error) spin_unlock_irqrestore(&dio->bio_lock, flags); if (remaining == 0) { - dio_complete(dio, dio->iocb->ki_pos, 0, true); + dio_complete(dio, dio->iocb->ki_pos, 0, true, batch); kmem_cache_free(dio_cache, dio); } } @@ -328,7 +330,7 @@ void dio_end_io(struct bio *bio, int error) struct dio *dio = bio->bi_private; if (dio->is_async) - dio_bio_end_aio(bio, error); + dio_bio_end_aio(bio, error, NULL); else dio_bio_end_io(bio, error); } @@ -349,9 +351,10 @@ dio_bio_alloc(struct dio *dio, struct dio_submit *sdio, bio->bi_bdev = bdev; bio->bi_sector = first_sector; - if (dio->is_async) - bio->bi_end_io = dio_bio_end_aio; - else + if (dio->is_async) { + bio->bi_batch_end_io = dio_bio_end_aio; + bio->bi_flags |= 1 << BIO_BATCH_ENDIO; + } else bio->bi_end_io = dio_bio_end_io; sdio->bio = bio; @@ -1272,7 +1275,7 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, dio_await_completion(dio); if (drop_refcount(dio) == 0) { - retval = dio_complete(dio, offset, retval, false); + retval = dio_complete(dio, offset, retval, false, NULL); kmem_cache_free(dio_cache, dio); } else BUG_ON(retval != -EIOCBQUEUED); diff --git a/fs/dlm/config.c b/fs/dlm/config.c index a0387dd8b1f0..7d58d5b112b5 100644 --- a/fs/dlm/config.c +++ b/fs/dlm/config.c @@ -158,7 +158,7 @@ static ssize_t cluster_set(struct dlm_cluster *cl, unsigned int *cl_field, unsigned int x; if (!capable(CAP_SYS_ADMIN)) - return -EACCES; + return -EPERM; x = simple_strtoul(buf, NULL, 0); diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c index f7501651762d..1b1146670c4b 100644 --- a/fs/dlm/lock.c +++ b/fs/dlm/lock.c @@ -1183,7 +1183,7 @@ static void detach_lkb(struct dlm_lkb *lkb) static int create_lkb(struct dlm_ls *ls, struct dlm_lkb **lkb_ret) { struct dlm_lkb *lkb; - int rv, id; + int rv; lkb = dlm_allocate_lkb(ls); if (!lkb) @@ -1199,19 +1199,13 @@ static int create_lkb(struct dlm_ls *ls, struct dlm_lkb **lkb_ret) mutex_init(&lkb->lkb_cb_mutex); INIT_WORK(&lkb->lkb_cb_work, dlm_callback_work); - retry: - rv = idr_pre_get(&ls->ls_lkbidr, GFP_NOFS); - if (!rv) - return -ENOMEM; - + idr_preload(GFP_NOFS); spin_lock(&ls->ls_lkbidr_spin); - rv = idr_get_new_above(&ls->ls_lkbidr, lkb, 1, &id); - if (!rv) - lkb->lkb_id = id; + rv = idr_alloc(&ls->ls_lkbidr, lkb, 1, 0, GFP_NOWAIT); + if (rv >= 0) + lkb->lkb_id = rv; spin_unlock(&ls->ls_lkbidr_spin); - - if (rv == -EAGAIN) - goto retry; + idr_preload_end(); if (rv < 0) { log_error(ls, "create_lkb idr error %d", rv); diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c index 2e99fb0c9737..3ca79d3253b9 100644 --- a/fs/dlm/lockspace.c +++ b/fs/dlm/lockspace.c @@ -796,7 +796,6 @@ static int release_lockspace(struct dlm_ls *ls, int force) */ idr_for_each(&ls->ls_lkbidr, lkb_idr_free, ls); - idr_remove_all(&ls->ls_lkbidr); idr_destroy(&ls->ls_lkbidr); /* diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index dd87a31bcc21..036ecb5c17db 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -177,12 +177,11 @@ static inline int nodeid_hash(int nodeid) static struct connection *__find_con(int nodeid) { int r; - struct hlist_node *h; struct connection *con; r = nodeid_hash(nodeid); - hlist_for_each_entry(con, h, &connection_hash[r], list) { + hlist_for_each_entry(con, &connection_hash[r], list) { if (con->nodeid == nodeid) return con; } @@ -232,11 +231,11 @@ static struct connection *__nodeid2con(int nodeid, gfp_t alloc) static void foreach_conn(void (*conn_func)(struct connection *c)) { int i; - struct hlist_node *h, *n; + struct hlist_node *n; struct connection *con; for (i = 0; i < CONN_HASH_SIZE; i++) { - hlist_for_each_entry_safe(con, h, n, &connection_hash[i], list){ + hlist_for_each_entry_safe(con, n, &connection_hash[i], list){ conn_func(con); } } @@ -257,13 +256,12 @@ static struct connection *nodeid2con(int nodeid, gfp_t allocation) static struct connection *assoc2con(int assoc_id) { int i; - struct hlist_node *h; struct connection *con; mutex_lock(&connections_lock); for (i = 0 ; i < CONN_HASH_SIZE; i++) { - hlist_for_each_entry(con, h, &connection_hash[i], list) { + hlist_for_each_entry(con, &connection_hash[i], list) { if (con->sctp_assoc == assoc_id) { mutex_unlock(&connections_lock); return con; diff --git a/fs/dlm/recover.c b/fs/dlm/recover.c index aedea28a86a1..a6bc63f6e31b 100644 --- a/fs/dlm/recover.c +++ b/fs/dlm/recover.c @@ -305,27 +305,26 @@ static int recover_idr_empty(struct dlm_ls *ls) static int recover_idr_add(struct dlm_rsb *r) { struct dlm_ls *ls = r->res_ls; - int rv, id; - - rv = idr_pre_get(&ls->ls_recover_idr, GFP_NOFS); - if (!rv) - return -ENOMEM; + int rv; + idr_preload(GFP_NOFS); spin_lock(&ls->ls_recover_idr_lock); if (r->res_id) { - spin_unlock(&ls->ls_recover_idr_lock); - return -1; - } - rv = idr_get_new_above(&ls->ls_recover_idr, r, 1, &id); - if (rv) { - spin_unlock(&ls->ls_recover_idr_lock); - return rv; + rv = -1; + goto out_unlock; } - r->res_id = id; + rv = idr_alloc(&ls->ls_recover_idr, r, 1, 0, GFP_NOWAIT); + if (rv < 0) + goto out_unlock; + + r->res_id = rv; ls->ls_recover_list_count++; dlm_hold_rsb(r); + rv = 0; +out_unlock: spin_unlock(&ls->ls_recover_idr_lock); - return 0; + idr_preload_end(); + return rv; } static void recover_idr_del(struct dlm_rsb *r) @@ -351,24 +350,21 @@ static struct dlm_rsb *recover_idr_find(struct dlm_ls *ls, uint64_t id) return r; } -static int recover_idr_clear_rsb(int id, void *p, void *data) +static void recover_idr_clear(struct dlm_ls *ls) { - struct dlm_ls *ls = data; - struct dlm_rsb *r = p; + struct dlm_rsb *r; + int id; - r->res_id = 0; - r->res_recover_locks_count = 0; - ls->ls_recover_list_count--; + spin_lock(&ls->ls_recover_idr_lock); - dlm_put_rsb(r); - return 0; -} + idr_for_each_entry(&ls->ls_recover_idr, r, id) { + idr_remove(&ls->ls_recover_idr, id); + r->res_id = 0; + r->res_recover_locks_count = 0; + ls->ls_recover_list_count--; -static void recover_idr_clear(struct dlm_ls *ls) -{ - spin_lock(&ls->ls_recover_idr_lock); - idr_for_each(&ls->ls_recover_idr, recover_idr_clear_rsb, ls); - idr_remove_all(&ls->ls_recover_idr); + dlm_put_rsb(r); + } if (ls->ls_recover_list_count != 0) { log_error(ls, "warning: recover_list_count %d", diff --git a/fs/drop_caches.c b/fs/drop_caches.c index c00e055b6282..f23d2a7ed438 100644 --- a/fs/drop_caches.c +++ b/fs/drop_caches.c @@ -58,6 +58,8 @@ int drop_caches_sysctl_handler(ctl_table *table, int write, if (ret) return ret; if (write) { + printk(KERN_NOTICE "%s (%d): dropped kernel caches: %d\n", + current->comm, task_pid_nr(current), sysctl_drop_caches); if (sysctl_drop_caches & 1) iterate_supers(drop_pagecache_sb, NULL); if (sysctl_drop_caches & 2) diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c index bfa52d2ef460..857d545c7ef7 100644 --- a/fs/ecryptfs/file.c +++ b/fs/ecryptfs/file.c @@ -31,6 +31,7 @@ #include <linux/security.h> #include <linux/compat.h> #include <linux/fs_stack.h> +#include <linux/aio.h> #include "ecryptfs_kernel.h" /** diff --git a/fs/ecryptfs/messaging.c b/fs/ecryptfs/messaging.c index 5fa2471796c2..8d7a577ae497 100644 --- a/fs/ecryptfs/messaging.c +++ b/fs/ecryptfs/messaging.c @@ -115,10 +115,9 @@ void ecryptfs_msg_ctx_alloc_to_free(struct ecryptfs_msg_ctx *msg_ctx) */ int ecryptfs_find_daemon_by_euid(struct ecryptfs_daemon **daemon) { - struct hlist_node *elem; int rc; - hlist_for_each_entry(*daemon, elem, + hlist_for_each_entry(*daemon, &ecryptfs_daemon_hash[ecryptfs_current_euid_hash()], euid_chain) { if (uid_eq((*daemon)->file->f_cred->euid, current_euid())) { @@ -445,7 +444,6 @@ void ecryptfs_release_messaging(void) mutex_unlock(&ecryptfs_msg_ctx_lists_mux); } if (ecryptfs_daemon_hash) { - struct hlist_node *elem; struct ecryptfs_daemon *daemon; int i; @@ -453,7 +451,7 @@ void ecryptfs_release_messaging(void) for (i = 0; i < (1 << ecryptfs_hash_bits); i++) { int rc; - hlist_for_each_entry(daemon, elem, + hlist_for_each_entry(daemon, &ecryptfs_daemon_hash[i], euid_chain) { rc = ecryptfs_exorcise_daemon(daemon); diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 9fec1836057a..5dcc470879c7 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -348,7 +348,7 @@ static inline struct epitem *ep_item_from_epqueue(poll_table *p) /* Tells if the epoll_ctl(2) operation needs an event copy from userspace */ static inline int ep_op_has_event(int op) { - return op != EPOLL_CTL_DEL; + return op == EPOLL_CTL_ADD || op == EPOLL_CTL_MOD; } /* Initialize the poll safe wake up structure */ @@ -678,6 +678,36 @@ static int ep_remove(struct eventpoll *ep, struct epitem *epi) return 0; } +/* + * Disables a "struct epitem" in the eventpoll set. Returns -EBUSY if the item + * had no event flags set, indicating that another thread may be currently + * handling that item's events (in the case that EPOLLONESHOT was being + * used). Otherwise a zero result indicates that the item has been disabled + * from receiving events. A disabled item may be re-enabled via + * EPOLL_CTL_MOD. Must be called with "mtx" held. + */ +static int ep_disable(struct eventpoll *ep, struct epitem *epi) +{ + int result = 0; + unsigned long flags; + + spin_lock_irqsave(&ep->lock, flags); + if (epi->event.events & EPOLLONESHOT) { + if (epi->event.events & ~EP_PRIVATE_BITS) { + if (ep_is_linked(&epi->rdllink)) + list_del_init(&epi->rdllink); + /* Ensure ep_poll_callback will not add epi back onto + ready list: */ + epi->event.events &= EP_PRIVATE_BITS; + } else + result = -EBUSY; + } else + result = -EINVAL; + spin_unlock_irqrestore(&ep->lock, flags); + + return result; +} + static void ep_free(struct eventpoll *ep) { struct rb_node *rbp; @@ -1048,8 +1078,6 @@ static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi) rb_insert_color(&epi->rbn, &ep->rbr); } - - #define PATH_ARR_SIZE 5 /* * These are the number paths of length 1 to 5, that we are allowing to emanate @@ -1835,6 +1863,12 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, } else error = -ENOENT; break; + case EPOLL_CTL_DISABLE: + if (epi) + error = ep_disable(ep, epi); + else + error = -ENOENT; + break; } mutex_unlock(&ep->mtx); diff --git a/fs/exec.c b/fs/exec.c index 20df02c1cc70..dc38755fe538 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -355,7 +355,7 @@ static bool valid_arg_len(struct linux_binprm *bprm, long len) * flags, permissions, and offset, so we use temporary values. We'll update * them later in setup_arg_pages(). */ -int bprm_mm_init(struct linux_binprm *bprm) +static int bprm_mm_init(struct linux_binprm *bprm) { int err; struct mm_struct *mm = NULL; @@ -1111,7 +1111,7 @@ void setup_new_exec(struct linux_binprm * bprm) current->sas_ss_sp = current->sas_ss_size = 0; if (uid_eq(current_euid(), current_uid()) && gid_eq(current_egid(), current_gid())) - set_dumpable(current->mm, SUID_DUMPABLE_ENABLED); + set_dumpable(current->mm, SUID_DUMP_USER); else set_dumpable(current->mm, suid_dumpable); @@ -1639,17 +1639,17 @@ EXPORT_SYMBOL(set_binfmt); void set_dumpable(struct mm_struct *mm, int value) { switch (value) { - case SUID_DUMPABLE_DISABLED: + case SUID_DUMP_DISABLE: clear_bit(MMF_DUMPABLE, &mm->flags); smp_wmb(); clear_bit(MMF_DUMP_SECURELY, &mm->flags); break; - case SUID_DUMPABLE_ENABLED: + case SUID_DUMP_USER: set_bit(MMF_DUMPABLE, &mm->flags); smp_wmb(); clear_bit(MMF_DUMP_SECURELY, &mm->flags); break; - case SUID_DUMPABLE_SAFE: + case SUID_DUMP_ROOT: set_bit(MMF_DUMP_SECURELY, &mm->flags); smp_wmb(); set_bit(MMF_DUMPABLE, &mm->flags); @@ -1662,7 +1662,7 @@ int __get_dumpable(unsigned long mm_flags) int ret; ret = mm_flags & MMF_DUMPABLE_MASK; - return (ret > SUID_DUMPABLE_ENABLED) ? SUID_DUMPABLE_SAFE : ret; + return (ret > SUID_DUMP_USER) ? SUID_DUMP_ROOT : ret; } int get_dumpable(struct mm_struct *mm) diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index 5df4bb4aab14..262fc9940982 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -44,14 +44,13 @@ find_acceptable_alias(struct dentry *result, { struct dentry *dentry, *toput = NULL; struct inode *inode; - struct hlist_node *p; if (acceptable(context, result)) return result; inode = result->d_inode; spin_lock(&inode->i_lock); - hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) { dget(dentry); spin_unlock(&inode->i_lock); if (toput) diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index c3881e56662e..43d72d0ec7e2 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -31,6 +31,7 @@ #include <linux/mpage.h> #include <linux/fiemap.h> #include <linux/namei.h> +#include <linux/aio.h> #include "ext2.h" #include "acl.h" #include "xip.h" diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index d512c4bc4ad7..eac4f041f5fc 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -27,6 +27,7 @@ #include <linux/writeback.h> #include <linux/mpage.h> #include <linux/namei.h> +#include <linux/aio.h> #include "ext3.h" #include "xattr.h" #include "acl.h" diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 0926fe46ae3e..5546ca225ffe 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -2067,6 +2067,7 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) test_opt(sb,DATA_FLAGS) == EXT3_MOUNT_JOURNAL_DATA ? "journal": test_opt(sb,DATA_FLAGS) == EXT3_MOUNT_ORDERED_DATA ? "ordered": "writeback"); + sb->s_flags |= MS_SNAP_STABLE; return 0; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index afaf9f15303e..fe2afd554622 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -23,6 +23,7 @@ #include <linux/jbd2.h> #include <linux/mount.h> #include <linux/path.h> +#include <linux/aio.h> #include <linux/quotaops.h> #include <linux/pagevec.h> #include "ext4.h" diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index bdd20231e66c..5ef1408276e3 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -20,6 +20,7 @@ * (sct@redhat.com), 1993, 1998 */ +#include <linux/aio.h> #include "ext4_jbd2.h" #include "truncate.h" #include "ext4_extents.h" /* Needed for EXT_MAX_BLOCKS */ diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index d0da1f26f20d..4b8d3c6c168c 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -37,6 +37,7 @@ #include <linux/printk.h> #include <linux/slab.h> #include <linux/ratelimit.h> +#include <linux/aio.h> #include "ext4_jbd2.h" #include "xattr.h" @@ -4841,7 +4842,7 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) 0, len, NULL, ext4_bh_unmapped)) { /* Wait so that we don't change page under IO */ - wait_on_page_writeback(page); + wait_for_stable_page(page); ret = VM_FAULT_LOCKED; goto out; } diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 809b31003ecc..d9903af92e51 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -18,6 +18,7 @@ #include <linux/pagevec.h> #include <linux/mpage.h> #include <linux/namei.h> +#include <linux/aio.h> #include <linux/uio.h> #include <linux/bio.h> #include <linux/workqueue.h> diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 7bd22a201125..d0ed4ba4b61b 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -12,6 +12,7 @@ #include <linux/f2fs_fs.h> #include <linux/buffer_head.h> #include <linux/mpage.h> +#include <linux/aio.h> #include <linux/writeback.h> #include <linux/backing-dev.h> #include <linux/blkdev.h> diff --git a/fs/fat/dir.c b/fs/fat/dir.c index 58bf744dbf39..78dabf00f46f 100644 --- a/fs/fat/dir.c +++ b/fs/fat/dir.c @@ -484,10 +484,10 @@ parse_record: nr_slots = 0; if (de->name[0] == DELETED_FLAG) continue; + if (!de->name[0]) + goto end_of_dir; if (de->attr != ATTR_EXT && (de->attr & ATTR_VOLUME)) continue; - if (de->attr != ATTR_EXT && IS_FREE(de->name)) - continue; if (de->attr == ATTR_EXT) { int status = fat_parse_long(inode, &cpos, &bh, &de, &unicode, &nr_slots); @@ -608,8 +608,8 @@ parse_record: goto record_end; if (de->attr != ATTR_EXT && (de->attr & ATTR_VOLUME)) goto record_end; - if (de->attr != ATTR_EXT && IS_FREE(de->name)) - goto record_end; + if (!de->name[0]) + goto end_of_dir; } else { if ((de->attr & ATTR_VOLUME) || IS_FREE(de->name)) goto record_end; diff --git a/fs/fat/fat.h b/fs/fat/fat.h index 12701a567752..e9cc3f0d58e2 100644 --- a/fs/fat/fat.h +++ b/fs/fat/fat.h @@ -95,6 +95,8 @@ struct msdos_sb_info { spinlock_t dir_hash_lock; struct hlist_head dir_hashtable[FAT_HASH_SIZE]; + + unsigned int dirty; /* fs state before mount */ }; #define FAT_CACHE_VALID 0 /* special case for valid cache */ diff --git a/fs/fat/inode.c b/fs/fat/inode.c index f8f491677a4a..d1d502a026a5 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -20,6 +20,7 @@ #include <linux/buffer_head.h> #include <linux/exportfs.h> #include <linux/mount.h> +#include <linux/aio.h> #include <linux/vfs.h> #include <linux/parser.h> #include <linux/uio.h> @@ -341,12 +342,11 @@ struct inode *fat_iget(struct super_block *sb, loff_t i_pos) { struct msdos_sb_info *sbi = MSDOS_SB(sb); struct hlist_head *head = sbi->inode_hashtable + fat_hash(i_pos); - struct hlist_node *_p; struct msdos_inode_info *i; struct inode *inode = NULL; spin_lock(&sbi->inode_hash_lock); - hlist_for_each_entry(i, _p, head, i_fat_hash) { + hlist_for_each_entry(i, head, i_fat_hash) { BUG_ON(i->vfs_inode.i_sb != sb); if (i->i_pos != i_pos) continue; @@ -488,10 +488,59 @@ static void fat_evict_inode(struct inode *inode) fat_detach(inode); } +static void fat_set_state(struct super_block *sb, + unsigned int set, unsigned int force) +{ + struct buffer_head *bh; + struct fat_boot_sector *b; + struct msdos_sb_info *sbi = sb->s_fs_info; + + /* do not change any thing if mounted read only */ + if ((sb->s_flags & MS_RDONLY) && !force) + return; + + /* do not change state if fs was dirty */ + if (sbi->dirty) { + /* warn only on set (mount). */ + if (set) + fat_msg(sb, KERN_WARNING, "Volume was not properly " + "unmounted. Some data may be corrupt. " + "Please run fsck."); + return; + } + + bh = sb_bread(sb, 0); + if (bh == NULL) { + fat_msg(sb, KERN_ERR, "unable to read boot sector " + "to mark fs as dirty"); + return; + } + + b = (struct fat_boot_sector *) bh->b_data; + + if (sbi->fat_bits == 32) { + if (set) + b->fat32.state |= FAT_STATE_DIRTY; + else + b->fat32.state &= ~FAT_STATE_DIRTY; + } else /* fat 16 and 12 */ { + if (set) + b->fat16.state |= FAT_STATE_DIRTY; + else + b->fat16.state &= ~FAT_STATE_DIRTY; + } + + mark_buffer_dirty(bh); + sync_dirty_buffer(bh); + brelse(bh); +} + static void fat_put_super(struct super_block *sb) { struct msdos_sb_info *sbi = MSDOS_SB(sb); + fat_set_state(sb, 0, 0); + iput(sbi->fsinfo_inode); iput(sbi->fat_inode); @@ -566,8 +615,18 @@ static void __exit fat_destroy_inodecache(void) static int fat_remount(struct super_block *sb, int *flags, char *data) { + int new_rdonly; struct msdos_sb_info *sbi = MSDOS_SB(sb); *flags |= MS_NODIRATIME | (sbi->options.isvfat ? 0 : MS_NOATIME); + + /* make sure we update state on remount. */ + new_rdonly = *flags & MS_RDONLY; + if (new_rdonly != (sb->s_flags & MS_RDONLY)) { + if (new_rdonly) + fat_set_state(sb, 0, 0); + else + fat_set_state(sb, 1, 1); + } return 0; } @@ -1298,17 +1357,17 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, sbi->prev_free = FAT_START_ENT; sb->s_maxbytes = 0xffffffff; - if (!sbi->fat_length && b->fat32_length) { + if (!sbi->fat_length && b->fat32.length) { struct fat_boot_fsinfo *fsinfo; struct buffer_head *fsinfo_bh; /* Must be FAT32 */ sbi->fat_bits = 32; - sbi->fat_length = le32_to_cpu(b->fat32_length); - sbi->root_cluster = le32_to_cpu(b->root_cluster); + sbi->fat_length = le32_to_cpu(b->fat32.length); + sbi->root_cluster = le32_to_cpu(b->fat32.root_cluster); /* MC - if info_sector is 0, don't multiply by 0 */ - sbi->fsinfo_sector = le16_to_cpu(b->info_sector); + sbi->fsinfo_sector = le16_to_cpu(b->fat32.info_sector); if (sbi->fsinfo_sector == 0) sbi->fsinfo_sector = 1; @@ -1362,6 +1421,12 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, if (sbi->fat_bits != 32) sbi->fat_bits = (total_clusters > MAX_FAT12) ? 16 : 12; + /* some OSes set FAT_STATE_DIRTY and clean it on unmount. */ + if (sbi->fat_bits == 32) + sbi->dirty = b->fat32.state & FAT_STATE_DIRTY; + else /* fat 16 or 12 */ + sbi->dirty = b->fat16.state & FAT_STATE_DIRTY; + /* check that FAT table does not overflow */ fat_clusters = sbi->fat_length * sb->s_blocksize * 8 / sbi->fat_bits; total_clusters = min(total_clusters, fat_clusters - FAT_START_ENT); @@ -1456,6 +1521,7 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, "the device does not support discard"); } + fat_set_state(sb, 1, 0); return 0; out_invalid: diff --git a/fs/fat/nfs.c b/fs/fat/nfs.c index ef4b5faba87b..499c10438ca2 100644 --- a/fs/fat/nfs.c +++ b/fs/fat/nfs.c @@ -21,13 +21,12 @@ static struct inode *fat_dget(struct super_block *sb, int i_logstart) { struct msdos_sb_info *sbi = MSDOS_SB(sb); struct hlist_head *head; - struct hlist_node *_p; struct msdos_inode_info *i; struct inode *inode = NULL; head = sbi->dir_hashtable + fat_dir_hash(i_logstart); spin_lock(&sbi->dir_hash_lock); - hlist_for_each_entry(i, _p, head, i_dir_hash) { + hlist_for_each_entry(i, head, i_dir_hash) { BUG_ON(i->vfs_inode.i_sb != sb); if (i->i_logstart != i_logstart) continue; diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index 8dcb114758e3..e2cba1f60c21 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -237,13 +237,12 @@ static int fscache_alloc_object(struct fscache_cache *cache, struct fscache_cookie *cookie) { struct fscache_object *object; - struct hlist_node *_n; int ret; _enter("%p,%p{%s}", cache, cookie, cookie->def->name); spin_lock(&cookie->lock); - hlist_for_each_entry(object, _n, &cookie->backing_objects, + hlist_for_each_entry(object, &cookie->backing_objects, cookie_link) { if (object->cache == cache) goto object_already_extant; @@ -311,7 +310,6 @@ static int fscache_attach_object(struct fscache_cookie *cookie, { struct fscache_object *p; struct fscache_cache *cache = object->cache; - struct hlist_node *_n; int ret; _enter("{%s},{OBJ%x}", cookie->def->name, object->debug_id); @@ -321,7 +319,7 @@ static int fscache_attach_object(struct fscache_cookie *cookie, /* there may be multiple initial creations of this object, but we only * want one */ ret = -EEXIST; - hlist_for_each_entry(p, _n, &cookie->backing_objects, cookie_link) { + hlist_for_each_entry(p, &cookie->backing_objects, cookie_link) { if (p->cache == object->cache) { if (p->state >= FSCACHE_OBJECT_DYING) ret = -ENOBUFS; @@ -331,7 +329,7 @@ static int fscache_attach_object(struct fscache_cookie *cookie, /* pin the parent object */ spin_lock_nested(&cookie->parent->lock, 1); - hlist_for_each_entry(p, _n, &cookie->parent->backing_objects, + hlist_for_each_entry(p, &cookie->parent->backing_objects, cookie_link) { if (p->cache == object->cache) { if (p->state >= FSCACHE_OBJECT_DYING) { @@ -435,7 +433,6 @@ EXPORT_SYMBOL(__fscache_wait_on_invalidate); void __fscache_update_cookie(struct fscache_cookie *cookie) { struct fscache_object *object; - struct hlist_node *_p; fscache_stat(&fscache_n_updates); @@ -452,7 +449,7 @@ void __fscache_update_cookie(struct fscache_cookie *cookie) spin_lock(&cookie->lock); /* update the index entry on disk in each cache backing this cookie */ - hlist_for_each_entry(object, _p, + hlist_for_each_entry(object, &cookie->backing_objects, cookie_link) { fscache_raise_event(object, FSCACHE_OBJECT_EV_UPDATE); } diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c index 6f96a8def147..06b5e086ab3a 100644 --- a/fs/fuse/cuse.c +++ b/fs/fuse/cuse.c @@ -38,6 +38,7 @@ #include <linux/device.h> #include <linux/file.h> #include <linux/fs.h> +#include <linux/aio.h> #include <linux/kdev_t.h> #include <linux/kthread.h> #include <linux/list.h> diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index cbae09e5a491..95de0a2b8f0b 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -19,6 +19,7 @@ #include <linux/pipe_fs_i.h> #include <linux/swap.h> #include <linux/splice.h> +#include <linux/aio.h> MODULE_ALIAS_MISCDEV(FUSE_MINOR); MODULE_ALIAS("devname:fuse"); diff --git a/fs/fuse/file.c b/fs/fuse/file.c index a010585b0a74..3f95325a0312 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -15,6 +15,7 @@ #include <linux/module.h> #include <linux/compat.h> #include <linux/swap.h> +#include <linux/aio.h> static const struct file_operations fuse_direct_io_file_operations; diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 24f414f0ce61..371bd144d802 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -20,6 +20,7 @@ #include <linux/swap.h> #include <linux/gfs2_ondisk.h> #include <linux/backing-dev.h> +#include <linux/aio.h> #include "gfs2.h" #include "incore.h" diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 06b7092a3f25..2d42817442fb 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -25,6 +25,7 @@ #include <asm/uaccess.h> #include <linux/dlm.h> #include <linux/dlm_plock.h> +#include <linux/aio.h> #include "gfs2.h" #include "incore.h" @@ -483,7 +484,7 @@ out: gfs2_holder_uninit(&gh); if (ret == 0) { set_page_dirty(page); - wait_on_page_writeback(page); + wait_for_stable_page(page); } sb_end_pagefault(inode->i_sb); return block_page_mkwrite_return(ret); diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c index 462e84142759..eb81cef67fa3 100644 --- a/fs/gfs2/sys.c +++ b/fs/gfs2/sys.c @@ -103,7 +103,7 @@ static ssize_t freeze_store(struct gfs2_sbd *sdp, const char *buf, size_t len) int n = simple_strtol(buf, NULL, 0); if (!capable(CAP_SYS_ADMIN)) - return -EACCES; + return -EPERM; switch (n) { case 0: @@ -133,7 +133,7 @@ static ssize_t withdraw_show(struct gfs2_sbd *sdp, char *buf) static ssize_t withdraw_store(struct gfs2_sbd *sdp, const char *buf, size_t len) { if (!capable(CAP_SYS_ADMIN)) - return -EACCES; + return -EPERM; if (simple_strtol(buf, NULL, 0) != 1) return -EINVAL; @@ -148,7 +148,7 @@ static ssize_t statfs_sync_store(struct gfs2_sbd *sdp, const char *buf, size_t len) { if (!capable(CAP_SYS_ADMIN)) - return -EACCES; + return -EPERM; if (simple_strtol(buf, NULL, 0) != 1) return -EINVAL; @@ -161,7 +161,7 @@ static ssize_t quota_sync_store(struct gfs2_sbd *sdp, const char *buf, size_t len) { if (!capable(CAP_SYS_ADMIN)) - return -EACCES; + return -EPERM; if (simple_strtol(buf, NULL, 0) != 1) return -EINVAL; @@ -177,7 +177,7 @@ static ssize_t quota_refresh_user_store(struct gfs2_sbd *sdp, const char *buf, u32 id; if (!capable(CAP_SYS_ADMIN)) - return -EACCES; + return -EPERM; id = simple_strtoul(buf, NULL, 0); @@ -192,7 +192,7 @@ static ssize_t quota_refresh_group_store(struct gfs2_sbd *sdp, const char *buf, u32 id; if (!capable(CAP_SYS_ADMIN)) - return -EACCES; + return -EPERM; id = simple_strtoul(buf, NULL, 0); @@ -211,7 +211,7 @@ static ssize_t demote_rq_store(struct gfs2_sbd *sdp, const char *buf, size_t len int rv; if (!capable(CAP_SYS_ADMIN)) - return -EACCES; + return -EPERM; rv = sscanf(buf, "%u:%llu %15s", &gltype, &glnum, mode); @@ -500,7 +500,7 @@ static ssize_t quota_scale_store(struct gfs2_sbd *sdp, const char *buf, unsigned int x, y; if (!capable(CAP_SYS_ADMIN)) - return -EACCES; + return -EPERM; if (sscanf(buf, "%u %u", &x, &y) != 2 || !y) return -EINVAL; @@ -519,7 +519,7 @@ static ssize_t tune_set(struct gfs2_sbd *sdp, unsigned int *field, unsigned int x; if (!capable(CAP_SYS_ADMIN)) - return -EACCES; + return -EPERM; x = simple_strtoul(buf, NULL, 0); diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index d47f11658c17..b2f3025827a1 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -14,6 +14,7 @@ #include <linux/pagemap.h> #include <linux/mpage.h> #include <linux/sched.h> +#include <linux/aio.h> #include "hfs_fs.h" #include "btree.h" diff --git a/fs/hfsplus/Makefile b/fs/hfsplus/Makefile index 3cc0df730156..09d278bb7b91 100644 --- a/fs/hfsplus/Makefile +++ b/fs/hfsplus/Makefile @@ -5,5 +5,5 @@ obj-$(CONFIG_HFSPLUS_FS) += hfsplus.o hfsplus-objs := super.o options.o inode.o ioctl.o extents.o catalog.o dir.o btree.o \ - bnode.o brec.o bfind.o tables.o unicode.o wrapper.o bitmap.o part_tbl.o - + bnode.o brec.o bfind.o tables.o unicode.o wrapper.o bitmap.o part_tbl.o \ + attributes.o xattr.o xattr_user.o xattr_security.o xattr_trusted.o diff --git a/fs/hfsplus/attributes.c b/fs/hfsplus/attributes.c new file mode 100644 index 000000000000..8d691f124714 --- /dev/null +++ b/fs/hfsplus/attributes.c @@ -0,0 +1,399 @@ +/* + * linux/fs/hfsplus/attributes.c + * + * Vyacheslav Dubeyko <slava@dubeyko.com> + * + * Handling of records in attributes tree + */ + +#include "hfsplus_fs.h" +#include "hfsplus_raw.h" + +static struct kmem_cache *hfsplus_attr_tree_cachep; + +int hfsplus_create_attr_tree_cache(void) +{ + if (hfsplus_attr_tree_cachep) + return -EEXIST; + + hfsplus_attr_tree_cachep = + kmem_cache_create("hfsplus_attr_cache", + sizeof(hfsplus_attr_entry), 0, + SLAB_HWCACHE_ALIGN, NULL); + if (!hfsplus_attr_tree_cachep) + return -ENOMEM; + + return 0; +} + +void hfsplus_destroy_attr_tree_cache(void) +{ + kmem_cache_destroy(hfsplus_attr_tree_cachep); +} + +int hfsplus_attr_bin_cmp_key(const hfsplus_btree_key *k1, + const hfsplus_btree_key *k2) +{ + __be32 k1_cnid, k2_cnid; + + k1_cnid = k1->attr.cnid; + k2_cnid = k2->attr.cnid; + if (k1_cnid != k2_cnid) + return be32_to_cpu(k1_cnid) < be32_to_cpu(k2_cnid) ? -1 : 1; + + return hfsplus_strcmp( + (const struct hfsplus_unistr *)&k1->attr.key_name, + (const struct hfsplus_unistr *)&k2->attr.key_name); +} + +int hfsplus_attr_build_key(struct super_block *sb, hfsplus_btree_key *key, + u32 cnid, const char *name) +{ + int len; + + memset(key, 0, sizeof(struct hfsplus_attr_key)); + key->attr.cnid = cpu_to_be32(cnid); + if (name) { + len = strlen(name); + if (len > HFSPLUS_ATTR_MAX_STRLEN) { + printk(KERN_ERR "hfs: invalid xattr name's length\n"); + return -EINVAL; + } + hfsplus_asc2uni(sb, + (struct hfsplus_unistr *)&key->attr.key_name, + HFSPLUS_ATTR_MAX_STRLEN, name, len); + len = be16_to_cpu(key->attr.key_name.length); + } else { + key->attr.key_name.length = 0; + len = 0; + } + + /* The length of the key, as stored in key_len field, does not include + * the size of the key_len field itself. + * So, offsetof(hfsplus_attr_key, key_name) is a trick because + * it takes into consideration key_len field (__be16) of + * hfsplus_attr_key structure instead of length field (__be16) of + * hfsplus_attr_unistr structure. + */ + key->key_len = + cpu_to_be16(offsetof(struct hfsplus_attr_key, key_name) + + 2 * len); + + return 0; +} + +void hfsplus_attr_build_key_uni(hfsplus_btree_key *key, + u32 cnid, + struct hfsplus_attr_unistr *name) +{ + int ustrlen; + + memset(key, 0, sizeof(struct hfsplus_attr_key)); + ustrlen = be16_to_cpu(name->length); + key->attr.cnid = cpu_to_be32(cnid); + key->attr.key_name.length = cpu_to_be16(ustrlen); + ustrlen *= 2; + memcpy(key->attr.key_name.unicode, name->unicode, ustrlen); + + /* The length of the key, as stored in key_len field, does not include + * the size of the key_len field itself. + * So, offsetof(hfsplus_attr_key, key_name) is a trick because + * it takes into consideration key_len field (__be16) of + * hfsplus_attr_key structure instead of length field (__be16) of + * hfsplus_attr_unistr structure. + */ + key->key_len = + cpu_to_be16(offsetof(struct hfsplus_attr_key, key_name) + + ustrlen); +} + +hfsplus_attr_entry *hfsplus_alloc_attr_entry(void) +{ + return kmem_cache_alloc(hfsplus_attr_tree_cachep, GFP_KERNEL); +} + +void hfsplus_destroy_attr_entry(hfsplus_attr_entry *entry) +{ + if (entry) + kmem_cache_free(hfsplus_attr_tree_cachep, entry); +} + +#define HFSPLUS_INVALID_ATTR_RECORD -1 + +static int hfsplus_attr_build_record(hfsplus_attr_entry *entry, int record_type, + u32 cnid, const void *value, size_t size) +{ + if (record_type == HFSPLUS_ATTR_FORK_DATA) { + /* + * Mac OS X supports only inline data attributes. + * Do nothing + */ + memset(entry, 0, sizeof(*entry)); + return sizeof(struct hfsplus_attr_fork_data); + } else if (record_type == HFSPLUS_ATTR_EXTENTS) { + /* + * Mac OS X supports only inline data attributes. + * Do nothing. + */ + memset(entry, 0, sizeof(*entry)); + return sizeof(struct hfsplus_attr_extents); + } else if (record_type == HFSPLUS_ATTR_INLINE_DATA) { + u16 len; + + memset(entry, 0, sizeof(struct hfsplus_attr_inline_data)); + entry->inline_data.record_type = cpu_to_be32(record_type); + if (size <= HFSPLUS_MAX_INLINE_DATA_SIZE) + len = size; + else + return HFSPLUS_INVALID_ATTR_RECORD; + entry->inline_data.length = cpu_to_be16(len); + memcpy(entry->inline_data.raw_bytes, value, len); + /* + * Align len on two-byte boundary. + * It needs to add pad byte if we have odd len. + */ + len = round_up(len, 2); + return offsetof(struct hfsplus_attr_inline_data, raw_bytes) + + len; + } else /* invalid input */ + memset(entry, 0, sizeof(*entry)); + + return HFSPLUS_INVALID_ATTR_RECORD; +} + +int hfsplus_find_attr(struct super_block *sb, u32 cnid, + const char *name, struct hfs_find_data *fd) +{ + int err = 0; + + dprint(DBG_ATTR_MOD, "find_attr: %s,%d\n", name ? name : NULL, cnid); + + if (!HFSPLUS_SB(sb)->attr_tree) { + printk(KERN_ERR "hfs: attributes file doesn't exist\n"); + return -EINVAL; + } + + if (name) { + err = hfsplus_attr_build_key(sb, fd->search_key, cnid, name); + if (err) + goto failed_find_attr; + err = hfs_brec_find(fd, hfs_find_rec_by_key); + if (err) + goto failed_find_attr; + } else { + err = hfsplus_attr_build_key(sb, fd->search_key, cnid, NULL); + if (err) + goto failed_find_attr; + err = hfs_brec_find(fd, hfs_find_1st_rec_by_cnid); + if (err) + goto failed_find_attr; + } + +failed_find_attr: + return err; +} + +int hfsplus_attr_exists(struct inode *inode, const char *name) +{ + int err = 0; + struct super_block *sb = inode->i_sb; + struct hfs_find_data fd; + + if (!HFSPLUS_SB(sb)->attr_tree) + return 0; + + err = hfs_find_init(HFSPLUS_SB(sb)->attr_tree, &fd); + if (err) + return 0; + + err = hfsplus_find_attr(sb, inode->i_ino, name, &fd); + if (err) + goto attr_not_found; + + hfs_find_exit(&fd); + return 1; + +attr_not_found: + hfs_find_exit(&fd); + return 0; +} + +int hfsplus_create_attr(struct inode *inode, + const char *name, + const void *value, size_t size) +{ + struct super_block *sb = inode->i_sb; + struct hfs_find_data fd; + hfsplus_attr_entry *entry_ptr; + int entry_size; + int err; + + dprint(DBG_ATTR_MOD, "create_attr: %s,%ld\n", + name ? name : NULL, inode->i_ino); + + if (!HFSPLUS_SB(sb)->attr_tree) { + printk(KERN_ERR "hfs: attributes file doesn't exist\n"); + return -EINVAL; + } + + entry_ptr = hfsplus_alloc_attr_entry(); + if (!entry_ptr) + return -ENOMEM; + + err = hfs_find_init(HFSPLUS_SB(sb)->attr_tree, &fd); + if (err) + goto failed_init_create_attr; + + if (name) { + err = hfsplus_attr_build_key(sb, fd.search_key, + inode->i_ino, name); + if (err) + goto failed_create_attr; + } else { + err = -EINVAL; + goto failed_create_attr; + } + + /* Mac OS X supports only inline data attributes. */ + entry_size = hfsplus_attr_build_record(entry_ptr, + HFSPLUS_ATTR_INLINE_DATA, + inode->i_ino, + value, size); + if (entry_size == HFSPLUS_INVALID_ATTR_RECORD) { + err = -EINVAL; + goto failed_create_attr; + } + + err = hfs_brec_find(&fd, hfs_find_rec_by_key); + if (err != -ENOENT) { + if (!err) + err = -EEXIST; + goto failed_create_attr; + } + + err = hfs_brec_insert(&fd, entry_ptr, entry_size); + if (err) + goto failed_create_attr; + + hfsplus_mark_inode_dirty(inode, HFSPLUS_I_ATTR_DIRTY); + +failed_create_attr: + hfs_find_exit(&fd); + +failed_init_create_attr: + hfsplus_destroy_attr_entry(entry_ptr); + return err; +} + +static int __hfsplus_delete_attr(struct inode *inode, u32 cnid, + struct hfs_find_data *fd) +{ + int err = 0; + __be32 found_cnid, record_type; + + hfs_bnode_read(fd->bnode, &found_cnid, + fd->keyoffset + + offsetof(struct hfsplus_attr_key, cnid), + sizeof(__be32)); + if (cnid != be32_to_cpu(found_cnid)) + return -ENOENT; + + hfs_bnode_read(fd->bnode, &record_type, + fd->entryoffset, sizeof(record_type)); + + switch (be32_to_cpu(record_type)) { + case HFSPLUS_ATTR_INLINE_DATA: + /* All is OK. Do nothing. */ + break; + case HFSPLUS_ATTR_FORK_DATA: + case HFSPLUS_ATTR_EXTENTS: + printk(KERN_ERR "hfs: only inline data xattr are supported\n"); + return -EOPNOTSUPP; + default: + printk(KERN_ERR "hfs: invalid extended attribute record\n"); + return -ENOENT; + } + + err = hfs_brec_remove(fd); + if (err) + return err; + + hfsplus_mark_inode_dirty(inode, HFSPLUS_I_ATTR_DIRTY); + return err; +} + +int hfsplus_delete_attr(struct inode *inode, const char *name) +{ + int err = 0; + struct super_block *sb = inode->i_sb; + struct hfs_find_data fd; + + dprint(DBG_ATTR_MOD, "delete_attr: %s,%ld\n", + name ? name : NULL, inode->i_ino); + + if (!HFSPLUS_SB(sb)->attr_tree) { + printk(KERN_ERR "hfs: attributes file doesn't exist\n"); + return -EINVAL; + } + + err = hfs_find_init(HFSPLUS_SB(sb)->attr_tree, &fd); + if (err) + return err; + + if (name) { + err = hfsplus_attr_build_key(sb, fd.search_key, + inode->i_ino, name); + if (err) + goto out; + } else { + printk(KERN_ERR "hfs: invalid extended attribute name\n"); + err = -EINVAL; + goto out; + } + + err = hfs_brec_find(&fd, hfs_find_rec_by_key); + if (err) + goto out; + + err = __hfsplus_delete_attr(inode, inode->i_ino, &fd); + if (err) + goto out; + +out: + hfs_find_exit(&fd); + return err; +} + +int hfsplus_delete_all_attrs(struct inode *dir, u32 cnid) +{ + int err = 0; + struct hfs_find_data fd; + + dprint(DBG_ATTR_MOD, "delete_all_attrs: %d\n", cnid); + + if (!HFSPLUS_SB(dir->i_sb)->attr_tree) { + printk(KERN_ERR "hfs: attributes file doesn't exist\n"); + return -EINVAL; + } + + err = hfs_find_init(HFSPLUS_SB(dir->i_sb)->attr_tree, &fd); + if (err) + return err; + + for (;;) { + err = hfsplus_find_attr(dir->i_sb, cnid, NULL, &fd); + if (err) { + if (err != -ENOENT) + printk(KERN_ERR "hfs: xattr search failed.\n"); + goto end_delete_all; + } + + err = __hfsplus_delete_attr(dir, cnid, &fd); + if (err) + goto end_delete_all; + } + +end_delete_all: + hfs_find_exit(&fd); + return err; +} diff --git a/fs/hfsplus/bfind.c b/fs/hfsplus/bfind.c index 5d799c13205f..d73c98d1ee99 100644 --- a/fs/hfsplus/bfind.c +++ b/fs/hfsplus/bfind.c @@ -24,7 +24,19 @@ int hfs_find_init(struct hfs_btree *tree, struct hfs_find_data *fd) fd->key = ptr + tree->max_key_len + 2; dprint(DBG_BNODE_REFS, "find_init: %d (%p)\n", tree->cnid, __builtin_return_address(0)); - mutex_lock(&tree->tree_lock); + switch (tree->cnid) { + case HFSPLUS_CAT_CNID: + mutex_lock_nested(&tree->tree_lock, CATALOG_BTREE_MUTEX); + break; + case HFSPLUS_EXT_CNID: + mutex_lock_nested(&tree->tree_lock, EXTENTS_BTREE_MUTEX); + break; + case HFSPLUS_ATTR_CNID: + mutex_lock_nested(&tree->tree_lock, ATTR_BTREE_MUTEX); + break; + default: + BUG(); + } return 0; } @@ -38,15 +50,73 @@ void hfs_find_exit(struct hfs_find_data *fd) fd->tree = NULL; } -/* Find the record in bnode that best matches key (not greater than...)*/ -int __hfs_brec_find(struct hfs_bnode *bnode, struct hfs_find_data *fd) +int hfs_find_1st_rec_by_cnid(struct hfs_bnode *bnode, + struct hfs_find_data *fd, + int *begin, + int *end, + int *cur_rec) +{ + __be32 cur_cnid, search_cnid; + + if (bnode->tree->cnid == HFSPLUS_EXT_CNID) { + cur_cnid = fd->key->ext.cnid; + search_cnid = fd->search_key->ext.cnid; + } else if (bnode->tree->cnid == HFSPLUS_CAT_CNID) { + cur_cnid = fd->key->cat.parent; + search_cnid = fd->search_key->cat.parent; + } else if (bnode->tree->cnid == HFSPLUS_ATTR_CNID) { + cur_cnid = fd->key->attr.cnid; + search_cnid = fd->search_key->attr.cnid; + } else + BUG(); + + if (cur_cnid == search_cnid) { + (*end) = (*cur_rec); + if ((*begin) == (*end)) + return 1; + } else { + if (be32_to_cpu(cur_cnid) < be32_to_cpu(search_cnid)) + (*begin) = (*cur_rec) + 1; + else + (*end) = (*cur_rec) - 1; + } + + return 0; +} + +int hfs_find_rec_by_key(struct hfs_bnode *bnode, + struct hfs_find_data *fd, + int *begin, + int *end, + int *cur_rec) { int cmpval; + + cmpval = bnode->tree->keycmp(fd->key, fd->search_key); + if (!cmpval) { + (*end) = (*cur_rec); + return 1; + } + if (cmpval < 0) + (*begin) = (*cur_rec) + 1; + else + *(end) = (*cur_rec) - 1; + + return 0; +} + +/* Find the record in bnode that best matches key (not greater than...)*/ +int __hfs_brec_find(struct hfs_bnode *bnode, struct hfs_find_data *fd, + search_strategy_t rec_found) +{ u16 off, len, keylen; int rec; int b, e; int res; + if (!rec_found) + BUG(); + b = 0; e = bnode->num_recs - 1; res = -ENOENT; @@ -59,17 +129,12 @@ int __hfs_brec_find(struct hfs_bnode *bnode, struct hfs_find_data *fd) goto fail; } hfs_bnode_read(bnode, fd->key, off, keylen); - cmpval = bnode->tree->keycmp(fd->key, fd->search_key); - if (!cmpval) { - e = rec; + if (rec_found(bnode, fd, &b, &e, &rec)) { res = 0; goto done; } - if (cmpval < 0) - b = rec + 1; - else - e = rec - 1; } while (b <= e); + if (rec != e && e >= 0) { len = hfs_brec_lenoff(bnode, e, &off); keylen = hfs_brec_keylen(bnode, e); @@ -79,19 +144,21 @@ int __hfs_brec_find(struct hfs_bnode *bnode, struct hfs_find_data *fd) } hfs_bnode_read(bnode, fd->key, off, keylen); } + done: fd->record = e; fd->keyoffset = off; fd->keylength = keylen; fd->entryoffset = off + keylen; fd->entrylength = len - keylen; + fail: return res; } /* Traverse a B*Tree from the root to a leaf finding best fit to key */ /* Return allocated copy of node found, set recnum to best record */ -int hfs_brec_find(struct hfs_find_data *fd) +int hfs_brec_find(struct hfs_find_data *fd, search_strategy_t do_key_compare) { struct hfs_btree *tree; struct hfs_bnode *bnode; @@ -122,7 +189,7 @@ int hfs_brec_find(struct hfs_find_data *fd) goto invalid; bnode->parent = parent; - res = __hfs_brec_find(bnode, fd); + res = __hfs_brec_find(bnode, fd, do_key_compare); if (!height) break; if (fd->record < 0) @@ -149,7 +216,7 @@ int hfs_brec_read(struct hfs_find_data *fd, void *rec, int rec_len) { int res; - res = hfs_brec_find(fd); + res = hfs_brec_find(fd, hfs_find_rec_by_key); if (res) return res; if (fd->entrylength > rec_len) diff --git a/fs/hfsplus/bnode.c b/fs/hfsplus/bnode.c index 1c42cc5b899f..5c125ce6bd72 100644 --- a/fs/hfsplus/bnode.c +++ b/fs/hfsplus/bnode.c @@ -62,7 +62,8 @@ void hfs_bnode_read_key(struct hfs_bnode *node, void *key, int off) tree = node->tree; if (node->type == HFS_NODE_LEAF || - tree->attributes & HFS_TREE_VARIDXKEYS) + tree->attributes & HFS_TREE_VARIDXKEYS || + node->tree->cnid == HFSPLUS_ATTR_CNID) key_len = hfs_bnode_read_u16(node, off) + 2; else key_len = tree->max_key_len + 2; @@ -314,7 +315,8 @@ void hfs_bnode_dump(struct hfs_bnode *node) if (i && node->type == HFS_NODE_INDEX) { int tmp; - if (node->tree->attributes & HFS_TREE_VARIDXKEYS) + if (node->tree->attributes & HFS_TREE_VARIDXKEYS || + node->tree->cnid == HFSPLUS_ATTR_CNID) tmp = hfs_bnode_read_u16(node, key_off) + 2; else tmp = node->tree->max_key_len + 2; diff --git a/fs/hfsplus/brec.c b/fs/hfsplus/brec.c index 2a734cfccc92..298d4e45604b 100644 --- a/fs/hfsplus/brec.c +++ b/fs/hfsplus/brec.c @@ -36,7 +36,8 @@ u16 hfs_brec_keylen(struct hfs_bnode *node, u16 rec) return 0; if ((node->type == HFS_NODE_INDEX) && - !(node->tree->attributes & HFS_TREE_VARIDXKEYS)) { + !(node->tree->attributes & HFS_TREE_VARIDXKEYS) && + (node->tree->cnid != HFSPLUS_ATTR_CNID)) { retval = node->tree->max_key_len + 2; } else { recoff = hfs_bnode_read_u16(node, @@ -151,12 +152,13 @@ skip: /* get index key */ hfs_bnode_read_key(new_node, fd->search_key, 14); - __hfs_brec_find(fd->bnode, fd); + __hfs_brec_find(fd->bnode, fd, hfs_find_rec_by_key); hfs_bnode_put(new_node); new_node = NULL; - if (tree->attributes & HFS_TREE_VARIDXKEYS) + if ((tree->attributes & HFS_TREE_VARIDXKEYS) || + (tree->cnid == HFSPLUS_ATTR_CNID)) key_len = be16_to_cpu(fd->search_key->key_len) + 2; else { fd->search_key->key_len = @@ -201,7 +203,7 @@ again: hfs_bnode_put(node); node = fd->bnode = parent; - __hfs_brec_find(node, fd); + __hfs_brec_find(node, fd, hfs_find_rec_by_key); goto again; } hfs_bnode_write_u16(node, @@ -367,12 +369,13 @@ again: parent = hfs_bnode_find(tree, node->parent); if (IS_ERR(parent)) return PTR_ERR(parent); - __hfs_brec_find(parent, fd); + __hfs_brec_find(parent, fd, hfs_find_rec_by_key); hfs_bnode_dump(parent); rec = fd->record; /* size difference between old and new key */ - if (tree->attributes & HFS_TREE_VARIDXKEYS) + if ((tree->attributes & HFS_TREE_VARIDXKEYS) || + (tree->cnid == HFSPLUS_ATTR_CNID)) newkeylen = hfs_bnode_read_u16(node, 14) + 2; else fd->keylength = newkeylen = tree->max_key_len + 2; @@ -427,7 +430,7 @@ skip: hfs_bnode_read_key(new_node, fd->search_key, 14); cnid = cpu_to_be32(new_node->this); - __hfs_brec_find(fd->bnode, fd); + __hfs_brec_find(fd->bnode, fd, hfs_find_rec_by_key); hfs_brec_insert(fd, &cnid, sizeof(cnid)); hfs_bnode_put(fd->bnode); hfs_bnode_put(new_node); @@ -495,13 +498,15 @@ static int hfs_btree_inc_height(struct hfs_btree *tree) /* insert old root idx into new root */ node->parent = tree->root; if (node->type == HFS_NODE_LEAF || - tree->attributes & HFS_TREE_VARIDXKEYS) + tree->attributes & HFS_TREE_VARIDXKEYS || + tree->cnid == HFSPLUS_ATTR_CNID) key_size = hfs_bnode_read_u16(node, 14) + 2; else key_size = tree->max_key_len + 2; hfs_bnode_copy(new_node, 14, node, 14, key_size); - if (!(tree->attributes & HFS_TREE_VARIDXKEYS)) { + if (!(tree->attributes & HFS_TREE_VARIDXKEYS) && + (tree->cnid != HFSPLUS_ATTR_CNID)) { key_size = tree->max_key_len + 2; hfs_bnode_write_u16(new_node, 14, tree->max_key_len); } diff --git a/fs/hfsplus/btree.c b/fs/hfsplus/btree.c index 685d07d0ed18..efb689c21a95 100644 --- a/fs/hfsplus/btree.c +++ b/fs/hfsplus/btree.c @@ -98,6 +98,14 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id) set_bit(HFSPLUS_SB_CASEFOLD, &HFSPLUS_SB(sb)->flags); } break; + case HFSPLUS_ATTR_CNID: + if (tree->max_key_len != HFSPLUS_ATTR_KEYLEN - sizeof(u16)) { + printk(KERN_ERR "hfs: invalid attributes max_key_len %d\n", + tree->max_key_len); + goto fail_page; + } + tree->keycmp = hfsplus_attr_bin_cmp_key; + break; default: printk(KERN_ERR "hfs: unknown B*Tree requested\n"); goto fail_page; diff --git a/fs/hfsplus/catalog.c b/fs/hfsplus/catalog.c index 798d9c4c5e71..840d71edd193 100644 --- a/fs/hfsplus/catalog.c +++ b/fs/hfsplus/catalog.c @@ -45,7 +45,8 @@ void hfsplus_cat_build_key(struct super_block *sb, hfsplus_btree_key *key, key->cat.parent = cpu_to_be32(parent); if (str) { - hfsplus_asc2uni(sb, &key->cat.name, str->name, str->len); + hfsplus_asc2uni(sb, &key->cat.name, HFSPLUS_MAX_STRLEN, + str->name, str->len); len = be16_to_cpu(key->cat.name.length); } else { key->cat.name.length = 0; @@ -167,7 +168,8 @@ static int hfsplus_fill_cat_thread(struct super_block *sb, entry->type = cpu_to_be16(type); entry->thread.reserved = 0; entry->thread.parentID = cpu_to_be32(parentid); - hfsplus_asc2uni(sb, &entry->thread.nodeName, str->name, str->len); + hfsplus_asc2uni(sb, &entry->thread.nodeName, HFSPLUS_MAX_STRLEN, + str->name, str->len); return 10 + be16_to_cpu(entry->thread.nodeName.length) * 2; } @@ -198,7 +200,7 @@ int hfsplus_find_cat(struct super_block *sb, u32 cnid, hfsplus_cat_build_key_uni(fd->search_key, be32_to_cpu(tmp.thread.parentID), &tmp.thread.nodeName); - return hfs_brec_find(fd); + return hfs_brec_find(fd, hfs_find_rec_by_key); } int hfsplus_create_cat(u32 cnid, struct inode *dir, @@ -221,7 +223,7 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir, S_ISDIR(inode->i_mode) ? HFSPLUS_FOLDER_THREAD : HFSPLUS_FILE_THREAD, dir->i_ino, str); - err = hfs_brec_find(&fd); + err = hfs_brec_find(&fd, hfs_find_rec_by_key); if (err != -ENOENT) { if (!err) err = -EEXIST; @@ -233,7 +235,7 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir, hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, str); entry_size = hfsplus_cat_build_record(&entry, cnid, inode); - err = hfs_brec_find(&fd); + err = hfs_brec_find(&fd, hfs_find_rec_by_key); if (err != -ENOENT) { /* panic? */ if (!err) @@ -253,7 +255,7 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir, err1: hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL); - if (!hfs_brec_find(&fd)) + if (!hfs_brec_find(&fd, hfs_find_rec_by_key)) hfs_brec_remove(&fd); err2: hfs_find_exit(&fd); @@ -279,7 +281,7 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str) int len; hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL); - err = hfs_brec_find(&fd); + err = hfs_brec_find(&fd, hfs_find_rec_by_key); if (err) goto out; @@ -296,7 +298,7 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str) } else hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, str); - err = hfs_brec_find(&fd); + err = hfs_brec_find(&fd, hfs_find_rec_by_key); if (err) goto out; @@ -326,7 +328,7 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str) goto out; hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL); - err = hfs_brec_find(&fd); + err = hfs_brec_find(&fd, hfs_find_rec_by_key); if (err) goto out; @@ -337,6 +339,12 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str) dir->i_size--; dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC; hfsplus_mark_inode_dirty(dir, HFSPLUS_I_CAT_DIRTY); + + if (type == HFSPLUS_FILE || type == HFSPLUS_FOLDER) { + if (HFSPLUS_SB(sb)->attr_tree) + hfsplus_delete_all_attrs(dir, cnid); + } + out: hfs_find_exit(&fd); @@ -363,7 +371,7 @@ int hfsplus_rename_cat(u32 cnid, /* find the old dir entry and read the data */ hfsplus_cat_build_key(sb, src_fd.search_key, src_dir->i_ino, src_name); - err = hfs_brec_find(&src_fd); + err = hfs_brec_find(&src_fd, hfs_find_rec_by_key); if (err) goto out; if (src_fd.entrylength > sizeof(entry) || src_fd.entrylength < 0) { @@ -376,7 +384,7 @@ int hfsplus_rename_cat(u32 cnid, /* create new dir entry with the data from the old entry */ hfsplus_cat_build_key(sb, dst_fd.search_key, dst_dir->i_ino, dst_name); - err = hfs_brec_find(&dst_fd); + err = hfs_brec_find(&dst_fd, hfs_find_rec_by_key); if (err != -ENOENT) { if (!err) err = -EEXIST; @@ -391,7 +399,7 @@ int hfsplus_rename_cat(u32 cnid, /* finally remove the old entry */ hfsplus_cat_build_key(sb, src_fd.search_key, src_dir->i_ino, src_name); - err = hfs_brec_find(&src_fd); + err = hfs_brec_find(&src_fd, hfs_find_rec_by_key); if (err) goto out; err = hfs_brec_remove(&src_fd); @@ -402,7 +410,7 @@ int hfsplus_rename_cat(u32 cnid, /* remove old thread entry */ hfsplus_cat_build_key(sb, src_fd.search_key, cnid, NULL); - err = hfs_brec_find(&src_fd); + err = hfs_brec_find(&src_fd, hfs_find_rec_by_key); if (err) goto out; type = hfs_bnode_read_u16(src_fd.bnode, src_fd.entryoffset); @@ -414,7 +422,7 @@ int hfsplus_rename_cat(u32 cnid, hfsplus_cat_build_key(sb, dst_fd.search_key, cnid, NULL); entry_size = hfsplus_fill_cat_thread(sb, &entry, type, dst_dir->i_ino, dst_name); - err = hfs_brec_find(&dst_fd); + err = hfs_brec_find(&dst_fd, hfs_find_rec_by_key); if (err != -ENOENT) { if (!err) err = -EEXIST; diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c index 6b9f921ef2fa..47699d87bc33 100644 --- a/fs/hfsplus/dir.c +++ b/fs/hfsplus/dir.c @@ -15,6 +15,7 @@ #include "hfsplus_fs.h" #include "hfsplus_raw.h" +#include "xattr.h" static inline void hfsplus_instantiate(struct dentry *dentry, struct inode *inode, u32 cnid) @@ -138,7 +139,7 @@ static int hfsplus_readdir(struct file *filp, void *dirent, filldir_t filldir) if (err) return err; hfsplus_cat_build_key(sb, fd.search_key, inode->i_ino, NULL); - err = hfs_brec_find(&fd); + err = hfs_brec_find(&fd, hfs_find_rec_by_key); if (err) goto out; @@ -421,6 +422,15 @@ static int hfsplus_symlink(struct inode *dir, struct dentry *dentry, if (res) goto out_err; + res = hfsplus_init_inode_security(inode, dir, &dentry->d_name); + if (res == -EOPNOTSUPP) + res = 0; /* Operation is not supported. */ + else if (res) { + /* Try to delete anyway without error analysis. */ + hfsplus_delete_cat(inode->i_ino, dir, &dentry->d_name); + goto out_err; + } + hfsplus_instantiate(dentry, inode, inode->i_ino); mark_inode_dirty(inode); goto out; @@ -450,15 +460,26 @@ static int hfsplus_mknod(struct inode *dir, struct dentry *dentry, init_special_inode(inode, mode, rdev); res = hfsplus_create_cat(inode->i_ino, dir, &dentry->d_name, inode); - if (res) { - clear_nlink(inode); - hfsplus_delete_inode(inode); - iput(inode); - goto out; + if (res) + goto failed_mknod; + + res = hfsplus_init_inode_security(inode, dir, &dentry->d_name); + if (res == -EOPNOTSUPP) + res = 0; /* Operation is not supported. */ + else if (res) { + /* Try to delete anyway without error analysis. */ + hfsplus_delete_cat(inode->i_ino, dir, &dentry->d_name); + goto failed_mknod; } hfsplus_instantiate(dentry, inode, inode->i_ino); mark_inode_dirty(inode); + goto out; + +failed_mknod: + clear_nlink(inode); + hfsplus_delete_inode(inode); + iput(inode); out: mutex_unlock(&sbi->vh_mutex); return res; @@ -499,15 +520,19 @@ static int hfsplus_rename(struct inode *old_dir, struct dentry *old_dentry, } const struct inode_operations hfsplus_dir_inode_operations = { - .lookup = hfsplus_lookup, - .create = hfsplus_create, - .link = hfsplus_link, - .unlink = hfsplus_unlink, - .mkdir = hfsplus_mkdir, - .rmdir = hfsplus_rmdir, - .symlink = hfsplus_symlink, - .mknod = hfsplus_mknod, - .rename = hfsplus_rename, + .lookup = hfsplus_lookup, + .create = hfsplus_create, + .link = hfsplus_link, + .unlink = hfsplus_unlink, + .mkdir = hfsplus_mkdir, + .rmdir = hfsplus_rmdir, + .symlink = hfsplus_symlink, + .mknod = hfsplus_mknod, + .rename = hfsplus_rename, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, + .listxattr = hfsplus_listxattr, + .removexattr = hfsplus_removexattr, }; const struct file_operations hfsplus_dir_operations = { diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c index eba76eab6d62..a94f0f779d5e 100644 --- a/fs/hfsplus/extents.c +++ b/fs/hfsplus/extents.c @@ -95,7 +95,7 @@ static void __hfsplus_ext_write_extent(struct inode *inode, HFSPLUS_IS_RSRC(inode) ? HFSPLUS_TYPE_RSRC : HFSPLUS_TYPE_DATA); - res = hfs_brec_find(fd); + res = hfs_brec_find(fd, hfs_find_rec_by_key); if (hip->extent_state & HFSPLUS_EXT_NEW) { if (res != -ENOENT) return; @@ -154,7 +154,7 @@ static inline int __hfsplus_ext_read_extent(struct hfs_find_data *fd, hfsplus_ext_build_key(fd->search_key, cnid, block, type); fd->key->ext.cnid = 0; - res = hfs_brec_find(fd); + res = hfs_brec_find(fd, hfs_find_rec_by_key); if (res && res != -ENOENT) return res; if (fd->key->ext.cnid != fd->search_key->ext.cnid || diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h index a6da86b1b4c1..05b11f36024c 100644 --- a/fs/hfsplus/hfsplus_fs.h +++ b/fs/hfsplus/hfsplus_fs.h @@ -23,6 +23,7 @@ #define DBG_SUPER 0x00000010 #define DBG_EXTENT 0x00000020 #define DBG_BITMAP 0x00000040 +#define DBG_ATTR_MOD 0x00000080 #if 0 #define DBG_MASK (DBG_EXTENT|DBG_INODE|DBG_BNODE_MOD) @@ -46,6 +47,13 @@ typedef int (*btree_keycmp)(const hfsplus_btree_key *, #define NODE_HASH_SIZE 256 +/* B-tree mutex nested subclasses */ +enum hfsplus_btree_mutex_classes { + CATALOG_BTREE_MUTEX, + EXTENTS_BTREE_MUTEX, + ATTR_BTREE_MUTEX, +}; + /* An HFS+ BTree held in memory */ struct hfs_btree { struct super_block *sb; @@ -223,6 +231,7 @@ struct hfsplus_inode_info { #define HFSPLUS_I_CAT_DIRTY 1 /* has changes in the catalog tree */ #define HFSPLUS_I_EXT_DIRTY 2 /* has changes in the extent tree */ #define HFSPLUS_I_ALLOC_DIRTY 3 /* has changes in the allocation file */ +#define HFSPLUS_I_ATTR_DIRTY 4 /* has changes in the attributes tree */ #define HFSPLUS_IS_RSRC(inode) \ test_bit(HFSPLUS_I_RSRC, &HFSPLUS_I(inode)->flags) @@ -302,7 +311,7 @@ static inline unsigned short hfsplus_min_io_size(struct super_block *sb) #define hfs_brec_remove hfsplus_brec_remove #define hfs_find_init hfsplus_find_init #define hfs_find_exit hfsplus_find_exit -#define __hfs_brec_find __hplusfs_brec_find +#define __hfs_brec_find __hfsplus_brec_find #define hfs_brec_find hfsplus_brec_find #define hfs_brec_read hfsplus_brec_read #define hfs_brec_goto hfsplus_brec_goto @@ -324,10 +333,33 @@ static inline unsigned short hfsplus_min_io_size(struct super_block *sb) */ #define HFSPLUS_IOC_BLESS _IO('h', 0x80) +typedef int (*search_strategy_t)(struct hfs_bnode *, + struct hfs_find_data *, + int *, int *, int *); + /* * Functions in any *.c used in other files */ +/* attributes.c */ +int hfsplus_create_attr_tree_cache(void); +void hfsplus_destroy_attr_tree_cache(void); +hfsplus_attr_entry *hfsplus_alloc_attr_entry(void); +void hfsplus_destroy_attr_entry(hfsplus_attr_entry *entry_p); +int hfsplus_attr_bin_cmp_key(const hfsplus_btree_key *, + const hfsplus_btree_key *); +int hfsplus_attr_build_key(struct super_block *, hfsplus_btree_key *, + u32, const char *); +void hfsplus_attr_build_key_uni(hfsplus_btree_key *key, + u32 cnid, + struct hfsplus_attr_unistr *name); +int hfsplus_find_attr(struct super_block *, u32, + const char *, struct hfs_find_data *); +int hfsplus_attr_exists(struct inode *inode, const char *name); +int hfsplus_create_attr(struct inode *, const char *, const void *, size_t); +int hfsplus_delete_attr(struct inode *, const char *); +int hfsplus_delete_all_attrs(struct inode *dir, u32 cnid); + /* bitmap.c */ int hfsplus_block_allocate(struct super_block *, u32, u32, u32 *); int hfsplus_block_free(struct super_block *, u32, u32); @@ -369,8 +401,15 @@ int hfs_brec_remove(struct hfs_find_data *); /* bfind.c */ int hfs_find_init(struct hfs_btree *, struct hfs_find_data *); void hfs_find_exit(struct hfs_find_data *); -int __hfs_brec_find(struct hfs_bnode *, struct hfs_find_data *); -int hfs_brec_find(struct hfs_find_data *); +int hfs_find_1st_rec_by_cnid(struct hfs_bnode *, + struct hfs_find_data *, + int *, int *, int *); +int hfs_find_rec_by_key(struct hfs_bnode *, + struct hfs_find_data *, + int *, int *, int *); +int __hfs_brec_find(struct hfs_bnode *, struct hfs_find_data *, + search_strategy_t); +int hfs_brec_find(struct hfs_find_data *, search_strategy_t); int hfs_brec_read(struct hfs_find_data *, void *, int); int hfs_brec_goto(struct hfs_find_data *, int); @@ -417,11 +456,6 @@ int hfsplus_file_fsync(struct file *file, loff_t start, loff_t end, /* ioctl.c */ long hfsplus_ioctl(struct file *filp, unsigned int cmd, unsigned long arg); -int hfsplus_setxattr(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags); -ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name, - void *value, size_t size); -ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size); /* options.c */ int hfsplus_parse_options(char *, struct hfsplus_sb_info *); @@ -446,7 +480,7 @@ int hfsplus_strcmp(const struct hfsplus_unistr *, int hfsplus_uni2asc(struct super_block *, const struct hfsplus_unistr *, char *, int *); int hfsplus_asc2uni(struct super_block *, - struct hfsplus_unistr *, const char *, int); + struct hfsplus_unistr *, int, const char *, int); int hfsplus_hash_dentry(const struct dentry *dentry, const struct inode *inode, struct qstr *str); int hfsplus_compare_dentry(const struct dentry *parent, diff --git a/fs/hfsplus/hfsplus_raw.h b/fs/hfsplus/hfsplus_raw.h index 921967e5abb1..452ede01b036 100644 --- a/fs/hfsplus/hfsplus_raw.h +++ b/fs/hfsplus/hfsplus_raw.h @@ -52,13 +52,23 @@ typedef __be32 hfsplus_cnid; typedef __be16 hfsplus_unichr; +#define HFSPLUS_MAX_STRLEN 255 +#define HFSPLUS_ATTR_MAX_STRLEN 127 + /* A "string" as used in filenames, etc. */ struct hfsplus_unistr { __be16 length; - hfsplus_unichr unicode[255]; + hfsplus_unichr unicode[HFSPLUS_MAX_STRLEN]; } __packed; -#define HFSPLUS_MAX_STRLEN 255 +/* + * A "string" is used in attributes file + * for name of extended attribute + */ +struct hfsplus_attr_unistr { + __be16 length; + hfsplus_unichr unicode[HFSPLUS_ATTR_MAX_STRLEN]; +} __packed; /* POSIX permissions */ struct hfsplus_perm { @@ -291,6 +301,8 @@ struct hfsplus_cat_file { /* File attribute bits */ #define HFSPLUS_FILE_LOCKED 0x0001 #define HFSPLUS_FILE_THREAD_EXISTS 0x0002 +#define HFSPLUS_XATTR_EXISTS 0x0004 +#define HFSPLUS_ACL_EXISTS 0x0008 /* HFS+ catalog thread (part of a cat_entry) */ struct hfsplus_cat_thread { @@ -327,11 +339,63 @@ struct hfsplus_ext_key { #define HFSPLUS_EXT_KEYLEN sizeof(struct hfsplus_ext_key) +#define HFSPLUS_XATTR_FINDER_INFO_NAME "com.apple.FinderInfo" +#define HFSPLUS_XATTR_ACL_NAME "com.apple.system.Security" + +#define HFSPLUS_ATTR_INLINE_DATA 0x10 +#define HFSPLUS_ATTR_FORK_DATA 0x20 +#define HFSPLUS_ATTR_EXTENTS 0x30 + +/* HFS+ attributes tree key */ +struct hfsplus_attr_key { + __be16 key_len; + __be16 pad; + hfsplus_cnid cnid; + __be32 start_block; + struct hfsplus_attr_unistr key_name; +} __packed; + +#define HFSPLUS_ATTR_KEYLEN sizeof(struct hfsplus_attr_key) + +/* HFS+ fork data attribute */ +struct hfsplus_attr_fork_data { + __be32 record_type; + __be32 reserved; + struct hfsplus_fork_raw the_fork; +} __packed; + +/* HFS+ extension attribute */ +struct hfsplus_attr_extents { + __be32 record_type; + __be32 reserved; + struct hfsplus_extent extents; +} __packed; + +#define HFSPLUS_MAX_INLINE_DATA_SIZE 3802 + +/* HFS+ attribute inline data */ +struct hfsplus_attr_inline_data { + __be32 record_type; + __be32 reserved1; + u8 reserved2[6]; + __be16 length; + u8 raw_bytes[HFSPLUS_MAX_INLINE_DATA_SIZE]; +} __packed; + +/* A data record in the attributes tree */ +typedef union { + __be32 record_type; + struct hfsplus_attr_fork_data fork_data; + struct hfsplus_attr_extents extents; + struct hfsplus_attr_inline_data inline_data; +} __packed hfsplus_attr_entry; + /* HFS+ generic BTree key */ typedef union { __be16 key_len; struct hfsplus_cat_key cat; struct hfsplus_ext_key ext; + struct hfsplus_attr_key attr; } __packed hfsplus_btree_key; #endif diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 799b336b59f9..0aff99fdeb16 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -14,9 +14,11 @@ #include <linux/pagemap.h> #include <linux/mpage.h> #include <linux/sched.h> +#include <linux/aio.h> #include "hfsplus_fs.h" #include "hfsplus_raw.h" +#include "xattr.h" static int hfsplus_readpage(struct file *file, struct page *page) { @@ -348,6 +350,18 @@ int hfsplus_file_fsync(struct file *file, loff_t start, loff_t end, error = error2; } + if (test_and_clear_bit(HFSPLUS_I_ATTR_DIRTY, &hip->flags)) { + if (sbi->attr_tree) { + error2 = + filemap_write_and_wait( + sbi->attr_tree->inode->i_mapping); + if (!error) + error = error2; + } else { + printk(KERN_ERR "hfs: sync non-existent attributes tree\n"); + } + } + if (test_and_clear_bit(HFSPLUS_I_ALLOC_DIRTY, &hip->flags)) { error2 = filemap_write_and_wait(sbi->alloc_file->i_mapping); if (!error) @@ -365,9 +379,10 @@ int hfsplus_file_fsync(struct file *file, loff_t start, loff_t end, static const struct inode_operations hfsplus_file_inode_operations = { .lookup = hfsplus_file_lookup, .setattr = hfsplus_setattr, - .setxattr = hfsplus_setxattr, - .getxattr = hfsplus_getxattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, .listxattr = hfsplus_listxattr, + .removexattr = hfsplus_removexattr, }; static const struct file_operations hfsplus_file_operations = { diff --git a/fs/hfsplus/ioctl.c b/fs/hfsplus/ioctl.c index 09addc8615fa..83a434d0c2e7 100644 --- a/fs/hfsplus/ioctl.c +++ b/fs/hfsplus/ioctl.c @@ -16,7 +16,6 @@ #include <linux/fs.h> #include <linux/mount.h> #include <linux/sched.h> -#include <linux/xattr.h> #include <asm/uaccess.h> #include "hfsplus_fs.h" @@ -151,110 +150,3 @@ long hfsplus_ioctl(struct file *file, unsigned int cmd, unsigned long arg) return -ENOTTY; } } - -int hfsplus_setxattr(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags) -{ - struct inode *inode = dentry->d_inode; - struct hfs_find_data fd; - hfsplus_cat_entry entry; - struct hfsplus_cat_file *file; - int res; - - if (!S_ISREG(inode->i_mode) || HFSPLUS_IS_RSRC(inode)) - return -EOPNOTSUPP; - - res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &fd); - if (res) - return res; - res = hfsplus_find_cat(inode->i_sb, inode->i_ino, &fd); - if (res) - goto out; - hfs_bnode_read(fd.bnode, &entry, fd.entryoffset, - sizeof(struct hfsplus_cat_file)); - file = &entry.file; - - if (!strcmp(name, "hfs.type")) { - if (size == 4) - memcpy(&file->user_info.fdType, value, 4); - else - res = -ERANGE; - } else if (!strcmp(name, "hfs.creator")) { - if (size == 4) - memcpy(&file->user_info.fdCreator, value, 4); - else - res = -ERANGE; - } else - res = -EOPNOTSUPP; - if (!res) { - hfs_bnode_write(fd.bnode, &entry, fd.entryoffset, - sizeof(struct hfsplus_cat_file)); - hfsplus_mark_inode_dirty(inode, HFSPLUS_I_CAT_DIRTY); - } -out: - hfs_find_exit(&fd); - return res; -} - -ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name, - void *value, size_t size) -{ - struct inode *inode = dentry->d_inode; - struct hfs_find_data fd; - hfsplus_cat_entry entry; - struct hfsplus_cat_file *file; - ssize_t res = 0; - - if (!S_ISREG(inode->i_mode) || HFSPLUS_IS_RSRC(inode)) - return -EOPNOTSUPP; - - if (size) { - res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &fd); - if (res) - return res; - res = hfsplus_find_cat(inode->i_sb, inode->i_ino, &fd); - if (res) - goto out; - hfs_bnode_read(fd.bnode, &entry, fd.entryoffset, - sizeof(struct hfsplus_cat_file)); - } - file = &entry.file; - - if (!strcmp(name, "hfs.type")) { - if (size >= 4) { - memcpy(value, &file->user_info.fdType, 4); - res = 4; - } else - res = size ? -ERANGE : 4; - } else if (!strcmp(name, "hfs.creator")) { - if (size >= 4) { - memcpy(value, &file->user_info.fdCreator, 4); - res = 4; - } else - res = size ? -ERANGE : 4; - } else - res = -EOPNOTSUPP; -out: - if (size) - hfs_find_exit(&fd); - return res; -} - -#define HFSPLUS_ATTRLIST_SIZE (sizeof("hfs.creator")+sizeof("hfs.type")) - -ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size) -{ - struct inode *inode = dentry->d_inode; - - if (!S_ISREG(inode->i_mode) || HFSPLUS_IS_RSRC(inode)) - return -EOPNOTSUPP; - - if (!buffer || !size) - return HFSPLUS_ATTRLIST_SIZE; - if (size < HFSPLUS_ATTRLIST_SIZE) - return -ERANGE; - strcpy(buffer, "hfs.type"); - strcpy(buffer + sizeof("hfs.type"), "hfs.creator"); - - return HFSPLUS_ATTRLIST_SIZE; -} diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index 796198d26553..974c26f96fae 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -20,6 +20,7 @@ static struct inode *hfsplus_alloc_inode(struct super_block *sb); static void hfsplus_destroy_inode(struct inode *inode); #include "hfsplus_fs.h" +#include "xattr.h" static int hfsplus_system_read_inode(struct inode *inode) { @@ -118,6 +119,7 @@ static int hfsplus_system_write_inode(struct inode *inode) case HFSPLUS_ATTR_CNID: fork = &vhdr->attr_file; tree = sbi->attr_tree; + break; default: return -EIO; } @@ -191,6 +193,12 @@ static int hfsplus_sync_fs(struct super_block *sb, int wait) error2 = filemap_write_and_wait(sbi->ext_tree->inode->i_mapping); if (!error) error = error2; + if (sbi->attr_tree) { + error2 = + filemap_write_and_wait(sbi->attr_tree->inode->i_mapping); + if (!error) + error = error2; + } error2 = filemap_write_and_wait(sbi->alloc_file->i_mapping); if (!error) error = error2; @@ -281,6 +289,7 @@ static void hfsplus_put_super(struct super_block *sb) hfsplus_sync_fs(sb, 1); } + hfs_btree_close(sbi->attr_tree); hfs_btree_close(sbi->cat_tree); hfs_btree_close(sbi->ext_tree); iput(sbi->alloc_file); @@ -477,12 +486,20 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) printk(KERN_ERR "hfs: failed to load catalog file\n"); goto out_close_ext_tree; } + if (vhdr->attr_file.total_blocks != 0) { + sbi->attr_tree = hfs_btree_open(sb, HFSPLUS_ATTR_CNID); + if (!sbi->attr_tree) { + printk(KERN_ERR "hfs: failed to load attributes file\n"); + goto out_close_cat_tree; + } + } + sb->s_xattr = hfsplus_xattr_handlers; inode = hfsplus_iget(sb, HFSPLUS_ALLOC_CNID); if (IS_ERR(inode)) { printk(KERN_ERR "hfs: failed to load allocation file\n"); err = PTR_ERR(inode); - goto out_close_cat_tree; + goto out_close_attr_tree; } sbi->alloc_file = inode; @@ -542,10 +559,27 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) } err = hfsplus_create_cat(sbi->hidden_dir->i_ino, root, &str, sbi->hidden_dir); - mutex_unlock(&sbi->vh_mutex); - if (err) + if (err) { + mutex_unlock(&sbi->vh_mutex); + goto out_put_hidden_dir; + } + + err = hfsplus_init_inode_security(sbi->hidden_dir, + root, &str); + if (err == -EOPNOTSUPP) + err = 0; /* Operation is not supported. */ + else if (err) { + /* + * Try to delete anyway without + * error analysis. + */ + hfsplus_delete_cat(sbi->hidden_dir->i_ino, + root, &str); + mutex_unlock(&sbi->vh_mutex); goto out_put_hidden_dir; + } + mutex_unlock(&sbi->vh_mutex); hfsplus_mark_inode_dirty(sbi->hidden_dir, HFSPLUS_I_CAT_DIRTY); } @@ -562,6 +596,8 @@ out_put_root: sb->s_root = NULL; out_put_alloc_file: iput(sbi->alloc_file); +out_close_attr_tree: + hfs_btree_close(sbi->attr_tree); out_close_cat_tree: hfs_btree_close(sbi->cat_tree); out_close_ext_tree: @@ -635,9 +671,20 @@ static int __init init_hfsplus_fs(void) hfsplus_init_once); if (!hfsplus_inode_cachep) return -ENOMEM; + err = hfsplus_create_attr_tree_cache(); + if (err) + goto destroy_inode_cache; err = register_filesystem(&hfsplus_fs_type); if (err) - kmem_cache_destroy(hfsplus_inode_cachep); + goto destroy_attr_tree_cache; + return 0; + +destroy_attr_tree_cache: + hfsplus_destroy_attr_tree_cache(); + +destroy_inode_cache: + kmem_cache_destroy(hfsplus_inode_cachep); + return err; } @@ -650,6 +697,7 @@ static void __exit exit_hfsplus_fs(void) * destroy cache. */ rcu_barrier(); + hfsplus_destroy_attr_tree_cache(); kmem_cache_destroy(hfsplus_inode_cachep); } diff --git a/fs/hfsplus/unicode.c b/fs/hfsplus/unicode.c index a32998f29f0b..2c2e47dcfdd8 100644 --- a/fs/hfsplus/unicode.c +++ b/fs/hfsplus/unicode.c @@ -295,7 +295,8 @@ static inline u16 *decompose_unichar(wchar_t uc, int *size) return hfsplus_decompose_table + (off / 4); } -int hfsplus_asc2uni(struct super_block *sb, struct hfsplus_unistr *ustr, +int hfsplus_asc2uni(struct super_block *sb, + struct hfsplus_unistr *ustr, int max_unistr_len, const char *astr, int len) { int size, dsize, decompose; @@ -303,7 +304,7 @@ int hfsplus_asc2uni(struct super_block *sb, struct hfsplus_unistr *ustr, wchar_t c; decompose = !test_bit(HFSPLUS_SB_NODECOMPOSE, &HFSPLUS_SB(sb)->flags); - while (outlen < HFSPLUS_MAX_STRLEN && len > 0) { + while (outlen < max_unistr_len && len > 0) { size = asc2unichar(sb, astr, len, &c); if (decompose) @@ -311,7 +312,7 @@ int hfsplus_asc2uni(struct super_block *sb, struct hfsplus_unistr *ustr, else dstr = NULL; if (dstr) { - if (outlen + dsize > HFSPLUS_MAX_STRLEN) + if (outlen + dsize > max_unistr_len) break; do { ustr->unicode[outlen++] = cpu_to_be16(*dstr++); diff --git a/fs/hfsplus/xattr.c b/fs/hfsplus/xattr.c new file mode 100644 index 000000000000..e8a4b0815c61 --- /dev/null +++ b/fs/hfsplus/xattr.c @@ -0,0 +1,709 @@ +/* + * linux/fs/hfsplus/xattr.c + * + * Vyacheslav Dubeyko <slava@dubeyko.com> + * + * Logic of processing extended attributes + */ + +#include "hfsplus_fs.h" +#include "xattr.h" + +const struct xattr_handler *hfsplus_xattr_handlers[] = { + &hfsplus_xattr_osx_handler, + &hfsplus_xattr_user_handler, + &hfsplus_xattr_trusted_handler, + &hfsplus_xattr_security_handler, + NULL +}; + +static int strcmp_xattr_finder_info(const char *name) +{ + if (name) { + return strncmp(name, HFSPLUS_XATTR_FINDER_INFO_NAME, + sizeof(HFSPLUS_XATTR_FINDER_INFO_NAME)); + } + return -1; +} + +static int strcmp_xattr_acl(const char *name) +{ + if (name) { + return strncmp(name, HFSPLUS_XATTR_ACL_NAME, + sizeof(HFSPLUS_XATTR_ACL_NAME)); + } + return -1; +} + +static inline int is_known_namespace(const char *name) +{ + if (strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN) && + strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) && + strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) && + strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN)) + return false; + + return true; +} + +static int can_set_xattr(struct inode *inode, const char *name, + const void *value, size_t value_len) +{ + if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) + return -EOPNOTSUPP; /* TODO: implement ACL support */ + + if (!strncmp(name, XATTR_MAC_OSX_PREFIX, XATTR_MAC_OSX_PREFIX_LEN)) { + /* + * This makes sure that we aren't trying to set an + * attribute in a different namespace by prefixing it + * with "osx." + */ + if (is_known_namespace(name + XATTR_MAC_OSX_PREFIX_LEN)) + return -EOPNOTSUPP; + + return 0; + } + + /* + * Don't allow setting an attribute in an unknown namespace. + */ + if (strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) && + strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) && + strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) + return -EOPNOTSUPP; + + return 0; +} + +int __hfsplus_setxattr(struct inode *inode, const char *name, + const void *value, size_t size, int flags) +{ + int err = 0; + struct hfs_find_data cat_fd; + hfsplus_cat_entry entry; + u16 cat_entry_flags, cat_entry_type; + u16 folder_finderinfo_len = sizeof(struct DInfo) + + sizeof(struct DXInfo); + u16 file_finderinfo_len = sizeof(struct FInfo) + + sizeof(struct FXInfo); + + if ((!S_ISREG(inode->i_mode) && + !S_ISDIR(inode->i_mode)) || + HFSPLUS_IS_RSRC(inode)) + return -EOPNOTSUPP; + + err = can_set_xattr(inode, name, value, size); + if (err) + return err; + + if (strncmp(name, XATTR_MAC_OSX_PREFIX, + XATTR_MAC_OSX_PREFIX_LEN) == 0) + name += XATTR_MAC_OSX_PREFIX_LEN; + + if (value == NULL) { + value = ""; + size = 0; + } + + err = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &cat_fd); + if (err) { + printk(KERN_ERR "hfs: can't init xattr find struct\n"); + return err; + } + + err = hfsplus_find_cat(inode->i_sb, inode->i_ino, &cat_fd); + if (err) { + printk(KERN_ERR "hfs: catalog searching failed\n"); + goto end_setxattr; + } + + if (!strcmp_xattr_finder_info(name)) { + if (flags & XATTR_CREATE) { + printk(KERN_ERR "hfs: xattr exists yet\n"); + err = -EOPNOTSUPP; + goto end_setxattr; + } + hfs_bnode_read(cat_fd.bnode, &entry, cat_fd.entryoffset, + sizeof(hfsplus_cat_entry)); + if (be16_to_cpu(entry.type) == HFSPLUS_FOLDER) { + if (size == folder_finderinfo_len) { + memcpy(&entry.folder.user_info, value, + folder_finderinfo_len); + hfs_bnode_write(cat_fd.bnode, &entry, + cat_fd.entryoffset, + sizeof(struct hfsplus_cat_folder)); + hfsplus_mark_inode_dirty(inode, + HFSPLUS_I_CAT_DIRTY); + } else { + err = -ERANGE; + goto end_setxattr; + } + } else if (be16_to_cpu(entry.type) == HFSPLUS_FILE) { + if (size == file_finderinfo_len) { + memcpy(&entry.file.user_info, value, + file_finderinfo_len); + hfs_bnode_write(cat_fd.bnode, &entry, + cat_fd.entryoffset, + sizeof(struct hfsplus_cat_file)); + hfsplus_mark_inode_dirty(inode, + HFSPLUS_I_CAT_DIRTY); + } else { + err = -ERANGE; + goto end_setxattr; + } + } else { + err = -EOPNOTSUPP; + goto end_setxattr; + } + goto end_setxattr; + } + + if (!HFSPLUS_SB(inode->i_sb)->attr_tree) { + err = -EOPNOTSUPP; + goto end_setxattr; + } + + if (hfsplus_attr_exists(inode, name)) { + if (flags & XATTR_CREATE) { + printk(KERN_ERR "hfs: xattr exists yet\n"); + err = -EOPNOTSUPP; + goto end_setxattr; + } + err = hfsplus_delete_attr(inode, name); + if (err) + goto end_setxattr; + err = hfsplus_create_attr(inode, name, value, size); + if (err) + goto end_setxattr; + } else { + if (flags & XATTR_REPLACE) { + printk(KERN_ERR "hfs: cannot replace xattr\n"); + err = -EOPNOTSUPP; + goto end_setxattr; + } + err = hfsplus_create_attr(inode, name, value, size); + if (err) + goto end_setxattr; + } + + cat_entry_type = hfs_bnode_read_u16(cat_fd.bnode, cat_fd.entryoffset); + if (cat_entry_type == HFSPLUS_FOLDER) { + cat_entry_flags = hfs_bnode_read_u16(cat_fd.bnode, + cat_fd.entryoffset + + offsetof(struct hfsplus_cat_folder, flags)); + cat_entry_flags |= HFSPLUS_XATTR_EXISTS; + if (!strcmp_xattr_acl(name)) + cat_entry_flags |= HFSPLUS_ACL_EXISTS; + hfs_bnode_write_u16(cat_fd.bnode, cat_fd.entryoffset + + offsetof(struct hfsplus_cat_folder, flags), + cat_entry_flags); + hfsplus_mark_inode_dirty(inode, HFSPLUS_I_CAT_DIRTY); + } else if (cat_entry_type == HFSPLUS_FILE) { + cat_entry_flags = hfs_bnode_read_u16(cat_fd.bnode, + cat_fd.entryoffset + + offsetof(struct hfsplus_cat_file, flags)); + cat_entry_flags |= HFSPLUS_XATTR_EXISTS; + if (!strcmp_xattr_acl(name)) + cat_entry_flags |= HFSPLUS_ACL_EXISTS; + hfs_bnode_write_u16(cat_fd.bnode, cat_fd.entryoffset + + offsetof(struct hfsplus_cat_file, flags), + cat_entry_flags); + hfsplus_mark_inode_dirty(inode, HFSPLUS_I_CAT_DIRTY); + } else { + printk(KERN_ERR "hfs: invalid catalog entry type\n"); + err = -EIO; + goto end_setxattr; + } + +end_setxattr: + hfs_find_exit(&cat_fd); + return err; +} + +static inline int is_osx_xattr(const char *xattr_name) +{ + return !is_known_namespace(xattr_name); +} + +static int name_len(const char *xattr_name, int xattr_name_len) +{ + int len = xattr_name_len + 1; + + if (is_osx_xattr(xattr_name)) + len += XATTR_MAC_OSX_PREFIX_LEN; + + return len; +} + +static int copy_name(char *buffer, const char *xattr_name, int name_len) +{ + int len = name_len; + int offset = 0; + + if (is_osx_xattr(xattr_name)) { + strncpy(buffer, XATTR_MAC_OSX_PREFIX, XATTR_MAC_OSX_PREFIX_LEN); + offset += XATTR_MAC_OSX_PREFIX_LEN; + len += XATTR_MAC_OSX_PREFIX_LEN; + } + + strncpy(buffer + offset, xattr_name, name_len); + memset(buffer + offset + name_len, 0, 1); + len += 1; + + return len; +} + +static ssize_t hfsplus_getxattr_finder_info(struct dentry *dentry, + void *value, size_t size) +{ + ssize_t res = 0; + struct inode *inode = dentry->d_inode; + struct hfs_find_data fd; + u16 entry_type; + u16 folder_rec_len = sizeof(struct DInfo) + sizeof(struct DXInfo); + u16 file_rec_len = sizeof(struct FInfo) + sizeof(struct FXInfo); + u16 record_len = max(folder_rec_len, file_rec_len); + u8 folder_finder_info[sizeof(struct DInfo) + sizeof(struct DXInfo)]; + u8 file_finder_info[sizeof(struct FInfo) + sizeof(struct FXInfo)]; + + if (size >= record_len) { + res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &fd); + if (res) { + printk(KERN_ERR "hfs: can't init xattr find struct\n"); + return res; + } + res = hfsplus_find_cat(inode->i_sb, inode->i_ino, &fd); + if (res) + goto end_getxattr_finder_info; + entry_type = hfs_bnode_read_u16(fd.bnode, fd.entryoffset); + + if (entry_type == HFSPLUS_FOLDER) { + hfs_bnode_read(fd.bnode, folder_finder_info, + fd.entryoffset + + offsetof(struct hfsplus_cat_folder, user_info), + folder_rec_len); + memcpy(value, folder_finder_info, folder_rec_len); + res = folder_rec_len; + } else if (entry_type == HFSPLUS_FILE) { + hfs_bnode_read(fd.bnode, file_finder_info, + fd.entryoffset + + offsetof(struct hfsplus_cat_file, user_info), + file_rec_len); + memcpy(value, file_finder_info, file_rec_len); + res = file_rec_len; + } else { + res = -EOPNOTSUPP; + goto end_getxattr_finder_info; + } + } else + res = size ? -ERANGE : record_len; + +end_getxattr_finder_info: + if (size >= record_len) + hfs_find_exit(&fd); + return res; +} + +ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name, + void *value, size_t size) +{ + struct inode *inode = dentry->d_inode; + struct hfs_find_data fd; + hfsplus_attr_entry *entry; + __be32 xattr_record_type; + u32 record_type; + u16 record_length = 0; + ssize_t res = 0; + + if ((!S_ISREG(inode->i_mode) && + !S_ISDIR(inode->i_mode)) || + HFSPLUS_IS_RSRC(inode)) + return -EOPNOTSUPP; + + if (strncmp(name, XATTR_MAC_OSX_PREFIX, + XATTR_MAC_OSX_PREFIX_LEN) == 0) { + /* skip "osx." prefix */ + name += XATTR_MAC_OSX_PREFIX_LEN; + /* + * Don't allow retrieving properly prefixed attributes + * by prepending them with "osx." + */ + if (is_known_namespace(name)) + return -EOPNOTSUPP; + } + + if (!strcmp_xattr_finder_info(name)) + return hfsplus_getxattr_finder_info(dentry, value, size); + + if (!HFSPLUS_SB(inode->i_sb)->attr_tree) + return -EOPNOTSUPP; + + entry = hfsplus_alloc_attr_entry(); + if (!entry) { + printk(KERN_ERR "hfs: can't allocate xattr entry\n"); + return -ENOMEM; + } + + res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->attr_tree, &fd); + if (res) { + printk(KERN_ERR "hfs: can't init xattr find struct\n"); + goto failed_getxattr_init; + } + + res = hfsplus_find_attr(inode->i_sb, inode->i_ino, name, &fd); + if (res) { + if (res == -ENOENT) + res = -ENODATA; + else + printk(KERN_ERR "hfs: xattr searching failed\n"); + goto out; + } + + hfs_bnode_read(fd.bnode, &xattr_record_type, + fd.entryoffset, sizeof(xattr_record_type)); + record_type = be32_to_cpu(xattr_record_type); + if (record_type == HFSPLUS_ATTR_INLINE_DATA) { + record_length = hfs_bnode_read_u16(fd.bnode, + fd.entryoffset + + offsetof(struct hfsplus_attr_inline_data, + length)); + if (record_length > HFSPLUS_MAX_INLINE_DATA_SIZE) { + printk(KERN_ERR "hfs: invalid xattr record size\n"); + res = -EIO; + goto out; + } + } else if (record_type == HFSPLUS_ATTR_FORK_DATA || + record_type == HFSPLUS_ATTR_EXTENTS) { + printk(KERN_ERR "hfs: only inline data xattr are supported\n"); + res = -EOPNOTSUPP; + goto out; + } else { + printk(KERN_ERR "hfs: invalid xattr record\n"); + res = -EIO; + goto out; + } + + if (size) { + hfs_bnode_read(fd.bnode, entry, fd.entryoffset, + offsetof(struct hfsplus_attr_inline_data, + raw_bytes) + record_length); + } + + if (size >= record_length) { + memcpy(value, entry->inline_data.raw_bytes, record_length); + res = record_length; + } else + res = size ? -ERANGE : record_length; + +out: + hfs_find_exit(&fd); + +failed_getxattr_init: + hfsplus_destroy_attr_entry(entry); + return res; +} + +static inline int can_list(const char *xattr_name) +{ + if (!xattr_name) + return 0; + + return strncmp(xattr_name, XATTR_TRUSTED_PREFIX, + XATTR_TRUSTED_PREFIX_LEN) || + capable(CAP_SYS_ADMIN); +} + +static ssize_t hfsplus_listxattr_finder_info(struct dentry *dentry, + char *buffer, size_t size) +{ + ssize_t res = 0; + struct inode *inode = dentry->d_inode; + struct hfs_find_data fd; + u16 entry_type; + u8 folder_finder_info[sizeof(struct DInfo) + sizeof(struct DXInfo)]; + u8 file_finder_info[sizeof(struct FInfo) + sizeof(struct FXInfo)]; + unsigned long len, found_bit; + int xattr_name_len, symbols_count; + + res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &fd); + if (res) { + printk(KERN_ERR "hfs: can't init xattr find struct\n"); + return res; + } + + res = hfsplus_find_cat(inode->i_sb, inode->i_ino, &fd); + if (res) + goto end_listxattr_finder_info; + + entry_type = hfs_bnode_read_u16(fd.bnode, fd.entryoffset); + if (entry_type == HFSPLUS_FOLDER) { + len = sizeof(struct DInfo) + sizeof(struct DXInfo); + hfs_bnode_read(fd.bnode, folder_finder_info, + fd.entryoffset + + offsetof(struct hfsplus_cat_folder, user_info), + len); + found_bit = find_first_bit((void *)folder_finder_info, len*8); + } else if (entry_type == HFSPLUS_FILE) { + len = sizeof(struct FInfo) + sizeof(struct FXInfo); + hfs_bnode_read(fd.bnode, file_finder_info, + fd.entryoffset + + offsetof(struct hfsplus_cat_file, user_info), + len); + found_bit = find_first_bit((void *)file_finder_info, len*8); + } else { + res = -EOPNOTSUPP; + goto end_listxattr_finder_info; + } + + if (found_bit >= (len*8)) + res = 0; + else { + symbols_count = sizeof(HFSPLUS_XATTR_FINDER_INFO_NAME) - 1; + xattr_name_len = + name_len(HFSPLUS_XATTR_FINDER_INFO_NAME, symbols_count); + if (!buffer || !size) { + if (can_list(HFSPLUS_XATTR_FINDER_INFO_NAME)) + res = xattr_name_len; + } else if (can_list(HFSPLUS_XATTR_FINDER_INFO_NAME)) { + if (size < xattr_name_len) + res = -ERANGE; + else { + res = copy_name(buffer, + HFSPLUS_XATTR_FINDER_INFO_NAME, + symbols_count); + } + } + } + +end_listxattr_finder_info: + hfs_find_exit(&fd); + + return res; +} + +ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size) +{ + ssize_t err; + ssize_t res = 0; + struct inode *inode = dentry->d_inode; + struct hfs_find_data fd; + u16 key_len = 0; + struct hfsplus_attr_key attr_key; + char strbuf[HFSPLUS_ATTR_MAX_STRLEN + + XATTR_MAC_OSX_PREFIX_LEN + 1] = {0}; + int xattr_name_len; + + if ((!S_ISREG(inode->i_mode) && + !S_ISDIR(inode->i_mode)) || + HFSPLUS_IS_RSRC(inode)) + return -EOPNOTSUPP; + + res = hfsplus_listxattr_finder_info(dentry, buffer, size); + if (res < 0) + return res; + else if (!HFSPLUS_SB(inode->i_sb)->attr_tree) + return (res == 0) ? -EOPNOTSUPP : res; + + err = hfs_find_init(HFSPLUS_SB(inode->i_sb)->attr_tree, &fd); + if (err) { + printk(KERN_ERR "hfs: can't init xattr find struct\n"); + return err; + } + + err = hfsplus_find_attr(inode->i_sb, inode->i_ino, NULL, &fd); + if (err) { + if (err == -ENOENT) { + if (res == 0) + res = -ENODATA; + goto end_listxattr; + } else { + res = err; + goto end_listxattr; + } + } + + for (;;) { + key_len = hfs_bnode_read_u16(fd.bnode, fd.keyoffset); + if (key_len == 0 || key_len > fd.tree->max_key_len) { + printk(KERN_ERR "hfs: invalid xattr key length: %d\n", + key_len); + res = -EIO; + goto end_listxattr; + } + + hfs_bnode_read(fd.bnode, &attr_key, + fd.keyoffset, key_len + sizeof(key_len)); + + if (be32_to_cpu(attr_key.cnid) != inode->i_ino) + goto end_listxattr; + + xattr_name_len = HFSPLUS_ATTR_MAX_STRLEN; + if (hfsplus_uni2asc(inode->i_sb, + (const struct hfsplus_unistr *)&fd.key->attr.key_name, + strbuf, &xattr_name_len)) { + printk(KERN_ERR "hfs: unicode conversion failed\n"); + res = -EIO; + goto end_listxattr; + } + + if (!buffer || !size) { + if (can_list(strbuf)) + res += name_len(strbuf, xattr_name_len); + } else if (can_list(strbuf)) { + if (size < (res + name_len(strbuf, xattr_name_len))) { + res = -ERANGE; + goto end_listxattr; + } else + res += copy_name(buffer + res, + strbuf, xattr_name_len); + } + + if (hfs_brec_goto(&fd, 1)) + goto end_listxattr; + } + +end_listxattr: + hfs_find_exit(&fd); + return res; +} + +int hfsplus_removexattr(struct dentry *dentry, const char *name) +{ + int err = 0; + struct inode *inode = dentry->d_inode; + struct hfs_find_data cat_fd; + u16 flags; + u16 cat_entry_type; + int is_xattr_acl_deleted = 0; + int is_all_xattrs_deleted = 0; + + if ((!S_ISREG(inode->i_mode) && + !S_ISDIR(inode->i_mode)) || + HFSPLUS_IS_RSRC(inode)) + return -EOPNOTSUPP; + + if (!HFSPLUS_SB(inode->i_sb)->attr_tree) + return -EOPNOTSUPP; + + err = can_set_xattr(inode, name, NULL, 0); + if (err) + return err; + + if (strncmp(name, XATTR_MAC_OSX_PREFIX, + XATTR_MAC_OSX_PREFIX_LEN) == 0) + name += XATTR_MAC_OSX_PREFIX_LEN; + + if (!strcmp_xattr_finder_info(name)) + return -EOPNOTSUPP; + + err = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &cat_fd); + if (err) { + printk(KERN_ERR "hfs: can't init xattr find struct\n"); + return err; + } + + err = hfsplus_find_cat(inode->i_sb, inode->i_ino, &cat_fd); + if (err) { + printk(KERN_ERR "hfs: catalog searching failed\n"); + goto end_removexattr; + } + + err = hfsplus_delete_attr(inode, name); + if (err) + goto end_removexattr; + + is_xattr_acl_deleted = !strcmp_xattr_acl(name); + is_all_xattrs_deleted = !hfsplus_attr_exists(inode, NULL); + + if (!is_xattr_acl_deleted && !is_all_xattrs_deleted) + goto end_removexattr; + + cat_entry_type = hfs_bnode_read_u16(cat_fd.bnode, cat_fd.entryoffset); + + if (cat_entry_type == HFSPLUS_FOLDER) { + flags = hfs_bnode_read_u16(cat_fd.bnode, cat_fd.entryoffset + + offsetof(struct hfsplus_cat_folder, flags)); + if (is_xattr_acl_deleted) + flags &= ~HFSPLUS_ACL_EXISTS; + if (is_all_xattrs_deleted) + flags &= ~HFSPLUS_XATTR_EXISTS; + hfs_bnode_write_u16(cat_fd.bnode, cat_fd.entryoffset + + offsetof(struct hfsplus_cat_folder, flags), + flags); + hfsplus_mark_inode_dirty(inode, HFSPLUS_I_CAT_DIRTY); + } else if (cat_entry_type == HFSPLUS_FILE) { + flags = hfs_bnode_read_u16(cat_fd.bnode, cat_fd.entryoffset + + offsetof(struct hfsplus_cat_file, flags)); + if (is_xattr_acl_deleted) + flags &= ~HFSPLUS_ACL_EXISTS; + if (is_all_xattrs_deleted) + flags &= ~HFSPLUS_XATTR_EXISTS; + hfs_bnode_write_u16(cat_fd.bnode, cat_fd.entryoffset + + offsetof(struct hfsplus_cat_file, flags), + flags); + hfsplus_mark_inode_dirty(inode, HFSPLUS_I_CAT_DIRTY); + } else { + printk(KERN_ERR "hfs: invalid catalog entry type\n"); + err = -EIO; + goto end_removexattr; + } + +end_removexattr: + hfs_find_exit(&cat_fd); + return err; +} + +static int hfsplus_osx_getxattr(struct dentry *dentry, const char *name, + void *buffer, size_t size, int type) +{ + char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + + XATTR_MAC_OSX_PREFIX_LEN + 1] = {0}; + size_t len = strlen(name); + + if (!strcmp(name, "")) + return -EINVAL; + + if (len > HFSPLUS_ATTR_MAX_STRLEN) + return -EOPNOTSUPP; + + strcpy(xattr_name, XATTR_MAC_OSX_PREFIX); + strcpy(xattr_name + XATTR_MAC_OSX_PREFIX_LEN, name); + + return hfsplus_getxattr(dentry, xattr_name, buffer, size); +} + +static int hfsplus_osx_setxattr(struct dentry *dentry, const char *name, + const void *buffer, size_t size, int flags, int type) +{ + char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + + XATTR_MAC_OSX_PREFIX_LEN + 1] = {0}; + size_t len = strlen(name); + + if (!strcmp(name, "")) + return -EINVAL; + + if (len > HFSPLUS_ATTR_MAX_STRLEN) + return -EOPNOTSUPP; + + strcpy(xattr_name, XATTR_MAC_OSX_PREFIX); + strcpy(xattr_name + XATTR_MAC_OSX_PREFIX_LEN, name); + + return hfsplus_setxattr(dentry, xattr_name, buffer, size, flags); +} + +static size_t hfsplus_osx_listxattr(struct dentry *dentry, char *list, + size_t list_size, const char *name, size_t name_len, int type) +{ + /* + * This method is not used. + * It is used hfsplus_listxattr() instead of generic_listxattr(). + */ + return -EOPNOTSUPP; +} + +const struct xattr_handler hfsplus_xattr_osx_handler = { + .prefix = XATTR_MAC_OSX_PREFIX, + .list = hfsplus_osx_listxattr, + .get = hfsplus_osx_getxattr, + .set = hfsplus_osx_setxattr, +}; diff --git a/fs/hfsplus/xattr.h b/fs/hfsplus/xattr.h new file mode 100644 index 000000000000..847b695b984d --- /dev/null +++ b/fs/hfsplus/xattr.h @@ -0,0 +1,60 @@ +/* + * linux/fs/hfsplus/xattr.h + * + * Vyacheslav Dubeyko <slava@dubeyko.com> + * + * Logic of processing extended attributes + */ + +#ifndef _LINUX_HFSPLUS_XATTR_H +#define _LINUX_HFSPLUS_XATTR_H + +#include <linux/xattr.h> + +extern const struct xattr_handler hfsplus_xattr_osx_handler; +extern const struct xattr_handler hfsplus_xattr_user_handler; +extern const struct xattr_handler hfsplus_xattr_trusted_handler; +/*extern const struct xattr_handler hfsplus_xattr_acl_access_handler;*/ +/*extern const struct xattr_handler hfsplus_xattr_acl_default_handler;*/ +extern const struct xattr_handler hfsplus_xattr_security_handler; + +extern const struct xattr_handler *hfsplus_xattr_handlers[]; + +int __hfsplus_setxattr(struct inode *inode, const char *name, + const void *value, size_t size, int flags); + +static inline int hfsplus_setxattr(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) +{ + return __hfsplus_setxattr(dentry->d_inode, name, value, size, flags); +} + +ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name, + void *value, size_t size); + +ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size); + +int hfsplus_removexattr(struct dentry *dentry, const char *name); + +int hfsplus_init_security(struct inode *inode, struct inode *dir, + const struct qstr *qstr); + +static inline int hfsplus_init_acl(struct inode *inode, struct inode *dir) +{ + /*TODO: implement*/ + return 0; +} + +static inline int hfsplus_init_inode_security(struct inode *inode, + struct inode *dir, + const struct qstr *qstr) +{ + int err; + + err = hfsplus_init_acl(inode, dir); + if (!err) + err = hfsplus_init_security(inode, dir, qstr); + return err; +} + +#endif diff --git a/fs/hfsplus/xattr_security.c b/fs/hfsplus/xattr_security.c new file mode 100644 index 000000000000..83b842f113c5 --- /dev/null +++ b/fs/hfsplus/xattr_security.c @@ -0,0 +1,104 @@ +/* + * linux/fs/hfsplus/xattr_trusted.c + * + * Vyacheslav Dubeyko <slava@dubeyko.com> + * + * Handler for storing security labels as extended attributes. + */ + +#include <linux/security.h> +#include "hfsplus_fs.h" +#include "xattr.h" + +static int hfsplus_security_getxattr(struct dentry *dentry, const char *name, + void *buffer, size_t size, int type) +{ + char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0}; + size_t len = strlen(name); + + if (!strcmp(name, "")) + return -EINVAL; + + if (len + XATTR_SECURITY_PREFIX_LEN > HFSPLUS_ATTR_MAX_STRLEN) + return -EOPNOTSUPP; + + strcpy(xattr_name, XATTR_SECURITY_PREFIX); + strcpy(xattr_name + XATTR_SECURITY_PREFIX_LEN, name); + + return hfsplus_getxattr(dentry, xattr_name, buffer, size); +} + +static int hfsplus_security_setxattr(struct dentry *dentry, const char *name, + const void *buffer, size_t size, int flags, int type) +{ + char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0}; + size_t len = strlen(name); + + if (!strcmp(name, "")) + return -EINVAL; + + if (len + XATTR_SECURITY_PREFIX_LEN > HFSPLUS_ATTR_MAX_STRLEN) + return -EOPNOTSUPP; + + strcpy(xattr_name, XATTR_SECURITY_PREFIX); + strcpy(xattr_name + XATTR_SECURITY_PREFIX_LEN, name); + + return hfsplus_setxattr(dentry, xattr_name, buffer, size, flags); +} + +static size_t hfsplus_security_listxattr(struct dentry *dentry, char *list, + size_t list_size, const char *name, size_t name_len, int type) +{ + /* + * This method is not used. + * It is used hfsplus_listxattr() instead of generic_listxattr(). + */ + return -EOPNOTSUPP; +} + +static int hfsplus_initxattrs(struct inode *inode, + const struct xattr *xattr_array, + void *fs_info) +{ + const struct xattr *xattr; + char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0}; + size_t xattr_name_len; + int err = 0; + + for (xattr = xattr_array; xattr->name != NULL; xattr++) { + xattr_name_len = strlen(xattr->name); + + if (xattr_name_len == 0) + continue; + + if (xattr_name_len + XATTR_SECURITY_PREFIX_LEN > + HFSPLUS_ATTR_MAX_STRLEN) + return -EOPNOTSUPP; + + strcpy(xattr_name, XATTR_SECURITY_PREFIX); + strcpy(xattr_name + + XATTR_SECURITY_PREFIX_LEN, xattr->name); + memset(xattr_name + + XATTR_SECURITY_PREFIX_LEN + xattr_name_len, 0, 1); + + err = __hfsplus_setxattr(inode, xattr_name, + xattr->value, xattr->value_len, 0); + if (err) + break; + } + return err; +} + +int hfsplus_init_security(struct inode *inode, struct inode *dir, + const struct qstr *qstr) +{ + return security_inode_init_security(inode, dir, qstr, + &hfsplus_initxattrs, NULL); +} + +const struct xattr_handler hfsplus_xattr_security_handler = { + .prefix = XATTR_SECURITY_PREFIX, + .list = hfsplus_security_listxattr, + .get = hfsplus_security_getxattr, + .set = hfsplus_security_setxattr, +}; diff --git a/fs/hfsplus/xattr_trusted.c b/fs/hfsplus/xattr_trusted.c new file mode 100644 index 000000000000..426cee277542 --- /dev/null +++ b/fs/hfsplus/xattr_trusted.c @@ -0,0 +1,63 @@ +/* + * linux/fs/hfsplus/xattr_trusted.c + * + * Vyacheslav Dubeyko <slava@dubeyko.com> + * + * Handler for trusted extended attributes. + */ + +#include "hfsplus_fs.h" +#include "xattr.h" + +static int hfsplus_trusted_getxattr(struct dentry *dentry, const char *name, + void *buffer, size_t size, int type) +{ + char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0}; + size_t len = strlen(name); + + if (!strcmp(name, "")) + return -EINVAL; + + if (len + XATTR_TRUSTED_PREFIX_LEN > HFSPLUS_ATTR_MAX_STRLEN) + return -EOPNOTSUPP; + + strcpy(xattr_name, XATTR_TRUSTED_PREFIX); + strcpy(xattr_name + XATTR_TRUSTED_PREFIX_LEN, name); + + return hfsplus_getxattr(dentry, xattr_name, buffer, size); +} + +static int hfsplus_trusted_setxattr(struct dentry *dentry, const char *name, + const void *buffer, size_t size, int flags, int type) +{ + char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0}; + size_t len = strlen(name); + + if (!strcmp(name, "")) + return -EINVAL; + + if (len + XATTR_TRUSTED_PREFIX_LEN > HFSPLUS_ATTR_MAX_STRLEN) + return -EOPNOTSUPP; + + strcpy(xattr_name, XATTR_TRUSTED_PREFIX); + strcpy(xattr_name + XATTR_TRUSTED_PREFIX_LEN, name); + + return hfsplus_setxattr(dentry, xattr_name, buffer, size, flags); +} + +static size_t hfsplus_trusted_listxattr(struct dentry *dentry, char *list, + size_t list_size, const char *name, size_t name_len, int type) +{ + /* + * This method is not used. + * It is used hfsplus_listxattr() instead of generic_listxattr(). + */ + return -EOPNOTSUPP; +} + +const struct xattr_handler hfsplus_xattr_trusted_handler = { + .prefix = XATTR_TRUSTED_PREFIX, + .list = hfsplus_trusted_listxattr, + .get = hfsplus_trusted_getxattr, + .set = hfsplus_trusted_setxattr, +}; diff --git a/fs/hfsplus/xattr_user.c b/fs/hfsplus/xattr_user.c new file mode 100644 index 000000000000..e34016561ae0 --- /dev/null +++ b/fs/hfsplus/xattr_user.c @@ -0,0 +1,63 @@ +/* + * linux/fs/hfsplus/xattr_user.c + * + * Vyacheslav Dubeyko <slava@dubeyko.com> + * + * Handler for user extended attributes. + */ + +#include "hfsplus_fs.h" +#include "xattr.h" + +static int hfsplus_user_getxattr(struct dentry *dentry, const char *name, + void *buffer, size_t size, int type) +{ + char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0}; + size_t len = strlen(name); + + if (!strcmp(name, "")) + return -EINVAL; + + if (len + XATTR_USER_PREFIX_LEN > HFSPLUS_ATTR_MAX_STRLEN) + return -EOPNOTSUPP; + + strcpy(xattr_name, XATTR_USER_PREFIX); + strcpy(xattr_name + XATTR_USER_PREFIX_LEN, name); + + return hfsplus_getxattr(dentry, xattr_name, buffer, size); +} + +static int hfsplus_user_setxattr(struct dentry *dentry, const char *name, + const void *buffer, size_t size, int flags, int type) +{ + char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0}; + size_t len = strlen(name); + + if (!strcmp(name, "")) + return -EINVAL; + + if (len + XATTR_USER_PREFIX_LEN > HFSPLUS_ATTR_MAX_STRLEN) + return -EOPNOTSUPP; + + strcpy(xattr_name, XATTR_USER_PREFIX); + strcpy(xattr_name + XATTR_USER_PREFIX_LEN, name); + + return hfsplus_setxattr(dentry, xattr_name, buffer, size, flags); +} + +static size_t hfsplus_user_listxattr(struct dentry *dentry, char *list, + size_t list_size, const char *name, size_t name_len, int type) +{ + /* + * This method is not used. + * It is used hfsplus_listxattr() instead of generic_listxattr(). + */ + return -EOPNOTSUPP; +} + +const struct xattr_handler hfsplus_xattr_user_handler = { + .prefix = XATTR_USER_PREFIX, + .list = hfsplus_user_listxattr, + .get = hfsplus_user_getxattr, + .set = hfsplus_user_setxattr, +}; diff --git a/fs/inode.c b/fs/inode.c index 14084b72b259..83a601c2ad55 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -798,11 +798,10 @@ static struct inode *find_inode(struct super_block *sb, int (*test)(struct inode *, void *), void *data) { - struct hlist_node *node; struct inode *inode = NULL; repeat: - hlist_for_each_entry(inode, node, head, i_hash) { + hlist_for_each_entry(inode, head, i_hash) { spin_lock(&inode->i_lock); if (inode->i_sb != sb) { spin_unlock(&inode->i_lock); @@ -830,11 +829,10 @@ repeat: static struct inode *find_inode_fast(struct super_block *sb, struct hlist_head *head, unsigned long ino) { - struct hlist_node *node; struct inode *inode = NULL; repeat: - hlist_for_each_entry(inode, node, head, i_hash) { + hlist_for_each_entry(inode, head, i_hash) { spin_lock(&inode->i_lock); if (inode->i_ino != ino) { spin_unlock(&inode->i_lock); @@ -1132,11 +1130,10 @@ EXPORT_SYMBOL(iget_locked); static int test_inode_iunique(struct super_block *sb, unsigned long ino) { struct hlist_head *b = inode_hashtable + hash(sb, ino); - struct hlist_node *node; struct inode *inode; spin_lock(&inode_hash_lock); - hlist_for_each_entry(inode, node, b, i_hash) { + hlist_for_each_entry(inode, b, i_hash) { if (inode->i_ino == ino && inode->i_sb == sb) { spin_unlock(&inode_hash_lock); return 0; @@ -1291,10 +1288,9 @@ int insert_inode_locked(struct inode *inode) struct hlist_head *head = inode_hashtable + hash(sb, ino); while (1) { - struct hlist_node *node; struct inode *old = NULL; spin_lock(&inode_hash_lock); - hlist_for_each_entry(old, node, head, i_hash) { + hlist_for_each_entry(old, head, i_hash) { if (old->i_ino != ino) continue; if (old->i_sb != sb) @@ -1306,7 +1302,7 @@ int insert_inode_locked(struct inode *inode) } break; } - if (likely(!node)) { + if (likely(!old)) { spin_lock(&inode->i_lock); inode->i_state |= I_NEW; hlist_add_head(&inode->i_hash, head); @@ -1334,11 +1330,10 @@ int insert_inode_locked4(struct inode *inode, unsigned long hashval, struct hlist_head *head = inode_hashtable + hash(sb, hashval); while (1) { - struct hlist_node *node; struct inode *old = NULL; spin_lock(&inode_hash_lock); - hlist_for_each_entry(old, node, head, i_hash) { + hlist_for_each_entry(old, head, i_hash) { if (old->i_sb != sb) continue; if (!test(old, data)) @@ -1350,7 +1345,7 @@ int insert_inode_locked4(struct inode *inode, unsigned long hashval, } break; } - if (likely(!node)) { + if (likely(!old)) { spin_lock(&inode->i_lock); inode->i_state |= I_NEW; hlist_add_head(&inode->i_hash, head); diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index b7dc47ba675e..1781f06aa1c1 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -23,6 +23,7 @@ #include <linux/pagemap.h> #include <linux/quotaops.h> #include <linux/writeback.h> +#include <linux/aio.h> #include "jfs_incore.h" #include "jfs_inode.h" #include "jfs_filsys.h" diff --git a/fs/lockd/host.c b/fs/lockd/host.c index 0e17090c310f..abdd75d44dd4 100644 --- a/fs/lockd/host.c +++ b/fs/lockd/host.c @@ -32,15 +32,15 @@ static struct hlist_head nlm_server_hosts[NLM_HOST_NRHASH]; static struct hlist_head nlm_client_hosts[NLM_HOST_NRHASH]; -#define for_each_host(host, pos, chain, table) \ +#define for_each_host(host, chain, table) \ for ((chain) = (table); \ (chain) < (table) + NLM_HOST_NRHASH; ++(chain)) \ - hlist_for_each_entry((host), (pos), (chain), h_hash) + hlist_for_each_entry((host), (chain), h_hash) -#define for_each_host_safe(host, pos, next, chain, table) \ +#define for_each_host_safe(host, next, chain, table) \ for ((chain) = (table); \ (chain) < (table) + NLM_HOST_NRHASH; ++(chain)) \ - hlist_for_each_entry_safe((host), (pos), (next), \ + hlist_for_each_entry_safe((host), (next), \ (chain), h_hash) static unsigned long nrhosts; @@ -225,7 +225,6 @@ struct nlm_host *nlmclnt_lookup_host(const struct sockaddr *sap, .net = net, }; struct hlist_head *chain; - struct hlist_node *pos; struct nlm_host *host; struct nsm_handle *nsm = NULL; struct lockd_net *ln = net_generic(net, lockd_net_id); @@ -237,7 +236,7 @@ struct nlm_host *nlmclnt_lookup_host(const struct sockaddr *sap, mutex_lock(&nlm_host_mutex); chain = &nlm_client_hosts[nlm_hash_address(sap)]; - hlist_for_each_entry(host, pos, chain, h_hash) { + hlist_for_each_entry(host, chain, h_hash) { if (host->net != net) continue; if (!rpc_cmp_addr(nlm_addr(host), sap)) @@ -322,7 +321,6 @@ struct nlm_host *nlmsvc_lookup_host(const struct svc_rqst *rqstp, const size_t hostname_len) { struct hlist_head *chain; - struct hlist_node *pos; struct nlm_host *host = NULL; struct nsm_handle *nsm = NULL; struct sockaddr *src_sap = svc_daddr(rqstp); @@ -350,7 +348,7 @@ struct nlm_host *nlmsvc_lookup_host(const struct svc_rqst *rqstp, nlm_gc_hosts(net); chain = &nlm_server_hosts[nlm_hash_address(ni.sap)]; - hlist_for_each_entry(host, pos, chain, h_hash) { + hlist_for_each_entry(host, chain, h_hash) { if (host->net != net) continue; if (!rpc_cmp_addr(nlm_addr(host), ni.sap)) @@ -515,10 +513,9 @@ static struct nlm_host *next_host_state(struct hlist_head *cache, { struct nlm_host *host; struct hlist_head *chain; - struct hlist_node *pos; mutex_lock(&nlm_host_mutex); - for_each_host(host, pos, chain, cache) { + for_each_host(host, chain, cache) { if (host->h_nsmhandle == nsm && host->h_nsmstate != info->state) { host->h_nsmstate = info->state; @@ -570,7 +567,6 @@ void nlm_host_rebooted(const struct nlm_reboot *info) static void nlm_complain_hosts(struct net *net) { struct hlist_head *chain; - struct hlist_node *pos; struct nlm_host *host; if (net) { @@ -587,7 +583,7 @@ static void nlm_complain_hosts(struct net *net) dprintk("lockd: %lu hosts left:\n", nrhosts); } - for_each_host(host, pos, chain, nlm_server_hosts) { + for_each_host(host, chain, nlm_server_hosts) { if (net && host->net != net) continue; dprintk(" %s (cnt %d use %d exp %ld net %p)\n", @@ -600,14 +596,13 @@ void nlm_shutdown_hosts_net(struct net *net) { struct hlist_head *chain; - struct hlist_node *pos; struct nlm_host *host; mutex_lock(&nlm_host_mutex); /* First, make all hosts eligible for gc */ dprintk("lockd: nuking all hosts in net %p...\n", net); - for_each_host(host, pos, chain, nlm_server_hosts) { + for_each_host(host, chain, nlm_server_hosts) { if (net && host->net != net) continue; host->h_expires = jiffies - 1; @@ -644,11 +639,11 @@ static void nlm_gc_hosts(struct net *net) { struct hlist_head *chain; - struct hlist_node *pos, *next; + struct hlist_node *next; struct nlm_host *host; dprintk("lockd: host garbage collection for net %p\n", net); - for_each_host(host, pos, chain, nlm_server_hosts) { + for_each_host(host, chain, nlm_server_hosts) { if (net && host->net != net) continue; host->h_inuse = 0; @@ -657,7 +652,7 @@ nlm_gc_hosts(struct net *net) /* Mark all hosts that hold locks, blocks or shares */ nlmsvc_mark_resources(net); - for_each_host_safe(host, pos, next, chain, nlm_server_hosts) { + for_each_host_safe(host, next, chain, nlm_server_hosts) { if (net && host->net != net) continue; if (atomic_read(&host->h_count) || host->h_inuse diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c index 0deb5f6c9dd4..747d40591675 100644 --- a/fs/lockd/svcsubs.c +++ b/fs/lockd/svcsubs.c @@ -84,7 +84,6 @@ __be32 nlm_lookup_file(struct svc_rqst *rqstp, struct nlm_file **result, struct nfs_fh *f) { - struct hlist_node *pos; struct nlm_file *file; unsigned int hash; __be32 nfserr; @@ -96,7 +95,7 @@ nlm_lookup_file(struct svc_rqst *rqstp, struct nlm_file **result, /* Lock file table */ mutex_lock(&nlm_file_mutex); - hlist_for_each_entry(file, pos, &nlm_files[hash], f_list) + hlist_for_each_entry(file, &nlm_files[hash], f_list) if (!nfs_compare_fh(&file->f_handle, f)) goto found; @@ -248,13 +247,13 @@ static int nlm_traverse_files(void *data, nlm_host_match_fn_t match, int (*is_failover_file)(void *data, struct nlm_file *file)) { - struct hlist_node *pos, *next; + struct hlist_node *next; struct nlm_file *file; int i, ret = 0; mutex_lock(&nlm_file_mutex); for (i = 0; i < FILE_NRHASH; i++) { - hlist_for_each_entry_safe(file, pos, next, &nlm_files[i], f_list) { + hlist_for_each_entry_safe(file, next, &nlm_files[i], f_list) { if (is_failover_file && !is_failover_file(data, file)) continue; file->f_count++; diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c index 6958adfaff08..24a05ba3de26 100644 --- a/fs/ncpfs/ioctl.c +++ b/fs/ncpfs/ioctl.c @@ -819,7 +819,7 @@ long ncp_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) case NCP_IOC_CONN_LOGGED_IN: case NCP_IOC_SETROOT: if (!capable(CAP_SYS_ADMIN)) { - ret = -EACCES; + ret = -EPERM; goto out; } break; diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 9f3c66438d0e..84d8eae203a7 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -197,7 +197,6 @@ error_0: EXPORT_SYMBOL_GPL(nfs_alloc_client); #if IS_ENABLED(CONFIG_NFS_V4) -/* idr_remove_all is not needed as all id's are removed by nfs_put_client */ void nfs_cleanup_cb_ident_idr(struct net *net) { struct nfs_net *nn = net_generic(net, nfs_net_id); diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 2e9779b58b7a..47d100872390 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -29,15 +29,14 @@ static int nfs_get_cb_ident_idr(struct nfs_client *clp, int minorversion) if (clp->rpc_ops->version != 4 || minorversion != 0) return ret; -retry: - if (!idr_pre_get(&nn->cb_ident_idr, GFP_KERNEL)) - return -ENOMEM; + idr_preload(GFP_KERNEL); spin_lock(&nn->nfs_client_lock); - ret = idr_get_new(&nn->cb_ident_idr, clp, &clp->cl_cb_ident); + ret = idr_alloc(&nn->cb_ident_idr, clp, 0, 0, GFP_NOWAIT); + if (ret >= 0) + clp->cl_cb_ident = ret; spin_unlock(&nn->nfs_client_lock); - if (ret == -EAGAIN) - goto retry; - return ret; + idr_preload_end(); + return ret < 0 ? ret : 0; } #ifdef CONFIG_NFS_V4_1 diff --git a/fs/nfs/pnfs_dev.c b/fs/nfs/pnfs_dev.c index d35b62e83ea6..6da209bd9408 100644 --- a/fs/nfs/pnfs_dev.c +++ b/fs/nfs/pnfs_dev.c @@ -77,9 +77,8 @@ _lookup_deviceid(const struct pnfs_layoutdriver_type *ld, long hash) { struct nfs4_deviceid_node *d; - struct hlist_node *n; - hlist_for_each_entry_rcu(d, n, &nfs4_deviceid_cache[hash], node) + hlist_for_each_entry_rcu(d, &nfs4_deviceid_cache[hash], node) if (d->ld == ld && d->nfs_client == clp && !memcmp(&d->deviceid, id, sizeof(*id))) { if (atomic_read(&d->ref)) @@ -248,12 +247,11 @@ static void _deviceid_purge_client(const struct nfs_client *clp, long hash) { struct nfs4_deviceid_node *d; - struct hlist_node *n; HLIST_HEAD(tmp); spin_lock(&nfs4_deviceid_lock); rcu_read_lock(); - hlist_for_each_entry_rcu(d, n, &nfs4_deviceid_cache[hash], node) + hlist_for_each_entry_rcu(d, &nfs4_deviceid_cache[hash], node) if (d->nfs_client == clp && atomic_read(&d->ref)) { hlist_del_init_rcu(&d->node); hlist_add_head(&d->tmpnode, &tmp); @@ -291,12 +289,11 @@ void nfs4_deviceid_mark_client_invalid(struct nfs_client *clp) { struct nfs4_deviceid_node *d; - struct hlist_node *n; int i; rcu_read_lock(); for (i = 0; i < NFS4_DEVICE_ID_HASH_SIZE; i ++){ - hlist_for_each_entry_rcu(d, n, &nfs4_deviceid_cache[i], node) + hlist_for_each_entry_rcu(d, &nfs4_deviceid_cache[i], node) if (d->nfs_client == clp) set_bit(NFS_DEVICEID_INVALID, &d->flags); } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index a6637de7ae13..b99ccde31d06 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -151,7 +151,7 @@ get_nfs4_file(struct nfs4_file *fi) } static int num_delegations; -unsigned int max_delegations; +unsigned long max_delegations; /* * Open owner state (share locks) @@ -700,8 +700,8 @@ static int nfsd4_get_drc_mem(int slotsize, u32 num) num = min_t(u32, num, NFSD_MAX_SLOTS_PER_SESSION); spin_lock(&nfsd_drc_lock); - avail = min_t(int, NFSD_MAX_MEM_PER_SESSION, - nfsd_drc_max_mem - nfsd_drc_mem_used); + avail = min((unsigned long)NFSD_MAX_MEM_PER_SESSION, + nfsd_drc_max_mem - nfsd_drc_mem_used); num = min_t(int, num, avail / slotsize); nfsd_drc_mem_used += num * slotsize; spin_unlock(&nfsd_drc_lock); @@ -1060,7 +1060,6 @@ free_client(struct nfs4_client *clp) } free_svc_cred(&clp->cl_cred); kfree(clp->cl_name.data); - idr_remove_all(&clp->cl_stateids); idr_destroy(&clp->cl_stateids); kfree(clp); } diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index d16a5d6435f2..35cdb934c663 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -246,7 +246,6 @@ static struct svc_cacherep * nfsd_cache_search(struct svc_rqst *rqstp) { struct svc_cacherep *rp; - struct hlist_node *hn; struct hlist_head *rh; __be32 xid = rqstp->rq_xid; u32 proto = rqstp->rq_prot, @@ -254,7 +253,7 @@ nfsd_cache_search(struct svc_rqst *rqstp) proc = rqstp->rq_proc; rh = &cache_hash[request_hash(xid)]; - hlist_for_each_entry(rp, hn, rh, c_hash) { + hlist_for_each_entry(rp, rh, c_hash) { if (xid == rp->c_xid && proc == rp->c_proc && proto == rp->c_prot && vers == rp->c_vers && rpc_cmp_addr(svc_addr(rqstp), (struct sockaddr *)&rp->c_addr) && diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index de23db255c69..07a473fd49bc 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -56,8 +56,8 @@ extern struct svc_version nfsd_version2, nfsd_version3, extern u32 nfsd_supported_minorversion; extern struct mutex nfsd_mutex; extern spinlock_t nfsd_drc_lock; -extern unsigned int nfsd_drc_max_mem; -extern unsigned int nfsd_drc_mem_used; +extern unsigned long nfsd_drc_max_mem; +extern unsigned long nfsd_drc_mem_used; extern const struct seq_operations nfs_exports_op; @@ -106,7 +106,7 @@ static inline int nfsd_v4client(struct svc_rqst *rq) * NFSv4 State */ #ifdef CONFIG_NFSD_V4 -extern unsigned int max_delegations; +extern unsigned long max_delegations; void nfs4_state_init(void); int nfsd4_init_slabs(void); void nfsd4_free_slabs(void); diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 40cb1cbaba4e..53e7f4585dc4 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -59,8 +59,8 @@ DEFINE_MUTEX(nfsd_mutex); * nfsd_drc_pages_used tracks the current version 4.1 DRC memory usage. */ spinlock_t nfsd_drc_lock; -unsigned int nfsd_drc_max_mem; -unsigned int nfsd_drc_mem_used; +unsigned long nfsd_drc_max_mem; +unsigned long nfsd_drc_mem_used; #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) static struct svc_stat nfsd_acl_svcstats; @@ -342,7 +342,7 @@ static void set_max_drc(void) >> NFSD_DRC_SIZE_SHIFT) * PAGE_SIZE; nfsd_drc_mem_used = 0; spin_lock_init(&nfsd_drc_lock); - dprintk("%s nfsd_drc_max_mem %u \n", __func__, nfsd_drc_max_mem); + dprintk("%s nfsd_drc_max_mem %lu \n", __func__, nfsd_drc_max_mem); } static int nfsd_get_default_max_blksize(void) diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index 61946883025c..bec4af6eab13 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -126,7 +126,7 @@ static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) nilfs_transaction_commit(inode->i_sb); mapped: - wait_on_page_writeback(page); + wait_for_stable_page(page); out: sb_end_pagefault(inode->i_sb); return block_page_mkwrite_return(ret); diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 6b49f14eac8c..1e92930d59c3 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -25,7 +25,7 @@ #include <linux/gfp.h> #include <linux/mpage.h> #include <linux/writeback.h> -#include <linux/uio.h> +#include <linux/aio.h> #include "nilfs.h" #include "btnode.h" #include "segment.h" diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 6baadb5a8430..4bb21d67d9b1 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -52,7 +52,6 @@ void __fsnotify_vfsmount_delete(struct vfsmount *mnt) void __fsnotify_update_child_dentry_flags(struct inode *inode) { struct dentry *alias; - struct hlist_node *p; int watched; if (!S_ISDIR(inode->i_mode)) @@ -64,7 +63,7 @@ void __fsnotify_update_child_dentry_flags(struct inode *inode) spin_lock(&inode->i_lock); /* run all of the dentries associated with this inode. Since this is a * directory, there damn well better only be one item on this list */ - hlist_for_each_entry(alias, p, &inode->i_dentry, d_alias) { + hlist_for_each_entry(alias, &inode->i_dentry, d_alias) { struct dentry *child; /* run all of the children of the original inode and fix their diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c index f31e90fc050d..74825be65b7b 100644 --- a/fs/notify/inode_mark.c +++ b/fs/notify/inode_mark.c @@ -36,12 +36,11 @@ static void fsnotify_recalc_inode_mask_locked(struct inode *inode) { struct fsnotify_mark *mark; - struct hlist_node *pos; __u32 new_mask = 0; assert_spin_locked(&inode->i_lock); - hlist_for_each_entry(mark, pos, &inode->i_fsnotify_marks, i.i_list) + hlist_for_each_entry(mark, &inode->i_fsnotify_marks, i.i_list) new_mask |= mark->mask; inode->i_fsnotify_mask = new_mask; } @@ -87,11 +86,11 @@ void fsnotify_destroy_inode_mark(struct fsnotify_mark *mark) void fsnotify_clear_marks_by_inode(struct inode *inode) { struct fsnotify_mark *mark, *lmark; - struct hlist_node *pos, *n; + struct hlist_node *n; LIST_HEAD(free_list); spin_lock(&inode->i_lock); - hlist_for_each_entry_safe(mark, pos, n, &inode->i_fsnotify_marks, i.i_list) { + hlist_for_each_entry_safe(mark, n, &inode->i_fsnotify_marks, i.i_list) { list_add(&mark->i.free_i_list, &free_list); hlist_del_init_rcu(&mark->i.i_list); fsnotify_get_mark(mark); @@ -129,11 +128,10 @@ static struct fsnotify_mark *fsnotify_find_inode_mark_locked( struct inode *inode) { struct fsnotify_mark *mark; - struct hlist_node *pos; assert_spin_locked(&inode->i_lock); - hlist_for_each_entry(mark, pos, &inode->i_fsnotify_marks, i.i_list) { + hlist_for_each_entry(mark, &inode->i_fsnotify_marks, i.i_list) { if (mark->group == group) { fsnotify_get_mark(mark); return mark; @@ -194,8 +192,7 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark, struct fsnotify_group *group, struct inode *inode, int allow_dups) { - struct fsnotify_mark *lmark; - struct hlist_node *node, *last = NULL; + struct fsnotify_mark *lmark, *last = NULL; int ret = 0; mark->flags |= FSNOTIFY_MARK_FLAG_INODE; @@ -214,8 +211,8 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark, } /* should mark be in the middle of the current list? */ - hlist_for_each_entry(lmark, node, &inode->i_fsnotify_marks, i.i_list) { - last = node; + hlist_for_each_entry(lmark, &inode->i_fsnotify_marks, i.i_list) { + last = lmark; if ((lmark->group == group) && !allow_dups) { ret = -EEXIST; @@ -235,7 +232,7 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark, BUG_ON(last == NULL); /* mark should be the last entry. last is the current last entry */ - hlist_add_after_rcu(last, &mark->i.i_list); + hlist_add_after_rcu(&last->i.i_list, &mark->i.i_list); out: fsnotify_recalc_inode_mask_locked(inode); spin_unlock(&inode->i_lock); diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c index 871569c7d609..4216308b81b4 100644 --- a/fs/notify/inotify/inotify_fsnotify.c +++ b/fs/notify/inotify/inotify_fsnotify.c @@ -197,7 +197,6 @@ static void inotify_free_group_priv(struct fsnotify_group *group) { /* ideally the idr is empty and we won't hit the BUG in the callback */ idr_for_each(&group->inotify_data.idr, idr_callback, group); - idr_remove_all(&group->inotify_data.idr); idr_destroy(&group->inotify_data.idr); atomic_dec(&group->inotify_data.user->inotify_devs); free_uid(group->inotify_data.user); diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 228a2c2ad8d7..e0f7c1241a6a 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -364,22 +364,20 @@ static int inotify_add_to_idr(struct idr *idr, spinlock_t *idr_lock, { int ret; - do { - if (unlikely(!idr_pre_get(idr, GFP_KERNEL))) - return -ENOMEM; + idr_preload(GFP_KERNEL); + spin_lock(idr_lock); - spin_lock(idr_lock); - ret = idr_get_new_above(idr, i_mark, *last_wd + 1, - &i_mark->wd); + ret = idr_alloc(idr, i_mark, *last_wd + 1, 0, GFP_NOWAIT); + if (ret >= 0) { /* we added the mark to the idr, take a reference */ - if (!ret) { - *last_wd = i_mark->wd; - fsnotify_get_mark(&i_mark->fsn_mark); - } - spin_unlock(idr_lock); - } while (ret == -EAGAIN); + i_mark->wd = ret; + *last_wd = i_mark->wd; + fsnotify_get_mark(&i_mark->fsn_mark); + } - return ret; + spin_unlock(idr_lock); + idr_preload_end(); + return ret < 0 ? ret : 0; } static struct inotify_inode_mark *inotify_idr_find_locked(struct fsnotify_group *group, @@ -576,8 +574,6 @@ static int inotify_update_existing_watch(struct fsnotify_group *group, /* don't allow invalid bits: we don't want flags set */ mask = inotify_arg_to_mask(arg); - if (unlikely(!(mask & IN_ALL_EVENTS))) - return -EINVAL; fsn_mark = fsnotify_find_inode_mark(group, inode); if (!fsn_mark) @@ -629,8 +625,6 @@ static int inotify_new_watch(struct fsnotify_group *group, /* don't allow invalid bits: we don't want flags set */ mask = inotify_arg_to_mask(arg); - if (unlikely(!(mask & IN_ALL_EVENTS))) - return -EINVAL; tmp_i_mark = kmem_cache_alloc(inotify_inode_mark_cachep, GFP_KERNEL); if (unlikely(!tmp_i_mark)) diff --git a/fs/notify/vfsmount_mark.c b/fs/notify/vfsmount_mark.c index 4df58b8ea64a..68ca5a8704b5 100644 --- a/fs/notify/vfsmount_mark.c +++ b/fs/notify/vfsmount_mark.c @@ -33,12 +33,12 @@ void fsnotify_clear_marks_by_mount(struct vfsmount *mnt) { struct fsnotify_mark *mark, *lmark; - struct hlist_node *pos, *n; + struct hlist_node *n; struct mount *m = real_mount(mnt); LIST_HEAD(free_list); spin_lock(&mnt->mnt_root->d_lock); - hlist_for_each_entry_safe(mark, pos, n, &m->mnt_fsnotify_marks, m.m_list) { + hlist_for_each_entry_safe(mark, n, &m->mnt_fsnotify_marks, m.m_list) { list_add(&mark->m.free_m_list, &free_list); hlist_del_init_rcu(&mark->m.m_list); fsnotify_get_mark(mark); @@ -71,12 +71,11 @@ static void fsnotify_recalc_vfsmount_mask_locked(struct vfsmount *mnt) { struct mount *m = real_mount(mnt); struct fsnotify_mark *mark; - struct hlist_node *pos; __u32 new_mask = 0; assert_spin_locked(&mnt->mnt_root->d_lock); - hlist_for_each_entry(mark, pos, &m->mnt_fsnotify_marks, m.m_list) + hlist_for_each_entry(mark, &m->mnt_fsnotify_marks, m.m_list) new_mask |= mark->mask; m->mnt_fsnotify_mask = new_mask; } @@ -114,11 +113,10 @@ static struct fsnotify_mark *fsnotify_find_vfsmount_mark_locked(struct fsnotify_ { struct mount *m = real_mount(mnt); struct fsnotify_mark *mark; - struct hlist_node *pos; assert_spin_locked(&mnt->mnt_root->d_lock); - hlist_for_each_entry(mark, pos, &m->mnt_fsnotify_marks, m.m_list) { + hlist_for_each_entry(mark, &m->mnt_fsnotify_marks, m.m_list) { if (mark->group == group) { fsnotify_get_mark(mark); return mark; @@ -153,8 +151,7 @@ int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark, int allow_dups) { struct mount *m = real_mount(mnt); - struct fsnotify_mark *lmark; - struct hlist_node *node, *last = NULL; + struct fsnotify_mark *lmark, *last = NULL; int ret = 0; mark->flags |= FSNOTIFY_MARK_FLAG_VFSMOUNT; @@ -173,8 +170,8 @@ int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark, } /* should mark be in the middle of the current list? */ - hlist_for_each_entry(lmark, node, &m->mnt_fsnotify_marks, m.m_list) { - last = node; + hlist_for_each_entry(lmark, &m->mnt_fsnotify_marks, m.m_list) { + last = lmark; if ((lmark->group == group) && !allow_dups) { ret = -EEXIST; @@ -194,7 +191,7 @@ int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark, BUG_ON(last == NULL); /* mark should be the last entry. last is the current last entry */ - hlist_add_after_rcu(last, &mark->m.m_list); + hlist_add_after_rcu(&last->m.m_list, &mark->m.m_list); out: fsnotify_recalc_vfsmount_mask_locked(mnt); spin_unlock(&mnt->mnt_root->d_lock); diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 5b2d4f0853ac..600af8fbae56 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -27,6 +27,7 @@ #include <linux/swap.h> #include <linux/uio.h> #include <linux/writeback.h> +#include <linux/aio.h> #include <asm/page.h> #include <asm/uaccess.h> diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index d3e118cc6ffa..2778b0255dc6 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -28,6 +28,7 @@ #include <linux/quotaops.h> #include <linux/slab.h> #include <linux/log2.h> +#include <linux/aio.h> #include "aops.h" #include "attrib.h" diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 657743254eb9..f6fff671bb34 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -593,9 +593,9 @@ static void ocfs2_dio_end_io(struct kiocb *iocb, level = ocfs2_iocb_rw_locked_level(iocb); ocfs2_rw_unlock(inode, level); + inode_dio_done(inode); if (is_async) aio_complete(iocb, ret, 0); - inode_dio_done(inode); } /* @@ -1194,6 +1194,7 @@ static int ocfs2_grab_pages_for_write(struct address_space *mapping, goto out; } } + wait_for_stable_page(wc->w_pages[i]); if (index == target_index) wc->w_target_page = wc->w_pages[i]; diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h index ffb2da370a99..f671e49beb34 100644 --- a/fs/ocfs2/aops.h +++ b/fs/ocfs2/aops.h @@ -22,6 +22,8 @@ #ifndef OCFS2_AOPS_H #define OCFS2_AOPS_H +#include <linux/aio.h> + handle_t *ocfs2_start_walk_page_trans(struct inode *inode, struct page *page, unsigned from, diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index a1d83c58b296..33b892464d14 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -304,28 +304,22 @@ static u8 o2net_num_from_nn(struct o2net_node *nn) static int o2net_prep_nsw(struct o2net_node *nn, struct o2net_status_wait *nsw) { - int ret = 0; - - do { - if (!idr_pre_get(&nn->nn_status_idr, GFP_ATOMIC)) { - ret = -EAGAIN; - break; - } - spin_lock(&nn->nn_lock); - ret = idr_get_new(&nn->nn_status_idr, nsw, &nsw->ns_id); - if (ret == 0) - list_add_tail(&nsw->ns_node_item, - &nn->nn_status_list); - spin_unlock(&nn->nn_lock); - } while (ret == -EAGAIN); + int ret; - if (ret == 0) { - init_waitqueue_head(&nsw->ns_wq); - nsw->ns_sys_status = O2NET_ERR_NONE; - nsw->ns_status = 0; + spin_lock(&nn->nn_lock); + ret = idr_alloc(&nn->nn_status_idr, nsw, 0, 0, GFP_ATOMIC); + if (ret >= 0) { + nsw->ns_id = ret; + list_add_tail(&nsw->ns_node_item, &nn->nn_status_list); } + spin_unlock(&nn->nn_lock); + if (ret < 0) + return ret; - return ret; + init_waitqueue_head(&nsw->ns_wq); + nsw->ns_sys_status = O2NET_ERR_NONE; + nsw->ns_status = 0; + return 0; } static void o2net_complete_nsw_locked(struct o2net_node *nn, diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c index 8db4b58b2e4b..ef999729e274 100644 --- a/fs/ocfs2/dcache.c +++ b/fs/ocfs2/dcache.c @@ -169,11 +169,10 @@ struct dentry *ocfs2_find_local_alias(struct inode *inode, u64 parent_blkno, int skip_unhashed) { - struct hlist_node *p; struct dentry *dentry; spin_lock(&inode->i_lock); - hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) { spin_lock(&dentry->d_lock); if (ocfs2_match_dentry(dentry, parent_blkno, skip_unhashed)) { trace_ocfs2_find_local_alias(dentry->d_name.len, diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index 15d81adb8d77..ba1e68923b21 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -2090,7 +2090,6 @@ static void dlm_finish_local_lockres_recovery(struct dlm_ctxt *dlm, u8 dead_node, u8 new_master) { int i; - struct hlist_node *hash_iter; struct hlist_head *bucket; struct dlm_lock_resource *res, *next; @@ -2121,7 +2120,7 @@ static void dlm_finish_local_lockres_recovery(struct dlm_ctxt *dlm, * if necessary */ for (i = 0; i < DLM_HASH_BUCKETS; i++) { bucket = dlm_lockres_hash(dlm, i); - hlist_for_each_entry(res, hash_iter, bucket, hash_node) { + hlist_for_each_entry(res, bucket, hash_node) { if (!(res->state & DLM_LOCK_RES_RECOVERING)) continue; @@ -2280,7 +2279,6 @@ static void dlm_free_dead_locks(struct dlm_ctxt *dlm, static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node) { - struct hlist_node *iter; struct dlm_lock_resource *res; int i; struct hlist_head *bucket; @@ -2306,7 +2304,7 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node) */ for (i = 0; i < DLM_HASH_BUCKETS; i++) { bucket = dlm_lockres_hash(dlm, i); - hlist_for_each_entry(res, iter, bucket, hash_node) { + hlist_for_each_entry(res, bucket, hash_node) { /* always prune any $RECOVERY entries for dead nodes, * otherwise hangs can occur during later recovery */ if (dlm_is_recovery_lock(res->lockname.name, diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 4f7795fb5fc0..bad2583881c8 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -2322,7 +2322,7 @@ int ocfs2_inode_lock_full_nested(struct inode *inode, status = __ocfs2_cluster_lock(osb, lockres, level, dlm_flags, arg_flags, subclass, _RET_IP_); if (status < 0) { - if (status != -EAGAIN && status != -EIOCBRETRY) + if (status != -EAGAIN) mlog_errno(status); goto bail; } diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h index 88924a3133fa..c765bdf6d60e 100644 --- a/fs/ocfs2/inode.h +++ b/fs/ocfs2/inode.h @@ -28,6 +28,8 @@ #include "extent_map.h" +struct iocb; + /* OCFS2 Inode Private Data */ struct ocfs2_inode_info { diff --git a/fs/pipe.c b/fs/pipe.c index bd3479db4b62..dc86533457b2 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -21,6 +21,7 @@ #include <linux/audit.h> #include <linux/syscalls.h> #include <linux/fcntl.h> +#include <linux/aio.h> #include <asm/uaccess.h> #include <asm/ioctls.h> diff --git a/fs/proc/base.c b/fs/proc/base.c index 9b43ff77a51e..c6528c663df4 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -73,6 +73,7 @@ #include <linux/security.h> #include <linux/ptrace.h> #include <linux/tracehook.h> +#include <linux/printk.h> #include <linux/cgroup.h> #include <linux/cpuset.h> #include <linux/audit.h> @@ -952,7 +953,7 @@ static ssize_t oom_adj_write(struct file *file, const char __user *buf, * /proc/pid/oom_adj is provided for legacy purposes, ask users to use * /proc/pid/oom_score_adj instead. */ - printk_once(KERN_WARNING "%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n", + pr_warn_once("%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n", current->comm, task_pid_nr(current), task_pid_nr(task), task_pid_nr(task)); @@ -1711,7 +1712,7 @@ static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags) return -ECHILD; if (!capable(CAP_SYS_ADMIN)) { - status = -EACCES; + status = -EPERM; goto out_notask; } @@ -1844,7 +1845,7 @@ static struct dentry *proc_map_files_lookup(struct inode *dir, struct dentry *result; struct mm_struct *mm; - result = ERR_PTR(-EACCES); + result = ERR_PTR(-EPERM); if (!capable(CAP_SYS_ADMIN)) goto out; @@ -1900,7 +1901,7 @@ proc_map_files_readdir(struct file *filp, void *dirent, filldir_t filldir) ino_t ino; int ret; - ret = -EACCES; + ret = -EPERM; if (!capable(CAP_SYS_ADMIN)) goto out; diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 76ddae83daa5..d00072351cd5 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -15,6 +15,7 @@ #include <linux/mm.h> #include <linux/module.h> #include <linux/slab.h> +#include <linux/printk.h> #include <linux/mount.h> #include <linux/init.h> #include <linux/idr.h> @@ -132,11 +133,8 @@ __proc_file_read(struct file *file, char __user *buf, size_t nbytes, } if (start == NULL) { - if (n > PAGE_SIZE) { - printk(KERN_ERR - "proc_file_read: Apparent buffer overflow!\n"); + if (n > PAGE_SIZE) /* Apparent buffer overflow */ n = PAGE_SIZE; - } n -= *ppos; if (n <= 0) break; @@ -144,26 +142,19 @@ __proc_file_read(struct file *file, char __user *buf, size_t nbytes, n = count; start = page + *ppos; } else if (start < page) { - if (n > PAGE_SIZE) { - printk(KERN_ERR - "proc_file_read: Apparent buffer overflow!\n"); + if (n > PAGE_SIZE) /* Apparent buffer overflow */ n = PAGE_SIZE; - } if (n > count) { /* * Don't reduce n because doing so might * cut off part of a data block. */ - printk(KERN_WARNING - "proc_file_read: Read count exceeded\n"); + pr_warn("proc_file_read: count exceeded\n"); } } else /* start >= page */ { unsigned long startoff = (unsigned long)(start - page); - if (n > (PAGE_SIZE - startoff)) { - printk(KERN_ERR - "proc_file_read: Apparent buffer overflow!\n"); + if (n > (PAGE_SIZE - startoff)) /* buffer overflow? */ n = PAGE_SIZE - startoff; - } if (n > count) n = count; } @@ -576,7 +567,7 @@ static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp for (tmp = dir->subdir; tmp; tmp = tmp->next) if (strcmp(tmp->name, dp->name) == 0) { - WARN(1, KERN_WARNING "proc_dir_entry '%s/%s' already registered\n", + WARN(1, "proc_dir_entry '%s/%s' already registered\n", dir->name, dp->name); break; } @@ -837,7 +828,7 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent) if (S_ISDIR(de->mode)) parent->nlink--; de->nlink = 0; - WARN(de->subdir, KERN_WARNING "%s: removing non-empty directory " + WARN(de->subdir, "%s: removing non-empty directory " "'%s/%s', leaking at least '%s'\n", __func__, de->parent->name, de->name, de->subdir->name); pde_put(de); diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 439ae6886507..7a59f50f64d6 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -13,6 +13,7 @@ #include <linux/stat.h> #include <linux/completion.h> #include <linux/poll.h> +#include <linux/printk.h> #include <linux/file.h> #include <linux/limits.h> #include <linux/init.h> @@ -486,6 +487,8 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de) int proc_fill_super(struct super_block *s) { + struct inode *root_inode; + s->s_flags |= MS_NODIRATIME | MS_NOSUID | MS_NOEXEC; s->s_blocksize = 1024; s->s_blocksize_bits = 10; @@ -494,11 +497,18 @@ int proc_fill_super(struct super_block *s) s->s_time_gran = 1; pde_get(&proc_root); - s->s_root = d_make_root(proc_get_inode(s, &proc_root)); - if (s->s_root) - return 0; + root_inode = proc_get_inode(s, &proc_root); + if (!root_inode) { + pr_warn("proc_fill_super: get root inode failed\n"); + pde_put(&proc_root); + return -ENOMEM; + } - printk("proc_read_super: get root inode failed\n"); - pde_put(&proc_root); - return -ENOMEM; + s->s_root = d_make_root(root_inode); + if (!s->s_root) { + pr_err("proc_fill_super: allocate dentry failed\n"); + return -ENOMEM; + } + + return 0; } diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 252544c05207..85ff3a4598b3 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -11,6 +11,7 @@ #include <linux/sched.h> #include <linux/proc_fs.h> +#include <linux/binfmts.h> struct ctl_table_header; struct mempolicy; @@ -108,7 +109,7 @@ static inline int task_dumpable(struct task_struct *task) if (mm) dumpable = get_dumpable(mm); task_unlock(task); - if (dumpable == SUID_DUMPABLE_ENABLED) + if (dumpable == SUID_DUMP_USER) return 1; return 0; } diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index e96d4f18ca3a..eda6f017f272 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -17,6 +17,7 @@ #include <linux/elfcore.h> #include <linux/vmalloc.h> #include <linux/highmem.h> +#include <linux/printk.h> #include <linux/bootmem.h> #include <linux/init.h> #include <linux/slab.h> @@ -619,7 +620,7 @@ static int __init proc_kcore_init(void) proc_root_kcore = proc_create("kcore", S_IRUSR, NULL, &proc_kcore_operations); if (!proc_root_kcore) { - printk(KERN_ERR "couldn't create /proc/kcore\n"); + pr_err("couldn't create /proc/kcore\n"); return 0; /* Always returns 0. */ } /* Store text area if it's special */ diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index 80e4645f7990..1efaaa19c4f3 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -40,7 +40,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) * sysctl_overcommit_ratio / 100) + total_swap_pages; cached = global_page_state(NR_FILE_PAGES) - - total_swapcache_pages - i.bufferram; + total_swapcache_pages() - i.bufferram; if (cached < 0) cached = 0; @@ -109,7 +109,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) K(i.freeram), K(i.bufferram), K(cached), - K(total_swapcache_pages), + K(total_swapcache_pages()), K(pages[LRU_ACTIVE_ANON] + pages[LRU_ACTIVE_FILE]), K(pages[LRU_INACTIVE_ANON] + pages[LRU_INACTIVE_FILE]), K(pages[LRU_ACTIVE_ANON]), @@ -158,7 +158,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) vmi.used >> 10, vmi.largest_chunk >> 10 #ifdef CONFIG_MEMORY_FAILURE - ,atomic_long_read(&mce_bad_pages) << (PAGE_SHIFT - 10) + ,atomic_long_read(&num_poisoned_pages) << (PAGE_SHIFT - 10) #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE ,K(global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) * diff --git a/fs/proc/proc_devtree.c b/fs/proc/proc_devtree.c index de20ec480fa0..30b590f5bd35 100644 --- a/fs/proc/proc_devtree.c +++ b/fs/proc/proc_devtree.c @@ -8,6 +8,7 @@ #include <linux/time.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <linux/printk.h> #include <linux/stat.h> #include <linux/string.h> #include <linux/of.h> @@ -110,8 +111,8 @@ void proc_device_tree_update_prop(struct proc_dir_entry *pde, if (ent->data == oldprop) break; if (ent == NULL) { - printk(KERN_WARNING "device-tree: property \"%s\" " - " does not exist\n", oldprop->name); + pr_warn("device-tree: property \"%s\" does not exist\n", + oldprop->name); } else { ent->data = newprop; ent->size = newprop->length; @@ -153,8 +154,8 @@ static const char *fixup_name(struct device_node *np, struct proc_dir_entry *de, realloc: fixed_name = kmalloc(fixup_len, GFP_KERNEL); if (fixed_name == NULL) { - printk(KERN_ERR "device-tree: Out of memory trying to fixup " - "name \"%s\"\n", name); + pr_err("device-tree: Out of memory trying to fixup " + "name \"%s\"\n", name); return name; } @@ -175,8 +176,8 @@ retry: goto retry; } - printk(KERN_WARNING "device-tree: Duplicate name in %s, " - "renamed to \"%s\"\n", np->full_name, fixed_name); + pr_warn("device-tree: Duplicate name in %s, renamed to \"%s\"\n", + np->full_name, fixed_name); return fixed_name; } diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 1827d88ad58b..6384b04175af 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -5,6 +5,7 @@ #include <linux/sysctl.h> #include <linux/poll.h> #include <linux/proc_fs.h> +#include <linux/printk.h> #include <linux/security.h> #include <linux/sched.h> #include <linux/namei.h> @@ -57,7 +58,7 @@ static void sysctl_print_dir(struct ctl_dir *dir) { if (dir->header.parent) sysctl_print_dir(dir->header.parent); - printk(KERN_CONT "%s/", dir->header.ctl_table[0].procname); + pr_cont("%s/", dir->header.ctl_table[0].procname); } static int namecmp(const char *name1, int len1, const char *name2, int len2) @@ -134,9 +135,9 @@ static int insert_entry(struct ctl_table_header *head, struct ctl_table *entry) else if (cmp > 0) p = &(*p)->rb_right; else { - printk(KERN_ERR "sysctl duplicate entry: "); + pr_err("sysctl duplicate entry: "); sysctl_print_dir(head->parent); - printk(KERN_CONT "/%s\n", entry->procname); + pr_cont("/%s\n", entry->procname); return -EEXIST; } } @@ -927,9 +928,9 @@ found: subdir->header.nreg++; failed: if (unlikely(IS_ERR(subdir))) { - printk(KERN_ERR "sysctl could not get directory: "); + pr_err("sysctl could not get directory: "); sysctl_print_dir(dir); - printk(KERN_CONT "/%*.*s %ld\n", + pr_cont("/%*.*s %ld\n", namelen, namelen, name, PTR_ERR(subdir)); } drop_sysctl_table(&dir->header); @@ -995,8 +996,8 @@ static int sysctl_err(const char *path, struct ctl_table *table, char *fmt, ...) vaf.fmt = fmt; vaf.va = &args; - printk(KERN_ERR "sysctl table check failed: %s/%s %pV\n", - path, table->procname, &vaf); + pr_err("sysctl table check failed: %s/%s %pV\n", + path, table->procname, &vaf); va_end(args); return -EINVAL; @@ -1510,9 +1511,9 @@ static void put_links(struct ctl_table_header *header) drop_sysctl_table(link_head); } else { - printk(KERN_ERR "sysctl link missing during unregister: "); + pr_err("sysctl link missing during unregister: "); sysctl_print_dir(parent); - printk(KERN_CONT "/%s\n", name); + pr_cont("/%s\n", name); } } } diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 0d5071d29985..41dd018f72dd 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -15,6 +15,7 @@ #include <linux/export.h> #include <linux/slab.h> #include <linux/highmem.h> +#include <linux/printk.h> #include <linux/bootmem.h> #include <linux/init.h> #include <linux/crash_dump.h> @@ -553,8 +554,7 @@ static int __init parse_crash_elf64_headers(void) ehdr.e_ehsize != sizeof(Elf64_Ehdr) || ehdr.e_phentsize != sizeof(Elf64_Phdr) || ehdr.e_phnum == 0) { - printk(KERN_WARNING "Warning: Core image elf header is not" - "sane\n"); + pr_warn("Warning: Core image elf header is not sane\n"); return -EINVAL; } @@ -609,8 +609,7 @@ static int __init parse_crash_elf32_headers(void) ehdr.e_ehsize != sizeof(Elf32_Ehdr) || ehdr.e_phentsize != sizeof(Elf32_Phdr) || ehdr.e_phnum == 0) { - printk(KERN_WARNING "Warning: Core image elf header is not" - "sane\n"); + pr_warn("Warning: Core image elf header is not sane\n"); return -EINVAL; } @@ -653,8 +652,7 @@ static int __init parse_crash_elf_headers(void) if (rc < 0) return rc; if (memcmp(e_ident, ELFMAG, SELFMAG) != 0) { - printk(KERN_WARNING "Warning: Core image elf header" - " not found\n"); + pr_warn("Warning: Core image elf header not found\n"); return -EINVAL; } @@ -673,8 +671,7 @@ static int __init parse_crash_elf_headers(void) /* Determine vmcore size. */ vmcore_size = get_vmcore_size_elf32(elfcorebuf); } else { - printk(KERN_WARNING "Warning: Core image elf header is not" - " sane\n"); + pr_warn("Warning: Core image elf header is not sane\n"); return -EINVAL; } return 0; @@ -690,7 +687,7 @@ static int __init vmcore_init(void) return rc; rc = parse_crash_elf_headers(); if (rc) { - printk(KERN_WARNING "Kdump: vmcore not initialized\n"); + pr_warn("Kdump: vmcore not initialized\n"); return rc; } diff --git a/fs/read_write.c b/fs/read_write.c index bb34af315280..616bc3962bb0 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -15,6 +15,7 @@ #include <linux/syscalls.h> #include <linux/pagemap.h> #include <linux/splice.h> +#include <linux/aio.h> #include "read_write.h" #include <asm/uaccess.h> @@ -318,16 +319,6 @@ int rw_verify_area(int read_write, struct file *file, loff_t *ppos, size_t count return count > MAX_RW_COUNT ? MAX_RW_COUNT : count; } -static void wait_on_retry_sync_kiocb(struct kiocb *iocb) -{ - set_current_state(TASK_UNINTERRUPTIBLE); - if (!kiocbIsKicked(iocb)) - schedule(); - else - kiocbClearKicked(iocb); - __set_current_state(TASK_RUNNING); -} - ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos) { struct iovec iov = { .iov_base = buf, .iov_len = len }; @@ -339,13 +330,7 @@ ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *pp kiocb.ki_left = len; kiocb.ki_nbytes = len; - for (;;) { - ret = filp->f_op->aio_read(&kiocb, &iov, 1, kiocb.ki_pos); - if (ret != -EIOCBRETRY) - break; - wait_on_retry_sync_kiocb(&kiocb); - } - + ret = filp->f_op->aio_read(&kiocb, &iov, 1, kiocb.ki_pos); if (-EIOCBQUEUED == ret) ret = wait_on_sync_kiocb(&kiocb); *ppos = kiocb.ki_pos; @@ -395,13 +380,7 @@ ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, lof kiocb.ki_left = len; kiocb.ki_nbytes = len; - for (;;) { - ret = filp->f_op->aio_write(&kiocb, &iov, 1, kiocb.ki_pos); - if (ret != -EIOCBRETRY) - break; - wait_on_retry_sync_kiocb(&kiocb); - } - + ret = filp->f_op->aio_write(&kiocb, &iov, 1, kiocb.ki_pos); if (-EIOCBQUEUED == ret) ret = wait_on_sync_kiocb(&kiocb); *ppos = kiocb.ki_pos; @@ -568,13 +547,7 @@ ssize_t do_sync_readv_writev(struct file *filp, const struct iovec *iov, kiocb.ki_left = len; kiocb.ki_nbytes = len; - for (;;) { - ret = fn(&kiocb, iov, nr_segs, kiocb.ki_pos); - if (ret != -EIOCBRETRY) - break; - wait_on_retry_sync_kiocb(&kiocb); - } - + ret = fn(&kiocb, iov, nr_segs, kiocb.ki_pos); if (ret == -EIOCBQUEUED) ret = wait_on_sync_kiocb(&kiocb); *ppos = kiocb.ki_pos; diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 95d7680ead47..30195bcbbfc3 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -18,6 +18,7 @@ #include <linux/writeback.h> #include <linux/quotaops.h> #include <linux/swap.h> +#include <linux/aio.h> int reiserfs_commit_write(struct file *f, struct page *page, unsigned from, unsigned to); diff --git a/fs/seq_file.c b/fs/seq_file.c index f2bc3dfd0b88..15c6304bab71 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -308,27 +308,27 @@ loff_t seq_lseek(struct file *file, loff_t offset, int whence) mutex_lock(&m->lock); m->version = file->f_version; switch (whence) { - case 1: - offset += file->f_pos; - case 0: - if (offset < 0) - break; - retval = offset; - if (offset != m->read_pos) { - while ((retval=traverse(m, offset)) == -EAGAIN) - ; - if (retval) { - /* with extreme prejudice... */ - file->f_pos = 0; - m->read_pos = 0; - m->version = 0; - m->index = 0; - m->count = 0; - } else { - m->read_pos = offset; - retval = file->f_pos = offset; - } + case SEEK_CUR: + offset += file->f_pos; + case SEEK_SET: + if (offset < 0) + break; + retval = offset; + if (offset != m->read_pos) { + while ((retval = traverse(m, offset)) == -EAGAIN) + ; + if (retval) { + /* with extreme prejudice... */ + file->f_pos = 0; + m->read_pos = 0; + m->version = 0; + m->index = 0; + m->count = 0; + } else { + m->read_pos = offset; + retval = file->f_pos = offset; } + } } file->f_version = m->version; mutex_unlock(&m->lock); diff --git a/fs/signalfd.c b/fs/signalfd.c index b53486961735..c723b5d56c8f 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -30,6 +30,7 @@ #include <linux/signalfd.h> #include <linux/syscalls.h> #include <linux/proc_fs.h> +#include <linux/compat.h> void signalfd_cleanup(struct sighand_struct *sighand) { @@ -74,6 +75,39 @@ static unsigned int signalfd_poll(struct file *file, poll_table *wait) } /* + * Copy a whole siginfo into userspace. + * The main idea of this format is that it should be enough + * for restoring siginfo back into the kernel. + */ +static int signalfd_copy_raw_info(struct signalfd_siginfo __user *siginfo, + siginfo_t *kinfo) +{ + siginfo_t __user *uinfo = (siginfo_t __user *)siginfo; + int err; + + BUILD_BUG_ON(sizeof(siginfo_t) != sizeof(struct signalfd_siginfo)); + + err = __clear_user(uinfo, sizeof(*uinfo)); + +#ifdef CONFIG_COMPAT + if (unlikely(is_compat_task())) { + compat_siginfo_t __user *compat_uinfo; + + compat_uinfo = (compat_siginfo_t __user *)siginfo; + err |= copy_siginfo_to_user32(compat_uinfo, kinfo); + err |= put_user(kinfo->si_code, &compat_uinfo->si_code); + + return err ? -EFAULT : sizeof(*compat_uinfo); + } +#endif + + err |= copy_siginfo_to_user(uinfo, kinfo); + err |= put_user(kinfo->si_code, &uinfo->si_code); + + return err ? -EFAULT : sizeof(*uinfo); +} + +/* * Copied from copy_siginfo_to_user() in kernel/signal.c */ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo, @@ -205,6 +239,7 @@ static ssize_t signalfd_read(struct file *file, char __user *buf, size_t count, struct signalfd_ctx *ctx = file->private_data; struct signalfd_siginfo __user *siginfo; int nonblock = file->f_flags & O_NONBLOCK; + bool raw = file->f_flags & SFD_RAW; ssize_t ret, total = 0; siginfo_t info; @@ -217,7 +252,12 @@ static ssize_t signalfd_read(struct file *file, char __user *buf, size_t count, ret = signalfd_dequeue(ctx, &info, nonblock); if (unlikely(ret <= 0)) break; - ret = signalfd_copyinfo(siginfo, &info); + + if (raw) + ret = signalfd_copy_raw_info(siginfo, &info); + else + ret = signalfd_copyinfo(siginfo, &info); + if (ret < 0) break; siginfo++; @@ -262,7 +302,7 @@ SYSCALL_DEFINE4(signalfd4, int, ufd, sigset_t __user *, user_mask, BUILD_BUG_ON(SFD_CLOEXEC != O_CLOEXEC); BUILD_BUG_ON(SFD_NONBLOCK != O_NONBLOCK); - if (flags & ~(SFD_CLOEXEC | SFD_NONBLOCK)) + if (flags & ~(SFD_CLOEXEC | SFD_NONBLOCK | SFD_RAW)) return -EINVAL; if (sizemask != sizeof(sigset_t) || @@ -272,20 +312,35 @@ SYSCALL_DEFINE4(signalfd4, int, ufd, sigset_t __user *, user_mask, signotset(&sigmask); if (ufd == -1) { + struct file *file; ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) return -ENOMEM; ctx->sigmask = sigmask; + ufd = get_unused_fd_flags(flags); + if (ufd < 0) { + kfree(ctx); + goto out; + } + /* * When we call this, the initialization must be complete, since * anon_inode_getfd() will install the fd. */ - ufd = anon_inode_getfd("[signalfd]", &signalfd_fops, ctx, + file = anon_inode_getfile("[signalfd]", &signalfd_fops, ctx, O_RDWR | (flags & (O_CLOEXEC | O_NONBLOCK))); - if (ufd < 0) + if (IS_ERR(file)) { + put_unused_fd(ufd); + ufd = PTR_ERR(file); kfree(ctx); + goto out; + } + + file->f_flags |= flags & SFD_RAW; + + fd_install(ufd, file); } else { struct fd f = fdget(ufd); if (!f.file) @@ -302,7 +357,7 @@ SYSCALL_DEFINE4(signalfd4, int, ufd, sigset_t __user *, user_mask, wake_up(¤t->sighand->signalfd_wqh); fdput(f); } - +out: return ufd; } diff --git a/fs/super.c b/fs/super.c index 12f123712161..c290cca1069a 100644 --- a/fs/super.c +++ b/fs/super.c @@ -447,14 +447,13 @@ struct super_block *sget(struct file_system_type *type, void *data) { struct super_block *s = NULL; - struct hlist_node *node; struct super_block *old; int err; retry: spin_lock(&sb_lock); if (test) { - hlist_for_each_entry(old, node, &type->fs_supers, s_instances) { + hlist_for_each_entry(old, &type->fs_supers, s_instances) { if (!test(old, data)) continue; if (!grab_super(old)) @@ -554,10 +553,9 @@ void iterate_supers_type(struct file_system_type *type, void (*f)(struct super_block *, void *), void *arg) { struct super_block *sb, *p = NULL; - struct hlist_node *node; spin_lock(&sb_lock); - hlist_for_each_entry(sb, node, &type->fs_supers, s_instances) { + hlist_for_each_entry(sb, &type->fs_supers, s_instances) { sb->s_count++; spin_unlock(&sb_lock); diff --git a/fs/sysfs/bin.c b/fs/sysfs/bin.c index 614b2b544880..f186e277a127 100644 --- a/fs/sysfs/bin.c +++ b/fs/sysfs/bin.c @@ -461,14 +461,13 @@ const struct file_operations bin_fops = { void unmap_bin_file(struct sysfs_dirent *attr_sd) { struct bin_buffer *bb; - struct hlist_node *tmp; if (sysfs_type(attr_sd) != SYSFS_KOBJ_BIN_ATTR) return; mutex_lock(&sysfs_bin_lock); - hlist_for_each_entry(bb, tmp, &attr_sd->s_bin_attr.buffers, list) { + hlist_for_each_entry(bb, &attr_sd->s_bin_attr.buffers, list) { struct inode *inode = bb->file->f_path.dentry->d_inode; unmap_mapping_range(inode->i_mapping, 0, 0, 1); diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 5bc77817f382..deaf954368ad 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -50,6 +50,7 @@ */ #include "ubifs.h" +#include <linux/aio.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/slab.h> @@ -1522,6 +1523,7 @@ static int ubifs_vm_page_mkwrite(struct vm_area_struct *vma, ubifs_release_dirty_inode_budget(c, ui); } + wait_for_stable_page(page); unlock_page(page); return 0; diff --git a/fs/udf/file.c b/fs/udf/file.c index 77b5953eaac8..63e25fc83328 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -204,7 +204,7 @@ long udf_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) goto out; case UDF_RELOCATE_BLOCKS: if (!capable(CAP_SYS_ADMIN)) { - result = -EACCES; + result = -EPERM; goto out; } if (get_user(old_block, (long __user *)arg)) { diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 7a12e48ad819..b6d15d349810 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -38,6 +38,7 @@ #include <linux/slab.h> #include <linux/crc-itu-t.h> #include <linux/mpage.h> +#include <linux/aio.h> #include "udf_i.h" #include "udf_sb.h" diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 5f707e537171..c24ce0e9c67c 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -31,6 +31,7 @@ #include "xfs_vnodeops.h" #include "xfs_trace.h" #include "xfs_bmap.h" +#include <linux/aio.h> #include <linux/gfp.h> #include <linux/mpage.h> #include <linux/pagevec.h> diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 67284edb84d7..a4d7ef78fd56 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -36,6 +36,7 @@ #include "xfs_ioctl.h" #include "xfs_trace.h" +#include <linux/aio.h> #include <linux/dcache.h> #include <linux/falloc.h> #include <linux/pagevec.h> diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 96fcbb85ff83..d1dba7ce75ae 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -1442,9 +1442,8 @@ xlog_recover_find_tid( xlog_tid_t tid) { xlog_recover_t *trans; - struct hlist_node *n; - hlist_for_each_entry(trans, n, head, r_list) { + hlist_for_each_entry(trans, head, r_list) { if (trans->r_log_tid == tid) return trans; } diff --git a/include/linux/acpi.h b/include/linux/acpi.h index c6ccd9fa8f08..21ef6f1c36b0 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -486,6 +486,14 @@ static inline bool acpi_driver_match_device(struct device *dev, #endif /* !CONFIG_ACPI */ +#ifdef CONFIG_ACPI_NUMA +void __init early_parse_srat(void); +#else +static inline void early_parse_srat(void) +{ +} +#endif + #ifdef CONFIG_ACPI void acpi_os_set_prepare_sleep(int (*func)(u8 sleep_state, u32 pm1a_ctrl, u32 pm1b_ctrl)); diff --git a/include/linux/aio.h b/include/linux/aio.h index 31ff6dba4872..a7e4c595825e 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -6,94 +6,38 @@ #include <linux/aio_abi.h> #include <linux/uio.h> #include <linux/rcupdate.h> - #include <linux/atomic.h> - -#define AIO_MAXSEGS 4 -#define AIO_KIOGRP_NR_ATOMIC 8 +#include <linux/batch_complete.h> struct kioctx; +struct kiocb; +struct batch_complete; -/* Notes on cancelling a kiocb: - * If a kiocb is cancelled, aio_complete may return 0 to indicate - * that cancel has not yet disposed of the kiocb. All cancel - * operations *must* call aio_put_req to dispose of the kiocb - * to guard against races with the completion code. - */ -#define KIOCB_C_CANCELLED 0x01 -#define KIOCB_C_COMPLETE 0x02 - -#define KIOCB_SYNC_KEY (~0U) +#define KIOCB_KEY 0 -/* ki_flags bits */ /* - * This may be used for cancel/retry serialization in the future, but - * for now it's unused and we probably don't want modules to even - * think they can use it. + * We use ki_cancel == KIOCB_CANCELLED to indicate that a kiocb has been either + * cancelled or completed (this makes a certain amount of sense because + * successful cancellation - io_cancel() - does deliver the completion to + * userspace). + * + * And since most things don't implement kiocb cancellation and we'd really like + * kiocb completion to be lockless when possible, we use ki_cancel to + * synchronize cancellation and completion - we only set it to KIOCB_CANCELLED + * with xchg() or cmpxchg(), see batch_complete_aio() and kiocb_cancel(). */ -/* #define KIF_LOCKED 0 */ -#define KIF_KICKED 1 -#define KIF_CANCELLED 2 - -#define kiocbTryLock(iocb) test_and_set_bit(KIF_LOCKED, &(iocb)->ki_flags) -#define kiocbTryKick(iocb) test_and_set_bit(KIF_KICKED, &(iocb)->ki_flags) +#define KIOCB_CANCELLED ((void *) (~0ULL)) -#define kiocbSetLocked(iocb) set_bit(KIF_LOCKED, &(iocb)->ki_flags) -#define kiocbSetKicked(iocb) set_bit(KIF_KICKED, &(iocb)->ki_flags) -#define kiocbSetCancelled(iocb) set_bit(KIF_CANCELLED, &(iocb)->ki_flags) +typedef int (kiocb_cancel_fn)(struct kiocb *, struct io_event *); -#define kiocbClearLocked(iocb) clear_bit(KIF_LOCKED, &(iocb)->ki_flags) -#define kiocbClearKicked(iocb) clear_bit(KIF_KICKED, &(iocb)->ki_flags) -#define kiocbClearCancelled(iocb) clear_bit(KIF_CANCELLED, &(iocb)->ki_flags) - -#define kiocbIsLocked(iocb) test_bit(KIF_LOCKED, &(iocb)->ki_flags) -#define kiocbIsKicked(iocb) test_bit(KIF_KICKED, &(iocb)->ki_flags) -#define kiocbIsCancelled(iocb) test_bit(KIF_CANCELLED, &(iocb)->ki_flags) - -/* is there a better place to document function pointer methods? */ -/** - * ki_retry - iocb forward progress callback - * @kiocb: The kiocb struct to advance by performing an operation. - * - * This callback is called when the AIO core wants a given AIO operation - * to make forward progress. The kiocb argument describes the operation - * that is to be performed. As the operation proceeds, perhaps partially, - * ki_retry is expected to update the kiocb with progress made. Typically - * ki_retry is set in the AIO core and it itself calls file_operations - * helpers. - * - * ki_retry's return value determines when the AIO operation is completed - * and an event is generated in the AIO event ring. Except the special - * return values described below, the value that is returned from ki_retry - * is transferred directly into the completion ring as the operation's - * resulting status. Once this has happened ki_retry *MUST NOT* reference - * the kiocb pointer again. - * - * If ki_retry returns -EIOCBQUEUED it has made a promise that aio_complete() - * will be called on the kiocb pointer in the future. The AIO core will - * not ask the method again -- ki_retry must ensure forward progress. - * aio_complete() must be called once and only once in the future, multiple - * calls may result in undefined behaviour. - * - * If ki_retry returns -EIOCBRETRY it has made a promise that kick_iocb() - * will be called on the kiocb pointer in the future. This may happen - * through generic helpers that associate kiocb->ki_wait with a wait - * queue head that ki_retry uses via current->io_wait. It can also happen - * with custom tracking and manual calls to kick_iocb(), though that is - * discouraged. In either case, kick_iocb() must be called once and only - * once. ki_retry must ensure forward progress, the AIO core will wait - * indefinitely for kick_iocb() to be called. - */ struct kiocb { - struct list_head ki_run_list; - unsigned long ki_flags; - int ki_users; - unsigned ki_key; /* id of this request */ + struct rb_node ki_node; + + atomic_t ki_users; struct file *ki_filp; - struct kioctx *ki_ctx; /* may be NULL for sync ops */ - int (*ki_cancel)(struct kiocb *, struct io_event *); - ssize_t (*ki_retry)(struct kiocb *); + struct kioctx *ki_ctx; /* NULL for sync ops */ + kiocb_cancel_fn *ki_cancel; void (*ki_dtor)(struct kiocb *); union { @@ -102,6 +46,9 @@ struct kiocb { } ki_obj; __u64 ki_user_data; /* user's data for completion */ + long ki_res; + long ki_res2; + loff_t ki_pos; void *private; @@ -117,7 +64,6 @@ struct kiocb { struct list_head ki_list; /* the aio core uses this * for cancellation */ - struct list_head ki_batch; /* batch allocation */ /* * If the aio_resfd field of the userspace iocb is not zero, @@ -128,108 +74,55 @@ struct kiocb { static inline bool is_sync_kiocb(struct kiocb *kiocb) { - return kiocb->ki_key == KIOCB_SYNC_KEY; + return kiocb->ki_ctx == NULL; } static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) { *kiocb = (struct kiocb) { - .ki_users = 1, - .ki_key = KIOCB_SYNC_KEY, + .ki_users = ATOMIC_INIT(1), + .ki_ctx = NULL, .ki_filp = filp, .ki_obj.tsk = current, }; } -#define AIO_RING_MAGIC 0xa10a10a1 -#define AIO_RING_COMPAT_FEATURES 1 -#define AIO_RING_INCOMPAT_FEATURES 0 -struct aio_ring { - unsigned id; /* kernel internal index number */ - unsigned nr; /* number of io_events */ - unsigned head; - unsigned tail; - - unsigned magic; - unsigned compat_features; - unsigned incompat_features; - unsigned header_length; /* size of aio_ring */ - - - struct io_event io_events[0]; -}; /* 128 bytes + ring size */ - -#define AIO_RING_PAGES 8 -struct aio_ring_info { - unsigned long mmap_base; - unsigned long mmap_size; - - struct page **ring_pages; - spinlock_t ring_lock; - long nr_pages; - - unsigned nr, tail; - - struct page *internal_pages[AIO_RING_PAGES]; -}; - -static inline unsigned aio_ring_avail(struct aio_ring_info *info, - struct aio_ring *ring) -{ - return (ring->head + info->nr - 1 - ring->tail) % info->nr; -} - -struct kioctx { - atomic_t users; - int dead; - struct mm_struct *mm; - - /* This needs improving */ - unsigned long user_id; - struct hlist_node list; - - wait_queue_head_t wait; - - spinlock_t ctx_lock; - - int reqs_active; - struct list_head active_reqs; /* used for cancellation */ - struct list_head run_list; /* used for kicked reqs */ - - /* sys_io_setup currently limits this to an unsigned int */ - unsigned max_reqs; - - struct aio_ring_info ring_info; - - struct delayed_work wq; - - struct rcu_head rcu_head; -}; - /* prototypes */ -extern unsigned aio_max_size; - #ifdef CONFIG_AIO extern ssize_t wait_on_sync_kiocb(struct kiocb *iocb); -extern int aio_put_req(struct kiocb *iocb); -extern void kick_iocb(struct kiocb *iocb); -extern int aio_complete(struct kiocb *iocb, long res, long res2); +extern void aio_put_req(struct kiocb *iocb); +extern void batch_complete_aio(struct batch_complete *batch); +extern void aio_complete_batch(struct kiocb *iocb, long res, long res2, + struct batch_complete *batch); struct mm_struct; extern void exit_aio(struct mm_struct *mm); extern long do_io_submit(aio_context_t ctx_id, long nr, struct iocb __user *__user *iocbpp, bool compat); +void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel); #else static inline ssize_t wait_on_sync_kiocb(struct kiocb *iocb) { return 0; } -static inline int aio_put_req(struct kiocb *iocb) { return 0; } -static inline void kick_iocb(struct kiocb *iocb) { } -static inline int aio_complete(struct kiocb *iocb, long res, long res2) { return 0; } +static inline void aio_put_req(struct kiocb *iocb) { } + +static inline void batch_complete_aio(struct batch_complete *batch) { } +static inline void aio_complete_batch(struct kiocb *iocb, long res, long res2, + struct batch_complete *batch) +{ + return; +} struct mm_struct; static inline void exit_aio(struct mm_struct *mm) { } static inline long do_io_submit(aio_context_t ctx_id, long nr, struct iocb __user * __user *iocbpp, bool compat) { return 0; } +static inline void kiocb_set_cancel_fn(struct kiocb *req, + kiocb_cancel_fn *cancel) { } #endif /* CONFIG_AIO */ +static inline void aio_complete(struct kiocb *iocb, long res, long res2) +{ + aio_complete_batch(iocb, res, res2, NULL); +} + static inline struct kiocb *list_kiocb(struct list_head *h) { return list_entry(h, struct kiocb, ki_list); diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 12731a19ef06..350459910fe1 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -254,6 +254,7 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); #define BDI_CAP_EXEC_MAP 0x00000040 #define BDI_CAP_NO_ACCT_WB 0x00000080 #define BDI_CAP_SWAP_BACKED 0x00000100 +#define BDI_CAP_STABLE_WRITES 0x00000200 #define BDI_CAP_VMFLAGS \ (BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP) @@ -308,6 +309,11 @@ long wait_iff_congested(struct zone *zone, int sync, long timeout); int pdflush_proc_obsolete(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); +static inline bool bdi_cap_stable_pages_required(struct backing_dev_info *bdi) +{ + return bdi->capabilities & BDI_CAP_STABLE_WRITES; +} + static inline bool bdi_cap_writeback_dirty(struct backing_dev_info *bdi) { return !(bdi->capabilities & BDI_CAP_NO_WRITEBACK); diff --git a/include/linux/balloon_compaction.h b/include/linux/balloon_compaction.h index f7f1d7169b11..6fd5cc80f62f 100644 --- a/include/linux/balloon_compaction.h +++ b/include/linux/balloon_compaction.h @@ -213,8 +213,15 @@ static inline bool balloon_compaction_check(void) return true; } +static inline void balloon_event_count(enum vm_event_item item) +{ + count_vm_event(item); +} #else /* !CONFIG_BALLOON_COMPACTION */ +/* A macro, to avoid generating references to the undefined COMPACTBALLOON* */ +#define balloon_event_count(item) do { } while (0) + static inline void *balloon_mapping_alloc(void *balloon_device, const struct address_space_operations *a_ops) { diff --git a/include/linux/batch_complete.h b/include/linux/batch_complete.h new file mode 100644 index 000000000000..8167a9d306fb --- /dev/null +++ b/include/linux/batch_complete.h @@ -0,0 +1,23 @@ +#ifndef _LINUX_BATCH_COMPLETE_H +#define _LINUX_BATCH_COMPLETE_H + +#include <linux/rbtree.h> + +/* + * Common stuff to the aio and block code for batch completion. Everything + * important is elsewhere: + */ + +struct bio; + +struct bio_list { + struct bio *head; + struct bio *tail; +}; + +struct batch_complete { + struct bio_list bio; + struct rb_root kiocb; +}; + +#endif diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 0530b9860359..c3a09149f793 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -111,7 +111,6 @@ extern int suid_dumpable; extern int setup_arg_pages(struct linux_binprm * bprm, unsigned long stack_top, int executable_stack); -extern int bprm_mm_init(struct linux_binprm *bprm); extern int bprm_change_interp(char *interp, struct linux_binprm *bprm); extern int copy_strings_kernel(int argc, const char *const *argv, struct linux_binprm *bprm); diff --git a/include/linux/bio.h b/include/linux/bio.h index 820e7aaad4fd..5f549176745c 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -24,6 +24,7 @@ #include <linux/mempool.h> #include <linux/ioprio.h> #include <linux/bug.h> +#include <linux/batch_complete.h> #ifdef CONFIG_BLOCK @@ -68,6 +69,8 @@ #define bio_segments(bio) ((bio)->bi_vcnt - (bio)->bi_idx) #define bio_sectors(bio) ((bio)->bi_size >> 9) +void bio_endio_batch(struct bio *bio, int error, struct batch_complete *batch); + static inline unsigned int bio_cur_bytes(struct bio *bio) { if (bio->bi_vcnt) @@ -241,7 +244,25 @@ static inline struct bio *bio_clone_kmalloc(struct bio *bio, gfp_t gfp_mask) } -extern void bio_endio(struct bio *, int); +/** + * bio_endio - end I/O on a bio + * @bio: bio + * @error: error, if any + * + * Description: + * bio_endio() will end I/O on the whole bio. bio_endio() is the + * preferred way to end I/O on a bio, it takes care of clearing + * BIO_UPTODATE on error. @error is 0 on success, and and one of the + * established -Exxxx (-EIO, for instance) error values in case + * something went wrong. No one should call bi_end_io() directly on a + * bio unless they own it and thus know that it has an end_io + * function. + **/ +static inline void bio_endio(struct bio *bio, int error) +{ + bio_endio_batch(bio, error, NULL); +} + struct request_queue; extern int bio_phys_segments(struct request_queue *, struct bio *); @@ -420,10 +441,6 @@ static inline bool bio_mergeable(struct bio *bio) * member of the bio. The bio_list also caches the last list member to allow * fast access to the tail. */ -struct bio_list { - struct bio *head; - struct bio *tail; -}; static inline int bio_list_empty(const struct bio_list *bl) { @@ -527,6 +544,15 @@ static inline struct bio *bio_list_get(struct bio_list *bl) return bio; } +static inline void batch_complete_init(struct batch_complete *batch) +{ + bio_list_init(&batch->bio); + batch->kiocb = RB_ROOT; +} + +void batch_complete(struct batch_complete *batch); + + #if defined(CONFIG_BLK_DEV_INTEGRITY) #define bip_vec_idx(bip, idx) (&(bip->bip_vec[(idx)])) diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index cdf11191e645..d4e7bab9a17e 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -16,7 +16,9 @@ struct page; struct block_device; struct io_context; struct cgroup_subsys_state; +struct batch_complete; typedef void (bio_end_io_t) (struct bio *, int); +typedef void (bio_batch_end_io_t) (struct bio *, int, struct batch_complete *); typedef void (bio_destructor_t) (struct bio *); /* @@ -42,6 +44,7 @@ struct bio { * top bits priority */ + short bi_error; unsigned short bi_vcnt; /* how many bio_vec's */ unsigned short bi_idx; /* current index into bvl_vec */ @@ -59,7 +62,10 @@ struct bio { unsigned int bi_seg_front_size; unsigned int bi_seg_back_size; - bio_end_io_t *bi_end_io; + union { + bio_end_io_t *bi_end_io; + bio_batch_end_io_t *bi_batch_end_io; + }; void *bi_private; #ifdef CONFIG_BLK_CGROUP @@ -111,12 +117,13 @@ struct bio { #define BIO_FS_INTEGRITY 9 /* fs owns integrity data, not block layer */ #define BIO_QUIET 10 /* Make BIO Quiet */ #define BIO_MAPPED_INTEGRITY 11/* integrity metadata has been remapped */ +#define BIO_BATCH_ENDIO 12 /* * Flags starting here get preserved by bio_reset() - this includes * BIO_POOL_IDX() */ -#define BIO_RESET_BITS 12 +#define BIO_RESET_BITS 13 #define bio_flagged(bio, flag) ((bio)->bi_flags & (1 << (flag))) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 78feda9bbae2..2f91edb6e2d3 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -877,7 +877,8 @@ extern struct request *blk_fetch_request(struct request_queue *q); * This prevents code duplication in drivers. */ extern bool blk_update_request(struct request *rq, int error, - unsigned int nr_bytes); + unsigned int nr_bytes, + struct batch_complete *batch); extern bool blk_end_request(struct request *rq, int error, unsigned int nr_bytes); extern void blk_end_request_all(struct request *rq, int error); @@ -885,10 +886,17 @@ extern bool blk_end_request_cur(struct request *rq, int error); extern bool blk_end_request_err(struct request *rq, int error); extern bool __blk_end_request(struct request *rq, int error, unsigned int nr_bytes); -extern void __blk_end_request_all(struct request *rq, int error); extern bool __blk_end_request_cur(struct request *rq, int error); extern bool __blk_end_request_err(struct request *rq, int error); +extern void blk_end_request_all_batch(struct request *rq, int error, + struct batch_complete *batch); + +static inline void __blk_end_request_all(struct request *rq, int error) +{ + blk_end_request_all_batch(rq, error, NULL); +} + extern void blk_complete_request(struct request *); extern void __blk_complete_request(struct request *); extern void blk_abort_request(struct request *); diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 3cd16ba82f15..cdc3bab01832 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -53,6 +53,7 @@ extern void free_bootmem_node(pg_data_t *pgdat, unsigned long size); extern void free_bootmem(unsigned long physaddr, unsigned long size); extern void free_bootmem_late(unsigned long physaddr, unsigned long size); +extern void __free_pages_bootmem(struct page *page, unsigned int order); /* * Flags for reserve_bootmem (also if CONFIG_HAVE_ARCH_BOOTMEM_NODE, diff --git a/include/linux/bug.h b/include/linux/bug.h index b1cf40de847e..7f4818673c41 100644 --- a/include/linux/bug.h +++ b/include/linux/bug.h @@ -2,6 +2,7 @@ #define _LINUX_BUG_H #include <asm/bug.h> +#include <linux/compiler.h> enum bug_trap_type { BUG_TRAP_TYPE_NONE = 0, @@ -12,11 +13,12 @@ enum bug_trap_type { struct pt_regs; #ifdef __CHECKER__ -#define BUILD_BUG_ON_NOT_POWER_OF_2(n) +#define BUILD_BUG_ON_NOT_POWER_OF_2(n) (0) #define BUILD_BUG_ON_ZERO(e) (0) #define BUILD_BUG_ON_NULL(e) ((void*)0) #define BUILD_BUG_ON_INVALID(e) (0) -#define BUILD_BUG_ON(condition) +#define BUILD_BUG_ON_MSG(cond, msg) (0) +#define BUILD_BUG_ON(condition) (0) #define BUILD_BUG() (0) #else /* __CHECKER__ */ @@ -39,29 +41,37 @@ struct pt_regs; #define BUILD_BUG_ON_INVALID(e) ((void)(sizeof((__force long)(e)))) /** + * BUILD_BUG_ON_MSG - break compile if a condition is true & emit supplied + * error message. + * @condition: the condition which the compiler should know is false. + * + * See BUILD_BUG_ON for description. + */ +#define BUILD_BUG_ON_MSG(cond, msg) compiletime_assert(!(cond), msg) + +/** * BUILD_BUG_ON - break compile if a condition is true. * @condition: the condition which the compiler should know is false. * * If you have some code which relies on certain constants being equal, or - * other compile-time-evaluated condition, you should use BUILD_BUG_ON to + * some other compile-time-evaluated condition, you should use BUILD_BUG_ON to * detect if someone changes it. * - * The implementation uses gcc's reluctance to create a negative array, but - * gcc (as of 4.4) only emits that error for obvious cases (eg. not arguments - * to inline functions). So as a fallback we use the optimizer; if it can't - * prove the condition is false, it will cause a link error on the undefined - * "__build_bug_on_failed". This error message can be harder to track down - * though, hence the two different methods. + * The implementation uses gcc's reluctance to create a negative array, but gcc + * (as of 4.4) only emits that error for obvious cases (e.g. not arguments to + * inline functions). Luckily, in 4.3 they added the "error" function + * attribute just for this type of case. Thus, we use a negative sized array + * (should always create an error on gcc versions older than 4.4) and then call + * an undefined function with the error attribute (should always create an + * error on gcc 4.3 and later). If for some reason, neither creates a + * compile-time error, we'll still have a link-time error, which is harder to + * track down. */ #ifndef __OPTIMIZE__ #define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)])) #else -extern int __build_bug_on_failed; -#define BUILD_BUG_ON(condition) \ - do { \ - ((void)sizeof(char[1 - 2*!!(condition)])); \ - if (condition) __build_bug_on_failed = 1; \ - } while(0) +#define BUILD_BUG_ON(condition) \ + BUILD_BUG_ON_MSG(condition, "BUILD_BUG_ON failed: " #condition) #endif /** @@ -71,12 +81,7 @@ extern int __build_bug_on_failed; * build time, you should use BUILD_BUG to detect if it is * unexpectedly used. */ -#define BUILD_BUG() \ - do { \ - extern void __build_bug_failed(void) \ - __linktime_error("BUILD_BUG failed"); \ - __build_bug_failed(); \ - } while (0) +#define BUILD_BUG() BUILD_BUG_ON_MSG(1, "BUILD_BUG failed") #endif /* __CHECKER__ */ diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 900af5964f55..906e5c59be3c 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -27,6 +27,7 @@ struct cgroup_subsys; struct inode; struct cgroup; struct css_id; +struct eventfd_ctx; extern int cgroup_init_early(void); extern int cgroup_init(void); diff --git a/include/linux/compaction.h b/include/linux/compaction.h index cc7bddeaf553..091d72e70d8a 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -23,7 +23,7 @@ extern int fragmentation_index(struct zone *zone, unsigned int order); extern unsigned long try_to_compact_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask, bool sync, bool *contended); -extern int compact_pgdat(pg_data_t *pgdat, int order); +extern void compact_pgdat(pg_data_t *pgdat, int order); extern void reset_isolation_suitable(pg_data_t *pgdat); extern unsigned long compaction_suitable(struct zone *zone, int order); @@ -80,9 +80,8 @@ static inline unsigned long try_to_compact_pages(struct zonelist *zonelist, return COMPACT_CONTINUE; } -static inline int compact_pgdat(pg_data_t *pgdat, int order) +static inline void compact_pgdat(pg_data_t *pgdat, int order) { - return COMPACT_CONTINUE; } static inline void reset_isolation_suitable(pg_data_t *pgdat) diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 6a6d7aefe12d..24545cd90a25 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -5,6 +5,9 @@ /* * Common definitions for all gcc versions go here. */ +#define GCC_VERSION (__GNUC__ * 10000 \ + + __GNUC_MINOR__ * 100 \ + + __GNUC_PATCHLEVEL__) /* Optimization barrier */ diff --git a/include/linux/compiler-gcc3.h b/include/linux/compiler-gcc3.h index 37d412436d0f..7d89febe4d79 100644 --- a/include/linux/compiler-gcc3.h +++ b/include/linux/compiler-gcc3.h @@ -2,22 +2,22 @@ #error "Please don't include <linux/compiler-gcc3.h> directly, include <linux/compiler.h> instead." #endif -#if __GNUC_MINOR__ < 2 +#if GCC_VERSION < 30200 # error Sorry, your compiler is too old - please upgrade it. #endif -#if __GNUC_MINOR__ >= 3 +#if GCC_VERSION >= 30300 # define __used __attribute__((__used__)) #else # define __used __attribute__((__unused__)) #endif -#if __GNUC_MINOR__ >= 4 +#if GCC_VERSION >= 30400 #define __must_check __attribute__((warn_unused_result)) #endif #ifdef CONFIG_GCOV_KERNEL -# if __GNUC_MINOR__ < 4 +# if GCC_VERSION < 30400 # error "GCOV profiling support for gcc versions below 3.4 not included" # endif /* __GNUC_MINOR__ */ #endif /* CONFIG_GCOV_KERNEL */ diff --git a/include/linux/compiler-gcc4.h b/include/linux/compiler-gcc4.h index 662fd1b4c42a..68b162d92254 100644 --- a/include/linux/compiler-gcc4.h +++ b/include/linux/compiler-gcc4.h @@ -4,7 +4,7 @@ /* GCC 4.1.[01] miscompiles __weak */ #ifdef __KERNEL__ -# if __GNUC_MINOR__ == 1 && __GNUC_PATCHLEVEL__ <= 1 +# if GCC_VERSION >= 40100 && GCC_VERSION <= 40101 # error Your version of gcc miscompiles the __weak directive # endif #endif @@ -13,7 +13,11 @@ #define __must_check __attribute__((warn_unused_result)) #define __compiler_offsetof(a,b) __builtin_offsetof(a,b) -#if __GNUC_MINOR__ >= 3 +#if GCC_VERSION >= 40100 +# define __compiletime_object_size(obj) __builtin_object_size(obj, 0) +#endif + +#if GCC_VERSION >= 40300 /* Mark functions as cold. gcc will assume any path leading to a call to them will be unlikely. This means a lot of manual unlikely()s are unnecessary now for any paths leading to the usual suspects @@ -29,11 +33,15 @@ the kernel context */ #define __cold __attribute__((__cold__)) -#define __linktime_error(message) __attribute__((__error__(message))) - #define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) -#if __GNUC_MINOR__ >= 5 +#ifndef __CHECKER__ +# define __compiletime_warning(message) __attribute__((warning(message))) +# define __compiletime_error(message) __attribute__((error(message))) +#endif /* __CHECKER__ */ +#endif /* GCC_VERSION >= 40300 */ + +#if GCC_VERSION >= 40500 /* * Mark a position in code as unreachable. This can be used to * suppress control flow warnings after asm blocks that transfer @@ -48,30 +56,22 @@ /* Mark a function definition as prohibited from being cloned. */ #define __noclone __attribute__((__noclone__)) -#endif -#endif +#endif /* GCC_VERSION >= 40500 */ -#if __GNUC_MINOR__ >= 6 +#if GCC_VERSION >= 40600 /* * Tell the optimizer that something else uses this function or variable. */ #define __visible __attribute__((externally_visible)) #endif -#if __GNUC_MINOR__ > 0 -#define __compiletime_object_size(obj) __builtin_object_size(obj, 0) -#endif -#if __GNUC_MINOR__ >= 3 && !defined(__CHECKER__) -#define __compiletime_warning(message) __attribute__((warning(message))) -#define __compiletime_error(message) __attribute__((error(message))) -#endif #ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP -#if __GNUC_MINOR__ >= 4 +#if GCC_VERSION >= 40400 #define __HAVE_BUILTIN_BSWAP32__ #define __HAVE_BUILTIN_BSWAP64__ #endif -#if __GNUC_MINOR__ >= 8 || (defined(__powerpc__) && __GNUC_MINOR__ >= 6) +#if GCC_VERSION >= 40800 || (defined(__powerpc__) && GCC_VERSION >= 40600) #define __HAVE_BUILTIN_BSWAP16__ #endif -#endif +#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */ diff --git a/include/linux/compiler.h b/include/linux/compiler.h index dd852b73b286..10b8f23fab0f 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -307,10 +307,36 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); #endif #ifndef __compiletime_error # define __compiletime_error(message) +# define __compiletime_error_fallback(condition) \ + do { ((void)sizeof(char[1 - 2 * condition])); } while (0) +#else +# define __compiletime_error_fallback(condition) do { } while (0) #endif -#ifndef __linktime_error -# define __linktime_error(message) -#endif + +#define __compiletime_assert(condition, msg, prefix, suffix) \ + do { \ + bool __cond = !(condition); \ + extern void prefix ## suffix(void) __compiletime_error(msg); \ + if (__cond) \ + prefix ## suffix(); \ + __compiletime_error_fallback(__cond); \ + } while (0) + +#define _compiletime_assert(condition, msg, prefix, suffix) \ + __compiletime_assert(condition, msg, prefix, suffix) + +/** + * compiletime_assert - break build and emit msg if condition is false + * @condition: a compile-time constant condition to check + * @msg: a message to emit if condition is false + * + * In tradition of POSIX assert, this macro will break the build if the + * supplied condition is *false*, emitting the supplied error message if the + * compiler has support to do so. + */ +#define compiletime_assert(condition, msg) \ + _compiletime_assert(condition, msg, __compiletime_assert_, __LINE__) + /* * Prevent the compiler from merging or refetching accesses. The compiler * is also forbidden from reordering successive instances of ACCESS_ONCE(), diff --git a/include/linux/errno.h b/include/linux/errno.h index f6bf082d4d4f..89627b9187f9 100644 --- a/include/linux/errno.h +++ b/include/linux/errno.h @@ -28,6 +28,5 @@ #define EBADTYPE 527 /* Type not supported by server */ #define EJUKEBOX 528 /* Request initiated, but will not complete before timeout */ #define EIOCBQUEUED 529 /* iocb queued, will get completion event */ -#define EIOCBRETRY 530 /* iocb queued, will trigger a retry */ #endif diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h index 3c3ef19a625a..cf5d2af61b81 100644 --- a/include/linux/eventfd.h +++ b/include/linux/eventfd.h @@ -13,7 +13,7 @@ #include <linux/wait.h> /* - * CAREFUL: Check include/asm-generic/fcntl.h when defining + * CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining * new flags, since they might collide with O_* ones. We want * to re-use O_* flags that couldn't possibly have a meaning * from eventfd, in order to leave a free define-space for diff --git a/include/linux/firmware-map.h b/include/linux/firmware-map.h index 43fe52fcef0f..71d4fa721db9 100644 --- a/include/linux/firmware-map.h +++ b/include/linux/firmware-map.h @@ -25,6 +25,7 @@ int firmware_map_add_early(u64 start, u64 end, const char *type); int firmware_map_add_hotplug(u64 start, u64 end, const char *type); +int firmware_map_remove(u64 start, u64 end, const char *type); #else /* CONFIG_FIRMWARE_MEMMAP */ @@ -38,6 +39,11 @@ static inline int firmware_map_add_hotplug(u64 start, u64 end, const char *type) return 0; } +static inline int firmware_map_remove(u64 start, u64 end, const char *type) +{ + return 0; +} + #endif /* CONFIG_FIRMWARE_MEMMAP */ #endif /* _LINUX_FIRMWARE_MAP_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 7d2e893ec3d1..7e36028df720 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -675,9 +675,11 @@ static inline loff_t i_size_read(const struct inode *inode) static inline void i_size_write(struct inode *inode, loff_t i_size) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) + preempt_disable(); write_seqcount_begin(&inode->i_size_seqcount); inode->i_size = i_size; write_seqcount_end(&inode->i_size_seqcount); + preempt_enable(); #elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT) preempt_disable(); inode->i_size = i_size; diff --git a/include/linux/hashtable.h b/include/linux/hashtable.h index 227c62424f3c..ce316adcd2bb 100644 --- a/include/linux/hashtable.h +++ b/include/linux/hashtable.h @@ -115,51 +115,47 @@ static inline void hash_del_rcu(struct hlist_node *node) * hash_for_each - iterate over a hashtable * @name: hashtable to iterate * @bkt: integer to use as bucket loop cursor - * @node: the &struct list_head to use as a loop cursor for each entry * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct */ -#define hash_for_each(name, bkt, node, obj, member) \ - for ((bkt) = 0, node = NULL; node == NULL && (bkt) < HASH_SIZE(name); (bkt)++)\ - hlist_for_each_entry(obj, node, &name[bkt], member) +#define hash_for_each(name, bkt, obj, member) \ + for ((bkt) = 0, obj = NULL; obj == NULL && (bkt) < HASH_SIZE(name); (bkt)++)\ + hlist_for_each_entry(obj, &name[bkt], member) /** * hash_for_each_rcu - iterate over a rcu enabled hashtable * @name: hashtable to iterate * @bkt: integer to use as bucket loop cursor - * @node: the &struct list_head to use as a loop cursor for each entry * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct */ -#define hash_for_each_rcu(name, bkt, node, obj, member) \ - for ((bkt) = 0, node = NULL; node == NULL && (bkt) < HASH_SIZE(name); (bkt)++)\ - hlist_for_each_entry_rcu(obj, node, &name[bkt], member) +#define hash_for_each_rcu(name, bkt, obj, member) \ + for ((bkt) = 0, obj = NULL; obj == NULL && (bkt) < HASH_SIZE(name); (bkt)++)\ + hlist_for_each_entry_rcu(obj, &name[bkt], member) /** * hash_for_each_safe - iterate over a hashtable safe against removal of * hash entry * @name: hashtable to iterate * @bkt: integer to use as bucket loop cursor - * @node: the &struct list_head to use as a loop cursor for each entry * @tmp: a &struct used for temporary storage * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct */ -#define hash_for_each_safe(name, bkt, node, tmp, obj, member) \ - for ((bkt) = 0, node = NULL; node == NULL && (bkt) < HASH_SIZE(name); (bkt)++)\ - hlist_for_each_entry_safe(obj, node, tmp, &name[bkt], member) +#define hash_for_each_safe(name, bkt, tmp, obj, member) \ + for ((bkt) = 0, obj = NULL; obj == NULL && (bkt) < HASH_SIZE(name); (bkt)++)\ + hlist_for_each_entry_safe(obj, tmp, &name[bkt], member) /** * hash_for_each_possible - iterate over all possible objects hashing to the * same bucket * @name: hashtable to iterate * @obj: the type * to use as a loop cursor for each entry - * @node: the &struct list_head to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct * @key: the key of the objects to iterate over */ -#define hash_for_each_possible(name, obj, node, member, key) \ - hlist_for_each_entry(obj, node, &name[hash_min(key, HASH_BITS(name))], member) +#define hash_for_each_possible(name, obj, member, key) \ + hlist_for_each_entry(obj, &name[hash_min(key, HASH_BITS(name))], member) /** * hash_for_each_possible_rcu - iterate over all possible objects hashing to the @@ -167,26 +163,23 @@ static inline void hash_del_rcu(struct hlist_node *node) * in a rcu enabled hashtable * @name: hashtable to iterate * @obj: the type * to use as a loop cursor for each entry - * @node: the &struct list_head to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct * @key: the key of the objects to iterate over */ -#define hash_for_each_possible_rcu(name, obj, node, member, key) \ - hlist_for_each_entry_rcu(obj, node, &name[hash_min(key, HASH_BITS(name))], member) +#define hash_for_each_possible_rcu(name, obj, member, key) \ + hlist_for_each_entry_rcu(obj, &name[hash_min(key, HASH_BITS(name))], member) /** * hash_for_each_possible_safe - iterate over all possible objects hashing to the * same bucket safe against removals * @name: hashtable to iterate * @obj: the type * to use as a loop cursor for each entry - * @node: the &struct list_head to use as a loop cursor for each entry * @tmp: a &struct used for temporary storage * @member: the name of the hlist_node within the struct * @key: the key of the objects to iterate over */ -#define hash_for_each_possible_safe(name, obj, node, tmp, member, key) \ - hlist_for_each_entry_safe(obj, node, tmp, \ - &name[hash_min(key, HASH_BITS(name))], member) +#define hash_for_each_possible_safe(name, obj, tmp, member, key) \ + hlist_for_each_entry_safe(obj, tmp, &name[hash_min(key, HASH_BITS(name))], member) #endif diff --git a/include/linux/highmem.h b/include/linux/highmem.h index ef788b5b4a35..7fb31da45d03 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -219,12 +219,6 @@ static inline void zero_user(struct page *page, zero_user_segments(page, start, start + size, 0, 0); } -static inline void __deprecated memclear_highpage_flush(struct page *page, - unsigned int offset, unsigned int size) -{ - zero_user(page, offset, size); -} - #ifndef __HAVE_ARCH_COPY_USER_HIGHPAGE static inline void copy_user_highpage(struct page *to, struct page *from, diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 1d76f8ca90f0..ee1c244a62a1 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -113,7 +113,7 @@ extern void __split_huge_page_pmd(struct vm_area_struct *vma, do { \ pmd_t *____pmd = (__pmd); \ anon_vma_lock_write(__anon_vma); \ - anon_vma_unlock(__anon_vma); \ + anon_vma_unlock_write(__anon_vma); \ BUG_ON(pmd_trans_splitting(*____pmd) || \ pmd_trans_huge(*____pmd)); \ } while (0) diff --git a/include/linux/idr.h b/include/linux/idr.h index de7e190f1af4..8d3ffe130d0c 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -49,37 +49,27 @@ #define MAX_IDR_FREE (MAX_IDR_LEVEL * 2) struct idr_layer { - unsigned long bitmap; /* A zero bit means "space here" */ + unsigned long bitmap; /* A zero bit means "space here" */ struct idr_layer __rcu *ary[1<<IDR_BITS]; - int count; /* When zero, we can release it */ - int layer; /* distance from leaf */ - struct rcu_head rcu_head; + int count; /* When zero, we can release it */ + int layer; /* distance from leaf */ + struct rcu_head rcu_head; }; struct idr { - struct idr_layer __rcu *top; - struct idr_layer *id_free; - int layers; /* only valid without concurrent changes */ - int id_free_cnt; - spinlock_t lock; + struct idr_layer __rcu *top; + struct idr_layer *id_free; + int layers; /* only valid w/o concurrent changes */ + int id_free_cnt; + spinlock_t lock; }; -#define IDR_INIT(name) \ -{ \ - .top = NULL, \ - .id_free = NULL, \ - .layers = 0, \ - .id_free_cnt = 0, \ - .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ +#define IDR_INIT(name) \ +{ \ + .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ } #define DEFINE_IDR(name) struct idr name = IDR_INIT(name) -/* Actions to be taken after a call to _idr_sub_alloc */ -#define IDR_NEED_TO_GROW -2 -#define IDR_NOMORE_SPACE -3 - -#define _idr_rc_to_errno(rc) ((rc) == -1 ? -EAGAIN : -ENOSPC) - /** * DOC: idr sync * idr synchronization (stolen from radix-tree.h) @@ -103,17 +93,66 @@ struct idr { void *idr_find(struct idr *idp, int id); int idr_pre_get(struct idr *idp, gfp_t gfp_mask); -int idr_get_new(struct idr *idp, void *ptr, int *id); int idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id); +void idr_preload(gfp_t gfp_mask); +int idr_alloc(struct idr *idp, void *ptr, int start, int end, gfp_t gfp_mask); int idr_for_each(struct idr *idp, int (*fn)(int id, void *p, void *data), void *data); void *idr_get_next(struct idr *idp, int *nextid); void *idr_replace(struct idr *idp, void *ptr, int id); void idr_remove(struct idr *idp, int id); -void idr_remove_all(struct idr *idp); +void idr_free(struct idr *idp, int id); void idr_destroy(struct idr *idp); void idr_init(struct idr *idp); +/** + * idr_preload_end - end preload section started with idr_preload() + * + * Each idr_preload() should be matched with an invocation of this + * function. See idr_preload() for details. + */ +static inline void idr_preload_end(void) +{ + preempt_enable(); +} + +/** + * idr_get_new - allocate new idr entry + * @idp: idr handle + * @ptr: pointer you want associated with the id + * @id: pointer to the allocated handle + * + * Simple wrapper around idr_get_new_above() w/ @starting_id of zero. + */ +static inline int idr_get_new(struct idr *idp, void *ptr, int *id) +{ + return idr_get_new_above(idp, ptr, 0, id); +} + +/** + * idr_for_each_entry - iterate over an idr's elements of a given type + * @idp: idr handle + * @entry: the type * to use as cursor + * @id: id entry's key + */ +#define idr_for_each_entry(idp, entry, id) \ + for (id = 0, entry = (typeof(entry))idr_get_next((idp), &(id)); \ + entry != NULL; \ + ++id, entry = (typeof(entry))idr_get_next((idp), &(id))) + +void __idr_remove_all(struct idr *idp); /* don't use */ + +/** + * idr_remove_all - remove all ids from the given idr tree + * @idp: idr handle + * + * If you're trying to destroy @idp, calling idr_destroy() is enough. + * This is going away. Don't use. + */ +static inline void __deprecated idr_remove_all(struct idr *idp) +{ + __idr_remove_all(idp); +} /* * IDA - IDR based id allocator, use when translation from id to @@ -141,7 +180,6 @@ struct ida { int ida_pre_get(struct ida *ida, gfp_t gfp_mask); int ida_get_new_above(struct ida *ida, int starting_id, int *p_id); -int ida_get_new(struct ida *ida, int *p_id); void ida_remove(struct ida *ida, int id); void ida_destroy(struct ida *ida); void ida_init(struct ida *ida); @@ -150,17 +188,18 @@ int ida_simple_get(struct ida *ida, unsigned int start, unsigned int end, gfp_t gfp_mask); void ida_simple_remove(struct ida *ida, unsigned int id); -void __init idr_init_cache(void); - /** - * idr_for_each_entry - iterate over an idr's elements of a given type - * @idp: idr handle - * @entry: the type * to use as cursor - * @id: id entry's key + * ida_get_new - allocate new ID + * @ida: idr handle + * @p_id: pointer to the allocated handle + * + * Simple wrapper around ida_get_new_above() w/ @starting_id of zero. */ -#define idr_for_each_entry(idp, entry, id) \ - for (id = 0, entry = (typeof(entry))idr_get_next((idp), &(id)); \ - entry != NULL; \ - ++id, entry = (typeof(entry))idr_get_next((idp), &(id))) +static inline int ida_get_new(struct ida *ida, int *p_id) +{ + return ida_get_new_above(ida, 0, p_id); +} + +void __init idr_init_cache(void); #endif /* __IDR_H__ */ diff --git a/include/linux/if_team.h b/include/linux/if_team.h index 4648d8021244..cfd21e3d5506 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -216,11 +216,10 @@ static inline struct hlist_head *team_port_index_hash(struct team *team, static inline struct team_port *team_get_port_by_index(struct team *team, int port_index) { - struct hlist_node *p; struct team_port *port; struct hlist_head *head = team_port_index_hash(team, port_index); - hlist_for_each_entry(port, p, head, hlist) + hlist_for_each_entry(port, head, hlist) if (port->index == port_index) return port; return NULL; @@ -228,11 +227,10 @@ static inline struct team_port *team_get_port_by_index(struct team *team, static inline struct team_port *team_get_port_by_index_rcu(struct team *team, int port_index) { - struct hlist_node *p; struct team_port *port; struct hlist_head *head = team_port_index_hash(team, port_index); - hlist_for_each_entry_rcu(port, p, head, hlist) + hlist_for_each_entry_rcu(port, head, hlist) if (port->index == port_index) return port; return NULL; diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h index 1487e7906bbd..1f9f56e28851 100644 --- a/include/linux/ipmi.h +++ b/include/linux/ipmi.h @@ -35,10 +35,6 @@ #include <uapi/linux/ipmi.h> - -/* - * The in-kernel interface. - */ #include <linux/list.h> #include <linux/proc_fs.h> diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 3319a6967626..45c9b6a17bcb 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -16,9 +16,6 @@ struct stable_node; struct mem_cgroup; -struct page *ksm_does_need_to_copy(struct page *page, - struct vm_area_struct *vma, unsigned long address); - #ifdef CONFIG_KSM int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, unsigned long *vm_flags); @@ -73,15 +70,8 @@ static inline void set_page_stable_node(struct page *page, * We'd like to make this conditional on vma->vm_flags & VM_MERGEABLE, * but what if the vma was unmerged while the page was swapped out? */ -static inline int ksm_might_need_to_copy(struct page *page, - struct vm_area_struct *vma, unsigned long address) -{ - struct anon_vma *anon_vma = page_anon_vma(page); - - return anon_vma && - (anon_vma->root != vma->anon_vma->root || - page->index != linear_page_index(vma, address)); -} +struct page *ksm_might_need_to_copy(struct page *page, + struct vm_area_struct *vma, unsigned long address); int page_referenced_ksm(struct page *page, struct mem_cgroup *memcg, unsigned long *vm_flags); @@ -113,10 +103,10 @@ static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start, return 0; } -static inline int ksm_might_need_to_copy(struct page *page, +static inline struct page *ksm_might_need_to_copy(struct page *page, struct vm_area_struct *vma, unsigned long address) { - return 0; + return page; } static inline int page_referenced_ksm(struct page *page, diff --git a/include/linux/list.h b/include/linux/list.h index cc6d2aa6b415..433f8865d989 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -666,54 +666,49 @@ static inline void hlist_move_list(struct hlist_head *old, for (pos = (head)->first; pos && ({ n = pos->next; 1; }); \ pos = n) +#define hlist_entry_safe(ptr, type, member) \ + (ptr) ? hlist_entry(ptr, type, member) : NULL + /** * hlist_for_each_entry - iterate over list of given type - * @tpos: the type * to use as a loop cursor. - * @pos: the &struct hlist_node to use as a loop cursor. + * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. */ -#define hlist_for_each_entry(tpos, pos, head, member) \ - for (pos = (head)->first; \ - pos && \ - ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \ - pos = pos->next) +#define hlist_for_each_entry(pos, head, member) \ + for (pos = hlist_entry_safe((head)->first, typeof(*(pos)), member); \ + pos; \ + pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) /** * hlist_for_each_entry_continue - iterate over a hlist continuing after current point - * @tpos: the type * to use as a loop cursor. - * @pos: the &struct hlist_node to use as a loop cursor. + * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ -#define hlist_for_each_entry_continue(tpos, pos, member) \ - for (pos = (pos)->next; \ - pos && \ - ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \ - pos = pos->next) +#define hlist_for_each_entry_continue(pos, member) \ + for (pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member);\ + pos; \ + pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) /** * hlist_for_each_entry_from - iterate over a hlist continuing from current point - * @tpos: the type * to use as a loop cursor. - * @pos: the &struct hlist_node to use as a loop cursor. + * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ -#define hlist_for_each_entry_from(tpos, pos, member) \ - for (; pos && \ - ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \ - pos = pos->next) +#define hlist_for_each_entry_from(pos, member) \ + for (; pos; \ + pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) /** * hlist_for_each_entry_safe - iterate over list of given type safe against removal of list entry - * @tpos: the type * to use as a loop cursor. - * @pos: the &struct hlist_node to use as a loop cursor. + * @pos: the type * to use as a loop cursor. * @n: another &struct hlist_node to use as temporary storage * @head: the head for your list. * @member: the name of the hlist_node within the struct. */ -#define hlist_for_each_entry_safe(tpos, pos, n, head, member) \ - for (pos = (head)->first; \ - pos && ({ n = pos->next; 1; }) && \ - ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \ - pos = n) +#define hlist_for_each_entry_safe(pos, n, head, member) \ + for (pos = hlist_entry_safe((head)->first, typeof(*pos), member); \ + pos && ({ n = pos->member.next; 1; }); \ + pos = hlist_entry_safe(n, typeof(*pos), member)) #endif diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index f05631effc73..f1e877b79ed8 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -359,7 +359,9 @@ extern void lockdep_trace_alloc(gfp_t mask); #define lockdep_depth(tsk) (debug_locks ? (tsk)->lockdep_depth : 0) -#define lockdep_assert_held(l) WARN_ON(debug_locks && !lockdep_is_held(l)) +#define lockdep_assert_held(l) do { \ + WARN_ON(debug_locks && !lockdep_is_held(l)); \ + } while (0) #define lockdep_recursing(tsk) ((tsk)->lockdep_recursion) diff --git a/include/linux/memblock.h b/include/linux/memblock.h index f388203db7e8..3e5ecb2d790e 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -42,6 +42,7 @@ struct memblock { extern struct memblock memblock; extern int memblock_debug; +extern struct movablemem_map movablemem_map; #define memblock_dbg(fmt, ...) \ if (memblock_debug) printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) @@ -60,6 +61,7 @@ int memblock_reserve(phys_addr_t base, phys_addr_t size); void memblock_trim_memory(phys_addr_t align); #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP + void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, unsigned long *out_end_pfn, int *out_nid); diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 28bd5fa2ff2e..d6183f06d8c1 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -116,7 +116,6 @@ void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); * For memory reclaim. */ int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec); -int mem_cgroup_inactive_file_is_low(struct lruvec *lruvec); int mem_cgroup_select_victim_node(struct mem_cgroup *memcg); unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list); void mem_cgroup_update_lru_size(struct lruvec *, enum lru_list, int); @@ -321,12 +320,6 @@ mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec) return 1; } -static inline int -mem_cgroup_inactive_file_is_low(struct lruvec *lruvec) -{ - return 1; -} - static inline unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru) { diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 4a45c4e50025..b6a3be7d47bf 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -96,6 +96,7 @@ extern void __online_page_free(struct page *page); #ifdef CONFIG_MEMORY_HOTREMOVE extern bool is_pageblock_removable_nolock(struct page *page); +extern int arch_remove_memory(u64 start, u64 size); #endif /* CONFIG_MEMORY_HOTREMOVE */ /* reasonably generic interface to expand the physical pages in a zone */ @@ -173,17 +174,16 @@ static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat) #endif /* CONFIG_NUMA */ #endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */ -#ifdef CONFIG_SPARSEMEM_VMEMMAP +#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE +extern void register_page_bootmem_info_node(struct pglist_data *pgdat); +#else static inline void register_page_bootmem_info_node(struct pglist_data *pgdat) { } -static inline void put_page_bootmem(struct page *page) -{ -} -#else -extern void register_page_bootmem_info_node(struct pglist_data *pgdat); -extern void put_page_bootmem(struct page *page); #endif +extern void put_page_bootmem(struct page *page); +extern void get_page_bootmem(unsigned long ingo, struct page *page, + unsigned long type); /* * Lock for memory hotplug guarantees 1) all callbacks for memory hotplug @@ -233,6 +233,7 @@ static inline void unlock_memory_hotplug(void) {} #ifdef CONFIG_MEMORY_HOTREMOVE extern int is_mem_section_removable(unsigned long pfn, unsigned long nr_pages); +extern void try_offline_node(int nid); #else static inline int is_mem_section_removable(unsigned long pfn, @@ -240,6 +241,8 @@ static inline int is_mem_section_removable(unsigned long pfn, { return 0; } + +static inline void try_offline_node(int nid) {} #endif /* CONFIG_MEMORY_HOTREMOVE */ extern int mem_online_node(int nid); @@ -247,7 +250,8 @@ extern int add_memory(int nid, u64 start, u64 size); extern int arch_add_memory(int nid, u64 start, u64 size); extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); extern int offline_memory_block(struct memory_block *mem); -extern int remove_memory(u64 start, u64 size); +extern bool is_memblock_offlined(struct memory_block *mem); +extern int remove_memory(int nid, u64 start, u64 size); extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn, int nr_pages); extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms); diff --git a/include/linux/mfd/lp8788.h b/include/linux/mfd/lp8788.h index 2a32b16f79cb..69d4fd243d43 100644 --- a/include/linux/mfd/lp8788.h +++ b/include/linux/mfd/lp8788.h @@ -229,16 +229,6 @@ struct lp8788_charger_platform_data { }; /* - * struct lp8788_bl_pwm_data - * @pwm_set_intensity : set duty of pwm - * @pwm_get_intensity : get current duty of pwm - */ -struct lp8788_bl_pwm_data { - void (*pwm_set_intensity) (int brightness, int max_brightness); - int (*pwm_get_intensity) (int max_brightness); -}; - -/* * struct lp8788_backlight_platform_data * @name : backlight driver name. (default: "lcd-backlight") * @initial_brightness : initial value of backlight brightness @@ -248,8 +238,8 @@ struct lp8788_bl_pwm_data { * @rise_time : brightness ramp up step time * @fall_time : brightness ramp down step time * @pwm_pol : pwm polarity setting when bl_mode is pwm based - * @pwm_data : platform specific pwm generation functions - * only valid when bl_mode is pwm based + * @period_ns : platform specific pwm period value. unit is nano. + Only valid when bl_mode is LP8788_BL_COMB_PWM_BASED */ struct lp8788_backlight_platform_data { char *name; @@ -260,7 +250,7 @@ struct lp8788_backlight_platform_data { enum lp8788_bl_ramp_step rise_time; enum lp8788_bl_ramp_step fall_time; enum lp8788_bl_pwm_polarity pwm_pol; - struct lp8788_bl_pwm_data pwm_data; + unsigned int period_ns; }; /* diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 1e9f627967a3..a405d3dc0f61 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -40,11 +40,9 @@ extern void putback_movable_pages(struct list_head *l); extern int migrate_page(struct address_space *, struct page *, struct page *, enum migrate_mode); extern int migrate_pages(struct list_head *l, new_page_t x, - unsigned long private, bool offlining, - enum migrate_mode mode, int reason); + unsigned long private, enum migrate_mode mode, int reason); extern int migrate_huge_page(struct page *, new_page_t x, - unsigned long private, bool offlining, - enum migrate_mode mode); + unsigned long private, enum migrate_mode mode); extern int fail_migrate_page(struct address_space *, struct page *, struct page *); @@ -62,11 +60,11 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping, static inline void putback_lru_pages(struct list_head *l) {} static inline void putback_movable_pages(struct list_head *l) {} static inline int migrate_pages(struct list_head *l, new_page_t x, - unsigned long private, bool offlining, - enum migrate_mode mode, int reason) { return -ENOSYS; } + unsigned long private, enum migrate_mode mode, int reason) + { return -ENOSYS; } static inline int migrate_huge_page(struct page *page, new_page_t x, - unsigned long private, bool offlining, - enum migrate_mode mode) { return -ENOSYS; } + unsigned long private, enum migrate_mode mode) + { return -ENOSYS; } static inline int migrate_prep(void) { return -ENOSYS; } static inline int migrate_prep_local(void) { return -ENOSYS; } diff --git a/include/linux/mm.h b/include/linux/mm.h index 82b3b3e1b9c8..107c28808e8a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -87,6 +87,7 @@ extern unsigned int kobjsize(const void *objp); #define VM_PFNMAP 0x00000400 /* Page-ranges managed without "struct page", just pure PFN */ #define VM_DENYWRITE 0x00000800 /* ETXTBSY on write attempts.. */ +#define VM_POPULATE 0x00001000 #define VM_LOCKED 0x00002000 #define VM_IO 0x00004000 /* Memory mapped I/O or similar */ @@ -368,7 +369,7 @@ static inline struct page *compound_head(struct page *page) * both from it and to it can be tracked, using atomic_inc_and_test * and atomic_add_negative(-1). */ -static inline void reset_page_mapcount(struct page *page) +static inline void page_mapcount_reset(struct page *page) { atomic_set(&(page)->_mapcount, -1); } @@ -582,50 +583,11 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) * sets it, so none of the operations on it need to be atomic. */ - -/* - * page->flags layout: - * - * There are three possibilities for how page->flags get - * laid out. The first is for the normal case, without - * sparsemem. The second is for sparsemem when there is - * plenty of space for node and section. The last is when - * we have run out of space and have to fall back to an - * alternate (slower) way of determining the node. - * - * No sparsemem or sparsemem vmemmap: | NODE | ZONE | ... | FLAGS | - * classic sparse with space for node:| SECTION | NODE | ZONE | ... | FLAGS | - * classic sparse no space for node: | SECTION | ZONE | ... | FLAGS | - */ -#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) -#define SECTIONS_WIDTH SECTIONS_SHIFT -#else -#define SECTIONS_WIDTH 0 -#endif - -#define ZONES_WIDTH ZONES_SHIFT - -#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS -#define NODES_WIDTH NODES_SHIFT -#else -#ifdef CONFIG_SPARSEMEM_VMEMMAP -#error "Vmemmap: No space for nodes field in page flags" -#endif -#define NODES_WIDTH 0 -#endif - -/* Page flags: | [SECTION] | [NODE] | ZONE | ... | FLAGS | */ +/* Page flags: | [SECTION] | [NODE] | ZONE | [LAST_NID] | ... | FLAGS | */ #define SECTIONS_PGOFF ((sizeof(unsigned long)*8) - SECTIONS_WIDTH) #define NODES_PGOFF (SECTIONS_PGOFF - NODES_WIDTH) #define ZONES_PGOFF (NODES_PGOFF - ZONES_WIDTH) - -/* - * We are going to use the flags for the page to node mapping if its in - * there. This includes the case where there is no node, so it is implicit. - */ -#if !(NODES_WIDTH > 0 || NODES_SHIFT == 0) -#define NODE_NOT_IN_PAGE_FLAGS -#endif +#define LAST_NID_PGOFF (ZONES_PGOFF - LAST_NID_WIDTH) /* * Define the bit shifts to access each section. For non-existent @@ -635,6 +597,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) #define SECTIONS_PGSHIFT (SECTIONS_PGOFF * (SECTIONS_WIDTH != 0)) #define NODES_PGSHIFT (NODES_PGOFF * (NODES_WIDTH != 0)) #define ZONES_PGSHIFT (ZONES_PGOFF * (ZONES_WIDTH != 0)) +#define LAST_NID_PGSHIFT (LAST_NID_PGOFF * (LAST_NID_WIDTH != 0)) /* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allocator */ #ifdef NODE_NOT_IN_PAGE_FLAGS @@ -656,6 +619,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) #define ZONES_MASK ((1UL << ZONES_WIDTH) - 1) #define NODES_MASK ((1UL << NODES_WIDTH) - 1) #define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1) +#define LAST_NID_MASK ((1UL << LAST_NID_WIDTH) - 1) #define ZONEID_MASK ((1UL << ZONEID_SHIFT) - 1) static inline enum zone_type page_zonenum(const struct page *page) @@ -663,6 +627,10 @@ static inline enum zone_type page_zonenum(const struct page *page) return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK; } +#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) +#define SECTION_IN_PAGE_FLAGS +#endif + /* * The identification function is only used by the buddy allocator for * determining if two pages could be buddies. We are not really @@ -695,31 +663,48 @@ static inline int page_to_nid(const struct page *page) #endif #ifdef CONFIG_NUMA_BALANCING -static inline int page_xchg_last_nid(struct page *page, int nid) +#ifdef LAST_NID_NOT_IN_PAGE_FLAGS +static inline int page_nid_xchg_last(struct page *page, int nid) { return xchg(&page->_last_nid, nid); } -static inline int page_last_nid(struct page *page) +static inline int page_nid_last(struct page *page) { return page->_last_nid; } -static inline void reset_page_last_nid(struct page *page) +static inline void page_nid_reset_last(struct page *page) { page->_last_nid = -1; } #else -static inline int page_xchg_last_nid(struct page *page, int nid) +static inline int page_nid_last(struct page *page) +{ + return (page->flags >> LAST_NID_PGSHIFT) & LAST_NID_MASK; +} + +extern int page_nid_xchg_last(struct page *page, int nid); + +static inline void page_nid_reset_last(struct page *page) +{ + int nid = (1 << LAST_NID_SHIFT) - 1; + + page->flags &= ~(LAST_NID_MASK << LAST_NID_PGSHIFT); + page->flags |= (nid & LAST_NID_MASK) << LAST_NID_PGSHIFT; +} +#endif /* LAST_NID_NOT_IN_PAGE_FLAGS */ +#else +static inline int page_nid_xchg_last(struct page *page, int nid) { return page_to_nid(page); } -static inline int page_last_nid(struct page *page) +static inline int page_nid_last(struct page *page) { return page_to_nid(page); } -static inline void reset_page_last_nid(struct page *page) +static inline void page_nid_reset_last(struct page *page) { } #endif @@ -729,7 +714,7 @@ static inline struct zone *page_zone(const struct page *page) return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)]; } -#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) +#ifdef SECTION_IN_PAGE_FLAGS static inline void set_page_section(struct page *page, unsigned long section) { page->flags &= ~(SECTIONS_MASK << SECTIONS_PGSHIFT); @@ -759,7 +744,7 @@ static inline void set_page_links(struct page *page, enum zone_type zone, { set_page_zone(page, zone); set_page_node(page, node); -#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) +#ifdef SECTION_IN_PAGE_FLAGS set_page_section(page, pfn_to_section_nr(pfn)); #endif } @@ -819,18 +804,7 @@ void page_address_init(void); #define PAGE_MAPPING_KSM 2 #define PAGE_MAPPING_FLAGS (PAGE_MAPPING_ANON | PAGE_MAPPING_KSM) -extern struct address_space swapper_space; -static inline struct address_space *page_mapping(struct page *page) -{ - struct address_space *mapping = page->mapping; - - VM_BUG_ON(PageSlab(page)); - if (unlikely(PageSwapCache(page))) - mapping = &swapper_space; - else if ((unsigned long)mapping & PAGE_MAPPING_ANON) - mapping = NULL; - return mapping; -} +extern struct address_space *page_mapping(struct page *page); /* Neutral page->mapping pointer to address_space or anon_vma or other */ static inline void *page_rmapping(struct page *page) @@ -1037,7 +1011,6 @@ static inline int fixup_user_fault(struct task_struct *tsk, } #endif -extern int make_pages_present(unsigned long addr, unsigned long end); extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write); extern int access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, int write); @@ -1361,6 +1334,23 @@ extern void free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn); extern void sparse_memory_present_with_active_regions(int nid); +#define MOVABLEMEM_MAP_MAX MAX_NUMNODES +struct movablemem_entry { + unsigned long start_pfn; /* start pfn of memory segment */ + unsigned long end_pfn; /* end pfn of memory segment (exclusive) */ +}; + +struct movablemem_map { + bool acpi; /* true if using SRAT info */ + int nr_map; + struct movablemem_entry map[MOVABLEMEM_MAP_MAX]; + nodemask_t numa_nodes_hotplug; /* on which nodes we specify memory */ +}; + +extern void __init insert_movablemem_map(unsigned long start_pfn, + unsigned long end_pfn); +extern int __init movablemem_map_overlap(unsigned long start_pfn, + unsigned long end_pfn); #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ #if !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) && \ @@ -1397,6 +1387,9 @@ extern void setup_per_cpu_pageset(void); extern void zone_pcp_update(struct zone *zone); extern void zone_pcp_reset(struct zone *zone); +/* page_alloc.c */ +extern int min_free_kbytes; + /* nommu.c */ extern atomic_long_t mmap_pages_allocated; extern int nommu_shrink_inode_mappings(struct inode *, size_t, size_t); @@ -1474,13 +1467,24 @@ extern int install_special_mapping(struct mm_struct *mm, extern unsigned long get_unmapped_area(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); extern unsigned long mmap_region(struct file *file, unsigned long addr, - unsigned long len, unsigned long flags, - vm_flags_t vm_flags, unsigned long pgoff); -extern unsigned long do_mmap_pgoff(struct file *, unsigned long, - unsigned long, unsigned long, - unsigned long, unsigned long); + unsigned long len, vm_flags_t vm_flags, unsigned long pgoff); +extern unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, + unsigned long len, unsigned long prot, unsigned long flags, + unsigned long pgoff, unsigned long *populate); extern int do_munmap(struct mm_struct *, unsigned long, size_t); +#ifdef CONFIG_MMU +extern int __mm_populate(unsigned long addr, unsigned long len, + int ignore_errors); +static inline void mm_populate(unsigned long addr, unsigned long len) +{ + /* Ignore errors */ + (void) __mm_populate(addr, len, 1); +} +#else +static inline void mm_populate(unsigned long addr, unsigned long len) {} +#endif + /* These take the mm semaphore themselves */ extern unsigned long vm_brk(unsigned long, unsigned long); extern int vm_munmap(unsigned long, size_t); @@ -1709,7 +1713,11 @@ int vmemmap_populate_basepages(struct page *start_page, unsigned long pages, int node); int vmemmap_populate(struct page *start_page, unsigned long pages, int node); void vmemmap_populate_print_last(void); - +#ifdef CONFIG_MEMORY_HOTPLUG +void vmemmap_free(struct page *memmap, unsigned long nr_pages); +#endif +void register_page_bootmem_memmap(unsigned long section_nr, struct page *map, + unsigned long size); enum mf_flags { MF_COUNT_INCREASED = 1 << 0, @@ -1722,7 +1730,7 @@ extern int unpoison_memory(unsigned long pfn); extern int sysctl_memory_failure_early_kill; extern int sysctl_memory_failure_recovery; extern void shake_page(struct page *p, int access); -extern atomic_long_t mce_bad_pages; +extern atomic_long_t num_poisoned_pages; extern int soft_offline_page(struct page *page, int flags); extern void dump_page(struct page *page); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index f8f5162a3571..fb425aa16c01 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -12,6 +12,7 @@ #include <linux/cpumask.h> #include <linux/page-debug-flags.h> #include <linux/uprobes.h> +#include <linux/page-flags-layout.h> #include <asm/page.h> #include <asm/mmu.h> @@ -173,7 +174,7 @@ struct page { void *shadow; #endif -#ifdef CONFIG_NUMA_BALANCING +#ifdef LAST_NID_NOT_IN_PAGE_FLAGS int _last_nid; #endif } @@ -329,12 +330,9 @@ struct mm_struct { unsigned long (*get_unmapped_area) (struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); - void (*unmap_area) (struct mm_struct *mm, unsigned long addr); #endif unsigned long mmap_base; /* base of mmap area */ unsigned long task_size; /* size of task vm space */ - unsigned long cached_hole_size; /* if non-zero, the largest hole below free_area_cache */ - unsigned long free_area_cache; /* first hole of size cached_hole_size or larger */ unsigned long highest_vm_end; /* highest vma end address */ pgd_t * pgd; atomic_t mm_users; /* How many users with user space? */ @@ -414,9 +412,9 @@ struct mm_struct { #endif #ifdef CONFIG_NUMA_BALANCING /* - * numa_next_scan is the next time when the PTEs will me marked - * pte_numa to gather statistics and migrate pages to new nodes - * if necessary + * numa_next_scan is the next time that the PTEs will be marked + * pte_numa. NUMA hinting faults will gather statistics and migrate + * pages to new nodes if necessary. */ unsigned long numa_next_scan; diff --git a/include/linux/mman.h b/include/linux/mman.h index 9aa863da287f..61c7a87e5d2b 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -79,6 +79,8 @@ calc_vm_flag_bits(unsigned long flags) { return _calc_vm_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN ) | _calc_vm_trans(flags, MAP_DENYWRITE, VM_DENYWRITE ) | - _calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED ); + ((flags & MAP_LOCKED) ? (VM_LOCKED | VM_POPULATE) : 0) | + (((flags & (MAP_POPULATE | MAP_NONBLOCK)) == MAP_POPULATE) ? + VM_POPULATE : 0); } #endif /* _LINUX_MMAN_H */ diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 73b64a38b984..ab20a60d2671 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -15,7 +15,7 @@ #include <linux/seqlock.h> #include <linux/nodemask.h> #include <linux/pageblock-flags.h> -#include <generated/bounds.h> +#include <linux/page-flags-layout.h> #include <linux/atomic.h> #include <asm/page.h> @@ -57,7 +57,9 @@ enum { */ MIGRATE_CMA, #endif +#ifdef CONFIG_MEMORY_ISOLATION MIGRATE_ISOLATE, /* can't allocate from here */ +#endif MIGRATE_TYPES }; @@ -308,24 +310,6 @@ enum zone_type { #ifndef __GENERATING_BOUNDS_H -/* - * When a memory allocation must conform to specific limitations (such - * as being suitable for DMA) the caller will pass in hints to the - * allocator in the gfp_mask, in the zone modifier bits. These bits - * are used to select a priority ordered list of memory zones which - * match the requested limits. See gfp_zone() in include/linux/gfp.h - */ - -#if MAX_NR_ZONES < 2 -#define ZONES_SHIFT 0 -#elif MAX_NR_ZONES <= 2 -#define ZONES_SHIFT 1 -#elif MAX_NR_ZONES <= 4 -#define ZONES_SHIFT 2 -#else -#error ZONES_SHIFT -- too many zones configured adjust calculation -#endif - struct zone { /* Fields commonly accessed by the page allocator */ @@ -543,6 +527,26 @@ static inline int zone_is_oom_locked(const struct zone *zone) return test_bit(ZONE_OOM_LOCKED, &zone->flags); } +static inline unsigned zone_end_pfn(const struct zone *zone) +{ + return zone->zone_start_pfn + zone->spanned_pages; +} + +static inline bool zone_spans_pfn(const struct zone *zone, unsigned long pfn) +{ + return zone->zone_start_pfn <= pfn && pfn < zone_end_pfn(zone); +} + +static inline bool zone_is_initialized(struct zone *zone) +{ + return !!zone->wait_table; +} + +static inline bool zone_is_empty(struct zone *zone) +{ + return zone->spanned_pages == 0; +} + /* * The "priority" of VM scanning is how much of the queues we will scan in one * go. A value of 12 for DEF_PRIORITY implies that we will scan 1/4096th of the @@ -752,11 +756,17 @@ typedef struct pglist_data { #define nid_page_nr(nid, pagenr) pgdat_page_nr(NODE_DATA(nid),(pagenr)) #define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) +#define node_end_pfn(nid) pgdat_end_pfn(NODE_DATA(nid)) -#define node_end_pfn(nid) ({\ - pg_data_t *__pgdat = NODE_DATA(nid);\ - __pgdat->node_start_pfn + __pgdat->node_spanned_pages;\ -}) +static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat) +{ + return pgdat->node_start_pfn + pgdat->node_spanned_pages; +} + +static inline bool pgdat_is_empty(pg_data_t *pgdat) +{ + return !pgdat->node_start_pfn && !pgdat->node_spanned_pages; +} #include <linux/memory_hotplug.h> @@ -805,7 +815,10 @@ unsigned long __init node_memmap_size_bytes(int, unsigned long, unsigned long); /* * zone_idx() returns 0 for the ZONE_DMA zone, 1 for the ZONE_NORMAL zone, etc. */ -#define zone_idx(zone) ((zone) - (zone)->zone_pgdat->node_zones) +static inline enum zone_type zone_idx(struct zone *zone) +{ + return zone - zone->zone_pgdat->node_zones; +} static inline int populated_zone(struct zone *zone) { @@ -846,25 +859,18 @@ static inline int is_normal_idx(enum zone_type idx) */ static inline int is_highmem(struct zone *zone) { -#ifdef CONFIG_HIGHMEM - int zone_off = (char *)zone - (char *)zone->zone_pgdat->node_zones; - return zone_off == ZONE_HIGHMEM * sizeof(*zone) || - (zone_off == ZONE_MOVABLE * sizeof(*zone) && - zone_movable_is_highmem()); -#else - return 0; -#endif + return is_highmem_idx(zone_idx(zone)); } static inline int is_normal(struct zone *zone) { - return zone == zone->zone_pgdat->node_zones + ZONE_NORMAL; + return zone_idx(zone) == ZONE_NORMAL; } static inline int is_dma32(struct zone *zone) { #ifdef CONFIG_ZONE_DMA32 - return zone == zone->zone_pgdat->node_zones + ZONE_DMA32; + return zone_idx(zone) == ZONE_DMA32; #else return 0; #endif @@ -873,7 +879,7 @@ static inline int is_dma32(struct zone *zone) static inline int is_dma(struct zone *zone) { #ifdef CONFIG_ZONE_DMA - return zone == zone->zone_pgdat->node_zones + ZONE_DMA; + return zone_idx(zone) == ZONE_DMA; #else return 0; #endif @@ -1053,8 +1059,6 @@ static inline unsigned long early_pfn_to_nid(unsigned long pfn) * PA_SECTION_SHIFT physical address to/from section number * PFN_SECTION_SHIFT pfn to/from section number */ -#define SECTIONS_SHIFT (MAX_PHYSMEM_BITS - SECTION_SIZE_BITS) - #define PA_SECTION_SHIFT (SECTION_SIZE_BITS) #define PFN_SECTION_SHIFT (SECTION_SIZE_BITS - PAGE_SHIFT) diff --git a/include/linux/page-flags-layout.h b/include/linux/page-flags-layout.h new file mode 100644 index 000000000000..93506a114034 --- /dev/null +++ b/include/linux/page-flags-layout.h @@ -0,0 +1,88 @@ +#ifndef PAGE_FLAGS_LAYOUT_H +#define PAGE_FLAGS_LAYOUT_H + +#include <linux/numa.h> +#include <generated/bounds.h> + +/* + * When a memory allocation must conform to specific limitations (such + * as being suitable for DMA) the caller will pass in hints to the + * allocator in the gfp_mask, in the zone modifier bits. These bits + * are used to select a priority ordered list of memory zones which + * match the requested limits. See gfp_zone() in include/linux/gfp.h + */ +#if MAX_NR_ZONES < 2 +#define ZONES_SHIFT 0 +#elif MAX_NR_ZONES <= 2 +#define ZONES_SHIFT 1 +#elif MAX_NR_ZONES <= 4 +#define ZONES_SHIFT 2 +#else +#error ZONES_SHIFT -- too many zones configured adjust calculation +#endif + +#ifdef CONFIG_SPARSEMEM +#include <asm/sparsemem.h> + +/* SECTION_SHIFT #bits space required to store a section # */ +#define SECTIONS_SHIFT (MAX_PHYSMEM_BITS - SECTION_SIZE_BITS) + +#endif /* CONFIG_SPARSEMEM */ + +/* + * page->flags layout: + * + * There are five possibilities for how page->flags get laid out. The first + * pair is for the normal case without sparsemem. The second pair is for + * sparsemem when there is plenty of space for node and section information. + * The last is when there is insufficient space in page->flags and a separate + * lookup is necessary. + * + * No sparsemem or sparsemem vmemmap: | NODE | ZONE | ... | FLAGS | + * " plus space for last_nid: | NODE | ZONE | LAST_NID ... | FLAGS | + * classic sparse with space for node:| SECTION | NODE | ZONE | ... | FLAGS | + * " plus space for last_nid: | SECTION | NODE | ZONE | LAST_NID ... | FLAGS | + * classic sparse no space for node: | SECTION | ZONE | ... | FLAGS | + */ +#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) +#define SECTIONS_WIDTH SECTIONS_SHIFT +#else +#define SECTIONS_WIDTH 0 +#endif + +#define ZONES_WIDTH ZONES_SHIFT + +#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS +#define NODES_WIDTH NODES_SHIFT +#else +#ifdef CONFIG_SPARSEMEM_VMEMMAP +#error "Vmemmap: No space for nodes field in page flags" +#endif +#define NODES_WIDTH 0 +#endif + +#ifdef CONFIG_NUMA_BALANCING +#define LAST_NID_SHIFT NODES_SHIFT +#else +#define LAST_NID_SHIFT 0 +#endif + +#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT+LAST_NID_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS +#define LAST_NID_WIDTH LAST_NID_SHIFT +#else +#define LAST_NID_WIDTH 0 +#endif + +/* + * We are going to use the flags for the page to node mapping if its in + * there. This includes the case where there is no node, so it is implicit. + */ +#if !(NODES_WIDTH > 0 || NODES_SHIFT == 0) +#define NODE_NOT_IN_PAGE_FLAGS +#endif + +#if defined(CONFIG_NUMA_BALANCING) && LAST_NID_WIDTH == 0 +#define LAST_NID_NOT_IN_PAGE_FLAGS +#endif + +#endif /* _LINUX_PAGE_FLAGS_LAYOUT */ diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index a92061e08d48..3fff8e774067 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -1,6 +1,25 @@ #ifndef __LINUX_PAGEISOLATION_H #define __LINUX_PAGEISOLATION_H +#ifdef CONFIG_MEMORY_ISOLATION +static inline bool is_migrate_isolate_page(struct page *page) +{ + return get_pageblock_migratetype(page) == MIGRATE_ISOLATE; +} +static inline bool is_migrate_isolate(int migratetype) +{ + return migratetype == MIGRATE_ISOLATE; +} +#else +static inline bool is_migrate_isolate_page(struct page *page) +{ + return false; +} +static inline bool is_migrate_isolate(int migratetype) +{ + return false; +} +#endif bool has_unmovable_pages(struct zone *zone, struct page *page, int count, bool skip_hwpoisoned_pages); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 6da609d14c15..0e38e13eb249 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -414,6 +414,7 @@ static inline void wait_on_page_writeback(struct page *page) } extern void end_page_writeback(struct page *page); +void wait_for_stable_page(struct page *page); /* * Add an arbitrary waiter to a page's wait queue diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h new file mode 100644 index 000000000000..d0cf8872dc43 --- /dev/null +++ b/include/linux/percpu-refcount.h @@ -0,0 +1,114 @@ +/* + * Dynamic percpu refcounts: + * (C) 2012 Google, Inc. + * Author: Kent Overstreet <koverstreet@google.com> + * + * This implements a refcount with similar semantics to atomic_t - atomic_inc(), + * atomic_dec_and_test() - but potentially percpu. + * + * There's one important difference between percpu refs and normal atomic_t + * refcounts; you have to keep track of your initial refcount, and then when you + * start shutting down you call percpu_ref_kill() _before_ dropping the initial + * refcount. + * + * Before you call percpu_ref_kill(), percpu_ref_put() does not check for the + * refcount hitting 0 - it can't, if it was in percpu mode. percpu_ref_kill() + * puts the ref back in single atomic_t mode, collecting the per cpu refs and + * issuing the appropriate barriers, and then marks the ref as shutting down so + * that percpu_ref_put() will check for the ref hitting 0. After it returns, + * it's safe to drop the initial ref. + * + * BACKGROUND: + * + * Percpu refcounts are quite useful for performance, but if we blindly + * converted all refcounts to percpu counters we'd waste quite a bit of memory. + * + * Think about all the refcounts embedded in kobjects, files, etc. most of which + * aren't used much. These start out as simple atomic counters - a little bigger + * than a bare atomic_t, 16 bytes instead of 4 - but if we exceed some arbitrary + * number of gets in one second, we then switch to percpu counters. + * + * This heuristic isn't perfect because it'll fire if the refcount was only + * being used on one cpu; ideally we'd be able to count the number of cache + * misses on percpu_ref_get() or something similar, but that'd make the non + * percpu path significantly heavier/more complex. We can count the number of + * gets() without any extra atomic instructions on arches that support + * atomic64_t - simply by changing the atomic_inc() to atomic_add_return(). + * + * USAGE: + * + * See fs/aio.c for some example usage; it's used there for struct kioctx, which + * is created when userspaces calls io_setup(), and destroyed when userspace + * calls io_destroy() or the process exits. + * + * In the aio code, kill_ioctx() is called when we wish to destroy a kioctx; it + * calls percpu_ref_kill(), then hlist_del_rcu() and sychronize_rcu() to remove + * the kioctx from the proccess's list of kioctxs - after that, there can't be + * any new users of the kioctx (from lookup_ioctx()) and it's then safe to drop + * the initial ref with percpu_ref_put(). + * + * Code that does a two stage shutdown like this often needs some kind of + * explicit synchronization to ensure the initial refcount can only be dropped + * once - percpu_ref_kill() does this for you, it returns true once and false if + * someone else already called it. The aio code uses it this way, but it's not + * necessary if the code has some other mechanism to synchronize teardown. + * + * As mentioned previously, we decide when to convert a ref to percpu counters + * in percpu_ref_get(). However, since percpu_ref_get() will often be called + * with rcu_read_lock() held, it's not done there - percpu_ref_get() returns + * true if the ref should be converted to percpu counters. + * + * The caller should then call percpu_ref_alloc() after dropping + * rcu_read_lock(); if there is an uncommonly used codepath where it's + * inconvenient to call percpu_ref_alloc() after get(), it may be safely skipped + * and percpu_ref_get() will return true again the next time the counter wraps + * around. + */ + +#ifndef _LINUX_PERCPU_REFCOUNT_H +#define _LINUX_PERCPU_REFCOUNT_H + +#include <linux/atomic.h> +#include <linux/percpu.h> + +struct percpu_ref { + atomic64_t count; + unsigned long pcpu_count; +}; + +void percpu_ref_init(struct percpu_ref *ref); +void __percpu_ref_get(struct percpu_ref *ref, bool alloc); +int percpu_ref_put(struct percpu_ref *ref); + +int percpu_ref_kill(struct percpu_ref *ref); +int percpu_ref_dead(struct percpu_ref *ref); + +/** + * percpu_ref_get - increment a dynamic percpu refcount + * + * Increments @ref and possibly converts it to percpu counters. Must be called + * with rcu_read_lock() held, and may potentially drop/reacquire rcu_read_lock() + * to allocate percpu counters - if sleeping/allocation isn't safe for some + * other reason (e.g. a spinlock), see percpu_ref_get_noalloc(). + * + * Analagous to atomic_inc(). + */ +static inline void percpu_ref_get(struct percpu_ref *ref) +{ + __percpu_ref_get(ref, true); +} + +/** + * percpu_ref_get_noalloc - increment a dynamic percpu refcount + * + * Increments @ref, to be used when it's not safe to allocate percpu counters. + * Must be called with rcu_read_lock() held. + * + * Analagous to atomic_inc(). + */ +static inline void percpu_ref_get_noalloc(struct percpu_ref *ref) +{ + __percpu_ref_get(ref, false); +} + +#endif diff --git a/include/linux/pid.h b/include/linux/pid.h index 2381c973d897..a089a3c447fc 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -176,9 +176,8 @@ pid_t pid_vnr(struct pid *pid); #define do_each_pid_task(pid, type, task) \ do { \ - struct hlist_node *pos___; \ if ((pid) != NULL) \ - hlist_for_each_entry_rcu((task), pos___, \ + hlist_for_each_entry_rcu((task), \ &(pid)->tasks[type], pids[type].node) { /* diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index 215e5e3dda10..6051177a890d 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -4,6 +4,7 @@ #include <linux/sched.h> #include <linux/bug.h> #include <linux/mm.h> +#include <linux/workqueue.h> #include <linux/threads.h> #include <linux/nsproxy.h> #include <linux/kref.h> diff --git a/include/linux/pm.h b/include/linux/pm.h index 03d7bb145311..1a8a69db7b1c 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -538,6 +538,7 @@ struct dev_pm_info { unsigned int irq_safe:1; unsigned int use_autosuspend:1; unsigned int timer_autosuspends:1; + unsigned int memalloc_noio:1; enum rpm_request request; enum rpm_status runtime_status; int runtime_error; diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index c785c215abfc..7d7e09efff9b 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -47,6 +47,7 @@ extern void pm_runtime_set_autosuspend_delay(struct device *dev, int delay); extern unsigned long pm_runtime_autosuspend_expiration(struct device *dev); extern void pm_runtime_update_max_time_suspended(struct device *dev, s64 delta_ns); +extern void pm_runtime_set_memalloc_noio(struct device *dev, bool enable); static inline bool pm_children_suspended(struct device *dev) { @@ -156,6 +157,8 @@ static inline void pm_runtime_set_autosuspend_delay(struct device *dev, int delay) {} static inline unsigned long pm_runtime_autosuspend_expiration( struct device *dev) { return 0; } +static inline void pm_runtime_set_memalloc_noio(struct device *dev, + bool enable){} #endif /* !CONFIG_PM_RUNTIME */ diff --git a/include/linux/rculist.h b/include/linux/rculist.h index c92dd28eaa6c..bc7094d978fe 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -445,8 +445,7 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev, /** * hlist_for_each_entry_rcu - iterate over rcu list of given type - * @tpos: the type * to use as a loop cursor. - * @pos: the &struct hlist_node to use as a loop cursor. + * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * @@ -454,16 +453,16 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev, * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ -#define hlist_for_each_entry_rcu(tpos, pos, head, member) \ - for (pos = rcu_dereference_raw(hlist_first_rcu(head)); \ - pos && \ - ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); \ - pos = rcu_dereference_raw(hlist_next_rcu(pos))) +#define hlist_for_each_entry_rcu(pos, head, member) \ + for (pos = hlist_entry_safe (rcu_dereference_raw(hlist_first_rcu(head)),\ + typeof(*(pos)), member); \ + pos; \ + pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ + &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_rcu_bh - iterate over rcu list of given type - * @tpos: the type * to use as a loop cursor. - * @pos: the &struct hlist_node to use as a loop cursor. + * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * @@ -471,35 +470,36 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev, * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ -#define hlist_for_each_entry_rcu_bh(tpos, pos, head, member) \ - for (pos = rcu_dereference_bh((head)->first); \ - pos && \ - ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); \ - pos = rcu_dereference_bh(pos->next)) +#define hlist_for_each_entry_rcu_bh(pos, head, member) \ + for (pos = hlist_entry_safe(rcu_dereference_bh(hlist_first_rcu(head)), \ + typeof(*(pos)), member); \ + pos; \ + pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu( \ + &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_continue_rcu - iterate over a hlist continuing after current point - * @tpos: the type * to use as a loop cursor. - * @pos: the &struct hlist_node to use as a loop cursor. + * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ -#define hlist_for_each_entry_continue_rcu(tpos, pos, member) \ - for (pos = rcu_dereference((pos)->next); \ - pos && \ - ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); \ - pos = rcu_dereference(pos->next)) +#define hlist_for_each_entry_continue_rcu(pos, member) \ + for (pos = hlist_entry_safe(rcu_dereference((pos)->member.next), \ + typeof(*(pos)), member); \ + pos; \ + pos = hlist_entry_safe(rcu_dereference((pos)->member.next), \ + typeof(*(pos)), member)) /** * hlist_for_each_entry_continue_rcu_bh - iterate over a hlist continuing after current point - * @tpos: the type * to use as a loop cursor. - * @pos: the &struct hlist_node to use as a loop cursor. + * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ -#define hlist_for_each_entry_continue_rcu_bh(tpos, pos, member) \ - for (pos = rcu_dereference_bh((pos)->next); \ - pos && \ - ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); \ - pos = rcu_dereference_bh(pos->next)) +#define hlist_for_each_entry_continue_rcu_bh(pos, member) \ + for (pos = hlist_entry_safe(rcu_dereference_bh((pos)->member.next), \ + typeof(*(pos)), member); \ + pos; \ + pos = hlist_entry_safe(rcu_dereference_bh((pos)->member.next), \ + typeof(*(pos)), member)) #endif /* __KERNEL__ */ diff --git a/include/linux/rmap.h b/include/linux/rmap.h index c20635c527a9..6dacb93a6d94 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -123,7 +123,7 @@ static inline void anon_vma_lock_write(struct anon_vma *anon_vma) down_write(&anon_vma->root->rwsem); } -static inline void anon_vma_unlock(struct anon_vma *anon_vma) +static inline void anon_vma_unlock_write(struct anon_vma *anon_vma) { up_write(&anon_vma->root->rwsem); } diff --git a/include/linux/rtc-pxa.h b/include/linux/rtc-pxa.h new file mode 100644 index 000000000000..71bc45f060fc --- /dev/null +++ b/include/linux/rtc-pxa.h @@ -0,0 +1,18 @@ +/* + * include/linux/rtc-pxa.h + * + * RTC PXA Header file + * + * Copyright (C) 2010 Marvell International Ltd. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __LINUX_RTC_PXA_H +#define __LINUX_RTC_PXA_H + +extern int pxa_rtc_sync_time(unsigned int ticks); + +#endif /* __LINUX_RTC_PXA_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 6a5b46736183..f0e3a11e4906 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -51,6 +51,7 @@ struct sched_param { #include <linux/cred.h> #include <linux/llist.h> #include <linux/uidgid.h> +#include <linux/gfp.h> #include <asm/processor.h> @@ -355,8 +356,6 @@ struct user_namespace; extern int sysctl_max_map_count; -#include <linux/aio.h> - #ifdef CONFIG_MMU extern void arch_pick_mmap_layout(struct mm_struct *mm); extern unsigned long @@ -366,8 +365,6 @@ extern unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); -extern void arch_unmap_area(struct mm_struct *, unsigned long); -extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long); #else static inline void arch_pick_mmap_layout(struct mm_struct *mm) {} #endif @@ -376,11 +373,6 @@ static inline void arch_pick_mmap_layout(struct mm_struct *mm) {} extern void set_dumpable(struct mm_struct *mm, int value); extern int get_dumpable(struct mm_struct *mm); -/* get/set_dumpable() values */ -#define SUID_DUMPABLE_DISABLED 0 -#define SUID_DUMPABLE_ENABLED 1 -#define SUID_DUMPABLE_SAFE 2 - /* mm flags */ /* dumpable bits */ #define MMF_DUMPABLE 0 /* core dump is permitted */ @@ -1856,6 +1848,7 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, #define PF_FROZEN 0x00010000 /* frozen for system suspend */ #define PF_FSTRANS 0x00020000 /* inside a filesystem transaction */ #define PF_KSWAPD 0x00040000 /* I am kswapd */ +#define PF_MEMALLOC_NOIO 0x00080000 /* Allocating memory without IO involved */ #define PF_LESS_THROTTLE 0x00100000 /* Throttle me less: I clean memory */ #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* randomize virtual address space */ @@ -1893,6 +1886,26 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, #define tsk_used_math(p) ((p)->flags & PF_USED_MATH) #define used_math() tsk_used_math(current) +/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags */ +static inline gfp_t memalloc_noio_flags(gfp_t flags) +{ + if (unlikely(current->flags & PF_MEMALLOC_NOIO)) + flags &= ~__GFP_IO; + return flags; +} + +static inline unsigned int memalloc_noio_save(void) +{ + unsigned int flags = current->flags & PF_MEMALLOC_NOIO; + current->flags |= PF_MEMALLOC_NOIO; + return flags; +} + +static inline void memalloc_noio_restore(unsigned int flags) +{ + current->flags = (current->flags & ~PF_MEMALLOC_NOIO) | flags; +} + /* * task->jobctl flags */ diff --git a/include/linux/smp.h b/include/linux/smp.h index dd6f06be3c9f..3e07a7df6478 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -89,7 +89,8 @@ void kick_all_cpus_sync(void); #ifdef CONFIG_USE_GENERIC_SMP_HELPERS void __init call_function_init(void); void generic_smp_call_function_single_interrupt(void); -void generic_smp_call_function_interrupt(void); +#define generic_smp_call_function_interrupt \ + generic_smp_call_function_single_interrupt #else static inline void call_function_init(void) { } #endif diff --git a/include/linux/swap.h b/include/linux/swap.h index 68df9c17fbbb..2818a123f3ea 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -8,7 +8,7 @@ #include <linux/memcontrol.h> #include <linux/sched.h> #include <linux/node.h> - +#include <linux/fs.h> #include <linux/atomic.h> #include <asm/page.h> @@ -156,7 +156,7 @@ enum { SWP_SCANNING = (1 << 8), /* refcount in scan_swap_map */ }; -#define SWAP_CLUSTER_MAX 32 +#define SWAP_CLUSTER_MAX 32UL #define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX /* @@ -202,6 +202,18 @@ struct swap_info_struct { unsigned long *frontswap_map; /* frontswap in-use, one bit per page */ atomic_t frontswap_pages; /* frontswap pages in-use counter */ #endif + spinlock_t lock; /* + * protect map scan related fields like + * swap_map, lowest_bit, highest_bit, + * inuse_pages, cluster_next, + * cluster_nr, lowest_alloc and + * highest_alloc. other fields are only + * changed at swapon/swapoff, so are + * protected by swap_lock. changing + * flags need hold this lock and + * swap_lock. If both locks need hold, + * hold swap_lock first. + */ }; struct swap_list_t { @@ -209,15 +221,12 @@ struct swap_list_t { int next; /* swapfile to be used next */ }; -/* Swap 50% full? Release swapcache more aggressively.. */ -#define vm_swap_full() (nr_swap_pages*2 < total_swap_pages) - /* linux/mm/page_alloc.c */ extern unsigned long totalram_pages; extern unsigned long totalreserve_pages; extern unsigned long dirty_balance_reserve; -extern unsigned int nr_free_buffer_pages(void); -extern unsigned int nr_free_pagecache_pages(void); +extern unsigned long nr_free_buffer_pages(void); +extern unsigned long nr_free_pagecache_pages(void); /* Definition of global_page_state not available yet */ #define nr_free_pages() global_page_state(NR_FREE_PAGES) @@ -266,7 +275,7 @@ extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem, extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; extern int remove_mapping(struct address_space *mapping, struct page *page); -extern long vm_total_pages; +extern unsigned long vm_total_pages; #ifdef CONFIG_NUMA extern int zone_reclaim_mode; @@ -330,8 +339,9 @@ int generic_swapfile_activate(struct swap_info_struct *, struct file *, sector_t *); /* linux/mm/swap_state.c */ -extern struct address_space swapper_space; -#define total_swapcache_pages swapper_space.nrpages +extern struct address_space swapper_spaces[]; +#define swap_address_space(entry) (&swapper_spaces[swp_type(entry)]) +extern unsigned long total_swapcache_pages(void); extern void show_swap_cache_info(void); extern int add_to_swap(struct page *); extern int add_to_swap_cache(struct page *, swp_entry_t, gfp_t); @@ -346,8 +356,20 @@ extern struct page *swapin_readahead(swp_entry_t, gfp_t, struct vm_area_struct *vma, unsigned long addr); /* linux/mm/swapfile.c */ -extern long nr_swap_pages; +extern atomic_long_t nr_swap_pages; extern long total_swap_pages; + +/* Swap 50% full? Release swapcache more aggressively.. */ +static inline bool vm_swap_full(void) +{ + return atomic_long_read(&nr_swap_pages) * 2 < total_swap_pages; +} + +static inline long get_nr_swap_pages(void) +{ + return atomic_long_read(&nr_swap_pages); +} + extern void si_swapinfo(struct sysinfo *); extern swp_entry_t get_swap_page(void); extern swp_entry_t get_swap_page_of_type(int); @@ -380,9 +402,10 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout) #else /* CONFIG_SWAP */ -#define nr_swap_pages 0L +#define get_nr_swap_pages() 0L #define total_swap_pages 0L -#define total_swapcache_pages 0UL +#define total_swapcache_pages() 0UL +#define vm_swap_full() 0 #define si_swapinfo(val) \ do { (val)->freeswap = (val)->totalswap = 0; } while (0) diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index fce0a2799d43..d4b7a184f08c 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -36,7 +36,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #endif PGINODESTEAL, SLABS_SCANNED, KSWAPD_INODESTEAL, KSWAPD_LOW_WMARK_HIT_QUICKLY, KSWAPD_HIGH_WMARK_HIT_QUICKLY, - KSWAPD_SKIP_CONGESTION_WAIT, PAGEOUTRUN, ALLOCSTALL, PGROTATED, #ifdef CONFIG_NUMA_BALANCING NUMA_PTE_UPDATES, @@ -51,7 +50,12 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, COMPACTMIGRATE_SCANNED, COMPACTFREE_SCANNED, COMPACTISOLATED, COMPACTSTALL, COMPACTFAIL, COMPACTSUCCESS, -#endif +#ifdef CONFIG_BALLOON_COMPACTION + COMPACTBALLOONISOLATED, /* isolated from balloon pagelist */ + COMPACTBALLOONMIGRATED, /* balloon page sucessfully migrated */ + COMPACTBALLOONRETURNED, /* putback to pagelist, not-migrated */ +#endif /* CONFIG_BALLOON_COMPACTION */ +#endif /* CONFIG_COMPACTION */ #ifdef CONFIG_HUGETLB_PAGE HTLB_BUDDY_PGALLOC, HTLB_BUDDY_PGALLOC_FAIL, #endif diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index a13291f7da88..5fd71a7d0dfd 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -85,7 +85,7 @@ static inline void vm_events_fold_cpu(int cpu) #define count_vm_numa_events(x, y) count_vm_events(x, y) #else #define count_vm_numa_event(x) do {} while (0) -#define count_vm_numa_events(x, y) do {} while (0) +#define count_vm_numa_events(x, y) do { (void)(y); } while (0) #endif /* CONFIG_NUMA_BALANCING */ #define __count_zone_vm_events(item, zone, delta) \ diff --git a/include/linux/wait.h b/include/linux/wait.h index 7cb64d4b499d..ac38be2692d8 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -330,6 +330,92 @@ do { \ __ret; \ }) +#define __wait_event_hrtimeout(wq, condition, timeout, state) \ +({ \ + int __ret = 0; \ + DEFINE_WAIT(__wait); \ + struct hrtimer_sleeper __t; \ + \ + hrtimer_init_on_stack(&__t.timer, CLOCK_MONOTONIC, \ + HRTIMER_MODE_REL); \ + hrtimer_init_sleeper(&__t, current); \ + if ((timeout).tv64 != KTIME_MAX) \ + hrtimer_start_range_ns(&__t.timer, timeout, \ + current->timer_slack_ns, \ + HRTIMER_MODE_REL); \ + \ + for (;;) { \ + prepare_to_wait(&wq, &__wait, state); \ + if (condition) \ + break; \ + if (state == TASK_INTERRUPTIBLE && \ + signal_pending(current)) { \ + __ret = -ERESTARTSYS; \ + break; \ + } \ + if (!__t.task) { \ + __ret = -ETIME; \ + break; \ + } \ + schedule(); \ + } \ + \ + hrtimer_cancel(&__t.timer); \ + destroy_hrtimer_on_stack(&__t.timer); \ + finish_wait(&wq, &__wait); \ + __ret; \ +}) + +/** + * wait_event_hrtimeout - sleep until a condition gets true or a timeout elapses + * @wq: the waitqueue to wait on + * @condition: a C expression for the event to wait for + * @timeout: timeout, as a ktime_t + * + * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the + * @condition evaluates to true or a signal is received. + * The @condition is checked each time the waitqueue @wq is woken up. + * + * wake_up() has to be called after changing any variable that could + * change the result of the wait condition. + * + * The function returns 0 if @condition became true, or -ETIME if the timeout + * elapsed. + */ +#define wait_event_hrtimeout(wq, condition, timeout) \ +({ \ + int __ret = 0; \ + if (!(condition)) \ + __ret = __wait_event_hrtimeout(wq, condition, timeout, \ + TASK_UNINTERRUPTIBLE); \ + __ret; \ +}) + +/** + * wait_event_interruptible_hrtimeout - sleep until a condition gets true or a timeout elapses + * @wq: the waitqueue to wait on + * @condition: a C expression for the event to wait for + * @timeout: timeout, as a ktime_t + * + * The process is put to sleep (TASK_INTERRUPTIBLE) until the + * @condition evaluates to true or a signal is received. + * The @condition is checked each time the waitqueue @wq is woken up. + * + * wake_up() has to be called after changing any variable that could + * change the result of the wait condition. + * + * The function returns 0 if @condition became true, -ERESTARTSYS if it was + * interrupted by a signal, or -ETIME if the timeout elapsed. + */ +#define wait_event_interruptible_hrtimeout(wq, condition, timeout) \ +({ \ + long __ret = 0; \ + if (!(condition)) \ + __ret = __wait_event_hrtimeout(wq, condition, timeout, \ + TASK_INTERRUPTIBLE); \ + __ret; \ +}) + #define __wait_event_interruptible_exclusive(wq, condition, ret) \ do { \ DEFINE_WAIT(__wait); \ diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 9a9367c0c076..579a5007c696 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -5,6 +5,7 @@ #define WRITEBACK_H #include <linux/sched.h> +#include <linux/workqueue.h> #include <linux/fs.h> DECLARE_PER_CPU(int, dirty_throttle_leaks); diff --git a/include/net/ax25.h b/include/net/ax25.h index 53539acbd81a..89ed9ac5701f 100644 --- a/include/net/ax25.h +++ b/include/net/ax25.h @@ -161,8 +161,8 @@ typedef struct ax25_uid_assoc { ax25_address call; } ax25_uid_assoc; -#define ax25_uid_for_each(__ax25, node, list) \ - hlist_for_each_entry(__ax25, node, list, uid_node) +#define ax25_uid_for_each(__ax25, list) \ + hlist_for_each_entry(__ax25, list, uid_node) #define ax25_uid_hold(ax25) \ atomic_inc(&((ax25)->refcount)) @@ -247,8 +247,8 @@ typedef struct ax25_cb { #define ax25_sk(__sk) ((ax25_cb *)(__sk)->sk_protinfo) -#define ax25_for_each(__ax25, node, list) \ - hlist_for_each_entry(__ax25, node, list, ax25_node) +#define ax25_for_each(__ax25, list) \ + hlist_for_each_entry(__ax25, list, ax25_node) #define ax25_cb_hold(__ax25) \ atomic_inc(&((__ax25)->refcount)) diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 7b2ae9d37076..ef83d9e844b5 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -94,8 +94,8 @@ static inline struct net *ib_net(struct inet_bind_bucket *ib) return read_pnet(&ib->ib_net); } -#define inet_bind_bucket_for_each(tb, pos, head) \ - hlist_for_each_entry(tb, pos, head, node) +#define inet_bind_bucket_for_each(tb, head) \ + hlist_for_each_entry(tb, head, node) struct inet_bind_hashbucket { spinlock_t lock; diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index 7d658d577368..f908dfc06505 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -178,11 +178,11 @@ static inline int inet_twsk_del_dead_node(struct inet_timewait_sock *tw) #define inet_twsk_for_each(tw, node, head) \ hlist_nulls_for_each_entry(tw, node, head, tw_node) -#define inet_twsk_for_each_inmate(tw, node, jail) \ - hlist_for_each_entry(tw, node, jail, tw_death_node) +#define inet_twsk_for_each_inmate(tw, jail) \ + hlist_for_each_entry(tw, jail, tw_death_node) -#define inet_twsk_for_each_inmate_safe(tw, node, safe, jail) \ - hlist_for_each_entry_safe(tw, node, safe, jail, tw_death_node) +#define inet_twsk_for_each_inmate_safe(tw, safe, jail) \ + hlist_for_each_entry_safe(tw, safe, jail, tw_death_node) static inline struct inet_timewait_sock *inet_twsk(const struct sock *sk) { diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 68c69d54d392..66e6c013bff4 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -966,7 +966,7 @@ struct netns_ipvs { int sysctl_snat_reroute; int sysctl_sync_ver; int sysctl_sync_ports; - int sysctl_sync_qlen_max; + unsigned long sysctl_sync_qlen_max; int sysctl_sync_sock_size; int sysctl_cache_bypass; int sysctl_expire_nodest_conn; diff --git a/include/net/netrom.h b/include/net/netrom.h index f0793c1cb5f8..121dcf854db5 100644 --- a/include/net/netrom.h +++ b/include/net/netrom.h @@ -154,17 +154,17 @@ static __inline__ void nr_node_unlock(struct nr_node *nr_node) nr_node_put(nr_node); } -#define nr_neigh_for_each(__nr_neigh, node, list) \ - hlist_for_each_entry(__nr_neigh, node, list, neigh_node) +#define nr_neigh_for_each(__nr_neigh, list) \ + hlist_for_each_entry(__nr_neigh, list, neigh_node) -#define nr_neigh_for_each_safe(__nr_neigh, node, node2, list) \ - hlist_for_each_entry_safe(__nr_neigh, node, node2, list, neigh_node) +#define nr_neigh_for_each_safe(__nr_neigh, node2, list) \ + hlist_for_each_entry_safe(__nr_neigh, node2, list, neigh_node) -#define nr_node_for_each(__nr_node, node, list) \ - hlist_for_each_entry(__nr_node, node, list, node_node) +#define nr_node_for_each(__nr_node, list) \ + hlist_for_each_entry(__nr_node, list, node_node) -#define nr_node_for_each_safe(__nr_node, node, node2, list) \ - hlist_for_each_entry_safe(__nr_node, node, node2, list, node_node) +#define nr_node_for_each_safe(__nr_node, node2, list) \ + hlist_for_each_entry_safe(__nr_node, node2, list, node_node) /*********************************************************************/ diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 2d06c2a53de1..cfd484e2a55a 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -339,11 +339,10 @@ static inline struct Qdisc_class_common * qdisc_class_find(const struct Qdisc_class_hash *hash, u32 id) { struct Qdisc_class_common *cl; - struct hlist_node *n; unsigned int h; h = qdisc_class_hash(id, hash->hashmask); - hlist_for_each_entry(cl, n, &hash->hash[h], hnode) { + hlist_for_each_entry(cl, &hash->hash[h], hnode) { if (cl->classid == id) return cl; } diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 7fdf298a47ef..df85a0c0f2d5 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -675,8 +675,8 @@ static inline int sctp_vtag_hashfn(__u16 lport, __u16 rport, __u32 vtag) return h & (sctp_assoc_hashsize - 1); } -#define sctp_for_each_hentry(epb, node, head) \ - hlist_for_each_entry(epb, node, head, node) +#define sctp_for_each_hentry(epb, head) \ + hlist_for_each_entry(epb, head, node) /* Is a socket of this style? */ #define sctp_style(sk, style) __sctp_style((sk), (SCTP_SOCKET_##style)) diff --git a/include/net/sock.h b/include/net/sock.h index a340ab46b41c..62da8d1a1036 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -606,24 +606,23 @@ static inline void sk_add_bind_node(struct sock *sk, hlist_add_head(&sk->sk_bind_node, list); } -#define sk_for_each(__sk, node, list) \ - hlist_for_each_entry(__sk, node, list, sk_node) -#define sk_for_each_rcu(__sk, node, list) \ - hlist_for_each_entry_rcu(__sk, node, list, sk_node) +#define sk_for_each(__sk, list) \ + hlist_for_each_entry(__sk, list, sk_node) +#define sk_for_each_rcu(__sk, list) \ + hlist_for_each_entry_rcu(__sk, list, sk_node) #define sk_nulls_for_each(__sk, node, list) \ hlist_nulls_for_each_entry(__sk, node, list, sk_nulls_node) #define sk_nulls_for_each_rcu(__sk, node, list) \ hlist_nulls_for_each_entry_rcu(__sk, node, list, sk_nulls_node) -#define sk_for_each_from(__sk, node) \ - if (__sk && ({ node = &(__sk)->sk_node; 1; })) \ - hlist_for_each_entry_from(__sk, node, sk_node) +#define sk_for_each_from(__sk) \ + hlist_for_each_entry_from(__sk, sk_node) #define sk_nulls_for_each_from(__sk, node) \ if (__sk && ({ node = &(__sk)->sk_nulls_node; 1; })) \ hlist_nulls_for_each_entry_from(__sk, node, sk_nulls_node) -#define sk_for_each_safe(__sk, node, tmp, list) \ - hlist_for_each_entry_safe(__sk, node, tmp, list, sk_node) -#define sk_for_each_bound(__sk, node, list) \ - hlist_for_each_entry(__sk, node, list, sk_bind_node) +#define sk_for_each_safe(__sk, tmp, list) \ + hlist_for_each_entry_safe(__sk, tmp, list, sk_node) +#define sk_for_each_bound(__sk, list) \ + hlist_for_each_entry(__sk, list, sk_bind_node) static inline struct user_namespace *sk_user_ns(struct sock *sk) { diff --git a/include/uapi/linux/eventpoll.h b/include/uapi/linux/eventpoll.h index 2c267bcbb85c..8c99ce7202c5 100644 --- a/include/uapi/linux/eventpoll.h +++ b/include/uapi/linux/eventpoll.h @@ -25,6 +25,7 @@ #define EPOLL_CTL_ADD 1 #define EPOLL_CTL_DEL 2 #define EPOLL_CTL_MOD 3 +#define EPOLL_CTL_DISABLE 4 /* * Request the handling of system wakeup events so as to prevent system suspends diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 780d4c6093eb..c7fc1e6517c3 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -86,6 +86,9 @@ struct inodes_stat_t { #define MS_KERNMOUNT (1<<22) /* this is a kern_mount call */ #define MS_I_VERSION (1<<23) /* Update inode I_version field */ #define MS_STRICTATIME (1<<24) /* Always perform atime updates */ + +/* These sb flags are internal to the kernel */ +#define MS_SNAP_STABLE (1<<27) /* Snapshot pages during writeback, if needed */ #define MS_NOSEC (1<<28) #define MS_BORN (1<<29) #define MS_ACTIVE (1<<30) diff --git a/include/uapi/linux/ipmi.h b/include/uapi/linux/ipmi.h index 33fbc99b3812..7b26a62e5707 100644 --- a/include/uapi/linux/ipmi.h +++ b/include/uapi/linux/ipmi.h @@ -59,15 +59,7 @@ * if it becomes full and it is queried once a second to see if * anything is in it. Incoming commands to the driver will get * delivered as commands. - * - * This driver provides two main interfaces: one for in-kernel - * applications and another for userland applications. The - * capabilities are basically the same for both interface, although - * the interfaces are somewhat different. The stuff in the - * #ifdef __KERNEL__ below is the in-kernel interface. The userland - * interface is defined later in the file. */ - - + */ /* * This is an overlay for all the address types, so it's easy to diff --git a/include/uapi/linux/msdos_fs.h b/include/uapi/linux/msdos_fs.h index 996719f82e28..f055e58b3147 100644 --- a/include/uapi/linux/msdos_fs.h +++ b/include/uapi/linux/msdos_fs.h @@ -87,6 +87,8 @@ #define IS_FSINFO(x) (le32_to_cpu((x)->signature1) == FAT_FSINFO_SIG1 \ && le32_to_cpu((x)->signature2) == FAT_FSINFO_SIG2) +#define FAT_STATE_DIRTY 0x01 + struct __fat_dirent { long d_ino; __kernel_off_t d_off; @@ -120,14 +122,34 @@ struct fat_boot_sector { __le32 hidden; /* hidden sectors (unused) */ __le32 total_sect; /* number of sectors (if sectors == 0) */ - /* The following fields are only used by FAT32 */ - __le32 fat32_length; /* sectors/FAT */ - __le16 flags; /* bit 8: fat mirroring, low 4: active fat */ - __u8 version[2]; /* major, minor filesystem version */ - __le32 root_cluster; /* first cluster in root directory */ - __le16 info_sector; /* filesystem info sector */ - __le16 backup_boot; /* backup boot sector */ - __le16 reserved2[6]; /* Unused */ + union { + struct { + /* Extended BPB Fields for FAT16 */ + __u8 drive_number; /* Physical drive number */ + __u8 state; /* undocumented, but used + for mount state. */ + /* other fiealds are not added here */ + } fat16; + + struct { + /* only used by FAT32 */ + __le32 length; /* sectors/FAT */ + __le16 flags; /* bit 8: fat mirroring, + low 4: active fat */ + __u8 version[2]; /* major, minor filesystem + version */ + __le32 root_cluster; /* first cluster in + root directory */ + __le16 info_sector; /* filesystem info sector */ + __le16 backup_boot; /* backup boot sector */ + __le16 reserved2[6]; /* Unused */ + /* Extended BPB Fields for FAT32 */ + __u8 drive_number; /* Physical drive number */ + __u8 state; /* undocumented, but used + for mount state. */ + /* other fiealds are not added here */ + } fat32; + }; }; struct fat_boot_fsinfo { diff --git a/include/uapi/linux/signalfd.h b/include/uapi/linux/signalfd.h index 492c6def340d..bc3184965b89 100644 --- a/include/uapi/linux/signalfd.h +++ b/include/uapi/linux/signalfd.h @@ -15,6 +15,7 @@ /* Flags for signalfd4. */ #define SFD_CLOEXEC O_CLOEXEC #define SFD_NONBLOCK O_NONBLOCK +#define SFD_RAW O_DIRECT struct signalfd_siginfo { __u32 ssi_signo; diff --git a/include/uapi/linux/xattr.h b/include/uapi/linux/xattr.h index 26607bd965fa..e4629b93bdd6 100644 --- a/include/uapi/linux/xattr.h +++ b/include/uapi/linux/xattr.h @@ -15,19 +15,22 @@ /* Namespaces */ #define XATTR_OS2_PREFIX "os2." -#define XATTR_OS2_PREFIX_LEN (sizeof (XATTR_OS2_PREFIX) - 1) +#define XATTR_OS2_PREFIX_LEN (sizeof(XATTR_OS2_PREFIX) - 1) + +#define XATTR_MAC_OSX_PREFIX "osx." +#define XATTR_MAC_OSX_PREFIX_LEN (sizeof(XATTR_MAC_OSX_PREFIX) - 1) #define XATTR_SECURITY_PREFIX "security." -#define XATTR_SECURITY_PREFIX_LEN (sizeof (XATTR_SECURITY_PREFIX) - 1) +#define XATTR_SECURITY_PREFIX_LEN (sizeof(XATTR_SECURITY_PREFIX) - 1) #define XATTR_SYSTEM_PREFIX "system." -#define XATTR_SYSTEM_PREFIX_LEN (sizeof (XATTR_SYSTEM_PREFIX) - 1) +#define XATTR_SYSTEM_PREFIX_LEN (sizeof(XATTR_SYSTEM_PREFIX) - 1) #define XATTR_TRUSTED_PREFIX "trusted." -#define XATTR_TRUSTED_PREFIX_LEN (sizeof (XATTR_TRUSTED_PREFIX) - 1) +#define XATTR_TRUSTED_PREFIX_LEN (sizeof(XATTR_TRUSTED_PREFIX) - 1) #define XATTR_USER_PREFIX "user." -#define XATTR_USER_PREFIX_LEN (sizeof (XATTR_USER_PREFIX) - 1) +#define XATTR_USER_PREFIX_LEN (sizeof(XATTR_USER_PREFIX) - 1) /* Security namespace */ #define XATTR_EVM_SUFFIX "evm" diff --git a/include/video/mmp_disp.h b/include/video/mmp_disp.h new file mode 100644 index 000000000000..b9dd1fbb0082 --- /dev/null +++ b/include/video/mmp_disp.h @@ -0,0 +1,352 @@ +/* + * linux/include/video/mmp_disp.h + * Header file for Marvell MMP Display Controller + * + * Copyright (C) 2012 Marvell Technology Group Ltd. + * Authors: Zhou Zhu <zzhu3@marvell.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + * + */ + +#ifndef _MMP_DISP_H_ +#define _MMP_DISP_H_ +#include <linux/kthread.h> + +enum { + PIXFMT_UYVY = 0, + PIXFMT_VYUY, + PIXFMT_YUYV, + PIXFMT_YUV422P, + PIXFMT_YVU422P, + PIXFMT_YUV420P, + PIXFMT_YVU420P, + PIXFMT_RGB565 = 0x100, + PIXFMT_BGR565, + PIXFMT_RGB1555, + PIXFMT_BGR1555, + PIXFMT_RGB888PACK, + PIXFMT_BGR888PACK, + PIXFMT_RGB888UNPACK, + PIXFMT_BGR888UNPACK, + PIXFMT_RGBA888, + PIXFMT_BGRA888, + PIXFMT_RGB666, /* for output usage */ + PIXFMT_PSEUDOCOLOR = 0x200, +}; + +static inline int pixfmt_to_stride(int pix_fmt) +{ + switch (pix_fmt) { + case PIXFMT_RGB565: + case PIXFMT_BGR565: + case PIXFMT_RGB1555: + case PIXFMT_BGR1555: + case PIXFMT_UYVY: + case PIXFMT_VYUY: + case PIXFMT_YUYV: + return 2; + case PIXFMT_RGB888UNPACK: + case PIXFMT_BGR888UNPACK: + case PIXFMT_RGBA888: + case PIXFMT_BGRA888: + return 4; + case PIXFMT_RGB888PACK: + case PIXFMT_BGR888PACK: + return 3; + case PIXFMT_YUV422P: + case PIXFMT_YVU422P: + case PIXFMT_YUV420P: + case PIXFMT_YVU420P: + case PIXFMT_PSEUDOCOLOR: + return 1; + default: + return 0; + } +} + +/* parameters used by path/overlay */ +/* overlay related para: win/addr */ +struct mmp_win { + /* position/size of window */ + u16 xsrc; + u16 ysrc; + u16 xdst; + u16 ydst; + u16 xpos; + u16 ypos; + u16 left_crop; + u16 right_crop; + u16 up_crop; + u16 bottom_crop; + int pix_fmt; +}; + +struct mmp_addr { + /* phys address */ + u32 phys[6]; +}; + +/* path related para: mode */ +struct mmp_mode { + const char *name; + u32 refresh; + u32 xres; + u32 yres; + u32 left_margin; + u32 right_margin; + u32 upper_margin; + u32 lower_margin; + u32 hsync_len; + u32 vsync_len; + u32 hsync_invert; + u32 vsync_invert; + u32 invert_pixclock; + u32 pixclock_freq; + int pix_fmt_out; +}; + +/* main structures */ +struct mmp_path; +struct mmp_overlay; +struct mmp_panel; + +/* status types */ +enum { + MMP_OFF = 0, + MMP_ON, +}; + +static inline const char *stat_name(int stat) +{ + switch (stat) { + case MMP_OFF: + return "OFF"; + case MMP_ON: + return "ON"; + default: + return "UNKNOWNSTAT"; + } +} + +struct mmp_overlay_ops { + /* should be provided by driver */ + void (*set_fetch)(struct mmp_overlay *overlay, int fetch_id); + void (*set_onoff)(struct mmp_overlay *overlay, int status); + void (*set_win)(struct mmp_overlay *overlay, struct mmp_win *win); + int (*set_addr)(struct mmp_overlay *overlay, struct mmp_addr *addr); +}; + +/* overlay describes a z-order indexed slot in each path. */ +struct mmp_overlay { + int id; + const char *name; + struct mmp_path *path; + + /* overlay info: private data */ + int dmafetch_id; + struct mmp_addr addr; + struct mmp_win win; + + /* state */ + int open_count; + int status; + struct mutex access_ok; + + struct mmp_overlay_ops *ops; +}; + +/* panel type */ +enum { + PANELTYPE_ACTIVE = 0, + PANELTYPE_SMART, + PANELTYPE_TV, + PANELTYPE_DSI_CMD, + PANELTYPE_DSI_VIDEO, +}; + +struct mmp_panel { + /* use node to register to list */ + struct list_head node; + const char *name; + /* path name used to connect to proper path configed */ + const char *plat_path_name; + struct device *dev; + int panel_type; + void *plat_data; + int (*get_modelist)(struct mmp_panel *panel, + struct mmp_mode **modelist); + void (*set_mode)(struct mmp_panel *panel, + struct mmp_mode *mode); + void (*set_onoff)(struct mmp_panel *panel, + int status); +}; + +struct mmp_path_ops { + int (*check_status)(struct mmp_path *path); + struct mmp_overlay *(*get_overlay)(struct mmp_path *path, + int overlay_id); + int (*get_modelist)(struct mmp_path *path, + struct mmp_mode **modelist); + + /* follow ops should be provided by driver */ + void (*set_mode)(struct mmp_path *path, struct mmp_mode *mode); + void (*set_onoff)(struct mmp_path *path, int status); + /* todo: add query */ +}; + +/* path output types */ +enum { + PATH_OUT_PARALLEL, + PATH_OUT_DSI, + PATH_OUT_HDMI, +}; + +/* path is main part of mmp-disp */ +struct mmp_path { + /* use node to register to list */ + struct list_head node; + + /* init data */ + struct device *dev; + + int id; + const char *name; + int output_type; + struct mmp_panel *panel; + void *plat_data; + + /* dynamic use */ + struct mmp_mode mode; + + /* state */ + int open_count; + int status; + struct mutex access_ok; + + struct mmp_path_ops ops; + + /* layers */ + int overlay_num; + struct mmp_overlay overlays[0]; +}; + +extern struct mmp_path *mmp_get_path(const char *name); +static inline void mmp_path_set_mode(struct mmp_path *path, + struct mmp_mode *mode) +{ + if (path) + path->ops.set_mode(path, mode); +} +static inline void mmp_path_set_onoff(struct mmp_path *path, int status) +{ + if (path) + path->ops.set_onoff(path, status); +} +static inline int mmp_path_get_modelist(struct mmp_path *path, + struct mmp_mode **modelist) +{ + if (path) + return path->ops.get_modelist(path, modelist); + return 0; +} +static inline struct mmp_overlay *mmp_path_get_overlay( + struct mmp_path *path, int overlay_id) +{ + if (path) + return path->ops.get_overlay(path, overlay_id); + return NULL; +} +static inline void mmp_overlay_set_fetch(struct mmp_overlay *overlay, + int fetch_id) +{ + if (overlay) + overlay->ops->set_fetch(overlay, fetch_id); +} +static inline void mmp_overlay_set_onoff(struct mmp_overlay *overlay, + int status) +{ + if (overlay) + overlay->ops->set_onoff(overlay, status); +} +static inline void mmp_overlay_set_win(struct mmp_overlay *overlay, + struct mmp_win *win) +{ + if (overlay) + overlay->ops->set_win(overlay, win); +} +static inline int mmp_overlay_set_addr(struct mmp_overlay *overlay, + struct mmp_addr *addr) +{ + if (overlay) + return overlay->ops->set_addr(overlay, addr); + return 0; +} + +/* + * driver data is set from each detailed ctrl driver for path usage + * it defined a common interface that plat driver need to implement + */ +struct mmp_path_info { + /* driver data, set when registed*/ + const char *name; + struct device *dev; + int id; + int output_type; + int overlay_num; + void (*set_mode)(struct mmp_path *path, struct mmp_mode *mode); + void (*set_onoff)(struct mmp_path *path, int status); + struct mmp_overlay_ops *overlay_ops; + void *plat_data; +}; + +extern struct mmp_path *mmp_register_path( + struct mmp_path_info *info); +extern void mmp_unregister_path(struct mmp_path *path); +extern void mmp_register_panel(struct mmp_panel *panel); +extern void mmp_unregister_panel(struct mmp_panel *panel); + +/* defintions for platform data */ +/* interface for buffer driver */ +struct mmp_buffer_driver_mach_info { + const char *name; + const char *path_name; + int overlay_id; + int dmafetch_id; + int default_pixfmt; +}; + +/* interface for controllers driver */ +struct mmp_mach_path_config { + const char *name; + int overlay_num; + int output_type; + u32 path_config; + u32 link_config; +}; + +struct mmp_mach_plat_info { + const char *name; + const char *clk_name; + int path_num; + struct mmp_mach_path_config *paths; +}; + +/* interface for panel drivers */ +struct mmp_mach_panel_info { + const char *name; + void (*plat_set_onoff)(int status); + const char *plat_path_name; +}; +#endif /* _MMP_DISP_H_ */ diff --git a/init/Kconfig b/init/Kconfig index aa830716f3b6..ed24d1bd454a 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -891,6 +891,23 @@ config MEMCG_KMEM the kmem extension can use it to guarantee that no group of processes will ever exhaust kernel resources alone. +config MEMCG_DEBUG_ASYNC_DESTROY + bool "Memory Resource Controller Debug asynchronous object destruction" + depends on MEMCG_KMEM || MEMCG_SWAP + default n + help + When a memcg is destroyed, the memory consumed by it may not be + immediately freed. This is because when some extensions are used, such + as swap or kernel memory, objects can outlive the group and hold a + reference to it. + + If this is the case, the dangling_memcgs file will show information + about what are the memcgs still alive, and which references are still + preventing it to be freed. There is nothing wrong with that, but it is + very useful when debugging, to know where this memory is being held. + This is a developer-oriented debugging facility only, and no + guarantees of interface stability will be given. + config CGROUP_HUGETLB bool "HugeTLB Resource Controller for Control Groups" depends on RESOURCE_COUNTERS && HUGETLB_PAGE diff --git a/ipc/sem.c b/ipc/sem.c index 58d31f1c1eb5..ebd8fececcfc 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -61,8 +61,8 @@ * - A woken up task may not even touch the semaphore array anymore, it may * have been destroyed already by a semctl(RMID). * - The synchronizations between wake-ups due to a timeout/signal and a - * wake-up due to a completed semaphore operation is achieved by using an - * intermediate state (IN_WAKEUP). + * wake-up due to a completed semaphore operation is achieved by using a + * special wakeup scheme (queuewakeup_wait and support functions) * - UNDO values are stored in an array (one per process and per * semaphore array, lazily allocated). For backwards compatibility, multiple * modes for the UNDO variables are supported (per process, per thread) @@ -90,6 +90,135 @@ #include <asm/uaccess.h> #include "util.h" + +#ifdef CONFIG_PREEMPT_RT_BASE + #define SYSVSEM_COMPLETION 1 +#else + #define SYSVSEM_CUSTOM 1 +#endif + +#ifdef SYSVSEM_COMPLETION + /* Using a completion causes some overhead, but avoids a busy loop + * that increases the worst case latency. + */ + struct queue_done { + struct completion done; + }; + + static void queuewakeup_prepare(void) + { + /* no preparation necessary */ + } + + static void queuewakeup_completed(void) + { + /* empty */ + } + + static void queuewakeup_block(struct queue_done *qd) + { + /* empty */ + } + + static void queuewakeup_handsoff(struct queue_done *qd) + { + complete_all(&qd->done); + } + + static void queuewakeup_init(struct queue_done *qd) + { + init_completion(&qd->done); + } + + static void queuewakeup_wait(struct queue_done *qd) + { + wait_for_completion(&qd->done); + } + +#elif defined(SYSVSEM_SPINLOCK) + /* Note: Spinlocks do not work because: + * - lockdep complains [could be fixed] + * - only 255 concurrent spin_lock() calls are permitted, then the + * preempt-counter overflows + */ +#error SYSVSEM_SPINLOCK is a prove of concept, does not work. + struct queue_done { + spinlock_t done; + }; + + static void queuewakeup_prepare(void) + { + /* empty */ + } + + static void queuewakeup_completed(void) + { + /* empty */ + } + + static void queuewakeup_block(struct queue_done *qd) + { + BUG_ON(spin_is_locked(&qd->done)); + spin_lock(&qd->done); + } + + static void queuewakeup_handsoff(struct queue_done *qd) + { + spin_unlock(&qd->done); + } + + static void queuewakeup_init(struct queue_done *qd) + { + spin_lock_init(&qd->done); + } + + static void queuewakeup_wait(struct queue_done *qd) + { + spin_unlock_wait(&qd->done); + } +#else + struct queue_done { + atomic_t done; + }; + + static void queuewakeup_prepare(void) + { + preempt_disable(); + } + + static void queuewakeup_completed(void) + { + preempt_enable(); + } + + static void queuewakeup_block(struct queue_done *qd) + { + BUG_ON(atomic_read(&qd->done) != 1); + atomic_set(&qd->done, 2); + } + + static void queuewakeup_handsoff(struct queue_done *qd) + { + BUG_ON(atomic_read(&qd->done) != 2); + smp_mb(); + atomic_set(&qd->done, 1); + } + + static void queuewakeup_init(struct queue_done *qd) + { + atomic_set(&qd->done, 1); + } + + static void queuewakeup_wait(struct queue_done *qd) + { + while (atomic_read(&qd->done) != 1) + cpu_relax(); + + smp_mb(); + } +#endif + + /* One semaphore structure for each semaphore in the system. */ struct sem { int semval; /* current value */ @@ -108,6 +237,7 @@ struct sem_queue { struct sembuf *sops; /* array of pending operations */ int nsops; /* number of operations */ int alter; /* does *sops alter the array? */ + struct queue_done done; /* completion synchronization */ }; /* Each task has a list of undo requests. They are executed automatically @@ -245,23 +375,27 @@ static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s) * - queue.status is initialized to -EINTR before blocking. * - wakeup is performed by * * unlinking the queue entry from sma->sem_pending - * * setting queue.status to IN_WAKEUP - * This is the notification for the blocked thread that a - * result value is imminent. + * * setting queue.status to the actual result code + * This is the notification for the blocked thread that someone + * (usually: update_queue()) completed the semtimedop() operation. * * call wake_up_process - * * set queue.status to the final value. + * * queuewakeup_handsoff(&q->done); * - the previously blocked thread checks queue.status: - * * if it's IN_WAKEUP, then it must wait until the value changes - * * if it's not -EINTR, then the operation was completed by - * update_queue. semtimedop can return queue.status without - * performing any operation on the sem array. - * * otherwise it must acquire the spinlock and check what's up. + * * if it's not -EINTR, then someone completed the operation. + * First, queuewakeup_wait() must be called. Afterwards, + * semtimedop must return queue.status without performing any + * operation on the sem array. + * - otherwise it must acquire the spinlock and repeat the test + * - If it is still -EINTR, then no update_queue() completed the + * operation, thus semtimedop() can proceed normally. * - * The two-stage algorithm is necessary to protect against the following + * queuewakeup_wait() is necessary to protect against the following * races: * - if queue.status is set after wake_up_process, then the woken up idle * thread could race forward and try (and fail) to acquire sma->lock - * before update_queue had a chance to set queue.status + * before update_queue had a chance to set queue.status. + * More importantly, it would mean that wake_up_process must be done + * while holding sma->lock, i.e. this would reduce the scalability. * - if queue.status is written before wake_up_process and if the * blocked process is woken up by a signal between writing * queue.status and the wake_up_process, then the woken up @@ -271,7 +405,6 @@ static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s) * (yes, this happened on s390 with sysv msg). * */ -#define IN_WAKEUP 1 /** * newary - Create a new semaphore set @@ -461,15 +594,11 @@ undo: static void wake_up_sem_queue_prepare(struct list_head *pt, struct sem_queue *q, int error) { - if (list_empty(pt)) { - /* - * Hold preempt off so that we don't get preempted and have the - * wakee busy-wait until we're scheduled back on. - */ - preempt_disable(); - } - q->status = IN_WAKEUP; - q->pid = error; + if (list_empty(pt)) + queuewakeup_prepare(); + + queuewakeup_block(&q->done); + q->status = error; list_add_tail(&q->simple_list, pt); } @@ -480,8 +609,8 @@ static void wake_up_sem_queue_prepare(struct list_head *pt, * * Do the actual wake-up. * The function is called without any locks held, thus the semaphore array - * could be destroyed already and the tasks can disappear as soon as the - * status is set to the actual return code. + * could be destroyed already and the tasks can disappear as soon as + * queuewakeup_handsoff() is called. */ static void wake_up_sem_queue_do(struct list_head *pt) { @@ -491,12 +620,11 @@ static void wake_up_sem_queue_do(struct list_head *pt) did_something = !list_empty(pt); list_for_each_entry_safe(q, t, pt, simple_list) { wake_up_process(q->sleeper); - /* q can disappear immediately after writing q->status. */ - smp_wmb(); - q->status = q->pid; + /* q can disappear immediately after completing q->done */ + queuewakeup_handsoff(&q->done); } if (did_something) - preempt_enable(); + queuewakeup_completed(); } static void unlink_queue(struct sem_array *sma, struct sem_queue *q) @@ -1302,33 +1430,6 @@ out: return un; } - -/** - * get_queue_result - Retrieve the result code from sem_queue - * @q: Pointer to queue structure - * - * Retrieve the return code from the pending queue. If IN_WAKEUP is found in - * q->status, then we must loop until the value is replaced with the final - * value: This may happen if a task is woken up by an unrelated event (e.g. - * signal) and in parallel the task is woken up by another task because it got - * the requested semaphores. - * - * The function can be called with or without holding the semaphore spinlock. - */ -static int get_queue_result(struct sem_queue *q) -{ - int error; - - error = q->status; - while (unlikely(error == IN_WAKEUP)) { - cpu_relax(); - error = q->status; - } - - return error; -} - - SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops, unsigned, nsops, const struct timespec __user *, timeout) { @@ -1474,6 +1575,7 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops, queue.status = -EINTR; queue.sleeper = current; + queuewakeup_init(&queue.done); sleep_again: current->state = TASK_INTERRUPTIBLE; @@ -1484,17 +1586,14 @@ sleep_again: else schedule(); - error = get_queue_result(&queue); + error = queue.status; if (error != -EINTR) { /* fast path: update_queue already obtained all requested - * resources. - * Perform a smp_mb(): User space could assume that semop() - * is a memory barrier: Without the mb(), the cpu could - * speculatively read in user space stale data that was - * overwritten by the previous owner of the semaphore. + * resources. Just ensure that update_queue completed + * it's access to &queue. */ - smp_mb(); + queuewakeup_wait(&queue.done); goto out_free; } @@ -1504,23 +1603,16 @@ sleep_again: /* * Wait until it's guaranteed that no wakeup_sem_queue_do() is ongoing. */ - error = get_queue_result(&queue); - - /* - * Array removed? If yes, leave without sem_unlock(). - */ - if (IS_ERR(sma)) { - goto out_free; - } - - - /* - * If queue.status != -EINTR we are woken up by another process. - * Leave without unlink_queue(), but with sem_unlock(). - */ - + error = queue.status; if (error != -EINTR) { - goto out_unlock_free; + /* If there is a return code, then we can leave immediately. */ + if (!IS_ERR(sma)) { + /* sem_lock() succeeded - then unlock */ + sem_unlock(sma); + } + /* Except that we must wait for the hands-off */ + queuewakeup_wait(&queue.done); + goto out_free; } /* diff --git a/ipc/shm.c b/ipc/shm.c index 4fa6d8fee730..be3ec9ae454e 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -967,11 +967,11 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr, unsigned long flags; unsigned long prot; int acc_mode; - unsigned long user_addr; struct ipc_namespace *ns; struct shm_file_data *sfd; struct path path; fmode_t f_mode; + unsigned long populate = 0; err = -EINVAL; if (shmid < 0) @@ -1070,13 +1070,15 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr, goto invalid; } - user_addr = do_mmap_pgoff(file, addr, size, prot, flags, 0); - *raddr = user_addr; + addr = do_mmap_pgoff(file, addr, size, prot, flags, 0, &populate); + *raddr = addr; err = 0; - if (IS_ERR_VALUE(user_addr)) - err = (long)user_addr; + if (IS_ERR_VALUE(addr)) + err = (long)addr; invalid: up_write(¤t->mm->mmap_sem); + if (populate) + mm_populate(addr, populate); out_fput: fput(file); diff --git a/ipc/util.c b/ipc/util.c index 74e1d9c7a98a..91ce0bc621b5 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -252,7 +252,7 @@ int ipc_addid(struct ipc_ids* ids, struct kern_ipc_perm* new, int size) { kuid_t euid; kgid_t egid; - int id, err; + int id; int next_id = ids->next_id; if (size > IPCMNI) @@ -261,17 +261,21 @@ int ipc_addid(struct ipc_ids* ids, struct kern_ipc_perm* new, int size) if (ids->in_use >= size) return -ENOSPC; + idr_preload(GFP_KERNEL); + spin_lock_init(&new->lock); new->deleted = 0; rcu_read_lock(); spin_lock(&new->lock); - err = idr_get_new_above(&ids->ipcs_idr, new, - (next_id < 0) ? 0 : ipcid_to_idx(next_id), &id); - if (err) { + id = idr_alloc(&ids->ipcs_idr, new, + (next_id < 0) ? 0 : ipcid_to_idx(next_id), 0, + GFP_NOWAIT); + idr_preload_end(); + if (id < 0) { spin_unlock(&new->lock); rcu_read_unlock(); - return err; + return id; } ids->in_use++; @@ -307,19 +311,10 @@ static int ipcget_new(struct ipc_namespace *ns, struct ipc_ids *ids, struct ipc_ops *ops, struct ipc_params *params) { int err; -retry: - err = idr_pre_get(&ids->ipcs_idr, GFP_KERNEL); - - if (!err) - return -ENOMEM; down_write(&ids->rw_mutex); err = ops->getnew(ns, params); up_write(&ids->rw_mutex); - - if (err == -EAGAIN) - goto retry; - return err; } @@ -375,9 +370,7 @@ static int ipcget_public(struct ipc_namespace *ns, struct ipc_ids *ids, { struct kern_ipc_perm *ipcp; int flg = params->flg; - int err; -retry: - err = idr_pre_get(&ids->ipcs_idr, GFP_KERNEL); + int err = 0; /* * Take the lock as a writer since we are potentially going to add @@ -413,9 +406,6 @@ retry: } up_write(&ids->rw_mutex); - if (err == -EAGAIN) - goto retry; - return err; } diff --git a/kernel/Makefile b/kernel/Makefile index 454ce54b2a0b..af79b864e068 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -7,7 +7,7 @@ obj-y = fork.o exec_domain.o panic.o printk.o \ sysctl.o sysctl_binary.o capability.o ptrace.o timer.o user.o \ signal.o sys.o kmod.o workqueue.o pid.o task_work.o \ rcupdate.o extable.o params.o posix-timers.o \ - kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \ + kthread.o wait.o sys_ni.o posix-cpu-timers.o mutex.o \ hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \ notifier.o ksysfs.o cred.o \ async.o range.o groups.o lglock.o smpboot.o diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 776ff752bfd8..3710ba80511d 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -554,7 +554,6 @@ static struct css_set *find_existing_css_set( { int i; struct cgroupfs_root *root = cgrp->root; - struct hlist_node *node; struct css_set *cg; unsigned long key; @@ -577,7 +576,7 @@ static struct css_set *find_existing_css_set( } key = css_set_hash(template); - hash_for_each_possible(css_set_table, cg, node, hlist, key) { + hash_for_each_possible(css_set_table, cg, hlist, key) { if (!compare_css_sets(cg, oldcg, cgrp, template)) continue; @@ -1611,7 +1610,6 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, struct cgroupfs_root *existing_root; const struct cred *cred; int i; - struct hlist_node *node; struct css_set *cg; BUG_ON(sb->s_root != NULL); @@ -1666,7 +1664,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, /* Link the top cgroup in this hierarchy into all * the css_set objects */ write_lock(&css_set_lock); - hash_for_each(css_set_table, i, node, cg, hlist) + hash_for_each(css_set_table, i, cg, hlist) link_css_set(&tmp_cg_links, cg, root_cgrp); write_unlock(&css_set_lock); @@ -4457,7 +4455,7 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss) { struct cgroup_subsys_state *css; int i, ret; - struct hlist_node *node, *tmp; + struct hlist_node *tmp; struct css_set *cg; unsigned long key; @@ -4525,7 +4523,7 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss) * this is all done under the css_set_lock. */ write_lock(&css_set_lock); - hash_for_each_safe(css_set_table, i, node, tmp, cg, hlist) { + hash_for_each_safe(css_set_table, i, tmp, cg, hlist) { /* skip entries that we already rehashed */ if (cg->subsys[ss->subsys_id]) continue; @@ -4535,7 +4533,7 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss) cg->subsys[ss->subsys_id] = css; /* recompute hash and restore entry */ key = css_set_hash(cg->subsys); - hash_add(css_set_table, node, key); + hash_add(css_set_table, &cg->hlist, key); } write_unlock(&css_set_lock); @@ -4582,10 +4580,8 @@ void cgroup_unload_subsys(struct cgroup_subsys *ss) offline_css(ss, dummytop); ss->active = 0; - if (ss->use_id) { - idr_remove_all(&ss->idr); + if (ss->use_id) idr_destroy(&ss->idr); - } /* deassign the subsys_id */ subsys[ss->subsys_id] = NULL; @@ -5286,7 +5282,7 @@ EXPORT_SYMBOL_GPL(free_css_id); static struct css_id *get_new_cssid(struct cgroup_subsys *ss, int depth) { struct css_id *newid; - int myid, error, size; + int ret, size; BUG_ON(!ss->use_id); @@ -5294,35 +5290,24 @@ static struct css_id *get_new_cssid(struct cgroup_subsys *ss, int depth) newid = kzalloc(size, GFP_KERNEL); if (!newid) return ERR_PTR(-ENOMEM); - /* get id */ - if (unlikely(!idr_pre_get(&ss->idr, GFP_KERNEL))) { - error = -ENOMEM; - goto err_out; - } + + idr_preload(GFP_KERNEL); spin_lock(&ss->id_lock); /* Don't use 0. allocates an ID of 1-65535 */ - error = idr_get_new_above(&ss->idr, newid, 1, &myid); + ret = idr_alloc(&ss->idr, newid, 1, CSS_ID_MAX + 1, GFP_NOWAIT); spin_unlock(&ss->id_lock); + idr_preload_end(); /* Returns error when there are no free spaces for new ID.*/ - if (error) { - error = -ENOSPC; + if (ret < 0) goto err_out; - } - if (myid > CSS_ID_MAX) - goto remove_idr; - newid->id = myid; + newid->id = ret; newid->depth = depth; return newid; -remove_idr: - error = -ENOSPC; - spin_lock(&ss->id_lock); - idr_remove(&ss->idr, myid); - spin_unlock(&ss->id_lock); err_out: kfree(newid); - return ERR_PTR(error); + return ERR_PTR(ret); } diff --git a/kernel/compat.c b/kernel/compat.c index de6f3244d325..19971d8c7299 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -593,7 +593,7 @@ COMPAT_SYSCALL_DEFINE5(waitid, else ret = put_compat_rusage(&ru, uru); if (ret) - return ret; + return -EFAULT; } BUG_ON(info.si_code & __SI_MASK); diff --git a/kernel/events/core.c b/kernel/events/core.c index 7b6646a8c067..d6df1b950769 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -5126,7 +5126,6 @@ static void do_perf_sw_event(enum perf_type_id type, u32 event_id, { struct swevent_htable *swhash = &__get_cpu_var(swevent_htable); struct perf_event *event; - struct hlist_node *node; struct hlist_head *head; rcu_read_lock(); @@ -5134,7 +5133,7 @@ static void do_perf_sw_event(enum perf_type_id type, u32 event_id, if (!head) goto end; - hlist_for_each_entry_rcu(event, node, head, hlist_entry) { + hlist_for_each_entry_rcu(event, head, hlist_entry) { if (perf_swevent_match(event, type, event_id, data, regs)) perf_swevent_event(event, nr, data, regs); } @@ -5419,7 +5418,6 @@ void perf_tp_event(u64 addr, u64 count, void *record, int entry_size, { struct perf_sample_data data; struct perf_event *event; - struct hlist_node *node; struct perf_raw_record raw = { .size = entry_size, @@ -5429,7 +5427,7 @@ void perf_tp_event(u64 addr, u64 count, void *record, int entry_size, perf_sample_data_init(&data, addr, 0); data.raw = &raw; - hlist_for_each_entry_rcu(event, node, head, hlist_entry) { + hlist_for_each_entry_rcu(event, head, hlist_entry) { if (perf_tp_event_match(event, &data, regs)) perf_swevent_event(event, count, &data, regs); } @@ -5965,13 +5963,9 @@ int perf_pmu_register(struct pmu *pmu, char *name, int type) pmu->name = name; if (type < 0) { - int err = idr_pre_get(&pmu_idr, GFP_KERNEL); - if (!err) - goto free_pdc; - - err = idr_get_new_above(&pmu_idr, pmu, PERF_TYPE_MAX, &type); - if (err) { - ret = err; + type = idr_alloc(&pmu_idr, pmu, PERF_TYPE_MAX, 0, GFP_KERNEL); + if (type < 0) { + ret = type; goto free_pdc; } } diff --git a/kernel/fork.c b/kernel/fork.c index 4133876d8cd2..e6d16bb80254 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -70,6 +70,7 @@ #include <linux/khugepaged.h> #include <linux/signalfd.h> #include <linux/uprobes.h> +#include <linux/aio.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> @@ -364,8 +365,6 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) mm->locked_vm = 0; mm->mmap = NULL; mm->mmap_cache = NULL; - mm->free_area_cache = oldmm->mmap_base; - mm->cached_hole_size = ~0UL; mm->map_count = 0; cpumask_clear(mm_cpumask(mm)); mm->mm_rb = RB_ROOT; @@ -539,8 +538,6 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p) mm->nr_ptes = 0; memset(&mm->rss_stat, 0, sizeof(mm->rss_stat)); spin_lock_init(&mm->page_table_lock); - mm->free_area_cache = TASK_UNMAPPED_BASE; - mm->cached_hole_size = ~0UL; mm_init_aio(mm); mm_init_owner(mm, p); @@ -1861,10 +1858,8 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags) exit_sem(current); } - if (new_nsproxy) { + if (new_nsproxy) switch_task_namespaces(current, new_nsproxy); - new_nsproxy = NULL; - } task_lock(current); @@ -1894,9 +1889,6 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags) } } - if (new_nsproxy) - put_nsproxy(new_nsproxy); - bad_unshare_cleanup_cred: if (new_cred) put_cred(new_cred); diff --git a/kernel/kexec.c b/kernel/kexec.c index 2436ffcec91f..ea097ad7cc37 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -503,8 +503,6 @@ static struct page *kimage_alloc_crash_control_pages(struct kimage *image, if (hole_end > KEXEC_CRASH_CONTROL_MEMORY_LIMIT) break; - if (hole_end > crashk_res.end) - break; /* See if I overlap any of the segments */ for (i = 0; i < image->nr_segments; i++) { unsigned long mstart, mend; @@ -1514,6 +1512,8 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_OFFSET(page, _count); VMCOREINFO_OFFSET(page, mapping); VMCOREINFO_OFFSET(page, lru); + VMCOREINFO_OFFSET(page, _mapcount); + VMCOREINFO_OFFSET(page, private); VMCOREINFO_OFFSET(pglist_data, node_zones); VMCOREINFO_OFFSET(pglist_data, nr_zones); #ifdef CONFIG_FLAT_NODE_MEM_MAP @@ -1536,6 +1536,8 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_NUMBER(PG_lru); VMCOREINFO_NUMBER(PG_private); VMCOREINFO_NUMBER(PG_swapcache); + VMCOREINFO_NUMBER(PG_slab); + VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE); arch_crash_save_vmcoreinfo(); update_vmcoreinfo_note(); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index f423c3ef4a82..b4f77a3ff17e 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -334,11 +334,10 @@ static inline void reset_kprobe_instance(void) struct kprobe __kprobes *get_kprobe(void *addr) { struct hlist_head *head; - struct hlist_node *node; struct kprobe *p; head = &kprobe_table[hash_ptr(addr, KPROBE_HASH_BITS)]; - hlist_for_each_entry_rcu(p, node, head, hlist) { + hlist_for_each_entry_rcu(p, head, hlist) { if (p->addr == addr) return p; } @@ -792,7 +791,6 @@ out: static void __kprobes optimize_all_kprobes(void) { struct hlist_head *head; - struct hlist_node *node; struct kprobe *p; unsigned int i; @@ -803,7 +801,7 @@ static void __kprobes optimize_all_kprobes(void) kprobes_allow_optimization = true; for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; - hlist_for_each_entry_rcu(p, node, head, hlist) + hlist_for_each_entry_rcu(p, head, hlist) if (!kprobe_disabled(p)) optimize_kprobe(p); } @@ -814,7 +812,6 @@ static void __kprobes optimize_all_kprobes(void) static void __kprobes unoptimize_all_kprobes(void) { struct hlist_head *head; - struct hlist_node *node; struct kprobe *p; unsigned int i; @@ -825,7 +822,7 @@ static void __kprobes unoptimize_all_kprobes(void) kprobes_allow_optimization = false; for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; - hlist_for_each_entry_rcu(p, node, head, hlist) { + hlist_for_each_entry_rcu(p, head, hlist) { if (!kprobe_disabled(p)) unoptimize_kprobe(p, false); } @@ -1141,7 +1138,7 @@ void __kprobes kprobe_flush_task(struct task_struct *tk) { struct kretprobe_instance *ri; struct hlist_head *head, empty_rp; - struct hlist_node *node, *tmp; + struct hlist_node *tmp; unsigned long hash, flags = 0; if (unlikely(!kprobes_initialized)) @@ -1152,12 +1149,12 @@ void __kprobes kprobe_flush_task(struct task_struct *tk) hash = hash_ptr(tk, KPROBE_HASH_BITS); head = &kretprobe_inst_table[hash]; kretprobe_table_lock(hash, &flags); - hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { + hlist_for_each_entry_safe(ri, tmp, head, hlist) { if (ri->task == tk) recycle_rp_inst(ri, &empty_rp); } kretprobe_table_unlock(hash, &flags); - hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) { + hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); kfree(ri); } @@ -1166,9 +1163,9 @@ void __kprobes kprobe_flush_task(struct task_struct *tk) static inline void free_rp_inst(struct kretprobe *rp) { struct kretprobe_instance *ri; - struct hlist_node *pos, *next; + struct hlist_node *next; - hlist_for_each_entry_safe(ri, pos, next, &rp->free_instances, hlist) { + hlist_for_each_entry_safe(ri, next, &rp->free_instances, hlist) { hlist_del(&ri->hlist); kfree(ri); } @@ -1178,14 +1175,14 @@ static void __kprobes cleanup_rp_inst(struct kretprobe *rp) { unsigned long flags, hash; struct kretprobe_instance *ri; - struct hlist_node *pos, *next; + struct hlist_node *next; struct hlist_head *head; /* No race here */ for (hash = 0; hash < KPROBE_TABLE_SIZE; hash++) { kretprobe_table_lock(hash, &flags); head = &kretprobe_inst_table[hash]; - hlist_for_each_entry_safe(ri, pos, next, head, hlist) { + hlist_for_each_entry_safe(ri, next, head, hlist) { if (ri->rp == rp) ri->rp = NULL; } @@ -2021,7 +2018,6 @@ static int __kprobes kprobes_module_callback(struct notifier_block *nb, { struct module *mod = data; struct hlist_head *head; - struct hlist_node *node; struct kprobe *p; unsigned int i; int checkcore = (val == MODULE_STATE_GOING); @@ -2038,7 +2034,7 @@ static int __kprobes kprobes_module_callback(struct notifier_block *nb, mutex_lock(&kprobe_mutex); for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; - hlist_for_each_entry_rcu(p, node, head, hlist) + hlist_for_each_entry_rcu(p, head, hlist) if (within_module_init((unsigned long)p->addr, mod) || (checkcore && within_module_core((unsigned long)p->addr, mod))) { @@ -2185,7 +2181,6 @@ static void __kprobes kprobe_seq_stop(struct seq_file *f, void *v) static int __kprobes show_kprobe_addr(struct seq_file *pi, void *v) { struct hlist_head *head; - struct hlist_node *node; struct kprobe *p, *kp; const char *sym = NULL; unsigned int i = *(loff_t *) v; @@ -2194,7 +2189,7 @@ static int __kprobes show_kprobe_addr(struct seq_file *pi, void *v) head = &kprobe_table[i]; preempt_disable(); - hlist_for_each_entry_rcu(p, node, head, hlist) { + hlist_for_each_entry_rcu(p, head, hlist) { sym = kallsyms_lookup((unsigned long)p->addr, NULL, &offset, &modname, namebuf); if (kprobe_aggrprobe(p)) { @@ -2229,7 +2224,6 @@ static const struct file_operations debugfs_kprobes_operations = { static void __kprobes arm_all_kprobes(void) { struct hlist_head *head; - struct hlist_node *node; struct kprobe *p; unsigned int i; @@ -2242,7 +2236,7 @@ static void __kprobes arm_all_kprobes(void) /* Arming kprobes doesn't optimize kprobe itself */ for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; - hlist_for_each_entry_rcu(p, node, head, hlist) + hlist_for_each_entry_rcu(p, head, hlist) if (!kprobe_disabled(p)) arm_kprobe(p); } @@ -2258,7 +2252,6 @@ already_enabled: static void __kprobes disarm_all_kprobes(void) { struct hlist_head *head; - struct hlist_node *node; struct kprobe *p; unsigned int i; @@ -2275,7 +2268,7 @@ static void __kprobes disarm_all_kprobes(void) for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; - hlist_for_each_entry_rcu(p, node, head, hlist) { + hlist_for_each_entry_rcu(p, head, hlist) { if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p)) disarm_kprobe(p, false); } diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c index 78e2ecb20165..b781e66a8f2c 100644 --- a/kernel/nsproxy.c +++ b/kernel/nsproxy.c @@ -153,8 +153,7 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk) goto out; } - new_ns = create_new_namespaces(flags, tsk, - task_cred_xxx(tsk, user_ns), tsk->fs); + new_ns = create_new_namespaces(flags, tsk, user_ns, tsk->fs); if (IS_ERR(new_ns)) { err = PTR_ERR(new_ns); goto out; diff --git a/kernel/pid.c b/kernel/pid.c index de9af600006f..5a4061e5559b 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -350,10 +350,9 @@ void disable_pid_allocation(struct pid_namespace *ns) struct pid *find_pid_ns(int nr, struct pid_namespace *ns) { - struct hlist_node *elem; struct upid *pnr; - hlist_for_each_entry_rcu(pnr, elem, + hlist_for_each_entry_rcu(pnr, &pid_hash[pid_hashfn(nr, ns)], pid_chain) if (pnr->nr == nr && pnr->ns == ns) return container_of(pnr, struct pid, diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index 10349d5f2ec3..b51bb086e5f3 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -552,24 +552,22 @@ SYSCALL_DEFINE3(timer_create, const clockid_t, which_clock, return -EAGAIN; spin_lock_init(&new_timer->it_lock); - retry: - if (unlikely(!idr_pre_get(&posix_timers_id, GFP_KERNEL))) { - error = -EAGAIN; - goto out; - } + + idr_preload(GFP_KERNEL); spin_lock_irq(&idr_lock); - error = idr_get_new(&posix_timers_id, new_timer, &new_timer_id); + error = idr_alloc(&posix_timers_id, new_timer, 0, 0, GFP_NOWAIT); spin_unlock_irq(&idr_lock); - if (error) { - if (error == -EAGAIN) - goto retry; + idr_preload_end(); + if (error < 0) { /* * Weird looking, but we return EAGAIN if the IDR is * full (proper POSIX return value for this) */ - error = -EAGAIN; + if (error == -ENOSPC) + error = -EAGAIN; goto out; } + new_timer_id = error; it_id_set = IT_ID_SET; new_timer->it_id = (timer_t) new_timer_id; diff --git a/kernel/printk.c b/kernel/printk.c index f24633afa46a..80b5db71bdba 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -32,6 +32,7 @@ #include <linux/security.h> #include <linux/bootmem.h> #include <linux/memblock.h> +#include <linux/aio.h> #include <linux/syscalls.h> #include <linux/kexec.h> #include <linux/kdb.h> diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 6cbeaae4406d..30b71f49bfe4 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -24,6 +24,7 @@ #include <linux/regset.h> #include <linux/hw_breakpoint.h> #include <linux/cn_proc.h> +#include <linux/uio.h> static int ptrace_trapping_sleep_fn(void *flags) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 6d99d16ce3fc..55a5ae3c58fd 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1132,18 +1132,28 @@ EXPORT_SYMBOL_GPL(kick_process); */ static int select_fallback_rq(int cpu, struct task_struct *p) { - const struct cpumask *nodemask = cpumask_of_node(cpu_to_node(cpu)); + int nid = cpu_to_node(cpu); + const struct cpumask *nodemask = NULL; enum { cpuset, possible, fail } state = cpuset; int dest_cpu; - /* Look for allowed, online CPU in same node. */ - for_each_cpu(dest_cpu, nodemask) { - if (!cpu_online(dest_cpu)) - continue; - if (!cpu_active(dest_cpu)) - continue; - if (cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p))) - return dest_cpu; + /* + * If the node that the cpu is on has been offlined, cpu_to_node() + * will return -1. There is no cpu on the node, and we should + * select the cpu on the other node. + */ + if (nid != -1) { + nodemask = cpumask_of_node(nid); + + /* Look for allowed, online CPU in same node. */ + for_each_cpu(dest_cpu, nodemask) { + if (!cpu_online(dest_cpu)) + continue; + if (!cpu_active(dest_cpu)) + continue; + if (cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p))) + return dest_cpu; + } } for (;;) { @@ -1742,9 +1752,8 @@ EXPORT_SYMBOL_GPL(preempt_notifier_unregister); static void fire_sched_in_preempt_notifiers(struct task_struct *curr) { struct preempt_notifier *notifier; - struct hlist_node *node; - hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link) + hlist_for_each_entry(notifier, &curr->preempt_notifiers, link) notifier->ops->sched_in(notifier, raw_smp_processor_id()); } @@ -1753,9 +1762,8 @@ fire_sched_out_preempt_notifiers(struct task_struct *curr, struct task_struct *next) { struct preempt_notifier *notifier; - struct hlist_node *node; - hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link) + hlist_for_each_entry(notifier, &curr->preempt_notifiers, link) notifier->ops->sched_out(notifier, next); } diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 557e7b53b323..75024a673520 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -262,11 +262,11 @@ static void print_cpu(struct seq_file *m, int cpu) { unsigned int freq = cpu_khz ? : 1; - SEQ_printf(m, "\ncpu#%d, %u.%03u MHz\n", + SEQ_printf(m, "cpu#%d, %u.%03u MHz\n", cpu, freq / 1000, (freq % 1000)); } #else - SEQ_printf(m, "\ncpu#%d\n", cpu); + SEQ_printf(m, "cpu#%d\n", cpu); #endif #define P(x) \ @@ -323,6 +323,7 @@ do { \ print_rq(m, rq, cpu); rcu_read_unlock(); spin_unlock_irqrestore(&sched_debug_lock, flags); + SEQ_printf(m, "\n"); } static const char *sched_tunable_scaling_names[] = { @@ -331,11 +332,10 @@ static const char *sched_tunable_scaling_names[] = { "linear" }; -static int sched_debug_show(struct seq_file *m, void *v) +static void sched_debug_header(struct seq_file *m) { u64 ktime, sched_clk, cpu_clk; unsigned long flags; - int cpu; local_irq_save(flags); ktime = ktime_to_ns(ktime_get()); @@ -377,33 +377,101 @@ static int sched_debug_show(struct seq_file *m, void *v) #undef PN #undef P - SEQ_printf(m, " .%-40s: %d (%s)\n", "sysctl_sched_tunable_scaling", + SEQ_printf(m, " .%-40s: %d (%s)\n", + "sysctl_sched_tunable_scaling", sysctl_sched_tunable_scaling, sched_tunable_scaling_names[sysctl_sched_tunable_scaling]); + SEQ_printf(m, "\n"); +} - for_each_online_cpu(cpu) - print_cpu(m, cpu); +static int sched_debug_show(struct seq_file *m, void *v) +{ + int cpu = (unsigned long)(v - 2); - SEQ_printf(m, "\n"); + if (cpu != -1) + print_cpu(m, cpu); + else + sched_debug_header(m); return 0; } void sysrq_sched_debug_show(void) { - sched_debug_show(NULL, NULL); + int cpu; + + sched_debug_header(NULL); + for_each_online_cpu(cpu) + print_cpu(NULL, cpu); + +} + +/* + * This itererator needs some explanation. + * It returns 1 for the header position. + * This means 2 is cpu 0. + * In a hotplugged system some cpus, including cpu 0, may be missing so we have + * to use cpumask_* to iterate over the cpus. + */ +static void *sched_debug_start(struct seq_file *file, loff_t *offset) +{ + unsigned long n = *offset; + + if (n == 0) + return (void *) 1; + + n--; + + if (n > 0) + n = cpumask_next(n - 1, cpu_online_mask); + else + n = cpumask_first(cpu_online_mask); + + *offset = n + 1; + + if (n < nr_cpu_ids) + return (void *)(unsigned long)(n + 2); + return NULL; +} + +static void *sched_debug_next(struct seq_file *file, void *data, loff_t *offset) +{ + (*offset)++; + return sched_debug_start(file, offset); +} + +static void sched_debug_stop(struct seq_file *file, void *data) +{ +} + +static const struct seq_operations sched_debug_sops = { + .start = sched_debug_start, + .next = sched_debug_next, + .stop = sched_debug_stop, + .show = sched_debug_show, +}; + +static int sched_debug_release(struct inode *inode, struct file *file) +{ + seq_release(inode, file); + + return 0; } static int sched_debug_open(struct inode *inode, struct file *filp) { - return single_open(filp, sched_debug_show, NULL); + int ret = 0; + + ret = seq_open(filp, &sched_debug_sops); + + return ret; } static const struct file_operations sched_debug_fops = { .open = sched_debug_open, .read = seq_read, .llseek = seq_lseek, - .release = single_release, + .release = sched_debug_release, }; static int __init init_sched_debug_procfs(void) diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c index 903ffa9e8872..e036eda1a9c9 100644 --- a/kernel/sched/stats.c +++ b/kernel/sched/stats.c @@ -21,14 +21,17 @@ static int show_schedstat(struct seq_file *seq, void *v) if (mask_str == NULL) return -ENOMEM; - seq_printf(seq, "version %d\n", SCHEDSTAT_VERSION); - seq_printf(seq, "timestamp %lu\n", jiffies); - for_each_online_cpu(cpu) { - struct rq *rq = cpu_rq(cpu); + if (v == (void *)1) { + seq_printf(seq, "version %d\n", SCHEDSTAT_VERSION); + seq_printf(seq, "timestamp %lu\n", jiffies); + } else { + struct rq *rq; #ifdef CONFIG_SMP struct sched_domain *sd; int dcount = 0; #endif + cpu = (unsigned long)(v - 2); + rq = cpu_rq(cpu); /* runqueue-specific stats */ seq_printf(seq, @@ -77,30 +80,66 @@ static int show_schedstat(struct seq_file *seq, void *v) return 0; } -static int schedstat_open(struct inode *inode, struct file *file) +/* + * This itererator needs some explanation. + * It returns 1 for the header position. + * This means 2 is cpu 0. + * In a hotplugged system some cpus, including cpu 0, may be missing so we have + * to use cpumask_* to iterate over the cpus. + */ +static void *schedstat_start(struct seq_file *file, loff_t *offset) { - unsigned int size = PAGE_SIZE * (1 + num_online_cpus() / 32); - char *buf = kmalloc(size, GFP_KERNEL); - struct seq_file *m; - int res; + unsigned long n = *offset; - if (!buf) - return -ENOMEM; - res = single_open(file, show_schedstat, NULL); - if (!res) { - m = file->private_data; - m->buf = buf; - m->size = size; - } else - kfree(buf); - return res; + if (n == 0) + return (void *) 1; + + n--; + + if (n > 0) + n = cpumask_next(n - 1, cpu_online_mask); + else + n = cpumask_first(cpu_online_mask); + + *offset = n + 1; + + if (n < nr_cpu_ids) + return (void *)(unsigned long)(n + 2); + return NULL; +} + +static void *schedstat_next(struct seq_file *file, void *data, loff_t *offset) +{ + (*offset)++; + return schedstat_start(file, offset); +} + +static void schedstat_stop(struct seq_file *file, void *data) +{ +} + +static const struct seq_operations schedstat_sops = { + .start = schedstat_start, + .next = schedstat_next, + .stop = schedstat_stop, + .show = show_schedstat, +}; + +static int schedstat_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &schedstat_sops); } +static int schedstat_release(struct inode *inode, struct file *file) +{ + return 0; +}; + static const struct file_operations proc_schedstat_operations = { .open = schedstat_open, .read = seq_read, .llseek = seq_lseek, - .release = single_release, + .release = schedstat_release, }; static int __init proc_schedstat_init(void) diff --git a/kernel/signal.c b/kernel/signal.c index 2a7ae2963185..c6209135cca4 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2996,7 +2996,8 @@ static int do_rt_sigqueueinfo(pid_t pid, int sig, siginfo_t *info) /* Not even root can pretend to send signals from the kernel. * Nor can they impersonate a kill()/tgkill(), which adds source info. */ - if (info->si_code >= 0 || info->si_code == SI_TKILL) { + if ((info->si_code >= 0 || info->si_code == SI_TKILL) && + (task_pid_vnr(current) != pid)) { /* We used to allow any < 0 si_code */ WARN_ON_ONCE(info->si_code < 0); return -EPERM; @@ -3045,7 +3046,8 @@ static int do_rt_tgsigqueueinfo(pid_t tgid, pid_t pid, int sig, siginfo_t *info) /* Not even root can pretend to send signals from the kernel. * Nor can they impersonate a kill()/tgkill(), which adds source info. */ - if (info->si_code >= 0 || info->si_code == SI_TKILL) { + if (((info->si_code >= 0 || info->si_code == SI_TKILL)) && + (task_pid_vnr(current) != pid)) { /* We used to allow any < 0 si_code */ WARN_ON_ONCE(info->si_code < 0); return -EPERM; diff --git a/kernel/smp.c b/kernel/smp.c index a2f0b2c73832..fc72ea6c554c 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -17,22 +17,12 @@ #include "smpboot.h" #ifdef CONFIG_USE_GENERIC_SMP_HELPERS -static struct { - struct list_head queue; - raw_spinlock_t lock; -} call_function __cacheline_aligned_in_smp = - { - .queue = LIST_HEAD_INIT(call_function.queue), - .lock = __RAW_SPIN_LOCK_UNLOCKED(call_function.lock), - }; - enum { CSD_FLAG_LOCK = 0x01, }; struct call_function_data { - struct call_single_data csd; - atomic_t refs; + struct call_single_data __percpu *csd; cpumask_var_t cpumask; cpumask_var_t cpumask_ipi; }; @@ -61,6 +51,11 @@ hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu) if (!zalloc_cpumask_var_node(&cfd->cpumask_ipi, GFP_KERNEL, cpu_to_node(cpu))) return notifier_from_errno(-ENOMEM); + cfd->csd = alloc_percpu(struct call_single_data); + if (!cfd->csd) { + free_cpumask_var(cfd->cpumask); + return notifier_from_errno(-ENOMEM); + } break; #ifdef CONFIG_HOTPLUG_CPU @@ -71,6 +66,7 @@ hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu) case CPU_DEAD_FROZEN: free_cpumask_var(cfd->cpumask); free_cpumask_var(cfd->cpumask_ipi); + free_percpu(cfd->csd); break; #endif }; @@ -105,16 +101,16 @@ void __init call_function_init(void) * previous function call. For multi-cpu calls its even more interesting * as we'll have to ensure no other cpu is observing our csd. */ -static void csd_lock_wait(struct call_single_data *data) +static void csd_lock_wait(struct call_single_data *csd) { - while (data->flags & CSD_FLAG_LOCK) + while (csd->flags & CSD_FLAG_LOCK) cpu_relax(); } -static void csd_lock(struct call_single_data *data) +static void csd_lock(struct call_single_data *csd) { - csd_lock_wait(data); - data->flags = CSD_FLAG_LOCK; + csd_lock_wait(csd); + csd->flags = CSD_FLAG_LOCK; /* * prevent CPU from reordering the above assignment @@ -124,16 +120,16 @@ static void csd_lock(struct call_single_data *data) smp_mb(); } -static void csd_unlock(struct call_single_data *data) +static void csd_unlock(struct call_single_data *csd) { - WARN_ON(!(data->flags & CSD_FLAG_LOCK)); + WARN_ON(!(csd->flags & CSD_FLAG_LOCK)); /* * ensure we're all done before releasing data: */ smp_mb(); - data->flags &= ~CSD_FLAG_LOCK; + csd->flags &= ~CSD_FLAG_LOCK; } /* @@ -142,7 +138,7 @@ static void csd_unlock(struct call_single_data *data) * ->func, ->info, and ->flags set. */ static -void generic_exec_single(int cpu, struct call_single_data *data, int wait) +void generic_exec_single(int cpu, struct call_single_data *csd, int wait) { struct call_single_queue *dst = &per_cpu(call_single_queue, cpu); unsigned long flags; @@ -150,7 +146,7 @@ void generic_exec_single(int cpu, struct call_single_data *data, int wait) raw_spin_lock_irqsave(&dst->lock, flags); ipi = list_empty(&dst->list); - list_add_tail(&data->list, &dst->list); + list_add_tail(&csd->list, &dst->list); raw_spin_unlock_irqrestore(&dst->lock, flags); /* @@ -168,86 +164,7 @@ void generic_exec_single(int cpu, struct call_single_data *data, int wait) arch_send_call_function_single_ipi(cpu); if (wait) - csd_lock_wait(data); -} - -/* - * Invoked by arch to handle an IPI for call function. Must be called with - * interrupts disabled. - */ -void generic_smp_call_function_interrupt(void) -{ - struct call_function_data *data; - int cpu = smp_processor_id(); - - /* - * Shouldn't receive this interrupt on a cpu that is not yet online. - */ - WARN_ON_ONCE(!cpu_online(cpu)); - - /* - * Ensure entry is visible on call_function_queue after we have - * entered the IPI. See comment in smp_call_function_many. - * If we don't have this, then we may miss an entry on the list - * and never get another IPI to process it. - */ - smp_mb(); - - /* - * It's ok to use list_for_each_rcu() here even though we may - * delete 'pos', since list_del_rcu() doesn't clear ->next - */ - list_for_each_entry_rcu(data, &call_function.queue, csd.list) { - int refs; - smp_call_func_t func; - - /* - * Since we walk the list without any locks, we might - * see an entry that was completed, removed from the - * list and is in the process of being reused. - * - * We must check that the cpu is in the cpumask before - * checking the refs, and both must be set before - * executing the callback on this cpu. - */ - - if (!cpumask_test_cpu(cpu, data->cpumask)) - continue; - - smp_rmb(); - - if (atomic_read(&data->refs) == 0) - continue; - - func = data->csd.func; /* save for later warn */ - func(data->csd.info); - - /* - * If the cpu mask is not still set then func enabled - * interrupts (BUG), and this cpu took another smp call - * function interrupt and executed func(info) twice - * on this cpu. That nested execution decremented refs. - */ - if (!cpumask_test_and_clear_cpu(cpu, data->cpumask)) { - WARN(1, "%pf enabled interrupts and double executed\n", func); - continue; - } - - refs = atomic_dec_return(&data->refs); - WARN_ON(refs < 0); - - if (refs) - continue; - - WARN_ON(!cpumask_empty(data->cpumask)); - - raw_spin_lock(&call_function.lock); - list_del_rcu(&data->csd.list); - raw_spin_unlock(&call_function.lock); - - csd_unlock(&data->csd); - } - + csd_lock_wait(csd); } /* @@ -257,7 +174,6 @@ void generic_smp_call_function_interrupt(void) void generic_smp_call_function_single_interrupt(void) { struct call_single_queue *q = &__get_cpu_var(call_single_queue); - unsigned int data_flags; LIST_HEAD(list); /* @@ -270,25 +186,26 @@ void generic_smp_call_function_single_interrupt(void) raw_spin_unlock(&q->lock); while (!list_empty(&list)) { - struct call_single_data *data; + struct call_single_data *csd; + unsigned int csd_flags; - data = list_entry(list.next, struct call_single_data, list); - list_del(&data->list); + csd = list_entry(list.next, struct call_single_data, list); + list_del(&csd->list); /* - * 'data' can be invalid after this call if flags == 0 + * 'csd' can be invalid after this call if flags == 0 * (when called through generic_exec_single()), * so save them away before making the call: */ - data_flags = data->flags; + csd_flags = csd->flags; - data->func(data->info); + csd->func(csd->info); /* * Unlocked CSDs are valid through generic_exec_single(): */ - if (data_flags & CSD_FLAG_LOCK) - csd_unlock(data); + if (csd_flags & CSD_FLAG_LOCK) + csd_unlock(csd); } } @@ -333,16 +250,16 @@ int smp_call_function_single(int cpu, smp_call_func_t func, void *info, local_irq_restore(flags); } else { if ((unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) { - struct call_single_data *data = &d; + struct call_single_data *csd = &d; if (!wait) - data = &__get_cpu_var(csd_data); + csd = &__get_cpu_var(csd_data); - csd_lock(data); + csd_lock(csd); - data->func = func; - data->info = info; - generic_exec_single(cpu, data, wait); + csd->func = func; + csd->info = info; + generic_exec_single(cpu, csd, wait); } else { err = -ENXIO; /* CPU not online */ } @@ -409,7 +326,7 @@ EXPORT_SYMBOL_GPL(smp_call_function_any); * pre-allocated data structure. Useful for embedding @data inside * other structures, for instance. */ -void __smp_call_function_single(int cpu, struct call_single_data *data, +void __smp_call_function_single(int cpu, struct call_single_data *csd, int wait) { unsigned int this_cpu; @@ -428,11 +345,11 @@ void __smp_call_function_single(int cpu, struct call_single_data *data, if (cpu == this_cpu) { local_irq_save(flags); - data->func(data->info); + csd->func(csd->info); local_irq_restore(flags); } else { - csd_lock(data); - generic_exec_single(cpu, data, wait); + csd_lock(csd); + generic_exec_single(cpu, csd, wait); } put_cpu(); } @@ -454,9 +371,8 @@ void __smp_call_function_single(int cpu, struct call_single_data *data, void smp_call_function_many(const struct cpumask *mask, smp_call_func_t func, void *info, bool wait) { - struct call_function_data *data; - unsigned long flags; - int refs, cpu, next_cpu, this_cpu = smp_processor_id(); + struct call_function_data *cfd; + int cpu, next_cpu, this_cpu = smp_processor_id(); /* * Can deadlock when called with interrupts disabled. @@ -487,86 +403,48 @@ void smp_call_function_many(const struct cpumask *mask, return; } - data = &__get_cpu_var(cfd_data); - csd_lock(&data->csd); - - /* This BUG_ON verifies our reuse assertions and can be removed */ - BUG_ON(atomic_read(&data->refs) || !cpumask_empty(data->cpumask)); - - /* - * The global call function queue list add and delete are protected - * by a lock, but the list is traversed without any lock, relying - * on the rcu list add and delete to allow safe concurrent traversal. - * We reuse the call function data without waiting for any grace - * period after some other cpu removes it from the global queue. - * This means a cpu might find our data block as it is being - * filled out. - * - * We hold off the interrupt handler on the other cpu by - * ordering our writes to the cpu mask vs our setting of the - * refs counter. We assert only the cpu owning the data block - * will set a bit in cpumask, and each bit will only be cleared - * by the subject cpu. Each cpu must first find its bit is - * set and then check that refs is set indicating the element is - * ready to be processed, otherwise it must skip the entry. - * - * On the previous iteration refs was set to 0 by another cpu. - * To avoid the use of transitivity, set the counter to 0 here - * so the wmb will pair with the rmb in the interrupt handler. - */ - atomic_set(&data->refs, 0); /* convert 3rd to 1st party write */ - - data->csd.func = func; - data->csd.info = info; - - /* Ensure 0 refs is visible before mask. Also orders func and info */ - smp_wmb(); + cfd = &__get_cpu_var(cfd_data); - /* We rely on the "and" being processed before the store */ - cpumask_and(data->cpumask, mask, cpu_online_mask); - cpumask_clear_cpu(this_cpu, data->cpumask); - refs = cpumask_weight(data->cpumask); + cpumask_and(cfd->cpumask, mask, cpu_online_mask); + cpumask_clear_cpu(this_cpu, cfd->cpumask); /* Some callers race with other cpus changing the passed mask */ - if (unlikely(!refs)) { - csd_unlock(&data->csd); + if (unlikely(!cpumask_weight(cfd->cpumask))) return; - } /* - * After we put an entry into the list, data->cpumask - * may be cleared again when another CPU sends another IPI for - * a SMP function call, so data->cpumask will be zero. - */ - cpumask_copy(data->cpumask_ipi, data->cpumask); - raw_spin_lock_irqsave(&call_function.lock, flags); - /* - * Place entry at the _HEAD_ of the list, so that any cpu still - * observing the entry in generic_smp_call_function_interrupt() - * will not miss any other list entries: - */ - list_add_rcu(&data->csd.list, &call_function.queue); - /* - * We rely on the wmb() in list_add_rcu to complete our writes - * to the cpumask before this write to refs, which indicates - * data is on the list and is ready to be processed. + * After we put an entry into the list, cfd->cpumask may be cleared + * again when another CPU sends another IPI for a SMP function call, so + * cfd->cpumask will be zero. */ - atomic_set(&data->refs, refs); - raw_spin_unlock_irqrestore(&call_function.lock, flags); + cpumask_copy(cfd->cpumask_ipi, cfd->cpumask); - /* - * Make the list addition visible before sending the ipi. - * (IPIs must obey or appear to obey normal Linux cache - * coherency rules -- see comment in generic_exec_single). - */ - smp_mb(); + for_each_cpu(cpu, cfd->cpumask) { + struct call_single_data *csd = per_cpu_ptr(cfd->csd, cpu); + struct call_single_queue *dst = + &per_cpu(call_single_queue, cpu); + unsigned long flags; + + csd_lock(csd); + csd->func = func; + csd->info = info; + + raw_spin_lock_irqsave(&dst->lock, flags); + list_add_tail(&csd->list, &dst->list); + raw_spin_unlock_irqrestore(&dst->lock, flags); + } /* Send a message to all CPUs in the map */ - arch_send_call_function_ipi_mask(data->cpumask_ipi); + arch_send_call_function_ipi_mask(cfd->cpumask_ipi); - /* Optionally wait for the CPUs to complete */ - if (wait) - csd_lock_wait(&data->csd); + if (wait) { + for_each_cpu(cpu, cfd->cpumask) { + struct call_single_data *csd; + + csd = per_cpu_ptr(cfd->csd, cpu); + csd_lock_wait(csd); + } + } } EXPORT_SYMBOL(smp_call_function_many); diff --git a/kernel/smpboot.c b/kernel/smpboot.c index d6c5fc054242..fc476704ccc9 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -131,7 +131,7 @@ static int smpboot_thread_fn(void *data) continue; } - BUG_ON(td->cpu != smp_processor_id()); + //BUG_ON(td->cpu != smp_processor_id()); /* Check for state change setup */ switch (td->status) { diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 7c777c90aa23..2509b744ea2a 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -104,7 +104,6 @@ extern char core_pattern[]; extern unsigned int core_pipe_limit; #endif extern int pid_max; -extern int min_free_kbytes; extern int pid_max_min, pid_max_max; extern int sysctl_drop_caches; extern int percpu_pagelist_fraction; @@ -2093,7 +2092,7 @@ int proc_dointvec_minmax(struct ctl_table *table, int write, static void validate_coredump_safety(void) { #ifdef CONFIG_COREDUMP - if (suid_dumpable == SUID_DUMPABLE_SAFE && + if (suid_dumpable == SUID_DUMP_ROOT && core_pattern[0] != '/' && core_pattern[0] != '|') { printk(KERN_WARNING "Unsafe core_pattern used with "\ "suid_dumpable=2. Pipe handler or fully qualified "\ diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c index b669ca1fa103..8ce70e518fa0 100644 --- a/kernel/sysctl_binary.c +++ b/kernel/sysctl_binary.c @@ -1193,9 +1193,10 @@ static ssize_t bin_dn_node_address(struct file *file, /* Convert the decnet address to binary */ result = -EIO; - nodep = strchr(buf, '.') + 1; + nodep = strchr(buf, '.'); if (!nodep) goto out; + ++nodep; area = simple_strtoul(buf, NULL, 10); node = simple_strtoul(nodep, NULL, 10); diff --git a/kernel/time.c b/kernel/time.c index d226c6a3fd28..dd6705d1eb8a 100644 --- a/kernel/time.c +++ b/kernel/time.c @@ -232,7 +232,7 @@ EXPORT_SYMBOL(current_fs_time); * Avoid unnecessary multiplications/divisions in the * two most common HZ cases: */ -inline unsigned int jiffies_to_msecs(const unsigned long j) +unsigned int jiffies_to_msecs(const unsigned long j) { #if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) return (MSEC_PER_SEC / HZ) * j; @@ -248,7 +248,7 @@ inline unsigned int jiffies_to_msecs(const unsigned long j) } EXPORT_SYMBOL(jiffies_to_msecs); -inline unsigned int jiffies_to_usecs(const unsigned long j) +unsigned int jiffies_to_usecs(const unsigned long j) { #if HZ <= USEC_PER_SEC && !(USEC_PER_SEC % HZ) return (USEC_PER_SEC / HZ) * j; diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index af5a7e9f164b..9904e4880d04 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -133,7 +133,6 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now) struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu); int i; - SEQ_printf(m, "\n"); SEQ_printf(m, "cpu: %d\n", cpu); for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { SEQ_printf(m, " clock %d:\n", i); @@ -187,6 +186,7 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now) #undef P #undef P_ns + SEQ_printf(m, "\n"); } #ifdef CONFIG_GENERIC_CLOCKEVENTS @@ -195,7 +195,6 @@ print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu) { struct clock_event_device *dev = td->evtdev; - SEQ_printf(m, "\n"); SEQ_printf(m, "Tick Device: mode: %d\n", td->mode); if (cpu < 0) SEQ_printf(m, "Broadcast device\n"); @@ -230,12 +229,11 @@ print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu) print_name_offset(m, dev->event_handler); SEQ_printf(m, "\n"); SEQ_printf(m, " retries: %lu\n", dev->retries); + SEQ_printf(m, "\n"); } -static void timer_list_show_tickdevices(struct seq_file *m) +static void timer_list_show_tickdevices_header(struct seq_file *m) { - int cpu; - #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST print_tickdevice(m, tick_get_broadcast_device(), -1); SEQ_printf(m, "tick_broadcast_mask: %08lx\n", @@ -246,12 +244,8 @@ static void timer_list_show_tickdevices(struct seq_file *m) #endif SEQ_printf(m, "\n"); #endif - for_each_online_cpu(cpu) - print_tickdevice(m, tick_get_device(cpu), cpu); SEQ_printf(m, "\n"); } -#else -static void timer_list_show_tickdevices(struct seq_file *m) { } #endif static int timer_list_show(struct seq_file *m, void *v) @@ -259,34 +253,114 @@ static int timer_list_show(struct seq_file *m, void *v) u64 now = ktime_to_ns(ktime_get()); int cpu; - SEQ_printf(m, "Timer List Version: v0.7\n"); - SEQ_printf(m, "HRTIMER_MAX_CLOCK_BASES: %d\n", HRTIMER_MAX_CLOCK_BASES); - SEQ_printf(m, "now at %Ld nsecs\n", (unsigned long long)now); - - for_each_online_cpu(cpu) + if (v == (void *)1) { + SEQ_printf(m, "Timer List Version: v0.7\n"); + SEQ_printf(m, "HRTIMER_MAX_CLOCK_BASES: %d\n", + HRTIMER_MAX_CLOCK_BASES); + SEQ_printf(m, "now at %Ld nsecs\n", (unsigned long long)now); + SEQ_printf(m, "\n"); + } else if (v < (void *)(unsigned long)(nr_cpu_ids + 2)) { + cpu = (unsigned long)(v - 2); print_cpu(m, cpu, now); + } +#ifdef CONFIG_GENERIC_CLOCKEVENTS + else if (v == (void *)(unsigned long)nr_cpu_ids + 2) { + timer_list_show_tickdevices_header(m); + } else { + cpu = (unsigned long)(v - 3 - nr_cpu_ids); + print_tickdevice(m, tick_get_device(cpu), cpu); + } +#endif + return 0; +} - SEQ_printf(m, "\n"); - timer_list_show_tickdevices(m); +/* + * This itererator really needs some explnation since it is offset and has + * two passes, one of which is controlled by a config option. + * In a hotplugged system some cpus, including cpu 0, may be missing so we have + * to use cpumask_* to iterate over the cpus. + * For the first pass: + * It returns 1 for the header position. + * For cpu 0 it returns 2 and the final possible cpu would be nr_cpu_ids + 1. + * On the second pass: + * It returnes nr_cpu_ids + 1 for the second header position. + * For cpu 0 it returns nr_cpu_ids + 2 + * The final possible cpu would be nr_cpu_ids + nr_cpu_ids + 2. + */ +static void *timer_list_start(struct seq_file *file, loff_t *offset) +{ + unsigned long n = *offset; + + if (n == 0) + return (void *) 1; + + if (n < nr_cpu_ids + 1) { + n--; + if (n > 0) + n = cpumask_next(n - 1, cpu_online_mask); + else + n = cpumask_first(cpu_online_mask); + *offset = n + 1; + return (void *)(unsigned long)(n + 2); + } - return 0; +#ifdef CONFIG_GENERIC_CLOCKEVENTS + if (n == nr_cpu_ids + 1) + return (void *)(unsigned long)(nr_cpu_ids + 2); + + if (n < nr_cpu_ids * 2 + 2) { + n -= (nr_cpu_ids + 2); + if (n > 0) + n = cpumask_next(n - 1, cpu_online_mask); + else + n = cpumask_first(cpu_online_mask); + *offset = n + 2 + nr_cpu_ids; + return (void *)(unsigned long)(n + 3 + nr_cpu_ids); + } +#endif + + return NULL; } +static void *timer_list_next(struct seq_file *file, void *data, loff_t *offset) +{ + (*offset)++; + return timer_list_start(file, offset); +} + +static void timer_list_stop(struct seq_file *file, void *data) +{ +} + +static const struct seq_operations timer_list_sops = { + .start = timer_list_start, + .next = timer_list_next, + .stop = timer_list_stop, + .show = timer_list_show, +}; + void sysrq_timer_list_show(void) { timer_list_show(NULL, NULL); } +static int timer_list_release(struct inode *inode, struct file *filep) +{ + seq_release(inode, filep); + + return 0; +} + static int timer_list_open(struct inode *inode, struct file *filp) { - return single_open(filp, timer_list_show, NULL); + return seq_open(filp, &timer_list_sops); } static const struct file_operations timer_list_fops = { .open = timer_list_open, .read = seq_read, .llseek = seq_lseek, - .release = single_release, + .release = timer_list_release, }; static int __init init_timer_list_procfs(void) diff --git a/kernel/timeconst.pl b/kernel/timeconst.pl index eb51d76e058a..04612394c53e 100644 --- a/kernel/timeconst.pl +++ b/kernel/timeconst.pl @@ -370,7 +370,7 @@ if ($hz eq '--can') { } @val = @{$canned_values{$hz}}; - if (!defined(@val)) { + if (!@val) { @val = compute_values($hz); } output($hz, @val); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index ce8c3d68292f..67b12e841897 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -762,7 +762,6 @@ ftrace_find_profiled_func(struct ftrace_profile_stat *stat, unsigned long ip) { struct ftrace_profile *rec; struct hlist_head *hhd; - struct hlist_node *n; unsigned long key; key = hash_long(ip, ftrace_profile_bits); @@ -771,7 +770,7 @@ ftrace_find_profiled_func(struct ftrace_profile_stat *stat, unsigned long ip) if (hlist_empty(hhd)) return NULL; - hlist_for_each_entry_rcu(rec, n, hhd, node) { + hlist_for_each_entry_rcu(rec, hhd, node) { if (rec->ip == ip) return rec; } @@ -1133,7 +1132,6 @@ ftrace_lookup_ip(struct ftrace_hash *hash, unsigned long ip) unsigned long key; struct ftrace_func_entry *entry; struct hlist_head *hhd; - struct hlist_node *n; if (ftrace_hash_empty(hash)) return NULL; @@ -1145,7 +1143,7 @@ ftrace_lookup_ip(struct ftrace_hash *hash, unsigned long ip) hhd = &hash->buckets[key]; - hlist_for_each_entry_rcu(entry, n, hhd, hlist) { + hlist_for_each_entry_rcu(entry, hhd, hlist) { if (entry->ip == ip) return entry; } @@ -1202,7 +1200,7 @@ remove_hash_entry(struct ftrace_hash *hash, static void ftrace_hash_clear(struct ftrace_hash *hash) { struct hlist_head *hhd; - struct hlist_node *tp, *tn; + struct hlist_node *tn; struct ftrace_func_entry *entry; int size = 1 << hash->size_bits; int i; @@ -1212,7 +1210,7 @@ static void ftrace_hash_clear(struct ftrace_hash *hash) for (i = 0; i < size; i++) { hhd = &hash->buckets[i]; - hlist_for_each_entry_safe(entry, tp, tn, hhd, hlist) + hlist_for_each_entry_safe(entry, tn, hhd, hlist) free_hash_entry(hash, entry); } FTRACE_WARN_ON(hash->count); @@ -1275,7 +1273,6 @@ alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash) { struct ftrace_func_entry *entry; struct ftrace_hash *new_hash; - struct hlist_node *tp; int size; int ret; int i; @@ -1290,7 +1287,7 @@ alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash) size = 1 << hash->size_bits; for (i = 0; i < size; i++) { - hlist_for_each_entry(entry, tp, &hash->buckets[i], hlist) { + hlist_for_each_entry(entry, &hash->buckets[i], hlist) { ret = add_hash_entry(new_hash, entry->ip); if (ret < 0) goto free_hash; @@ -1316,7 +1313,7 @@ ftrace_hash_move(struct ftrace_ops *ops, int enable, struct ftrace_hash **dst, struct ftrace_hash *src) { struct ftrace_func_entry *entry; - struct hlist_node *tp, *tn; + struct hlist_node *tn; struct hlist_head *hhd; struct ftrace_hash *old_hash; struct ftrace_hash *new_hash; @@ -1362,7 +1359,7 @@ ftrace_hash_move(struct ftrace_ops *ops, int enable, size = 1 << src->size_bits; for (i = 0; i < size; i++) { hhd = &src->buckets[i]; - hlist_for_each_entry_safe(entry, tp, tn, hhd, hlist) { + hlist_for_each_entry_safe(entry, tn, hhd, hlist) { if (bits > 0) key = hash_long(entry->ip, bits); else @@ -2901,7 +2898,6 @@ static void function_trace_probe_call(unsigned long ip, unsigned long parent_ip, { struct ftrace_func_probe *entry; struct hlist_head *hhd; - struct hlist_node *n; unsigned long key; key = hash_long(ip, FTRACE_HASH_BITS); @@ -2917,7 +2913,7 @@ static void function_trace_probe_call(unsigned long ip, unsigned long parent_ip, * on the hash. rcu_read_lock is too dangerous here. */ preempt_disable_notrace(); - hlist_for_each_entry_rcu(entry, n, hhd, node) { + hlist_for_each_entry_rcu(entry, hhd, node) { if (entry->ip == ip) entry->ops->func(ip, parent_ip, &entry->data); } @@ -3068,7 +3064,7 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, void *data, int flags) { struct ftrace_func_probe *entry; - struct hlist_node *n, *tmp; + struct hlist_node *tmp; char str[KSYM_SYMBOL_LEN]; int type = MATCH_FULL; int i, len = 0; @@ -3091,7 +3087,7 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, for (i = 0; i < FTRACE_FUNC_HASHSIZE; i++) { struct hlist_head *hhd = &ftrace_func_hash[i]; - hlist_for_each_entry_safe(entry, n, tmp, hhd, node) { + hlist_for_each_entry_safe(entry, tmp, hhd, node) { /* break up if statements for readability */ if ((flags & PROBE_TEST_FUNC) && entry->ops != ops) diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 194d79602dc7..697e88d13907 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -739,12 +739,11 @@ static int task_state_char(unsigned long state) struct trace_event *ftrace_find_event(int type) { struct trace_event *event; - struct hlist_node *n; unsigned key; key = type & (EVENT_HASHSIZE - 1); - hlist_for_each_entry(event, n, &event_hash[key], node) { + hlist_for_each_entry(event, &event_hash[key], node) { if (event->type == type) return event; } diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index d96ba22dabfa..0c05a4592047 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -192,12 +192,11 @@ tracepoint_entry_remove_probe(struct tracepoint_entry *entry, static struct tracepoint_entry *get_tracepoint(const char *name) { struct hlist_head *head; - struct hlist_node *node; struct tracepoint_entry *e; u32 hash = jhash(name, strlen(name), 0); head = &tracepoint_table[hash & (TRACEPOINT_TABLE_SIZE - 1)]; - hlist_for_each_entry(e, node, head, hlist) { + hlist_for_each_entry(e, head, hlist) { if (!strcmp(name, e->name)) return e; } @@ -211,13 +210,12 @@ static struct tracepoint_entry *get_tracepoint(const char *name) static struct tracepoint_entry *add_tracepoint(const char *name) { struct hlist_head *head; - struct hlist_node *node; struct tracepoint_entry *e; size_t name_len = strlen(name) + 1; u32 hash = jhash(name, name_len-1, 0); head = &tracepoint_table[hash & (TRACEPOINT_TABLE_SIZE - 1)]; - hlist_for_each_entry(e, node, head, hlist) { + hlist_for_each_entry(e, head, hlist) { if (!strcmp(name, e->name)) { printk(KERN_NOTICE "tracepoint %s busy\n", name); diff --git a/kernel/user-return-notifier.c b/kernel/user-return-notifier.c index 1744bb80f1fb..394f70b17162 100644 --- a/kernel/user-return-notifier.c +++ b/kernel/user-return-notifier.c @@ -34,11 +34,11 @@ EXPORT_SYMBOL_GPL(user_return_notifier_unregister); void fire_user_return_notifiers(void) { struct user_return_notifier *urn; - struct hlist_node *tmp1, *tmp2; + struct hlist_node *tmp2; struct hlist_head *head; head = &get_cpu_var(return_notifier_list); - hlist_for_each_entry_safe(urn, tmp1, tmp2, head, link) + hlist_for_each_entry_safe(urn, tmp2, head, link) urn->on_user_return(urn); put_cpu_var(return_notifier_list); } diff --git a/kernel/user.c b/kernel/user.c index 57ebfd42023c..e81978e8c03b 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -105,9 +105,8 @@ static void uid_hash_remove(struct user_struct *up) static struct user_struct *uid_hash_find(kuid_t uid, struct hlist_head *hashent) { struct user_struct *user; - struct hlist_node *h; - hlist_for_each_entry(user, h, hashent, uidhash_node) { + hlist_for_each_entry(user, hashent, uidhash_node) { if (uid_eq(user->uid, uid)) { atomic_inc(&user->__count); return user; diff --git a/kernel/utsname.c b/kernel/utsname.c index 08b197e8c485..a47fc5de3113 100644 --- a/kernel/utsname.c +++ b/kernel/utsname.c @@ -30,7 +30,7 @@ static struct uts_namespace *create_uts_ns(void) /* * Clone a new ns copying an original utsname, setting refcount to 1 * @old_ns: namespace to clone - * Return NULL on error (failure to kmalloc), new ns otherwise + * Return ERR_PTR(-ENOMEM) on error (failure to kmalloc), new ns otherwise */ static struct uts_namespace *clone_uts_ns(struct user_namespace *user_ns, struct uts_namespace *old_ns) diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c index 63da38c2d820..4f69f9a5e221 100644 --- a/kernel/utsname_sysctl.c +++ b/kernel/utsname_sysctl.c @@ -15,6 +15,8 @@ #include <linux/sysctl.h> #include <linux/wait.h> +#ifdef CONFIG_PROC_SYSCTL + static void *get_uts(ctl_table *table, int write) { char *which = table->data; @@ -38,7 +40,6 @@ static void put_uts(ctl_table *table, int write, void *which) up_write(&uts_sem); } -#ifdef CONFIG_PROC_SYSCTL /* * Special case of dostring for the UTS structure. This has locks * to observe. Should this be in kernel/sys.c ???? diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 082ca6878a3f..fe9ffc13b149 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -238,10 +238,12 @@ static void watchdog_overflow_callback(struct perf_event *event, if (__this_cpu_read(hard_watchdog_warn) == true) return; - if (hardlockup_panic) + if (hardlockup_panic) { + trigger_all_cpu_backtrace(); panic("Watchdog detected hard LOCKUP on cpu %d", this_cpu); - else + } else { WARN(1, "Watchdog detected hard LOCKUP on cpu %d", this_cpu); + } __this_cpu_write(hard_watchdog_warn, true); return; @@ -322,8 +324,10 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) else dump_stack(); - if (softlockup_panic) + if (softlockup_panic) { + trigger_all_cpu_backtrace(); panic("softlockup: hung tasks"); + } __this_cpu_write(soft_watchdog_warn, true); } else __this_cpu_write(soft_watchdog_warn, false); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 577de1073f24..d5aaede10df5 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -243,8 +243,8 @@ EXPORT_SYMBOL_GPL(system_freezable_wq); for ((pool) = &std_worker_pools(cpu)[0]; \ (pool) < &std_worker_pools(cpu)[NR_STD_WORKER_POOLS]; (pool)++) -#define for_each_busy_worker(worker, i, pos, pool) \ - hash_for_each(pool->busy_hash, i, pos, worker, hentry) +#define for_each_busy_worker(worker, i, pool) \ + hash_for_each(pool->busy_hash, i, worker, hentry) static inline int __next_wq_cpu(int cpu, const struct cpumask *mask, unsigned int sw) @@ -917,9 +917,8 @@ static struct worker *find_worker_executing_work(struct worker_pool *pool, struct work_struct *work) { struct worker *worker; - struct hlist_node *tmp; - hash_for_each_possible(pool->busy_hash, worker, tmp, hentry, + hash_for_each_possible(pool->busy_hash, worker, hentry, (unsigned long)work) if (worker->current_work == work && worker->current_func == work->func) @@ -1183,11 +1182,10 @@ static bool is_chained_work(struct workqueue_struct *wq) struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); struct worker_pool *pool = cwq->pool; struct worker *worker; - struct hlist_node *pos; int i; spin_lock_irqsave(&pool->lock, flags); - for_each_busy_worker(worker, i, pos, pool) { + for_each_busy_worker(worker, i, pool) { if (worker->task != current) continue; spin_unlock_irqrestore(&pool->lock, flags); @@ -1684,7 +1682,6 @@ static void busy_worker_rebind_fn(struct work_struct *work) static void rebind_workers(struct worker_pool *pool) { struct worker *worker, *n; - struct hlist_node *pos; int i; lockdep_assert_held(&pool->assoc_mutex); @@ -1706,7 +1703,7 @@ static void rebind_workers(struct worker_pool *pool) } /* rebind busy workers */ - for_each_busy_worker(worker, i, pos, pool) { + for_each_busy_worker(worker, i, pool) { struct work_struct *rebind_work = &worker->rebind_work; struct workqueue_struct *wq; @@ -3491,7 +3488,6 @@ static void wq_unbind_fn(struct work_struct *work) int cpu = smp_processor_id(); struct worker_pool *pool; struct worker *worker; - struct hlist_node *pos; int i; for_each_std_worker_pool(pool, cpu) { @@ -3510,7 +3506,7 @@ static void wq_unbind_fn(struct work_struct *work) list_for_each_entry(worker, &pool->idle_list, entry) worker->flags |= WORKER_UNBOUND; - for_each_busy_worker(worker, i, pos, pool) + for_each_busy_worker(worker, i, pool) worker->flags |= WORKER_UNBOUND; pool->flags |= POOL_DISASSOCIATED; diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 4699db385210..28be08c09bab 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -243,8 +243,7 @@ config BOOTPARAM_SOFTLOCKUP_PANIC_VALUE default 1 if BOOTPARAM_SOFTLOCKUP_PANIC config PANIC_ON_OOPS - bool "Panic on Oops" if EXPERT - default n + bool "Panic on Oops" help Say Y here to enable the kernel to panic when it oopses. This has the same effect as setting oops=panic on the kernel command diff --git a/lib/Makefile b/lib/Makefile index 02ed6c04cd7d..32f445541423 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -13,7 +13,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \ sha1.o md5.o irq_regs.o reciprocal_div.o argv_split.o \ proportions.o flex_proportions.o prio_heap.o ratelimit.o show_mem.o \ is_single_threaded.o plist.o decompress.o kobject_uevent.o \ - earlycpio.o + earlycpio.o percpu-refcount.o lib-$(CONFIG_MMU) += ioremap.o lib-$(CONFIG_SMP) += cpumask.o @@ -23,7 +23,7 @@ lib-y += kobject.o klist.o obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \ bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \ string_helpers.o gcd.o lcm.o list_sort.o uuid.o flex_array.o \ - bsearch.o find_last_bit.o find_next_bit.o llist.o memweight.o + bsearch.o find_last_bit.o find_next_bit.o llist.o memweight.o kfifo.o obj-y += kstrtox.o obj-$(CONFIG_TEST_KSTRTOX) += test-kstrtox.o diff --git a/lib/debugobjects.c b/lib/debugobjects.c index d11808ca4bc4..37061ede8b81 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -109,11 +109,10 @@ static void fill_pool(void) */ static struct debug_obj *lookup_object(void *addr, struct debug_bucket *b) { - struct hlist_node *node; struct debug_obj *obj; int cnt = 0; - hlist_for_each_entry(obj, node, &b->list, node) { + hlist_for_each_entry(obj, &b->list, node) { cnt++; if (obj->object == addr) return obj; @@ -213,7 +212,7 @@ static void free_object(struct debug_obj *obj) static void debug_objects_oom(void) { struct debug_bucket *db = obj_hash; - struct hlist_node *node, *tmp; + struct hlist_node *tmp; HLIST_HEAD(freelist); struct debug_obj *obj; unsigned long flags; @@ -227,7 +226,7 @@ static void debug_objects_oom(void) raw_spin_unlock_irqrestore(&db->lock, flags); /* Now free them */ - hlist_for_each_entry_safe(obj, node, tmp, &freelist, node) { + hlist_for_each_entry_safe(obj, tmp, &freelist, node) { hlist_del(&obj->node); free_object(obj); } @@ -658,7 +657,7 @@ debug_object_active_state(void *addr, struct debug_obj_descr *descr, static void __debug_check_no_obj_freed(const void *address, unsigned long size) { unsigned long flags, oaddr, saddr, eaddr, paddr, chunks; - struct hlist_node *node, *tmp; + struct hlist_node *tmp; HLIST_HEAD(freelist); struct debug_obj_descr *descr; enum debug_obj_state state; @@ -678,7 +677,7 @@ static void __debug_check_no_obj_freed(const void *address, unsigned long size) repeat: cnt = 0; raw_spin_lock_irqsave(&db->lock, flags); - hlist_for_each_entry_safe(obj, node, tmp, &db->list, node) { + hlist_for_each_entry_safe(obj, tmp, &db->list, node) { cnt++; oaddr = (unsigned long) obj->object; if (oaddr < saddr || oaddr >= eaddr) @@ -702,7 +701,7 @@ repeat: raw_spin_unlock_irqrestore(&db->lock, flags); /* Now free them */ - hlist_for_each_entry_safe(obj, node, tmp, &freelist, node) { + hlist_for_each_entry_safe(obj, tmp, &freelist, node) { hlist_del(&obj->node); free_object(obj); } @@ -1013,7 +1012,7 @@ void __init debug_objects_early_init(void) static int __init debug_objects_replace_static_objects(void) { struct debug_bucket *db = obj_hash; - struct hlist_node *node, *tmp; + struct hlist_node *tmp; struct debug_obj *obj, *new; HLIST_HEAD(objects); int i, cnt = 0; @@ -1033,7 +1032,7 @@ static int __init debug_objects_replace_static_objects(void) local_irq_disable(); /* Remove the statically allocated objects from the pool */ - hlist_for_each_entry_safe(obj, node, tmp, &obj_pool, node) + hlist_for_each_entry_safe(obj, tmp, &obj_pool, node) hlist_del(&obj->node); /* Move the allocated objects to the pool */ hlist_move_list(&objects, &obj_pool); @@ -1042,7 +1041,7 @@ static int __init debug_objects_replace_static_objects(void) for (i = 0; i < ODEBUG_HASH_SIZE; i++, db++) { hlist_move_list(&db->list, &objects); - hlist_for_each_entry(obj, node, &objects, node) { + hlist_for_each_entry(obj, &objects, node) { new = hlist_entry(obj_pool.first, typeof(*obj), node); hlist_del(&new->node); /* copy object data */ @@ -1057,7 +1056,7 @@ static int __init debug_objects_replace_static_objects(void) obj_pool_used); return 0; free: - hlist_for_each_entry_safe(obj, node, tmp, &objects, node) { + hlist_for_each_entry_safe(obj, tmp, &objects, node) { hlist_del(&obj->node); kmem_cache_free(obj_cache, obj); } diff --git a/lib/idr.c b/lib/idr.c index 648239079dd2..511570584b2f 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -35,8 +35,12 @@ #include <linux/string.h> #include <linux/idr.h> #include <linux/spinlock.h> +#include <linux/percpu.h> +#include <linux/hardirq.h> static struct kmem_cache *idr_layer_cache; +static DEFINE_PER_CPU(struct idr_layer *, idr_preload_head); +static DEFINE_PER_CPU(int, idr_preload_cnt); static DEFINE_SPINLOCK(simple_ida_lock); static struct idr_layer *get_from_free_list(struct idr *idp) @@ -54,6 +58,50 @@ static struct idr_layer *get_from_free_list(struct idr *idp) return(p); } +/** + * idr_layer_alloc - allocate a new idr_layer + * @gfp_mask: allocation mask + * @layer_idr: optional idr to allocate from + * + * If @layer_idr is %NULL, directly allocate one using @gfp_mask or fetch + * one from the per-cpu preload buffer. If @layer_idr is not %NULL, fetch + * an idr_layer from @idr->id_free. + * + * @layer_idr is to maintain backward compatibility with the old alloc + * interface - idr_pre_get() and idr_get_new*() - and will be removed + * together with per-pool preload buffer. + */ +static struct idr_layer *idr_layer_alloc(gfp_t gfp_mask, struct idr *layer_idr) +{ + struct idr_layer *new; + + /* this is the old path, bypass to get_from_free_list() */ + if (layer_idr) + return get_from_free_list(layer_idr); + + /* try to allocate directly from kmem_cache */ + new = kmem_cache_zalloc(idr_layer_cache, gfp_mask); + if (new) + return new; + + /* + * Try to fetch one from the per-cpu preload buffer if in process + * context. See idr_preload() for details. + */ + if (in_interrupt()) + return NULL; + + preempt_disable(); + new = __this_cpu_read(idr_preload_head); + if (new) { + __this_cpu_write(idr_preload_head, new->ary[0]); + __this_cpu_dec(idr_preload_cnt); + new->ary[0] = NULL; + } + preempt_enable(); + return new; +} + static void idr_layer_rcu_free(struct rcu_head *head) { struct idr_layer *layer; @@ -133,7 +181,25 @@ int idr_pre_get(struct idr *idp, gfp_t gfp_mask) } EXPORT_SYMBOL(idr_pre_get); -static int sub_alloc(struct idr *idp, int *starting_id, struct idr_layer **pa) +/** + * sub_alloc - try to allocate an id without growing the tree depth + * @idp: idr handle + * @starting_id: id to start search at + * @id: pointer to the allocated handle + * @pa: idr_layer[MAX_IDR_LEVEL] used as backtrack buffer + * @gfp_mask: allocation mask for idr_layer_alloc() + * @layer_idr: optional idr passed to idr_layer_alloc() + * + * Allocate an id in range [@starting_id, INT_MAX] from @idp without + * growing its depth. Returns + * + * the allocated id >= 0 if successful, + * -EAGAIN if the tree needs to grow for allocation to succeed, + * -ENOSPC if the id space is exhausted, + * -ENOMEM if more idr_layers need to be allocated. + */ +static int sub_alloc(struct idr *idp, int *starting_id, struct idr_layer **pa, + gfp_t gfp_mask, struct idr *layer_idr) { int n, m, sh; struct idr_layer *p, *new; @@ -161,7 +227,7 @@ static int sub_alloc(struct idr *idp, int *starting_id, struct idr_layer **pa) /* if already at the top layer, we need to grow */ if (id >= 1 << (idp->layers * IDR_BITS)) { *starting_id = id; - return IDR_NEED_TO_GROW; + return -EAGAIN; } p = pa[l]; BUG_ON(!p); @@ -180,16 +246,16 @@ static int sub_alloc(struct idr *idp, int *starting_id, struct idr_layer **pa) id = ((id >> sh) ^ n ^ m) << sh; } if ((id >= MAX_IDR_BIT) || (id < 0)) - return IDR_NOMORE_SPACE; + return -ENOSPC; if (l == 0) break; /* * Create the layer below if it is missing. */ if (!p->ary[m]) { - new = get_from_free_list(idp); + new = idr_layer_alloc(gfp_mask, layer_idr); if (!new) - return -1; + return -ENOMEM; new->layer = l-1; rcu_assign_pointer(p->ary[m], new); p->count++; @@ -203,7 +269,8 @@ static int sub_alloc(struct idr *idp, int *starting_id, struct idr_layer **pa) } static int idr_get_empty_slot(struct idr *idp, int starting_id, - struct idr_layer **pa) + struct idr_layer **pa, gfp_t gfp_mask, + struct idr *layer_idr) { struct idr_layer *p, *new; int layers, v, id; @@ -214,8 +281,8 @@ build_up: p = idp->top; layers = idp->layers; if (unlikely(!p)) { - if (!(p = get_from_free_list(idp))) - return -1; + if (!(p = idr_layer_alloc(gfp_mask, layer_idr))) + return -ENOMEM; p->layer = 0; layers = 1; } @@ -233,7 +300,7 @@ build_up: p->layer++; continue; } - if (!(new = get_from_free_list(idp))) { + if (!(new = idr_layer_alloc(gfp_mask, layer_idr))) { /* * The allocation failed. If we built part of * the structure tear it down. @@ -246,7 +313,7 @@ build_up: __move_to_free_list(idp, new); } spin_unlock_irqrestore(&idp->lock, flags); - return -1; + return -ENOMEM; } new->ary[0] = p; new->count = 1; @@ -257,30 +324,21 @@ build_up: } rcu_assign_pointer(idp->top, p); idp->layers = layers; - v = sub_alloc(idp, &id, pa); - if (v == IDR_NEED_TO_GROW) + v = sub_alloc(idp, &id, pa, gfp_mask, layer_idr); + if (v == -EAGAIN) goto build_up; return(v); } -static int idr_get_new_above_int(struct idr *idp, void *ptr, int starting_id) +/* + * @id and @pa are from a successful allocation from idr_get_empty_slot(). + * Install the user pointer @ptr and mark the slot full. + */ +static void idr_fill_slot(void *ptr, int id, struct idr_layer **pa) { - struct idr_layer *pa[MAX_IDR_LEVEL]; - int id; - - id = idr_get_empty_slot(idp, starting_id, pa); - if (id >= 0) { - /* - * Successfully found an empty slot. Install the user - * pointer and mark the slot full. - */ - rcu_assign_pointer(pa[0]->ary[id & IDR_MASK], - (struct idr_layer *)ptr); - pa[0]->count++; - idr_mark_full(pa, id); - } - - return id; + rcu_assign_pointer(pa[0]->ary[id & IDR_MASK], (struct idr_layer *)ptr); + pa[0]->count++; + idr_mark_full(pa, id); } /** @@ -303,49 +361,121 @@ static int idr_get_new_above_int(struct idr *idp, void *ptr, int starting_id) */ int idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id) { + struct idr_layer *pa[MAX_IDR_LEVEL]; int rv; - rv = idr_get_new_above_int(idp, ptr, starting_id); - /* - * This is a cheap hack until the IDR code can be fixed to - * return proper error values. - */ + rv = idr_get_empty_slot(idp, starting_id, pa, 0, idp); if (rv < 0) - return _idr_rc_to_errno(rv); + return rv == -ENOMEM ? -EAGAIN : rv; + + idr_fill_slot(ptr, rv, pa); *id = rv; return 0; } EXPORT_SYMBOL(idr_get_new_above); /** - * idr_get_new - allocate new idr entry - * @idp: idr handle - * @ptr: pointer you want associated with the id - * @id: pointer to the allocated handle + * idr_preload - preload for idr_alloc() + * @gfp_mask: allocation mask to use for preloading * - * If allocation from IDR's private freelist fails, idr_get_new_above() will - * return %-EAGAIN. The caller should retry the idr_pre_get() call to refill - * IDR's preallocation and then retry the idr_get_new_above() call. + * Preload per-cpu layer buffer for idr_alloc(). Can only be used from + * process context and each idr_preload() invocation should be matched with + * idr_preload_end(). Note that preemption is disabled while preloaded. * - * If the idr is full idr_get_new_above() will return %-ENOSPC. + * The first idr_alloc() in the preloaded section can be treated as if it + * were invoked with @gfp_mask used for preloading. This allows using more + * permissive allocation masks for idrs protected by spinlocks. * - * @id returns a value in the range %0 ... %0x7fffffff + * For example, if idr_alloc() below fails, the failure can be treated as + * if idr_alloc() were called with GFP_KERNEL rather than GFP_NOWAIT. + * + * idr_preload(GFP_KERNEL); + * spin_lock(lock); + * + * id = idr_alloc(idr, ptr, start, end, GFP_NOWAIT); + * + * spin_unlock(lock); + * idr_preload_end(); + * if (id < 0) + * error; */ -int idr_get_new(struct idr *idp, void *ptr, int *id) +void idr_preload(gfp_t gfp_mask) { - int rv; + /* + * Consuming preload buffer from non-process context breaks preload + * allocation guarantee. Disallow usage from those contexts. + */ + WARN_ON_ONCE(in_interrupt()); + might_sleep_if(gfp_mask & __GFP_WAIT); + + preempt_disable(); - rv = idr_get_new_above_int(idp, ptr, 0); /* - * This is a cheap hack until the IDR code can be fixed to - * return proper error values. + * idr_alloc() is likely to succeed w/o full idr_layer buffer and + * return value from idr_alloc() needs to be checked for failure + * anyway. Silently give up if allocation fails. The caller can + * treat failures from idr_alloc() as if idr_alloc() were called + * with @gfp_mask which should be enough. */ - if (rv < 0) - return _idr_rc_to_errno(rv); - *id = rv; - return 0; + while (__this_cpu_read(idr_preload_cnt) < MAX_IDR_FREE) { + struct idr_layer *new; + + preempt_enable(); + new = kmem_cache_zalloc(idr_layer_cache, gfp_mask); + preempt_disable(); + if (!new) + break; + + /* link the new one to per-cpu preload list */ + new->ary[0] = __this_cpu_read(idr_preload_head); + __this_cpu_write(idr_preload_head, new); + __this_cpu_inc(idr_preload_cnt); + } } -EXPORT_SYMBOL(idr_get_new); +EXPORT_SYMBOL(idr_preload); + +/** + * idr_alloc - allocate new idr entry + * @idr: the (initialized) idr + * @ptr: pointer to be associated with the new id + * @start: the minimum id (inclusive) + * @end: the maximum id (exclusive, 0 for max) + * @gfp_mask: memory allocation flags + * + * Allocate an id in [start, end) and associate it with @ptr. If no ID is + * available in the specified range, returns -ENOSPC. On memory allocation + * failure, returns -ENOMEM. + * + * The user is responsible for exclusively synchronizing all operations + * which may modify @idr. However, read-only accesses such as idr_find() + * or iteration can be performed under RCU read lock provided the user + * destroys @ptr in RCU-safe way after removal from idr. + */ +int idr_alloc(struct idr *idr, void *ptr, int start, int end, gfp_t gfp_mask) +{ + int max = end ? end - 1 : INT_MAX; /* inclusive upper limit */ + struct idr_layer *pa[MAX_IDR_LEVEL]; + int id; + + might_sleep_if(gfp_mask & __GFP_WAIT); + + /* sanity checks */ + if (WARN_ON_ONCE(start < 0 || end < 0)) + return -EINVAL; + if (unlikely(max < start)) + return -ENOSPC; + + /* allocate id */ + id = idr_get_empty_slot(idr, start, pa, gfp_mask, NULL); + if (unlikely(id < 0)) + return id; + if (unlikely(id > max)) + return -ENOSPC; + + idr_fill_slot(ptr, id, pa); + return id; +} +EXPORT_SYMBOL_GPL(idr_alloc); static void idr_remove_warning(int id) { @@ -433,20 +563,7 @@ void idr_remove(struct idr *idp, int id) } EXPORT_SYMBOL(idr_remove); -/** - * idr_remove_all - remove all ids from the given idr tree - * @idp: idr handle - * - * idr_destroy() only frees up unused, cached idp_layers, but this - * function will remove all id mappings and leave all idp_layers - * unused. - * - * A typical clean-up sequence for objects stored in an idr tree will - * use idr_for_each() to free all objects, if necessay, then - * idr_remove_all() to remove all ids, and idr_destroy() to free - * up the cached idr_layers. - */ -void idr_remove_all(struct idr *idp) +void __idr_remove_all(struct idr *idp) { int n, id, max; int bt_mask; @@ -479,14 +596,25 @@ void idr_remove_all(struct idr *idp) } idp->layers = 0; } -EXPORT_SYMBOL(idr_remove_all); +EXPORT_SYMBOL(__idr_remove_all); /** * idr_destroy - release all cached layers within an idr tree * @idp: idr handle + * + * Free all id mappings and all idp_layers. After this function, @idp is + * completely unused and can be freed / recycled. The caller is + * responsible for ensuring that no one else accesses @idp during or after + * idr_destroy(). + * + * A typical clean-up sequence for objects stored in an idr tree will use + * idr_for_each() to free all objects, if necessay, then idr_destroy() to + * free up the id mappings and cached idr_layers. */ void idr_destroy(struct idr *idp) { + __idr_remove_all(idp); + while (idp->id_free_cnt) { struct idr_layer *p = get_from_free_list(idp); kmem_cache_free(idr_layer_cache, p); @@ -625,7 +753,14 @@ void *idr_get_next(struct idr *idp, int *nextidp) return p; } - id += 1 << n; + /* + * Proceed to the next layer at the current level. Unlike + * idr_for_each(), @id isn't guaranteed to be aligned to + * layer boundary at this point and adding 1 << n may + * incorrectly skip IDs. Make sure we jump to the + * beginning of the next layer using round_up(). + */ + id = round_up(id + 1, 1 << n); while (n < fls(id)) { n += IDR_BITS; p = *--paa; @@ -789,9 +924,9 @@ int ida_get_new_above(struct ida *ida, int starting_id, int *p_id) restart: /* get vacant slot */ - t = idr_get_empty_slot(&ida->idr, idr_id, pa); + t = idr_get_empty_slot(&ida->idr, idr_id, pa, 0, &ida->idr); if (t < 0) - return _idr_rc_to_errno(t); + return t == -ENOMEM ? -EAGAIN : t; if (t * IDA_BITMAP_BITS >= MAX_IDR_BIT) return -ENOSPC; @@ -852,25 +987,6 @@ int ida_get_new_above(struct ida *ida, int starting_id, int *p_id) EXPORT_SYMBOL(ida_get_new_above); /** - * ida_get_new - allocate new ID - * @ida: idr handle - * @p_id: pointer to the allocated handle - * - * Allocate new ID. It should be called with any required locks. - * - * If memory is required, it will return %-EAGAIN, you should unlock - * and go back to the idr_pre_get() call. If the idr is full, it will - * return %-ENOSPC. - * - * @p_id returns a value in the range %0 ... %0x7fffffff. - */ -int ida_get_new(struct ida *ida, int *p_id) -{ - return ida_get_new_above(ida, 0, p_id); -} -EXPORT_SYMBOL(ida_get_new); - -/** * ida_remove - remove the given ID * @ida: ida handle * @id: ID to free diff --git a/kernel/kfifo.c b/lib/kfifo.c index 59dcf5b81d24..7b7f83027b7b 100644 --- a/kernel/kfifo.c +++ b/lib/kfifo.c @@ -42,8 +42,7 @@ int __kfifo_alloc(struct __kfifo *fifo, unsigned int size, * round down to the next power of 2, since our 'let the indices * wrap' technique works only in this case. */ - if (!is_power_of_2(size)) - size = rounddown_pow_of_two(size); + size = roundup_pow_of_two(size); fifo->in = 0; fifo->out = 0; @@ -83,8 +82,7 @@ int __kfifo_init(struct __kfifo *fifo, void *buffer, { size /= esize; - if (!is_power_of_2(size)) - size = rounddown_pow_of_two(size); + size = roundup_pow_of_two(size); fifo->in = 0; fifo->out = 0; diff --git a/lib/lru_cache.c b/lib/lru_cache.c index d71d89498943..8335d39d2ccd 100644 --- a/lib/lru_cache.c +++ b/lib/lru_cache.c @@ -262,12 +262,11 @@ static struct hlist_head *lc_hash_slot(struct lru_cache *lc, unsigned int enr) static struct lc_element *__lc_find(struct lru_cache *lc, unsigned int enr, bool include_changing) { - struct hlist_node *n; struct lc_element *e; BUG_ON(!lc); BUG_ON(!lc->nr_elements); - hlist_for_each_entry(e, n, lc_hash_slot(lc, enr), colision) { + hlist_for_each_entry(e, lc_hash_slot(lc, enr), colision) { /* "about to be changed" elements, pending transaction commit, * are hashed by their "new number". "Normal" elements have * lc_number == lc_new_number. */ diff --git a/lib/parser.c b/lib/parser.c index 52cfa69f73df..807b2aaa33fa 100644 --- a/lib/parser.c +++ b/lib/parser.c @@ -157,7 +157,7 @@ static int match_number(substring_t *s, int *result, int base) * * Description: Attempts to parse the &substring_t @s as a decimal integer. On * success, sets @result to the integer represented by the string and returns 0. - * Returns either -ENOMEM or -EINVAL on failure. + * Returns -ENOMEM, -EINVAL, or -ERANGE on failure. */ int match_int(substring_t *s, int *result) { @@ -171,7 +171,7 @@ int match_int(substring_t *s, int *result) * * Description: Attempts to parse the &substring_t @s as an octal integer. On * success, sets @result to the integer represented by the string and returns - * 0. Returns either -ENOMEM or -EINVAL on failure. + * 0. Returns -ENOMEM, -EINVAL, or -ERANGE on failure. */ int match_octal(substring_t *s, int *result) { @@ -185,7 +185,7 @@ int match_octal(substring_t *s, int *result) * * Description: Attempts to parse the &substring_t @s as a hexadecimal integer. * On success, sets @result to the integer represented by the string and - * returns 0. Returns either -ENOMEM or -EINVAL on failure. + * returns 0. Returns -ENOMEM, -EINVAL, or -ERANGE on failure. */ int match_hex(substring_t *s, int *result) { diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c new file mode 100644 index 000000000000..79c61580a211 --- /dev/null +++ b/lib/percpu-refcount.c @@ -0,0 +1,243 @@ +#define pr_fmt(fmt) "%s: " fmt "\n", __func__ + +#include <linux/kernel.h> +#include <linux/jiffies.h> +#include <linux/percpu-refcount.h> +#include <linux/rcupdate.h> + +/* + * A percpu refcount can be in 4 different modes. The state is tracked in the + * low two bits of percpu_ref->pcpu_count: + * + * PCPU_REF_NONE - the initial state, no percpu counters allocated. + * + * PCPU_REF_PTR - using percpu counters for the refcount. + * + * PCPU_REF_DYING - we're shutting down so get()/put() should use the embedded + * atomic counter, but we're not finished updating the atomic counter from the + * percpu counters - this means that percpu_ref_put() can't check for the ref + * hitting 0 yet. + * + * PCPU_REF_DEAD - we've finished the teardown sequence, percpu_ref_put() should + * now check for the ref hitting 0. + * + * In PCPU_REF_NONE mode, we need to count the number of times percpu_ref_get() + * is called; this is done with the high bits of the raw atomic counter. We also + * track the time, in jiffies, when the get count last wrapped - this is done + * with the remaining bits of percpu_ref->percpu_count. + * + * So, when percpu_ref_get() is called it increments the get count and checks if + * it wrapped; if it did, it checks if the last time it wrapped was less than + * one second ago; if so, we want to allocate percpu counters. + * + * PCPU_COUNT_BITS determines the threshold where we convert to percpu: of the + * raw 64 bit counter, we use PCPU_COUNT_BITS for the refcount, and the + * remaining (high) bits to count the number of times percpu_ref_get() has been + * called. It's currently (completely arbitrarily) 16384 times in one second. + * + * Percpu mode (PCPU_REF_PTR): + * + * In percpu mode all we do on get and put is increment or decrement the cpu + * local counter, which is a 32 bit unsigned int. + * + * Note that all the gets() could be happening on one cpu, and all the puts() on + * another - the individual cpu counters can wrap (potentially many times). + * + * But this is fine because we don't need to check for the ref hitting 0 in + * percpu mode; before we set the state to PCPU_REF_DEAD we simply sum up all + * the percpu counters and add them to the atomic counter. Since addition and + * subtraction in modular arithmatic is still associative, the result will be + * correct. + */ + +#define PCPU_COUNT_BITS 50 +#define PCPU_COUNT_MASK ((1LL << PCPU_COUNT_BITS) - 1) + +#define PCPU_STATUS_BITS 2 +#define PCPU_STATUS_MASK ((1 << PCPU_STATUS_BITS) - 1) + +#define PCPU_REF_PTR 0 +#define PCPU_REF_NONE 1 +#define PCPU_REF_DYING 2 +#define PCPU_REF_DEAD 3 + +#define REF_STATUS(count) (count & PCPU_STATUS_MASK) + +/** + * percpu_ref_init - initialize a dynamic percpu refcount + * + * Initializes the refcount in single atomic counter mode with a refcount of 1; + * analagous to atomic_set(ref, 1). + */ +void percpu_ref_init(struct percpu_ref *ref) +{ + unsigned long now = jiffies; + + atomic64_set(&ref->count, 1); + + now <<= PCPU_STATUS_BITS; + now |= PCPU_REF_NONE; + + ref->pcpu_count = now; +} + +static void percpu_ref_alloc(struct percpu_ref *ref, unsigned long pcpu_count) +{ + unsigned long new, now = jiffies; + + now <<= PCPU_STATUS_BITS; + now |= PCPU_REF_NONE; + + if (now - pcpu_count <= HZ << PCPU_STATUS_BITS) { + rcu_read_unlock(); + new = (unsigned long) alloc_percpu(unsigned); + rcu_read_lock(); + + if (!new) + goto update_time; + + BUG_ON(new & PCPU_STATUS_MASK); + + if (cmpxchg(&ref->pcpu_count, pcpu_count, new) != pcpu_count) + free_percpu((void __percpu *) new); + else + pr_debug("created"); + } else { +update_time: + new = now; + cmpxchg(&ref->pcpu_count, pcpu_count, new); + } +} + +void __percpu_ref_get(struct percpu_ref *ref, bool alloc) +{ + unsigned long pcpu_count; + uint64_t v; + + pcpu_count = ACCESS_ONCE(ref->pcpu_count); + + if (REF_STATUS(pcpu_count) == PCPU_REF_PTR) { + /* for rcu - we're not using rcu_dereference() */ + smp_read_barrier_depends(); + __this_cpu_inc(*((unsigned __percpu *) pcpu_count)); + } else { + v = atomic64_add_return(1 + (1ULL << PCPU_COUNT_BITS), + &ref->count); + + if (!(v >> PCPU_COUNT_BITS) && + REF_STATUS(pcpu_count) == PCPU_REF_NONE && alloc) + percpu_ref_alloc(ref, pcpu_count); + } +} + +/** + * percpu_ref_put - decrement a dynamic percpu refcount + * + * Returns true if the result is 0, otherwise false; only checks for the ref + * hitting 0 after percpu_ref_kill() has been called. Analagous to + * atomic_dec_and_test(). + */ +int percpu_ref_put(struct percpu_ref *ref) +{ + unsigned long pcpu_count; + uint64_t v; + int ret = 0; + + rcu_read_lock(); + + pcpu_count = ACCESS_ONCE(ref->pcpu_count); + + switch (REF_STATUS(pcpu_count)) { + case PCPU_REF_PTR: + /* for rcu - we're not using rcu_dereference() */ + smp_read_barrier_depends(); + __this_cpu_dec(*((unsigned __percpu *) pcpu_count)); + break; + case PCPU_REF_NONE: + case PCPU_REF_DYING: + atomic64_dec(&ref->count); + break; + case PCPU_REF_DEAD: + v = atomic64_dec_return(&ref->count); + v &= PCPU_COUNT_MASK; + + ret = v == 0; + break; + } + + rcu_read_unlock(); + + return ret; +} + +/** + * percpu_ref_kill - prepare a dynamic percpu refcount for teardown + * + * Must be called before dropping the initial ref, so that percpu_ref_put() + * knows to check for the refcount hitting 0. If the refcount was in percpu + * mode, converts it back to single atomic counter mode. + * + * Returns true the first time called on @ref and false if @ref is already + * shutting down, so it may be used by the caller for synchronizing other parts + * of a two stage shutdown. + */ +int percpu_ref_kill(struct percpu_ref *ref) +{ + unsigned long old, new, status, pcpu_count; + + pcpu_count = ACCESS_ONCE(ref->pcpu_count); + + do { + status = REF_STATUS(pcpu_count); + + switch (status) { + case PCPU_REF_PTR: + new = PCPU_REF_DYING; + break; + case PCPU_REF_NONE: + new = PCPU_REF_DEAD; + break; + case PCPU_REF_DYING: + case PCPU_REF_DEAD: + return 0; + } + + old = pcpu_count; + pcpu_count = cmpxchg(&ref->pcpu_count, old, new); + } while (pcpu_count != old); + + if (status == PCPU_REF_PTR) { + unsigned count = 0, cpu; + + synchronize_rcu(); + + for_each_possible_cpu(cpu) + count += *per_cpu_ptr((unsigned __percpu *) pcpu_count, cpu); + + pr_debug("global %lli pcpu %i", + atomic64_read(&ref->count) & PCPU_COUNT_MASK, + (int) count); + + atomic64_add((int) count, &ref->count); + smp_wmb(); + /* Between setting global count and setting PCPU_REF_DEAD */ + ref->pcpu_count = PCPU_REF_DEAD; + + free_percpu((unsigned __percpu *) pcpu_count); + } + + return 1; +} + +/** + * percpu_ref_dead - check if a dynamic percpu refcount is shutting down + * + * Returns true if percpu_ref_kill() has been called on @ref, false otherwise. + */ +int percpu_ref_dead(struct percpu_ref *ref) +{ + unsigned status = REF_STATUS(ref->pcpu_count); + + return status == PCPU_REF_DYING || + status == PCPU_REF_DEAD; +} diff --git a/lib/vsprintf.c b/lib/vsprintf.c index fab33a9c5318..0d62fd700f68 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -1030,6 +1030,7 @@ int kptr_restrict __read_mostly; * N no separator * The maximum supported length is 64 bytes of the input. Consider * to use print_hex_dump() for the larger input. + * - 'a' For a phys_addr_t type and its derivative types (passed by reference) * * Note: The difference between 'S' and 'F' is that on ia64 and ppc64 * function pointers are really function descriptors, which contain a @@ -1120,6 +1121,12 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr, return netdev_feature_string(buf, end, ptr, spec); } break; + case 'a': + spec.flags |= SPECIAL | SMALL | ZEROPAD; + spec.field_width = sizeof(phys_addr_t) * 2 + 2; + spec.base = 16; + return number(buf, end, + (unsigned long long) *((phys_addr_t *)ptr), spec); } spec.flags |= SMALL; if (spec.field_width == -1) { diff --git a/lib/xz/Kconfig b/lib/xz/Kconfig index 60a6088d0e5e..82a04d7ba99e 100644 --- a/lib/xz/Kconfig +++ b/lib/xz/Kconfig @@ -6,42 +6,40 @@ config XZ_DEC the .xz file format as the container. For integrity checking, CRC32 is supported. See Documentation/xz.txt for more information. +if XZ_DEC + config XZ_DEC_X86 - bool "x86 BCJ filter decoder" if EXPERT - default y - depends on XZ_DEC + bool "x86 BCJ filter decoder" + default y if X86 select XZ_DEC_BCJ config XZ_DEC_POWERPC - bool "PowerPC BCJ filter decoder" if EXPERT - default y - depends on XZ_DEC + bool "PowerPC BCJ filter decoder" + default y if POWERPC select XZ_DEC_BCJ config XZ_DEC_IA64 - bool "IA-64 BCJ filter decoder" if EXPERT - default y - depends on XZ_DEC + bool "IA-64 BCJ filter decoder" + default y if IA64 select XZ_DEC_BCJ config XZ_DEC_ARM - bool "ARM BCJ filter decoder" if EXPERT - default y - depends on XZ_DEC + bool "ARM BCJ filter decoder" + default y if ARM select XZ_DEC_BCJ config XZ_DEC_ARMTHUMB - bool "ARM-Thumb BCJ filter decoder" if EXPERT - default y - depends on XZ_DEC + bool "ARM-Thumb BCJ filter decoder" + default y if (ARM && ARM_THUMB) select XZ_DEC_BCJ config XZ_DEC_SPARC - bool "SPARC BCJ filter decoder" if EXPERT - default y - depends on XZ_DEC + bool "SPARC BCJ filter decoder" + default y if SPARC select XZ_DEC_BCJ +endif + config XZ_DEC_BCJ bool default n diff --git a/mm/Kconfig b/mm/Kconfig index 308fdcaeed77..2c7aea7106f9 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -162,10 +162,16 @@ config MOVABLE_NODE Say Y here if you want to hotplug a whole node. Say N here if you want kernel to use memory on all nodes evenly. +# +# Only be set on architectures that have completely implemented memory hotplug +# feature. If you are not sure, don't touch it. +# +config HAVE_BOOTMEM_INFO_NODE + def_bool n + # eventually, we can have this option just 'select SPARSEMEM' config MEMORY_HOTPLUG bool "Allow for memory hot-add" - select MEMORY_ISOLATION depends on SPARSEMEM || X86_64_ACPI_NUMA depends on HOTPLUG && ARCH_ENABLE_MEMORY_HOTPLUG depends on (IA64 || X86 || PPC_BOOK3S_64 || SUPERH || S390) @@ -176,6 +182,8 @@ config MEMORY_HOTPLUG_SPARSE config MEMORY_HOTREMOVE bool "Allow for memory hot remove" + select MEMORY_ISOLATION + select HAVE_BOOTMEM_INFO_NODE if X86_64 depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE depends on MIGRATION @@ -258,6 +266,19 @@ config BOUNCE def_bool y depends on BLOCK && MMU && (ZONE_DMA || HIGHMEM) +# On the 'tile' arch, USB OHCI needs the bounce pool since tilegx will often +# have more than 4GB of memory, but we don't currently use the IOTLB to present +# a 32-bit address to OHCI. So we need to use a bounce pool instead. +# +# We also use the bounce pool to provide stable page writes for jbd. jbd +# initiates buffer writeback without locking the page or setting PG_writeback, +# and fixing that behavior (a second time; jbd2 doesn't have this problem) is +# a major rework effort. Instead, use the bounce buffer to snapshot pages +# (until jbd goes away). The only jbd user is ext3. +config NEED_BOUNCE_POOL + bool + default y if (TILE && USB_OHCI_HCD) || (BLK_DEV_INTEGRITY && JBD) + config NR_QUICK int depends on QUICKLIST diff --git a/mm/backing-dev.c b/mm/backing-dev.c index d3ca2b3ee176..41733c5dc820 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -221,12 +221,23 @@ static ssize_t max_ratio_store(struct device *dev, } BDI_SHOW(max_ratio, bdi->max_ratio) +static ssize_t stable_pages_required_show(struct device *dev, + struct device_attribute *attr, + char *page) +{ + struct backing_dev_info *bdi = dev_get_drvdata(dev); + + return snprintf(page, PAGE_SIZE-1, "%d\n", + bdi_cap_stable_pages_required(bdi) ? 1 : 0); +} + #define __ATTR_RW(attr) __ATTR(attr, 0644, attr##_show, attr##_store) static struct device_attribute bdi_dev_attrs[] = { __ATTR_RW(read_ahead_kb), __ATTR_RW(min_ratio), __ATTR_RW(max_ratio), + __ATTR_RO(stable_pages_required), __ATTR_NULL, }; diff --git a/mm/balloon_compaction.c b/mm/balloon_compaction.c index 07dbc8ec46cf..2c8ce496804f 100644 --- a/mm/balloon_compaction.c +++ b/mm/balloon_compaction.c @@ -242,6 +242,7 @@ bool balloon_page_isolate(struct page *page) if (__is_movable_balloon_page(page) && page_count(page) == 2) { __isolate_balloon_page(page); + balloon_event_count(COMPACTBALLOONISOLATED); unlock_page(page); return true; } @@ -265,6 +266,7 @@ void balloon_page_putback(struct page *page) __putback_balloon_page(page); /* drop the extra ref count taken for page isolation */ put_page(page); + balloon_event_count(COMPACTBALLOONRETURNED); } else { WARN_ON(1); dump_page(page); diff --git a/mm/bounce.c b/mm/bounce.c index 042086775561..5f8901768602 100644 --- a/mm/bounce.c +++ b/mm/bounce.c @@ -178,8 +178,45 @@ static void bounce_end_io_read_isa(struct bio *bio, int err) __bounce_end_io_read(bio, isa_page_pool, err); } +#ifdef CONFIG_NEED_BOUNCE_POOL +static int must_snapshot_stable_pages(struct request_queue *q, struct bio *bio) +{ + struct page *page; + struct backing_dev_info *bdi; + struct address_space *mapping; + struct bio_vec *from; + int i; + + if (bio_data_dir(bio) != WRITE) + return 0; + + if (!bdi_cap_stable_pages_required(&q->backing_dev_info)) + return 0; + + /* + * Based on the first page that has a valid mapping, decide whether or + * not we have to employ bounce buffering to guarantee stable pages. + */ + bio_for_each_segment(from, bio, i) { + page = from->bv_page; + mapping = page_mapping(page); + if (!mapping) + continue; + bdi = mapping->backing_dev_info; + return mapping->host->i_sb->s_flags & MS_SNAP_STABLE; + } + + return 0; +} +#else +static int must_snapshot_stable_pages(struct request_queue *q, struct bio *bio) +{ + return 0; +} +#endif /* CONFIG_NEED_BOUNCE_POOL */ + static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig, - mempool_t *pool) + mempool_t *pool, int force) { struct page *page; struct bio *bio = NULL; @@ -192,7 +229,7 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig, /* * is destination page below bounce pfn? */ - if (page_to_pfn(page) <= queue_bounce_pfn(q)) + if (page_to_pfn(page) <= queue_bounce_pfn(q) && !force) continue; /* @@ -270,6 +307,7 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig, void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig) { + int must_bounce; mempool_t *pool; /* @@ -278,13 +316,15 @@ void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig) if (!bio_has_data(*bio_orig)) return; + must_bounce = must_snapshot_stable_pages(q, *bio_orig); + /* * for non-isa bounce case, just check if the bounce pfn is equal * to or bigger than the highest pfn in the system -- in that case, * don't waste time iterating over bio segments */ if (!(q->bounce_gfp & GFP_DMA)) { - if (queue_bounce_pfn(q) >= blk_max_pfn) + if (queue_bounce_pfn(q) >= blk_max_pfn && !must_bounce) return; pool = page_pool; } else { @@ -295,7 +335,7 @@ void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig) /* * slow path */ - __blk_queue_bounce(q, bio_orig, pool); + __blk_queue_bounce(q, bio_orig, pool, must_bounce); } EXPORT_SYMBOL(blk_queue_bounce); diff --git a/mm/compaction.c b/mm/compaction.c index c62bd063d766..05ccb4cc0bdb 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -15,6 +15,7 @@ #include <linux/sysctl.h> #include <linux/sysfs.h> #include <linux/balloon_compaction.h> +#include <linux/page-isolation.h> #include "internal.h" #ifdef CONFIG_COMPACTION @@ -85,7 +86,7 @@ static inline bool isolation_suitable(struct compact_control *cc, static void __reset_isolation_suitable(struct zone *zone) { unsigned long start_pfn = zone->zone_start_pfn; - unsigned long end_pfn = zone->zone_start_pfn + zone->spanned_pages; + unsigned long end_pfn = zone_end_pfn(zone); unsigned long pfn; zone->compact_cached_migrate_pfn = start_pfn; @@ -215,7 +216,10 @@ static bool suitable_migration_target(struct page *page) int migratetype = get_pageblock_migratetype(page); /* Don't interfere with memory hot-remove or the min_free_kbytes blocks */ - if (migratetype == MIGRATE_ISOLATE || migratetype == MIGRATE_RESERVE) + if (migratetype == MIGRATE_RESERVE) + return false; + + if (is_migrate_isolate(migratetype)) return false; /* If the page is a large free page, then allow migration */ @@ -611,8 +615,7 @@ check_compact_cluster: continue; next_pageblock: - low_pfn += pageblock_nr_pages; - low_pfn = ALIGN(low_pfn, pageblock_nr_pages) - 1; + low_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages) - 1; last_pageblock_nr = pageblock_nr; } @@ -644,7 +647,7 @@ static void isolate_freepages(struct zone *zone, struct compact_control *cc) { struct page *page; - unsigned long high_pfn, low_pfn, pfn, zone_end_pfn, end_pfn; + unsigned long high_pfn, low_pfn, pfn, z_end_pfn, end_pfn; int nr_freepages = cc->nr_freepages; struct list_head *freelist = &cc->freepages; @@ -663,7 +666,7 @@ static void isolate_freepages(struct zone *zone, */ high_pfn = min(low_pfn, pfn); - zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages; + z_end_pfn = zone_end_pfn(zone); /* * Isolate free pages until enough are available to migrate the @@ -706,7 +709,7 @@ static void isolate_freepages(struct zone *zone, * only scans within a pageblock */ end_pfn = ALIGN(pfn + 1, pageblock_nr_pages); - end_pfn = min(end_pfn, zone_end_pfn); + end_pfn = min(end_pfn, z_end_pfn); isolated = isolate_freepages_block(cc, pfn, end_pfn, freelist, false); nr_freepages += isolated; @@ -795,7 +798,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, low_pfn = max(cc->migrate_pfn, zone->zone_start_pfn); /* Only scan within a pageblock boundary */ - end_pfn = ALIGN(low_pfn + pageblock_nr_pages, pageblock_nr_pages); + end_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages); /* Do not cross the free scanner or scan within a memory hole */ if (end_pfn > cc->free_pfn || !pfn_valid(low_pfn)) { @@ -920,7 +923,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) { int ret; unsigned long start_pfn = zone->zone_start_pfn; - unsigned long end_pfn = zone->zone_start_pfn + zone->spanned_pages; + unsigned long end_pfn = zone_end_pfn(zone); ret = compaction_suitable(zone, cc->order); switch (ret) { @@ -977,7 +980,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) nr_migrate = cc->nr_migratepages; err = migrate_pages(&cc->migratepages, compaction_alloc, - (unsigned long)cc, false, + (unsigned long)cc, cc->sync ? MIGRATE_SYNC_LIGHT : MIGRATE_ASYNC, MR_COMPACTION); update_nr_listpages(cc); @@ -1086,7 +1089,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist, /* Compact all zones within a node */ -static int __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc) +static void __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc) { int zoneid; struct zone *zone; @@ -1119,28 +1122,26 @@ static int __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc) VM_BUG_ON(!list_empty(&cc->freepages)); VM_BUG_ON(!list_empty(&cc->migratepages)); } - - return 0; } -int compact_pgdat(pg_data_t *pgdat, int order) +void compact_pgdat(pg_data_t *pgdat, int order) { struct compact_control cc = { .order = order, .sync = false, }; - return __compact_pgdat(pgdat, &cc); + __compact_pgdat(pgdat, &cc); } -static int compact_node(int nid) +static void compact_node(int nid) { struct compact_control cc = { .order = -1, .sync = true, }; - return __compact_pgdat(NODE_DATA(nid), &cc); + __compact_pgdat(NODE_DATA(nid), &cc); } /* Compact all nodes in the system */ diff --git a/mm/dmapool.c b/mm/dmapool.c index c69781e97cf9..668f26316e2e 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -132,6 +132,7 @@ struct dma_pool *dma_pool_create(const char *name, struct device *dev, { struct dma_pool *retval; size_t allocation; + int node; if (align == 0) { align = 1; @@ -156,7 +157,9 @@ struct dma_pool *dma_pool_create(const char *name, struct device *dev, return NULL; } - retval = kmalloc_node(sizeof(*retval), GFP_KERNEL, dev_to_node(dev)); + node = WARN_ON(!dev) ? -1 : dev_to_node(dev); + + retval = kmalloc_node(sizeof(*retval), GFP_KERNEL, node); if (!retval) return retval; diff --git a/mm/filemap.c b/mm/filemap.c index 24a7ea583f0c..c610076c30e1 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1728,6 +1728,7 @@ int filemap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) * see the dirty page and writeprotect it again. */ set_page_dirty(page); + wait_for_stable_page(page); out: sb_end_pagefault(inode->i_sb); return ret; @@ -2274,7 +2275,7 @@ repeat: return NULL; } found: - wait_on_page_writeback(page); + wait_for_stable_page(page); return page; } EXPORT_SYMBOL(grab_cache_page_write_begin); diff --git a/mm/fremap.c b/mm/fremap.c index a0aaf0e56800..0cd4c11488ed 100644 --- a/mm/fremap.c +++ b/mm/fremap.c @@ -129,6 +129,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, struct vm_area_struct *vma; int err = -EINVAL; int has_write_lock = 0; + vm_flags_t vm_flags; if (prot) return err; @@ -160,15 +161,11 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, /* * Make sure the vma is shared, that it supports prefaulting, * and that the remapped range is valid and fully within - * the single existing vma. vm_private_data is used as a - * swapout cursor in a VM_NONLINEAR vma. + * the single existing vma. */ if (!vma || !(vma->vm_flags & VM_SHARED)) goto out; - if (vma->vm_private_data && !(vma->vm_flags & VM_NONLINEAR)) - goto out; - if (!vma->vm_ops || !vma->vm_ops->remap_pages) goto out; @@ -177,6 +174,13 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, /* Must set VM_NONLINEAR before any pages are populated. */ if (!(vma->vm_flags & VM_NONLINEAR)) { + /* + * vm_private_data is used as a swapout cursor + * in a VM_NONLINEAR vma. + */ + if (vma->vm_private_data) + goto out; + /* Don't need a nonlinear mapping, exit success */ if (pgoff == linear_page_index(vma, start)) { err = 0; @@ -184,6 +188,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, } if (!has_write_lock) { +get_write_lock: up_read(&mm->mmap_sem); down_write(&mm->mmap_sem); has_write_lock = 1; @@ -199,9 +204,10 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, unsigned long addr; struct file *file = get_file(vma->vm_file); - flags &= MAP_NONBLOCK; - addr = mmap_region(file, start, size, - flags, vma->vm_flags, pgoff); + vm_flags = vma->vm_flags; + if (!(flags & MAP_NONBLOCK)) + vm_flags |= VM_POPULATE; + addr = mmap_region(file, start, size, vm_flags, pgoff); fput(file); if (IS_ERR_VALUE(addr)) { err = addr; @@ -220,32 +226,26 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, mutex_unlock(&mapping->i_mmap_mutex); } + if (!(flags & MAP_NONBLOCK) && !(vma->vm_flags & VM_POPULATE)) { + if (!has_write_lock) + goto get_write_lock; + vma->vm_flags |= VM_POPULATE; + } + if (vma->vm_flags & VM_LOCKED) { /* * drop PG_Mlocked flag for over-mapped range */ - vm_flags_t saved_flags = vma->vm_flags; + if (!has_write_lock) + goto get_write_lock; + vm_flags = vma->vm_flags; munlock_vma_pages_range(vma, start, start + size); - vma->vm_flags = saved_flags; + vma->vm_flags = vm_flags; } mmu_notifier_invalidate_range_start(mm, start, start + size); err = vma->vm_ops->remap_pages(vma, start, size, pgoff); mmu_notifier_invalidate_range_end(mm, start, start + size); - if (!err && !(flags & MAP_NONBLOCK)) { - if (vma->vm_flags & VM_LOCKED) { - /* - * might be mapping previously unmapped range of file - */ - mlock_vma_pages_range(vma, start, start + size); - } else { - if (unlikely(has_write_lock)) { - downgrade_write(&mm->mmap_sem); - has_write_lock = 0; - } - make_pages_present(start, start+size); - } - } /* * We can't clear VM_NONLINEAR because we'd have to do @@ -254,10 +254,13 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, */ out: + vm_flags = vma->vm_flags; if (likely(!has_write_lock)) up_read(&mm->mmap_sem); else up_write(&mm->mmap_sem); + if (!err && ((vm_flags & VM_LOCKED) || !(flags & MAP_NONBLOCK))) + mm_populate(start, size); return err; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index b5783d81eda9..e2f7f5aaaafb 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -20,6 +20,7 @@ #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/migrate.h> +#include <linux/hashtable.h> #include <asm/tlb.h> #include <asm/pgalloc.h> @@ -62,12 +63,11 @@ static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait); static unsigned int khugepaged_max_ptes_none __read_mostly = HPAGE_PMD_NR-1; static int khugepaged(void *none); -static int mm_slots_hash_init(void); static int khugepaged_slab_init(void); -static void khugepaged_slab_free(void); -#define MM_SLOTS_HASH_HEADS 1024 -static struct hlist_head *mm_slots_hash __read_mostly; +#define MM_SLOTS_HASH_BITS 10 +static __read_mostly DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS); + static struct kmem_cache *mm_slot_cache __read_mostly; /** @@ -105,7 +105,6 @@ static int set_recommended_min_free_kbytes(void) struct zone *zone; int nr_zones = 0; unsigned long recommended_min; - extern int min_free_kbytes; if (!khugepaged_enabled()) return 0; @@ -634,12 +633,6 @@ static int __init hugepage_init(void) if (err) goto out; - err = mm_slots_hash_init(); - if (err) { - khugepaged_slab_free(); - goto out; - } - register_shrinker(&huge_zero_page_shrinker); /* @@ -1302,7 +1295,6 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, int target_nid; int current_nid = -1; bool migrated; - bool page_locked = false; spin_lock(&mm->page_table_lock); if (unlikely(!pmd_same(pmd, *pmdp))) @@ -1324,7 +1316,6 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, /* Acquire the page lock to serialise THP migrations */ spin_unlock(&mm->page_table_lock); lock_page(page); - page_locked = true; /* Confirm the PTE did not while locked */ spin_lock(&mm->page_table_lock); @@ -1337,34 +1328,26 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, /* Migrate the THP to the requested node */ migrated = migrate_misplaced_transhuge_page(mm, vma, - pmdp, pmd, addr, - page, target_nid); - if (migrated) - current_nid = target_nid; - else { - spin_lock(&mm->page_table_lock); - if (unlikely(!pmd_same(pmd, *pmdp))) { - unlock_page(page); - goto out_unlock; - } - goto clear_pmdnuma; - } + pmdp, pmd, addr, page, target_nid); + if (!migrated) + goto check_same; - task_numa_fault(current_nid, HPAGE_PMD_NR, migrated); + task_numa_fault(target_nid, HPAGE_PMD_NR, true); return 0; +check_same: + spin_lock(&mm->page_table_lock); + if (unlikely(!pmd_same(pmd, *pmdp))) + goto out_unlock; clear_pmdnuma: pmd = pmd_mknonnuma(pmd); set_pmd_at(mm, haddr, pmdp, pmd); VM_BUG_ON(pmd_numa(*pmdp)); update_mmu_cache_pmd(vma, addr, pmdp); - if (page_locked) - unlock_page(page); - out_unlock: spin_unlock(&mm->page_table_lock); if (current_nid != -1) - task_numa_fault(current_nid, HPAGE_PMD_NR, migrated); + task_numa_fault(current_nid, HPAGE_PMD_NR, false); return 0; } @@ -1656,7 +1639,7 @@ static void __split_huge_page_refcount(struct page *page) page_tail->mapping = page->mapping; page_tail->index = page->index + i; - page_xchg_last_nid(page_tail, page_last_nid(page)); + page_nid_xchg_last(page_tail, page_nid_last(page)); BUG_ON(!PageAnon(page_tail)); BUG_ON(!PageUptodate(page_tail)); @@ -1846,7 +1829,7 @@ int split_huge_page(struct page *page) BUG_ON(PageCompound(page)); out_unlock: - anon_vma_unlock(anon_vma); + anon_vma_unlock_write(anon_vma); put_anon_vma(anon_vma); out: return ret; @@ -1908,12 +1891,6 @@ static int __init khugepaged_slab_init(void) return 0; } -static void __init khugepaged_slab_free(void) -{ - kmem_cache_destroy(mm_slot_cache); - mm_slot_cache = NULL; -} - static inline struct mm_slot *alloc_mm_slot(void) { if (!mm_slot_cache) /* initialization failed */ @@ -1926,47 +1903,22 @@ static inline void free_mm_slot(struct mm_slot *mm_slot) kmem_cache_free(mm_slot_cache, mm_slot); } -static int __init mm_slots_hash_init(void) -{ - mm_slots_hash = kzalloc(MM_SLOTS_HASH_HEADS * sizeof(struct hlist_head), - GFP_KERNEL); - if (!mm_slots_hash) - return -ENOMEM; - return 0; -} - -#if 0 -static void __init mm_slots_hash_free(void) -{ - kfree(mm_slots_hash); - mm_slots_hash = NULL; -} -#endif - static struct mm_slot *get_mm_slot(struct mm_struct *mm) { struct mm_slot *mm_slot; - struct hlist_head *bucket; - struct hlist_node *node; - bucket = &mm_slots_hash[((unsigned long)mm / sizeof(struct mm_struct)) - % MM_SLOTS_HASH_HEADS]; - hlist_for_each_entry(mm_slot, node, bucket, hash) { + hash_for_each_possible(mm_slots_hash, mm_slot, hash, (unsigned long)mm) if (mm == mm_slot->mm) return mm_slot; - } + return NULL; } static void insert_to_mm_slots_hash(struct mm_struct *mm, struct mm_slot *mm_slot) { - struct hlist_head *bucket; - - bucket = &mm_slots_hash[((unsigned long)mm / sizeof(struct mm_struct)) - % MM_SLOTS_HASH_HEADS]; mm_slot->mm = mm; - hlist_add_head(&mm_slot->hash, bucket); + hash_add(mm_slots_hash, &mm_slot->hash, (long)mm); } static inline int khugepaged_test_exit(struct mm_struct *mm) @@ -2035,7 +1987,7 @@ void __khugepaged_exit(struct mm_struct *mm) spin_lock(&khugepaged_mm_lock); mm_slot = get_mm_slot(mm); if (mm_slot && khugepaged_scan.mm_slot != mm_slot) { - hlist_del(&mm_slot->hash); + hash_del(&mm_slot->hash); list_del(&mm_slot->mm_node); free = 1; } @@ -2368,7 +2320,7 @@ static void collapse_huge_page(struct mm_struct *mm, BUG_ON(!pmd_none(*pmd)); set_pmd_at(mm, address, pmd, _pmd); spin_unlock(&mm->page_table_lock); - anon_vma_unlock(vma->anon_vma); + anon_vma_unlock_write(vma->anon_vma); goto out; } @@ -2376,7 +2328,7 @@ static void collapse_huge_page(struct mm_struct *mm, * All pages are isolated and locked so anon_vma rmap * can't run anymore. */ - anon_vma_unlock(vma->anon_vma); + anon_vma_unlock_write(vma->anon_vma); __collapse_huge_page_copy(pte, new_page, vma, address, ptl); pte_unmap(pte); @@ -2423,7 +2375,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, struct page *page; unsigned long _address; spinlock_t *ptl; - int node = -1; + int node = NUMA_NO_NODE; VM_BUG_ON(address & ~HPAGE_PMD_MASK); @@ -2453,7 +2405,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, * be more sophisticated and look at more pages, * but isn't for now. */ - if (node == -1) + if (node == NUMA_NO_NODE) node = page_to_nid(page); VM_BUG_ON(PageCompound(page)); if (!PageLRU(page) || PageLocked(page) || !PageAnon(page)) @@ -2484,7 +2436,7 @@ static void collect_mm_slot(struct mm_slot *mm_slot) if (khugepaged_test_exit(mm)) { /* free mm_slot */ - hlist_del(&mm_slot->hash); + hash_del(&mm_slot->hash); list_del(&mm_slot->mm_node); /* diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 546db81820e4..e14a8c79a1eb 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1293,8 +1293,7 @@ static void __init report_hugepages(void) for_each_hstate(h) { char buf[32]; - printk(KERN_INFO "HugeTLB registered %s page size, " - "pre-allocated %ld pages\n", + pr_info("HugeTLB registered %s page size, pre-allocated %ld pages\n", memfmt(buf, huge_page_size(h)), h->free_huge_pages); } @@ -1702,8 +1701,7 @@ static void __init hugetlb_sysfs_init(void) err = hugetlb_sysfs_add_hstate(h, hugepages_kobj, hstate_kobjs, &hstate_attr_group); if (err) - printk(KERN_ERR "Hugetlb: Unable to add hstate %s", - h->name); + pr_err("Hugetlb: Unable to add hstate %s", h->name); } } @@ -1826,9 +1824,8 @@ void hugetlb_register_node(struct node *node) nhs->hstate_kobjs, &per_node_hstate_attr_group); if (err) { - printk(KERN_ERR "Hugetlb: Unable to add hstate %s" - " for node %d\n", - h->name, node->dev.id); + pr_err("Hugetlb: Unable to add hstate %s for node %d\n", + h->name, node->dev.id); hugetlb_unregister_node(node); break; } @@ -1924,7 +1921,7 @@ void __init hugetlb_add_hstate(unsigned order) unsigned long i; if (size_to_hstate(PAGE_SIZE << order)) { - printk(KERN_WARNING "hugepagesz= specified twice, ignoring\n"); + pr_warning("hugepagesz= specified twice, ignoring\n"); return; } BUG_ON(hugetlb_max_hstate >= HUGE_MAX_HSTATE); @@ -1960,8 +1957,8 @@ static int __init hugetlb_nrpages_setup(char *s) mhp = &parsed_hstate->max_huge_pages; if (mhp == last_mhp) { - printk(KERN_WARNING "hugepages= specified twice without " - "interleaving hugepagesz=, ignoring\n"); + pr_warning("hugepages= specified twice without " + "interleaving hugepagesz=, ignoring\n"); return 1; } @@ -2692,9 +2689,8 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, * COW. Warn that such a situation has occurred as it may not be obvious */ if (is_vma_resv_set(vma, HPAGE_RESV_UNMAPPED)) { - printk(KERN_WARNING - "PID %d killed due to inadequate hugepage pool\n", - current->pid); + pr_warning("PID %d killed due to inadequate hugepage pool\n", + current->pid); return ret; } diff --git a/mm/internal.h b/mm/internal.h index 9ba21100ebf3..1c0c4cc0fcf7 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -162,8 +162,8 @@ void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, struct rb_node *rb_parent); #ifdef CONFIG_MMU -extern long mlock_vma_pages_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end); +extern long __mlock_vma_pages_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end, int *nonblocking); extern void munlock_vma_pages_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); static inline void munlock_vma_pages_all(struct vm_area_struct *vma) diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 752a705c77c2..c8d7f3110fd0 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -436,7 +436,7 @@ static int get_object(struct kmemleak_object *object) */ static void free_object_rcu(struct rcu_head *rcu) { - struct hlist_node *elem, *tmp; + struct hlist_node *tmp; struct kmemleak_scan_area *area; struct kmemleak_object *object = container_of(rcu, struct kmemleak_object, rcu); @@ -445,8 +445,8 @@ static void free_object_rcu(struct rcu_head *rcu) * Once use_count is 0 (guaranteed by put_object), there is no other * code accessing this object, hence no need for locking. */ - hlist_for_each_entry_safe(area, elem, tmp, &object->area_list, node) { - hlist_del(elem); + hlist_for_each_entry_safe(area, tmp, &object->area_list, node) { + hlist_del(&area->node); kmem_cache_free(scan_area_cache, area); } kmem_cache_free(object_cache, object); @@ -1177,7 +1177,6 @@ static void scan_block(void *_start, void *_end, static void scan_object(struct kmemleak_object *object) { struct kmemleak_scan_area *area; - struct hlist_node *elem; unsigned long flags; /* @@ -1205,7 +1204,7 @@ static void scan_object(struct kmemleak_object *object) spin_lock_irqsave(&object->lock, flags); } } else - hlist_for_each_entry(area, elem, &object->area_list, node) + hlist_for_each_entry(area, &object->area_list, node) scan_block((void *)area->start, (void *)(area->start + area->size), object, 0); @@ -1300,9 +1299,8 @@ static void kmemleak_scan(void) */ lock_memory_hotplug(); for_each_online_node(i) { - pg_data_t *pgdat = NODE_DATA(i); - unsigned long start_pfn = pgdat->node_start_pfn; - unsigned long end_pfn = start_pfn + pgdat->node_spanned_pages; + unsigned long start_pfn = node_start_pfn(i); + unsigned long end_pfn = node_end_pfn(i); unsigned long pfn; for (pfn = start_pfn; pfn < end_pfn; pfn++) { @@ -33,13 +33,22 @@ #include <linux/mmu_notifier.h> #include <linux/swap.h> #include <linux/ksm.h> -#include <linux/hash.h> +#include <linux/hashtable.h> #include <linux/freezer.h> #include <linux/oom.h> +#include <linux/numa.h> #include <asm/tlbflush.h> #include "internal.h" +#ifdef CONFIG_NUMA +#define NUMA(x) (x) +#define DO_NUMA(x) do { (x); } while (0) +#else +#define NUMA(x) (0) +#define DO_NUMA(x) do { } while (0) +#endif + /* * A few notes about the KSM scanning process, * to make it easier to understand the data structures below: @@ -113,13 +122,25 @@ struct ksm_scan { /** * struct stable_node - node of the stable rbtree * @node: rb node of this ksm page in the stable tree + * @head: (overlaying parent) &migrate_nodes indicates temporarily on that list + * @list: linked into migrate_nodes, pending placement in the proper node tree * @hlist: hlist head of rmap_items using this ksm page - * @kpfn: page frame number of this ksm page + * @kpfn: page frame number of this ksm page (perhaps temporarily on wrong nid) + * @nid: NUMA node id of stable tree in which linked (may not match kpfn) */ struct stable_node { - struct rb_node node; + union { + struct rb_node node; /* when node of stable tree */ + struct { /* when listed for migration */ + struct list_head *head; + struct list_head list; + }; + }; struct hlist_head hlist; unsigned long kpfn; +#ifdef CONFIG_NUMA + int nid; +#endif }; /** @@ -129,6 +150,7 @@ struct stable_node { * @mm: the memory structure this rmap_item is pointing into * @address: the virtual address this rmap_item tracks (+ flags in low bits) * @oldchecksum: previous checksum of the page at that virtual address + * @nid: NUMA node id of unstable tree in which linked (may not match page) * @node: rb node of this rmap_item in the unstable tree * @head: pointer to stable_node heading this list in the stable tree * @hlist: link into hlist of rmap_items hanging off that stable_node @@ -139,6 +161,9 @@ struct rmap_item { struct mm_struct *mm; unsigned long address; /* + low bits used for flags below */ unsigned int oldchecksum; /* when unstable */ +#ifdef CONFIG_NUMA + int nid; +#endif union { struct rb_node node; /* when node of unstable tree */ struct { /* when listed from stable tree */ @@ -153,12 +178,14 @@ struct rmap_item { #define STABLE_FLAG 0x200 /* is listed from the stable tree */ /* The stable and unstable tree heads */ -static struct rb_root root_stable_tree = RB_ROOT; -static struct rb_root root_unstable_tree = RB_ROOT; +static struct rb_root root_unstable_tree[MAX_NUMNODES]; +static struct rb_root root_stable_tree[MAX_NUMNODES]; + +/* Recently migrated nodes of stable tree, pending proper placement */ +static LIST_HEAD(migrate_nodes); -#define MM_SLOTS_HASH_SHIFT 10 -#define MM_SLOTS_HASH_HEADS (1 << MM_SLOTS_HASH_SHIFT) -static struct hlist_head mm_slots_hash[MM_SLOTS_HASH_HEADS]; +#define MM_SLOTS_HASH_BITS 10 +static DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS); static struct mm_slot ksm_mm_head = { .mm_list = LIST_HEAD_INIT(ksm_mm_head.mm_list), @@ -189,10 +216,19 @@ static unsigned int ksm_thread_pages_to_scan = 100; /* Milliseconds ksmd should sleep between batches */ static unsigned int ksm_thread_sleep_millisecs = 20; +#ifdef CONFIG_NUMA +/* Zeroed when merging across nodes is not allowed */ +static unsigned int ksm_merge_across_nodes = 1; +#else +#define ksm_merge_across_nodes 1U +#endif + #define KSM_RUN_STOP 0 #define KSM_RUN_MERGE 1 #define KSM_RUN_UNMERGE 2 -static unsigned int ksm_run = KSM_RUN_STOP; +#define KSM_RUN_OFFLINE 4 +static unsigned long ksm_run = KSM_RUN_STOP; +static void wait_while_offlining(void); static DECLARE_WAIT_QUEUE_HEAD(ksm_thread_wait); static DEFINE_MUTEX(ksm_thread_mutex); @@ -275,31 +311,20 @@ static inline void free_mm_slot(struct mm_slot *mm_slot) static struct mm_slot *get_mm_slot(struct mm_struct *mm) { - struct mm_slot *mm_slot; - struct hlist_head *bucket; - struct hlist_node *node; + struct mm_slot *slot; + + hash_for_each_possible(mm_slots_hash, slot, link, (unsigned long)mm) + if (slot->mm == mm) + return slot; - bucket = &mm_slots_hash[hash_ptr(mm, MM_SLOTS_HASH_SHIFT)]; - hlist_for_each_entry(mm_slot, node, bucket, link) { - if (mm == mm_slot->mm) - return mm_slot; - } return NULL; } static void insert_to_mm_slots_hash(struct mm_struct *mm, struct mm_slot *mm_slot) { - struct hlist_head *bucket; - - bucket = &mm_slots_hash[hash_ptr(mm, MM_SLOTS_HASH_SHIFT)]; mm_slot->mm = mm; - hlist_add_head(&mm_slot->link, bucket); -} - -static inline int in_stable_tree(struct rmap_item *rmap_item) -{ - return rmap_item->address & STABLE_FLAG; + hash_add(mm_slots_hash, &mm_slot->link, (unsigned long)mm); } /* @@ -447,12 +472,22 @@ out: page = NULL; return page; } +/* + * This helper is used for getting right index into array of tree roots. + * When merge_across_nodes knob is set to 1, there are only two rb-trees for + * stable and unstable pages from all nodes with roots in index 0. Otherwise, + * every node has its own stable and unstable tree. + */ +static inline int get_kpfn_nid(unsigned long kpfn) +{ + return ksm_merge_across_nodes ? 0 : pfn_to_nid(kpfn); +} + static void remove_node_from_stable_tree(struct stable_node *stable_node) { struct rmap_item *rmap_item; - struct hlist_node *hlist; - hlist_for_each_entry(rmap_item, hlist, &stable_node->hlist, hlist) { + hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) { if (rmap_item->hlist.next) ksm_pages_sharing--; else @@ -462,7 +497,11 @@ static void remove_node_from_stable_tree(struct stable_node *stable_node) cond_resched(); } - rb_erase(&stable_node->node, &root_stable_tree); + if (stable_node->head == &migrate_nodes) + list_del(&stable_node->list); + else + rb_erase(&stable_node->node, + &root_stable_tree[NUMA(stable_node->nid)]); free_stable_node(stable_node); } @@ -472,6 +511,7 @@ static void remove_node_from_stable_tree(struct stable_node *stable_node) * In which case we can trust the content of the page, and it * returns the gotten page; but if the page has now been zapped, * remove the stale node from the stable tree and return NULL. + * But beware, the stable node's page might be being migrated. * * You would expect the stable_node to hold a reference to the ksm page. * But if it increments the page's count, swapping out has to wait for @@ -482,40 +522,77 @@ static void remove_node_from_stable_tree(struct stable_node *stable_node) * pointing back to this stable node. This relies on freeing a PageAnon * page to reset its page->mapping to NULL, and relies on no other use of * a page to put something that might look like our key in page->mapping. - * - * include/linux/pagemap.h page_cache_get_speculative() is a good reference, - * but this is different - made simpler by ksm_thread_mutex being held, but - * interesting for assuming that no other use of the struct page could ever - * put our expected_mapping into page->mapping (or a field of the union which - * coincides with page->mapping). The RCU calls are not for KSM at all, but - * to keep the page_count protocol described with page_cache_get_speculative. - * - * Note: it is possible that get_ksm_page() will return NULL one moment, - * then page the next, if the page is in between page_freeze_refs() and - * page_unfreeze_refs(): this shouldn't be a problem anywhere, the page * is on its way to being freed; but it is an anomaly to bear in mind. */ -static struct page *get_ksm_page(struct stable_node *stable_node) +static struct page *get_ksm_page(struct stable_node *stable_node, bool locked) { struct page *page; void *expected_mapping; + unsigned long kpfn; - page = pfn_to_page(stable_node->kpfn); expected_mapping = (void *)stable_node + (PAGE_MAPPING_ANON | PAGE_MAPPING_KSM); - rcu_read_lock(); - if (page->mapping != expected_mapping) - goto stale; - if (!get_page_unless_zero(page)) +again: + kpfn = ACCESS_ONCE(stable_node->kpfn); + page = pfn_to_page(kpfn); + + /* + * page is computed from kpfn, so on most architectures reading + * page->mapping is naturally ordered after reading node->kpfn, + * but on Alpha we need to be more careful. + */ + smp_read_barrier_depends(); + if (ACCESS_ONCE(page->mapping) != expected_mapping) goto stale; - if (page->mapping != expected_mapping) { + + /* + * We cannot do anything with the page while its refcount is 0. + * Usually 0 means free, or tail of a higher-order page: in which + * case this node is no longer referenced, and should be freed; + * however, it might mean that the page is under page_freeze_refs(). + * The __remove_mapping() case is easy, again the node is now stale; + * but if page is swapcache in migrate_page_move_mapping(), it might + * still be our page, in which case it's essential to keep the node. + */ + while (!get_page_unless_zero(page)) { + /* + * Another check for page->mapping != expected_mapping would + * work here too. We have chosen the !PageSwapCache test to + * optimize the common case, when the page is or is about to + * be freed: PageSwapCache is cleared (under spin_lock_irq) + * in the freeze_refs section of __remove_mapping(); but Anon + * page->mapping reset to NULL later, in free_pages_prepare(). + */ + if (!PageSwapCache(page)) + goto stale; + cpu_relax(); + } + + if (ACCESS_ONCE(page->mapping) != expected_mapping) { put_page(page); goto stale; } - rcu_read_unlock(); + + if (locked) { + lock_page(page); + if (ACCESS_ONCE(page->mapping) != expected_mapping) { + unlock_page(page); + put_page(page); + goto stale; + } + } return page; + stale: - rcu_read_unlock(); + /* + * We come here from above when page->mapping or !PageSwapCache + * suggests that the node is stale; but it might be under migration. + * We need smp_rmb(), matching the smp_wmb() in ksm_migrate_page(), + * before checking whether node->kpfn has been changed. + */ + smp_rmb(); + if (ACCESS_ONCE(stable_node->kpfn) != kpfn) + goto again; remove_node_from_stable_tree(stable_node); return NULL; } @@ -531,11 +608,10 @@ static void remove_rmap_item_from_tree(struct rmap_item *rmap_item) struct page *page; stable_node = rmap_item->head; - page = get_ksm_page(stable_node); + page = get_ksm_page(stable_node, true); if (!page) goto out; - lock_page(page); hlist_del(&rmap_item->hlist); unlock_page(page); put_page(page); @@ -560,8 +636,8 @@ static void remove_rmap_item_from_tree(struct rmap_item *rmap_item) age = (unsigned char)(ksm_scan.seqnr - rmap_item->address); BUG_ON(age > 1); if (!age) - rb_erase(&rmap_item->node, &root_unstable_tree); - + rb_erase(&rmap_item->node, + &root_unstable_tree[NUMA(rmap_item->nid)]); ksm_pages_unshared--; rmap_item->address &= PAGE_MASK; } @@ -581,7 +657,7 @@ static void remove_trailing_rmap_items(struct mm_slot *mm_slot, } /* - * Though it's very tempting to unmerge in_stable_tree(rmap_item)s rather + * Though it's very tempting to unmerge rmap_items from stable tree rather * than check every pte of a given vma, the locking doesn't quite work for * that - an rmap_item is assigned to the stable tree after inserting ksm * page and upping mmap_sem. Nor does it fit with the way we skip dup'ing @@ -614,6 +690,64 @@ static int unmerge_ksm_pages(struct vm_area_struct *vma, /* * Only called through the sysfs control interface: */ +static int remove_stable_node(struct stable_node *stable_node) +{ + struct page *page; + int err; + + page = get_ksm_page(stable_node, true); + if (!page) { + /* + * get_ksm_page did remove_node_from_stable_tree itself. + */ + return 0; + } + + if (WARN_ON_ONCE(page_mapped(page))) + err = -EBUSY; + else { + /* + * This page might be in a pagevec waiting to be freed, + * or it might be PageSwapCache (perhaps under writeback), + * or it might have been removed from swapcache a moment ago. + */ + set_page_stable_node(page, NULL); + remove_node_from_stable_tree(stable_node); + err = 0; + } + + unlock_page(page); + put_page(page); + return err; +} + +static int remove_all_stable_nodes(void) +{ + struct stable_node *stable_node; + struct list_head *this, *next; + int nid; + int err = 0; + + for (nid = 0; nid < nr_node_ids; nid++) { + while (root_stable_tree[nid].rb_node) { + stable_node = rb_entry(root_stable_tree[nid].rb_node, + struct stable_node, node); + if (remove_stable_node(stable_node)) { + err = -EBUSY; + break; /* proceed to next nid */ + } + cond_resched(); + } + } + list_for_each_safe(this, next, &migrate_nodes) { + stable_node = list_entry(this, struct stable_node, list); + if (remove_stable_node(stable_node)) + err = -EBUSY; + cond_resched(); + } + return err; +} + static int unmerge_and_remove_all_rmap_items(void) { struct mm_slot *mm_slot; @@ -647,7 +781,7 @@ static int unmerge_and_remove_all_rmap_items(void) ksm_scan.mm_slot = list_entry(mm_slot->mm_list.next, struct mm_slot, mm_list); if (ksm_test_exit(mm)) { - hlist_del(&mm_slot->link); + hash_del(&mm_slot->link); list_del(&mm_slot->mm_list); spin_unlock(&ksm_mmlist_lock); @@ -661,6 +795,8 @@ static int unmerge_and_remove_all_rmap_items(void) } } + /* Clean up stable nodes, but don't worry if some are still busy */ + remove_all_stable_nodes(); ksm_scan.seqnr = 0; return 0; @@ -996,42 +1132,98 @@ static struct page *try_to_merge_two_pages(struct rmap_item *rmap_item, */ static struct page *stable_tree_search(struct page *page) { - struct rb_node *node = root_stable_tree.rb_node; + int nid; + struct rb_node **new; + struct rb_node *parent; struct stable_node *stable_node; + struct stable_node *page_node; - stable_node = page_stable_node(page); - if (stable_node) { /* ksm page forked */ + page_node = page_stable_node(page); + if (page_node && page_node->head != &migrate_nodes) { + /* ksm page forked */ get_page(page); return page; } - while (node) { + nid = get_kpfn_nid(page_to_pfn(page)); +again: + new = &root_stable_tree[nid].rb_node; + parent = NULL; + + while (*new) { struct page *tree_page; int ret; cond_resched(); - stable_node = rb_entry(node, struct stable_node, node); - tree_page = get_ksm_page(stable_node); + stable_node = rb_entry(*new, struct stable_node, node); + tree_page = get_ksm_page(stable_node, false); if (!tree_page) return NULL; ret = memcmp_pages(page, tree_page); + put_page(tree_page); - if (ret < 0) { - put_page(tree_page); - node = node->rb_left; - } else if (ret > 0) { - put_page(tree_page); - node = node->rb_right; - } else - return tree_page; + parent = *new; + if (ret < 0) + new = &parent->rb_left; + else if (ret > 0) + new = &parent->rb_right; + else { + /* + * Lock and unlock the stable_node's page (which + * might already have been migrated) so that page + * migration is sure to notice its raised count. + * It would be more elegant to return stable_node + * than kpage, but that involves more changes. + */ + tree_page = get_ksm_page(stable_node, true); + if (tree_page) { + unlock_page(tree_page); + if (get_kpfn_nid(stable_node->kpfn) != + NUMA(stable_node->nid)) { + put_page(tree_page); + goto replace; + } + return tree_page; + } + /* + * There is now a place for page_node, but the tree may + * have been rebalanced, so re-evaluate parent and new. + */ + if (page_node) + goto again; + return NULL; + } } - return NULL; + if (!page_node) + return NULL; + + list_del(&page_node->list); + DO_NUMA(page_node->nid = nid); + rb_link_node(&page_node->node, parent, new); + rb_insert_color(&page_node->node, &root_stable_tree[nid]); + get_page(page); + return page; + +replace: + if (page_node) { + list_del(&page_node->list); + DO_NUMA(page_node->nid = nid); + rb_replace_node(&stable_node->node, + &page_node->node, &root_stable_tree[nid]); + get_page(page); + } else { + rb_erase(&stable_node->node, &root_stable_tree[nid]); + page = NULL; + } + stable_node->head = &migrate_nodes; + list_add(&stable_node->list, stable_node->head); + return page; } /* - * stable_tree_insert - insert rmap_item pointing to new ksm page + * stable_tree_insert - insert stable tree node pointing to new ksm page * into the stable tree. * * This function returns the stable tree node just allocated on success, @@ -1039,17 +1231,23 @@ static struct page *stable_tree_search(struct page *page) */ static struct stable_node *stable_tree_insert(struct page *kpage) { - struct rb_node **new = &root_stable_tree.rb_node; + int nid; + unsigned long kpfn; + struct rb_node **new; struct rb_node *parent = NULL; struct stable_node *stable_node; + kpfn = page_to_pfn(kpage); + nid = get_kpfn_nid(kpfn); + new = &root_stable_tree[nid].rb_node; + while (*new) { struct page *tree_page; int ret; cond_resched(); stable_node = rb_entry(*new, struct stable_node, node); - tree_page = get_ksm_page(stable_node); + tree_page = get_ksm_page(stable_node, false); if (!tree_page) return NULL; @@ -1075,13 +1273,12 @@ static struct stable_node *stable_tree_insert(struct page *kpage) if (!stable_node) return NULL; - rb_link_node(&stable_node->node, parent, new); - rb_insert_color(&stable_node->node, &root_stable_tree); - INIT_HLIST_HEAD(&stable_node->hlist); - - stable_node->kpfn = page_to_pfn(kpage); + stable_node->kpfn = kpfn; set_page_stable_node(kpage, stable_node); + DO_NUMA(stable_node->nid = nid); + rb_link_node(&stable_node->node, parent, new); + rb_insert_color(&stable_node->node, &root_stable_tree[nid]); return stable_node; } @@ -1104,10 +1301,15 @@ static struct rmap_item *unstable_tree_search_insert(struct rmap_item *rmap_item, struct page *page, struct page **tree_pagep) - { - struct rb_node **new = &root_unstable_tree.rb_node; + struct rb_node **new; + struct rb_root *root; struct rb_node *parent = NULL; + int nid; + + nid = get_kpfn_nid(page_to_pfn(page)); + root = &root_unstable_tree[nid]; + new = &root->rb_node; while (*new) { struct rmap_item *tree_rmap_item; @@ -1128,6 +1330,16 @@ struct rmap_item *unstable_tree_search_insert(struct rmap_item *rmap_item, return NULL; } + /* + * If tree_page has been migrated to another NUMA node, it + * will be flushed out and put into the right unstable tree + * next time: only merge with it if merge_across_nodes. + */ + if (!ksm_merge_across_nodes && page_to_nid(tree_page) != nid) { + put_page(tree_page); + return NULL; + } + ret = memcmp_pages(page, tree_page); parent = *new; @@ -1145,8 +1357,9 @@ struct rmap_item *unstable_tree_search_insert(struct rmap_item *rmap_item, rmap_item->address |= UNSTABLE_FLAG; rmap_item->address |= (ksm_scan.seqnr & SEQNR_MASK); + DO_NUMA(rmap_item->nid = nid); rb_link_node(&rmap_item->node, parent, new); - rb_insert_color(&rmap_item->node, &root_unstable_tree); + rb_insert_color(&rmap_item->node, root); ksm_pages_unshared++; return NULL; @@ -1188,10 +1401,29 @@ static void cmp_and_merge_page(struct page *page, struct rmap_item *rmap_item) unsigned int checksum; int err; - remove_rmap_item_from_tree(rmap_item); + stable_node = page_stable_node(page); + if (stable_node) { + if (stable_node->head != &migrate_nodes && + get_kpfn_nid(stable_node->kpfn) != NUMA(stable_node->nid)) { + rb_erase(&stable_node->node, + &root_stable_tree[NUMA(stable_node->nid)]); + stable_node->head = &migrate_nodes; + list_add(&stable_node->list, stable_node->head); + } + if (stable_node->head != &migrate_nodes && + rmap_item->head == stable_node) + return; + } /* We first start with searching the page inside the stable tree */ kpage = stable_tree_search(page); + if (kpage == page && rmap_item->head == stable_node) { + put_page(kpage); + return; + } + + remove_rmap_item_from_tree(rmap_item); + if (kpage) { err = try_to_merge_with_ksm_page(rmap_item, page, kpage); if (!err) { @@ -1289,6 +1521,7 @@ static struct rmap_item *scan_get_next_rmap_item(struct page **page) struct mm_slot *slot; struct vm_area_struct *vma; struct rmap_item *rmap_item; + int nid; if (list_empty(&ksm_mm_head.mm_list)) return NULL; @@ -1307,7 +1540,29 @@ static struct rmap_item *scan_get_next_rmap_item(struct page **page) */ lru_add_drain_all(); - root_unstable_tree = RB_ROOT; + /* + * Whereas stale stable_nodes on the stable_tree itself + * get pruned in the regular course of stable_tree_search(), + * those moved out to the migrate_nodes list can accumulate: + * so prune them once before each full scan. + */ + if (!ksm_merge_across_nodes) { + struct stable_node *stable_node; + struct list_head *this, *next; + struct page *page; + + list_for_each_safe(this, next, &migrate_nodes) { + stable_node = list_entry(this, + struct stable_node, list); + page = get_ksm_page(stable_node, false); + if (page) + put_page(page); + cond_resched(); + } + } + + for (nid = 0; nid < nr_node_ids; nid++) + root_unstable_tree[nid] = RB_ROOT; spin_lock(&ksm_mmlist_lock); slot = list_entry(slot->mm_list.next, struct mm_slot, mm_list); @@ -1392,7 +1647,7 @@ next_mm: * or when all VM_MERGEABLE areas have been unmapped (and * mmap_sem then protects against race with MADV_MERGEABLE). */ - hlist_del(&slot->link); + hash_del(&slot->link); list_del(&slot->mm_list); spin_unlock(&ksm_mmlist_lock); @@ -1428,8 +1683,7 @@ static void ksm_do_scan(unsigned int scan_npages) rmap_item = scan_get_next_rmap_item(&page); if (!rmap_item) return; - if (!PageKsm(page) || !in_stable_tree(rmap_item)) - cmp_and_merge_page(page, rmap_item); + cmp_and_merge_page(page, rmap_item); put_page(page); } } @@ -1446,6 +1700,7 @@ static int ksm_scan_thread(void *nothing) while (!kthread_should_stop()) { mutex_lock(&ksm_thread_mutex); + wait_while_offlining(); if (ksmd_should_run()) ksm_do_scan(ksm_thread_pages_to_scan); mutex_unlock(&ksm_thread_mutex); @@ -1525,11 +1780,19 @@ int __ksm_enter(struct mm_struct *mm) spin_lock(&ksm_mmlist_lock); insert_to_mm_slots_hash(mm, mm_slot); /* - * Insert just behind the scanning cursor, to let the area settle + * When KSM_RUN_MERGE (or KSM_RUN_STOP), + * insert just behind the scanning cursor, to let the area settle * down a little; when fork is followed by immediate exec, we don't * want ksmd to waste time setting up and tearing down an rmap_list. + * + * But when KSM_RUN_UNMERGE, it's important to insert ahead of its + * scanning cursor, otherwise KSM pages in newly forked mms will be + * missed: then we might as well insert at the end of the list. */ - list_add_tail(&mm_slot->mm_list, &ksm_scan.mm_slot->mm_list); + if (ksm_run & KSM_RUN_UNMERGE) + list_add_tail(&mm_slot->mm_list, &ksm_mm_head.mm_list); + else + list_add_tail(&mm_slot->mm_list, &ksm_scan.mm_slot->mm_list); spin_unlock(&ksm_mmlist_lock); set_bit(MMF_VM_MERGEABLE, &mm->flags); @@ -1559,7 +1822,7 @@ void __ksm_exit(struct mm_struct *mm) mm_slot = get_mm_slot(mm); if (mm_slot && ksm_scan.mm_slot != mm_slot) { if (!mm_slot->rmap_list) { - hlist_del(&mm_slot->link); + hash_del(&mm_slot->link); list_del(&mm_slot->mm_list); easy_to_free = 1; } else { @@ -1579,24 +1842,32 @@ void __ksm_exit(struct mm_struct *mm) } } -struct page *ksm_does_need_to_copy(struct page *page, +struct page *ksm_might_need_to_copy(struct page *page, struct vm_area_struct *vma, unsigned long address) { + struct anon_vma *anon_vma = page_anon_vma(page); struct page *new_page; + if (PageKsm(page)) { + if (page_stable_node(page) && + !(ksm_run & KSM_RUN_UNMERGE)) + return page; /* no need to copy it */ + } else if (!anon_vma) { + return page; /* no need to copy it */ + } else if (anon_vma->root == vma->anon_vma->root && + page->index == linear_page_index(vma, address)) { + return page; /* still no need to copy it */ + } + if (!PageUptodate(page)) + return page; /* let do_swap_page report the error */ + new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); if (new_page) { copy_user_highpage(new_page, page, address, vma); SetPageDirty(new_page); __SetPageUptodate(new_page); - SetPageSwapBacked(new_page); __set_page_locked(new_page); - - if (!mlocked_vma_newpage(vma, new_page)) - lru_cache_add_lru(new_page, LRU_ACTIVE_ANON); - else - add_page_to_unevictable_list(new_page); } return new_page; @@ -1607,7 +1878,6 @@ int page_referenced_ksm(struct page *page, struct mem_cgroup *memcg, { struct stable_node *stable_node; struct rmap_item *rmap_item; - struct hlist_node *hlist; unsigned int mapcount = page_mapcount(page); int referenced = 0; int search_new_forks = 0; @@ -1619,7 +1889,7 @@ int page_referenced_ksm(struct page *page, struct mem_cgroup *memcg, if (!stable_node) return 0; again: - hlist_for_each_entry(rmap_item, hlist, &stable_node->hlist, hlist) { + hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) { struct anon_vma *anon_vma = rmap_item->anon_vma; struct anon_vma_chain *vmac; struct vm_area_struct *vma; @@ -1661,7 +1931,6 @@ out: int try_to_unmap_ksm(struct page *page, enum ttu_flags flags) { struct stable_node *stable_node; - struct hlist_node *hlist; struct rmap_item *rmap_item; int ret = SWAP_AGAIN; int search_new_forks = 0; @@ -1673,7 +1942,7 @@ int try_to_unmap_ksm(struct page *page, enum ttu_flags flags) if (!stable_node) return SWAP_FAIL; again: - hlist_for_each_entry(rmap_item, hlist, &stable_node->hlist, hlist) { + hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) { struct anon_vma *anon_vma = rmap_item->anon_vma; struct anon_vma_chain *vmac; struct vm_area_struct *vma; @@ -1714,7 +1983,6 @@ int rmap_walk_ksm(struct page *page, int (*rmap_one)(struct page *, struct vm_area_struct *, unsigned long, void *), void *arg) { struct stable_node *stable_node; - struct hlist_node *hlist; struct rmap_item *rmap_item; int ret = SWAP_AGAIN; int search_new_forks = 0; @@ -1726,7 +1994,7 @@ int rmap_walk_ksm(struct page *page, int (*rmap_one)(struct page *, if (!stable_node) return ret; again: - hlist_for_each_entry(rmap_item, hlist, &stable_node->hlist, hlist) { + hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) { struct anon_vma *anon_vma = rmap_item->anon_vma; struct anon_vma_chain *vmac; struct vm_area_struct *vma; @@ -1773,64 +2041,115 @@ void ksm_migrate_page(struct page *newpage, struct page *oldpage) if (stable_node) { VM_BUG_ON(stable_node->kpfn != page_to_pfn(oldpage)); stable_node->kpfn = page_to_pfn(newpage); + /* + * newpage->mapping was set in advance; now we need smp_wmb() + * to make sure that the new stable_node->kpfn is visible + * to get_ksm_page() before it can see that oldpage->mapping + * has gone stale (or that PageSwapCache has been cleared). + */ + smp_wmb(); + set_page_stable_node(oldpage, NULL); } } #endif /* CONFIG_MIGRATION */ #ifdef CONFIG_MEMORY_HOTREMOVE -static struct stable_node *ksm_check_stable_tree(unsigned long start_pfn, - unsigned long end_pfn) +static int just_wait(void *word) { - struct rb_node *node; + schedule(); + return 0; +} - for (node = rb_first(&root_stable_tree); node; node = rb_next(node)) { - struct stable_node *stable_node; +static void wait_while_offlining(void) +{ + while (ksm_run & KSM_RUN_OFFLINE) { + mutex_unlock(&ksm_thread_mutex); + wait_on_bit(&ksm_run, ilog2(KSM_RUN_OFFLINE), + just_wait, TASK_UNINTERRUPTIBLE); + mutex_lock(&ksm_thread_mutex); + } +} - stable_node = rb_entry(node, struct stable_node, node); +static void ksm_check_stable_tree(unsigned long start_pfn, + unsigned long end_pfn) +{ + struct stable_node *stable_node; + struct list_head *this, *next; + struct rb_node *node; + int nid; + + for (nid = 0; nid < nr_node_ids; nid++) { + node = rb_first(&root_stable_tree[nid]); + while (node) { + stable_node = rb_entry(node, struct stable_node, node); + if (stable_node->kpfn >= start_pfn && + stable_node->kpfn < end_pfn) { + /* + * Don't get_ksm_page, page has already gone: + * which is why we keep kpfn instead of page* + */ + remove_node_from_stable_tree(stable_node); + node = rb_first(&root_stable_tree[nid]); + } else + node = rb_next(node); + cond_resched(); + } + } + list_for_each_safe(this, next, &migrate_nodes) { + stable_node = list_entry(this, struct stable_node, list); if (stable_node->kpfn >= start_pfn && stable_node->kpfn < end_pfn) - return stable_node; + remove_node_from_stable_tree(stable_node); + cond_resched(); } - return NULL; } static int ksm_memory_callback(struct notifier_block *self, unsigned long action, void *arg) { struct memory_notify *mn = arg; - struct stable_node *stable_node; switch (action) { case MEM_GOING_OFFLINE: /* - * Keep it very simple for now: just lock out ksmd and - * MADV_UNMERGEABLE while any memory is going offline. - * mutex_lock_nested() is necessary because lockdep was alarmed - * that here we take ksm_thread_mutex inside notifier chain - * mutex, and later take notifier chain mutex inside - * ksm_thread_mutex to unlock it. But that's safe because both - * are inside mem_hotplug_mutex. + * Prevent ksm_do_scan(), unmerge_and_remove_all_rmap_items() + * and remove_all_stable_nodes() while memory is going offline: + * it is unsafe for them to touch the stable tree at this time. + * But unmerge_ksm_pages(), rmap lookups and other entry points + * which do not need the ksm_thread_mutex are all safe. */ - mutex_lock_nested(&ksm_thread_mutex, SINGLE_DEPTH_NESTING); + mutex_lock(&ksm_thread_mutex); + ksm_run |= KSM_RUN_OFFLINE; + mutex_unlock(&ksm_thread_mutex); break; case MEM_OFFLINE: /* * Most of the work is done by page migration; but there might * be a few stable_nodes left over, still pointing to struct - * pages which have been offlined: prune those from the tree. + * pages which have been offlined: prune those from the tree, + * otherwise get_ksm_page() might later try to access a + * non-existent struct page. */ - while ((stable_node = ksm_check_stable_tree(mn->start_pfn, - mn->start_pfn + mn->nr_pages)) != NULL) - remove_node_from_stable_tree(stable_node); + ksm_check_stable_tree(mn->start_pfn, + mn->start_pfn + mn->nr_pages); /* fallthrough */ case MEM_CANCEL_OFFLINE: + mutex_lock(&ksm_thread_mutex); + ksm_run &= ~KSM_RUN_OFFLINE; mutex_unlock(&ksm_thread_mutex); + + smp_mb(); /* wake_up_bit advises this */ + wake_up_bit(&ksm_run, ilog2(KSM_RUN_OFFLINE)); break; } return NOTIFY_OK; } +#else +static void wait_while_offlining(void) +{ +} #endif /* CONFIG_MEMORY_HOTREMOVE */ #ifdef CONFIG_SYSFS @@ -1893,7 +2212,7 @@ KSM_ATTR(pages_to_scan); static ssize_t run_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%u\n", ksm_run); + return sprintf(buf, "%lu\n", ksm_run); } static ssize_t run_store(struct kobject *kobj, struct kobj_attribute *attr, @@ -1916,6 +2235,7 @@ static ssize_t run_store(struct kobject *kobj, struct kobj_attribute *attr, */ mutex_lock(&ksm_thread_mutex); + wait_while_offlining(); if (ksm_run != flags) { ksm_run = flags; if (flags & KSM_RUN_UNMERGE) { @@ -1937,6 +2257,41 @@ static ssize_t run_store(struct kobject *kobj, struct kobj_attribute *attr, } KSM_ATTR(run); +#ifdef CONFIG_NUMA +static ssize_t merge_across_nodes_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%u\n", ksm_merge_across_nodes); +} + +static ssize_t merge_across_nodes_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int err; + unsigned long knob; + + err = kstrtoul(buf, 10, &knob); + if (err) + return err; + if (knob > 1) + return -EINVAL; + + mutex_lock(&ksm_thread_mutex); + wait_while_offlining(); + if (ksm_merge_across_nodes != knob) { + if (ksm_pages_shared || remove_all_stable_nodes()) + err = -EBUSY; + else + ksm_merge_across_nodes = knob; + } + mutex_unlock(&ksm_thread_mutex); + + return err ? err : count; +} +KSM_ATTR(merge_across_nodes); +#endif + static ssize_t pages_shared_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { @@ -1991,6 +2346,9 @@ static struct attribute *ksm_attrs[] = { &pages_unshared_attr.attr, &pages_volatile_attr.attr, &full_scans_attr.attr, +#ifdef CONFIG_NUMA + &merge_across_nodes_attr.attr, +#endif NULL, }; @@ -2004,11 +2362,15 @@ static int __init ksm_init(void) { struct task_struct *ksm_thread; int err; + int nid; err = ksm_slab_init(); if (err) goto out; + for (nid = 0; nid < nr_node_ids; nid++) + root_stable_tree[nid] = RB_ROOT; + ksm_thread = kthread_run(ksm_scan_thread, NULL, "ksmd"); if (IS_ERR(ksm_thread)) { printk(KERN_ERR "ksm: creating kthread failed\n"); @@ -2029,10 +2391,7 @@ static int __init ksm_init(void) #endif /* CONFIG_SYSFS */ #ifdef CONFIG_MEMORY_HOTREMOVE - /* - * Choose a high priority since the callback takes ksm_thread_mutex: - * later callbacks could only be taking locks which nest within that. - */ + /* There is no significance to this priority 100 */ hotplug_memory_notifier(ksm_memory_callback, 100); #endif return 0; diff --git a/mm/madvise.c b/mm/madvise.c index 03dfa5c7adb3..c58c94b56c3d 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -16,6 +16,9 @@ #include <linux/ksm.h> #include <linux/fs.h> #include <linux/file.h> +#include <linux/blkdev.h> +#include <linux/swap.h> +#include <linux/swapops.h> /* * Any behaviour which results in changes to the vma->vm_flags needs to @@ -131,6 +134,84 @@ out: return error; } +#ifdef CONFIG_SWAP +static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start, + unsigned long end, struct mm_walk *walk) +{ + pte_t *orig_pte; + struct vm_area_struct *vma = walk->private; + unsigned long index; + + if (pmd_none_or_trans_huge_or_clear_bad(pmd)) + return 0; + + for (index = start; index != end; index += PAGE_SIZE) { + pte_t pte; + swp_entry_t entry; + struct page *page; + spinlock_t *ptl; + + orig_pte = pte_offset_map_lock(vma->vm_mm, pmd, start, &ptl); + pte = *(orig_pte + ((index - start) / PAGE_SIZE)); + pte_unmap_unlock(orig_pte, ptl); + + if (pte_present(pte) || pte_none(pte) || pte_file(pte)) + continue; + entry = pte_to_swp_entry(pte); + if (unlikely(non_swap_entry(entry))) + continue; + + page = read_swap_cache_async(entry, GFP_HIGHUSER_MOVABLE, + vma, index); + if (page) + page_cache_release(page); + } + + return 0; +} + +static void force_swapin_readahead(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + struct mm_walk walk = { + .mm = vma->vm_mm, + .pmd_entry = swapin_walk_pmd_entry, + .private = vma, + }; + + walk_page_range(start, end, &walk); + + lru_add_drain(); /* Push any new pages onto the LRU now */ +} + +static void force_shm_swapin_readahead(struct vm_area_struct *vma, + unsigned long start, unsigned long end, + struct address_space *mapping) +{ + pgoff_t index; + struct page *page; + swp_entry_t swap; + + for (; start < end; start += PAGE_SIZE) { + index = ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; + + page = find_get_page(mapping, index); + if (!radix_tree_exceptional_entry(page)) { + if (page) + page_cache_release(page); + continue; + } + swap = radix_to_swp_entry(page); + page = read_swap_cache_async(swap, GFP_HIGHUSER_MOVABLE, + NULL, 0); + if (page) + page_cache_release(page); + } + + lru_add_drain(); /* Push any new pages onto the LRU now */ +} +#endif /* CONFIG_SWAP */ + /* * Schedule all required I/O operations. Do not wait for completion. */ @@ -140,6 +221,18 @@ static long madvise_willneed(struct vm_area_struct * vma, { struct file *file = vma->vm_file; +#ifdef CONFIG_SWAP + if (!file || mapping_cap_swap_backed(file->f_mapping)) { + *prev = vma; + if (!file) + force_swapin_readahead(vma, start, end); + else + force_shm_swapin_readahead(vma, start, end, + file->f_mapping); + return 0; + } +#endif + if (!file) return -EBADF; @@ -371,6 +464,7 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) int error = -EINVAL; int write; size_t len; + struct blk_plug plug; #ifdef CONFIG_MEMORY_FAILURE if (behavior == MADV_HWPOISON || behavior == MADV_SOFT_OFFLINE) @@ -410,18 +504,19 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) if (vma && start > vma->vm_start) prev = vma; + blk_start_plug(&plug); for (;;) { /* Still start < end. */ error = -ENOMEM; if (!vma) - goto out; + goto out_plug; /* Here start < (end|vma->vm_end). */ if (start < vma->vm_start) { unmapped_error = -ENOMEM; start = vma->vm_start; if (start >= end) - goto out; + goto out_plug; } /* Here vma->vm_start <= start < (end|vma->vm_end) */ @@ -432,18 +527,20 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) /* Here vma->vm_start <= start < tmp <= (end|vma->vm_end). */ error = madvise_vma(vma, &prev, start, tmp, behavior); if (error) - goto out; + goto out_plug; start = tmp; if (prev && start < prev->vm_end) start = prev->vm_end; error = unmapped_error; if (start >= end) - goto out; + goto out_plug; if (prev) vma = prev->vm_next; else /* madvise_remove dropped mmap_sem */ vma = find_vma(current->mm, start); } +out_plug: + blk_finish_plug(&plug); out: if (write) up_write(¤t->mm->mmap_sem); diff --git a/mm/memblock.c b/mm/memblock.c index b8d9147e5c08..1bcd9b970564 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -92,9 +92,58 @@ static long __init_memblock memblock_overlaps_region(struct memblock_type *type, * * Find @size free area aligned to @align in the specified range and node. * + * If we have CONFIG_HAVE_MEMBLOCK_NODE_MAP defined, we need to check if the + * memory we found if not in hotpluggable ranges. + * * RETURNS: * Found address on success, %0 on failure. */ +#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP +phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t start, + phys_addr_t end, phys_addr_t size, + phys_addr_t align, int nid) +{ + phys_addr_t this_start, this_end, cand; + u64 i; + int curr = movablemem_map.nr_map - 1; + + /* pump up @end */ + if (end == MEMBLOCK_ALLOC_ACCESSIBLE) + end = memblock.current_limit; + + /* avoid allocating the first page */ + start = max_t(phys_addr_t, start, PAGE_SIZE); + end = max(start, end); + + for_each_free_mem_range_reverse(i, nid, &this_start, &this_end, NULL) { + this_start = clamp(this_start, start, end); + this_end = clamp(this_end, start, end); + +restart: + if (this_end <= this_start || this_end < size) + continue; + + for (; curr >= 0; curr--) { + if ((movablemem_map.map[curr].start_pfn << PAGE_SHIFT) + < this_end) + break; + } + + cand = round_down(this_end - size, align); + if (curr >= 0 && + cand < movablemem_map.map[curr].end_pfn << PAGE_SHIFT) { + this_end = movablemem_map.map[curr].start_pfn + << PAGE_SHIFT; + goto restart; + } + + if (cand >= this_start) + return cand; + } + + return 0; +} +#else /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align, int nid) @@ -123,6 +172,7 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t start, } return 0; } +#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ /** * memblock_find_in_range - find free area in given range diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 09255ec8159c..25ac5f4abe33 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -120,6 +120,14 @@ static const char * const mem_cgroup_events_names[] = { "pgmajfault", }; +static const char * const mem_cgroup_lru_names[] = { + "inactive_anon", + "active_anon", + "inactive_file", + "active_file", + "unevictable", +}; + /* * Per memcg event counter is incremented at every pagein/pageout. With THP, * it will be incremated by the number of pages. This counter is used for @@ -172,7 +180,7 @@ struct mem_cgroup_per_node { }; struct mem_cgroup_lru_info { - struct mem_cgroup_per_node *nodeinfo[MAX_NUMNODES]; + struct mem_cgroup_per_node *nodeinfo[0]; }; /* @@ -276,17 +284,6 @@ struct mem_cgroup { */ struct res_counter kmem; /* - * Per cgroup active and inactive list, similar to the - * per zone LRU lists. - */ - struct mem_cgroup_lru_info info; - int last_scanned_node; -#if MAX_NUMNODES > 1 - nodemask_t scan_nodes; - atomic_t numainfo_events; - atomic_t numainfo_updating; -#endif - /* * Should the accounting and control be hierarchical, per subtree? */ bool use_hierarchy; @@ -313,14 +310,31 @@ struct mem_cgroup { /* thresholds for mem+swap usage. RCU-protected */ struct mem_cgroup_thresholds memsw_thresholds; - /* For oom notifier event fd */ - struct list_head oom_notify; + union { + /* For oom notifier event fd */ + struct list_head oom_notify; + /* + * we can only trigger an oom event if the memcg is alive. + * so we will reuse this field to hook the memcg in the list + * of dead memcgs. + */ + struct list_head dead; + }; + + union { + /* + * Should we move charges of a task when a task is moved into + * this mem_cgroup ? And what type of charges should we move ? + */ + unsigned long move_charge_at_immigrate; - /* - * Should we move charges of a task when a task is moved into this - * mem_cgroup ? And what type of charges should we move ? - */ - unsigned long move_charge_at_immigrate; + /* + * We are no longer concerned about moving charges after memcg + * is dead. So we will fill this up with its name, to aid + * debugging. + */ + char *memcg_name; + }; /* * set > 0 if pages under this cgroup are moving to other cgroup. */ @@ -349,8 +363,78 @@ struct mem_cgroup { /* Index in the kmem_cache->memcg_params->memcg_caches array */ int kmemcg_id; #endif + + int last_scanned_node; +#if MAX_NUMNODES > 1 + nodemask_t scan_nodes; + atomic_t numainfo_events; + atomic_t numainfo_updating; +#endif + /* + * Per cgroup active and inactive list, similar to the + * per zone LRU lists. + * + * WARNING: This has to be the last element of the struct. Don't + * add new fields after this point. + */ + struct mem_cgroup_lru_info info; }; +static size_t memcg_size(void) +{ + return sizeof(struct mem_cgroup) + + nr_node_ids * sizeof(struct mem_cgroup_per_node); +} + +#ifdef CONFIG_MEMCG_DEBUG_ASYNC_DESTROY +static LIST_HEAD(dangling_memcgs); +static DEFINE_MUTEX(dangling_memcgs_mutex); + +static inline void memcg_dangling_free(struct mem_cgroup *memcg) +{ + mutex_lock(&dangling_memcgs_mutex); + list_del(&memcg->dead); + mutex_unlock(&dangling_memcgs_mutex); + free_pages((unsigned long)memcg->memcg_name, 0); +} + +static inline void memcg_dangling_add(struct mem_cgroup *memcg) +{ + /* + * cgroup.c will do page-sized allocations most of the time, + * so we'll just follow the pattern. Also, __get_free_pages + * is a better interface than kmalloc for us here, because + * we'd like this memory to be always billed to the root cgroup, + * not to the process removing the memcg. While kmalloc would + * require us to wrap it into memcg_stop/resume_kmem_account, + * with __get_free_pages we just don't pass the memcg flag. + */ + memcg->memcg_name = (char *)__get_free_pages(GFP_KERNEL, 0); + + /* + * we will, in general, just ignore failures. No need to go crazy, + * being this just a debugging interface. It is nice to copy a memcg + * name over, but if we (unlikely) can't, just the address will do + */ + if (!memcg->memcg_name) + goto add_list; + + if (cgroup_path(memcg->css.cgroup, memcg->memcg_name, PAGE_SIZE) < 0) { + free_pages((unsigned long)memcg->memcg_name, 0); + memcg->memcg_name = NULL; + } + +add_list: + INIT_LIST_HEAD(&memcg->dead); + mutex_lock(&dangling_memcgs_mutex); + list_add(&memcg->dead, &dangling_memcgs); + mutex_unlock(&dangling_memcgs_mutex); +} +#else +static inline void memcg_dangling_free(struct mem_cgroup *memcg) {} +static inline void memcg_dangling_add(struct mem_cgroup *memcg) {} +#endif + /* internal only representation about the status of kmem accounting. */ enum { KMEM_ACCOUNTED_ACTIVE = 0, /* accounted by this cgroup itself */ @@ -398,8 +482,8 @@ static bool memcg_kmem_test_and_clear_dead(struct mem_cgroup *memcg) /* Stuffs for move charges at task migration. */ /* - * Types of charges to be moved. "move_charge_at_immitgrate" is treated as a - * left-shifted bitmap of these types. + * Types of charges to be moved. "move_charge_at_immitgrate" and + * "immigrate_flags" are treated as a left-shifted bitmap of these types. */ enum move_type { MOVE_CHARGE_TYPE_ANON, /* private anonymous page and swap of it */ @@ -412,6 +496,7 @@ static struct move_charge_struct { spinlock_t lock; /* for from, to */ struct mem_cgroup *from; struct mem_cgroup *to; + unsigned long immigrate_flags; unsigned long precharge; unsigned long moved_charge; unsigned long moved_swap; @@ -424,14 +509,12 @@ static struct move_charge_struct { static bool move_anon(void) { - return test_bit(MOVE_CHARGE_TYPE_ANON, - &mc.to->move_charge_at_immigrate); + return test_bit(MOVE_CHARGE_TYPE_ANON, &mc.immigrate_flags); } static bool move_file(void) { - return test_bit(MOVE_CHARGE_TYPE_FILE, - &mc.to->move_charge_at_immigrate); + return test_bit(MOVE_CHARGE_TYPE_FILE, &mc.immigrate_flags); } /* @@ -471,6 +554,13 @@ enum res_type { #define MEM_CGROUP_RECLAIM_SHRINK_BIT 0x1 #define MEM_CGROUP_RECLAIM_SHRINK (1 << MEM_CGROUP_RECLAIM_SHRINK_BIT) +/* + * The memcg_create_mutex will be held whenever a new cgroup is created. + * As a consequence, any change that needs to protect against new child cgroups + * appearing has to hold it as well. + */ +static DEFINE_MUTEX(memcg_create_mutex); + static void mem_cgroup_get(struct mem_cgroup *memcg); static void mem_cgroup_put(struct mem_cgroup *memcg); @@ -627,6 +717,7 @@ static void drain_all_stock_async(struct mem_cgroup *memcg); static struct mem_cgroup_per_zone * mem_cgroup_zoneinfo(struct mem_cgroup *memcg, int nid, int zid) { + VM_BUG_ON((unsigned)nid >= nr_node_ids); return &memcg->info.nodeinfo[nid]->zoneinfo[zid]; } @@ -1371,17 +1462,6 @@ int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec) return inactive * inactive_ratio < active; } -int mem_cgroup_inactive_file_is_low(struct lruvec *lruvec) -{ - unsigned long active; - unsigned long inactive; - - inactive = mem_cgroup_get_lru_size(lruvec, LRU_INACTIVE_FILE); - active = mem_cgroup_get_lru_size(lruvec, LRU_ACTIVE_FILE); - - return (active > inactive); -} - #define mem_cgroup_from_res_counter(counter, member) \ container_of(counter, struct mem_cgroup, member) @@ -1524,8 +1604,9 @@ static void move_unlock_mem_cgroup(struct mem_cgroup *memcg, spin_unlock_irqrestore(&memcg->move_lock, *flags); } +#define K(x) ((x) << (PAGE_SHIFT-10)) /** - * mem_cgroup_print_oom_info: Called from OOM with tasklist_lock held in read mode. + * mem_cgroup_print_oom_info: Print OOM information relevant to memory controller. * @memcg: The memory cgroup that went over limit * @p: Task that is going to be killed * @@ -1543,8 +1624,10 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) */ static char memcg_name[PATH_MAX]; int ret; + struct mem_cgroup *iter; + unsigned int i; - if (!memcg || !p) + if (!p) return; rcu_read_lock(); @@ -1563,7 +1646,7 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) } rcu_read_unlock(); - printk(KERN_INFO "Task in %s killed", memcg_name); + pr_info("Task in %s killed", memcg_name); rcu_read_lock(); ret = cgroup_path(mem_cgrp, memcg_name, PATH_MAX); @@ -1576,22 +1659,45 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) /* * Continues from above, so we don't need an KERN_ level */ - printk(KERN_CONT " as a result of limit of %s\n", memcg_name); + pr_cont(" as a result of limit of %s\n", memcg_name); done: - printk(KERN_INFO "memory: usage %llukB, limit %llukB, failcnt %llu\n", + pr_info("memory: usage %llukB, limit %llukB, failcnt %llu\n", res_counter_read_u64(&memcg->res, RES_USAGE) >> 10, res_counter_read_u64(&memcg->res, RES_LIMIT) >> 10, res_counter_read_u64(&memcg->res, RES_FAILCNT)); - printk(KERN_INFO "memory+swap: usage %llukB, limit %llukB, " - "failcnt %llu\n", + pr_info("memory+swap: usage %llukB, limit %llukB, failcnt %llu\n", res_counter_read_u64(&memcg->memsw, RES_USAGE) >> 10, res_counter_read_u64(&memcg->memsw, RES_LIMIT) >> 10, res_counter_read_u64(&memcg->memsw, RES_FAILCNT)); - printk(KERN_INFO "kmem: usage %llukB, limit %llukB, failcnt %llu\n", + pr_info("kmem: usage %llukB, limit %llukB, failcnt %llu\n", res_counter_read_u64(&memcg->kmem, RES_USAGE) >> 10, res_counter_read_u64(&memcg->kmem, RES_LIMIT) >> 10, res_counter_read_u64(&memcg->kmem, RES_FAILCNT)); + + for_each_mem_cgroup_tree(iter, memcg) { + pr_info("Memory cgroup stats"); + + rcu_read_lock(); + ret = cgroup_path(iter->css.cgroup, memcg_name, PATH_MAX); + if (!ret) + pr_cont(" for %s", memcg_name); + rcu_read_unlock(); + pr_cont(":"); + + for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) { + if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account) + continue; + pr_cont(" %s:%ldKB", mem_cgroup_stat_names[i], + K(mem_cgroup_read_stat(iter, i))); + } + + for (i = 0; i < NR_LRU_LISTS; i++) + pr_cont(" %s:%luKB", mem_cgroup_lru_names[i], + K(mem_cgroup_nr_lru_pages(iter, BIT(i)))); + + pr_cont("\n"); + } } /* @@ -2256,6 +2362,17 @@ static void drain_local_stock(struct work_struct *dummy) clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags); } +static void __init memcg_stock_init(void) +{ + int cpu; + + for_each_possible_cpu(cpu) { + struct memcg_stock_pcp *stock = + &per_cpu(memcg_stock, cpu); + INIT_WORK(&stock->work, drain_local_stock); + } +} + /* * Cache charges(val) which is from res_counter, to local per_cpu area. * This will be consumed by consume_stock() function, later. @@ -4389,8 +4506,8 @@ void mem_cgroup_print_bad_page(struct page *page) pc = lookup_page_cgroup_used(page); if (pc) { - printk(KERN_ALERT "pc:%p pc->flags:%lx pc->mem_cgroup:%p\n", - pc, pc->flags, pc->mem_cgroup); + pr_alert("pc:%p pc->flags:%lx pc->mem_cgroup:%p\n", + pc, pc->flags, pc->mem_cgroup); } } #endif @@ -4717,6 +4834,33 @@ static void mem_cgroup_reparent_charges(struct mem_cgroup *memcg) } /* + * This mainly exists for tests during the setting of set of use_hierarchy. + * Since this is the very setting we are changing, the current hierarchy value + * is meaningless + */ +static inline bool __memcg_has_children(struct mem_cgroup *memcg) +{ + struct cgroup *pos; + + /* bounce at first found */ + cgroup_for_each_child(pos, memcg->css.cgroup) + return true; + return false; +} + +/* + * Must be called with memcg_create_mutex held, unless the cgroup is guaranteed + * to be already dead (as in mem_cgroup_force_empty, for instance). This is + * from mem_cgroup_count_children(), in the sense that we don't really care how + * many children we have; we only need to know if we have any. It also counts + * any memcg without hierarchy as infertile. + */ +static inline bool memcg_has_children(struct mem_cgroup *memcg) +{ + return memcg->use_hierarchy && __memcg_has_children(memcg); +} + +/* * Reclaims as many pages from the given memcg as possible and moves * the rest to the parent. * @@ -4786,7 +4930,7 @@ static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft, if (parent) parent_memcg = mem_cgroup_from_cont(parent); - cgroup_lock(); + mutex_lock(&memcg_create_mutex); if (memcg->use_hierarchy == val) goto out; @@ -4801,7 +4945,7 @@ static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft, */ if ((!parent_memcg || !parent_memcg->use_hierarchy) && (val == 1 || val == 0)) { - if (list_empty(&cont->children)) + if (!__memcg_has_children(memcg)) memcg->use_hierarchy = val; else retval = -EBUSY; @@ -4809,7 +4953,7 @@ static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft, retval = -EINVAL; out: - cgroup_unlock(); + mutex_unlock(&memcg_create_mutex); return retval; } @@ -4890,12 +5034,111 @@ static ssize_t mem_cgroup_read(struct cgroup *cont, struct cftype *cft, return simple_read_from_buffer(buf, nbytes, ppos, str, len); } +#ifdef CONFIG_MEMCG_DEBUG_ASYNC_DESTROY +static void +mem_cgroup_dangling_swap(struct mem_cgroup *memcg, struct seq_file *m) +{ +#ifdef CONFIG_MEMCG_SWAP + u64 kmem; + u64 memsw; + + /* + * kmem will also propagate here, so we are only interested in the + * difference. See comment in mem_cgroup_reparent_charges for details. + * + * We could save this value for later consumption by kmem reports, but + * there is not a lot of problem if the figures differ slightly. + */ + kmem = res_counter_read_u64(&memcg->kmem, RES_USAGE); + memsw = res_counter_read_u64(&memcg->memsw, RES_USAGE) - kmem; + seq_printf(m, "\t%llu swap bytes\n", memsw); +#endif +} + + +static void +mem_cgroup_dangling_tcp(struct mem_cgroup *memcg, struct seq_file *m) +{ +#if defined(CONFIG_INET) && defined(CONFIG_MEMCG_KMEM) + struct tcp_memcontrol *tcp = &memcg->tcp_mem; + s64 tcp_socks; + u64 tcp_bytes; + + tcp_socks = percpu_counter_sum_positive(&tcp->tcp_sockets_allocated); + tcp_bytes = res_counter_read_u64(&tcp->tcp_memory_allocated, RES_USAGE); + seq_printf(m, "\t%llu tcp bytes", tcp_bytes); + /* + * if tcp_bytes == 0, tcp_socks != 0 is a bug. One more reason to print + * it! + */ + if (tcp_bytes || tcp_socks) + seq_printf(m, ", in %lld sockets", tcp_socks); + seq_printf(m, "\n"); + +#endif +} + +static void +mem_cgroup_dangling_kmem(struct mem_cgroup *memcg, struct seq_file *m) +{ +#ifdef CONFIG_MEMCG_KMEM + u64 kmem; + struct memcg_cache_params *params; + + kmem = res_counter_read_u64(&memcg->kmem, RES_USAGE); + seq_printf(m, "\t%llu kmem bytes", kmem); + + /* list below may not be initialized, so not even try */ + if (!kmem) + return; + + seq_printf(m, " in caches"); + mutex_lock(&memcg->slab_caches_mutex); + list_for_each_entry(params, &memcg->memcg_slab_caches, list) { + struct kmem_cache *s = memcg_params_to_cache(params); + + seq_printf(m, " %s", s->name); + } + mutex_unlock(&memcg->slab_caches_mutex); + seq_printf(m, "\n"); +#endif +} + +/* + * After a memcg is destroyed, it may still be kept around in memory. + * Currently, the two main reasons for it are swap entries, and kernel memory. + * Because they will be freed assynchronously, they will pin the memcg structure + * and its resources until the last reference goes away. + * + * This root-only file will show information about which users + */ +static int mem_cgroup_dangling_read(struct cgroup *cont, struct cftype *cft, + struct seq_file *m) +{ + struct mem_cgroup *memcg; + + mutex_lock(&dangling_memcgs_mutex); + + list_for_each_entry(memcg, &dangling_memcgs, dead) { + if (memcg->memcg_name) + seq_printf(m, "%s:\n", memcg->memcg_name); + else + seq_printf(m, "%p (name lost):\n", memcg); + + mem_cgroup_dangling_swap(memcg, m); + mem_cgroup_dangling_tcp(memcg, m); + mem_cgroup_dangling_kmem(memcg, m); + } + + mutex_unlock(&dangling_memcgs_mutex); + return 0; +} +#endif + static int memcg_update_kmem_limit(struct cgroup *cont, u64 val) { int ret = -EINVAL; #ifdef CONFIG_MEMCG_KMEM - bool must_inc_static_branch = false; - struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); /* * For simplicity, we won't allow this to be disabled. It also can't @@ -4908,18 +5151,11 @@ static int memcg_update_kmem_limit(struct cgroup *cont, u64 val) * * After it first became limited, changes in the value of the limit are * of course permitted. - * - * Taking the cgroup_lock is really offensive, but it is so far the only - * way to guarantee that no children will appear. There are plenty of - * other offenders, and they should all go away. Fine grained locking - * is probably the way to go here. When we are fully hierarchical, we - * can also get rid of the use_hierarchy check. */ - cgroup_lock(); + mutex_lock(&memcg_create_mutex); mutex_lock(&set_limit_mutex); if (!memcg->kmem_account_flags && val != RESOURCE_MAX) { - if (cgroup_task_count(cont) || (memcg->use_hierarchy && - !list_empty(&cont->children))) { + if (cgroup_task_count(cont) || memcg_has_children(memcg)) { ret = -EBUSY; goto out; } @@ -4931,7 +5167,13 @@ static int memcg_update_kmem_limit(struct cgroup *cont, u64 val) res_counter_set_limit(&memcg->kmem, RESOURCE_MAX); goto out; } - must_inc_static_branch = true; + static_key_slow_inc(&memcg_kmem_enabled_key); + /* + * setting the active bit after the inc will guarantee no one + * starts accounting before all call sites are patched + */ + memcg_kmem_set_active(memcg); + /* * kmem charges can outlive the cgroup. In the case of slab * pages, for instance, a page contain objects from various @@ -4943,28 +5185,7 @@ static int memcg_update_kmem_limit(struct cgroup *cont, u64 val) ret = res_counter_set_limit(&memcg->kmem, val); out: mutex_unlock(&set_limit_mutex); - cgroup_unlock(); - - /* - * We are by now familiar with the fact that we can't inc the static - * branch inside cgroup_lock. See disarm functions for details. A - * worker here is overkill, but also wrong: After the limit is set, we - * must start accounting right away. Since this operation can't fail, - * we can safely defer it to here - no rollback will be needed. - * - * The boolean used to control this is also safe, because - * KMEM_ACCOUNTED_ACTIVATED guarantees that only one process will be - * able to set it to true; - */ - if (must_inc_static_branch) { - static_key_slow_inc(&memcg_kmem_enabled_key); - /* - * setting the active bit after the inc will guarantee no one - * starts accounting before all call sites are patched - */ - memcg_kmem_set_active(memcg); - } - + mutex_unlock(&memcg_create_mutex); #endif return ret; } @@ -5146,15 +5367,14 @@ static int mem_cgroup_move_charge_write(struct cgroup *cgrp, if (val >= (1 << NR_MOVE_TYPE)) return -EINVAL; + /* - * We check this value several times in both in can_attach() and - * attach(), so we need cgroup lock to prevent this value from being - * inconsistent. + * No kind of locking is needed in here, because ->can_attach() will + * check this value once in the beginning of the process, and then carry + * on with stale data. This means that changes to this value will only + * affect task migrations starting after the change. */ - cgroup_lock(); memcg->move_charge_at_immigrate = val; - cgroup_unlock(); - return 0; } #else @@ -5212,14 +5432,6 @@ static int memcg_numa_stat_show(struct cgroup *cont, struct cftype *cft, } #endif /* CONFIG_NUMA */ -static const char * const mem_cgroup_lru_names[] = { - "inactive_anon", - "active_anon", - "inactive_file", - "active_file", - "unevictable", -}; - static inline void mem_cgroup_lru_names_not_uptodate(void) { BUILD_BUG_ON(ARRAY_SIZE(mem_cgroup_lru_names) != NR_LRU_LISTS); @@ -5333,18 +5545,17 @@ static int mem_cgroup_swappiness_write(struct cgroup *cgrp, struct cftype *cft, parent = mem_cgroup_from_cont(cgrp->parent); - cgroup_lock(); + mutex_lock(&memcg_create_mutex); /* If under hierarchy, only empty-root can set this value */ - if ((parent->use_hierarchy) || - (memcg->use_hierarchy && !list_empty(&cgrp->children))) { - cgroup_unlock(); + if ((parent->use_hierarchy) || memcg_has_children(memcg)) { + mutex_unlock(&memcg_create_mutex); return -EINVAL; } memcg->swappiness = val; - cgroup_unlock(); + mutex_unlock(&memcg_create_mutex); return 0; } @@ -5670,7 +5881,7 @@ static int mem_cgroup_oom_control_write(struct cgroup *cgrp, parent = mem_cgroup_from_cont(cgrp->parent); - cgroup_lock(); + mutex_lock(&memcg_create_mutex); /* oom-kill-disable is a flag for subhierarchy. */ if ((parent->use_hierarchy) || (memcg->use_hierarchy && !list_empty(&cgrp->children))) { @@ -5680,7 +5891,7 @@ static int mem_cgroup_oom_control_write(struct cgroup *cgrp, memcg->oom_kill_disable = val; if (!val) memcg_oom_recover(memcg); - cgroup_unlock(); + mutex_unlock(&memcg_create_mutex); return 0; } @@ -5795,33 +6006,6 @@ static struct cftype mem_cgroup_files[] = { .read_seq_string = memcg_numa_stat_show, }, #endif -#ifdef CONFIG_MEMCG_SWAP - { - .name = "memsw.usage_in_bytes", - .private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE), - .read = mem_cgroup_read, - .register_event = mem_cgroup_usage_register_event, - .unregister_event = mem_cgroup_usage_unregister_event, - }, - { - .name = "memsw.max_usage_in_bytes", - .private = MEMFILE_PRIVATE(_MEMSWAP, RES_MAX_USAGE), - .trigger = mem_cgroup_reset, - .read = mem_cgroup_read, - }, - { - .name = "memsw.limit_in_bytes", - .private = MEMFILE_PRIVATE(_MEMSWAP, RES_LIMIT), - .write_string = mem_cgroup_write, - .read = mem_cgroup_read, - }, - { - .name = "memsw.failcnt", - .private = MEMFILE_PRIVATE(_MEMSWAP, RES_FAILCNT), - .trigger = mem_cgroup_reset, - .read = mem_cgroup_read, - }, -#endif #ifdef CONFIG_MEMCG_KMEM { .name = "kmem.limit_in_bytes", @@ -5853,9 +6037,47 @@ static struct cftype mem_cgroup_files[] = { }, #endif #endif + +#ifdef CONFIG_MEMCG_DEBUG_ASYNC_DESTROY + { + .name = "dangling_memcgs", + .read_seq_string = mem_cgroup_dangling_read, + .flags = CFTYPE_ONLY_ON_ROOT, + }, +#endif { }, /* terminate */ }; +#ifdef CONFIG_MEMCG_SWAP +static struct cftype memsw_cgroup_files[] = { + { + .name = "memsw.usage_in_bytes", + .private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE), + .read = mem_cgroup_read, + .register_event = mem_cgroup_usage_register_event, + .unregister_event = mem_cgroup_usage_unregister_event, + }, + { + .name = "memsw.max_usage_in_bytes", + .private = MEMFILE_PRIVATE(_MEMSWAP, RES_MAX_USAGE), + .trigger = mem_cgroup_reset, + .read = mem_cgroup_read, + }, + { + .name = "memsw.limit_in_bytes", + .private = MEMFILE_PRIVATE(_MEMSWAP, RES_LIMIT), + .write_string = mem_cgroup_write, + .read = mem_cgroup_read, + }, + { + .name = "memsw.failcnt", + .private = MEMFILE_PRIVATE(_MEMSWAP, RES_FAILCNT), + .trigger = mem_cgroup_reset, + .read = mem_cgroup_read, + }, + { }, /* terminate */ +}; +#endif static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node) { struct mem_cgroup_per_node *pn; @@ -5894,9 +6116,9 @@ static void free_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node) static struct mem_cgroup *mem_cgroup_alloc(void) { struct mem_cgroup *memcg; - int size = sizeof(struct mem_cgroup); + size_t size = memcg_size(); - /* Can be very big if MAX_NUMNODES is very big */ + /* Can be very big if nr_node_ids is very big */ if (size < PAGE_SIZE) memcg = kzalloc(size, GFP_KERNEL); else @@ -5933,7 +6155,7 @@ out_free: static void __mem_cgroup_free(struct mem_cgroup *memcg) { int node; - int size = sizeof(struct mem_cgroup); + size_t size = memcg_size(); mem_cgroup_remove_from_trees(memcg); free_css_id(&mem_cgroup_subsys, &memcg->css); @@ -5972,6 +6194,8 @@ static void free_work(struct work_struct *work) struct mem_cgroup *memcg; memcg = container_of(work, struct mem_cgroup, work_freeing); + + memcg_dangling_free(memcg); __mem_cgroup_free(memcg); } @@ -6015,19 +6239,7 @@ struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) } EXPORT_SYMBOL(parent_mem_cgroup); -#ifdef CONFIG_MEMCG_SWAP -static void __init enable_swap_cgroup(void) -{ - if (!mem_cgroup_disabled() && really_do_swap_account) - do_swap_account = 1; -} -#else -static void __init enable_swap_cgroup(void) -{ -} -#endif - -static int mem_cgroup_soft_limit_tree_init(void) +static void __init mem_cgroup_soft_limit_tree_init(void) { struct mem_cgroup_tree_per_node *rtpn; struct mem_cgroup_tree_per_zone *rtpz; @@ -6038,8 +6250,7 @@ static int mem_cgroup_soft_limit_tree_init(void) if (!node_state(node, N_NORMAL_MEMORY)) tmp = -1; rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL, tmp); - if (!rtpn) - goto err_cleanup; + BUG_ON(!rtpn); soft_limit_tree.rb_tree_per_node[node] = rtpn; @@ -6049,23 +6260,12 @@ static int mem_cgroup_soft_limit_tree_init(void) spin_lock_init(&rtpz->lock); } } - return 0; - -err_cleanup: - for_each_node(node) { - if (!soft_limit_tree.rb_tree_per_node[node]) - break; - kfree(soft_limit_tree.rb_tree_per_node[node]); - soft_limit_tree.rb_tree_per_node[node] = NULL; - } - return 1; - } static struct cgroup_subsys_state * __ref mem_cgroup_css_alloc(struct cgroup *cont) { - struct mem_cgroup *memcg, *parent; + struct mem_cgroup *memcg; long error = -ENOMEM; int node; @@ -6079,24 +6279,44 @@ mem_cgroup_css_alloc(struct cgroup *cont) /* root ? */ if (cont->parent == NULL) { - int cpu; - enable_swap_cgroup(); - parent = NULL; - if (mem_cgroup_soft_limit_tree_init()) - goto free_out; root_mem_cgroup = memcg; - for_each_possible_cpu(cpu) { - struct memcg_stock_pcp *stock = - &per_cpu(memcg_stock, cpu); - INIT_WORK(&stock->work, drain_local_stock); - } - } else { - parent = mem_cgroup_from_cont(cont->parent); - memcg->use_hierarchy = parent->use_hierarchy; - memcg->oom_kill_disable = parent->oom_kill_disable; + res_counter_init(&memcg->res, NULL); + res_counter_init(&memcg->memsw, NULL); + res_counter_init(&memcg->kmem, NULL); } - if (parent && parent->use_hierarchy) { + memcg->last_scanned_node = MAX_NUMNODES; + INIT_LIST_HEAD(&memcg->oom_notify); + atomic_set(&memcg->refcnt, 1); + memcg->move_charge_at_immigrate = 0; + mutex_init(&memcg->thresholds_lock); + spin_lock_init(&memcg->move_lock); + + return &memcg->css; + +free_out: + __mem_cgroup_free(memcg); + return ERR_PTR(error); +} + +static int +mem_cgroup_css_online(struct cgroup *cont) +{ + struct mem_cgroup *memcg, *parent; + int error = 0; + + if (!cont->parent) + return 0; + + mutex_lock(&memcg_create_mutex); + memcg = mem_cgroup_from_cont(cont); + parent = mem_cgroup_from_cont(cont->parent); + + memcg->use_hierarchy = parent->use_hierarchy; + memcg->oom_kill_disable = parent->oom_kill_disable; + memcg->swappiness = mem_cgroup_swappiness(parent); + + if (parent->use_hierarchy) { res_counter_init(&memcg->res, &parent->res); res_counter_init(&memcg->memsw, &parent->memsw); res_counter_init(&memcg->kmem, &parent->kmem); @@ -6117,20 +6337,12 @@ mem_cgroup_css_alloc(struct cgroup *cont) * much sense so let cgroup subsystem know about this * unfortunate state in our controller. */ - if (parent && parent != root_mem_cgroup) + if (parent != root_mem_cgroup) mem_cgroup_subsys.broken_hierarchy = true; } - memcg->last_scanned_node = MAX_NUMNODES; - INIT_LIST_HEAD(&memcg->oom_notify); - - if (parent) - memcg->swappiness = mem_cgroup_swappiness(parent); - atomic_set(&memcg->refcnt, 1); - memcg->move_charge_at_immigrate = 0; - mutex_init(&memcg->thresholds_lock); - spin_lock_init(&memcg->move_lock); error = memcg_init_kmem(memcg, &mem_cgroup_subsys); + mutex_unlock(&memcg_create_mutex); if (error) { /* * We call put now because our (and parent's) refcnts @@ -6138,12 +6350,10 @@ mem_cgroup_css_alloc(struct cgroup *cont) * call __mem_cgroup_free, so return directly */ mem_cgroup_put(memcg); - return ERR_PTR(error); + if (parent->use_hierarchy) + mem_cgroup_put(parent); } - return &memcg->css; -free_out: - __mem_cgroup_free(memcg); - return ERR_PTR(error); + return error; } static void mem_cgroup_css_offline(struct cgroup *cont) @@ -6160,6 +6370,7 @@ static void mem_cgroup_css_free(struct cgroup *cont) kmem_cgroup_destroy(memcg); + memcg_dangling_add(memcg); mem_cgroup_put(memcg); } @@ -6279,7 +6490,7 @@ static struct page *mc_handle_swap_pte(struct vm_area_struct *vma, * Because lookup_swap_cache() updates some statistics counter, * we call find_get_page() with swapper_space directly. */ - page = find_get_page(&swapper_space, ent.val); + page = find_get_page(swap_address_space(ent), ent.val); if (do_swap_account) entry->val = ent.val; @@ -6320,7 +6531,7 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma, swp_entry_t swap = radix_to_swp_entry(page); if (do_swap_account) *entry = swap; - page = find_get_page(&swapper_space, swap.val); + page = find_get_page(swap_address_space(swap), swap.val); } #endif return page; @@ -6530,8 +6741,15 @@ static int mem_cgroup_can_attach(struct cgroup *cgroup, struct task_struct *p = cgroup_taskset_first(tset); int ret = 0; struct mem_cgroup *memcg = mem_cgroup_from_cont(cgroup); + unsigned long move_charge_at_immigrate; - if (memcg->move_charge_at_immigrate) { + /* + * We are now commited to this value whatever it is. Changes in this + * tunable will only affect upcoming migrations, not the current one. + * So we need to save it, and keep it going. + */ + move_charge_at_immigrate = memcg->move_charge_at_immigrate; + if (move_charge_at_immigrate) { struct mm_struct *mm; struct mem_cgroup *from = mem_cgroup_from_task(p); @@ -6551,6 +6769,7 @@ static int mem_cgroup_can_attach(struct cgroup *cgroup, spin_lock(&mc.lock); mc.from = from; mc.to = memcg; + mc.immigrate_flags = move_charge_at_immigrate; spin_unlock(&mc.lock); /* We set mc.moving_task later */ @@ -6745,6 +6964,7 @@ struct cgroup_subsys mem_cgroup_subsys = { .name = "memory", .subsys_id = mem_cgroup_subsys_id, .css_alloc = mem_cgroup_css_alloc, + .css_online = mem_cgroup_css_online, .css_offline = mem_cgroup_css_offline, .css_free = mem_cgroup_css_free, .can_attach = mem_cgroup_can_attach, @@ -6755,19 +6975,6 @@ struct cgroup_subsys mem_cgroup_subsys = { .use_id = 1, }; -/* - * The rest of init is performed during ->css_alloc() for root css which - * happens before initcalls. hotcpu_notifier() can't be done together as - * it would introduce circular locking by adding cgroup_lock -> cpu hotplug - * dependency. Do it from a subsys_initcall(). - */ -static int __init mem_cgroup_init(void) -{ - hotcpu_notifier(memcg_cpu_hotplug_callback, 0); - return 0; -} -subsys_initcall(mem_cgroup_init); - #ifdef CONFIG_MEMCG_SWAP static int __init enable_swap_account(char *s) { @@ -6780,4 +6987,39 @@ static int __init enable_swap_account(char *s) } __setup("swapaccount=", enable_swap_account); +static void __init memsw_file_init(void) +{ + WARN_ON(cgroup_add_cftypes(&mem_cgroup_subsys, memsw_cgroup_files)); +} + +static void __init enable_swap_cgroup(void) +{ + if (!mem_cgroup_disabled() && really_do_swap_account) { + do_swap_account = 1; + memsw_file_init(); + } +} + +#else +static void __init enable_swap_cgroup(void) +{ +} #endif + +/* + * subsys_initcall() for memory controller. + * + * Some parts like hotcpu_notifier() have to be initialized from this context + * because of lock dependencies (cgroup_lock -> cpu hotplug) but basically + * everything that doesn't depend on a specific mem_cgroup structure should + * be initialized from here. + */ +static int __init mem_cgroup_init(void) +{ + hotcpu_notifier(memcg_cpu_hotplug_callback, 0); + enable_swap_cgroup(); + mem_cgroup_soft_limit_tree_init(); + memcg_stock_init(); + return 0; +} +subsys_initcall(mem_cgroup_init); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index c6e4dd3e1c08..e4683459ab26 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -61,7 +61,7 @@ int sysctl_memory_failure_early_kill __read_mostly = 0; int sysctl_memory_failure_recovery __read_mostly = 1; -atomic_long_t mce_bad_pages __read_mostly = ATOMIC_LONG_INIT(0); +atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0); #if defined(CONFIG_HWPOISON_INJECT) || defined(CONFIG_HWPOISON_INJECT_MODULE) @@ -1039,8 +1039,18 @@ int memory_failure(unsigned long pfn, int trapno, int flags) return 0; } - nr_pages = 1 << compound_trans_order(hpage); - atomic_long_add(nr_pages, &mce_bad_pages); + /* + * Currently errors on hugetlbfs pages are measured in hugepage units, + * so nr_pages should be 1 << compound_order. OTOH when errors are on + * transparent hugepages, they are supposed to be split and error + * measurement is done in normal page units. So nr_pages should be one + * in this case. + */ + if (PageHuge(p)) + nr_pages = 1 << compound_order(hpage); + else /* normal page or thp */ + nr_pages = 1; + atomic_long_add(nr_pages, &num_poisoned_pages); /* * We need/can do nothing about count=0 pages. @@ -1070,7 +1080,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags) if (!PageHWPoison(hpage) || (hwpoison_filter(p) && TestClearPageHWPoison(p)) || (p != hpage && TestSetPageHWPoison(hpage))) { - atomic_long_sub(nr_pages, &mce_bad_pages); + atomic_long_sub(nr_pages, &num_poisoned_pages); return 0; } set_page_hwpoison_huge_page(hpage); @@ -1128,7 +1138,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags) } if (hwpoison_filter(p)) { if (TestClearPageHWPoison(p)) - atomic_long_sub(nr_pages, &mce_bad_pages); + atomic_long_sub(nr_pages, &num_poisoned_pages); unlock_page(hpage); put_page(hpage); return 0; @@ -1323,7 +1333,7 @@ int unpoison_memory(unsigned long pfn) return 0; } if (TestClearPageHWPoison(p)) - atomic_long_sub(nr_pages, &mce_bad_pages); + atomic_long_sub(nr_pages, &num_poisoned_pages); pr_info("MCE: Software-unpoisoned free page %#lx\n", pfn); return 0; } @@ -1337,7 +1347,7 @@ int unpoison_memory(unsigned long pfn) */ if (TestClearPageHWPoison(page)) { pr_info("MCE: Software-unpoisoned page %#lx\n", pfn); - atomic_long_sub(nr_pages, &mce_bad_pages); + atomic_long_sub(nr_pages, &num_poisoned_pages); freeit = 1; if (PageHuge(page)) clear_page_hwpoison_huge_page(page); @@ -1368,7 +1378,7 @@ static struct page *new_page(struct page *p, unsigned long private, int **x) * that is not free, and 1 for any other page type. * For 1 the page is returned with increased page count, otherwise not. */ -static int get_any_page(struct page *p, unsigned long pfn, int flags) +static int __get_any_page(struct page *p, unsigned long pfn, int flags) { int ret; @@ -1393,11 +1403,9 @@ static int get_any_page(struct page *p, unsigned long pfn, int flags) if (!get_page_unless_zero(compound_head(p))) { if (PageHuge(p)) { pr_info("%s: %#lx free huge page\n", __func__, pfn); - ret = dequeue_hwpoisoned_huge_page(compound_head(p)); + ret = 0; } else if (is_free_buddy_page(p)) { pr_info("%s: %#lx free buddy page\n", __func__, pfn); - /* Set hwpoison bit while page is still isolated */ - SetPageHWPoison(p); ret = 0; } else { pr_info("%s: %#lx: unknown zero refcount page type %lx\n", @@ -1413,43 +1421,68 @@ static int get_any_page(struct page *p, unsigned long pfn, int flags) return ret; } +static int get_any_page(struct page *page, unsigned long pfn, int flags) +{ + int ret = __get_any_page(page, pfn, flags); + + if (ret == 1 && !PageHuge(page) && !PageLRU(page)) { + /* + * Try to free it. + */ + put_page(page); + shake_page(page, 1); + + /* + * Did it turn free? + */ + ret = __get_any_page(page, pfn, 0); + if (!PageLRU(page)) { + pr_info("soft_offline: %#lx: unknown non LRU page type %lx\n", + pfn, page->flags); + return -EIO; + } + } + return ret; +} + static int soft_offline_huge_page(struct page *page, int flags) { int ret; unsigned long pfn = page_to_pfn(page); struct page *hpage = compound_head(page); - ret = get_any_page(page, pfn, flags); - if (ret < 0) - return ret; - if (ret == 0) - goto done; - + /* + * This double-check of PageHWPoison is to avoid the race with + * memory_failure(). See also comment in __soft_offline_page(). + */ + lock_page(hpage); if (PageHWPoison(hpage)) { + unlock_page(hpage); put_page(hpage); pr_info("soft offline: %#lx hugepage already poisoned\n", pfn); return -EBUSY; } + unlock_page(hpage); /* Keep page count to indicate a given hugepage is isolated. */ - ret = migrate_huge_page(hpage, new_page, MPOL_MF_MOVE_ALL, false, + ret = migrate_huge_page(hpage, new_page, MPOL_MF_MOVE_ALL, MIGRATE_SYNC); put_page(hpage); if (ret) { pr_info("soft offline: %#lx: migration failed %d, type %lx\n", pfn, ret, page->flags); - return ret; - } -done: - if (!PageHWPoison(hpage)) + } else { + set_page_hwpoison_huge_page(hpage); + dequeue_hwpoisoned_huge_page(hpage); atomic_long_add(1 << compound_trans_order(hpage), - &mce_bad_pages); - set_page_hwpoison_huge_page(hpage); - dequeue_hwpoisoned_huge_page(hpage); + &num_poisoned_pages); + } /* keep elevated page count for bad page */ return ret; } +static int __soft_offline_page(struct page *page, int flags); + /** * soft_offline_page - Soft offline a page. * @page: page to offline @@ -1478,9 +1511,11 @@ int soft_offline_page(struct page *page, int flags) unsigned long pfn = page_to_pfn(page); struct page *hpage = compound_trans_head(page); - if (PageHuge(page)) - return soft_offline_huge_page(page, flags); - if (PageTransHuge(hpage)) { + if (PageHWPoison(page)) { + pr_info("soft offline: %#lx page already poisoned\n", pfn); + return -EBUSY; + } + if (!PageHuge(page) && PageTransHuge(hpage)) { if (PageAnon(hpage) && unlikely(split_huge_page(hpage))) { pr_info("soft offline: %#lx: failed to split THP\n", pfn); @@ -1491,47 +1526,45 @@ int soft_offline_page(struct page *page, int flags) ret = get_any_page(page, pfn, flags); if (ret < 0) return ret; - if (ret == 0) - goto done; - - /* - * Page cache page we can handle? - */ - if (!PageLRU(page)) { - /* - * Try to free it. - */ - put_page(page); - shake_page(page, 1); - - /* - * Did it turn free? - */ - ret = get_any_page(page, pfn, 0); - if (ret < 0) - return ret; - if (ret == 0) - goto done; - } - if (!PageLRU(page)) { - pr_info("soft_offline: %#lx: unknown non LRU page type %lx\n", - pfn, page->flags); - return -EIO; + if (ret) { /* for in-use pages */ + if (PageHuge(page)) + ret = soft_offline_huge_page(page, flags); + else + ret = __soft_offline_page(page, flags); + } else { /* for free pages */ + if (PageHuge(page)) { + set_page_hwpoison_huge_page(hpage); + dequeue_hwpoisoned_huge_page(hpage); + atomic_long_add(1 << compound_trans_order(hpage), + &num_poisoned_pages); + } else { + SetPageHWPoison(page); + atomic_long_inc(&num_poisoned_pages); + } } + /* keep elevated page count for bad page */ + return ret; +} - lock_page(page); - wait_on_page_writeback(page); +static int __soft_offline_page(struct page *page, int flags) +{ + int ret; + unsigned long pfn = page_to_pfn(page); /* - * Synchronized using the page lock with memory_failure() + * Check PageHWPoison again inside page lock because PageHWPoison + * is set by memory_failure() outside page lock. Note that + * memory_failure() also double-checks PageHWPoison inside page lock, + * so there's no race between soft_offline_page() and memory_failure(). */ + lock_page(page); + wait_on_page_writeback(page); if (PageHWPoison(page)) { unlock_page(page); put_page(page); pr_info("soft offline: %#lx page already poisoned\n", pfn); return -EBUSY; } - /* * Try to invalidate first. This should work for * non dirty unmapped page cache pages. @@ -1544,9 +1577,10 @@ int soft_offline_page(struct page *page, int flags) */ if (ret == 1) { put_page(page); - ret = 0; pr_info("soft_offline: %#lx: invalidated\n", pfn); - goto done; + SetPageHWPoison(page); + atomic_long_inc(&num_poisoned_pages); + return 0; } /* @@ -1563,28 +1597,23 @@ int soft_offline_page(struct page *page, int flags) if (!ret) { LIST_HEAD(pagelist); inc_zone_page_state(page, NR_ISOLATED_ANON + - page_is_file_cache(page)); + page_is_file_cache(page)); list_add(&page->lru, &pagelist); ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, - false, MIGRATE_SYNC, - MR_MEMORY_FAILURE); + MIGRATE_SYNC, MR_MEMORY_FAILURE); if (ret) { putback_lru_pages(&pagelist); pr_info("soft offline: %#lx: migration failed %d, type %lx\n", pfn, ret, page->flags); if (ret > 0) ret = -EIO; + } else { + SetPageHWPoison(page); + atomic_long_inc(&num_poisoned_pages); } } else { pr_info("soft offline: %#lx: isolation failed: %d, page count %d, type %lx\n", pfn, ret, page_count(page), page->flags); } - if (ret) - return ret; - -done: - atomic_long_add(1, &mce_bad_pages); - SetPageHWPoison(page); - /* keep elevated page count for bad page */ return ret; } diff --git a/mm/memory.c b/mm/memory.c index bc8bec762db7..e309153ffc5a 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -69,6 +69,10 @@ #include "internal.h" +#ifdef LAST_NID_NOT_IN_PAGE_FLAGS +#warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_nid. +#endif + #ifndef CONFIG_NEED_MULTIPLE_NODES /* use the per-pgdat data instead for discontigmem - mbligh */ unsigned long max_mapnr; @@ -2990,17 +2994,16 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, if (unlikely(!PageSwapCache(page) || page_private(page) != entry.val)) goto out_page; - if (ksm_might_need_to_copy(page, vma, address)) { - swapcache = page; - page = ksm_does_need_to_copy(page, vma, address); - - if (unlikely(!page)) { - ret = VM_FAULT_OOM; - page = swapcache; - swapcache = NULL; - goto out_page; - } + swapcache = page; + page = ksm_might_need_to_copy(page, vma, address); + if (unlikely(!page)) { + ret = VM_FAULT_OOM; + page = swapcache; + swapcache = NULL; + goto out_page; } + if (page == swapcache) + swapcache = NULL; if (mem_cgroup_try_charge_swapin(mm, page, GFP_KERNEL, &ptr)) { ret = VM_FAULT_OOM; @@ -3044,7 +3047,10 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, } flush_icache_page(vma, page); set_pte_at(mm, address, page_table, pte); - do_page_add_anon_rmap(page, vma, address, exclusive); + if (swapcache) /* ksm created a completely new copy */ + page_add_new_anon_rmap(page, vma, address); + else + do_page_add_anon_rmap(page, vma, address, exclusive); /* It's better to call commit-charge after rmap is established */ mem_cgroup_commit_charge_swapin(page, ptr); @@ -3821,30 +3827,6 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) } #endif /* __PAGETABLE_PMD_FOLDED */ -int make_pages_present(unsigned long addr, unsigned long end) -{ - int ret, len, write; - struct vm_area_struct * vma; - - vma = find_vma(current->mm, addr); - if (!vma) - return -ENOMEM; - /* - * We want to touch writable mappings with a write fault in order - * to break COW, except for shared mappings because these don't COW - * and we would not want to dirty them for nothing. - */ - write = (vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE; - BUG_ON(addr >= end); - BUG_ON(end > vma->vm_end); - len = DIV_ROUND_UP(end, PAGE_SIZE) - addr/PAGE_SIZE; - ret = get_user_pages(current, current->mm, addr, - len, write, 0, NULL, NULL); - if (ret < 0) - return ret; - return ret == len ? 0 : -EFAULT; -} - #if !defined(__HAVE_ARCH_GATE_AREA) #if defined(AT_SYSINFO_EHDR) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index d04ed87bfacb..db68c02893e9 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -29,6 +29,7 @@ #include <linux/suspend.h> #include <linux/mm_inline.h> #include <linux/firmware-map.h> +#include <linux/stop_machine.h> #include <asm/tlbflush.h> @@ -91,9 +92,8 @@ static void release_memory_resource(struct resource *res) } #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE -#ifndef CONFIG_SPARSEMEM_VMEMMAP -static void get_page_bootmem(unsigned long info, struct page *page, - unsigned long type) +void get_page_bootmem(unsigned long info, struct page *page, + unsigned long type) { page->lru.next = (struct list_head *) type; SetPagePrivate(page); @@ -124,10 +124,12 @@ void __ref put_page_bootmem(struct page *page) mutex_lock(&ppb_lock); __free_pages_bootmem(page, 0); mutex_unlock(&ppb_lock); + totalram_pages++; } } +#ifndef CONFIG_SPARSEMEM_VMEMMAP static void register_page_bootmem_info_section(unsigned long start_pfn) { unsigned long *usemap, mapsize, section_nr, i; @@ -161,7 +163,34 @@ static void register_page_bootmem_info_section(unsigned long start_pfn) get_page_bootmem(section_nr, page, MIX_SECTION_INFO); } +#else +static void register_page_bootmem_info_section(unsigned long start_pfn) +{ + unsigned long *usemap, mapsize, section_nr, i; + struct mem_section *ms; + struct page *page, *memmap; + if (!pfn_valid(start_pfn)) + return; + + section_nr = pfn_to_section_nr(start_pfn); + ms = __nr_to_section(section_nr); + + memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr); + + register_page_bootmem_memmap(section_nr, memmap, PAGES_PER_SECTION); + + usemap = __nr_to_section(section_nr)->pageblock_flags; + page = virt_to_page(usemap); + + mapsize = PAGE_ALIGN(usemap_size()) >> PAGE_SHIFT; + + for (i = 0; i < mapsize; i++, page++) + get_page_bootmem(section_nr, page, MIX_SECTION_INFO); +} +#endif + +#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE void register_page_bootmem_info_node(struct pglist_data *pgdat) { unsigned long i, pfn, end_pfn, nr_pages; @@ -189,7 +218,7 @@ void register_page_bootmem_info_node(struct pglist_data *pgdat) } pfn = pgdat->node_start_pfn; - end_pfn = pfn + pgdat->node_spanned_pages; + end_pfn = pgdat_end_pfn(pgdat); /* register_section info */ for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) { @@ -203,7 +232,7 @@ void register_page_bootmem_info_node(struct pglist_data *pgdat) register_page_bootmem_info_section(pfn); } } -#endif /* !CONFIG_SPARSEMEM_VMEMMAP */ +#endif static void grow_zone_span(struct zone *zone, unsigned long start_pfn, unsigned long end_pfn) @@ -253,6 +282,17 @@ static void fix_zone_id(struct zone *zone, unsigned long start_pfn, set_page_links(pfn_to_page(pfn), zid, nid, pfn); } +/* Can fail with -ENOMEM from allocating a wait table with vmalloc() or + * alloc_bootmem_node_nopanic() */ +static int __ref ensure_zone_is_initialized(struct zone *zone, + unsigned long start_pfn, unsigned long num_pages) +{ + if (!zone_is_initialized(zone)) + return init_currently_empty_zone(zone, start_pfn, num_pages, + MEMMAP_HOTPLUG); + return 0; +} + static int __meminit move_pfn_range_left(struct zone *z1, struct zone *z2, unsigned long start_pfn, unsigned long end_pfn) { @@ -260,17 +300,14 @@ static int __meminit move_pfn_range_left(struct zone *z1, struct zone *z2, unsigned long flags; unsigned long z1_start_pfn; - if (!z1->wait_table) { - ret = init_currently_empty_zone(z1, start_pfn, - end_pfn - start_pfn, MEMMAP_HOTPLUG); - if (ret) - return ret; - } + ret = ensure_zone_is_initialized(z1, start_pfn, end_pfn - start_pfn); + if (ret) + return ret; pgdat_resize_lock(z1->zone_pgdat, &flags); /* can't move pfns which are higher than @z2 */ - if (end_pfn > z2->zone_start_pfn + z2->spanned_pages) + if (end_pfn > zone_end_pfn(z2)) goto out_fail; /* the move out part mast at the left most of @z2 */ if (start_pfn > z2->zone_start_pfn) @@ -286,7 +323,7 @@ static int __meminit move_pfn_range_left(struct zone *z1, struct zone *z2, z1_start_pfn = start_pfn; resize_zone(z1, z1_start_pfn, end_pfn); - resize_zone(z2, end_pfn, z2->zone_start_pfn + z2->spanned_pages); + resize_zone(z2, end_pfn, zone_end_pfn(z2)); pgdat_resize_unlock(z1->zone_pgdat, &flags); @@ -305,12 +342,9 @@ static int __meminit move_pfn_range_right(struct zone *z1, struct zone *z2, unsigned long flags; unsigned long z2_end_pfn; - if (!z2->wait_table) { - ret = init_currently_empty_zone(z2, start_pfn, - end_pfn - start_pfn, MEMMAP_HOTPLUG); - if (ret) - return ret; - } + ret = ensure_zone_is_initialized(z2, start_pfn, end_pfn - start_pfn); + if (ret) + return ret; pgdat_resize_lock(z1->zone_pgdat, &flags); @@ -318,15 +352,15 @@ static int __meminit move_pfn_range_right(struct zone *z1, struct zone *z2, if (z1->zone_start_pfn > start_pfn) goto out_fail; /* the move out part mast at the right most of @z1 */ - if (z1->zone_start_pfn + z1->spanned_pages > end_pfn) + if (zone_end_pfn(z1) > end_pfn) goto out_fail; /* must included/overlap */ - if (start_pfn >= z1->zone_start_pfn + z1->spanned_pages) + if (start_pfn >= zone_end_pfn(z1)) goto out_fail; /* use end_pfn for z2's end_pfn if z2 is empty */ if (z2->spanned_pages) - z2_end_pfn = z2->zone_start_pfn + z2->spanned_pages; + z2_end_pfn = zone_end_pfn(z2); else z2_end_pfn = end_pfn; @@ -363,16 +397,13 @@ static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn) int nid = pgdat->node_id; int zone_type; unsigned long flags; + int ret; zone_type = zone - pgdat->node_zones; - if (!zone->wait_table) { - int ret; + ret = ensure_zone_is_initialized(zone, phys_start_pfn, nr_pages); + if (ret) + return ret; - ret = init_currently_empty_zone(zone, phys_start_pfn, - nr_pages, MEMMAP_HOTPLUG); - if (ret) - return ret; - } pgdat_resize_lock(zone->zone_pgdat, &flags); grow_zone_span(zone, phys_start_pfn, phys_start_pfn + nr_pages); grow_pgdat_span(zone->zone_pgdat, phys_start_pfn, @@ -405,20 +436,211 @@ static int __meminit __add_section(int nid, struct zone *zone, return register_new_memory(nid, __pfn_to_section(phys_start_pfn)); } -#ifdef CONFIG_SPARSEMEM_VMEMMAP -static int __remove_section(struct zone *zone, struct mem_section *ms) +/* find the smallest valid pfn in the range [start_pfn, end_pfn) */ +static int find_smallest_section_pfn(int nid, struct zone *zone, + unsigned long start_pfn, + unsigned long end_pfn) +{ + struct mem_section *ms; + + for (; start_pfn < end_pfn; start_pfn += PAGES_PER_SECTION) { + ms = __pfn_to_section(start_pfn); + + if (unlikely(!valid_section(ms))) + continue; + + if (unlikely(pfn_to_nid(start_pfn) != nid)) + continue; + + if (zone && zone != page_zone(pfn_to_page(start_pfn))) + continue; + + return start_pfn; + } + + return 0; +} + +/* find the biggest valid pfn in the range [start_pfn, end_pfn). */ +static int find_biggest_section_pfn(int nid, struct zone *zone, + unsigned long start_pfn, + unsigned long end_pfn) +{ + struct mem_section *ms; + unsigned long pfn; + + /* pfn is the end pfn of a memory section. */ + pfn = end_pfn - 1; + for (; pfn >= start_pfn; pfn -= PAGES_PER_SECTION) { + ms = __pfn_to_section(pfn); + + if (unlikely(!valid_section(ms))) + continue; + + if (unlikely(pfn_to_nid(pfn) != nid)) + continue; + + if (zone && zone != page_zone(pfn_to_page(pfn))) + continue; + + return pfn; + } + + return 0; +} + +static void shrink_zone_span(struct zone *zone, unsigned long start_pfn, + unsigned long end_pfn) { + unsigned long zone_start_pfn = zone->zone_start_pfn; + unsigned long zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages; + unsigned long pfn; + struct mem_section *ms; + int nid = zone_to_nid(zone); + + zone_span_writelock(zone); + if (zone_start_pfn == start_pfn) { + /* + * If the section is smallest section in the zone, it need + * shrink zone->zone_start_pfn and zone->zone_spanned_pages. + * In this case, we find second smallest valid mem_section + * for shrinking zone. + */ + pfn = find_smallest_section_pfn(nid, zone, end_pfn, + zone_end_pfn); + if (pfn) { + zone->zone_start_pfn = pfn; + zone->spanned_pages = zone_end_pfn - pfn; + } + } else if (zone_end_pfn == end_pfn) { + /* + * If the section is biggest section in the zone, it need + * shrink zone->spanned_pages. + * In this case, we find second biggest valid mem_section for + * shrinking zone. + */ + pfn = find_biggest_section_pfn(nid, zone, zone_start_pfn, + start_pfn); + if (pfn) + zone->spanned_pages = pfn - zone_start_pfn + 1; + } + /* - * XXX: Freeing memmap with vmemmap is not implement yet. - * This should be removed later. + * The section is not biggest or smallest mem_section in the zone, it + * only creates a hole in the zone. So in this case, we need not + * change the zone. But perhaps, the zone has only hole data. Thus + * it check the zone has only hole or not. */ - return -EBUSY; + pfn = zone_start_pfn; + for (; pfn < zone_end_pfn; pfn += PAGES_PER_SECTION) { + ms = __pfn_to_section(pfn); + + if (unlikely(!valid_section(ms))) + continue; + + if (page_zone(pfn_to_page(pfn)) != zone) + continue; + + /* If the section is current section, it continues the loop */ + if (start_pfn == pfn) + continue; + + /* If we find valid section, we have nothing to do */ + zone_span_writeunlock(zone); + return; + } + + /* The zone has no valid section */ + zone->zone_start_pfn = 0; + zone->spanned_pages = 0; + zone_span_writeunlock(zone); } -#else -static int __remove_section(struct zone *zone, struct mem_section *ms) + +static void shrink_pgdat_span(struct pglist_data *pgdat, + unsigned long start_pfn, unsigned long end_pfn) +{ + unsigned long pgdat_start_pfn = pgdat->node_start_pfn; + unsigned long pgdat_end_pfn = + pgdat->node_start_pfn + pgdat->node_spanned_pages; + unsigned long pfn; + struct mem_section *ms; + int nid = pgdat->node_id; + + if (pgdat_start_pfn == start_pfn) { + /* + * If the section is smallest section in the pgdat, it need + * shrink pgdat->node_start_pfn and pgdat->node_spanned_pages. + * In this case, we find second smallest valid mem_section + * for shrinking zone. + */ + pfn = find_smallest_section_pfn(nid, NULL, end_pfn, + pgdat_end_pfn); + if (pfn) { + pgdat->node_start_pfn = pfn; + pgdat->node_spanned_pages = pgdat_end_pfn - pfn; + } + } else if (pgdat_end_pfn == end_pfn) { + /* + * If the section is biggest section in the pgdat, it need + * shrink pgdat->node_spanned_pages. + * In this case, we find second biggest valid mem_section for + * shrinking zone. + */ + pfn = find_biggest_section_pfn(nid, NULL, pgdat_start_pfn, + start_pfn); + if (pfn) + pgdat->node_spanned_pages = pfn - pgdat_start_pfn + 1; + } + + /* + * If the section is not biggest or smallest mem_section in the pgdat, + * it only creates a hole in the pgdat. So in this case, we need not + * change the pgdat. + * But perhaps, the pgdat has only hole data. Thus it check the pgdat + * has only hole or not. + */ + pfn = pgdat_start_pfn; + for (; pfn < pgdat_end_pfn; pfn += PAGES_PER_SECTION) { + ms = __pfn_to_section(pfn); + + if (unlikely(!valid_section(ms))) + continue; + + if (pfn_to_nid(pfn) != nid) + continue; + + /* If the section is current section, it continues the loop */ + if (start_pfn == pfn) + continue; + + /* If we find valid section, we have nothing to do */ + return; + } + + /* The pgdat has no valid section */ + pgdat->node_start_pfn = 0; + pgdat->node_spanned_pages = 0; +} + +static void __remove_zone(struct zone *zone, unsigned long start_pfn) { - unsigned long flags; struct pglist_data *pgdat = zone->zone_pgdat; + int nr_pages = PAGES_PER_SECTION; + int zone_type; + unsigned long flags; + + zone_type = zone - pgdat->node_zones; + + pgdat_resize_lock(zone->zone_pgdat, &flags); + shrink_zone_span(zone, start_pfn, start_pfn + nr_pages); + shrink_pgdat_span(pgdat, start_pfn, start_pfn + nr_pages); + pgdat_resize_unlock(zone->zone_pgdat, &flags); +} + +static int __remove_section(struct zone *zone, struct mem_section *ms) +{ + unsigned long start_pfn; + int scn_nr; int ret = -EINVAL; if (!valid_section(ms)) @@ -428,12 +650,13 @@ static int __remove_section(struct zone *zone, struct mem_section *ms) if (ret) return ret; - pgdat_resize_lock(pgdat, &flags); + scn_nr = __section_nr(ms); + start_pfn = section_nr_to_pfn(scn_nr); + __remove_zone(zone, start_pfn); + sparse_remove_one_section(zone, ms); - pgdat_resize_unlock(pgdat, &flags); return 0; } -#endif /* * Reasonably generic function for adding memory. It is @@ -797,11 +1020,14 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start) unsigned long zholes_size[MAX_NR_ZONES] = {0}; unsigned long start_pfn = start >> PAGE_SHIFT; - pgdat = arch_alloc_nodedata(nid); - if (!pgdat) - return NULL; + pgdat = NODE_DATA(nid); + if (!pgdat) { + pgdat = arch_alloc_nodedata(nid); + if (!pgdat) + return NULL; - arch_refresh_nodedata(nid, pgdat); + arch_refresh_nodedata(nid, pgdat); + } /* we can use NODE_DATA(nid) from here */ @@ -854,7 +1080,8 @@ out: int __ref add_memory(int nid, u64 start, u64 size) { pg_data_t *pgdat = NULL; - int new_pgdat = 0; + bool new_pgdat; + bool new_node; struct resource *res; int ret; @@ -865,12 +1092,16 @@ int __ref add_memory(int nid, u64 start, u64 size) if (!res) goto out; - if (!node_online(nid)) { + { /* Stupid hack to suppress address-never-null warning */ + void *p = NODE_DATA(nid); + new_pgdat = !p; + } + new_node = !node_online(nid); + if (new_node) { pgdat = hotadd_new_pgdat(nid, start); ret = -ENOMEM; if (!pgdat) goto error; - new_pgdat = 1; } /* call arch's memory hotadd */ @@ -882,7 +1113,7 @@ int __ref add_memory(int nid, u64 start, u64 size) /* we online node here. we can't roll back from here. */ node_set_online(nid); - if (new_pgdat) { + if (new_node) { ret = register_one_node(nid); /* * If sysfs file of new node can't create, cpu on the node @@ -901,8 +1132,7 @@ error: /* rollback pgdat allocation and others */ if (new_pgdat) rollback_node_hotadd(nid, pgdat); - if (res) - release_memory_resource(res); + release_memory_resource(res); out: unlock_memory_hotplug(); @@ -1058,8 +1288,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) * migrate_pages returns # of failed pages. */ ret = migrate_pages(&source, alloc_migrate_target, 0, - true, MIGRATE_SYNC, - MR_MEMORY_HOTPLUG); + MIGRATE_SYNC, MR_MEMORY_HOTPLUG); if (ret) putback_lru_pages(&source); } @@ -1381,17 +1610,26 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages) return __offline_pages(start_pfn, start_pfn + nr_pages, 120 * HZ); } -int remove_memory(u64 start, u64 size) +/** + * walk_memory_range - walks through all mem sections in [start_pfn, end_pfn) + * @start_pfn: start pfn of the memory range + * @end_pfn: end pft of the memory range + * @arg: argument passed to func + * @func: callback for each memory section walked + * + * This function walks through all present mem sections in range + * [start_pfn, end_pfn) and call func on each mem section. + * + * Returns the return value of func. + */ +static int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn, + void *arg, int (*func)(struct memory_block *, void *)) { struct memory_block *mem = NULL; struct mem_section *section; - unsigned long start_pfn, end_pfn; unsigned long pfn, section_nr; int ret; - start_pfn = PFN_DOWN(start); - end_pfn = start_pfn + PFN_DOWN(size); - for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) { section_nr = pfn_to_section_nr(pfn); if (!present_section_nr(section_nr)) @@ -1408,7 +1646,7 @@ int remove_memory(u64 start, u64 size) if (!mem) continue; - ret = offline_memory_block(mem); + ret = func(mem, arg); if (ret) { kobject_put(&mem->dev.kobj); return ret; @@ -1420,12 +1658,209 @@ int remove_memory(u64 start, u64 size) return 0; } + +/** + * offline_memory_block_cb - callback function for offlining memory block + * @mem: the memory block to be offlined + * @arg: buffer to hold error msg + * + * Always return 0, and put the error msg in arg if any. + */ +static int offline_memory_block_cb(struct memory_block *mem, void *arg) +{ + int *ret = arg; + int error = offline_memory_block(mem); + + if (error != 0 && *ret == 0) + *ret = error; + + return 0; +} + +static int is_memblock_offlined_cb(struct memory_block *mem, void *arg) +{ + int ret = !is_memblock_offlined(mem); + + if (unlikely(ret)) + pr_warn("removing memory fails, because memory " + "[%#010llx-%#010llx] is onlined\n", + PFN_PHYS(section_nr_to_pfn(mem->start_section_nr)), + PFN_PHYS(section_nr_to_pfn(mem->end_section_nr + 1))-1); + + return ret; +} + +static int check_cpu_on_node(void *data) +{ + struct pglist_data *pgdat = data; + int cpu; + + for_each_present_cpu(cpu) { + if (cpu_to_node(cpu) == pgdat->node_id) + /* + * the cpu on this node isn't removed, and we can't + * offline this node. + */ + return -EBUSY; + } + + return 0; +} + +static void unmap_cpu_on_node(void *data) +{ +#ifdef CONFIG_ACPI_NUMA + struct pglist_data *pgdat = data; + int cpu; + + for_each_possible_cpu(cpu) + if (cpu_to_node(cpu) == pgdat->node_id) + numa_clear_node(cpu); +#endif +} + +static int check_and_unmap_cpu_on_node(void *data) +{ + int ret = check_cpu_on_node(data); + + if (ret) + return ret; + + /* + * the node will be offlined when we come here, so we can clear + * the cpu_to_node() now. + */ + + unmap_cpu_on_node(data); + return 0; +} + +/* offline the node if all memory sections of this node are removed */ +void try_offline_node(int nid) +{ + pg_data_t *pgdat = NODE_DATA(nid); + unsigned long start_pfn = pgdat->node_start_pfn; + unsigned long end_pfn = start_pfn + pgdat->node_spanned_pages; + unsigned long pfn; + struct page *pgdat_page = virt_to_page(pgdat); + int i; + + for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) { + unsigned long section_nr = pfn_to_section_nr(pfn); + + if (!present_section_nr(section_nr)) + continue; + + if (pfn_to_nid(pfn) != nid) + continue; + + /* + * some memory sections of this node are not removed, and we + * can't offline node now. + */ + return; + } + + if (stop_machine(check_and_unmap_cpu_on_node, pgdat, NULL)) + return; + + /* + * all memory/cpu of this node are removed, we can offline this + * node now. + */ + node_set_offline(nid); + unregister_one_node(nid); + + if (!PageSlab(pgdat_page) && !PageCompound(pgdat_page)) + /* node data is allocated from boot memory */ + return; + + /* free waittable in each zone */ + for (i = 0; i < MAX_NR_ZONES; i++) { + struct zone *zone = pgdat->node_zones + i; + + if (zone->wait_table) + vfree(zone->wait_table); + } + + /* + * Since there is no way to guarentee the address of pgdat/zone is not + * on stack of any kernel threads or used by other kernel objects + * without reference counting or other symchronizing method, do not + * reset node_data and free pgdat here. Just reset it to 0 and reuse + * the memory when the node is online again. + */ + memset(pgdat, 0, sizeof(*pgdat)); +} +EXPORT_SYMBOL(try_offline_node); + +int __ref remove_memory(int nid, u64 start, u64 size) +{ + unsigned long start_pfn, end_pfn; + int ret = 0; + int retry = 1; + + start_pfn = PFN_DOWN(start); + end_pfn = start_pfn + PFN_DOWN(size); + + /* + * When CONFIG_MEMCG is on, one memory block may be used by other + * blocks to store page cgroup when onlining pages. But we don't know + * in what order pages are onlined. So we iterate twice to offline + * memory: + * 1st iterate: offline every non primary memory block. + * 2nd iterate: offline primary (i.e. first added) memory block. + */ +repeat: + walk_memory_range(start_pfn, end_pfn, &ret, + offline_memory_block_cb); + if (ret) { + if (!retry) + return ret; + + retry = 0; + ret = 0; + goto repeat; + } + + lock_memory_hotplug(); + + /* + * we have offlined all memory blocks like this: + * 1. lock memory hotplug + * 2. offline a memory block + * 3. unlock memory hotplug + * + * repeat step1-3 to offline the memory block. All memory blocks + * must be offlined before removing memory. But we don't hold the + * lock in the whole operation. So we should check whether all + * memory blocks are offlined. + */ + + ret = walk_memory_range(start_pfn, end_pfn, NULL, + is_memblock_offlined_cb); + if (ret) { + unlock_memory_hotplug(); + return ret; + } + + /* remove memmap entry */ + firmware_map_remove(start, start + size, "System RAM"); + + arch_remove_memory(start, size); + + try_offline_node(nid); + + unlock_memory_hotplug(); + + return 0; +} #else int offline_pages(unsigned long start_pfn, unsigned long nr_pages) { return -EINVAL; } -int remove_memory(u64 start, u64 size) +int remove_memory(int nid, u64 start, u64 size) { return -EINVAL; } diff --git a/mm/mempolicy.c b/mm/mempolicy.c index e2df1c1fb41f..31d26637b658 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -26,7 +26,7 @@ * the allocation to memory nodes instead * * preferred Try a specific node first before normal fallback. - * As a special case node -1 here means do the allocation + * As a special case NUMA_NO_NODE here means do the allocation * on the local CPU. This is normally identical to default, * but useful to set in a VMA when you have a non default * process policy. @@ -127,7 +127,7 @@ static struct mempolicy *get_task_policy(struct task_struct *p) if (!pol) { node = numa_node_id(); - if (node != -1) + if (node != NUMA_NO_NODE) pol = &preferred_node_policy[node]; /* preferred_node_policy is not initialised early in boot */ @@ -161,19 +161,7 @@ static const struct mempolicy_operations { /* Check that the nodemask contains at least one populated zone */ static int is_valid_nodemask(const nodemask_t *nodemask) { - int nd, k; - - for_each_node_mask(nd, *nodemask) { - struct zone *z; - - for (k = 0; k <= policy_zone; k++) { - z = &NODE_DATA(nd)->node_zones[k]; - if (z->present_pages > 0) - return 1; - } - } - - return 0; + return nodes_intersects(*nodemask, node_states[N_MEMORY]); } static inline int mpol_store_user_nodemask(const struct mempolicy *pol) @@ -270,7 +258,7 @@ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags, struct mempolicy *policy; pr_debug("setting mode %d flags %d nodes[0] %lx\n", - mode, flags, nodes ? nodes_addr(*nodes)[0] : -1); + mode, flags, nodes ? nodes_addr(*nodes)[0] : NUMA_NO_NODE); if (mode == MPOL_DEFAULT) { if (nodes && !nodes_empty(*nodes)) @@ -508,9 +496,8 @@ static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd, /* * vm_normal_page() filters out zero pages, but there might * still be PageReserved pages to skip, perhaps in a VDSO. - * And we cannot move PageKsm pages sensibly or safely yet. */ - if (PageReserved(page) || PageKsm(page)) + if (PageReserved(page)) continue; nid = page_to_nid(page); if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT)) @@ -1027,8 +1014,7 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest, if (!list_empty(&pagelist)) { err = migrate_pages(&pagelist, new_node_page, dest, - false, MIGRATE_SYNC, - MR_SYSCALL); + MIGRATE_SYNC, MR_SYSCALL); if (err) putback_lru_pages(&pagelist); } @@ -1235,7 +1221,7 @@ static long do_mbind(unsigned long start, unsigned long len, pr_debug("mbind %lx-%lx mode:%d flags:%d nodes:%lx\n", start, start + len, mode, mode_flags, - nmask ? nodes_addr(*nmask)[0] : -1); + nmask ? nodes_addr(*nmask)[0] : NUMA_NO_NODE); if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { @@ -1272,9 +1258,8 @@ static long do_mbind(unsigned long start, unsigned long len, if (!list_empty(&pagelist)) { WARN_ON_ONCE(flags & MPOL_MF_LAZY); nr_failed = migrate_pages(&pagelist, new_vma_page, - (unsigned long)vma, - false, MIGRATE_SYNC, - MR_MEMPOLICY_MBIND); + (unsigned long)vma, + MIGRATE_SYNC, MR_MEMPOLICY_MBIND); if (nr_failed) putback_lru_pages(&pagelist); } @@ -1644,6 +1629,26 @@ struct mempolicy *get_vma_policy(struct task_struct *task, return pol; } +static int apply_policy_zone(struct mempolicy *policy, enum zone_type zone) +{ + enum zone_type dynamic_policy_zone = policy_zone; + + BUG_ON(dynamic_policy_zone == ZONE_MOVABLE); + + /* + * if policy->v.nodes has movable memory only, + * we apply policy when gfp_zone(gfp) = ZONE_MOVABLE only. + * + * policy->v.nodes is intersect with node_states[N_MEMORY]. + * so if the following test faile, it implies + * policy->v.nodes has movable memory only. + */ + if (!nodes_intersects(policy->v.nodes, node_states[N_HIGH_MEMORY])) + dynamic_policy_zone = ZONE_MOVABLE; + + return zone >= dynamic_policy_zone; +} + /* * Return a nodemask representing a mempolicy for filtering nodes for * page allocation @@ -1652,7 +1657,7 @@ static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy) { /* Lower zones don't get a nodemask applied for MPOL_BIND */ if (unlikely(policy->mode == MPOL_BIND) && - gfp_zone(gfp) >= policy_zone && + apply_policy_zone(policy, gfp_zone(gfp)) && cpuset_nodemask_valid_mems_allowed(&policy->v.nodes)) return &policy->v.nodes; @@ -2308,7 +2313,7 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long * it less likely we act on an unlikely task<->page * relation. */ - last_nid = page_xchg_last_nid(page, polnid); + last_nid = page_nid_xchg_last(page, polnid); if (last_nid != polnid) goto out; } @@ -2483,7 +2488,7 @@ int mpol_set_shared_policy(struct shared_policy *info, vma->vm_pgoff, sz, npol ? npol->mode : -1, npol ? npol->flags : -1, - npol ? nodes_addr(npol->v.nodes)[0] : -1); + npol ? nodes_addr(npol->v.nodes)[0] : NUMA_NO_NODE); if (npol) { new = sp_alloc(vma->vm_pgoff, vma->vm_pgoff + sz, npol); diff --git a/mm/migrate.c b/mm/migrate.c index 2fd8b4af4744..4e3dab51f8fa 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -464,7 +464,10 @@ void migrate_page_copy(struct page *newpage, struct page *page) mlock_migrate_page(newpage, page); ksm_migrate_page(newpage, page); - + /* + * Please do not reorder this without considering how mm/ksm.c's + * get_ksm_page() depends upon ksm_migrate_page() and PageSwapCache(). + */ ClearPageSwapCache(page); ClearPagePrivate(page); set_page_private(page, 0); @@ -698,7 +701,7 @@ static int move_to_new_page(struct page *newpage, struct page *page, } static int __unmap_and_move(struct page *page, struct page *newpage, - int force, bool offlining, enum migrate_mode mode) + int force, enum migrate_mode mode) { int rc = -EAGAIN; int remap_swapcache = 1; @@ -728,20 +731,6 @@ static int __unmap_and_move(struct page *page, struct page *newpage, lock_page(page); } - /* - * Only memory hotplug's offline_pages() caller has locked out KSM, - * and can safely migrate a KSM page. The other cases have skipped - * PageKsm along with PageReserved - but it is only now when we have - * the page lock that we can be certain it will not go KSM beneath us - * (KSM will not upgrade a page from PageAnon to PageKsm when it sees - * its pagecount raised, but only here do we take the page lock which - * serializes that). - */ - if (PageKsm(page) && !offlining) { - rc = -EBUSY; - goto unlock; - } - /* charge against new page */ mem_cgroup_prepare_migration(page, newpage, &mem); @@ -768,7 +757,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage, * File Caches may use write_page() or lock_page() in migration, then, * just care Anon page here. */ - if (PageAnon(page)) { + if (PageAnon(page) && !PageKsm(page)) { /* * Only page_lock_anon_vma_read() understands the subtleties of * getting a hold on an anon_vma from outside one of its mms. @@ -848,7 +837,6 @@ uncharge: mem_cgroup_end_migration(mem, page, newpage, (rc == MIGRATEPAGE_SUCCESS || rc == MIGRATEPAGE_BALLOON_SUCCESS)); -unlock: unlock_page(page); out: return rc; @@ -859,8 +847,7 @@ out: * to the newly allocated page in newpage. */ static int unmap_and_move(new_page_t get_new_page, unsigned long private, - struct page *page, int force, bool offlining, - enum migrate_mode mode) + struct page *page, int force, enum migrate_mode mode) { int rc = 0; int *result = NULL; @@ -878,7 +865,7 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private, if (unlikely(split_huge_page(page))) goto out; - rc = __unmap_and_move(page, newpage, force, offlining, mode); + rc = __unmap_and_move(page, newpage, force, mode); if (unlikely(rc == MIGRATEPAGE_BALLOON_SUCCESS)) { /* @@ -889,6 +876,7 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private, dec_zone_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); balloon_page_free(page); + balloon_event_count(COMPACTBALLOONMIGRATED); return MIGRATEPAGE_SUCCESS; } out: @@ -938,8 +926,7 @@ out: */ static int unmap_and_move_huge_page(new_page_t get_new_page, unsigned long private, struct page *hpage, - int force, bool offlining, - enum migrate_mode mode) + int force, enum migrate_mode mode) { int rc = 0; int *result = NULL; @@ -1001,9 +988,8 @@ out: * * Return: Number of pages not migrated or error code. */ -int migrate_pages(struct list_head *from, - new_page_t get_new_page, unsigned long private, bool offlining, - enum migrate_mode mode, int reason) +int migrate_pages(struct list_head *from, new_page_t get_new_page, + unsigned long private, enum migrate_mode mode, int reason) { int retry = 1; int nr_failed = 0; @@ -1024,8 +1010,7 @@ int migrate_pages(struct list_head *from, cond_resched(); rc = unmap_and_move(get_new_page, private, - page, pass > 2, offlining, - mode); + page, pass > 2, mode); switch(rc) { case -ENOMEM: @@ -1058,15 +1043,13 @@ out: } int migrate_huge_page(struct page *hpage, new_page_t get_new_page, - unsigned long private, bool offlining, - enum migrate_mode mode) + unsigned long private, enum migrate_mode mode) { int pass, rc; for (pass = 0; pass < 10; pass++) { - rc = unmap_and_move_huge_page(get_new_page, - private, hpage, pass > 2, offlining, - mode); + rc = unmap_and_move_huge_page(get_new_page, private, + hpage, pass > 2, mode); switch (rc) { case -ENOMEM: goto out; @@ -1152,7 +1135,7 @@ static int do_move_page_to_node_array(struct mm_struct *mm, goto set_status; /* Use PageReserved to check for zero page */ - if (PageReserved(page) || PageKsm(page)) + if (PageReserved(page)) goto put_and_set; pp->page = page; @@ -1189,8 +1172,7 @@ set_status: err = 0; if (!list_empty(&pagelist)) { err = migrate_pages(&pagelist, new_page_node, - (unsigned long)pm, 0, MIGRATE_SYNC, - MR_SYSCALL); + (unsigned long)pm, MIGRATE_SYNC, MR_SYSCALL); if (err) putback_lru_pages(&pagelist); } @@ -1314,7 +1296,7 @@ static void do_pages_stat_array(struct mm_struct *mm, unsigned long nr_pages, err = -ENOENT; /* Use PageReserved to check for zero page */ - if (!page || PageReserved(page) || PageKsm(page)) + if (!page || PageReserved(page)) goto set_status; err = page_to_nid(page); @@ -1461,7 +1443,7 @@ int migrate_vmas(struct mm_struct *mm, const nodemask_t *to, * pages. Currently it only checks the watermarks which crude */ static bool migrate_balanced_pgdat(struct pglist_data *pgdat, - int nr_migrate_pages) + unsigned long nr_migrate_pages) { int z; for (z = pgdat->nr_zones - 1; z >= 0; z--) { @@ -1497,7 +1479,7 @@ static struct page *alloc_misplaced_dst_page(struct page *page, __GFP_NOWARN) & ~GFP_IOFS, 0); if (newpage) - page_xchg_last_nid(newpage, page_last_nid(page)); + page_nid_xchg_last(newpage, page_nid_last(page)); return newpage; } @@ -1557,39 +1539,40 @@ bool numamigrate_update_ratelimit(pg_data_t *pgdat, unsigned long nr_pages) int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) { - int ret = 0; + int page_lru; + + VM_BUG_ON(compound_order(page) && !PageTransHuge(page)); /* Avoid migrating to a node that is nearly full */ - if (migrate_balanced_pgdat(pgdat, 1)) { - int page_lru; + if (!migrate_balanced_pgdat(pgdat, 1UL << compound_order(page))) + return 0; - if (isolate_lru_page(page)) { - put_page(page); - return 0; - } + if (isolate_lru_page(page)) + return 0; - /* Page is isolated */ - ret = 1; - page_lru = page_is_file_cache(page); - if (!PageTransHuge(page)) - inc_zone_page_state(page, NR_ISOLATED_ANON + page_lru); - else - mod_zone_page_state(page_zone(page), - NR_ISOLATED_ANON + page_lru, - HPAGE_PMD_NR); + /* + * migrate_misplaced_transhuge_page() skips page migration's usual + * check on page_count(), so we must do it here, now that the page + * has been isolated: a GUP pin, or any other pin, prevents migration. + * The expected page count is 3: 1 for page's mapcount and 1 for the + * caller's pin and 1 for the reference taken by isolate_lru_page(). + */ + if (PageTransHuge(page) && page_count(page) != 3) { + putback_lru_page(page); + return 0; } + page_lru = page_is_file_cache(page); + mod_zone_page_state(page_zone(page), NR_ISOLATED_ANON + page_lru, + hpage_nr_pages(page)); + /* - * Page is either isolated or there is not enough space on the target - * node. If isolated, then it has taken a reference count and the - * callers reference can be safely dropped without the page - * disappearing underneath us during migration. Otherwise the page is - * not to be migrated but the callers reference should still be - * dropped so it does not leak. + * Isolating the page has taken another reference, so the + * caller's reference can be safely dropped without the page + * disappearing underneath us during migration. */ put_page(page); - - return ret; + return 1; } /* @@ -1600,7 +1583,7 @@ int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) int migrate_misplaced_page(struct page *page, int node) { pg_data_t *pgdat = NODE_DATA(node); - int isolated = 0; + int isolated; int nr_remaining; LIST_HEAD(migratepages); @@ -1608,42 +1591,43 @@ int migrate_misplaced_page(struct page *page, int node) * Don't migrate pages that are mapped in multiple processes. * TODO: Handle false sharing detection instead of this hammer */ - if (page_mapcount(page) != 1) { - put_page(page); + if (page_mapcount(page) != 1) goto out; - } /* * Rate-limit the amount of data that is being migrated to a node. * Optimal placement is no good if the memory bus is saturated and * all the time is being spent migrating! */ - if (numamigrate_update_ratelimit(pgdat, 1)) { - put_page(page); + if (numamigrate_update_ratelimit(pgdat, 1)) goto out; - } isolated = numamigrate_isolate_page(pgdat, page); if (!isolated) goto out; list_add(&page->lru, &migratepages); - nr_remaining = migrate_pages(&migratepages, - alloc_misplaced_dst_page, - node, false, MIGRATE_ASYNC, - MR_NUMA_MISPLACED); + nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_page, + node, MIGRATE_ASYNC, MR_NUMA_MISPLACED); if (nr_remaining) { putback_lru_pages(&migratepages); isolated = 0; } else count_vm_numa_event(NUMA_PAGE_MIGRATE); BUG_ON(!list_empty(&migratepages)); -out: return isolated; + +out: + put_page(page); + return 0; } #endif /* CONFIG_NUMA_BALANCING */ #if defined(CONFIG_NUMA_BALANCING) && defined(CONFIG_TRANSPARENT_HUGEPAGE) +/* + * Migrates a THP to a given target node. page must be locked and is unlocked + * before returning. + */ int migrate_misplaced_transhuge_page(struct mm_struct *mm, struct vm_area_struct *vma, pmd_t *pmd, pmd_t entry, @@ -1674,29 +1658,15 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, new_page = alloc_pages_node(node, (GFP_TRANSHUGE | GFP_THISNODE) & ~__GFP_WAIT, HPAGE_PMD_ORDER); - if (!new_page) { - count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR); - goto out_dropref; - } - page_xchg_last_nid(new_page, page_last_nid(page)); + if (!new_page) + goto out_fail; - isolated = numamigrate_isolate_page(pgdat, page); + page_nid_xchg_last(new_page, page_nid_last(page)); - /* - * Failing to isolate or a GUP pin prevents migration. The expected - * page count is 2. 1 for anonymous pages without a mapping and 1 - * for the callers pin. If the page was isolated, the page will - * need to be put back on the LRU. - */ - if (!isolated || page_count(page) != 2) { - count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR); + isolated = numamigrate_isolate_page(pgdat, page); + if (!isolated) { put_page(new_page); - if (isolated) { - putback_lru_page(page); - isolated = 0; - goto out; - } - goto out_keep_locked; + goto out_fail; } /* Prepare a page as a migration target */ @@ -1728,6 +1698,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, putback_lru_page(page); count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR); + isolated = 0; goto out; } @@ -1772,9 +1743,11 @@ out: -HPAGE_PMD_NR); return isolated; +out_fail: + count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR); out_dropref: + unlock_page(page); put_page(page); -out_keep_locked: return 0; } #endif /* CONFIG_NUMA_BALANCING */ diff --git a/mm/mincore.c b/mm/mincore.c index 936b4cee8cb1..da2be56a7b8f 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -75,7 +75,7 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff) /* shmem/tmpfs may return swap: account for swapcache page too. */ if (radix_tree_exceptional_entry(page)) { swp_entry_t swap = radix_to_swp_entry(page); - page = find_get_page(&swapper_space, swap.val); + page = find_get_page(swap_address_space(swap), swap.val); } #endif if (page) { @@ -135,7 +135,8 @@ static void mincore_pte_range(struct vm_area_struct *vma, pmd_t *pmd, } else { #ifdef CONFIG_SWAP pgoff = entry.val; - *vec = mincore_page(&swapper_space, pgoff); + *vec = mincore_page(swap_address_space(entry), + pgoff); #else WARN_ON(1); *vec = 1; diff --git a/mm/mlock.c b/mm/mlock.c index c9bd528b01d2..38db3b094105 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -155,9 +155,8 @@ void munlock_vma_page(struct page *page) * * vma->vm_mm->mmap_sem must be held for at least read. */ -static long __mlock_vma_pages_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end, - int *nonblocking) +long __mlock_vma_pages_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end, int *nonblocking) { struct mm_struct *mm = vma->vm_mm; unsigned long addr = start; @@ -186,6 +185,10 @@ static long __mlock_vma_pages_range(struct vm_area_struct *vma, if (vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC)) gup_flags |= FOLL_FORCE; + /* + * We made sure addr is within a VMA, so the following will + * not result in a stack expansion that recurses back here. + */ return __get_user_pages(current, mm, addr, nr_pages, gup_flags, NULL, NULL, nonblocking); } @@ -202,56 +205,6 @@ static int __mlock_posix_error_return(long retval) return retval; } -/** - * mlock_vma_pages_range() - mlock pages in specified vma range. - * @vma - the vma containing the specfied address range - * @start - starting address in @vma to mlock - * @end - end address [+1] in @vma to mlock - * - * For mmap()/mremap()/expansion of mlocked vma. - * - * return 0 on success for "normal" vmas. - * - * return number of pages [> 0] to be removed from locked_vm on success - * of "special" vmas. - */ -long mlock_vma_pages_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end) -{ - int nr_pages = (end - start) / PAGE_SIZE; - BUG_ON(!(vma->vm_flags & VM_LOCKED)); - - /* - * filter unlockable vmas - */ - if (vma->vm_flags & (VM_IO | VM_PFNMAP)) - goto no_mlock; - - if (!((vma->vm_flags & VM_DONTEXPAND) || - is_vm_hugetlb_page(vma) || - vma == get_gate_vma(current->mm))) { - - __mlock_vma_pages_range(vma, start, end, NULL); - - /* Hide errors from mmap() and other callers */ - return 0; - } - - /* - * User mapped kernel pages or huge pages: - * make these pages present to populate the ptes, but - * fall thru' to reset VM_LOCKED--no need to unlock, and - * return nr_pages so these don't get counted against task's - * locked limit. huge pages are already counted against - * locked vm limit. - */ - make_pages_present(start, end); - -no_mlock: - vma->vm_flags &= ~VM_LOCKED; /* and don't come back! */ - return nr_pages; /* error or pages NOT mlocked */ -} - /* * munlock_vma_pages_range() - munlock all pages in the vma range.' * @vma - vma containing range to be munlock()ed. @@ -303,7 +256,7 @@ void munlock_vma_pages_range(struct vm_area_struct *vma, * * Filters out "special" vmas -- VM_LOCKED never gets set for these, and * munlock is a no-op. However, for some special vmas, we go ahead and - * populate the ptes via make_pages_present(). + * populate the ptes. * * For vmas that pass the filters, merge/split as appropriate. */ @@ -391,9 +344,9 @@ static int do_mlock(unsigned long start, size_t len, int on) /* Here we know that vma->vm_start <= nstart < vma->vm_end. */ - newflags = vma->vm_flags | VM_LOCKED; - if (!on) - newflags &= ~VM_LOCKED; + newflags = vma->vm_flags & ~VM_LOCKED; + if (on) + newflags |= VM_LOCKED | VM_POPULATE; tmp = vma->vm_end; if (tmp > end) @@ -416,7 +369,14 @@ static int do_mlock(unsigned long start, size_t len, int on) return error; } -static int do_mlock_pages(unsigned long start, size_t len, int ignore_errors) +/* + * __mm_populate - populate and/or mlock pages within a range of address space. + * + * This is used to implement mlock() and the MAP_POPULATE / MAP_LOCKED mmap + * flags. VMAs must be already marked with the desired vm_flags, and + * mmap_sem must not be held. + */ +int __mm_populate(unsigned long start, unsigned long len, int ignore_errors) { struct mm_struct *mm = current->mm; unsigned long end, nstart, nend; @@ -446,7 +406,8 @@ static int do_mlock_pages(unsigned long start, size_t len, int ignore_errors) * range with the first VMA. Also, skip undesirable VMA types. */ nend = min(end, vma->vm_end); - if (vma->vm_flags & (VM_IO | VM_PFNMAP)) + if ((vma->vm_flags & (VM_IO | VM_PFNMAP | VM_POPULATE)) != + VM_POPULATE) continue; if (nstart < vma->vm_start) nstart = vma->vm_start; @@ -498,7 +459,7 @@ SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len) error = do_mlock(start, len, 1); up_write(¤t->mm->mmap_sem); if (!error) - error = do_mlock_pages(start, len, 0); + error = __mm_populate(start, len, 0); return error; } @@ -519,18 +480,18 @@ static int do_mlockall(int flags) struct vm_area_struct * vma, * prev = NULL; if (flags & MCL_FUTURE) - current->mm->def_flags |= VM_LOCKED; + current->mm->def_flags |= VM_LOCKED | VM_POPULATE; else - current->mm->def_flags &= ~VM_LOCKED; + current->mm->def_flags &= ~(VM_LOCKED | VM_POPULATE); if (flags == MCL_FUTURE) goto out; for (vma = current->mm->mmap; vma ; vma = prev->vm_next) { vm_flags_t newflags; - newflags = vma->vm_flags | VM_LOCKED; - if (!(flags & MCL_CURRENT)) - newflags &= ~VM_LOCKED; + newflags = vma->vm_flags & ~VM_LOCKED; + if (flags & MCL_CURRENT) + newflags |= VM_LOCKED | VM_POPULATE; /* Ignore errors */ mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags); @@ -564,10 +525,8 @@ SYSCALL_DEFINE1(mlockall, int, flags) capable(CAP_IPC_LOCK)) ret = do_mlockall(flags); up_write(¤t->mm->mmap_sem); - if (!ret && (flags & MCL_CURRENT)) { - /* Ignore errors */ - do_mlock_pages(0, TASK_SIZE, 1); - } + if (!ret && (flags & MCL_CURRENT)) + mm_populate(0, TASK_SIZE); out: return ret; } diff --git a/mm/mm_init.c b/mm/mm_init.c index 1ffd97ae26d7..c280a02ea11e 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -69,34 +69,41 @@ void __init mminit_verify_pageflags_layout(void) unsigned long or_mask, add_mask; shift = 8 * sizeof(unsigned long); - width = shift - SECTIONS_WIDTH - NODES_WIDTH - ZONES_WIDTH; + width = shift - SECTIONS_WIDTH - NODES_WIDTH - ZONES_WIDTH - LAST_NID_SHIFT; mminit_dprintk(MMINIT_TRACE, "pageflags_layout_widths", - "Section %d Node %d Zone %d Flags %d\n", + "Section %d Node %d Zone %d Lastnid %d Flags %d\n", SECTIONS_WIDTH, NODES_WIDTH, ZONES_WIDTH, + LAST_NID_WIDTH, NR_PAGEFLAGS); mminit_dprintk(MMINIT_TRACE, "pageflags_layout_shifts", - "Section %d Node %d Zone %d\n", + "Section %d Node %d Zone %d Lastnid %d\n", SECTIONS_SHIFT, NODES_SHIFT, - ZONES_SHIFT); - mminit_dprintk(MMINIT_TRACE, "pageflags_layout_offsets", - "Section %lu Node %lu Zone %lu\n", + ZONES_SHIFT, + LAST_NID_SHIFT); + mminit_dprintk(MMINIT_TRACE, "pageflags_layout_pgshifts", + "Section %lu Node %lu Zone %lu Lastnid %lu\n", (unsigned long)SECTIONS_PGSHIFT, (unsigned long)NODES_PGSHIFT, - (unsigned long)ZONES_PGSHIFT); - mminit_dprintk(MMINIT_TRACE, "pageflags_layout_zoneid", - "Zone ID: %lu -> %lu\n", - (unsigned long)ZONEID_PGOFF, - (unsigned long)(ZONEID_PGOFF + ZONEID_SHIFT)); + (unsigned long)ZONES_PGSHIFT, + (unsigned long)LAST_NID_PGSHIFT); + mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodezoneid", + "Node/Zone ID: %lu -> %lu\n", + (unsigned long)(ZONEID_PGOFF + ZONEID_SHIFT), + (unsigned long)ZONEID_PGOFF); mminit_dprintk(MMINIT_TRACE, "pageflags_layout_usage", - "location: %d -> %d unused %d -> %d flags %d -> %d\n", + "location: %d -> %d layout %d -> %d unused %d -> %d page-flags\n", shift, width, width, NR_PAGEFLAGS, NR_PAGEFLAGS, 0); #ifdef NODE_NOT_IN_PAGE_FLAGS mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodeflags", "Node not in page flags"); #endif +#ifdef LAST_NID_NOT_IN_PAGE_FLAGS + mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodeflags", + "Last nid not in page flags"); +#endif if (SECTIONS_WIDTH) { shift -= SECTIONS_WIDTH; diff --git a/mm/mmap.c b/mm/mmap.c index d1e4124f3d0e..14a681bf31e4 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -143,7 +143,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) */ free -= global_page_state(NR_SHMEM); - free += nr_swap_pages; + free += get_nr_swap_pages(); /* * Any slabs which are created with the @@ -255,6 +255,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) unsigned long newbrk, oldbrk; struct mm_struct *mm = current->mm; unsigned long min_brk; + bool populate; down_write(&mm->mmap_sem); @@ -304,8 +305,15 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) /* Ok, looks good - let it rip. */ if (do_brk(oldbrk, newbrk-oldbrk) != oldbrk) goto out; + set_brk: mm->brk = brk; + populate = newbrk > oldbrk && (mm->def_flags & VM_LOCKED) != 0; + up_write(&mm->mmap_sem); + if (populate) + mm_populate(oldbrk, newbrk - oldbrk); + return brk; + out: retval = mm->brk; up_write(&mm->mmap_sem); @@ -800,7 +808,7 @@ again: remove_next = 1 + (end > next->vm_end); anon_vma_interval_tree_post_update_vma(vma); if (adjust_next) anon_vma_interval_tree_post_update_vma(next); - anon_vma_unlock(anon_vma); + anon_vma_unlock_write(anon_vma); } if (mapping) mutex_unlock(&mapping->i_mmap_mutex); @@ -1153,12 +1161,15 @@ static inline unsigned long round_hint_to_min(unsigned long hint) unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, - unsigned long flags, unsigned long pgoff) + unsigned long flags, unsigned long pgoff, + unsigned long *populate) { struct mm_struct * mm = current->mm; struct inode *inode; vm_flags_t vm_flags; + *populate = 0; + /* * Does the application expect PROT_READ to imply PROT_EXEC? * @@ -1279,7 +1290,24 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, } } - return mmap_region(file, addr, len, flags, vm_flags, pgoff); + /* + * Set 'VM_NORESERVE' if we should not account for the + * memory use of this mapping. + */ + if (flags & MAP_NORESERVE) { + /* We honor MAP_NORESERVE if allowed to overcommit */ + if (sysctl_overcommit_memory != OVERCOMMIT_NEVER) + vm_flags |= VM_NORESERVE; + + /* hugetlb applies strict overcommit unless MAP_NORESERVE */ + if (file && is_file_hugepages(file)) + vm_flags |= VM_NORESERVE; + } + + addr = mmap_region(file, addr, len, vm_flags, pgoff); + if (!IS_ERR_VALUE(addr) && (vm_flags & VM_POPULATE)) + *populate = len; + return addr; } SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len, @@ -1394,8 +1422,7 @@ static inline int accountable_mapping(struct file *file, vm_flags_t vm_flags) } unsigned long mmap_region(struct file *file, unsigned long addr, - unsigned long len, unsigned long flags, - vm_flags_t vm_flags, unsigned long pgoff) + unsigned long len, vm_flags_t vm_flags, unsigned long pgoff) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; @@ -1419,20 +1446,6 @@ munmap_back: return -ENOMEM; /* - * Set 'VM_NORESERVE' if we should not account for the - * memory use of this mapping. - */ - if ((flags & MAP_NORESERVE)) { - /* We honor MAP_NORESERVE if allowed to overcommit */ - if (sysctl_overcommit_memory != OVERCOMMIT_NEVER) - vm_flags |= VM_NORESERVE; - - /* hugetlb applies strict overcommit unless MAP_NORESERVE */ - if (file && is_file_hugepages(file)) - vm_flags |= VM_NORESERVE; - } - - /* * Private writable mapping: check memory availability */ if (accountable_mapping(file, vm_flags)) { @@ -1530,10 +1543,12 @@ out: vm_stat_account(mm, vm_flags, file, len >> PAGE_SHIFT); if (vm_flags & VM_LOCKED) { - if (!mlock_vma_pages_range(vma, addr, addr + len)) + if (!((vm_flags & VM_SPECIAL) || is_vm_hugetlb_page(vma) || + vma == get_gate_vma(current->mm))) mm->locked_vm += (len >> PAGE_SHIFT); - } else if ((flags & MAP_POPULATE) && !(flags & MAP_NONBLOCK)) - make_pages_present(addr, addr + len); + else + vma->vm_flags &= ~VM_LOCKED; + } if (file) uprobe_mmap(vma); @@ -1800,15 +1815,6 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, } #endif -void arch_unmap_area(struct mm_struct *mm, unsigned long addr) -{ - /* - * Is this a new hole at the lowest possible address? - */ - if (addr >= TASK_UNMAPPED_BASE && addr < mm->free_area_cache) - mm->free_area_cache = addr; -} - /* * This mmap-allocator allocates new areas top-down from below the * stack's low limit (the base): @@ -1865,19 +1871,6 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, } #endif -void arch_unmap_area_topdown(struct mm_struct *mm, unsigned long addr) -{ - /* - * Is this a new hole at the highest possible address? - */ - if (addr > mm->free_area_cache) - mm->free_area_cache = addr; - - /* dont allow allocations above current base */ - if (mm->free_area_cache > mm->mmap_base) - mm->free_area_cache = mm->mmap_base; -} - unsigned long get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) @@ -2186,9 +2179,8 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr) return vma; if (!prev || expand_stack(prev, addr)) return NULL; - if (prev->vm_flags & VM_LOCKED) { - mlock_vma_pages_range(prev, addr, prev->vm_end); - } + if (prev->vm_flags & VM_LOCKED) + __mlock_vma_pages_range(prev, addr, prev->vm_end, NULL); return prev; } #else @@ -2214,9 +2206,8 @@ find_extend_vma(struct mm_struct * mm, unsigned long addr) start = vma->vm_start; if (expand_stack(vma, addr)) return NULL; - if (vma->vm_flags & VM_LOCKED) { - mlock_vma_pages_range(vma, addr, start); - } + if (vma->vm_flags & VM_LOCKED) + __mlock_vma_pages_range(vma, addr, start, NULL); return vma; } #endif @@ -2276,7 +2267,6 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma, { struct vm_area_struct **insertion_point; struct vm_area_struct *tail_vma = NULL; - unsigned long addr; insertion_point = (prev ? &prev->vm_next : &mm->mmap); vma->vm_prev = NULL; @@ -2293,11 +2283,6 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma, } else mm->highest_vm_end = prev ? prev->vm_end : 0; tail_vma->vm_next = NULL; - if (mm->unmap_area == arch_unmap_area) - addr = prev ? prev->vm_end : mm->mmap_base; - else - addr = vma ? vma->vm_start : mm->mmap_base; - mm->unmap_area(mm, addr); mm->mmap_cache = NULL; /* Kill the cache. */ } @@ -2589,10 +2574,8 @@ static unsigned long do_brk(unsigned long addr, unsigned long len) out: perf_event_mmap(vma); mm->total_vm += len >> PAGE_SHIFT; - if (flags & VM_LOCKED) { - if (!mlock_vma_pages_range(vma, addr, addr + len)) - mm->locked_vm += (len >> PAGE_SHIFT); - } + if (flags & VM_LOCKED) + mm->locked_vm += (len >> PAGE_SHIFT); return addr; } @@ -2600,10 +2583,14 @@ unsigned long vm_brk(unsigned long addr, unsigned long len) { struct mm_struct *mm = current->mm; unsigned long ret; + bool populate; down_write(&mm->mmap_sem); ret = do_brk(addr, len); + populate = ((mm->def_flags & VM_LOCKED) != 0); up_write(&mm->mmap_sem); + if (populate) + mm_populate(addr, len); return ret; } EXPORT_SYMBOL(vm_brk); @@ -3001,7 +2988,7 @@ static void vm_unlock_anon_vma(struct anon_vma *anon_vma) if (!__test_and_clear_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_node)) BUG(); - anon_vma_unlock(anon_vma); + anon_vma_unlock_write(anon_vma); } } diff --git a/mm/mmu_context.c b/mm/mmu_context.c index 3dcfaf4ed355..8a8cd0265e52 100644 --- a/mm/mmu_context.c +++ b/mm/mmu_context.c @@ -14,9 +14,6 @@ * use_mm * Makes the calling kernel thread take on the specified * mm context. - * Called by the retry thread execute retries within the - * iocb issuer's mm context, so that copy_from/to_user - * operations work seamlessly for aio. * (Note: this routine is intended to be called only * from a kernel thread context) */ diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c index 8a5ac8c686b0..e20e7dce3018 100644 --- a/mm/mmu_notifier.c +++ b/mm/mmu_notifier.c @@ -37,49 +37,51 @@ static struct srcu_struct srcu; void __mmu_notifier_release(struct mm_struct *mm) { struct mmu_notifier *mn; - struct hlist_node *n; int id; /* - * SRCU here will block mmu_notifier_unregister until - * ->release returns. + * srcu_read_lock() here will block synchronize_srcu() in + * mmu_notifier_unregister() until all registered + * ->release() callouts this function makes have + * returned. */ id = srcu_read_lock(&srcu); - hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) - /* - * if ->release runs before mmu_notifier_unregister it - * must be handled as it's the only way for the driver - * to flush all existing sptes and stop the driver - * from establishing any more sptes before all the - * pages in the mm are freed. - */ - if (mn->ops->release) - mn->ops->release(mn, mm); - srcu_read_unlock(&srcu, id); - spin_lock(&mm->mmu_notifier_mm->lock); while (unlikely(!hlist_empty(&mm->mmu_notifier_mm->list))) { mn = hlist_entry(mm->mmu_notifier_mm->list.first, struct mmu_notifier, hlist); + /* - * We arrived before mmu_notifier_unregister so - * mmu_notifier_unregister will do nothing other than - * to wait ->release to finish and - * mmu_notifier_unregister to return. + * Unlink. This will prevent mmu_notifier_unregister() + * from also making the ->release() callout. */ hlist_del_init_rcu(&mn->hlist); + spin_unlock(&mm->mmu_notifier_mm->lock); + + /* + * Clear sptes. (see 'release' description in mmu_notifier.h) + */ + if (mn->ops->release) + mn->ops->release(mn, mm); + + spin_lock(&mm->mmu_notifier_mm->lock); } spin_unlock(&mm->mmu_notifier_mm->lock); /* - * synchronize_srcu here prevents mmu_notifier_release to - * return to exit_mmap (which would proceed freeing all pages - * in the mm) until the ->release method returns, if it was - * invoked by mmu_notifier_unregister. - * - * The mmu_notifier_mm can't go away from under us because one - * mm_count is hold by exit_mmap. + * All callouts to ->release() which we have done are complete. + * Allow synchronize_srcu() in mmu_notifier_unregister() to complete + */ + srcu_read_unlock(&srcu, id); + + /* + * mmu_notifier_unregister() may have unlinked a notifier and may + * still be calling out to it. Additionally, other notifiers + * may have been active via vmtruncate() et. al. Block here + * to ensure that all notifier callouts for this mm have been + * completed and the sptes are really cleaned up before returning + * to exit_mmap(). */ synchronize_srcu(&srcu); } @@ -93,11 +95,10 @@ int __mmu_notifier_clear_flush_young(struct mm_struct *mm, unsigned long address) { struct mmu_notifier *mn; - struct hlist_node *n; int young = 0, id; id = srcu_read_lock(&srcu); - hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) { + hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) { if (mn->ops->clear_flush_young) young |= mn->ops->clear_flush_young(mn, mm, address); } @@ -110,11 +111,10 @@ int __mmu_notifier_test_young(struct mm_struct *mm, unsigned long address) { struct mmu_notifier *mn; - struct hlist_node *n; int young = 0, id; id = srcu_read_lock(&srcu); - hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) { + hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) { if (mn->ops->test_young) { young = mn->ops->test_young(mn, mm, address); if (young) @@ -130,11 +130,10 @@ void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address, pte_t pte) { struct mmu_notifier *mn; - struct hlist_node *n; int id; id = srcu_read_lock(&srcu); - hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) { + hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) { if (mn->ops->change_pte) mn->ops->change_pte(mn, mm, address, pte); } @@ -145,11 +144,10 @@ void __mmu_notifier_invalidate_page(struct mm_struct *mm, unsigned long address) { struct mmu_notifier *mn; - struct hlist_node *n; int id; id = srcu_read_lock(&srcu); - hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) { + hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) { if (mn->ops->invalidate_page) mn->ops->invalidate_page(mn, mm, address); } @@ -160,11 +158,10 @@ void __mmu_notifier_invalidate_range_start(struct mm_struct *mm, unsigned long start, unsigned long end) { struct mmu_notifier *mn; - struct hlist_node *n; int id; id = srcu_read_lock(&srcu); - hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) { + hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) { if (mn->ops->invalidate_range_start) mn->ops->invalidate_range_start(mn, mm, start, end); } @@ -175,11 +172,10 @@ void __mmu_notifier_invalidate_range_end(struct mm_struct *mm, unsigned long start, unsigned long end) { struct mmu_notifier *mn; - struct hlist_node *n; int id; id = srcu_read_lock(&srcu); - hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) { + hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) { if (mn->ops->invalidate_range_end) mn->ops->invalidate_range_end(mn, mm, start, end); } @@ -294,31 +290,31 @@ void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm) { BUG_ON(atomic_read(&mm->mm_count) <= 0); + spin_lock(&mm->mmu_notifier_mm->lock); if (!hlist_unhashed(&mn->hlist)) { - /* - * SRCU here will force exit_mmap to wait ->release to finish - * before freeing the pages. - */ int id; - id = srcu_read_lock(&srcu); /* - * exit_mmap will block in mmu_notifier_release to - * guarantee ->release is called before freeing the - * pages. + * Ensure we synchronize up with __mmu_notifier_release(). */ + id = srcu_read_lock(&srcu); + + hlist_del_rcu(&mn->hlist); + spin_unlock(&mm->mmu_notifier_mm->lock); + if (mn->ops->release) mn->ops->release(mn, mm); - srcu_read_unlock(&srcu, id); - spin_lock(&mm->mmu_notifier_mm->lock); - hlist_del_rcu(&mn->hlist); + /* + * Allow __mmu_notifier_release() to complete. + */ + srcu_read_unlock(&srcu, id); + } else spin_unlock(&mm->mmu_notifier_mm->lock); - } /* - * Wait any running method to finish, of course including - * ->release if it was run by mmu_notifier_relase instead of us. + * Wait for any running method to finish, including ->release() if it + * was run by __mmu_notifier_release() instead of us. */ synchronize_srcu(&srcu); diff --git a/mm/mmzone.c b/mm/mmzone.c index 4596d81b89b1..2ac0afbd68f3 100644 --- a/mm/mmzone.c +++ b/mm/mmzone.c @@ -1,7 +1,7 @@ /* * linux/mm/mmzone.c * - * management codes for pgdats and zones. + * management codes for pgdats, zones and page flags */ @@ -96,3 +96,21 @@ void lruvec_init(struct lruvec *lruvec) for_each_lru(lru) INIT_LIST_HEAD(&lruvec->lists[lru]); } + +#if defined(CONFIG_NUMA_BALANCING) && !defined(LAST_NID_NOT_IN_PAGE_FLAGS) +int page_nid_xchg_last(struct page *page, int nid) +{ + unsigned long old_flags, flags; + int last_nid; + + do { + old_flags = flags = page->flags; + last_nid = page_nid_last(page); + + flags &= ~(LAST_NID_MASK << LAST_NID_PGSHIFT); + flags |= (nid & LAST_NID_MASK) << LAST_NID_PGSHIFT; + } while (unlikely(cmpxchg(&page->flags, old_flags, flags) != old_flags)); + + return last_nid; +} +#endif diff --git a/mm/mremap.c b/mm/mremap.c index e1031e1f6a61..38fffd89e27e 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -134,7 +134,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, pte_unmap(new_pte - 1); pte_unmap_unlock(old_pte - 1, old_ptl); if (anon_vma) - anon_vma_unlock(anon_vma); + anon_vma_unlock_write(anon_vma); if (mapping) mutex_unlock(&mapping->i_mmap_mutex); } @@ -208,7 +208,7 @@ unsigned long move_page_tables(struct vm_area_struct *vma, static unsigned long move_vma(struct vm_area_struct *vma, unsigned long old_addr, unsigned long old_len, - unsigned long new_len, unsigned long new_addr) + unsigned long new_len, unsigned long new_addr, bool *locked) { struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *new_vma; @@ -299,9 +299,7 @@ static unsigned long move_vma(struct vm_area_struct *vma, if (vm_flags & VM_LOCKED) { mm->locked_vm += new_len >> PAGE_SHIFT; - if (new_len > old_len) - mlock_vma_pages_range(new_vma, new_addr + old_len, - new_addr + new_len); + *locked = true; } return new_addr; @@ -366,9 +364,8 @@ Eagain: return ERR_PTR(-EAGAIN); } -static unsigned long mremap_to(unsigned long addr, - unsigned long old_len, unsigned long new_addr, - unsigned long new_len) +static unsigned long mremap_to(unsigned long addr, unsigned long old_len, + unsigned long new_addr, unsigned long new_len, bool *locked) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; @@ -418,7 +415,7 @@ static unsigned long mremap_to(unsigned long addr, if (ret & ~PAGE_MASK) goto out1; - ret = move_vma(vma, addr, old_len, new_len, new_addr); + ret = move_vma(vma, addr, old_len, new_len, new_addr, locked); if (!(ret & ~PAGE_MASK)) goto out; out1: @@ -456,6 +453,7 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, struct vm_area_struct *vma; unsigned long ret = -EINVAL; unsigned long charged = 0; + bool locked = false; down_write(¤t->mm->mmap_sem); @@ -478,7 +476,8 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, if (flags & MREMAP_FIXED) { if (flags & MREMAP_MAYMOVE) - ret = mremap_to(addr, old_len, new_addr, new_len); + ret = mremap_to(addr, old_len, new_addr, new_len, + &locked); goto out; } @@ -520,8 +519,8 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, vm_stat_account(mm, vma->vm_flags, vma->vm_file, pages); if (vma->vm_flags & VM_LOCKED) { mm->locked_vm += pages; - mlock_vma_pages_range(vma, addr + old_len, - addr + new_len); + locked = true; + new_addr = addr; } ret = addr; goto out; @@ -547,11 +546,13 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, goto out; } - ret = move_vma(vma, addr, old_len, new_len, new_addr); + ret = move_vma(vma, addr, old_len, new_len, new_addr, &locked); } out: if (ret & ~PAGE_MASK) vm_unacct_memory(charged); up_write(¤t->mm->mmap_sem); + if (locked && new_len > old_len) + mm_populate(new_addr + old_len, new_len - old_len); return ret; } diff --git a/mm/nommu.c b/mm/nommu.c index 79c3cac87afa..94b170a8ccc7 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1249,7 +1249,8 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long len, unsigned long prot, unsigned long flags, - unsigned long pgoff) + unsigned long pgoff, + unsigned long *populate) { struct vm_area_struct *vma; struct vm_region *region; @@ -1259,6 +1260,8 @@ unsigned long do_mmap_pgoff(struct file *file, kenter(",%lx,%lx,%lx,%lx,%lx", addr, len, prot, flags, pgoff); + *populate = 0; + /* decide whether we should attempt the mapping, and if so what sort of * mapping */ ret = validate_mmap_request(file, addr, len, prot, flags, pgoff, @@ -1852,10 +1855,6 @@ unsigned long arch_get_unmapped_area(struct file *file, unsigned long addr, return -ENOMEM; } -void arch_unmap_area(struct mm_struct *mm, unsigned long addr) -{ -} - void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows) @@ -1903,7 +1902,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) */ free -= global_page_state(NR_SHMEM); - free += nr_swap_pages; + free += get_nr_swap_pages(); /* * Any slabs which are created with the diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 0399f146ae49..79e451a78c9e 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -386,8 +386,10 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order, cpuset_print_task_mems_allowed(current); task_unlock(current); dump_stack(); - mem_cgroup_print_oom_info(memcg, p); - show_mem(SHOW_MEM_FILTER_NODES); + if (memcg) + mem_cgroup_print_oom_info(memcg, p); + else + show_mem(SHOW_MEM_FILTER_NODES); if (sysctl_oom_dump_tasks) dump_tasks(memcg, nodemask); } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 437052241f93..611ddf66293c 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -240,6 +240,9 @@ static unsigned long global_dirtyable_memory(void) if (!vm_highmem_is_dirtyable) x -= highmem_dirtyable_memory(x); + /* Subtract min_free_kbytes */ + x -= min_t(unsigned long, x, min_free_kbytes >> (PAGE_SHIFT - 10)); + return x + 1; /* Ensure that we never return 0 */ } @@ -2291,3 +2294,27 @@ int mapping_tagged(struct address_space *mapping, int tag) return radix_tree_tagged(&mapping->page_tree, tag); } EXPORT_SYMBOL(mapping_tagged); + +/** + * wait_for_stable_page() - wait for writeback to finish, if necessary. + * @page: The page to wait on. + * + * This function determines if the given page is related to a backing device + * that requires page contents to be held stable during writeback. If so, then + * it will wait for any pending writeback to complete. + */ +void wait_for_stable_page(struct page *page) +{ + struct address_space *mapping = page_mapping(page); + struct backing_dev_info *bdi = mapping->backing_dev_info; + + if (!bdi_cap_stable_pages_required(bdi)) + return; +#ifdef CONFIG_NEED_BOUNCE_POOL + if (mapping->host->i_sb->s_flags & MS_SNAP_STABLE) + return; +#endif /* CONFIG_NEED_BOUNCE_POOL */ + + wait_on_page_writeback(page); +} +EXPORT_SYMBOL_GPL(wait_for_stable_page); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index de1fdef2f0fd..d2a08c138cdc 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -201,11 +201,18 @@ static unsigned long __meminitdata nr_all_pages; static unsigned long __meminitdata dma_reserve; #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP +/* Movable memory ranges, will also be used by memblock subsystem. */ +struct movablemem_map movablemem_map = { + .acpi = false, + .nr_map = 0, +}; + static unsigned long __meminitdata arch_zone_lowest_possible_pfn[MAX_NR_ZONES]; static unsigned long __meminitdata arch_zone_highest_possible_pfn[MAX_NR_ZONES]; static unsigned long __initdata required_kernelcore; static unsigned long __initdata required_movablecore; static unsigned long __meminitdata zone_movable_pfn[MAX_NUMNODES]; +static unsigned long __meminitdata zone_movable_limit[MAX_NUMNODES]; /* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */ int movable_zone; @@ -239,15 +246,20 @@ static int page_outside_zone_boundaries(struct zone *zone, struct page *page) int ret = 0; unsigned seq; unsigned long pfn = page_to_pfn(page); + unsigned long sp, start_pfn; do { seq = zone_span_seqbegin(zone); - if (pfn >= zone->zone_start_pfn + zone->spanned_pages) - ret = 1; - else if (pfn < zone->zone_start_pfn) + start_pfn = zone->zone_start_pfn; + sp = zone->spanned_pages; + if (!zone_spans_pfn(zone, pfn)) ret = 1; } while (zone_span_seqretry(zone, seq)); + if (ret) + pr_err("page %lu outside zone [ %lu - %lu ]\n", + pfn, start_pfn, start_pfn + sp); + return ret; } @@ -287,7 +299,7 @@ static void bad_page(struct page *page) /* Don't complain about poisoned pages */ if (PageHWPoison(page)) { - reset_page_mapcount(page); /* remove PageBuddy */ + page_mapcount_reset(page); /* remove PageBuddy */ return; } @@ -319,7 +331,7 @@ static void bad_page(struct page *page) dump_stack(); out: /* Leave bad fields for debug, except PageBuddy could make trouble */ - reset_page_mapcount(page); /* remove PageBuddy */ + page_mapcount_reset(page); /* remove PageBuddy */ add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } @@ -532,6 +544,8 @@ static inline void __free_one_page(struct page *page, unsigned long uninitialized_var(buddy_idx); struct page *buddy; + VM_BUG_ON(!zone_is_initialized(zone)); + if (unlikely(PageCompound(page))) if (unlikely(destroy_compound_page(page, order))) return; @@ -605,7 +619,7 @@ static inline int free_pages_check(struct page *page) bad_page(page); return 1; } - reset_page_last_nid(page); + page_nid_reset_last(page); if (page->flags & PAGE_FLAGS_CHECK_AT_PREP) page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; return 0; @@ -665,7 +679,7 @@ static void free_pcppages_bulk(struct zone *zone, int count, /* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */ __free_one_page(page, zone, 0, mt); trace_mm_page_pcpu_drain(page, 0, mt); - if (likely(get_pageblock_migratetype(page) != MIGRATE_ISOLATE)) { + if (likely(!is_migrate_isolate_page(page))) { __mod_zone_page_state(zone, NR_FREE_PAGES, 1); if (is_migrate_cma(mt)) __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, 1); @@ -683,7 +697,7 @@ static void free_one_page(struct zone *zone, struct page *page, int order, zone->pages_scanned = 0; __free_one_page(page, zone, order, migratetype); - if (unlikely(migratetype != MIGRATE_ISOLATE)) + if (unlikely(!is_migrate_isolate(migratetype))) __mod_zone_freepage_state(zone, 1 << order, migratetype); spin_unlock(&zone->lock); } @@ -915,7 +929,9 @@ static int fallbacks[MIGRATE_TYPES][4] = { [MIGRATE_MOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE }, #endif [MIGRATE_RESERVE] = { MIGRATE_RESERVE }, /* Never used */ +#ifdef CONFIG_MEMORY_ISOLATION [MIGRATE_ISOLATE] = { MIGRATE_RESERVE }, /* Never used */ +#endif }; /* @@ -980,9 +996,9 @@ int move_freepages_block(struct zone *zone, struct page *page, end_pfn = start_pfn + pageblock_nr_pages - 1; /* Do not cross zone boundaries */ - if (start_pfn < zone->zone_start_pfn) + if (!zone_spans_pfn(zone, start_pfn)) start_page = page; - if (end_pfn >= zone->zone_start_pfn + zone->spanned_pages) + if (!zone_spans_pfn(zone, end_pfn)) return 0; return move_freepages(zone, start_page, end_page, migratetype); @@ -1141,7 +1157,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, list_add_tail(&page->lru, list); if (IS_ENABLED(CONFIG_CMA)) { mt = get_pageblock_migratetype(page); - if (!is_migrate_cma(mt) && mt != MIGRATE_ISOLATE) + if (!is_migrate_cma(mt) && !is_migrate_isolate(mt)) mt = migratetype; } set_freepage_migratetype(page, mt); @@ -1276,7 +1292,7 @@ void mark_free_pages(struct zone *zone) spin_lock_irqsave(&zone->lock, flags); - max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages; + max_zone_pfn = zone_end_pfn(zone); for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) if (pfn_valid(pfn)) { struct page *page = pfn_to_page(pfn); @@ -1325,7 +1341,7 @@ void free_hot_cold_page(struct page *page, int cold) * excessively into the page allocator */ if (migratetype >= MIGRATE_PCPTYPES) { - if (unlikely(migratetype == MIGRATE_ISOLATE)) { + if (unlikely(is_migrate_isolate(migratetype))) { free_one_page(zone, page, 0, migratetype); goto out; } @@ -1399,7 +1415,7 @@ static int __isolate_free_page(struct page *page, unsigned int order) zone = page_zone(page); mt = get_pageblock_migratetype(page); - if (mt != MIGRATE_ISOLATE) { + if (!is_migrate_isolate(mt)) { /* Obey watermarks as if the page was being allocated */ watermark = low_wmark_pages(zone) + (1 << order); if (!zone_watermark_ok(zone, 0, watermark, 0, 0)) @@ -1418,7 +1434,7 @@ static int __isolate_free_page(struct page *page, unsigned int order) struct page *endpage = page + (1 << order) - 1; for (; page < endpage; page += pageblock_nr_pages) { int mt = get_pageblock_migratetype(page); - if (mt != MIGRATE_ISOLATE && !is_migrate_cma(mt)) + if (!is_migrate_isolate(mt) && !is_migrate_cma(mt)) set_pageblock_migratetype(page, MIGRATE_MOVABLE); } @@ -2614,10 +2630,17 @@ retry_cpuset: page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order, zonelist, high_zoneidx, alloc_flags, preferred_zone, migratetype); - if (unlikely(!page)) + if (unlikely(!page)) { + /* + * Runtime PM, block IO and its error handling path + * can deadlock because I/O on the device might not + * complete. + */ + gfp_mask = memalloc_noio_flags(gfp_mask); page = __alloc_pages_slowpath(gfp_mask, order, zonelist, high_zoneidx, nodemask, preferred_zone, migratetype); + } trace_mm_page_alloc(page, order, gfp_mask, migratetype); @@ -2789,18 +2812,18 @@ void free_pages_exact(void *virt, size_t size) } EXPORT_SYMBOL(free_pages_exact); -static unsigned int nr_free_zone_pages(int offset) +static unsigned long nr_free_zone_pages(int offset) { struct zoneref *z; struct zone *zone; /* Just pick one node, since fallback list is circular */ - unsigned int sum = 0; + unsigned long sum = 0; struct zonelist *zonelist = node_zonelist(numa_node_id(), GFP_KERNEL); for_each_zone_zonelist(zone, z, zonelist, offset) { - unsigned long size = zone->present_pages; + unsigned long size = zone->managed_pages; unsigned long high = high_wmark_pages(zone); if (size > high) sum += size - high; @@ -2812,7 +2835,7 @@ static unsigned int nr_free_zone_pages(int offset) /* * Amount of free RAM allocatable within ZONE_DMA and ZONE_NORMAL */ -unsigned int nr_free_buffer_pages(void) +unsigned long nr_free_buffer_pages(void) { return nr_free_zone_pages(gfp_zone(GFP_USER)); } @@ -2821,7 +2844,7 @@ EXPORT_SYMBOL_GPL(nr_free_buffer_pages); /* * Amount of free RAM allocatable within all zones */ -unsigned int nr_free_pagecache_pages(void) +unsigned long nr_free_pagecache_pages(void) { return nr_free_zone_pages(gfp_zone(GFP_HIGHUSER_MOVABLE)); } @@ -2853,7 +2876,7 @@ void si_meminfo_node(struct sysinfo *val, int nid) val->totalram = pgdat->node_present_pages; val->freeram = node_page_state(nid, NR_FREE_PAGES); #ifdef CONFIG_HIGHMEM - val->totalhigh = pgdat->node_zones[ZONE_HIGHMEM].present_pages; + val->totalhigh = pgdat->node_zones[ZONE_HIGHMEM].managed_pages; val->freehigh = zone_page_state(&pgdat->node_zones[ZONE_HIGHMEM], NR_FREE_PAGES); #else @@ -2896,7 +2919,9 @@ static void show_migration_types(unsigned char type) #ifdef CONFIG_CMA [MIGRATE_CMA] = 'C', #endif +#ifdef CONFIG_MEMORY_ISOLATION [MIGRATE_ISOLATE] = 'I', +#endif }; char tmp[MIGRATE_TYPES + 1]; char *p = tmp; @@ -3235,7 +3260,7 @@ static int find_next_best_node(int node, nodemask_t *used_node_mask) { int n, val; int min_val = INT_MAX; - int best_node = -1; + int best_node = NUMA_NO_NODE; const struct cpumask *tmp = cpumask_of_node(0); /* Use the local node if we haven't already */ @@ -3779,7 +3804,7 @@ static void setup_zone_migrate_reserve(struct zone *zone) * the block. */ start_pfn = zone->zone_start_pfn; - end_pfn = start_pfn + zone->spanned_pages; + end_pfn = zone_end_pfn(zone); start_pfn = roundup(start_pfn, pageblock_nr_pages); reserve = roundup(min_wmark_pages(zone), pageblock_nr_pages) >> pageblock_order; @@ -3866,8 +3891,11 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, * exist on hotplugged memory. */ if (context == MEMMAP_EARLY) { - if (!early_pfn_valid(pfn)) + if (!early_pfn_valid(pfn)) { + pfn = ALIGN(pfn + MAX_ORDER_NR_PAGES, + MAX_ORDER_NR_PAGES) - 1; continue; + } if (!early_pfn_in_nid(pfn, nid)) continue; } @@ -3875,8 +3903,8 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, set_page_links(page, zone, nid, pfn); mminit_verify_page_links(page, zone, nid, pfn); init_page_count(page); - reset_page_mapcount(page); - reset_page_last_nid(page); + page_mapcount_reset(page); + page_nid_reset_last(page); SetPageReserved(page); /* * Mark the block movable so that blocks are reserved for @@ -3893,7 +3921,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, * pfn out of zone. */ if ((z->zone_start_pfn <= pfn) - && (pfn < z->zone_start_pfn + z->spanned_pages) + && (pfn < zone_end_pfn(z)) && !(pfn & (pageblock_nr_pages - 1))) set_pageblock_migratetype(page, MIGRATE_MOVABLE); @@ -3931,7 +3959,7 @@ static int __meminit zone_batchsize(struct zone *zone) * * OK, so we don't know how big the cache is. So guess. */ - batch = zone->present_pages / 1024; + batch = zone->managed_pages / 1024; if (batch * PAGE_SIZE > 512 * 1024) batch = (512 * 1024) / PAGE_SIZE; batch /= 4; /* We effectively *= 4 below */ @@ -4015,7 +4043,7 @@ static void __meminit setup_zone_pageset(struct zone *zone) if (percpu_pagelist_fraction) setup_pagelist_highmark(pcp, - (zone->present_pages / + (zone->managed_pages / percpu_pagelist_fraction)); } } @@ -4371,6 +4399,77 @@ static unsigned long __meminit zone_absent_pages_in_node(int nid, return __absent_pages_in_range(nid, zone_start_pfn, zone_end_pfn); } +/** + * sanitize_zone_movable_limit - Sanitize the zone_movable_limit array. + * + * zone_movable_limit is initialized as 0. This function will try to get + * the first ZONE_MOVABLE pfn of each node from movablemem_map, and + * assigne them to zone_movable_limit. + * zone_movable_limit[nid] == 0 means no limit for the node. + * + * Note: Each range is represented as [start_pfn, end_pfn) + */ +static void __meminit sanitize_zone_movable_limit(void) +{ + int map_pos = 0, i, nid; + unsigned long start_pfn, end_pfn; + + if (!movablemem_map.nr_map) + return; + + /* Iterate all ranges from minimum to maximum */ + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { + /* + * If we have found lowest pfn of ZONE_MOVABLE of the node + * specified by user, just go on to check next range. + */ + if (zone_movable_limit[nid]) + continue; + +#ifdef CONFIG_ZONE_DMA + /* Skip DMA memory. */ + if (start_pfn < arch_zone_highest_possible_pfn[ZONE_DMA]) + start_pfn = arch_zone_highest_possible_pfn[ZONE_DMA]; +#endif + +#ifdef CONFIG_ZONE_DMA32 + /* Skip DMA32 memory. */ + if (start_pfn < arch_zone_highest_possible_pfn[ZONE_DMA32]) + start_pfn = arch_zone_highest_possible_pfn[ZONE_DMA32]; +#endif + +#ifdef CONFIG_HIGHMEM + /* Skip lowmem if ZONE_MOVABLE is highmem. */ + if (zone_movable_is_highmem() && + start_pfn < arch_zone_lowest_possible_pfn[ZONE_HIGHMEM]) + start_pfn = arch_zone_lowest_possible_pfn[ZONE_HIGHMEM]; +#endif + + if (start_pfn >= end_pfn) + continue; + + while (map_pos < movablemem_map.nr_map) { + if (end_pfn <= movablemem_map.map[map_pos].start_pfn) + break; + + if (start_pfn >= movablemem_map.map[map_pos].end_pfn) { + map_pos++; + continue; + } + + /* + * The start_pfn of ZONE_MOVABLE is either the minimum + * pfn specified by movablemem_map, or 0, which means + * the node has no ZONE_MOVABLE. + */ + zone_movable_limit[nid] = max(start_pfn, + movablemem_map.map[map_pos].start_pfn); + + break; + } + } +} + #else /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ static inline unsigned long __meminit zone_spanned_pages_in_node(int nid, unsigned long zone_type, @@ -4388,7 +4487,6 @@ static inline unsigned long __meminit zone_absent_pages_in_node(int nid, return zholes_size[zone_type]; } - #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ static void __meminit calculate_node_totalpages(struct pglist_data *pgdat, @@ -4569,7 +4667,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat, nr_all_pages += freesize; zone->spanned_pages = size; - zone->present_pages = freesize; + zone->present_pages = realsize; /* * Set an approximate value for lowmem here, it will be adjusted * when the bootmem allocator frees pages into the buddy system. @@ -4621,7 +4719,7 @@ static void __init_refok alloc_node_mem_map(struct pglist_data *pgdat) * for the buddy allocator to function correctly. */ start = pgdat->node_start_pfn & ~(MAX_ORDER_NR_PAGES - 1); - end = pgdat->node_start_pfn + pgdat->node_spanned_pages; + end = pgdat_end_pfn(pgdat); end = ALIGN(end, MAX_ORDER_NR_PAGES); size = (end - start) * sizeof(struct page); map = alloc_remap(pgdat->node_id, size); @@ -4827,12 +4925,19 @@ static void __init find_zone_movable_pfns_for_nodes(void) required_kernelcore = max(required_kernelcore, corepages); } - /* If kernelcore was not specified, there is no ZONE_MOVABLE */ - if (!required_kernelcore) + /* + * If neither kernelcore/movablecore nor movablemem_map is specified, + * there is no ZONE_MOVABLE. But if movablemem_map is specified, the + * start pfn of ZONE_MOVABLE has been stored in zone_movable_limit[]. + */ + if (!required_kernelcore) { + if (movablemem_map.nr_map) + memcpy(zone_movable_pfn, zone_movable_limit, + sizeof(zone_movable_pfn)); goto out; + } /* usable_startpfn is the lowest possible pfn ZONE_MOVABLE can be at */ - find_usable_zone_for_movable(); usable_startpfn = arch_zone_lowest_possible_pfn[movable_zone]; restart: @@ -4860,10 +4965,24 @@ restart: for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) { unsigned long size_pages; + /* + * Find more memory for kernelcore in + * [zone_movable_pfn[nid], zone_movable_limit[nid]). + */ start_pfn = max(start_pfn, zone_movable_pfn[nid]); if (start_pfn >= end_pfn) continue; + if (zone_movable_limit[nid]) { + end_pfn = min(end_pfn, zone_movable_limit[nid]); + /* No range left for kernelcore in this node */ + if (start_pfn >= end_pfn) { + zone_movable_pfn[nid] = + zone_movable_limit[nid]; + break; + } + } + /* Account for what is only usable for kernelcore */ if (start_pfn < usable_startpfn) { unsigned long kernel_pages; @@ -4923,12 +5042,12 @@ restart: if (usable_nodes && required_kernelcore > usable_nodes) goto restart; +out: /* Align start of ZONE_MOVABLE on all nids to MAX_ORDER_NR_PAGES */ for (nid = 0; nid < MAX_NUMNODES; nid++) zone_movable_pfn[nid] = roundup(zone_movable_pfn[nid], MAX_ORDER_NR_PAGES); -out: /* restore the node_state */ node_states[N_MEMORY] = saved_node_state; } @@ -4991,6 +5110,8 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn) /* Find the PFNs that ZONE_MOVABLE begins at in each node */ memset(zone_movable_pfn, 0, sizeof(zone_movable_pfn)); + find_usable_zone_for_movable(); + sanitize_zone_movable_limit(); find_zone_movable_pfns_for_nodes(); /* Print out the zone ranges */ @@ -5074,6 +5195,181 @@ static int __init cmdline_parse_movablecore(char *p) early_param("kernelcore", cmdline_parse_kernelcore); early_param("movablecore", cmdline_parse_movablecore); +/** + * movablemem_map_overlap() - Check if a range overlaps movablemem_map.map[]. + * @start_pfn: start pfn of the range to be checked + * @end_pfn: end pfn of the range to be checked (exclusive) + * + * This function checks if a given memory range [start_pfn, end_pfn) overlaps + * the movablemem_map.map[] array. + * + * Return: index of the first overlapped element in movablemem_map.map[] + * or -1 if they don't overlap each other. + */ +int __init movablemem_map_overlap(unsigned long start_pfn, + unsigned long end_pfn) +{ + int overlap; + + if (!movablemem_map.nr_map) + return -1; + + for (overlap = 0; overlap < movablemem_map.nr_map; overlap++) + if (start_pfn < movablemem_map.map[overlap].end_pfn) + break; + + if (overlap == movablemem_map.nr_map || + end_pfn <= movablemem_map.map[overlap].start_pfn) + return -1; + + return overlap; +} + +/** + * insert_movablemem_map - Insert a memory range in to movablemem_map.map. + * @start_pfn: start pfn of the range + * @end_pfn: end pfn of the range + * + * This function will also merge the overlapped ranges, and sort the array + * by start_pfn in monotonic increasing order. + */ +void __init insert_movablemem_map(unsigned long start_pfn, + unsigned long end_pfn) +{ + int pos, overlap; + + /* + * pos will be at the 1st overlapped range, or the position + * where the element should be inserted. + */ + for (pos = 0; pos < movablemem_map.nr_map; pos++) + if (start_pfn <= movablemem_map.map[pos].end_pfn) + break; + + /* If there is no overlapped range, just insert the element. */ + if (pos == movablemem_map.nr_map || + end_pfn < movablemem_map.map[pos].start_pfn) { + /* + * If pos is not the end of array, we need to move all + * the rest elements backward. + */ + if (pos < movablemem_map.nr_map) + memmove(&movablemem_map.map[pos+1], + &movablemem_map.map[pos], + sizeof(struct movablemem_entry) * + (movablemem_map.nr_map - pos)); + movablemem_map.map[pos].start_pfn = start_pfn; + movablemem_map.map[pos].end_pfn = end_pfn; + movablemem_map.nr_map++; + return; + } + + /* overlap will be at the last overlapped range */ + for (overlap = pos + 1; overlap < movablemem_map.nr_map; overlap++) + if (end_pfn < movablemem_map.map[overlap].start_pfn) + break; + + /* + * If there are more ranges overlapped, we need to merge them, + * and move the rest elements forward. + */ + overlap--; + movablemem_map.map[pos].start_pfn = min(start_pfn, + movablemem_map.map[pos].start_pfn); + movablemem_map.map[pos].end_pfn = max(end_pfn, + movablemem_map.map[overlap].end_pfn); + + if (pos != overlap && overlap + 1 != movablemem_map.nr_map) + memmove(&movablemem_map.map[pos+1], + &movablemem_map.map[overlap+1], + sizeof(struct movablemem_entry) * + (movablemem_map.nr_map - overlap - 1)); + + movablemem_map.nr_map -= overlap - pos; +} + +/** + * movablemem_map_add_region - Add a memory range into movablemem_map. + * @start: physical start address of range + * @end: physical end address of range + * + * This function transform the physical address into pfn, and then add the + * range into movablemem_map by calling insert_movablemem_map(). + */ +static void __init movablemem_map_add_region(u64 start, u64 size) +{ + unsigned long start_pfn, end_pfn; + + /* In case size == 0 or start + size overflows */ + if (start + size <= start) + return; + + if (movablemem_map.nr_map >= ARRAY_SIZE(movablemem_map.map)) { + pr_err("movablemem_map: too many entries;" + " ignoring [mem %#010llx-%#010llx]\n", + (unsigned long long) start, + (unsigned long long) (start + size - 1)); + return; + } + + start_pfn = PFN_DOWN(start); + end_pfn = PFN_UP(start + size); + insert_movablemem_map(start_pfn, end_pfn); +} + +/* + * cmdline_parse_movablemem_map - Parse boot option movablemem_map. + * @p: The boot option of the following format: + * movablemem_map=nn[KMG]@ss[KMG] + * + * This option sets the memory range [ss, ss+nn) to be used as movable memory. + * + * Return: 0 on success or -EINVAL on failure. + */ +static int __init cmdline_parse_movablemem_map(char *p) +{ + char *oldp; + u64 start_at, mem_size; + + if (!p) + goto err; + + if (!strcmp(p, "acpi")) + movablemem_map.acpi = true; + + /* + * If user decide to use info from BIOS, all the other user specified + * ranges will be ingored. + */ + if (movablemem_map.acpi) { + if (movablemem_map.nr_map) { + memset(movablemem_map.map, 0, + sizeof(struct movablemem_entry) + * movablemem_map.nr_map); + movablemem_map.nr_map = 0; + } + return 0; + } + + oldp = p; + mem_size = memparse(p, &p); + if (p == oldp) + goto err; + + if (*p == '@') { + oldp = ++p; + start_at = memparse(p, &p); + if (p == oldp || *p != '\0') + goto err; + + movablemem_map_add_region(start_at, mem_size); + return 0; + } +err: + return -EINVAL; +} +early_param("movablemem_map", cmdline_parse_movablemem_map); + #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ /** @@ -5156,8 +5452,8 @@ static void calculate_totalreserve_pages(void) /* we treat the high watermark as reserved pages. */ max += high_wmark_pages(zone); - if (max > zone->present_pages) - max = zone->present_pages; + if (max > zone->managed_pages) + max = zone->managed_pages; reserve_pages += max; /* * Lowmem reserves are not available to @@ -5189,7 +5485,7 @@ static void setup_per_zone_lowmem_reserve(void) for_each_online_pgdat(pgdat) { for (j = 0; j < MAX_NR_ZONES; j++) { struct zone *zone = pgdat->node_zones + j; - unsigned long present_pages = zone->present_pages; + unsigned long managed_pages = zone->managed_pages; zone->lowmem_reserve[j] = 0; @@ -5203,9 +5499,9 @@ static void setup_per_zone_lowmem_reserve(void) sysctl_lowmem_reserve_ratio[idx] = 1; lower_zone = pgdat->node_zones + idx; - lower_zone->lowmem_reserve[j] = present_pages / + lower_zone->lowmem_reserve[j] = managed_pages / sysctl_lowmem_reserve_ratio[idx]; - present_pages += lower_zone->present_pages; + managed_pages += lower_zone->managed_pages; } } } @@ -5224,14 +5520,14 @@ static void __setup_per_zone_wmarks(void) /* Calculate total number of !ZONE_HIGHMEM pages */ for_each_zone(zone) { if (!is_highmem(zone)) - lowmem_pages += zone->present_pages; + lowmem_pages += zone->managed_pages; } for_each_zone(zone) { u64 tmp; spin_lock_irqsave(&zone->lock, flags); - tmp = (u64)pages_min * zone->present_pages; + tmp = (u64)pages_min * zone->managed_pages; do_div(tmp, lowmem_pages); if (is_highmem(zone)) { /* @@ -5243,13 +5539,10 @@ static void __setup_per_zone_wmarks(void) * deltas controls asynch page reclaim, and so should * not be capped for highmem. */ - int min_pages; + unsigned long min_pages; - min_pages = zone->present_pages / 1024; - if (min_pages < SWAP_CLUSTER_MAX) - min_pages = SWAP_CLUSTER_MAX; - if (min_pages > 128) - min_pages = 128; + min_pages = zone->managed_pages / 1024; + min_pages = clamp(min_pages, SWAP_CLUSTER_MAX, 128UL); zone->watermark[WMARK_MIN] = min_pages; } else { /* @@ -5310,7 +5603,7 @@ static void __meminit calculate_zone_inactive_ratio(struct zone *zone) unsigned int gb, ratio; /* Zone size in gigabytes */ - gb = zone->present_pages >> (30 - PAGE_SHIFT); + gb = zone->managed_pages >> (30 - PAGE_SHIFT); if (gb) ratio = int_sqrt(10 * gb); else @@ -5396,7 +5689,7 @@ int sysctl_min_unmapped_ratio_sysctl_handler(ctl_table *table, int write, return rc; for_each_zone(zone) - zone->min_unmapped_pages = (zone->present_pages * + zone->min_unmapped_pages = (zone->managed_pages * sysctl_min_unmapped_ratio) / 100; return 0; } @@ -5412,7 +5705,7 @@ int sysctl_min_slab_ratio_sysctl_handler(ctl_table *table, int write, return rc; for_each_zone(zone) - zone->min_slab_pages = (zone->present_pages * + zone->min_slab_pages = (zone->managed_pages * sysctl_min_slab_ratio) / 100; return 0; } @@ -5454,7 +5747,7 @@ int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write, for_each_populated_zone(zone) { for_each_possible_cpu(cpu) { unsigned long high; - high = zone->present_pages / percpu_pagelist_fraction; + high = zone->managed_pages / percpu_pagelist_fraction; setup_pagelist_highmark( per_cpu_ptr(zone->pageset, cpu), high); } @@ -5641,8 +5934,7 @@ void set_pageblock_flags_group(struct page *page, unsigned long flags, pfn = page_to_pfn(page); bitmap = get_pageblock_bitmap(zone, pfn); bitidx = pfn_to_bitidx(zone, pfn); - VM_BUG_ON(pfn < zone->zone_start_pfn); - VM_BUG_ON(pfn >= zone->zone_start_pfn + zone->spanned_pages); + VM_BUG_ON(!zone_spans_pfn(zone, pfn)); for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1) if (flags & value) @@ -5740,8 +6032,7 @@ bool is_pageblock_removable_nolock(struct page *page) zone = page_zone(page); pfn = page_to_pfn(page); - if (zone->zone_start_pfn > pfn || - zone->zone_start_pfn + zone->spanned_pages <= pfn) + if (!zone_spans_pfn(zone, pfn)) return false; return !has_unmovable_pages(zone, page, 0, true); @@ -5797,14 +6088,14 @@ static int __alloc_contig_migrate_range(struct compact_control *cc, &cc->migratepages); cc->nr_migratepages -= nr_reclaimed; - ret = migrate_pages(&cc->migratepages, - alloc_migrate_target, - 0, false, MIGRATE_SYNC, - MR_CMA); + ret = migrate_pages(&cc->migratepages, alloc_migrate_target, + 0, MIGRATE_SYNC, MR_CMA); } - - putback_movable_pages(&cc->migratepages); - return ret > 0 ? 0 : ret; + if (ret < 0) { + putback_movable_pages(&cc->migratepages); + return ret; + } + return 0; } /** diff --git a/mm/page_io.c b/mm/page_io.c index 78eee32ee486..c535d395a440 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -20,6 +20,7 @@ #include <linux/buffer_head.h> #include <linux/writeback.h> #include <linux/frontswap.h> +#include <linux/aio.h> #include <asm/pgtable.h> static struct bio *get_swap_bio(gfp_t gfp_flags, diff --git a/mm/rmap.c b/mm/rmap.c index 2c78f8cadc95..92b4529ad541 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -105,7 +105,7 @@ static inline void anon_vma_free(struct anon_vma *anon_vma) */ if (rwsem_is_locked(&anon_vma->root->rwsem)) { anon_vma_lock_write(anon_vma); - anon_vma_unlock(anon_vma); + anon_vma_unlock_write(anon_vma); } kmem_cache_free(anon_vma_cachep, anon_vma); @@ -191,7 +191,7 @@ int anon_vma_prepare(struct vm_area_struct *vma) avc = NULL; } spin_unlock(&mm->page_table_lock); - anon_vma_unlock(anon_vma); + anon_vma_unlock_write(anon_vma); if (unlikely(allocated)) put_anon_vma(allocated); @@ -308,7 +308,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) vma->anon_vma = anon_vma; anon_vma_lock_write(anon_vma); anon_vma_chain_link(vma, avc, anon_vma); - anon_vma_unlock(anon_vma); + anon_vma_unlock_write(anon_vma); return 0; diff --git a/mm/shmem.c b/mm/shmem.c index 2bad33a585b4..a43ae7f7fed7 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -30,6 +30,7 @@ #include <linux/mm.h> #include <linux/export.h> #include <linux/swap.h> +#include <linux/aio.h> static struct vfsmount *shm_mnt; @@ -335,19 +336,19 @@ static unsigned shmem_find_get_pages_and_swap(struct address_space *mapping, pgoff_t start, unsigned int nr_pages, struct page **pages, pgoff_t *indices) { - unsigned int i; - unsigned int ret; - unsigned int nr_found; + void **slot; + unsigned int ret = 0; + struct radix_tree_iter iter; + + if (!nr_pages) + return 0; rcu_read_lock(); restart: - nr_found = radix_tree_gang_lookup_slot(&mapping->page_tree, - (void ***)pages, indices, start, nr_pages); - ret = 0; - for (i = 0; i < nr_found; i++) { + radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) { struct page *page; repeat: - page = radix_tree_deref_slot((void **)pages[i]); + page = radix_tree_deref_slot(slot); if (unlikely(!page)) continue; if (radix_tree_exception(page)) { @@ -364,17 +365,16 @@ repeat: goto repeat; /* Has the page moved? */ - if (unlikely(page != *((void **)pages[i]))) { + if (unlikely(page != *slot)) { page_cache_release(page); goto repeat; } export: - indices[ret] = indices[i]; + indices[ret] = iter.index; pages[ret] = page; - ret++; + if (++ret == nr_pages) + break; } - if (unlikely(!ret && nr_found)) - goto restart; rcu_read_unlock(); return ret; } diff --git a/mm/slob.c b/mm/slob.c index a99fdf7a0907..eeed4a05a2ef 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -360,7 +360,7 @@ static void slob_free(void *block, int size) clear_slob_page_free(sp); spin_unlock_irqrestore(&slob_lock, flags); __ClearPageSlab(sp); - reset_page_mapcount(sp); + page_mapcount_reset(sp); slob_free_pages(b, 0); return; } diff --git a/mm/slub.c b/mm/slub.c index 36ead8f2d231..aa1a88c73627 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1408,7 +1408,7 @@ static void __free_slab(struct kmem_cache *s, struct page *page) __ClearPageSlab(page); memcg_release_pages(s, order); - reset_page_mapcount(page); + page_mapcount_reset(page); if (current->reclaim_state) current->reclaim_state->reclaimed_slab += pages; __free_memcg_kmem_pages(page, order); diff --git a/mm/sparse.c b/mm/sparse.c index 6b5fb762e2ca..7ca6dc847947 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -615,10 +615,11 @@ static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid, } static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages) { - return; /* XXX: Not implemented yet */ + vmemmap_free(memmap, nr_pages); } static void free_map_bootmem(struct page *memmap, unsigned long nr_pages) { + vmemmap_free(memmap, nr_pages); } #else static struct page *__kmalloc_section_memmap(unsigned long nr_pages) @@ -697,7 +698,7 @@ static void free_section_usemap(struct page *memmap, unsigned long *usemap) /* * Check to see if allocation came from hot-plug-add */ - if (PageSlab(usemap_page)) { + if (PageSlab(usemap_page) || PageCompound(usemap_page)) { kfree(usemap); if (memmap) __kfree_section_memmap(memmap, PAGES_PER_SECTION); @@ -782,7 +783,7 @@ static void clear_hwpoisoned_pages(struct page *memmap, int nr_pages) for (i = 0; i < PAGES_PER_SECTION; i++) { if (PageHWPoison(&memmap[i])) { - atomic_long_sub(1, &mce_bad_pages); + atomic_long_sub(1, &num_poisoned_pages); ClearPageHWPoison(&memmap[i]); } } @@ -796,8 +797,10 @@ static inline void clear_hwpoisoned_pages(struct page *memmap, int nr_pages) void sparse_remove_one_section(struct zone *zone, struct mem_section *ms) { struct page *memmap = NULL; - unsigned long *usemap = NULL; + unsigned long *usemap = NULL, flags; + struct pglist_data *pgdat = zone->zone_pgdat; + pgdat_resize_lock(pgdat, &flags); if (ms->section_mem_map) { usemap = ms->pageblock_flags; memmap = sparse_decode_mem_map(ms->section_mem_map, @@ -805,6 +808,7 @@ void sparse_remove_one_section(struct zone *zone, struct mem_section *ms) ms->section_mem_map = 0; ms->pageblock_flags = NULL; } + pgdat_resize_unlock(pgdat, &flags); clear_hwpoisoned_pages(memmap, PAGES_PER_SECTION); free_section_usemap(memmap, usemap); diff --git a/mm/swap.c b/mm/swap.c index 6310dc2008ff..92a9be551846 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -30,6 +30,7 @@ #include <linux/backing-dev.h> #include <linux/memcontrol.h> #include <linux/gfp.h> +#include <linux/uio.h> #include "internal.h" @@ -855,9 +856,14 @@ EXPORT_SYMBOL(pagevec_lookup_tag); void __init swap_setup(void) { unsigned long megs = totalram_pages >> (20 - PAGE_SHIFT); - #ifdef CONFIG_SWAP - bdi_init(swapper_space.backing_dev_info); + int i; + + bdi_init(swapper_spaces[0].backing_dev_info); + for (i = 0; i < MAX_SWAPFILES; i++) { + spin_lock_init(&swapper_spaces[i].tree_lock); + INIT_LIST_HEAD(&swapper_spaces[i].i_mmap_nonlinear); + } #endif /* Use a smaller cluster for small-memory machines */ diff --git a/mm/swap_state.c b/mm/swap_state.c index 0cb36fb1f61c..7efcf1525921 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -36,12 +36,12 @@ static struct backing_dev_info swap_backing_dev_info = { .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED, }; -struct address_space swapper_space = { - .page_tree = RADIX_TREE_INIT(GFP_ATOMIC|__GFP_NOWARN), - .tree_lock = __SPIN_LOCK_UNLOCKED(swapper_space.tree_lock), - .a_ops = &swap_aops, - .i_mmap_nonlinear = LIST_HEAD_INIT(swapper_space.i_mmap_nonlinear), - .backing_dev_info = &swap_backing_dev_info, +struct address_space swapper_spaces[MAX_SWAPFILES] = { + [0 ... MAX_SWAPFILES - 1] = { + .page_tree = RADIX_TREE_INIT(GFP_ATOMIC|__GFP_NOWARN), + .a_ops = &swap_aops, + .backing_dev_info = &swap_backing_dev_info, + } }; #define INC_CACHE_INFO(x) do { swap_cache_info.x++; } while (0) @@ -53,13 +53,24 @@ static struct { unsigned long find_total; } swap_cache_info; +unsigned long total_swapcache_pages(void) +{ + int i; + unsigned long ret = 0; + + for (i = 0; i < MAX_SWAPFILES; i++) + ret += swapper_spaces[i].nrpages; + return ret; +} + void show_swap_cache_info(void) { - printk("%lu pages in swap cache\n", total_swapcache_pages); + printk("%lu pages in swap cache\n", total_swapcache_pages()); printk("Swap cache stats: add %lu, delete %lu, find %lu/%lu\n", swap_cache_info.add_total, swap_cache_info.del_total, swap_cache_info.find_success, swap_cache_info.find_total); - printk("Free swap = %ldkB\n", nr_swap_pages << (PAGE_SHIFT - 10)); + printk("Free swap = %ldkB\n", + get_nr_swap_pages() << (PAGE_SHIFT - 10)); printk("Total swap = %lukB\n", total_swap_pages << (PAGE_SHIFT - 10)); } @@ -70,6 +81,7 @@ void show_swap_cache_info(void) static int __add_to_swap_cache(struct page *page, swp_entry_t entry) { int error; + struct address_space *address_space; VM_BUG_ON(!PageLocked(page)); VM_BUG_ON(PageSwapCache(page)); @@ -79,14 +91,16 @@ static int __add_to_swap_cache(struct page *page, swp_entry_t entry) SetPageSwapCache(page); set_page_private(page, entry.val); - spin_lock_irq(&swapper_space.tree_lock); - error = radix_tree_insert(&swapper_space.page_tree, entry.val, page); + address_space = swap_address_space(entry); + spin_lock_irq(&address_space->tree_lock); + error = radix_tree_insert(&address_space->page_tree, + entry.val, page); if (likely(!error)) { - total_swapcache_pages++; + address_space->nrpages++; __inc_zone_page_state(page, NR_FILE_PAGES); INC_CACHE_INFO(add_total); } - spin_unlock_irq(&swapper_space.tree_lock); + spin_unlock_irq(&address_space->tree_lock); if (unlikely(error)) { /* @@ -122,14 +136,19 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask) */ void __delete_from_swap_cache(struct page *page) { + swp_entry_t entry; + struct address_space *address_space; + VM_BUG_ON(!PageLocked(page)); VM_BUG_ON(!PageSwapCache(page)); VM_BUG_ON(PageWriteback(page)); - radix_tree_delete(&swapper_space.page_tree, page_private(page)); + entry.val = page_private(page); + address_space = swap_address_space(entry); + radix_tree_delete(&address_space->page_tree, page_private(page)); set_page_private(page, 0); ClearPageSwapCache(page); - total_swapcache_pages--; + address_space->nrpages--; __dec_zone_page_state(page, NR_FILE_PAGES); INC_CACHE_INFO(del_total); } @@ -195,12 +214,14 @@ int add_to_swap(struct page *page) void delete_from_swap_cache(struct page *page) { swp_entry_t entry; + struct address_space *address_space; entry.val = page_private(page); - spin_lock_irq(&swapper_space.tree_lock); + address_space = swap_address_space(entry); + spin_lock_irq(&address_space->tree_lock); __delete_from_swap_cache(page); - spin_unlock_irq(&swapper_space.tree_lock); + spin_unlock_irq(&address_space->tree_lock); swapcache_free(entry, page); page_cache_release(page); @@ -263,7 +284,7 @@ struct page * lookup_swap_cache(swp_entry_t entry) { struct page *page; - page = find_get_page(&swapper_space, entry.val); + page = find_get_page(swap_address_space(entry), entry.val); if (page) INC_CACHE_INFO(find_success); @@ -290,7 +311,8 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, * called after lookup_swap_cache() failed, re-calling * that would confuse statistics. */ - found_page = find_get_page(&swapper_space, entry.val); + found_page = find_get_page(swap_address_space(entry), + entry.val); if (found_page) break; diff --git a/mm/swapfile.c b/mm/swapfile.c index e97a0e5aea91..9b51266413cd 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -47,9 +47,11 @@ static sector_t map_swap_entry(swp_entry_t, struct block_device**); DEFINE_SPINLOCK(swap_lock); static unsigned int nr_swapfiles; -long nr_swap_pages; +atomic_long_t nr_swap_pages; +/* protected with swap_lock. reading in vm_swap_full() doesn't need lock */ long total_swap_pages; static int least_priority; +static atomic_t highest_priority_index = ATOMIC_INIT(-1); static const char Bad_file[] = "Bad swap file entry "; static const char Unused_file[] = "Unused swap file entry "; @@ -79,7 +81,7 @@ __try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset) struct page *page; int ret = 0; - page = find_get_page(&swapper_space, entry.val); + page = find_get_page(swap_address_space(entry), entry.val); if (!page) return 0; /* @@ -223,7 +225,7 @@ static unsigned long scan_swap_map(struct swap_info_struct *si, si->lowest_alloc = si->max; si->highest_alloc = 0; } - spin_unlock(&swap_lock); + spin_unlock(&si->lock); /* * If seek is expensive, start searching for new cluster from @@ -242,7 +244,7 @@ static unsigned long scan_swap_map(struct swap_info_struct *si, if (si->swap_map[offset]) last_in_cluster = offset + SWAPFILE_CLUSTER; else if (offset == last_in_cluster) { - spin_lock(&swap_lock); + spin_lock(&si->lock); offset -= SWAPFILE_CLUSTER - 1; si->cluster_next = offset; si->cluster_nr = SWAPFILE_CLUSTER - 1; @@ -263,7 +265,7 @@ static unsigned long scan_swap_map(struct swap_info_struct *si, if (si->swap_map[offset]) last_in_cluster = offset + SWAPFILE_CLUSTER; else if (offset == last_in_cluster) { - spin_lock(&swap_lock); + spin_lock(&si->lock); offset -= SWAPFILE_CLUSTER - 1; si->cluster_next = offset; si->cluster_nr = SWAPFILE_CLUSTER - 1; @@ -277,7 +279,7 @@ static unsigned long scan_swap_map(struct swap_info_struct *si, } offset = scan_base; - spin_lock(&swap_lock); + spin_lock(&si->lock); si->cluster_nr = SWAPFILE_CLUSTER - 1; si->lowest_alloc = 0; } @@ -293,9 +295,9 @@ checks: /* reuse swap entry of cache-only swap if not busy. */ if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { int swap_was_freed; - spin_unlock(&swap_lock); + spin_unlock(&si->lock); swap_was_freed = __try_to_reclaim_swap(si, offset); - spin_lock(&swap_lock); + spin_lock(&si->lock); /* entry was freed successfully, try to use this again */ if (swap_was_freed) goto checks; @@ -335,13 +337,13 @@ checks: si->lowest_alloc <= last_in_cluster) last_in_cluster = si->lowest_alloc - 1; si->flags |= SWP_DISCARDING; - spin_unlock(&swap_lock); + spin_unlock(&si->lock); if (offset < last_in_cluster) discard_swap_cluster(si, offset, last_in_cluster - offset + 1); - spin_lock(&swap_lock); + spin_lock(&si->lock); si->lowest_alloc = 0; si->flags &= ~SWP_DISCARDING; @@ -355,10 +357,10 @@ checks: * could defer that delay until swap_writepage, * but it's easier to keep this self-contained. */ - spin_unlock(&swap_lock); + spin_unlock(&si->lock); wait_on_bit(&si->flags, ilog2(SWP_DISCARDING), wait_for_discard, TASK_UNINTERRUPTIBLE); - spin_lock(&swap_lock); + spin_lock(&si->lock); } else { /* * Note pages allocated by racing tasks while @@ -374,14 +376,14 @@ checks: return offset; scan: - spin_unlock(&swap_lock); + spin_unlock(&si->lock); while (++offset <= si->highest_bit) { if (!si->swap_map[offset]) { - spin_lock(&swap_lock); + spin_lock(&si->lock); goto checks; } if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { - spin_lock(&swap_lock); + spin_lock(&si->lock); goto checks; } if (unlikely(--latency_ration < 0)) { @@ -392,11 +394,11 @@ scan: offset = si->lowest_bit; while (++offset < scan_base) { if (!si->swap_map[offset]) { - spin_lock(&swap_lock); + spin_lock(&si->lock); goto checks; } if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { - spin_lock(&swap_lock); + spin_lock(&si->lock); goto checks; } if (unlikely(--latency_ration < 0)) { @@ -404,7 +406,7 @@ scan: latency_ration = LATENCY_LIMIT; } } - spin_lock(&swap_lock); + spin_lock(&si->lock); no_page: si->flags -= SWP_SCANNING; @@ -417,13 +419,34 @@ swp_entry_t get_swap_page(void) pgoff_t offset; int type, next; int wrapped = 0; + int hp_index; spin_lock(&swap_lock); - if (nr_swap_pages <= 0) + if (atomic_long_read(&nr_swap_pages) <= 0) goto noswap; - nr_swap_pages--; + atomic_long_dec(&nr_swap_pages); for (type = swap_list.next; type >= 0 && wrapped < 2; type = next) { + hp_index = atomic_xchg(&highest_priority_index, -1); + /* + * highest_priority_index records current highest priority swap + * type which just frees swap entries. If its priority is + * higher than that of swap_list.next swap type, we use it. It + * isn't protected by swap_lock, so it can be an invalid value + * if the corresponding swap type is swapoff. We double check + * the flags here. It's even possible the swap type is swapoff + * and swapon again and its priority is changed. In such rare + * case, low prority swap type might be used, but eventually + * high priority swap will be used after several rounds of + * swap. + */ + if (hp_index != -1 && hp_index != type && + swap_info[type]->prio < swap_info[hp_index]->prio && + (swap_info[hp_index]->flags & SWP_WRITEOK)) { + type = hp_index; + swap_list.next = type; + } + si = swap_info[type]; next = si->next; if (next < 0 || @@ -432,22 +455,29 @@ swp_entry_t get_swap_page(void) wrapped++; } - if (!si->highest_bit) + spin_lock(&si->lock); + if (!si->highest_bit) { + spin_unlock(&si->lock); continue; - if (!(si->flags & SWP_WRITEOK)) + } + if (!(si->flags & SWP_WRITEOK)) { + spin_unlock(&si->lock); continue; + } swap_list.next = next; + + spin_unlock(&swap_lock); /* This is called for allocating swap entry for cache */ offset = scan_swap_map(si, SWAP_HAS_CACHE); - if (offset) { - spin_unlock(&swap_lock); + spin_unlock(&si->lock); + if (offset) return swp_entry(type, offset); - } + spin_lock(&swap_lock); next = swap_list.next; } - nr_swap_pages++; + atomic_long_inc(&nr_swap_pages); noswap: spin_unlock(&swap_lock); return (swp_entry_t) {0}; @@ -459,19 +489,19 @@ swp_entry_t get_swap_page_of_type(int type) struct swap_info_struct *si; pgoff_t offset; - spin_lock(&swap_lock); si = swap_info[type]; + spin_lock(&si->lock); if (si && (si->flags & SWP_WRITEOK)) { - nr_swap_pages--; + atomic_long_dec(&nr_swap_pages); /* This is called for allocating swap entry, not cache */ offset = scan_swap_map(si, 1); if (offset) { - spin_unlock(&swap_lock); + spin_unlock(&si->lock); return swp_entry(type, offset); } - nr_swap_pages++; + atomic_long_inc(&nr_swap_pages); } - spin_unlock(&swap_lock); + spin_unlock(&si->lock); return (swp_entry_t) {0}; } @@ -493,7 +523,7 @@ static struct swap_info_struct *swap_info_get(swp_entry_t entry) goto bad_offset; if (!p->swap_map[offset]) goto bad_free; - spin_lock(&swap_lock); + spin_lock(&p->lock); return p; bad_free: @@ -511,6 +541,27 @@ out: return NULL; } +/* + * This swap type frees swap entry, check if it is the highest priority swap + * type which just frees swap entry. get_swap_page() uses + * highest_priority_index to search highest priority swap type. The + * swap_info_struct.lock can't protect us if there are multiple swap types + * active, so we use atomic_cmpxchg. + */ +static void set_highest_priority_index(int type) +{ + int old_hp_index, new_hp_index; + + do { + old_hp_index = atomic_read(&highest_priority_index); + if (old_hp_index != -1 && + swap_info[old_hp_index]->prio >= swap_info[type]->prio) + break; + new_hp_index = type; + } while (atomic_cmpxchg(&highest_priority_index, + old_hp_index, new_hp_index) != old_hp_index); +} + static unsigned char swap_entry_free(struct swap_info_struct *p, swp_entry_t entry, unsigned char usage) { @@ -553,10 +604,8 @@ static unsigned char swap_entry_free(struct swap_info_struct *p, p->lowest_bit = offset; if (offset > p->highest_bit) p->highest_bit = offset; - if (swap_list.next >= 0 && - p->prio > swap_info[swap_list.next]->prio) - swap_list.next = p->type; - nr_swap_pages++; + set_highest_priority_index(p->type); + atomic_long_inc(&nr_swap_pages); p->inuse_pages--; frontswap_invalidate_page(p->type, offset); if (p->flags & SWP_BLKDEV) { @@ -581,7 +630,7 @@ void swap_free(swp_entry_t entry) p = swap_info_get(entry); if (p) { swap_entry_free(p, entry, 1); - spin_unlock(&swap_lock); + spin_unlock(&p->lock); } } @@ -598,7 +647,7 @@ void swapcache_free(swp_entry_t entry, struct page *page) count = swap_entry_free(p, entry, SWAP_HAS_CACHE); if (page) mem_cgroup_uncharge_swapcache(page, entry, count != 0); - spin_unlock(&swap_lock); + spin_unlock(&p->lock); } } @@ -617,7 +666,7 @@ int page_swapcount(struct page *page) p = swap_info_get(entry); if (p) { count = swap_count(p->swap_map[swp_offset(entry)]); - spin_unlock(&swap_lock); + spin_unlock(&p->lock); } return count; } @@ -699,13 +748,14 @@ int free_swap_and_cache(swp_entry_t entry) p = swap_info_get(entry); if (p) { if (swap_entry_free(p, entry, 1) == SWAP_HAS_CACHE) { - page = find_get_page(&swapper_space, entry.val); + page = find_get_page(swap_address_space(entry), + entry.val); if (page && !trylock_page(page)) { page_cache_release(page); page = NULL; } } - spin_unlock(&swap_lock); + spin_unlock(&p->lock); } if (page) { /* @@ -803,11 +853,13 @@ unsigned int count_swap_pages(int type, int free) if ((unsigned int)type < nr_swapfiles) { struct swap_info_struct *sis = swap_info[type]; + spin_lock(&sis->lock); if (sis->flags & SWP_WRITEOK) { n = sis->pages; if (free) n -= sis->inuse_pages; } + spin_unlock(&sis->lock); } spin_unlock(&swap_lock); return n; @@ -1456,7 +1508,7 @@ static void _enable_swap_info(struct swap_info_struct *p, int prio, p->swap_map = swap_map; frontswap_map_set(p, frontswap_map); p->flags |= SWP_WRITEOK; - nr_swap_pages += p->pages; + atomic_long_add(p->pages, &nr_swap_pages); total_swap_pages += p->pages; /* insert swap space into swap_list: */ @@ -1478,15 +1530,19 @@ static void enable_swap_info(struct swap_info_struct *p, int prio, unsigned long *frontswap_map) { spin_lock(&swap_lock); + spin_lock(&p->lock); _enable_swap_info(p, prio, swap_map, frontswap_map); frontswap_init(p->type); + spin_unlock(&p->lock); spin_unlock(&swap_lock); } static void reinsert_swap_info(struct swap_info_struct *p) { spin_lock(&swap_lock); + spin_lock(&p->lock); _enable_swap_info(p, p->prio, p->swap_map, frontswap_map_get(p)); + spin_unlock(&p->lock); spin_unlock(&swap_lock); } @@ -1546,14 +1602,16 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) /* just pick something that's safe... */ swap_list.next = swap_list.head; } + spin_lock(&p->lock); if (p->prio < 0) { for (i = p->next; i >= 0; i = swap_info[i]->next) swap_info[i]->prio = p->prio--; least_priority++; } - nr_swap_pages -= p->pages; + atomic_long_sub(p->pages, &nr_swap_pages); total_swap_pages -= p->pages; p->flags &= ~SWP_WRITEOK; + spin_unlock(&p->lock); spin_unlock(&swap_lock); set_current_oom_origin(); @@ -1572,14 +1630,17 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) mutex_lock(&swapon_mutex); spin_lock(&swap_lock); + spin_lock(&p->lock); drain_mmlist(); /* wait for anyone still in scan_swap_map */ p->highest_bit = 0; /* cuts scans short */ while (p->flags >= SWP_SCANNING) { + spin_unlock(&p->lock); spin_unlock(&swap_lock); schedule_timeout_uninterruptible(1); spin_lock(&swap_lock); + spin_lock(&p->lock); } swap_file = p->swap_file; @@ -1589,6 +1650,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) p->swap_map = NULL; p->flags = 0; frontswap_invalidate_area(type); + spin_unlock(&p->lock); spin_unlock(&swap_lock); mutex_unlock(&swapon_mutex); vfree(swap_map); @@ -1794,6 +1856,7 @@ static struct swap_info_struct *alloc_swap_info(void) p->flags = SWP_USED; p->next = -1; spin_unlock(&swap_lock); + spin_lock_init(&p->lock); return p; } @@ -2116,7 +2179,7 @@ void si_swapinfo(struct sysinfo *val) if ((si->flags & SWP_USED) && !(si->flags & SWP_WRITEOK)) nr_to_be_unused += si->inuse_pages; } - val->freeswap = nr_swap_pages + nr_to_be_unused; + val->freeswap = atomic_long_read(&nr_swap_pages) + nr_to_be_unused; val->totalswap = total_swap_pages + nr_to_be_unused; spin_unlock(&swap_lock); } @@ -2149,7 +2212,7 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage) p = swap_info[type]; offset = swp_offset(entry); - spin_lock(&swap_lock); + spin_lock(&p->lock); if (unlikely(offset >= p->max)) goto unlock_out; @@ -2184,7 +2247,7 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage) p->swap_map[offset] = count | has_cache; unlock_out: - spin_unlock(&swap_lock); + spin_unlock(&p->lock); out: return err; @@ -2309,7 +2372,7 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) } if (!page) { - spin_unlock(&swap_lock); + spin_unlock(&si->lock); return -ENOMEM; } @@ -2357,7 +2420,7 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) list_add_tail(&page->lru, &head->lru); page = NULL; /* now it's attached, don't free it */ out: - spin_unlock(&swap_lock); + spin_unlock(&si->lock); outer: if (page) __free_page(page); diff --git a/mm/util.c b/mm/util.c index c55e26b17d93..7441c41d00f6 100644 --- a/mm/util.c +++ b/mm/util.c @@ -5,6 +5,8 @@ #include <linux/err.h> #include <linux/sched.h> #include <linux/security.h> +#include <linux/swap.h> +#include <linux/swapops.h> #include <asm/uaccess.h> #include "internal.h" @@ -293,7 +295,6 @@ void arch_pick_mmap_layout(struct mm_struct *mm) { mm->mmap_base = TASK_UNMAPPED_BASE; mm->get_unmapped_area = arch_get_unmapped_area; - mm->unmap_area = arch_unmap_area; } #endif @@ -355,12 +356,16 @@ unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr, { unsigned long ret; struct mm_struct *mm = current->mm; + unsigned long populate; ret = security_mmap_file(file, prot, flag); if (!ret) { down_write(&mm->mmap_sem); - ret = do_mmap_pgoff(file, addr, len, prot, flag, pgoff); + ret = do_mmap_pgoff(file, addr, len, prot, flag, pgoff, + &populate); up_write(&mm->mmap_sem); + if (populate) + mm_populate(ret, populate); } return ret; } @@ -378,6 +383,24 @@ unsigned long vm_mmap(struct file *file, unsigned long addr, } EXPORT_SYMBOL(vm_mmap); +struct address_space *page_mapping(struct page *page) +{ + struct address_space *mapping = page->mapping; + + VM_BUG_ON(PageSlab(page)); +#ifdef CONFIG_SWAP + if (unlikely(PageSwapCache(page))) { + swp_entry_t entry; + + entry.val = page_private(page); + mapping = swap_address_space(entry); + } else +#endif + if ((unsigned long)mapping & PAGE_MAPPING_ANON) + mapping = NULL; + return mapping; +} + /* Tracepoints definitions. */ EXPORT_TRACEPOINT_SYMBOL(kmalloc); EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 5123a169ab7b..0f751f2068c3 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1376,8 +1376,8 @@ static struct vm_struct *__get_vm_area_node(unsigned long size, struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags, unsigned long start, unsigned long end) { - return __get_vm_area_node(size, 1, flags, start, end, -1, GFP_KERNEL, - __builtin_return_address(0)); + return __get_vm_area_node(size, 1, flags, start, end, NUMA_NO_NODE, + GFP_KERNEL, __builtin_return_address(0)); } EXPORT_SYMBOL_GPL(__get_vm_area); @@ -1385,8 +1385,8 @@ struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags, unsigned long start, unsigned long end, const void *caller) { - return __get_vm_area_node(size, 1, flags, start, end, -1, GFP_KERNEL, - caller); + return __get_vm_area_node(size, 1, flags, start, end, NUMA_NO_NODE, + GFP_KERNEL, caller); } /** @@ -1401,14 +1401,15 @@ struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags, struct vm_struct *get_vm_area(unsigned long size, unsigned long flags) { return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END, - -1, GFP_KERNEL, __builtin_return_address(0)); + NUMA_NO_NODE, GFP_KERNEL, + __builtin_return_address(0)); } struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags, const void *caller) { return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END, - -1, GFP_KERNEL, caller); + NUMA_NO_NODE, GFP_KERNEL, caller); } /** @@ -1650,7 +1651,7 @@ fail: * @end: vm area range end * @gfp_mask: flags for the page level allocator * @prot: protection mask for the allocated pages - * @node: node to use for allocation or -1 + * @node: node to use for allocation or NUMA_NO_NODE * @caller: caller's return address * * Allocate enough pages to cover @size from the page level @@ -1706,7 +1707,7 @@ fail: * @align: desired alignment * @gfp_mask: flags for the page level allocator * @prot: protection mask for the allocated pages - * @node: node to use for allocation or -1 + * @node: node to use for allocation or NUMA_NO_NODE * @caller: caller's return address * * Allocate enough pages to cover @size from the page level @@ -1723,7 +1724,7 @@ static void *__vmalloc_node(unsigned long size, unsigned long align, void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot) { - return __vmalloc_node(size, 1, gfp_mask, prot, -1, + return __vmalloc_node(size, 1, gfp_mask, prot, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(__vmalloc); @@ -1746,7 +1747,8 @@ static inline void *__vmalloc_node_flags(unsigned long size, */ void *vmalloc(unsigned long size) { - return __vmalloc_node_flags(size, -1, GFP_KERNEL | __GFP_HIGHMEM); + return __vmalloc_node_flags(size, NUMA_NO_NODE, + GFP_KERNEL | __GFP_HIGHMEM); } EXPORT_SYMBOL(vmalloc); @@ -1762,7 +1764,7 @@ EXPORT_SYMBOL(vmalloc); */ void *vzalloc(unsigned long size) { - return __vmalloc_node_flags(size, -1, + return __vmalloc_node_flags(size, NUMA_NO_NODE, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO); } EXPORT_SYMBOL(vzalloc); @@ -1781,7 +1783,8 @@ void *vmalloc_user(unsigned long size) ret = __vmalloc_node(size, SHMLBA, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, - PAGE_KERNEL, -1, __builtin_return_address(0)); + PAGE_KERNEL, NUMA_NO_NODE, + __builtin_return_address(0)); if (ret) { area = find_vm_area(ret); area->flags |= VM_USERMAP; @@ -1846,7 +1849,7 @@ EXPORT_SYMBOL(vzalloc_node); void *vmalloc_exec(unsigned long size) { return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC, - -1, __builtin_return_address(0)); + NUMA_NO_NODE, __builtin_return_address(0)); } #if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32) @@ -1867,7 +1870,7 @@ void *vmalloc_exec(unsigned long size) void *vmalloc_32(unsigned long size) { return __vmalloc_node(size, 1, GFP_VMALLOC32, PAGE_KERNEL, - -1, __builtin_return_address(0)); + NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc_32); @@ -1884,7 +1887,7 @@ void *vmalloc_32_user(unsigned long size) void *ret; ret = __vmalloc_node(size, 1, GFP_VMALLOC32 | __GFP_ZERO, PAGE_KERNEL, - -1, __builtin_return_address(0)); + NUMA_NO_NODE, __builtin_return_address(0)); if (ret) { area = find_vm_area(ret); area->flags |= VM_USERMAP; diff --git a/mm/vmscan.c b/mm/vmscan.c index 196709f5ee58..88c5fed8b9a4 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -128,7 +128,7 @@ struct scan_control { * From 0 .. 100. Higher means more swappy. */ int vm_swappiness = 60; -long vm_total_pages; /* The total number of pages which the VM controls */ +unsigned long vm_total_pages; /* The total number of pages which the VM controls */ static LIST_HEAD(shrinker_list); static DECLARE_RWSEM(shrinker_rwsem); @@ -1579,16 +1579,6 @@ static inline int inactive_anon_is_low(struct lruvec *lruvec) } #endif -static int inactive_file_is_low_global(struct zone *zone) -{ - unsigned long active, inactive; - - active = zone_page_state(zone, NR_ACTIVE_FILE); - inactive = zone_page_state(zone, NR_INACTIVE_FILE); - - return (active > inactive); -} - /** * inactive_file_is_low - check if file pages need to be deactivated * @lruvec: LRU vector to check @@ -1605,10 +1595,13 @@ static int inactive_file_is_low_global(struct zone *zone) */ static int inactive_file_is_low(struct lruvec *lruvec) { - if (!mem_cgroup_disabled()) - return mem_cgroup_inactive_file_is_low(lruvec); + unsigned long inactive; + unsigned long active; + + inactive = get_lru_size(lruvec, LRU_INACTIVE_FILE); + active = get_lru_size(lruvec, LRU_ACTIVE_FILE); - return inactive_file_is_low_global(lruvec_zone(lruvec)); + return active > inactive; } static int inactive_list_is_low(struct lruvec *lruvec, enum lru_list lru) @@ -1638,6 +1631,13 @@ static int vmscan_swappiness(struct scan_control *sc) return mem_cgroup_swappiness(sc->target_mem_cgroup); } +enum scan_balance { + SCAN_EQUAL, + SCAN_FRACT, + SCAN_ANON, + SCAN_FILE, +}; + /* * Determine how aggressively the anon and file LRU lists should be * scanned. The relative value of each set of LRU lists is determined @@ -1650,15 +1650,16 @@ static int vmscan_swappiness(struct scan_control *sc) static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, unsigned long *nr) { - unsigned long anon, file, free; + struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat; + u64 fraction[2]; + u64 denominator = 0; /* gcc */ + struct zone *zone = lruvec_zone(lruvec); unsigned long anon_prio, file_prio; + enum scan_balance scan_balance; + unsigned long anon, file, free; + bool force_scan = false; unsigned long ap, fp; - struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat; - u64 fraction[2], denominator; enum lru_list lru; - int noswap = 0; - bool force_scan = false; - struct zone *zone = lruvec_zone(lruvec); /* * If the zone or memcg is small, nr[l] can be 0. This @@ -1676,11 +1677,30 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, force_scan = true; /* If we have no swap space, do not bother scanning anon pages. */ - if (!sc->may_swap || (nr_swap_pages <= 0)) { - noswap = 1; - fraction[0] = 0; - fraction[1] = 1; - denominator = 1; + if (!sc->may_swap || (get_nr_swap_pages() <= 0)) { + scan_balance = SCAN_FILE; + goto out; + } + + /* + * Global reclaim will swap to prevent OOM even with no + * swappiness, but memcg users want to use this knob to + * disable swapping for individual groups completely when + * using the memory controller's swap limit feature would be + * too expensive. + */ + if (!global_reclaim(sc) && !vmscan_swappiness(sc)) { + scan_balance = SCAN_FILE; + goto out; + } + + /* + * Do not apply any pressure balancing cleverness when the + * system is close to OOM, scan both anon and file equally + * (unless the swappiness setting disagrees with swapping). + */ + if (!sc->priority && vmscan_swappiness(sc)) { + scan_balance = SCAN_EQUAL; goto out; } @@ -1689,30 +1709,32 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, file = get_lru_size(lruvec, LRU_ACTIVE_FILE) + get_lru_size(lruvec, LRU_INACTIVE_FILE); + /* + * If it's foreseeable that reclaiming the file cache won't be + * enough to get the zone back into a desirable shape, we have + * to swap. Better start now and leave the - probably heavily + * thrashing - remaining file pages alone. + */ if (global_reclaim(sc)) { - free = zone_page_state(zone, NR_FREE_PAGES); + free = zone_page_state(zone, NR_FREE_PAGES); if (unlikely(file + free <= high_wmark_pages(zone))) { - /* - * If we have very few page cache pages, force-scan - * anon pages. - */ - fraction[0] = 1; - fraction[1] = 0; - denominator = 1; - goto out; - } else if (!inactive_file_is_low_global(zone)) { - /* - * There is enough inactive page cache, do not - * reclaim anything from the working set right now. - */ - fraction[0] = 0; - fraction[1] = 1; - denominator = 1; + scan_balance = SCAN_ANON; goto out; } } /* + * There is enough inactive page cache, do not reclaim + * anything from the anonymous working set right now. + */ + if (!inactive_file_is_low(lruvec)) { + scan_balance = SCAN_FILE; + goto out; + } + + scan_balance = SCAN_FRACT; + + /* * With swappiness at 100, anonymous and file have the same priority. * This scanning priority is essentially the inverse of IO cost. */ @@ -1759,19 +1781,92 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, out: for_each_evictable_lru(lru) { int file = is_file_lru(lru); + unsigned long size; unsigned long scan; - scan = get_lru_size(lruvec, lru); - if (sc->priority || noswap || !vmscan_swappiness(sc)) { - scan >>= sc->priority; - if (!scan && force_scan) - scan = SWAP_CLUSTER_MAX; + size = get_lru_size(lruvec, lru); + scan = size >> sc->priority; + + if (!scan && force_scan) + scan = min(size, SWAP_CLUSTER_MAX); + + switch (scan_balance) { + case SCAN_EQUAL: + /* Scan lists relative to size */ + break; + case SCAN_FRACT: + /* + * Scan types proportional to swappiness and + * their relative recent reclaim efficiency. + */ scan = div64_u64(scan * fraction[file], denominator); + break; + case SCAN_FILE: + case SCAN_ANON: + /* Scan one type exclusively */ + if ((scan_balance == SCAN_FILE) != file) + scan = 0; + break; + default: + /* Look ma, no brain */ + BUG(); } nr[lru] = scan; } } +/* + * This is a basic per-zone page freer. Used by both kswapd and direct reclaim. + */ +static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) +{ + unsigned long nr[NR_LRU_LISTS]; + unsigned long nr_to_scan; + enum lru_list lru; + unsigned long nr_reclaimed = 0; + unsigned long nr_to_reclaim = sc->nr_to_reclaim; + struct blk_plug plug; + + get_scan_count(lruvec, sc, nr); + + blk_start_plug(&plug); + while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] || + nr[LRU_INACTIVE_FILE]) { + for_each_evictable_lru(lru) { + if (nr[lru]) { + nr_to_scan = min(nr[lru], SWAP_CLUSTER_MAX); + nr[lru] -= nr_to_scan; + + nr_reclaimed += shrink_list(lru, nr_to_scan, + lruvec, sc); + } + } + /* + * On large memory systems, scan >> priority can become + * really large. This is fine for the starting priority; + * we want to put equal scanning pressure on each zone. + * However, if the VM has a harder time of freeing pages, + * with multiple processes reclaiming pages, the total + * freeing target can get unreasonably large. + */ + if (nr_reclaimed >= nr_to_reclaim && + sc->priority < DEF_PRIORITY) + break; + } + blk_finish_plug(&plug); + sc->nr_reclaimed += nr_reclaimed; + + /* + * Even if we did not try to evict anon pages at all, we want to + * rebalance the anon lru active/inactive ratio. + */ + if (inactive_anon_is_low(lruvec)) + shrink_active_list(SWAP_CLUSTER_MAX, lruvec, + sc, LRU_ACTIVE_ANON); + + throttle_vm_writeout(sc->gfp_mask); +} + /* Use reclaim/compaction for costly allocs or under memory pressure */ static bool in_reclaim_compaction(struct scan_control *sc) { @@ -1790,7 +1885,7 @@ static bool in_reclaim_compaction(struct scan_control *sc) * calls try_to_compact_zone() that it will have enough free pages to succeed. * It will give up earlier than that if there is difficulty reclaiming pages. */ -static inline bool should_continue_reclaim(struct lruvec *lruvec, +static inline bool should_continue_reclaim(struct zone *zone, unsigned long nr_reclaimed, unsigned long nr_scanned, struct scan_control *sc) @@ -1830,15 +1925,15 @@ static inline bool should_continue_reclaim(struct lruvec *lruvec, * inactive lists are large enough, continue reclaiming */ pages_for_compaction = (2UL << sc->order); - inactive_lru_pages = get_lru_size(lruvec, LRU_INACTIVE_FILE); - if (nr_swap_pages > 0) - inactive_lru_pages += get_lru_size(lruvec, LRU_INACTIVE_ANON); + inactive_lru_pages = zone_page_state(zone, NR_INACTIVE_FILE); + if (get_nr_swap_pages() > 0) + inactive_lru_pages += zone_page_state(zone, NR_INACTIVE_ANON); if (sc->nr_reclaimed < pages_for_compaction && inactive_lru_pages > pages_for_compaction) return true; /* If compaction would go ahead or the allocation would succeed, stop */ - switch (compaction_suitable(lruvec_zone(lruvec), sc->order)) { + switch (compaction_suitable(zone, sc->order)) { case COMPACT_PARTIAL: case COMPACT_CONTINUE: return false; @@ -1847,98 +1942,48 @@ static inline bool should_continue_reclaim(struct lruvec *lruvec, } } -/* - * This is a basic per-zone page freer. Used by both kswapd and direct reclaim. - */ -static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) +static void shrink_zone(struct zone *zone, struct scan_control *sc) { - unsigned long nr[NR_LRU_LISTS]; - unsigned long nr_to_scan; - enum lru_list lru; unsigned long nr_reclaimed, nr_scanned; - unsigned long nr_to_reclaim = sc->nr_to_reclaim; - struct blk_plug plug; - -restart: - nr_reclaimed = 0; - nr_scanned = sc->nr_scanned; - get_scan_count(lruvec, sc, nr); - - blk_start_plug(&plug); - while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] || - nr[LRU_INACTIVE_FILE]) { - for_each_evictable_lru(lru) { - if (nr[lru]) { - nr_to_scan = min_t(unsigned long, - nr[lru], SWAP_CLUSTER_MAX); - nr[lru] -= nr_to_scan; - - nr_reclaimed += shrink_list(lru, nr_to_scan, - lruvec, sc); - } - } - /* - * On large memory systems, scan >> priority can become - * really large. This is fine for the starting priority; - * we want to put equal scanning pressure on each zone. - * However, if the VM has a harder time of freeing pages, - * with multiple processes reclaiming pages, the total - * freeing target can get unreasonably large. - */ - if (nr_reclaimed >= nr_to_reclaim && - sc->priority < DEF_PRIORITY) - break; - } - blk_finish_plug(&plug); - sc->nr_reclaimed += nr_reclaimed; - /* - * Even if we did not try to evict anon pages at all, we want to - * rebalance the anon lru active/inactive ratio. - */ - if (inactive_anon_is_low(lruvec)) - shrink_active_list(SWAP_CLUSTER_MAX, lruvec, - sc, LRU_ACTIVE_ANON); - - /* reclaim/compaction might need reclaim to continue */ - if (should_continue_reclaim(lruvec, nr_reclaimed, - sc->nr_scanned - nr_scanned, sc)) - goto restart; + do { + struct mem_cgroup *root = sc->target_mem_cgroup; + struct mem_cgroup_reclaim_cookie reclaim = { + .zone = zone, + .priority = sc->priority, + }; + struct mem_cgroup *memcg; - throttle_vm_writeout(sc->gfp_mask); -} + nr_reclaimed = sc->nr_reclaimed; + nr_scanned = sc->nr_scanned; -static void shrink_zone(struct zone *zone, struct scan_control *sc) -{ - struct mem_cgroup *root = sc->target_mem_cgroup; - struct mem_cgroup_reclaim_cookie reclaim = { - .zone = zone, - .priority = sc->priority, - }; - struct mem_cgroup *memcg; + memcg = mem_cgroup_iter(root, NULL, &reclaim); + do { + struct lruvec *lruvec; - memcg = mem_cgroup_iter(root, NULL, &reclaim); - do { - struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg); + lruvec = mem_cgroup_zone_lruvec(zone, memcg); - shrink_lruvec(lruvec, sc); + shrink_lruvec(lruvec, sc); - /* - * Limit reclaim has historically picked one memcg and - * scanned it with decreasing priority levels until - * nr_to_reclaim had been reclaimed. This priority - * cycle is thus over after a single memcg. - * - * Direct reclaim and kswapd, on the other hand, have - * to scan all memory cgroups to fulfill the overall - * scan target for the zone. - */ - if (!global_reclaim(sc)) { - mem_cgroup_iter_break(root, memcg); - break; - } - memcg = mem_cgroup_iter(root, memcg, &reclaim); - } while (memcg); + /* + * Direct reclaim and kswapd have to scan all memory + * cgroups to fulfill the overall scan target for the + * zone. + * + * Limit reclaim, on the other hand, only cares about + * nr_to_reclaim pages to be reclaimed and it will + * retry with decreasing priority if one round over the + * whole hierarchy is not sufficient. + */ + if (!global_reclaim(sc) && + sc->nr_reclaimed >= sc->nr_to_reclaim) { + mem_cgroup_iter_break(root, memcg); + break; + } + memcg = mem_cgroup_iter(root, memcg, &reclaim); + } while (memcg); + } while (should_continue_reclaim(zone, sc->nr_reclaimed - nr_reclaimed, + sc->nr_scanned - nr_scanned, sc)); } /* Returns true if compaction should go ahead for a high-order request */ @@ -1958,7 +2003,7 @@ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) * a reasonable chance of completing and allocating the page */ balance_gap = min(low_wmark_pages(zone), - (zone->present_pages + KSWAPD_ZONE_BALANCE_GAP_RATIO-1) / + (zone->managed_pages + KSWAPD_ZONE_BALANCE_GAP_RATIO-1) / KSWAPD_ZONE_BALANCE_GAP_RATIO); watermark = high_wmark_pages(zone) + balance_gap + (2UL << sc->order); watermark_ok = zone_watermark_ok_safe(zone, 0, watermark, 0, 0); @@ -2150,6 +2195,13 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, goto out; /* + * If we're getting trouble reclaiming, start doing + * writepage even in laptop mode. + */ + if (sc->priority < DEF_PRIORITY - 2) + sc->may_writepage = 1; + + /* * Try to write back as many pages as we just scanned. This * tends to cause slow streaming writers to write data to the * disk smoothly, at the dirtying rate, which is nice. But @@ -2300,7 +2352,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, { unsigned long nr_reclaimed; struct scan_control sc = { - .gfp_mask = gfp_mask, + .gfp_mask = (gfp_mask = memalloc_noio_flags(gfp_mask)), .may_writepage = !laptop_mode, .nr_to_reclaim = SWAP_CLUSTER_MAX, .may_unmap = 1, @@ -2473,7 +2525,7 @@ static bool zone_balanced(struct zone *zone, int order, */ static bool pgdat_balanced(pg_data_t *pgdat, int order, int classzone_idx) { - unsigned long present_pages = 0; + unsigned long managed_pages = 0; unsigned long balanced_pages = 0; int i; @@ -2484,7 +2536,7 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int classzone_idx) if (!populated_zone(zone)) continue; - present_pages += zone->present_pages; + managed_pages += zone->managed_pages; /* * A special case here: @@ -2494,18 +2546,18 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int classzone_idx) * they must be considered balanced here as well! */ if (zone->all_unreclaimable) { - balanced_pages += zone->present_pages; + balanced_pages += zone->managed_pages; continue; } if (zone_balanced(zone, order, 0, i)) - balanced_pages += zone->present_pages; + balanced_pages += zone->managed_pages; else if (!order) return false; } if (order) - return balanced_pages >= (present_pages >> 2); + return balanced_pages >= (managed_pages >> 2); else return true; } @@ -2564,7 +2616,7 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining, static unsigned long balance_pgdat(pg_data_t *pgdat, int order, int *classzone_idx) { - struct zone *unbalanced_zone; + bool pgdat_is_balanced = false; int i; int end_zone = 0; /* Inclusive. 0 = ZONE_DMA */ unsigned long total_scanned; @@ -2595,9 +2647,6 @@ loop_again: do { unsigned long lru_pages = 0; - int has_under_min_watermark_zone = 0; - - unbalanced_zone = NULL; /* * Scan in the highmem->dma direction for the highest @@ -2638,8 +2687,11 @@ loop_again: zone_clear_flag(zone, ZONE_CONGESTED); } } - if (i < 0) + + if (i < 0) { + pgdat_is_balanced = true; goto out; + } for (i = 0; i <= end_zone; i++) { struct zone *zone = pgdat->node_zones + i; @@ -2689,7 +2741,7 @@ loop_again: * of the zone, whichever is smaller. */ balance_gap = min(low_wmark_pages(zone), - (zone->present_pages + + (zone->managed_pages + KSWAPD_ZONE_BALANCE_GAP_RATIO-1) / KSWAPD_ZONE_BALANCE_GAP_RATIO); /* @@ -2720,12 +2772,10 @@ loop_again: } /* - * If we've done a decent amount of scanning and - * the reclaim ratio is low, start doing writepage - * even in laptop mode + * If we're getting trouble reclaiming, start doing + * writepage even in laptop mode. */ - if (total_scanned > SWAP_CLUSTER_MAX * 2 && - total_scanned > sc.nr_reclaimed + sc.nr_reclaimed / 2) + if (sc.priority < DEF_PRIORITY - 2) sc.may_writepage = 1; if (zone->all_unreclaimable) { @@ -2734,17 +2784,7 @@ loop_again: continue; } - if (!zone_balanced(zone, testorder, 0, end_zone)) { - unbalanced_zone = zone; - /* - * We are still under min water mark. This - * means that we have a GFP_ATOMIC allocation - * failure risk. Hurry up! - */ - if (!zone_watermark_ok_safe(zone, order, - min_wmark_pages(zone), end_zone, 0)) - has_under_min_watermark_zone = 1; - } else { + if (zone_balanced(zone, testorder, 0, end_zone)) /* * If a zone reaches its high watermark, * consider it to be no longer congested. It's @@ -2753,8 +2793,6 @@ loop_again: * speculatively avoid congestion waits */ zone_clear_flag(zone, ZONE_CONGESTED); - } - } /* @@ -2766,17 +2804,9 @@ loop_again: pfmemalloc_watermark_ok(pgdat)) wake_up(&pgdat->pfmemalloc_wait); - if (pgdat_balanced(pgdat, order, *classzone_idx)) + if (pgdat_balanced(pgdat, order, *classzone_idx)) { + pgdat_is_balanced = true; break; /* kswapd: all done */ - /* - * OK, kswapd is getting into trouble. Take a nap, then take - * another pass across the zones. - */ - if (total_scanned && (sc.priority < DEF_PRIORITY - 2)) { - if (has_under_min_watermark_zone) - count_vm_event(KSWAPD_SKIP_CONGESTION_WAIT); - else if (unbalanced_zone) - wait_iff_congested(unbalanced_zone, BLK_RW_ASYNC, HZ/10); } /* @@ -2788,9 +2818,9 @@ loop_again: if (sc.nr_reclaimed >= SWAP_CLUSTER_MAX) break; } while (--sc.priority >= 0); -out: - if (!pgdat_balanced(pgdat, order, *classzone_idx)) { +out: + if (!pgdat_is_balanced) { cond_resched(); try_to_freeze(); @@ -3053,7 +3083,7 @@ unsigned long global_reclaimable_pages(void) nr = global_page_state(NR_ACTIVE_FILE) + global_page_state(NR_INACTIVE_FILE); - if (nr_swap_pages > 0) + if (get_nr_swap_pages() > 0) nr += global_page_state(NR_ACTIVE_ANON) + global_page_state(NR_INACTIVE_ANON); @@ -3067,7 +3097,7 @@ unsigned long zone_reclaimable_pages(struct zone *zone) nr = zone_page_state(zone, NR_ACTIVE_FILE) + zone_page_state(zone, NR_INACTIVE_FILE); - if (nr_swap_pages > 0) + if (get_nr_swap_pages() > 0) nr += zone_page_state(zone, NR_ACTIVE_ANON) + zone_page_state(zone, NR_INACTIVE_ANON); @@ -3280,9 +3310,8 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) .may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE), .may_unmap = !!(zone_reclaim_mode & RECLAIM_SWAP), .may_swap = 1, - .nr_to_reclaim = max_t(unsigned long, nr_pages, - SWAP_CLUSTER_MAX), - .gfp_mask = gfp_mask, + .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), + .gfp_mask = (gfp_mask = memalloc_noio_flags(gfp_mask)), .order = order, .priority = ZONE_RECLAIM_PRIORITY, }; diff --git a/mm/vmstat.c b/mm/vmstat.c index 9800306c8195..292b1cf785e0 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -142,7 +142,7 @@ int calculate_normal_threshold(struct zone *zone) * 125 1024 10 16-32 GB 9 */ - mem = zone->present_pages >> (27 - PAGE_SHIFT); + mem = zone->managed_pages >> (27 - PAGE_SHIFT); threshold = 2 * fls(num_online_cpus()) * (1 + fls(mem)); @@ -628,7 +628,9 @@ static char * const migratetype_names[MIGRATE_TYPES] = { #ifdef CONFIG_CMA "CMA", #endif +#ifdef CONFIG_MEMORY_ISOLATION "Isolate", +#endif }; static void *frag_start(struct seq_file *m, loff_t *pos) @@ -768,7 +770,6 @@ const char * const vmstat_text[] = { "kswapd_inodesteal", "kswapd_low_wmark_hit_quickly", "kswapd_high_wmark_hit_quickly", - "kswapd_skip_congestion_wait", "pageoutrun", "allocstall", @@ -791,7 +792,14 @@ const char * const vmstat_text[] = { "compact_stall", "compact_fail", "compact_success", -#endif + +#ifdef CONFIG_BALLOON_COMPACTION + "compact_balloon_isolated", + "compact_balloon_migrated", + "compact_balloon_returned", +#endif /* CONFIG_BALLOON_COMPACTION */ + +#endif /* CONFIG_COMPACTION */ #ifdef CONFIG_HUGETLB_PAGE "htlb_buddy_alloc_success", @@ -890,7 +898,7 @@ static void pagetypeinfo_showblockcount_print(struct seq_file *m, int mtype; unsigned long pfn; unsigned long start_pfn = zone->zone_start_pfn; - unsigned long end_pfn = start_pfn + zone->spanned_pages; + unsigned long end_pfn = zone_end_pfn(zone); unsigned long count[MIGRATE_TYPES] = { 0, }; for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) { diff --git a/net/9p/error.c b/net/9p/error.c index 2ab2de76010f..126fd0dceea2 100644 --- a/net/9p/error.c +++ b/net/9p/error.c @@ -221,15 +221,13 @@ EXPORT_SYMBOL(p9_error_init); int p9_errstr2errno(char *errstr, int len) { int errno; - struct hlist_node *p; struct errormap *c; int bucket; errno = 0; - p = NULL; c = NULL; bucket = jhash(errstr, len, 0) % ERRHASHSZ; - hlist_for_each_entry(c, p, &hash_errmap[bucket], list) { + hlist_for_each_entry(c, &hash_errmap[bucket], list) { if (c->namelen == len && !memcmp(c->name, errstr, len)) { errno = c->val; break; diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index fd05c81cb348..74dea377fe5b 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -87,7 +87,7 @@ struct virtio_chan { /* This is global limit. Since we don't have a global structure, * will be placing it in each channel. */ - int p9_max_pages; + unsigned long p9_max_pages; /* Scatterlist: can be too big for stack. */ struct scatterlist sg[VIRTQUEUE_NUM]; @@ -655,7 +655,7 @@ static struct p9_trans_module p9_virtio_trans = { .create = p9_virtio_create, .close = p9_virtio_close, .request = p9_virtio_request, - .zc_request = p9_virtio_zc_request, + //.zc_request = p9_virtio_zc_request, .cancel = p9_virtio_cancel, /* * We leave one entry for input and one entry for response diff --git a/net/9p/util.c b/net/9p/util.c index 6ceeeb384de7..59f278e64f58 100644 --- a/net/9p/util.c +++ b/net/9p/util.c @@ -87,23 +87,18 @@ EXPORT_SYMBOL(p9_idpool_destroy); int p9_idpool_get(struct p9_idpool *p) { - int i = 0; - int error; + int i; unsigned long flags; -retry: - if (idr_pre_get(&p->pool, GFP_NOFS) == 0) - return -1; - + idr_preload(GFP_NOFS); spin_lock_irqsave(&p->lock, flags); /* no need to store exactly p, we just need something non-null */ - error = idr_get_new(&p->pool, p, &i); - spin_unlock_irqrestore(&p->lock, flags); + i = idr_alloc(&p->pool, p, 0, 0, GFP_NOWAIT); - if (error == -EAGAIN) - goto retry; - else if (error) + spin_unlock_irqrestore(&p->lock, flags); + idr_preload_end(); + if (i < 0) return -1; p9_debug(P9_DEBUG_MUX, " id %d pool %p\n", i, p); diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 33475291c9c1..4a141e3cf076 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -93,10 +93,9 @@ static struct sock *atalk_search_socket(struct sockaddr_at *to, struct atalk_iface *atif) { struct sock *s; - struct hlist_node *node; read_lock_bh(&atalk_sockets_lock); - sk_for_each(s, node, &atalk_sockets) { + sk_for_each(s, &atalk_sockets) { struct atalk_sock *at = at_sk(s); if (to->sat_port != at->src_port) @@ -141,11 +140,10 @@ static struct sock *atalk_find_or_insert_socket(struct sock *sk, struct sockaddr_at *sat) { struct sock *s; - struct hlist_node *node; struct atalk_sock *at; write_lock_bh(&atalk_sockets_lock); - sk_for_each(s, node, &atalk_sockets) { + sk_for_each(s, &atalk_sockets) { at = at_sk(s); if (at->src_net == sat->sat_addr.s_net && @@ -1084,9 +1082,8 @@ static int atalk_pick_and_bind_port(struct sock *sk, struct sockaddr_at *sat) sat->sat_port < ATPORT_LAST; sat->sat_port++) { struct sock *s; - struct hlist_node *node; - sk_for_each(s, node, &atalk_sockets) { + sk_for_each(s, &atalk_sockets) { struct atalk_sock *at = at_sk(s); if (at->src_net == sat->sat_addr.s_net && diff --git a/net/atm/common.c b/net/atm/common.c index 806fc0a40051..7b491006eaf4 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -270,11 +270,11 @@ void atm_dev_release_vccs(struct atm_dev *dev) write_lock_irq(&vcc_sklist_lock); for (i = 0; i < VCC_HTABLE_SIZE; i++) { struct hlist_head *head = &vcc_hash[i]; - struct hlist_node *node, *tmp; + struct hlist_node *tmp; struct sock *s; struct atm_vcc *vcc; - sk_for_each_safe(s, node, tmp, head) { + sk_for_each_safe(s, tmp, head) { vcc = atm_sk(s); if (vcc->dev == dev) { vcc_release_async(vcc, -EPIPE); @@ -317,11 +317,10 @@ static int adjust_tp(struct atm_trafprm *tp, unsigned char aal) static int check_ci(const struct atm_vcc *vcc, short vpi, int vci) { struct hlist_head *head = &vcc_hash[vci & (VCC_HTABLE_SIZE - 1)]; - struct hlist_node *node; struct sock *s; struct atm_vcc *walk; - sk_for_each(s, node, head) { + sk_for_each(s, head) { walk = atm_sk(s); if (walk->dev != vcc->dev) continue; diff --git a/net/atm/lec.c b/net/atm/lec.c index 2e3d942e77f1..f23916be18fb 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -842,7 +842,9 @@ static void *lec_tbl_walk(struct lec_state *state, struct hlist_head *tbl, --*l; } - hlist_for_each_entry_from(tmp, e, next) { + tmp = container_of(e, struct lec_arp_table, next); + + hlist_for_each_entry_from(tmp, next) { if (--*l < 0) break; } @@ -1307,7 +1309,6 @@ lec_arp_add(struct lec_priv *priv, struct lec_arp_table *entry) static int lec_arp_remove(struct lec_priv *priv, struct lec_arp_table *to_remove) { - struct hlist_node *node; struct lec_arp_table *entry; int i, remove_vcc = 1; @@ -1326,7 +1327,7 @@ lec_arp_remove(struct lec_priv *priv, struct lec_arp_table *to_remove) * ESI_FLUSH_PENDING, ESI_FORWARD_DIRECT */ for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { - hlist_for_each_entry(entry, node, + hlist_for_each_entry(entry, &priv->lec_arp_tables[i], next) { if (memcmp(to_remove->atm_addr, entry->atm_addr, ATM_ESA_LEN) == 0) { @@ -1364,14 +1365,13 @@ static const char *get_status_string(unsigned char st) static void dump_arp_table(struct lec_priv *priv) { - struct hlist_node *node; struct lec_arp_table *rulla; char buf[256]; int i, j, offset; pr_info("Dump %p:\n", priv); for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { - hlist_for_each_entry(rulla, node, + hlist_for_each_entry(rulla, &priv->lec_arp_tables[i], next) { offset = 0; offset += sprintf(buf, "%d: %p\n", i, rulla); @@ -1403,7 +1403,7 @@ static void dump_arp_table(struct lec_priv *priv) if (!hlist_empty(&priv->lec_no_forward)) pr_info("No forward\n"); - hlist_for_each_entry(rulla, node, &priv->lec_no_forward, next) { + hlist_for_each_entry(rulla, &priv->lec_no_forward, next) { offset = 0; offset += sprintf(buf + offset, "Mac: %pM", rulla->mac_addr); offset += sprintf(buf + offset, " Atm:"); @@ -1428,7 +1428,7 @@ static void dump_arp_table(struct lec_priv *priv) if (!hlist_empty(&priv->lec_arp_empty_ones)) pr_info("Empty ones\n"); - hlist_for_each_entry(rulla, node, &priv->lec_arp_empty_ones, next) { + hlist_for_each_entry(rulla, &priv->lec_arp_empty_ones, next) { offset = 0; offset += sprintf(buf + offset, "Mac: %pM", rulla->mac_addr); offset += sprintf(buf + offset, " Atm:"); @@ -1453,7 +1453,7 @@ static void dump_arp_table(struct lec_priv *priv) if (!hlist_empty(&priv->mcast_fwds)) pr_info("Multicast Forward VCCs\n"); - hlist_for_each_entry(rulla, node, &priv->mcast_fwds, next) { + hlist_for_each_entry(rulla, &priv->mcast_fwds, next) { offset = 0; offset += sprintf(buf + offset, "Mac: %pM", rulla->mac_addr); offset += sprintf(buf + offset, " Atm:"); @@ -1487,7 +1487,7 @@ static void dump_arp_table(struct lec_priv *priv) static void lec_arp_destroy(struct lec_priv *priv) { unsigned long flags; - struct hlist_node *node, *next; + struct hlist_node *next; struct lec_arp_table *entry; int i; @@ -1499,7 +1499,7 @@ static void lec_arp_destroy(struct lec_priv *priv) spin_lock_irqsave(&priv->lec_arp_lock, flags); for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { - hlist_for_each_entry_safe(entry, node, next, + hlist_for_each_entry_safe(entry, next, &priv->lec_arp_tables[i], next) { lec_arp_remove(priv, entry); lec_arp_put(entry); @@ -1507,7 +1507,7 @@ static void lec_arp_destroy(struct lec_priv *priv) INIT_HLIST_HEAD(&priv->lec_arp_tables[i]); } - hlist_for_each_entry_safe(entry, node, next, + hlist_for_each_entry_safe(entry, next, &priv->lec_arp_empty_ones, next) { del_timer_sync(&entry->timer); lec_arp_clear_vccs(entry); @@ -1516,7 +1516,7 @@ static void lec_arp_destroy(struct lec_priv *priv) } INIT_HLIST_HEAD(&priv->lec_arp_empty_ones); - hlist_for_each_entry_safe(entry, node, next, + hlist_for_each_entry_safe(entry, next, &priv->lec_no_forward, next) { del_timer_sync(&entry->timer); lec_arp_clear_vccs(entry); @@ -1525,7 +1525,7 @@ static void lec_arp_destroy(struct lec_priv *priv) } INIT_HLIST_HEAD(&priv->lec_no_forward); - hlist_for_each_entry_safe(entry, node, next, &priv->mcast_fwds, next) { + hlist_for_each_entry_safe(entry, next, &priv->mcast_fwds, next) { /* No timer, LANEv2 7.1.20 and 2.3.5.3 */ lec_arp_clear_vccs(entry); hlist_del(&entry->next); @@ -1542,14 +1542,13 @@ static void lec_arp_destroy(struct lec_priv *priv) static struct lec_arp_table *lec_arp_find(struct lec_priv *priv, const unsigned char *mac_addr) { - struct hlist_node *node; struct hlist_head *head; struct lec_arp_table *entry; pr_debug("%pM\n", mac_addr); head = &priv->lec_arp_tables[HASH(mac_addr[ETH_ALEN - 1])]; - hlist_for_each_entry(entry, node, head, next) { + hlist_for_each_entry(entry, head, next) { if (ether_addr_equal(mac_addr, entry->mac_addr)) return entry; } @@ -1686,7 +1685,7 @@ static void lec_arp_check_expire(struct work_struct *work) unsigned long flags; struct lec_priv *priv = container_of(work, struct lec_priv, lec_arp_work.work); - struct hlist_node *node, *next; + struct hlist_node *next; struct lec_arp_table *entry; unsigned long now; int i; @@ -1696,7 +1695,7 @@ static void lec_arp_check_expire(struct work_struct *work) restart: spin_lock_irqsave(&priv->lec_arp_lock, flags); for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { - hlist_for_each_entry_safe(entry, node, next, + hlist_for_each_entry_safe(entry, next, &priv->lec_arp_tables[i], next) { if (__lec_arp_check_expire(entry, now, priv)) { struct sk_buff *skb; @@ -1823,14 +1822,14 @@ lec_addr_delete(struct lec_priv *priv, const unsigned char *atm_addr, unsigned long permanent) { unsigned long flags; - struct hlist_node *node, *next; + struct hlist_node *next; struct lec_arp_table *entry; int i; pr_debug("\n"); spin_lock_irqsave(&priv->lec_arp_lock, flags); for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { - hlist_for_each_entry_safe(entry, node, next, + hlist_for_each_entry_safe(entry, next, &priv->lec_arp_tables[i], next) { if (!memcmp(atm_addr, entry->atm_addr, ATM_ESA_LEN) && (permanent || @@ -1855,7 +1854,7 @@ lec_arp_update(struct lec_priv *priv, const unsigned char *mac_addr, unsigned int targetless_le_arp) { unsigned long flags; - struct hlist_node *node, *next; + struct hlist_node *next; struct lec_arp_table *entry, *tmp; int i; @@ -1870,7 +1869,7 @@ lec_arp_update(struct lec_priv *priv, const unsigned char *mac_addr, * we have no entry in the cache. 7.1.30 */ if (!hlist_empty(&priv->lec_arp_empty_ones)) { - hlist_for_each_entry_safe(entry, node, next, + hlist_for_each_entry_safe(entry, next, &priv->lec_arp_empty_ones, next) { if (memcmp(entry->atm_addr, atm_addr, ATM_ESA_LEN) == 0) { hlist_del(&entry->next); @@ -1915,7 +1914,7 @@ lec_arp_update(struct lec_priv *priv, const unsigned char *mac_addr, memcpy(entry->atm_addr, atm_addr, ATM_ESA_LEN); del_timer(&entry->timer); for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { - hlist_for_each_entry(tmp, node, + hlist_for_each_entry(tmp, &priv->lec_arp_tables[i], next) { if (entry != tmp && !memcmp(tmp->atm_addr, atm_addr, ATM_ESA_LEN)) { @@ -1956,7 +1955,6 @@ lec_vcc_added(struct lec_priv *priv, const struct atmlec_ioc *ioc_data, void (*old_push) (struct atm_vcc *vcc, struct sk_buff *skb)) { unsigned long flags; - struct hlist_node *node; struct lec_arp_table *entry; int i, found_entry = 0; @@ -2026,7 +2024,7 @@ lec_vcc_added(struct lec_priv *priv, const struct atmlec_ioc *ioc_data, ioc_data->atm_addr[16], ioc_data->atm_addr[17], ioc_data->atm_addr[18], ioc_data->atm_addr[19]); for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { - hlist_for_each_entry(entry, node, + hlist_for_each_entry(entry, &priv->lec_arp_tables[i], next) { if (memcmp (ioc_data->atm_addr, entry->atm_addr, @@ -2103,7 +2101,6 @@ out: static void lec_flush_complete(struct lec_priv *priv, unsigned long tran_id) { unsigned long flags; - struct hlist_node *node; struct lec_arp_table *entry; int i; @@ -2111,7 +2108,7 @@ static void lec_flush_complete(struct lec_priv *priv, unsigned long tran_id) restart: spin_lock_irqsave(&priv->lec_arp_lock, flags); for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { - hlist_for_each_entry(entry, node, + hlist_for_each_entry(entry, &priv->lec_arp_tables[i], next) { if (entry->flush_tran_id == tran_id && entry->status == ESI_FLUSH_PENDING) { @@ -2140,13 +2137,12 @@ lec_set_flush_tran_id(struct lec_priv *priv, const unsigned char *atm_addr, unsigned long tran_id) { unsigned long flags; - struct hlist_node *node; struct lec_arp_table *entry; int i; spin_lock_irqsave(&priv->lec_arp_lock, flags); for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) - hlist_for_each_entry(entry, node, + hlist_for_each_entry(entry, &priv->lec_arp_tables[i], next) { if (!memcmp(atm_addr, entry->atm_addr, ATM_ESA_LEN)) { entry->flush_tran_id = tran_id; @@ -2198,7 +2194,7 @@ out: static void lec_vcc_close(struct lec_priv *priv, struct atm_vcc *vcc) { unsigned long flags; - struct hlist_node *node, *next; + struct hlist_node *next; struct lec_arp_table *entry; int i; @@ -2208,7 +2204,7 @@ static void lec_vcc_close(struct lec_priv *priv, struct atm_vcc *vcc) spin_lock_irqsave(&priv->lec_arp_lock, flags); for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { - hlist_for_each_entry_safe(entry, node, next, + hlist_for_each_entry_safe(entry, next, &priv->lec_arp_tables[i], next) { if (vcc == entry->vcc) { lec_arp_remove(priv, entry); @@ -2219,7 +2215,7 @@ static void lec_vcc_close(struct lec_priv *priv, struct atm_vcc *vcc) } } - hlist_for_each_entry_safe(entry, node, next, + hlist_for_each_entry_safe(entry, next, &priv->lec_arp_empty_ones, next) { if (entry->vcc == vcc) { lec_arp_clear_vccs(entry); @@ -2229,7 +2225,7 @@ static void lec_vcc_close(struct lec_priv *priv, struct atm_vcc *vcc) } } - hlist_for_each_entry_safe(entry, node, next, + hlist_for_each_entry_safe(entry, next, &priv->lec_no_forward, next) { if (entry->recv_vcc == vcc) { lec_arp_clear_vccs(entry); @@ -2239,7 +2235,7 @@ static void lec_vcc_close(struct lec_priv *priv, struct atm_vcc *vcc) } } - hlist_for_each_entry_safe(entry, node, next, &priv->mcast_fwds, next) { + hlist_for_each_entry_safe(entry, next, &priv->mcast_fwds, next) { if (entry->recv_vcc == vcc) { lec_arp_clear_vccs(entry); /* No timer, LANEv2 7.1.20 and 2.3.5.3 */ @@ -2257,13 +2253,13 @@ lec_arp_check_empties(struct lec_priv *priv, struct atm_vcc *vcc, struct sk_buff *skb) { unsigned long flags; - struct hlist_node *node, *next; + struct hlist_node *next; struct lec_arp_table *entry, *tmp; struct lecdatahdr_8023 *hdr = (struct lecdatahdr_8023 *)skb->data; unsigned char *src = hdr->h_source; spin_lock_irqsave(&priv->lec_arp_lock, flags); - hlist_for_each_entry_safe(entry, node, next, + hlist_for_each_entry_safe(entry, next, &priv->lec_arp_empty_ones, next) { if (vcc == entry->vcc) { del_timer(&entry->timer); diff --git a/net/atm/signaling.c b/net/atm/signaling.c index 86767ca908a3..4176887e72eb 100644 --- a/net/atm/signaling.c +++ b/net/atm/signaling.c @@ -217,7 +217,6 @@ static void purge_vcc(struct atm_vcc *vcc) static void sigd_close(struct atm_vcc *vcc) { - struct hlist_node *node; struct sock *s; int i; @@ -231,7 +230,7 @@ static void sigd_close(struct atm_vcc *vcc) for (i = 0; i < VCC_HTABLE_SIZE; ++i) { struct hlist_head *head = &vcc_hash[i]; - sk_for_each(s, node, head) { + sk_for_each(s, head) { vcc = atm_sk(s); purge_vcc(vcc); diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 779095ded689..282c66ae09f0 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -81,14 +81,13 @@ static void ax25_kill_by_device(struct net_device *dev) { ax25_dev *ax25_dev; ax25_cb *s; - struct hlist_node *node; if ((ax25_dev = ax25_dev_ax25dev(dev)) == NULL) return; spin_lock_bh(&ax25_list_lock); again: - ax25_for_each(s, node, &ax25_list) { + ax25_for_each(s, &ax25_list) { if (s->ax25_dev == ax25_dev) { s->ax25_dev = NULL; spin_unlock_bh(&ax25_list_lock); @@ -158,10 +157,9 @@ struct sock *ax25_find_listener(ax25_address *addr, int digi, struct net_device *dev, int type) { ax25_cb *s; - struct hlist_node *node; spin_lock(&ax25_list_lock); - ax25_for_each(s, node, &ax25_list) { + ax25_for_each(s, &ax25_list) { if ((s->iamdigi && !digi) || (!s->iamdigi && digi)) continue; if (s->sk && !ax25cmp(&s->source_addr, addr) && @@ -187,10 +185,9 @@ struct sock *ax25_get_socket(ax25_address *my_addr, ax25_address *dest_addr, { struct sock *sk = NULL; ax25_cb *s; - struct hlist_node *node; spin_lock(&ax25_list_lock); - ax25_for_each(s, node, &ax25_list) { + ax25_for_each(s, &ax25_list) { if (s->sk && !ax25cmp(&s->source_addr, my_addr) && !ax25cmp(&s->dest_addr, dest_addr) && s->sk->sk_type == type) { @@ -213,10 +210,9 @@ ax25_cb *ax25_find_cb(ax25_address *src_addr, ax25_address *dest_addr, ax25_digi *digi, struct net_device *dev) { ax25_cb *s; - struct hlist_node *node; spin_lock_bh(&ax25_list_lock); - ax25_for_each(s, node, &ax25_list) { + ax25_for_each(s, &ax25_list) { if (s->sk && s->sk->sk_type != SOCK_SEQPACKET) continue; if (s->ax25_dev == NULL) @@ -248,10 +244,9 @@ void ax25_send_to_raw(ax25_address *addr, struct sk_buff *skb, int proto) { ax25_cb *s; struct sk_buff *copy; - struct hlist_node *node; spin_lock(&ax25_list_lock); - ax25_for_each(s, node, &ax25_list) { + ax25_for_each(s, &ax25_list) { if (s->sk != NULL && ax25cmp(&s->source_addr, addr) == 0 && s->sk->sk_type == SOCK_RAW && s->sk->sk_protocol == proto && diff --git a/net/ax25/ax25_ds_subr.c b/net/ax25/ax25_ds_subr.c index 5ea7fd3e2af9..e05bd57b5afd 100644 --- a/net/ax25/ax25_ds_subr.c +++ b/net/ax25/ax25_ds_subr.c @@ -39,7 +39,6 @@ void ax25_ds_nr_error_recovery(ax25_cb *ax25) void ax25_ds_enquiry_response(ax25_cb *ax25) { ax25_cb *ax25o; - struct hlist_node *node; /* Please note that neither DK4EG's nor DG2FEF's * DAMA spec mention the following behaviour as seen @@ -80,7 +79,7 @@ void ax25_ds_enquiry_response(ax25_cb *ax25) ax25_ds_set_timer(ax25->ax25_dev); spin_lock(&ax25_list_lock); - ax25_for_each(ax25o, node, &ax25_list) { + ax25_for_each(ax25o, &ax25_list) { if (ax25o == ax25) continue; @@ -159,10 +158,9 @@ static int ax25_check_dama_slave(ax25_dev *ax25_dev) { ax25_cb *ax25; int res = 0; - struct hlist_node *node; spin_lock(&ax25_list_lock); - ax25_for_each(ax25, node, &ax25_list) + ax25_for_each(ax25, &ax25_list) if (ax25->ax25_dev == ax25_dev && (ax25->condition & AX25_COND_DAMA_MODE) && ax25->state > AX25_STATE_1) { res = 1; break; diff --git a/net/ax25/ax25_ds_timer.c b/net/ax25/ax25_ds_timer.c index 993c439b4f71..951cd57bb07d 100644 --- a/net/ax25/ax25_ds_timer.c +++ b/net/ax25/ax25_ds_timer.c @@ -70,7 +70,6 @@ static void ax25_ds_timeout(unsigned long arg) { ax25_dev *ax25_dev = (struct ax25_dev *) arg; ax25_cb *ax25; - struct hlist_node *node; if (ax25_dev == NULL || !ax25_dev->dama.slave) return; /* Yikes! */ @@ -81,7 +80,7 @@ static void ax25_ds_timeout(unsigned long arg) } spin_lock(&ax25_list_lock); - ax25_for_each(ax25, node, &ax25_list) { + ax25_for_each(ax25, &ax25_list) { if (ax25->ax25_dev != ax25_dev || !(ax25->condition & AX25_COND_DAMA_MODE)) continue; diff --git a/net/ax25/ax25_iface.c b/net/ax25/ax25_iface.c index 7d5f24b82cc8..7f16e8a931b2 100644 --- a/net/ax25/ax25_iface.c +++ b/net/ax25/ax25_iface.c @@ -193,10 +193,9 @@ int ax25_listen_mine(ax25_address *callsign, struct net_device *dev) void ax25_link_failed(ax25_cb *ax25, int reason) { struct ax25_linkfail *lf; - struct hlist_node *node; spin_lock_bh(&linkfail_lock); - hlist_for_each_entry(lf, node, &ax25_linkfail_list, lf_node) + hlist_for_each_entry(lf, &ax25_linkfail_list, lf_node) lf->func(ax25, reason); spin_unlock_bh(&linkfail_lock); } diff --git a/net/ax25/ax25_uid.c b/net/ax25/ax25_uid.c index 957999e43ff7..71c4badbc807 100644 --- a/net/ax25/ax25_uid.c +++ b/net/ax25/ax25_uid.c @@ -54,10 +54,9 @@ EXPORT_SYMBOL(ax25_uid_policy); ax25_uid_assoc *ax25_findbyuid(kuid_t uid) { ax25_uid_assoc *ax25_uid, *res = NULL; - struct hlist_node *node; read_lock(&ax25_uid_lock); - ax25_uid_for_each(ax25_uid, node, &ax25_uid_list) { + ax25_uid_for_each(ax25_uid, &ax25_uid_list) { if (uid_eq(ax25_uid->uid, uid)) { ax25_uid_hold(ax25_uid); res = ax25_uid; @@ -74,7 +73,6 @@ EXPORT_SYMBOL(ax25_findbyuid); int ax25_uid_ioctl(int cmd, struct sockaddr_ax25 *sax) { ax25_uid_assoc *ax25_uid; - struct hlist_node *node; ax25_uid_assoc *user; unsigned long res; @@ -82,7 +80,7 @@ int ax25_uid_ioctl(int cmd, struct sockaddr_ax25 *sax) case SIOCAX25GETUID: res = -ENOENT; read_lock(&ax25_uid_lock); - ax25_uid_for_each(ax25_uid, node, &ax25_uid_list) { + ax25_uid_for_each(ax25_uid, &ax25_uid_list) { if (ax25cmp(&sax->sax25_call, &ax25_uid->call) == 0) { res = from_kuid_munged(current_user_ns(), ax25_uid->uid); break; @@ -126,7 +124,7 @@ int ax25_uid_ioctl(int cmd, struct sockaddr_ax25 *sax) ax25_uid = NULL; write_lock(&ax25_uid_lock); - ax25_uid_for_each(ax25_uid, node, &ax25_uid_list) { + ax25_uid_for_each(ax25_uid, &ax25_uid_list) { if (ax25cmp(&sax->sax25_call, &ax25_uid->call) == 0) break; } @@ -212,11 +210,10 @@ const struct file_operations ax25_uid_fops = { void __exit ax25_uid_free(void) { ax25_uid_assoc *ax25_uid; - struct hlist_node *node; write_lock(&ax25_uid_lock); again: - ax25_uid_for_each(ax25_uid, node, &ax25_uid_list) { + ax25_uid_for_each(ax25_uid, &ax25_uid_list) { hlist_del_init(&ax25_uid->uid_node); ax25_uid_put(ax25_uid); goto again; diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 72fe1bbf7721..a0b253ecadaf 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -487,7 +487,6 @@ static void batadv_iv_ogm_queue_add(struct batadv_priv *bat_priv, */ struct batadv_forw_packet *forw_packet_aggr = NULL; struct batadv_forw_packet *forw_packet_pos = NULL; - struct hlist_node *tmp_node; struct batadv_ogm_packet *batadv_ogm_packet; bool direct_link; unsigned long max_aggregation_jiffies; @@ -500,7 +499,7 @@ static void batadv_iv_ogm_queue_add(struct batadv_priv *bat_priv, spin_lock_bh(&bat_priv->forw_bat_list_lock); /* own packets are not to be aggregated */ if ((atomic_read(&bat_priv->aggregated_ogms)) && (!own_packet)) { - hlist_for_each_entry(forw_packet_pos, tmp_node, + hlist_for_each_entry(forw_packet_pos, &bat_priv->forw_bat_list, list) { if (batadv_iv_ogm_can_aggregate(batadv_ogm_packet, bat_priv, packet_len, @@ -655,7 +654,6 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, struct batadv_neigh_node *neigh_node = NULL, *tmp_neigh_node = NULL; struct batadv_neigh_node *router = NULL; struct batadv_orig_node *orig_node_tmp; - struct hlist_node *node; int if_num; uint8_t sum_orig, sum_neigh; uint8_t *neigh_addr; @@ -665,7 +663,7 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, "update_originator(): Searching and updating originator entry of received packet\n"); rcu_read_lock(); - hlist_for_each_entry_rcu(tmp_neigh_node, node, + hlist_for_each_entry_rcu(tmp_neigh_node, &orig_node->neigh_list, list) { neigh_addr = tmp_neigh_node->addr; if (batadv_compare_eth(neigh_addr, ethhdr->h_source) && @@ -801,7 +799,6 @@ static int batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, { struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); struct batadv_neigh_node *neigh_node = NULL, *tmp_neigh_node; - struct hlist_node *node; uint8_t total_count; uint8_t orig_eq_count, neigh_rq_count, neigh_rq_inv, tq_own; unsigned int neigh_rq_inv_cube, neigh_rq_max_cube; @@ -810,7 +807,7 @@ static int batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, /* find corresponding one hop neighbor */ rcu_read_lock(); - hlist_for_each_entry_rcu(tmp_neigh_node, node, + hlist_for_each_entry_rcu(tmp_neigh_node, &orig_neigh_node->neigh_list, list) { if (!batadv_compare_eth(tmp_neigh_node->addr, orig_neigh_node->orig)) @@ -920,7 +917,6 @@ batadv_iv_ogm_update_seqnos(const struct ethhdr *ethhdr, struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); struct batadv_orig_node *orig_node; struct batadv_neigh_node *tmp_neigh_node; - struct hlist_node *node; int is_duplicate = 0; int32_t seq_diff; int need_update = 0; @@ -943,7 +939,7 @@ batadv_iv_ogm_update_seqnos(const struct ethhdr *ethhdr, goto out; rcu_read_lock(); - hlist_for_each_entry_rcu(tmp_neigh_node, node, + hlist_for_each_entry_rcu(tmp_neigh_node, &orig_node->neigh_list, list) { is_duplicate |= batadv_test_bit(tmp_neigh_node->real_bits, orig_node->last_real_seqno, diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 30f46526cbbd..6a4f728680ae 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -144,7 +144,6 @@ static struct batadv_bla_claim { struct batadv_hashtable *hash = bat_priv->bla.claim_hash; struct hlist_head *head; - struct hlist_node *node; struct batadv_bla_claim *claim; struct batadv_bla_claim *claim_tmp = NULL; int index; @@ -156,7 +155,7 @@ static struct batadv_bla_claim head = &hash->table[index]; rcu_read_lock(); - hlist_for_each_entry_rcu(claim, node, head, hash_entry) { + hlist_for_each_entry_rcu(claim, head, hash_entry) { if (!batadv_compare_claim(&claim->hash_entry, data)) continue; @@ -185,7 +184,6 @@ batadv_backbone_hash_find(struct batadv_priv *bat_priv, { struct batadv_hashtable *hash = bat_priv->bla.backbone_hash; struct hlist_head *head; - struct hlist_node *node; struct batadv_bla_backbone_gw search_entry, *backbone_gw; struct batadv_bla_backbone_gw *backbone_gw_tmp = NULL; int index; @@ -200,7 +198,7 @@ batadv_backbone_hash_find(struct batadv_priv *bat_priv, head = &hash->table[index]; rcu_read_lock(); - hlist_for_each_entry_rcu(backbone_gw, node, head, hash_entry) { + hlist_for_each_entry_rcu(backbone_gw, head, hash_entry) { if (!batadv_compare_backbone_gw(&backbone_gw->hash_entry, &search_entry)) continue; @@ -221,7 +219,7 @@ static void batadv_bla_del_backbone_claims(struct batadv_bla_backbone_gw *backbone_gw) { struct batadv_hashtable *hash; - struct hlist_node *node, *node_tmp; + struct hlist_node *node_tmp; struct hlist_head *head; struct batadv_bla_claim *claim; int i; @@ -236,13 +234,13 @@ batadv_bla_del_backbone_claims(struct batadv_bla_backbone_gw *backbone_gw) list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); - hlist_for_each_entry_safe(claim, node, node_tmp, + hlist_for_each_entry_safe(claim, node_tmp, head, hash_entry) { if (claim->backbone_gw != backbone_gw) continue; batadv_claim_free_ref(claim); - hlist_del_rcu(node); + hlist_del_rcu(&claim->hash_entry); } spin_unlock_bh(list_lock); } @@ -460,7 +458,6 @@ static void batadv_bla_answer_request(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, short vid) { - struct hlist_node *node; struct hlist_head *head; struct batadv_hashtable *hash; struct batadv_bla_claim *claim; @@ -481,7 +478,7 @@ static void batadv_bla_answer_request(struct batadv_priv *bat_priv, head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(claim, node, head, hash_entry) { + hlist_for_each_entry_rcu(claim, head, hash_entry) { /* only own claims are interesting */ if (claim->backbone_gw != backbone_gw) continue; @@ -958,7 +955,7 @@ static int batadv_bla_process_claim(struct batadv_priv *bat_priv, static void batadv_bla_purge_backbone_gw(struct batadv_priv *bat_priv, int now) { struct batadv_bla_backbone_gw *backbone_gw; - struct hlist_node *node, *node_tmp; + struct hlist_node *node_tmp; struct hlist_head *head; struct batadv_hashtable *hash; spinlock_t *list_lock; /* protects write access to the hash lists */ @@ -973,7 +970,7 @@ static void batadv_bla_purge_backbone_gw(struct batadv_priv *bat_priv, int now) list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); - hlist_for_each_entry_safe(backbone_gw, node, node_tmp, + hlist_for_each_entry_safe(backbone_gw, node_tmp, head, hash_entry) { if (now) goto purge_now; @@ -992,7 +989,7 @@ purge_now: batadv_bla_del_backbone_claims(backbone_gw); - hlist_del_rcu(node); + hlist_del_rcu(&backbone_gw->hash_entry); batadv_backbone_gw_free_ref(backbone_gw); } spin_unlock_bh(list_lock); @@ -1013,7 +1010,6 @@ static void batadv_bla_purge_claims(struct batadv_priv *bat_priv, int now) { struct batadv_bla_claim *claim; - struct hlist_node *node; struct hlist_head *head; struct batadv_hashtable *hash; int i; @@ -1026,7 +1022,7 @@ static void batadv_bla_purge_claims(struct batadv_priv *bat_priv, head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(claim, node, head, hash_entry) { + hlist_for_each_entry_rcu(claim, head, hash_entry) { if (now) goto purge_now; if (!batadv_compare_eth(claim->backbone_gw->orig, @@ -1062,7 +1058,6 @@ void batadv_bla_update_orig_address(struct batadv_priv *bat_priv, struct batadv_hard_iface *oldif) { struct batadv_bla_backbone_gw *backbone_gw; - struct hlist_node *node; struct hlist_head *head; struct batadv_hashtable *hash; __be16 group; @@ -1086,7 +1081,7 @@ void batadv_bla_update_orig_address(struct batadv_priv *bat_priv, head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(backbone_gw, node, head, hash_entry) { + hlist_for_each_entry_rcu(backbone_gw, head, hash_entry) { /* own orig still holds the old value. */ if (!batadv_compare_eth(backbone_gw->orig, oldif->net_dev->dev_addr)) @@ -1112,7 +1107,6 @@ static void batadv_bla_periodic_work(struct work_struct *work) struct delayed_work *delayed_work; struct batadv_priv *bat_priv; struct batadv_priv_bla *priv_bla; - struct hlist_node *node; struct hlist_head *head; struct batadv_bla_backbone_gw *backbone_gw; struct batadv_hashtable *hash; @@ -1140,7 +1134,7 @@ static void batadv_bla_periodic_work(struct work_struct *work) head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(backbone_gw, node, head, hash_entry) { + hlist_for_each_entry_rcu(backbone_gw, head, hash_entry) { if (!batadv_compare_eth(backbone_gw->orig, primary_if->net_dev->dev_addr)) continue; @@ -1322,7 +1316,6 @@ int batadv_bla_is_backbone_gw_orig(struct batadv_priv *bat_priv, uint8_t *orig) { struct batadv_hashtable *hash = bat_priv->bla.backbone_hash; struct hlist_head *head; - struct hlist_node *node; struct batadv_bla_backbone_gw *backbone_gw; int i; @@ -1336,7 +1329,7 @@ int batadv_bla_is_backbone_gw_orig(struct batadv_priv *bat_priv, uint8_t *orig) head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(backbone_gw, node, head, hash_entry) { + hlist_for_each_entry_rcu(backbone_gw, head, hash_entry) { if (batadv_compare_eth(backbone_gw->orig, orig)) { rcu_read_unlock(); return 1; @@ -1607,7 +1600,6 @@ int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset) struct batadv_hashtable *hash = bat_priv->bla.claim_hash; struct batadv_bla_claim *claim; struct batadv_hard_iface *primary_if; - struct hlist_node *node; struct hlist_head *head; uint32_t i; bool is_own; @@ -1628,7 +1620,7 @@ int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset) head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(claim, node, head, hash_entry) { + hlist_for_each_entry_rcu(claim, head, hash_entry) { is_own = batadv_compare_eth(claim->backbone_gw->orig, primary_addr); seq_printf(seq, " * %pM on % 5d by %pM [%c] (%#.4x)\n", @@ -1652,7 +1644,6 @@ int batadv_bla_backbone_table_seq_print_text(struct seq_file *seq, void *offset) struct batadv_hashtable *hash = bat_priv->bla.backbone_hash; struct batadv_bla_backbone_gw *backbone_gw; struct batadv_hard_iface *primary_if; - struct hlist_node *node; struct hlist_head *head; int secs, msecs; uint32_t i; @@ -1674,7 +1665,7 @@ int batadv_bla_backbone_table_seq_print_text(struct seq_file *seq, void *offset) head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(backbone_gw, node, head, hash_entry) { + hlist_for_each_entry_rcu(backbone_gw, head, hash_entry) { msecs = jiffies_to_msecs(jiffies - backbone_gw->lasttime); secs = msecs / 1000; diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index ea0bd31d41c2..0e05ad4a7343 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -83,7 +83,7 @@ static void __batadv_dat_purge(struct batadv_priv *bat_priv, { spinlock_t *list_lock; /* protects write access to the hash lists */ struct batadv_dat_entry *dat_entry; - struct hlist_node *node, *node_tmp; + struct hlist_node *node_tmp; struct hlist_head *head; uint32_t i; @@ -95,7 +95,7 @@ static void __batadv_dat_purge(struct batadv_priv *bat_priv, list_lock = &bat_priv->dat.hash->list_locks[i]; spin_lock_bh(list_lock); - hlist_for_each_entry_safe(dat_entry, node, node_tmp, head, + hlist_for_each_entry_safe(dat_entry, node_tmp, head, hash_entry) { /* if an helper function has been passed as parameter, * ask it if the entry has to be purged or not @@ -103,7 +103,7 @@ static void __batadv_dat_purge(struct batadv_priv *bat_priv, if (to_purge && !to_purge(dat_entry)) continue; - hlist_del_rcu(node); + hlist_del_rcu(&dat_entry->hash_entry); batadv_dat_entry_free_ref(dat_entry); } spin_unlock_bh(list_lock); @@ -235,7 +235,6 @@ static struct batadv_dat_entry * batadv_dat_entry_hash_find(struct batadv_priv *bat_priv, __be32 ip) { struct hlist_head *head; - struct hlist_node *node; struct batadv_dat_entry *dat_entry, *dat_entry_tmp = NULL; struct batadv_hashtable *hash = bat_priv->dat.hash; uint32_t index; @@ -247,7 +246,7 @@ batadv_dat_entry_hash_find(struct batadv_priv *bat_priv, __be32 ip) head = &hash->table[index]; rcu_read_lock(); - hlist_for_each_entry_rcu(dat_entry, node, head, hash_entry) { + hlist_for_each_entry_rcu(dat_entry, head, hash_entry) { if (dat_entry->ip != ip) continue; @@ -465,7 +464,6 @@ static void batadv_choose_next_candidate(struct batadv_priv *bat_priv, batadv_dat_addr_t max = 0, tmp_max = 0; struct batadv_orig_node *orig_node, *max_orig_node = NULL; struct batadv_hashtable *hash = bat_priv->orig_hash; - struct hlist_node *node; struct hlist_head *head; int i; @@ -481,7 +479,7 @@ static void batadv_choose_next_candidate(struct batadv_priv *bat_priv, head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(orig_node, node, head, hash_entry) { + hlist_for_each_entry_rcu(orig_node, head, hash_entry) { /* the dht space is a ring and addresses are unsigned */ tmp_max = BATADV_DAT_ADDR_MAX - orig_node->dat_addr + ip_key; @@ -686,7 +684,6 @@ int batadv_dat_cache_seq_print_text(struct seq_file *seq, void *offset) struct batadv_hashtable *hash = bat_priv->dat.hash; struct batadv_dat_entry *dat_entry; struct batadv_hard_iface *primary_if; - struct hlist_node *node; struct hlist_head *head; unsigned long last_seen_jiffies; int last_seen_msecs, last_seen_secs, last_seen_mins; @@ -704,7 +701,7 @@ int batadv_dat_cache_seq_print_text(struct seq_file *seq, void *offset) head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(dat_entry, node, head, hash_entry) { + hlist_for_each_entry_rcu(dat_entry, head, hash_entry) { last_seen_jiffies = jiffies - dat_entry->last_update; last_seen_msecs = jiffies_to_msecs(last_seen_jiffies); last_seen_mins = last_seen_msecs / 60000; diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 074107f2cfaa..34f99a46ec1d 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -114,7 +114,6 @@ static struct batadv_gw_node * batadv_gw_get_best_gw_node(struct batadv_priv *bat_priv) { struct batadv_neigh_node *router; - struct hlist_node *node; struct batadv_gw_node *gw_node, *curr_gw = NULL; uint32_t max_gw_factor = 0, tmp_gw_factor = 0; uint32_t gw_divisor; @@ -127,7 +126,7 @@ batadv_gw_get_best_gw_node(struct batadv_priv *bat_priv) gw_divisor *= 64; rcu_read_lock(); - hlist_for_each_entry_rcu(gw_node, node, &bat_priv->gw.list, list) { + hlist_for_each_entry_rcu(gw_node, &bat_priv->gw.list, list) { if (gw_node->deleted) continue; @@ -344,7 +343,6 @@ void batadv_gw_node_update(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, uint8_t new_gwflags) { - struct hlist_node *node; struct batadv_gw_node *gw_node, *curr_gw; /* Note: We don't need a NULL check here, since curr_gw never gets @@ -355,7 +353,7 @@ void batadv_gw_node_update(struct batadv_priv *bat_priv, curr_gw = batadv_gw_get_selected_gw_node(bat_priv); rcu_read_lock(); - hlist_for_each_entry_rcu(gw_node, node, &bat_priv->gw.list, list) { + hlist_for_each_entry_rcu(gw_node, &bat_priv->gw.list, list) { if (gw_node->orig_node != orig_node) continue; @@ -403,7 +401,7 @@ void batadv_gw_node_delete(struct batadv_priv *bat_priv, void batadv_gw_node_purge(struct batadv_priv *bat_priv) { struct batadv_gw_node *gw_node, *curr_gw; - struct hlist_node *node, *node_tmp; + struct hlist_node *node_tmp; unsigned long timeout = msecs_to_jiffies(2 * BATADV_PURGE_TIMEOUT); int do_deselect = 0; @@ -411,7 +409,7 @@ void batadv_gw_node_purge(struct batadv_priv *bat_priv) spin_lock_bh(&bat_priv->gw.list_lock); - hlist_for_each_entry_safe(gw_node, node, node_tmp, + hlist_for_each_entry_safe(gw_node, node_tmp, &bat_priv->gw.list, list) { if (((!gw_node->deleted) || (time_before(jiffies, gw_node->deleted + timeout))) && @@ -476,7 +474,6 @@ int batadv_gw_client_seq_print_text(struct seq_file *seq, void *offset) struct batadv_priv *bat_priv = netdev_priv(net_dev); struct batadv_hard_iface *primary_if; struct batadv_gw_node *gw_node; - struct hlist_node *node; int gw_count = 0; primary_if = batadv_seq_print_text_primary_if_get(seq); @@ -490,7 +487,7 @@ int batadv_gw_client_seq_print_text(struct seq_file *seq, void *offset) primary_if->net_dev->dev_addr, net_dev->name); rcu_read_lock(); - hlist_for_each_entry_rcu(gw_node, node, &bat_priv->gw.list, list) { + hlist_for_each_entry_rcu(gw_node, &bat_priv->gw.list, list) { if (gw_node->deleted) continue; diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 21fe6987733b..0488d70c8c35 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -345,9 +345,8 @@ void batadv_recv_handler_unregister(uint8_t packet_type) static struct batadv_algo_ops *batadv_algo_get(char *name) { struct batadv_algo_ops *bat_algo_ops = NULL, *bat_algo_ops_tmp; - struct hlist_node *node; - hlist_for_each_entry(bat_algo_ops_tmp, node, &batadv_algo_list, list) { + hlist_for_each_entry(bat_algo_ops_tmp, &batadv_algo_list, list) { if (strcmp(bat_algo_ops_tmp->name, name) != 0) continue; @@ -411,11 +410,10 @@ out: int batadv_algo_seq_print_text(struct seq_file *seq, void *offset) { struct batadv_algo_ops *bat_algo_ops; - struct hlist_node *node; seq_printf(seq, "Available routing algorithms:\n"); - hlist_for_each_entry(bat_algo_ops, node, &batadv_algo_list, list) { + hlist_for_each_entry(bat_algo_ops, &batadv_algo_list, list) { seq_printf(seq, "%s\n", bat_algo_ops->name); } diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 457ea445217c..96fb80b724dc 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -118,7 +118,7 @@ out: static void batadv_orig_node_free_rcu(struct rcu_head *rcu) { - struct hlist_node *node, *node_tmp; + struct hlist_node *node_tmp; struct batadv_neigh_node *neigh_node, *tmp_neigh_node; struct batadv_orig_node *orig_node; @@ -134,7 +134,7 @@ static void batadv_orig_node_free_rcu(struct rcu_head *rcu) } /* for all neighbors towards this originator ... */ - hlist_for_each_entry_safe(neigh_node, node, node_tmp, + hlist_for_each_entry_safe(neigh_node, node_tmp, &orig_node->neigh_list, list) { hlist_del_rcu(&neigh_node->list); batadv_neigh_node_free_ref(neigh_node); @@ -161,7 +161,7 @@ void batadv_orig_node_free_ref(struct batadv_orig_node *orig_node) void batadv_originator_free(struct batadv_priv *bat_priv) { struct batadv_hashtable *hash = bat_priv->orig_hash; - struct hlist_node *node, *node_tmp; + struct hlist_node *node_tmp; struct hlist_head *head; spinlock_t *list_lock; /* spinlock to protect write access */ struct batadv_orig_node *orig_node; @@ -179,9 +179,9 @@ void batadv_originator_free(struct batadv_priv *bat_priv) list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); - hlist_for_each_entry_safe(orig_node, node, node_tmp, + hlist_for_each_entry_safe(orig_node, node_tmp, head, hash_entry) { - hlist_del_rcu(node); + hlist_del_rcu(&orig_node->hash_entry); batadv_orig_node_free_ref(orig_node); } spin_unlock_bh(list_lock); @@ -274,7 +274,7 @@ batadv_purge_orig_neighbors(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, struct batadv_neigh_node **best_neigh_node) { - struct hlist_node *node, *node_tmp; + struct hlist_node *node_tmp; struct batadv_neigh_node *neigh_node; bool neigh_purged = false; unsigned long last_seen; @@ -285,7 +285,7 @@ batadv_purge_orig_neighbors(struct batadv_priv *bat_priv, spin_lock_bh(&orig_node->neigh_list_lock); /* for all neighbors towards this originator ... */ - hlist_for_each_entry_safe(neigh_node, node, node_tmp, + hlist_for_each_entry_safe(neigh_node, node_tmp, &orig_node->neigh_list, list) { last_seen = neigh_node->last_seen; if_incoming = neigh_node->if_incoming; @@ -348,7 +348,7 @@ static bool batadv_purge_orig_node(struct batadv_priv *bat_priv, static void _batadv_purge_orig(struct batadv_priv *bat_priv) { struct batadv_hashtable *hash = bat_priv->orig_hash; - struct hlist_node *node, *node_tmp; + struct hlist_node *node_tmp; struct hlist_head *head; spinlock_t *list_lock; /* spinlock to protect write access */ struct batadv_orig_node *orig_node; @@ -363,13 +363,13 @@ static void _batadv_purge_orig(struct batadv_priv *bat_priv) list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); - hlist_for_each_entry_safe(orig_node, node, node_tmp, + hlist_for_each_entry_safe(orig_node, node_tmp, head, hash_entry) { if (batadv_purge_orig_node(bat_priv, orig_node)) { if (orig_node->gw_flags) batadv_gw_node_delete(bat_priv, orig_node); - hlist_del_rcu(node); + hlist_del_rcu(&orig_node->hash_entry); batadv_orig_node_free_ref(orig_node); continue; } @@ -408,7 +408,6 @@ int batadv_orig_seq_print_text(struct seq_file *seq, void *offset) struct net_device *net_dev = (struct net_device *)seq->private; struct batadv_priv *bat_priv = netdev_priv(net_dev); struct batadv_hashtable *hash = bat_priv->orig_hash; - struct hlist_node *node, *node_tmp; struct hlist_head *head; struct batadv_hard_iface *primary_if; struct batadv_orig_node *orig_node; @@ -434,7 +433,7 @@ int batadv_orig_seq_print_text(struct seq_file *seq, void *offset) head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(orig_node, node, head, hash_entry) { + hlist_for_each_entry_rcu(orig_node, head, hash_entry) { neigh_node = batadv_orig_node_get_router(orig_node); if (!neigh_node) continue; @@ -453,7 +452,7 @@ int batadv_orig_seq_print_text(struct seq_file *seq, void *offset) neigh_node->addr, neigh_node->if_incoming->net_dev->name); - hlist_for_each_entry_rcu(neigh_node_tmp, node_tmp, + hlist_for_each_entry_rcu(neigh_node_tmp, &orig_node->neigh_list, list) { seq_printf(seq, " %pM (%3i)", neigh_node_tmp->addr, @@ -511,7 +510,6 @@ int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface, { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); struct batadv_hashtable *hash = bat_priv->orig_hash; - struct hlist_node *node; struct hlist_head *head; struct batadv_orig_node *orig_node; uint32_t i; @@ -524,7 +522,7 @@ int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface, head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(orig_node, node, head, hash_entry) { + hlist_for_each_entry_rcu(orig_node, head, hash_entry) { spin_lock_bh(&orig_node->ogm_cnt_lock); ret = batadv_orig_node_add_if(orig_node, max_if_num); spin_unlock_bh(&orig_node->ogm_cnt_lock); @@ -595,7 +593,6 @@ int batadv_orig_hash_del_if(struct batadv_hard_iface *hard_iface, { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); struct batadv_hashtable *hash = bat_priv->orig_hash; - struct hlist_node *node; struct hlist_head *head; struct batadv_hard_iface *hard_iface_tmp; struct batadv_orig_node *orig_node; @@ -609,7 +606,7 @@ int batadv_orig_hash_del_if(struct batadv_hard_iface *hard_iface, head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(orig_node, node, head, hash_entry) { + hlist_for_each_entry_rcu(orig_node, head, hash_entry) { spin_lock_bh(&orig_node->ogm_cnt_lock); ret = batadv_orig_node_del_if(orig_node, max_if_num, hard_iface->if_num); diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index 286bf743e76a..7df48fa7669d 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -68,7 +68,6 @@ batadv_orig_hash_find(struct batadv_priv *bat_priv, const void *data) { struct batadv_hashtable *hash = bat_priv->orig_hash; struct hlist_head *head; - struct hlist_node *node; struct batadv_orig_node *orig_node, *orig_node_tmp = NULL; int index; @@ -79,7 +78,7 @@ batadv_orig_hash_find(struct batadv_priv *bat_priv, const void *data) head = &hash->table[index]; rcu_read_lock(); - hlist_for_each_entry_rcu(orig_node, node, head, hash_entry) { + hlist_for_each_entry_rcu(orig_node, head, hash_entry) { if (!batadv_compare_eth(orig_node, data)) continue; diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 60ba03fc8390..5ee21cebbbb0 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -37,7 +37,6 @@ void batadv_slide_own_bcast_window(struct batadv_hard_iface *hard_iface) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); struct batadv_hashtable *hash = bat_priv->orig_hash; - struct hlist_node *node; struct hlist_head *head; struct batadv_orig_node *orig_node; unsigned long *word; @@ -49,7 +48,7 @@ void batadv_slide_own_bcast_window(struct batadv_hard_iface *hard_iface) head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(orig_node, node, head, hash_entry) { + hlist_for_each_entry_rcu(orig_node, head, hash_entry) { spin_lock_bh(&orig_node->ogm_cnt_lock); word_index = hard_iface->if_num * BATADV_NUM_WORDS; word = &(orig_node->bcast_own[word_index]); @@ -146,7 +145,6 @@ out: void batadv_bonding_candidate_add(struct batadv_orig_node *orig_node, struct batadv_neigh_node *neigh_node) { - struct hlist_node *node; struct batadv_neigh_node *tmp_neigh_node, *router = NULL; uint8_t interference_candidate = 0; @@ -169,7 +167,7 @@ void batadv_bonding_candidate_add(struct batadv_orig_node *orig_node, * interface. If we do, we won't select this candidate because of * possible interference. */ - hlist_for_each_entry_rcu(tmp_neigh_node, node, + hlist_for_each_entry_rcu(tmp_neigh_node, &orig_node->neigh_list, list) { if (tmp_neigh_node == neigh_node) continue; diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 80ca65fc89a1..a67cffde37ae 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -316,7 +316,7 @@ batadv_purge_outstanding_packets(struct batadv_priv *bat_priv, const struct batadv_hard_iface *hard_iface) { struct batadv_forw_packet *forw_packet; - struct hlist_node *tmp_node, *safe_tmp_node; + struct hlist_node *safe_tmp_node; bool pending; if (hard_iface) @@ -329,7 +329,7 @@ batadv_purge_outstanding_packets(struct batadv_priv *bat_priv, /* free bcast list */ spin_lock_bh(&bat_priv->forw_bcast_list_lock); - hlist_for_each_entry_safe(forw_packet, tmp_node, safe_tmp_node, + hlist_for_each_entry_safe(forw_packet, safe_tmp_node, &bat_priv->forw_bcast_list, list) { /* if purge_outstanding_packets() was called with an argument * we delete only packets belonging to the given interface @@ -355,7 +355,7 @@ batadv_purge_outstanding_packets(struct batadv_priv *bat_priv, /* free batman packet list */ spin_lock_bh(&bat_priv->forw_bat_list_lock); - hlist_for_each_entry_safe(forw_packet, tmp_node, safe_tmp_node, + hlist_for_each_entry_safe(forw_packet, safe_tmp_node, &bat_priv->forw_bat_list, list) { /* if purge_outstanding_packets() was called with an argument * we delete only packets belonging to the given interface diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index d44672f4a349..98a66a021a60 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -56,7 +56,6 @@ static struct batadv_tt_common_entry * batadv_tt_hash_find(struct batadv_hashtable *hash, const void *data) { struct hlist_head *head; - struct hlist_node *node; struct batadv_tt_common_entry *tt_common_entry; struct batadv_tt_common_entry *tt_common_entry_tmp = NULL; uint32_t index; @@ -68,7 +67,7 @@ batadv_tt_hash_find(struct batadv_hashtable *hash, const void *data) head = &hash->table[index]; rcu_read_lock(); - hlist_for_each_entry_rcu(tt_common_entry, node, head, hash_entry) { + hlist_for_each_entry_rcu(tt_common_entry, head, hash_entry) { if (!batadv_compare_eth(tt_common_entry, data)) continue; @@ -257,7 +256,6 @@ void batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, struct batadv_tt_local_entry *tt_local; struct batadv_tt_global_entry *tt_global; struct hlist_head *head; - struct hlist_node *node; struct batadv_tt_orig_list_entry *orig_entry; int hash_added; bool roamed_back = false; @@ -339,7 +337,7 @@ check_roaming: /* These node are probably going to update their tt table */ head = &tt_global->orig_list; rcu_read_lock(); - hlist_for_each_entry_rcu(orig_entry, node, head, list) { + hlist_for_each_entry_rcu(orig_entry, head, list) { batadv_send_roam_adv(bat_priv, tt_global->common.addr, orig_entry->orig_node); } @@ -470,7 +468,6 @@ int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset) struct batadv_tt_common_entry *tt_common_entry; struct batadv_tt_local_entry *tt_local; struct batadv_hard_iface *primary_if; - struct hlist_node *node; struct hlist_head *head; uint32_t i; int last_seen_secs; @@ -494,7 +491,7 @@ int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset) head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(tt_common_entry, node, + hlist_for_each_entry_rcu(tt_common_entry, head, hash_entry) { tt_local = container_of(tt_common_entry, struct batadv_tt_local_entry, @@ -605,9 +602,9 @@ static void batadv_tt_local_purge_list(struct batadv_priv *bat_priv, { struct batadv_tt_local_entry *tt_local_entry; struct batadv_tt_common_entry *tt_common_entry; - struct hlist_node *node, *node_tmp; + struct hlist_node *node_tmp; - hlist_for_each_entry_safe(tt_common_entry, node, node_tmp, head, + hlist_for_each_entry_safe(tt_common_entry, node_tmp, head, hash_entry) { tt_local_entry = container_of(tt_common_entry, struct batadv_tt_local_entry, @@ -651,7 +648,7 @@ static void batadv_tt_local_table_free(struct batadv_priv *bat_priv) spinlock_t *list_lock; /* protects write access to the hash lists */ struct batadv_tt_common_entry *tt_common_entry; struct batadv_tt_local_entry *tt_local; - struct hlist_node *node, *node_tmp; + struct hlist_node *node_tmp; struct hlist_head *head; uint32_t i; @@ -665,9 +662,9 @@ static void batadv_tt_local_table_free(struct batadv_priv *bat_priv) list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); - hlist_for_each_entry_safe(tt_common_entry, node, node_tmp, + hlist_for_each_entry_safe(tt_common_entry, node_tmp, head, hash_entry) { - hlist_del_rcu(node); + hlist_del_rcu(&tt_common_entry->hash_entry); tt_local = container_of(tt_common_entry, struct batadv_tt_local_entry, common); @@ -724,11 +721,10 @@ batadv_tt_global_orig_entry_find(const struct batadv_tt_global_entry *entry, { struct batadv_tt_orig_list_entry *tmp_orig_entry, *orig_entry = NULL; const struct hlist_head *head; - struct hlist_node *node; rcu_read_lock(); head = &entry->orig_list; - hlist_for_each_entry_rcu(tmp_orig_entry, node, head, list) { + hlist_for_each_entry_rcu(tmp_orig_entry, head, list) { if (tmp_orig_entry->orig_node != orig_node) continue; if (!atomic_inc_not_zero(&tmp_orig_entry->refcount)) @@ -940,12 +936,11 @@ batadv_transtable_best_orig(struct batadv_tt_global_entry *tt_global_entry) { struct batadv_neigh_node *router = NULL; struct hlist_head *head; - struct hlist_node *node; struct batadv_tt_orig_list_entry *orig_entry, *best_entry = NULL; int best_tq = 0; head = &tt_global_entry->orig_list; - hlist_for_each_entry_rcu(orig_entry, node, head, list) { + hlist_for_each_entry_rcu(orig_entry, head, list) { router = batadv_orig_node_get_router(orig_entry->orig_node); if (!router) continue; @@ -973,7 +968,6 @@ batadv_tt_global_print_entry(struct batadv_tt_global_entry *tt_global_entry, struct seq_file *seq) { struct hlist_head *head; - struct hlist_node *node; struct batadv_tt_orig_list_entry *orig_entry, *best_entry; struct batadv_tt_common_entry *tt_common_entry; uint16_t flags; @@ -997,7 +991,7 @@ batadv_tt_global_print_entry(struct batadv_tt_global_entry *tt_global_entry, head = &tt_global_entry->orig_list; - hlist_for_each_entry_rcu(orig_entry, node, head, list) { + hlist_for_each_entry_rcu(orig_entry, head, list) { if (best_entry == orig_entry) continue; @@ -1020,7 +1014,6 @@ int batadv_tt_global_seq_print_text(struct seq_file *seq, void *offset) struct batadv_tt_common_entry *tt_common_entry; struct batadv_tt_global_entry *tt_global; struct batadv_hard_iface *primary_if; - struct hlist_node *node; struct hlist_head *head; uint32_t i; @@ -1039,7 +1032,7 @@ int batadv_tt_global_seq_print_text(struct seq_file *seq, void *offset) head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(tt_common_entry, node, + hlist_for_each_entry_rcu(tt_common_entry, head, hash_entry) { tt_global = container_of(tt_common_entry, struct batadv_tt_global_entry, @@ -1059,13 +1052,13 @@ static void batadv_tt_global_del_orig_list(struct batadv_tt_global_entry *tt_global_entry) { struct hlist_head *head; - struct hlist_node *node, *safe; + struct hlist_node *safe; struct batadv_tt_orig_list_entry *orig_entry; spin_lock_bh(&tt_global_entry->list_lock); head = &tt_global_entry->orig_list; - hlist_for_each_entry_safe(orig_entry, node, safe, head, list) { - hlist_del_rcu(node); + hlist_for_each_entry_safe(orig_entry, safe, head, list) { + hlist_del_rcu(&orig_entry->list); batadv_tt_orig_list_entry_free_ref(orig_entry); } spin_unlock_bh(&tt_global_entry->list_lock); @@ -1078,18 +1071,18 @@ batadv_tt_global_del_orig_entry(struct batadv_priv *bat_priv, const char *message) { struct hlist_head *head; - struct hlist_node *node, *safe; + struct hlist_node *safe; struct batadv_tt_orig_list_entry *orig_entry; spin_lock_bh(&tt_global_entry->list_lock); head = &tt_global_entry->orig_list; - hlist_for_each_entry_safe(orig_entry, node, safe, head, list) { + hlist_for_each_entry_safe(orig_entry, safe, head, list) { if (orig_entry->orig_node == orig_node) { batadv_dbg(BATADV_DBG_TT, bat_priv, "Deleting %pM from global tt entry %pM: %s\n", orig_node->orig, tt_global_entry->common.addr, message); - hlist_del_rcu(node); + hlist_del_rcu(&orig_entry->list); batadv_tt_orig_list_entry_free_ref(orig_entry); } } @@ -1108,7 +1101,6 @@ batadv_tt_global_del_roaming(struct batadv_priv *bat_priv, { bool last_entry = true; struct hlist_head *head; - struct hlist_node *node; struct batadv_tt_orig_list_entry *orig_entry; /* no local entry exists, case 1: @@ -1117,7 +1109,7 @@ batadv_tt_global_del_roaming(struct batadv_priv *bat_priv, rcu_read_lock(); head = &tt_global_entry->orig_list; - hlist_for_each_entry_rcu(orig_entry, node, head, list) { + hlist_for_each_entry_rcu(orig_entry, head, list) { if (orig_entry->orig_node != orig_node) { last_entry = false; break; @@ -1202,7 +1194,7 @@ void batadv_tt_global_del_orig(struct batadv_priv *bat_priv, struct batadv_tt_common_entry *tt_common_entry; uint32_t i; struct batadv_hashtable *hash = bat_priv->tt.global_hash; - struct hlist_node *node, *safe; + struct hlist_node *safe; struct hlist_head *head; spinlock_t *list_lock; /* protects write access to the hash lists */ @@ -1214,7 +1206,7 @@ void batadv_tt_global_del_orig(struct batadv_priv *bat_priv, list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); - hlist_for_each_entry_safe(tt_common_entry, node, safe, + hlist_for_each_entry_safe(tt_common_entry, safe, head, hash_entry) { tt_global = container_of(tt_common_entry, struct batadv_tt_global_entry, @@ -1227,7 +1219,7 @@ void batadv_tt_global_del_orig(struct batadv_priv *bat_priv, batadv_dbg(BATADV_DBG_TT, bat_priv, "Deleting global tt entry %pM: %s\n", tt_global->common.addr, message); - hlist_del_rcu(node); + hlist_del_rcu(&tt_common_entry->hash_entry); batadv_tt_global_entry_free_ref(tt_global); } } @@ -1262,7 +1254,7 @@ static void batadv_tt_global_purge(struct batadv_priv *bat_priv) { struct batadv_hashtable *hash = bat_priv->tt.global_hash; struct hlist_head *head; - struct hlist_node *node, *node_tmp; + struct hlist_node *node_tmp; spinlock_t *list_lock; /* protects write access to the hash lists */ uint32_t i; char *msg = NULL; @@ -1274,7 +1266,7 @@ static void batadv_tt_global_purge(struct batadv_priv *bat_priv) list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); - hlist_for_each_entry_safe(tt_common, node, node_tmp, head, + hlist_for_each_entry_safe(tt_common, node_tmp, head, hash_entry) { tt_global = container_of(tt_common, struct batadv_tt_global_entry, @@ -1287,7 +1279,7 @@ static void batadv_tt_global_purge(struct batadv_priv *bat_priv) "Deleting global tt entry (%pM): %s\n", tt_global->common.addr, msg); - hlist_del_rcu(node); + hlist_del_rcu(&tt_common->hash_entry); batadv_tt_global_entry_free_ref(tt_global); } @@ -1301,7 +1293,7 @@ static void batadv_tt_global_table_free(struct batadv_priv *bat_priv) spinlock_t *list_lock; /* protects write access to the hash lists */ struct batadv_tt_common_entry *tt_common_entry; struct batadv_tt_global_entry *tt_global; - struct hlist_node *node, *node_tmp; + struct hlist_node *node_tmp; struct hlist_head *head; uint32_t i; @@ -1315,9 +1307,9 @@ static void batadv_tt_global_table_free(struct batadv_priv *bat_priv) list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); - hlist_for_each_entry_safe(tt_common_entry, node, node_tmp, + hlist_for_each_entry_safe(tt_common_entry, node_tmp, head, hash_entry) { - hlist_del_rcu(node); + hlist_del_rcu(&tt_common_entry->hash_entry); tt_global = container_of(tt_common_entry, struct batadv_tt_global_entry, common); @@ -1397,7 +1389,6 @@ static uint16_t batadv_tt_global_crc(struct batadv_priv *bat_priv, struct batadv_hashtable *hash = bat_priv->tt.global_hash; struct batadv_tt_common_entry *tt_common; struct batadv_tt_global_entry *tt_global; - struct hlist_node *node; struct hlist_head *head; uint32_t i; int j; @@ -1406,7 +1397,7 @@ static uint16_t batadv_tt_global_crc(struct batadv_priv *bat_priv, head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(tt_common, node, head, hash_entry) { + hlist_for_each_entry_rcu(tt_common, head, hash_entry) { tt_global = container_of(tt_common, struct batadv_tt_global_entry, common); @@ -1449,7 +1440,6 @@ static uint16_t batadv_tt_local_crc(struct batadv_priv *bat_priv) uint16_t total = 0, total_one; struct batadv_hashtable *hash = bat_priv->tt.local_hash; struct batadv_tt_common_entry *tt_common; - struct hlist_node *node; struct hlist_head *head; uint32_t i; int j; @@ -1458,7 +1448,7 @@ static uint16_t batadv_tt_local_crc(struct batadv_priv *bat_priv) head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(tt_common, node, head, hash_entry) { + hlist_for_each_entry_rcu(tt_common, head, hash_entry) { /* not yet committed clients have not to be taken into * account while computing the CRC */ @@ -1597,7 +1587,6 @@ batadv_tt_response_fill_table(uint16_t tt_len, uint8_t ttvn, struct batadv_tt_common_entry *tt_common_entry; struct batadv_tt_query_packet *tt_response; struct batadv_tt_change *tt_change; - struct hlist_node *node; struct hlist_head *head; struct sk_buff *skb = NULL; uint16_t tt_tot, tt_count; @@ -1627,7 +1616,7 @@ batadv_tt_response_fill_table(uint16_t tt_len, uint8_t ttvn, for (i = 0; i < hash->size; i++) { head = &hash->table[i]; - hlist_for_each_entry_rcu(tt_common_entry, node, + hlist_for_each_entry_rcu(tt_common_entry, head, hash_entry) { if (tt_count == tt_tot) break; @@ -2307,7 +2296,6 @@ static uint16_t batadv_tt_set_flags(struct batadv_hashtable *hash, uint32_t i; uint16_t changed_num = 0; struct hlist_head *head; - struct hlist_node *node; struct batadv_tt_common_entry *tt_common_entry; if (!hash) @@ -2317,7 +2305,7 @@ static uint16_t batadv_tt_set_flags(struct batadv_hashtable *hash, head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(tt_common_entry, node, + hlist_for_each_entry_rcu(tt_common_entry, head, hash_entry) { if (enable) { if ((tt_common_entry->flags & flags) == flags) @@ -2342,7 +2330,7 @@ static void batadv_tt_local_purge_pending_clients(struct batadv_priv *bat_priv) struct batadv_hashtable *hash = bat_priv->tt.local_hash; struct batadv_tt_common_entry *tt_common; struct batadv_tt_local_entry *tt_local; - struct hlist_node *node, *node_tmp; + struct hlist_node *node_tmp; struct hlist_head *head; spinlock_t *list_lock; /* protects write access to the hash lists */ uint32_t i; @@ -2355,7 +2343,7 @@ static void batadv_tt_local_purge_pending_clients(struct batadv_priv *bat_priv) list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); - hlist_for_each_entry_safe(tt_common, node, node_tmp, head, + hlist_for_each_entry_safe(tt_common, node_tmp, head, hash_entry) { if (!(tt_common->flags & BATADV_TT_CLIENT_PENDING)) continue; @@ -2365,7 +2353,7 @@ static void batadv_tt_local_purge_pending_clients(struct batadv_priv *bat_priv) tt_common->addr); atomic_dec(&bat_priv->tt.local_entry_num); - hlist_del_rcu(node); + hlist_del_rcu(&tt_common->hash_entry); tt_local = container_of(tt_common, struct batadv_tt_local_entry, common); diff --git a/net/batman-adv/vis.c b/net/batman-adv/vis.c index 22d2785177d1..c053244b97bd 100644 --- a/net/batman-adv/vis.c +++ b/net/batman-adv/vis.c @@ -97,7 +97,6 @@ batadv_vis_hash_find(struct batadv_priv *bat_priv, const void *data) { struct batadv_hashtable *hash = bat_priv->vis.hash; struct hlist_head *head; - struct hlist_node *node; struct batadv_vis_info *vis_info, *vis_info_tmp = NULL; uint32_t index; @@ -108,8 +107,8 @@ batadv_vis_hash_find(struct batadv_priv *bat_priv, const void *data) head = &hash->table[index]; rcu_read_lock(); - hlist_for_each_entry_rcu(vis_info, node, head, hash_entry) { - if (!batadv_vis_info_cmp(node, data)) + hlist_for_each_entry_rcu(vis_info, head, hash_entry) { + if (!batadv_vis_info_cmp(&vis_info->hash_entry, data)) continue; vis_info_tmp = vis_info; @@ -128,9 +127,8 @@ static void batadv_vis_data_insert_interface(const uint8_t *interface, bool primary) { struct batadv_vis_if_list_entry *entry; - struct hlist_node *pos; - hlist_for_each_entry(entry, pos, if_list, list) { + hlist_for_each_entry(entry, if_list, list) { if (batadv_compare_eth(entry->addr, interface)) return; } @@ -148,9 +146,8 @@ static void batadv_vis_data_read_prim_sec(struct seq_file *seq, const struct hlist_head *if_list) { struct batadv_vis_if_list_entry *entry; - struct hlist_node *pos; - hlist_for_each_entry(entry, pos, if_list, list) { + hlist_for_each_entry(entry, if_list, list) { if (entry->primary) seq_printf(seq, "PRIMARY, "); else @@ -198,9 +195,8 @@ static void batadv_vis_data_read_entries(struct seq_file *seq, { int i; struct batadv_vis_if_list_entry *entry; - struct hlist_node *pos; - hlist_for_each_entry(entry, pos, list, list) { + hlist_for_each_entry(entry, list, list) { seq_printf(seq, "%pM,", entry->addr); for (i = 0; i < packet->entries; i++) @@ -218,17 +214,16 @@ static void batadv_vis_data_read_entries(struct seq_file *seq, static void batadv_vis_seq_print_text_bucket(struct seq_file *seq, const struct hlist_head *head) { - struct hlist_node *node; struct batadv_vis_info *info; struct batadv_vis_packet *packet; uint8_t *entries_pos; struct batadv_vis_info_entry *entries; struct batadv_vis_if_list_entry *entry; - struct hlist_node *pos, *n; + struct hlist_node *n; HLIST_HEAD(vis_if_list); - hlist_for_each_entry_rcu(info, node, head, hash_entry) { + hlist_for_each_entry_rcu(info, head, hash_entry) { packet = (struct batadv_vis_packet *)info->skb_packet->data; entries_pos = (uint8_t *)packet + sizeof(*packet); entries = (struct batadv_vis_info_entry *)entries_pos; @@ -240,7 +235,7 @@ static void batadv_vis_seq_print_text_bucket(struct seq_file *seq, batadv_vis_data_read_entries(seq, &vis_if_list, packet, entries); - hlist_for_each_entry_safe(entry, pos, n, &vis_if_list, list) { + hlist_for_each_entry_safe(entry, n, &vis_if_list, list) { hlist_del(&entry->list); kfree(entry); } @@ -519,7 +514,6 @@ static int batadv_find_best_vis_server(struct batadv_priv *bat_priv, { struct batadv_hashtable *hash = bat_priv->orig_hash; struct batadv_neigh_node *router; - struct hlist_node *node; struct hlist_head *head; struct batadv_orig_node *orig_node; struct batadv_vis_packet *packet; @@ -532,7 +526,7 @@ static int batadv_find_best_vis_server(struct batadv_priv *bat_priv, head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(orig_node, node, head, hash_entry) { + hlist_for_each_entry_rcu(orig_node, head, hash_entry) { router = batadv_orig_node_get_router(orig_node); if (!router) continue; @@ -571,7 +565,6 @@ static bool batadv_vis_packet_full(const struct batadv_vis_info *info) static int batadv_generate_vis_packet(struct batadv_priv *bat_priv) { struct batadv_hashtable *hash = bat_priv->orig_hash; - struct hlist_node *node; struct hlist_head *head; struct batadv_orig_node *orig_node; struct batadv_neigh_node *router; @@ -605,7 +598,7 @@ static int batadv_generate_vis_packet(struct batadv_priv *bat_priv) head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(orig_node, node, head, hash_entry) { + hlist_for_each_entry_rcu(orig_node, head, hash_entry) { router = batadv_orig_node_get_router(orig_node); if (!router) continue; @@ -644,7 +637,7 @@ next: head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(tt_common_entry, node, head, + hlist_for_each_entry_rcu(tt_common_entry, head, hash_entry) { packet_pos = skb_put(info->skb_packet, sizeof(*entry)); entry = (struct batadv_vis_info_entry *)packet_pos; @@ -673,14 +666,14 @@ static void batadv_purge_vis_packets(struct batadv_priv *bat_priv) { uint32_t i; struct batadv_hashtable *hash = bat_priv->vis.hash; - struct hlist_node *node, *node_tmp; + struct hlist_node *node_tmp; struct hlist_head *head; struct batadv_vis_info *info; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; - hlist_for_each_entry_safe(info, node, node_tmp, + hlist_for_each_entry_safe(info, node_tmp, head, hash_entry) { /* never purge own data. */ if (info == bat_priv->vis.my_info) @@ -688,7 +681,7 @@ static void batadv_purge_vis_packets(struct batadv_priv *bat_priv) if (batadv_has_timed_out(info->first_seen, BATADV_VIS_TIMEOUT)) { - hlist_del(node); + hlist_del(&info->hash_entry); batadv_send_list_del(info); kref_put(&info->refcount, batadv_free_info); } @@ -700,7 +693,6 @@ static void batadv_broadcast_vis_packet(struct batadv_priv *bat_priv, struct batadv_vis_info *info) { struct batadv_hashtable *hash = bat_priv->orig_hash; - struct hlist_node *node; struct hlist_head *head; struct batadv_orig_node *orig_node; struct batadv_vis_packet *packet; @@ -715,7 +707,7 @@ static void batadv_broadcast_vis_packet(struct batadv_priv *bat_priv, head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(orig_node, node, head, hash_entry) { + hlist_for_each_entry_rcu(orig_node, head, hash_entry) { /* if it's a vis server and reachable, send it. */ if (!(orig_node->flags & BATADV_VIS_SERVER)) continue; diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 07f073935811..6a93614f2c49 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -70,14 +70,13 @@ static struct bt_sock_list hci_sk_list = { void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb) { struct sock *sk; - struct hlist_node *node; struct sk_buff *skb_copy = NULL; BT_DBG("hdev %p len %d", hdev, skb->len); read_lock(&hci_sk_list.lock); - sk_for_each(sk, node, &hci_sk_list.head) { + sk_for_each(sk, &hci_sk_list.head) { struct hci_filter *flt; struct sk_buff *nskb; @@ -142,13 +141,12 @@ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb) void hci_send_to_control(struct sk_buff *skb, struct sock *skip_sk) { struct sock *sk; - struct hlist_node *node; BT_DBG("len %d", skb->len); read_lock(&hci_sk_list.lock); - sk_for_each(sk, node, &hci_sk_list.head) { + sk_for_each(sk, &hci_sk_list.head) { struct sk_buff *nskb; /* Skip the original socket */ @@ -176,7 +174,6 @@ void hci_send_to_control(struct sk_buff *skb, struct sock *skip_sk) void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb) { struct sock *sk; - struct hlist_node *node; struct sk_buff *skb_copy = NULL; __le16 opcode; @@ -210,7 +207,7 @@ void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb) read_lock(&hci_sk_list.lock); - sk_for_each(sk, node, &hci_sk_list.head) { + sk_for_each(sk, &hci_sk_list.head) { struct sk_buff *nskb; if (sk->sk_state != BT_BOUND) @@ -251,13 +248,12 @@ void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb) static void send_monitor_event(struct sk_buff *skb) { struct sock *sk; - struct hlist_node *node; BT_DBG("len %d", skb->len); read_lock(&hci_sk_list.lock); - sk_for_each(sk, node, &hci_sk_list.head) { + sk_for_each(sk, &hci_sk_list.head) { struct sk_buff *nskb; if (sk->sk_state != BT_BOUND) @@ -393,11 +389,10 @@ void hci_sock_dev_event(struct hci_dev *hdev, int event) if (event == HCI_DEV_UNREG) { struct sock *sk; - struct hlist_node *node; /* Detach sockets from device */ read_lock(&hci_sk_list.lock); - sk_for_each(sk, node, &hci_sk_list.head) { + sk_for_each(sk, &hci_sk_list.head) { bh_lock_sock_nested(sk); if (hci_pi(sk)->hdev == hdev) { hci_pi(sk)->hdev = NULL; diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index ce3f6658f4b2..c23bae86263b 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -107,15 +107,14 @@ static void rfcomm_sk_state_change(struct rfcomm_dlc *d, int err) static struct sock *__rfcomm_get_sock_by_addr(u8 channel, bdaddr_t *src) { struct sock *sk = NULL; - struct hlist_node *node; - sk_for_each(sk, node, &rfcomm_sk_list.head) { + sk_for_each(sk, &rfcomm_sk_list.head) { if (rfcomm_pi(sk)->channel == channel && !bacmp(&bt_sk(sk)->src, src)) break; } - return node ? sk : NULL; + return sk ? sk : NULL; } /* Find socket with channel and source bdaddr. @@ -124,11 +123,10 @@ static struct sock *__rfcomm_get_sock_by_addr(u8 channel, bdaddr_t *src) static struct sock *rfcomm_get_sock_by_channel(int state, u8 channel, bdaddr_t *src) { struct sock *sk = NULL, *sk1 = NULL; - struct hlist_node *node; read_lock(&rfcomm_sk_list.lock); - sk_for_each(sk, node, &rfcomm_sk_list.head) { + sk_for_each(sk, &rfcomm_sk_list.head) { if (state && sk->sk_state != state) continue; @@ -145,7 +143,7 @@ static struct sock *rfcomm_get_sock_by_channel(int state, u8 channel, bdaddr_t * read_unlock(&rfcomm_sk_list.lock); - return node ? sk : sk1; + return sk ? sk : sk1; } static void rfcomm_sock_destruct(struct sock *sk) @@ -970,11 +968,10 @@ done: static int rfcomm_sock_debugfs_show(struct seq_file *f, void *p) { struct sock *sk; - struct hlist_node *node; read_lock(&rfcomm_sk_list.lock); - sk_for_each(sk, node, &rfcomm_sk_list.head) { + sk_for_each(sk, &rfcomm_sk_list.head) { seq_printf(f, "%pMR %pMR %d %d\n", &bt_sk(sk)->src, &bt_sk(sk)->dst, sk->sk_state, rfcomm_pi(sk)->channel); diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index b5178d62064e..79d87d8d4f51 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -259,10 +259,9 @@ drop: /* -------- Socket interface ---------- */ static struct sock *__sco_get_sock_listen_by_addr(bdaddr_t *ba) { - struct hlist_node *node; struct sock *sk; - sk_for_each(sk, node, &sco_sk_list.head) { + sk_for_each(sk, &sco_sk_list.head) { if (sk->sk_state != BT_LISTEN) continue; @@ -279,11 +278,10 @@ static struct sock *__sco_get_sock_listen_by_addr(bdaddr_t *ba) static struct sock *sco_get_sock_listen(bdaddr_t *src) { struct sock *sk = NULL, *sk1 = NULL; - struct hlist_node *node; read_lock(&sco_sk_list.lock); - sk_for_each(sk, node, &sco_sk_list.head) { + sk_for_each(sk, &sco_sk_list.head) { if (sk->sk_state != BT_LISTEN) continue; @@ -298,7 +296,7 @@ static struct sock *sco_get_sock_listen(bdaddr_t *src) read_unlock(&sco_sk_list.lock); - return node ? sk : sk1; + return sk ? sk : sk1; } static void sco_sock_destruct(struct sock *sk) @@ -951,14 +949,13 @@ static void sco_conn_ready(struct sco_conn *conn) int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) { struct sock *sk; - struct hlist_node *node; int lm = 0; BT_DBG("hdev %s, bdaddr %pMR", hdev->name, bdaddr); /* Find listening sockets */ read_lock(&sco_sk_list.lock); - sk_for_each(sk, node, &sco_sk_list.head) { + sk_for_each(sk, &sco_sk_list.head) { if (sk->sk_state != BT_LISTEN) continue; @@ -1018,11 +1015,10 @@ drop: static int sco_debugfs_show(struct seq_file *f, void *p) { struct sock *sk; - struct hlist_node *node; read_lock(&sco_sk_list.lock); - sk_for_each(sk, node, &sco_sk_list.head) { + sk_for_each(sk, &sco_sk_list.head) { seq_printf(f, "%pMR %pMR %d\n", &bt_sk(sk)->src, &bt_sk(sk)->dst, sk->sk_state); } diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index d9576e6de2b8..4fb0461eb391 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -149,9 +149,9 @@ void br_fdb_cleanup(unsigned long _data) spin_lock(&br->hash_lock); for (i = 0; i < BR_HASH_SIZE; i++) { struct net_bridge_fdb_entry *f; - struct hlist_node *h, *n; + struct hlist_node *n; - hlist_for_each_entry_safe(f, h, n, &br->hash[i], hlist) { + hlist_for_each_entry_safe(f, n, &br->hash[i], hlist) { unsigned long this_timer; if (f->is_static) continue; @@ -175,8 +175,8 @@ void br_fdb_flush(struct net_bridge *br) spin_lock_bh(&br->hash_lock); for (i = 0; i < BR_HASH_SIZE; i++) { struct net_bridge_fdb_entry *f; - struct hlist_node *h, *n; - hlist_for_each_entry_safe(f, h, n, &br->hash[i], hlist) { + struct hlist_node *n; + hlist_for_each_entry_safe(f, n, &br->hash[i], hlist) { if (!f->is_static) fdb_delete(br, f); } @@ -233,10 +233,9 @@ void br_fdb_delete_by_port(struct net_bridge *br, struct net_bridge_fdb_entry *__br_fdb_get(struct net_bridge *br, const unsigned char *addr) { - struct hlist_node *h; struct net_bridge_fdb_entry *fdb; - hlist_for_each_entry_rcu(fdb, h, &br->hash[br_mac_hash(addr)], hlist) { + hlist_for_each_entry_rcu(fdb, &br->hash[br_mac_hash(addr)], hlist) { if (ether_addr_equal(fdb->addr.addr, addr)) { if (unlikely(has_expired(br, fdb))) break; @@ -280,14 +279,13 @@ int br_fdb_fillbuf(struct net_bridge *br, void *buf, { struct __fdb_entry *fe = buf; int i, num = 0; - struct hlist_node *h; struct net_bridge_fdb_entry *f; memset(buf, 0, maxnum*sizeof(struct __fdb_entry)); rcu_read_lock(); for (i = 0; i < BR_HASH_SIZE; i++) { - hlist_for_each_entry_rcu(f, h, &br->hash[i], hlist) { + hlist_for_each_entry_rcu(f, &br->hash[i], hlist) { if (num >= maxnum) goto out; @@ -327,10 +325,9 @@ int br_fdb_fillbuf(struct net_bridge *br, void *buf, static struct net_bridge_fdb_entry *fdb_find(struct hlist_head *head, const unsigned char *addr) { - struct hlist_node *h; struct net_bridge_fdb_entry *fdb; - hlist_for_each_entry(fdb, h, head, hlist) { + hlist_for_each_entry(fdb, head, hlist) { if (ether_addr_equal(fdb->addr.addr, addr)) return fdb; } @@ -340,10 +337,9 @@ static struct net_bridge_fdb_entry *fdb_find(struct hlist_head *head, static struct net_bridge_fdb_entry *fdb_find_rcu(struct hlist_head *head, const unsigned char *addr) { - struct hlist_node *h; struct net_bridge_fdb_entry *fdb; - hlist_for_each_entry_rcu(fdb, h, head, hlist) { + hlist_for_each_entry_rcu(fdb, head, hlist) { if (ether_addr_equal(fdb->addr.addr, addr)) return fdb; } @@ -547,10 +543,9 @@ int br_fdb_dump(struct sk_buff *skb, goto out; for (i = 0; i < BR_HASH_SIZE; i++) { - struct hlist_node *h; struct net_bridge_fdb_entry *f; - hlist_for_each_entry_rcu(f, h, &br->hash[i], hlist) { + hlist_for_each_entry_rcu(f, &br->hash[i], hlist) { if (idx < cb->args[0]) goto skip; diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 38991e03646d..9f97b850fc65 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -18,7 +18,6 @@ static int br_rports_fill_info(struct sk_buff *skb, struct netlink_callback *cb, { struct net_bridge *br = netdev_priv(dev); struct net_bridge_port *p; - struct hlist_node *n; struct nlattr *nest; if (!br->multicast_router || hlist_empty(&br->router_list)) @@ -28,7 +27,7 @@ static int br_rports_fill_info(struct sk_buff *skb, struct netlink_callback *cb, if (nest == NULL) return -EMSGSIZE; - hlist_for_each_entry_rcu(p, n, &br->router_list, rlist) { + hlist_for_each_entry_rcu(p, &br->router_list, rlist) { if (p && nla_put_u32(skb, MDBA_ROUTER_PORT, p->dev->ifindex)) goto fail; } @@ -61,12 +60,11 @@ static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb, return -EMSGSIZE; for (i = 0; i < mdb->max; i++) { - struct hlist_node *h; struct net_bridge_mdb_entry *mp; struct net_bridge_port_group *p, **pp; struct net_bridge_port *port; - hlist_for_each_entry_rcu(mp, h, &mdb->mhash[i], hlist[mdb->ver]) { + hlist_for_each_entry_rcu(mp, &mdb->mhash[i], hlist[mdb->ver]) { if (idx < s_idx) goto skip; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 6d6f26531de2..fda3101d28e7 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -81,9 +81,8 @@ static struct net_bridge_mdb_entry *__br_mdb_ip_get( struct net_bridge_mdb_htable *mdb, struct br_ip *dst, int hash) { struct net_bridge_mdb_entry *mp; - struct hlist_node *p; - hlist_for_each_entry_rcu(mp, p, &mdb->mhash[hash], hlist[mdb->ver]) { + hlist_for_each_entry_rcu(mp, &mdb->mhash[hash], hlist[mdb->ver]) { if (br_ip_equal(&mp->addr, dst)) return mp; } @@ -170,13 +169,12 @@ static int br_mdb_copy(struct net_bridge_mdb_htable *new, int elasticity) { struct net_bridge_mdb_entry *mp; - struct hlist_node *p; int maxlen; int len; int i; for (i = 0; i < old->max; i++) - hlist_for_each_entry(mp, p, &old->mhash[i], hlist[old->ver]) + hlist_for_each_entry(mp, &old->mhash[i], hlist[old->ver]) hlist_add_head(&mp->hlist[new->ver], &new->mhash[br_ip_hash(new, &mp->addr)]); @@ -186,7 +184,7 @@ static int br_mdb_copy(struct net_bridge_mdb_htable *new, maxlen = 0; for (i = 0; i < new->max; i++) { len = 0; - hlist_for_each_entry(mp, p, &new->mhash[i], hlist[new->ver]) + hlist_for_each_entry(mp, &new->mhash[i], hlist[new->ver]) len++; if (len > maxlen) maxlen = len; @@ -502,14 +500,13 @@ static struct net_bridge_mdb_entry *br_multicast_get_group( { struct net_bridge_mdb_htable *mdb; struct net_bridge_mdb_entry *mp; - struct hlist_node *p; unsigned int count = 0; unsigned int max; int elasticity; int err; mdb = rcu_dereference_protected(br->mdb, 1); - hlist_for_each_entry(mp, p, &mdb->mhash[hash], hlist[mdb->ver]) { + hlist_for_each_entry(mp, &mdb->mhash[hash], hlist[mdb->ver]) { count++; if (unlikely(br_ip_equal(group, &mp->addr))) return mp; @@ -870,10 +867,10 @@ void br_multicast_disable_port(struct net_bridge_port *port) { struct net_bridge *br = port->br; struct net_bridge_port_group *pg; - struct hlist_node *p, *n; + struct hlist_node *n; spin_lock(&br->multicast_lock); - hlist_for_each_entry_safe(pg, p, n, &port->mglist, mglist) + hlist_for_each_entry_safe(pg, n, &port->mglist, mglist) br_multicast_del_pg(br, pg); if (!hlist_unhashed(&port->rlist)) @@ -1008,12 +1005,12 @@ static void br_multicast_add_router(struct net_bridge *br, struct net_bridge_port *port) { struct net_bridge_port *p; - struct hlist_node *n, *slot = NULL; + struct hlist_node *slot = NULL; - hlist_for_each_entry(p, n, &br->router_list, rlist) { + hlist_for_each_entry(p, &br->router_list, rlist) { if ((unsigned long) port >= (unsigned long) p) break; - slot = n; + slot = &p->rlist; } if (slot) @@ -1624,7 +1621,7 @@ void br_multicast_stop(struct net_bridge *br) { struct net_bridge_mdb_htable *mdb; struct net_bridge_mdb_entry *mp; - struct hlist_node *p, *n; + struct hlist_node *n; u32 ver; int i; @@ -1641,7 +1638,7 @@ void br_multicast_stop(struct net_bridge *br) ver = mdb->ver; for (i = 0; i < mdb->max; i++) { - hlist_for_each_entry_safe(mp, p, n, &mdb->mhash[i], + hlist_for_each_entry_safe(mp, n, &mdb->mhash[i], hlist[ver]) { del_timer(&mp->timer); call_rcu_bh(&mp->rcu, br_multicast_free_group); diff --git a/net/can/af_can.c b/net/can/af_can.c index ddac1ee2ed20..c48e5220bbac 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -516,7 +516,6 @@ void can_rx_unregister(struct net_device *dev, canid_t can_id, canid_t mask, { struct receiver *r = NULL; struct hlist_head *rl; - struct hlist_node *next; struct dev_rcv_lists *d; if (dev && dev->type != ARPHRD_CAN) @@ -540,7 +539,7 @@ void can_rx_unregister(struct net_device *dev, canid_t can_id, canid_t mask, * been registered before. */ - hlist_for_each_entry_rcu(r, next, rl, list) { + hlist_for_each_entry_rcu(r, rl, list) { if (r->can_id == can_id && r->mask == mask && r->func == func && r->data == data) break; @@ -552,7 +551,7 @@ void can_rx_unregister(struct net_device *dev, canid_t can_id, canid_t mask, * will be NULL, while r will point to the last item of the list. */ - if (!next) { + if (!r) { printk(KERN_ERR "BUG: receive list entry not found for " "dev %s, id %03X, mask %03X\n", DNAME(dev), can_id, mask); @@ -590,7 +589,6 @@ static inline void deliver(struct sk_buff *skb, struct receiver *r) static int can_rcv_filter(struct dev_rcv_lists *d, struct sk_buff *skb) { struct receiver *r; - struct hlist_node *n; int matches = 0; struct can_frame *cf = (struct can_frame *)skb->data; canid_t can_id = cf->can_id; @@ -600,7 +598,7 @@ static int can_rcv_filter(struct dev_rcv_lists *d, struct sk_buff *skb) if (can_id & CAN_ERR_FLAG) { /* check for error message frame entries only */ - hlist_for_each_entry_rcu(r, n, &d->rx[RX_ERR], list) { + hlist_for_each_entry_rcu(r, &d->rx[RX_ERR], list) { if (can_id & r->mask) { deliver(skb, r); matches++; @@ -610,13 +608,13 @@ static int can_rcv_filter(struct dev_rcv_lists *d, struct sk_buff *skb) } /* check for unfiltered entries */ - hlist_for_each_entry_rcu(r, n, &d->rx[RX_ALL], list) { + hlist_for_each_entry_rcu(r, &d->rx[RX_ALL], list) { deliver(skb, r); matches++; } /* check for can_id/mask entries */ - hlist_for_each_entry_rcu(r, n, &d->rx[RX_FIL], list) { + hlist_for_each_entry_rcu(r, &d->rx[RX_FIL], list) { if ((can_id & r->mask) == r->can_id) { deliver(skb, r); matches++; @@ -624,7 +622,7 @@ static int can_rcv_filter(struct dev_rcv_lists *d, struct sk_buff *skb) } /* check for inverted can_id/mask entries */ - hlist_for_each_entry_rcu(r, n, &d->rx[RX_INV], list) { + hlist_for_each_entry_rcu(r, &d->rx[RX_INV], list) { if ((can_id & r->mask) != r->can_id) { deliver(skb, r); matches++; @@ -636,7 +634,7 @@ static int can_rcv_filter(struct dev_rcv_lists *d, struct sk_buff *skb) return matches; if (can_id & CAN_EFF_FLAG) { - hlist_for_each_entry_rcu(r, n, &d->rx[RX_EFF], list) { + hlist_for_each_entry_rcu(r, &d->rx[RX_EFF], list) { if (r->can_id == can_id) { deliver(skb, r); matches++; @@ -644,7 +642,7 @@ static int can_rcv_filter(struct dev_rcv_lists *d, struct sk_buff *skb) } } else { can_id &= CAN_SFF_MASK; - hlist_for_each_entry_rcu(r, n, &d->rx_sff[can_id], list) { + hlist_for_each_entry_rcu(r, &d->rx_sff[can_id], list) { deliver(skb, r); matches++; } diff --git a/net/can/gw.c b/net/can/gw.c index c185fcd5e828..2d117dc5ebea 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -457,11 +457,11 @@ static int cgw_notifier(struct notifier_block *nb, if (msg == NETDEV_UNREGISTER) { struct cgw_job *gwj = NULL; - struct hlist_node *n, *nx; + struct hlist_node *nx; ASSERT_RTNL(); - hlist_for_each_entry_safe(gwj, n, nx, &cgw_list, list) { + hlist_for_each_entry_safe(gwj, nx, &cgw_list, list) { if (gwj->src.dev == dev || gwj->dst.dev == dev) { hlist_del(&gwj->list); @@ -575,12 +575,11 @@ cancel: static int cgw_dump_jobs(struct sk_buff *skb, struct netlink_callback *cb) { struct cgw_job *gwj = NULL; - struct hlist_node *n; int idx = 0; int s_idx = cb->args[0]; rcu_read_lock(); - hlist_for_each_entry_rcu(gwj, n, &cgw_list, list) { + hlist_for_each_entry_rcu(gwj, &cgw_list, list) { if (idx < s_idx) goto cont; @@ -858,11 +857,11 @@ out: static void cgw_remove_all_jobs(void) { struct cgw_job *gwj = NULL; - struct hlist_node *n, *nx; + struct hlist_node *nx; ASSERT_RTNL(); - hlist_for_each_entry_safe(gwj, n, nx, &cgw_list, list) { + hlist_for_each_entry_safe(gwj, nx, &cgw_list, list) { hlist_del(&gwj->list); cgw_unregister_filter(gwj); kfree(gwj); @@ -872,7 +871,7 @@ static void cgw_remove_all_jobs(void) static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { struct cgw_job *gwj = NULL; - struct hlist_node *n, *nx; + struct hlist_node *nx; struct rtcanmsg *r; struct cf_mod mod; struct can_can_gw ccgw; @@ -907,7 +906,7 @@ static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) ASSERT_RTNL(); /* remove only the first matching entry */ - hlist_for_each_entry_safe(gwj, n, nx, &cgw_list, list) { + hlist_for_each_entry_safe(gwj, nx, &cgw_list, list) { if (gwj->flags != r->flags) continue; diff --git a/net/can/proc.c b/net/can/proc.c index ae566902d2bf..e21e13382a50 100644 --- a/net/can/proc.c +++ b/net/can/proc.c @@ -195,9 +195,8 @@ static void can_print_rcvlist(struct seq_file *m, struct hlist_head *rx_list, struct net_device *dev) { struct receiver *r; - struct hlist_node *n; - hlist_for_each_entry_rcu(r, n, rx_list, list) { + hlist_for_each_entry_rcu(r, rx_list, list) { char *fmt = (r->can_id & CAN_EFF_FLAG)? " %-5s %08x %08x %pK %pK %8ld %s\n" : " %-5s %03x %08x %pK %pK %8ld %s\n"; diff --git a/net/core/dev.c b/net/core/dev.c index 2f31bf97ba65..82ed6988832c 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -694,11 +694,10 @@ __setup("netdev=", netdev_boot_setup); struct net_device *__dev_get_by_name(struct net *net, const char *name) { - struct hlist_node *p; struct net_device *dev; struct hlist_head *head = dev_name_hash(net, name); - hlist_for_each_entry(dev, p, head, name_hlist) + hlist_for_each_entry(dev, head, name_hlist) if (!strncmp(dev->name, name, IFNAMSIZ)) return dev; @@ -720,11 +719,10 @@ EXPORT_SYMBOL(__dev_get_by_name); struct net_device *dev_get_by_name_rcu(struct net *net, const char *name) { - struct hlist_node *p; struct net_device *dev; struct hlist_head *head = dev_name_hash(net, name); - hlist_for_each_entry_rcu(dev, p, head, name_hlist) + hlist_for_each_entry_rcu(dev, head, name_hlist) if (!strncmp(dev->name, name, IFNAMSIZ)) return dev; @@ -771,11 +769,10 @@ EXPORT_SYMBOL(dev_get_by_name); struct net_device *__dev_get_by_index(struct net *net, int ifindex) { - struct hlist_node *p; struct net_device *dev; struct hlist_head *head = dev_index_hash(net, ifindex); - hlist_for_each_entry(dev, p, head, index_hlist) + hlist_for_each_entry(dev, head, index_hlist) if (dev->ifindex == ifindex) return dev; @@ -796,11 +793,10 @@ EXPORT_SYMBOL(__dev_get_by_index); struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex) { - struct hlist_node *p; struct net_device *dev; struct hlist_head *head = dev_index_hash(net, ifindex); - hlist_for_each_entry_rcu(dev, p, head, index_hlist) + hlist_for_each_entry_rcu(dev, head, index_hlist) if (dev->ifindex == ifindex) return dev; @@ -4407,12 +4403,11 @@ static inline struct net_device *dev_from_same_bucket(struct seq_file *seq, loff { struct net *net = seq_file_net(seq); struct net_device *dev; - struct hlist_node *p; struct hlist_head *h; unsigned int count = 0, offset = get_offset(*pos); h = &net->dev_name_head[get_bucket(*pos)]; - hlist_for_each_entry_rcu(dev, p, h, name_hlist) { + hlist_for_each_entry_rcu(dev, h, name_hlist) { if (++count == offset) return dev; } diff --git a/net/core/flow.c b/net/core/flow.c index 43f7495df27a..c56ea6f7f6c7 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -132,14 +132,14 @@ static void __flow_cache_shrink(struct flow_cache *fc, int shrink_to) { struct flow_cache_entry *fle; - struct hlist_node *entry, *tmp; + struct hlist_node *tmp; LIST_HEAD(gc_list); int i, deleted = 0; for (i = 0; i < flow_cache_hash_size(fc); i++) { int saved = 0; - hlist_for_each_entry_safe(fle, entry, tmp, + hlist_for_each_entry_safe(fle, tmp, &fcp->hash_table[i], u.hlist) { if (saved < shrink_to && flow_entry_valid(fle)) { @@ -211,7 +211,6 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir, struct flow_cache *fc = &flow_cache_global; struct flow_cache_percpu *fcp; struct flow_cache_entry *fle, *tfle; - struct hlist_node *entry; struct flow_cache_object *flo; size_t keysize; unsigned int hash; @@ -235,7 +234,7 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir, flow_new_hash_rnd(fc, fcp); hash = flow_hash_code(fc, fcp, key, keysize); - hlist_for_each_entry(tfle, entry, &fcp->hash_table[hash], u.hlist) { + hlist_for_each_entry(tfle, &fcp->hash_table[hash], u.hlist) { if (tfle->net == net && tfle->family == family && tfle->dir == dir && @@ -301,13 +300,13 @@ static void flow_cache_flush_tasklet(unsigned long data) struct flow_cache *fc = info->cache; struct flow_cache_percpu *fcp; struct flow_cache_entry *fle; - struct hlist_node *entry, *tmp; + struct hlist_node *tmp; LIST_HEAD(gc_list); int i, deleted = 0; fcp = this_cpu_ptr(fc->percpu); for (i = 0; i < flow_cache_hash_size(fc); i++) { - hlist_for_each_entry_safe(fle, entry, tmp, + hlist_for_each_entry_safe(fle, tmp, &fcp->hash_table[i], u.hlist) { if (flow_entry_valid(fle)) continue; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index a5b89a6fec6d..7427ab5e27d8 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -21,6 +21,7 @@ #include <linux/vmalloc.h> #include <linux/export.h> #include <linux/jiffies.h> +#include <linux/pm_runtime.h> #include "net-sysfs.h" @@ -1257,6 +1258,8 @@ void netdev_unregister_kobject(struct net_device * net) remove_queue_kobjects(net); + pm_runtime_set_memalloc_noio(dev, false); + device_del(dev); } @@ -1301,6 +1304,8 @@ int netdev_register_kobject(struct net_device *net) return error; } + pm_runtime_set_memalloc_noio(dev, true); + return error; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index c1e4db60eeca..4a432cc7cd59 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1060,7 +1060,6 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) int idx = 0, s_idx; struct net_device *dev; struct hlist_head *head; - struct hlist_node *node; struct nlattr *tb[IFLA_MAX+1]; u32 ext_filter_mask = 0; @@ -1080,7 +1079,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; head = &net->dev_index_head[h]; - hlist_for_each_entry_rcu(dev, node, head, index_hlist) { + hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 64d9843f9e04..ae06bd349d53 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -175,12 +175,11 @@ static struct hlist_head *dn_find_list(struct sock *sk) static int check_port(__le16 port) { struct sock *sk; - struct hlist_node *node; if (port == 0) return -1; - sk_for_each(sk, node, &dn_sk_hash[le16_to_cpu(port) & DN_SK_HASH_MASK]) { + sk_for_each(sk, &dn_sk_hash[le16_to_cpu(port) & DN_SK_HASH_MASK]) { struct dn_scp *scp = DN_SK(sk); if (scp->addrloc == port) return -1; @@ -374,11 +373,10 @@ int dn_username2sockaddr(unsigned char *data, int len, struct sockaddr_dn *sdn, struct sock *dn_sklist_find_listener(struct sockaddr_dn *addr) { struct hlist_head *list = listen_hash(addr); - struct hlist_node *node; struct sock *sk; read_lock(&dn_hash_lock); - sk_for_each(sk, node, list) { + sk_for_each(sk, list) { struct dn_scp *scp = DN_SK(sk); if (sk->sk_state != TCP_LISTEN) continue; @@ -414,11 +412,10 @@ struct sock *dn_find_by_skb(struct sk_buff *skb) { struct dn_skb_cb *cb = DN_SKB_CB(skb); struct sock *sk; - struct hlist_node *node; struct dn_scp *scp; read_lock(&dn_hash_lock); - sk_for_each(sk, node, &dn_sk_hash[le16_to_cpu(cb->dst_port) & DN_SK_HASH_MASK]) { + sk_for_each(sk, &dn_sk_hash[le16_to_cpu(cb->dst_port) & DN_SK_HASH_MASK]) { scp = DN_SK(sk); if (cb->src != dn_saddr2dn(&scp->peer)) continue; diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c index f968c1b58f47..6c2445bcaba1 100644 --- a/net/decnet/dn_table.c +++ b/net/decnet/dn_table.c @@ -483,7 +483,6 @@ int dn_fib_dump(struct sk_buff *skb, struct netlink_callback *cb) unsigned int h, s_h; unsigned int e = 0, s_e; struct dn_fib_table *tb; - struct hlist_node *node; int dumped = 0; if (!net_eq(net, &init_net)) @@ -498,7 +497,7 @@ int dn_fib_dump(struct sk_buff *skb, struct netlink_callback *cb) for (h = s_h; h < DN_FIB_TABLE_HASHSZ; h++, s_h = 0) { e = 0; - hlist_for_each_entry(tb, node, &dn_fib_table_hash[h], hlist) { + hlist_for_each_entry(tb, &dn_fib_table_hash[h], hlist) { if (e < s_e) goto next; if (dumped) @@ -828,7 +827,6 @@ out: struct dn_fib_table *dn_fib_get_table(u32 n, int create) { struct dn_fib_table *t; - struct hlist_node *node; unsigned int h; if (n < RT_TABLE_MIN) @@ -839,7 +837,7 @@ struct dn_fib_table *dn_fib_get_table(u32 n, int create) h = n & (DN_FIB_TABLE_HASHSZ - 1); rcu_read_lock(); - hlist_for_each_entry_rcu(t, node, &dn_fib_table_hash[h], hlist) { + hlist_for_each_entry_rcu(t, &dn_fib_table_hash[h], hlist) { if (t->n == n) { rcu_read_unlock(); return t; @@ -885,11 +883,10 @@ void dn_fib_flush(void) { int flushed = 0; struct dn_fib_table *tb; - struct hlist_node *node; unsigned int h; for (h = 0; h < DN_FIB_TABLE_HASHSZ; h++) { - hlist_for_each_entry(tb, node, &dn_fib_table_hash[h], hlist) + hlist_for_each_entry(tb, &dn_fib_table_hash[h], hlist) flushed += tb->flush(tb); } @@ -908,12 +905,12 @@ void __init dn_fib_table_init(void) void __exit dn_fib_table_cleanup(void) { struct dn_fib_table *t; - struct hlist_node *node, *next; + struct hlist_node *next; unsigned int h; write_lock(&dn_fib_tables_lock); for (h = 0; h < DN_FIB_TABLE_HASHSZ; h++) { - hlist_for_each_entry_safe(t, node, next, &dn_fib_table_hash[h], + hlist_for_each_entry_safe(t, next, &dn_fib_table_hash[h], hlist) { hlist_del(&t->hlist); kfree(t); diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c index 16705611589a..e0da175f8e5b 100644 --- a/net/ieee802154/dgram.c +++ b/net/ieee802154/dgram.c @@ -350,7 +350,6 @@ static inline int ieee802154_match_sock(u8 *hw_addr, u16 pan_id, int ieee802154_dgram_deliver(struct net_device *dev, struct sk_buff *skb) { struct sock *sk, *prev = NULL; - struct hlist_node *node; int ret = NET_RX_SUCCESS; u16 pan_id, short_addr; @@ -361,7 +360,7 @@ int ieee802154_dgram_deliver(struct net_device *dev, struct sk_buff *skb) short_addr = ieee802154_mlme_ops(dev)->get_short_addr(dev); read_lock(&dgram_lock); - sk_for_each(sk, node, &dgram_head) { + sk_for_each(sk, &dgram_head) { if (ieee802154_match_sock(dev->dev_addr, pan_id, short_addr, dgram_sk(sk))) { if (prev) { diff --git a/net/ieee802154/raw.c b/net/ieee802154/raw.c index 50e823927d49..41f538b8e59c 100644 --- a/net/ieee802154/raw.c +++ b/net/ieee802154/raw.c @@ -221,10 +221,9 @@ static int raw_rcv_skb(struct sock *sk, struct sk_buff *skb) void ieee802154_raw_deliver(struct net_device *dev, struct sk_buff *skb) { struct sock *sk; - struct hlist_node *node; read_lock(&raw_lock); - sk_for_each(sk, node, &raw_head) { + sk_for_each(sk, &raw_head) { bh_lock_sock(sk); if (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == dev->ifindex) { diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 5281314886c1..f678507bc829 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -139,10 +139,9 @@ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref) u32 hash = inet_addr_hash(net, addr); struct net_device *result = NULL; struct in_ifaddr *ifa; - struct hlist_node *node; rcu_read_lock(); - hlist_for_each_entry_rcu(ifa, node, &inet_addr_lst[hash], hash) { + hlist_for_each_entry_rcu(ifa, &inet_addr_lst[hash], hash) { if (ifa->ifa_local == addr) { struct net_device *dev = ifa->ifa_dev->dev; @@ -588,7 +587,6 @@ static void check_lifetime(struct work_struct *work) { unsigned long now, next, next_sec, next_sched; struct in_ifaddr *ifa; - struct hlist_node *node; int i; now = jiffies; @@ -596,8 +594,7 @@ static void check_lifetime(struct work_struct *work) rcu_read_lock(); for (i = 0; i < IN4_ADDR_HSIZE; i++) { - hlist_for_each_entry_rcu(ifa, node, - &inet_addr_lst[i], hash) { + hlist_for_each_entry_rcu(ifa, &inet_addr_lst[i], hash) { unsigned long age; if (ifa->ifa_flags & IFA_F_PERMANENT) @@ -1493,7 +1490,6 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) struct in_device *in_dev; struct in_ifaddr *ifa; struct hlist_head *head; - struct hlist_node *node; s_h = cb->args[0]; s_idx = idx = cb->args[1]; @@ -1503,7 +1499,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) idx = 0; head = &net->dev_index_head[h]; rcu_read_lock(); - hlist_for_each_entry_rcu(dev, node, head, index_hlist) { + hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; if (h > s_h || idx > s_idx) diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 99f00d39d10b..eb4bb12b3eb4 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -112,7 +112,6 @@ struct fib_table *fib_new_table(struct net *net, u32 id) struct fib_table *fib_get_table(struct net *net, u32 id) { struct fib_table *tb; - struct hlist_node *node; struct hlist_head *head; unsigned int h; @@ -122,7 +121,7 @@ struct fib_table *fib_get_table(struct net *net, u32 id) rcu_read_lock(); head = &net->ipv4.fib_table_hash[h]; - hlist_for_each_entry_rcu(tb, node, head, tb_hlist) { + hlist_for_each_entry_rcu(tb, head, tb_hlist) { if (tb->tb_id == id) { rcu_read_unlock(); return tb; @@ -137,13 +136,12 @@ static void fib_flush(struct net *net) { int flushed = 0; struct fib_table *tb; - struct hlist_node *node; struct hlist_head *head; unsigned int h; for (h = 0; h < FIB_TABLE_HASHSZ; h++) { head = &net->ipv4.fib_table_hash[h]; - hlist_for_each_entry(tb, node, head, tb_hlist) + hlist_for_each_entry(tb, head, tb_hlist) flushed += fib_table_flush(tb); } @@ -656,7 +654,6 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) unsigned int h, s_h; unsigned int e = 0, s_e; struct fib_table *tb; - struct hlist_node *node; struct hlist_head *head; int dumped = 0; @@ -670,7 +667,7 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) for (h = s_h; h < FIB_TABLE_HASHSZ; h++, s_e = 0) { e = 0; head = &net->ipv4.fib_table_hash[h]; - hlist_for_each_entry(tb, node, head, tb_hlist) { + hlist_for_each_entry(tb, head, tb_hlist) { if (e < s_e) goto next; if (dumped) @@ -1117,11 +1114,11 @@ static void ip_fib_net_exit(struct net *net) for (i = 0; i < FIB_TABLE_HASHSZ; i++) { struct fib_table *tb; struct hlist_head *head; - struct hlist_node *node, *tmp; + struct hlist_node *tmp; head = &net->ipv4.fib_table_hash[i]; - hlist_for_each_entry_safe(tb, node, tmp, head, tb_hlist) { - hlist_del(node); + hlist_for_each_entry_safe(tb, tmp, head, tb_hlist) { + hlist_del(&tb->tb_hlist); fib_table_flush(tb); fib_free_table(tb); } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 4797a800faf8..8f6cb7a87cd6 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -298,14 +298,13 @@ static inline unsigned int fib_info_hashfn(const struct fib_info *fi) static struct fib_info *fib_find_info(const struct fib_info *nfi) { struct hlist_head *head; - struct hlist_node *node; struct fib_info *fi; unsigned int hash; hash = fib_info_hashfn(nfi); head = &fib_info_hash[hash]; - hlist_for_each_entry(fi, node, head, fib_hash) { + hlist_for_each_entry(fi, head, fib_hash) { if (!net_eq(fi->fib_net, nfi->fib_net)) continue; if (fi->fib_nhs != nfi->fib_nhs) @@ -331,7 +330,6 @@ static struct fib_info *fib_find_info(const struct fib_info *nfi) int ip_fib_check_default(__be32 gw, struct net_device *dev) { struct hlist_head *head; - struct hlist_node *node; struct fib_nh *nh; unsigned int hash; @@ -339,7 +337,7 @@ int ip_fib_check_default(__be32 gw, struct net_device *dev) hash = fib_devindex_hashfn(dev->ifindex); head = &fib_info_devhash[hash]; - hlist_for_each_entry(nh, node, head, nh_hash) { + hlist_for_each_entry(nh, head, nh_hash) { if (nh->nh_dev == dev && nh->nh_gw == gw && !(nh->nh_flags & RTNH_F_DEAD)) { @@ -721,10 +719,10 @@ static void fib_info_hash_move(struct hlist_head *new_info_hash, for (i = 0; i < old_size; i++) { struct hlist_head *head = &fib_info_hash[i]; - struct hlist_node *node, *n; + struct hlist_node *n; struct fib_info *fi; - hlist_for_each_entry_safe(fi, node, n, head, fib_hash) { + hlist_for_each_entry_safe(fi, n, head, fib_hash) { struct hlist_head *dest; unsigned int new_hash; @@ -739,10 +737,10 @@ static void fib_info_hash_move(struct hlist_head *new_info_hash, for (i = 0; i < old_size; i++) { struct hlist_head *lhead = &fib_info_laddrhash[i]; - struct hlist_node *node, *n; + struct hlist_node *n; struct fib_info *fi; - hlist_for_each_entry_safe(fi, node, n, lhead, fib_lhash) { + hlist_for_each_entry_safe(fi, n, lhead, fib_lhash) { struct hlist_head *ldest; unsigned int new_hash; @@ -1096,13 +1094,12 @@ int fib_sync_down_addr(struct net *net, __be32 local) int ret = 0; unsigned int hash = fib_laddr_hashfn(local); struct hlist_head *head = &fib_info_laddrhash[hash]; - struct hlist_node *node; struct fib_info *fi; if (fib_info_laddrhash == NULL || local == 0) return 0; - hlist_for_each_entry(fi, node, head, fib_lhash) { + hlist_for_each_entry(fi, head, fib_lhash) { if (!net_eq(fi->fib_net, net)) continue; if (fi->fib_prefsrc == local) { @@ -1120,13 +1117,12 @@ int fib_sync_down_dev(struct net_device *dev, int force) struct fib_info *prev_fi = NULL; unsigned int hash = fib_devindex_hashfn(dev->ifindex); struct hlist_head *head = &fib_info_devhash[hash]; - struct hlist_node *node; struct fib_nh *nh; if (force) scope = -1; - hlist_for_each_entry(nh, node, head, nh_hash) { + hlist_for_each_entry(nh, head, nh_hash) { struct fib_info *fi = nh->nh_parent; int dead; @@ -1232,7 +1228,6 @@ int fib_sync_up(struct net_device *dev) struct fib_info *prev_fi; unsigned int hash; struct hlist_head *head; - struct hlist_node *node; struct fib_nh *nh; int ret; @@ -1244,7 +1239,7 @@ int fib_sync_up(struct net_device *dev) head = &fib_info_devhash[hash]; ret = 0; - hlist_for_each_entry(nh, node, head, nh_hash) { + hlist_for_each_entry(nh, head, nh_hash) { struct fib_info *fi = nh->nh_parent; int alive; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 31d771ca9a70..c13dc7675a45 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -920,10 +920,9 @@ nomem: static struct leaf_info *find_leaf_info(struct leaf *l, int plen) { struct hlist_head *head = &l->list; - struct hlist_node *node; struct leaf_info *li; - hlist_for_each_entry_rcu(li, node, head, hlist) + hlist_for_each_entry_rcu(li, head, hlist) if (li->plen == plen) return li; @@ -943,12 +942,11 @@ static inline struct list_head *get_fa_head(struct leaf *l, int plen) static void insert_leaf_info(struct hlist_head *head, struct leaf_info *new) { struct leaf_info *li = NULL, *last = NULL; - struct hlist_node *node; if (hlist_empty(head)) { hlist_add_head_rcu(&new->hlist, head); } else { - hlist_for_each_entry(li, node, head, hlist) { + hlist_for_each_entry(li, head, hlist) { if (new->plen > li->plen) break; @@ -1354,9 +1352,8 @@ static int check_leaf(struct fib_table *tb, struct trie *t, struct leaf *l, { struct leaf_info *li; struct hlist_head *hhead = &l->list; - struct hlist_node *node; - hlist_for_each_entry_rcu(li, node, hhead, hlist) { + hlist_for_each_entry_rcu(li, hhead, hlist) { struct fib_alias *fa; if (l->key != (key & li->mask_plen)) @@ -1740,10 +1737,10 @@ static int trie_flush_leaf(struct leaf *l) { int found = 0; struct hlist_head *lih = &l->list; - struct hlist_node *node, *tmp; + struct hlist_node *tmp; struct leaf_info *li = NULL; - hlist_for_each_entry_safe(li, node, tmp, lih, hlist) { + hlist_for_each_entry_safe(li, tmp, lih, hlist) { found += trie_flush_list(&li->falh); if (list_empty(&li->falh)) { @@ -1895,14 +1892,13 @@ static int fn_trie_dump_leaf(struct leaf *l, struct fib_table *tb, struct sk_buff *skb, struct netlink_callback *cb) { struct leaf_info *li; - struct hlist_node *node; int i, s_i; s_i = cb->args[4]; i = 0; /* rcu_read_lock is hold by caller */ - hlist_for_each_entry_rcu(li, node, &l->list, hlist) { + hlist_for_each_entry_rcu(li, &l->list, hlist) { if (i < s_i) { i++; continue; @@ -2092,14 +2088,13 @@ static void trie_collect_stats(struct trie *t, struct trie_stat *s) if (IS_LEAF(n)) { struct leaf *l = (struct leaf *)n; struct leaf_info *li; - struct hlist_node *tmp; s->leaves++; s->totdepth += iter.depth; if (iter.depth > s->maxdepth) s->maxdepth = iter.depth; - hlist_for_each_entry_rcu(li, tmp, &l->list, hlist) + hlist_for_each_entry_rcu(li, &l->list, hlist) ++s->prefixes; } else { const struct tnode *tn = (const struct tnode *) n; @@ -2200,10 +2195,9 @@ static int fib_triestat_seq_show(struct seq_file *seq, void *v) for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; - struct hlist_node *node; struct fib_table *tb; - hlist_for_each_entry_rcu(tb, node, head, tb_hlist) { + hlist_for_each_entry_rcu(tb, head, tb_hlist) { struct trie *t = (struct trie *) tb->tb_data; struct trie_stat stat; @@ -2245,10 +2239,9 @@ static struct rt_trie_node *fib_trie_get_idx(struct seq_file *seq, loff_t pos) for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; - struct hlist_node *node; struct fib_table *tb; - hlist_for_each_entry_rcu(tb, node, head, tb_hlist) { + hlist_for_each_entry_rcu(tb, head, tb_hlist) { struct rt_trie_node *n; for (n = fib_trie_get_first(iter, @@ -2298,7 +2291,7 @@ static void *fib_trie_seq_next(struct seq_file *seq, void *v, loff_t *pos) /* new hash chain */ while (++h < FIB_TABLE_HASHSZ) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; - hlist_for_each_entry_rcu(tb, tb_node, head, tb_hlist) { + hlist_for_each_entry_rcu(tb, head, tb_hlist) { n = fib_trie_get_first(iter, (struct trie *) tb->tb_data); if (n) goto found; @@ -2381,13 +2374,12 @@ static int fib_trie_seq_show(struct seq_file *seq, void *v) } else { struct leaf *l = (struct leaf *) n; struct leaf_info *li; - struct hlist_node *node; __be32 val = htonl(l->key); seq_indent(seq, iter->depth); seq_printf(seq, " |-- %pI4\n", &val); - hlist_for_each_entry_rcu(li, node, &l->list, hlist) { + hlist_for_each_entry_rcu(li, &l->list, hlist) { struct fib_alias *fa; list_for_each_entry_rcu(fa, &li->falh, fa_list) { @@ -2532,7 +2524,6 @@ static int fib_route_seq_show(struct seq_file *seq, void *v) { struct leaf *l = v; struct leaf_info *li; - struct hlist_node *node; if (v == SEQ_START_TOKEN) { seq_printf(seq, "%-127s\n", "Iface\tDestination\tGateway " @@ -2541,7 +2532,7 @@ static int fib_route_seq_show(struct seq_file *seq, void *v) return 0; } - hlist_for_each_entry_rcu(li, node, &l->list, hlist) { + hlist_for_each_entry_rcu(li, &l->list, hlist) { struct fib_alias *fa; __be32 mask, prefix; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 11cb4979a465..7d1874be1df3 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -57,7 +57,6 @@ int inet_csk_bind_conflict(const struct sock *sk, const struct inet_bind_bucket *tb, bool relax) { struct sock *sk2; - struct hlist_node *node; int reuse = sk->sk_reuse; int reuseport = sk->sk_reuseport; kuid_t uid = sock_i_uid((struct sock *)sk); @@ -69,7 +68,7 @@ int inet_csk_bind_conflict(const struct sock *sk, * one this bucket belongs to. */ - sk_for_each_bound(sk2, node, &tb->owners) { + sk_for_each_bound(sk2, &tb->owners) { if (sk != sk2 && !inet_v6_ipv6only(sk2) && (!sk->sk_bound_dev_if || @@ -95,7 +94,7 @@ int inet_csk_bind_conflict(const struct sock *sk, } } } - return node != NULL; + return sk2 != NULL; } EXPORT_SYMBOL_GPL(inet_csk_bind_conflict); @@ -106,7 +105,6 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum) { struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; struct inet_bind_hashbucket *head; - struct hlist_node *node; struct inet_bind_bucket *tb; int ret, attempts = 5; struct net *net = sock_net(sk); @@ -129,7 +127,7 @@ again: head = &hashinfo->bhash[inet_bhashfn(net, rover, hashinfo->bhash_size)]; spin_lock(&head->lock); - inet_bind_bucket_for_each(tb, node, &head->chain) + inet_bind_bucket_for_each(tb, &head->chain) if (net_eq(ib_net(tb), net) && tb->port == rover) { if (((tb->fastreuse > 0 && sk->sk_reuse && @@ -183,7 +181,7 @@ have_snum: head = &hashinfo->bhash[inet_bhashfn(net, snum, hashinfo->bhash_size)]; spin_lock(&head->lock); - inet_bind_bucket_for_each(tb, node, &head->chain) + inet_bind_bucket_for_each(tb, &head->chain) if (net_eq(ib_net(tb), net) && tb->port == snum) goto tb_found; } diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 2e453bde6992..245ae078a07f 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -33,9 +33,9 @@ static void inet_frag_secret_rebuild(unsigned long dummy) get_random_bytes(&f->rnd, sizeof(u32)); for (i = 0; i < INETFRAGS_HASHSZ; i++) { struct inet_frag_queue *q; - struct hlist_node *p, *n; + struct hlist_node *n; - hlist_for_each_entry_safe(q, p, n, &f->hash[i], list) { + hlist_for_each_entry_safe(q, n, &f->hash[i], list) { unsigned int hval = f->hashfn(q); if (hval != i) { @@ -203,7 +203,6 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf, { struct inet_frag_queue *qp; #ifdef CONFIG_SMP - struct hlist_node *n; #endif unsigned int hash; @@ -219,7 +218,7 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf, * such entry could be created on other cpu, while we * promoted read lock to write lock. */ - hlist_for_each_entry(qp, n, &f->hash[hash], list) { + hlist_for_each_entry(qp, &f->hash[hash], list) { if (qp->net == nf && f->match(qp, arg)) { atomic_inc(&qp->refcnt); write_unlock(&f->lock); @@ -278,9 +277,8 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, __releases(&f->lock) { struct inet_frag_queue *q; - struct hlist_node *n; - hlist_for_each_entry(q, n, &f->hash[hash], list) { + hlist_for_each_entry(q, &f->hash[hash], list) { if (q->net == nf && f->match(q, key)) { atomic_inc(&q->refcnt); read_unlock(&f->lock); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 0ce0595d9861..6af375afeeef 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -120,13 +120,12 @@ int __inet_inherit_port(struct sock *sk, struct sock *child) * that the listener socket's icsk_bind_hash is the same * as that of the child socket. We have to look up or * create a new bind bucket for the child here. */ - struct hlist_node *node; - inet_bind_bucket_for_each(tb, node, &head->chain) { + inet_bind_bucket_for_each(tb, &head->chain) { if (net_eq(ib_net(tb), sock_net(sk)) && tb->port == port) break; } - if (!node) { + if (!tb) { tb = inet_bind_bucket_create(table->bind_bucket_cachep, sock_net(sk), head, port); if (!tb) { @@ -493,7 +492,6 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, int i, remaining, low, high, port; static u32 hint; u32 offset = hint + port_offset; - struct hlist_node *node; struct inet_timewait_sock *tw = NULL; inet_get_local_port_range(&low, &high); @@ -512,7 +510,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, * because the established check is already * unique enough. */ - inet_bind_bucket_for_each(tb, node, &head->chain) { + inet_bind_bucket_for_each(tb, &head->chain) { if (net_eq(ib_net(tb), net) && tb->port == port) { if (tb->fastreuse >= 0 || diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 2784db3155fb..1f27c9f4afd0 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -216,7 +216,6 @@ static int inet_twdr_do_twkill_work(struct inet_timewait_death_row *twdr, const int slot) { struct inet_timewait_sock *tw; - struct hlist_node *node; unsigned int killed; int ret; @@ -229,7 +228,7 @@ static int inet_twdr_do_twkill_work(struct inet_timewait_death_row *twdr, killed = 0; ret = 0; rescan: - inet_twsk_for_each_inmate(tw, node, &twdr->cells[slot]) { + inet_twsk_for_each_inmate(tw, &twdr->cells[slot]) { __inet_twsk_del_dead_node(tw); spin_unlock(&twdr->death_lock); __inet_twsk_kill(tw, twdr->hashinfo); @@ -438,10 +437,10 @@ void inet_twdr_twcal_tick(unsigned long data) for (n = 0; n < INET_TWDR_RECYCLE_SLOTS; n++) { if (time_before_eq(j, now)) { - struct hlist_node *node, *safe; + struct hlist_node *safe; struct inet_timewait_sock *tw; - inet_twsk_for_each_inmate_safe(tw, node, safe, + inet_twsk_for_each_inmate_safe(tw, safe, &twdr->twcal_row[slot]) { __inet_twsk_del_dead_node(tw); __inet_twsk_kill(tw, twdr->hashinfo); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 6f08991409c3..f5a8d7dd5165 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -111,9 +111,7 @@ EXPORT_SYMBOL_GPL(raw_unhash_sk); static struct sock *__raw_v4_lookup(struct net *net, struct sock *sk, unsigned short num, __be32 raddr, __be32 laddr, int dif) { - struct hlist_node *node; - - sk_for_each_from(sk, node) { + sk_for_each_from(sk) { struct inet_sock *inet = inet_sk(sk); if (net_eq(sock_net(sk), net) && inet->inet_num == num && @@ -122,6 +120,11 @@ static struct sock *__raw_v4_lookup(struct net *net, struct sock *sk, !(sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)) goto found; /* gotcha */ } + sk_for_each_from (sk) { + struct inet_sock *inet=inet_sk(sk); + if (net_eq(sock_net(sk), net) && inet->inet_num == num && !(inet->inet_daddr && inet->inet_daddr != raddr) && !(inet->inet_rcv_saddr && inet->inet_rcv_saddr != laddr) && !(sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)) + goto found; + } sk = NULL; found: return sk; @@ -914,9 +917,7 @@ static struct sock *raw_get_first(struct seq_file *seq) for (state->bucket = 0; state->bucket < RAW_HTABLE_SIZE; ++state->bucket) { - struct hlist_node *node; - - sk_for_each(sk, node, &state->h->ht[state->bucket]) + sk_for_each(sk, &state->h->ht[state->bucket]) if (sock_net(sk) == seq_file_net(seq)) goto found; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 0eaf685bddc9..922e5cc8e29b 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -952,7 +952,6 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, { struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; - struct hlist_node *pos; unsigned int size = sizeof(struct in_addr); struct tcp_md5sig_info *md5sig; @@ -966,7 +965,7 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, if (family == AF_INET6) size = sizeof(struct in6_addr); #endif - hlist_for_each_entry_rcu(key, pos, &md5sig->head, node) { + hlist_for_each_entry_rcu(key, &md5sig->head, node) { if (key->family != family) continue; if (!memcmp(&key->addr, addr, size)) @@ -1067,14 +1066,14 @@ static void tcp_clear_md5_list(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; - struct hlist_node *pos, *n; + struct hlist_node *n; struct tcp_md5sig_info *md5sig; md5sig = rcu_dereference_protected(tp->md5sig_info, 1); if (!hlist_empty(&md5sig->head)) tcp_free_md5sig_pool(); - hlist_for_each_entry_safe(key, pos, n, &md5sig->head, node) { + hlist_for_each_entry_safe(key, n, &md5sig->head, node) { hlist_del_rcu(&key->node); atomic_sub(sizeof(*key), &sk->sk_omem_alloc); kfree_rcu(key, rcu); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index bd9f9360f769..82c0f0c47506 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1408,11 +1408,10 @@ int ipv6_chk_addr(struct net *net, const struct in6_addr *addr, struct net_device *dev, int strict) { struct inet6_ifaddr *ifp; - struct hlist_node *node; unsigned int hash = inet6_addr_hash(addr); rcu_read_lock_bh(); - hlist_for_each_entry_rcu(ifp, node, &inet6_addr_lst[hash], addr_lst) { + hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) { if (!net_eq(dev_net(ifp->idev->dev), net)) continue; if (ipv6_addr_equal(&ifp->addr, addr) && @@ -1434,9 +1433,8 @@ static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, { unsigned int hash = inet6_addr_hash(addr); struct inet6_ifaddr *ifp; - struct hlist_node *node; - hlist_for_each_entry(ifp, node, &inet6_addr_lst[hash], addr_lst) { + hlist_for_each_entry(ifp, &inet6_addr_lst[hash], addr_lst) { if (!net_eq(dev_net(ifp->idev->dev), net)) continue; if (ipv6_addr_equal(&ifp->addr, addr)) { @@ -1476,10 +1474,9 @@ struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *add { struct inet6_ifaddr *ifp, *result = NULL; unsigned int hash = inet6_addr_hash(addr); - struct hlist_node *node; rcu_read_lock_bh(); - hlist_for_each_entry_rcu_bh(ifp, node, &inet6_addr_lst[hash], addr_lst) { + hlist_for_each_entry_rcu_bh(ifp, &inet6_addr_lst[hash], addr_lst) { if (!net_eq(dev_net(ifp->idev->dev), net)) continue; if (ipv6_addr_equal(&ifp->addr, addr)) { @@ -2896,11 +2893,10 @@ static int addrconf_ifdown(struct net_device *dev, int how) /* Step 2: clear hash table */ for (i = 0; i < IN6_ADDR_HSIZE; i++) { struct hlist_head *h = &inet6_addr_lst[i]; - struct hlist_node *n; spin_lock_bh(&addrconf_hash_lock); restart: - hlist_for_each_entry_rcu(ifa, n, h, addr_lst) { + hlist_for_each_entry_rcu(ifa, h, addr_lst) { if (ifa->idev == idev) { hlist_del_init_rcu(&ifa->addr_lst); addrconf_del_timer(ifa); @@ -3207,8 +3203,7 @@ static struct inet6_ifaddr *if6_get_first(struct seq_file *seq, loff_t pos) } for (; state->bucket < IN6_ADDR_HSIZE; ++state->bucket) { - struct hlist_node *n; - hlist_for_each_entry_rcu_bh(ifa, n, &inet6_addr_lst[state->bucket], + hlist_for_each_entry_rcu_bh(ifa, &inet6_addr_lst[state->bucket], addr_lst) { if (!net_eq(dev_net(ifa->idev->dev), net)) continue; @@ -3233,9 +3228,8 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq, { struct if6_iter_state *state = seq->private; struct net *net = seq_file_net(seq); - struct hlist_node *n = &ifa->addr_lst; - hlist_for_each_entry_continue_rcu_bh(ifa, n, addr_lst) { + hlist_for_each_entry_continue_rcu_bh(ifa, addr_lst) { if (!net_eq(dev_net(ifa->idev->dev), net)) continue; state->offset++; @@ -3244,7 +3238,7 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq, while (++state->bucket < IN6_ADDR_HSIZE) { state->offset = 0; - hlist_for_each_entry_rcu_bh(ifa, n, + hlist_for_each_entry_rcu_bh(ifa, &inet6_addr_lst[state->bucket], addr_lst) { if (!net_eq(dev_net(ifa->idev->dev), net)) continue; @@ -3346,11 +3340,10 @@ int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr) { int ret = 0; struct inet6_ifaddr *ifp = NULL; - struct hlist_node *n; unsigned int hash = inet6_addr_hash(addr); rcu_read_lock_bh(); - hlist_for_each_entry_rcu_bh(ifp, n, &inet6_addr_lst[hash], addr_lst) { + hlist_for_each_entry_rcu_bh(ifp, &inet6_addr_lst[hash], addr_lst) { if (!net_eq(dev_net(ifp->idev->dev), net)) continue; if (ipv6_addr_equal(&ifp->addr, addr) && @@ -3372,7 +3365,6 @@ static void addrconf_verify(unsigned long foo) { unsigned long now, next, next_sec, next_sched; struct inet6_ifaddr *ifp; - struct hlist_node *node; int i; rcu_read_lock_bh(); @@ -3384,7 +3376,7 @@ static void addrconf_verify(unsigned long foo) for (i = 0; i < IN6_ADDR_HSIZE; i++) { restart: - hlist_for_each_entry_rcu_bh(ifp, node, + hlist_for_each_entry_rcu_bh(ifp, &inet6_addr_lst[i], addr_lst) { unsigned long age; @@ -3855,7 +3847,6 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev; struct inet6_dev *idev; struct hlist_head *head; - struct hlist_node *node; s_h = cb->args[0]; s_idx = idx = cb->args[1]; @@ -3865,7 +3856,7 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; head = &net->dev_index_head[h]; - hlist_for_each_entry_rcu(dev, node, head, index_hlist) { + hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; if (h > s_h || idx > s_idx) @@ -4211,7 +4202,6 @@ static int inet6_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) struct net_device *dev; struct inet6_dev *idev; struct hlist_head *head; - struct hlist_node *node; s_h = cb->args[0]; s_idx = cb->args[1]; @@ -4220,7 +4210,7 @@ static int inet6_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; head = &net->dev_index_head[h]; - hlist_for_each_entry_rcu(dev, node, head, index_hlist) { + hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; idev = __in6_dev_get(dev); diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index ff76eecfd622..aad64352cb60 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -173,9 +173,8 @@ static struct ip6addrlbl_entry *__ipv6_addr_label(struct net *net, const struct in6_addr *addr, int type, int ifindex) { - struct hlist_node *pos; struct ip6addrlbl_entry *p; - hlist_for_each_entry_rcu(p, pos, &ip6addrlbl_table.head, list) { + hlist_for_each_entry_rcu(p, &ip6addrlbl_table.head, list) { if (__ip6addrlbl_match(net, p, addr, type, ifindex)) return p; } @@ -261,9 +260,9 @@ static int __ip6addrlbl_add(struct ip6addrlbl_entry *newp, int replace) if (hlist_empty(&ip6addrlbl_table.head)) { hlist_add_head_rcu(&newp->list, &ip6addrlbl_table.head); } else { - struct hlist_node *pos, *n; + struct hlist_node *n; struct ip6addrlbl_entry *p = NULL; - hlist_for_each_entry_safe(p, pos, n, + hlist_for_each_entry_safe(p, n, &ip6addrlbl_table.head, list) { if (p->prefixlen == newp->prefixlen && net_eq(ip6addrlbl_net(p), ip6addrlbl_net(newp)) && @@ -319,13 +318,13 @@ static int __ip6addrlbl_del(struct net *net, int ifindex) { struct ip6addrlbl_entry *p = NULL; - struct hlist_node *pos, *n; + struct hlist_node *n; int ret = -ESRCH; ADDRLABEL(KERN_DEBUG "%s(prefix=%pI6, prefixlen=%d, ifindex=%d)\n", __func__, prefix, prefixlen, ifindex); - hlist_for_each_entry_safe(p, pos, n, &ip6addrlbl_table.head, list) { + hlist_for_each_entry_safe(p, n, &ip6addrlbl_table.head, list) { if (p->prefixlen == prefixlen && net_eq(ip6addrlbl_net(p), net) && p->ifindex == ifindex && @@ -380,11 +379,11 @@ static int __net_init ip6addrlbl_net_init(struct net *net) static void __net_exit ip6addrlbl_net_exit(struct net *net) { struct ip6addrlbl_entry *p = NULL; - struct hlist_node *pos, *n; + struct hlist_node *n; /* Remove all labels belonging to the exiting net */ spin_lock(&ip6addrlbl_table.lock); - hlist_for_each_entry_safe(p, pos, n, &ip6addrlbl_table.head, list) { + hlist_for_each_entry_safe(p, n, &ip6addrlbl_table.head, list) { if (net_eq(ip6addrlbl_net(p), net)) { hlist_del_rcu(&p->list); ip6addrlbl_put(p); @@ -505,12 +504,11 @@ static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); struct ip6addrlbl_entry *p; - struct hlist_node *pos; int idx = 0, s_idx = cb->args[0]; int err; rcu_read_lock(); - hlist_for_each_entry_rcu(p, pos, &ip6addrlbl_table.head, list) { + hlist_for_each_entry_rcu(p, &ip6addrlbl_table.head, list) { if (idx >= s_idx && net_eq(ip6addrlbl_net(p), net)) { if ((err = ip6addrlbl_fill(skb, p, diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index b386a2ce4c6f..9bfab19ff3c0 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -31,7 +31,6 @@ int inet6_csk_bind_conflict(const struct sock *sk, const struct inet_bind_bucket *tb, bool relax) { const struct sock *sk2; - const struct hlist_node *node; int reuse = sk->sk_reuse; int reuseport = sk->sk_reuseport; kuid_t uid = sock_i_uid((struct sock *)sk); @@ -41,7 +40,7 @@ int inet6_csk_bind_conflict(const struct sock *sk, * See comment in inet_csk_bind_conflict about sock lookup * vs net namespaces issues. */ - sk_for_each_bound(sk2, node, &tb->owners) { + sk_for_each_bound(sk2, &tb->owners) { if (sk != sk2 && (!sk->sk_bound_dev_if || !sk2->sk_bound_dev_if || @@ -58,7 +57,7 @@ int inet6_csk_bind_conflict(const struct sock *sk, } } - return node != NULL; + return sk2 != NULL; } EXPORT_SYMBOL_GPL(inet6_csk_bind_conflict); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 710cafd2e1a9..192dd1a0e188 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -224,7 +224,6 @@ struct fib6_table *fib6_get_table(struct net *net, u32 id) { struct fib6_table *tb; struct hlist_head *head; - struct hlist_node *node; unsigned int h; if (id == 0) @@ -232,7 +231,7 @@ struct fib6_table *fib6_get_table(struct net *net, u32 id) h = id & (FIB6_TABLE_HASHSZ - 1); rcu_read_lock(); head = &net->ipv6.fib_table_hash[h]; - hlist_for_each_entry_rcu(tb, node, head, tb6_hlist) { + hlist_for_each_entry_rcu(tb, head, tb6_hlist) { if (tb->tb6_id == id) { rcu_read_unlock(); return tb; @@ -363,7 +362,6 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) struct rt6_rtnl_dump_arg arg; struct fib6_walker_t *w; struct fib6_table *tb; - struct hlist_node *node; struct hlist_head *head; int res = 0; @@ -398,7 +396,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) for (h = s_h; h < FIB6_TABLE_HASHSZ; h++, s_e = 0) { e = 0; head = &net->ipv6.fib_table_hash[h]; - hlist_for_each_entry_rcu(tb, node, head, tb6_hlist) { + hlist_for_each_entry_rcu(tb, head, tb6_hlist) { if (e < s_e) goto next; res = fib6_dump_table(tb, skb, cb); @@ -1520,14 +1518,13 @@ void fib6_clean_all_ro(struct net *net, int (*func)(struct rt6_info *, void *arg int prune, void *arg) { struct fib6_table *table; - struct hlist_node *node; struct hlist_head *head; unsigned int h; rcu_read_lock(); for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { head = &net->ipv6.fib_table_hash[h]; - hlist_for_each_entry_rcu(table, node, head, tb6_hlist) { + hlist_for_each_entry_rcu(table, head, tb6_hlist) { read_lock_bh(&table->tb6_lock); fib6_clean_tree(net, &table->tb6_root, func, prune, arg); @@ -1540,14 +1537,13 @@ void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg), int prune, void *arg) { struct fib6_table *table; - struct hlist_node *node; struct hlist_head *head; unsigned int h; rcu_read_lock(); for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { head = &net->ipv6.fib_table_hash[h]; - hlist_for_each_entry_rcu(table, node, head, tb6_hlist) { + hlist_for_each_entry_rcu(table, head, tb6_hlist) { write_lock_bh(&table->tb6_lock); fib6_clean_tree(net, &table->tb6_root, func, prune, arg); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 70fa81449997..e2405853ff40 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -71,10 +71,9 @@ static struct sock *__raw_v6_lookup(struct net *net, struct sock *sk, unsigned short num, const struct in6_addr *loc_addr, const struct in6_addr *rmt_addr, int dif) { - struct hlist_node *node; bool is_multicast = ipv6_addr_is_multicast(loc_addr); - sk_for_each_from(sk, node) + sk_for_each_from(sk) if (inet_sk(sk)->inet_num == num) { struct ipv6_pinfo *np = inet6_sk(sk); @@ -98,6 +97,24 @@ static struct sock *__raw_v6_lookup(struct net *net, struct sock *sk, } goto found; } + sk_for_each_from (sk) + if (inet_sk(sk)->inet_num == num) { + struct ipv6_pinfo *np=inet6_sk(sk); + if (!net_eq(sock_net(sk), net)) + continue; + if (!ipv6_addr_any(&np->daddr) && !ipv6_addr_equal(&np->daddr, rmt_addr)) + continue; + if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif) + continue; + if (!ipv6_addr_any(&np->rcv_saddr)) { + if (ipv6_addr_equal(&np->rcv_saddr, loc_addr)) + goto found; + if (is_multicast && inet6_mc_check(sk, loc_addr, rmt_addr)) + goto found; + continue; + } + goto found; + } sk = NULL; found: return sk; diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index 6cc48012b730..de2bcfaaf759 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -89,9 +89,8 @@ static struct xfrm6_tunnel_spi *__xfrm6_tunnel_spi_lookup(struct net *net, const { struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); struct xfrm6_tunnel_spi *x6spi; - struct hlist_node *pos; - hlist_for_each_entry_rcu(x6spi, pos, + hlist_for_each_entry_rcu(x6spi, &xfrm6_tn->spi_byaddr[xfrm6_tunnel_spi_hash_byaddr(saddr)], list_byaddr) { if (xfrm6_addr_equal(&x6spi->addr, saddr)) @@ -120,9 +119,8 @@ static int __xfrm6_tunnel_spi_check(struct net *net, u32 spi) struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); struct xfrm6_tunnel_spi *x6spi; int index = xfrm6_tunnel_spi_hash_byspi(spi); - struct hlist_node *pos; - hlist_for_each_entry(x6spi, pos, + hlist_for_each_entry(x6spi, &xfrm6_tn->spi_byspi[index], list_byspi) { if (x6spi->spi == spi) @@ -203,11 +201,11 @@ static void xfrm6_tunnel_free_spi(struct net *net, xfrm_address_t *saddr) { struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); struct xfrm6_tunnel_spi *x6spi; - struct hlist_node *pos, *n; + struct hlist_node *n; spin_lock_bh(&xfrm6_tunnel_spi_lock); - hlist_for_each_entry_safe(x6spi, pos, n, + hlist_for_each_entry_safe(x6spi, n, &xfrm6_tn->spi_byaddr[xfrm6_tunnel_spi_hash_byaddr(saddr)], list_byaddr) { diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c index dfd6faaf0ea7..f547a47d381c 100644 --- a/net/ipx/af_ipx.c +++ b/net/ipx/af_ipx.c @@ -228,9 +228,8 @@ static struct sock *__ipxitf_find_socket(struct ipx_interface *intrfc, __be16 port) { struct sock *s; - struct hlist_node *node; - sk_for_each(s, node, &intrfc->if_sklist) + sk_for_each(s, &intrfc->if_sklist) if (ipx_sk(s)->port == port) goto found; s = NULL; @@ -259,12 +258,11 @@ static struct sock *ipxitf_find_internal_socket(struct ipx_interface *intrfc, __be16 port) { struct sock *s; - struct hlist_node *node; ipxitf_hold(intrfc); spin_lock_bh(&intrfc->if_sklist_lock); - sk_for_each(s, node, &intrfc->if_sklist) { + sk_for_each(s, &intrfc->if_sklist) { struct ipx_sock *ipxs = ipx_sk(s); if (ipxs->port == port && @@ -282,14 +280,14 @@ found: static void __ipxitf_down(struct ipx_interface *intrfc) { struct sock *s; - struct hlist_node *node, *t; + struct hlist_node *t; /* Delete all routes associated with this interface */ ipxrtr_del_routes(intrfc); spin_lock_bh(&intrfc->if_sklist_lock); /* error sockets */ - sk_for_each_safe(s, node, t, &intrfc->if_sklist) { + sk_for_each_safe(s, t, &intrfc->if_sklist) { struct ipx_sock *ipxs = ipx_sk(s); s->sk_err = ENOLINK; @@ -385,12 +383,11 @@ static int ipxitf_demux_socket(struct ipx_interface *intrfc, int is_broadcast = !memcmp(ipx->ipx_dest.node, ipx_broadcast_node, IPX_NODE_LEN); struct sock *s; - struct hlist_node *node; int rc; spin_lock_bh(&intrfc->if_sklist_lock); - sk_for_each(s, node, &intrfc->if_sklist) { + sk_for_each(s, &intrfc->if_sklist) { struct ipx_sock *ipxs = ipx_sk(s); if (ipxs->port == ipx->ipx_dest.sock && @@ -446,12 +443,11 @@ static struct sock *ncp_connection_hack(struct ipx_interface *intrfc, connection = (((int) *(ncphdr + 9)) << 8) | (int) *(ncphdr + 8); if (connection) { - struct hlist_node *node; /* Now we have to look for a special NCP connection handling * socket. Only these sockets have ipx_ncp_conn != 0, set by * SIOCIPXNCPCONN. */ spin_lock_bh(&intrfc->if_sklist_lock); - sk_for_each(sk, node, &intrfc->if_sklist) + sk_for_each(sk, &intrfc->if_sklist) if (ipx_sk(sk)->ipx_ncp_conn == connection) { sock_hold(sk); goto found; diff --git a/net/ipx/ipx_proc.c b/net/ipx/ipx_proc.c index 02ff7f2f60d4..65e8833a2510 100644 --- a/net/ipx/ipx_proc.c +++ b/net/ipx/ipx_proc.c @@ -103,19 +103,18 @@ out: static __inline__ struct sock *ipx_get_socket_idx(loff_t pos) { struct sock *s = NULL; - struct hlist_node *node; struct ipx_interface *i; list_for_each_entry(i, &ipx_interfaces, node) { spin_lock_bh(&i->if_sklist_lock); - sk_for_each(s, node, &i->if_sklist) { + sk_for_each(s, &i->if_sklist) { if (!pos) break; --pos; } spin_unlock_bh(&i->if_sklist_lock); if (!pos) { - if (node) + if (s) goto found; break; } diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index cd6f7a991d80..a7d11ffe4284 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -156,14 +156,13 @@ static int afiucv_pm_freeze(struct device *dev) { struct iucv_sock *iucv; struct sock *sk; - struct hlist_node *node; int err = 0; #ifdef CONFIG_PM_DEBUG printk(KERN_WARNING "afiucv_pm_freeze\n"); #endif read_lock(&iucv_sk_list.lock); - sk_for_each(sk, node, &iucv_sk_list.head) { + sk_for_each(sk, &iucv_sk_list.head) { iucv = iucv_sk(sk); switch (sk->sk_state) { case IUCV_DISCONN: @@ -194,13 +193,12 @@ static int afiucv_pm_freeze(struct device *dev) static int afiucv_pm_restore_thaw(struct device *dev) { struct sock *sk; - struct hlist_node *node; #ifdef CONFIG_PM_DEBUG printk(KERN_WARNING "afiucv_pm_restore_thaw\n"); #endif read_lock(&iucv_sk_list.lock); - sk_for_each(sk, node, &iucv_sk_list.head) { + sk_for_each(sk, &iucv_sk_list.head) { switch (sk->sk_state) { case IUCV_CONNECTED: sk->sk_err = EPIPE; @@ -390,9 +388,8 @@ static int afiucv_hs_send(struct iucv_message *imsg, struct sock *sock, static struct sock *__iucv_get_sock_by_name(char *nm) { struct sock *sk; - struct hlist_node *node; - sk_for_each(sk, node, &iucv_sk_list.head) + sk_for_each(sk, &iucv_sk_list.head) if (!memcmp(&iucv_sk(sk)->src_name, nm, 8)) return sk; @@ -1678,7 +1675,6 @@ static int iucv_callback_connreq(struct iucv_path *path, unsigned char user_data[16]; unsigned char nuser_data[16]; unsigned char src_name[8]; - struct hlist_node *node; struct sock *sk, *nsk; struct iucv_sock *iucv, *niucv; int err; @@ -1689,7 +1685,7 @@ static int iucv_callback_connreq(struct iucv_path *path, read_lock(&iucv_sk_list.lock); iucv = NULL; sk = NULL; - sk_for_each(sk, node, &iucv_sk_list.head) + sk_for_each(sk, &iucv_sk_list.head) if (sk->sk_state == IUCV_LISTEN && !memcmp(&iucv_sk(sk)->src_name, src_name, 8)) { /* @@ -2115,7 +2111,6 @@ static int afiucv_hs_callback_rx(struct sock *sk, struct sk_buff *skb) static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { - struct hlist_node *node; struct sock *sk; struct iucv_sock *iucv; struct af_iucv_trans_hdr *trans_hdr; @@ -2132,7 +2127,7 @@ static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev, iucv = NULL; sk = NULL; read_lock(&iucv_sk_list.lock); - sk_for_each(sk, node, &iucv_sk_list.head) { + sk_for_each(sk, &iucv_sk_list.head) { if (trans_hdr->flags == AF_IUCV_FLAG_SYN) { if ((!memcmp(&iucv_sk(sk)->src_name, trans_hdr->destAppName, 8)) && @@ -2225,10 +2220,9 @@ static void afiucv_hs_callback_txnotify(struct sk_buff *skb, struct sk_buff *list_skb; struct sk_buff *nskb; unsigned long flags; - struct hlist_node *node; read_lock_irqsave(&iucv_sk_list.lock, flags); - sk_for_each(sk, node, &iucv_sk_list.head) + sk_for_each(sk, &iucv_sk_list.head) if (sk == isk) { iucv = iucv_sk(sk); break; @@ -2299,14 +2293,13 @@ static int afiucv_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *event_dev = (struct net_device *)ptr; - struct hlist_node *node; struct sock *sk; struct iucv_sock *iucv; switch (event) { case NETDEV_REBOOT: case NETDEV_GOING_DOWN: - sk_for_each(sk, node, &iucv_sk_list.head) { + sk_for_each(sk, &iucv_sk_list.head) { iucv = iucv_sk(sk); if ((iucv->hs_dev == event_dev) && (sk->sk_state == IUCV_CONNECTED)) { diff --git a/net/key/af_key.c b/net/key/af_key.c index 7b3ba32ca678..ace8212022a9 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -225,7 +225,6 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation, { struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); struct sock *sk; - struct hlist_node *node; struct sk_buff *skb2 = NULL; int err = -ESRCH; @@ -236,7 +235,7 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation, return -ENOMEM; rcu_read_lock(); - sk_for_each_rcu(sk, node, &net_pfkey->table) { + sk_for_each_rcu(sk, &net_pfkey->table) { struct pfkey_sock *pfk = pfkey_sk(sk); int err2; diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index b6ba65fa3c50..a000dfd93117 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -221,10 +221,9 @@ static struct l2tp_session *l2tp_session_find_2(struct net *net, u32 session_id) struct hlist_head *session_list = l2tp_session_id_hash_2(pn, session_id); struct l2tp_session *session; - struct hlist_node *walk; rcu_read_lock_bh(); - hlist_for_each_entry_rcu(session, walk, session_list, global_hlist) { + hlist_for_each_entry_rcu(session, session_list, global_hlist) { if (session->session_id == session_id) { rcu_read_unlock_bh(); return session; @@ -253,7 +252,6 @@ struct l2tp_session *l2tp_session_find(struct net *net, struct l2tp_tunnel *tunn { struct hlist_head *session_list; struct l2tp_session *session; - struct hlist_node *walk; /* In L2TPv3, session_ids are unique over all tunnels and we * sometimes need to look them up before we know the @@ -264,7 +262,7 @@ struct l2tp_session *l2tp_session_find(struct net *net, struct l2tp_tunnel *tunn session_list = l2tp_session_id_hash(tunnel, session_id); read_lock_bh(&tunnel->hlist_lock); - hlist_for_each_entry(session, walk, session_list, hlist) { + hlist_for_each_entry(session, session_list, hlist) { if (session->session_id == session_id) { read_unlock_bh(&tunnel->hlist_lock); return session; @@ -279,13 +277,12 @@ EXPORT_SYMBOL_GPL(l2tp_session_find); struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth) { int hash; - struct hlist_node *walk; struct l2tp_session *session; int count = 0; read_lock_bh(&tunnel->hlist_lock); for (hash = 0; hash < L2TP_HASH_SIZE; hash++) { - hlist_for_each_entry(session, walk, &tunnel->session_hlist[hash], hlist) { + hlist_for_each_entry(session, &tunnel->session_hlist[hash], hlist) { if (++count > nth) { read_unlock_bh(&tunnel->hlist_lock); return session; @@ -306,12 +303,11 @@ struct l2tp_session *l2tp_session_find_by_ifname(struct net *net, char *ifname) { struct l2tp_net *pn = l2tp_pernet(net); int hash; - struct hlist_node *walk; struct l2tp_session *session; rcu_read_lock_bh(); for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++) { - hlist_for_each_entry_rcu(session, walk, &pn->l2tp_session_hlist[hash], global_hlist) { + hlist_for_each_entry_rcu(session, &pn->l2tp_session_hlist[hash], global_hlist) { if (!strcmp(session->ifname, ifname)) { rcu_read_unlock_bh(); return session; diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index f7ac8f42fee2..7f41b7051269 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -49,10 +49,9 @@ static inline struct l2tp_ip_sock *l2tp_ip_sk(const struct sock *sk) static struct sock *__l2tp_ip_bind_lookup(struct net *net, __be32 laddr, int dif, u32 tunnel_id) { - struct hlist_node *node; struct sock *sk; - sk_for_each_bound(sk, node, &l2tp_ip_bind_table) { + sk_for_each_bound(sk, &l2tp_ip_bind_table) { struct inet_sock *inet = inet_sk(sk); struct l2tp_ip_sock *l2tp = l2tp_ip_sk(sk); diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 8ee4a86ae996..41f2f8126ebc 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -60,10 +60,9 @@ static struct sock *__l2tp_ip6_bind_lookup(struct net *net, struct in6_addr *laddr, int dif, u32 tunnel_id) { - struct hlist_node *node; struct sock *sk; - sk_for_each_bound(sk, node, &l2tp_ip6_bind_table) { + sk_for_each_bound(sk, &l2tp_ip6_bind_table) { struct in6_addr *addr = inet6_rcv_saddr(sk); struct l2tp_ip6_sock *l2tp = l2tp_ip6_sk(sk); diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c index 7c5073badc73..78be45cda5c1 100644 --- a/net/llc/llc_sap.c +++ b/net/llc/llc_sap.c @@ -393,12 +393,11 @@ static void llc_sap_mcast(struct llc_sap *sap, { int i = 0, count = 256 / sizeof(struct sock *); struct sock *sk, *stack[count]; - struct hlist_node *node; struct llc_sock *llc; struct hlist_head *dev_hb = llc_sk_dev_hash(sap, skb->dev->ifindex); spin_lock_bh(&sap->sk_lock); - hlist_for_each_entry(llc, node, dev_hb, dev_hash_node) { + hlist_for_each_entry(llc, dev_hb, dev_hash_node) { sk = &llc->sk; diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 2bdd454e8bcf..632f2a71a6e1 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -647,8 +647,6 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, spin_lock_init(&local->ack_status_lock); idr_init(&local->ack_status_frames); - /* preallocate at least one entry */ - idr_pre_get(&local->ack_status_frames, GFP_KERNEL); sta_info_init(local); diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index aa749818860e..4ac7a7ab1be6 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -69,9 +69,9 @@ static inline struct mesh_table *resize_dereference_mpp_paths(void) * it's used twice. So it is illegal to do * for_each_mesh_entry(rcu_dereference(...), ...) */ -#define for_each_mesh_entry(tbl, p, node, i) \ +#define for_each_mesh_entry(tbl, node, i) \ for (i = 0; i <= tbl->hash_mask; i++) \ - hlist_for_each_entry_rcu(node, p, &tbl->hash_buckets[i], list) + hlist_for_each_entry_rcu(node, &tbl->hash_buckets[i], list) static struct mesh_table *mesh_table_alloc(int size_order) @@ -136,7 +136,7 @@ static void mesh_table_free(struct mesh_table *tbl, bool free_leafs) } if (free_leafs) { spin_lock_bh(&tbl->gates_lock); - hlist_for_each_entry_safe(gate, p, q, + hlist_for_each_entry_safe(gate, q, tbl->known_gates, list) { hlist_del(&gate->list); kfree(gate); @@ -329,12 +329,11 @@ static struct mesh_path *mpath_lookup(struct mesh_table *tbl, u8 *dst, struct ieee80211_sub_if_data *sdata) { struct mesh_path *mpath; - struct hlist_node *n; struct hlist_head *bucket; struct mpath_node *node; bucket = &tbl->hash_buckets[mesh_table_hash(dst, sdata, tbl)]; - hlist_for_each_entry_rcu(node, n, bucket, list) { + hlist_for_each_entry_rcu(node, bucket, list) { mpath = node->mpath; if (mpath->sdata == sdata && ether_addr_equal(dst, mpath->dst)) { @@ -382,11 +381,10 @@ struct mesh_path *mesh_path_lookup_by_idx(int idx, struct ieee80211_sub_if_data { struct mesh_table *tbl = rcu_dereference(mesh_paths); struct mpath_node *node; - struct hlist_node *p; int i; int j = 0; - for_each_mesh_entry(tbl, p, node, i) { + for_each_mesh_entry(tbl, node, i) { if (sdata && node->mpath->sdata != sdata) continue; if (j++ == idx) { @@ -410,13 +408,12 @@ int mesh_path_add_gate(struct mesh_path *mpath) { struct mesh_table *tbl; struct mpath_node *gate, *new_gate; - struct hlist_node *n; int err; rcu_read_lock(); tbl = rcu_dereference(mesh_paths); - hlist_for_each_entry_rcu(gate, n, tbl->known_gates, list) + hlist_for_each_entry_rcu(gate, tbl->known_gates, list) if (gate->mpath == mpath) { err = -EEXIST; goto err_rcu; @@ -456,9 +453,9 @@ err_rcu: static int mesh_gate_del(struct mesh_table *tbl, struct mesh_path *mpath) { struct mpath_node *gate; - struct hlist_node *p, *q; + struct hlist_node *q; - hlist_for_each_entry_safe(gate, p, q, tbl->known_gates, list) + hlist_for_each_entry_safe(gate, q, tbl->known_gates, list) if (gate->mpath == mpath) { spin_lock_bh(&tbl->gates_lock); hlist_del_rcu(&gate->list); @@ -501,7 +498,6 @@ int mesh_path_add(u8 *dst, struct ieee80211_sub_if_data *sdata) struct mesh_path *mpath, *new_mpath; struct mpath_node *node, *new_node; struct hlist_head *bucket; - struct hlist_node *n; int grow = 0; int err = 0; u32 hash_idx; @@ -547,7 +543,7 @@ int mesh_path_add(u8 *dst, struct ieee80211_sub_if_data *sdata) spin_lock(&tbl->hashwlock[hash_idx]); err = -EEXIST; - hlist_for_each_entry(node, n, bucket, list) { + hlist_for_each_entry(node, bucket, list) { mpath = node->mpath; if (mpath->sdata == sdata && ether_addr_equal(dst, mpath->dst)) @@ -636,7 +632,6 @@ int mpp_path_add(u8 *dst, u8 *mpp, struct ieee80211_sub_if_data *sdata) struct mesh_path *mpath, *new_mpath; struct mpath_node *node, *new_node; struct hlist_head *bucket; - struct hlist_node *n; int grow = 0; int err = 0; u32 hash_idx; @@ -676,7 +671,7 @@ int mpp_path_add(u8 *dst, u8 *mpp, struct ieee80211_sub_if_data *sdata) spin_lock(&tbl->hashwlock[hash_idx]); err = -EEXIST; - hlist_for_each_entry(node, n, bucket, list) { + hlist_for_each_entry(node, bucket, list) { mpath = node->mpath; if (mpath->sdata == sdata && ether_addr_equal(dst, mpath->dst)) @@ -721,14 +716,13 @@ void mesh_plink_broken(struct sta_info *sta) static const u8 bcast[ETH_ALEN] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}; struct mesh_path *mpath; struct mpath_node *node; - struct hlist_node *p; struct ieee80211_sub_if_data *sdata = sta->sdata; int i; __le16 reason = cpu_to_le16(WLAN_REASON_MESH_PATH_DEST_UNREACHABLE); rcu_read_lock(); tbl = rcu_dereference(mesh_paths); - for_each_mesh_entry(tbl, p, node, i) { + for_each_mesh_entry(tbl, node, i) { mpath = node->mpath; if (rcu_dereference(mpath->next_hop) == sta && mpath->flags & MESH_PATH_ACTIVE && @@ -787,13 +781,12 @@ void mesh_path_flush_by_nexthop(struct sta_info *sta) struct mesh_table *tbl; struct mesh_path *mpath; struct mpath_node *node; - struct hlist_node *p; int i; rcu_read_lock(); read_lock_bh(&pathtbl_resize_lock); tbl = resize_dereference_mesh_paths(); - for_each_mesh_entry(tbl, p, node, i) { + for_each_mesh_entry(tbl, node, i) { mpath = node->mpath; if (rcu_dereference(mpath->next_hop) == sta) { spin_lock(&tbl->hashwlock[i]); @@ -810,11 +803,10 @@ static void table_flush_by_iface(struct mesh_table *tbl, { struct mesh_path *mpath; struct mpath_node *node; - struct hlist_node *p; int i; WARN_ON(!rcu_read_lock_held()); - for_each_mesh_entry(tbl, p, node, i) { + for_each_mesh_entry(tbl, node, i) { mpath = node->mpath; if (mpath->sdata != sdata) continue; @@ -860,7 +852,6 @@ int mesh_path_del(u8 *addr, struct ieee80211_sub_if_data *sdata) struct mesh_path *mpath; struct mpath_node *node; struct hlist_head *bucket; - struct hlist_node *n; int hash_idx; int err = 0; @@ -870,7 +861,7 @@ int mesh_path_del(u8 *addr, struct ieee80211_sub_if_data *sdata) bucket = &tbl->hash_buckets[hash_idx]; spin_lock(&tbl->hashwlock[hash_idx]); - hlist_for_each_entry(node, n, bucket, list) { + hlist_for_each_entry(node, bucket, list) { mpath = node->mpath; if (mpath->sdata == sdata && ether_addr_equal(addr, mpath->dst)) { @@ -915,7 +906,6 @@ void mesh_path_tx_pending(struct mesh_path *mpath) int mesh_path_send_to_gates(struct mesh_path *mpath) { struct ieee80211_sub_if_data *sdata = mpath->sdata; - struct hlist_node *n; struct mesh_table *tbl; struct mesh_path *from_mpath = mpath; struct mpath_node *gate = NULL; @@ -930,7 +920,7 @@ int mesh_path_send_to_gates(struct mesh_path *mpath) if (!known_gates) return -EHOSTUNREACH; - hlist_for_each_entry_rcu(gate, n, known_gates, list) { + hlist_for_each_entry_rcu(gate, known_gates, list) { if (gate->mpath->sdata != sdata) continue; @@ -946,7 +936,7 @@ int mesh_path_send_to_gates(struct mesh_path *mpath) } } - hlist_for_each_entry_rcu(gate, n, known_gates, list) + hlist_for_each_entry_rcu(gate, known_gates, list) if (gate->mpath->sdata == sdata) { mpath_dbg(sdata, "Sending to %pM\n", gate->mpath->dst); mesh_path_tx_pending(gate->mpath); @@ -1091,12 +1081,11 @@ void mesh_path_expire(struct ieee80211_sub_if_data *sdata) struct mesh_table *tbl; struct mesh_path *mpath; struct mpath_node *node; - struct hlist_node *p; int i; rcu_read_lock(); tbl = rcu_dereference(mesh_paths); - for_each_mesh_entry(tbl, p, node, i) { + for_each_mesh_entry(tbl, node, i) { if (node->mpath->sdata != sdata) continue; mpath = node->mpath; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index a2cb6a302cc7..5a62468e634d 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1999,24 +1999,14 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, skb = skb_clone(skb, GFP_ATOMIC); if (skb) { unsigned long flags; - int id, r; + int id; spin_lock_irqsave(&local->ack_status_lock, flags); - r = idr_get_new_above(&local->ack_status_frames, - orig_skb, 1, &id); - if (r == -EAGAIN) { - idr_pre_get(&local->ack_status_frames, - GFP_ATOMIC); - r = idr_get_new_above(&local->ack_status_frames, - orig_skb, 1, &id); - } - if (WARN_ON(!id) || id > 0xffff) { - idr_remove(&local->ack_status_frames, id); - r = -ERANGE; - } + id = idr_alloc(&local->ack_status_frames, orig_skb, + 1, 0x10000, GFP_ATOMIC); spin_unlock_irqrestore(&local->ack_status_lock, flags); - if (!r) { + if (id >= 0) { info_id = id; info_flags |= IEEE80211_TX_CTL_REQ_TX_STATUS; } else if (skb_shared(skb)) { diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 68e368a4beed..b1d164eeb8e8 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -259,13 +259,12 @@ __ip_vs_conn_in_get(const struct ip_vs_conn_param *p) { unsigned int hash; struct ip_vs_conn *cp; - struct hlist_node *n; hash = ip_vs_conn_hashkey_param(p, false); ct_read_lock(hash); - hlist_for_each_entry(cp, n, &ip_vs_conn_tab[hash], c_list) { + hlist_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { if (cp->af == p->af && p->cport == cp->cport && p->vport == cp->vport && ip_vs_addr_equal(p->af, p->caddr, &cp->caddr) && @@ -344,13 +343,12 @@ struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p) { unsigned int hash; struct ip_vs_conn *cp; - struct hlist_node *n; hash = ip_vs_conn_hashkey_param(p, false); ct_read_lock(hash); - hlist_for_each_entry(cp, n, &ip_vs_conn_tab[hash], c_list) { + hlist_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { if (!ip_vs_conn_net_eq(cp, p->net)) continue; if (p->pe_data && p->pe->ct_match) { @@ -394,7 +392,6 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p) { unsigned int hash; struct ip_vs_conn *cp, *ret=NULL; - struct hlist_node *n; /* * Check for "full" addressed entries @@ -403,7 +400,7 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p) ct_read_lock(hash); - hlist_for_each_entry(cp, n, &ip_vs_conn_tab[hash], c_list) { + hlist_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { if (cp->af == p->af && p->vport == cp->cport && p->cport == cp->dport && ip_vs_addr_equal(p->af, p->vaddr, &cp->caddr) && @@ -953,11 +950,10 @@ static void *ip_vs_conn_array(struct seq_file *seq, loff_t pos) int idx; struct ip_vs_conn *cp; struct ip_vs_iter_state *iter = seq->private; - struct hlist_node *n; for (idx = 0; idx < ip_vs_conn_tab_size; idx++) { ct_read_lock_bh(idx); - hlist_for_each_entry(cp, n, &ip_vs_conn_tab[idx], c_list) { + hlist_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) { if (pos-- == 0) { iter->l = &ip_vs_conn_tab[idx]; return cp; @@ -981,7 +977,6 @@ static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ip_vs_conn *cp = v; struct ip_vs_iter_state *iter = seq->private; - struct hlist_node *e; struct hlist_head *l = iter->l; int idx; @@ -990,15 +985,15 @@ static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos) return ip_vs_conn_array(seq, 0); /* more on same hash chain? */ - if ((e = cp->c_list.next)) - return hlist_entry(e, struct ip_vs_conn, c_list); + if (cp->c_list.next) + return hlist_entry(cp->c_list.next, struct ip_vs_conn, c_list); idx = l - ip_vs_conn_tab; ct_read_unlock_bh(idx); while (++idx < ip_vs_conn_tab_size) { ct_read_lock_bh(idx); - hlist_for_each_entry(cp, e, &ip_vs_conn_tab[idx], c_list) { + hlist_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) { iter->l = &ip_vs_conn_tab[idx]; return cp; } @@ -1200,14 +1195,13 @@ void ip_vs_random_dropentry(struct net *net) */ for (idx = 0; idx < (ip_vs_conn_tab_size>>5); idx++) { unsigned int hash = net_random() & ip_vs_conn_tab_mask; - struct hlist_node *n; /* * Lock is actually needed in this loop. */ ct_write_lock_bh(hash); - hlist_for_each_entry(cp, n, &ip_vs_conn_tab[hash], c_list) { + hlist_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { if (cp->flags & IP_VS_CONN_F_TEMPLATE) /* connection template */ continue; @@ -1255,14 +1249,12 @@ static void ip_vs_conn_flush(struct net *net) flush_again: for (idx = 0; idx < ip_vs_conn_tab_size; idx++) { - struct hlist_node *n; - /* * Lock is actually needed in this loop. */ ct_write_lock_bh(idx); - hlist_for_each_entry(cp, n, &ip_vs_conn_tab[idx], c_list) { + hlist_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) { if (!ip_vs_conn_net_eq(cp, net)) continue; IP_VS_DBG(4, "del connection\n"); diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index bdd341899ed3..3e3bf8933a17 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -90,14 +90,13 @@ __nf_ct_expect_find(struct net *net, u16 zone, const struct nf_conntrack_tuple *tuple) { struct nf_conntrack_expect *i; - struct hlist_node *n; unsigned int h; if (!net->ct.expect_count) return NULL; h = nf_ct_expect_dst_hash(tuple); - hlist_for_each_entry_rcu(i, n, &net->ct.expect_hash[h], hnode) { + hlist_for_each_entry_rcu(i, &net->ct.expect_hash[h], hnode) { if (nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask) && nf_ct_zone(i->master) == zone) return i; @@ -130,14 +129,13 @@ nf_ct_find_expectation(struct net *net, u16 zone, const struct nf_conntrack_tuple *tuple) { struct nf_conntrack_expect *i, *exp = NULL; - struct hlist_node *n; unsigned int h; if (!net->ct.expect_count) return NULL; h = nf_ct_expect_dst_hash(tuple); - hlist_for_each_entry(i, n, &net->ct.expect_hash[h], hnode) { + hlist_for_each_entry(i, &net->ct.expect_hash[h], hnode) { if (!(i->flags & NF_CT_EXPECT_INACTIVE) && nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask) && nf_ct_zone(i->master) == zone) { @@ -172,13 +170,13 @@ void nf_ct_remove_expectations(struct nf_conn *ct) { struct nf_conn_help *help = nfct_help(ct); struct nf_conntrack_expect *exp; - struct hlist_node *n, *next; + struct hlist_node *next; /* Optimization: most connection never expect any others. */ if (!help) return; - hlist_for_each_entry_safe(exp, n, next, &help->expectations, lnode) { + hlist_for_each_entry_safe(exp, next, &help->expectations, lnode) { if (del_timer(&exp->timeout)) { nf_ct_unlink_expect(exp); nf_ct_expect_put(exp); @@ -348,9 +346,8 @@ static void evict_oldest_expect(struct nf_conn *master, { struct nf_conn_help *master_help = nfct_help(master); struct nf_conntrack_expect *exp, *last = NULL; - struct hlist_node *n; - hlist_for_each_entry(exp, n, &master_help->expectations, lnode) { + hlist_for_each_entry(exp, &master_help->expectations, lnode) { if (exp->class == new->class) last = exp; } @@ -369,7 +366,7 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect) struct nf_conn_help *master_help = nfct_help(master); struct nf_conntrack_helper *helper; struct net *net = nf_ct_exp_net(expect); - struct hlist_node *n, *next; + struct hlist_node *next; unsigned int h; int ret = 1; @@ -378,7 +375,7 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect) goto out; } h = nf_ct_expect_dst_hash(&expect->tuple); - hlist_for_each_entry_safe(i, n, next, &net->ct.expect_hash[h], hnode) { + hlist_for_each_entry_safe(i, next, &net->ct.expect_hash[h], hnode) { if (expect_matches(i, expect)) { if (del_timer(&i->timeout)) { nf_ct_unlink_expect(i); diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 2f380f73c4c0..c0619f2b2d65 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -115,14 +115,13 @@ __nf_ct_helper_find(const struct nf_conntrack_tuple *tuple) { struct nf_conntrack_helper *helper; struct nf_conntrack_tuple_mask mask = { .src.u.all = htons(0xFFFF) }; - struct hlist_node *n; unsigned int h; if (!nf_ct_helper_count) return NULL; h = helper_hash(tuple); - hlist_for_each_entry_rcu(helper, n, &nf_ct_helper_hash[h], hnode) { + hlist_for_each_entry_rcu(helper, &nf_ct_helper_hash[h], hnode) { if (nf_ct_tuple_src_mask_cmp(tuple, &helper->tuple, &mask)) return helper; } @@ -133,11 +132,10 @@ struct nf_conntrack_helper * __nf_conntrack_helper_find(const char *name, u16 l3num, u8 protonum) { struct nf_conntrack_helper *h; - struct hlist_node *n; unsigned int i; for (i = 0; i < nf_ct_helper_hsize; i++) { - hlist_for_each_entry_rcu(h, n, &nf_ct_helper_hash[i], hnode) { + hlist_for_each_entry_rcu(h, &nf_ct_helper_hash[i], hnode) { if (!strcmp(h->name, name) && h->tuple.src.l3num == l3num && h->tuple.dst.protonum == protonum) @@ -336,7 +334,6 @@ int nf_conntrack_helper_register(struct nf_conntrack_helper *me) { int ret = 0; struct nf_conntrack_helper *cur; - struct hlist_node *n; unsigned int h = helper_hash(&me->tuple); BUG_ON(me->expect_policy == NULL); @@ -344,7 +341,7 @@ int nf_conntrack_helper_register(struct nf_conntrack_helper *me) BUG_ON(strlen(me->name) > NF_CT_HELPER_NAME_LEN - 1); mutex_lock(&nf_ct_helper_mutex); - hlist_for_each_entry(cur, n, &nf_ct_helper_hash[h], hnode) { + hlist_for_each_entry(cur, &nf_ct_helper_hash[h], hnode) { if (strncmp(cur->name, me->name, NF_CT_HELPER_NAME_LEN) == 0 && cur->tuple.src.l3num == me->tuple.src.l3num && cur->tuple.dst.protonum == me->tuple.dst.protonum) { @@ -365,13 +362,13 @@ static void __nf_conntrack_helper_unregister(struct nf_conntrack_helper *me, { struct nf_conntrack_tuple_hash *h; struct nf_conntrack_expect *exp; - const struct hlist_node *n, *next; + const struct hlist_node *next; const struct hlist_nulls_node *nn; unsigned int i; /* Get rid of expectations */ for (i = 0; i < nf_ct_expect_hsize; i++) { - hlist_for_each_entry_safe(exp, n, next, + hlist_for_each_entry_safe(exp, next, &net->ct.expect_hash[i], hnode) { struct nf_conn_help *help = nfct_help(exp->master); if ((rcu_dereference_protected( diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 2334cc5d2b16..4790d0b54efd 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2367,14 +2367,13 @@ ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb) struct net *net = sock_net(skb->sk); struct nf_conntrack_expect *exp, *last; struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); - struct hlist_node *n; u_int8_t l3proto = nfmsg->nfgen_family; rcu_read_lock(); last = (struct nf_conntrack_expect *)cb->args[1]; for (; cb->args[0] < nf_ct_expect_hsize; cb->args[0]++) { restart: - hlist_for_each_entry(exp, n, &net->ct.expect_hash[cb->args[0]], + hlist_for_each_entry(exp, &net->ct.expect_hash[cb->args[0]], hnode) { if (l3proto && exp->tuple.src.l3num != l3proto) continue; @@ -2507,7 +2506,7 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, struct nf_conntrack_expect *exp; struct nf_conntrack_tuple tuple; struct nfgenmsg *nfmsg = nlmsg_data(nlh); - struct hlist_node *n, *next; + struct hlist_node *next; u_int8_t u3 = nfmsg->nfgen_family; unsigned int i; u16 zone; @@ -2554,7 +2553,7 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, /* delete all expectations for this helper */ spin_lock_bh(&nf_conntrack_lock); for (i = 0; i < nf_ct_expect_hsize; i++) { - hlist_for_each_entry_safe(exp, n, next, + hlist_for_each_entry_safe(exp, next, &net->ct.expect_hash[i], hnode) { m_help = nfct_help(exp->master); @@ -2572,7 +2571,7 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, /* This basically means we have to flush everything*/ spin_lock_bh(&nf_conntrack_lock); for (i = 0; i < nf_ct_expect_hsize; i++) { - hlist_for_each_entry_safe(exp, n, next, + hlist_for_each_entry_safe(exp, next, &net->ct.expect_hash[i], hnode) { if (del_timer(&exp->timeout)) { diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 72a67bbe3518..603154ff3ef9 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -855,11 +855,11 @@ static int refresh_signalling_expectation(struct nf_conn *ct, { struct nf_conn_help *help = nfct_help(ct); struct nf_conntrack_expect *exp; - struct hlist_node *n, *next; + struct hlist_node *next; int found = 0; spin_lock_bh(&nf_conntrack_lock); - hlist_for_each_entry_safe(exp, n, next, &help->expectations, lnode) { + hlist_for_each_entry_safe(exp, next, &help->expectations, lnode) { if (exp->class != SIP_EXPECT_SIGNALLING || !nf_inet_addr_cmp(&exp->tuple.dst.u3, addr) || exp->tuple.dst.protonum != proto || @@ -881,10 +881,10 @@ static void flush_expectations(struct nf_conn *ct, bool media) { struct nf_conn_help *help = nfct_help(ct); struct nf_conntrack_expect *exp; - struct hlist_node *n, *next; + struct hlist_node *next; spin_lock_bh(&nf_conntrack_lock); - hlist_for_each_entry_safe(exp, n, next, &help->expectations, lnode) { + hlist_for_each_entry_safe(exp, next, &help->expectations, lnode) { if ((exp->class != SIP_EXPECT_SIGNALLING) ^ media) continue; if (!del_timer(&exp->timeout)) diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 5f2f9109f461..8d5769c6d16e 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -191,9 +191,8 @@ find_appropriate_src(struct net *net, u16 zone, unsigned int h = hash_by_src(net, zone, tuple); const struct nf_conn_nat *nat; const struct nf_conn *ct; - const struct hlist_node *n; - hlist_for_each_entry_rcu(nat, n, &net->ct.nat_bysource[h], bysource) { + hlist_for_each_entry_rcu(nat, &net->ct.nat_bysource[h], bysource) { ct = nat->ct; if (same_src(ct, tuple) && nf_ct_zone(ct) == zone) { /* Copy source part from reply tuple. */ diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index 945950a8b1f1..a191b6db657e 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -282,7 +282,6 @@ nfnl_cthelper_new(struct sock *nfnl, struct sk_buff *skb, const char *helper_name; struct nf_conntrack_helper *cur, *helper = NULL; struct nf_conntrack_tuple tuple; - struct hlist_node *n; int ret = 0, i; if (!tb[NFCTH_NAME] || !tb[NFCTH_TUPLE]) @@ -296,7 +295,7 @@ nfnl_cthelper_new(struct sock *nfnl, struct sk_buff *skb, rcu_read_lock(); for (i = 0; i < nf_ct_helper_hsize && !helper; i++) { - hlist_for_each_entry_rcu(cur, n, &nf_ct_helper_hash[i], hnode) { + hlist_for_each_entry_rcu(cur, &nf_ct_helper_hash[i], hnode) { /* skip non-userspace conntrack helpers. */ if (!(cur->flags & NF_CT_HELPER_F_USERSPACE)) @@ -452,13 +451,12 @@ static int nfnl_cthelper_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { struct nf_conntrack_helper *cur, *last; - struct hlist_node *n; rcu_read_lock(); last = (struct nf_conntrack_helper *)cb->args[1]; for (; cb->args[0] < nf_ct_helper_hsize; cb->args[0]++) { restart: - hlist_for_each_entry_rcu(cur, n, + hlist_for_each_entry_rcu(cur, &nf_ct_helper_hash[cb->args[0]], hnode) { /* skip non-userspace conntrack helpers. */ @@ -495,7 +493,6 @@ nfnl_cthelper_get(struct sock *nfnl, struct sk_buff *skb, { int ret = -ENOENT, i; struct nf_conntrack_helper *cur; - struct hlist_node *n; struct sk_buff *skb2; char *helper_name = NULL; struct nf_conntrack_tuple tuple; @@ -520,7 +517,7 @@ nfnl_cthelper_get(struct sock *nfnl, struct sk_buff *skb, } for (i = 0; i < nf_ct_helper_hsize; i++) { - hlist_for_each_entry_rcu(cur, n, &nf_ct_helper_hash[i], hnode) { + hlist_for_each_entry_rcu(cur, &nf_ct_helper_hash[i], hnode) { /* skip non-userspace conntrack helpers. */ if (!(cur->flags & NF_CT_HELPER_F_USERSPACE)) @@ -568,7 +565,7 @@ nfnl_cthelper_del(struct sock *nfnl, struct sk_buff *skb, { char *helper_name = NULL; struct nf_conntrack_helper *cur; - struct hlist_node *n, *tmp; + struct hlist_node *tmp; struct nf_conntrack_tuple tuple; bool tuple_set = false, found = false; int i, j = 0, ret; @@ -585,7 +582,7 @@ nfnl_cthelper_del(struct sock *nfnl, struct sk_buff *skb, } for (i = 0; i < nf_ct_helper_hsize; i++) { - hlist_for_each_entry_safe(cur, n, tmp, &nf_ct_helper_hash[i], + hlist_for_each_entry_safe(cur, tmp, &nf_ct_helper_hash[i], hnode) { /* skip non-userspace conntrack helpers. */ if (!(cur->flags & NF_CT_HELPER_F_USERSPACE)) @@ -654,13 +651,13 @@ err_out: static void __exit nfnl_cthelper_exit(void) { struct nf_conntrack_helper *cur; - struct hlist_node *n, *tmp; + struct hlist_node *tmp; int i; nfnetlink_subsys_unregister(&nfnl_cthelper_subsys); for (i=0; i<nf_ct_helper_hsize; i++) { - hlist_for_each_entry_safe(cur, n, tmp, &nf_ct_helper_hash[i], + hlist_for_each_entry_safe(cur, tmp, &nf_ct_helper_hash[i], hnode) { /* skip non-userspace conntrack helpers. */ if (!(cur->flags & NF_CT_HELPER_F_USERSPACE)) diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 92fd8eca0d31..f248db572972 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -87,11 +87,10 @@ static struct nfulnl_instance * __instance_lookup(u_int16_t group_num) { struct hlist_head *head; - struct hlist_node *pos; struct nfulnl_instance *inst; head = &instance_table[instance_hashfn(group_num)]; - hlist_for_each_entry_rcu(inst, pos, head, hlist) { + hlist_for_each_entry_rcu(inst, head, hlist) { if (inst->group_num == group_num) return inst; } @@ -717,11 +716,11 @@ nfulnl_rcv_nl_event(struct notifier_block *this, /* destroy all instances for this portid */ spin_lock_bh(&instances_lock); for (i = 0; i < INSTANCE_BUCKETS; i++) { - struct hlist_node *tmp, *t2; + struct hlist_node *t2; struct nfulnl_instance *inst; struct hlist_head *head = &instance_table[i]; - hlist_for_each_entry_safe(inst, tmp, t2, head, hlist) { + hlist_for_each_entry_safe(inst, t2, head, hlist) { if ((net_eq(n->net, &init_net)) && (n->portid == inst->peer_portid)) __instance_destroy(inst); diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index 3158d87b56a8..858fd52c1040 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -80,11 +80,10 @@ static struct nfqnl_instance * instance_lookup(u_int16_t queue_num) { struct hlist_head *head; - struct hlist_node *pos; struct nfqnl_instance *inst; head = &instance_table[instance_hashfn(queue_num)]; - hlist_for_each_entry_rcu(inst, pos, head, hlist) { + hlist_for_each_entry_rcu(inst, head, hlist) { if (inst->queue_num == queue_num) return inst; } @@ -583,11 +582,10 @@ nfqnl_dev_drop(int ifindex) rcu_read_lock(); for (i = 0; i < INSTANCE_BUCKETS; i++) { - struct hlist_node *tmp; struct nfqnl_instance *inst; struct hlist_head *head = &instance_table[i]; - hlist_for_each_entry_rcu(inst, tmp, head, hlist) + hlist_for_each_entry_rcu(inst, head, hlist) nfqnl_flush(inst, dev_cmp, ifindex); } @@ -627,11 +625,11 @@ nfqnl_rcv_nl_event(struct notifier_block *this, /* destroy all instances for this portid */ spin_lock(&instances_lock); for (i = 0; i < INSTANCE_BUCKETS; i++) { - struct hlist_node *tmp, *t2; + struct hlist_node *t2; struct nfqnl_instance *inst; struct hlist_head *head = &instance_table[i]; - hlist_for_each_entry_safe(inst, tmp, t2, head, hlist) { + hlist_for_each_entry_safe(inst, t2, head, hlist) { if ((n->net == &init_net) && (n->portid == inst->peer_portid)) __instance_destroy(inst); diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c index f264032b8c56..370adf622cef 100644 --- a/net/netfilter/xt_RATEEST.c +++ b/net/netfilter/xt_RATEEST.c @@ -43,12 +43,11 @@ static void xt_rateest_hash_insert(struct xt_rateest *est) struct xt_rateest *xt_rateest_lookup(const char *name) { struct xt_rateest *est; - struct hlist_node *n; unsigned int h; h = xt_rateest_hash(name); mutex_lock(&xt_rateest_mutex); - hlist_for_each_entry(est, n, &rateest_hash[h], list) { + hlist_for_each_entry(est, &rateest_hash[h], list) { if (strcmp(est->name, name) == 0) { est->refcnt++; mutex_unlock(&xt_rateest_mutex); diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c index 70b5591a2586..c40b2695633b 100644 --- a/net/netfilter/xt_connlimit.c +++ b/net/netfilter/xt_connlimit.c @@ -101,7 +101,7 @@ static int count_them(struct net *net, { const struct nf_conntrack_tuple_hash *found; struct xt_connlimit_conn *conn; - struct hlist_node *pos, *n; + struct hlist_node *n; struct nf_conn *found_ct; struct hlist_head *hash; bool addit = true; @@ -115,7 +115,7 @@ static int count_them(struct net *net, rcu_read_lock(); /* check the saved connections */ - hlist_for_each_entry_safe(conn, pos, n, hash, node) { + hlist_for_each_entry_safe(conn, n, hash, node) { found = nf_conntrack_find_get(net, NF_CT_DEFAULT_ZONE, &conn->tuple); found_ct = NULL; @@ -258,14 +258,14 @@ static void connlimit_mt_destroy(const struct xt_mtdtor_param *par) { const struct xt_connlimit_info *info = par->matchinfo; struct xt_connlimit_conn *conn; - struct hlist_node *pos, *n; + struct hlist_node *n; struct hlist_head *hash = info->data->iphash; unsigned int i; nf_ct_l3proto_module_put(par->family); for (i = 0; i < ARRAY_SIZE(info->data->iphash); ++i) { - hlist_for_each_entry_safe(conn, pos, n, &hash[i], node) { + hlist_for_each_entry_safe(conn, n, &hash[i], node) { hlist_del(&conn->node); kfree(conn); } diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index a9d7af953ceb..78e4a45cbf29 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -141,11 +141,10 @@ dsthash_find(const struct xt_hashlimit_htable *ht, const struct dsthash_dst *dst) { struct dsthash_ent *ent; - struct hlist_node *pos; u_int32_t hash = hash_dst(ht, dst); if (!hlist_empty(&ht->hash[hash])) { - hlist_for_each_entry_rcu(ent, pos, &ht->hash[hash], node) + hlist_for_each_entry_rcu(ent, &ht->hash[hash], node) if (dst_cmp(ent, dst)) { spin_lock(&ent->lock); return ent; @@ -297,8 +296,8 @@ static void htable_selective_cleanup(struct xt_hashlimit_htable *ht, spin_lock_bh(&ht->lock); for (i = 0; i < ht->cfg.size; i++) { struct dsthash_ent *dh; - struct hlist_node *pos, *n; - hlist_for_each_entry_safe(dh, pos, n, &ht->hash[i], node) { + struct hlist_node *n; + hlist_for_each_entry_safe(dh, n, &ht->hash[i], node) { if ((*select)(ht, dh)) dsthash_free(ht, dh); } @@ -343,9 +342,8 @@ static struct xt_hashlimit_htable *htable_find_get(struct net *net, { struct hashlimit_net *hashlimit_net = hashlimit_pernet(net); struct xt_hashlimit_htable *hinfo; - struct hlist_node *pos; - hlist_for_each_entry(hinfo, pos, &hashlimit_net->htables, node) { + hlist_for_each_entry(hinfo, &hashlimit_net->htables, node) { if (!strcmp(name, hinfo->pde->name) && hinfo->family == family) { hinfo->use++; @@ -821,10 +819,9 @@ static int dl_seq_show(struct seq_file *s, void *v) struct xt_hashlimit_htable *htable = s->private; unsigned int *bucket = (unsigned int *)v; struct dsthash_ent *ent; - struct hlist_node *pos; if (!hlist_empty(&htable->hash[*bucket])) { - hlist_for_each_entry(ent, pos, &htable->hash[*bucket], node) + hlist_for_each_entry(ent, &htable->hash[*bucket], node) if (dl_seq_real_show(ent, htable->family, s)) return -1; } @@ -877,7 +874,6 @@ static int __net_init hashlimit_proc_net_init(struct net *net) static void __net_exit hashlimit_proc_net_exit(struct net *net) { struct xt_hashlimit_htable *hinfo; - struct hlist_node *pos; struct proc_dir_entry *pde; struct hashlimit_net *hashlimit_net = hashlimit_pernet(net); @@ -890,7 +886,7 @@ static void __net_exit hashlimit_proc_net_exit(struct net *net) if (pde == NULL) pde = hashlimit_net->ip6t_hashlimit; - hlist_for_each_entry(hinfo, pos, &hashlimit_net->htables, node) + hlist_for_each_entry(hinfo, &hashlimit_net->htables, node) remove_proc_entry(hinfo->pde->name, pde); hashlimit_net->ipt_hashlimit = NULL; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 74827e3b26a1..3b479680e1cf 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -248,11 +248,10 @@ static struct sock *netlink_lookup(struct net *net, int protocol, u32 portid) struct nl_portid_hash *hash = &nl_table[protocol].hash; struct hlist_head *head; struct sock *sk; - struct hlist_node *node; read_lock(&nl_table_lock); head = nl_portid_hashfn(hash, portid); - sk_for_each(sk, node, head) { + sk_for_each(sk, head) { if (net_eq(sock_net(sk), net) && (nlk_sk(sk)->portid == portid)) { sock_hold(sk); goto found; @@ -312,9 +311,9 @@ static int nl_portid_hash_rehash(struct nl_portid_hash *hash, int grow) for (i = 0; i <= omask; i++) { struct sock *sk; - struct hlist_node *node, *tmp; + struct hlist_node *tmp; - sk_for_each_safe(sk, node, tmp, &otable[i]) + sk_for_each_safe(sk, tmp, &otable[i]) __sk_add_node(sk, nl_portid_hashfn(hash, nlk_sk(sk)->portid)); } @@ -344,7 +343,6 @@ static void netlink_update_listeners(struct sock *sk) { struct netlink_table *tbl = &nl_table[sk->sk_protocol]; - struct hlist_node *node; unsigned long mask; unsigned int i; struct listeners *listeners; @@ -355,7 +353,7 @@ netlink_update_listeners(struct sock *sk) for (i = 0; i < NLGRPLONGS(tbl->groups); i++) { mask = 0; - sk_for_each_bound(sk, node, &tbl->mc_list) { + sk_for_each_bound(sk, &tbl->mc_list) { if (i < NLGRPLONGS(nlk_sk(sk)->ngroups)) mask |= nlk_sk(sk)->groups[i]; } @@ -371,18 +369,17 @@ static int netlink_insert(struct sock *sk, struct net *net, u32 portid) struct hlist_head *head; int err = -EADDRINUSE; struct sock *osk; - struct hlist_node *node; int len; netlink_table_grab(); head = nl_portid_hashfn(hash, portid); len = 0; - sk_for_each(osk, node, head) { + sk_for_each(osk, head) { if (net_eq(sock_net(osk), net) && (nlk_sk(osk)->portid == portid)) break; len++; } - if (node) + if (osk) goto err; err = -EBUSY; @@ -575,7 +572,6 @@ static int netlink_autobind(struct socket *sock) struct nl_portid_hash *hash = &nl_table[sk->sk_protocol].hash; struct hlist_head *head; struct sock *osk; - struct hlist_node *node; s32 portid = task_tgid_vnr(current); int err; static s32 rover = -4097; @@ -584,7 +580,7 @@ retry: cond_resched(); netlink_table_grab(); head = nl_portid_hashfn(hash, portid); - sk_for_each(osk, node, head) { + sk_for_each(osk, head) { if (!net_eq(sock_net(osk), net)) continue; if (nlk_sk(osk)->portid == portid) { @@ -1101,7 +1097,6 @@ int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, u32 portid { struct net *net = sock_net(ssk); struct netlink_broadcast_data info; - struct hlist_node *node; struct sock *sk; skb = netlink_trim(skb, allocation); @@ -1124,7 +1119,7 @@ int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, u32 portid netlink_lock_table(); - sk_for_each_bound(sk, node, &nl_table[ssk->sk_protocol].mc_list) + sk_for_each_bound(sk, &nl_table[ssk->sk_protocol].mc_list) do_one_broadcast(sk, &info); consume_skb(skb); @@ -1200,7 +1195,6 @@ out: int netlink_set_err(struct sock *ssk, u32 portid, u32 group, int code) { struct netlink_set_err_data info; - struct hlist_node *node; struct sock *sk; int ret = 0; @@ -1212,7 +1206,7 @@ int netlink_set_err(struct sock *ssk, u32 portid, u32 group, int code) read_lock(&nl_table_lock); - sk_for_each_bound(sk, node, &nl_table[ssk->sk_protocol].mc_list) + sk_for_each_bound(sk, &nl_table[ssk->sk_protocol].mc_list) ret += do_one_set_err(sk, &info); read_unlock(&nl_table_lock); @@ -1676,10 +1670,9 @@ int netlink_change_ngroups(struct sock *sk, unsigned int groups) void __netlink_clear_multicast_users(struct sock *ksk, unsigned int group) { struct sock *sk; - struct hlist_node *node; struct netlink_table *tbl = &nl_table[ksk->sk_protocol]; - sk_for_each_bound(sk, node, &tbl->mc_list) + sk_for_each_bound(sk, &tbl->mc_list) netlink_update_socket_mc(nlk_sk(sk), group, 0); } @@ -1974,14 +1967,13 @@ static struct sock *netlink_seq_socket_idx(struct seq_file *seq, loff_t pos) struct nl_seq_iter *iter = seq->private; int i, j; struct sock *s; - struct hlist_node *node; loff_t off = 0; for (i = 0; i < MAX_LINKS; i++) { struct nl_portid_hash *hash = &nl_table[i].hash; for (j = 0; j <= hash->mask; j++) { - sk_for_each(s, node, &hash->table[j]) { + sk_for_each(s, &hash->table[j]) { if (sock_net(s) != seq_file_net(seq)) continue; if (off == pos) { diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 7261eb81974f..92c43aacd91e 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -104,10 +104,9 @@ static void nr_remove_socket(struct sock *sk) static void nr_kill_by_device(struct net_device *dev) { struct sock *s; - struct hlist_node *node; spin_lock_bh(&nr_list_lock); - sk_for_each(s, node, &nr_list) + sk_for_each(s, &nr_list) if (nr_sk(s)->device == dev) nr_disconnect(s, ENETUNREACH); spin_unlock_bh(&nr_list_lock); @@ -149,10 +148,9 @@ static void nr_insert_socket(struct sock *sk) static struct sock *nr_find_listener(ax25_address *addr) { struct sock *s; - struct hlist_node *node; spin_lock_bh(&nr_list_lock); - sk_for_each(s, node, &nr_list) + sk_for_each(s, &nr_list) if (!ax25cmp(&nr_sk(s)->source_addr, addr) && s->sk_state == TCP_LISTEN) { bh_lock_sock(s); @@ -170,10 +168,9 @@ found: static struct sock *nr_find_socket(unsigned char index, unsigned char id) { struct sock *s; - struct hlist_node *node; spin_lock_bh(&nr_list_lock); - sk_for_each(s, node, &nr_list) { + sk_for_each(s, &nr_list) { struct nr_sock *nr = nr_sk(s); if (nr->my_index == index && nr->my_id == id) { @@ -194,10 +191,9 @@ static struct sock *nr_find_peer(unsigned char index, unsigned char id, ax25_address *dest) { struct sock *s; - struct hlist_node *node; spin_lock_bh(&nr_list_lock); - sk_for_each(s, node, &nr_list) { + sk_for_each(s, &nr_list) { struct nr_sock *nr = nr_sk(s); if (nr->your_index == index && nr->your_id == id && diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index 70ffff76a967..b976d5eff2de 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -49,10 +49,9 @@ static struct nr_node *nr_node_get(ax25_address *callsign) { struct nr_node *found = NULL; struct nr_node *nr_node; - struct hlist_node *node; spin_lock_bh(&nr_node_list_lock); - nr_node_for_each(nr_node, node, &nr_node_list) + nr_node_for_each(nr_node, &nr_node_list) if (ax25cmp(callsign, &nr_node->callsign) == 0) { nr_node_hold(nr_node); found = nr_node; @@ -67,10 +66,9 @@ static struct nr_neigh *nr_neigh_get_dev(ax25_address *callsign, { struct nr_neigh *found = NULL; struct nr_neigh *nr_neigh; - struct hlist_node *node; spin_lock_bh(&nr_neigh_list_lock); - nr_neigh_for_each(nr_neigh, node, &nr_neigh_list) + nr_neigh_for_each(nr_neigh, &nr_neigh_list) if (ax25cmp(callsign, &nr_neigh->callsign) == 0 && nr_neigh->dev == dev) { nr_neigh_hold(nr_neigh); @@ -114,10 +112,9 @@ static int __must_check nr_add_node(ax25_address *nr, const char *mnemonic, */ if (nr_neigh != NULL && nr_neigh->failed != 0 && quality == 0) { struct nr_node *nr_nodet; - struct hlist_node *node; spin_lock_bh(&nr_node_list_lock); - nr_node_for_each(nr_nodet, node, &nr_node_list) { + nr_node_for_each(nr_nodet, &nr_node_list) { nr_node_lock(nr_nodet); for (i = 0; i < nr_nodet->count; i++) if (nr_nodet->routes[i].neighbour == nr_neigh) @@ -485,11 +482,11 @@ static int nr_dec_obs(void) { struct nr_neigh *nr_neigh; struct nr_node *s; - struct hlist_node *node, *nodet; + struct hlist_node *nodet; int i; spin_lock_bh(&nr_node_list_lock); - nr_node_for_each_safe(s, node, nodet, &nr_node_list) { + nr_node_for_each_safe(s, nodet, &nr_node_list) { nr_node_lock(s); for (i = 0; i < s->count; i++) { switch (s->routes[i].obs_count) { @@ -540,15 +537,15 @@ static int nr_dec_obs(void) void nr_rt_device_down(struct net_device *dev) { struct nr_neigh *s; - struct hlist_node *node, *nodet, *node2, *node2t; + struct hlist_node *nodet, *node2t; struct nr_node *t; int i; spin_lock_bh(&nr_neigh_list_lock); - nr_neigh_for_each_safe(s, node, nodet, &nr_neigh_list) { + nr_neigh_for_each_safe(s, nodet, &nr_neigh_list) { if (s->dev == dev) { spin_lock_bh(&nr_node_list_lock); - nr_node_for_each_safe(t, node2, node2t, &nr_node_list) { + nr_node_for_each_safe(t, node2t, &nr_node_list) { nr_node_lock(t); for (i = 0; i < t->count; i++) { if (t->routes[i].neighbour == s) { @@ -737,11 +734,10 @@ int nr_rt_ioctl(unsigned int cmd, void __user *arg) void nr_link_failed(ax25_cb *ax25, int reason) { struct nr_neigh *s, *nr_neigh = NULL; - struct hlist_node *node; struct nr_node *nr_node = NULL; spin_lock_bh(&nr_neigh_list_lock); - nr_neigh_for_each(s, node, &nr_neigh_list) { + nr_neigh_for_each(s, &nr_neigh_list) { if (s->ax25 == ax25) { nr_neigh_hold(s); nr_neigh = s; @@ -761,7 +757,7 @@ void nr_link_failed(ax25_cb *ax25, int reason) return; } spin_lock_bh(&nr_node_list_lock); - nr_node_for_each(nr_node, node, &nr_node_list) { + nr_node_for_each(nr_node, &nr_node_list) { nr_node_lock(nr_node); if (nr_node->which < nr_node->count && nr_node->routes[nr_node->which].neighbour == nr_neigh) @@ -1013,16 +1009,16 @@ void __exit nr_rt_free(void) { struct nr_neigh *s = NULL; struct nr_node *t = NULL; - struct hlist_node *node, *nodet; + struct hlist_node *nodet; spin_lock_bh(&nr_neigh_list_lock); spin_lock_bh(&nr_node_list_lock); - nr_node_for_each_safe(t, node, nodet, &nr_node_list) { + nr_node_for_each_safe(t, nodet, &nr_node_list) { nr_node_lock(t); nr_remove_node_locked(t); nr_node_unlock(t); } - nr_neigh_for_each_safe(s, node, nodet, &nr_neigh_list) { + nr_neigh_for_each_safe(s, nodet, &nr_neigh_list) { while(s->count) { s->count--; nr_neigh_put(s); diff --git a/net/nfc/llcp/llcp.c b/net/nfc/llcp/llcp.c index 85bc75c38dea..07bd65bf04af 100644 --- a/net/nfc/llcp/llcp.c +++ b/net/nfc/llcp/llcp.c @@ -71,14 +71,14 @@ static void nfc_llcp_socket_purge(struct nfc_llcp_sock *sock) static void nfc_llcp_socket_release(struct nfc_llcp_local *local, bool listen) { struct sock *sk; - struct hlist_node *node, *tmp; + struct hlist_node *tmp; struct nfc_llcp_sock *llcp_sock; skb_queue_purge(&local->tx_queue); write_lock(&local->sockets.lock); - sk_for_each_safe(sk, node, tmp, &local->sockets.head) { + sk_for_each_safe(sk, tmp, &local->sockets.head) { llcp_sock = nfc_llcp_sock(sk); bh_lock_sock(sk); @@ -171,7 +171,6 @@ static struct nfc_llcp_sock *nfc_llcp_sock_get(struct nfc_llcp_local *local, u8 ssap, u8 dsap) { struct sock *sk; - struct hlist_node *node; struct nfc_llcp_sock *llcp_sock, *tmp_sock; pr_debug("ssap dsap %d %d\n", ssap, dsap); @@ -183,7 +182,7 @@ static struct nfc_llcp_sock *nfc_llcp_sock_get(struct nfc_llcp_local *local, llcp_sock = NULL; - sk_for_each(sk, node, &local->sockets.head) { + sk_for_each(sk, &local->sockets.head) { tmp_sock = nfc_llcp_sock(sk); if (tmp_sock->ssap == ssap && tmp_sock->dsap == dsap) { @@ -272,7 +271,6 @@ struct nfc_llcp_sock *nfc_llcp_sock_from_sn(struct nfc_llcp_local *local, u8 *sn, size_t sn_len) { struct sock *sk; - struct hlist_node *node; struct nfc_llcp_sock *llcp_sock, *tmp_sock; pr_debug("sn %zd %p\n", sn_len, sn); @@ -284,7 +282,7 @@ struct nfc_llcp_sock *nfc_llcp_sock_from_sn(struct nfc_llcp_local *local, llcp_sock = NULL; - sk_for_each(sk, node, &local->sockets.head) { + sk_for_each(sk, &local->sockets.head) { tmp_sock = nfc_llcp_sock(sk); pr_debug("llcp sock %p\n", tmp_sock); @@ -602,14 +600,13 @@ static void nfc_llcp_set_nrns(struct nfc_llcp_sock *sock, struct sk_buff *pdu) void nfc_llcp_send_to_raw_sock(struct nfc_llcp_local *local, struct sk_buff *skb, u8 direction) { - struct hlist_node *node; struct sk_buff *skb_copy = NULL, *nskb; struct sock *sk; u8 *data; read_lock(&local->raw_sockets.lock); - sk_for_each(sk, node, &local->raw_sockets.head) { + sk_for_each(sk, &local->raw_sockets.head) { if (sk->sk_state != LLCP_BOUND) continue; @@ -698,11 +695,10 @@ static struct nfc_llcp_sock *nfc_llcp_connecting_sock_get(struct nfc_llcp_local { struct sock *sk; struct nfc_llcp_sock *llcp_sock; - struct hlist_node *node; read_lock(&local->connecting_sockets.lock); - sk_for_each(sk, node, &local->connecting_sockets.head) { + sk_for_each(sk, &local->connecting_sockets.head) { llcp_sock = nfc_llcp_sock(sk); if (llcp_sock->ssap == ssap) { diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 9dc537df46c4..e87a26506dba 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -158,11 +158,10 @@ static struct hlist_head *vport_hash_bucket(const struct datapath *dp, struct vport *ovs_lookup_vport(const struct datapath *dp, u16 port_no) { struct vport *vport; - struct hlist_node *n; struct hlist_head *head; head = vport_hash_bucket(dp, port_no); - hlist_for_each_entry_rcu(vport, n, head, dp_hash_node) { + hlist_for_each_entry_rcu(vport, head, dp_hash_node) { if (vport->port_no == port_no) return vport; } @@ -1386,9 +1385,9 @@ static void __dp_destroy(struct datapath *dp) for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) { struct vport *vport; - struct hlist_node *node, *n; + struct hlist_node *n; - hlist_for_each_entry_safe(vport, node, n, &dp->ports[i], dp_hash_node) + hlist_for_each_entry_safe(vport, n, &dp->ports[i], dp_hash_node) if (vport->port_no != OVSP_LOCAL) ovs_dp_detach_port(vport); } @@ -1825,10 +1824,9 @@ static int ovs_vport_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); for (i = bucket; i < DP_VPORT_HASH_BUCKETS; i++) { struct vport *vport; - struct hlist_node *n; j = 0; - hlist_for_each_entry_rcu(vport, n, &dp->ports[i], dp_hash_node) { + hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node) { if (j >= skip && ovs_vport_cmd_fill_info(vport, skb, NETLINK_CB(cb->skb).portid, diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index c3294cebc4f2..20605ecf100b 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -299,10 +299,10 @@ void ovs_flow_tbl_destroy(struct flow_table *table) for (i = 0; i < table->n_buckets; i++) { struct sw_flow *flow; struct hlist_head *head = flex_array_get(table->buckets, i); - struct hlist_node *node, *n; + struct hlist_node *n; int ver = table->node_ver; - hlist_for_each_entry_safe(flow, node, n, head, hash_node[ver]) { + hlist_for_each_entry_safe(flow, n, head, hash_node[ver]) { hlist_del_rcu(&flow->hash_node[ver]); ovs_flow_free(flow); } @@ -332,7 +332,6 @@ struct sw_flow *ovs_flow_tbl_next(struct flow_table *table, u32 *bucket, u32 *la { struct sw_flow *flow; struct hlist_head *head; - struct hlist_node *n; int ver; int i; @@ -340,7 +339,7 @@ struct sw_flow *ovs_flow_tbl_next(struct flow_table *table, u32 *bucket, u32 *la while (*bucket < table->n_buckets) { i = 0; head = flex_array_get(table->buckets, *bucket); - hlist_for_each_entry_rcu(flow, n, head, hash_node[ver]) { + hlist_for_each_entry_rcu(flow, head, hash_node[ver]) { if (i < *last) { i++; continue; @@ -367,11 +366,10 @@ static void flow_table_copy_flows(struct flow_table *old, struct flow_table *new for (i = 0; i < old->n_buckets; i++) { struct sw_flow *flow; struct hlist_head *head; - struct hlist_node *n; head = flex_array_get(old->buckets, i); - hlist_for_each_entry(flow, n, head, hash_node[old_ver]) + hlist_for_each_entry(flow, head, hash_node[old_ver]) ovs_flow_tbl_insert(new, flow); } old->keep_flows = true; @@ -766,14 +764,13 @@ struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *table, struct sw_flow_key *key, int key_len) { struct sw_flow *flow; - struct hlist_node *n; struct hlist_head *head; u32 hash; hash = ovs_flow_hash(key, key_len); head = find_bucket(table, hash); - hlist_for_each_entry_rcu(flow, n, head, hash_node[table->node_ver]) { + hlist_for_each_entry_rcu(flow, head, hash_node[table->node_ver]) { if (flow->hash == hash && !memcmp(&flow->key, key, key_len)) { diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 70af0bedbac4..ba717cc038b3 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -86,9 +86,8 @@ struct vport *ovs_vport_locate(struct net *net, const char *name) { struct hlist_head *bucket = hash_bucket(net, name); struct vport *vport; - struct hlist_node *node; - hlist_for_each_entry_rcu(vport, node, bucket, hash_node) + hlist_for_each_entry_rcu(vport, bucket, hash_node) if (!strcmp(name, vport->ops->get_name(vport)) && net_eq(ovs_dp_get_net(vport->dp), net)) return vport; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index c111bd0e083a..6a5d5904c234 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3263,12 +3263,11 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, static int packet_notifier(struct notifier_block *this, unsigned long msg, void *data) { struct sock *sk; - struct hlist_node *node; struct net_device *dev = data; struct net *net = dev_net(dev); rcu_read_lock(); - sk_for_each_rcu(sk, node, &net->packet.sklist) { + sk_for_each_rcu(sk, &net->packet.sklist) { struct packet_sock *po = pkt_sk(sk); switch (msg) { diff --git a/net/packet/diag.c b/net/packet/diag.c index 8db6e21c46bd..d3fcd1ebef7e 100644 --- a/net/packet/diag.c +++ b/net/packet/diag.c @@ -172,13 +172,12 @@ static int packet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) struct packet_diag_req *req; struct net *net; struct sock *sk; - struct hlist_node *node; net = sock_net(skb->sk); req = nlmsg_data(cb->nlh); mutex_lock(&net->packet.sklist_lock); - sk_for_each(sk, node, &net->packet.sklist) { + sk_for_each(sk, &net->packet.sklist) { if (!net_eq(sock_net(sk), net)) continue; if (num < s_num) diff --git a/net/phonet/pep.c b/net/phonet/pep.c index 576f22c9c76e..e77411735de8 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -640,11 +640,10 @@ static struct sock *pep_find_pipe(const struct hlist_head *hlist, const struct sockaddr_pn *dst, u8 pipe_handle) { - struct hlist_node *node; struct sock *sknode; u16 dobj = pn_sockaddr_get_object(dst); - sk_for_each(sknode, node, hlist) { + sk_for_each(sknode, hlist) { struct pep_sock *pnnode = pep_sk(sknode); /* Ports match, but addresses might not: */ diff --git a/net/phonet/socket.c b/net/phonet/socket.c index b7e982782255..1afd1381cdc7 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -76,7 +76,6 @@ static struct hlist_head *pn_hash_list(u16 obj) */ struct sock *pn_find_sock_by_sa(struct net *net, const struct sockaddr_pn *spn) { - struct hlist_node *node; struct sock *sknode; struct sock *rval = NULL; u16 obj = pn_sockaddr_get_object(spn); @@ -84,7 +83,7 @@ struct sock *pn_find_sock_by_sa(struct net *net, const struct sockaddr_pn *spn) struct hlist_head *hlist = pn_hash_list(obj); rcu_read_lock(); - sk_for_each_rcu(sknode, node, hlist) { + sk_for_each_rcu(sknode, hlist) { struct pn_sock *pn = pn_sk(sknode); BUG_ON(!pn->sobject); /* unbound socket */ @@ -120,10 +119,9 @@ void pn_deliver_sock_broadcast(struct net *net, struct sk_buff *skb) rcu_read_lock(); for (h = 0; h < PN_HASHSIZE; h++) { - struct hlist_node *node; struct sock *sknode; - sk_for_each(sknode, node, hlist) { + sk_for_each(sknode, hlist) { struct sk_buff *clone; if (!net_eq(sock_net(sknode), net)) @@ -543,12 +541,11 @@ static struct sock *pn_sock_get_idx(struct seq_file *seq, loff_t pos) { struct net *net = seq_file_net(seq); struct hlist_head *hlist = pnsocks.hlist; - struct hlist_node *node; struct sock *sknode; unsigned int h; for (h = 0; h < PN_HASHSIZE; h++) { - sk_for_each_rcu(sknode, node, hlist) { + sk_for_each_rcu(sknode, hlist) { if (!net_eq(net, sock_net(sknode))) continue; if (!pos) diff --git a/net/rds/bind.c b/net/rds/bind.c index 637bde56c9db..b5ad65a0067e 100644 --- a/net/rds/bind.c +++ b/net/rds/bind.c @@ -52,13 +52,12 @@ static struct rds_sock *rds_bind_lookup(__be32 addr, __be16 port, struct rds_sock *insert) { struct rds_sock *rs; - struct hlist_node *node; struct hlist_head *head = hash_to_bucket(addr, port); u64 cmp; u64 needle = ((u64)be32_to_cpu(addr) << 32) | be16_to_cpu(port); rcu_read_lock(); - hlist_for_each_entry_rcu(rs, node, head, rs_bound_node) { + hlist_for_each_entry_rcu(rs, head, rs_bound_node) { cmp = ((u64)be32_to_cpu(rs->rs_bound_addr) << 32) | be16_to_cpu(rs->rs_bound_port); diff --git a/net/rds/connection.c b/net/rds/connection.c index 9e07c756d1f9..642ad42c416b 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -69,9 +69,8 @@ static struct rds_connection *rds_conn_lookup(struct hlist_head *head, struct rds_transport *trans) { struct rds_connection *conn, *ret = NULL; - struct hlist_node *pos; - hlist_for_each_entry_rcu(conn, pos, head, c_hash_node) { + hlist_for_each_entry_rcu(conn, head, c_hash_node) { if (conn->c_faddr == faddr && conn->c_laddr == laddr && conn->c_trans == trans) { ret = conn; @@ -376,7 +375,6 @@ static void rds_conn_message_info(struct socket *sock, unsigned int len, int want_send) { struct hlist_head *head; - struct hlist_node *pos; struct list_head *list; struct rds_connection *conn; struct rds_message *rm; @@ -390,7 +388,7 @@ static void rds_conn_message_info(struct socket *sock, unsigned int len, for (i = 0, head = rds_conn_hash; i < ARRAY_SIZE(rds_conn_hash); i++, head++) { - hlist_for_each_entry_rcu(conn, pos, head, c_hash_node) { + hlist_for_each_entry_rcu(conn, head, c_hash_node) { if (want_send) list = &conn->c_send_queue; else @@ -439,7 +437,6 @@ void rds_for_each_conn_info(struct socket *sock, unsigned int len, { uint64_t buffer[(item_len + 7) / 8]; struct hlist_head *head; - struct hlist_node *pos; struct rds_connection *conn; size_t i; @@ -450,7 +447,7 @@ void rds_for_each_conn_info(struct socket *sock, unsigned int len, for (i = 0, head = rds_conn_hash; i < ARRAY_SIZE(rds_conn_hash); i++, head++) { - hlist_for_each_entry_rcu(conn, pos, head, c_hash_node) { + hlist_for_each_entry_rcu(conn, head, c_hash_node) { /* XXX no c_lock usage.. */ if (!visitor(conn, buffer)) diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index c4719ce604c2..39396d8fd5f6 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -165,10 +165,9 @@ static void rose_remove_socket(struct sock *sk) void rose_kill_by_neigh(struct rose_neigh *neigh) { struct sock *s; - struct hlist_node *node; spin_lock_bh(&rose_list_lock); - sk_for_each(s, node, &rose_list) { + sk_for_each(s, &rose_list) { struct rose_sock *rose = rose_sk(s); if (rose->neighbour == neigh) { @@ -186,10 +185,9 @@ void rose_kill_by_neigh(struct rose_neigh *neigh) static void rose_kill_by_device(struct net_device *dev) { struct sock *s; - struct hlist_node *node; spin_lock_bh(&rose_list_lock); - sk_for_each(s, node, &rose_list) { + sk_for_each(s, &rose_list) { struct rose_sock *rose = rose_sk(s); if (rose->device == dev) { @@ -246,10 +244,9 @@ static void rose_insert_socket(struct sock *sk) static struct sock *rose_find_listener(rose_address *addr, ax25_address *call) { struct sock *s; - struct hlist_node *node; spin_lock_bh(&rose_list_lock); - sk_for_each(s, node, &rose_list) { + sk_for_each(s, &rose_list) { struct rose_sock *rose = rose_sk(s); if (!rosecmp(&rose->source_addr, addr) && @@ -258,7 +255,7 @@ static struct sock *rose_find_listener(rose_address *addr, ax25_address *call) goto found; } - sk_for_each(s, node, &rose_list) { + sk_for_each(s, &rose_list) { struct rose_sock *rose = rose_sk(s); if (!rosecmp(&rose->source_addr, addr) && @@ -278,10 +275,9 @@ found: struct sock *rose_find_socket(unsigned int lci, struct rose_neigh *neigh) { struct sock *s; - struct hlist_node *node; spin_lock_bh(&rose_list_lock); - sk_for_each(s, node, &rose_list) { + sk_for_each(s, &rose_list) { struct rose_sock *rose = rose_sk(s); if (rose->lci == lci && rose->neighbour == neigh) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index d84f7e734cd7..fca07bddb718 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -545,7 +545,7 @@ static void qdisc_class_hash_free(struct hlist_head *h, unsigned int n) void qdisc_class_hash_grow(struct Qdisc *sch, struct Qdisc_class_hash *clhash) { struct Qdisc_class_common *cl; - struct hlist_node *n, *next; + struct hlist_node *next; struct hlist_head *nhash, *ohash; unsigned int nsize, nmask, osize; unsigned int i, h; @@ -564,7 +564,7 @@ void qdisc_class_hash_grow(struct Qdisc *sch, struct Qdisc_class_hash *clhash) sch_tree_lock(sch); for (i = 0; i < osize; i++) { - hlist_for_each_entry_safe(cl, n, next, &ohash[i], hnode) { + hlist_for_each_entry_safe(cl, next, &ohash[i], hnode) { h = qdisc_class_hash(cl->classid, nmask); hlist_add_head(&cl->hnode, &nhash[h]); } diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 0e19948470b8..13aa47aa2ffb 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1041,14 +1041,13 @@ static void cbq_adjust_levels(struct cbq_class *this) static void cbq_normalize_quanta(struct cbq_sched_data *q, int prio) { struct cbq_class *cl; - struct hlist_node *n; unsigned int h; if (q->quanta[prio] == 0) return; for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry(cl, n, &q->clhash.hash[h], common.hnode) { + hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) { /* BUGGGG... Beware! This expression suffer of * arithmetic overflows! */ @@ -1087,10 +1086,9 @@ static void cbq_sync_defmap(struct cbq_class *cl) continue; for (h = 0; h < q->clhash.hashsize; h++) { - struct hlist_node *n; struct cbq_class *c; - hlist_for_each_entry(c, n, &q->clhash.hash[h], + hlist_for_each_entry(c, &q->clhash.hash[h], common.hnode) { if (c->split == split && c->level < level && c->defmap & (1<<i)) { @@ -1210,7 +1208,6 @@ cbq_reset(struct Qdisc *sch) { struct cbq_sched_data *q = qdisc_priv(sch); struct cbq_class *cl; - struct hlist_node *n; int prio; unsigned int h; @@ -1228,7 +1225,7 @@ cbq_reset(struct Qdisc *sch) q->active[prio] = NULL; for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry(cl, n, &q->clhash.hash[h], common.hnode) { + hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) { qdisc_reset(cl->q); cl->next_alive = NULL; @@ -1697,7 +1694,7 @@ static void cbq_destroy_class(struct Qdisc *sch, struct cbq_class *cl) static void cbq_destroy(struct Qdisc *sch) { struct cbq_sched_data *q = qdisc_priv(sch); - struct hlist_node *n, *next; + struct hlist_node *next; struct cbq_class *cl; unsigned int h; @@ -1710,11 +1707,11 @@ static void cbq_destroy(struct Qdisc *sch) * be bound to classes which have been destroyed already. --TGR '04 */ for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry(cl, n, &q->clhash.hash[h], common.hnode) + hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) tcf_destroy_chain(&cl->filter_list); } for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry_safe(cl, n, next, &q->clhash.hash[h], + hlist_for_each_entry_safe(cl, next, &q->clhash.hash[h], common.hnode) cbq_destroy_class(sch, cl); } @@ -2013,14 +2010,13 @@ static void cbq_walk(struct Qdisc *sch, struct qdisc_walker *arg) { struct cbq_sched_data *q = qdisc_priv(sch); struct cbq_class *cl; - struct hlist_node *n; unsigned int h; if (arg->stop) return; for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry(cl, n, &q->clhash.hash[h], common.hnode) { + hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) { if (arg->count < arg->skip) { arg->count++; continue; diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index 71e50c80315f..759b308d1a8d 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -293,14 +293,13 @@ static void drr_walk(struct Qdisc *sch, struct qdisc_walker *arg) { struct drr_sched *q = qdisc_priv(sch); struct drr_class *cl; - struct hlist_node *n; unsigned int i; if (arg->stop) return; for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry(cl, n, &q->clhash.hash[i], common.hnode) { + hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) { if (arg->count < arg->skip) { arg->count++; continue; @@ -451,11 +450,10 @@ static void drr_reset_qdisc(struct Qdisc *sch) { struct drr_sched *q = qdisc_priv(sch); struct drr_class *cl; - struct hlist_node *n; unsigned int i; for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry(cl, n, &q->clhash.hash[i], common.hnode) { + hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) { if (cl->qdisc->q.qlen) list_del(&cl->alist); qdisc_reset(cl->qdisc); @@ -468,13 +466,13 @@ static void drr_destroy_qdisc(struct Qdisc *sch) { struct drr_sched *q = qdisc_priv(sch); struct drr_class *cl; - struct hlist_node *n, *next; + struct hlist_node *next; unsigned int i; tcf_destroy_chain(&q->filter_list); for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry_safe(cl, n, next, &q->clhash.hash[i], + hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], common.hnode) drr_destroy_class(sch, cl); } diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 6c2ec4510540..9facea03faeb 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1389,7 +1389,6 @@ static void hfsc_walk(struct Qdisc *sch, struct qdisc_walker *arg) { struct hfsc_sched *q = qdisc_priv(sch); - struct hlist_node *n; struct hfsc_class *cl; unsigned int i; @@ -1397,7 +1396,7 @@ hfsc_walk(struct Qdisc *sch, struct qdisc_walker *arg) return; for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry(cl, n, &q->clhash.hash[i], + hlist_for_each_entry(cl, &q->clhash.hash[i], cl_common.hnode) { if (arg->count < arg->skip) { arg->count++; @@ -1523,11 +1522,10 @@ hfsc_reset_qdisc(struct Qdisc *sch) { struct hfsc_sched *q = qdisc_priv(sch); struct hfsc_class *cl; - struct hlist_node *n; unsigned int i; for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry(cl, n, &q->clhash.hash[i], cl_common.hnode) + hlist_for_each_entry(cl, &q->clhash.hash[i], cl_common.hnode) hfsc_reset_class(cl); } q->eligible = RB_ROOT; @@ -1540,16 +1538,16 @@ static void hfsc_destroy_qdisc(struct Qdisc *sch) { struct hfsc_sched *q = qdisc_priv(sch); - struct hlist_node *n, *next; + struct hlist_node *next; struct hfsc_class *cl; unsigned int i; for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry(cl, n, &q->clhash.hash[i], cl_common.hnode) + hlist_for_each_entry(cl, &q->clhash.hash[i], cl_common.hnode) tcf_destroy_chain(&cl->filter_list); } for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry_safe(cl, n, next, &q->clhash.hash[i], + hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], cl_common.hnode) hfsc_destroy_class(sch, cl); } @@ -1564,12 +1562,11 @@ hfsc_dump_qdisc(struct Qdisc *sch, struct sk_buff *skb) unsigned char *b = skb_tail_pointer(skb); struct tc_hfsc_qopt qopt; struct hfsc_class *cl; - struct hlist_node *n; unsigned int i; sch->qstats.backlog = 0; for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry(cl, n, &q->clhash.hash[i], cl_common.hnode) + hlist_for_each_entry(cl, &q->clhash.hash[i], cl_common.hnode) sch->qstats.backlog += cl->qdisc->qstats.backlog; } diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 51561eafcb72..bb31a0ef89c9 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -993,11 +993,10 @@ static void htb_reset(struct Qdisc *sch) { struct htb_sched *q = qdisc_priv(sch); struct htb_class *cl; - struct hlist_node *n; unsigned int i; for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry(cl, n, &q->clhash.hash[i], common.hnode) { + hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) { if (cl->level) memset(&cl->un.inner, 0, sizeof(cl->un.inner)); else { @@ -1262,7 +1261,7 @@ static void htb_destroy_class(struct Qdisc *sch, struct htb_class *cl) static void htb_destroy(struct Qdisc *sch) { struct htb_sched *q = qdisc_priv(sch); - struct hlist_node *n, *next; + struct hlist_node *next; struct htb_class *cl; unsigned int i; @@ -1276,11 +1275,11 @@ static void htb_destroy(struct Qdisc *sch) tcf_destroy_chain(&q->filter_list); for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry(cl, n, &q->clhash.hash[i], common.hnode) + hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) tcf_destroy_chain(&cl->filter_list); } for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry_safe(cl, n, next, &q->clhash.hash[i], + hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], common.hnode) htb_destroy_class(sch, cl); } @@ -1566,14 +1565,13 @@ static void htb_walk(struct Qdisc *sch, struct qdisc_walker *arg) { struct htb_sched *q = qdisc_priv(sch); struct htb_class *cl; - struct hlist_node *n; unsigned int i; if (arg->stop) return; for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry(cl, n, &q->clhash.hash[i], common.hnode) { + hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) { if (arg->count < arg->skip) { arg->count++; continue; diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 6ed37652a4c3..e9a77f621c3d 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -276,9 +276,8 @@ static struct qfq_aggregate *qfq_find_agg(struct qfq_sched *q, u32 lmax, u32 weight) { struct qfq_aggregate *agg; - struct hlist_node *n; - hlist_for_each_entry(agg, n, &q->nonfull_aggs, nonfull_next) + hlist_for_each_entry(agg, &q->nonfull_aggs, nonfull_next) if (agg->lmax == lmax && agg->class_weight == weight) return agg; @@ -670,14 +669,13 @@ static void qfq_walk(struct Qdisc *sch, struct qdisc_walker *arg) { struct qfq_sched *q = qdisc_priv(sch); struct qfq_class *cl; - struct hlist_node *n; unsigned int i; if (arg->stop) return; for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry(cl, n, &q->clhash.hash[i], common.hnode) { + hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) { if (arg->count < arg->skip) { arg->count++; continue; @@ -1376,11 +1374,10 @@ static unsigned int qfq_drop_from_slot(struct qfq_sched *q, struct hlist_head *slot) { struct qfq_aggregate *agg; - struct hlist_node *n; struct qfq_class *cl; unsigned int len; - hlist_for_each_entry(agg, n, slot, next) { + hlist_for_each_entry(agg, slot, next) { list_for_each_entry(cl, &agg->active, alist) { if (!cl->qdisc->ops->drop) @@ -1459,11 +1456,10 @@ static void qfq_reset_qdisc(struct Qdisc *sch) { struct qfq_sched *q = qdisc_priv(sch); struct qfq_class *cl; - struct hlist_node *n; unsigned int i; for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry(cl, n, &q->clhash.hash[i], common.hnode) { + hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) { if (cl->qdisc->q.qlen > 0) qfq_deactivate_class(q, cl); @@ -1477,13 +1473,13 @@ static void qfq_destroy_qdisc(struct Qdisc *sch) { struct qfq_sched *q = qdisc_priv(sch); struct qfq_class *cl; - struct hlist_node *n, *next; + struct hlist_node *next; unsigned int i; tcf_destroy_chain(&q->filter_list); for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry_safe(cl, n, next, &q->clhash.hash[i], + hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], common.hnode) { qfq_destroy_class(sch, cl); } diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 2f95f5a5145d..43cd0dd9149d 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1591,32 +1591,31 @@ int sctp_assoc_lookup_laddr(struct sctp_association *asoc, /* Set an association id for a given association */ int sctp_assoc_set_id(struct sctp_association *asoc, gfp_t gfp) { - int assoc_id; - int error = 0; + bool preload = gfp & __GFP_WAIT; + int ret; /* If the id is already assigned, keep it. */ if (asoc->assoc_id) - return error; -retry: - if (unlikely(!idr_pre_get(&sctp_assocs_id, gfp))) - return -ENOMEM; + return 0; + if (preload) + idr_preload(gfp); spin_lock_bh(&sctp_assocs_id_lock); - error = idr_get_new_above(&sctp_assocs_id, (void *)asoc, - idr_low, &assoc_id); - if (!error) { - idr_low = assoc_id + 1; + /* 0 is not a valid id, idr_low is always >= 1 */ + ret = idr_alloc(&sctp_assocs_id, asoc, idr_low, 0, GFP_NOWAIT); + if (ret >= 0) { + idr_low = ret + 1; if (idr_low == INT_MAX) idr_low = 1; } spin_unlock_bh(&sctp_assocs_id_lock); - if (error == -EAGAIN) - goto retry; - else if (error) - return error; + if (preload) + idr_preload_end(); + if (ret < 0) + return ret; - asoc->assoc_id = (sctp_assoc_t) assoc_id; - return error; + asoc->assoc_id = (sctp_assoc_t)ret; + return 0; } /* Free the ASCONF queue */ diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index 17a001bac2cc..90845f331921 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -332,7 +332,6 @@ static struct sctp_association *__sctp_endpoint_lookup_assoc( struct sctp_transport *t = NULL; struct sctp_hashbucket *head; struct sctp_ep_common *epb; - struct hlist_node *node; int hash; int rport; @@ -350,7 +349,7 @@ static struct sctp_association *__sctp_endpoint_lookup_assoc( rport); head = &sctp_assoc_hashtable[hash]; read_lock(&head->lock); - sctp_for_each_hentry(epb, node, &head->chain) { + sctp_for_each_hentry(epb, &head->chain) { tmp = sctp_assoc(epb); if (tmp->ep != ep || rport != tmp->peer.port) continue; diff --git a/net/sctp/input.c b/net/sctp/input.c index 965bbbbe48d4..4b2c83146aa7 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -784,13 +784,12 @@ static struct sctp_endpoint *__sctp_rcv_lookup_endpoint(struct net *net, struct sctp_hashbucket *head; struct sctp_ep_common *epb; struct sctp_endpoint *ep; - struct hlist_node *node; int hash; hash = sctp_ep_hashfn(net, ntohs(laddr->v4.sin_port)); head = &sctp_ep_hashtable[hash]; read_lock(&head->lock); - sctp_for_each_hentry(epb, node, &head->chain) { + sctp_for_each_hentry(epb, &head->chain) { ep = sctp_ep(epb); if (sctp_endpoint_is_match(ep, net, laddr)) goto hit; @@ -876,7 +875,6 @@ static struct sctp_association *__sctp_lookup_association( struct sctp_ep_common *epb; struct sctp_association *asoc; struct sctp_transport *transport; - struct hlist_node *node; int hash; /* Optimize here for direct hit, only listening connections can @@ -886,7 +884,7 @@ static struct sctp_association *__sctp_lookup_association( ntohs(peer->v4.sin_port)); head = &sctp_assoc_hashtable[hash]; read_lock(&head->lock); - sctp_for_each_hentry(epb, node, &head->chain) { + sctp_for_each_hentry(epb, &head->chain) { asoc = sctp_assoc(epb); transport = sctp_assoc_is_match(asoc, net, local, peer); if (transport) diff --git a/net/sctp/proc.c b/net/sctp/proc.c index 8c19e97262ca..ab3bba8cb0a8 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -213,7 +213,6 @@ static int sctp_eps_seq_show(struct seq_file *seq, void *v) struct sctp_ep_common *epb; struct sctp_endpoint *ep; struct sock *sk; - struct hlist_node *node; int hash = *(loff_t *)v; if (hash >= sctp_ep_hashsize) @@ -222,7 +221,7 @@ static int sctp_eps_seq_show(struct seq_file *seq, void *v) head = &sctp_ep_hashtable[hash]; sctp_local_bh_disable(); read_lock(&head->lock); - sctp_for_each_hentry(epb, node, &head->chain) { + sctp_for_each_hentry(epb, &head->chain) { ep = sctp_ep(epb); sk = epb->sk; if (!net_eq(sock_net(sk), seq_file_net(seq))) @@ -321,7 +320,6 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) struct sctp_ep_common *epb; struct sctp_association *assoc; struct sock *sk; - struct hlist_node *node; int hash = *(loff_t *)v; if (hash >= sctp_assoc_hashsize) @@ -330,7 +328,7 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) head = &sctp_assoc_hashtable[hash]; sctp_local_bh_disable(); read_lock(&head->lock); - sctp_for_each_hentry(epb, node, &head->chain) { + sctp_for_each_hentry(epb, &head->chain) { assoc = sctp_assoc(epb); sk = epb->sk; if (!net_eq(sock_net(sk), seq_file_net(seq))) @@ -436,7 +434,6 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v) struct sctp_hashbucket *head; struct sctp_ep_common *epb; struct sctp_association *assoc; - struct hlist_node *node; struct sctp_transport *tsp; int hash = *(loff_t *)v; @@ -447,7 +444,7 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v) sctp_local_bh_disable(); read_lock(&head->lock); rcu_read_lock(); - sctp_for_each_hentry(epb, node, &head->chain) { + sctp_for_each_hentry(epb, &head->chain) { if (!net_eq(sock_net(epb->sk), seq_file_net(seq))) continue; assoc = sctp_assoc(epb); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 9e65758cb038..794b1cf3eaf6 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -5882,8 +5882,7 @@ static struct sctp_bind_bucket *sctp_bucket_create( static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr) { struct sctp_bind_hashbucket *head; /* hash list */ - struct sctp_bind_bucket *pp; /* hash list port iterator */ - struct hlist_node *node; + struct sctp_bind_bucket *pp; unsigned short snum; int ret; @@ -5910,7 +5909,7 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr) index = sctp_phashfn(sock_net(sk), rover); head = &sctp_port_hashtable[index]; sctp_spin_lock(&head->lock); - sctp_for_each_hentry(pp, node, &head->chain) + sctp_for_each_hentry(pp, &head->chain) if ((pp->port == rover) && net_eq(sock_net(sk), pp->net)) goto next; @@ -5938,7 +5937,7 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr) */ head = &sctp_port_hashtable[sctp_phashfn(sock_net(sk), snum)]; sctp_spin_lock(&head->lock); - sctp_for_each_hentry(pp, node, &head->chain) { + sctp_for_each_hentry(pp, &head->chain) { if ((pp->port == snum) && net_eq(pp->net, sock_net(sk))) goto pp_found; } @@ -5970,7 +5969,7 @@ pp_found: * that this port/socket (sk) combination are already * in an endpoint. */ - sk_for_each_bound(sk2, node, &pp->owner) { + sk_for_each_bound(sk2, &pp->owner) { struct sctp_endpoint *ep2; ep2 = sctp_sk(sk2)->ep; diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index b5c067bccc45..cd9639f1b63c 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -407,7 +407,6 @@ rpcauth_lookup_credcache(struct rpc_auth *auth, struct auth_cred * acred, { LIST_HEAD(free); struct rpc_cred_cache *cache = auth->au_credcache; - struct hlist_node *pos; struct rpc_cred *cred = NULL, *entry, *new; unsigned int nr; @@ -415,7 +414,7 @@ rpcauth_lookup_credcache(struct rpc_auth *auth, struct auth_cred * acred, nr = hash_long(acred->uid, cache->hashbits); rcu_read_lock(); - hlist_for_each_entry_rcu(entry, pos, &cache->hashtable[nr], cr_hash) { + hlist_for_each_entry_rcu(entry, &cache->hashtable[nr], cr_hash) { if (!entry->cr_ops->crmatch(acred, entry, flags)) continue; spin_lock(&cache->lock); @@ -439,7 +438,7 @@ rpcauth_lookup_credcache(struct rpc_auth *auth, struct auth_cred * acred, } spin_lock(&cache->lock); - hlist_for_each_entry(entry, pos, &cache->hashtable[nr], cr_hash) { + hlist_for_each_entry(entry, &cache->hashtable[nr], cr_hash) { if (!entry->cr_ops->crmatch(acred, entry, flags)) continue; cred = get_rpccred(entry); diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 9f8470353362..94a8d2bd1eca 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -670,13 +670,13 @@ static void cache_revisit_request(struct cache_head *item) { struct cache_deferred_req *dreq; struct list_head pending; - struct hlist_node *lp, *tmp; + struct hlist_node *tmp; int hash = DFR_HASH(item); INIT_LIST_HEAD(&pending); spin_lock(&cache_defer_lock); - hlist_for_each_entry_safe(dreq, lp, tmp, &cache_defer_hash[hash], hash) + hlist_for_each_entry_safe(dreq, tmp, &cache_defer_hash[hash], hash) if (dreq->item == item) { __unhash_deferred_req(dreq); list_add(&dreq->recent, &pending); diff --git a/net/sunrpc/svcauth.c b/net/sunrpc/svcauth.c index 7963569fc04f..2af7b0cba43a 100644 --- a/net/sunrpc/svcauth.c +++ b/net/sunrpc/svcauth.c @@ -138,13 +138,12 @@ auth_domain_lookup(char *name, struct auth_domain *new) { struct auth_domain *hp; struct hlist_head *head; - struct hlist_node *np; head = &auth_domain_table[hash_str(name, DN_HASHBITS)]; spin_lock(&auth_domain_lock); - hlist_for_each_entry(hp, np, head, hash) { + hlist_for_each_entry(hp, head, hash) { if (strcmp(hp->name, name)==0) { kref_get(&hp->ref); spin_unlock(&auth_domain_lock); diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 46754779fd3d..24b167914311 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -473,11 +473,10 @@ static void tipc_nameseq_subscribe(struct name_seq *nseq, static struct name_seq *nametbl_find_seq(u32 type) { struct hlist_head *seq_head; - struct hlist_node *seq_node; struct name_seq *ns; seq_head = &table.types[hash(type)]; - hlist_for_each_entry(ns, seq_node, seq_head, ns_list) { + hlist_for_each_entry(ns, seq_head, ns_list) { if (ns->type == type) return ns; } @@ -853,7 +852,6 @@ static int nametbl_list(char *buf, int len, u32 depth_info, u32 type, u32 lowbound, u32 upbound) { struct hlist_head *seq_head; - struct hlist_node *seq_node; struct name_seq *seq; int all_types; int ret = 0; @@ -873,7 +871,7 @@ static int nametbl_list(char *buf, int len, u32 depth_info, upbound = ~0; for (i = 0; i < TIPC_NAMETBL_SIZE; i++) { seq_head = &table.types[i]; - hlist_for_each_entry(seq, seq_node, seq_head, ns_list) { + hlist_for_each_entry(seq, seq_head, ns_list) { ret += nameseq_list(seq, buf + ret, len - ret, depth, seq->type, lowbound, upbound, i); @@ -889,7 +887,7 @@ static int nametbl_list(char *buf, int len, u32 depth_info, ret += nametbl_header(buf + ret, len - ret, depth); i = hash(type); seq_head = &table.types[i]; - hlist_for_each_entry(seq, seq_node, seq_head, ns_list) { + hlist_for_each_entry(seq, seq_head, ns_list) { if (seq->type == type) { ret += nameseq_list(seq, buf + ret, len - ret, depth, type, diff --git a/net/tipc/node.c b/net/tipc/node.c index 48f39dd3eae8..6e6c434872e8 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -69,12 +69,11 @@ static unsigned int tipc_hashfn(u32 addr) struct tipc_node *tipc_node_find(u32 addr) { struct tipc_node *node; - struct hlist_node *pos; if (unlikely(!in_own_cluster_exact(addr))) return NULL; - hlist_for_each_entry(node, pos, &node_htable[tipc_hashfn(addr)], hash) { + hlist_for_each_entry(node, &node_htable[tipc_hashfn(addr)], hash) { if (node->addr == addr) return node; } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 0c612361c153..97d303caf460 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -263,9 +263,8 @@ static struct sock *__unix_find_socket_byname(struct net *net, int len, int type, unsigned int hash) { struct sock *s; - struct hlist_node *node; - sk_for_each(s, node, &unix_socket_table[hash ^ type]) { + sk_for_each(s, &unix_socket_table[hash ^ type]) { struct unix_sock *u = unix_sk(s); if (!net_eq(sock_net(s), net)) @@ -298,10 +297,9 @@ static inline struct sock *unix_find_socket_byname(struct net *net, static struct sock *unix_find_socket_byinode(struct inode *i) { struct sock *s; - struct hlist_node *node; spin_lock(&unix_table_lock); - sk_for_each(s, node, + sk_for_each(s, &unix_socket_table[i->i_ino & (UNIX_HASH_SIZE - 1)]) { struct dentry *dentry = unix_sk(s)->path.dentry; diff --git a/net/unix/diag.c b/net/unix/diag.c index 5ac19dc1d5e4..d591091603bf 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -192,10 +192,9 @@ static int unix_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) slot < ARRAY_SIZE(unix_socket_table); s_num = 0, slot++) { struct sock *sk; - struct hlist_node *node; num = 0; - sk_for_each(sk, node, &unix_socket_table[slot]) { + sk_for_each(sk, &unix_socket_table[slot]) { if (!net_eq(sock_net(sk), net)) continue; if (num < s_num) @@ -226,9 +225,7 @@ static struct sock *unix_lookup_by_ino(int ino) spin_lock(&unix_table_lock); for (i = 0; i < ARRAY_SIZE(unix_socket_table); i++) { - struct hlist_node *node; - - sk_for_each(sk, node, &unix_socket_table[i]) + sk_for_each(sk, &unix_socket_table[i]) if (ino == sock_i_ino(sk)) { sock_hold(sk); spin_unlock(&unix_table_lock); diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index a306bc66000e..37ca9694aabe 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -208,11 +208,10 @@ static void x25_remove_socket(struct sock *sk) static void x25_kill_by_device(struct net_device *dev) { struct sock *s; - struct hlist_node *node; write_lock_bh(&x25_list_lock); - sk_for_each(s, node, &x25_list) + sk_for_each(s, &x25_list) if (x25_sk(s)->neighbour && x25_sk(s)->neighbour->dev == dev) x25_disconnect(s, ENETUNREACH, 0, 0); @@ -280,12 +279,11 @@ static struct sock *x25_find_listener(struct x25_address *addr, { struct sock *s; struct sock *next_best; - struct hlist_node *node; read_lock_bh(&x25_list_lock); next_best = NULL; - sk_for_each(s, node, &x25_list) + sk_for_each(s, &x25_list) if ((!strcmp(addr->x25_addr, x25_sk(s)->source_addr.x25_addr) || !strcmp(addr->x25_addr, @@ -323,9 +321,8 @@ found: static struct sock *__x25_find_socket(unsigned int lci, struct x25_neigh *nb) { struct sock *s; - struct hlist_node *node; - sk_for_each(s, node, &x25_list) + sk_for_each(s, &x25_list) if (x25_sk(s)->lci == lci && x25_sk(s)->neighbour == nb) { sock_hold(s); goto found; @@ -1782,11 +1779,10 @@ static struct notifier_block x25_dev_notifier = { void x25_kill_by_neigh(struct x25_neigh *nb) { struct sock *s; - struct hlist_node *node; write_lock_bh(&x25_list_lock); - sk_for_each(s, node, &x25_list) + sk_for_each(s, &x25_list) if (x25_sk(s)->neighbour == nb) x25_disconnect(s, ENETUNREACH, 0, 0); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 6c9aa642a2ba..2de7d57f3f60 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -359,27 +359,27 @@ static void xfrm_dst_hash_transfer(struct hlist_head *list, struct hlist_head *ndsttable, unsigned int nhashmask) { - struct hlist_node *entry, *tmp, *entry0 = NULL; + struct hlist_node *tmp, *entry0 = NULL; struct xfrm_policy *pol; unsigned int h0 = 0; redo: - hlist_for_each_entry_safe(pol, entry, tmp, list, bydst) { + hlist_for_each_entry_safe(pol, tmp, list, bydst) { unsigned int h; h = __addr_hash(&pol->selector.daddr, &pol->selector.saddr, pol->family, nhashmask); if (!entry0) { - hlist_del(entry); + hlist_del(&pol->bydst); hlist_add_head(&pol->bydst, ndsttable+h); h0 = h; } else { if (h != h0) continue; - hlist_del(entry); + hlist_del(&pol->bydst); hlist_add_after(entry0, &pol->bydst); } - entry0 = entry; + entry0 = &pol->bydst; } if (!hlist_empty(list)) { entry0 = NULL; @@ -391,10 +391,10 @@ static void xfrm_idx_hash_transfer(struct hlist_head *list, struct hlist_head *nidxtable, unsigned int nhashmask) { - struct hlist_node *entry, *tmp; + struct hlist_node *tmp; struct xfrm_policy *pol; - hlist_for_each_entry_safe(pol, entry, tmp, list, byidx) { + hlist_for_each_entry_safe(pol, tmp, list, byidx) { unsigned int h; h = __idx_hash(pol->index, nhashmask); @@ -524,7 +524,6 @@ static u32 xfrm_gen_index(struct net *net, int dir) static u32 idx_generator; for (;;) { - struct hlist_node *entry; struct hlist_head *list; struct xfrm_policy *p; u32 idx; @@ -536,7 +535,7 @@ static u32 xfrm_gen_index(struct net *net, int dir) idx = 8; list = net->xfrm.policy_byidx + idx_hash(net, idx); found = 0; - hlist_for_each_entry(p, entry, list, byidx) { + hlist_for_each_entry(p, list, byidx) { if (p->index == idx) { found = 1; break; @@ -568,14 +567,14 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) struct xfrm_policy *pol; struct xfrm_policy *delpol; struct hlist_head *chain; - struct hlist_node *entry, *newpos; + struct hlist_node *newpos; u32 mark = policy->mark.v & policy->mark.m; write_lock_bh(&xfrm_policy_lock); chain = policy_hash_bysel(net, &policy->selector, policy->family, dir); delpol = NULL; newpos = NULL; - hlist_for_each_entry(pol, entry, chain, bydst) { + hlist_for_each_entry(pol, chain, bydst) { if (pol->type == policy->type && !selector_cmp(&pol->selector, &policy->selector) && (mark & pol->mark.m) == pol->mark.v && @@ -630,13 +629,12 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type, { struct xfrm_policy *pol, *ret; struct hlist_head *chain; - struct hlist_node *entry; *err = 0; write_lock_bh(&xfrm_policy_lock); chain = policy_hash_bysel(net, sel, sel->family, dir); ret = NULL; - hlist_for_each_entry(pol, entry, chain, bydst) { + hlist_for_each_entry(pol, chain, bydst) { if (pol->type == type && (mark & pol->mark.m) == pol->mark.v && !selector_cmp(sel, &pol->selector) && @@ -668,7 +666,6 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type, { struct xfrm_policy *pol, *ret; struct hlist_head *chain; - struct hlist_node *entry; *err = -ENOENT; if (xfrm_policy_id2dir(id) != dir) @@ -678,7 +675,7 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type, write_lock_bh(&xfrm_policy_lock); chain = net->xfrm.policy_byidx + idx_hash(net, id); ret = NULL; - hlist_for_each_entry(pol, entry, chain, byidx) { + hlist_for_each_entry(pol, chain, byidx) { if (pol->type == type && pol->index == id && (mark & pol->mark.m) == pol->mark.v) { xfrm_pol_hold(pol); @@ -711,10 +708,9 @@ xfrm_policy_flush_secctx_check(struct net *net, u8 type, struct xfrm_audit *audi for (dir = 0; dir < XFRM_POLICY_MAX; dir++) { struct xfrm_policy *pol; - struct hlist_node *entry; int i; - hlist_for_each_entry(pol, entry, + hlist_for_each_entry(pol, &net->xfrm.policy_inexact[dir], bydst) { if (pol->type != type) continue; @@ -728,7 +724,7 @@ xfrm_policy_flush_secctx_check(struct net *net, u8 type, struct xfrm_audit *audi } } for (i = net->xfrm.policy_bydst[dir].hmask; i >= 0; i--) { - hlist_for_each_entry(pol, entry, + hlist_for_each_entry(pol, net->xfrm.policy_bydst[dir].table + i, bydst) { if (pol->type != type) @@ -767,11 +763,10 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info) for (dir = 0; dir < XFRM_POLICY_MAX; dir++) { struct xfrm_policy *pol; - struct hlist_node *entry; int i; again1: - hlist_for_each_entry(pol, entry, + hlist_for_each_entry(pol, &net->xfrm.policy_inexact[dir], bydst) { if (pol->type != type) continue; @@ -791,7 +786,7 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info) for (i = net->xfrm.policy_bydst[dir].hmask; i >= 0; i--) { again2: - hlist_for_each_entry(pol, entry, + hlist_for_each_entry(pol, net->xfrm.policy_bydst[dir].table + i, bydst) { if (pol->type != type) @@ -919,7 +914,6 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, int err; struct xfrm_policy *pol, *ret; const xfrm_address_t *daddr, *saddr; - struct hlist_node *entry; struct hlist_head *chain; u32 priority = ~0U; @@ -931,7 +925,7 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, read_lock_bh(&xfrm_policy_lock); chain = policy_hash_direct(net, daddr, saddr, family, dir); ret = NULL; - hlist_for_each_entry(pol, entry, chain, bydst) { + hlist_for_each_entry(pol, chain, bydst) { err = xfrm_policy_match(pol, fl, type, family, dir); if (err) { if (err == -ESRCH) @@ -947,7 +941,7 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, } } chain = &net->xfrm.policy_inexact[dir]; - hlist_for_each_entry(pol, entry, chain, bydst) { + hlist_for_each_entry(pol, chain, bydst) { err = xfrm_policy_match(pol, fl, type, family, dir); if (err) { if (err == -ESRCH) @@ -2806,13 +2800,12 @@ static struct xfrm_policy * xfrm_migrate_policy_find(const struct xfrm_selector u8 dir, u8 type) { struct xfrm_policy *pol, *ret = NULL; - struct hlist_node *entry; struct hlist_head *chain; u32 priority = ~0U; read_lock_bh(&xfrm_policy_lock); chain = policy_hash_direct(&init_net, &sel->daddr, &sel->saddr, sel->family, dir); - hlist_for_each_entry(pol, entry, chain, bydst) { + hlist_for_each_entry(pol, chain, bydst) { if (xfrm_migrate_selector_match(sel, &pol->selector) && pol->type == type) { ret = pol; @@ -2821,7 +2814,7 @@ static struct xfrm_policy * xfrm_migrate_policy_find(const struct xfrm_selector } } chain = &init_net.xfrm.policy_inexact[dir]; - hlist_for_each_entry(pol, entry, chain, bydst) { + hlist_for_each_entry(pol, chain, bydst) { if (xfrm_migrate_selector_match(sel, &pol->selector) && pol->type == type && pol->priority < priority) { diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index ae01bdbcb294..2c341bdaf47c 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -72,10 +72,10 @@ static void xfrm_hash_transfer(struct hlist_head *list, struct hlist_head *nspitable, unsigned int nhashmask) { - struct hlist_node *entry, *tmp; + struct hlist_node *tmp; struct xfrm_state *x; - hlist_for_each_entry_safe(x, entry, tmp, list, bydst) { + hlist_for_each_entry_safe(x, tmp, list, bydst) { unsigned int h; h = __xfrm_dst_hash(&x->id.daddr, &x->props.saddr, @@ -368,14 +368,14 @@ static void xfrm_state_gc_task(struct work_struct *work) { struct net *net = container_of(work, struct net, xfrm.state_gc_work); struct xfrm_state *x; - struct hlist_node *entry, *tmp; + struct hlist_node *tmp; struct hlist_head gc_list; spin_lock_bh(&xfrm_state_gc_lock); hlist_move_list(&net->xfrm.state_gc_list, &gc_list); spin_unlock_bh(&xfrm_state_gc_lock); - hlist_for_each_entry_safe(x, entry, tmp, &gc_list, gclist) + hlist_for_each_entry_safe(x, tmp, &gc_list, gclist) xfrm_state_gc_destroy(x); wake_up(&net->xfrm.km_waitq); @@ -577,10 +577,9 @@ xfrm_state_flush_secctx_check(struct net *net, u8 proto, struct xfrm_audit *audi int i, err = 0; for (i = 0; i <= net->xfrm.state_hmask; i++) { - struct hlist_node *entry; struct xfrm_state *x; - hlist_for_each_entry(x, entry, net->xfrm.state_bydst+i, bydst) { + hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) { if (xfrm_id_proto_match(x->id.proto, proto) && (err = security_xfrm_state_delete(x)) != 0) { xfrm_audit_state_delete(x, 0, @@ -613,10 +612,9 @@ int xfrm_state_flush(struct net *net, u8 proto, struct xfrm_audit *audit_info) err = -ESRCH; for (i = 0; i <= net->xfrm.state_hmask; i++) { - struct hlist_node *entry; struct xfrm_state *x; restart: - hlist_for_each_entry(x, entry, net->xfrm.state_bydst+i, bydst) { + hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) { if (!xfrm_state_kern(x) && xfrm_id_proto_match(x->id.proto, proto)) { xfrm_state_hold(x); @@ -685,9 +683,8 @@ static struct xfrm_state *__xfrm_state_lookup(struct net *net, u32 mark, { unsigned int h = xfrm_spi_hash(net, daddr, spi, proto, family); struct xfrm_state *x; - struct hlist_node *entry; - hlist_for_each_entry(x, entry, net->xfrm.state_byspi+h, byspi) { + hlist_for_each_entry(x, net->xfrm.state_byspi+h, byspi) { if (x->props.family != family || x->id.spi != spi || x->id.proto != proto || @@ -710,9 +707,8 @@ static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, u32 mark, { unsigned int h = xfrm_src_hash(net, daddr, saddr, family); struct xfrm_state *x; - struct hlist_node *entry; - hlist_for_each_entry(x, entry, net->xfrm.state_bysrc+h, bysrc) { + hlist_for_each_entry(x, net->xfrm.state_bysrc+h, bysrc) { if (x->props.family != family || x->id.proto != proto || !xfrm_addr_equal(&x->id.daddr, daddr, family) || @@ -798,7 +794,6 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, static xfrm_address_t saddr_wildcard = { }; struct net *net = xp_net(pol); unsigned int h, h_wildcard; - struct hlist_node *entry; struct xfrm_state *x, *x0, *to_put; int acquire_in_progress = 0; int error = 0; @@ -810,7 +805,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, spin_lock_bh(&xfrm_state_lock); h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family); - hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h, bydst) { + hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { if (x->props.family == encap_family && x->props.reqid == tmpl->reqid && (mark & x->mark.m) == x->mark.v && @@ -826,7 +821,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, goto found; h_wildcard = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, encap_family); - hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h_wildcard, bydst) { + hlist_for_each_entry(x, net->xfrm.state_bydst+h_wildcard, bydst) { if (x->props.family == encap_family && x->props.reqid == tmpl->reqid && (mark & x->mark.m) == x->mark.v && @@ -906,11 +901,10 @@ xfrm_stateonly_find(struct net *net, u32 mark, { unsigned int h; struct xfrm_state *rx = NULL, *x = NULL; - struct hlist_node *entry; spin_lock(&xfrm_state_lock); h = xfrm_dst_hash(net, daddr, saddr, reqid, family); - hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h, bydst) { + hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { if (x->props.family == family && x->props.reqid == reqid && (mark & x->mark.m) == x->mark.v && @@ -972,12 +966,11 @@ static void __xfrm_state_bump_genids(struct xfrm_state *xnew) unsigned short family = xnew->props.family; u32 reqid = xnew->props.reqid; struct xfrm_state *x; - struct hlist_node *entry; unsigned int h; u32 mark = xnew->mark.v & xnew->mark.m; h = xfrm_dst_hash(net, &xnew->id.daddr, &xnew->props.saddr, reqid, family); - hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h, bydst) { + hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { if (x->props.family == family && x->props.reqid == reqid && (mark & x->mark.m) == x->mark.v && @@ -1004,11 +997,10 @@ static struct xfrm_state *__find_acq_core(struct net *net, struct xfrm_mark *m, const xfrm_address_t *saddr, int create) { unsigned int h = xfrm_dst_hash(net, daddr, saddr, reqid, family); - struct hlist_node *entry; struct xfrm_state *x; u32 mark = m->v & m->m; - hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h, bydst) { + hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { if (x->props.reqid != reqid || x->props.mode != mode || x->props.family != family || @@ -1215,12 +1207,11 @@ struct xfrm_state * xfrm_migrate_state_find(struct xfrm_migrate *m) { unsigned int h; struct xfrm_state *x; - struct hlist_node *entry; if (m->reqid) { h = xfrm_dst_hash(&init_net, &m->old_daddr, &m->old_saddr, m->reqid, m->old_family); - hlist_for_each_entry(x, entry, init_net.xfrm.state_bydst+h, bydst) { + hlist_for_each_entry(x, init_net.xfrm.state_bydst+h, bydst) { if (x->props.mode != m->mode || x->id.proto != m->proto) continue; @@ -1237,7 +1228,7 @@ struct xfrm_state * xfrm_migrate_state_find(struct xfrm_migrate *m) } else { h = xfrm_src_hash(&init_net, &m->old_daddr, &m->old_saddr, m->old_family); - hlist_for_each_entry(x, entry, init_net.xfrm.state_bysrc+h, bysrc) { + hlist_for_each_entry(x, init_net.xfrm.state_bysrc+h, bysrc) { if (x->props.mode != m->mode || x->id.proto != m->proto) continue; @@ -1466,10 +1457,9 @@ static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 mark, u32 s int i; for (i = 0; i <= net->xfrm.state_hmask; i++) { - struct hlist_node *entry; struct xfrm_state *x; - hlist_for_each_entry(x, entry, net->xfrm.state_bydst+i, bydst) { + hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) { if (x->km.seq == seq && (mark & x->mark.m) == x->mark.v && x->km.state == XFRM_STATE_ACQ) { diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 2bb08a962ce3..747bcd768da0 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -1931,6 +1931,12 @@ sub process { "use the SSYNC() macro in asm/blackfin.h\n" . $herevet); } +# check for old HOTPLUG __dev<foo> section markings + if ($line =~ /\b(__dev(init|exit)(data|const|))\b/) { + WARN("HOTPLUG_SECTION", + "Using $1 is unnecessary\n" . $herecurr); + } + # Check for potential 'bare' types my ($stat, $cond, $line_nr_next, $remain_next, $off_next, $realline_next); @@ -2430,6 +2436,15 @@ sub process { "Prefer pr_warn(... to pr_warning(...\n" . $herecurr); } + if ($line =~ /\bdev_printk\s*\(\s*KERN_([A-Z]+)/) { + my $orig = $1; + my $level = lc($orig); + $level = "warn" if ($level eq "warning"); + $level = "dbg" if ($level eq "debug"); + WARN("PREFER_DEV_LEVEL", + "Prefer dev_$level(... to dev_printk(KERN_$orig, ...\n" . $herecurr); + } + # function brace can't be on same line, except for #defines of do while, # or if closed on same line if (($line=~/$Type\s*$Ident\(.*\).*\s{/) and @@ -2915,6 +2930,7 @@ sub process { my $var = $1; if ($var !~ /$Constant/ && $var =~ /[A-Z]\w*[a-z]|[a-z]\w*[A-Z]/ && + $var !~ /^Page[A-Z]/ && !defined $camelcase{$var}) { $camelcase{$var} = 1; WARN("CAMELCASE", @@ -3237,9 +3253,9 @@ sub process { } # prefer usleep_range over udelay - if ($line =~ /\budelay\s*\(\s*(\w+)\s*\)/) { + if ($line =~ /\budelay\s*\(\s*(\d+)\s*\)/) { # ignore udelay's < 10, however - if (! (($1 =~ /(\d+)/) && ($1 < 10)) ) { + if (! ($1 < 10) ) { CHK("USLEEP_RANGE", "usleep_range is preferred over udelay; see Documentation/timers/timers-howto.txt\n" . $line); } @@ -3460,6 +3476,12 @@ sub process { "unnecessary cast may hide bugs, see http://c-faq.com/malloc/mallocnocast.html\n" . $herecurr); } +# check for alloc argument mismatch + if ($line =~ /\b(kcalloc|kmalloc_array)\s*\(\s*sizeof\b/) { + WARN("ALLOC_ARRAY_ARGS", + "$1 uses number as first arg, sizeof is generally wrong\n" . $herecurr); + } + # check for multiple semicolons if ($line =~ /;\s*;\s*$/) { WARN("ONE_SEMICOLON", diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index 8b673dd4627f..18d4ab55606b 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -433,7 +433,7 @@ foreach my $file (@ARGV) { while (<$patch>) { my $patch_line = $_; - if (m/^\+\+\+\s+(\S+)/) { + if (m/^\+\+\+\s+(\S+)/ or m/^---\s+(\S+)/) { my $filename = $1; $filename =~ s@^[^/]*/@@; $filename =~ s@\n@@; diff --git a/scripts/pnmtologo.c b/scripts/pnmtologo.c index 68bb4efc5af4..ce937970cf98 100644 --- a/scripts/pnmtologo.c +++ b/scripts/pnmtologo.c @@ -104,9 +104,11 @@ static unsigned int get_number(FILE *fp) val = 0; while (isdigit(c)) { val = 10*val+c-'0'; - /* some PBM are 'broken'; GiMP for example exports a PBM without space - * between the digits. This is Ok cause we know a PBM can only have a '1' - * or a '0' for the digit. */ + /* + * Some PBM are 'broken'; GiMP for example exports a PBM without space + * between the digits. This is OK because we know a PBM can only have a + * '1' or a '0' for the digit. + */ if (is_plain_pbm) break; c = fgetc(fp); diff --git a/scripts/tags.sh b/scripts/tags.sh index 4c53b7d883d3..26a87e68afed 100755 --- a/scripts/tags.sh +++ b/scripts/tags.sh @@ -149,12 +149,17 @@ dogtags() exuberant() { all_target_sources | xargs $1 -a \ - -I __initdata,__exitdata,__acquires,__releases \ - -I __read_mostly,____cacheline_aligned \ + -I __initdata,__exitdata,__initconst,__devinitdata \ + -I __devinitconst,__cpuinitdata,__initdata_memblock \ + -I __refdata,__attribute \ + -I __acquires,__releases,__deprecated \ + -I __read_mostly,__aligned,____cacheline_aligned \ -I ____cacheline_aligned_in_smp \ -I ____cacheline_internodealigned_in_smp \ + -I __used,__packed,__packed2__,__must_check,__must_hold \ -I EXPORT_SYMBOL,EXPORT_SYMBOL_GPL \ -I DEFINE_TRACE,EXPORT_TRACEPOINT_SYMBOL,EXPORT_TRACEPOINT_SYMBOL_GPL \ + -I static,const \ --extra=+f --c-kinds=+px \ --regex-asm='/^(ENTRY|_GLOBAL)\(([^)]*)\).*/\2/' \ --regex-c='/^SYSCALL_DEFINE[[:digit:]]?\(([^,)]*).*/sys_\1/' \ @@ -182,8 +187,19 @@ exuberant() --regex-c++='/TESTCLEARFLAG_FALSE\(([^,)]*).*/TestClearPage\1/' \ --regex-c++='/__TESTCLEARFLAG_FALSE\(([^,)]*).*/__TestClearPage\1/' \ --regex-c++='/_PE\(([^,)]*).*/PEVENT_ERRNO__\1/' \ - --regex-c='/PCI_OP_READ\(([a-z]*[a-z]).*[1-4]\)/pci_bus_read_config_\1/' \ - --regex-c='/PCI_OP_WRITE\(([a-z]*[a-z]).*[1-4]\)/pci_bus_write_config_\1/' + --regex-c='/PCI_OP_READ\((\w*).*[1-4]\)/pci_bus_read_config_\1/' \ + --regex-c='/PCI_OP_WRITE\((\w*).*[1-4]\)/pci_bus_write_config_\1/' \ + --regex-c='/DEFINE_(MUTEX|SEMAPHORE|SPINLOCK)\((\w*)/\2/v/' \ + --regex-c='/DEFINE_(RAW_SPINLOCK|RWLOCK|SEQLOCK)\((\w*)/\2/v/' \ + --regex-c='/DECLARE_(RWSEM|COMPLETION)\((\w*)/\2/v/' \ + --regex-c='/DECLARE_BITMAP\((\w*)/\1/v/' \ + --regex-c='/(^|\s)(|L|H)LIST_HEAD\((\w*)/\3/v/' \ + --regex-c='/(^|\s)RADIX_TREE\((\w*)/\2/v/' \ + --regex-c='/DEFINE_PER_CPU\(([^,]*,\s*)(\w*).*\)/\2/v/' \ + --regex-c='/DEFINE_PER_CPU_SHARED_ALIGNED\(([^,]*,\s*)(\w*).*\)/\2/v/' \ + --regex-c='/DECLARE_WAIT_QUEUE_HEAD\((\w*)/\1/v/' \ + --regex-c='/DECLARE_(TASKLET|WORK|DELAYED_WORK)\((\w*)/\2/v/' \ + --regex-c='/DEFINE_PCI_DEVICE_TABLE\((\w*)/\1/v/' all_kconfigs | xargs $1 -a \ --langdef=kconfig --language-force=kconfig \ diff --git a/security/integrity/ima/ima_queue.c b/security/integrity/ima/ima_queue.c index 55a6271bce7a..ff63fe00c195 100644 --- a/security/integrity/ima/ima_queue.c +++ b/security/integrity/ima/ima_queue.c @@ -45,12 +45,11 @@ static struct ima_queue_entry *ima_lookup_digest_entry(u8 *digest_value) { struct ima_queue_entry *qe, *ret = NULL; unsigned int key; - struct hlist_node *pos; int rc; key = ima_hash_key(digest_value); rcu_read_lock(); - hlist_for_each_entry_rcu(qe, pos, &ima_htable.queue[key], hnext) { + hlist_for_each_entry_rcu(qe, &ima_htable.queue[key], hnext) { rc = memcmp(qe->entry->digest, digest_value, IMA_DIGEST_SIZE); if (rc == 0) { ret = qe; diff --git a/security/keys/internal.h b/security/keys/internal.h index 8bbefc3b55d4..d4f1468b9b50 100644 --- a/security/keys/internal.h +++ b/security/keys/internal.h @@ -16,6 +16,8 @@ #include <linux/key-type.h> #include <linux/task_work.h> +struct iovec; + #ifdef __KDEBUG #define kenter(FMT, ...) \ printk(KERN_DEBUG "==> %s("FMT")\n", __func__, ##__VA_ARGS__) diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c index 4b5c948eb414..33cfd27b4de2 100644 --- a/security/keys/keyctl.c +++ b/security/keys/keyctl.c @@ -22,6 +22,7 @@ #include <linux/err.h> #include <linux/vmalloc.h> #include <linux/security.h> +#include <linux/uio.h> #include <asm/uaccess.h> #include "internal.h" diff --git a/security/selinux/avc.c b/security/selinux/avc.c index 4d3fab47e643..dad36a6ab45f 100644 --- a/security/selinux/avc.c +++ b/security/selinux/avc.c @@ -188,11 +188,9 @@ int avc_get_hash_stats(char *page) for (i = 0; i < AVC_CACHE_SLOTS; i++) { head = &avc_cache.slots[i]; if (!hlist_empty(head)) { - struct hlist_node *next; - slots_used++; chain_len = 0; - hlist_for_each_entry_rcu(node, next, head, list) + hlist_for_each_entry_rcu(node, head, list) chain_len++; if (chain_len > max_chain_len) max_chain_len = chain_len; @@ -241,7 +239,6 @@ static inline int avc_reclaim_node(void) int hvalue, try, ecx; unsigned long flags; struct hlist_head *head; - struct hlist_node *next; spinlock_t *lock; for (try = 0, ecx = 0; try < AVC_CACHE_SLOTS; try++) { @@ -253,7 +250,7 @@ static inline int avc_reclaim_node(void) continue; rcu_read_lock(); - hlist_for_each_entry(node, next, head, list) { + hlist_for_each_entry(node, head, list) { avc_node_delete(node); avc_cache_stats_incr(reclaims); ecx++; @@ -301,11 +298,10 @@ static inline struct avc_node *avc_search_node(u32 ssid, u32 tsid, u16 tclass) struct avc_node *node, *ret = NULL; int hvalue; struct hlist_head *head; - struct hlist_node *next; hvalue = avc_hash(ssid, tsid, tclass); head = &avc_cache.slots[hvalue]; - hlist_for_each_entry_rcu(node, next, head, list) { + hlist_for_each_entry_rcu(node, head, list) { if (ssid == node->ae.ssid && tclass == node->ae.tclass && tsid == node->ae.tsid) { @@ -394,7 +390,6 @@ static struct avc_node *avc_insert(u32 ssid, u32 tsid, u16 tclass, struct av_dec node = avc_alloc_node(); if (node) { struct hlist_head *head; - struct hlist_node *next; spinlock_t *lock; hvalue = avc_hash(ssid, tsid, tclass); @@ -404,7 +399,7 @@ static struct avc_node *avc_insert(u32 ssid, u32 tsid, u16 tclass, struct av_dec lock = &avc_cache.slots_lock[hvalue]; spin_lock_irqsave(lock, flag); - hlist_for_each_entry(pos, next, head, list) { + hlist_for_each_entry(pos, head, list) { if (pos->ae.ssid == ssid && pos->ae.tsid == tsid && pos->ae.tclass == tclass) { @@ -541,7 +536,6 @@ static int avc_update_node(u32 event, u32 perms, u32 ssid, u32 tsid, u16 tclass, unsigned long flag; struct avc_node *pos, *node, *orig = NULL; struct hlist_head *head; - struct hlist_node *next; spinlock_t *lock; node = avc_alloc_node(); @@ -558,7 +552,7 @@ static int avc_update_node(u32 event, u32 perms, u32 ssid, u32 tsid, u16 tclass, spin_lock_irqsave(lock, flag); - hlist_for_each_entry(pos, next, head, list) { + hlist_for_each_entry(pos, head, list) { if (ssid == pos->ae.ssid && tsid == pos->ae.tsid && tclass == pos->ae.tclass && @@ -614,7 +608,6 @@ out: static void avc_flush(void) { struct hlist_head *head; - struct hlist_node *next; struct avc_node *node; spinlock_t *lock; unsigned long flag; @@ -630,7 +623,7 @@ static void avc_flush(void) * prevent RCU grace periods from ending. */ rcu_read_lock(); - hlist_for_each_entry(node, next, head, list) + hlist_for_each_entry(node, head, list) avc_node_delete(node); rcu_read_unlock(); spin_unlock_irqrestore(lock, flag); diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 09b4286c65f9..857223c11278 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -25,7 +25,7 @@ #include <linux/slab.h> #include <linux/time.h> #include <linux/pm_qos.h> -#include <linux/uio.h> +#include <linux/aio.h> #include <linux/dma-mapping.h> #include <sound/core.h> #include <sound/control.h> diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index bc4ad7977438..c8be0fbc5145 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -314,7 +314,6 @@ static int perf_evlist__id_add_fd(struct perf_evlist *evlist, struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id) { struct hlist_head *head; - struct hlist_node *pos; struct perf_sample_id *sid; int hash; @@ -324,7 +323,7 @@ struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id) hash = hash_64(id, PERF_EVLIST__HLIST_BITS); head = &evlist->heads[hash]; - hlist_for_each_entry(sid, pos, head, node) + hlist_for_each_entry(sid, head, node) if (sid->id == id) return sid->evsel; diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 85baf11e2acd..c5aab2bb9fbd 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -1,4 +1,4 @@ -TARGETS = breakpoints kcmp mqueue vm cpu-hotplug memory-hotplug +TARGETS = breakpoints epoll kcmp mqueue vm cpu-hotplug memory-hotplug all: for TARGET in $(TARGETS); do \ diff --git a/tools/testing/selftests/epoll/Makefile b/tools/testing/selftests/epoll/Makefile new file mode 100644 index 000000000000..19806ed62f50 --- /dev/null +++ b/tools/testing/selftests/epoll/Makefile @@ -0,0 +1,11 @@ +# Makefile for epoll selftests + +all: test_epoll +%: %.c + gcc -pthread -g -o $@ $^ + +run_tests: all + ./test_epoll + +clean: + $(RM) test_epoll diff --git a/tools/testing/selftests/epoll/test_epoll.c b/tools/testing/selftests/epoll/test_epoll.c new file mode 100644 index 000000000000..1034ed4cc5b4 --- /dev/null +++ b/tools/testing/selftests/epoll/test_epoll.c @@ -0,0 +1,364 @@ +/* + * tools/testing/selftests/epoll/test_epoll.c + * + * Copyright 2012 Adobe Systems Incorporated + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * Paton J. Lewis <palewis@adobe.com> + * + */ + +#include <errno.h> +#include <fcntl.h> +#include <pthread.h> +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <sys/epoll.h> +#include <sys/socket.h> + +/* + * A pointer to an epoll_item_private structure will be stored in the epoll + * item's event structure so that we can get access to the epoll_item_private + * data after calling epoll_wait: + */ +struct epoll_item_private { + int index; /* Position of this struct within the epoll_items array. */ + int fd; + uint32_t events; + pthread_mutex_t mutex; /* Guards the following variables... */ + int stop; + int status; /* Stores any error encountered while handling item. */ + /* The following variable allows us to test whether we have encountered + a problem while attempting to cancel and delete the associated + event. When the test program exits, 'deleted' should be exactly + one. If it is greater than one, then the failed test reflects a real + world situation where we would have tried to access the epoll item's + private data after deleting it: */ + int deleted; +}; + +struct epoll_item_private *epoll_items; + +/* + * Delete the specified item from the epoll set. In a real-world secneario this + * is where we would free the associated data structure, but in this testing + * environment we retain the structure so that we can test for double-deletion: + */ +void delete_item(int index) +{ + __sync_fetch_and_add(&epoll_items[index].deleted, 1); +} + +/* + * A pointer to a read_thread_data structure will be passed as the argument to + * each read thread: + */ +struct read_thread_data { + int stop; + int status; /* Indicates any error encountered by the read thread. */ + int epoll_set; +}; + +/* + * The function executed by the read threads: + */ +void *read_thread_function(void *function_data) +{ + struct read_thread_data *thread_data = + (struct read_thread_data *)function_data; + struct epoll_event event_data; + struct epoll_item_private *item_data; + char socket_data; + + /* Handle events until we encounter an error or this thread's 'stop' + condition is set: */ + while (1) { + int result = epoll_wait(thread_data->epoll_set, + &event_data, + 1, /* Number of desired events */ + 1000); /* Timeout in ms */ + if (result < 0) { + /* Breakpoints signal all threads. Ignore that while + debugging: */ + if (errno == EINTR) + continue; + thread_data->status = errno; + return 0; + } else if (thread_data->stop) + return 0; + else if (result == 0) /* Timeout */ + continue; + + /* We need the mutex here because checking for the stop + condition and re-enabling the epoll item need to be done + together as one atomic operation when EPOLL_CTL_DISABLE is + available: */ + item_data = (struct epoll_item_private *)event_data.data.ptr; + pthread_mutex_lock(&item_data->mutex); + + /* Remove the item from the epoll set if we want to stop + handling that event: */ + if (item_data->stop) + delete_item(item_data->index); + else { + /* Clear the data that was written to the other end of + our non-blocking socket: */ + do { + if (read(item_data->fd, &socket_data, 1) < 1) { + if ((errno == EAGAIN) || + (errno == EWOULDBLOCK)) + break; + else + goto error_unlock; + } + } while (item_data->events & EPOLLET); + + /* The item was one-shot, so re-enable it: */ + event_data.events = item_data->events; + if (epoll_ctl(thread_data->epoll_set, + EPOLL_CTL_MOD, + item_data->fd, + &event_data) < 0) + goto error_unlock; + } + + pthread_mutex_unlock(&item_data->mutex); + } + +error_unlock: + thread_data->status = item_data->status = errno; + pthread_mutex_unlock(&item_data->mutex); + return 0; +} + +/* + * A pointer to a write_thread_data structure will be passed as the argument to + * the write thread: + */ +struct write_thread_data { + int stop; + int status; /* Indicates any error encountered by the write thread. */ + int n_fds; + int *fds; +}; + +/* + * The function executed by the write thread. It writes a single byte to each + * socket in turn until the stop condition for this thread is set. If writing to + * a socket would block (i.e. errno was EAGAIN), we leave that socket alone for + * the moment and just move on to the next socket in the list. We don't care + * about the order in which we deliver events to the epoll set. In fact we don't + * care about the data we're writing to the pipes at all; we just want to + * trigger epoll events: + */ +void *write_thread_function(void *function_data) +{ + const char data = 'X'; + int index; + struct write_thread_data *thread_data = + (struct write_thread_data *)function_data; + while (!thread_data->stop) + for (index = 0; + !thread_data->stop && (index < thread_data->n_fds); + ++index) + if ((write(thread_data->fds[index], &data, 1) < 1) && + (errno != EAGAIN) && + (errno != EWOULDBLOCK)) { + thread_data->status = errno; + return; + } +} + +/* + * Arguments are currently ignored: + */ +int main(int argc, char **argv) +{ + const int n_read_threads = 100; + const int n_epoll_items = 500; + int index; + int epoll_set = epoll_create1(0); + struct write_thread_data write_thread_data = { + 0, 0, n_epoll_items, malloc(n_epoll_items * sizeof(int)) + }; + struct read_thread_data *read_thread_data = + malloc(n_read_threads * sizeof(struct read_thread_data)); + pthread_t *read_threads = malloc(n_read_threads * sizeof(pthread_t)); + pthread_t write_thread; + int socket_pair[2]; + struct epoll_event event_data; + + printf("-----------------\n"); + printf("Runing test_epoll\n"); + printf("-----------------\n"); + + epoll_items = malloc(n_epoll_items * sizeof(struct epoll_item_private)); + + if (epoll_set < 0 || !epoll_items || write_thread_data.fds == NULL || + !read_thread_data || !read_threads) + goto error; + + if (sysconf(_SC_NPROCESSORS_ONLN) < 2) { + printf("Error: please run this test on a multi-core system.\n"); + goto error; + } + + /* Create the socket pairs and epoll items: */ + for (index = 0; index < n_epoll_items; ++index) { + if (socketpair(AF_UNIX, + SOCK_STREAM | SOCK_NONBLOCK, + 0, + socket_pair) < 0) + goto error; + write_thread_data.fds[index] = socket_pair[0]; + epoll_items[index].index = index; + epoll_items[index].fd = socket_pair[1]; + if (pthread_mutex_init(&epoll_items[index].mutex, NULL) != 0) + goto error; + /* We always use EPOLLONESHOT because this test is currently + structured to demonstrate the need for EPOLL_CTL_DISABLE, + which only produces useful information in the EPOLLONESHOT + case (without EPOLLONESHOT, calling epoll_ctl with + EPOLL_CTL_DISABLE will never return EBUSY). If support for + testing events without EPOLLONESHOT is desired, it should + probably be implemented in a separate unit test. */ + epoll_items[index].events = EPOLLIN | EPOLLONESHOT; + if (index < n_epoll_items / 2) + epoll_items[index].events |= EPOLLET; + epoll_items[index].stop = 0; + epoll_items[index].status = 0; + epoll_items[index].deleted = 0; + event_data.events = epoll_items[index].events; + event_data.data.ptr = &epoll_items[index]; + if (epoll_ctl(epoll_set, + EPOLL_CTL_ADD, + epoll_items[index].fd, + &event_data) < 0) + goto error; + } + +#ifdef EPOLL_CTL_DISABLE + /* Test to make sure that using EPOLL_CTL_DISABLE without EPOLLONESHOT + returns a clear error: */ + if (socketpair(AF_UNIX, + SOCK_STREAM | SOCK_NONBLOCK, + 0, + socket_pair) < 0) + goto error; + event_data.events = EPOLLIN; + event_data.data.ptr = NULL; + if (epoll_ctl(epoll_set, EPOLL_CTL_ADD, + socket_pair[1], &event_data) < 0) + goto error; + if ((epoll_ctl(epoll_set, EPOLL_CTL_DISABLE, + socket_pair[1], NULL) == 0) || (errno != EINVAL)) + goto error; + if (epoll_ctl(epoll_set, EPOLL_CTL_DEL, socket_pair[1], NULL) != 0) + goto error; +#endif + + /* Create and start the read threads: */ + for (index = 0; index < n_read_threads; ++index) { + read_thread_data[index].stop = 0; + read_thread_data[index].status = 0; + read_thread_data[index].epoll_set = epoll_set; + if (pthread_create(&read_threads[index], + NULL, + read_thread_function, + &read_thread_data[index]) != 0) + goto error; + } + + if (pthread_create(&write_thread, + NULL, + write_thread_function, + &write_thread_data) != 0) + goto error; + + /* Cancel all event pollers: */ +#ifdef EPOLL_CTL_DISABLE + for (index = 0; index < n_epoll_items; ++index) { + pthread_mutex_lock(&epoll_items[index].mutex); + ++epoll_items[index].stop; + if (epoll_ctl(epoll_set, + EPOLL_CTL_DISABLE, + epoll_items[index].fd, + NULL) == 0) + delete_item(index); + else if (errno != EBUSY) { + pthread_mutex_unlock(&epoll_items[index].mutex); + goto error; + } + /* EBUSY means events were being handled; allow the other thread + to delete the item. */ + pthread_mutex_unlock(&epoll_items[index].mutex); + } +#else + for (index = 0; index < n_epoll_items; ++index) { + pthread_mutex_lock(&epoll_items[index].mutex); + ++epoll_items[index].stop; + pthread_mutex_unlock(&epoll_items[index].mutex); + /* Wait in case a thread running read_thread_function is + currently executing code between epoll_wait and + pthread_mutex_lock with this item. Note that a longer delay + would make double-deletion less likely (at the expense of + performance), but there is no guarantee that any delay would + ever be sufficient. Note also that we delete all event + pollers at once for testing purposes, but in a real-world + environment we are likely to want to be able to cancel event + pollers at arbitrary times. Therefore we can't improve this + situation by just splitting this loop into two loops + (i.e. signal 'stop' for all items, sleep, and then delete all + items). We also can't fix the problem via EPOLL_CTL_DEL + because that command can't prevent the case where some other + thread is executing read_thread_function within the region + mentioned above: */ + usleep(1); + pthread_mutex_lock(&epoll_items[index].mutex); + if (!epoll_items[index].deleted) + delete_item(index); + pthread_mutex_unlock(&epoll_items[index].mutex); + } +#endif + + /* Shut down the read threads: */ + for (index = 0; index < n_read_threads; ++index) + __sync_fetch_and_add(&read_thread_data[index].stop, 1); + for (index = 0; index < n_read_threads; ++index) { + if (pthread_join(read_threads[index], NULL) != 0) + goto error; + if (read_thread_data[index].status) + goto error; + } + + /* Shut down the write thread: */ + __sync_fetch_and_add(&write_thread_data.stop, 1); + if ((pthread_join(write_thread, NULL) != 0) || write_thread_data.status) + goto error; + + /* Check for final error conditions: */ + for (index = 0; index < n_epoll_items; ++index) { + if (epoll_items[index].status != 0) + goto error; + if (pthread_mutex_destroy(&epoll_items[index].mutex) < 0) + goto error; + } + for (index = 0; index < n_epoll_items; ++index) + if (epoll_items[index].deleted != 1) { + printf("Error: item data deleted %1d times.\n", + epoll_items[index].deleted); + goto error; + } + + printf("[PASS]\n"); + return 0; + + error: + printf("[FAIL]\n"); + return errno; +} diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index b6eea5cc7b34..adb17f266b28 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -268,14 +268,13 @@ static void irqfd_update(struct kvm *kvm, struct _irqfd *irqfd, struct kvm_irq_routing_table *irq_rt) { struct kvm_kernel_irq_routing_entry *e; - struct hlist_node *n; if (irqfd->gsi >= irq_rt->nr_rt_entries) { rcu_assign_pointer(irqfd->irq_entry, NULL); return; } - hlist_for_each_entry(e, n, &irq_rt->map[irqfd->gsi], link) { + hlist_for_each_entry(e, &irq_rt->map[irqfd->gsi], link) { /* Only fast-path MSI. */ if (e->type == KVM_IRQ_ROUTING_MSI) rcu_assign_pointer(irqfd->irq_entry, e); diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index ff6d40e2c06d..e9073cf4d040 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -173,7 +173,6 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level) struct kvm_kernel_irq_routing_entry *e, irq_set[KVM_NR_IRQCHIPS]; int ret = -1, i = 0; struct kvm_irq_routing_table *irq_rt; - struct hlist_node *n; trace_kvm_set_irq(irq, level, irq_source_id); @@ -184,7 +183,7 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level) rcu_read_lock(); irq_rt = rcu_dereference(kvm->irq_routing); if (irq < irq_rt->nr_rt_entries) - hlist_for_each_entry(e, n, &irq_rt->map[irq], link) + hlist_for_each_entry(e, &irq_rt->map[irq], link) irq_set[i++] = *e; rcu_read_unlock(); @@ -212,7 +211,6 @@ int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level) struct kvm_kernel_irq_routing_entry *e; int ret = -EINVAL; struct kvm_irq_routing_table *irq_rt; - struct hlist_node *n; trace_kvm_set_irq(irq, level, irq_source_id); @@ -227,7 +225,7 @@ int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level) rcu_read_lock(); irq_rt = rcu_dereference(kvm->irq_routing); if (irq < irq_rt->nr_rt_entries) - hlist_for_each_entry(e, n, &irq_rt->map[irq], link) { + hlist_for_each_entry(e, &irq_rt->map[irq], link) { if (likely(e->type == KVM_IRQ_ROUTING_MSI)) ret = kvm_set_msi_inatomic(e, kvm); else @@ -241,13 +239,12 @@ int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level) bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin) { struct kvm_irq_ack_notifier *kian; - struct hlist_node *n; int gsi; rcu_read_lock(); gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin]; if (gsi != -1) - hlist_for_each_entry_rcu(kian, n, &kvm->irq_ack_notifier_list, + hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list, link) if (kian->gsi == gsi) { rcu_read_unlock(); @@ -263,7 +260,6 @@ EXPORT_SYMBOL_GPL(kvm_irq_has_notifier); void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin) { struct kvm_irq_ack_notifier *kian; - struct hlist_node *n; int gsi; trace_kvm_ack_irq(irqchip, pin); @@ -271,7 +267,7 @@ void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin) rcu_read_lock(); gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin]; if (gsi != -1) - hlist_for_each_entry_rcu(kian, n, &kvm->irq_ack_notifier_list, + hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list, link) if (kian->gsi == gsi) kian->irq_acked(kian); @@ -369,13 +365,12 @@ void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin, bool mask) { struct kvm_irq_mask_notifier *kimn; - struct hlist_node *n; int gsi; rcu_read_lock(); gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin]; if (gsi != -1) - hlist_for_each_entry_rcu(kimn, n, &kvm->mask_notifier_list, link) + hlist_for_each_entry_rcu(kimn, &kvm->mask_notifier_list, link) if (kimn->irq == gsi) kimn->func(kimn, mask); rcu_read_unlock(); @@ -396,13 +391,12 @@ static int setup_routing_entry(struct kvm_irq_routing_table *rt, int delta; unsigned max_pin; struct kvm_kernel_irq_routing_entry *ei; - struct hlist_node *n; /* * Do not allow GSI to be mapped to the same irqchip more than once. * Allow only one to one mapping between GSI and MSI. */ - hlist_for_each_entry(ei, n, &rt->map[ue->gsi], link) + hlist_for_each_entry(ei, &rt->map[ue->gsi], link) if (ei->type == KVM_IRQ_ROUTING_MSI || ue->type == KVM_IRQ_ROUTING_MSI || ue->u.irqchip.irqchip == ei->irqchip.irqchip) |