diff options
154 files changed, 6874 insertions, 2489 deletions
diff --git a/Documentation/ABI/testing/sysfs-fs-ext4 b/Documentation/ABI/testing/sysfs-fs-ext4 index 5fb709997d96..f22ac0872ae8 100644 --- a/Documentation/ABI/testing/sysfs-fs-ext4 +++ b/Documentation/ABI/testing/sysfs-fs-ext4 @@ -48,7 +48,7 @@ Description: will have its blocks allocated out of its own unique preallocation pool. -What: /sys/fs/ext4/<disk>/inode_readahead +What: /sys/fs/ext4/<disk>/inode_readahead_blks Date: March 2008 Contact: "Theodore Ts'o" <tytso@mit.edu> Description: @@ -85,7 +85,14 @@ Date: June 2008 Contact: "Theodore Ts'o" <tytso@mit.edu> Description: Tuning parameter which (if non-zero) controls the goal - inode used by the inode allocator in p0reference to - all other allocation hueristics. This is intended for + inode used by the inode allocator in preference to + all other allocation heuristics. This is intended for debugging use only, and should be 0 on production systems. + +What: /sys/fs/ext4/<disk>/max_writeback_mb_bump +Date: September 2009 +Contact: "Theodore Ts'o" <tytso@mit.edu> +Description: + The maximum number of megabytes the writeback code will + try to write out before move on to another inode. diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt index 6ab9442d7eeb..6b050464a90d 100644 --- a/Documentation/filesystems/ext4.txt +++ b/Documentation/filesystems/ext4.txt @@ -367,12 +367,47 @@ init_itable=n The lazy itable init code will wait n times the minimizes the impact on the systme performance while file system's inode table is being initialized. -discard Controls whether ext4 should issue discard/TRIM +discard Controls whether ext4 should issue discard/TRIM nodiscard(*) commands to the underlying block device when blocks are freed. This is useful for SSD devices and sparse/thinly-provisioned LUNs, but it is off by default until sufficient testing has been done. +nouid32 Disables 32-bit UIDs and GIDs. This is for + interoperability with older kernels which only + store and expect 16-bit values. + +resize Allows to resize filesystem to the end of the last + existing block group, further resize has to be done + with resize2fs either online, or offline. It can be + used only with conjunction with remount. + +block_validity This options allows to enables/disables the in-kernel +noblock_validity facility for tracking filesystem metadata blocks + within internal data structures. This allows multi- + block allocator and other routines to quickly locate + extents which might overlap with filesystem metadata + blocks. This option is intended for debugging + purposes and since it negatively affects the + performance, it is off by default. + +dioread_lock Controls whether or not ext4 should use the DIO read +dioread_nolock locking. If the dioread_nolock option is specified + ext4 will allocate uninitialized extent before buffer + write and convert the extent to initialized after IO + completes. This approach allows ext4 code to avoid + using inode mutex, which improves scalability on high + speed storages. However this does not work with nobh + option and the mount will fail. Nor does it work with + data journaling and dioread_nolock option will be + ignored with kernel warning. Note that dioread_nolock + code path is only used for extent-based files. + Because of the restrictions this options comprises + it is off by default (e.g. dioread_lock). + +i_version Enable 64-bit inode version support. This option is + off by default. + Data Mode ========= There are 3 different data modes: @@ -400,6 +435,176 @@ needs to be read from and written to disk at the same time where it outperforms all others modes. Currently ext4 does not have delayed allocation support if this data journalling mode is selected. +/proc entries +============= + +Information about mounted ext4 file systems can be found in +/proc/fs/ext4. Each mounted filesystem will have a directory in +/proc/fs/ext4 based on its device name (i.e., /proc/fs/ext4/hdc or +/proc/fs/ext4/dm-0). The files in each per-device directory are shown +in table below. + +Files in /proc/fs/ext4/<devname> +.............................................................................. + File Content + mb_groups details of multiblock allocator buddy cache of free blocks +.............................................................................. + +/sys entries +============ + +Information about mounted ext4 file systems can be found in +/sys/fs/ext4. Each mounted filesystem will have a directory in +/sys/fs/ext4 based on its device name (i.e., /sys/fs/ext4/hdc or +/sys/fs/ext4/dm-0). The files in each per-device directory are shown +in table below. + +Files in /sys/fs/ext4/<devname> +(see also Documentation/ABI/testing/sysfs-fs-ext4) +.............................................................................. + File Content + + delayed_allocation_blocks This file is read-only and shows the number of + blocks that are dirty in the page cache, but + which do not have their location in the + filesystem allocated yet. + + inode_goal Tuning parameter which (if non-zero) controls + the goal inode used by the inode allocator in + preference to all other allocation heuristics. + This is intended for debugging use only, and + should be 0 on production systems. + + inode_readahead_blks Tuning parameter which controls the maximum + number of inode table blocks that ext4's inode + table readahead algorithm will pre-read into + the buffer cache + + lifetime_write_kbytes This file is read-only and shows the number of + kilobytes of data that have been written to this + filesystem since it was created. + + max_writeback_mb_bump The maximum number of megabytes the writeback + code will try to write out before move on to + another inode. + + mb_group_prealloc The multiblock allocator will round up allocation + requests to a multiple of this tuning parameter if + the stripe size is not set in the ext4 superblock + + mb_max_to_scan The maximum number of extents the multiblock + allocator will search to find the best extent + + mb_min_to_scan The minimum number of extents the multiblock + allocator will search to find the best extent + + mb_order2_req Tuning parameter which controls the minimum size + for requests (as a power of 2) where the buddy + cache is used + + mb_stats Controls whether the multiblock allocator should + collect statistics, which are shown during the + unmount. 1 means to collect statistics, 0 means + not to collect statistics + + mb_stream_req Files which have fewer blocks than this tunable + parameter will have their blocks allocated out + of a block group specific preallocation pool, so + that small files are packed closely together. + Each large file will have its blocks allocated + out of its own unique preallocation pool. + + session_write_kbytes This file is read-only and shows the number of + kilobytes of data that have been written to this + filesystem since it was mounted. +.............................................................................. + +Ioctls +====== + +There is some Ext4 specific functionality which can be accessed by applications +through the system call interfaces. The list of all Ext4 specific ioctls are +shown in the table below. + +Table of Ext4 specific ioctls +.............................................................................. + Ioctl Description + EXT4_IOC_GETFLAGS Get additional attributes associated with inode. + The ioctl argument is an integer bitfield, with + bit values described in ext4.h. This ioctl is an + alias for FS_IOC_GETFLAGS. + + EXT4_IOC_SETFLAGS Set additional attributes associated with inode. + The ioctl argument is an integer bitfield, with + bit values described in ext4.h. This ioctl is an + alias for FS_IOC_SETFLAGS. + + EXT4_IOC_GETVERSION + EXT4_IOC_GETVERSION_OLD + Get the inode i_generation number stored for + each inode. The i_generation number is normally + changed only when new inode is created and it is + particularly useful for network filesystems. The + '_OLD' version of this ioctl is an alias for + FS_IOC_GETVERSION. + + EXT4_IOC_SETVERSION + EXT4_IOC_SETVERSION_OLD + Set the inode i_generation number stored for + each inode. The '_OLD' version of this ioctl + is an alias for FS_IOC_SETVERSION. + + EXT4_IOC_GROUP_EXTEND This ioctl has the same purpose as the resize + mount option. It allows to resize filesystem + to the end of the last existing block group, + further resize has to be done with resize2fs, + either online, or offline. The argument points + to the unsigned logn number representing the + filesystem new block count. + + EXT4_IOC_MOVE_EXT Move the block extents from orig_fd (the one + this ioctl is pointing to) to the donor_fd (the + one specified in move_extent structure passed + as an argument to this ioctl). Then, exchange + inode metadata between orig_fd and donor_fd. + This is especially useful for online + defragmentation, because the allocator has the + opportunity to allocate moved blocks better, + ideally into one contiguous extent. + + EXT4_IOC_GROUP_ADD Add a new group descriptor to an existing or + new group descriptor block. The new group + descriptor is described by ext4_new_group_input + structure, which is passed as an argument to + this ioctl. This is especially useful in + conjunction with EXT4_IOC_GROUP_EXTEND, + which allows online resize of the filesystem + to the end of the last existing block group. + Those two ioctls combined is used in userspace + online resize tool (e.g. resize2fs). + + EXT4_IOC_MIGRATE This ioctl operates on the filesystem itself. + It converts (migrates) ext3 indirect block mapped + inode to ext4 extent mapped inode by walking + through indirect block mapping of the original + inode and converting contiguous block ranges + into ext4 extents of the temporary inode. Then, + inodes are swapped. This ioctl might help, when + migrating from ext3 to ext4 filesystem, however + suggestion is to create fresh ext4 filesystem + and copy data from the backup. Note, that + filesystem has to support extents for this ioctl + to work. + + EXT4_IOC_ALLOC_DA_BLKS Force all of the delay allocated blocks to be + allocated to preserve application-expected ext3 + behaviour. Note that this will also start + triggering a write of the data blocks, but this + behaviour may change in the future as it is + not necessary and has been done this way only + for sake of simplicity. +.............................................................................. + References ========== diff --git a/MAINTAINERS b/MAINTAINERS index 749f9cd38089..4fb9017b4413 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5291,6 +5291,11 @@ S: Maintained F: drivers/mtd/nand/r852.c F: drivers/mtd/nand/r852.h +RICOH R5C592 MEMORYSTICK DRIVER +M: Maxim Levitsky <maximlevitsky@gmail.com> +S: Maintained +F: drivers/memstick/host/r592.* + RISCOM8 DRIVER S: Orphan F: Documentation/serial/riscom8.txt diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 9905e2e85de4..83aa5fb8e8f1 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -22,6 +22,7 @@ config MIPS select HAVE_DMA_API_DEBUG select HAVE_GENERIC_HARDIRQS select GENERIC_IRQ_PROBE + select GENERIC_IRQ_SHOW select HAVE_ARCH_JUMP_LABEL menu "Machine selection" @@ -862,6 +863,9 @@ config GPIO_TXX9 config CFE bool +config ARCH_DMA_ADDR_T_64BIT + def_bool (HIGHMEM && 64BIT_PHYS_ADDR) || 64BIT + config DMA_COHERENT bool diff --git a/arch/mips/alchemy/common/irq.c b/arch/mips/alchemy/common/irq.c index 9f78ada83b3c..55dd7c888517 100644 --- a/arch/mips/alchemy/common/irq.c +++ b/arch/mips/alchemy/common/irq.c @@ -39,7 +39,7 @@ #include <asm/mach-pb1x00/pb1000.h> #endif -static int au1x_ic_settype(unsigned int irq, unsigned int flow_type); +static int au1x_ic_settype(struct irq_data *d, unsigned int flow_type); /* NOTE on interrupt priorities: The original writers of this code said: * @@ -218,17 +218,17 @@ struct au1xxx_irqmap au1200_irqmap[] __initdata = { }; -static void au1x_ic0_unmask(unsigned int irq_nr) +static void au1x_ic0_unmask(struct irq_data *d) { - unsigned int bit = irq_nr - AU1000_INTC0_INT_BASE; + unsigned int bit = d->irq - AU1000_INTC0_INT_BASE; au_writel(1 << bit, IC0_MASKSET); au_writel(1 << bit, IC0_WAKESET); au_sync(); } -static void au1x_ic1_unmask(unsigned int irq_nr) +static void au1x_ic1_unmask(struct irq_data *d) { - unsigned int bit = irq_nr - AU1000_INTC1_INT_BASE; + unsigned int bit = d->irq - AU1000_INTC1_INT_BASE; au_writel(1 << bit, IC1_MASKSET); au_writel(1 << bit, IC1_WAKESET); @@ -236,31 +236,31 @@ static void au1x_ic1_unmask(unsigned int irq_nr) * nowhere in the current kernel sources is it disabled. --mlau */ #if defined(CONFIG_MIPS_PB1000) - if (irq_nr == AU1000_GPIO15_INT) + if (d->irq == AU1000_GPIO15_INT) au_writel(0x4000, PB1000_MDR); /* enable int */ #endif au_sync(); } -static void au1x_ic0_mask(unsigned int irq_nr) +static void au1x_ic0_mask(struct irq_data *d) { - unsigned int bit = irq_nr - AU1000_INTC0_INT_BASE; + unsigned int bit = d->irq - AU1000_INTC0_INT_BASE; au_writel(1 << bit, IC0_MASKCLR); au_writel(1 << bit, IC0_WAKECLR); au_sync(); } -static void au1x_ic1_mask(unsigned int irq_nr) +static void au1x_ic1_mask(struct irq_data *d) { - unsigned int bit = irq_nr - AU1000_INTC1_INT_BASE; + unsigned int bit = d->irq - AU1000_INTC1_INT_BASE; au_writel(1 << bit, IC1_MASKCLR); au_writel(1 << bit, IC1_WAKECLR); au_sync(); } -static void au1x_ic0_ack(unsigned int irq_nr) +static void au1x_ic0_ack(struct irq_data *d) { - unsigned int bit = irq_nr - AU1000_INTC0_INT_BASE; + unsigned int bit = d->irq - AU1000_INTC0_INT_BASE; /* * This may assume that we don't get interrupts from @@ -271,9 +271,9 @@ static void au1x_ic0_ack(unsigned int irq_nr) au_sync(); } -static void au1x_ic1_ack(unsigned int irq_nr) +static void au1x_ic1_ack(struct irq_data *d) { - unsigned int bit = irq_nr - AU1000_INTC1_INT_BASE; + unsigned int bit = d->irq - AU1000_INTC1_INT_BASE; /* * This may assume that we don't get interrupts from @@ -284,9 +284,9 @@ static void au1x_ic1_ack(unsigned int irq_nr) au_sync(); } -static void au1x_ic0_maskack(unsigned int irq_nr) +static void au1x_ic0_maskack(struct irq_data *d) { - unsigned int bit = irq_nr - AU1000_INTC0_INT_BASE; + unsigned int bit = d->irq - AU1000_INTC0_INT_BASE; au_writel(1 << bit, IC0_WAKECLR); au_writel(1 << bit, IC0_MASKCLR); @@ -295,9 +295,9 @@ static void au1x_ic0_maskack(unsigned int irq_nr) au_sync(); } -static void au1x_ic1_maskack(unsigned int irq_nr) +static void au1x_ic1_maskack(struct irq_data *d) { - unsigned int bit = irq_nr - AU1000_INTC1_INT_BASE; + unsigned int bit = d->irq - AU1000_INTC1_INT_BASE; au_writel(1 << bit, IC1_WAKECLR); au_writel(1 << bit, IC1_MASKCLR); @@ -306,9 +306,9 @@ static void au1x_ic1_maskack(unsigned int irq_nr) au_sync(); } -static int au1x_ic1_setwake(unsigned int irq, unsigned int on) +static int au1x_ic1_setwake(struct irq_data *d, unsigned int on) { - int bit = irq - AU1000_INTC1_INT_BASE; + int bit = d->irq - AU1000_INTC1_INT_BASE; unsigned long wakemsk, flags; /* only GPIO 0-7 can act as wakeup source. Fortunately these @@ -336,28 +336,30 @@ static int au1x_ic1_setwake(unsigned int irq, unsigned int on) */ static struct irq_chip au1x_ic0_chip = { .name = "Alchemy-IC0", - .ack = au1x_ic0_ack, - .mask = au1x_ic0_mask, - .mask_ack = au1x_ic0_maskack, - .unmask = au1x_ic0_unmask, - .set_type = au1x_ic_settype, + .irq_ack = au1x_ic0_ack, + .irq_mask = au1x_ic0_mask, + .irq_mask_ack = au1x_ic0_maskack, + .irq_unmask = au1x_ic0_unmask, + .irq_set_type = au1x_ic_settype, }; static struct irq_chip au1x_ic1_chip = { .name = "Alchemy-IC1", - .ack = au1x_ic1_ack, - .mask = au1x_ic1_mask, - .mask_ack = au1x_ic1_maskack, - .unmask = au1x_ic1_unmask, - .set_type = au1x_ic_settype, - .set_wake = au1x_ic1_setwake, + .irq_ack = au1x_ic1_ack, + .irq_mask = au1x_ic1_mask, + .irq_mask_ack = au1x_ic1_maskack, + .irq_unmask = au1x_ic1_unmask, + .irq_set_type = au1x_ic_settype, + .irq_set_wake = au1x_ic1_setwake, }; -static int au1x_ic_settype(unsigned int irq, unsigned int flow_type) +static int au1x_ic_settype(struct irq_data *d, unsigned int flow_type) { struct irq_chip *chip; unsigned long icr[6]; - unsigned int bit, ic; + unsigned int bit, ic, irq = d->irq; + irq_flow_handler_t handler = NULL; + unsigned char *name = NULL; int ret; if (irq >= AU1000_INTC1_INT_BASE) { @@ -387,47 +389,47 @@ static int au1x_ic_settype(unsigned int irq, unsigned int flow_type) au_writel(1 << bit, icr[5]); au_writel(1 << bit, icr[4]); au_writel(1 << bit, icr[0]); - set_irq_chip_and_handler_name(irq, chip, - handle_edge_irq, "riseedge"); + handler = handle_edge_irq; + name = "riseedge"; break; case IRQ_TYPE_EDGE_FALLING: /* 0:1:0 */ au_writel(1 << bit, icr[5]); au_writel(1 << bit, icr[1]); au_writel(1 << bit, icr[3]); - set_irq_chip_and_handler_name(irq, chip, - handle_edge_irq, "falledge"); + handler = handle_edge_irq; + name = "falledge"; break; case IRQ_TYPE_EDGE_BOTH: /* 0:1:1 */ au_writel(1 << bit, icr[5]); au_writel(1 << bit, icr[1]); au_writel(1 << bit, icr[0]); - set_irq_chip_and_handler_name(irq, chip, - handle_edge_irq, "bothedge"); + handler = handle_edge_irq; + name = "bothedge"; break; case IRQ_TYPE_LEVEL_HIGH: /* 1:0:1 */ au_writel(1 << bit, icr[2]); au_writel(1 << bit, icr[4]); au_writel(1 << bit, icr[0]); - set_irq_chip_and_handler_name(irq, chip, - handle_level_irq, "hilevel"); + handler = handle_level_irq; + name = "hilevel"; break; case IRQ_TYPE_LEVEL_LOW: /* 1:1:0 */ au_writel(1 << bit, icr[2]); au_writel(1 << bit, icr[1]); au_writel(1 << bit, icr[3]); - set_irq_chip_and_handler_name(irq, chip, - handle_level_irq, "lowlevel"); + handler = handle_level_irq; + name = "lowlevel"; break; case IRQ_TYPE_NONE: /* 0:0:0 */ au_writel(1 << bit, icr[5]); au_writel(1 << bit, icr[4]); au_writel(1 << bit, icr[3]); - /* set at least chip so we can call set_irq_type() on it */ - set_irq_chip(irq, chip); break; default: ret = -EINVAL; } + __irq_set_chip_handler_name_locked(d->irq, chip, handler, name); + au_sync(); return ret; @@ -504,11 +506,11 @@ static void __init au1000_init_irq(struct au1xxx_irqmap *map) */ for (i = AU1000_INTC0_INT_BASE; (i < AU1000_INTC0_INT_BASE + 32); i++) - au1x_ic_settype(i, IRQ_TYPE_NONE); + au1x_ic_settype(irq_get_irq_data(i), IRQ_TYPE_NONE); for (i = AU1000_INTC1_INT_BASE; (i < AU1000_INTC1_INT_BASE + 32); i++) - au1x_ic_settype(i, IRQ_TYPE_NONE); + au1x_ic_settype(irq_get_irq_data(i), IRQ_TYPE_NONE); /* * Initialize IC0, which is fixed per processor. @@ -526,7 +528,7 @@ static void __init au1000_init_irq(struct au1xxx_irqmap *map) au_writel(1 << bit, IC0_ASSIGNSET); } - au1x_ic_settype(irq_nr, map->im_type); + au1x_ic_settype(irq_get_irq_data(irq_nr), map->im_type); ++map; } diff --git a/arch/mips/alchemy/devboards/bcsr.c b/arch/mips/alchemy/devboards/bcsr.c index c52af8821da0..f91c43a7d5dc 100644 --- a/arch/mips/alchemy/devboards/bcsr.c +++ b/arch/mips/alchemy/devboards/bcsr.c @@ -97,26 +97,26 @@ static void bcsr_csc_handler(unsigned int irq, struct irq_desc *d) * CPLD generates tons of spurious interrupts (at least on my DB1200). * -- mlau */ -static void bcsr_irq_mask(unsigned int irq_nr) +static void bcsr_irq_mask(struct irq_data *d) { - unsigned short v = 1 << (irq_nr - bcsr_csc_base); + unsigned short v = 1 << (d->irq - bcsr_csc_base); __raw_writew(v, bcsr_virt + BCSR_REG_INTCLR); __raw_writew(v, bcsr_virt + BCSR_REG_MASKCLR); wmb(); } -static void bcsr_irq_maskack(unsigned int irq_nr) +static void bcsr_irq_maskack(struct irq_data *d) { - unsigned short v = 1 << (irq_nr - bcsr_csc_base); + unsigned short v = 1 << (d->irq - bcsr_csc_base); __raw_writew(v, bcsr_virt + BCSR_REG_INTCLR); __raw_writew(v, bcsr_virt + BCSR_REG_MASKCLR); __raw_writew(v, bcsr_virt + BCSR_REG_INTSTAT); /* ack */ wmb(); } -static void bcsr_irq_unmask(unsigned int irq_nr) +static void bcsr_irq_unmask(struct irq_data *d) { - unsigned short v = 1 << (irq_nr - bcsr_csc_base); + unsigned short v = 1 << (d->irq - bcsr_csc_base); __raw_writew(v, bcsr_virt + BCSR_REG_INTSET); __raw_writew(v, bcsr_virt + BCSR_REG_MASKSET); wmb(); @@ -124,9 +124,9 @@ static void bcsr_irq_unmask(unsigned int irq_nr) static struct irq_chip bcsr_irq_type = { .name = "CPLD", - .mask = bcsr_irq_mask, - .mask_ack = bcsr_irq_maskack, - .unmask = bcsr_irq_unmask, + .irq_mask = bcsr_irq_mask, + .irq_mask_ack = bcsr_irq_maskack, + .irq_unmask = bcsr_irq_unmask, }; void __init bcsr_init_irq(int csc_start, int csc_end, int hook_irq) diff --git a/arch/mips/ar7/irq.c b/arch/mips/ar7/irq.c index 4ec2642c568f..a6484b60642f 100644 --- a/arch/mips/ar7/irq.c +++ b/arch/mips/ar7/irq.c @@ -49,51 +49,51 @@ static int ar7_irq_base; -static void ar7_unmask_irq(unsigned int irq) +static void ar7_unmask_irq(struct irq_data *d) { - writel(1 << ((irq - ar7_irq_base) % 32), - REG(ESR_OFFSET(irq - ar7_irq_base))); + writel(1 << ((d->irq - ar7_irq_base) % 32), + REG(ESR_OFFSET(d->irq - ar7_irq_base))); } -static void ar7_mask_irq(unsigned int irq) +static void ar7_mask_irq(struct irq_data *d) { - writel(1 << ((irq - ar7_irq_base) % 32), - REG(ECR_OFFSET(irq - ar7_irq_base))); + writel(1 << ((d->irq - ar7_irq_base) % 32), + REG(ECR_OFFSET(d->irq - ar7_irq_base))); } -static void ar7_ack_irq(unsigned int irq) +static void ar7_ack_irq(struct irq_data *d) { - writel(1 << ((irq - ar7_irq_base) % 32), - REG(CR_OFFSET(irq - ar7_irq_base))); + writel(1 << ((d->irq - ar7_irq_base) % 32), + REG(CR_OFFSET(d->irq - ar7_irq_base))); } -static void ar7_unmask_sec_irq(unsigned int irq) +static void ar7_unmask_sec_irq(struct irq_data *d) { - writel(1 << (irq - ar7_irq_base - 40), REG(SEC_ESR_OFFSET)); + writel(1 << (d->irq - ar7_irq_base - 40), REG(SEC_ESR_OFFSET)); } -static void ar7_mask_sec_irq(unsigned int irq) +static void ar7_mask_sec_irq(struct irq_data *d) { - writel(1 << (irq - ar7_irq_base - 40), REG(SEC_ECR_OFFSET)); + writel(1 << (d->irq - ar7_irq_base - 40), REG(SEC_ECR_OFFSET)); } -static void ar7_ack_sec_irq(unsigned int irq) +static void ar7_ack_sec_irq(struct irq_data *d) { - writel(1 << (irq - ar7_irq_base - 40), REG(SEC_CR_OFFSET)); + writel(1 << (d->irq - ar7_irq_base - 40), REG(SEC_CR_OFFSET)); } static struct irq_chip ar7_irq_type = { .name = "AR7", - .unmask = ar7_unmask_irq, - .mask = ar7_mask_irq, - .ack = ar7_ack_irq + .irq_unmask = ar7_unmask_irq, + .irq_mask = ar7_mask_irq, + .irq_ack = ar7_ack_irq }; static struct irq_chip ar7_sec_irq_type = { .name = "AR7", - .unmask = ar7_unmask_sec_irq, - .mask = ar7_mask_sec_irq, - .ack = ar7_ack_sec_irq, + .irq_unmask = ar7_unmask_sec_irq, + .irq_mask = ar7_mask_sec_irq, + .irq_ack = ar7_ack_sec_irq, }; static struct irqaction ar7_cascade_action = { diff --git a/arch/mips/ath79/irq.c b/arch/mips/ath79/irq.c index 1bf7f719ba53..7c02bc948a31 100644 --- a/arch/mips/ath79/irq.c +++ b/arch/mips/ath79/irq.c @@ -62,13 +62,12 @@ static void ath79_misc_irq_handler(unsigned int irq, struct irq_desc *desc) spurious_interrupt(); } -static void ar71xx_misc_irq_unmask(unsigned int irq) +static void ar71xx_misc_irq_unmask(struct irq_data *d) { + unsigned int irq = d->irq - ATH79_MISC_IRQ_BASE; void __iomem *base = ath79_reset_base; u32 t; - irq -= ATH79_MISC_IRQ_BASE; - t = __raw_readl(base + AR71XX_RESET_REG_MISC_INT_ENABLE); __raw_writel(t | (1 << irq), base + AR71XX_RESET_REG_MISC_INT_ENABLE); @@ -76,13 +75,12 @@ static void ar71xx_misc_irq_unmask(unsigned int irq) __raw_readl(base + AR71XX_RESET_REG_MISC_INT_ENABLE); } -static void ar71xx_misc_irq_mask(unsigned int irq) +static void ar71xx_misc_irq_mask(struct irq_data *d) { + unsigned int irq = d->irq - ATH79_MISC_IRQ_BASE; void __iomem *base = ath79_reset_base; u32 t; - irq -= ATH79_MISC_IRQ_BASE; - t = __raw_readl(base + AR71XX_RESET_REG_MISC_INT_ENABLE); __raw_writel(t & ~(1 << irq), base + AR71XX_RESET_REG_MISC_INT_ENABLE); @@ -90,13 +88,12 @@ static void ar71xx_misc_irq_mask(unsigned int irq) __raw_readl(base + AR71XX_RESET_REG_MISC_INT_ENABLE); } -static void ar724x_misc_irq_ack(unsigned int irq) +static void ar724x_misc_irq_ack(struct irq_data *d) { + unsigned int irq = d->irq - ATH79_MISC_IRQ_BASE; void __iomem *base = ath79_reset_base; u32 t; - irq -= ATH79_MISC_IRQ_BASE; - t = __raw_readl(base + AR71XX_RESET_REG_MISC_INT_STATUS); __raw_writel(t & ~(1 << irq), base + AR71XX_RESET_REG_MISC_INT_STATUS); @@ -106,8 +103,8 @@ static void ar724x_misc_irq_ack(unsigned int irq) static struct irq_chip ath79_misc_irq_chip = { .name = "MISC", - .unmask = ar71xx_misc_irq_unmask, - .mask = ar71xx_misc_irq_mask, + .irq_unmask = ar71xx_misc_irq_unmask, + .irq_mask = ar71xx_misc_irq_mask, }; static void __init ath79_misc_irq_init(void) @@ -119,15 +116,14 @@ static void __init ath79_misc_irq_init(void) __raw_writel(0, base + AR71XX_RESET_REG_MISC_INT_STATUS); if (soc_is_ar71xx() || soc_is_ar913x()) - ath79_misc_irq_chip.mask_ack = ar71xx_misc_irq_mask; + ath79_misc_irq_chip.irq_mask_ack = ar71xx_misc_irq_mask; else if (soc_is_ar724x()) - ath79_misc_irq_chip.ack = ar724x_misc_irq_ack; + ath79_misc_irq_chip.irq_ack = ar724x_misc_irq_ack; else BUG(); for (i = ATH79_MISC_IRQ_BASE; i < ATH79_MISC_IRQ_BASE + ATH79_MISC_IRQ_COUNT; i++) { - irq_desc[i].status = IRQ_DISABLED; set_irq_chip_and_handler(i, &ath79_misc_irq_chip, handle_level_irq); } diff --git a/arch/mips/bcm63xx/irq.c b/arch/mips/bcm63xx/irq.c index 3be87f2422f0..1691531aa34d 100644 --- a/arch/mips/bcm63xx/irq.c +++ b/arch/mips/bcm63xx/irq.c @@ -76,88 +76,80 @@ asmlinkage void plat_irq_dispatch(void) * internal IRQs operations: only mask/unmask on PERF irq mask * register. */ -static inline void bcm63xx_internal_irq_mask(unsigned int irq) +static inline void bcm63xx_internal_irq_mask(struct irq_data *d) { + unsigned int irq = d->irq - IRQ_INTERNAL_BASE; u32 mask; - irq -= IRQ_INTERNAL_BASE; mask = bcm_perf_readl(PERF_IRQMASK_REG); mask &= ~(1 << irq); bcm_perf_writel(mask, PERF_IRQMASK_REG); } -static void bcm63xx_internal_irq_unmask(unsigned int irq) +static void bcm63xx_internal_irq_unmask(struct irq_data *d) { + unsigned int irq = d->irq - IRQ_INTERNAL_BASE; u32 mask; - irq -= IRQ_INTERNAL_BASE; mask = bcm_perf_readl(PERF_IRQMASK_REG); mask |= (1 << irq); bcm_perf_writel(mask, PERF_IRQMASK_REG); } -static unsigned int bcm63xx_internal_irq_startup(unsigned int irq) -{ - bcm63xx_internal_irq_unmask(irq); - return 0; -} - /* * external IRQs operations: mask/unmask and clear on PERF external * irq control register. */ -static void bcm63xx_external_irq_mask(unsigned int irq) +static void bcm63xx_external_irq_mask(struct irq_data *d) { + unsigned int irq = d->irq - IRQ_EXT_BASE; u32 reg; - irq -= IRQ_EXT_BASE; reg = bcm_perf_readl(PERF_EXTIRQ_CFG_REG); reg &= ~EXTIRQ_CFG_MASK(irq); bcm_perf_writel(reg, PERF_EXTIRQ_CFG_REG); } -static void bcm63xx_external_irq_unmask(unsigned int irq) +static void bcm63xx_external_irq_unmask(struct irq_data *d) { + unsigned int irq = d->irq - IRQ_EXT_BASE; u32 reg; - irq -= IRQ_EXT_BASE; reg = bcm_perf_readl(PERF_EXTIRQ_CFG_REG); reg |= EXTIRQ_CFG_MASK(irq); bcm_perf_writel(reg, PERF_EXTIRQ_CFG_REG); } -static void bcm63xx_external_irq_clear(unsigned int irq) +static void bcm63xx_external_irq_clear(struct irq_data *d) { + unsigned int irq = d->irq - IRQ_EXT_BASE; u32 reg; - irq -= IRQ_EXT_BASE; reg = bcm_perf_readl(PERF_EXTIRQ_CFG_REG); reg |= EXTIRQ_CFG_CLEAR(irq); bcm_perf_writel(reg, PERF_EXTIRQ_CFG_REG); } -static unsigned int bcm63xx_external_irq_startup(unsigned int irq) +static unsigned int bcm63xx_external_irq_startup(struct irq_data *d) { - set_c0_status(0x100 << (irq - IRQ_MIPS_BASE)); + set_c0_status(0x100 << (d->irq - IRQ_MIPS_BASE)); irq_enable_hazard(); - bcm63xx_external_irq_unmask(irq); + bcm63xx_external_irq_unmask(d); return 0; } -static void bcm63xx_external_irq_shutdown(unsigned int irq) +static void bcm63xx_external_irq_shutdown(struct irq_data *d) { - bcm63xx_external_irq_mask(irq); - clear_c0_status(0x100 << (irq - IRQ_MIPS_BASE)); + bcm63xx_external_irq_mask(d); + clear_c0_status(0x100 << (d->irq - IRQ_MIPS_BASE)); irq_disable_hazard(); } -static int bcm63xx_external_irq_set_type(unsigned int irq, +static int bcm63xx_external_irq_set_type(struct irq_data *d, unsigned int flow_type) { + unsigned int irq = d->irq - IRQ_EXT_BASE; u32 reg; - struct irq_desc *desc = irq_desc + irq; - - irq -= IRQ_EXT_BASE; flow_type &= IRQ_TYPE_SENSE_MASK; @@ -199,37 +191,32 @@ static int bcm63xx_external_irq_set_type(unsigned int irq, } bcm_perf_writel(reg, PERF_EXTIRQ_CFG_REG); - if (flow_type & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH)) { - desc->status |= IRQ_LEVEL; - desc->handle_irq = handle_level_irq; - } else { - desc->handle_irq = handle_edge_irq; - } + irqd_set_trigger_type(d, flow_type); + if (flow_type & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH)) + __irq_set_handler_locked(d->irq, handle_level_irq); + else + __irq_set_handler_locked(d->irq, handle_edge_irq); - return 0; + return IRQ_SET_MASK_OK_NOCOPY; } static struct irq_chip bcm63xx_internal_irq_chip = { .name = "bcm63xx_ipic", - .startup = bcm63xx_internal_irq_startup, - .shutdown = bcm63xx_internal_irq_mask, - - .mask = bcm63xx_internal_irq_mask, - .mask_ack = bcm63xx_internal_irq_mask, - .unmask = bcm63xx_internal_irq_unmask, + .irq_mask = bcm63xx_internal_irq_mask, + .irq_unmask = bcm63xx_internal_irq_unmask, }; static struct irq_chip bcm63xx_external_irq_chip = { .name = "bcm63xx_epic", - .startup = bcm63xx_external_irq_startup, - .shutdown = bcm63xx_external_irq_shutdown, + .irq_startup = bcm63xx_external_irq_startup, + .irq_shutdown = bcm63xx_external_irq_shutdown, - .ack = bcm63xx_external_irq_clear, + .irq_ack = bcm63xx_external_irq_clear, - .mask = bcm63xx_external_irq_mask, - .unmask = bcm63xx_external_irq_unmask, + .irq_mask = bcm63xx_external_irq_mask, + .irq_unmask = bcm63xx_external_irq_unmask, - .set_type = bcm63xx_external_irq_set_type, + .irq_set_type = bcm63xx_external_irq_set_type, }; static struct irqaction cpu_ip2_cascade_action = { diff --git a/arch/mips/dec/ioasic-irq.c b/arch/mips/dec/ioasic-irq.c index cb41954fc321..8d9a5fc607e4 100644 --- a/arch/mips/dec/ioasic-irq.c +++ b/arch/mips/dec/ioasic-irq.c @@ -17,80 +17,48 @@ #include <asm/dec/ioasic_addrs.h> #include <asm/dec/ioasic_ints.h> - static int ioasic_irq_base; - -static inline void unmask_ioasic_irq(unsigned int irq) +static void unmask_ioasic_irq(struct irq_data *d) { u32 simr; simr = ioasic_read(IO_REG_SIMR); - simr |= (1 << (irq - ioasic_irq_base)); + simr |= (1 << (d->irq - ioasic_irq_base)); ioasic_write(IO_REG_SIMR, simr); } -static inline void mask_ioasic_irq(unsigned int irq) +static void mask_ioasic_irq(struct irq_data *d) { u32 simr; simr = ioasic_read(IO_REG_SIMR); - simr &= ~(1 << (irq - ioasic_irq_base)); + simr &= ~(1 << (d->irq - ioasic_irq_base)); ioasic_write(IO_REG_SIMR, simr); } -static inline void clear_ioasic_irq(unsigned int irq) +static void ack_ioasic_irq(struct irq_data *d) { - u32 sir; - - sir = ~(1 << (irq - ioasic_irq_base)); - ioasic_write(IO_REG_SIR, sir); -} - -static inline void ack_ioasic_irq(unsigned int irq) -{ - mask_ioasic_irq(irq); + mask_ioasic_irq(d); fast_iob(); } -static inline void end_ioasic_irq(unsigned int irq) -{ - if (!(irq_desc[irq].status & (IRQ_DISABLED | IRQ_INPROGRESS))) - unmask_ioasic_irq(irq); -} - static struct irq_chip ioasic_irq_type = { .name = "IO-ASIC", - .ack = ack_ioasic_irq, - .mask = mask_ioasic_irq, - .mask_ack = ack_ioasic_irq, - .unmask = unmask_ioasic_irq, + .irq_ack = ack_ioasic_irq, + .irq_mask = mask_ioasic_irq, + .irq_mask_ack = ack_ioasic_irq, + .irq_unmask = unmask_ioasic_irq, }; - -#define unmask_ioasic_dma_irq unmask_ioasic_irq - -#define mask_ioasic_dma_irq mask_ioasic_irq - -#define ack_ioasic_dma_irq ack_ioasic_irq - -static inline void end_ioasic_dma_irq(unsigned int irq) -{ - clear_ioasic_irq(irq); - fast_iob(); - end_ioasic_irq(irq); -} - static struct irq_chip ioasic_dma_irq_type = { .name = "IO-ASIC-DMA", - .ack = ack_ioasic_dma_irq, - .mask = mask_ioasic_dma_irq, - .mask_ack = ack_ioasic_dma_irq, - .unmask = unmask_ioasic_dma_irq, - .end = end_ioasic_dma_irq, + .irq_ack = ack_ioasic_irq, + .irq_mask = mask_ioasic_irq, + .irq_mask_ack = ack_ioasic_irq, + .irq_unmask = unmask_ioasic_irq, }; - void __init init_ioasic_irqs(int base) { int i; diff --git a/arch/mips/dec/kn02-irq.c b/arch/mips/dec/kn02-irq.c index ed90a8deabcc..ef31d98c4fb8 100644 --- a/arch/mips/dec/kn02-irq.c +++ b/arch/mips/dec/kn02-irq.c @@ -27,43 +27,40 @@ */ u32 cached_kn02_csr; - static int kn02_irq_base; - -static inline void unmask_kn02_irq(unsigned int irq) +static void unmask_kn02_irq(struct irq_data *d) { volatile u32 *csr = (volatile u32 *)CKSEG1ADDR(KN02_SLOT_BASE + KN02_CSR); - cached_kn02_csr |= (1 << (irq - kn02_irq_base + 16)); + cached_kn02_csr |= (1 << (d->irq - kn02_irq_base + 16)); *csr = cached_kn02_csr; } -static inline void mask_kn02_irq(unsigned int irq) +static void mask_kn02_irq(struct irq_data *d) { volatile u32 *csr = (volatile u32 *)CKSEG1ADDR(KN02_SLOT_BASE + KN02_CSR); - cached_kn02_csr &= ~(1 << (irq - kn02_irq_base + 16)); + cached_kn02_csr &= ~(1 << (d->irq - kn02_irq_base + 16)); *csr = cached_kn02_csr; } -static void ack_kn02_irq(unsigned int irq) +static void ack_kn02_irq(struct irq_data *d) { - mask_kn02_irq(irq); + mask_kn02_irq(d); iob(); } static struct irq_chip kn02_irq_type = { .name = "KN02-CSR", - .ack = ack_kn02_irq, - .mask = mask_kn02_irq, - .mask_ack = ack_kn02_irq, - .unmask = unmask_kn02_irq, + .irq_ack = ack_kn02_irq, + .irq_mask = mask_kn02_irq, + .irq_mask_ack = ack_kn02_irq, + .irq_unmask = unmask_kn02_irq, }; - void __init init_kn02_irqs(int base) { volatile u32 *csr = (volatile u32 *)CKSEG1ADDR(KN02_SLOT_BASE + diff --git a/arch/mips/emma/markeins/irq.c b/arch/mips/emma/markeins/irq.c index 3a96799eb65f..9b1207ae2256 100644 --- a/arch/mips/emma/markeins/irq.c +++ b/arch/mips/emma/markeins/irq.c @@ -34,13 +34,10 @@ #include <asm/emma/emma2rh.h> -static void emma2rh_irq_enable(unsigned int irq) +static void emma2rh_irq_enable(struct irq_data *d) { - u32 reg_value; - u32 reg_bitmask; - u32 reg_index; - - irq -= EMMA2RH_IRQ_BASE; + unsigned int irq = d->irq - EMMA2RH_IRQ_BASE; + u32 reg_value, reg_bitmask, reg_index; reg_index = EMMA2RH_BHIF_INT_EN_0 + (EMMA2RH_BHIF_INT_EN_1 - EMMA2RH_BHIF_INT_EN_0) * (irq / 32); @@ -49,13 +46,10 @@ static void emma2rh_irq_enable(unsigned int irq) emma2rh_out32(reg_index, reg_value | reg_bitmask); } -static void emma2rh_irq_disable(unsigned int irq) +static void emma2rh_irq_disable(struct irq_data *d) { - u32 reg_value; - u32 reg_bitmask; - u32 reg_index; - - irq -= EMMA2RH_IRQ_BASE; + unsigned int irq = d->irq - EMMA2RH_IRQ_BASE; + u32 reg_value, reg_bitmask, reg_index; reg_index = EMMA2RH_BHIF_INT_EN_0 + (EMMA2RH_BHIF_INT_EN_1 - EMMA2RH_BHIF_INT_EN_0) * (irq / 32); @@ -66,10 +60,8 @@ static void emma2rh_irq_disable(unsigned int irq) struct irq_chip emma2rh_irq_controller = { .name = "emma2rh_irq", - .ack = emma2rh_irq_disable, - .mask = emma2rh_irq_disable, - .mask_ack = emma2rh_irq_disable, - .unmask = emma2rh_irq_enable, + .irq_mask = emma2rh_irq_disable, + .irq_unmask = emma2rh_irq_enable, }; void emma2rh_irq_init(void) @@ -82,23 +74,21 @@ void emma2rh_irq_init(void) handle_level_irq, "level"); } -static void emma2rh_sw_irq_enable(unsigned int irq) +static void emma2rh_sw_irq_enable(struct irq_data *d) { + unsigned int irq = d->irq - EMMA2RH_SW_IRQ_BASE; u32 reg; - irq -= EMMA2RH_SW_IRQ_BASE; - reg = emma2rh_in32(EMMA2RH_BHIF_SW_INT_EN); reg |= 1 << irq; emma2rh_out32(EMMA2RH_BHIF_SW_INT_EN, reg); } -static void emma2rh_sw_irq_disable(unsigned int irq) +static void emma2rh_sw_irq_disable(struct irq_data *d) { + unsigned int irq = d->irq - EMMA2RH_SW_IRQ_BASE; u32 reg; - irq -= EMMA2RH_SW_IRQ_BASE; - reg = emma2rh_in32(EMMA2RH_BHIF_SW_INT_EN); reg &= ~(1 << irq); emma2rh_out32(EMMA2RH_BHIF_SW_INT_EN, reg); @@ -106,10 +96,8 @@ static void emma2rh_sw_irq_disable(unsigned int irq) struct irq_chip emma2rh_sw_irq_controller = { .name = "emma2rh_sw_irq", - .ack = emma2rh_sw_irq_disable, - .mask = emma2rh_sw_irq_disable, - .mask_ack = emma2rh_sw_irq_disable, - .unmask = emma2rh_sw_irq_enable, + .irq_mask = emma2rh_sw_irq_disable, + .irq_unmask = emma2rh_sw_irq_enable, }; void emma2rh_sw_irq_init(void) @@ -122,39 +110,38 @@ void emma2rh_sw_irq_init(void) handle_level_irq, "level"); } -static void emma2rh_gpio_irq_enable(unsigned int irq) +static void emma2rh_gpio_irq_enable(struct irq_data *d) { + unsigned int irq = d->irq - EMMA2RH_GPIO_IRQ_BASE; u32 reg; - irq -= EMMA2RH_GPIO_IRQ_BASE; - reg = emma2rh_in32(EMMA2RH_GPIO_INT_MASK); reg |= 1 << irq; emma2rh_out32(EMMA2RH_GPIO_INT_MASK, reg); } -static void emma2rh_gpio_irq_disable(unsigned int irq) +static void emma2rh_gpio_irq_disable(struct irq_data *d) { + unsigned int irq = d->irq - EMMA2RH_GPIO_IRQ_BASE; u32 reg; - irq -= EMMA2RH_GPIO_IRQ_BASE; - reg = emma2rh_in32(EMMA2RH_GPIO_INT_MASK); reg &= ~(1 << irq); emma2rh_out32(EMMA2RH_GPIO_INT_MASK, reg); } -static void emma2rh_gpio_irq_ack(unsigned int irq) +static void emma2rh_gpio_irq_ack(struct irq_data *d) { - irq -= EMMA2RH_GPIO_IRQ_BASE; + unsigned int irq = d->irq - EMMA2RH_GPIO_IRQ_BASE; + emma2rh_out32(EMMA2RH_GPIO_INT_ST, ~(1 << irq)); } -static void emma2rh_gpio_irq_mask_ack(unsigned int irq) +static void emma2rh_gpio_irq_mask_ack(struct irq_data *d) { + unsigned int irq = d->irq - EMMA2RH_GPIO_IRQ_BASE; u32 reg; - irq -= EMMA2RH_GPIO_IRQ_BASE; emma2rh_out32(EMMA2RH_GPIO_INT_ST, ~(1 << irq)); reg = emma2rh_in32(EMMA2RH_GPIO_INT_MASK); @@ -164,10 +151,10 @@ static void emma2rh_gpio_irq_mask_ack(unsigned int irq) struct irq_chip emma2rh_gpio_irq_controller = { .name = "emma2rh_gpio_irq", - .ack = emma2rh_gpio_irq_ack, - .mask = emma2rh_gpio_irq_disable, - .mask_ack = emma2rh_gpio_irq_mask_ack, - .unmask = emma2rh_gpio_irq_enable, + .irq_ack = emma2rh_gpio_irq_ack, + .irq_mask = emma2rh_gpio_irq_disable, + .irq_mask_ack = emma2rh_gpio_irq_mask_ack, + .irq_unmask = emma2rh_gpio_irq_enable, }; void emma2rh_gpio_irq_init(void) diff --git a/arch/mips/include/asm/irq.h b/arch/mips/include/asm/irq.h index b003ed52ed17..0ec01294b063 100644 --- a/arch/mips/include/asm/irq.h +++ b/arch/mips/include/asm/irq.h @@ -55,9 +55,9 @@ static inline void smtc_im_ack_irq(unsigned int irq) #ifdef CONFIG_MIPS_MT_SMTC_IRQAFF #include <linux/cpumask.h> -extern int plat_set_irq_affinity(unsigned int irq, - const struct cpumask *affinity); -extern void smtc_forward_irq(unsigned int irq); +extern int plat_set_irq_affinity(struct irq_data *d, + const struct cpumask *affinity, bool force); +extern void smtc_forward_irq(struct irq_data *d); /* * IRQ affinity hook invoked at the beginning of interrupt dispatch @@ -70,51 +70,53 @@ extern void smtc_forward_irq(unsigned int irq); * cpumask implementations, this version is optimistically assuming * that cpumask.h macro overhead is reasonable during interrupt dispatch. */ -#define IRQ_AFFINITY_HOOK(irq) \ -do { \ - if (!cpumask_test_cpu(smp_processor_id(), irq_desc[irq].affinity)) {\ - smtc_forward_irq(irq); \ - irq_exit(); \ - return; \ - } \ -} while (0) +static inline int handle_on_other_cpu(unsigned int irq) +{ + struct irq_data *d = irq_get_irq_data(irq); + + if (cpumask_test_cpu(smp_processor_id(), d->affinity)) + return 0; + smtc_forward_irq(d); + return 1; +} #else /* Not doing SMTC affinity */ -#define IRQ_AFFINITY_HOOK(irq) do { } while (0) +static inline int handle_on_other_cpu(unsigned int irq) { return 0; } #endif /* CONFIG_MIPS_MT_SMTC_IRQAFF */ #ifdef CONFIG_MIPS_MT_SMTC_IM_BACKSTOP +static inline void smtc_im_backstop(unsigned int irq) +{ + if (irq_hwmask[irq] & 0x0000ff00) + write_c0_tccontext(read_c0_tccontext() & + ~(irq_hwmask[irq] & 0x0000ff00)); +} + /* * Clear interrupt mask handling "backstop" if irq_hwmask * entry so indicates. This implies that the ack() or end() * functions will take over re-enabling the low-level mask. * Otherwise it will be done on return from exception. */ -#define __DO_IRQ_SMTC_HOOK(irq) \ -do { \ - IRQ_AFFINITY_HOOK(irq); \ - if (irq_hwmask[irq] & 0x0000ff00) \ - write_c0_tccontext(read_c0_tccontext() & \ - ~(irq_hwmask[irq] & 0x0000ff00)); \ -} while (0) - -#define __NO_AFFINITY_IRQ_SMTC_HOOK(irq) \ -do { \ - if (irq_hwmask[irq] & 0x0000ff00) \ - write_c0_tccontext(read_c0_tccontext() & \ - ~(irq_hwmask[irq] & 0x0000ff00)); \ -} while (0) +static inline int smtc_handle_on_other_cpu(unsigned int irq) +{ + int ret = handle_on_other_cpu(irq); + + if (!ret) + smtc_im_backstop(irq); + return ret; +} #else -#define __DO_IRQ_SMTC_HOOK(irq) \ -do { \ - IRQ_AFFINITY_HOOK(irq); \ -} while (0) -#define __NO_AFFINITY_IRQ_SMTC_HOOK(irq) do { } while (0) +static inline void smtc_im_backstop(unsigned int irq) { } +static inline int smtc_handle_on_other_cpu(unsigned int irq) +{ + return handle_on_other_cpu(irq); +} #endif diff --git a/arch/mips/include/asm/pmc-sierra/msp71xx/cpu-feature-overrides.h b/arch/mips/include/asm/pmc-sierra/msp71xx/cpu-feature-overrides.h new file mode 100644 index 000000000000..a80801b094bd --- /dev/null +++ b/arch/mips/include/asm/pmc-sierra/msp71xx/cpu-feature-overrides.h @@ -0,0 +1,21 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 2003, 04, 07 Ralf Baechle (ralf@linux-mips.org) + */ +#ifndef __ASM_MACH_MSP71XX_CPU_FEATURE_OVERRIDES_H +#define __ASM_MACH_MSP71XX_CPU_FEATURE_OVERRIDES_H + +#define cpu_has_mips16 1 +#define cpu_has_dsp 1 +#define cpu_has_mipsmt 1 +#define cpu_has_fpu 0 + +#define cpu_has_mips32r1 0 +#define cpu_has_mips32r2 1 +#define cpu_has_mips64r1 0 +#define cpu_has_mips64r2 0 + +#endif /* __ASM_MACH_MSP71XX_CPU_FEATURE_OVERRIDES_H */ diff --git a/arch/mips/include/asm/pmc-sierra/msp71xx/msp_gpio_macros.h b/arch/mips/include/asm/pmc-sierra/msp71xx/msp_gpio_macros.h new file mode 100644 index 000000000000..156f320c69e7 --- /dev/null +++ b/arch/mips/include/asm/pmc-sierra/msp71xx/msp_gpio_macros.h @@ -0,0 +1,343 @@ +/* + * + * Macros for external SMP-safe access to the PMC MSP71xx reference + * board GPIO pins + * + * Copyright 2010 PMC-Sierra, Inc. + * + * 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 SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED + * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN + * NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, + * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT + * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF + * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON + * ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF + * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + * 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., + * 675 Mass Ave, Cambridge, MA 02139, USA. + */ + +#ifndef __MSP_GPIO_MACROS_H__ +#define __MSP_GPIO_MACROS_H__ + +#include <msp_regops.h> +#include <msp_regs.h> + +#ifdef CONFIG_PMC_MSP7120_GW +#define MSP_NUM_GPIOS 20 +#else +#define MSP_NUM_GPIOS 28 +#endif + +/* -- GPIO Enumerations -- */ +enum msp_gpio_data { + MSP_GPIO_LO = 0, + MSP_GPIO_HI = 1, + MSP_GPIO_NONE, /* Special - Means pin is out of range */ + MSP_GPIO_TOGGLE, /* Special - Sets pin to opposite */ +}; + +enum msp_gpio_mode { + MSP_GPIO_INPUT = 0x0, + /* MSP_GPIO_ INTERRUPT = 0x1, Not supported yet */ + MSP_GPIO_UART_INPUT = 0x2, /* Only GPIO 4 or 5 */ + MSP_GPIO_OUTPUT = 0x8, + MSP_GPIO_UART_OUTPUT = 0x9, /* Only GPIO 2 or 3 */ + MSP_GPIO_PERIF_TIMERA = 0x9, /* Only GPIO 0 or 1 */ + MSP_GPIO_PERIF_TIMERB = 0xa, /* Only GPIO 0 or 1 */ + MSP_GPIO_UNKNOWN = 0xb, /* No such GPIO or mode */ +}; + +/* -- Static Tables -- */ + +/* Maps pins to data register */ +static volatile u32 * const MSP_GPIO_DATA_REGISTER[] = { + /* GPIO 0 and 1 on the first register */ + GPIO_DATA1_REG, GPIO_DATA1_REG, + /* GPIO 2, 3, 4, and 5 on the second register */ + GPIO_DATA2_REG, GPIO_DATA2_REG, GPIO_DATA2_REG, GPIO_DATA2_REG, + /* GPIO 6, 7, 8, and 9 on the third register */ + GPIO_DATA3_REG, GPIO_DATA3_REG, GPIO_DATA3_REG, GPIO_DATA3_REG, + /* GPIO 10, 11, 12, 13, 14, and 15 on the fourth register */ + GPIO_DATA4_REG, GPIO_DATA4_REG, GPIO_DATA4_REG, GPIO_DATA4_REG, + GPIO_DATA4_REG, GPIO_DATA4_REG, + /* GPIO 16 - 23 on the first strange EXTENDED register */ + EXTENDED_GPIO1_REG, EXTENDED_GPIO1_REG, EXTENDED_GPIO1_REG, + EXTENDED_GPIO1_REG, EXTENDED_GPIO1_REG, EXTENDED_GPIO1_REG, + EXTENDED_GPIO1_REG, EXTENDED_GPIO1_REG, + /* GPIO 24 - 27 on the second strange EXTENDED register */ + EXTENDED_GPIO2_REG, EXTENDED_GPIO2_REG, EXTENDED_GPIO2_REG, + EXTENDED_GPIO2_REG, +}; + +/* Maps pins to mode register */ +static volatile u32 * const MSP_GPIO_MODE_REGISTER[] = { + /* GPIO 0 and 1 on the first register */ + GPIO_CFG1_REG, GPIO_CFG1_REG, + /* GPIO 2, 3, 4, and 5 on the second register */ + GPIO_CFG2_REG, GPIO_CFG2_REG, GPIO_CFG2_REG, GPIO_CFG2_REG, + /* GPIO 6, 7, 8, and 9 on the third register */ + GPIO_CFG3_REG, GPIO_CFG3_REG, GPIO_CFG3_REG, GPIO_CFG3_REG, + /* GPIO 10, 11, 12, 13, 14, and 15 on the fourth register */ + GPIO_CFG4_REG, GPIO_CFG4_REG, GPIO_CFG4_REG, GPIO_CFG4_REG, + GPIO_CFG4_REG, GPIO_CFG4_REG, + /* GPIO 16 - 23 on the first strange EXTENDED register */ + EXTENDED_GPIO1_REG, EXTENDED_GPIO1_REG, EXTENDED_GPIO1_REG, + EXTENDED_GPIO1_REG, EXTENDED_GPIO1_REG, EXTENDED_GPIO1_REG, + EXTENDED_GPIO1_REG, EXTENDED_GPIO1_REG, + /* GPIO 24 - 27 on the second strange EXTENDED register */ + EXTENDED_GPIO2_REG, EXTENDED_GPIO2_REG, EXTENDED_GPIO2_REG, + EXTENDED_GPIO2_REG, +}; + +/* Maps 'basic' pins to relative offset from 0 per register */ +static int MSP_GPIO_OFFSET[] = { + /* GPIO 0 and 1 on the first register */ + 0, 0, + /* GPIO 2, 3, 4, and 5 on the second register */ + 2, 2, 2, 2, + /* GPIO 6, 7, 8, and 9 on the third register */ + 6, 6, 6, 6, + /* GPIO 10, 11, 12, 13, 14, and 15 on the fourth register */ + 10, 10, 10, 10, 10, 10, +}; + +/* Maps MODE to allowed pin mask */ +static unsigned int MSP_GPIO_MODE_ALLOWED[] = { + 0xffffffff, /* Mode 0 - INPUT */ + 0x00000, /* Mode 1 - INTERRUPT */ + 0x00030, /* Mode 2 - UART_INPUT (GPIO 4, 5)*/ + 0, 0, 0, 0, 0, /* Modes 3, 4, 5, 6, and 7 are reserved */ + 0xffffffff, /* Mode 8 - OUTPUT */ + 0x0000f, /* Mode 9 - UART_OUTPUT/ + PERF_TIMERA (GPIO 0, 1, 2, 3) */ + 0x00003, /* Mode a - PERF_TIMERB (GPIO 0, 1) */ + 0x00000, /* Mode b - Not really a mode! */ +}; + +/* -- Bit masks -- */ + +/* This gives you the 'register relative offset gpio' number */ +#define OFFSET_GPIO_NUMBER(gpio) (gpio - MSP_GPIO_OFFSET[gpio]) + +/* These take the 'register relative offset gpio' number */ +#define BASIC_DATA_REG_MASK(ogpio) (1 << ogpio) +#define BASIC_MODE_REG_VALUE(mode, ogpio) \ + (mode << BASIC_MODE_REG_SHIFT(ogpio)) +#define BASIC_MODE_REG_MASK(ogpio) \ + BASIC_MODE_REG_VALUE(0xf, ogpio) +#define BASIC_MODE_REG_SHIFT(ogpio) (ogpio * 4) +#define BASIC_MODE_REG_FROM_REG(data, ogpio) \ + ((data & BASIC_MODE_REG_MASK(ogpio)) >> BASIC_MODE_REG_SHIFT(ogpio)) + +/* These take the actual GPIO number (0 through 15) */ +#define BASIC_DATA_MASK(gpio) \ + BASIC_DATA_REG_MASK(OFFSET_GPIO_NUMBER(gpio)) +#define BASIC_MODE_MASK(gpio) \ + BASIC_MODE_REG_MASK(OFFSET_GPIO_NUMBER(gpio)) +#define BASIC_MODE(mode, gpio) \ + BASIC_MODE_REG_VALUE(mode, OFFSET_GPIO_NUMBER(gpio)) +#define BASIC_MODE_SHIFT(gpio) \ + BASIC_MODE_REG_SHIFT(OFFSET_GPIO_NUMBER(gpio)) +#define BASIC_MODE_FROM_REG(data, gpio) \ + BASIC_MODE_REG_FROM_REG(data, OFFSET_GPIO_NUMBER(gpio)) + +/* + * Each extended GPIO register is 32 bits long and is responsible for up to + * eight GPIOs. The least significant 16 bits contain the set and clear bit + * pair for each of the GPIOs. The most significant 16 bits contain the + * disable and enable bit pair for each of the GPIOs. For example, the + * extended GPIO reg for GPIOs 16-23 is as follows: + * + * 31: GPIO23_DISABLE + * ... + * 19: GPIO17_DISABLE + * 18: GPIO17_ENABLE + * 17: GPIO16_DISABLE + * 16: GPIO16_ENABLE + * ... + * 3: GPIO17_SET + * 2: GPIO17_CLEAR + * 1: GPIO16_SET + * 0: GPIO16_CLEAR + */ + +/* This gives the 'register relative offset gpio' number */ +#define EXTENDED_OFFSET_GPIO(gpio) (gpio < 24 ? gpio - 16 : gpio - 24) + +/* These take the 'register relative offset gpio' number */ +#define EXTENDED_REG_DISABLE(ogpio) (0x2 << ((ogpio * 2) + 16)) +#define EXTENDED_REG_ENABLE(ogpio) (0x1 << ((ogpio * 2) + 16)) +#define EXTENDED_REG_SET(ogpio) (0x2 << (ogpio * 2)) +#define EXTENDED_REG_CLR(ogpio) (0x1 << (ogpio * 2)) + +/* These take the actual GPIO number (16 through 27) */ +#define EXTENDED_DISABLE(gpio) \ + EXTENDED_REG_DISABLE(EXTENDED_OFFSET_GPIO(gpio)) +#define EXTENDED_ENABLE(gpio) \ + EXTENDED_REG_ENABLE(EXTENDED_OFFSET_GPIO(gpio)) +#define EXTENDED_SET(gpio) \ + EXTENDED_REG_SET(EXTENDED_OFFSET_GPIO(gpio)) +#define EXTENDED_CLR(gpio) \ + EXTENDED_REG_CLR(EXTENDED_OFFSET_GPIO(gpio)) + +#define EXTENDED_FULL_MASK (0xffffffff) + +/* -- API inline-functions -- */ + +/* + * Gets the current value of the specified pin + */ +static inline enum msp_gpio_data msp_gpio_pin_get(unsigned int gpio) +{ + u32 pinhi_mask = 0, pinhi_mask2 = 0; + + if (gpio >= MSP_NUM_GPIOS) + return MSP_GPIO_NONE; + + if (gpio < 16) { + pinhi_mask = BASIC_DATA_MASK(gpio); + } else { + /* + * Two cases are possible with the EXTENDED register: + * - In output mode (ENABLED flag set), check the CLR bit + * - In input mode (ENABLED flag not set), check the SET bit + */ + pinhi_mask = EXTENDED_ENABLE(gpio) | EXTENDED_CLR(gpio); + pinhi_mask2 = EXTENDED_SET(gpio); + } + if (((*MSP_GPIO_DATA_REGISTER[gpio] & pinhi_mask) == pinhi_mask) || + (*MSP_GPIO_DATA_REGISTER[gpio] & pinhi_mask2)) + return MSP_GPIO_HI; + else + return MSP_GPIO_LO; +} + +/* Sets the specified pin to the specified value */ +static inline void msp_gpio_pin_set(enum msp_gpio_data data, unsigned int gpio) +{ + if (gpio >= MSP_NUM_GPIOS) + return; + + if (gpio < 16) { + if (data == MSP_GPIO_TOGGLE) + toggle_reg32(MSP_GPIO_DATA_REGISTER[gpio], + BASIC_DATA_MASK(gpio)); + else if (data == MSP_GPIO_HI) + set_reg32(MSP_GPIO_DATA_REGISTER[gpio], + BASIC_DATA_MASK(gpio)); + else + clear_reg32(MSP_GPIO_DATA_REGISTER[gpio], + BASIC_DATA_MASK(gpio)); + } else { + if (data == MSP_GPIO_TOGGLE) { + /* Special ugly case: + * We have to read the CLR bit. + * If set, we write the CLR bit. + * If not, we write the SET bit. + */ + u32 tmpdata; + + custom_read_reg32(MSP_GPIO_DATA_REGISTER[gpio], + tmpdata); + if (tmpdata & EXTENDED_CLR(gpio)) + tmpdata = EXTENDED_CLR(gpio); + else + tmpdata = EXTENDED_SET(gpio); + custom_write_reg32(MSP_GPIO_DATA_REGISTER[gpio], + tmpdata); + } else { + u32 newdata; + + if (data == MSP_GPIO_HI) + newdata = EXTENDED_SET(gpio); + else + newdata = EXTENDED_CLR(gpio); + set_value_reg32(MSP_GPIO_DATA_REGISTER[gpio], + EXTENDED_FULL_MASK, newdata); + } + } +} + +/* Sets the specified pin to the specified value */ +static inline void msp_gpio_pin_hi(unsigned int gpio) +{ + msp_gpio_pin_set(MSP_GPIO_HI, gpio); +} + +/* Sets the specified pin to the specified value */ +static inline void msp_gpio_pin_lo(unsigned int gpio) +{ + msp_gpio_pin_set(MSP_GPIO_LO, gpio); +} + +/* Sets the specified pin to the opposite value */ +static inline void msp_gpio_pin_toggle(unsigned int gpio) +{ + msp_gpio_pin_set(MSP_GPIO_TOGGLE, gpio); +} + +/* Gets the mode of the specified pin */ +static inline enum msp_gpio_mode msp_gpio_pin_get_mode(unsigned int gpio) +{ + enum msp_gpio_mode retval = MSP_GPIO_UNKNOWN; + uint32_t data; + + if (gpio >= MSP_NUM_GPIOS) + return retval; + + data = *MSP_GPIO_MODE_REGISTER[gpio]; + + if (gpio < 16) { + retval = BASIC_MODE_FROM_REG(data, gpio); + } else { + /* Extended pins can only be either INPUT or OUTPUT */ + if (data & EXTENDED_ENABLE(gpio)) + retval = MSP_GPIO_OUTPUT; + else + retval = MSP_GPIO_INPUT; + } + + return retval; +} + +/* + * Sets the specified mode on the requested pin + * Returns 0 on success, or -1 if that mode is not allowed on this pin + */ +static inline int msp_gpio_pin_mode(enum msp_gpio_mode mode, unsigned int gpio) +{ + u32 modemask, newmode; + + if ((1 << gpio) & ~MSP_GPIO_MODE_ALLOWED[mode]) + return -1; + + if (gpio >= MSP_NUM_GPIOS) + return -1; + + if (gpio < 16) { + modemask = BASIC_MODE_MASK(gpio); + newmode = BASIC_MODE(mode, gpio); + } else { + modemask = EXTENDED_FULL_MASK; + if (mode == MSP_GPIO_INPUT) + newmode = EXTENDED_DISABLE(gpio); + else + newmode = EXTENDED_ENABLE(gpio); + } + /* Do the set atomically */ + set_value_reg32(MSP_GPIO_MODE_REGISTER[gpio], modemask, newmode); + + return 0; +} + +#endif /* __MSP_GPIO_MACROS_H__ */ diff --git a/arch/mips/include/asm/pmc-sierra/msp71xx/msp_regs.h b/arch/mips/include/asm/pmc-sierra/msp71xx/msp_regs.h index 603eb737b4a8..692c1b658b92 100644 --- a/arch/mips/include/asm/pmc-sierra/msp71xx/msp_regs.h +++ b/arch/mips/include/asm/pmc-sierra/msp71xx/msp_regs.h @@ -91,12 +91,10 @@ /* MAC C device registers */ #define MSP_ADSL2_BASE (MSP_MSB_BASE + 0xA80000) /* ADSL2 device registers */ -#define MSP_USB_BASE (MSP_MSB_BASE + 0xB40000) - /* USB device registers */ -#define MSP_USB_BASE_START (MSP_MSB_BASE + 0xB40100) - /* USB device registers */ -#define MSP_USB_BASE_END (MSP_MSB_BASE + 0xB401FF) - /* USB device registers */ +#define MSP_USB0_BASE (MSP_MSB_BASE + 0xB00000) + /* USB0 device registers */ +#define MSP_USB1_BASE (MSP_MSB_BASE + 0x300000) + /* USB1 device registers */ #define MSP_CPUIF_BASE (MSP_MSB_BASE + 0xC00000) /* CPU interface registers */ @@ -319,8 +317,11 @@ #define CPU_ERR2_REG regptr(MSP_SLP_BASE + 0x184) /* CPU/SLP Error status 1 */ -#define EXTENDED_GPIO_REG regptr(MSP_SLP_BASE + 0x188) - /* Extended GPIO register */ +/* Extended GPIO registers */ +#define EXTENDED_GPIO1_REG regptr(MSP_SLP_BASE + 0x188) +#define EXTENDED_GPIO2_REG regptr(MSP_SLP_BASE + 0x18c) +#define EXTENDED_GPIO_REG EXTENDED_GPIO1_REG + /* Backward-compatibility */ /* System Error registers */ #define SLP_ERR_STS_REG regptr(MSP_SLP_BASE + 0x190) diff --git a/arch/mips/include/asm/pmc-sierra/msp71xx/msp_usb.h b/arch/mips/include/asm/pmc-sierra/msp71xx/msp_usb.h new file mode 100644 index 000000000000..4c9348df9df2 --- /dev/null +++ b/arch/mips/include/asm/pmc-sierra/msp71xx/msp_usb.h @@ -0,0 +1,144 @@ +/****************************************************************** + * Copyright (c) 2000-2007 PMC-Sierra INC. + * + * 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, write to the Free + * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA + * 02139, USA. + * + * PMC-SIERRA INC. DISCLAIMS ANY LIABILITY OF ANY KIND + * FOR ANY DAMAGES WHATSOEVER RESULTING FROM THE USE OF THIS + * SOFTWARE. + */ +#ifndef MSP_USB_H_ +#define MSP_USB_H_ + +#ifdef CONFIG_MSP_HAS_DUAL_USB +#define NUM_USB_DEVS 2 +#else +#define NUM_USB_DEVS 1 +#endif + +/* Register spaces for USB host 0 */ +#define MSP_USB0_MAB_START (MSP_USB0_BASE + 0x0) +#define MSP_USB0_MAB_END (MSP_USB0_BASE + 0x17) +#define MSP_USB0_ID_START (MSP_USB0_BASE + 0x40000) +#define MSP_USB0_ID_END (MSP_USB0_BASE + 0x4008f) +#define MSP_USB0_HS_START (MSP_USB0_BASE + 0x40100) +#define MSP_USB0_HS_END (MSP_USB0_BASE + 0x401FF) + +/* Register spaces for USB host 1 */ +#define MSP_USB1_MAB_START (MSP_USB1_BASE + 0x0) +#define MSP_USB1_MAB_END (MSP_USB1_BASE + 0x17) +#define MSP_USB1_ID_START (MSP_USB1_BASE + 0x40000) +#define MSP_USB1_ID_END (MSP_USB1_BASE + 0x4008f) +#define MSP_USB1_HS_START (MSP_USB1_BASE + 0x40100) +#define MSP_USB1_HS_END (MSP_USB1_BASE + 0x401ff) + +/* USB Identification registers */ +struct msp_usbid_regs { + u32 id; /* 0x0: Identification register */ + u32 hwgen; /* 0x4: General HW params */ + u32 hwhost; /* 0x8: Host HW params */ + u32 hwdev; /* 0xc: Device HW params */ + u32 hwtxbuf; /* 0x10: Tx buffer HW params */ + u32 hwrxbuf; /* 0x14: Rx buffer HW params */ + u32 reserved[26]; + u32 timer0_load; /* 0x80: General-purpose timer 0 load*/ + u32 timer0_ctrl; /* 0x84: General-purpose timer 0 control */ + u32 timer1_load; /* 0x88: General-purpose timer 1 load*/ + u32 timer1_ctrl; /* 0x8c: General-purpose timer 1 control */ +}; + +/* MSBus to AMBA registers */ +struct msp_mab_regs { + u32 isr; /* 0x0: Interrupt status */ + u32 imr; /* 0x4: Interrupt mask */ + u32 thcr0; /* 0x8: Transaction header capture 0 */ + u32 thcr1; /* 0xc: Transaction header capture 1 */ + u32 int_stat; /* 0x10: Interrupt status summary */ + u32 phy_cfg; /* 0x14: USB phy config */ +}; + +/* EHCI registers */ +struct msp_usbhs_regs { + u32 hciver; /* 0x0: Version and offset to operational regs */ + u32 hcsparams; /* 0x4: Host control structural parameters */ + u32 hccparams; /* 0x8: Host control capability parameters */ + u32 reserved0[5]; + u32 dciver; /* 0x20: Device interface version */ + u32 dccparams; /* 0x24: Device control capability parameters */ + u32 reserved1[6]; + u32 cmd; /* 0x40: USB command */ + u32 sts; /* 0x44: USB status */ + u32 int_ena; /* 0x48: USB interrupt enable */ + u32 frindex; /* 0x4c: Frame index */ + u32 reserved3; + union { + struct { + u32 flb_addr; /* 0x54: Frame list base address */ + u32 next_async_addr; /* 0x58: next asynchronous addr */ + u32 ttctrl; /* 0x5c: embedded transaction translator + async buffer status */ + u32 burst_size; /* 0x60: Controller burst size */ + u32 tx_fifo_ctrl; /* 0x64: Tx latency FIFO tuning */ + u32 reserved0[4]; + u32 endpt_nak; /* 0x78: Endpoint NAK */ + u32 endpt_nak_ena; /* 0x7c: Endpoint NAK enable */ + u32 cfg_flag; /* 0x80: Config flag */ + u32 port_sc1; /* 0x84: Port status & control 1 */ + u32 reserved1[7]; + u32 otgsc; /* 0xa4: OTG status & control */ + u32 mode; /* 0xa8: USB controller mode */ + } host; + + struct { + u32 dev_addr; /* 0x54: Device address */ + u32 endpt_list_addr; /* 0x58: Endpoint list address */ + u32 reserved0[7]; + u32 endpt_nak; /* 0x74 */ + u32 endpt_nak_ctrl; /* 0x78 */ + u32 cfg_flag; /* 0x80 */ + u32 port_sc1; /* 0x84: Port status & control 1 */ + u32 reserved[7]; + u32 otgsc; /* 0xa4: OTG status & control */ + u32 mode; /* 0xa8: USB controller mode */ + u32 endpt_setup_stat; /* 0xac */ + u32 endpt_prime; /* 0xb0 */ + u32 endpt_flush; /* 0xb4 */ + u32 endpt_stat; /* 0xb8 */ + u32 endpt_complete; /* 0xbc */ + u32 endpt_ctrl0; /* 0xc0 */ + u32 endpt_ctrl1; /* 0xc4 */ + u32 endpt_ctrl2; /* 0xc8 */ + u32 endpt_ctrl3; /* 0xcc */ + } device; + } u; +}; +/* + * Container for the more-generic platform_device. + * This exists mainly as a way to map the non-standard register + * spaces and make them accessible to the USB ISR. + */ +struct mspusb_device { + struct msp_mab_regs __iomem *mab_regs; + struct msp_usbid_regs __iomem *usbid_regs; + struct msp_usbhs_regs __iomem *usbhs_regs; + struct platform_device dev; +}; + +#define to_mspusb_device(x) container_of((x), struct mspusb_device, dev) +#define TO_HOST_ID(x) ((x) & 0x3) +#endif /*MSP_USB_H_*/ diff --git a/arch/mips/include/asm/spinlock.h b/arch/mips/include/asm/spinlock.h index 396e402fbe2c..ca61e846ab0f 100644 --- a/arch/mips/include/asm/spinlock.h +++ b/arch/mips/include/asm/spinlock.h @@ -245,16 +245,16 @@ static inline void arch_read_lock(arch_rwlock_t *rw) __asm__ __volatile__( " .set noreorder # arch_read_lock \n" "1: ll %1, %2 \n" - " bltz %1, 2f \n" + " bltz %1, 3f \n" " addu %1, 1 \n" - " sc %1, %0 \n" + "2: sc %1, %0 \n" " beqz %1, 1b \n" " nop \n" " .subsection 2 \n" - "2: ll %1, %2 \n" - " bltz %1, 2b \n" + "3: ll %1, %2 \n" + " bltz %1, 3b \n" " addu %1, 1 \n" - " b 1b \n" + " b 2b \n" " nop \n" " .previous \n" " .set reorder \n" @@ -324,16 +324,16 @@ static inline void arch_write_lock(arch_rwlock_t *rw) __asm__ __volatile__( " .set noreorder # arch_write_lock \n" "1: ll %1, %2 \n" - " bnez %1, 2f \n" + " bnez %1, 3f \n" " lui %1, 0x8000 \n" - " sc %1, %0 \n" - " beqz %1, 2f \n" + "2: sc %1, %0 \n" + " beqz %1, 3f \n" " nop \n" " .subsection 2 \n" - "2: ll %1, %2 \n" - " bnez %1, 2b \n" + "3: ll %1, %2 \n" + " bnez %1, 3b \n" " lui %1, 0x8000 \n" - " b 1b \n" + " b 2b \n" " nop \n" " .previous \n" " .set reorder \n" diff --git a/arch/mips/include/asm/unistd.h b/arch/mips/include/asm/unistd.h index 550725b881d5..dae22c1d2c82 100644 --- a/arch/mips/include/asm/unistd.h +++ b/arch/mips/include/asm/unistd.h @@ -359,16 +359,20 @@ #define __NR_fanotify_init (__NR_Linux + 336) #define __NR_fanotify_mark (__NR_Linux + 337) #define __NR_prlimit64 (__NR_Linux + 338) +#define __NR_name_to_handle_at (__NR_Linux + 339) +#define __NR_open_by_handle_at (__NR_Linux + 340) +#define __NR_clock_adjtime (__NR_Linux + 341) +#define __NR_syncfs (__NR_Linux + 342) /* * Offset of the last Linux o32 flavoured syscall */ -#define __NR_Linux_syscalls 338 +#define __NR_Linux_syscalls 342 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */ #define __NR_O32_Linux 4000 -#define __NR_O32_Linux_syscalls 338 +#define __NR_O32_Linux_syscalls 342 #if _MIPS_SIM == _MIPS_SIM_ABI64 @@ -674,16 +678,20 @@ #define __NR_fanotify_init (__NR_Linux + 295) #define __NR_fanotify_mark (__NR_Linux + 296) #define __NR_prlimit64 (__NR_Linux + 297) +#define __NR_name_to_handle_at (__NR_Linux + 298) +#define __NR_open_by_handle_at (__NR_Linux + 299) +#define __NR_clock_adjtime (__NR_Linux + 300) +#define __NR_syncfs (__NR_Linux + 301) /* * Offset of the last Linux 64-bit flavoured syscall */ -#define __NR_Linux_syscalls 297 +#define __NR_Linux_syscalls 301 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */ #define __NR_64_Linux 5000 -#define __NR_64_Linux_syscalls 297 +#define __NR_64_Linux_syscalls 301 #if _MIPS_SIM == _MIPS_SIM_NABI32 @@ -994,16 +1002,20 @@ #define __NR_fanotify_init (__NR_Linux + 300) #define __NR_fanotify_mark (__NR_Linux + 301) #define __NR_prlimit64 (__NR_Linux + 302) +#define __NR_name_to_handle_at (__NR_Linux + 303) +#define __NR_open_by_handle_at (__NR_Linux + 304) +#define __NR_clock_adjtime (__NR_Linux + 305) +#define __NR_clock_adjtime (__NR_Linux + 306) /* * Offset of the last N32 flavoured syscall */ -#define __NR_Linux_syscalls 302 +#define __NR_Linux_syscalls 306 #endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */ #define __NR_N32_Linux 6000 -#define __NR_N32_Linux_syscalls 302 +#define __NR_N32_Linux_syscalls 306 #ifdef __KERNEL__ diff --git a/arch/mips/jazz/irq.c b/arch/mips/jazz/irq.c index 35b3e2f0af04..40f7c6b1e260 100644 --- a/arch/mips/jazz/irq.c +++ b/arch/mips/jazz/irq.c @@ -23,9 +23,9 @@ static DEFINE_RAW_SPINLOCK(r4030_lock); -static void enable_r4030_irq(unsigned int irq) +static void enable_r4030_irq(struct irq_data *d) { - unsigned int mask = 1 << (irq - JAZZ_IRQ_START); + unsigned int mask = 1 << (d->irq - JAZZ_IRQ_START); unsigned long flags; raw_spin_lock_irqsave(&r4030_lock, flags); @@ -34,9 +34,9 @@ static void enable_r4030_irq(unsigned int irq) raw_spin_unlock_irqrestore(&r4030_lock, flags); } -void disable_r4030_irq(unsigned int irq) +void disable_r4030_irq(struct irq_data *d) { - unsigned int mask = ~(1 << (irq - JAZZ_IRQ_START)); + unsigned int mask = ~(1 << (d->irq - JAZZ_IRQ_START)); unsigned long flags; raw_spin_lock_irqsave(&r4030_lock, flags); @@ -47,10 +47,8 @@ void disable_r4030_irq(unsigned int irq) static struct irq_chip r4030_irq_type = { .name = "R4030", - .ack = disable_r4030_irq, - .mask = disable_r4030_irq, - .mask_ack = disable_r4030_irq, - .unmask = enable_r4030_irq, + .irq_mask = disable_r4030_irq, + .irq_unmask = enable_r4030_irq, }; void __init init_r4030_ints(void) diff --git a/arch/mips/jz4740/board-qi_lb60.c b/arch/mips/jz4740/board-qi_lb60.c index 2c0e107966ad..bc18daaa8f84 100644 --- a/arch/mips/jz4740/board-qi_lb60.c +++ b/arch/mips/jz4740/board-qi_lb60.c @@ -23,6 +23,7 @@ #include <linux/spi/spi_gpio.h> #include <linux/power_supply.h> #include <linux/power/jz4740-battery.h> +#include <linux/power/gpio-charger.h> #include <asm/mach-jz4740/jz4740_fb.h> #include <asm/mach-jz4740/jz4740_mmc.h> @@ -49,14 +50,14 @@ static bool is_avt2; /* NAND */ static struct nand_ecclayout qi_lb60_ecclayout_1gb = { -/* .eccbytes = 36, + .eccbytes = 36, .eccpos = { 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41 - },*/ + }, .oobfree = { { .offset = 2, .length = 4 }, { .offset = 42, .length = 22 } @@ -85,7 +86,7 @@ static struct mtd_partition qi_lb60_partitions_1gb[] = { }; static struct nand_ecclayout qi_lb60_ecclayout_2gb = { -/* .eccbytes = 72, + .eccbytes = 72, .eccpos = { 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, @@ -96,7 +97,7 @@ static struct nand_ecclayout qi_lb60_ecclayout_2gb = { 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83 - },*/ + }, .oobfree = { { .offset = 2, .length = 10 }, { .offset = 84, .length = 44 }, @@ -396,6 +397,28 @@ static struct platform_device qi_lb60_pwm_beeper = { }, }; +/* charger */ +static char *qi_lb60_batteries[] = { + "battery", +}; + +static struct gpio_charger_platform_data qi_lb60_charger_pdata = { + .name = "usb", + .type = POWER_SUPPLY_TYPE_USB, + .gpio = JZ_GPIO_PORTD(28), + .gpio_active_low = 1, + .supplied_to = qi_lb60_batteries, + .num_supplicants = ARRAY_SIZE(qi_lb60_batteries), +}; + +static struct platform_device qi_lb60_charger_device = { + .name = "gpio-charger", + .dev = { + .platform_data = &qi_lb60_charger_pdata, + }, +}; + + static struct platform_device *jz_platform_devices[] __initdata = { &jz4740_udc_device, &jz4740_mmc_device, @@ -410,6 +433,7 @@ static struct platform_device *jz_platform_devices[] __initdata = { &jz4740_adc_device, &qi_lb60_gpio_keys, &qi_lb60_pwm_beeper, + &qi_lb60_charger_device, }; static void __init board_gpio_setup(void) diff --git a/arch/mips/jz4740/gpio.c b/arch/mips/jz4740/gpio.c index 88e6aeda5bf1..bd2fc29b95e0 100644 --- a/arch/mips/jz4740/gpio.c +++ b/arch/mips/jz4740/gpio.c @@ -86,7 +86,6 @@ struct jz_gpio_chip { spinlock_t lock; struct gpio_chip gpio_chip; - struct irq_chip irq_chip; struct sys_device sysdev; }; @@ -102,9 +101,9 @@ static inline struct jz_gpio_chip *gpio_chip_to_jz_gpio_chip(struct gpio_chip *g return container_of(gpio_chip, struct jz_gpio_chip, gpio_chip); } -static inline struct jz_gpio_chip *irq_to_jz_gpio_chip(unsigned int irq) +static inline struct jz_gpio_chip *irq_to_jz_gpio_chip(struct irq_data *data) { - return get_irq_chip_data(irq); + return irq_data_get_irq_chip_data(data); } static inline void jz_gpio_write_bit(unsigned int gpio, unsigned int reg) @@ -325,62 +324,52 @@ static void jz_gpio_irq_demux_handler(unsigned int irq, struct irq_desc *desc) generic_handle_irq(gpio_irq); }; -static inline void jz_gpio_set_irq_bit(unsigned int irq, unsigned int reg) +static inline void jz_gpio_set_irq_bit(struct irq_data *data, unsigned int reg) { - struct jz_gpio_chip *chip = irq_to_jz_gpio_chip(irq); - writel(IRQ_TO_BIT(irq), chip->base + reg); + struct jz_gpio_chip *chip = irq_to_jz_gpio_chip(data); + writel(IRQ_TO_BIT(data->irq), chip->base + reg); } -static void jz_gpio_irq_mask(unsigned int irq) +static void jz_gpio_irq_mask(struct irq_data *data) { - jz_gpio_set_irq_bit(irq, JZ_REG_GPIO_MASK_SET); + jz_gpio_set_irq_bit(data, JZ_REG_GPIO_MASK_SET); }; -static void jz_gpio_irq_unmask(unsigned int irq) +static void jz_gpio_irq_unmask(struct irq_data *data) { - struct jz_gpio_chip *chip = irq_to_jz_gpio_chip(irq); + struct jz_gpio_chip *chip = irq_to_jz_gpio_chip(data); - jz_gpio_check_trigger_both(chip, irq); + jz_gpio_check_trigger_both(chip, data->irq); - jz_gpio_set_irq_bit(irq, JZ_REG_GPIO_MASK_CLEAR); + jz_gpio_set_irq_bit(data, JZ_REG_GPIO_MASK_CLEAR); }; /* TODO: Check if function is gpio */ -static unsigned int jz_gpio_irq_startup(unsigned int irq) +static unsigned int jz_gpio_irq_startup(struct irq_data *data) { - struct irq_desc *desc = irq_to_desc(irq); - - jz_gpio_set_irq_bit(irq, JZ_REG_GPIO_SELECT_SET); - - desc->status &= ~IRQ_MASKED; - jz_gpio_irq_unmask(irq); - + jz_gpio_set_irq_bit(data, JZ_REG_GPIO_SELECT_SET); + jz_gpio_irq_unmask(data); return 0; } -static void jz_gpio_irq_shutdown(unsigned int irq) +static void jz_gpio_irq_shutdown(struct irq_data *data) { - struct irq_desc *desc = irq_to_desc(irq); - - jz_gpio_irq_mask(irq); - desc->status |= IRQ_MASKED; + jz_gpio_irq_mask(data); /* Set direction to input */ - jz_gpio_set_irq_bit(irq, JZ_REG_GPIO_DIRECTION_CLEAR); - jz_gpio_set_irq_bit(irq, JZ_REG_GPIO_SELECT_CLEAR); + jz_gpio_set_irq_bit(data, JZ_REG_GPIO_DIRECTION_CLEAR); + jz_gpio_set_irq_bit(data, JZ_REG_GPIO_SELECT_CLEAR); } -static void jz_gpio_irq_ack(unsigned int irq) +static void jz_gpio_irq_ack(struct irq_data *data) { - jz_gpio_set_irq_bit(irq, JZ_REG_GPIO_FLAG_CLEAR); + jz_gpio_set_irq_bit(data, JZ_REG_GPIO_FLAG_CLEAR); }; -static int jz_gpio_irq_set_type(unsigned int irq, unsigned int flow_type) +static int jz_gpio_irq_set_type(struct irq_data *data, unsigned int flow_type) { - struct jz_gpio_chip *chip = irq_to_jz_gpio_chip(irq); - struct irq_desc *desc = irq_to_desc(irq); - - jz_gpio_irq_mask(irq); + struct jz_gpio_chip *chip = irq_to_jz_gpio_chip(data); + unsigned int irq = data->irq; if (flow_type == IRQ_TYPE_EDGE_BOTH) { uint32_t value = readl(chip->base + JZ_REG_GPIO_PIN); @@ -395,45 +384,54 @@ static int jz_gpio_irq_set_type(unsigned int irq, unsigned int flow_type) switch (flow_type) { case IRQ_TYPE_EDGE_RISING: - jz_gpio_set_irq_bit(irq, JZ_REG_GPIO_DIRECTION_SET); - jz_gpio_set_irq_bit(irq, JZ_REG_GPIO_TRIGGER_SET); + jz_gpio_set_irq_bit(data, JZ_REG_GPIO_DIRECTION_SET); + jz_gpio_set_irq_bit(data, JZ_REG_GPIO_TRIGGER_SET); break; case IRQ_TYPE_EDGE_FALLING: - jz_gpio_set_irq_bit(irq, JZ_REG_GPIO_DIRECTION_CLEAR); - jz_gpio_set_irq_bit(irq, JZ_REG_GPIO_TRIGGER_SET); + jz_gpio_set_irq_bit(data, JZ_REG_GPIO_DIRECTION_CLEAR); + jz_gpio_set_irq_bit(data, JZ_REG_GPIO_TRIGGER_SET); break; case IRQ_TYPE_LEVEL_HIGH: - jz_gpio_set_irq_bit(irq, JZ_REG_GPIO_DIRECTION_SET); - jz_gpio_set_irq_bit(irq, JZ_REG_GPIO_TRIGGER_CLEAR); + jz_gpio_set_irq_bit(data, JZ_REG_GPIO_DIRECTION_SET); + jz_gpio_set_irq_bit(data, JZ_REG_GPIO_TRIGGER_CLEAR); break; case IRQ_TYPE_LEVEL_LOW: - jz_gpio_set_irq_bit(irq, JZ_REG_GPIO_DIRECTION_CLEAR); - jz_gpio_set_irq_bit(irq, JZ_REG_GPIO_TRIGGER_CLEAR); + jz_gpio_set_irq_bit(data, JZ_REG_GPIO_DIRECTION_CLEAR); + jz_gpio_set_irq_bit(data, JZ_REG_GPIO_TRIGGER_CLEAR); break; default: return -EINVAL; } - if (!(desc->status & IRQ_MASKED)) - jz_gpio_irq_unmask(irq); - return 0; } -static int jz_gpio_irq_set_wake(unsigned int irq, unsigned int on) +static int jz_gpio_irq_set_wake(struct irq_data *data, unsigned int on) { - struct jz_gpio_chip *chip = irq_to_jz_gpio_chip(irq); + struct jz_gpio_chip *chip = irq_to_jz_gpio_chip(data); spin_lock(&chip->lock); if (on) - chip->wakeup |= IRQ_TO_BIT(irq); + chip->wakeup |= IRQ_TO_BIT(data->irq); else - chip->wakeup &= ~IRQ_TO_BIT(irq); + chip->wakeup &= ~IRQ_TO_BIT(data->irq); spin_unlock(&chip->lock); set_irq_wake(chip->irq, on); return 0; } +static struct irq_chip jz_gpio_irq_chip = { + .name = "GPIO", + .irq_mask = jz_gpio_irq_mask, + .irq_unmask = jz_gpio_irq_unmask, + .irq_ack = jz_gpio_irq_ack, + .irq_startup = jz_gpio_irq_startup, + .irq_shutdown = jz_gpio_irq_shutdown, + .irq_set_type = jz_gpio_irq_set_type, + .irq_set_wake = jz_gpio_irq_set_wake, + .flags = IRQCHIP_SET_TYPE_MASKED, +}; + /* * This lock class tells lockdep that GPIO irqs are in a different * category than their parents, so it won't report false recursion. @@ -452,16 +450,6 @@ static struct lock_class_key gpio_lock_class; .base = JZ4740_GPIO_BASE_ ## _bank, \ .ngpio = JZ4740_GPIO_NUM_ ## _bank, \ }, \ - .irq_chip = { \ - .name = "GPIO Bank " # _bank, \ - .mask = jz_gpio_irq_mask, \ - .unmask = jz_gpio_irq_unmask, \ - .ack = jz_gpio_irq_ack, \ - .startup = jz_gpio_irq_startup, \ - .shutdown = jz_gpio_irq_shutdown, \ - .set_type = jz_gpio_irq_set_type, \ - .set_wake = jz_gpio_irq_set_wake, \ - }, \ } static struct jz_gpio_chip jz4740_gpio_chips[] = { @@ -526,9 +514,10 @@ static int jz4740_gpio_chip_init(struct jz_gpio_chip *chip, unsigned int id) set_irq_chained_handler(chip->irq, jz_gpio_irq_demux_handler); for (irq = chip->irq_base; irq < chip->irq_base + chip->gpio_chip.ngpio; ++irq) { - lockdep_set_class(&irq_desc[irq].lock, &gpio_lock_class); + irq_set_lockdep_class(irq, &gpio_lock_class); set_irq_chip_data(irq, chip); - set_irq_chip_and_handler(irq, &chip->irq_chip, handle_level_irq); + set_irq_chip_and_handler(irq, &jz_gpio_irq_chip, + handle_level_irq); } return 0; diff --git a/arch/mips/jz4740/irq.c b/arch/mips/jz4740/irq.c index 7d33ff83580f..dcc5593a9389 100644 --- a/arch/mips/jz4740/irq.c +++ b/arch/mips/jz4740/irq.c @@ -43,32 +43,37 @@ static uint32_t jz_intc_saved; #define IRQ_BIT(x) BIT((x) - JZ4740_IRQ_BASE) -static void intc_irq_unmask(unsigned int irq) +static inline unsigned long intc_irq_bit(struct irq_data *data) { - writel(IRQ_BIT(irq), jz_intc_base + JZ_REG_INTC_CLEAR_MASK); + return (unsigned long)irq_data_get_irq_chip_data(data); } -static void intc_irq_mask(unsigned int irq) +static void intc_irq_unmask(struct irq_data *data) { - writel(IRQ_BIT(irq), jz_intc_base + JZ_REG_INTC_SET_MASK); + writel(intc_irq_bit(data), jz_intc_base + JZ_REG_INTC_CLEAR_MASK); } -static int intc_irq_set_wake(unsigned int irq, unsigned int on) +static void intc_irq_mask(struct irq_data *data) +{ + writel(intc_irq_bit(data), jz_intc_base + JZ_REG_INTC_SET_MASK); +} + +static int intc_irq_set_wake(struct irq_data *data, unsigned int on) { if (on) - jz_intc_wakeup |= IRQ_BIT(irq); + jz_intc_wakeup |= intc_irq_bit(data); else - jz_intc_wakeup &= ~IRQ_BIT(irq); + jz_intc_wakeup &= ~intc_irq_bit(data); return 0; } static struct irq_chip intc_irq_type = { .name = "INTC", - .mask = intc_irq_mask, - .mask_ack = intc_irq_mask, - .unmask = intc_irq_unmask, - .set_wake = intc_irq_set_wake, + .irq_mask = intc_irq_mask, + .irq_mask_ack = intc_irq_mask, + .irq_unmask = intc_irq_unmask, + .irq_set_wake = intc_irq_set_wake, }; static irqreturn_t jz4740_cascade(int irq, void *data) @@ -95,8 +100,11 @@ void __init arch_init_irq(void) jz_intc_base = ioremap(JZ4740_INTC_BASE_ADDR, 0x14); + /* Mask all irqs */ + writel(0xffffffff, jz_intc_base + JZ_REG_INTC_SET_MASK); + for (i = JZ4740_IRQ_BASE; i < JZ4740_IRQ_BASE + 32; i++) { - intc_irq_mask(i); + set_irq_chip_data(i, (void *)IRQ_BIT(i)); set_irq_chip_and_handler(i, &intc_irq_type, handle_level_irq); } diff --git a/arch/mips/kernel/i8259.c b/arch/mips/kernel/i8259.c index c58176cc796b..e221662bb80c 100644 --- a/arch/mips/kernel/i8259.c +++ b/arch/mips/kernel/i8259.c @@ -31,19 +31,19 @@ static int i8259A_auto_eoi = -1; DEFINE_RAW_SPINLOCK(i8259A_lock); -static void disable_8259A_irq(unsigned int irq); -static void enable_8259A_irq(unsigned int irq); -static void mask_and_ack_8259A(unsigned int irq); +static void disable_8259A_irq(struct irq_data *d); +static void enable_8259A_irq(struct irq_data *d); +static void mask_and_ack_8259A(struct irq_data *d); static void init_8259A(int auto_eoi); static struct irq_chip i8259A_chip = { - .name = "XT-PIC", - .mask = disable_8259A_irq, - .disable = disable_8259A_irq, - .unmask = enable_8259A_irq, - .mask_ack = mask_and_ack_8259A, + .name = "XT-PIC", + .irq_mask = disable_8259A_irq, + .irq_disable = disable_8259A_irq, + .irq_unmask = enable_8259A_irq, + .irq_mask_ack = mask_and_ack_8259A, #ifdef CONFIG_MIPS_MT_SMTC_IRQAFF - .set_affinity = plat_set_irq_affinity, + .irq_set_affinity = plat_set_irq_affinity, #endif /* CONFIG_MIPS_MT_SMTC_IRQAFF */ }; @@ -59,12 +59,11 @@ static unsigned int cached_irq_mask = 0xffff; #define cached_master_mask (cached_irq_mask) #define cached_slave_mask (cached_irq_mask >> 8) -static void disable_8259A_irq(unsigned int irq) +static void disable_8259A_irq(struct irq_data *d) { - unsigned int mask; + unsigned int mask, irq = d->irq - I8259A_IRQ_BASE; unsigned long flags; - irq -= I8259A_IRQ_BASE; mask = 1 << irq; raw_spin_lock_irqsave(&i8259A_lock, flags); cached_irq_mask |= mask; @@ -75,12 +74,11 @@ static void disable_8259A_irq(unsigned int irq) raw_spin_unlock_irqrestore(&i8259A_lock, flags); } -static void enable_8259A_irq(unsigned int irq) +static void enable_8259A_irq(struct irq_data *d) { - unsigned int mask; + unsigned int mask, irq = d->irq - I8259A_IRQ_BASE; unsigned long flags; - irq -= I8259A_IRQ_BASE; mask = ~(1 << irq); raw_spin_lock_irqsave(&i8259A_lock, flags); cached_irq_mask &= mask; @@ -145,12 +143,11 @@ static inline int i8259A_irq_real(unsigned int irq) * first, _then_ send the EOI, and the order of EOI * to the two 8259s is important! */ -static void mask_and_ack_8259A(unsigned int irq) +static void mask_and_ack_8259A(struct irq_data *d) { - unsigned int irqmask; + unsigned int irqmask, irq = d->irq - I8259A_IRQ_BASE; unsigned long flags; - irq -= I8259A_IRQ_BASE; irqmask = 1 << irq; raw_spin_lock_irqsave(&i8259A_lock, flags); /* @@ -290,9 +287,9 @@ static void init_8259A(int auto_eoi) * In AEOI mode we just have to mask the interrupt * when acking. */ - i8259A_chip.mask_ack = disable_8259A_irq; + i8259A_chip.irq_mask_ack = disable_8259A_irq; else - i8259A_chip.mask_ack = mask_and_ack_8259A; + i8259A_chip.irq_mask_ack = mask_and_ack_8259A; udelay(100); /* wait for 8259A to initialize */ diff --git a/arch/mips/kernel/irq-gic.c b/arch/mips/kernel/irq-gic.c index 1774271af848..43cd9628251a 100644 --- a/arch/mips/kernel/irq-gic.c +++ b/arch/mips/kernel/irq-gic.c @@ -87,17 +87,10 @@ unsigned int gic_get_int(void) return i; } -static unsigned int gic_irq_startup(unsigned int irq) +static void gic_irq_ack(struct irq_data *d) { - irq -= _irqbase; - pr_debug("CPU%d: %s: irq%d\n", smp_processor_id(), __func__, irq); - GIC_SET_INTR_MASK(irq); - return 0; -} + unsigned int irq = d->irq - _irqbase; -static void gic_irq_ack(unsigned int irq) -{ - irq -= _irqbase; pr_debug("CPU%d: %s: irq%d\n", smp_processor_id(), __func__, irq); GIC_CLR_INTR_MASK(irq); @@ -105,16 +98,16 @@ static void gic_irq_ack(unsigned int irq) GICWRITE(GIC_REG(SHARED, GIC_SH_WEDGE), irq); } -static void gic_mask_irq(unsigned int irq) +static void gic_mask_irq(struct irq_data *d) { - irq -= _irqbase; + unsigned int irq = d->irq - _irqbase; pr_debug("CPU%d: %s: irq%d\n", smp_processor_id(), __func__, irq); GIC_CLR_INTR_MASK(irq); } -static void gic_unmask_irq(unsigned int irq) +static void gic_unmask_irq(struct irq_data *d) { - irq -= _irqbase; + unsigned int irq = d->irq - _irqbase; pr_debug("CPU%d: %s: irq%d\n", smp_processor_id(), __func__, irq); GIC_SET_INTR_MASK(irq); } @@ -123,13 +116,14 @@ static void gic_unmask_irq(unsigned int irq) static DEFINE_SPINLOCK(gic_lock); -static int gic_set_affinity(unsigned int irq, const struct cpumask *cpumask) +static int gic_set_affinity(struct irq_data *d, const struct cpumask *cpumask, + bool force) { + unsigned int irq = d->irq - _irqbase; cpumask_t tmp = CPU_MASK_NONE; unsigned long flags; int i; - irq -= _irqbase; pr_debug("%s(%d) called\n", __func__, irq); cpumask_and(&tmp, cpumask, cpu_online_mask); if (cpus_empty(tmp)) @@ -147,23 +141,22 @@ static int gic_set_affinity(unsigned int irq, const struct cpumask *cpumask) set_bit(irq, pcpu_masks[first_cpu(tmp)].pcpu_mask); } - cpumask_copy(irq_desc[irq].affinity, cpumask); + cpumask_copy(d->affinity, cpumask); spin_unlock_irqrestore(&gic_lock, flags); - return 0; + return IRQ_SET_MASK_OK_NOCOPY; } #endif static struct irq_chip gic_irq_controller = { - .name = "MIPS GIC", - .startup = gic_irq_startup, - .ack = gic_irq_ack, - .mask = gic_mask_irq, - .mask_ack = gic_mask_irq, - .unmask = gic_unmask_irq, - .eoi = gic_unmask_irq, + .name = "MIPS GIC", + .irq_ack = gic_irq_ack, + .irq_mask = gic_mask_irq, + .irq_mask_ack = gic_mask_irq, + .irq_unmask = gic_unmask_irq, + .irq_eoi = gic_unmask_irq, #ifdef CONFIG_SMP - .set_affinity = gic_set_affinity, + .irq_set_affinity = gic_set_affinity, #endif }; diff --git a/arch/mips/kernel/irq-gt641xx.c b/arch/mips/kernel/irq-gt641xx.c index 42ef81461bfc..7fd176fa367a 100644 --- a/arch/mips/kernel/irq-gt641xx.c +++ b/arch/mips/kernel/irq-gt641xx.c @@ -29,64 +29,64 @@ static DEFINE_RAW_SPINLOCK(gt641xx_irq_lock); -static void ack_gt641xx_irq(unsigned int irq) +static void ack_gt641xx_irq(struct irq_data *d) { unsigned long flags; u32 cause; raw_spin_lock_irqsave(>641xx_irq_lock, flags); cause = GT_READ(GT_INTRCAUSE_OFS); - cause &= ~GT641XX_IRQ_TO_BIT(irq); + cause &= ~GT641XX_IRQ_TO_BIT(d->irq); GT_WRITE(GT_INTRCAUSE_OFS, cause); raw_spin_unlock_irqrestore(>641xx_irq_lock, flags); } -static void mask_gt641xx_irq(unsigned int irq) +static void mask_gt641xx_irq(struct irq_data *d) { unsigned long flags; u32 mask; raw_spin_lock_irqsave(>641xx_irq_lock, flags); mask = GT_READ(GT_INTRMASK_OFS); - mask &= ~GT641XX_IRQ_TO_BIT(irq); + mask &= ~GT641XX_IRQ_TO_BIT(d->irq); GT_WRITE(GT_INTRMASK_OFS, mask); raw_spin_unlock_irqrestore(>641xx_irq_lock, flags); } -static void mask_ack_gt641xx_irq(unsigned int irq) +static void mask_ack_gt641xx_irq(struct irq_data *d) { unsigned long flags; u32 cause, mask; raw_spin_lock_irqsave(>641xx_irq_lock, flags); mask = GT_READ(GT_INTRMASK_OFS); - mask &= ~GT641XX_IRQ_TO_BIT(irq); + mask &= ~GT641XX_IRQ_TO_BIT(d->irq); GT_WRITE(GT_INTRMASK_OFS, mask); cause = GT_READ(GT_INTRCAUSE_OFS); - cause &= ~GT641XX_IRQ_TO_BIT(irq); + cause &= ~GT641XX_IRQ_TO_BIT(d->irq); GT_WRITE(GT_INTRCAUSE_OFS, cause); raw_spin_unlock_irqrestore(>641xx_irq_lock, flags); } -static void unmask_gt641xx_irq(unsigned int irq) +static void unmask_gt641xx_irq(struct irq_data *d) { unsigned long flags; u32 mask; raw_spin_lock_irqsave(>641xx_irq_lock, flags); mask = GT_READ(GT_INTRMASK_OFS); - mask |= GT641XX_IRQ_TO_BIT(irq); + mask |= GT641XX_IRQ_TO_BIT(d->irq); GT_WRITE(GT_INTRMASK_OFS, mask); raw_spin_unlock_irqrestore(>641xx_irq_lock, flags); } static struct irq_chip gt641xx_irq_chip = { .name = "GT641xx", - .ack = ack_gt641xx_irq, - .mask = mask_gt641xx_irq, - .mask_ack = mask_ack_gt641xx_irq, - .unmask = unmask_gt641xx_irq, + .irq_ack = ack_gt641xx_irq, + .irq_mask = mask_gt641xx_irq, + .irq_mask_ack = mask_ack_gt641xx_irq, + .irq_unmask = unmask_gt641xx_irq, }; void gt641xx_irq_dispatch(void) diff --git a/arch/mips/kernel/irq-msc01.c b/arch/mips/kernel/irq-msc01.c index 6a8cd28133d5..fc800cd9947e 100644 --- a/arch/mips/kernel/irq-msc01.c +++ b/arch/mips/kernel/irq-msc01.c @@ -28,8 +28,10 @@ static unsigned long _icctrl_msc; static unsigned int irq_base; /* mask off an interrupt */ -static inline void mask_msc_irq(unsigned int irq) +static inline void mask_msc_irq(struct irq_data *d) { + unsigned int irq = d->irq; + if (irq < (irq_base + 32)) MSCIC_WRITE(MSC01_IC_DISL, 1<<(irq - irq_base)); else @@ -37,8 +39,10 @@ static inline void mask_msc_irq(unsigned int irq) } /* unmask an interrupt */ -static inline void unmask_msc_irq(unsigned int irq) +static inline void unmask_msc_irq(struct irq_data *d) { + unsigned int irq = d->irq; + if (irq < (irq_base + 32)) MSCIC_WRITE(MSC01_IC_ENAL, 1<<(irq - irq_base)); else @@ -48,9 +52,11 @@ static inline void unmask_msc_irq(unsigned int irq) /* * Masks and ACKs an IRQ */ -static void level_mask_and_ack_msc_irq(unsigned int irq) +static void level_mask_and_ack_msc_irq(struct irq_data *d) { - mask_msc_irq(irq); + unsigned int irq = d->irq; + + mask_msc_irq(d); if (!cpu_has_veic) MSCIC_WRITE(MSC01_IC_EOI, 0); /* This actually needs to be a call into platform code */ @@ -60,9 +66,11 @@ static void level_mask_and_ack_msc_irq(unsigned int irq) /* * Masks and ACKs an IRQ */ -static void edge_mask_and_ack_msc_irq(unsigned int irq) +static void edge_mask_and_ack_msc_irq(struct irq_data *d) { - mask_msc_irq(irq); + unsigned int irq = d->irq; + + mask_msc_irq(d); if (!cpu_has_veic) MSCIC_WRITE(MSC01_IC_EOI, 0); else { @@ -75,15 +83,6 @@ static void edge_mask_and_ack_msc_irq(unsigned int irq) } /* - * End IRQ processing - */ -static void end_msc_irq(unsigned int irq) -{ - if (!(irq_desc[irq].status & (IRQ_DISABLED|IRQ_INPROGRESS))) - unmask_msc_irq(irq); -} - -/* * Interrupt handler for interrupts coming from SOC-it. */ void ll_msc_irq(void) @@ -107,22 +106,20 @@ static void msc_bind_eic_interrupt(int irq, int set) static struct irq_chip msc_levelirq_type = { .name = "SOC-it-Level", - .ack = level_mask_and_ack_msc_irq, - .mask = mask_msc_irq, - .mask_ack = level_mask_and_ack_msc_irq, - .unmask = unmask_msc_irq, - .eoi = unmask_msc_irq, - .end = end_msc_irq, + .irq_ack = level_mask_and_ack_msc_irq, + .irq_mask = mask_msc_irq, + .irq_mask_ack = level_mask_and_ack_msc_irq, + .irq_unmask = unmask_msc_irq, + .irq_eoi = unmask_msc_irq, }; static struct irq_chip msc_edgeirq_type = { .name = "SOC-it-Edge", - .ack = edge_mask_and_ack_msc_irq, - .mask = mask_msc_irq, - .mask_ack = edge_mask_and_ack_msc_irq, - .unmask = unmask_msc_irq, - .eoi = unmask_msc_irq, - .end = end_msc_irq, + .irq_ack = edge_mask_and_ack_msc_irq, + .irq_mask = mask_msc_irq, + .irq_mask_ack = edge_mask_and_ack_msc_irq, + .irq_unmask = unmask_msc_irq, + .irq_eoi = unmask_msc_irq, }; diff --git a/arch/mips/kernel/irq-rm7000.c b/arch/mips/kernel/irq-rm7000.c index 9731e8b47862..fd24fd98b041 100644 --- a/arch/mips/kernel/irq-rm7000.c +++ b/arch/mips/kernel/irq-rm7000.c @@ -18,23 +18,23 @@ #include <asm/mipsregs.h> #include <asm/system.h> -static inline void unmask_rm7k_irq(unsigned int irq) +static inline void unmask_rm7k_irq(struct irq_data *d) { - set_c0_intcontrol(0x100 << (irq - RM7K_CPU_IRQ_BASE)); + set_c0_intcontrol(0x100 << (d->irq - RM7K_CPU_IRQ_BASE)); } -static inline void mask_rm7k_irq(unsigned int irq) +static inline void mask_rm7k_irq(struct irq_data *d) { - clear_c0_intcontrol(0x100 << (irq - RM7K_CPU_IRQ_BASE)); + clear_c0_intcontrol(0x100 << (d->irq - RM7K_CPU_IRQ_BASE)); } static struct irq_chip rm7k_irq_controller = { .name = "RM7000", - .ack = mask_rm7k_irq, - .mask = mask_rm7k_irq, - .mask_ack = mask_rm7k_irq, - .unmask = unmask_rm7k_irq, - .eoi = unmask_rm7k_irq + .irq_ack = mask_rm7k_irq, + .irq_mask = mask_rm7k_irq, + .irq_mask_ack = mask_rm7k_irq, + .irq_unmask = unmask_rm7k_irq, + .irq_eoi = unmask_rm7k_irq }; void __init rm7k_cpu_irq_init(void) diff --git a/arch/mips/kernel/irq-rm9000.c b/arch/mips/kernel/irq-rm9000.c index b7e4025b58a8..ca463ec9bad5 100644 --- a/arch/mips/kernel/irq-rm9000.c +++ b/arch/mips/kernel/irq-rm9000.c @@ -19,22 +19,22 @@ #include <asm/mipsregs.h> #include <asm/system.h> -static inline void unmask_rm9k_irq(unsigned int irq) +static inline void unmask_rm9k_irq(struct irq_data *d) { - set_c0_intcontrol(0x1000 << (irq - RM9K_CPU_IRQ_BASE)); + set_c0_intcontrol(0x1000 << (d->irq - RM9K_CPU_IRQ_BASE)); } -static inline void mask_rm9k_irq(unsigned int irq) +static inline void mask_rm9k_irq(struct irq_data *d) { - clear_c0_intcontrol(0x1000 << (irq - RM9K_CPU_IRQ_BASE)); + clear_c0_intcontrol(0x1000 << (d->irq - RM9K_CPU_IRQ_BASE)); } -static inline void rm9k_cpu_irq_enable(unsigned int irq) +static inline void rm9k_cpu_irq_enable(struct irq_data *d) { unsigned long flags; local_irq_save(flags); - unmask_rm9k_irq(irq); + unmask_rm9k_irq(d); local_irq_restore(flags); } @@ -43,50 +43,47 @@ static inline void rm9k_cpu_irq_enable(unsigned int irq) */ static void local_rm9k_perfcounter_irq_startup(void *args) { - unsigned int irq = (unsigned int) args; - - rm9k_cpu_irq_enable(irq); + rm9k_cpu_irq_enable(args); } -static unsigned int rm9k_perfcounter_irq_startup(unsigned int irq) +static unsigned int rm9k_perfcounter_irq_startup(struct irq_data *d) { - on_each_cpu(local_rm9k_perfcounter_irq_startup, (void *) irq, 1); + on_each_cpu(local_rm9k_perfcounter_irq_startup, d, 1); return 0; } static void local_rm9k_perfcounter_irq_shutdown(void *args) { - unsigned int irq = (unsigned int) args; unsigned long flags; local_irq_save(flags); - mask_rm9k_irq(irq); + mask_rm9k_irq(args); local_irq_restore(flags); } -static void rm9k_perfcounter_irq_shutdown(unsigned int irq) +static void rm9k_perfcounter_irq_shutdown(struct irq_data *d) { - on_each_cpu(local_rm9k_perfcounter_irq_shutdown, (void *) irq, 1); + on_each_cpu(local_rm9k_perfcounter_irq_shutdown, d, 1); } static struct irq_chip rm9k_irq_controller = { .name = "RM9000", - .ack = mask_rm9k_irq, - .mask = mask_rm9k_irq, - .mask_ack = mask_rm9k_irq, - .unmask = unmask_rm9k_irq, - .eoi = unmask_rm9k_irq + .irq_ack = mask_rm9k_irq, + .irq_mask = mask_rm9k_irq, + .irq_mask_ack = mask_rm9k_irq, + .irq_unmask = unmask_rm9k_irq, + .irq_eoi = unmask_rm9k_irq }; static struct irq_chip rm9k_perfcounter_irq = { .name = "RM9000", - .startup = rm9k_perfcounter_irq_startup, - .shutdown = rm9k_perfcounter_irq_shutdown, - .ack = mask_rm9k_irq, - .mask = mask_rm9k_irq, - .mask_ack = mask_rm9k_irq, - .unmask = unmask_rm9k_irq, + .irq_startup = rm9k_perfcounter_irq_startup, + .irq_shutdown = rm9k_perfcounter_irq_shutdown, + .irq_ack = mask_rm9k_irq, + .irq_mask = mask_rm9k_irq, + .irq_mask_ack = mask_rm9k_irq, + .irq_unmask = unmask_rm9k_irq, }; unsigned int rm9000_perfcount_irq; diff --git a/arch/mips/kernel/irq.c b/arch/mips/kernel/irq.c index 4f93db58a79e..1b68ebe1b458 100644 --- a/arch/mips/kernel/irq.c +++ b/arch/mips/kernel/irq.c @@ -81,48 +81,9 @@ void ack_bad_irq(unsigned int irq) atomic_t irq_err_count; -/* - * Generic, controller-independent functions: - */ - -int show_interrupts(struct seq_file *p, void *v) +int arch_show_interrupts(struct seq_file *p, int prec) { - int i = *(loff_t *) v, j; - struct irqaction * action; - unsigned long flags; - - if (i == 0) { - seq_printf(p, " "); - for_each_online_cpu(j) - seq_printf(p, "CPU%d ", j); - seq_putc(p, '\n'); - } - - if (i < NR_IRQS) { - raw_spin_lock_irqsave(&irq_desc[i].lock, flags); - action = irq_desc[i].action; - if (!action) - goto skip; - seq_printf(p, "%3d: ", i); -#ifndef CONFIG_SMP - seq_printf(p, "%10u ", kstat_irqs(i)); -#else - for_each_online_cpu(j) - seq_printf(p, "%10u ", kstat_irqs_cpu(i, j)); -#endif - seq_printf(p, " %14s", irq_desc[i].chip->name); - seq_printf(p, " %s", action->name); - - for (action=action->next; action; action = action->next) - seq_printf(p, ", %s", action->name); - - seq_putc(p, '\n'); -skip: - raw_spin_unlock_irqrestore(&irq_desc[i].lock, flags); - } else if (i == NR_IRQS) { - seq_putc(p, '\n'); - seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count)); - } + seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count)); return 0; } @@ -183,8 +144,8 @@ void __irq_entry do_IRQ(unsigned int irq) { irq_enter(); check_stack_overflow(); - __DO_IRQ_SMTC_HOOK(irq); - generic_handle_irq(irq); + if (!smtc_handle_on_other_cpu(irq)) + generic_handle_irq(irq); irq_exit(); } @@ -197,7 +158,7 @@ void __irq_entry do_IRQ(unsigned int irq) void __irq_entry do_IRQ_no_affinity(unsigned int irq) { irq_enter(); - __NO_AFFINITY_IRQ_SMTC_HOOK(irq); + smtc_im_backstop(irq); generic_handle_irq(irq); irq_exit(); } diff --git a/arch/mips/kernel/irq_cpu.c b/arch/mips/kernel/irq_cpu.c index 0262abe09121..fd945c56bc33 100644 --- a/arch/mips/kernel/irq_cpu.c +++ b/arch/mips/kernel/irq_cpu.c @@ -37,42 +37,38 @@ #include <asm/mipsmtregs.h> #include <asm/system.h> -static inline void unmask_mips_irq(unsigned int irq) +static inline void unmask_mips_irq(struct irq_data *d) { - set_c0_status(0x100 << (irq - MIPS_CPU_IRQ_BASE)); + set_c0_status(0x100 << (d->irq - MIPS_CPU_IRQ_BASE)); irq_enable_hazard(); } -static inline void mask_mips_irq(unsigned int irq) +static inline void mask_mips_irq(struct irq_data *d) { - clear_c0_status(0x100 << (irq - MIPS_CPU_IRQ_BASE)); + clear_c0_status(0x100 << (d->irq - MIPS_CPU_IRQ_BASE)); irq_disable_hazard(); } static struct irq_chip mips_cpu_irq_controller = { .name = "MIPS", - .ack = mask_mips_irq, - .mask = mask_mips_irq, - .mask_ack = mask_mips_irq, - .unmask = unmask_mips_irq, - .eoi = unmask_mips_irq, + .irq_ack = mask_mips_irq, + .irq_mask = mask_mips_irq, + .irq_mask_ack = mask_mips_irq, + .irq_unmask = unmask_mips_irq, + .irq_eoi = unmask_mips_irq, }; /* * Basically the same as above but taking care of all the MT stuff */ -#define unmask_mips_mt_irq unmask_mips_irq -#define mask_mips_mt_irq mask_mips_irq - -static unsigned int mips_mt_cpu_irq_startup(unsigned int irq) +static unsigned int mips_mt_cpu_irq_startup(struct irq_data *d) { unsigned int vpflags = dvpe(); - clear_c0_cause(0x100 << (irq - MIPS_CPU_IRQ_BASE)); + clear_c0_cause(0x100 << (d->irq - MIPS_CPU_IRQ_BASE)); evpe(vpflags); - unmask_mips_mt_irq(irq); - + unmask_mips_irq(d); return 0; } @@ -80,22 +76,22 @@ static unsigned int mips_mt_cpu_irq_startup(unsigned int irq) * While we ack the interrupt interrupts are disabled and thus we don't need * to deal with concurrency issues. Same for mips_cpu_irq_end. */ -static void mips_mt_cpu_irq_ack(unsigned int irq) +static void mips_mt_cpu_irq_ack(struct irq_data *d) { unsigned int vpflags = dvpe(); - clear_c0_cause(0x100 << (irq - MIPS_CPU_IRQ_BASE)); + clear_c0_cause(0x100 << (d->irq - MIPS_CPU_IRQ_BASE)); evpe(vpflags); - mask_mips_mt_irq(irq); + mask_mips_irq(d); } static struct irq_chip mips_mt_cpu_irq_controller = { .name = "MIPS", - .startup = mips_mt_cpu_irq_startup, - .ack = mips_mt_cpu_irq_ack, - .mask = mask_mips_mt_irq, - .mask_ack = mips_mt_cpu_irq_ack, - .unmask = unmask_mips_mt_irq, - .eoi = unmask_mips_mt_irq, + .irq_startup = mips_mt_cpu_irq_startup, + .irq_ack = mips_mt_cpu_irq_ack, + .irq_mask = mask_mips_irq, + .irq_mask_ack = mips_mt_cpu_irq_ack, + .irq_unmask = unmask_mips_irq, + .irq_eoi = unmask_mips_irq, }; void __init mips_cpu_irq_init(void) diff --git a/arch/mips/kernel/irq_txx9.c b/arch/mips/kernel/irq_txx9.c index 95a96f69172d..526e1581549a 100644 --- a/arch/mips/kernel/irq_txx9.c +++ b/arch/mips/kernel/irq_txx9.c @@ -63,9 +63,9 @@ static struct { unsigned char mode; } txx9irq[TXx9_MAX_IR] __read_mostly; -static void txx9_irq_unmask(unsigned int irq) +static void txx9_irq_unmask(struct irq_data *d) { - unsigned int irq_nr = irq - TXX9_IRQ_BASE; + unsigned int irq_nr = d->irq - TXX9_IRQ_BASE; u32 __iomem *ilrp = &txx9_ircptr->ilr[(irq_nr % 16 ) / 2]; int ofs = irq_nr / 16 * 16 + (irq_nr & 1) * 8; @@ -79,9 +79,9 @@ static void txx9_irq_unmask(unsigned int irq) #endif } -static inline void txx9_irq_mask(unsigned int irq) +static inline void txx9_irq_mask(struct irq_data *d) { - unsigned int irq_nr = irq - TXX9_IRQ_BASE; + unsigned int irq_nr = d->irq - TXX9_IRQ_BASE; u32 __iomem *ilrp = &txx9_ircptr->ilr[(irq_nr % 16) / 2]; int ofs = irq_nr / 16 * 16 + (irq_nr & 1) * 8; @@ -99,19 +99,19 @@ static inline void txx9_irq_mask(unsigned int irq) #endif } -static void txx9_irq_mask_ack(unsigned int irq) +static void txx9_irq_mask_ack(struct irq_data *d) { - unsigned int irq_nr = irq - TXX9_IRQ_BASE; + unsigned int irq_nr = d->irq - TXX9_IRQ_BASE; - txx9_irq_mask(irq); + txx9_irq_mask(d); /* clear edge detection */ if (unlikely(TXx9_IRCR_EDGE(txx9irq[irq_nr].mode))) __raw_writel(TXx9_IRSCR_EIClrE | irq_nr, &txx9_ircptr->scr); } -static int txx9_irq_set_type(unsigned int irq, unsigned int flow_type) +static int txx9_irq_set_type(struct irq_data *d, unsigned int flow_type) { - unsigned int irq_nr = irq - TXX9_IRQ_BASE; + unsigned int irq_nr = d->irq - TXX9_IRQ_BASE; u32 cr; u32 __iomem *crp; int ofs; @@ -139,11 +139,11 @@ static int txx9_irq_set_type(unsigned int irq, unsigned int flow_type) static struct irq_chip txx9_irq_chip = { .name = "TXX9", - .ack = txx9_irq_mask_ack, - .mask = txx9_irq_mask, - .mask_ack = txx9_irq_mask_ack, - .unmask = txx9_irq_unmask, - .set_type = txx9_irq_set_type, + .irq_ack = txx9_irq_mask_ack, + .irq_mask = txx9_irq_mask, + .irq_mask_ack = txx9_irq_mask_ack, + .irq_unmask = txx9_irq_unmask, + .irq_set_type = txx9_irq_set_type, }; void __init txx9_irq_init(unsigned long baseaddr) diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S index fbaabad0e6e2..7f5468b38d4c 100644 --- a/arch/mips/kernel/scall32-o32.S +++ b/arch/mips/kernel/scall32-o32.S @@ -586,6 +586,10 @@ einval: li v0, -ENOSYS sys sys_fanotify_init 2 sys sys_fanotify_mark 6 sys sys_prlimit64 4 + sys sys_name_to_handle_at 5 + sys sys_open_by_handle_at 3 /* 4340 */ + sys sys_clock_adjtime 2 + sys sys_syncfs 1 .endm /* We pre-compute the number of _instruction_ bytes needed to diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S index 3f4179283207..a2e1fcbc41dc 100644 --- a/arch/mips/kernel/scall64-64.S +++ b/arch/mips/kernel/scall64-64.S @@ -425,4 +425,8 @@ sys_call_table: PTR sys_fanotify_init /* 5295 */ PTR sys_fanotify_mark PTR sys_prlimit64 + PTR sys_name_to_handle_at + PTR sys_open_by_handle_at + PTR sys_clock_adjtime /* 5300 */ + PTR sys_syncfs .size sys_call_table,.-sys_call_table diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index f08ece6d8acc..b2c7624995b8 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -425,4 +425,8 @@ EXPORT(sysn32_call_table) PTR sys_fanotify_init /* 6300 */ PTR sys_fanotify_mark PTR sys_prlimit64 + PTR sys_name_to_handle_at + PTR sys_open_by_handle_at + PTR compat_sys_clock_adjtime /* 6305 */ + PTR sys_syncfs .size sysn32_call_table,.-sysn32_call_table diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index 78d768a3e19d..049a9c8c49a0 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -543,4 +543,8 @@ sys_call_table: PTR sys_fanotify_init PTR sys_32_fanotify_mark PTR sys_prlimit64 + PTR sys_name_to_handle_at + PTR compat_sys_open_by_handle_at /* 4340 */ + PTR compat_sys_clock_adjtime + PTR sys_syncfs .size sys_call_table,.-sys_call_table diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c index 39c08254b0f1..f7e2c7807d7b 100644 --- a/arch/mips/kernel/smtc.c +++ b/arch/mips/kernel/smtc.c @@ -677,8 +677,9 @@ void smtc_set_irq_affinity(unsigned int irq, cpumask_t affinity) */ } -void smtc_forward_irq(unsigned int irq) +void smtc_forward_irq(struct irq_data *d) { + unsigned int irq = d->irq; int target; /* @@ -692,7 +693,7 @@ void smtc_forward_irq(unsigned int irq) * and efficiency, we just pick the easiest one to find. */ - target = cpumask_first(irq_desc[irq].affinity); + target = cpumask_first(d->affinity); /* * We depend on the platform code to have correctly processed @@ -707,12 +708,10 @@ void smtc_forward_irq(unsigned int irq) */ /* If no one is eligible, service locally */ - if (target >= NR_CPUS) { + if (target >= NR_CPUS) do_IRQ_no_affinity(irq); - return; - } - - smtc_send_ipi(target, IRQ_AFFINITY_IPI, irq); + else + smtc_send_ipi(target, IRQ_AFFINITY_IPI, irq); } #endif /* CONFIG_MIPS_MT_SMTC_IRQAFF */ diff --git a/arch/mips/lasat/interrupt.c b/arch/mips/lasat/interrupt.c index 1353fb135ed3..670e3e70d198 100644 --- a/arch/mips/lasat/interrupt.c +++ b/arch/mips/lasat/interrupt.c @@ -32,24 +32,24 @@ static volatile int *lasat_int_status; static volatile int *lasat_int_mask; static volatile int lasat_int_mask_shift; -void disable_lasat_irq(unsigned int irq_nr) +void disable_lasat_irq(struct irq_data *d) { - irq_nr -= LASAT_IRQ_BASE; + unsigned int irq_nr = d->irq - LASAT_IRQ_BASE; + *lasat_int_mask &= ~(1 << irq_nr) << lasat_int_mask_shift; } -void enable_lasat_irq(unsigned int irq_nr) +void enable_lasat_irq(struct irq_data *d) { - irq_nr -= LASAT_IRQ_BASE; + unsigned int irq_nr = d->irq - LASAT_IRQ_BASE; + *lasat_int_mask |= (1 << irq_nr) << lasat_int_mask_shift; } static struct irq_chip lasat_irq_type = { .name = "Lasat", - .ack = disable_lasat_irq, - .mask = disable_lasat_irq, - .mask_ack = disable_lasat_irq, - .unmask = enable_lasat_irq, + .irq_mask = disable_lasat_irq, + .irq_unmask = enable_lasat_irq, }; static inline int ls1bit32(unsigned int x) diff --git a/arch/mips/loongson/common/bonito-irq.c b/arch/mips/loongson/common/bonito-irq.c index 2dc2a4cc632a..1549361696ad 100644 --- a/arch/mips/loongson/common/bonito-irq.c +++ b/arch/mips/loongson/common/bonito-irq.c @@ -16,24 +16,22 @@ #include <loongson.h> -static inline void bonito_irq_enable(unsigned int irq) +static inline void bonito_irq_enable(struct irq_data *d) { - LOONGSON_INTENSET = (1 << (irq - LOONGSON_IRQ_BASE)); + LOONGSON_INTENSET = (1 << (d->irq - LOONGSON_IRQ_BASE)); mmiowb(); } -static inline void bonito_irq_disable(unsigned int irq) +static inline void bonito_irq_disable(struct irq_data *d) { - LOONGSON_INTENCLR = (1 << (irq - LOONGSON_IRQ_BASE)); + LOONGSON_INTENCLR = (1 << (d->irq - LOONGSON_IRQ_BASE)); mmiowb(); } static struct irq_chip bonito_irq_type = { - .name = "bonito_irq", - .ack = bonito_irq_disable, - .mask = bonito_irq_disable, - .mask_ack = bonito_irq_disable, - .unmask = bonito_irq_enable, + .name = "bonito_irq", + .irq_mask = bonito_irq_disable, + .irq_unmask = bonito_irq_enable, }; static struct irqaction __maybe_unused dma_timeout_irqaction = { diff --git a/arch/mips/mipssim/sim_smtc.c b/arch/mips/mipssim/sim_smtc.c index 5da30b6a65b7..30df47258c2c 100644 --- a/arch/mips/mipssim/sim_smtc.c +++ b/arch/mips/mipssim/sim_smtc.c @@ -27,6 +27,7 @@ #include <asm/atomic.h> #include <asm/cpu.h> #include <asm/processor.h> +#include <asm/smtc.h> #include <asm/system.h> #include <asm/mmu_context.h> #include <asm/smtc_ipi.h> @@ -57,8 +58,6 @@ static inline void ssmtc_send_ipi_mask(const struct cpumask *mask, */ static void __cpuinit ssmtc_init_secondary(void) { - void smtc_init_secondary(void); - smtc_init_secondary(); } diff --git a/arch/mips/mti-malta/malta-smtc.c b/arch/mips/mti-malta/malta-smtc.c index 192cfd2a539c..e67891521ac1 100644 --- a/arch/mips/mti-malta/malta-smtc.c +++ b/arch/mips/mti-malta/malta-smtc.c @@ -34,7 +34,6 @@ static void msmtc_send_ipi_mask(const struct cpumask *mask, unsigned int action) */ static void __cpuinit msmtc_init_secondary(void) { - void smtc_init_secondary(void); int myvpe; /* Don't enable Malta I/O interrupts (IP2) for secondary VPEs */ @@ -114,7 +113,8 @@ struct plat_smp_ops msmtc_smp_ops = { */ -int plat_set_irq_affinity(unsigned int irq, const struct cpumask *affinity) +int plat_set_irq_affinity(struct irq_data *d, const struct cpumask *affinity, + bool force) { cpumask_t tmask; int cpu = 0; @@ -144,7 +144,7 @@ int plat_set_irq_affinity(unsigned int irq, const struct cpumask *affinity) if ((cpu_data[cpu].vpe_id != 0) || !cpu_online(cpu)) cpu_clear(cpu, tmask); } - cpumask_copy(irq_desc[irq].affinity, &tmask); + cpumask_copy(d->affinity, &tmask); if (cpus_empty(tmask)) /* @@ -155,8 +155,8 @@ int plat_set_irq_affinity(unsigned int irq, const struct cpumask *affinity) "IRQ affinity leaves no legal CPU for IRQ %d\n", irq); /* Do any generic SMTC IRQ affinity setup */ - smtc_set_irq_affinity(irq, tmask); + smtc_set_irq_affinity(d->irq, tmask); - return 0; + return IRQ_SET_MASK_OK_NOCOPY; } #endif /* CONFIG_MIPS_MT_SMTC_IRQAFF */ diff --git a/arch/mips/pmc-sierra/Kconfig b/arch/mips/pmc-sierra/Kconfig index 8d798497c614..bbd76082fa8c 100644 --- a/arch/mips/pmc-sierra/Kconfig +++ b/arch/mips/pmc-sierra/Kconfig @@ -23,6 +23,8 @@ config PMC_MSP7120_GW select SYS_SUPPORTS_MULTITHREADING select IRQ_MSP_CIC select HW_HAS_PCI + select MSP_HAS_USB + select MSP_ETH config PMC_MSP7120_FPGA bool "PMC-Sierra MSP7120 FPGA" @@ -35,3 +37,16 @@ endchoice config HYPERTRANSPORT bool "Hypertransport Support for PMC-Sierra Yosemite" depends on PMC_YOSEMITE + +config MSP_HAS_USB + boolean + depends on PMC_MSP + +config MSP_ETH + boolean + select MSP_HAS_MAC + depends on PMC_MSP + +config MSP_HAS_MAC + boolean + depends on PMC_MSP diff --git a/arch/mips/pmc-sierra/msp71xx/Makefile b/arch/mips/pmc-sierra/msp71xx/Makefile index e107f79b1491..cefba7733b73 100644 --- a/arch/mips/pmc-sierra/msp71xx/Makefile +++ b/arch/mips/pmc-sierra/msp71xx/Makefile @@ -6,7 +6,9 @@ obj-y += msp_prom.o msp_setup.o msp_irq.o \ obj-$(CONFIG_HAVE_GPIO_LIB) += gpio.o gpio_extended.o obj-$(CONFIG_PMC_MSP7120_GW) += msp_hwbutton.o obj-$(CONFIG_IRQ_MSP_SLP) += msp_irq_slp.o -obj-$(CONFIG_IRQ_MSP_CIC) += msp_irq_cic.o +obj-$(CONFIG_IRQ_MSP_CIC) += msp_irq_cic.o msp_irq_per.o obj-$(CONFIG_PCI) += msp_pci.o -obj-$(CONFIG_MSPETH) += msp_eth.o -obj-$(CONFIG_USB_MSP71XX) += msp_usb.o +obj-$(CONFIG_MSP_HAS_MAC) += msp_eth.o +obj-$(CONFIG_MSP_HAS_USB) += msp_usb.o +obj-$(CONFIG_MIPS_MT_SMP) += msp_smp.o +obj-$(CONFIG_MIPS_MT_SMTC) += msp_smtc.o diff --git a/arch/mips/pmc-sierra/msp71xx/msp_eth.c b/arch/mips/pmc-sierra/msp71xx/msp_eth.c new file mode 100644 index 000000000000..c584df393de2 --- /dev/null +++ b/arch/mips/pmc-sierra/msp71xx/msp_eth.c @@ -0,0 +1,187 @@ +/* + * The setup file for ethernet related hardware on PMC-Sierra MSP processors. + * + * Copyright 2010 PMC-Sierra, Inc. + * + * 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 SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED + * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN + * NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, + * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT + * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF + * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON + * ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF + * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + * 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., + * 675 Mass Ave, Cambridge, MA 02139, USA. + */ + +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/ioport.h> +#include <linux/platform_device.h> +#include <linux/delay.h> +#include <msp_regs.h> +#include <msp_int.h> +#include <msp_gpio_macros.h> + + +#define MSP_ETHERNET_GPIO0 14 +#define MSP_ETHERNET_GPIO1 15 +#define MSP_ETHERNET_GPIO2 16 + +#ifdef CONFIG_MSP_HAS_TSMAC +#define MSP_TSMAC_SIZE 0x10020 +#define MSP_TSMAC_ID "pmc_tsmac" + +static struct resource msp_tsmac0_resources[] = { + [0] = { + .start = MSP_MAC0_BASE, + .end = MSP_MAC0_BASE + MSP_TSMAC_SIZE - 1, + .flags = IORESOURCE_MEM, + }, + [1] = { + .start = MSP_INT_MAC0, + .end = MSP_INT_MAC0, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct resource msp_tsmac1_resources[] = { + [0] = { + .start = MSP_MAC1_BASE, + .end = MSP_MAC1_BASE + MSP_TSMAC_SIZE - 1, + .flags = IORESOURCE_MEM, + }, + [1] = { + .start = MSP_INT_MAC1, + .end = MSP_INT_MAC1, + .flags = IORESOURCE_IRQ, + }, +}; +static struct resource msp_tsmac2_resources[] = { + [0] = { + .start = MSP_MAC2_BASE, + .end = MSP_MAC2_BASE + MSP_TSMAC_SIZE - 1, + .flags = IORESOURCE_MEM, + }, + [1] = { + .start = MSP_INT_SAR, + .end = MSP_INT_SAR, + .flags = IORESOURCE_IRQ, + }, +}; + + +static struct platform_device tsmac_device[] = { + [0] = { + .name = MSP_TSMAC_ID, + .id = 0, + .num_resources = ARRAY_SIZE(msp_tsmac0_resources), + .resource = msp_tsmac0_resources, + }, + [1] = { + .name = MSP_TSMAC_ID, + .id = 1, + .num_resources = ARRAY_SIZE(msp_tsmac1_resources), + .resource = msp_tsmac1_resources, + }, + [2] = { + .name = MSP_TSMAC_ID, + .id = 2, + .num_resources = ARRAY_SIZE(msp_tsmac2_resources), + .resource = msp_tsmac2_resources, + }, +}; +#define msp_eth_devs tsmac_device + +#else +/* If it is not TSMAC assume MSP_ETH (100Mbps) */ +#define MSP_ETH_ID "pmc_mspeth" +#define MSP_ETH_SIZE 0xE0 +static struct resource msp_eth0_resources[] = { + [0] = { + .start = MSP_MAC0_BASE, + .end = MSP_MAC0_BASE + MSP_ETH_SIZE - 1, + .flags = IORESOURCE_MEM, + }, + [1] = { + .start = MSP_INT_MAC0, + .end = MSP_INT_MAC0, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct resource msp_eth1_resources[] = { + [0] = { + .start = MSP_MAC1_BASE, + .end = MSP_MAC1_BASE + MSP_ETH_SIZE - 1, + .flags = IORESOURCE_MEM, + }, + [1] = { + .start = MSP_INT_MAC1, + .end = MSP_INT_MAC1, + .flags = IORESOURCE_IRQ, + }, +}; + + + +static struct platform_device mspeth_device[] = { + [0] = { + .name = MSP_ETH_ID, + .id = 0, + .num_resources = ARRAY_SIZE(msp_eth0_resources), + .resource = msp_eth0_resources, + }, + [1] = { + .name = MSP_ETH_ID, + .id = 1, + .num_resources = ARRAY_SIZE(msp_eth1_resources), + .resource = msp_eth1_resources, + }, + +}; +#define msp_eth_devs mspeth_device + +#endif +int __init msp_eth_setup(void) +{ + int i, ret = 0; + + /* Configure the GPIO and take the ethernet PHY out of reset */ + msp_gpio_pin_mode(MSP_GPIO_OUTPUT, MSP_ETHERNET_GPIO0); + msp_gpio_pin_hi(MSP_ETHERNET_GPIO0); + +#ifdef CONFIG_MSP_HAS_TSMAC + /* 3 phys on boards with TSMAC */ + msp_gpio_pin_mode(MSP_GPIO_OUTPUT, MSP_ETHERNET_GPIO1); + msp_gpio_pin_hi(MSP_ETHERNET_GPIO1); + + msp_gpio_pin_mode(MSP_GPIO_OUTPUT, MSP_ETHERNET_GPIO2); + msp_gpio_pin_hi(MSP_ETHERNET_GPIO2); +#endif + for (i = 0; i < ARRAY_SIZE(msp_eth_devs); i++) { + ret = platform_device_register(&msp_eth_devs[i]); + printk(KERN_INFO "device: %d, return value = %d\n", i, ret); + if (ret) { + platform_device_unregister(&msp_eth_devs[i]); + break; + } + } + + if (ret) + printk(KERN_WARNING "Could not initialize " + "MSPETH device structures.\n"); + + return ret; +} +subsys_initcall(msp_eth_setup); diff --git a/arch/mips/pmc-sierra/msp71xx/msp_irq.c b/arch/mips/pmc-sierra/msp71xx/msp_irq.c index 734d598a2e3a..4531c4a514bc 100644 --- a/arch/mips/pmc-sierra/msp71xx/msp_irq.c +++ b/arch/mips/pmc-sierra/msp71xx/msp_irq.c @@ -19,8 +19,6 @@ #include <msp_int.h> -extern void msp_int_handle(void); - /* SLP bases systems */ extern void msp_slp_irq_init(void); extern void msp_slp_irq_dispatch(void); @@ -29,6 +27,18 @@ extern void msp_slp_irq_dispatch(void); extern void msp_cic_irq_init(void); extern void msp_cic_irq_dispatch(void); +/* VSMP support init */ +extern void msp_vsmp_int_init(void); + +/* vectored interrupt implementation */ + +/* SW0/1 interrupts are used for SMP/SMTC */ +static inline void mac0_int_dispatch(void) { do_IRQ(MSP_INT_MAC0); } +static inline void mac1_int_dispatch(void) { do_IRQ(MSP_INT_MAC1); } +static inline void mac2_int_dispatch(void) { do_IRQ(MSP_INT_SAR); } +static inline void usb_int_dispatch(void) { do_IRQ(MSP_INT_USB); } +static inline void sec_int_dispatch(void) { do_IRQ(MSP_INT_SEC); } + /* * The PMC-Sierra MSP interrupts are arranged in a 3 level cascaded * hierarchical system. The first level are the direct MIPS interrupts @@ -96,29 +106,57 @@ asmlinkage void plat_irq_dispatch(struct pt_regs *regs) do_IRQ(MSP_INT_SW1); } -static struct irqaction cascade_msp = { +static struct irqaction cic_cascade_msp = { .handler = no_action, - .name = "MSP cascade" + .name = "MSP CIC cascade" }; +static struct irqaction per_cascade_msp = { + .handler = no_action, + .name = "MSP PER cascade" +}; void __init arch_init_irq(void) { + /* assume we'll be using vectored interrupt mode except in UP mode*/ +#ifdef CONFIG_MIPS_MT + BUG_ON(!cpu_has_vint); +#endif /* initialize the 1st-level CPU based interrupt controller */ mips_cpu_irq_init(); #ifdef CONFIG_IRQ_MSP_CIC msp_cic_irq_init(); - +#ifdef CONFIG_MIPS_MT + set_vi_handler(MSP_INT_CIC, msp_cic_irq_dispatch); + set_vi_handler(MSP_INT_MAC0, mac0_int_dispatch); + set_vi_handler(MSP_INT_MAC1, mac1_int_dispatch); + set_vi_handler(MSP_INT_SAR, mac2_int_dispatch); + set_vi_handler(MSP_INT_USB, usb_int_dispatch); + set_vi_handler(MSP_INT_SEC, sec_int_dispatch); +#ifdef CONFIG_MIPS_MT_SMP + msp_vsmp_int_init(); +#elif defined CONFIG_MIPS_MT_SMTC + /*Set hwmask for all platform devices */ + irq_hwmask[MSP_INT_MAC0] = C_IRQ0; + irq_hwmask[MSP_INT_MAC1] = C_IRQ1; + irq_hwmask[MSP_INT_USB] = C_IRQ2; + irq_hwmask[MSP_INT_SAR] = C_IRQ3; + irq_hwmask[MSP_INT_SEC] = C_IRQ5; + +#endif /* CONFIG_MIPS_MT_SMP */ +#endif /* CONFIG_MIPS_MT */ /* setup the cascaded interrupts */ - setup_irq(MSP_INT_CIC, &cascade_msp); - setup_irq(MSP_INT_PER, &cascade_msp); + setup_irq(MSP_INT_CIC, &cic_cascade_msp); + setup_irq(MSP_INT_PER, &per_cascade_msp); + #else /* setup the 2nd-level SLP register based interrupt controller */ + /* VSMP /SMTC support support is not enabled for SLP */ msp_slp_irq_init(); /* setup the cascaded SLP/PER interrupts */ - setup_irq(MSP_INT_SLP, &cascade_msp); - setup_irq(MSP_INT_PER, &cascade_msp); + setup_irq(MSP_INT_SLP, &cic_cascade_msp); + setup_irq(MSP_INT_PER, &per_cascade_msp); #endif } diff --git a/arch/mips/pmc-sierra/msp71xx/msp_irq_cic.c b/arch/mips/pmc-sierra/msp71xx/msp_irq_cic.c index 07e71ff2433f..352f29d9226f 100644 --- a/arch/mips/pmc-sierra/msp71xx/msp_irq_cic.c +++ b/arch/mips/pmc-sierra/msp71xx/msp_irq_cic.c @@ -1,8 +1,7 @@ /* - * This file define the irq handler for MSP SLM subsystem interrupts. + * Copyright 2010 PMC-Sierra, Inc, derived from irq_cpu.c * - * Copyright 2005-2007 PMC-Sierra, Inc, derived from irq_cpu.c - * Author: Andrew Hughes, Andrew_Hughes@pmc-sierra.com + * This file define the irq handler for MSP CIC subsystem interrupts. * * 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 @@ -16,119 +15,203 @@ #include <linux/bitops.h> #include <linux/irq.h> +#include <asm/mipsregs.h> #include <asm/system.h> #include <msp_cic_int.h> #include <msp_regs.h> /* - * NOTE: We are only enabling support for VPE0 right now. + * External API */ +extern void msp_per_irq_init(void); +extern void msp_per_irq_dispatch(void); -static inline void unmask_msp_cic_irq(unsigned int irq) + +/* + * Convenience Macro. Should be somewhere generic. + */ +#define get_current_vpe() \ + ((read_c0_tcbind() >> TCBIND_CURVPE_SHIFT) & TCBIND_CURVPE) + +#ifdef CONFIG_SMP + +#define LOCK_VPE(flags, mtflags) \ +do { \ + local_irq_save(flags); \ + mtflags = dmt(); \ +} while (0) + +#define UNLOCK_VPE(flags, mtflags) \ +do { \ + emt(mtflags); \ + local_irq_restore(flags);\ +} while (0) + +#define LOCK_CORE(flags, mtflags) \ +do { \ + local_irq_save(flags); \ + mtflags = dvpe(); \ +} while (0) + +#define UNLOCK_CORE(flags, mtflags) \ +do { \ + evpe(mtflags); \ + local_irq_restore(flags);\ +} while (0) + +#else + +#define LOCK_VPE(flags, mtflags) +#define UNLOCK_VPE(flags, mtflags) +#endif + +/* ensure writes to cic are completed */ +static inline void cic_wmb(void) { + const volatile void __iomem *cic_mem = CIC_VPE0_MSK_REG; + volatile u32 dummy_read; - /* check for PER interrupt range */ - if (irq < MSP_PER_INTBASE) - *CIC_VPE0_MSK_REG |= (1 << (irq - MSP_CIC_INTBASE)); - else - *PER_INT_MSK_REG |= (1 << (irq - MSP_PER_INTBASE)); + wmb(); + dummy_read = __raw_readl(cic_mem); + dummy_read++; } -static inline void mask_msp_cic_irq(unsigned int irq) +static void unmask_cic_irq(struct irq_data *d) { - /* check for PER interrupt range */ - if (irq < MSP_PER_INTBASE) - *CIC_VPE0_MSK_REG &= ~(1 << (irq - MSP_CIC_INTBASE)); - else - *PER_INT_MSK_REG &= ~(1 << (irq - MSP_PER_INTBASE)); + volatile u32 *cic_msk_reg = CIC_VPE0_MSK_REG; + int vpe; +#ifdef CONFIG_SMP + unsigned int mtflags; + unsigned long flags; + + /* + * Make sure we have IRQ affinity. It may have changed while + * we were processing the IRQ. + */ + if (!cpumask_test_cpu(smp_processor_id(), d->affinity)) + return; +#endif + + vpe = get_current_vpe(); + LOCK_VPE(flags, mtflags); + cic_msk_reg[vpe] |= (1 << (d->irq - MSP_CIC_INTBASE)); + UNLOCK_VPE(flags, mtflags); + cic_wmb(); } -/* - * While we ack the interrupt interrupts are disabled and thus we don't need - * to deal with concurrency issues. Same for msp_cic_irq_end. - */ -static inline void ack_msp_cic_irq(unsigned int irq) +static void mask_cic_irq(struct irq_data *d) { - mask_msp_cic_irq(irq); - + volatile u32 *cic_msk_reg = CIC_VPE0_MSK_REG; + int vpe = get_current_vpe(); +#ifdef CONFIG_SMP + unsigned long flags, mtflags; +#endif + LOCK_VPE(flags, mtflags); + cic_msk_reg[vpe] &= ~(1 << (d->irq - MSP_CIC_INTBASE)); + UNLOCK_VPE(flags, mtflags); + cic_wmb(); +} +static void msp_cic_irq_ack(struct irq_data *d) +{ + mask_cic_irq(d); /* - * only really necessary for 18, 16-14 and sometimes 3:0 (since - * these can be edge sensitive) but it doesn't hurt for the others. - */ - - /* check for PER interrupt range */ - if (irq < MSP_PER_INTBASE) - *CIC_STS_REG = (1 << (irq - MSP_CIC_INTBASE)); - else - *PER_INT_STS_REG = (1 << (irq - MSP_PER_INTBASE)); + * Only really necessary for 18, 16-14 and sometimes 3:0 + * (since these can be edge sensitive) but it doesn't + * hurt for the others + */ + *CIC_STS_REG = (1 << (d->irq - MSP_CIC_INTBASE)); + smtc_im_ack_irq(d->irq); } +/*Note: Limiting to VSMP . Not tested in SMTC */ + +#ifdef CONFIG_MIPS_MT_SMP +static int msp_cic_irq_set_affinity(struct irq_data *d, + const struct cpumask *cpumask, bool force) +{ + int cpu; + unsigned long flags; + unsigned int mtflags; + unsigned long imask = (1 << (irq - MSP_CIC_INTBASE)); + volatile u32 *cic_mask = (volatile u32 *)CIC_VPE0_MSK_REG; + + /* timer balancing should be disabled in kernel code */ + BUG_ON(irq == MSP_INT_VPE0_TIMER || irq == MSP_INT_VPE1_TIMER); + + LOCK_CORE(flags, mtflags); + /* enable if any of each VPE's TCs require this IRQ */ + for_each_online_cpu(cpu) { + if (cpumask_test_cpu(cpu, cpumask)) + cic_mask[cpu] |= imask; + else + cic_mask[cpu] &= ~imask; + + } + + UNLOCK_CORE(flags, mtflags); + return 0; + +} +#endif + static struct irq_chip msp_cic_irq_controller = { .name = "MSP_CIC", - .ack = ack_msp_cic_irq, - .mask = ack_msp_cic_irq, - .mask_ack = ack_msp_cic_irq, - .unmask = unmask_msp_cic_irq, + .irq_mask = mask_cic_irq, + .irq_mask_ack = msp_cic_irq_ack, + .irq_unmask = unmask_cic_irq, + .irq_ack = msp_cic_irq_ack, +#ifdef CONFIG_MIPS_MT_SMP + .irq_set_affinity = msp_cic_irq_set_affinity, +#endif }; - void __init msp_cic_irq_init(void) { int i; - /* Mask/clear interrupts. */ *CIC_VPE0_MSK_REG = 0x00000000; - *PER_INT_MSK_REG = 0x00000000; + *CIC_VPE1_MSK_REG = 0x00000000; *CIC_STS_REG = 0xFFFFFFFF; - *PER_INT_STS_REG = 0xFFFFFFFF; - -#if defined(CONFIG_PMC_MSP7120_GW) || \ - defined(CONFIG_PMC_MSP7120_EVAL) /* - * The MSP7120 RG and EVBD boards use IRQ[6:4] for PCI. - * These inputs map to EXT_INT_POL[6:4] inside the CIC. - * They are to be active low, level sensitive. - */ + * The MSP7120 RG and EVBD boards use IRQ[6:4] for PCI. + * These inputs map to EXT_INT_POL[6:4] inside the CIC. + * They are to be active low, level sensitive. + */ *CIC_EXT_CFG_REG &= 0xFFFF8F8F; -#endif /* initialize all the IRQ descriptors */ - for (i = MSP_CIC_INTBASE; i < MSP_PER_INTBASE + 32; i++) + for (i = MSP_CIC_INTBASE ; i < MSP_CIC_INTBASE + 32 ; i++) { set_irq_chip_and_handler(i, &msp_cic_irq_controller, handle_level_irq); +#ifdef CONFIG_MIPS_MT_SMTC + /* Mask of CIC interrupt */ + irq_hwmask[i] = C_IRQ4; +#endif + } + + /* Initialize the PER interrupt sub-system */ + msp_per_irq_init(); } +/* CIC masked by CIC vector processing before dispatch called */ void msp_cic_irq_dispatch(void) { - u32 pending; - int intbase; - - intbase = MSP_CIC_INTBASE; - pending = *CIC_STS_REG & *CIC_VPE0_MSK_REG; - - /* check for PER interrupt */ - if (pending == (1 << (MSP_INT_PER - MSP_CIC_INTBASE))) { - intbase = MSP_PER_INTBASE; - pending = *PER_INT_STS_REG & *PER_INT_MSK_REG; - } - - /* check for spurious interrupt */ - if (pending == 0x00000000) { - printk(KERN_ERR - "Spurious %s interrupt? status %08x, mask %08x\n", - (intbase == MSP_CIC_INTBASE) ? "CIC" : "PER", - (intbase == MSP_CIC_INTBASE) ? - *CIC_STS_REG : *PER_INT_STS_REG, - (intbase == MSP_CIC_INTBASE) ? - *CIC_VPE0_MSK_REG : *PER_INT_MSK_REG); - return; - } - - /* check for the timer and dispatch it first */ - if ((intbase == MSP_CIC_INTBASE) && - (pending & (1 << (MSP_INT_VPE0_TIMER - MSP_CIC_INTBASE)))) + volatile u32 *cic_msk_reg = (volatile u32 *)CIC_VPE0_MSK_REG; + u32 cic_mask; + u32 pending; + int cic_status = *CIC_STS_REG; + cic_mask = cic_msk_reg[get_current_vpe()]; + pending = cic_status & cic_mask; + if (pending & (1 << (MSP_INT_VPE0_TIMER - MSP_CIC_INTBASE))) { do_IRQ(MSP_INT_VPE0_TIMER); - else - do_IRQ(ffs(pending) + intbase - 1); + } else if (pending & (1 << (MSP_INT_VPE1_TIMER - MSP_CIC_INTBASE))) { + do_IRQ(MSP_INT_VPE1_TIMER); + } else if (pending & (1 << (MSP_INT_PER - MSP_CIC_INTBASE))) { + msp_per_irq_dispatch(); + } else if (pending) { + do_IRQ(ffs(pending) + MSP_CIC_INTBASE - 1); + } else{ + spurious_interrupt(); + } } diff --git a/arch/mips/pmc-sierra/msp71xx/msp_irq_per.c b/arch/mips/pmc-sierra/msp71xx/msp_irq_per.c new file mode 100644 index 000000000000..f9b9dcdfa9dd --- /dev/null +++ b/arch/mips/pmc-sierra/msp71xx/msp_irq_per.c @@ -0,0 +1,135 @@ +/* + * Copyright 2010 PMC-Sierra, Inc, derived from irq_cpu.c + * + * This file define the irq handler for MSP PER subsystem interrupts. + * + * 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/init.h> +#include <linux/interrupt.h> +#include <linux/kernel.h> +#include <linux/spinlock.h> +#include <linux/bitops.h> + +#include <asm/mipsregs.h> +#include <asm/system.h> + +#include <msp_cic_int.h> +#include <msp_regs.h> + + +/* + * Convenience Macro. Should be somewhere generic. + */ +#define get_current_vpe() \ + ((read_c0_tcbind() >> TCBIND_CURVPE_SHIFT) & TCBIND_CURVPE) + +#ifdef CONFIG_SMP +/* + * The PER registers must be protected from concurrent access. + */ + +static DEFINE_SPINLOCK(per_lock); +#endif + +/* ensure writes to per are completed */ + +static inline void per_wmb(void) +{ + const volatile void __iomem *per_mem = PER_INT_MSK_REG; + volatile u32 dummy_read; + + wmb(); + dummy_read = __raw_readl(per_mem); + dummy_read++; +} + +static inline void unmask_per_irq(struct irq_data *d) +{ +#ifdef CONFIG_SMP + unsigned long flags; + spin_lock_irqsave(&per_lock, flags); + *PER_INT_MSK_REG |= (1 << (d->irq - MSP_PER_INTBASE)); + spin_unlock_irqrestore(&per_lock, flags); +#else + *PER_INT_MSK_REG |= (1 << (d->irq - MSP_PER_INTBASE)); +#endif + per_wmb(); +} + +static inline void mask_per_irq(struct irq_data *d) +{ +#ifdef CONFIG_SMP + unsigned long flags; + spin_lock_irqsave(&per_lock, flags); + *PER_INT_MSK_REG &= ~(1 << (d->irq - MSP_PER_INTBASE)); + spin_unlock_irqrestore(&per_lock, flags); +#else + *PER_INT_MSK_REG &= ~(1 << (d->irq - MSP_PER_INTBASE)); +#endif + per_wmb(); +} + +static inline void msp_per_irq_ack(struct irq_data *d) +{ + mask_per_irq(d); + /* + * In the PER interrupt controller, only bits 11 and 10 + * are write-to-clear, (SPI TX complete, SPI RX complete). + * It does nothing for any others. + */ + *PER_INT_STS_REG = (1 << (d->irq - MSP_PER_INTBASE)); +} + +#ifdef CONFIG_SMP +static int msp_per_irq_set_affinity(struct irq_data *d, + const struct cpumask *affinity, bool force) +{ + /* WTF is this doing ????? */ + unmask_per_irq(d); + return 0; +} +#endif + +static struct irq_chip msp_per_irq_controller = { + .name = "MSP_PER", + .irq_enable = unmask_per_irq. + .irq_disable = mask_per_irq, + .irq_ack = msp_per_irq_ack, +#ifdef CONFIG_SMP + .irq_set_affinity = msp_per_irq_set_affinity, +#endif +}; + +void __init msp_per_irq_init(void) +{ + int i; + /* Mask/clear interrupts. */ + *PER_INT_MSK_REG = 0x00000000; + *PER_INT_STS_REG = 0xFFFFFFFF; + /* initialize all the IRQ descriptors */ + for (i = MSP_PER_INTBASE; i < MSP_PER_INTBASE + 32; i++) { + irq_set_chip(i, &msp_per_irq_controller); +#ifdef CONFIG_MIPS_MT_SMTC + irq_hwmask[i] = C_IRQ4; +#endif + } +} + +void msp_per_irq_dispatch(void) +{ + u32 per_mask = *PER_INT_MSK_REG; + u32 per_status = *PER_INT_STS_REG; + u32 pending; + + pending = per_status & per_mask; + if (pending) { + do_IRQ(ffs(pending) + MSP_PER_INTBASE - 1); + } else { + spurious_interrupt(); + } +} diff --git a/arch/mips/pmc-sierra/msp71xx/msp_irq_slp.c b/arch/mips/pmc-sierra/msp71xx/msp_irq_slp.c index 61f390232346..8f51e4adc438 100644 --- a/arch/mips/pmc-sierra/msp71xx/msp_irq_slp.c +++ b/arch/mips/pmc-sierra/msp71xx/msp_irq_slp.c @@ -21,8 +21,10 @@ #include <msp_slp_int.h> #include <msp_regs.h> -static inline void unmask_msp_slp_irq(unsigned int irq) +static inline void unmask_msp_slp_irq(struct irq_data *d) { + unsigned int irq = d->irq; + /* check for PER interrupt range */ if (irq < MSP_PER_INTBASE) *SLP_INT_MSK_REG |= (1 << (irq - MSP_SLP_INTBASE)); @@ -30,8 +32,10 @@ static inline void unmask_msp_slp_irq(unsigned int irq) *PER_INT_MSK_REG |= (1 << (irq - MSP_PER_INTBASE)); } -static inline void mask_msp_slp_irq(unsigned int irq) +static inline void mask_msp_slp_irq(struct irq_data *d) { + unsigned int irq = d->irq; + /* check for PER interrupt range */ if (irq < MSP_PER_INTBASE) *SLP_INT_MSK_REG &= ~(1 << (irq - MSP_SLP_INTBASE)); @@ -43,8 +47,10 @@ static inline void mask_msp_slp_irq(unsigned int irq) * While we ack the interrupt interrupts are disabled and thus we don't need * to deal with concurrency issues. Same for msp_slp_irq_end. */ -static inline void ack_msp_slp_irq(unsigned int irq) +static inline void ack_msp_slp_irq(struct irq_data *d) { + unsigned int irq = d->irq; + /* check for PER interrupt range */ if (irq < MSP_PER_INTBASE) *SLP_INT_STS_REG = (1 << (irq - MSP_SLP_INTBASE)); @@ -54,9 +60,9 @@ static inline void ack_msp_slp_irq(unsigned int irq) static struct irq_chip msp_slp_irq_controller = { .name = "MSP_SLP", - .ack = ack_msp_slp_irq, - .mask = mask_msp_slp_irq, - .unmask = unmask_msp_slp_irq, + .irq_ack = ack_msp_slp_irq, + .irq_mask = mask_msp_slp_irq, + .irq_unmask = unmask_msp_slp_irq, }; void __init msp_slp_irq_init(void) diff --git a/arch/mips/pmc-sierra/msp71xx/msp_setup.c b/arch/mips/pmc-sierra/msp71xx/msp_setup.c index a54e85b3cf29..fb37a10e0309 100644 --- a/arch/mips/pmc-sierra/msp71xx/msp_setup.c +++ b/arch/mips/pmc-sierra/msp71xx/msp_setup.c @@ -146,6 +146,8 @@ void __init plat_mem_setup(void) pm_power_off = msp_power_off; } +extern struct plat_smp_ops msp_smtc_smp_ops; + void __init prom_init(void) { unsigned long family; @@ -226,6 +228,14 @@ void __init prom_init(void) */ msp_serial_setup(); +#ifdef CONFIG_MIPS_MT_SMP + register_smp_ops(&vsmp_smp_ops); +#endif + +#ifdef CONFIG_MIPS_MT_SMTC + register_smp_ops(&msp_smtc_smp_ops); +#endif + #ifdef CONFIG_PMCTWILED /* * Setup LED states before the subsys_initcall loads other diff --git a/arch/mips/pmc-sierra/msp71xx/msp_smp.c b/arch/mips/pmc-sierra/msp71xx/msp_smp.c new file mode 100644 index 000000000000..43a9e26e1c69 --- /dev/null +++ b/arch/mips/pmc-sierra/msp71xx/msp_smp.c @@ -0,0 +1,77 @@ +/* + * Copyright (C) 2000, 2001, 2004 MIPS Technologies, Inc. + * Copyright (C) 2001 Ralf Baechle + * Copyright (C) 2010 PMC-Sierra, Inc. + * + * VSMP support for MSP platforms . Derived from malta vsmp support. + * + * This program is free software; you can distribute it and/or modify it + * under the terms of the GNU General Public License (Version 2) as + * published by the Free Software Foundation. + * + * This program is distributed in the hope 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/smp.h> +#include <linux/interrupt.h> + +#ifdef CONFIG_MIPS_MT_SMP +#define MIPS_CPU_IPI_RESCHED_IRQ 0 /* SW int 0 for resched */ +#define MIPS_CPU_IPI_CALL_IRQ 1 /* SW int 1 for call */ + + +static void ipi_resched_dispatch(void) +{ + do_IRQ(MIPS_CPU_IPI_RESCHED_IRQ); +} + +static void ipi_call_dispatch(void) +{ + do_IRQ(MIPS_CPU_IPI_CALL_IRQ); +} + +static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id) +{ + return IRQ_HANDLED; +} + +static irqreturn_t ipi_call_interrupt(int irq, void *dev_id) +{ + smp_call_function_interrupt(); + + return IRQ_HANDLED; +} + +static struct irqaction irq_resched = { + .handler = ipi_resched_interrupt, + .flags = IRQF_DISABLED | IRQF_PERCPU, + .name = "IPI_resched" +}; + +static struct irqaction irq_call = { + .handler = ipi_call_interrupt, + .flags = IRQF_DISABLED | IRQF_PERCPU, + .name = "IPI_call" +}; + +void __init arch_init_ipiirq(int irq, struct irqaction *action) +{ + setup_irq(irq, action); + set_irq_handler(irq, handle_percpu_irq); +} + +void __init msp_vsmp_int_init(void) +{ + set_vi_handler(MIPS_CPU_IPI_RESCHED_IRQ, ipi_resched_dispatch); + set_vi_handler(MIPS_CPU_IPI_CALL_IRQ, ipi_call_dispatch); + arch_init_ipiirq(MIPS_CPU_IPI_RESCHED_IRQ, &irq_resched); + arch_init_ipiirq(MIPS_CPU_IPI_CALL_IRQ, &irq_call); +} +#endif /* CONFIG_MIPS_MT_SMP */ diff --git a/arch/mips/pmc-sierra/msp71xx/msp_smtc.c b/arch/mips/pmc-sierra/msp71xx/msp_smtc.c new file mode 100644 index 000000000000..c8dcc1c01e18 --- /dev/null +++ b/arch/mips/pmc-sierra/msp71xx/msp_smtc.c @@ -0,0 +1,105 @@ +/* + * MSP71xx Platform-specific hooks for SMP operation + */ +#include <linux/irq.h> +#include <linux/init.h> + +#include <asm/mipsmtregs.h> +#include <asm/mipsregs.h> +#include <asm/smtc.h> +#include <asm/smtc_ipi.h> + +/* VPE/SMP Prototype implements platform interfaces directly */ + +/* + * Cause the specified action to be performed on a targeted "CPU" + */ + +static void msp_smtc_send_ipi_single(int cpu, unsigned int action) +{ + /* "CPU" may be TC of same VPE, VPE of same CPU, or different CPU */ + smtc_send_ipi(cpu, LINUX_SMP_IPI, action); +} + +static void msp_smtc_send_ipi_mask(const struct cpumask *mask, + unsigned int action) +{ + unsigned int i; + + for_each_cpu(i, mask) + msp_smtc_send_ipi_single(i, action); +} + +/* + * Post-config but pre-boot cleanup entry point + */ +static void __cpuinit msp_smtc_init_secondary(void) +{ + int myvpe; + + /* Don't enable Malta I/O interrupts (IP2) for secondary VPEs */ + myvpe = read_c0_tcbind() & TCBIND_CURVPE; + if (myvpe > 0) + change_c0_status(ST0_IM, STATUSF_IP0 | STATUSF_IP1 | + STATUSF_IP6 | STATUSF_IP7); + smtc_init_secondary(); +} + +/* + * Platform "CPU" startup hook + */ +static void __cpuinit msp_smtc_boot_secondary(int cpu, + struct task_struct *idle) +{ + smtc_boot_secondary(cpu, idle); +} + +/* + * SMP initialization finalization entry point + */ +static void __cpuinit msp_smtc_smp_finish(void) +{ + smtc_smp_finish(); +} + +/* + * Hook for after all CPUs are online + */ + +static void msp_smtc_cpus_done(void) +{ +} + +/* + * Platform SMP pre-initialization + * + * As noted above, we can assume a single CPU for now + * but it may be multithreaded. + */ + +static void __init msp_smtc_smp_setup(void) +{ + /* + * we won't get the definitive value until + * we've run smtc_prepare_cpus later, but + */ + + if (read_c0_config3() & (1 << 2)) + smp_num_siblings = smtc_build_cpu_map(0); +} + +static void __init msp_smtc_prepare_cpus(unsigned int max_cpus) +{ + smtc_prepare_cpus(max_cpus); +} + +struct plat_smp_ops msp_smtc_smp_ops = { + .send_ipi_single = msp_smtc_send_ipi_single, + .send_ipi_mask = msp_smtc_send_ipi_mask, + .init_secondary = msp_smtc_init_secondary, + .smp_finish = msp_smtc_smp_finish, + .cpus_done = msp_smtc_cpus_done, + .boot_secondary = msp_smtc_boot_secondary, + .smp_setup = msp_smtc_smp_setup, + .prepare_cpus = msp_smtc_prepare_cpus, +}; diff --git a/arch/mips/pmc-sierra/msp71xx/msp_time.c b/arch/mips/pmc-sierra/msp71xx/msp_time.c index 01df84ce31e2..8b42f307a7a7 100644 --- a/arch/mips/pmc-sierra/msp71xx/msp_time.c +++ b/arch/mips/pmc-sierra/msp71xx/msp_time.c @@ -29,6 +29,7 @@ #include <linux/module.h> #include <linux/ptrace.h> +#include <asm/cevt-r4k.h> #include <asm/mipsregs.h> #include <asm/time.h> @@ -36,6 +37,12 @@ #include <msp_int.h> #include <msp_regs.h> +#define get_current_vpe() \ + ((read_c0_tcbind() >> TCBIND_CURVPE_SHIFT) & TCBIND_CURVPE) + +static struct irqaction timer_vpe1; +static int tim_installed; + void __init plat_time_init(void) { char *endp, *s; @@ -83,5 +90,12 @@ void __init plat_time_init(void) unsigned int __cpuinit get_c0_compare_int(void) { - return MSP_INT_VPE0_TIMER; + /* MIPS_MT modes may want timer for second VPE */ + if ((get_current_vpe()) && !tim_installed) { + memcpy(&timer_vpe1, &c0_compare_irqaction, sizeof(timer_vpe1)); + setup_irq(MSP_INT_VPE1_TIMER, &timer_vpe1); + tim_installed++; + } + + return get_current_vpe() ? MSP_INT_VPE1_TIMER : MSP_INT_VPE0_TIMER; } diff --git a/arch/mips/pmc-sierra/msp71xx/msp_usb.c b/arch/mips/pmc-sierra/msp71xx/msp_usb.c index 0ee01e359dd8..9a1aef89bd4c 100644 --- a/arch/mips/pmc-sierra/msp71xx/msp_usb.c +++ b/arch/mips/pmc-sierra/msp71xx/msp_usb.c @@ -1,7 +1,7 @@ /* * The setup file for USB related hardware on PMC-Sierra MSP processors. * - * Copyright 2006-2007 PMC-Sierra, Inc. + * Copyright 2006 PMC-Sierra, Inc. * * 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 @@ -23,8 +23,8 @@ * with this program; if not, write to the Free Software Foundation, Inc., * 675 Mass Ave, Cambridge, MA 02139, USA. */ +#if defined(CONFIG_USB_EHCI_HCD) || defined(CONFIG_USB_GADGET) -#include <linux/dma-mapping.h> #include <linux/init.h> #include <linux/ioport.h> #include <linux/platform_device.h> @@ -34,40 +34,56 @@ #include <msp_regs.h> #include <msp_int.h> #include <msp_prom.h> +#include <msp_usb.h> + #if defined(CONFIG_USB_EHCI_HCD) -static struct resource msp_usbhost_resources [] = { - [0] = { - .start = MSP_USB_BASE_START, - .end = MSP_USB_BASE_END, - .flags = IORESOURCE_MEM, +static struct resource msp_usbhost0_resources[] = { + [0] = { /* EHCI-HS operational and capabilities registers */ + .start = MSP_USB0_HS_START, + .end = MSP_USB0_HS_END, + .flags = IORESOURCE_MEM, }, [1] = { - .start = MSP_INT_USB, - .end = MSP_INT_USB, - .flags = IORESOURCE_IRQ, + .start = MSP_INT_USB, + .end = MSP_INT_USB, + .flags = IORESOURCE_IRQ, + }, + [2] = { /* MSBus-to-AMBA bridge register space */ + .start = MSP_USB0_MAB_START, + .end = MSP_USB0_MAB_END, + .flags = IORESOURCE_MEM, + }, + [3] = { /* Identification and general hardware parameters */ + .start = MSP_USB0_ID_START, + .end = MSP_USB0_ID_END, + .flags = IORESOURCE_MEM, }, }; -static u64 msp_usbhost_dma_mask = DMA_BIT_MASK(32); +static u64 msp_usbhost0_dma_mask = 0xffffffffUL; -static struct platform_device msp_usbhost_device = { - .name = "pmcmsp-ehci", - .id = 0, +static struct mspusb_device msp_usbhost0_device = { .dev = { - .dma_mask = &msp_usbhost_dma_mask, - .coherent_dma_mask = DMA_BIT_MASK(32), + .name = "pmcmsp-ehci", + .id = 0, + .dev = { + .dma_mask = &msp_usbhost0_dma_mask, + .coherent_dma_mask = 0xffffffffUL, + }, + .num_resources = ARRAY_SIZE(msp_usbhost0_resources), + .resource = msp_usbhost0_resources, }, - .num_resources = ARRAY_SIZE(msp_usbhost_resources), - .resource = msp_usbhost_resources, }; -#endif /* CONFIG_USB_EHCI_HCD */ -#if defined(CONFIG_USB_GADGET) -static struct resource msp_usbdev_resources [] = { - [0] = { - .start = MSP_USB_BASE, - .end = MSP_USB_BASE_END, +/* MSP7140/MSP82XX has two USB2 hosts. */ +#ifdef CONFIG_MSP_HAS_DUAL_USB +static u64 msp_usbhost1_dma_mask = 0xffffffffUL; + +static struct resource msp_usbhost1_resources[] = { + [0] = { /* EHCI-HS operational and capabilities registers */ + .start = MSP_USB1_HS_START, + .end = MSP_USB1_HS_END, .flags = IORESOURCE_MEM, }, [1] = { @@ -75,76 +91,173 @@ static struct resource msp_usbdev_resources [] = { .end = MSP_INT_USB, .flags = IORESOURCE_IRQ, }, + [2] = { /* MSBus-to-AMBA bridge register space */ + .start = MSP_USB1_MAB_START, + .end = MSP_USB1_MAB_END, + .flags = IORESOURCE_MEM, + }, + [3] = { /* Identification and general hardware parameters */ + .start = MSP_USB1_ID_START, + .end = MSP_USB1_ID_END, + .flags = IORESOURCE_MEM, + }, +}; + +static struct mspusb_device msp_usbhost1_device = { + .dev = { + .name = "pmcmsp-ehci", + .id = 1, + .dev = { + .dma_mask = &msp_usbhost1_dma_mask, + .coherent_dma_mask = 0xffffffffUL, + }, + .num_resources = ARRAY_SIZE(msp_usbhost1_resources), + .resource = msp_usbhost1_resources, + }, }; +#endif /* CONFIG_MSP_HAS_DUAL_USB */ +#endif /* CONFIG_USB_EHCI_HCD */ -static u64 msp_usbdev_dma_mask = DMA_BIT_MASK(32); +#if defined(CONFIG_USB_GADGET) +static struct resource msp_usbdev0_resources[] = { + [0] = { /* EHCI-HS operational and capabilities registers */ + .start = MSP_USB0_HS_START, + .end = MSP_USB0_HS_END, + .flags = IORESOURCE_MEM, + }, + [1] = { + .start = MSP_INT_USB, + .end = MSP_INT_USB, + .flags = IORESOURCE_IRQ, + }, + [2] = { /* MSBus-to-AMBA bridge register space */ + .start = MSP_USB0_MAB_START, + .end = MSP_USB0_MAB_END, + .flags = IORESOURCE_MEM, + }, + [3] = { /* Identification and general hardware parameters */ + .start = MSP_USB0_ID_START, + .end = MSP_USB0_ID_END, + .flags = IORESOURCE_MEM, + }, +}; -static struct platform_device msp_usbdev_device = { - .name = "msp71xx_udc", - .id = 0, +static u64 msp_usbdev_dma_mask = 0xffffffffUL; + +/* This may need to be converted to a mspusb_device, too. */ +static struct mspusb_device msp_usbdev0_device = { .dev = { - .dma_mask = &msp_usbdev_dma_mask, - .coherent_dma_mask = DMA_BIT_MASK(32), + .name = "msp71xx_udc", + .id = 0, + .dev = { + .dma_mask = &msp_usbdev_dma_mask, + .coherent_dma_mask = 0xffffffffUL, + }, + .num_resources = ARRAY_SIZE(msp_usbdev0_resources), + .resource = msp_usbdev0_resources, }, - .num_resources = ARRAY_SIZE(msp_usbdev_resources), - .resource = msp_usbdev_resources, }; -#endif /* CONFIG_USB_GADGET */ -#if defined(CONFIG_USB_EHCI_HCD) || defined(CONFIG_USB_GADGET) -static struct platform_device *msp_devs[1]; -#endif +#ifdef CONFIG_MSP_HAS_DUAL_USB +static struct resource msp_usbdev1_resources[] = { + [0] = { /* EHCI-HS operational and capabilities registers */ + .start = MSP_USB1_HS_START, + .end = MSP_USB1_HS_END, + .flags = IORESOURCE_MEM, + }, + [1] = { + .start = MSP_INT_USB, + .end = MSP_INT_USB, + .flags = IORESOURCE_IRQ, + }, + [2] = { /* MSBus-to-AMBA bridge register space */ + .start = MSP_USB1_MAB_START, + .end = MSP_USB1_MAB_END, + .flags = IORESOURCE_MEM, + }, + [3] = { /* Identification and general hardware parameters */ + .start = MSP_USB1_ID_START, + .end = MSP_USB1_ID_END, + .flags = IORESOURCE_MEM, + }, +}; +/* This may need to be converted to a mspusb_device, too. */ +static struct mspusb_device msp_usbdev1_device = { + .dev = { + .name = "msp71xx_udc", + .id = 0, + .dev = { + .dma_mask = &msp_usbdev_dma_mask, + .coherent_dma_mask = 0xffffffffUL, + }, + .num_resources = ARRAY_SIZE(msp_usbdev1_resources), + .resource = msp_usbdev1_resources, + }, +}; + +#endif /* CONFIG_MSP_HAS_DUAL_USB */ +#endif /* CONFIG_USB_GADGET */ static int __init msp_usb_setup(void) { -#if defined(CONFIG_USB_EHCI_HCD) || defined(CONFIG_USB_GADGET) - char *strp; - char envstr[32]; - unsigned int val = 0; - int result = 0; + char *strp; + char envstr[32]; + struct platform_device *msp_devs[NUM_USB_DEVS]; + unsigned int val; + /* construct environment name usbmode */ + /* set usbmode <host/device> as pmon environment var */ /* - * construct environment name usbmode - * set usbmode <host/device> as pmon environment var + * Could this perhaps be integrated into the "features" env var? + * Use the features key "U", and follow with "H" for host-mode, + * "D" for device-mode. If it works for Ethernet, why not USB... + * -- hammtrev, 2007/03/22 */ snprintf((char *)&envstr[0], sizeof(envstr), "usbmode"); -#if defined(CONFIG_USB_EHCI_HCD) - /* default to host mode */ + /* set default host mode */ val = 1; -#endif /* get environment string */ strp = prom_getenv((char *)&envstr[0]); if (strp) { + /* compare string */ if (!strcmp(strp, "device")) val = 0; } if (val) { #if defined(CONFIG_USB_EHCI_HCD) - /* get host mode device */ - msp_devs[0] = &msp_usbhost_device; - ppfinit("platform add USB HOST done %s.\n", - msp_devs[0]->name); - - result = platform_add_devices(msp_devs, ARRAY_SIZE(msp_devs)); -#endif /* CONFIG_USB_EHCI_HCD */ - } + msp_devs[0] = &msp_usbhost0_device.dev; + ppfinit("platform add USB HOST done %s.\n", msp_devs[0]->name); +#ifdef CONFIG_MSP_HAS_DUAL_USB + msp_devs[1] = &msp_usbhost1_device.dev; + ppfinit("platform add USB HOST done %s.\n", msp_devs[1]->name); +#endif +#else + ppfinit("%s: echi_hcd not supported\n", __FILE__); +#endif /* CONFIG_USB_EHCI_HCD */ + } else { #if defined(CONFIG_USB_GADGET) - else { /* get device mode structure */ - msp_devs[0] = &msp_usbdev_device; - ppfinit("platform add USB DEVICE done %s.\n", - msp_devs[0]->name); - - result = platform_add_devices(msp_devs, ARRAY_SIZE(msp_devs)); + msp_devs[0] = &msp_usbdev0_device.dev; + ppfinit("platform add USB DEVICE done %s.\n" + , msp_devs[0]->name); +#ifdef CONFIG_MSP_HAS_DUAL_USB + msp_devs[1] = &msp_usbdev1_device.dev; + ppfinit("platform add USB DEVICE done %s.\n" + , msp_devs[1]->name); +#endif +#else + ppfinit("%s: usb_gadget not supported\n", __FILE__); +#endif /* CONFIG_USB_GADGET */ } -#endif /* CONFIG_USB_GADGET */ -#endif /* CONFIG_USB_EHCI_HCD || CONFIG_USB_GADGET */ + /* add device */ + platform_add_devices(msp_devs, ARRAY_SIZE(msp_devs)); - return result; + return 0; } subsys_initcall(msp_usb_setup); +#endif /* CONFIG_USB_EHCI_HCD || CONFIG_USB_GADGET */ diff --git a/arch/mips/pnx833x/common/interrupts.c b/arch/mips/pnx833x/common/interrupts.c index 941916f8aaff..b226bcb0a2f4 100644 --- a/arch/mips/pnx833x/common/interrupts.c +++ b/arch/mips/pnx833x/common/interrupts.c @@ -152,10 +152,6 @@ static inline void pnx833x_hard_disable_pic_irq(unsigned int irq) PNX833X_PIC_INT_REG(irq) = 0; } -static int irqflags[PNX833X_PIC_NUM_IRQ]; /* initialized by zeroes */ -#define IRQFLAG_STARTED 1 -#define IRQFLAG_DISABLED 2 - static DEFINE_RAW_SPINLOCK(pnx833x_irq_lock); static unsigned int pnx833x_startup_pic_irq(unsigned int irq) @@ -164,108 +160,54 @@ static unsigned int pnx833x_startup_pic_irq(unsigned int irq) unsigned int pic_irq = irq - PNX833X_PIC_IRQ_BASE; raw_spin_lock_irqsave(&pnx833x_irq_lock, flags); - - irqflags[pic_irq] = IRQFLAG_STARTED; /* started, not disabled */ pnx833x_hard_enable_pic_irq(pic_irq); - raw_spin_unlock_irqrestore(&pnx833x_irq_lock, flags); return 0; } -static void pnx833x_shutdown_pic_irq(unsigned int irq) -{ - unsigned long flags; - unsigned int pic_irq = irq - PNX833X_PIC_IRQ_BASE; - - raw_spin_lock_irqsave(&pnx833x_irq_lock, flags); - - irqflags[pic_irq] = 0; /* not started */ - pnx833x_hard_disable_pic_irq(pic_irq); - - raw_spin_unlock_irqrestore(&pnx833x_irq_lock, flags); -} - -static void pnx833x_enable_pic_irq(unsigned int irq) +static void pnx833x_enable_pic_irq(struct irq_data *d) { unsigned long flags; - unsigned int pic_irq = irq - PNX833X_PIC_IRQ_BASE; + unsigned int pic_irq = d->irq - PNX833X_PIC_IRQ_BASE; raw_spin_lock_irqsave(&pnx833x_irq_lock, flags); - - irqflags[pic_irq] &= ~IRQFLAG_DISABLED; - if (irqflags[pic_irq] == IRQFLAG_STARTED) - pnx833x_hard_enable_pic_irq(pic_irq); - + pnx833x_hard_enable_pic_irq(pic_irq); raw_spin_unlock_irqrestore(&pnx833x_irq_lock, flags); } -static void pnx833x_disable_pic_irq(unsigned int irq) +static void pnx833x_disable_pic_irq(struct irq_data *d) { unsigned long flags; - unsigned int pic_irq = irq - PNX833X_PIC_IRQ_BASE; + unsigned int pic_irq = d->irq - PNX833X_PIC_IRQ_BASE; raw_spin_lock_irqsave(&pnx833x_irq_lock, flags); - - irqflags[pic_irq] |= IRQFLAG_DISABLED; pnx833x_hard_disable_pic_irq(pic_irq); - raw_spin_unlock_irqrestore(&pnx833x_irq_lock, flags); } -static void pnx833x_ack_pic_irq(unsigned int irq) -{ -} - -static void pnx833x_end_pic_irq(unsigned int irq) -{ -} - static DEFINE_RAW_SPINLOCK(pnx833x_gpio_pnx833x_irq_lock); -static unsigned int pnx833x_startup_gpio_irq(unsigned int irq) -{ - int pin = irq - PNX833X_GPIO_IRQ_BASE; - unsigned long flags; - raw_spin_lock_irqsave(&pnx833x_gpio_pnx833x_irq_lock, flags); - pnx833x_gpio_enable_irq(pin); - raw_spin_unlock_irqrestore(&pnx833x_gpio_pnx833x_irq_lock, flags); - return 0; -} - -static void pnx833x_enable_gpio_irq(unsigned int irq) +static void pnx833x_enable_gpio_irq(struct irq_data *d) { - int pin = irq - PNX833X_GPIO_IRQ_BASE; + int pin = d->irq - PNX833X_GPIO_IRQ_BASE; unsigned long flags; raw_spin_lock_irqsave(&pnx833x_gpio_pnx833x_irq_lock, flags); pnx833x_gpio_enable_irq(pin); raw_spin_unlock_irqrestore(&pnx833x_gpio_pnx833x_irq_lock, flags); } -static void pnx833x_disable_gpio_irq(unsigned int irq) +static void pnx833x_disable_gpio_irq(struct irq_data *d) { - int pin = irq - PNX833X_GPIO_IRQ_BASE; + int pin = d->irq - PNX833X_GPIO_IRQ_BASE; unsigned long flags; raw_spin_lock_irqsave(&pnx833x_gpio_pnx833x_irq_lock, flags); pnx833x_gpio_disable_irq(pin); raw_spin_unlock_irqrestore(&pnx833x_gpio_pnx833x_irq_lock, flags); } -static void pnx833x_ack_gpio_irq(unsigned int irq) -{ -} - -static void pnx833x_end_gpio_irq(unsigned int irq) -{ - int pin = irq - PNX833X_GPIO_IRQ_BASE; - unsigned long flags; - raw_spin_lock_irqsave(&pnx833x_gpio_pnx833x_irq_lock, flags); - pnx833x_gpio_clear_irq(pin); - raw_spin_unlock_irqrestore(&pnx833x_gpio_pnx833x_irq_lock, flags); -} - -static int pnx833x_set_type_gpio_irq(unsigned int irq, unsigned int flow_type) +static int pnx833x_set_type_gpio_irq(struct irq_data *d, unsigned int flow_type) { - int pin = irq - PNX833X_GPIO_IRQ_BASE; + int pin = d->irq - PNX833X_GPIO_IRQ_BASE; int gpio_mode; switch (flow_type) { @@ -296,23 +238,15 @@ static int pnx833x_set_type_gpio_irq(unsigned int irq, unsigned int flow_type) static struct irq_chip pnx833x_pic_irq_type = { .name = "PNX-PIC", - .startup = pnx833x_startup_pic_irq, - .shutdown = pnx833x_shutdown_pic_irq, - .enable = pnx833x_enable_pic_irq, - .disable = pnx833x_disable_pic_irq, - .ack = pnx833x_ack_pic_irq, - .end = pnx833x_end_pic_irq + .irq_enable = pnx833x_enable_pic_irq, + .irq_disable = pnx833x_disable_pic_irq, }; static struct irq_chip pnx833x_gpio_irq_type = { .name = "PNX-GPIO", - .startup = pnx833x_startup_gpio_irq, - .shutdown = pnx833x_disable_gpio_irq, - .enable = pnx833x_enable_gpio_irq, - .disable = pnx833x_disable_gpio_irq, - .ack = pnx833x_ack_gpio_irq, - .end = pnx833x_end_gpio_irq, - .set_type = pnx833x_set_type_gpio_irq + .irq_enable = pnx833x_enable_gpio_irq, + .irq_disable = pnx833x_disable_gpio_irq, + .irq_set_type = pnx833x_set_type_gpio_irq, }; void __init arch_init_irq(void) diff --git a/arch/mips/pnx8550/common/int.c b/arch/mips/pnx8550/common/int.c index cfed5051dc6d..dbdc35c3531d 100644 --- a/arch/mips/pnx8550/common/int.c +++ b/arch/mips/pnx8550/common/int.c @@ -114,8 +114,10 @@ static inline void unmask_gic_int(unsigned int irq_nr) PNX8550_GIC_REQ(irq_nr) = (1<<26 | 1<<16) | (1<<28) | gic_prio[irq_nr]; } -static inline void mask_irq(unsigned int irq_nr) +static inline void mask_irq(struct irq_data *d) { + unsigned int irq_nr = d->irq; + if ((PNX8550_INT_CP0_MIN <= irq_nr) && (irq_nr <= PNX8550_INT_CP0_MAX)) { modify_cp0_intmask(1 << irq_nr, 0); } else if ((PNX8550_INT_GIC_MIN <= irq_nr) && @@ -129,8 +131,10 @@ static inline void mask_irq(unsigned int irq_nr) } } -static inline void unmask_irq(unsigned int irq_nr) +static inline void unmask_irq(struct irq_data *d) { + unsigned int irq_nr = d->irq; + if ((PNX8550_INT_CP0_MIN <= irq_nr) && (irq_nr <= PNX8550_INT_CP0_MAX)) { modify_cp0_intmask(0, 1 << irq_nr); } else if ((PNX8550_INT_GIC_MIN <= irq_nr) && @@ -157,10 +161,8 @@ int pnx8550_set_gic_priority(int irq, int priority) static struct irq_chip level_irq_type = { .name = "PNX Level IRQ", - .ack = mask_irq, - .mask = mask_irq, - .mask_ack = mask_irq, - .unmask = unmask_irq, + .irq_mask = mask_irq, + .irq_unmask = unmask_irq, }; static struct irqaction gic_action = { @@ -180,10 +182,8 @@ void __init arch_init_irq(void) int i; int configPR; - for (i = 0; i < PNX8550_INT_CP0_TOTINT; i++) { + for (i = 0; i < PNX8550_INT_CP0_TOTINT; i++) set_irq_chip_and_handler(i, &level_irq_type, handle_level_irq); - mask_irq(i); /* mask the irq just in case */ - } /* init of GIC/IPC interrupts */ /* should be done before cp0 since cp0 init enables the GIC int */ diff --git a/arch/mips/powertv/asic/irq_asic.c b/arch/mips/powertv/asic/irq_asic.c index e55382434155..6f1c8ef6a719 100644 --- a/arch/mips/powertv/asic/irq_asic.c +++ b/arch/mips/powertv/asic/irq_asic.c @@ -21,9 +21,10 @@ #include <asm/mach-powertv/asic_regs.h> -static inline void unmask_asic_irq(unsigned int irq) +static inline void unmask_asic_irq(struct irq_data *d) { unsigned long enable_bit; + unsigned int irq = d->irq; enable_bit = (1 << (irq & 0x1f)); @@ -45,9 +46,10 @@ static inline void unmask_asic_irq(unsigned int irq) } } -static inline void mask_asic_irq(unsigned int irq) +static inline void mask_asic_irq(struct irq_data *d) { unsigned long disable_mask; + unsigned int irq = d->irq; disable_mask = ~(1 << (irq & 0x1f)); @@ -71,11 +73,8 @@ static inline void mask_asic_irq(unsigned int irq) static struct irq_chip asic_irq_chip = { .name = "ASIC Level", - .ack = mask_asic_irq, - .mask = mask_asic_irq, - .mask_ack = mask_asic_irq, - .unmask = unmask_asic_irq, - .eoi = unmask_asic_irq, + .irq_mask = mask_asic_irq, + .irq_unmask = unmask_asic_irq, }; void __init asic_irq_init(void) diff --git a/arch/mips/rb532/irq.c b/arch/mips/rb532/irq.c index ea6cec3c1e0d..b32a768da894 100644 --- a/arch/mips/rb532/irq.c +++ b/arch/mips/rb532/irq.c @@ -111,10 +111,10 @@ static inline void ack_local_irq(unsigned int ip) clear_c0_cause(ipnum); } -static void rb532_enable_irq(unsigned int irq_nr) +static void rb532_enable_irq(struct irq_data *d) { + unsigned int group, intr_bit, irq_nr = d->irq; int ip = irq_nr - GROUP0_IRQ_BASE; - unsigned int group, intr_bit; volatile unsigned int *addr; if (ip < 0) @@ -132,10 +132,10 @@ static void rb532_enable_irq(unsigned int irq_nr) } } -static void rb532_disable_irq(unsigned int irq_nr) +static void rb532_disable_irq(struct irq_data *d) { + unsigned int group, intr_bit, mask, irq_nr = d->irq; int ip = irq_nr - GROUP0_IRQ_BASE; - unsigned int group, intr_bit, mask; volatile unsigned int *addr; if (ip < 0) { @@ -163,18 +163,18 @@ static void rb532_disable_irq(unsigned int irq_nr) } } -static void rb532_mask_and_ack_irq(unsigned int irq_nr) +static void rb532_mask_and_ack_irq(struct irq_data *d) { - rb532_disable_irq(irq_nr); - ack_local_irq(group_to_ip(irq_to_group(irq_nr))); + rb532_disable_irq(d); + ack_local_irq(group_to_ip(irq_to_group(d->irq))); } -static int rb532_set_type(unsigned int irq_nr, unsigned type) +static int rb532_set_type(struct irq_data *d, unsigned type) { - int gpio = irq_nr - GPIO_MAPPED_IRQ_BASE; - int group = irq_to_group(irq_nr); + int gpio = d->irq - GPIO_MAPPED_IRQ_BASE; + int group = irq_to_group(d->irq); - if (group != GPIO_MAPPED_IRQ_GROUP || irq_nr > (GROUP4_IRQ_BASE + 13)) + if (group != GPIO_MAPPED_IRQ_GROUP || d->irq > (GROUP4_IRQ_BASE + 13)) return (type == IRQ_TYPE_LEVEL_HIGH) ? 0 : -EINVAL; switch (type) { @@ -193,11 +193,11 @@ static int rb532_set_type(unsigned int irq_nr, unsigned type) static struct irq_chip rc32434_irq_type = { .name = "RB532", - .ack = rb532_disable_irq, - .mask = rb532_disable_irq, - .mask_ack = rb532_mask_and_ack_irq, - .unmask = rb532_enable_irq, - .set_type = rb532_set_type, + .irq_ack = rb532_disable_irq, + .irq_mask = rb532_disable_irq, + .irq_mask_ack = rb532_mask_and_ack_irq, + .irq_unmask = rb532_enable_irq, + .irq_set_type = rb532_set_type, }; void __init arch_init_irq(void) diff --git a/arch/mips/sgi-ip22/ip22-int.c b/arch/mips/sgi-ip22/ip22-int.c index 383f11d7f442..e6e64750e90a 100644 --- a/arch/mips/sgi-ip22/ip22-int.c +++ b/arch/mips/sgi-ip22/ip22-int.c @@ -31,88 +31,80 @@ static char lc3msk_to_irqnr[256]; extern int ip22_eisa_init(void); -static void enable_local0_irq(unsigned int irq) +static void enable_local0_irq(struct irq_data *d) { /* don't allow mappable interrupt to be enabled from setup_irq, * we have our own way to do so */ - if (irq != SGI_MAP_0_IRQ) - sgint->imask0 |= (1 << (irq - SGINT_LOCAL0)); + if (d->irq != SGI_MAP_0_IRQ) + sgint->imask0 |= (1 << (d->irq - SGINT_LOCAL0)); } -static void disable_local0_irq(unsigned int irq) +static void disable_local0_irq(struct irq_data *d) { - sgint->imask0 &= ~(1 << (irq - SGINT_LOCAL0)); + sgint->imask0 &= ~(1 << (d->irq - SGINT_LOCAL0)); } static struct irq_chip ip22_local0_irq_type = { .name = "IP22 local 0", - .ack = disable_local0_irq, - .mask = disable_local0_irq, - .mask_ack = disable_local0_irq, - .unmask = enable_local0_irq, + .irq_mask = disable_local0_irq, + .irq_unmask = enable_local0_irq, }; -static void enable_local1_irq(unsigned int irq) +static void enable_local1_irq(struct irq_data *d) { /* don't allow mappable interrupt to be enabled from setup_irq, * we have our own way to do so */ - if (irq != SGI_MAP_1_IRQ) - sgint->imask1 |= (1 << (irq - SGINT_LOCAL1)); + if (d->irq != SGI_MAP_1_IRQ) + sgint->imask1 |= (1 << (d->irq - SGINT_LOCAL1)); } -static void disable_local1_irq(unsigned int irq) +static void disable_local1_irq(struct irq_data *d) { - sgint->imask1 &= ~(1 << (irq - SGINT_LOCAL1)); + sgint->imask1 &= ~(1 << (d->irq - SGINT_LOCAL1)); } static struct irq_chip ip22_local1_irq_type = { .name = "IP22 local 1", - .ack = disable_local1_irq, - .mask = disable_local1_irq, - .mask_ack = disable_local1_irq, - .unmask = enable_local1_irq, + .irq_mask = disable_local1_irq, + .irq_unmask = enable_local1_irq, }; -static void enable_local2_irq(unsigned int irq) +static void enable_local2_irq(struct irq_data *d) { sgint->imask0 |= (1 << (SGI_MAP_0_IRQ - SGINT_LOCAL0)); - sgint->cmeimask0 |= (1 << (irq - SGINT_LOCAL2)); + sgint->cmeimask0 |= (1 << (d->irq - SGINT_LOCAL2)); } -static void disable_local2_irq(unsigned int irq) +static void disable_local2_irq(struct irq_data *d) { - sgint->cmeimask0 &= ~(1 << (irq - SGINT_LOCAL2)); + sgint->cmeimask0 &= ~(1 << (d->irq - SGINT_LOCAL2)); if (!sgint->cmeimask0) sgint->imask0 &= ~(1 << (SGI_MAP_0_IRQ - SGINT_LOCAL0)); } static struct irq_chip ip22_local2_irq_type = { .name = "IP22 local 2", - .ack = disable_local2_irq, - .mask = disable_local2_irq, - .mask_ack = disable_local2_irq, - .unmask = enable_local2_irq, + .irq_mask = disable_local2_irq, + .irq_unmask = enable_local2_irq, }; -static void enable_local3_irq(unsigned int irq) +static void enable_local3_irq(struct irq_data *d) { sgint->imask1 |= (1 << (SGI_MAP_1_IRQ - SGINT_LOCAL1)); - sgint->cmeimask1 |= (1 << (irq - SGINT_LOCAL3)); + sgint->cmeimask1 |= (1 << (d->irq - SGINT_LOCAL3)); } -static void disable_local3_irq(unsigned int irq) +static void disable_local3_irq(struct irq_data *d) { - sgint->cmeimask1 &= ~(1 << (irq - SGINT_LOCAL3)); + sgint->cmeimask1 &= ~(1 << (d->irq - SGINT_LOCAL3)); if (!sgint->cmeimask1) sgint->imask1 &= ~(1 << (SGI_MAP_1_IRQ - SGINT_LOCAL1)); } static struct irq_chip ip22_local3_irq_type = { .name = "IP22 local 3", - .ack = disable_local3_irq, - .mask = disable_local3_irq, - .mask_ack = disable_local3_irq, - .unmask = enable_local3_irq, + .irq_mask = disable_local3_irq, + .irq_unmask = enable_local3_irq, }; static void indy_local0_irqdispatch(void) diff --git a/arch/mips/sgi-ip27/ip27-irq.c b/arch/mips/sgi-ip27/ip27-irq.c index 6a123ea72de5..f2d09d7700dd 100644 --- a/arch/mips/sgi-ip27/ip27-irq.c +++ b/arch/mips/sgi-ip27/ip27-irq.c @@ -240,7 +240,7 @@ static int intr_disconnect_level(int cpu, int bit) } /* Startup one of the (PCI ...) IRQs routes over a bridge. */ -static unsigned int startup_bridge_irq(unsigned int irq) +static unsigned int startup_bridge_irq(struct irq_data *d) { struct bridge_controller *bc; bridgereg_t device; @@ -248,16 +248,16 @@ static unsigned int startup_bridge_irq(unsigned int irq) int pin, swlevel; cpuid_t cpu; - pin = SLOT_FROM_PCI_IRQ(irq); - bc = IRQ_TO_BRIDGE(irq); + pin = SLOT_FROM_PCI_IRQ(d->irq); + bc = IRQ_TO_BRIDGE(d->irq); bridge = bc->base; - pr_debug("bridge_startup(): irq= 0x%x pin=%d\n", irq, pin); + pr_debug("bridge_startup(): irq= 0x%x pin=%d\n", d->irq, pin); /* * "map" irq to a swlevel greater than 6 since the first 6 bits * of INT_PEND0 are taken */ - swlevel = find_level(&cpu, irq); + swlevel = find_level(&cpu, d->irq); bridge->b_int_addr[pin].addr = (0x20000 | swlevel | (bc->nasid << 8)); bridge->b_int_enable |= (1 << pin); bridge->b_int_enable |= 0x7ffffe00; /* more stuff in int_enable */ @@ -288,53 +288,51 @@ static unsigned int startup_bridge_irq(unsigned int irq) } /* Shutdown one of the (PCI ...) IRQs routes over a bridge. */ -static void shutdown_bridge_irq(unsigned int irq) +static void shutdown_bridge_irq(struct irq_data *d) { - struct bridge_controller *bc = IRQ_TO_BRIDGE(irq); + struct bridge_controller *bc = IRQ_TO_BRIDGE(d->irq); bridge_t *bridge = bc->base; int pin, swlevel; cpuid_t cpu; - pr_debug("bridge_shutdown: irq 0x%x\n", irq); - pin = SLOT_FROM_PCI_IRQ(irq); + pr_debug("bridge_shutdown: irq 0x%x\n", d->irq); + pin = SLOT_FROM_PCI_IRQ(d->irq); /* * map irq to a swlevel greater than 6 since the first 6 bits * of INT_PEND0 are taken */ - swlevel = find_level(&cpu, irq); + swlevel = find_level(&cpu, d->irq); intr_disconnect_level(cpu, swlevel); bridge->b_int_enable &= ~(1 << pin); bridge->b_wid_tflush; } -static inline void enable_bridge_irq(unsigned int irq) +static inline void enable_bridge_irq(struct irq_data *d) { cpuid_t cpu; int swlevel; - swlevel = find_level(&cpu, irq); /* Criminal offence */ + swlevel = find_level(&cpu, d->irq); /* Criminal offence */ intr_connect_level(cpu, swlevel); } -static inline void disable_bridge_irq(unsigned int irq) +static inline void disable_bridge_irq(struct irq_data *d) { cpuid_t cpu; int swlevel; - swlevel = find_level(&cpu, irq); /* Criminal offence */ + swlevel = find_level(&cpu, d->irq); /* Criminal offence */ intr_disconnect_level(cpu, swlevel); } static struct irq_chip bridge_irq_type = { .name = "bridge", - .startup = startup_bridge_irq, - .shutdown = shutdown_bridge_irq, - .ack = disable_bridge_irq, - .mask = disable_bridge_irq, - .mask_ack = disable_bridge_irq, - .unmask = enable_bridge_irq, + .irq_startup = startup_bridge_irq, + .irq_shutdown = shutdown_bridge_irq, + .irq_mask = disable_bridge_irq, + .irq_unmask = enable_bridge_irq, }; void __devinit register_bridge_irq(unsigned int irq) diff --git a/arch/mips/sgi-ip27/ip27-timer.c b/arch/mips/sgi-ip27/ip27-timer.c index d6802d6d1f82..c01f558a2a09 100644 --- a/arch/mips/sgi-ip27/ip27-timer.c +++ b/arch/mips/sgi-ip27/ip27-timer.c @@ -36,21 +36,18 @@ #include <asm/sn/sn0/hubio.h> #include <asm/pci/bridge.h> -static void enable_rt_irq(unsigned int irq) +static void enable_rt_irq(struct irq_data *d) { } -static void disable_rt_irq(unsigned int irq) +static void disable_rt_irq(struct irq_data *d) { } static struct irq_chip rt_irq_type = { .name = "SN HUB RT timer", - .ack = disable_rt_irq, - .mask = disable_rt_irq, - .mask_ack = disable_rt_irq, - .unmask = enable_rt_irq, - .eoi = enable_rt_irq, + .irq_mask = disable_rt_irq, + .irq_unmask = enable_rt_irq, }; static int rt_next_event(unsigned long delta, struct clock_event_device *evt) diff --git a/arch/mips/sgi-ip32/ip32-irq.c b/arch/mips/sgi-ip32/ip32-irq.c index eb40824b172a..e0a3ce4a8d48 100644 --- a/arch/mips/sgi-ip32/ip32-irq.c +++ b/arch/mips/sgi-ip32/ip32-irq.c @@ -130,70 +130,48 @@ static struct irqaction cpuerr_irq = { static uint64_t crime_mask; -static inline void crime_enable_irq(unsigned int irq) +static inline void crime_enable_irq(struct irq_data *d) { - unsigned int bit = irq - CRIME_IRQ_BASE; + unsigned int bit = d->irq - CRIME_IRQ_BASE; crime_mask |= 1 << bit; crime->imask = crime_mask; } -static inline void crime_disable_irq(unsigned int irq) +static inline void crime_disable_irq(struct irq_data *d) { - unsigned int bit = irq - CRIME_IRQ_BASE; + unsigned int bit = d->irq - CRIME_IRQ_BASE; crime_mask &= ~(1 << bit); crime->imask = crime_mask; flush_crime_bus(); } -static void crime_level_mask_and_ack_irq(unsigned int irq) -{ - crime_disable_irq(irq); -} - -static void crime_level_end_irq(unsigned int irq) -{ - if (!(irq_desc[irq].status & (IRQ_DISABLED | IRQ_INPROGRESS))) - crime_enable_irq(irq); -} - static struct irq_chip crime_level_interrupt = { .name = "IP32 CRIME", - .ack = crime_level_mask_and_ack_irq, - .mask = crime_disable_irq, - .mask_ack = crime_level_mask_and_ack_irq, - .unmask = crime_enable_irq, - .end = crime_level_end_irq, + .irq_mask = crime_disable_irq, + .irq_unmask = crime_enable_irq, }; -static void crime_edge_mask_and_ack_irq(unsigned int irq) +static void crime_edge_mask_and_ack_irq(struct irq_data *d) { - unsigned int bit = irq - CRIME_IRQ_BASE; + unsigned int bit = d->irq - CRIME_IRQ_BASE; uint64_t crime_int; /* Edge triggered interrupts must be cleared. */ - crime_int = crime->hard_int; crime_int &= ~(1 << bit); crime->hard_int = crime_int; - crime_disable_irq(irq); -} - -static void crime_edge_end_irq(unsigned int irq) -{ - if (!(irq_desc[irq].status & (IRQ_DISABLED | IRQ_INPROGRESS))) - crime_enable_irq(irq); + crime_disable_irq(d); } static struct irq_chip crime_edge_interrupt = { .name = "IP32 CRIME", - .ack = crime_edge_mask_and_ack_irq, - .mask = crime_disable_irq, - .mask_ack = crime_edge_mask_and_ack_irq, - .unmask = crime_enable_irq, - .end = crime_edge_end_irq, + .irq_ack = crime_edge_mask_and_ack_irq, + .irq_mask = crime_disable_irq, + .irq_mask_ack = crime_edge_mask_and_ack_irq, + .irq_unmask = crime_enable_irq, }; /* @@ -204,37 +182,28 @@ static struct irq_chip crime_edge_interrupt = { static unsigned long macepci_mask; -static void enable_macepci_irq(unsigned int irq) +static void enable_macepci_irq(struct irq_data *d) { - macepci_mask |= MACEPCI_CONTROL_INT(irq - MACEPCI_SCSI0_IRQ); + macepci_mask |= MACEPCI_CONTROL_INT(d->irq - MACEPCI_SCSI0_IRQ); mace->pci.control = macepci_mask; - crime_mask |= 1 << (irq - CRIME_IRQ_BASE); + crime_mask |= 1 << (d->irq - CRIME_IRQ_BASE); crime->imask = crime_mask; } -static void disable_macepci_irq(unsigned int irq) +static void disable_macepci_irq(struct irq_data *d) { - crime_mask &= ~(1 << (irq - CRIME_IRQ_BASE)); + crime_mask &= ~(1 << (d->irq - CRIME_IRQ_BASE)); crime->imask = crime_mask; flush_crime_bus(); - macepci_mask &= ~MACEPCI_CONTROL_INT(irq - MACEPCI_SCSI0_IRQ); + macepci_mask &= ~MACEPCI_CONTROL_INT(d->irq - MACEPCI_SCSI0_IRQ); mace->pci.control = macepci_mask; flush_mace_bus(); } -static void end_macepci_irq(unsigned int irq) -{ - if (!(irq_desc[irq].status & (IRQ_DISABLED|IRQ_INPROGRESS))) - enable_macepci_irq(irq); -} - static struct irq_chip ip32_macepci_interrupt = { .name = "IP32 MACE PCI", - .ack = disable_macepci_irq, - .mask = disable_macepci_irq, - .mask_ack = disable_macepci_irq, - .unmask = enable_macepci_irq, - .end = end_macepci_irq, + .irq_mask = disable_macepci_irq, + .irq_unmask = enable_macepci_irq, }; /* This is used for MACE ISA interrupts. That means bits 4-6 in the @@ -276,13 +245,13 @@ static struct irq_chip ip32_macepci_interrupt = { static unsigned long maceisa_mask; -static void enable_maceisa_irq(unsigned int irq) +static void enable_maceisa_irq(struct irq_data *d) { unsigned int crime_int = 0; - pr_debug("maceisa enable: %u\n", irq); + pr_debug("maceisa enable: %u\n", d->irq); - switch (irq) { + switch (d->irq) { case MACEISA_AUDIO_SW_IRQ ... MACEISA_AUDIO3_MERR_IRQ: crime_int = MACE_AUDIO_INT; break; @@ -296,15 +265,15 @@ static void enable_maceisa_irq(unsigned int irq) pr_debug("crime_int %08x enabled\n", crime_int); crime_mask |= crime_int; crime->imask = crime_mask; - maceisa_mask |= 1 << (irq - MACEISA_AUDIO_SW_IRQ); + maceisa_mask |= 1 << (d->irq - MACEISA_AUDIO_SW_IRQ); mace->perif.ctrl.imask = maceisa_mask; } -static void disable_maceisa_irq(unsigned int irq) +static void disable_maceisa_irq(struct irq_data *d) { unsigned int crime_int = 0; - maceisa_mask &= ~(1 << (irq - MACEISA_AUDIO_SW_IRQ)); + maceisa_mask &= ~(1 << (d->irq - MACEISA_AUDIO_SW_IRQ)); if (!(maceisa_mask & MACEISA_AUDIO_INT)) crime_int |= MACE_AUDIO_INT; if (!(maceisa_mask & MACEISA_MISC_INT)) @@ -318,76 +287,57 @@ static void disable_maceisa_irq(unsigned int irq) flush_mace_bus(); } -static void mask_and_ack_maceisa_irq(unsigned int irq) +static void mask_and_ack_maceisa_irq(struct irq_data *d) { unsigned long mace_int; /* edge triggered */ mace_int = mace->perif.ctrl.istat; - mace_int &= ~(1 << (irq - MACEISA_AUDIO_SW_IRQ)); + mace_int &= ~(1 << (d->irq - MACEISA_AUDIO_SW_IRQ)); mace->perif.ctrl.istat = mace_int; - disable_maceisa_irq(irq); -} - -static void end_maceisa_irq(unsigned irq) -{ - if (!(irq_desc[irq].status & (IRQ_DISABLED | IRQ_INPROGRESS))) - enable_maceisa_irq(irq); + disable_maceisa_irq(d); } static struct irq_chip ip32_maceisa_level_interrupt = { .name = "IP32 MACE ISA", - .ack = disable_maceisa_irq, - .mask = disable_maceisa_irq, - .mask_ack = disable_maceisa_irq, - .unmask = enable_maceisa_irq, - .end = end_maceisa_irq, + .irq_mask = disable_maceisa_irq, + .irq_unmask = enable_maceisa_irq, }; static struct irq_chip ip32_maceisa_edge_interrupt = { .name = "IP32 MACE ISA", - .ack = mask_and_ack_maceisa_irq, - .mask = disable_maceisa_irq, - .mask_ack = mask_and_ack_maceisa_irq, - .unmask = enable_maceisa_irq, - .end = end_maceisa_irq, + .irq_ack = mask_and_ack_maceisa_irq, + .irq_mask = disable_maceisa_irq, + .irq_mask_ack = mask_and_ack_maceisa_irq, + .irq_unmask = enable_maceisa_irq, }; /* This is used for regular non-ISA, non-PCI MACE interrupts. That means * bits 0-3 and 7 in the CRIME register. */ -static void enable_mace_irq(unsigned int irq) +static void enable_mace_irq(struct irq_data *d) { - unsigned int bit = irq - CRIME_IRQ_BASE; + unsigned int bit = d->irq - CRIME_IRQ_BASE; crime_mask |= (1 << bit); crime->imask = crime_mask; } -static void disable_mace_irq(unsigned int irq) +static void disable_mace_irq(struct irq_data *d) { - unsigned int bit = irq - CRIME_IRQ_BASE; + unsigned int bit = d->irq - CRIME_IRQ_BASE; crime_mask &= ~(1 << bit); crime->imask = crime_mask; flush_crime_bus(); } -static void end_mace_irq(unsigned int irq) -{ - if (!(irq_desc[irq].status & (IRQ_DISABLED|IRQ_INPROGRESS))) - enable_mace_irq(irq); -} - static struct irq_chip ip32_mace_interrupt = { .name = "IP32 MACE", - .ack = disable_mace_irq, - .mask = disable_mace_irq, - .mask_ack = disable_mace_irq, - .unmask = enable_mace_irq, - .end = end_mace_irq, + .irq_mask = disable_mace_irq, + .irq_unmask = enable_mace_irq, }; static void ip32_unknown_interrupt(void) diff --git a/arch/mips/sibyte/bcm1480/irq.c b/arch/mips/sibyte/bcm1480/irq.c index 044bbe462c2c..89e8188a4665 100644 --- a/arch/mips/sibyte/bcm1480/irq.c +++ b/arch/mips/sibyte/bcm1480/irq.c @@ -44,31 +44,10 @@ * for interrupt lines */ - -static void end_bcm1480_irq(unsigned int irq); -static void enable_bcm1480_irq(unsigned int irq); -static void disable_bcm1480_irq(unsigned int irq); -static void ack_bcm1480_irq(unsigned int irq); -#ifdef CONFIG_SMP -static int bcm1480_set_affinity(unsigned int irq, const struct cpumask *mask); -#endif - #ifdef CONFIG_PCI extern unsigned long ht_eoi_space; #endif -static struct irq_chip bcm1480_irq_type = { - .name = "BCM1480-IMR", - .ack = ack_bcm1480_irq, - .mask = disable_bcm1480_irq, - .mask_ack = ack_bcm1480_irq, - .unmask = enable_bcm1480_irq, - .end = end_bcm1480_irq, -#ifdef CONFIG_SMP - .set_affinity = bcm1480_set_affinity -#endif -}; - /* Store the CPU id (not the logical number) */ int bcm1480_irq_owner[BCM1480_NR_IRQS]; @@ -109,12 +88,13 @@ void bcm1480_unmask_irq(int cpu, int irq) } #ifdef CONFIG_SMP -static int bcm1480_set_affinity(unsigned int irq, const struct cpumask *mask) +static int bcm1480_set_affinity(struct irq_data *d, const struct cpumask *mask, + bool force) { + unsigned int irq_dirty, irq = d->irq; int i = 0, old_cpu, cpu, int_on, k; u64 cur_ints; unsigned long flags; - unsigned int irq_dirty; i = cpumask_first(mask); @@ -156,21 +136,25 @@ static int bcm1480_set_affinity(unsigned int irq, const struct cpumask *mask) /*****************************************************************************/ -static void disable_bcm1480_irq(unsigned int irq) +static void disable_bcm1480_irq(struct irq_data *d) { + unsigned int irq = d->irq; + bcm1480_mask_irq(bcm1480_irq_owner[irq], irq); } -static void enable_bcm1480_irq(unsigned int irq) +static void enable_bcm1480_irq(struct irq_data *d) { + unsigned int irq = d->irq; + bcm1480_unmask_irq(bcm1480_irq_owner[irq], irq); } -static void ack_bcm1480_irq(unsigned int irq) +static void ack_bcm1480_irq(struct irq_data *d) { + unsigned int irq_dirty, irq = d->irq; u64 pending; - unsigned int irq_dirty; int k; /* @@ -217,14 +201,15 @@ static void ack_bcm1480_irq(unsigned int irq) bcm1480_mask_irq(bcm1480_irq_owner[irq], irq); } - -static void end_bcm1480_irq(unsigned int irq) -{ - if (!(irq_desc[irq].status & (IRQ_DISABLED | IRQ_INPROGRESS))) { - bcm1480_unmask_irq(bcm1480_irq_owner[irq], irq); - } -} - +static struct irq_chip bcm1480_irq_type = { + .name = "BCM1480-IMR", + .irq_mask_ack = ack_bcm1480_irq, + .irq_mask = disable_bcm1480_irq, + .irq_unmask = enable_bcm1480_irq, +#ifdef CONFIG_SMP + .irq_set_affinity = bcm1480_set_affinity +#endif +}; void __init init_bcm1480_irqs(void) { diff --git a/arch/mips/sibyte/sb1250/irq.c b/arch/mips/sibyte/sb1250/irq.c index 12ac04a658ee..fd269ea8d8a8 100644 --- a/arch/mips/sibyte/sb1250/irq.c +++ b/arch/mips/sibyte/sb1250/irq.c @@ -43,31 +43,10 @@ * for interrupt lines */ - -static void end_sb1250_irq(unsigned int irq); -static void enable_sb1250_irq(unsigned int irq); -static void disable_sb1250_irq(unsigned int irq); -static void ack_sb1250_irq(unsigned int irq); -#ifdef CONFIG_SMP -static int sb1250_set_affinity(unsigned int irq, const struct cpumask *mask); -#endif - #ifdef CONFIG_SIBYTE_HAS_LDT extern unsigned long ldt_eoi_space; #endif -static struct irq_chip sb1250_irq_type = { - .name = "SB1250-IMR", - .ack = ack_sb1250_irq, - .mask = disable_sb1250_irq, - .mask_ack = ack_sb1250_irq, - .unmask = enable_sb1250_irq, - .end = end_sb1250_irq, -#ifdef CONFIG_SMP - .set_affinity = sb1250_set_affinity -#endif -}; - /* Store the CPU id (not the logical number) */ int sb1250_irq_owner[SB1250_NR_IRQS]; @@ -102,9 +81,11 @@ void sb1250_unmask_irq(int cpu, int irq) } #ifdef CONFIG_SMP -static int sb1250_set_affinity(unsigned int irq, const struct cpumask *mask) +static int sb1250_set_affinity(struct irq_data *d, const struct cpumask *mask, + bool force) { int i = 0, old_cpu, cpu, int_on; + unsigned int irq = d->irq; u64 cur_ints; unsigned long flags; @@ -142,21 +123,17 @@ static int sb1250_set_affinity(unsigned int irq, const struct cpumask *mask) } #endif -/*****************************************************************************/ - -static void disable_sb1250_irq(unsigned int irq) +static void enable_sb1250_irq(struct irq_data *d) { - sb1250_mask_irq(sb1250_irq_owner[irq], irq); -} + unsigned int irq = d->irq; -static void enable_sb1250_irq(unsigned int irq) -{ sb1250_unmask_irq(sb1250_irq_owner[irq], irq); } -static void ack_sb1250_irq(unsigned int irq) +static void ack_sb1250_irq(struct irq_data *d) { + unsigned int irq = d->irq; #ifdef CONFIG_SIBYTE_HAS_LDT u64 pending; @@ -199,14 +176,14 @@ static void ack_sb1250_irq(unsigned int irq) sb1250_mask_irq(sb1250_irq_owner[irq], irq); } - -static void end_sb1250_irq(unsigned int irq) -{ - if (!(irq_desc[irq].status & (IRQ_DISABLED | IRQ_INPROGRESS))) { - sb1250_unmask_irq(sb1250_irq_owner[irq], irq); - } -} - +static struct irq_chip sb1250_irq_type = { + .name = "SB1250-IMR", + .irq_mask_ack = ack_sb1250_irq, + .irq_unmask = enable_sb1250_irq, +#ifdef CONFIG_SMP + .irq_set_affinity = sb1250_set_affinity +#endif +}; void __init init_sb1250_irqs(void) { diff --git a/arch/mips/sni/a20r.c b/arch/mips/sni/a20r.c index bbe7187879fa..72b94155778d 100644 --- a/arch/mips/sni/a20r.c +++ b/arch/mips/sni/a20r.c @@ -168,33 +168,22 @@ static u32 a20r_ack_hwint(void) return status; } -static inline void unmask_a20r_irq(unsigned int irq) +static inline void unmask_a20r_irq(struct irq_data *d) { - set_c0_status(0x100 << (irq - SNI_A20R_IRQ_BASE)); + set_c0_status(0x100 << (d->irq - SNI_A20R_IRQ_BASE)); irq_enable_hazard(); } -static inline void mask_a20r_irq(unsigned int irq) +static inline void mask_a20r_irq(struct irq_data *d) { - clear_c0_status(0x100 << (irq - SNI_A20R_IRQ_BASE)); + clear_c0_status(0x100 << (d->irq - SNI_A20R_IRQ_BASE)); irq_disable_hazard(); } -static void end_a20r_irq(unsigned int irq) -{ - if (!(irq_desc[irq].status & (IRQ_DISABLED | IRQ_INPROGRESS))) { - a20r_ack_hwint(); - unmask_a20r_irq(irq); - } -} - static struct irq_chip a20r_irq_type = { .name = "A20R", - .ack = mask_a20r_irq, - .mask = mask_a20r_irq, - .mask_ack = mask_a20r_irq, - .unmask = unmask_a20r_irq, - .end = end_a20r_irq, + .irq_mask = mask_a20r_irq, + .irq_unmask = unmask_a20r_irq, }; /* diff --git a/arch/mips/sni/pcimt.c b/arch/mips/sni/pcimt.c index 8c92c73bc717..cfcc68abc5b2 100644 --- a/arch/mips/sni/pcimt.c +++ b/arch/mips/sni/pcimt.c @@ -194,33 +194,24 @@ static struct pci_controller sni_controller = { .io_map_base = SNI_PORT_BASE }; -static void enable_pcimt_irq(unsigned int irq) +static void enable_pcimt_irq(struct irq_data *d) { - unsigned int mask = 1 << (irq - PCIMT_IRQ_INT2); + unsigned int mask = 1 << (d->irq - PCIMT_IRQ_INT2); *(volatile u8 *) PCIMT_IRQSEL |= mask; } -void disable_pcimt_irq(unsigned int irq) +void disable_pcimt_irq(struct irq_data *d) { - unsigned int mask = ~(1 << (irq - PCIMT_IRQ_INT2)); + unsigned int mask = ~(1 << (d->irq - PCIMT_IRQ_INT2)); *(volatile u8 *) PCIMT_IRQSEL &= mask; } -static void end_pcimt_irq(unsigned int irq) -{ - if (!(irq_desc[irq].status & (IRQ_DISABLED|IRQ_INPROGRESS))) - enable_pcimt_irq(irq); -} - static struct irq_chip pcimt_irq_type = { .name = "PCIMT", - .ack = disable_pcimt_irq, - .mask = disable_pcimt_irq, - .mask_ack = disable_pcimt_irq, - .unmask = enable_pcimt_irq, - .end = end_pcimt_irq, + .irq_mask = disable_pcimt_irq, + .irq_unmask = enable_pcimt_irq, }; /* diff --git a/arch/mips/sni/pcit.c b/arch/mips/sni/pcit.c index dc9874553bec..0846e99a6efe 100644 --- a/arch/mips/sni/pcit.c +++ b/arch/mips/sni/pcit.c @@ -156,33 +156,24 @@ static struct pci_controller sni_pcit_controller = { .io_map_base = SNI_PORT_BASE }; -static void enable_pcit_irq(unsigned int irq) +static void enable_pcit_irq(struct irq_data *d) { - u32 mask = 1 << (irq - SNI_PCIT_INT_START + 24); + u32 mask = 1 << (d->irq - SNI_PCIT_INT_START + 24); *(volatile u32 *)SNI_PCIT_INT_REG |= mask; } -void disable_pcit_irq(unsigned int irq) +void disable_pcit_irq(struct irq_data *d) { - u32 mask = 1 << (irq - SNI_PCIT_INT_START + 24); + u32 mask = 1 << (d->irq - SNI_PCIT_INT_START + 24); *(volatile u32 *)SNI_PCIT_INT_REG &= ~mask; } -void end_pcit_irq(unsigned int irq) -{ - if (!(irq_desc[irq].status & (IRQ_DISABLED|IRQ_INPROGRESS))) - enable_pcit_irq(irq); -} - static struct irq_chip pcit_irq_type = { .name = "PCIT", - .ack = disable_pcit_irq, - .mask = disable_pcit_irq, - .mask_ack = disable_pcit_irq, - .unmask = enable_pcit_irq, - .end = end_pcit_irq, + .irq_mask = disable_pcit_irq, + .irq_unmask = enable_pcit_irq, }; static void pcit_hwint1(void) diff --git a/arch/mips/sni/rm200.c b/arch/mips/sni/rm200.c index 0e6f42c2bbc8..f05d8e593300 100644 --- a/arch/mips/sni/rm200.c +++ b/arch/mips/sni/rm200.c @@ -155,12 +155,11 @@ static __iomem u8 *rm200_pic_slave; #define cached_master_mask (rm200_cached_irq_mask) #define cached_slave_mask (rm200_cached_irq_mask >> 8) -static void sni_rm200_disable_8259A_irq(unsigned int irq) +static void sni_rm200_disable_8259A_irq(struct irq_data *d) { - unsigned int mask; + unsigned int mask, irq = d->irq - RM200_I8259A_IRQ_BASE; unsigned long flags; - irq -= RM200_I8259A_IRQ_BASE; mask = 1 << irq; raw_spin_lock_irqsave(&sni_rm200_i8259A_lock, flags); rm200_cached_irq_mask |= mask; @@ -171,12 +170,11 @@ static void sni_rm200_disable_8259A_irq(unsigned int irq) raw_spin_unlock_irqrestore(&sni_rm200_i8259A_lock, flags); } -static void sni_rm200_enable_8259A_irq(unsigned int irq) +static void sni_rm200_enable_8259A_irq(struct irq_data *d) { - unsigned int mask; + unsigned int mask, irq = d->irq - RM200_I8259A_IRQ_BASE; unsigned long flags; - irq -= RM200_I8259A_IRQ_BASE; mask = ~(1 << irq); raw_spin_lock_irqsave(&sni_rm200_i8259A_lock, flags); rm200_cached_irq_mask &= mask; @@ -210,12 +208,11 @@ static inline int sni_rm200_i8259A_irq_real(unsigned int irq) * first, _then_ send the EOI, and the order of EOI * to the two 8259s is important! */ -void sni_rm200_mask_and_ack_8259A(unsigned int irq) +void sni_rm200_mask_and_ack_8259A(struct irq_data *d) { - unsigned int irqmask; + unsigned int irqmask, irq = d->irq - RM200_I8259A_IRQ_BASE; unsigned long flags; - irq -= RM200_I8259A_IRQ_BASE; irqmask = 1 << irq; raw_spin_lock_irqsave(&sni_rm200_i8259A_lock, flags); /* @@ -285,9 +282,9 @@ spurious_8259A_irq: static struct irq_chip sni_rm200_i8259A_chip = { .name = "RM200-XT-PIC", - .mask = sni_rm200_disable_8259A_irq, - .unmask = sni_rm200_enable_8259A_irq, - .mask_ack = sni_rm200_mask_and_ack_8259A, + .irq_mask = sni_rm200_disable_8259A_irq, + .irq_unmask = sni_rm200_enable_8259A_irq, + .irq_mask_ack = sni_rm200_mask_and_ack_8259A, }; /* @@ -429,33 +426,24 @@ void __init sni_rm200_i8259_irqs(void) #define SNI_RM200_INT_START 24 #define SNI_RM200_INT_END 28 -static void enable_rm200_irq(unsigned int irq) +static void enable_rm200_irq(struct irq_data *d) { - unsigned int mask = 1 << (irq - SNI_RM200_INT_START); + unsigned int mask = 1 << (d->irq - SNI_RM200_INT_START); *(volatile u8 *)SNI_RM200_INT_ENA_REG &= ~mask; } -void disable_rm200_irq(unsigned int irq) +void disable_rm200_irq(struct irq_data *d) { - unsigned int mask = 1 << (irq - SNI_RM200_INT_START); + unsigned int mask = 1 << (d->irq - SNI_RM200_INT_START); *(volatile u8 *)SNI_RM200_INT_ENA_REG |= mask; } -void end_rm200_irq(unsigned int irq) -{ - if (!(irq_desc[irq].status & (IRQ_DISABLED|IRQ_INPROGRESS))) - enable_rm200_irq(irq); -} - static struct irq_chip rm200_irq_type = { .name = "RM200", - .ack = disable_rm200_irq, - .mask = disable_rm200_irq, - .mask_ack = disable_rm200_irq, - .unmask = enable_rm200_irq, - .end = end_rm200_irq, + .irq_mask = disable_rm200_irq, + .irq_unmask = enable_rm200_irq, }; static void sni_rm200_hwint(void) diff --git a/arch/mips/txx9/generic/irq_tx4939.c b/arch/mips/txx9/generic/irq_tx4939.c index 3886ad77cbad..93b6edbedd64 100644 --- a/arch/mips/txx9/generic/irq_tx4939.c +++ b/arch/mips/txx9/generic/irq_tx4939.c @@ -50,9 +50,9 @@ static struct { unsigned char mode; } tx4939irq[TX4939_NUM_IR] __read_mostly; -static void tx4939_irq_unmask(unsigned int irq) +static void tx4939_irq_unmask(struct irq_data *d) { - unsigned int irq_nr = irq - TXX9_IRQ_BASE; + unsigned int irq_nr = d->irq - TXX9_IRQ_BASE; u32 __iomem *lvlp; int ofs; if (irq_nr < 32) { @@ -68,9 +68,9 @@ static void tx4939_irq_unmask(unsigned int irq) lvlp); } -static inline void tx4939_irq_mask(unsigned int irq) +static inline void tx4939_irq_mask(struct irq_data *d) { - unsigned int irq_nr = irq - TXX9_IRQ_BASE; + unsigned int irq_nr = d->irq - TXX9_IRQ_BASE; u32 __iomem *lvlp; int ofs; if (irq_nr < 32) { @@ -87,11 +87,11 @@ static inline void tx4939_irq_mask(unsigned int irq) mmiowb(); } -static void tx4939_irq_mask_ack(unsigned int irq) +static void tx4939_irq_mask_ack(struct irq_data *d) { - unsigned int irq_nr = irq - TXX9_IRQ_BASE; + unsigned int irq_nr = d->irq - TXX9_IRQ_BASE; - tx4939_irq_mask(irq); + tx4939_irq_mask(d); if (TXx9_IRCR_EDGE(tx4939irq[irq_nr].mode)) { irq_nr--; /* clear edge detection */ @@ -101,9 +101,9 @@ static void tx4939_irq_mask_ack(unsigned int irq) } } -static int tx4939_irq_set_type(unsigned int irq, unsigned int flow_type) +static int tx4939_irq_set_type(struct irq_data *d, unsigned int flow_type) { - unsigned int irq_nr = irq - TXX9_IRQ_BASE; + unsigned int irq_nr = d->irq - TXX9_IRQ_BASE; u32 cr; u32 __iomem *crp; int ofs; @@ -145,11 +145,11 @@ static int tx4939_irq_set_type(unsigned int irq, unsigned int flow_type) static struct irq_chip tx4939_irq_chip = { .name = "TX4939", - .ack = tx4939_irq_mask_ack, - .mask = tx4939_irq_mask, - .mask_ack = tx4939_irq_mask_ack, - .unmask = tx4939_irq_unmask, - .set_type = tx4939_irq_set_type, + .irq_ack = tx4939_irq_mask_ack, + .irq_mask = tx4939_irq_mask, + .irq_mask_ack = tx4939_irq_mask_ack, + .irq_unmask = tx4939_irq_unmask, + .irq_set_type = tx4939_irq_set_type, }; static int tx4939_irq_set_pri(int irc_irq, int new_pri) diff --git a/arch/mips/txx9/jmr3927/irq.c b/arch/mips/txx9/jmr3927/irq.c index 0a7f8e3b9fd7..92a5c1b400f0 100644 --- a/arch/mips/txx9/jmr3927/irq.c +++ b/arch/mips/txx9/jmr3927/irq.c @@ -47,20 +47,20 @@ * CP0_STATUS is a thread's resource (saved/restored on context switch). * So disable_irq/enable_irq MUST handle IOC/IRC registers. */ -static void mask_irq_ioc(unsigned int irq) +static void mask_irq_ioc(struct irq_data *d) { /* 0: mask */ - unsigned int irq_nr = irq - JMR3927_IRQ_IOC; + unsigned int irq_nr = d->irq - JMR3927_IRQ_IOC; unsigned char imask = jmr3927_ioc_reg_in(JMR3927_IOC_INTM_ADDR); unsigned int bit = 1 << irq_nr; jmr3927_ioc_reg_out(imask & ~bit, JMR3927_IOC_INTM_ADDR); /* flush write buffer */ (void)jmr3927_ioc_reg_in(JMR3927_IOC_REV_ADDR); } -static void unmask_irq_ioc(unsigned int irq) +static void unmask_irq_ioc(struct irq_data *d) { /* 0: mask */ - unsigned int irq_nr = irq - JMR3927_IRQ_IOC; + unsigned int irq_nr = d->irq - JMR3927_IRQ_IOC; unsigned char imask = jmr3927_ioc_reg_in(JMR3927_IOC_INTM_ADDR); unsigned int bit = 1 << irq_nr; jmr3927_ioc_reg_out(imask | bit, JMR3927_IOC_INTM_ADDR); @@ -95,10 +95,8 @@ static int jmr3927_irq_dispatch(int pending) static struct irq_chip jmr3927_irq_ioc = { .name = "jmr3927_ioc", - .ack = mask_irq_ioc, - .mask = mask_irq_ioc, - .mask_ack = mask_irq_ioc, - .unmask = unmask_irq_ioc, + .irq_mask = mask_irq_ioc, + .irq_unmask = unmask_irq_ioc, }; void __init jmr3927_irq_setup(void) diff --git a/arch/mips/txx9/rbtx4927/irq.c b/arch/mips/txx9/rbtx4927/irq.c index c4b54d20efd3..7c0a048b307c 100644 --- a/arch/mips/txx9/rbtx4927/irq.c +++ b/arch/mips/txx9/rbtx4927/irq.c @@ -117,18 +117,6 @@ #include <asm/txx9/generic.h> #include <asm/txx9/rbtx4927.h> -static void toshiba_rbtx4927_irq_ioc_enable(unsigned int irq); -static void toshiba_rbtx4927_irq_ioc_disable(unsigned int irq); - -#define TOSHIBA_RBTX4927_IOC_NAME "RBTX4927-IOC" -static struct irq_chip toshiba_rbtx4927_irq_ioc_type = { - .name = TOSHIBA_RBTX4927_IOC_NAME, - .ack = toshiba_rbtx4927_irq_ioc_disable, - .mask = toshiba_rbtx4927_irq_ioc_disable, - .mask_ack = toshiba_rbtx4927_irq_ioc_disable, - .unmask = toshiba_rbtx4927_irq_ioc_enable, -}; - static int toshiba_rbtx4927_irq_nested(int sw_irq) { u8 level3; @@ -139,41 +127,47 @@ static int toshiba_rbtx4927_irq_nested(int sw_irq) return RBTX4927_IRQ_IOC + __fls8(level3); } -static void __init toshiba_rbtx4927_irq_ioc_init(void) -{ - int i; - - /* mask all IOC interrupts */ - writeb(0, rbtx4927_imask_addr); - /* clear SoftInt interrupts */ - writeb(0, rbtx4927_softint_addr); - - for (i = RBTX4927_IRQ_IOC; - i < RBTX4927_IRQ_IOC + RBTX4927_NR_IRQ_IOC; i++) - set_irq_chip_and_handler(i, &toshiba_rbtx4927_irq_ioc_type, - handle_level_irq); - set_irq_chained_handler(RBTX4927_IRQ_IOCINT, handle_simple_irq); -} - -static void toshiba_rbtx4927_irq_ioc_enable(unsigned int irq) +static void toshiba_rbtx4927_irq_ioc_enable(struct irq_data *d) { unsigned char v; v = readb(rbtx4927_imask_addr); - v |= (1 << (irq - RBTX4927_IRQ_IOC)); + v |= (1 << (d->irq - RBTX4927_IRQ_IOC)); writeb(v, rbtx4927_imask_addr); } -static void toshiba_rbtx4927_irq_ioc_disable(unsigned int irq) +static void toshiba_rbtx4927_irq_ioc_disable(struct irq_data *d) { unsigned char v; v = readb(rbtx4927_imask_addr); - v &= ~(1 << (irq - RBTX4927_IRQ_IOC)); + v &= ~(1 << (d->irq - RBTX4927_IRQ_IOC)); writeb(v, rbtx4927_imask_addr); mmiowb(); } +#define TOSHIBA_RBTX4927_IOC_NAME "RBTX4927-IOC" +static struct irq_chip toshiba_rbtx4927_irq_ioc_type = { + .name = TOSHIBA_RBTX4927_IOC_NAME, + .irq_mask = toshiba_rbtx4927_irq_ioc_disable, + .irq_unmask = toshiba_rbtx4927_irq_ioc_enable, +}; + +static void __init toshiba_rbtx4927_irq_ioc_init(void) +{ + int i; + + /* mask all IOC interrupts */ + writeb(0, rbtx4927_imask_addr); + /* clear SoftInt interrupts */ + writeb(0, rbtx4927_softint_addr); + + for (i = RBTX4927_IRQ_IOC; + i < RBTX4927_IRQ_IOC + RBTX4927_NR_IRQ_IOC; i++) + set_irq_chip_and_handler(i, &toshiba_rbtx4927_irq_ioc_type, + handle_level_irq); + set_irq_chained_handler(RBTX4927_IRQ_IOCINT, handle_simple_irq); +} static int rbtx4927_irq_dispatch(int pending) { diff --git a/arch/mips/txx9/rbtx4938/irq.c b/arch/mips/txx9/rbtx4938/irq.c index 67a73a8065ec..2ec4fe1b1670 100644 --- a/arch/mips/txx9/rbtx4938/irq.c +++ b/arch/mips/txx9/rbtx4938/irq.c @@ -69,18 +69,6 @@ #include <asm/txx9/generic.h> #include <asm/txx9/rbtx4938.h> -static void toshiba_rbtx4938_irq_ioc_enable(unsigned int irq); -static void toshiba_rbtx4938_irq_ioc_disable(unsigned int irq); - -#define TOSHIBA_RBTX4938_IOC_NAME "RBTX4938-IOC" -static struct irq_chip toshiba_rbtx4938_irq_ioc_type = { - .name = TOSHIBA_RBTX4938_IOC_NAME, - .ack = toshiba_rbtx4938_irq_ioc_disable, - .mask = toshiba_rbtx4938_irq_ioc_disable, - .mask_ack = toshiba_rbtx4938_irq_ioc_disable, - .unmask = toshiba_rbtx4938_irq_ioc_enable, -}; - static int toshiba_rbtx4938_irq_nested(int sw_irq) { u8 level3; @@ -92,41 +80,33 @@ static int toshiba_rbtx4938_irq_nested(int sw_irq) return RBTX4938_IRQ_IOC + __fls8(level3); } -static void __init -toshiba_rbtx4938_irq_ioc_init(void) -{ - int i; - - for (i = RBTX4938_IRQ_IOC; - i < RBTX4938_IRQ_IOC + RBTX4938_NR_IRQ_IOC; i++) - set_irq_chip_and_handler(i, &toshiba_rbtx4938_irq_ioc_type, - handle_level_irq); - - set_irq_chained_handler(RBTX4938_IRQ_IOCINT, handle_simple_irq); -} - -static void -toshiba_rbtx4938_irq_ioc_enable(unsigned int irq) +static void toshiba_rbtx4938_irq_ioc_enable(struct irq_data *d) { unsigned char v; v = readb(rbtx4938_imask_addr); - v |= (1 << (irq - RBTX4938_IRQ_IOC)); + v |= (1 << (d->irq - RBTX4938_IRQ_IOC)); writeb(v, rbtx4938_imask_addr); mmiowb(); } -static void -toshiba_rbtx4938_irq_ioc_disable(unsigned int irq) +static void toshiba_rbtx4938_irq_ioc_disable(struct irq_data *d) { unsigned char v; v = readb(rbtx4938_imask_addr); - v &= ~(1 << (irq - RBTX4938_IRQ_IOC)); + v &= ~(1 << (d->irq - RBTX4938_IRQ_IOC)); writeb(v, rbtx4938_imask_addr); mmiowb(); } +#define TOSHIBA_RBTX4938_IOC_NAME "RBTX4938-IOC" +static struct irq_chip toshiba_rbtx4938_irq_ioc_type = { + .name = TOSHIBA_RBTX4938_IOC_NAME, + .irq_mask = toshiba_rbtx4938_irq_ioc_disable, + .irq_unmask = toshiba_rbtx4938_irq_ioc_enable, +}; + static int rbtx4938_irq_dispatch(int pending) { int irq; @@ -146,6 +126,18 @@ static int rbtx4938_irq_dispatch(int pending) return irq; } +static void __init toshiba_rbtx4938_irq_ioc_init(void) +{ + int i; + + for (i = RBTX4938_IRQ_IOC; + i < RBTX4938_IRQ_IOC + RBTX4938_NR_IRQ_IOC; i++) + set_irq_chip_and_handler(i, &toshiba_rbtx4938_irq_ioc_type, + handle_level_irq); + + set_irq_chained_handler(RBTX4938_IRQ_IOCINT, handle_simple_irq); +} + void __init rbtx4938_irq_setup(void) { txx9_irq_dispatch = rbtx4938_irq_dispatch; diff --git a/arch/mips/txx9/rbtx4939/irq.c b/arch/mips/txx9/rbtx4939/irq.c index 57fa740a7205..70074632fb99 100644 --- a/arch/mips/txx9/rbtx4939/irq.c +++ b/arch/mips/txx9/rbtx4939/irq.c @@ -19,16 +19,16 @@ * RBTX4939 IOC controller definition */ -static void rbtx4939_ioc_irq_unmask(unsigned int irq) +static void rbtx4939_ioc_irq_unmask(struct irq_data *d) { - int ioc_nr = irq - RBTX4939_IRQ_IOC; + int ioc_nr = d->irq - RBTX4939_IRQ_IOC; writeb(readb(rbtx4939_ien_addr) | (1 << ioc_nr), rbtx4939_ien_addr); } -static void rbtx4939_ioc_irq_mask(unsigned int irq) +static void rbtx4939_ioc_irq_mask(struct irq_data *d) { - int ioc_nr = irq - RBTX4939_IRQ_IOC; + int ioc_nr = d->irq - RBTX4939_IRQ_IOC; writeb(readb(rbtx4939_ien_addr) & ~(1 << ioc_nr), rbtx4939_ien_addr); mmiowb(); @@ -36,10 +36,8 @@ static void rbtx4939_ioc_irq_mask(unsigned int irq) static struct irq_chip rbtx4939_ioc_irq_chip = { .name = "IOC", - .ack = rbtx4939_ioc_irq_mask, - .mask = rbtx4939_ioc_irq_mask, - .mask_ack = rbtx4939_ioc_irq_mask, - .unmask = rbtx4939_ioc_irq_unmask, + .irq_mask = rbtx4939_ioc_irq_mask, + .irq_unmask = rbtx4939_ioc_irq_unmask, }; diff --git a/arch/mips/vr41xx/common/icu.c b/arch/mips/vr41xx/common/icu.c index 6153b6a05ccf..f53156bb9aa8 100644 --- a/arch/mips/vr41xx/common/icu.c +++ b/arch/mips/vr41xx/common/icu.c @@ -154,7 +154,7 @@ static inline uint16_t icu2_clear(uint8_t offset, uint16_t clear) void vr41xx_enable_piuint(uint16_t mask) { - struct irq_desc *desc = irq_desc + PIU_IRQ; + struct irq_desc *desc = irq_to_desc(PIU_IRQ); unsigned long flags; if (current_cpu_type() == CPU_VR4111 || @@ -169,7 +169,7 @@ EXPORT_SYMBOL(vr41xx_enable_piuint); void vr41xx_disable_piuint(uint16_t mask) { - struct irq_desc *desc = irq_desc + PIU_IRQ; + struct irq_desc *desc = irq_to_desc(PIU_IRQ); unsigned long flags; if (current_cpu_type() == CPU_VR4111 || @@ -184,7 +184,7 @@ EXPORT_SYMBOL(vr41xx_disable_piuint); void vr41xx_enable_aiuint(uint16_t mask) { - struct irq_desc *desc = irq_desc + AIU_IRQ; + struct irq_desc *desc = irq_to_desc(AIU_IRQ); unsigned long flags; if (current_cpu_type() == CPU_VR4111 || @@ -199,7 +199,7 @@ EXPORT_SYMBOL(vr41xx_enable_aiuint); void vr41xx_disable_aiuint(uint16_t mask) { - struct irq_desc *desc = irq_desc + AIU_IRQ; + struct irq_desc *desc = irq_to_desc(AIU_IRQ); unsigned long flags; if (current_cpu_type() == CPU_VR4111 || @@ -214,7 +214,7 @@ EXPORT_SYMBOL(vr41xx_disable_aiuint); void vr41xx_enable_kiuint(uint16_t mask) { - struct irq_desc *desc = irq_desc + KIU_IRQ; + struct irq_desc *desc = irq_to_desc(KIU_IRQ); unsigned long flags; if (current_cpu_type() == CPU_VR4111 || @@ -229,7 +229,7 @@ EXPORT_SYMBOL(vr41xx_enable_kiuint); void vr41xx_disable_kiuint(uint16_t mask) { - struct irq_desc *desc = irq_desc + KIU_IRQ; + struct irq_desc *desc = irq_to_desc(KIU_IRQ); unsigned long flags; if (current_cpu_type() == CPU_VR4111 || @@ -244,7 +244,7 @@ EXPORT_SYMBOL(vr41xx_disable_kiuint); void vr41xx_enable_macint(uint16_t mask) { - struct irq_desc *desc = irq_desc + ETHERNET_IRQ; + struct irq_desc *desc = irq_to_desc(ETHERNET_IRQ); unsigned long flags; raw_spin_lock_irqsave(&desc->lock, flags); @@ -256,7 +256,7 @@ EXPORT_SYMBOL(vr41xx_enable_macint); void vr41xx_disable_macint(uint16_t mask) { - struct irq_desc *desc = irq_desc + ETHERNET_IRQ; + struct irq_desc *desc = irq_to_desc(ETHERNET_IRQ); unsigned long flags; raw_spin_lock_irqsave(&desc->lock, flags); @@ -268,7 +268,7 @@ EXPORT_SYMBOL(vr41xx_disable_macint); void vr41xx_enable_dsiuint(uint16_t mask) { - struct irq_desc *desc = irq_desc + DSIU_IRQ; + struct irq_desc *desc = irq_to_desc(DSIU_IRQ); unsigned long flags; raw_spin_lock_irqsave(&desc->lock, flags); @@ -280,7 +280,7 @@ EXPORT_SYMBOL(vr41xx_enable_dsiuint); void vr41xx_disable_dsiuint(uint16_t mask) { - struct irq_desc *desc = irq_desc + DSIU_IRQ; + struct irq_desc *desc = irq_to_desc(DSIU_IRQ); unsigned long flags; raw_spin_lock_irqsave(&desc->lock, flags); @@ -292,7 +292,7 @@ EXPORT_SYMBOL(vr41xx_disable_dsiuint); void vr41xx_enable_firint(uint16_t mask) { - struct irq_desc *desc = irq_desc + FIR_IRQ; + struct irq_desc *desc = irq_to_desc(FIR_IRQ); unsigned long flags; raw_spin_lock_irqsave(&desc->lock, flags); @@ -304,7 +304,7 @@ EXPORT_SYMBOL(vr41xx_enable_firint); void vr41xx_disable_firint(uint16_t mask) { - struct irq_desc *desc = irq_desc + FIR_IRQ; + struct irq_desc *desc = irq_to_desc(FIR_IRQ); unsigned long flags; raw_spin_lock_irqsave(&desc->lock, flags); @@ -316,7 +316,7 @@ EXPORT_SYMBOL(vr41xx_disable_firint); void vr41xx_enable_pciint(void) { - struct irq_desc *desc = irq_desc + PCI_IRQ; + struct irq_desc *desc = irq_to_desc(PCI_IRQ); unsigned long flags; if (current_cpu_type() == CPU_VR4122 || @@ -332,7 +332,7 @@ EXPORT_SYMBOL(vr41xx_enable_pciint); void vr41xx_disable_pciint(void) { - struct irq_desc *desc = irq_desc + PCI_IRQ; + struct irq_desc *desc = irq_to_desc(PCI_IRQ); unsigned long flags; if (current_cpu_type() == CPU_VR4122 || @@ -348,7 +348,7 @@ EXPORT_SYMBOL(vr41xx_disable_pciint); void vr41xx_enable_scuint(void) { - struct irq_desc *desc = irq_desc + SCU_IRQ; + struct irq_desc *desc = irq_to_desc(SCU_IRQ); unsigned long flags; if (current_cpu_type() == CPU_VR4122 || @@ -364,7 +364,7 @@ EXPORT_SYMBOL(vr41xx_enable_scuint); void vr41xx_disable_scuint(void) { - struct irq_desc *desc = irq_desc + SCU_IRQ; + struct irq_desc *desc = irq_to_desc(SCU_IRQ); unsigned long flags; if (current_cpu_type() == CPU_VR4122 || @@ -380,7 +380,7 @@ EXPORT_SYMBOL(vr41xx_disable_scuint); void vr41xx_enable_csiint(uint16_t mask) { - struct irq_desc *desc = irq_desc + CSI_IRQ; + struct irq_desc *desc = irq_to_desc(CSI_IRQ); unsigned long flags; if (current_cpu_type() == CPU_VR4122 || @@ -396,7 +396,7 @@ EXPORT_SYMBOL(vr41xx_enable_csiint); void vr41xx_disable_csiint(uint16_t mask) { - struct irq_desc *desc = irq_desc + CSI_IRQ; + struct irq_desc *desc = irq_to_desc(CSI_IRQ); unsigned long flags; if (current_cpu_type() == CPU_VR4122 || @@ -412,7 +412,7 @@ EXPORT_SYMBOL(vr41xx_disable_csiint); void vr41xx_enable_bcuint(void) { - struct irq_desc *desc = irq_desc + BCU_IRQ; + struct irq_desc *desc = irq_to_desc(BCU_IRQ); unsigned long flags; if (current_cpu_type() == CPU_VR4122 || @@ -428,7 +428,7 @@ EXPORT_SYMBOL(vr41xx_enable_bcuint); void vr41xx_disable_bcuint(void) { - struct irq_desc *desc = irq_desc + BCU_IRQ; + struct irq_desc *desc = irq_to_desc(BCU_IRQ); unsigned long flags; if (current_cpu_type() == CPU_VR4122 || @@ -442,45 +442,41 @@ void vr41xx_disable_bcuint(void) EXPORT_SYMBOL(vr41xx_disable_bcuint); -static void disable_sysint1_irq(unsigned int irq) +static void disable_sysint1_irq(struct irq_data *d) { - icu1_clear(MSYSINT1REG, 1 << SYSINT1_IRQ_TO_PIN(irq)); + icu1_clear(MSYSINT1REG, 1 << SYSINT1_IRQ_TO_PIN(d->irq)); } -static void enable_sysint1_irq(unsigned int irq) +static void enable_sysint1_irq(struct irq_data *d) { - icu1_set(MSYSINT1REG, 1 << SYSINT1_IRQ_TO_PIN(irq)); + icu1_set(MSYSINT1REG, 1 << SYSINT1_IRQ_TO_PIN(d->irq)); } static struct irq_chip sysint1_irq_type = { .name = "SYSINT1", - .ack = disable_sysint1_irq, - .mask = disable_sysint1_irq, - .mask_ack = disable_sysint1_irq, - .unmask = enable_sysint1_irq, + .irq_mask = disable_sysint1_irq, + .irq_unmask = enable_sysint1_irq, }; -static void disable_sysint2_irq(unsigned int irq) +static void disable_sysint2_irq(struct irq_data *d) { - icu2_clear(MSYSINT2REG, 1 << SYSINT2_IRQ_TO_PIN(irq)); + icu2_clear(MSYSINT2REG, 1 << SYSINT2_IRQ_TO_PIN(d->irq)); } -static void enable_sysint2_irq(unsigned int irq) +static void enable_sysint2_irq(struct irq_data *d) { - icu2_set(MSYSINT2REG, 1 << SYSINT2_IRQ_TO_PIN(irq)); + icu2_set(MSYSINT2REG, 1 << SYSINT2_IRQ_TO_PIN(d->irq)); } static struct irq_chip sysint2_irq_type = { .name = "SYSINT2", - .ack = disable_sysint2_irq, - .mask = disable_sysint2_irq, - .mask_ack = disable_sysint2_irq, - .unmask = enable_sysint2_irq, + .irq_mask = disable_sysint2_irq, + .irq_unmask = enable_sysint2_irq, }; static inline int set_sysint1_assign(unsigned int irq, unsigned char assign) { - struct irq_desc *desc = irq_desc + irq; + struct irq_desc *desc = irq_to_desc(irq); uint16_t intassign0, intassign1; unsigned int pin; @@ -540,7 +536,7 @@ static inline int set_sysint1_assign(unsigned int irq, unsigned char assign) static inline int set_sysint2_assign(unsigned int irq, unsigned char assign) { - struct irq_desc *desc = irq_desc + irq; + struct irq_desc *desc = irq_to_desc(irq); uint16_t intassign2, intassign3; unsigned int pin; diff --git a/arch/mips/vr41xx/common/irq.c b/arch/mips/vr41xx/common/irq.c index 0975eb72d385..9ff7f397c0e1 100644 --- a/arch/mips/vr41xx/common/irq.c +++ b/arch/mips/vr41xx/common/irq.c @@ -62,7 +62,6 @@ EXPORT_SYMBOL_GPL(cascade_irq); static void irq_dispatch(unsigned int irq) { irq_cascade_t *cascade; - struct irq_desc *desc; if (irq >= NR_IRQS) { atomic_inc(&irq_err_count); @@ -71,14 +70,16 @@ static void irq_dispatch(unsigned int irq) cascade = irq_cascade + irq; if (cascade->get_irq != NULL) { - unsigned int source_irq = irq; + struct irq_desc *desc = irq_to_desc(irq); + struct irq_data *idata = irq_desc_get_irq_data(desc); + struct irq_chip *chip = irq_desc_get_chip(desc); int ret; - desc = irq_desc + source_irq; - if (desc->chip->mask_ack) - desc->chip->mask_ack(source_irq); + + if (chip->irq_mask_ack) + chip->irq_mask_ack(idata); else { - desc->chip->mask(source_irq); - desc->chip->ack(source_irq); + chip->irq_mask(idata); + chip->irq_ack(idata); } ret = cascade->get_irq(irq); irq = ret; @@ -86,8 +87,8 @@ static void irq_dispatch(unsigned int irq) atomic_inc(&irq_err_count); else irq_dispatch(irq); - if (!(desc->status & IRQ_DISABLED) && desc->chip->unmask) - desc->chip->unmask(source_irq); + if (!(desc->status & IRQ_DISABLED) && chip->irq_unmask) + chip->irq_unmask(idata); } else do_IRQ(irq); } diff --git a/arch/s390/include/asm/ccwdev.h b/arch/s390/include/asm/ccwdev.h index ff6f62e0ec3e..623f2fb71774 100644 --- a/arch/s390/include/asm/ccwdev.h +++ b/arch/s390/include/asm/ccwdev.h @@ -112,7 +112,6 @@ enum uc_todo { /** * struct ccw driver - device driver for channel attached devices - * @owner: owning module * @ids: ids supported by this driver * @probe: function called on probe * @remove: function called on remove @@ -128,10 +127,8 @@ enum uc_todo { * @restore: callback for restoring after hibernation * @uc_handler: callback for unit check handler * @driver: embedded device driver structure - * @name: device driver name */ struct ccw_driver { - struct module *owner; struct ccw_device_id *ids; int (*probe) (struct ccw_device *); void (*remove) (struct ccw_device *); @@ -147,7 +144,6 @@ struct ccw_driver { int (*restore)(struct ccw_device *); enum uc_todo (*uc_handler) (struct ccw_device *, struct irb *); struct device_driver driver; - char *name; }; extern struct ccw_device *get_ccwdev_by_busid(struct ccw_driver *cdrv, diff --git a/arch/s390/include/asm/ccwgroup.h b/arch/s390/include/asm/ccwgroup.h index c79c1e787b86..f2ea2c56a7e1 100644 --- a/arch/s390/include/asm/ccwgroup.h +++ b/arch/s390/include/asm/ccwgroup.h @@ -29,8 +29,6 @@ struct ccwgroup_device { /** * struct ccwgroup_driver - driver for ccw group devices - * @owner: driver owner - * @name: driver name * @max_slaves: maximum number of slave devices * @driver_id: unique id * @probe: function called on probe @@ -46,8 +44,6 @@ struct ccwgroup_device { * @driver: embedded driver structure */ struct ccwgroup_driver { - struct module *owner; - char *name; int max_slaves; unsigned long driver_id; diff --git a/arch/s390/include/asm/cmpxchg.h b/arch/s390/include/asm/cmpxchg.h new file mode 100644 index 000000000000..7488e52efa97 --- /dev/null +++ b/arch/s390/include/asm/cmpxchg.h @@ -0,0 +1,225 @@ +/* + * Copyright IBM Corp. 1999, 2011 + * + * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>, + */ + +#ifndef __ASM_CMPXCHG_H +#define __ASM_CMPXCHG_H + +#include <linux/types.h> + +extern void __xchg_called_with_bad_pointer(void); + +static inline unsigned long __xchg(unsigned long x, void *ptr, int size) +{ + unsigned long addr, old; + int shift; + + switch (size) { + case 1: + addr = (unsigned long) ptr; + shift = (3 ^ (addr & 3)) << 3; + addr ^= addr & 3; + asm volatile( + " l %0,%4\n" + "0: lr 0,%0\n" + " nr 0,%3\n" + " or 0,%2\n" + " cs %0,0,%4\n" + " jl 0b\n" + : "=&d" (old), "=Q" (*(int *) addr) + : "d" (x << shift), "d" (~(255 << shift)), + "Q" (*(int *) addr) : "memory", "cc", "0"); + return old >> shift; + case 2: + addr = (unsigned long) ptr; + shift = (2 ^ (addr & 2)) << 3; + addr ^= addr & 2; + asm volatile( + " l %0,%4\n" + "0: lr 0,%0\n" + " nr 0,%3\n" + " or 0,%2\n" + " cs %0,0,%4\n" + " jl 0b\n" + : "=&d" (old), "=Q" (*(int *) addr) + : "d" (x << shift), "d" (~(65535 << shift)), + "Q" (*(int *) addr) : "memory", "cc", "0"); + return old >> shift; + case 4: + asm volatile( + " l %0,%3\n" + "0: cs %0,%2,%3\n" + " jl 0b\n" + : "=&d" (old), "=Q" (*(int *) ptr) + : "d" (x), "Q" (*(int *) ptr) + : "memory", "cc"); + return old; +#ifdef CONFIG_64BIT + case 8: + asm volatile( + " lg %0,%3\n" + "0: csg %0,%2,%3\n" + " jl 0b\n" + : "=&d" (old), "=m" (*(long *) ptr) + : "d" (x), "Q" (*(long *) ptr) + : "memory", "cc"); + return old; +#endif /* CONFIG_64BIT */ + } + __xchg_called_with_bad_pointer(); + return x; +} + +#define xchg(ptr, x) \ +({ \ + __typeof__(*(ptr)) __ret; \ + __ret = (__typeof__(*(ptr))) \ + __xchg((unsigned long)(x), (void *)(ptr), sizeof(*(ptr)));\ + __ret; \ +}) + +/* + * Atomic compare and exchange. Compare OLD with MEM, if identical, + * store NEW in MEM. Return the initial value in MEM. Success is + * indicated by comparing RETURN with OLD. + */ + +#define __HAVE_ARCH_CMPXCHG + +extern void __cmpxchg_called_with_bad_pointer(void); + +static inline unsigned long __cmpxchg(void *ptr, unsigned long old, + unsigned long new, int size) +{ + unsigned long addr, prev, tmp; + int shift; + + switch (size) { + case 1: + addr = (unsigned long) ptr; + shift = (3 ^ (addr & 3)) << 3; + addr ^= addr & 3; + asm volatile( + " l %0,%2\n" + "0: nr %0,%5\n" + " lr %1,%0\n" + " or %0,%3\n" + " or %1,%4\n" + " cs %0,%1,%2\n" + " jnl 1f\n" + " xr %1,%0\n" + " nr %1,%5\n" + " jnz 0b\n" + "1:" + : "=&d" (prev), "=&d" (tmp), "=Q" (*(int *) ptr) + : "d" (old << shift), "d" (new << shift), + "d" (~(255 << shift)), "Q" (*(int *) ptr) + : "memory", "cc"); + return prev >> shift; + case 2: + addr = (unsigned long) ptr; + shift = (2 ^ (addr & 2)) << 3; + addr ^= addr & 2; + asm volatile( + " l %0,%2\n" + "0: nr %0,%5\n" + " lr %1,%0\n" + " or %0,%3\n" + " or %1,%4\n" + " cs %0,%1,%2\n" + " jnl 1f\n" + " xr %1,%0\n" + " nr %1,%5\n" + " jnz 0b\n" + "1:" + : "=&d" (prev), "=&d" (tmp), "=Q" (*(int *) ptr) + : "d" (old << shift), "d" (new << shift), + "d" (~(65535 << shift)), "Q" (*(int *) ptr) + : "memory", "cc"); + return prev >> shift; + case 4: + asm volatile( + " cs %0,%3,%1\n" + : "=&d" (prev), "=Q" (*(int *) ptr) + : "0" (old), "d" (new), "Q" (*(int *) ptr) + : "memory", "cc"); + return prev; +#ifdef CONFIG_64BIT + case 8: + asm volatile( + " csg %0,%3,%1\n" + : "=&d" (prev), "=Q" (*(long *) ptr) + : "0" (old), "d" (new), "Q" (*(long *) ptr) + : "memory", "cc"); + return prev; +#endif /* CONFIG_64BIT */ + } + __cmpxchg_called_with_bad_pointer(); + return old; +} + +#define cmpxchg(ptr, o, n) \ + ((__typeof__(*(ptr)))__cmpxchg((ptr), (unsigned long)(o), \ + (unsigned long)(n), sizeof(*(ptr)))) + +#ifdef CONFIG_64BIT +#define cmpxchg64(ptr, o, n) \ +({ \ + BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ + cmpxchg((ptr), (o), (n)); \ +}) +#else /* CONFIG_64BIT */ +static inline unsigned long long __cmpxchg64(void *ptr, + unsigned long long old, + unsigned long long new) +{ + register_pair rp_old = {.pair = old}; + register_pair rp_new = {.pair = new}; + + asm volatile( + " cds %0,%2,%1" + : "+&d" (rp_old), "=Q" (ptr) + : "d" (rp_new), "Q" (ptr) + : "cc"); + return rp_old.pair; +} +#define cmpxchg64(ptr, o, n) \ + ((__typeof__(*(ptr)))__cmpxchg64((ptr), \ + (unsigned long long)(o), \ + (unsigned long long)(n))) +#endif /* CONFIG_64BIT */ + +#include <asm-generic/cmpxchg-local.h> + +static inline unsigned long __cmpxchg_local(void *ptr, + unsigned long old, + unsigned long new, int size) +{ + switch (size) { + case 1: + case 2: + case 4: +#ifdef CONFIG_64BIT + case 8: +#endif + return __cmpxchg(ptr, old, new, size); + default: + return __cmpxchg_local_generic(ptr, old, new, size); + } + + return old; +} + +/* + * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make + * them available. + */ +#define cmpxchg_local(ptr, o, n) \ + ((__typeof__(*(ptr)))__cmpxchg_local((ptr), (unsigned long)(o), \ + (unsigned long)(n), sizeof(*(ptr)))) + +#define cmpxchg64_local(ptr, o, n) cmpxchg64((ptr), (o), (n)) + +#endif /* __ASM_CMPXCHG_H */ diff --git a/arch/s390/include/asm/system.h b/arch/s390/include/asm/system.h index 8f8d759f6a7b..d382629a0172 100644 --- a/arch/s390/include/asm/system.h +++ b/arch/s390/include/asm/system.h @@ -14,6 +14,7 @@ #include <asm/setup.h> #include <asm/processor.h> #include <asm/lowcore.h> +#include <asm/cmpxchg.h> #ifdef __KERNEL__ @@ -120,161 +121,6 @@ extern int memcpy_real(void *, void *, size_t); #define nop() asm volatile("nop") -#define xchg(ptr,x) \ -({ \ - __typeof__(*(ptr)) __ret; \ - __ret = (__typeof__(*(ptr))) \ - __xchg((unsigned long)(x), (void *)(ptr),sizeof(*(ptr))); \ - __ret; \ -}) - -extern void __xchg_called_with_bad_pointer(void); - -static inline unsigned long __xchg(unsigned long x, void * ptr, int size) -{ - unsigned long addr, old; - int shift; - - switch (size) { - case 1: - addr = (unsigned long) ptr; - shift = (3 ^ (addr & 3)) << 3; - addr ^= addr & 3; - asm volatile( - " l %0,%4\n" - "0: lr 0,%0\n" - " nr 0,%3\n" - " or 0,%2\n" - " cs %0,0,%4\n" - " jl 0b\n" - : "=&d" (old), "=Q" (*(int *) addr) - : "d" (x << shift), "d" (~(255 << shift)), - "Q" (*(int *) addr) : "memory", "cc", "0"); - return old >> shift; - case 2: - addr = (unsigned long) ptr; - shift = (2 ^ (addr & 2)) << 3; - addr ^= addr & 2; - asm volatile( - " l %0,%4\n" - "0: lr 0,%0\n" - " nr 0,%3\n" - " or 0,%2\n" - " cs %0,0,%4\n" - " jl 0b\n" - : "=&d" (old), "=Q" (*(int *) addr) - : "d" (x << shift), "d" (~(65535 << shift)), - "Q" (*(int *) addr) : "memory", "cc", "0"); - return old >> shift; - case 4: - asm volatile( - " l %0,%3\n" - "0: cs %0,%2,%3\n" - " jl 0b\n" - : "=&d" (old), "=Q" (*(int *) ptr) - : "d" (x), "Q" (*(int *) ptr) - : "memory", "cc"); - return old; -#ifdef __s390x__ - case 8: - asm volatile( - " lg %0,%3\n" - "0: csg %0,%2,%3\n" - " jl 0b\n" - : "=&d" (old), "=m" (*(long *) ptr) - : "d" (x), "Q" (*(long *) ptr) - : "memory", "cc"); - return old; -#endif /* __s390x__ */ - } - __xchg_called_with_bad_pointer(); - return x; -} - -/* - * Atomic compare and exchange. Compare OLD with MEM, if identical, - * store NEW in MEM. Return the initial value in MEM. Success is - * indicated by comparing RETURN with OLD. - */ - -#define __HAVE_ARCH_CMPXCHG 1 - -#define cmpxchg(ptr, o, n) \ - ((__typeof__(*(ptr)))__cmpxchg((ptr), (unsigned long)(o), \ - (unsigned long)(n), sizeof(*(ptr)))) - -extern void __cmpxchg_called_with_bad_pointer(void); - -static inline unsigned long -__cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, int size) -{ - unsigned long addr, prev, tmp; - int shift; - - switch (size) { - case 1: - addr = (unsigned long) ptr; - shift = (3 ^ (addr & 3)) << 3; - addr ^= addr & 3; - asm volatile( - " l %0,%2\n" - "0: nr %0,%5\n" - " lr %1,%0\n" - " or %0,%3\n" - " or %1,%4\n" - " cs %0,%1,%2\n" - " jnl 1f\n" - " xr %1,%0\n" - " nr %1,%5\n" - " jnz 0b\n" - "1:" - : "=&d" (prev), "=&d" (tmp), "=Q" (*(int *) ptr) - : "d" (old << shift), "d" (new << shift), - "d" (~(255 << shift)), "Q" (*(int *) ptr) - : "memory", "cc"); - return prev >> shift; - case 2: - addr = (unsigned long) ptr; - shift = (2 ^ (addr & 2)) << 3; - addr ^= addr & 2; - asm volatile( - " l %0,%2\n" - "0: nr %0,%5\n" - " lr %1,%0\n" - " or %0,%3\n" - " or %1,%4\n" - " cs %0,%1,%2\n" - " jnl 1f\n" - " xr %1,%0\n" - " nr %1,%5\n" - " jnz 0b\n" - "1:" - : "=&d" (prev), "=&d" (tmp), "=Q" (*(int *) ptr) - : "d" (old << shift), "d" (new << shift), - "d" (~(65535 << shift)), "Q" (*(int *) ptr) - : "memory", "cc"); - return prev >> shift; - case 4: - asm volatile( - " cs %0,%3,%1\n" - : "=&d" (prev), "=Q" (*(int *) ptr) - : "0" (old), "d" (new), "Q" (*(int *) ptr) - : "memory", "cc"); - return prev; -#ifdef __s390x__ - case 8: - asm volatile( - " csg %0,%3,%1\n" - : "=&d" (prev), "=Q" (*(long *) ptr) - : "0" (old), "d" (new), "Q" (*(long *) ptr) - : "memory", "cc"); - return prev; -#endif /* __s390x__ */ - } - __cmpxchg_called_with_bad_pointer(); - return old; -} - /* * Force strict CPU ordering. * And yes, this is required on UP too when we're talking @@ -353,46 +199,6 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, int size) __ctl_load(__dummy, cr, cr); \ }) -#include <linux/irqflags.h> - -#include <asm-generic/cmpxchg-local.h> - -static inline unsigned long __cmpxchg_local(volatile void *ptr, - unsigned long old, - unsigned long new, int size) -{ - switch (size) { - case 1: - case 2: - case 4: -#ifdef __s390x__ - case 8: -#endif - return __cmpxchg(ptr, old, new, size); - default: - return __cmpxchg_local_generic(ptr, old, new, size); - } - - return old; -} - -/* - * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make - * them available. - */ -#define cmpxchg_local(ptr, o, n) \ - ((__typeof__(*(ptr)))__cmpxchg_local((ptr), (unsigned long)(o), \ - (unsigned long)(n), sizeof(*(ptr)))) -#ifdef __s390x__ -#define cmpxchg64_local(ptr, o, n) \ - ({ \ - BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ - cmpxchg_local((ptr), (o), (n)); \ - }) -#else -#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n)) -#endif - /* * Use to set psw mask except for the first byte which * won't be changed by this function. diff --git a/arch/s390/include/asm/unistd.h b/arch/s390/include/asm/unistd.h index 1049ef27c15e..e82152572377 100644 --- a/arch/s390/include/asm/unistd.h +++ b/arch/s390/include/asm/unistd.h @@ -272,7 +272,11 @@ #define __NR_fanotify_init 332 #define __NR_fanotify_mark 333 #define __NR_prlimit64 334 -#define NR_syscalls 335 +#define __NR_name_to_handle_at 335 +#define __NR_open_by_handle_at 336 +#define __NR_clock_adjtime 337 +#define __NR_syncfs 338 +#define NR_syscalls 339 /* * There are some system calls that are not present on 64 bit, some diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S index 8e60fb23b90d..1dc96ea08fa8 100644 --- a/arch/s390/kernel/compat_wrapper.S +++ b/arch/s390/kernel/compat_wrapper.S @@ -1877,3 +1877,30 @@ sys_prlimit64_wrapper: llgtr %r4,%r4 # const struct rlimit64 __user * llgtr %r5,%r5 # struct rlimit64 __user * jg sys_prlimit64 # branch to system call + + .globl sys_name_to_handle_at_wrapper +sys_name_to_handle_at_wrapper: + lgfr %r2,%r2 # int + llgtr %r3,%r3 # const char __user * + llgtr %r4,%r4 # struct file_handle __user * + llgtr %r5,%r5 # int __user * + lgfr %r6,%r6 # int + jg sys_name_to_handle_at + + .globl compat_sys_open_by_handle_at_wrapper +compat_sys_open_by_handle_at_wrapper: + lgfr %r2,%r2 # int + llgtr %r3,%r3 # struct file_handle __user * + lgfr %r4,%r4 # int + jg compat_sys_open_by_handle_at + + .globl compat_sys_clock_adjtime_wrapper +compat_sys_clock_adjtime_wrapper: + lgfr %r2,%r2 # clockid_t (int) + llgtr %r3,%r3 # struct compat_timex __user * + jg compat_sys_clock_adjtime + + .globl sys_syncfs_wrapper +sys_syncfs_wrapper: + lgfr %r2,%r2 # int + jg sys_syncfs diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index 3b7e7dddc324..068f8465c4ee 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -94,6 +94,7 @@ static noinline __init void create_kernel_nss(void) unsigned int sinitrd_pfn, einitrd_pfn; #endif int response; + int hlen; size_t len; char *savesys_ptr; char defsys_cmd[DEFSYS_CMD_SIZE]; @@ -124,24 +125,27 @@ static noinline __init void create_kernel_nss(void) end_pfn = PFN_UP(__pa(&_end)); min_size = end_pfn << 2; - sprintf(defsys_cmd, "DEFSYS %s 00000-%.5X EW %.5X-%.5X SR %.5X-%.5X", - kernel_nss_name, stext_pfn - 1, stext_pfn, eshared_pfn - 1, - eshared_pfn, end_pfn); + hlen = snprintf(defsys_cmd, DEFSYS_CMD_SIZE, + "DEFSYS %s 00000-%.5X EW %.5X-%.5X SR %.5X-%.5X", + kernel_nss_name, stext_pfn - 1, stext_pfn, + eshared_pfn - 1, eshared_pfn, end_pfn); #ifdef CONFIG_BLK_DEV_INITRD if (INITRD_START && INITRD_SIZE) { sinitrd_pfn = PFN_DOWN(__pa(INITRD_START)); einitrd_pfn = PFN_UP(__pa(INITRD_START + INITRD_SIZE)); min_size = einitrd_pfn << 2; - sprintf(defsys_cmd, "%s EW %.5X-%.5X", defsys_cmd, - sinitrd_pfn, einitrd_pfn); + hlen += snprintf(defsys_cmd + hlen, DEFSYS_CMD_SIZE - hlen, + " EW %.5X-%.5X", sinitrd_pfn, einitrd_pfn); } #endif - sprintf(defsys_cmd, "%s EW MINSIZE=%.7iK PARMREGS=0-13", - defsys_cmd, min_size); - sprintf(savesys_cmd, "SAVESYS %s \n IPL %s", - kernel_nss_name, kernel_nss_name); + snprintf(defsys_cmd + hlen, DEFSYS_CMD_SIZE - hlen, + " EW MINSIZE=%.7iK PARMREGS=0-13", min_size); + defsys_cmd[DEFSYS_CMD_SIZE - 1] = '\0'; + snprintf(savesys_cmd, SAVESYS_CMD_SIZE, "SAVESYS %s \n IPL %s", + kernel_nss_name, kernel_nss_name); + savesys_cmd[SAVESYS_CMD_SIZE - 1] = '\0'; __cpcmd(defsys_cmd, NULL, 0, &response); diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 6f6350826c81..ed183c2c6168 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -102,16 +102,6 @@ EXPORT_SYMBOL(lowcore_ptr); #include <asm/setup.h> -static struct resource code_resource = { - .name = "Kernel code", - .flags = IORESOURCE_BUSY | IORESOURCE_MEM, -}; - -static struct resource data_resource = { - .name = "Kernel data", - .flags = IORESOURCE_BUSY | IORESOURCE_MEM, -}; - /* * condev= and conmode= setup parameter. */ @@ -436,21 +426,43 @@ setup_lowcore(void) lowcore_ptr[0] = lc; } -static void __init -setup_resources(void) +static struct resource code_resource = { + .name = "Kernel code", + .flags = IORESOURCE_BUSY | IORESOURCE_MEM, +}; + +static struct resource data_resource = { + .name = "Kernel data", + .flags = IORESOURCE_BUSY | IORESOURCE_MEM, +}; + +static struct resource bss_resource = { + .name = "Kernel bss", + .flags = IORESOURCE_BUSY | IORESOURCE_MEM, +}; + +static struct resource __initdata *standard_resources[] = { + &code_resource, + &data_resource, + &bss_resource, +}; + +static void __init setup_resources(void) { - struct resource *res, *sub_res; - int i; + struct resource *res, *std_res, *sub_res; + int i, j; code_resource.start = (unsigned long) &_text; code_resource.end = (unsigned long) &_etext - 1; data_resource.start = (unsigned long) &_etext; data_resource.end = (unsigned long) &_edata - 1; + bss_resource.start = (unsigned long) &__bss_start; + bss_resource.end = (unsigned long) &__bss_stop - 1; for (i = 0; i < MEMORY_CHUNKS; i++) { if (!memory_chunk[i].size) continue; - res = alloc_bootmem_low(sizeof(struct resource)); + res = alloc_bootmem_low(sizeof(*res)); res->flags = IORESOURCE_BUSY | IORESOURCE_MEM; switch (memory_chunk[i].type) { case CHUNK_READ_WRITE: @@ -464,40 +476,24 @@ setup_resources(void) res->name = "reserved"; } res->start = memory_chunk[i].addr; - res->end = memory_chunk[i].addr + memory_chunk[i].size - 1; + res->end = res->start + memory_chunk[i].size - 1; request_resource(&iomem_resource, res); - if (code_resource.start >= res->start && - code_resource.start <= res->end && - code_resource.end > res->end) { - sub_res = alloc_bootmem_low(sizeof(struct resource)); - memcpy(sub_res, &code_resource, - sizeof(struct resource)); - sub_res->end = res->end; - code_resource.start = res->end + 1; - request_resource(res, sub_res); - } - - if (code_resource.start >= res->start && - code_resource.start <= res->end && - code_resource.end <= res->end) - request_resource(res, &code_resource); - - if (data_resource.start >= res->start && - data_resource.start <= res->end && - data_resource.end > res->end) { - sub_res = alloc_bootmem_low(sizeof(struct resource)); - memcpy(sub_res, &data_resource, - sizeof(struct resource)); - sub_res->end = res->end; - data_resource.start = res->end + 1; - request_resource(res, sub_res); + for (j = 0; j < ARRAY_SIZE(standard_resources); j++) { + std_res = standard_resources[j]; + if (std_res->start < res->start || + std_res->start > res->end) + continue; + if (std_res->end > res->end) { + sub_res = alloc_bootmem_low(sizeof(*sub_res)); + *sub_res = *std_res; + sub_res->end = res->end; + std_res->start = res->end + 1; + request_resource(res, sub_res); + } else { + request_resource(res, std_res); + } } - - if (data_resource.start >= res->start && - data_resource.start <= res->end && - data_resource.end <= res->end) - request_resource(res, &data_resource); } } diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S index a8fee1b14395..9c65fd4ddce0 100644 --- a/arch/s390/kernel/syscalls.S +++ b/arch/s390/kernel/syscalls.S @@ -343,3 +343,7 @@ SYSCALL(sys_perf_event_open,sys_perf_event_open,sys_perf_event_open_wrapper) SYSCALL(sys_fanotify_init,sys_fanotify_init,sys_fanotify_init_wrapper) SYSCALL(sys_fanotify_mark,sys_fanotify_mark,sys_fanotify_mark_wrapper) SYSCALL(sys_prlimit64,sys_prlimit64,sys_prlimit64_wrapper) +SYSCALL(sys_name_to_handle_at,sys_name_to_handle_at,sys_name_to_handle_at_wrapper) /* 335 */ +SYSCALL(sys_open_by_handle_at,sys_open_by_handle_at,compat_sys_open_by_handle_at_wrapper) +SYSCALL(sys_clock_adjtime,sys_clock_adjtime,compat_sys_clock_adjtime_wrapper) +SYSCALL(sys_syncfs,sys_syncfs,sys_syncfs_wrapper) diff --git a/arch/s390/oprofile/Makefile b/arch/s390/oprofile/Makefile index d698cddcfbdd..524c4b615821 100644 --- a/arch/s390/oprofile/Makefile +++ b/arch/s390/oprofile/Makefile @@ -6,4 +6,5 @@ DRIVER_OBJS = $(addprefix ../../../drivers/oprofile/, \ oprofilefs.o oprofile_stats.o \ timer_int.o ) -oprofile-y := $(DRIVER_OBJS) init.o backtrace.o hwsampler.o +oprofile-y := $(DRIVER_OBJS) init.o backtrace.o +oprofile-$(CONFIG_64BIT) += hwsampler.o diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c index 16c76def4a9d..c63d7e58352b 100644 --- a/arch/s390/oprofile/init.c +++ b/arch/s390/oprofile/init.c @@ -18,6 +18,11 @@ #include <linux/fs.h> #include "../../../drivers/oprofile/oprof.h" + +extern void s390_backtrace(struct pt_regs * const regs, unsigned int depth); + +#ifdef CONFIG_64BIT + #include "hwsampler.h" #define DEFAULT_INTERVAL 4096 @@ -37,8 +42,6 @@ static int hwsampler_running; /* start_mutex must be held to change */ static struct oprofile_operations timer_ops; -extern void s390_backtrace(struct pt_regs * const regs, unsigned int depth); - static int oprofile_hwsampler_start(void) { int retval; @@ -172,14 +175,22 @@ static void oprofile_hwsampler_exit(void) hwsampler_shutdown(); } +#endif /* CONFIG_64BIT */ + int __init oprofile_arch_init(struct oprofile_operations *ops) { ops->backtrace = s390_backtrace; +#ifdef CONFIG_64BIT return oprofile_hwsampler_init(ops); +#else + return -ENODEV; +#endif } void oprofile_arch_exit(void) { +#ifdef CONFIG_64BIT oprofile_hwsampler_exit(); +#endif } diff --git a/arch/sparc/kernel/time_32.c b/arch/sparc/kernel/time_32.c index 8237dd4dfeb4..4e236391b635 100644 --- a/arch/sparc/kernel/time_32.c +++ b/arch/sparc/kernel/time_32.c @@ -145,6 +145,10 @@ static int __devinit clock_probe(struct platform_device *op) if (!model) return -ENODEV; + /* Only the primary RTC has an address property */ + if (!of_find_property(dp, "address", NULL)) + return -ENODEV; + m48t59_rtc.resource = &op->resource[0]; if (!strcmp(model, "mk48t02")) { /* Map the clock register io area read-only */ diff --git a/block/blk-core.c b/block/blk-core.c index 59b5c00c0126..e0a062363937 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -271,7 +271,7 @@ EXPORT_SYMBOL(blk_start_queue); **/ void blk_stop_queue(struct request_queue *q) { - cancel_delayed_work(&q->delay_work); + __cancel_delayed_work(&q->delay_work); queue_flag_set(QUEUE_FLAG_STOPPED, q); } EXPORT_SYMBOL(blk_stop_queue); @@ -2702,7 +2702,10 @@ static void flush_plug_list(struct blk_plug *plug) /* * rq is already accounted, so use raw insert */ - __elv_add_request(q, rq, ELEVATOR_INSERT_SORT_MERGE); + if (rq->cmd_flags & (REQ_FLUSH | REQ_FUA)) + __elv_add_request(q, rq, ELEVATOR_INSERT_FLUSH); + else + __elv_add_request(q, rq, ELEVATOR_INSERT_SORT_MERGE); } if (q) { diff --git a/drivers/memstick/host/Kconfig b/drivers/memstick/host/Kconfig index 4ce5c8dffb68..cc0997a05171 100644 --- a/drivers/memstick/host/Kconfig +++ b/drivers/memstick/host/Kconfig @@ -30,3 +30,15 @@ config MEMSTICK_JMICRON_38X To compile this driver as a module, choose M here: the module will be called jmb38x_ms. + +config MEMSTICK_R592 + tristate "Ricoh R5C592 MemoryStick interface support (EXPERIMENTAL)" + depends on EXPERIMENTAL && PCI + + help + Say Y here if you want to be able to access MemoryStick cards with + the Ricoh R5C592 MemoryStick card reader (which is part of 5 in one + multifunction reader) + + To compile this driver as a module, choose M here: the module will + be called r592. diff --git a/drivers/memstick/host/Makefile b/drivers/memstick/host/Makefile index a1815e9dd019..31ba8d378e46 100644 --- a/drivers/memstick/host/Makefile +++ b/drivers/memstick/host/Makefile @@ -4,3 +4,4 @@ obj-$(CONFIG_MEMSTICK_TIFM_MS) += tifm_ms.o obj-$(CONFIG_MEMSTICK_JMICRON_38X) += jmb38x_ms.o +obj-$(CONFIG_MEMSTICK_R592) += r592.o diff --git a/drivers/memstick/host/r592.c b/drivers/memstick/host/r592.c new file mode 100644 index 000000000000..767406c95291 --- /dev/null +++ b/drivers/memstick/host/r592.c @@ -0,0 +1,908 @@ +/* + * Copyright (C) 2010 - Maxim Levitsky + * driver for Ricoh memstick readers + * + * 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/kernel.h> +#include <linux/module.h> +#include <linux/freezer.h> +#include <linux/jiffies.h> +#include <linux/interrupt.h> +#include <linux/pci.h> +#include <linux/pci_ids.h> +#include <linux/delay.h> +#include <linux/slab.h> +#include <linux/kthread.h> +#include <linux/sched.h> +#include <linux/highmem.h> +#include <asm/byteorder.h> +#include <linux/swab.h> +#include "r592.h" + +static int enable_dma = 1; +static int debug; + +static const char *tpc_names[] = { + "MS_TPC_READ_MG_STATUS", + "MS_TPC_READ_LONG_DATA", + "MS_TPC_READ_SHORT_DATA", + "MS_TPC_READ_REG", + "MS_TPC_READ_QUAD_DATA", + "INVALID", + "MS_TPC_GET_INT", + "MS_TPC_SET_RW_REG_ADRS", + "MS_TPC_EX_SET_CMD", + "MS_TPC_WRITE_QUAD_DATA", + "MS_TPC_WRITE_REG", + "MS_TPC_WRITE_SHORT_DATA", + "MS_TPC_WRITE_LONG_DATA", + "MS_TPC_SET_CMD", +}; + +/** + * memstick_debug_get_tpc_name - debug helper that returns string for + * a TPC number + */ +const char *memstick_debug_get_tpc_name(int tpc) +{ + return tpc_names[tpc-1]; +} +EXPORT_SYMBOL(memstick_debug_get_tpc_name); + + +/* Read a register*/ +static inline u32 r592_read_reg(struct r592_device *dev, int address) +{ + u32 value = readl(dev->mmio + address); + dbg_reg("reg #%02d == 0x%08x", address, value); + return value; +} + +/* Write a register */ +static inline void r592_write_reg(struct r592_device *dev, + int address, u32 value) +{ + dbg_reg("reg #%02d <- 0x%08x", address, value); + writel(value, dev->mmio + address); +} + +/* Reads a big endian DWORD register */ +static inline u32 r592_read_reg_raw_be(struct r592_device *dev, int address) +{ + u32 value = __raw_readl(dev->mmio + address); + dbg_reg("reg #%02d == 0x%08x", address, value); + return be32_to_cpu(value); +} + +/* Writes a big endian DWORD register */ +static inline void r592_write_reg_raw_be(struct r592_device *dev, + int address, u32 value) +{ + dbg_reg("reg #%02d <- 0x%08x", address, value); + __raw_writel(cpu_to_be32(value), dev->mmio + address); +} + +/* Set specific bits in a register (little endian) */ +static inline void r592_set_reg_mask(struct r592_device *dev, + int address, u32 mask) +{ + u32 reg = readl(dev->mmio + address); + dbg_reg("reg #%02d |= 0x%08x (old =0x%08x)", address, mask, reg); + writel(reg | mask , dev->mmio + address); +} + +/* Clear specific bits in a register (little endian) */ +static inline void r592_clear_reg_mask(struct r592_device *dev, + int address, u32 mask) +{ + u32 reg = readl(dev->mmio + address); + dbg_reg("reg #%02d &= 0x%08x (old = 0x%08x, mask = 0x%08x)", + address, ~mask, reg, mask); + writel(reg & ~mask, dev->mmio + address); +} + + +/* Wait for status bits while checking for errors */ +static int r592_wait_status(struct r592_device *dev, u32 mask, u32 wanted_mask) +{ + unsigned long timeout = jiffies + msecs_to_jiffies(1000); + u32 reg = r592_read_reg(dev, R592_STATUS); + + if ((reg & mask) == wanted_mask) + return 0; + + while (time_before(jiffies, timeout)) { + + reg = r592_read_reg(dev, R592_STATUS); + + if ((reg & mask) == wanted_mask) + return 0; + + if (reg & (R592_STATUS_SEND_ERR | R592_STATUS_RECV_ERR)) + return -EIO; + + cpu_relax(); + } + return -ETIME; +} + + +/* Enable/disable device */ +static int r592_enable_device(struct r592_device *dev, bool enable) +{ + dbg("%sabling the device", enable ? "en" : "dis"); + + if (enable) { + + /* Power up the card */ + r592_write_reg(dev, R592_POWER, R592_POWER_0 | R592_POWER_1); + + /* Perform a reset */ + r592_set_reg_mask(dev, R592_IO, R592_IO_RESET); + + msleep(100); + } else + /* Power down the card */ + r592_write_reg(dev, R592_POWER, 0); + + return 0; +} + +/* Set serial/parallel mode */ +static int r592_set_mode(struct r592_device *dev, bool parallel_mode) +{ + if (!parallel_mode) { + dbg("switching to serial mode"); + + /* Set serial mode */ + r592_write_reg(dev, R592_IO_MODE, R592_IO_MODE_SERIAL); + + r592_clear_reg_mask(dev, R592_POWER, R592_POWER_20); + + } else { + dbg("switching to parallel mode"); + + /* This setting should be set _before_ switch TPC */ + r592_set_reg_mask(dev, R592_POWER, R592_POWER_20); + + r592_clear_reg_mask(dev, R592_IO, + R592_IO_SERIAL1 | R592_IO_SERIAL2); + + /* Set the parallel mode now */ + r592_write_reg(dev, R592_IO_MODE, R592_IO_MODE_PARALLEL); + } + + dev->parallel_mode = parallel_mode; + return 0; +} + +/* Perform a controller reset without powering down the card */ +static void r592_host_reset(struct r592_device *dev) +{ + r592_set_reg_mask(dev, R592_IO, R592_IO_RESET); + msleep(100); + r592_set_mode(dev, dev->parallel_mode); +} + +/* Disable all hardware interrupts */ +static void r592_clear_interrupts(struct r592_device *dev) +{ + /* Disable & ACK all interrupts */ + r592_clear_reg_mask(dev, R592_REG_MSC, IRQ_ALL_ACK_MASK); + r592_clear_reg_mask(dev, R592_REG_MSC, IRQ_ALL_EN_MASK); +} + +/* Tests if there is an CRC error */ +static int r592_test_io_error(struct r592_device *dev) +{ + if (!(r592_read_reg(dev, R592_STATUS) & + (R592_STATUS_SEND_ERR | R592_STATUS_RECV_ERR))) + return 0; + + return -EIO; +} + +/* Ensure that FIFO is ready for use */ +static int r592_test_fifo_empty(struct r592_device *dev) +{ + if (r592_read_reg(dev, R592_REG_MSC) & R592_REG_MSC_FIFO_EMPTY) + return 0; + + dbg("FIFO not ready, trying to reset the device"); + r592_host_reset(dev); + + if (r592_read_reg(dev, R592_REG_MSC) & R592_REG_MSC_FIFO_EMPTY) + return 0; + + message("FIFO still not ready, giving up"); + return -EIO; +} + +/* Activates the DMA transfer from to FIFO */ +static void r592_start_dma(struct r592_device *dev, bool is_write) +{ + unsigned long flags; + u32 reg; + spin_lock_irqsave(&dev->irq_lock, flags); + + /* Ack interrupts (just in case) + enable them */ + r592_clear_reg_mask(dev, R592_REG_MSC, DMA_IRQ_ACK_MASK); + r592_set_reg_mask(dev, R592_REG_MSC, DMA_IRQ_EN_MASK); + + /* Set DMA address */ + r592_write_reg(dev, R592_FIFO_DMA, sg_dma_address(&dev->req->sg)); + + /* Enable the DMA */ + reg = r592_read_reg(dev, R592_FIFO_DMA_SETTINGS); + reg |= R592_FIFO_DMA_SETTINGS_EN; + + if (!is_write) + reg |= R592_FIFO_DMA_SETTINGS_DIR; + else + reg &= ~R592_FIFO_DMA_SETTINGS_DIR; + r592_write_reg(dev, R592_FIFO_DMA_SETTINGS, reg); + + spin_unlock_irqrestore(&dev->irq_lock, flags); +} + +/* Cleanups DMA related settings */ +static void r592_stop_dma(struct r592_device *dev, int error) +{ + r592_clear_reg_mask(dev, R592_FIFO_DMA_SETTINGS, + R592_FIFO_DMA_SETTINGS_EN); + + /* This is only a precation */ + r592_write_reg(dev, R592_FIFO_DMA, + dev->dummy_dma_page_physical_address); + + r592_clear_reg_mask(dev, R592_REG_MSC, DMA_IRQ_EN_MASK); + r592_clear_reg_mask(dev, R592_REG_MSC, DMA_IRQ_ACK_MASK); + dev->dma_error = error; +} + +/* Test if hardware supports DMA */ +static void r592_check_dma(struct r592_device *dev) +{ + dev->dma_capable = enable_dma && + (r592_read_reg(dev, R592_FIFO_DMA_SETTINGS) & + R592_FIFO_DMA_SETTINGS_CAP); +} + +/* Transfers fifo contents in/out using DMA */ +static int r592_transfer_fifo_dma(struct r592_device *dev) +{ + int len, sg_count; + bool is_write; + + if (!dev->dma_capable || !dev->req->long_data) + return -EINVAL; + + len = dev->req->sg.length; + is_write = dev->req->data_dir == WRITE; + + if (len != R592_LFIFO_SIZE) + return -EINVAL; + + dbg_verbose("doing dma transfer"); + + dev->dma_error = 0; + INIT_COMPLETION(dev->dma_done); + + /* TODO: hidden assumption about nenth beeing always 1 */ + sg_count = dma_map_sg(&dev->pci_dev->dev, &dev->req->sg, 1, is_write ? + PCI_DMA_TODEVICE : PCI_DMA_FROMDEVICE); + + if (sg_count != 1 || + (sg_dma_len(&dev->req->sg) < dev->req->sg.length)) { + message("problem in dma_map_sg"); + return -EIO; + } + + r592_start_dma(dev, is_write); + + /* Wait for DMA completion */ + if (!wait_for_completion_timeout( + &dev->dma_done, msecs_to_jiffies(1000))) { + message("DMA timeout"); + r592_stop_dma(dev, -ETIMEDOUT); + } + + dma_unmap_sg(&dev->pci_dev->dev, &dev->req->sg, 1, is_write ? + PCI_DMA_TODEVICE : PCI_DMA_FROMDEVICE); + + + return dev->dma_error; +} + +/* + * Writes the FIFO in 4 byte chunks. + * If length isn't 4 byte aligned, rest of the data if put to a fifo + * to be written later + * Use r592_flush_fifo_write to flush that fifo when writing for the + * last time + */ +static void r592_write_fifo_pio(struct r592_device *dev, + unsigned char *buffer, int len) +{ + /* flush spill from former write */ + if (!kfifo_is_empty(&dev->pio_fifo)) { + + u8 tmp[4] = {0}; + int copy_len = kfifo_in(&dev->pio_fifo, buffer, len); + + if (!kfifo_is_full(&dev->pio_fifo)) + return; + len -= copy_len; + buffer += copy_len; + + copy_len = kfifo_out(&dev->pio_fifo, tmp, 4); + WARN_ON(copy_len != 4); + r592_write_reg_raw_be(dev, R592_FIFO_PIO, *(u32 *)tmp); + } + + WARN_ON(!kfifo_is_empty(&dev->pio_fifo)); + + /* write full dwords */ + while (len >= 4) { + r592_write_reg_raw_be(dev, R592_FIFO_PIO, *(u32 *)buffer); + buffer += 4; + len -= 4; + } + + /* put remaining bytes to the spill */ + if (len) + kfifo_in(&dev->pio_fifo, buffer, len); +} + +/* Flushes the temporary FIFO used to make aligned DWORD writes */ +static void r592_flush_fifo_write(struct r592_device *dev) +{ + u8 buffer[4] = { 0 }; + int len; + + if (kfifo_is_empty(&dev->pio_fifo)) + return; + + len = kfifo_out(&dev->pio_fifo, buffer, 4); + r592_write_reg_raw_be(dev, R592_FIFO_PIO, *(u32 *)buffer); +} + +/* + * Read a fifo in 4 bytes chunks. + * If input doesn't fit the buffer, it places bytes of last dword in spill + * buffer, so that they don't get lost on last read, just throw these away. + */ +static void r592_read_fifo_pio(struct r592_device *dev, + unsigned char *buffer, int len) +{ + u8 tmp[4]; + + /* Read from last spill */ + if (!kfifo_is_empty(&dev->pio_fifo)) { + int bytes_copied = + kfifo_out(&dev->pio_fifo, buffer, min(4, len)); + buffer += bytes_copied; + len -= bytes_copied; + + if (!kfifo_is_empty(&dev->pio_fifo)) + return; + } + + /* Reads dwords from FIFO */ + while (len >= 4) { + *(u32 *)buffer = r592_read_reg_raw_be(dev, R592_FIFO_PIO); + buffer += 4; + len -= 4; + } + + if (len) { + *(u32 *)tmp = r592_read_reg_raw_be(dev, R592_FIFO_PIO); + kfifo_in(&dev->pio_fifo, tmp, 4); + len -= kfifo_out(&dev->pio_fifo, buffer, len); + } + + WARN_ON(len); + return; +} + +/* Transfers actual data using PIO. */ +static int r592_transfer_fifo_pio(struct r592_device *dev) +{ + unsigned long flags; + + bool is_write = dev->req->tpc >= MS_TPC_SET_RW_REG_ADRS; + struct sg_mapping_iter miter; + + kfifo_reset(&dev->pio_fifo); + + if (!dev->req->long_data) { + if (is_write) { + r592_write_fifo_pio(dev, dev->req->data, + dev->req->data_len); + r592_flush_fifo_write(dev); + } else + r592_read_fifo_pio(dev, dev->req->data, + dev->req->data_len); + return 0; + } + + local_irq_save(flags); + sg_miter_start(&miter, &dev->req->sg, 1, SG_MITER_ATOMIC | + (is_write ? SG_MITER_FROM_SG : SG_MITER_TO_SG)); + + /* Do the transfer fifo<->memory*/ + while (sg_miter_next(&miter)) + if (is_write) + r592_write_fifo_pio(dev, miter.addr, miter.length); + else + r592_read_fifo_pio(dev, miter.addr, miter.length); + + + /* Write last few non aligned bytes*/ + if (is_write) + r592_flush_fifo_write(dev); + + sg_miter_stop(&miter); + local_irq_restore(flags); + return 0; +} + +/* Executes one TPC (data is read/written from small or large fifo) */ +static void r592_execute_tpc(struct r592_device *dev) +{ + bool is_write = dev->req->tpc >= MS_TPC_SET_RW_REG_ADRS; + int len, error; + u32 status, reg; + + if (!dev->req) { + message("BUG: tpc execution without request!"); + return; + } + + len = dev->req->long_data ? + dev->req->sg.length : dev->req->data_len; + + /* Ensure that FIFO can hold the input data */ + if (len > R592_LFIFO_SIZE) { + message("IO: hardware doesn't support TPCs longer that 512"); + error = -ENOSYS; + goto out; + } + + if (!(r592_read_reg(dev, R592_REG_MSC) & R592_REG_MSC_PRSNT)) { + dbg("IO: refusing to send TPC because card is absent"); + error = -ENODEV; + goto out; + } + + dbg("IO: executing %s LEN=%d", + memstick_debug_get_tpc_name(dev->req->tpc), len); + + /* Set IO direction */ + if (is_write) + r592_set_reg_mask(dev, R592_IO, R592_IO_DIRECTION); + else + r592_clear_reg_mask(dev, R592_IO, R592_IO_DIRECTION); + + + error = r592_test_fifo_empty(dev); + if (error) + goto out; + + /* Transfer write data */ + if (is_write) { + error = r592_transfer_fifo_dma(dev); + if (error == -EINVAL) + error = r592_transfer_fifo_pio(dev); + } + + if (error) + goto out; + + /* Trigger the TPC */ + reg = (len << R592_TPC_EXEC_LEN_SHIFT) | + (dev->req->tpc << R592_TPC_EXEC_TPC_SHIFT) | + R592_TPC_EXEC_BIG_FIFO; + + r592_write_reg(dev, R592_TPC_EXEC, reg); + + /* Wait for TPC completion */ + status = R592_STATUS_RDY; + if (dev->req->need_card_int) + status |= R592_STATUS_CED; + + error = r592_wait_status(dev, status, status); + if (error) { + message("card didn't respond"); + goto out; + } + + /* Test IO errors */ + error = r592_test_io_error(dev); + if (error) { + dbg("IO error"); + goto out; + } + + /* Read data from FIFO */ + if (!is_write) { + error = r592_transfer_fifo_dma(dev); + if (error == -EINVAL) + error = r592_transfer_fifo_pio(dev); + } + + /* read INT reg. This can be shortened with shifts, but that way + its more readable */ + if (dev->parallel_mode && dev->req->need_card_int) { + + dev->req->int_reg = 0; + status = r592_read_reg(dev, R592_STATUS); + + if (status & R592_STATUS_P_CMDNACK) + dev->req->int_reg |= MEMSTICK_INT_CMDNAK; + if (status & R592_STATUS_P_BREQ) + dev->req->int_reg |= MEMSTICK_INT_BREQ; + if (status & R592_STATUS_P_INTERR) + dev->req->int_reg |= MEMSTICK_INT_ERR; + if (status & R592_STATUS_P_CED) + dev->req->int_reg |= MEMSTICK_INT_CED; + } + + if (error) + dbg("FIFO read error"); +out: + dev->req->error = error; + r592_clear_reg_mask(dev, R592_REG_MSC, R592_REG_MSC_LED); + return; +} + +/* Main request processing thread */ +static int r592_process_thread(void *data) +{ + int error; + struct r592_device *dev = (struct r592_device *)data; + unsigned long flags; + + while (!kthread_should_stop()) { + spin_lock_irqsave(&dev->io_thread_lock, flags); + set_current_state(TASK_INTERRUPTIBLE); + error = memstick_next_req(dev->host, &dev->req); + spin_unlock_irqrestore(&dev->io_thread_lock, flags); + + if (error) { + if (error == -ENXIO || error == -EAGAIN) { + dbg_verbose("IO: done IO, sleeping"); + } else { + dbg("IO: unknown error from " + "memstick_next_req %d", error); + } + + if (kthread_should_stop()) + set_current_state(TASK_RUNNING); + + schedule(); + } else { + set_current_state(TASK_RUNNING); + r592_execute_tpc(dev); + } + } + return 0; +} + +/* Reprogram chip to detect change in card state */ +/* eg, if card is detected, arm it to detect removal, and vice versa */ +static void r592_update_card_detect(struct r592_device *dev) +{ + u32 reg = r592_read_reg(dev, R592_REG_MSC); + bool card_detected = reg & R592_REG_MSC_PRSNT; + + dbg("update card detect. card state: %s", card_detected ? + "present" : "absent"); + + reg &= ~((R592_REG_MSC_IRQ_REMOVE | R592_REG_MSC_IRQ_INSERT) << 16); + + if (card_detected) + reg |= (R592_REG_MSC_IRQ_REMOVE << 16); + else + reg |= (R592_REG_MSC_IRQ_INSERT << 16); + + r592_write_reg(dev, R592_REG_MSC, reg); +} + +/* Timer routine that fires 1 second after last card detection event, */ +static void r592_detect_timer(long unsigned int data) +{ + struct r592_device *dev = (struct r592_device *)data; + r592_update_card_detect(dev); + memstick_detect_change(dev->host); +} + +/* Interrupt handler */ +static irqreturn_t r592_irq(int irq, void *data) +{ + struct r592_device *dev = (struct r592_device *)data; + irqreturn_t ret = IRQ_NONE; + u32 reg; + u16 irq_enable, irq_status; + unsigned long flags; + int error; + + spin_lock_irqsave(&dev->irq_lock, flags); + + reg = r592_read_reg(dev, R592_REG_MSC); + irq_enable = reg >> 16; + irq_status = reg & 0xFFFF; + + /* Ack the interrupts */ + reg &= ~irq_status; + r592_write_reg(dev, R592_REG_MSC, reg); + + /* Get the IRQ status minus bits that aren't enabled */ + irq_status &= (irq_enable); + + /* Due to limitation of memstick core, we don't look at bits that + indicate that card was removed/inserted and/or present */ + if (irq_status & (R592_REG_MSC_IRQ_INSERT | R592_REG_MSC_IRQ_REMOVE)) { + + bool card_was_added = irq_status & R592_REG_MSC_IRQ_INSERT; + ret = IRQ_HANDLED; + + message("IRQ: card %s", card_was_added ? "added" : "removed"); + + mod_timer(&dev->detect_timer, + jiffies + msecs_to_jiffies(card_was_added ? 500 : 50)); + } + + if (irq_status & + (R592_REG_MSC_FIFO_DMA_DONE | R592_REG_MSC_FIFO_DMA_ERR)) { + ret = IRQ_HANDLED; + + if (irq_status & R592_REG_MSC_FIFO_DMA_ERR) { + message("IRQ: DMA error"); + error = -EIO; + } else { + dbg_verbose("IRQ: dma done"); + error = 0; + } + + r592_stop_dma(dev, error); + complete(&dev->dma_done); + } + + spin_unlock_irqrestore(&dev->irq_lock, flags); + return ret; +} + +/* External inteface: set settings */ +static int r592_set_param(struct memstick_host *host, + enum memstick_param param, int value) +{ + struct r592_device *dev = memstick_priv(host); + + switch (param) { + case MEMSTICK_POWER: + switch (value) { + case MEMSTICK_POWER_ON: + return r592_enable_device(dev, true); + case MEMSTICK_POWER_OFF: + return r592_enable_device(dev, false); + default: + return -EINVAL; + } + case MEMSTICK_INTERFACE: + switch (value) { + case MEMSTICK_SERIAL: + return r592_set_mode(dev, 0); + case MEMSTICK_PAR4: + return r592_set_mode(dev, 1); + default: + return -EINVAL; + } + default: + return -EINVAL; + } +} + +/* External interface: submit requests */ +static void r592_submit_req(struct memstick_host *host) +{ + struct r592_device *dev = memstick_priv(host); + unsigned long flags; + + if (dev->req) + return; + + spin_lock_irqsave(&dev->io_thread_lock, flags); + if (wake_up_process(dev->io_thread)) + dbg_verbose("IO thread woken to process requests"); + spin_unlock_irqrestore(&dev->io_thread_lock, flags); +} + +static const struct pci_device_id r592_pci_id_tbl[] = { + + { PCI_VDEVICE(RICOH, 0x0592), }, + { }, +}; + +/* Main entry */ +static int r592_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + int error = -ENOMEM; + struct memstick_host *host; + struct r592_device *dev; + + /* Allocate memory */ + host = memstick_alloc_host(sizeof(struct r592_device), &pdev->dev); + if (!host) + goto error1; + + dev = memstick_priv(host); + dev->host = host; + dev->pci_dev = pdev; + pci_set_drvdata(pdev, dev); + + /* pci initialization */ + error = pci_enable_device(pdev); + if (error) + goto error2; + + pci_set_master(pdev); + error = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); + if (error) + goto error3; + + error = pci_request_regions(pdev, DRV_NAME); + if (error) + goto error3; + + dev->mmio = pci_ioremap_bar(pdev, 0); + if (!dev->mmio) + goto error4; + + dev->irq = pdev->irq; + spin_lock_init(&dev->irq_lock); + spin_lock_init(&dev->io_thread_lock); + init_completion(&dev->dma_done); + INIT_KFIFO(dev->pio_fifo); + setup_timer(&dev->detect_timer, + r592_detect_timer, (long unsigned int)dev); + + /* Host initialization */ + host->caps = MEMSTICK_CAP_PAR4; + host->request = r592_submit_req; + host->set_param = r592_set_param; + r592_check_dma(dev); + + dev->io_thread = kthread_run(r592_process_thread, dev, "r592_io"); + if (IS_ERR(dev->io_thread)) { + error = PTR_ERR(dev->io_thread); + goto error5; + } + + /* This is just a precation, so don't fail */ + dev->dummy_dma_page = pci_alloc_consistent(pdev, PAGE_SIZE, + &dev->dummy_dma_page_physical_address); + r592_stop_dma(dev , 0); + + if (request_irq(dev->irq, &r592_irq, IRQF_SHARED, + DRV_NAME, dev)) + goto error6; + + r592_update_card_detect(dev); + if (memstick_add_host(host)) + goto error7; + + message("driver succesfully loaded"); + return 0; +error7: + free_irq(dev->irq, dev); +error6: + if (dev->dummy_dma_page) + pci_free_consistent(pdev, PAGE_SIZE, dev->dummy_dma_page, + dev->dummy_dma_page_physical_address); + + kthread_stop(dev->io_thread); +error5: + iounmap(dev->mmio); +error4: + pci_release_regions(pdev); +error3: + pci_disable_device(pdev); +error2: + memstick_free_host(host); +error1: + return error; +} + +static void r592_remove(struct pci_dev *pdev) +{ + int error = 0; + struct r592_device *dev = pci_get_drvdata(pdev); + + /* Stop the processing thread. + That ensures that we won't take any more requests */ + kthread_stop(dev->io_thread); + + r592_enable_device(dev, false); + + while (!error && dev->req) { + dev->req->error = -ETIME; + error = memstick_next_req(dev->host, &dev->req); + } + memstick_remove_host(dev->host); + + free_irq(dev->irq, dev); + iounmap(dev->mmio); + pci_release_regions(pdev); + pci_disable_device(pdev); + memstick_free_host(dev->host); + + if (dev->dummy_dma_page) + pci_free_consistent(pdev, PAGE_SIZE, dev->dummy_dma_page, + dev->dummy_dma_page_physical_address); +} + +#ifdef CONFIG_PM +static int r592_suspend(struct device *core_dev) +{ + struct pci_dev *pdev = to_pci_dev(core_dev); + struct r592_device *dev = pci_get_drvdata(pdev); + + r592_clear_interrupts(dev); + memstick_suspend_host(dev->host); + del_timer_sync(&dev->detect_timer); + return 0; +} + +static int r592_resume(struct device *core_dev) +{ + struct pci_dev *pdev = to_pci_dev(core_dev); + struct r592_device *dev = pci_get_drvdata(pdev); + + r592_clear_interrupts(dev); + r592_enable_device(dev, false); + memstick_resume_host(dev->host); + r592_update_card_detect(dev); + return 0; +} + +SIMPLE_DEV_PM_OPS(r592_pm_ops, r592_suspend, r592_resume); +#endif + +MODULE_DEVICE_TABLE(pci, r592_pci_id_tbl); + +static struct pci_driver r852_pci_driver = { + .name = DRV_NAME, + .id_table = r592_pci_id_tbl, + .probe = r592_probe, + .remove = r592_remove, +#ifdef CONFIG_PM + .driver.pm = &r592_pm_ops, +#endif +}; + +static __init int r592_module_init(void) +{ + return pci_register_driver(&r852_pci_driver); +} + +static void __exit r592_module_exit(void) +{ + pci_unregister_driver(&r852_pci_driver); +} + +module_init(r592_module_init); +module_exit(r592_module_exit); + +module_param(enable_dma, bool, S_IRUGO); +MODULE_PARM_DESC(enable_dma, "Enable usage of the DMA (default)"); +module_param(debug, int, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(debug, "Debug level (0-3)"); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Maxim Levitsky <maximlevitsky@gmail.com>"); +MODULE_DESCRIPTION("Ricoh R5C592 Memstick/Memstick PRO card reader driver"); diff --git a/drivers/memstick/host/r592.h b/drivers/memstick/host/r592.h new file mode 100644 index 000000000000..eee264e6028f --- /dev/null +++ b/drivers/memstick/host/r592.h @@ -0,0 +1,175 @@ +/* + * Copyright (C) 2010 - Maxim Levitsky + * driver for Ricoh memstick readers + * + * 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 R592_H + +#include <linux/memstick.h> +#include <linux/spinlock.h> +#include <linux/interrupt.h> +#include <linux/workqueue.h> +#include <linux/kfifo.h> +#include <linux/ctype.h> + +/* write to this reg (number,len) triggers TPC execution */ +#define R592_TPC_EXEC 0x00 +#define R592_TPC_EXEC_LEN_SHIFT 16 /* Bits 16..25 are TPC len */ +#define R592_TPC_EXEC_BIG_FIFO (1 << 26) /* If bit 26 is set, large fifo is used (reg 48) */ +#define R592_TPC_EXEC_TPC_SHIFT 28 /* Bits 28..31 are the TPC number */ + + +/* Window for small TPC fifo (big endian)*/ +/* reads and writes always are done in 8 byte chunks */ +/* Not used in driver, because large fifo does better job */ +#define R592_SFIFO 0x08 + + +/* Status register (ms int, small fifo, IO)*/ +#define R592_STATUS 0x10 + /* Parallel INT bits */ +#define R592_STATUS_P_CMDNACK (1 << 16) /* INT reg: NACK (parallel mode) */ +#define R592_STATUS_P_BREQ (1 << 17) /* INT reg: card ready (parallel mode)*/ +#define R592_STATUS_P_INTERR (1 << 18) /* INT reg: int error (parallel mode)*/ +#define R592_STATUS_P_CED (1 << 19) /* INT reg: command done (parallel mode) */ + + /* Fifo status */ +#define R592_STATUS_SFIFO_FULL (1 << 20) /* Small Fifo almost full (last chunk is written) */ +#define R592_STATUS_SFIFO_EMPTY (1 << 21) /* Small Fifo empty */ + + /* Error detection via CRC */ +#define R592_STATUS_SEND_ERR (1 << 24) /* Send failed */ +#define R592_STATUS_RECV_ERR (1 << 25) /* Recieve failed */ + + /* Card state */ +#define R592_STATUS_RDY (1 << 28) /* RDY signal recieved */ +#define R592_STATUS_CED (1 << 29) /* INT: Command done (serial mode)*/ +#define R592_STATUS_SFIFO_INPUT (1 << 30) /* Small fifo recieved data*/ + +#define R592_SFIFO_SIZE 32 /* total size of small fifo is 32 bytes */ +#define R592_SFIFO_PACKET 8 /* packet size of small fifo */ + +/* IO control */ +#define R592_IO 0x18 +#define R592_IO_16 (1 << 16) /* Set by default, can be cleared */ +#define R592_IO_18 (1 << 18) /* Set by default, can be cleared */ +#define R592_IO_SERIAL1 (1 << 20) /* Set by default, can be cleared, (cleared on parallel) */ +#define R592_IO_22 (1 << 22) /* Set by default, can be cleared */ +#define R592_IO_DIRECTION (1 << 24) /* TPC direction (1 write 0 read) */ +#define R592_IO_26 (1 << 26) /* Set by default, can be cleared */ +#define R592_IO_SERIAL2 (1 << 30) /* Set by default, can be cleared (cleared on parallel), serial doesn't work if unset */ +#define R592_IO_RESET (1 << 31) /* Reset, sets defaults*/ + + +/* Turns hardware on/off */ +#define R592_POWER 0x20 /* bits 0-7 writeable */ +#define R592_POWER_0 (1 << 0) /* set on start, cleared on stop - must be set*/ +#define R592_POWER_1 (1 << 1) /* set on start, cleared on stop - must be set*/ +#define R592_POWER_3 (1 << 3) /* must be clear */ +#define R592_POWER_20 (1 << 5) /* set before switch to parallel */ + +/* IO mode*/ +#define R592_IO_MODE 0x24 +#define R592_IO_MODE_SERIAL 1 +#define R592_IO_MODE_PARALLEL 3 + + +/* IRQ,card detection,large fifo (first word irq status, second enable) */ +/* IRQs are ACKed by clearing the bits */ +#define R592_REG_MSC 0x28 +#define R592_REG_MSC_PRSNT (1 << 1) /* card present (only status)*/ +#define R592_REG_MSC_IRQ_INSERT (1 << 8) /* detect insert / card insered */ +#define R592_REG_MSC_IRQ_REMOVE (1 << 9) /* detect removal / card removed */ +#define R592_REG_MSC_FIFO_EMPTY (1 << 10) /* fifo is empty */ +#define R592_REG_MSC_FIFO_DMA_DONE (1 << 11) /* dma enable / dma done */ + +#define R592_REG_MSC_FIFO_USER_ORN (1 << 12) /* set if software reads empty fifo (if R592_REG_MSC_FIFO_EMPTY is set) */ +#define R592_REG_MSC_FIFO_MISMATH (1 << 13) /* set if amount of data in fifo doesn't match amount in TPC */ +#define R592_REG_MSC_FIFO_DMA_ERR (1 << 14) /* IO failure */ +#define R592_REG_MSC_LED (1 << 15) /* clear to turn led off (only status)*/ + +#define DMA_IRQ_ACK_MASK \ + (R592_REG_MSC_FIFO_DMA_DONE | R592_REG_MSC_FIFO_DMA_ERR) + +#define DMA_IRQ_EN_MASK (DMA_IRQ_ACK_MASK << 16) + +#define IRQ_ALL_ACK_MASK 0x00007F00 +#define IRQ_ALL_EN_MASK (IRQ_ALL_ACK_MASK << 16) + +/* DMA address for large FIFO read/writes*/ +#define R592_FIFO_DMA 0x2C + +/* PIO access to large FIFO (512 bytes) (big endian)*/ +#define R592_FIFO_PIO 0x30 +#define R592_LFIFO_SIZE 512 /* large fifo size */ + + +/* large FIFO DMA settings */ +#define R592_FIFO_DMA_SETTINGS 0x34 +#define R592_FIFO_DMA_SETTINGS_EN (1 << 0) /* DMA enabled */ +#define R592_FIFO_DMA_SETTINGS_DIR (1 << 1) /* Dma direction (1 read, 0 write) */ +#define R592_FIFO_DMA_SETTINGS_CAP (1 << 24) /* Dma is aviable */ + +/* Maybe just an delay */ +/* Bits 17..19 are just number */ +/* bit 16 is set, then bit 20 is waited */ +/* time to wait is about 50 spins * 2 ^ (bits 17..19) */ +/* seems to be possible just to ignore */ +/* Probably debug register */ +#define R592_REG38 0x38 +#define R592_REG38_CHANGE (1 << 16) /* Start bit */ +#define R592_REG38_DONE (1 << 20) /* HW set this after the delay */ +#define R592_REG38_SHIFT 17 + +/* Debug register, written (0xABCDEF00) when error happens - not used*/ +#define R592_REG_3C 0x3C + +struct r592_device { + struct pci_dev *pci_dev; + struct memstick_host *host; /* host backpointer */ + struct memstick_request *req; /* current request */ + + /* Registers, IRQ */ + void __iomem *mmio; + int irq; + spinlock_t irq_lock; + spinlock_t io_thread_lock; + struct timer_list detect_timer; + + struct task_struct *io_thread; + bool parallel_mode; + + DECLARE_KFIFO(pio_fifo, u8, sizeof(u32)); + + /* DMA area */ + int dma_capable; + int dma_error; + struct completion dma_done; + void *dummy_dma_page; + dma_addr_t dummy_dma_page_physical_address; + +}; + +#define DRV_NAME "r592" + + +#define message(format, ...) \ + printk(KERN_INFO DRV_NAME ": " format "\n", ## __VA_ARGS__) + +#define __dbg(level, format, ...) \ + do { \ + if (debug >= level) \ + printk(KERN_DEBUG DRV_NAME \ + ": " format "\n", ## __VA_ARGS__); \ + } while (0) + + +#define dbg(format, ...) __dbg(1, format, ## __VA_ARGS__) +#define dbg_verbose(format, ...) __dbg(2, format, ## __VA_ARGS__) +#define dbg_reg(format, ...) __dbg(3, format, ## __VA_ARGS__) + +#endif diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index 379d8592bc6e..459f2cbe80fc 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -3982,8 +3982,10 @@ out_err: } static struct ccw_driver dasd_eckd_driver = { - .name = "dasd-eckd", - .owner = THIS_MODULE, + .driver = { + .name = "dasd-eckd", + .owner = THIS_MODULE, + }, .ids = dasd_eckd_ids, .probe = dasd_eckd_probe, .remove = dasd_generic_remove, diff --git a/drivers/s390/block/dasd_fba.c b/drivers/s390/block/dasd_fba.c index be89b3a893da..4b71b1164868 100644 --- a/drivers/s390/block/dasd_fba.c +++ b/drivers/s390/block/dasd_fba.c @@ -65,8 +65,10 @@ dasd_fba_set_online(struct ccw_device *cdev) } static struct ccw_driver dasd_fba_driver = { - .name = "dasd-fba", - .owner = THIS_MODULE, + .driver = { + .name = "dasd-fba", + .owner = THIS_MODULE, + }, .ids = dasd_fba_ids, .probe = dasd_fba_probe, .remove = dasd_generic_remove, diff --git a/drivers/s390/char/con3215.c b/drivers/s390/char/con3215.c index 3fb4335d491d..694464c65fcd 100644 --- a/drivers/s390/char/con3215.c +++ b/drivers/s390/char/con3215.c @@ -764,8 +764,10 @@ static struct ccw_device_id raw3215_id[] = { }; static struct ccw_driver raw3215_ccw_driver = { - .name = "3215", - .owner = THIS_MODULE, + .driver = { + .name = "3215", + .owner = THIS_MODULE, + }, .ids = raw3215_id, .probe = &raw3215_probe, .remove = &raw3215_remove, diff --git a/drivers/s390/char/raw3270.c b/drivers/s390/char/raw3270.c index 96ba2fd1c8ad..4c023761946f 100644 --- a/drivers/s390/char/raw3270.c +++ b/drivers/s390/char/raw3270.c @@ -1388,8 +1388,10 @@ static struct ccw_device_id raw3270_id[] = { }; static struct ccw_driver raw3270_ccw_driver = { - .name = "3270", - .owner = THIS_MODULE, + .driver = { + .name = "3270", + .owner = THIS_MODULE, + }, .ids = raw3270_id, .probe = &raw3270_probe, .remove = &raw3270_remove, diff --git a/drivers/s390/char/tape_34xx.c b/drivers/s390/char/tape_34xx.c index c26511171ffe..9eff2df70ddb 100644 --- a/drivers/s390/char/tape_34xx.c +++ b/drivers/s390/char/tape_34xx.c @@ -1320,8 +1320,10 @@ tape_34xx_online(struct ccw_device *cdev) } static struct ccw_driver tape_34xx_driver = { - .name = "tape_34xx", - .owner = THIS_MODULE, + .driver = { + .name = "tape_34xx", + .owner = THIS_MODULE, + }, .ids = tape_34xx_ids, .probe = tape_generic_probe, .remove = tape_generic_remove, diff --git a/drivers/s390/char/tape_3590.c b/drivers/s390/char/tape_3590.c index de2e99e0a71b..b98dcbd16711 100644 --- a/drivers/s390/char/tape_3590.c +++ b/drivers/s390/char/tape_3590.c @@ -1761,8 +1761,10 @@ tape_3590_online(struct ccw_device *cdev) } static struct ccw_driver tape_3590_driver = { - .name = "tape_3590", - .owner = THIS_MODULE, + .driver = { + .name = "tape_3590", + .owner = THIS_MODULE, + }, .ids = tape_3590_ids, .probe = tape_generic_probe, .remove = tape_generic_remove, diff --git a/drivers/s390/char/vmur.c b/drivers/s390/char/vmur.c index caef1757341d..f6b00c3df425 100644 --- a/drivers/s390/char/vmur.c +++ b/drivers/s390/char/vmur.c @@ -64,8 +64,10 @@ static int ur_set_offline(struct ccw_device *cdev); static int ur_pm_suspend(struct ccw_device *cdev); static struct ccw_driver ur_driver = { - .name = "vmur", - .owner = THIS_MODULE, + .driver = { + .name = "vmur", + .owner = THIS_MODULE, + }, .ids = ur_ids, .probe = ur_probe, .remove = ur_remove, diff --git a/drivers/s390/cio/ccwgroup.c b/drivers/s390/cio/ccwgroup.c index 2864581d8ecb..5c567414c4bb 100644 --- a/drivers/s390/cio/ccwgroup.c +++ b/drivers/s390/cio/ccwgroup.c @@ -428,7 +428,7 @@ ccwgroup_online_store (struct device *dev, struct device_attribute *attr, const gdev = to_ccwgroupdev(dev); gdrv = to_ccwgroupdrv(dev->driver); - if (!try_module_get(gdrv->owner)) + if (!try_module_get(gdrv->driver.owner)) return -EINVAL; ret = strict_strtoul(buf, 0, &value); @@ -442,7 +442,7 @@ ccwgroup_online_store (struct device *dev, struct device_attribute *attr, const else ret = -EINVAL; out: - module_put(gdrv->owner); + module_put(gdrv->driver.owner); return (ret == 0) ? count : ret; } @@ -616,8 +616,6 @@ int ccwgroup_driver_register(struct ccwgroup_driver *cdriver) { /* register our new driver with the core */ cdriver->driver.bus = &ccwgroup_bus_type; - cdriver->driver.name = cdriver->name; - cdriver->driver.owner = cdriver->owner; return driver_register(&cdriver->driver); } diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c index e50b12163afe..df14c51f6532 100644 --- a/drivers/s390/cio/device.c +++ b/drivers/s390/cio/device.c @@ -127,7 +127,7 @@ static int ccw_uevent(struct device *dev, struct kobj_uevent_env *env) return ret; } -struct bus_type ccw_bus_type; +static struct bus_type ccw_bus_type; static void io_subchannel_irq(struct subchannel *); static int io_subchannel_probe(struct subchannel *); @@ -547,7 +547,7 @@ static ssize_t online_store (struct device *dev, struct device_attribute *attr, if (atomic_cmpxchg(&cdev->private->onoff, 0, 1) != 0) return -EAGAIN; - if (cdev->drv && !try_module_get(cdev->drv->owner)) { + if (cdev->drv && !try_module_get(cdev->drv->driver.owner)) { atomic_set(&cdev->private->onoff, 0); return -EINVAL; } @@ -573,7 +573,7 @@ static ssize_t online_store (struct device *dev, struct device_attribute *attr, } out: if (cdev->drv) - module_put(cdev->drv->owner); + module_put(cdev->drv->driver.owner); atomic_set(&cdev->private->onoff, 0); return (ret < 0) ? ret : count; } @@ -1970,7 +1970,7 @@ static const struct dev_pm_ops ccw_pm_ops = { .restore = ccw_device_pm_restore, }; -struct bus_type ccw_bus_type = { +static struct bus_type ccw_bus_type = { .name = "ccw", .match = ccw_bus_match, .uevent = ccw_uevent, @@ -1993,8 +1993,6 @@ int ccw_driver_register(struct ccw_driver *cdriver) struct device_driver *drv = &cdriver->driver; drv->bus = &ccw_bus_type; - drv->name = cdriver->name; - drv->owner = cdriver->owner; return driver_register(drv); } @@ -2112,5 +2110,4 @@ EXPORT_SYMBOL(ccw_device_set_offline); EXPORT_SYMBOL(ccw_driver_register); EXPORT_SYMBOL(ccw_driver_unregister); EXPORT_SYMBOL(get_ccwdev_by_busid); -EXPORT_SYMBOL(ccw_bus_type); EXPORT_SYMBOL_GPL(ccw_device_get_subchannel_id); diff --git a/drivers/s390/cio/device.h b/drivers/s390/cio/device.h index 379de2d1ec49..7e297c7bb5ff 100644 --- a/drivers/s390/cio/device.h +++ b/drivers/s390/cio/device.h @@ -133,7 +133,6 @@ void ccw_device_set_notoper(struct ccw_device *cdev); /* qdio needs this. */ void ccw_device_set_timeout(struct ccw_device *, int); extern struct subchannel_id ccw_device_get_subchannel_id(struct ccw_device *); -extern struct bus_type ccw_bus_type; /* Channel measurement facility related */ void retry_set_schib(struct ccw_device *cdev); diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c index 5640c89cd9de..479c665e9e7c 100644 --- a/drivers/s390/cio/qdio_main.c +++ b/drivers/s390/cio/qdio_main.c @@ -1508,7 +1508,8 @@ int do_QDIO(struct ccw_device *cdev, unsigned int callflags, if (irq_ptr->state != QDIO_IRQ_STATE_ACTIVE) return -EBUSY; - + if (!count) + return 0; if (callflags & QDIO_FLAG_SYNC_INPUT) return handle_inbound(irq_ptr->input_qs[q_nr], callflags, bufnr, count); diff --git a/drivers/s390/net/claw.c b/drivers/s390/net/claw.c index ce3a5c13ce0b..9feb62febb3d 100644 --- a/drivers/s390/net/claw.c +++ b/drivers/s390/net/claw.c @@ -264,8 +264,10 @@ static struct device *claw_root_dev; /* ccwgroup table */ static struct ccwgroup_driver claw_group_driver = { - .owner = THIS_MODULE, - .name = "claw", + .driver = { + .owner = THIS_MODULE, + .name = "claw", + }, .max_slaves = 2, .driver_id = 0xC3D3C1E6, .probe = claw_probe, @@ -282,8 +284,10 @@ static struct ccw_device_id claw_ids[] = { MODULE_DEVICE_TABLE(ccw, claw_ids); static struct ccw_driver claw_ccw_driver = { - .owner = THIS_MODULE, - .name = "claw", + .driver = { + .owner = THIS_MODULE, + .name = "claw", + }, .ids = claw_ids, .probe = ccwgroup_probe_ccwdev, .remove = ccwgroup_remove_ccwdev, diff --git a/drivers/s390/net/ctcm_main.c b/drivers/s390/net/ctcm_main.c index 4c2845985927..c189296763a4 100644 --- a/drivers/s390/net/ctcm_main.c +++ b/drivers/s390/net/ctcm_main.c @@ -1764,16 +1764,20 @@ static struct ccw_device_id ctcm_ids[] = { MODULE_DEVICE_TABLE(ccw, ctcm_ids); static struct ccw_driver ctcm_ccw_driver = { - .owner = THIS_MODULE, - .name = "ctcm", + .driver = { + .owner = THIS_MODULE, + .name = "ctcm", + }, .ids = ctcm_ids, .probe = ccwgroup_probe_ccwdev, .remove = ccwgroup_remove_ccwdev, }; static struct ccwgroup_driver ctcm_group_driver = { - .owner = THIS_MODULE, - .name = CTC_DRIVER_NAME, + .driver = { + .owner = THIS_MODULE, + .name = CTC_DRIVER_NAME, + }, .max_slaves = 2, .driver_id = 0xC3E3C3D4, /* CTCM */ .probe = ctcm_probe_device, diff --git a/drivers/s390/net/lcs.c b/drivers/s390/net/lcs.c index 30b2a820e670..7fbc4adbb6d5 100644 --- a/drivers/s390/net/lcs.c +++ b/drivers/s390/net/lcs.c @@ -2396,8 +2396,10 @@ static struct ccw_device_id lcs_ids[] = { MODULE_DEVICE_TABLE(ccw, lcs_ids); static struct ccw_driver lcs_ccw_driver = { - .owner = THIS_MODULE, - .name = "lcs", + .driver = { + .owner = THIS_MODULE, + .name = "lcs", + }, .ids = lcs_ids, .probe = ccwgroup_probe_ccwdev, .remove = ccwgroup_remove_ccwdev, @@ -2407,8 +2409,10 @@ static struct ccw_driver lcs_ccw_driver = { * LCS ccwgroup driver registration */ static struct ccwgroup_driver lcs_group_driver = { - .owner = THIS_MODULE, - .name = "lcs", + .driver = { + .owner = THIS_MODULE, + .name = "lcs", + }, .max_slaves = 2, .driver_id = 0xD3C3E2, .probe = lcs_probe_device, diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 25eef304bd47..10a3a3b4dd3e 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -3902,7 +3902,9 @@ static struct ccw_device_id qeth_ids[] = { MODULE_DEVICE_TABLE(ccw, qeth_ids); static struct ccw_driver qeth_ccw_driver = { - .name = "qeth", + .driver = { + .name = "qeth", + }, .ids = qeth_ids, .probe = ccwgroup_probe_ccwdev, .remove = ccwgroup_remove_ccwdev, @@ -4428,8 +4430,10 @@ static int qeth_core_restore(struct ccwgroup_device *gdev) } static struct ccwgroup_driver qeth_core_ccwgroup_driver = { - .owner = THIS_MODULE, - .name = "qeth", + .driver = { + .owner = THIS_MODULE, + .name = "qeth", + }, .driver_id = 0xD8C5E3C8, .probe = qeth_core_probe_device, .remove = qeth_core_remove_device, diff --git a/drivers/s390/scsi/zfcp_ccw.c b/drivers/s390/scsi/zfcp_ccw.c index 4f7852dd30c7..e8b7cee62046 100644 --- a/drivers/s390/scsi/zfcp_ccw.c +++ b/drivers/s390/scsi/zfcp_ccw.c @@ -251,8 +251,10 @@ static void zfcp_ccw_shutdown(struct ccw_device *cdev) } struct ccw_driver zfcp_ccw_driver = { - .owner = THIS_MODULE, - .name = "zfcp", + .driver = { + .owner = THIS_MODULE, + .name = "zfcp", + }, .ids = zfcp_ccw_device_id, .probe = zfcp_ccw_probe, .remove = zfcp_ccw_remove, diff --git a/fs/coda/sysctl.c b/fs/coda/sysctl.c index 06d27a41807f..af56ad56a89a 100644 --- a/fs/coda/sysctl.c +++ b/fs/coda/sysctl.c @@ -61,4 +61,13 @@ void coda_sysctl_clean(void) fs_table_header = NULL; } } + +#else +void coda_sysctl_init(void) +{ +} + +void coda_sysctl_clean(void) +{ +} #endif diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index adf96b822781..97b970e7dd13 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -21,6 +21,8 @@ #include "ext4_jbd2.h" #include "mballoc.h" +#include <trace/events/ext4.h> + /* * balloc.c contains the blocks allocation and deallocation routines */ @@ -342,6 +344,7 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group) * We do it here so the bitmap uptodate bit * get set with buffer lock held. */ + trace_ext4_read_block_bitmap_load(sb, block_group); set_bitmap_uptodate(bh); if (bh_submit_read(bh) < 0) { put_bh(bh); diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index d8b992e658c1..e25e99bf7ee1 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -202,13 +202,6 @@ static inline int ext4_handle_has_enough_credits(handle_t *handle, int needed) return 1; } -static inline void ext4_journal_release_buffer(handle_t *handle, - struct buffer_head *bh) -{ - if (ext4_handle_valid(handle)) - jbd2_journal_release_buffer(handle, bh); -} - static inline handle_t *ext4_journal_start(struct inode *inode, int nblocks) { return ext4_journal_start_sb(inode->i_sb, nblocks); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 7516fb9c0bd5..dd2cb5076ff9 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -44,6 +44,8 @@ #include "ext4_jbd2.h" #include "ext4_extents.h" +#include <trace/events/ext4.h> + static int ext4_ext_truncate_extend_restart(handle_t *handle, struct inode *inode, int needed) @@ -664,6 +666,8 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block, if (unlikely(!bh)) goto err; if (!bh_uptodate_or_lock(bh)) { + trace_ext4_ext_load_extent(inode, block, + path[ppos].p_block); if (bh_submit_read(bh) < 0) { put_bh(bh); goto err; @@ -1034,7 +1038,7 @@ cleanup: for (i = 0; i < depth; i++) { if (!ablocks[i]) continue; - ext4_free_blocks(handle, inode, 0, ablocks[i], 1, + ext4_free_blocks(handle, inode, NULL, ablocks[i], 1, EXT4_FREE_BLOCKS_METADATA); } } @@ -2059,7 +2063,7 @@ static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode, if (err) return err; ext_debug("index is empty, remove it, free block %llu\n", leaf); - ext4_free_blocks(handle, inode, 0, leaf, 1, + ext4_free_blocks(handle, inode, NULL, leaf, 1, EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); return err; } @@ -2156,7 +2160,7 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode, num = le32_to_cpu(ex->ee_block) + ee_len - from; start = ext4_ext_pblock(ex) + ee_len - num; ext_debug("free last %u blocks starting %llu\n", num, start); - ext4_free_blocks(handle, inode, 0, start, num, flags); + ext4_free_blocks(handle, inode, NULL, start, num, flags); } else if (from == le32_to_cpu(ex->ee_block) && to <= le32_to_cpu(ex->ee_block) + ee_len - 1) { printk(KERN_INFO "strange request: removal %u-%u from %u:%u\n", @@ -3108,14 +3112,13 @@ static int check_eofblocks_fl(handle_t *handle, struct inode *inode, { int i, depth; struct ext4_extent_header *eh; - struct ext4_extent *ex, *last_ex; + struct ext4_extent *last_ex; if (!ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS)) return 0; depth = ext_depth(inode); eh = path[depth].p_hdr; - ex = path[depth].p_ext; if (unlikely(!eh->eh_entries)) { EXT4_ERROR_INODE(inode, "eh->eh_entries == 0 and " @@ -3295,9 +3298,8 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, int flags) { struct ext4_ext_path *path = NULL; - struct ext4_extent_header *eh; struct ext4_extent newex, *ex; - ext4_fsblk_t newblock; + ext4_fsblk_t newblock = 0; int err = 0, depth, ret; unsigned int allocated = 0; struct ext4_allocation_request ar; @@ -3305,6 +3307,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, ext_debug("blocks %u/%u requested for inode %lu\n", map->m_lblk, map->m_len, inode->i_ino); + trace_ext4_ext_map_blocks_enter(inode, map->m_lblk, map->m_len, flags); /* check in cache */ if (ext4_ext_in_cache(inode, map->m_lblk, &newex)) { @@ -3352,7 +3355,6 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, err = -EIO; goto out2; } - eh = path[depth].p_hdr; ex = path[depth].p_ext; if (ex) { @@ -3485,7 +3487,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, /* not a good idea to call discard here directly, * but otherwise we'd need to call it every free() */ ext4_discard_preallocations(inode); - ext4_free_blocks(handle, inode, 0, ext4_ext_pblock(&newex), + ext4_free_blocks(handle, inode, NULL, ext4_ext_pblock(&newex), ext4_ext_get_actual_len(&newex), 0); goto out2; } @@ -3525,6 +3527,8 @@ out2: ext4_ext_drop_refs(path); kfree(path); } + trace_ext4_ext_map_blocks_exit(inode, map->m_lblk, + newblock, map->m_len, err ? err : allocated); return err ? err : allocated; } @@ -3658,6 +3662,7 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) return -EOPNOTSUPP; + trace_ext4_fallocate_enter(inode, offset, len, mode); map.m_lblk = offset >> blkbits; /* * We can't just convert len to max_blocks because @@ -3673,6 +3678,7 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) ret = inode_newsize_ok(inode, (len + offset)); if (ret) { mutex_unlock(&inode->i_mutex); + trace_ext4_fallocate_exit(inode, offset, max_blocks, ret); return ret; } retry: @@ -3717,6 +3723,8 @@ retry: goto retry; } mutex_unlock(&inode->i_mutex); + trace_ext4_fallocate_exit(inode, offset, max_blocks, + ret > 0 ? ret2 : ret); return ret > 0 ? ret2 : ret; } @@ -3775,6 +3783,7 @@ int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset, } return ret > 0 ? ret2 : ret; } + /* * Callback function called for each extent to gather FIEMAP information. */ @@ -3782,38 +3791,162 @@ static int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path, struct ext4_ext_cache *newex, struct ext4_extent *ex, void *data) { - struct fiemap_extent_info *fieinfo = data; - unsigned char blksize_bits = inode->i_sb->s_blocksize_bits; __u64 logical; __u64 physical; __u64 length; + loff_t size; __u32 flags = 0; - int error; + int ret = 0; + struct fiemap_extent_info *fieinfo = data; + unsigned char blksize_bits; - logical = (__u64)newex->ec_block << blksize_bits; + blksize_bits = inode->i_sb->s_blocksize_bits; + logical = (__u64)newex->ec_block << blksize_bits; if (newex->ec_start == 0) { - pgoff_t offset; - struct page *page; + /* + * No extent in extent-tree contains block @newex->ec_start, + * then the block may stay in 1)a hole or 2)delayed-extent. + * + * Holes or delayed-extents are processed as follows. + * 1. lookup dirty pages with specified range in pagecache. + * If no page is got, then there is no delayed-extent and + * return with EXT_CONTINUE. + * 2. find the 1st mapped buffer, + * 3. check if the mapped buffer is both in the request range + * and a delayed buffer. If not, there is no delayed-extent, + * then return. + * 4. a delayed-extent is found, the extent will be collected. + */ + ext4_lblk_t end = 0; + pgoff_t last_offset; + pgoff_t offset; + pgoff_t index; + struct page **pages = NULL; struct buffer_head *bh = NULL; + struct buffer_head *head = NULL; + unsigned int nr_pages = PAGE_SIZE / sizeof(struct page *); + + pages = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (pages == NULL) + return -ENOMEM; offset = logical >> PAGE_SHIFT; - page = find_get_page(inode->i_mapping, offset); - if (!page || !page_has_buffers(page)) - return EXT_CONTINUE; +repeat: + last_offset = offset; + head = NULL; + ret = find_get_pages_tag(inode->i_mapping, &offset, + PAGECACHE_TAG_DIRTY, nr_pages, pages); + + if (!(flags & FIEMAP_EXTENT_DELALLOC)) { + /* First time, try to find a mapped buffer. */ + if (ret == 0) { +out: + for (index = 0; index < ret; index++) + page_cache_release(pages[index]); + /* just a hole. */ + kfree(pages); + return EXT_CONTINUE; + } - bh = page_buffers(page); + /* Try to find the 1st mapped buffer. */ + end = ((__u64)pages[0]->index << PAGE_SHIFT) >> + blksize_bits; + if (!page_has_buffers(pages[0])) + goto out; + head = page_buffers(pages[0]); + if (!head) + goto out; - if (!bh) - return EXT_CONTINUE; + bh = head; + do { + if (buffer_mapped(bh)) { + /* get the 1st mapped buffer. */ + if (end > newex->ec_block + + newex->ec_len) + /* The buffer is out of + * the request range. + */ + goto out; + goto found_mapped_buffer; + } + bh = bh->b_this_page; + end++; + } while (bh != head); - if (buffer_delay(bh)) { - flags |= FIEMAP_EXTENT_DELALLOC; - page_cache_release(page); + /* No mapped buffer found. */ + goto out; } else { - page_cache_release(page); - return EXT_CONTINUE; + /*Find contiguous delayed buffers. */ + if (ret > 0 && pages[0]->index == last_offset) + head = page_buffers(pages[0]); + bh = head; } + +found_mapped_buffer: + if (bh != NULL && buffer_delay(bh)) { + /* 1st or contiguous delayed buffer found. */ + if (!(flags & FIEMAP_EXTENT_DELALLOC)) { + /* + * 1st delayed buffer found, record + * the start of extent. + */ + flags |= FIEMAP_EXTENT_DELALLOC; + newex->ec_block = end; + logical = (__u64)end << blksize_bits; + } + /* Find contiguous delayed buffers. */ + do { + if (!buffer_delay(bh)) + goto found_delayed_extent; + bh = bh->b_this_page; + end++; + } while (bh != head); + + for (index = 1; index < ret; index++) { + if (!page_has_buffers(pages[index])) { + bh = NULL; + break; + } + head = page_buffers(pages[index]); + if (!head) { + bh = NULL; + break; + } + if (pages[index]->index != + pages[0]->index + index) { + /* Blocks are not contiguous. */ + bh = NULL; + break; + } + bh = head; + do { + if (!buffer_delay(bh)) + /* Delayed-extent ends. */ + goto found_delayed_extent; + bh = bh->b_this_page; + end++; + } while (bh != head); + } + } else if (!(flags & FIEMAP_EXTENT_DELALLOC)) + /* a hole found. */ + goto out; + +found_delayed_extent: + newex->ec_len = min(end - newex->ec_block, + (ext4_lblk_t)EXT_INIT_MAX_LEN); + if (ret == nr_pages && bh != NULL && + newex->ec_len < EXT_INIT_MAX_LEN && + buffer_delay(bh)) { + /* Have not collected an extent and continue. */ + for (index = 0; index < ret; index++) + page_cache_release(pages[index]); + goto repeat; + } + + for (index = 0; index < ret; index++) + page_cache_release(pages[index]); + kfree(pages); } physical = (__u64)newex->ec_start << blksize_bits; @@ -3822,32 +3955,16 @@ static int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path, if (ex && ext4_ext_is_uninitialized(ex)) flags |= FIEMAP_EXTENT_UNWRITTEN; - /* - * If this extent reaches EXT_MAX_BLOCK, it must be last. - * - * Or if ext4_ext_next_allocated_block is EXT_MAX_BLOCK, - * this also indicates no more allocated blocks. - * - * XXX this might miss a single-block extent at EXT_MAX_BLOCK - */ - if (ext4_ext_next_allocated_block(path) == EXT_MAX_BLOCK || - newex->ec_block + newex->ec_len - 1 == EXT_MAX_BLOCK) { - loff_t size = i_size_read(inode); - loff_t bs = EXT4_BLOCK_SIZE(inode->i_sb); - + size = i_size_read(inode); + if (logical + length >= size) flags |= FIEMAP_EXTENT_LAST; - if ((flags & FIEMAP_EXTENT_DELALLOC) && - logical+length > size) - length = (size - logical + bs - 1) & ~(bs-1); - } - error = fiemap_fill_next_extent(fieinfo, logical, physical, + ret = fiemap_fill_next_extent(fieinfo, logical, physical, length, flags); - if (error < 0) - return error; - if (error == 1) + if (ret < 0) + return ret; + if (ret == 1) return EXT_BREAK; - return EXT_CONTINUE; } diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 7829b287822a..7f74019d6d77 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -164,20 +164,20 @@ int ext4_sync_file(struct file *file, int datasync) J_ASSERT(ext4_journal_current_handle() == NULL); - trace_ext4_sync_file(file, datasync); + trace_ext4_sync_file_enter(file, datasync); if (inode->i_sb->s_flags & MS_RDONLY) return 0; ret = ext4_flush_completed_IO(inode); if (ret < 0) - return ret; + goto out; if (!journal) { ret = generic_file_fsync(file, datasync); if (!ret && !list_empty(&inode->i_dentry)) ext4_sync_parent(inode); - return ret; + goto out; } /* @@ -194,8 +194,10 @@ int ext4_sync_file(struct file *file, int datasync) * (they were dirtied by commit). But that's OK - the blocks are * safe in-journal, which is all fsync() needs to ensure. */ - if (ext4_should_journal_data(inode)) - return ext4_force_commit(inode->i_sb); + if (ext4_should_journal_data(inode)) { + ret = ext4_force_commit(inode->i_sb); + goto out; + } commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid; if (jbd2_log_start_commit(journal, commit_tid)) { @@ -215,5 +217,7 @@ int ext4_sync_file(struct file *file, int datasync) ret = jbd2_log_wait_commit(journal, commit_tid); } else if (journal->j_flags & JBD2_BARRIER) blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL); + out: + trace_ext4_sync_file_exit(inode, ret); return ret; } diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 78b79e1bd7ed..21bb2f61e502 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -152,6 +152,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) * We do it here so the bitmap uptodate bit * get set with buffer lock held. */ + trace_ext4_load_inode_bitmap(sb, block_group); set_bitmap_uptodate(bh); if (bh_submit_read(bh) < 0) { put_bh(bh); @@ -649,7 +650,7 @@ static int find_group_other(struct super_block *sb, struct inode *parent, *group = parent_group + flex_size; if (*group > ngroups) *group = 0; - return find_group_orlov(sb, parent, group, mode, 0); + return find_group_orlov(sb, parent, group, mode, NULL); } /* @@ -1054,6 +1055,11 @@ got: } } + if (ext4_handle_valid(handle)) { + ei->i_sync_tid = handle->h_transaction->t_tid; + ei->i_datasync_tid = handle->h_transaction->t_tid; + } + err = ext4_mark_inode_dirty(handle, inode); if (err) { ext4_std_error(sb, err); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 9297ad46c465..1a86282b9024 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -173,7 +173,7 @@ int ext4_truncate_restart_trans(handle_t *handle, struct inode *inode, BUG_ON(EXT4_JOURNAL(inode) == NULL); jbd_debug(2, "restarting handle %p\n", handle); up_write(&EXT4_I(inode)->i_data_sem); - ret = ext4_journal_restart(handle, blocks_for_truncate(inode)); + ret = ext4_journal_restart(handle, nblocks); down_write(&EXT4_I(inode)->i_data_sem); ext4_discard_preallocations(inode); @@ -720,7 +720,7 @@ allocated: return ret; failed_out: for (i = 0; i < index; i++) - ext4_free_blocks(handle, inode, 0, new_blocks[i], 1, 0); + ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1, 0); return ret; } @@ -823,20 +823,20 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode, return err; failed: /* Allocation failed, free what we already allocated */ - ext4_free_blocks(handle, inode, 0, new_blocks[0], 1, 0); + ext4_free_blocks(handle, inode, NULL, new_blocks[0], 1, 0); for (i = 1; i <= n ; i++) { /* * branch[i].bh is newly allocated, so there is no * need to revoke the block, which is why we don't * need to set EXT4_FREE_BLOCKS_METADATA. */ - ext4_free_blocks(handle, inode, 0, new_blocks[i], 1, + ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1, EXT4_FREE_BLOCKS_FORGET); } for (i = n+1; i < indirect_blks; i++) - ext4_free_blocks(handle, inode, 0, new_blocks[i], 1, 0); + ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1, 0); - ext4_free_blocks(handle, inode, 0, new_blocks[i], num, 0); + ext4_free_blocks(handle, inode, NULL, new_blocks[i], num, 0); return err; } @@ -924,7 +924,7 @@ err_out: ext4_free_blocks(handle, inode, where[i].bh, 0, 1, EXT4_FREE_BLOCKS_FORGET); } - ext4_free_blocks(handle, inode, 0, le32_to_cpu(where[num].key), + ext4_free_blocks(handle, inode, NULL, le32_to_cpu(where[num].key), blks, 0); return err; @@ -973,6 +973,7 @@ static int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, int count = 0; ext4_fsblk_t first_block = 0; + trace_ext4_ind_map_blocks_enter(inode, map->m_lblk, map->m_len, flags); J_ASSERT(!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))); J_ASSERT(handle != NULL || (flags & EXT4_GET_BLOCKS_CREATE) == 0); depth = ext4_block_to_path(inode, map->m_lblk, offsets, @@ -1058,6 +1059,8 @@ cleanup: partial--; } out: + trace_ext4_ind_map_blocks_exit(inode, map->m_lblk, + map->m_pblk, map->m_len, err); return err; } @@ -2060,7 +2063,7 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd, if (nr_pages == 0) break; for (i = 0; i < nr_pages; i++) { - int commit_write = 0, redirty_page = 0; + int commit_write = 0, skip_page = 0; struct page *page = pvec.pages[i]; index = page->index; @@ -2086,14 +2089,12 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd, * If the page does not have buffers (for * whatever reason), try to create them using * __block_write_begin. If this fails, - * redirty the page and move on. + * skip the page and move on. */ if (!page_has_buffers(page)) { if (__block_write_begin(page, 0, len, noalloc_get_block_write)) { - redirty_page: - redirty_page_for_writepage(mpd->wbc, - page); + skip_page: unlock_page(page); continue; } @@ -2104,7 +2105,7 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd, block_start = 0; do { if (!bh) - goto redirty_page; + goto skip_page; if (map && (cur_logical >= map->m_lblk) && (cur_logical <= (map->m_lblk + (map->m_len - 1)))) { @@ -2120,22 +2121,23 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd, clear_buffer_unwritten(bh); } - /* redirty page if block allocation undone */ + /* skip page if block allocation undone */ if (buffer_delay(bh) || buffer_unwritten(bh)) - redirty_page = 1; + skip_page = 1; bh = bh->b_this_page; block_start += bh->b_size; cur_logical++; pblock++; } while (bh != page_bufs); - if (redirty_page) - goto redirty_page; + if (skip_page) + goto skip_page; if (commit_write) /* mark the buffer_heads as dirty & uptodate */ block_commit_write(page, 0, len); + clear_page_dirty_for_io(page); /* * Delalloc doesn't support data journalling, * but eventually maybe we'll lift this @@ -2165,8 +2167,7 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd, return ret; } -static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd, - sector_t logical, long blk_cnt) +static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd) { int nr_pages, i; pgoff_t index, end; @@ -2174,9 +2175,8 @@ static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd, struct inode *inode = mpd->inode; struct address_space *mapping = inode->i_mapping; - index = logical >> (PAGE_CACHE_SHIFT - inode->i_blkbits); - end = (logical + blk_cnt - 1) >> - (PAGE_CACHE_SHIFT - inode->i_blkbits); + index = mpd->first_page; + end = mpd->next_page - 1; while (index <= end) { nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE); if (nr_pages == 0) @@ -2279,9 +2279,8 @@ static void mpage_da_map_and_submit(struct mpage_da_data *mpd) err = blks; /* * If get block returns EAGAIN or ENOSPC and there - * appears to be free blocks we will call - * ext4_writepage() for all of the pages which will - * just redirty the pages. + * appears to be free blocks we will just let + * mpage_da_submit_io() unlock all of the pages. */ if (err == -EAGAIN) goto submit_io; @@ -2312,8 +2311,10 @@ static void mpage_da_map_and_submit(struct mpage_da_data *mpd) ext4_print_free_blocks(mpd->inode); } /* invalidate all the pages */ - ext4_da_block_invalidatepages(mpd, next, - mpd->b_size >> mpd->inode->i_blkbits); + ext4_da_block_invalidatepages(mpd); + + /* Mark this page range as having been completed */ + mpd->io_done = 1; return; } BUG_ON(blks == 0); @@ -2438,102 +2439,6 @@ static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh) } /* - * __mpage_da_writepage - finds extent of pages and blocks - * - * @page: page to consider - * @wbc: not used, we just follow rules - * @data: context - * - * The function finds extents of pages and scan them for all blocks. - */ -static int __mpage_da_writepage(struct page *page, - struct writeback_control *wbc, - struct mpage_da_data *mpd) -{ - struct inode *inode = mpd->inode; - struct buffer_head *bh, *head; - sector_t logical; - - /* - * Can we merge this page to current extent? - */ - if (mpd->next_page != page->index) { - /* - * Nope, we can't. So, we map non-allocated blocks - * and start IO on them - */ - if (mpd->next_page != mpd->first_page) { - mpage_da_map_and_submit(mpd); - /* - * skip rest of the page in the page_vec - */ - redirty_page_for_writepage(wbc, page); - unlock_page(page); - return MPAGE_DA_EXTENT_TAIL; - } - - /* - * Start next extent of pages ... - */ - mpd->first_page = page->index; - - /* - * ... and blocks - */ - mpd->b_size = 0; - mpd->b_state = 0; - mpd->b_blocknr = 0; - } - - mpd->next_page = page->index + 1; - logical = (sector_t) page->index << - (PAGE_CACHE_SHIFT - inode->i_blkbits); - - if (!page_has_buffers(page)) { - mpage_add_bh_to_extent(mpd, logical, PAGE_CACHE_SIZE, - (1 << BH_Dirty) | (1 << BH_Uptodate)); - if (mpd->io_done) - return MPAGE_DA_EXTENT_TAIL; - } else { - /* - * Page with regular buffer heads, just add all dirty ones - */ - head = page_buffers(page); - bh = head; - do { - BUG_ON(buffer_locked(bh)); - /* - * We need to try to allocate - * unmapped blocks in the same page. - * Otherwise we won't make progress - * with the page in ext4_writepage - */ - if (ext4_bh_delay_or_unwritten(NULL, bh)) { - mpage_add_bh_to_extent(mpd, logical, - bh->b_size, - bh->b_state); - if (mpd->io_done) - return MPAGE_DA_EXTENT_TAIL; - } else if (buffer_dirty(bh) && (buffer_mapped(bh))) { - /* - * mapped dirty buffer. We need to update - * the b_state because we look at - * b_state in mpage_da_map_blocks. We don't - * update b_size because if we find an - * unmapped buffer_head later we need to - * use the b_state flag of that buffer_head. - */ - if (mpd->b_size == 0) - mpd->b_state = bh->b_state & BH_FLAGS; - } - logical++; - } while ((bh = bh->b_this_page) != head); - } - - return 0; -} - -/* * This is a special get_blocks_t callback which is used by * ext4_da_write_begin(). It will either return mapped block or * reserve space for a single block. @@ -2597,7 +2502,6 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, * for partial write. */ set_buffer_new(bh); - set_buffer_mapped(bh); } return 0; } @@ -2811,27 +2715,27 @@ static int ext4_da_writepages_trans_blocks(struct inode *inode) /* * write_cache_pages_da - walk the list of dirty pages of the given - * address space and call the callback function (which usually writes - * the pages). - * - * This is a forked version of write_cache_pages(). Differences: - * Range cyclic is ignored. - * no_nrwrite_index_update is always presumed true + * address space and accumulate pages that need writing, and call + * mpage_da_map_and_submit to map a single contiguous memory region + * and then write them. */ static int write_cache_pages_da(struct address_space *mapping, struct writeback_control *wbc, struct mpage_da_data *mpd, pgoff_t *done_index) { - int ret = 0; - int done = 0; - struct pagevec pvec; - unsigned nr_pages; - pgoff_t index; - pgoff_t end; /* Inclusive */ - long nr_to_write = wbc->nr_to_write; - int tag; - + struct buffer_head *bh, *head; + struct inode *inode = mapping->host; + struct pagevec pvec; + unsigned int nr_pages; + sector_t logical; + pgoff_t index, end; + long nr_to_write = wbc->nr_to_write; + int i, tag, ret = 0; + + memset(mpd, 0, sizeof(struct mpage_da_data)); + mpd->wbc = wbc; + mpd->inode = inode; pagevec_init(&pvec, 0); index = wbc->range_start >> PAGE_CACHE_SHIFT; end = wbc->range_end >> PAGE_CACHE_SHIFT; @@ -2842,13 +2746,11 @@ static int write_cache_pages_da(struct address_space *mapping, tag = PAGECACHE_TAG_DIRTY; *done_index = index; - while (!done && (index <= end)) { - int i; - + while (index <= end) { nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag, min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1); if (nr_pages == 0) - break; + return 0; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; @@ -2860,60 +2762,100 @@ static int write_cache_pages_da(struct address_space *mapping, * mapping. However, page->index will not change * because we have a reference on the page. */ - if (page->index > end) { - done = 1; - break; - } + if (page->index > end) + goto out; *done_index = page->index + 1; + /* + * If we can't merge this page, and we have + * accumulated an contiguous region, write it + */ + if ((mpd->next_page != page->index) && + (mpd->next_page != mpd->first_page)) { + mpage_da_map_and_submit(mpd); + goto ret_extent_tail; + } + lock_page(page); /* - * Page truncated or invalidated. We can freely skip it - * then, even for data integrity operations: the page - * has disappeared concurrently, so there could be no - * real expectation of this data interity operation - * even if there is now a new, dirty page at the same - * pagecache address. + * If the page is no longer dirty, or its + * mapping no longer corresponds to inode we + * are writing (which means it has been + * truncated or invalidated), or the page is + * already under writeback and we are not + * doing a data integrity writeback, skip the page */ - if (unlikely(page->mapping != mapping)) { -continue_unlock: + if (!PageDirty(page) || + (PageWriteback(page) && + (wbc->sync_mode == WB_SYNC_NONE)) || + unlikely(page->mapping != mapping)) { unlock_page(page); continue; } - if (!PageDirty(page)) { - /* someone wrote it for us */ - goto continue_unlock; - } - - if (PageWriteback(page)) { - if (wbc->sync_mode != WB_SYNC_NONE) - wait_on_page_writeback(page); - else - goto continue_unlock; - } + if (PageWriteback(page)) + wait_on_page_writeback(page); BUG_ON(PageWriteback(page)); - if (!clear_page_dirty_for_io(page)) - goto continue_unlock; - ret = __mpage_da_writepage(page, wbc, mpd); - if (unlikely(ret)) { - if (ret == AOP_WRITEPAGE_ACTIVATE) { - unlock_page(page); - ret = 0; - } else { - done = 1; - break; - } + if (mpd->next_page != page->index) + mpd->first_page = page->index; + mpd->next_page = page->index + 1; + logical = (sector_t) page->index << + (PAGE_CACHE_SHIFT - inode->i_blkbits); + + if (!page_has_buffers(page)) { + mpage_add_bh_to_extent(mpd, logical, + PAGE_CACHE_SIZE, + (1 << BH_Dirty) | (1 << BH_Uptodate)); + if (mpd->io_done) + goto ret_extent_tail; + } else { + /* + * Page with regular buffer heads, + * just add all dirty ones + */ + head = page_buffers(page); + bh = head; + do { + BUG_ON(buffer_locked(bh)); + /* + * We need to try to allocate + * unmapped blocks in the same page. + * Otherwise we won't make progress + * with the page in ext4_writepage + */ + if (ext4_bh_delay_or_unwritten(NULL, bh)) { + mpage_add_bh_to_extent(mpd, logical, + bh->b_size, + bh->b_state); + if (mpd->io_done) + goto ret_extent_tail; + } else if (buffer_dirty(bh) && (buffer_mapped(bh))) { + /* + * mapped dirty buffer. We need + * to update the b_state + * because we look at b_state + * in mpage_da_map_blocks. We + * don't update b_size because + * if we find an unmapped + * buffer_head later we need to + * use the b_state flag of that + * buffer_head. + */ + if (mpd->b_size == 0) + mpd->b_state = bh->b_state & BH_FLAGS; + } + logical++; + } while ((bh = bh->b_this_page) != head); } if (nr_to_write > 0) { nr_to_write--; if (nr_to_write == 0 && - wbc->sync_mode == WB_SYNC_NONE) { + wbc->sync_mode == WB_SYNC_NONE) /* * We stop writing back only if we are * not doing integrity sync. In case of @@ -2924,14 +2866,18 @@ continue_unlock: * pages, but have not synced all of the * old dirty pages. */ - done = 1; - break; - } + goto out; } } pagevec_release(&pvec); cond_resched(); } + return 0; +ret_extent_tail: + ret = MPAGE_DA_EXTENT_TAIL; +out: + pagevec_release(&pvec); + cond_resched(); return ret; } @@ -2945,7 +2891,6 @@ static int ext4_da_writepages(struct address_space *mapping, struct mpage_da_data mpd; struct inode *inode = mapping->host; int pages_written = 0; - long pages_skipped; unsigned int max_pages; int range_cyclic, cycled = 1, io_done = 0; int needed_blocks, ret = 0; @@ -3028,11 +2973,6 @@ static int ext4_da_writepages(struct address_space *mapping, wbc->nr_to_write = desired_nr_to_write; } - mpd.wbc = wbc; - mpd.inode = mapping->host; - - pages_skipped = wbc->pages_skipped; - retry: if (wbc->sync_mode == WB_SYNC_ALL) tag_pages_for_writeback(mapping, index, end); @@ -3059,22 +2999,10 @@ retry: } /* - * Now call __mpage_da_writepage to find the next + * Now call write_cache_pages_da() to find the next * contiguous region of logical blocks that need - * blocks to be allocated by ext4. We don't actually - * submit the blocks for I/O here, even though - * write_cache_pages thinks it will, and will set the - * pages as clean for write before calling - * __mpage_da_writepage(). + * blocks to be allocated by ext4 and submit them. */ - mpd.b_size = 0; - mpd.b_state = 0; - mpd.b_blocknr = 0; - mpd.first_page = 0; - mpd.next_page = 0; - mpd.io_done = 0; - mpd.pages_written = 0; - mpd.retval = 0; ret = write_cache_pages_da(mapping, wbc, &mpd, &done_index); /* * If we have a contiguous extent of pages and we @@ -3096,7 +3024,6 @@ retry: * and try again */ jbd2_journal_force_commit_nested(sbi->s_journal); - wbc->pages_skipped = pages_skipped; ret = 0; } else if (ret == MPAGE_DA_EXTENT_TAIL) { /* @@ -3104,7 +3031,6 @@ retry: * rest of the pages */ pages_written += mpd.pages_written; - wbc->pages_skipped = pages_skipped; ret = 0; io_done = 1; } else if (wbc->nr_to_write) @@ -3122,11 +3048,6 @@ retry: wbc->range_end = mapping->writeback_index - 1; goto retry; } - if (pages_skipped != wbc->pages_skipped) - ext4_msg(inode->i_sb, KERN_CRIT, - "This should not happen leaving %s " - "with nr_to_write = %ld ret = %d", - __func__, wbc->nr_to_write, ret); /* Update index */ wbc->range_cyclic = range_cyclic; @@ -3460,6 +3381,7 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block) static int ext4_readpage(struct file *file, struct page *page) { + trace_ext4_readpage(page); return mpage_readpage(page, ext4_get_block); } @@ -3494,6 +3416,8 @@ static void ext4_invalidatepage(struct page *page, unsigned long offset) { journal_t *journal = EXT4_JOURNAL(page->mapping->host); + trace_ext4_invalidatepage(page, offset); + /* * free any io_end structure allocated for buffers to be discarded */ @@ -3515,6 +3439,8 @@ static int ext4_releasepage(struct page *page, gfp_t wait) { journal_t *journal = EXT4_JOURNAL(page->mapping->host); + trace_ext4_releasepage(page); + WARN_ON(PageChecked(page)); if (!page_has_buffers(page)) return 0; @@ -3873,11 +3799,16 @@ static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb, { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; + ssize_t ret; + trace_ext4_direct_IO_enter(inode, offset, iov_length(iov, nr_segs), rw); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) - return ext4_ext_direct_IO(rw, iocb, iov, offset, nr_segs); - - return ext4_ind_direct_IO(rw, iocb, iov, offset, nr_segs); + ret = ext4_ext_direct_IO(rw, iocb, iov, offset, nr_segs); + else + ret = ext4_ind_direct_IO(rw, iocb, iov, offset, nr_segs); + trace_ext4_direct_IO_exit(inode, offset, + iov_length(iov, nr_segs), rw, ret); + return ret; } /* @@ -4173,6 +4104,9 @@ no_top: * * We release `count' blocks on disk, but (last - first) may be greater * than `count' because there can be holes in there. + * + * Return 0 on success, 1 on invalid block range + * and < 0 on fatal error. */ static int ext4_clear_blocks(handle_t *handle, struct inode *inode, struct buffer_head *bh, @@ -4199,33 +4133,32 @@ static int ext4_clear_blocks(handle_t *handle, struct inode *inode, if (bh) { BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); err = ext4_handle_dirty_metadata(handle, inode, bh); - if (unlikely(err)) { - ext4_std_error(inode->i_sb, err); - return 1; - } + if (unlikely(err)) + goto out_err; } err = ext4_mark_inode_dirty(handle, inode); - if (unlikely(err)) { - ext4_std_error(inode->i_sb, err); - return 1; - } + if (unlikely(err)) + goto out_err; err = ext4_truncate_restart_trans(handle, inode, blocks_for_truncate(inode)); - if (unlikely(err)) { - ext4_std_error(inode->i_sb, err); - return 1; - } + if (unlikely(err)) + goto out_err; if (bh) { BUFFER_TRACE(bh, "retaking write access"); - ext4_journal_get_write_access(handle, bh); + err = ext4_journal_get_write_access(handle, bh); + if (unlikely(err)) + goto out_err; } } for (p = first; p < last; p++) *p = 0; - ext4_free_blocks(handle, inode, 0, block_to_free, count, flags); + ext4_free_blocks(handle, inode, NULL, block_to_free, count, flags); return 0; +out_err: + ext4_std_error(inode->i_sb, err); + return err; } /** @@ -4259,7 +4192,7 @@ static void ext4_free_data(handle_t *handle, struct inode *inode, ext4_fsblk_t nr; /* Current block # */ __le32 *p; /* Pointer into inode/ind for current block */ - int err; + int err = 0; if (this_bh) { /* For indirect block */ BUFFER_TRACE(this_bh, "get_write_access"); @@ -4281,9 +4214,10 @@ static void ext4_free_data(handle_t *handle, struct inode *inode, } else if (nr == block_to_free + count) { count++; } else { - if (ext4_clear_blocks(handle, inode, this_bh, - block_to_free, count, - block_to_free_p, p)) + err = ext4_clear_blocks(handle, inode, this_bh, + block_to_free, count, + block_to_free_p, p); + if (err) break; block_to_free = nr; block_to_free_p = p; @@ -4292,9 +4226,12 @@ static void ext4_free_data(handle_t *handle, struct inode *inode, } } - if (count > 0) - ext4_clear_blocks(handle, inode, this_bh, block_to_free, - count, block_to_free_p, p); + if (!err && count > 0) + err = ext4_clear_blocks(handle, inode, this_bh, block_to_free, + count, block_to_free_p, p); + if (err < 0) + /* fatal error */ + return; if (this_bh) { BUFFER_TRACE(this_bh, "call ext4_handle_dirty_metadata"); @@ -4412,7 +4349,7 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode, * transaction where the data blocks are * actually freed. */ - ext4_free_blocks(handle, inode, 0, nr, 1, + ext4_free_blocks(handle, inode, NULL, nr, 1, EXT4_FREE_BLOCKS_METADATA| EXT4_FREE_BLOCKS_FORGET); @@ -4496,6 +4433,8 @@ void ext4_truncate(struct inode *inode) ext4_lblk_t last_block; unsigned blocksize = inode->i_sb->s_blocksize; + trace_ext4_truncate_enter(inode); + if (!ext4_can_truncate(inode)) return; @@ -4506,6 +4445,7 @@ void ext4_truncate(struct inode *inode) if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { ext4_ext_truncate(inode); + trace_ext4_truncate_exit(inode); return; } @@ -4635,6 +4575,7 @@ out_stop: ext4_orphan_del(handle, inode); ext4_journal_stop(handle); + trace_ext4_truncate_exit(inode); } /* @@ -4766,6 +4707,7 @@ make_io: * has in-inode xattrs, or we don't have this inode in memory. * Read the block from disk. */ + trace_ext4_load_inode(inode); get_bh(bh); bh->b_end_io = end_buffer_read_sync; submit_bh(READ_META, bh); @@ -4871,7 +4813,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) return inode; ei = EXT4_I(inode); - iloc.bh = 0; + iloc.bh = NULL; ret = __ext4_get_inode_loc(inode, &iloc, 0); if (ret < 0) diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index a84faa110bcd..808c554e773f 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -334,16 +334,22 @@ mext_out: case FITRIM: { struct super_block *sb = inode->i_sb; + struct request_queue *q = bdev_get_queue(sb->s_bdev); struct fstrim_range range; int ret = 0; if (!capable(CAP_SYS_ADMIN)) return -EPERM; + if (!blk_queue_discard(q)) + return -EOPNOTSUPP; + if (copy_from_user(&range, (struct fstrim_range *)arg, sizeof(range))) return -EFAULT; + range.minlen = max((unsigned int)range.minlen, + q->limits.discard_granularity); ret = ext4_trim_fs(sb, &range); if (ret < 0) return ret; @@ -421,6 +427,7 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) return err; } case EXT4_IOC_MOVE_EXT: + case FITRIM: break; default: return -ENOIOCTLCMD; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index d1fe09aea73d..a5837a837a8b 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -432,9 +432,10 @@ static void *mb_find_buddy(struct ext4_buddy *e4b, int order, int *max) } /* at order 0 we see each particular block */ - *max = 1 << (e4b->bd_blkbits + 3); - if (order == 0) + if (order == 0) { + *max = 1 << (e4b->bd_blkbits + 3); return EXT4_MB_BITMAP(e4b); + } bb = EXT4_MB_BUDDY(e4b) + EXT4_SB(e4b->bd_sb)->s_mb_offsets[order]; *max = EXT4_SB(e4b->bd_sb)->s_mb_maxs[order]; @@ -616,7 +617,6 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file, MB_CHECK_ASSERT(e4b->bd_info->bb_fragments == fragments); grp = ext4_get_group_info(sb, e4b->bd_group); - buddy = mb_find_buddy(e4b, 0, &max); list_for_each(cur, &grp->bb_prealloc_list) { ext4_group_t groupnr; struct ext4_prealloc_space *pa; @@ -635,7 +635,12 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file, #define mb_check_buddy(e4b) #endif -/* FIXME!! need more doc */ +/* + * Divide blocks started from @first with length @len into + * smaller chunks with power of 2 blocks. + * Clear the bits in bitmap which the blocks of the chunk(s) covered, + * then increase bb_counters[] for corresponded chunk size. + */ static void ext4_mb_mark_free_simple(struct super_block *sb, void *buddy, ext4_grpblk_t first, ext4_grpblk_t len, struct ext4_group_info *grp) @@ -2381,7 +2386,7 @@ static int ext4_mb_init_backend(struct super_block *sb) /* An 8TB filesystem with 64-bit pointers requires a 4096 byte * kmalloc. A 128kb malloc should suffice for a 256TB filesystem. * So a two level scheme suffices for now. */ - sbi->s_group_info = kmalloc(array_size, GFP_KERNEL); + sbi->s_group_info = kzalloc(array_size, GFP_KERNEL); if (sbi->s_group_info == NULL) { printk(KERN_ERR "EXT4-fs: can't allocate buddy meta group\n"); return -ENOMEM; @@ -3208,7 +3213,7 @@ ext4_mb_check_group_pa(ext4_fsblk_t goal_block, cur_distance = abs(goal_block - cpa->pa_pstart); new_distance = abs(goal_block - pa->pa_pstart); - if (cur_distance < new_distance) + if (cur_distance <= new_distance) return cpa; /* drop the previous reference */ @@ -3907,7 +3912,8 @@ static void ext4_mb_show_ac(struct ext4_allocation_context *ac) struct super_block *sb = ac->ac_sb; ext4_group_t ngroups, i; - if (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED) + if (!mb_enable_debug || + (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)) return; printk(KERN_ERR "EXT4-fs: Can't allocate:" @@ -4753,7 +4759,8 @@ static int ext4_trim_extent(struct super_block *sb, int start, int count, * bitmap. Then issue a TRIM command on this extent and free the extent in * the group buddy bitmap. This is done until whole group is scanned. */ -ext4_grpblk_t ext4_trim_all_free(struct super_block *sb, struct ext4_buddy *e4b, +static ext4_grpblk_t +ext4_trim_all_free(struct super_block *sb, struct ext4_buddy *e4b, ext4_grpblk_t start, ext4_grpblk_t max, ext4_grpblk_t minblocks) { void *bitmap; @@ -4863,10 +4870,15 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) break; } - if (len >= EXT4_BLOCKS_PER_GROUP(sb)) - len -= (EXT4_BLOCKS_PER_GROUP(sb) - first_block); - else + /* + * For all the groups except the last one, last block will + * always be EXT4_BLOCKS_PER_GROUP(sb), so we only need to + * change it for the last group in which case start + + * len < EXT4_BLOCKS_PER_GROUP(sb). + */ + if (first_block + len < EXT4_BLOCKS_PER_GROUP(sb)) last_block = first_block + len; + len -= last_block - first_block; if (e4b.bd_info->bb_free >= minlen) { cnt = ext4_trim_all_free(sb, &e4b, first_block, diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h index b619322c76f0..22bd4d7f289b 100644 --- a/fs/ext4/mballoc.h +++ b/fs/ext4/mballoc.h @@ -169,7 +169,7 @@ struct ext4_allocation_context { /* original request */ struct ext4_free_extent ac_o_ex; - /* goal request (after normalization) */ + /* goal request (normalized ac_o_ex) */ struct ext4_free_extent ac_g_ex; /* the best found extent */ diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index b0a126f23c20..d1bafa57f483 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -263,7 +263,7 @@ static int free_dind_blocks(handle_t *handle, for (i = 0; i < max_entries; i++) { if (tmp_idata[i]) { extend_credit_for_blkdel(handle, inode); - ext4_free_blocks(handle, inode, 0, + ext4_free_blocks(handle, inode, NULL, le32_to_cpu(tmp_idata[i]), 1, EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); @@ -271,7 +271,7 @@ static int free_dind_blocks(handle_t *handle, } put_bh(bh); extend_credit_for_blkdel(handle, inode); - ext4_free_blocks(handle, inode, 0, le32_to_cpu(i_data), 1, + ext4_free_blocks(handle, inode, NULL, le32_to_cpu(i_data), 1, EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); return 0; @@ -302,7 +302,7 @@ static int free_tind_blocks(handle_t *handle, } put_bh(bh); extend_credit_for_blkdel(handle, inode); - ext4_free_blocks(handle, inode, 0, le32_to_cpu(i_data), 1, + ext4_free_blocks(handle, inode, NULL, le32_to_cpu(i_data), 1, EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); return 0; @@ -315,7 +315,7 @@ static int free_ind_block(handle_t *handle, struct inode *inode, __le32 *i_data) /* ei->i_data[EXT4_IND_BLOCK] */ if (i_data[0]) { extend_credit_for_blkdel(handle, inode); - ext4_free_blocks(handle, inode, 0, + ext4_free_blocks(handle, inode, NULL, le32_to_cpu(i_data[0]), 1, EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); @@ -428,7 +428,7 @@ static int free_ext_idx(handle_t *handle, struct inode *inode, } put_bh(bh); extend_credit_for_blkdel(handle, inode); - ext4_free_blocks(handle, inode, 0, block, 1, + ext4_free_blocks(handle, inode, NULL, block, 1, EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); return retval; } diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index e781b7ea5630..67fd0b025858 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -40,6 +40,7 @@ #include "xattr.h" #include "acl.h" +#include <trace/events/ext4.h> /* * define how far ahead to read directories while searching them. */ @@ -2183,6 +2184,7 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) struct ext4_dir_entry_2 *de; handle_t *handle; + trace_ext4_unlink_enter(dir, dentry); /* Initialize quotas before so that eventual writes go * in separate transaction */ dquot_initialize(dir); @@ -2228,6 +2230,7 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) end_unlink: ext4_journal_stop(handle); brelse(bh); + trace_ext4_unlink_exit(dentry, retval); return retval; } @@ -2402,6 +2405,10 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, if (!new_inode && new_dir != old_dir && EXT4_DIR_LINK_MAX(new_dir)) goto end_rename; + BUFFER_TRACE(dir_bh, "get_write_access"); + retval = ext4_journal_get_write_access(handle, dir_bh); + if (retval) + goto end_rename; } if (!new_bh) { retval = ext4_add_entry(handle, new_dentry, old_inode); @@ -2409,7 +2416,9 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, goto end_rename; } else { BUFFER_TRACE(new_bh, "get write access"); - ext4_journal_get_write_access(handle, new_bh); + retval = ext4_journal_get_write_access(handle, new_bh); + if (retval) + goto end_rename; new_de->inode = cpu_to_le32(old_inode->i_ino); if (EXT4_HAS_INCOMPAT_FEATURE(new_dir->i_sb, EXT4_FEATURE_INCOMPAT_FILETYPE)) @@ -2470,8 +2479,6 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, old_dir->i_ctime = old_dir->i_mtime = ext4_current_time(old_dir); ext4_update_dx_flag(old_dir); if (dir_bh) { - BUFFER_TRACE(dir_bh, "get_write_access"); - ext4_journal_get_write_access(handle, dir_bh); PARENT_INO(dir_bh->b_data, new_dir->i_sb->s_blocksize) = cpu_to_le32(new_dir->i_ino); BUFFER_TRACE(dir_bh, "call ext4_handle_dirty_metadata"); diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index e2cd90e4bb7c..b6dbd056fcb1 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -259,6 +259,11 @@ static void ext4_end_bio(struct bio *bio, int error) bi_sector >> (inode->i_blkbits - 9)); } + if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) { + ext4_free_io_end(io_end); + return; + } + /* Add the io_end to per-inode completed io list*/ spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags); list_add_tail(&io_end->list, &EXT4_I(inode)->i_completed_io_list); @@ -279,9 +284,9 @@ void ext4_io_submit(struct ext4_io_submit *io) BUG_ON(bio_flagged(io->io_bio, BIO_EOPNOTSUPP)); bio_put(io->io_bio); } - io->io_bio = 0; + io->io_bio = NULL; io->io_op = 0; - io->io_end = 0; + io->io_end = NULL; } static int io_submit_init(struct ext4_io_submit *io, @@ -380,8 +385,6 @@ int ext4_bio_write_page(struct ext4_io_submit *io, BUG_ON(!PageLocked(page)); BUG_ON(PageWriteback(page)); - set_page_writeback(page); - ClearPageError(page); io_page = kmem_cache_alloc(io_page_cachep, GFP_NOFS); if (!io_page) { @@ -392,6 +395,8 @@ int ext4_bio_write_page(struct ext4_io_submit *io, io_page->p_page = page; atomic_set(&io_page->p_count, 1); get_page(page); + set_page_writeback(page); + ClearPageError(page); for (bh = head = page_buffers(page), block_start = 0; bh != head || !block_start; diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 3ecc6e45d2f9..80bbc9c60c24 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -230,7 +230,7 @@ static int setup_new_group_blocks(struct super_block *sb, } /* Zero out all of the reserved backup group descriptor table blocks */ - ext4_debug("clear inode table blocks %#04llx -> %#04llx\n", + ext4_debug("clear inode table blocks %#04llx -> %#04lx\n", block, sbi->s_itb_per_group); err = sb_issue_zeroout(sb, gdblocks + start + 1, reserved_gdb, GFP_NOFS); @@ -248,7 +248,7 @@ static int setup_new_group_blocks(struct super_block *sb, /* Zero out all of the inode table blocks */ block = input->inode_table; - ext4_debug("clear inode table blocks %#04llx -> %#04llx\n", + ext4_debug("clear inode table blocks %#04llx -> %#04lx\n", block, sbi->s_itb_per_group); err = sb_issue_zeroout(sb, block, sbi->s_itb_per_group, GFP_NOFS); if (err) @@ -499,12 +499,12 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, return err; exit_inode: - /* ext4_journal_release_buffer(handle, iloc.bh); */ + /* ext4_handle_release_buffer(handle, iloc.bh); */ brelse(iloc.bh); exit_dindj: - /* ext4_journal_release_buffer(handle, dind); */ + /* ext4_handle_release_buffer(handle, dind); */ exit_sbh: - /* ext4_journal_release_buffer(handle, EXT4_SB(sb)->s_sbh); */ + /* ext4_handle_release_buffer(handle, EXT4_SB(sb)->s_sbh); */ exit_dind: brelse(dind); exit_bh: @@ -586,7 +586,7 @@ static int reserve_backup_gdb(handle_t *handle, struct inode *inode, /* int j; for (j = 0; j < i; j++) - ext4_journal_release_buffer(handle, primary[j]); + ext4_handle_release_buffer(handle, primary[j]); */ goto exit_bh; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 203f9e4a70be..22546ad7f0ae 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -54,9 +54,9 @@ static struct proc_dir_entry *ext4_proc_root; static struct kset *ext4_kset; -struct ext4_lazy_init *ext4_li_info; -struct mutex ext4_li_mtx; -struct ext4_features *ext4_feat; +static struct ext4_lazy_init *ext4_li_info; +static struct mutex ext4_li_mtx; +static struct ext4_features *ext4_feat; static int ext4_load_journal(struct super_block *, struct ext4_super_block *, unsigned long journal_devnum); @@ -75,6 +75,7 @@ static void ext4_write_super(struct super_block *sb); static int ext4_freeze(struct super_block *sb); static struct dentry *ext4_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data); +static int ext4_feature_set_ok(struct super_block *sb, int readonly); static void ext4_destroy_lazyinit_thread(void); static void ext4_unregister_li_request(struct super_block *sb); static void ext4_clear_request_list(void); @@ -594,7 +595,7 @@ __acquires(bitlock) vaf.fmt = fmt; vaf.va = &args; - printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: group %u", + printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: group %u, ", sb->s_id, function, line, grp); if (ino) printk(KERN_CONT "inode %lu: ", ino); @@ -997,13 +998,10 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs) if (test_opt(sb, OLDALLOC)) seq_puts(seq, ",oldalloc"); #ifdef CONFIG_EXT4_FS_XATTR - if (test_opt(sb, XATTR_USER) && - !(def_mount_opts & EXT4_DEFM_XATTR_USER)) + if (test_opt(sb, XATTR_USER)) seq_puts(seq, ",user_xattr"); - if (!test_opt(sb, XATTR_USER) && - (def_mount_opts & EXT4_DEFM_XATTR_USER)) { + if (!test_opt(sb, XATTR_USER)) seq_puts(seq, ",nouser_xattr"); - } #endif #ifdef CONFIG_EXT4_FS_POSIX_ACL if (test_opt(sb, POSIX_ACL) && !(def_mount_opts & EXT4_DEFM_ACL)) @@ -1041,8 +1039,8 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs) !(def_mount_opts & EXT4_DEFM_NODELALLOC)) seq_puts(seq, ",nodelalloc"); - if (test_opt(sb, MBLK_IO_SUBMIT)) - seq_puts(seq, ",mblk_io_submit"); + if (!test_opt(sb, MBLK_IO_SUBMIT)) + seq_puts(seq, ",nomblk_io_submit"); if (sbi->s_stripe) seq_printf(seq, ",stripe=%lu", sbi->s_stripe); /* @@ -1451,7 +1449,7 @@ static int parse_options(char *options, struct super_block *sb, * Initialize args struct so we know whether arg was * found; some options take optional arguments. */ - args[0].to = args[0].from = 0; + args[0].to = args[0].from = NULL; token = match_token(p, tokens, args); switch (token) { case Opt_bsd_df: @@ -1771,7 +1769,7 @@ set_qf_format: return 0; if (option < 0 || option > (1 << 30)) return 0; - if (!is_power_of_2(option)) { + if (option && !is_power_of_2(option)) { ext4_msg(sb, KERN_ERR, "EXT4-fs: inode_readahead_blks" " must be a power of 2"); @@ -2120,6 +2118,13 @@ static void ext4_orphan_cleanup(struct super_block *sb, return; } + /* Check if feature set would not allow a r/w mount */ + if (!ext4_feature_set_ok(sb, 0)) { + ext4_msg(sb, KERN_INFO, "Skipping orphan cleanup due to " + "unknown ROCOMPAT features"); + return; + } + if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) { if (es->s_last_orphan) jbd_debug(1, "Errors on filesystem, " @@ -2412,7 +2417,7 @@ static ssize_t inode_readahead_blks_store(struct ext4_attr *a, if (parse_strtoul(buf, 0x40000000, &t)) return -EINVAL; - if (!is_power_of_2(t)) + if (t && !is_power_of_2(t)) return -EINVAL; sbi->s_inode_readahead_blks = t; @@ -3095,14 +3100,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } if (def_mount_opts & EXT4_DEFM_UID16) set_opt(sb, NO_UID32); + /* xattr user namespace & acls are now defaulted on */ #ifdef CONFIG_EXT4_FS_XATTR - if (def_mount_opts & EXT4_DEFM_XATTR_USER) - set_opt(sb, XATTR_USER); + set_opt(sb, XATTR_USER); #endif #ifdef CONFIG_EXT4_FS_POSIX_ACL - if (def_mount_opts & EXT4_DEFM_ACL) - set_opt(sb, POSIX_ACL); + set_opt(sb, POSIX_ACL); #endif + set_opt(sb, MBLK_IO_SUBMIT); if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_DATA) set_opt(sb, JOURNAL_DATA); else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_ORDERED) @@ -3516,7 +3521,7 @@ no_journal: * concurrency isn't really necessary. Limit it to 1. */ EXT4_SB(sb)->dio_unwritten_wq = - alloc_workqueue("ext4-dio-unwritten", WQ_MEM_RECLAIM, 1); + alloc_workqueue("ext4-dio-unwritten", WQ_MEM_RECLAIM | WQ_UNBOUND, 1); if (!EXT4_SB(sb)->dio_unwritten_wq) { printk(KERN_ERR "EXT4-fs: failed to create DIO workqueue\n"); goto failed_mount_wq; @@ -3531,17 +3536,16 @@ no_journal: if (IS_ERR(root)) { ext4_msg(sb, KERN_ERR, "get root inode failed"); ret = PTR_ERR(root); + root = NULL; goto failed_mount4; } if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) { - iput(root); ext4_msg(sb, KERN_ERR, "corrupt root inode, run e2fsck"); goto failed_mount4; } sb->s_root = d_alloc_root(root); if (!sb->s_root) { ext4_msg(sb, KERN_ERR, "get root dentry failed"); - iput(root); ret = -ENOMEM; goto failed_mount4; } @@ -3657,6 +3661,8 @@ cantfind_ext4: goto failed_mount; failed_mount4: + iput(root); + sb->s_root = NULL; ext4_msg(sb, KERN_ERR, "mount failed"); destroy_workqueue(EXT4_SB(sb)->dio_unwritten_wq); failed_mount_wq: diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index fc32176eee39..b545ca1c459c 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -735,7 +735,7 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, int offset = (char *)s->here - bs->bh->b_data; unlock_buffer(bs->bh); - jbd2_journal_release_buffer(handle, bs->bh); + ext4_handle_release_buffer(handle, bs->bh); if (ce) { mb_cache_entry_release(ce); ce = NULL; @@ -833,7 +833,7 @@ inserted: new_bh = sb_getblk(sb, block); if (!new_bh) { getblk_failed: - ext4_free_blocks(handle, inode, 0, block, 1, + ext4_free_blocks(handle, inode, NULL, block, 1, EXT4_FREE_BLOCKS_METADATA); error = -EIO; goto cleanup; diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index abdf38d5971d..7237672216c8 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -44,6 +44,7 @@ /* #define NFS_DEBUG_VERBOSE 1 */ static int nfs_opendir(struct inode *, struct file *); +static int nfs_closedir(struct inode *, struct file *); static int nfs_readdir(struct file *, void *, filldir_t); static struct dentry *nfs_lookup(struct inode *, struct dentry *, struct nameidata *); static int nfs_create(struct inode *, struct dentry *, int, struct nameidata *); @@ -64,7 +65,7 @@ const struct file_operations nfs_dir_operations = { .read = generic_read_dir, .readdir = nfs_readdir, .open = nfs_opendir, - .release = nfs_release, + .release = nfs_closedir, .fsync = nfs_fsync_dir, }; @@ -133,13 +134,35 @@ const struct inode_operations nfs4_dir_inode_operations = { #endif /* CONFIG_NFS_V4 */ +static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct rpc_cred *cred) +{ + struct nfs_open_dir_context *ctx; + ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); + if (ctx != NULL) { + ctx->duped = 0; + ctx->dir_cookie = 0; + ctx->dup_cookie = 0; + ctx->cred = get_rpccred(cred); + } else + ctx = ERR_PTR(-ENOMEM); + return ctx; +} + +static void put_nfs_open_dir_context(struct nfs_open_dir_context *ctx) +{ + put_rpccred(ctx->cred); + kfree(ctx); +} + /* * Open file */ static int nfs_opendir(struct inode *inode, struct file *filp) { - int res; + int res = 0; + struct nfs_open_dir_context *ctx; + struct rpc_cred *cred; dfprintk(FILE, "NFS: open dir(%s/%s)\n", filp->f_path.dentry->d_parent->d_name.name, @@ -147,8 +170,15 @@ nfs_opendir(struct inode *inode, struct file *filp) nfs_inc_stats(inode, NFSIOS_VFSOPEN); - /* Call generic open code in order to cache credentials */ - res = nfs_open(inode, filp); + cred = rpc_lookup_cred(); + if (IS_ERR(cred)) + return PTR_ERR(cred); + ctx = alloc_nfs_open_dir_context(cred); + if (IS_ERR(ctx)) { + res = PTR_ERR(ctx); + goto out; + } + filp->private_data = ctx; if (filp->f_path.dentry == filp->f_path.mnt->mnt_root) { /* This is a mountpoint, so d_revalidate will never * have been called, so we need to refresh the @@ -156,9 +186,18 @@ nfs_opendir(struct inode *inode, struct file *filp) */ __nfs_revalidate_inode(NFS_SERVER(inode), inode); } +out: + put_rpccred(cred); return res; } +static int +nfs_closedir(struct inode *inode, struct file *filp) +{ + put_nfs_open_dir_context(filp->private_data); + return 0; +} + struct nfs_cache_array_entry { u64 cookie; u64 ino; @@ -284,19 +323,20 @@ int nfs_readdir_search_for_pos(struct nfs_cache_array *array, nfs_readdir_descri { loff_t diff = desc->file->f_pos - desc->current_index; unsigned int index; + struct nfs_open_dir_context *ctx = desc->file->private_data; if (diff < 0) goto out_eof; if (diff >= array->size) { if (array->eof_index >= 0) goto out_eof; - desc->current_index += array->size; return -EAGAIN; } index = (unsigned int)diff; *desc->dir_cookie = array->array[index].cookie; desc->cache_entry_index = index; + ctx->duped = 0; return 0; out_eof: desc->eof = 1; @@ -307,10 +347,18 @@ static int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_descriptor_t *desc) { int i; + loff_t new_pos; int status = -EAGAIN; + struct nfs_open_dir_context *ctx = desc->file->private_data; for (i = 0; i < array->size; i++) { if (array->array[i].cookie == *desc->dir_cookie) { + new_pos = desc->current_index + i; + if (new_pos < desc->file->f_pos) { + ctx->dup_cookie = *desc->dir_cookie; + ctx->duped = 1; + } + desc->file->f_pos = new_pos; desc->cache_entry_index = i; return 0; } @@ -342,6 +390,7 @@ int nfs_readdir_search_array(nfs_readdir_descriptor_t *desc) if (status == -EAGAIN) { desc->last_cookie = array->last_cookie; + desc->current_index += array->size; desc->page_index++; } nfs_readdir_release_array(desc->page); @@ -354,7 +403,8 @@ static int nfs_readdir_xdr_filler(struct page **pages, nfs_readdir_descriptor_t *desc, struct nfs_entry *entry, struct file *file, struct inode *inode) { - struct rpc_cred *cred = nfs_file_cred(file); + struct nfs_open_dir_context *ctx = file->private_data; + struct rpc_cred *cred = ctx->cred; unsigned long timestamp, gencount; int error; @@ -693,6 +743,20 @@ int nfs_do_filldir(nfs_readdir_descriptor_t *desc, void *dirent, int i = 0; int res = 0; struct nfs_cache_array *array = NULL; + struct nfs_open_dir_context *ctx = file->private_data; + + if (ctx->duped != 0 && ctx->dup_cookie == *desc->dir_cookie) { + if (printk_ratelimit()) { + pr_notice("NFS: directory %s/%s contains a readdir loop. " + "Please contact your server vendor. " + "Offending cookie: %llu\n", + file->f_dentry->d_parent->d_name.name, + file->f_dentry->d_name.name, + *desc->dir_cookie); + } + res = -ELOOP; + goto out; + } array = nfs_readdir_get_array(desc->page); if (IS_ERR(array)) { @@ -785,6 +849,7 @@ static int nfs_readdir(struct file *filp, void *dirent, filldir_t filldir) struct inode *inode = dentry->d_inode; nfs_readdir_descriptor_t my_desc, *desc = &my_desc; + struct nfs_open_dir_context *dir_ctx = filp->private_data; int res; dfprintk(FILE, "NFS: readdir(%s/%s) starting at cookie %llu\n", @@ -801,7 +866,7 @@ static int nfs_readdir(struct file *filp, void *dirent, filldir_t filldir) memset(desc, 0, sizeof(*desc)); desc->file = filp; - desc->dir_cookie = &nfs_file_open_context(filp)->dir_cookie; + desc->dir_cookie = &dir_ctx->dir_cookie; desc->decode = NFS_PROTO(inode)->decode_dirent; desc->plus = NFS_USE_READDIRPLUS(inode); @@ -853,6 +918,7 @@ static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int origin) { struct dentry *dentry = filp->f_path.dentry; struct inode *inode = dentry->d_inode; + struct nfs_open_dir_context *dir_ctx = filp->private_data; dfprintk(FILE, "NFS: llseek dir(%s/%s, %lld, %d)\n", dentry->d_parent->d_name.name, @@ -872,7 +938,8 @@ static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int origin) } if (offset != filp->f_pos) { filp->f_pos = offset; - nfs_file_open_context(filp)->dir_cookie = 0; + dir_ctx->dir_cookie = 0; + dir_ctx->duped = 0; } out: mutex_unlock(&inode->i_mutex); @@ -1068,7 +1135,7 @@ static int nfs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd) if (fhandle == NULL || fattr == NULL) goto out_error; - error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr); + error = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, &dentry->d_name, fhandle, fattr); if (error) goto out_bad; if (nfs_compare_fh(NFS_FH(inode), fhandle)) @@ -1224,7 +1291,7 @@ static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, stru parent = dentry->d_parent; /* Protect against concurrent sillydeletes */ nfs_block_sillyrename(parent); - error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr); + error = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, &dentry->d_name, fhandle, fattr); if (error == -ENOENT) goto no_entry; if (error < 0) { @@ -1562,7 +1629,7 @@ int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fhandle, if (dentry->d_inode) goto out; if (fhandle->size == 0) { - error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr); + error = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, &dentry->d_name, fhandle, fattr); if (error) goto out_error; } diff --git a/fs/nfs/file.c b/fs/nfs/file.c index d85a534b15cd..3ac5bd695e5e 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -326,6 +326,9 @@ nfs_file_fsync(struct file *file, int datasync) ret = xchg(&ctx->error, 0); if (!ret && status < 0) ret = status; + if (!ret && !datasync) + /* application has asked for meta-data sync */ + ret = pnfs_layoutcommit_inode(inode, true); return ret; } diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c index 1084792bc0fe..dcb61548887f 100644 --- a/fs/nfs/getroot.c +++ b/fs/nfs/getroot.c @@ -222,6 +222,10 @@ struct dentry *nfs4_get_root(struct super_block *sb, struct nfs_fh *mntfh, goto out; } + if (fattr->valid & NFS_ATTR_FATTR_FSID && + !nfs_fsid_equal(&server->fsid, &fattr->fsid)) + memcpy(&server->fsid, &fattr->fsid, sizeof(server->fsid)); + inode = nfs_fhget(sb, mntfh, fattr); if (IS_ERR(inode)) { dprintk("nfs_get_root: get root inode failed\n"); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 01768e5e2c9b..57bb31ad7a5e 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -254,7 +254,9 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) struct inode *inode = ERR_PTR(-ENOENT); unsigned long hash; - if ((fattr->valid & NFS_ATTR_FATTR_FILEID) == 0) + nfs_attr_check_mountpoint(sb, fattr); + + if ((fattr->valid & NFS_ATTR_FATTR_FILEID) == 0 && (fattr->valid & NFS_ATTR_FATTR_MOUNTPOINT) == 0) goto out_no_inode; if ((fattr->valid & NFS_ATTR_FATTR_TYPE) == 0) goto out_no_inode; @@ -298,8 +300,8 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) if (nfs_server_capable(inode, NFS_CAP_READDIRPLUS)) set_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags); /* Deal with crossing mountpoints */ - if ((fattr->valid & NFS_ATTR_FATTR_FSID) - && !nfs_fsid_equal(&NFS_SB(sb)->fsid, &fattr->fsid)) { + if (fattr->valid & NFS_ATTR_FATTR_MOUNTPOINT || + fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) { if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) inode->i_op = &nfs_referral_inode_operations; else @@ -639,7 +641,6 @@ struct nfs_open_context *alloc_nfs_open_context(struct path *path, struct rpc_cr ctx->mode = f_mode; ctx->flags = 0; ctx->error = 0; - ctx->dir_cookie = 0; nfs_init_lock_context(&ctx->lock_context); ctx->lock_context.open_context = ctx; INIT_LIST_HEAD(&ctx->list); @@ -1471,6 +1472,7 @@ static inline void nfs4_init_once(struct nfs_inode *nfsi) nfsi->delegation_state = 0; init_rwsem(&nfsi->rwsem); nfsi->layout = NULL; + atomic_set(&nfsi->commits_outstanding, 0); #endif } diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 72e0bddf7a2f..ce118ce885dd 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -39,6 +39,12 @@ static inline int nfs4_has_persistent_session(const struct nfs_client *clp) return 0; } +static inline void nfs_attr_check_mountpoint(struct super_block *parent, struct nfs_fattr *fattr) +{ + if (!nfs_fsid_equal(&NFS_SB(parent)->fsid, &fattr->fsid)) + fattr->valid |= NFS_ATTR_FATTR_MOUNTPOINT; +} + struct nfs_clone_mount { const struct super_block *sb; const struct dentry *dentry; @@ -214,6 +220,7 @@ extern const u32 nfs41_maxwrite_overhead; /* nfs4proc.c */ #ifdef CONFIG_NFS_V4 extern struct rpc_procinfo nfs4_procedures[]; +void nfs_fixup_secinfo_attributes(struct nfs_fattr *, struct nfs_fh *); #endif extern int nfs4_init_ds_session(struct nfs_client *clp); @@ -276,11 +283,25 @@ extern int nfs_initiate_read(struct nfs_read_data *data, struct rpc_clnt *clnt, extern void nfs_read_prepare(struct rpc_task *task, void *calldata); /* write.c */ +extern void nfs_commit_free(struct nfs_write_data *p); extern int nfs_initiate_write(struct nfs_write_data *data, struct rpc_clnt *clnt, const struct rpc_call_ops *call_ops, int how); extern void nfs_write_prepare(struct rpc_task *task, void *calldata); +extern int nfs_initiate_commit(struct nfs_write_data *data, + struct rpc_clnt *clnt, + const struct rpc_call_ops *call_ops, + int how); +extern void nfs_init_commit(struct nfs_write_data *data, + struct list_head *head, + struct pnfs_layout_segment *lseg); +void nfs_retry_commit(struct list_head *page_list, + struct pnfs_layout_segment *lseg); +void nfs_commit_clear_lock(struct nfs_inode *nfsi); +void nfs_commitdata_release(void *data); +void nfs_commit_release_pages(struct nfs_write_data *data); + #ifdef CONFIG_MIGRATION extern int nfs_migrate_page(struct address_space *, struct page *, struct page *); @@ -296,12 +317,14 @@ extern int nfs4_init_client(struct nfs_client *clp, rpc_authflavor_t authflavour, int noresvport); extern void nfs4_reset_write(struct rpc_task *task, struct nfs_write_data *data); -extern int _nfs4_call_sync(struct nfs_server *server, +extern int _nfs4_call_sync(struct rpc_clnt *clnt, + struct nfs_server *server, struct rpc_message *msg, struct nfs4_sequence_args *args, struct nfs4_sequence_res *res, int cache_reply); -extern int _nfs4_call_sync_session(struct nfs_server *server, +extern int _nfs4_call_sync_session(struct rpc_clnt *clnt, + struct nfs_server *server, struct rpc_message *msg, struct nfs4_sequence_args *args, struct nfs4_sequence_res *res, diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index bf1c68009ffd..ad92bf731ff5 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -15,6 +15,7 @@ #include <linux/string.h> #include <linux/sunrpc/clnt.h> #include <linux/vfs.h> +#include <linux/sunrpc/gss_api.h> #include "internal.h" #define NFSDBG_FACILITY NFSDBG_VFS @@ -27,7 +28,8 @@ int nfs_mountpoint_expiry_timeout = 500 * HZ; static struct vfsmount *nfs_do_submount(struct dentry *dentry, struct nfs_fh *fh, - struct nfs_fattr *fattr); + struct nfs_fattr *fattr, + rpc_authflavor_t authflavor); /* * nfs_path - reconstruct the path given an arbitrary dentry @@ -116,6 +118,100 @@ Elong: return ERR_PTR(-ENAMETOOLONG); } +#ifdef CONFIG_NFS_V4 +static rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *flavors, struct inode *inode) +{ + struct gss_api_mech *mech; + struct xdr_netobj oid; + int i; + rpc_authflavor_t pseudoflavor = RPC_AUTH_UNIX; + + for (i = 0; i < flavors->num_flavors; i++) { + struct nfs4_secinfo_flavor *flavor; + flavor = &flavors->flavors[i]; + + if (flavor->flavor == RPC_AUTH_NULL || flavor->flavor == RPC_AUTH_UNIX) { + pseudoflavor = flavor->flavor; + break; + } else if (flavor->flavor == RPC_AUTH_GSS) { + oid.len = flavor->gss.sec_oid4.len; + oid.data = flavor->gss.sec_oid4.data; + mech = gss_mech_get_by_OID(&oid); + if (!mech) + continue; + pseudoflavor = gss_svc_to_pseudoflavor(mech, flavor->gss.service); + gss_mech_put(mech); + break; + } + } + + return pseudoflavor; +} + +static rpc_authflavor_t nfs_negotiate_security(const struct dentry *parent, const struct dentry *dentry) +{ + int status = 0; + struct page *page; + struct nfs4_secinfo_flavors *flavors; + int (*secinfo)(struct inode *, const struct qstr *, struct nfs4_secinfo_flavors *); + rpc_authflavor_t flavor = RPC_AUTH_UNIX; + + secinfo = NFS_PROTO(parent->d_inode)->secinfo; + if (secinfo != NULL) { + page = alloc_page(GFP_KERNEL); + if (!page) { + status = -ENOMEM; + goto out; + } + flavors = page_address(page); + status = secinfo(parent->d_inode, &dentry->d_name, flavors); + flavor = nfs_find_best_sec(flavors, dentry->d_inode); + put_page(page); + } + + return flavor; + +out: + status = -ENOMEM; + return status; +} + +static rpc_authflavor_t nfs_lookup_with_sec(struct nfs_server *server, struct dentry *parent, + struct dentry *dentry, struct path *path, + struct nfs_fh *fh, struct nfs_fattr *fattr) +{ + rpc_authflavor_t flavor; + struct rpc_clnt *clone; + struct rpc_auth *auth; + int err; + + flavor = nfs_negotiate_security(parent, path->dentry); + if (flavor < 0) + goto out; + clone = rpc_clone_client(server->client); + auth = rpcauth_create(flavor, clone); + if (!auth) { + flavor = -EIO; + goto out; + } + err = server->nfs_client->rpc_ops->lookup(clone, parent->d_inode, + &path->dentry->d_name, + fh, fattr); + if (err < 0) + flavor = err; +out: + return flavor; +} +#else /* CONFIG_NFS_V4 */ +static inline rpc_authflavor_t nfs_lookup_with_sec(struct nfs_server *server, + struct dentry *parent, struct dentry *dentry, + struct path *path, struct nfs_fh *fh, + struct nfs_fattr *fattr) +{ + return -EPERM; +} +#endif /* CONFIG_NFS_V4 */ + /* * nfs_d_automount - Handle crossing a mountpoint on the server * @path - The mountpoint @@ -136,6 +232,7 @@ struct vfsmount *nfs_d_automount(struct path *path) struct nfs_fh *fh = NULL; struct nfs_fattr *fattr = NULL; int err; + rpc_authflavor_t flavor = 1; dprintk("--> nfs_d_automount()\n"); @@ -153,9 +250,16 @@ struct vfsmount *nfs_d_automount(struct path *path) /* Look it up again to get its attributes */ parent = dget_parent(path->dentry); - err = server->nfs_client->rpc_ops->lookup(parent->d_inode, + err = server->nfs_client->rpc_ops->lookup(server->client, parent->d_inode, &path->dentry->d_name, fh, fattr); + if (err == -EPERM) { + flavor = nfs_lookup_with_sec(server, parent, path->dentry, path, fh, fattr); + if (flavor < 0) + err = flavor; + else + err = 0; + } dput(parent); if (err != 0) { mnt = ERR_PTR(err); @@ -165,7 +269,7 @@ struct vfsmount *nfs_d_automount(struct path *path) if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) mnt = nfs_do_refmount(path->dentry); else - mnt = nfs_do_submount(path->dentry, fh, fattr); + mnt = nfs_do_submount(path->dentry, fh, fattr, flavor); if (IS_ERR(mnt)) goto out; @@ -232,17 +336,20 @@ static struct vfsmount *nfs_do_clone_mount(struct nfs_server *server, * @dentry - parent directory * @fh - filehandle for new root dentry * @fattr - attributes for new root inode + * @authflavor - security flavor to use when performing the mount * */ static struct vfsmount *nfs_do_submount(struct dentry *dentry, struct nfs_fh *fh, - struct nfs_fattr *fattr) + struct nfs_fattr *fattr, + rpc_authflavor_t authflavor) { struct nfs_clone_mount mountdata = { .sb = dentry->d_sb, .dentry = dentry, .fh = fh, .fattr = fattr, + .authflavor = authflavor, }; struct vfsmount *mnt = ERR_PTR(-ENOMEM); char *page = (char *) __get_free_page(GFP_USER); diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index d0c80d8b3f96..38053d823eb0 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -141,7 +141,7 @@ nfs3_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr, } static int -nfs3_proc_lookup(struct inode *dir, struct qstr *name, +nfs3_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, struct qstr *name, struct nfs_fh *fhandle, struct nfs_fattr *fattr) { struct nfs3_diropargs arg = { diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index c64be1cff080..e1c261ddd65d 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -57,7 +57,8 @@ enum nfs4_session_state { struct nfs4_minor_version_ops { u32 minor_version; - int (*call_sync)(struct nfs_server *server, + int (*call_sync)(struct rpc_clnt *clnt, + struct nfs_server *server, struct rpc_message *msg, struct nfs4_sequence_args *args, struct nfs4_sequence_res *res, @@ -262,6 +263,8 @@ extern int nfs4_proc_destroy_session(struct nfs4_session *); extern int nfs4_init_session(struct nfs_server *server); extern int nfs4_proc_get_lease_time(struct nfs_client *clp, struct nfs_fsinfo *fsinfo); +extern int nfs4_proc_layoutcommit(struct nfs4_layoutcommit_data *data, + bool sync); static inline bool is_ds_only_client(struct nfs_client *clp) diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c index 428558464817..6f8192f4cfc7 100644 --- a/fs/nfs/nfs4filelayout.c +++ b/fs/nfs/nfs4filelayout.c @@ -154,6 +154,23 @@ static int filelayout_read_done_cb(struct rpc_task *task, } /* + * We reference the rpc_cred of the first WRITE that triggers the need for + * a LAYOUTCOMMIT, and use it to send the layoutcommit compound. + * rfc5661 is not clear about which credential should be used. + */ +static void +filelayout_set_layoutcommit(struct nfs_write_data *wdata) +{ + if (FILELAYOUT_LSEG(wdata->lseg)->commit_through_mds || + wdata->res.verf->committed == NFS_FILE_SYNC) + return; + + pnfs_set_layoutcommit(wdata); + dprintk("%s ionde %lu pls_end_pos %lu\n", __func__, wdata->inode->i_ino, + (unsigned long) wdata->lseg->pls_end_pos); +} + +/* * Call ops for the async read/write cases * In the case of dense layouts, the offset needs to be reset to its * original value. @@ -210,6 +227,38 @@ static int filelayout_write_done_cb(struct rpc_task *task, return -EAGAIN; } + filelayout_set_layoutcommit(data); + return 0; +} + +/* Fake up some data that will cause nfs_commit_release to retry the writes. */ +static void prepare_to_resend_writes(struct nfs_write_data *data) +{ + struct nfs_page *first = nfs_list_entry(data->pages.next); + + data->task.tk_status = 0; + memcpy(data->verf.verifier, first->wb_verf.verifier, + sizeof(first->wb_verf.verifier)); + data->verf.verifier[0]++; /* ensure verifier mismatch */ +} + +static int filelayout_commit_done_cb(struct rpc_task *task, + struct nfs_write_data *data) +{ + int reset = 0; + + if (filelayout_async_handle_error(task, data->args.context->state, + data->ds_clp, &reset) == -EAGAIN) { + dprintk("%s calling restart ds_clp %p ds_clp->cl_session %p\n", + __func__, data->ds_clp, data->ds_clp->cl_session); + if (reset) { + prepare_to_resend_writes(data); + filelayout_set_lo_fail(data->lseg); + } else + nfs_restart_rpc(task, data->ds_clp); + return -EAGAIN; + } + return 0; } @@ -240,6 +289,16 @@ static void filelayout_write_release(void *data) wdata->mds_ops->rpc_release(data); } +static void filelayout_commit_release(void *data) +{ + struct nfs_write_data *wdata = (struct nfs_write_data *)data; + + nfs_commit_release_pages(wdata); + if (atomic_dec_and_test(&NFS_I(wdata->inode)->commits_outstanding)) + nfs_commit_clear_lock(NFS_I(wdata->inode)); + nfs_commitdata_release(wdata); +} + struct rpc_call_ops filelayout_read_call_ops = { .rpc_call_prepare = filelayout_read_prepare, .rpc_call_done = filelayout_read_call_done, @@ -252,6 +311,12 @@ struct rpc_call_ops filelayout_write_call_ops = { .rpc_release = filelayout_write_release, }; +struct rpc_call_ops filelayout_commit_call_ops = { + .rpc_call_prepare = filelayout_write_prepare, + .rpc_call_done = filelayout_write_call_done, + .rpc_release = filelayout_commit_release, +}; + static enum pnfs_try_status filelayout_read_pagelist(struct nfs_read_data *data) { @@ -320,10 +385,6 @@ filelayout_write_pagelist(struct nfs_write_data *data, int sync) data->inode->i_ino, sync, (size_t) data->args.count, offset, ntohl(ds->ds_ip_addr), ntohs(ds->ds_port)); - /* We can't handle commit to ds yet */ - if (!FILELAYOUT_LSEG(lseg)->commit_through_mds) - data->args.stable = NFS_FILE_SYNC; - data->write_done_cb = filelayout_write_done_cb; data->ds_clp = ds->ds_clp; fh = nfs4_fl_select_ds_fh(lseg, j); @@ -441,12 +502,33 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo, struct nfs4_layoutget_res *lgr, struct nfs4_deviceid *id) { - uint32_t *p = (uint32_t *)lgr->layout.buf; + struct xdr_stream stream; + struct xdr_buf buf = { + .pages = lgr->layoutp->pages, + .page_len = lgr->layoutp->len, + .buflen = lgr->layoutp->len, + .len = lgr->layoutp->len, + }; + struct page *scratch; + __be32 *p; uint32_t nfl_util; int i; dprintk("%s: set_layout_map Begin\n", __func__); + scratch = alloc_page(GFP_KERNEL); + if (!scratch) + return -ENOMEM; + + xdr_init_decode(&stream, &buf, NULL); + xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE); + + /* 20 = ufl_util (4), first_stripe_index (4), pattern_offset (8), + * num_fh (4) */ + p = xdr_inline_decode(&stream, NFS4_DEVICEID4_SIZE + 20); + if (unlikely(!p)) + goto out_err; + memcpy(id, p, sizeof(*id)); p += XDR_QUADLEN(NFS4_DEVICEID4_SIZE); print_deviceid(id); @@ -468,32 +550,57 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo, __func__, nfl_util, fl->num_fh, fl->first_stripe_index, fl->pattern_offset); + if (!fl->num_fh) + goto out_err; + fl->fh_array = kzalloc(fl->num_fh * sizeof(struct nfs_fh *), GFP_KERNEL); if (!fl->fh_array) - return -ENOMEM; + goto out_err; for (i = 0; i < fl->num_fh; i++) { /* Do we want to use a mempool here? */ fl->fh_array[i] = kmalloc(sizeof(struct nfs_fh), GFP_KERNEL); - if (!fl->fh_array[i]) { - filelayout_free_fh_array(fl); - return -ENOMEM; - } + if (!fl->fh_array[i]) + goto out_err_free; + + p = xdr_inline_decode(&stream, 4); + if (unlikely(!p)) + goto out_err_free; fl->fh_array[i]->size = be32_to_cpup(p++); if (sizeof(struct nfs_fh) < fl->fh_array[i]->size) { printk(KERN_ERR "Too big fh %d received %d\n", i, fl->fh_array[i]->size); - filelayout_free_fh_array(fl); - return -EIO; + goto out_err_free; } + + p = xdr_inline_decode(&stream, fl->fh_array[i]->size); + if (unlikely(!p)) + goto out_err_free; memcpy(fl->fh_array[i]->data, p, fl->fh_array[i]->size); - p += XDR_QUADLEN(fl->fh_array[i]->size); dprintk("DEBUG: %s: fh len %d\n", __func__, fl->fh_array[i]->size); } + __free_page(scratch); return 0; + +out_err_free: + filelayout_free_fh_array(fl); +out_err: + __free_page(scratch); + return -EIO; +} + +static void +filelayout_free_lseg(struct pnfs_layout_segment *lseg) +{ + struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg); + + dprintk("--> %s\n", __func__); + nfs4_fl_put_deviceid(fl->dsaddr); + kfree(fl->commit_buckets); + _filelayout_free_lseg(fl); } static struct pnfs_layout_segment * @@ -514,17 +621,28 @@ filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid, _filelayout_free_lseg(fl); return NULL; } - return &fl->generic_hdr; -} -static void -filelayout_free_lseg(struct pnfs_layout_segment *lseg) -{ - struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg); - - dprintk("--> %s\n", __func__); - nfs4_fl_put_deviceid(fl->dsaddr); - _filelayout_free_lseg(fl); + /* This assumes there is only one IOMODE_RW lseg. What + * we really want to do is have a layout_hdr level + * dictionary of <multipath_list4, fh> keys, each + * associated with a struct list_head, populated by calls + * to filelayout_write_pagelist(). + * */ + if ((!fl->commit_through_mds) && (lgr->range.iomode == IOMODE_RW)) { + int i; + int size = (fl->stripe_type == STRIPE_SPARSE) ? + fl->dsaddr->ds_num : fl->dsaddr->stripe_count; + + fl->commit_buckets = kcalloc(size, sizeof(struct list_head), GFP_KERNEL); + if (!fl->commit_buckets) { + filelayout_free_lseg(&fl->generic_hdr); + return NULL; + } + fl->number_of_buckets = size; + for (i = 0; i < size; i++) + INIT_LIST_HEAD(&fl->commit_buckets[i]); + } + return &fl->generic_hdr; } /* @@ -552,6 +670,191 @@ filelayout_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, return (p_stripe == r_stripe); } +static bool filelayout_mark_pnfs_commit(struct pnfs_layout_segment *lseg) +{ + return !FILELAYOUT_LSEG(lseg)->commit_through_mds; +} + +static u32 select_bucket_index(struct nfs4_filelayout_segment *fl, u32 j) +{ + if (fl->stripe_type == STRIPE_SPARSE) + return nfs4_fl_calc_ds_index(&fl->generic_hdr, j); + else + return j; +} + +struct list_head *filelayout_choose_commit_list(struct nfs_page *req) +{ + struct pnfs_layout_segment *lseg = req->wb_commit_lseg; + struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg); + u32 i, j; + struct list_head *list; + + /* Note that we are calling nfs4_fl_calc_j_index on each page + * that ends up being committed to a data server. An attractive + * alternative is to add a field to nfs_write_data and nfs_page + * to store the value calculated in filelayout_write_pagelist + * and just use that here. + */ + j = nfs4_fl_calc_j_index(lseg, + (loff_t)req->wb_index << PAGE_CACHE_SHIFT); + i = select_bucket_index(fl, j); + list = &fl->commit_buckets[i]; + if (list_empty(list)) { + /* Non-empty buckets hold a reference on the lseg */ + get_lseg(lseg); + } + return list; +} + +static u32 calc_ds_index_from_commit(struct pnfs_layout_segment *lseg, u32 i) +{ + struct nfs4_filelayout_segment *flseg = FILELAYOUT_LSEG(lseg); + + if (flseg->stripe_type == STRIPE_SPARSE) + return i; + else + return nfs4_fl_calc_ds_index(lseg, i); +} + +static struct nfs_fh * +select_ds_fh_from_commit(struct pnfs_layout_segment *lseg, u32 i) +{ + struct nfs4_filelayout_segment *flseg = FILELAYOUT_LSEG(lseg); + + if (flseg->stripe_type == STRIPE_SPARSE) { + if (flseg->num_fh == 1) + i = 0; + else if (flseg->num_fh == 0) + /* Use the MDS OPEN fh set in nfs_read_rpcsetup */ + return NULL; + } + return flseg->fh_array[i]; +} + +static int filelayout_initiate_commit(struct nfs_write_data *data, int how) +{ + struct pnfs_layout_segment *lseg = data->lseg; + struct nfs4_pnfs_ds *ds; + u32 idx; + struct nfs_fh *fh; + + idx = calc_ds_index_from_commit(lseg, data->ds_commit_index); + ds = nfs4_fl_prepare_ds(lseg, idx); + if (!ds) { + printk(KERN_ERR "%s: prepare_ds failed, use MDS\n", __func__); + set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags); + set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags); + prepare_to_resend_writes(data); + data->mds_ops->rpc_release(data); + return -EAGAIN; + } + dprintk("%s ino %lu, how %d\n", __func__, data->inode->i_ino, how); + data->write_done_cb = filelayout_commit_done_cb; + data->ds_clp = ds->ds_clp; + fh = select_ds_fh_from_commit(lseg, data->ds_commit_index); + if (fh) + data->args.fh = fh; + return nfs_initiate_commit(data, ds->ds_clp->cl_rpcclient, + &filelayout_commit_call_ops, how); +} + +/* + * This is only useful while we are using whole file layouts. + */ +static struct pnfs_layout_segment *find_only_write_lseg(struct inode *inode) +{ + struct pnfs_layout_segment *lseg, *rv = NULL; + + spin_lock(&inode->i_lock); + list_for_each_entry(lseg, &NFS_I(inode)->layout->plh_segs, pls_list) + if (lseg->pls_range.iomode == IOMODE_RW) + rv = get_lseg(lseg); + spin_unlock(&inode->i_lock); + return rv; +} + +static int alloc_ds_commits(struct inode *inode, struct list_head *list) +{ + struct pnfs_layout_segment *lseg; + struct nfs4_filelayout_segment *fl; + struct nfs_write_data *data; + int i, j; + + /* Won't need this when non-whole file layout segments are supported + * instead we will use a pnfs_layout_hdr structure */ + lseg = find_only_write_lseg(inode); + if (!lseg) + return 0; + fl = FILELAYOUT_LSEG(lseg); + for (i = 0; i < fl->number_of_buckets; i++) { + if (list_empty(&fl->commit_buckets[i])) + continue; + data = nfs_commitdata_alloc(); + if (!data) + goto out_bad; + data->ds_commit_index = i; + data->lseg = lseg; + list_add(&data->pages, list); + } + put_lseg(lseg); + return 0; + +out_bad: + for (j = i; j < fl->number_of_buckets; j++) { + if (list_empty(&fl->commit_buckets[i])) + continue; + nfs_retry_commit(&fl->commit_buckets[i], lseg); + put_lseg(lseg); /* associated with emptying bucket */ + } + put_lseg(lseg); + /* Caller will clean up entries put on list */ + return -ENOMEM; +} + +/* This follows nfs_commit_list pretty closely */ +static int +filelayout_commit_pagelist(struct inode *inode, struct list_head *mds_pages, + int how) +{ + struct nfs_write_data *data, *tmp; + LIST_HEAD(list); + + if (!list_empty(mds_pages)) { + data = nfs_commitdata_alloc(); + if (!data) + goto out_bad; + data->lseg = NULL; + list_add(&data->pages, &list); + } + + if (alloc_ds_commits(inode, &list)) + goto out_bad; + + list_for_each_entry_safe(data, tmp, &list, pages) { + list_del_init(&data->pages); + atomic_inc(&NFS_I(inode)->commits_outstanding); + if (!data->lseg) { + nfs_init_commit(data, mds_pages, NULL); + nfs_initiate_commit(data, NFS_CLIENT(inode), + data->mds_ops, how); + } else { + nfs_init_commit(data, &FILELAYOUT_LSEG(data->lseg)->commit_buckets[data->ds_commit_index], data->lseg); + filelayout_initiate_commit(data, how); + } + } + return 0; + out_bad: + list_for_each_entry_safe(data, tmp, &list, pages) { + nfs_retry_commit(&data->pages, data->lseg); + list_del_init(&data->pages); + nfs_commit_free(data); + } + nfs_retry_commit(mds_pages, NULL); + nfs_commit_clear_lock(NFS_I(inode)); + return -ENOMEM; +} + static struct pnfs_layoutdriver_type filelayout_type = { .id = LAYOUT_NFSV4_1_FILES, .name = "LAYOUT_NFSV4_1_FILES", @@ -559,6 +862,9 @@ static struct pnfs_layoutdriver_type filelayout_type = { .alloc_lseg = filelayout_alloc_lseg, .free_lseg = filelayout_free_lseg, .pg_test = filelayout_pg_test, + .mark_pnfs_commit = filelayout_mark_pnfs_commit, + .choose_commit_list = filelayout_choose_commit_list, + .commit_pagelist = filelayout_commit_pagelist, .read_pagelist = filelayout_read_pagelist, .write_pagelist = filelayout_write_pagelist, }; diff --git a/fs/nfs/nfs4filelayout.h b/fs/nfs/nfs4filelayout.h index ee0c907742b5..085a354e0f08 100644 --- a/fs/nfs/nfs4filelayout.h +++ b/fs/nfs/nfs4filelayout.h @@ -79,6 +79,8 @@ struct nfs4_filelayout_segment { struct nfs4_file_layout_dsaddr *dsaddr; /* Point to GETDEVINFO data */ unsigned int num_fh; struct nfs_fh **fh_array; + struct list_head *commit_buckets; /* Sort commits to ds */ + int number_of_buckets; }; static inline struct nfs4_filelayout_segment * diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c index 68143c162e3b..de5350f2b249 100644 --- a/fs/nfs/nfs4filelayoutdev.c +++ b/fs/nfs/nfs4filelayoutdev.c @@ -261,7 +261,7 @@ out: * Currently only support ipv4, and one multi-path address. */ static struct nfs4_pnfs_ds * -decode_and_add_ds(__be32 **pp, struct inode *inode) +decode_and_add_ds(struct xdr_stream *streamp, struct inode *inode) { struct nfs4_pnfs_ds *ds = NULL; char *buf; @@ -269,25 +269,34 @@ decode_and_add_ds(__be32 **pp, struct inode *inode) u32 ip_addr, port; int nlen, rlen, i; int tmp[2]; - __be32 *r_netid, *r_addr, *p = *pp; + __be32 *p; /* r_netid */ + p = xdr_inline_decode(streamp, 4); + if (unlikely(!p)) + goto out_err; nlen = be32_to_cpup(p++); - r_netid = p; - p += XDR_QUADLEN(nlen); - /* r_addr */ - rlen = be32_to_cpup(p++); - r_addr = p; - p += XDR_QUADLEN(rlen); - *pp = p; + p = xdr_inline_decode(streamp, nlen); + if (unlikely(!p)) + goto out_err; /* Check that netid is "tcp" */ - if (nlen != 3 || memcmp((char *)r_netid, "tcp", 3)) { + if (nlen != 3 || memcmp((char *)p, "tcp", 3)) { dprintk("%s: ERROR: non ipv4 TCP r_netid\n", __func__); goto out_err; } + /* r_addr */ + p = xdr_inline_decode(streamp, 4); + if (unlikely(!p)) + goto out_err; + rlen = be32_to_cpup(p); + + p = xdr_inline_decode(streamp, rlen); + if (unlikely(!p)) + goto out_err; + /* ipv6 length plus port is legal */ if (rlen > INET6_ADDRSTRLEN + 8) { dprintk("%s: Invalid address, length %d\n", __func__, @@ -300,7 +309,7 @@ decode_and_add_ds(__be32 **pp, struct inode *inode) goto out_err; } buf[rlen] = '\0'; - memcpy(buf, r_addr, rlen); + memcpy(buf, p, rlen); /* replace the port dots with dashes for the in4_pton() delimiter*/ for (i = 0; i < 2; i++) { @@ -336,90 +345,154 @@ out_err: static struct nfs4_file_layout_dsaddr* decode_device(struct inode *ino, struct pnfs_device *pdev) { - int i, dummy; + int i; u32 cnt, num; u8 *indexp; - __be32 *p = (__be32 *)pdev->area, *indicesp; - struct nfs4_file_layout_dsaddr *dsaddr; + __be32 *p; + u8 *stripe_indices; + u8 max_stripe_index; + struct nfs4_file_layout_dsaddr *dsaddr = NULL; + struct xdr_stream stream; + struct xdr_buf buf = { + .pages = pdev->pages, + .page_len = pdev->pglen, + .buflen = pdev->pglen, + .len = pdev->pglen, + }; + struct page *scratch; + + /* set up xdr stream */ + scratch = alloc_page(GFP_KERNEL); + if (!scratch) + goto out_err; + + xdr_init_decode(&stream, &buf, NULL); + xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE); /* Get the stripe count (number of stripe index) */ - cnt = be32_to_cpup(p++); + p = xdr_inline_decode(&stream, 4); + if (unlikely(!p)) + goto out_err_free_scratch; + + cnt = be32_to_cpup(p); dprintk("%s stripe count %d\n", __func__, cnt); if (cnt > NFS4_PNFS_MAX_STRIPE_CNT) { printk(KERN_WARNING "%s: stripe count %d greater than " "supported maximum %d\n", __func__, cnt, NFS4_PNFS_MAX_STRIPE_CNT); - goto out_err; + goto out_err_free_scratch; + } + + /* read stripe indices */ + stripe_indices = kcalloc(cnt, sizeof(u8), GFP_KERNEL); + if (!stripe_indices) + goto out_err_free_scratch; + + p = xdr_inline_decode(&stream, cnt << 2); + if (unlikely(!p)) + goto out_err_free_stripe_indices; + + indexp = &stripe_indices[0]; + max_stripe_index = 0; + for (i = 0; i < cnt; i++) { + *indexp = be32_to_cpup(p++); + max_stripe_index = max(max_stripe_index, *indexp); + indexp++; } /* Check the multipath list count */ - indicesp = p; - p += XDR_QUADLEN(cnt << 2); - num = be32_to_cpup(p++); + p = xdr_inline_decode(&stream, 4); + if (unlikely(!p)) + goto out_err_free_stripe_indices; + + num = be32_to_cpup(p); dprintk("%s ds_num %u\n", __func__, num); if (num > NFS4_PNFS_MAX_MULTI_CNT) { printk(KERN_WARNING "%s: multipath count %d greater than " "supported maximum %d\n", __func__, num, NFS4_PNFS_MAX_MULTI_CNT); - goto out_err; + goto out_err_free_stripe_indices; } + + /* validate stripe indices are all < num */ + if (max_stripe_index >= num) { + printk(KERN_WARNING "%s: stripe index %u >= num ds %u\n", + __func__, max_stripe_index, num); + goto out_err_free_stripe_indices; + } + dsaddr = kzalloc(sizeof(*dsaddr) + (sizeof(struct nfs4_pnfs_ds *) * (num - 1)), GFP_KERNEL); if (!dsaddr) - goto out_err; - - dsaddr->stripe_indices = kzalloc(sizeof(u8) * cnt, GFP_KERNEL); - if (!dsaddr->stripe_indices) - goto out_err_free; + goto out_err_free_stripe_indices; dsaddr->stripe_count = cnt; + dsaddr->stripe_indices = stripe_indices; + stripe_indices = NULL; dsaddr->ds_num = num; memcpy(&dsaddr->deviceid, &pdev->dev_id, sizeof(pdev->dev_id)); - /* Go back an read stripe indices */ - p = indicesp; - indexp = &dsaddr->stripe_indices[0]; - for (i = 0; i < dsaddr->stripe_count; i++) { - *indexp = be32_to_cpup(p++); - if (*indexp >= num) - goto out_err_free; - indexp++; - } - /* Skip already read multipath list count */ - p++; - for (i = 0; i < dsaddr->ds_num; i++) { int j; + u32 mp_count; + + p = xdr_inline_decode(&stream, 4); + if (unlikely(!p)) + goto out_err_free_deviceid; - dummy = be32_to_cpup(p++); /* multipath count */ - if (dummy > 1) { + mp_count = be32_to_cpup(p); /* multipath count */ + if (mp_count > 1) { printk(KERN_WARNING "%s: Multipath count %d not supported, " "skipping all greater than 1\n", __func__, - dummy); + mp_count); } - for (j = 0; j < dummy; j++) { + for (j = 0; j < mp_count; j++) { if (j == 0) { - dsaddr->ds_list[i] = decode_and_add_ds(&p, ino); + dsaddr->ds_list[i] = decode_and_add_ds(&stream, + ino); if (dsaddr->ds_list[i] == NULL) - goto out_err_free; + goto out_err_free_deviceid; } else { u32 len; /* skip extra multipath */ - len = be32_to_cpup(p++); - p += XDR_QUADLEN(len); - len = be32_to_cpup(p++); - p += XDR_QUADLEN(len); - continue; + + /* read len, skip */ + p = xdr_inline_decode(&stream, 4); + if (unlikely(!p)) + goto out_err_free_deviceid; + len = be32_to_cpup(p); + + p = xdr_inline_decode(&stream, len); + if (unlikely(!p)) + goto out_err_free_deviceid; + + /* read len, skip */ + p = xdr_inline_decode(&stream, 4); + if (unlikely(!p)) + goto out_err_free_deviceid; + len = be32_to_cpup(p); + + p = xdr_inline_decode(&stream, len); + if (unlikely(!p)) + goto out_err_free_deviceid; } } } + + __free_page(scratch); return dsaddr; -out_err_free: +out_err_free_deviceid: nfs4_fl_free_deviceid(dsaddr); + /* stripe_indicies was part of dsaddr */ + goto out_err_free_scratch; +out_err_free_stripe_indices: + kfree(stripe_indices); +out_err_free_scratch: + __free_page(scratch); out_err: dprintk("%s ERROR: returning NULL\n", __func__); return NULL; @@ -498,11 +571,6 @@ get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id) goto out_free; } - /* set pdev->area */ - pdev->area = vmap(pages, max_pages, VM_MAP, PAGE_KERNEL); - if (!pdev->area) - goto out_free; - memcpy(&pdev->dev_id, dev_id, sizeof(*dev_id)); pdev->layout_type = LAYOUT_NFSV4_1_FILES; pdev->pages = pages; @@ -521,8 +589,6 @@ get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id) */ dsaddr = decode_and_add_device(inode, pdev); out_free: - if (pdev->area != NULL) - vunmap(pdev->area); for (i = 0; i < max_pages; i++) __free_page(pages[i]); kfree(pages); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 1d84e7088af9..dfd1e6d7e6c3 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -41,6 +41,7 @@ #include <linux/string.h> #include <linux/slab.h> #include <linux/sunrpc/clnt.h> +#include <linux/sunrpc/gss_api.h> #include <linux/nfs.h> #include <linux/nfs4.h> #include <linux/nfs_fs.h> @@ -71,7 +72,9 @@ static int _nfs4_proc_open(struct nfs4_opendata *data); static int _nfs4_recover_proc_open(struct nfs4_opendata *data); static int nfs4_do_fsinfo(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *); static int nfs4_async_handle_error(struct rpc_task *, const struct nfs_server *, struct nfs4_state *); -static int _nfs4_proc_lookup(struct inode *dir, const struct qstr *name, struct nfs_fh *fhandle, struct nfs_fattr *fattr); +static int _nfs4_proc_lookup(struct rpc_clnt *client, struct inode *dir, + const struct qstr *name, struct nfs_fh *fhandle, + struct nfs_fattr *fattr); static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fattr *fattr); static int nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred, struct nfs_fattr *fattr, struct iattr *sattr, @@ -85,6 +88,8 @@ static int nfs4_map_errors(int err) switch (err) { case -NFS4ERR_RESOURCE: return -EREMOTEIO; + case -NFS4ERR_WRONGSEC: + return -EPERM; case -NFS4ERR_BADOWNER: case -NFS4ERR_BADNAME: return -EINVAL; @@ -657,7 +662,8 @@ struct rpc_call_ops nfs41_call_priv_sync_ops = { .rpc_call_done = nfs41_call_sync_done, }; -static int nfs4_call_sync_sequence(struct nfs_server *server, +static int nfs4_call_sync_sequence(struct rpc_clnt *clnt, + struct nfs_server *server, struct rpc_message *msg, struct nfs4_sequence_args *args, struct nfs4_sequence_res *res, @@ -673,7 +679,7 @@ static int nfs4_call_sync_sequence(struct nfs_server *server, .cache_reply = cache_reply, }; struct rpc_task_setup task_setup = { - .rpc_client = server->client, + .rpc_client = clnt, .rpc_message = msg, .callback_ops = &nfs41_call_sync_ops, .callback_data = &data @@ -692,13 +698,14 @@ static int nfs4_call_sync_sequence(struct nfs_server *server, return ret; } -int _nfs4_call_sync_session(struct nfs_server *server, +int _nfs4_call_sync_session(struct rpc_clnt *clnt, + struct nfs_server *server, struct rpc_message *msg, struct nfs4_sequence_args *args, struct nfs4_sequence_res *res, int cache_reply) { - return nfs4_call_sync_sequence(server, msg, args, res, cache_reply, 0); + return nfs4_call_sync_sequence(clnt, server, msg, args, res, cache_reply, 0); } #else @@ -709,19 +716,28 @@ static int nfs4_sequence_done(struct rpc_task *task, } #endif /* CONFIG_NFS_V4_1 */ -int _nfs4_call_sync(struct nfs_server *server, +int _nfs4_call_sync(struct rpc_clnt *clnt, + struct nfs_server *server, struct rpc_message *msg, struct nfs4_sequence_args *args, struct nfs4_sequence_res *res, int cache_reply) { args->sa_session = res->sr_session = NULL; - return rpc_call_sync(server->client, msg, 0); + return rpc_call_sync(clnt, msg, 0); } -#define nfs4_call_sync(server, msg, args, res, cache_reply) \ - (server)->nfs_client->cl_mvops->call_sync((server), (msg), &(args)->seq_args, \ - &(res)->seq_res, (cache_reply)) +static inline +int nfs4_call_sync(struct rpc_clnt *clnt, + struct nfs_server *server, + struct rpc_message *msg, + struct nfs4_sequence_args *args, + struct nfs4_sequence_res *res, + int cache_reply) +{ + return server->nfs_client->cl_mvops->call_sync(clnt, server, msg, + args, res, cache_reply); +} static void update_changeattr(struct inode *dir, struct nfs4_change_info *cinfo) { @@ -1831,7 +1847,7 @@ static int _nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred, } else memcpy(&arg.stateid, &zero_stateid, sizeof(arg.stateid)); - status = nfs4_call_sync(server, &msg, &arg, &res, 1); + status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1); if (status == 0 && state != NULL) renew_lease(server, timestamp); return status; @@ -2090,7 +2106,7 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f }; int status; - status = nfs4_call_sync(server, &msg, &args, &res, 0); + status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0); if (status == 0) { memcpy(server->attr_bitmask, res.attr_bitmask, sizeof(server->attr_bitmask)); server->caps &= ~(NFS_CAP_ACLS|NFS_CAP_HARDLINKS| @@ -2160,7 +2176,7 @@ static int _nfs4_lookup_root(struct nfs_server *server, struct nfs_fh *fhandle, }; nfs_fattr_init(info->fattr); - return nfs4_call_sync(server, &msg, &args, &res, 0); + return nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0); } static int nfs4_lookup_root(struct nfs_server *server, struct nfs_fh *fhandle, @@ -2176,15 +2192,43 @@ static int nfs4_lookup_root(struct nfs_server *server, struct nfs_fh *fhandle, return err; } +static int nfs4_lookup_root_sec(struct nfs_server *server, struct nfs_fh *fhandle, + struct nfs_fsinfo *info, rpc_authflavor_t flavor) +{ + struct rpc_auth *auth; + int ret; + + auth = rpcauth_create(flavor, server->client); + if (!auth) { + ret = -EIO; + goto out; + } + ret = nfs4_lookup_root(server, fhandle, info); + if (ret < 0) + ret = -EAGAIN; +out: + return ret; +} + /* * get the file handle for the "/" directory on the server */ static int nfs4_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fsinfo *info) { - int status; + int i, len, status = 0; + rpc_authflavor_t flav_array[NFS_MAX_SECFLAVORS + 2]; + + flav_array[0] = RPC_AUTH_UNIX; + len = gss_mech_list_pseudoflavors(&flav_array[1]); + flav_array[1+len] = RPC_AUTH_NULL; + len += 2; - status = nfs4_lookup_root(server, fhandle, info); + for (i = 0; i < len; i++) { + status = nfs4_lookup_root_sec(server, fhandle, info, flav_array[i]); + if (status == 0) + break; + } if (status == 0) status = nfs4_server_capabilities(server, fhandle); if (status == 0) @@ -2249,7 +2293,7 @@ static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, }; nfs_fattr_init(fattr); - return nfs4_call_sync(server, &msg, &args, &res, 0); + return nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0); } static int nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fattr *fattr) @@ -2309,9 +2353,9 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr, return status; } -static int _nfs4_proc_lookupfh(struct nfs_server *server, const struct nfs_fh *dirfh, - const struct qstr *name, struct nfs_fh *fhandle, - struct nfs_fattr *fattr) +static int _nfs4_proc_lookupfh(struct rpc_clnt *clnt, struct nfs_server *server, + const struct nfs_fh *dirfh, const struct qstr *name, + struct nfs_fh *fhandle, struct nfs_fattr *fattr) { int status; struct nfs4_lookup_arg args = { @@ -2333,7 +2377,7 @@ static int _nfs4_proc_lookupfh(struct nfs_server *server, const struct nfs_fh *d nfs_fattr_init(fattr); dprintk("NFS call lookupfh %s\n", name->name); - status = nfs4_call_sync(server, &msg, &args, &res, 0); + status = nfs4_call_sync(clnt, server, &msg, &args.seq_args, &res.seq_res, 0); dprintk("NFS reply lookupfh: %d\n", status); return status; } @@ -2345,7 +2389,7 @@ static int nfs4_proc_lookupfh(struct nfs_server *server, struct nfs_fh *dirfh, struct nfs4_exception exception = { }; int err; do { - err = _nfs4_proc_lookupfh(server, dirfh, name, fhandle, fattr); + err = _nfs4_proc_lookupfh(server->client, server, dirfh, name, fhandle, fattr); /* FIXME: !!!! */ if (err == -NFS4ERR_MOVED) { err = -EREMOTE; @@ -2356,27 +2400,41 @@ static int nfs4_proc_lookupfh(struct nfs_server *server, struct nfs_fh *dirfh, return err; } -static int _nfs4_proc_lookup(struct inode *dir, const struct qstr *name, - struct nfs_fh *fhandle, struct nfs_fattr *fattr) +static int _nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, + const struct qstr *name, struct nfs_fh *fhandle, + struct nfs_fattr *fattr) { int status; dprintk("NFS call lookup %s\n", name->name); - status = _nfs4_proc_lookupfh(NFS_SERVER(dir), NFS_FH(dir), name, fhandle, fattr); + status = _nfs4_proc_lookupfh(clnt, NFS_SERVER(dir), NFS_FH(dir), name, fhandle, fattr); if (status == -NFS4ERR_MOVED) status = nfs4_get_referral(dir, name, fattr, fhandle); dprintk("NFS reply lookup: %d\n", status); return status; } -static int nfs4_proc_lookup(struct inode *dir, struct qstr *name, struct nfs_fh *fhandle, struct nfs_fattr *fattr) +void nfs_fixup_secinfo_attributes(struct nfs_fattr *fattr, struct nfs_fh *fh) +{ + memset(fh, 0, sizeof(struct nfs_fh)); + fattr->fsid.major = 1; + fattr->valid |= NFS_ATTR_FATTR_TYPE | NFS_ATTR_FATTR_MODE | + NFS_ATTR_FATTR_NLINK | NFS_ATTR_FATTR_FSID | NFS_ATTR_FATTR_MOUNTPOINT; + fattr->mode = S_IFDIR | S_IRUGO | S_IXUGO; + fattr->nlink = 2; +} + +static int nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, struct qstr *name, + struct nfs_fh *fhandle, struct nfs_fattr *fattr) { struct nfs4_exception exception = { }; int err; do { err = nfs4_handle_exception(NFS_SERVER(dir), - _nfs4_proc_lookup(dir, name, fhandle, fattr), + _nfs4_proc_lookup(clnt, dir, name, fhandle, fattr), &exception); + if (err == -EPERM) + nfs_fixup_secinfo_attributes(fattr, fhandle); } while (exception.retry); return err; } @@ -2421,7 +2479,7 @@ static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry if (res.fattr == NULL) return -ENOMEM; - status = nfs4_call_sync(server, &msg, &args, &res, 0); + status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0); if (!status) { entry->mask = 0; if (res.access & NFS4_ACCESS_READ) @@ -2488,7 +2546,7 @@ static int _nfs4_proc_readlink(struct inode *inode, struct page *page, .rpc_resp = &res, }; - return nfs4_call_sync(NFS_SERVER(inode), &msg, &args, &res, 0); + return nfs4_call_sync(NFS_SERVER(inode)->client, NFS_SERVER(inode), &msg, &args.seq_args, &res.seq_res, 0); } static int nfs4_proc_readlink(struct inode *inode, struct page *page, @@ -2577,7 +2635,7 @@ static int _nfs4_proc_remove(struct inode *dir, struct qstr *name) if (res.dir_attr == NULL) goto out; - status = nfs4_call_sync(server, &msg, &args, &res, 1); + status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 1); if (status == 0) { update_changeattr(dir, &res.cinfo); nfs_post_op_update_inode(dir, res.dir_attr); @@ -2678,7 +2736,7 @@ static int _nfs4_proc_rename(struct inode *old_dir, struct qstr *old_name, if (res.old_fattr == NULL || res.new_fattr == NULL) goto out; - status = nfs4_call_sync(server, &msg, &arg, &res, 1); + status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1); if (!status) { update_changeattr(old_dir, &res.old_cinfo); nfs_post_op_update_inode(old_dir, res.old_fattr); @@ -2729,7 +2787,7 @@ static int _nfs4_proc_link(struct inode *inode, struct inode *dir, struct qstr * if (res.fattr == NULL || res.dir_attr == NULL) goto out; - status = nfs4_call_sync(server, &msg, &arg, &res, 1); + status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1); if (!status) { update_changeattr(dir, &res.cinfo); nfs_post_op_update_inode(dir, res.dir_attr); @@ -2792,8 +2850,8 @@ static struct nfs4_createdata *nfs4_alloc_createdata(struct inode *dir, static int nfs4_do_create(struct inode *dir, struct dentry *dentry, struct nfs4_createdata *data) { - int status = nfs4_call_sync(NFS_SERVER(dir), &data->msg, - &data->arg, &data->res, 1); + int status = nfs4_call_sync(NFS_SERVER(dir)->client, NFS_SERVER(dir), &data->msg, + &data->arg.seq_args, &data->res.seq_res, 1); if (status == 0) { update_changeattr(dir, &data->res.dir_cinfo); nfs_post_op_update_inode(dir, data->res.dir_fattr); @@ -2905,7 +2963,7 @@ static int _nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, (unsigned long long)cookie); nfs4_setup_readdir(cookie, NFS_COOKIEVERF(dir), dentry, &args); res.pgbase = args.pgbase; - status = nfs4_call_sync(NFS_SERVER(dir), &msg, &args, &res, 0); + status = nfs4_call_sync(NFS_SERVER(dir)->client, NFS_SERVER(dir), &msg, &args.seq_args, &res.seq_res, 0); if (status >= 0) { memcpy(NFS_COOKIEVERF(dir), res.verifier.data, NFS4_VERIFIER_SIZE); status += args.pgbase; @@ -2997,7 +3055,7 @@ static int _nfs4_proc_statfs(struct nfs_server *server, struct nfs_fh *fhandle, }; nfs_fattr_init(fsstat->fattr); - return nfs4_call_sync(server, &msg, &args, &res, 0); + return nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0); } static int nfs4_proc_statfs(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fsstat *fsstat) @@ -3028,7 +3086,7 @@ static int _nfs4_do_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle, .rpc_resp = &res, }; - return nfs4_call_sync(server, &msg, &args, &res, 0); + return nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0); } static int nfs4_do_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fsinfo *fsinfo) @@ -3073,7 +3131,7 @@ static int _nfs4_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle } nfs_fattr_init(pathconf->fattr); - return nfs4_call_sync(server, &msg, &args, &res, 0); + return nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0); } static int nfs4_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle, @@ -3195,12 +3253,9 @@ static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_messag msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_WRITE]; } -static int nfs4_commit_done(struct rpc_task *task, struct nfs_write_data *data) +static int nfs4_commit_done_cb(struct rpc_task *task, struct nfs_write_data *data) { struct inode *inode = data->inode; - - if (!nfs4_sequence_done(task, &data->res.seq_res)) - return -EAGAIN; if (nfs4_async_handle_error(task, NFS_SERVER(inode), NULL) == -EAGAIN) { nfs_restart_rpc(task, NFS_SERVER(inode)->nfs_client); @@ -3210,11 +3265,24 @@ static int nfs4_commit_done(struct rpc_task *task, struct nfs_write_data *data) return 0; } +static int nfs4_commit_done(struct rpc_task *task, struct nfs_write_data *data) +{ + if (!nfs4_sequence_done(task, &data->res.seq_res)) + return -EAGAIN; + return data->write_done_cb(task, data); +} + static void nfs4_proc_commit_setup(struct nfs_write_data *data, struct rpc_message *msg) { struct nfs_server *server = NFS_SERVER(data->inode); - - data->args.bitmask = server->cache_consistency_bitmask; + + if (data->lseg) { + data->args.bitmask = NULL; + data->res.fattr = NULL; + } else + data->args.bitmask = server->cache_consistency_bitmask; + if (!data->write_done_cb) + data->write_done_cb = nfs4_commit_done_cb; data->res.server = server; msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_COMMIT]; } @@ -3452,7 +3520,7 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu resp_buf = buf; buf_to_pages(buf, buflen, args.acl_pages, &args.acl_pgbase); } - ret = nfs4_call_sync(NFS_SERVER(inode), &msg, &args, &res, 0); + ret = nfs4_call_sync(NFS_SERVER(inode)->client, NFS_SERVER(inode), &msg, &args.seq_args, &res.seq_res, 0); if (ret) goto out_free; if (res.acl_len > args.acl_len) @@ -3527,7 +3595,7 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl if (i < 0) return i; nfs_inode_return_delegation(inode); - ret = nfs4_call_sync(server, &msg, &arg, &res, 1); + ret = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1); /* * Free each page after tx, so the only ref left is @@ -3890,7 +3958,7 @@ static int _nfs4_proc_getlk(struct nfs4_state *state, int cmd, struct file_lock lsp = request->fl_u.nfs4_fl.owner; arg.lock_owner.id = lsp->ls_id.id; arg.lock_owner.s_dev = server->s_dev; - status = nfs4_call_sync(server, &msg, &arg, &res, 1); + status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1); switch (status) { case 0: request->fl_type = F_UNLCK; @@ -4618,12 +4686,46 @@ int nfs4_proc_fs_locations(struct inode *dir, const struct qstr *name, nfs_fattr_init(&fs_locations->fattr); fs_locations->server = server; fs_locations->nlocations = 0; - status = nfs4_call_sync(server, &msg, &args, &res, 0); + status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0); nfs_fixup_referral_attributes(&fs_locations->fattr); dprintk("%s: returned status = %d\n", __func__, status); return status; } +static int _nfs4_proc_secinfo(struct inode *dir, const struct qstr *name, struct nfs4_secinfo_flavors *flavors) +{ + int status; + struct nfs4_secinfo_arg args = { + .dir_fh = NFS_FH(dir), + .name = name, + }; + struct nfs4_secinfo_res res = { + .flavors = flavors, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_SECINFO], + .rpc_argp = &args, + .rpc_resp = &res, + }; + + dprintk("NFS call secinfo %s\n", name->name); + status = nfs4_call_sync(NFS_SERVER(dir)->client, NFS_SERVER(dir), &msg, &args.seq_args, &res.seq_res, 0); + dprintk("NFS reply secinfo: %d\n", status); + return status; +} + +int nfs4_proc_secinfo(struct inode *dir, const struct qstr *name, struct nfs4_secinfo_flavors *flavors) +{ + struct nfs4_exception exception = { }; + int err; + do { + err = nfs4_handle_exception(NFS_SERVER(dir), + _nfs4_proc_secinfo(dir, name, flavors), + &exception); + } while (exception.retry); + return err; +} + #ifdef CONFIG_NFS_V4_1 /* * Check the exchange flags returned by the server for invalid flags, having @@ -5516,8 +5618,6 @@ static void nfs4_layoutget_release(void *calldata) struct nfs4_layoutget *lgp = calldata; dprintk("--> %s\n", __func__); - if (lgp->res.layout.buf != NULL) - free_page((unsigned long) lgp->res.layout.buf); put_nfs_open_context(lgp->args.ctx); kfree(calldata); dprintk("<-- %s\n", __func__); @@ -5549,12 +5649,7 @@ int nfs4_proc_layoutget(struct nfs4_layoutget *lgp) dprintk("--> %s\n", __func__); - lgp->res.layout.buf = (void *)__get_free_page(GFP_NOFS); - if (lgp->res.layout.buf == NULL) { - nfs4_layoutget_release(lgp); - return -ENOMEM; - } - + lgp->res.layoutp = &lgp->args.layout; lgp->res.seq_res.sr_slot = NULL; task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) @@ -5586,7 +5681,7 @@ _nfs4_proc_getdeviceinfo(struct nfs_server *server, struct pnfs_device *pdev) int status; dprintk("--> %s\n", __func__); - status = nfs4_call_sync(server, &msg, &args, &res, 0); + status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0); dprintk("<-- %s status=%d\n", __func__, status); return status; @@ -5606,6 +5701,100 @@ int nfs4_proc_getdeviceinfo(struct nfs_server *server, struct pnfs_device *pdev) } EXPORT_SYMBOL_GPL(nfs4_proc_getdeviceinfo); +static void nfs4_layoutcommit_prepare(struct rpc_task *task, void *calldata) +{ + struct nfs4_layoutcommit_data *data = calldata; + struct nfs_server *server = NFS_SERVER(data->args.inode); + + if (nfs4_setup_sequence(server, &data->args.seq_args, + &data->res.seq_res, 1, task)) + return; + rpc_call_start(task); +} + +static void +nfs4_layoutcommit_done(struct rpc_task *task, void *calldata) +{ + struct nfs4_layoutcommit_data *data = calldata; + struct nfs_server *server = NFS_SERVER(data->args.inode); + + if (!nfs4_sequence_done(task, &data->res.seq_res)) + return; + + switch (task->tk_status) { /* Just ignore these failures */ + case NFS4ERR_DELEG_REVOKED: /* layout was recalled */ + case NFS4ERR_BADIOMODE: /* no IOMODE_RW layout for range */ + case NFS4ERR_BADLAYOUT: /* no layout */ + case NFS4ERR_GRACE: /* loca_recalim always false */ + task->tk_status = 0; + } + + if (nfs4_async_handle_error(task, server, NULL) == -EAGAIN) { + nfs_restart_rpc(task, server->nfs_client); + return; + } + + if (task->tk_status == 0) + nfs_post_op_update_inode_force_wcc(data->args.inode, + data->res.fattr); +} + +static void nfs4_layoutcommit_release(void *calldata) +{ + struct nfs4_layoutcommit_data *data = calldata; + + /* Matched by references in pnfs_set_layoutcommit */ + put_lseg(data->lseg); + put_rpccred(data->cred); + kfree(data); +} + +static const struct rpc_call_ops nfs4_layoutcommit_ops = { + .rpc_call_prepare = nfs4_layoutcommit_prepare, + .rpc_call_done = nfs4_layoutcommit_done, + .rpc_release = nfs4_layoutcommit_release, +}; + +int +nfs4_proc_layoutcommit(struct nfs4_layoutcommit_data *data, bool sync) +{ + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LAYOUTCOMMIT], + .rpc_argp = &data->args, + .rpc_resp = &data->res, + .rpc_cred = data->cred, + }; + struct rpc_task_setup task_setup_data = { + .task = &data->task, + .rpc_client = NFS_CLIENT(data->args.inode), + .rpc_message = &msg, + .callback_ops = &nfs4_layoutcommit_ops, + .callback_data = data, + .flags = RPC_TASK_ASYNC, + }; + struct rpc_task *task; + int status = 0; + + dprintk("NFS: %4d initiating layoutcommit call. sync %d " + "lbw: %llu inode %lu\n", + data->task.tk_pid, sync, + data->args.lastbytewritten, + data->args.inode->i_ino); + + task = rpc_run_task(&task_setup_data); + if (IS_ERR(task)) + return PTR_ERR(task); + if (sync == false) + goto out; + status = nfs4_wait_for_completion_rpc_task(task); + if (status != 0) + goto out; + status = task->tk_status; +out: + dprintk("%s: status %d\n", __func__, status); + rpc_put_task(task); + return status; +} #endif /* CONFIG_NFS_V4_1 */ struct nfs4_state_recovery_ops nfs40_reboot_recovery_ops = { @@ -5741,6 +5930,7 @@ const struct nfs_rpc_ops nfs_v4_clientops = { .close_context = nfs4_close_context, .open_context = nfs4_atomic_open, .init_client = nfs4_init_client, + .secinfo = nfs4_proc_secinfo, }; static const struct xattr_handler nfs4_xattr_nfs4_acl_handler = { diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 0cf560f77884..dddfb5795d7b 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -46,6 +46,7 @@ #include <linux/kdev_t.h> #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/msg_prot.h> +#include <linux/sunrpc/gss_api.h> #include <linux/nfs.h> #include <linux/nfs4.h> #include <linux/nfs_fs.h> @@ -112,7 +113,7 @@ static int nfs4_stat_to_errno(int); #define encode_restorefh_maxsz (op_encode_hdr_maxsz) #define decode_restorefh_maxsz (op_decode_hdr_maxsz) #define encode_fsinfo_maxsz (encode_getattr_maxsz) -#define decode_fsinfo_maxsz (op_decode_hdr_maxsz + 11) +#define decode_fsinfo_maxsz (op_decode_hdr_maxsz + 15) #define encode_renew_maxsz (op_encode_hdr_maxsz + 3) #define decode_renew_maxsz (op_decode_hdr_maxsz) #define encode_setclientid_maxsz \ @@ -253,6 +254,8 @@ static int nfs4_stat_to_errno(int); (encode_getattr_maxsz) #define decode_fs_locations_maxsz \ (0) +#define encode_secinfo_maxsz (op_encode_hdr_maxsz + nfs4_name_maxsz) +#define decode_secinfo_maxsz (op_decode_hdr_maxsz + 4 + (NFS_MAX_SECFLAVORS * (16 + GSS_OID_MAX_LEN))) #if defined(CONFIG_NFS_V4_1) #define NFS4_MAX_MACHINE_NAME_LEN (64) @@ -324,6 +327,18 @@ static int nfs4_stat_to_errno(int); #define decode_layoutget_maxsz (op_decode_hdr_maxsz + 8 + \ decode_stateid_maxsz + \ XDR_QUADLEN(PNFS_LAYOUT_MAXSIZE)) +#define encode_layoutcommit_maxsz (op_encode_hdr_maxsz + \ + 2 /* offset */ + \ + 2 /* length */ + \ + 1 /* reclaim */ + \ + encode_stateid_maxsz + \ + 1 /* new offset (true) */ + \ + 2 /* last byte written */ + \ + 1 /* nt_timechanged (false) */ + \ + 1 /* layoutupdate4 layout type */ + \ + 1 /* NULL filelayout layoutupdate4 payload */) +#define decode_layoutcommit_maxsz (op_decode_hdr_maxsz + 3) + #else /* CONFIG_NFS_V4_1 */ #define encode_sequence_maxsz 0 #define decode_sequence_maxsz 0 @@ -676,6 +691,14 @@ static int nfs4_stat_to_errno(int); decode_putfh_maxsz + \ decode_lookup_maxsz + \ decode_fs_locations_maxsz) +#define NFS4_enc_secinfo_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_secinfo_maxsz) +#define NFS4_dec_secinfo_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_secinfo_maxsz) #if defined(CONFIG_NFS_V4_1) #define NFS4_enc_exchange_id_sz \ (compound_encode_hdr_maxsz + \ @@ -727,6 +750,17 @@ static int nfs4_stat_to_errno(int); decode_sequence_maxsz + \ decode_putfh_maxsz + \ decode_layoutget_maxsz) +#define NFS4_enc_layoutcommit_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz +\ + encode_putfh_maxsz + \ + encode_layoutcommit_maxsz + \ + encode_getattr_maxsz) +#define NFS4_dec_layoutcommit_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_layoutcommit_maxsz + \ + decode_getattr_maxsz) + const u32 nfs41_maxwrite_overhead = ((RPC_MAX_HEADER_WITH_AUTH + compound_encode_hdr_maxsz + @@ -1620,6 +1654,18 @@ static void encode_delegreturn(struct xdr_stream *xdr, const nfs4_stateid *state hdr->replen += decode_delegreturn_maxsz; } +static void encode_secinfo(struct xdr_stream *xdr, const struct qstr *name, struct compound_hdr *hdr) +{ + int len = name->len; + __be32 *p; + + p = reserve_space(xdr, 8 + len); + *p++ = cpu_to_be32(OP_SECINFO); + xdr_encode_opaque(p, name->name, len); + hdr->nops++; + hdr->replen += decode_secinfo_maxsz; +} + #if defined(CONFIG_NFS_V4_1) /* NFSv4.1 operations */ static void encode_exchange_id(struct xdr_stream *xdr, @@ -1816,6 +1862,34 @@ encode_layoutget(struct xdr_stream *xdr, hdr->nops++; hdr->replen += decode_layoutget_maxsz; } + +static int +encode_layoutcommit(struct xdr_stream *xdr, + const struct nfs4_layoutcommit_args *args, + struct compound_hdr *hdr) +{ + __be32 *p; + + dprintk("%s: lbw: %llu type: %d\n", __func__, args->lastbytewritten, + NFS_SERVER(args->inode)->pnfs_curr_ld->id); + + p = reserve_space(xdr, 48 + NFS4_STATEID_SIZE); + *p++ = cpu_to_be32(OP_LAYOUTCOMMIT); + /* Only whole file layouts */ + p = xdr_encode_hyper(p, 0); /* offset */ + p = xdr_encode_hyper(p, NFS4_MAX_UINT64); /* length */ + *p++ = cpu_to_be32(0); /* reclaim */ + p = xdr_encode_opaque_fixed(p, args->stateid.data, NFS4_STATEID_SIZE); + *p++ = cpu_to_be32(1); /* newoffset = TRUE */ + p = xdr_encode_hyper(p, args->lastbytewritten); + *p++ = cpu_to_be32(0); /* Never send time_modify_changed */ + *p++ = cpu_to_be32(NFS_SERVER(args->inode)->pnfs_curr_ld->id);/* type */ + *p++ = cpu_to_be32(0); /* no file layout payload */ + + hdr->nops++; + hdr->replen += decode_layoutcommit_maxsz; + return 0; +} #endif /* CONFIG_NFS_V4_1 */ /* @@ -2294,7 +2368,8 @@ static void nfs4_xdr_enc_commit(struct rpc_rqst *req, struct xdr_stream *xdr, encode_sequence(xdr, &args->seq_args, &hdr); encode_putfh(xdr, args->fh, &hdr); encode_commit(xdr, args, &hdr); - encode_getfattr(xdr, args->bitmask, &hdr); + if (args->bitmask) + encode_getfattr(xdr, args->bitmask, &hdr); encode_nops(&hdr); } @@ -2465,6 +2540,24 @@ static void nfs4_xdr_enc_fs_locations(struct rpc_rqst *req, encode_nops(&hdr); } +/* + * Encode SECINFO request + */ +static void nfs4_xdr_enc_secinfo(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs4_secinfo_arg *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->dir_fh, &hdr); + encode_secinfo(xdr, args->name, &hdr); + encode_nops(&hdr); +} + #if defined(CONFIG_NFS_V4_1) /* * EXCHANGE_ID request @@ -2604,8 +2697,32 @@ static void nfs4_xdr_enc_layoutget(struct rpc_rqst *req, encode_sequence(xdr, &args->seq_args, &hdr); encode_putfh(xdr, NFS_FH(args->inode), &hdr); encode_layoutget(xdr, args, &hdr); + + xdr_inline_pages(&req->rq_rcv_buf, hdr.replen << 2, + args->layout.pages, 0, args->layout.pglen); + encode_nops(&hdr); } + +/* + * Encode LAYOUTCOMMIT request + */ +static int nfs4_xdr_enc_layoutcommit(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs4_layoutcommit_args *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, NFS_FH(args->inode), &hdr); + encode_layoutcommit(xdr, args, &hdr); + encode_getfattr(xdr, args->bitmask, &hdr); + encode_nops(&hdr); + return 0; +} #endif /* CONFIG_NFS_V4_1 */ static void print_overflow_msg(const char *func, const struct xdr_stream *xdr) @@ -2925,6 +3042,7 @@ static int decode_attr_error(struct xdr_stream *xdr, uint32_t *bitmap) if (unlikely(!p)) goto out_overflow; bitmap[0] &= ~FATTR4_WORD0_RDATTR_ERROR; + return -be32_to_cpup(p); } return 0; out_overflow: @@ -3912,6 +4030,10 @@ static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap, fattr->valid |= status; status = decode_attr_error(xdr, bitmap); + if (status == -NFS4ERR_WRONGSEC) { + nfs_fixup_secinfo_attributes(fattr, fh); + status = 0; + } if (status < 0) goto xdr_error; @@ -4680,6 +4802,73 @@ static int decode_delegreturn(struct xdr_stream *xdr) return decode_op_hdr(xdr, OP_DELEGRETURN); } +static int decode_secinfo_gss(struct xdr_stream *xdr, struct nfs4_secinfo_flavor *flavor) +{ + __be32 *p; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + flavor->gss.sec_oid4.len = be32_to_cpup(p); + if (flavor->gss.sec_oid4.len > GSS_OID_MAX_LEN) + goto out_err; + + p = xdr_inline_decode(xdr, flavor->gss.sec_oid4.len); + if (unlikely(!p)) + goto out_overflow; + memcpy(flavor->gss.sec_oid4.data, p, flavor->gss.sec_oid4.len); + + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + flavor->gss.qop4 = be32_to_cpup(p++); + flavor->gss.service = be32_to_cpup(p); + + return 0; + +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +out_err: + return -EINVAL; +} + +static int decode_secinfo(struct xdr_stream *xdr, struct nfs4_secinfo_res *res) +{ + struct nfs4_secinfo_flavor *sec_flavor; + int status; + __be32 *p; + int i; + + status = decode_op_hdr(xdr, OP_SECINFO); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + res->flavors->num_flavors = be32_to_cpup(p); + + for (i = 0; i < res->flavors->num_flavors; i++) { + sec_flavor = &res->flavors->flavors[i]; + if ((char *)&sec_flavor[1] - (char *)res > PAGE_SIZE) + break; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + sec_flavor->flavor = be32_to_cpup(p); + + if (sec_flavor->flavor == RPC_AUTH_GSS) { + if (decode_secinfo_gss(xdr, sec_flavor)) + break; + } + } + + return 0; + +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + #if defined(CONFIG_NFS_V4_1) static int decode_exchange_id(struct xdr_stream *xdr, struct nfs41_exchange_id_res *res) @@ -4950,6 +5139,9 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req, __be32 *p; int status; u32 layout_count; + struct xdr_buf *rcvbuf = &req->rq_rcv_buf; + struct kvec *iov = rcvbuf->head; + u32 hdrlen, recvd; status = decode_op_hdr(xdr, OP_LAYOUTGET); if (status) @@ -4966,17 +5158,14 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req, return -EINVAL; } - p = xdr_inline_decode(xdr, 24); + p = xdr_inline_decode(xdr, 28); if (unlikely(!p)) goto out_overflow; p = xdr_decode_hyper(p, &res->range.offset); p = xdr_decode_hyper(p, &res->range.length); res->range.iomode = be32_to_cpup(p++); res->type = be32_to_cpup(p++); - - status = decode_opaque_inline(xdr, &res->layout.len, (char **)&p); - if (unlikely(status)) - return status; + res->layoutp->len = be32_to_cpup(p); dprintk("%s roff:%lu rlen:%lu riomode:%d, lo_type:0x%x, lo.len:%d\n", __func__, @@ -4984,12 +5173,18 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req, (unsigned long)res->range.length, res->range.iomode, res->type, - res->layout.len); + res->layoutp->len); - /* nfs4_proc_layoutget allocated a single page */ - if (res->layout.len > PAGE_SIZE) - return -ENOMEM; - memcpy(res->layout.buf, p, res->layout.len); + hdrlen = (u8 *) xdr->p - (u8 *) iov->iov_base; + recvd = req->rq_rcv_buf.len - hdrlen; + if (res->layoutp->len > recvd) { + dprintk("NFS: server cheating in layoutget reply: " + "layout len %u > recvd %u\n", + res->layoutp->len, recvd); + return -EINVAL; + } + + xdr_read_pages(xdr, res->layoutp->len); if (layout_count > 1) { /* We only handle a length one array at the moment. Any @@ -5006,6 +5201,35 @@ out_overflow: print_overflow_msg(__func__, xdr); return -EIO; } + +static int decode_layoutcommit(struct xdr_stream *xdr, + struct rpc_rqst *req, + struct nfs4_layoutcommit_res *res) +{ + __be32 *p; + __u32 sizechanged; + int status; + + status = decode_op_hdr(xdr, OP_LAYOUTCOMMIT); + if (status) + return status; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + sizechanged = be32_to_cpup(p); + + if (sizechanged) { + /* throw away new size */ + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + } + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} #endif /* CONFIG_NFS_V4_1 */ /* @@ -5723,8 +5947,9 @@ static int nfs4_xdr_dec_commit(struct rpc_rqst *rqstp, struct xdr_stream *xdr, status = decode_commit(xdr, res); if (status) goto out; - decode_getfattr(xdr, res->fattr, res->server, - !RPC_IS_ASYNC(rqstp->rq_task)); + if (res->fattr) + decode_getfattr(xdr, res->fattr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)); out: return status; } @@ -5919,6 +6144,32 @@ out: return status; } +/* + * Decode SECINFO response + */ +static int nfs4_xdr_dec_secinfo(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs4_secinfo_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_secinfo(xdr, res); + if (status) + goto out; +out: + return status; +} + #if defined(CONFIG_NFS_V4_1) /* * Decode EXCHANGE_ID response @@ -6066,6 +6317,34 @@ static int nfs4_xdr_dec_layoutget(struct rpc_rqst *rqstp, out: return status; } + +/* + * Decode LAYOUTCOMMIT response + */ +static int nfs4_xdr_dec_layoutcommit(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs4_layoutcommit_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_layoutcommit(xdr, rqstp, res); + if (status) + goto out; + decode_getfattr(xdr, res->fattr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)); +out: + return status; +} #endif /* CONFIG_NFS_V4_1 */ /** @@ -6180,10 +6459,6 @@ static struct { { NFS4ERR_SYMLINK, -ELOOP }, { NFS4ERR_OP_ILLEGAL, -EOPNOTSUPP }, { NFS4ERR_DEADLOCK, -EDEADLK }, - { NFS4ERR_WRONGSEC, -EPERM }, /* FIXME: this needs - * to be handled by a - * middle-layer. - */ { -1, -EIO } }; @@ -6258,6 +6533,7 @@ struct rpc_procinfo nfs4_procedures[] = { PROC(SETACL, enc_setacl, dec_setacl), PROC(FS_LOCATIONS, enc_fs_locations, dec_fs_locations), PROC(RELEASE_LOCKOWNER, enc_release_lockowner, dec_release_lockowner), + PROC(SECINFO, enc_secinfo, dec_secinfo), #if defined(CONFIG_NFS_V4_1) PROC(EXCHANGE_ID, enc_exchange_id, dec_exchange_id), PROC(CREATE_SESSION, enc_create_session, dec_create_session), @@ -6267,6 +6543,7 @@ struct rpc_procinfo nfs4_procedures[] = { PROC(RECLAIM_COMPLETE, enc_reclaim_complete, dec_reclaim_complete), PROC(GETDEVICEINFO, enc_getdeviceinfo, dec_getdeviceinfo), PROC(LAYOUTGET, enc_layoutget, dec_layoutget), + PROC(LAYOUTCOMMIT, enc_layoutcommit, dec_layoutcommit), #endif /* CONFIG_NFS_V4_1 */ }; diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 23e794410669..87a593c2b055 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -223,6 +223,7 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc, desc->pg_count = 0; desc->pg_bsize = bsize; desc->pg_base = 0; + desc->pg_moreio = 0; desc->pg_inode = inode; desc->pg_doio = doio; desc->pg_ioflags = io_flags; @@ -335,9 +336,11 @@ int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, struct nfs_page *req) { while (!nfs_pageio_do_add_request(desc, req)) { + desc->pg_moreio = 1; nfs_pageio_doio(desc); if (desc->pg_error < 0) return 0; + desc->pg_moreio = 0; } return 1; } @@ -395,6 +398,7 @@ int nfs_scan_list(struct nfs_inode *nfsi, pgoff_t idx_end; int found, i; int res; + struct list_head *list; res = 0; if (npages == 0) @@ -415,10 +419,10 @@ int nfs_scan_list(struct nfs_inode *nfsi, idx_start = req->wb_index + 1; if (nfs_set_page_tag_locked(req)) { kref_get(&req->wb_kref); - nfs_list_remove_request(req); radix_tree_tag_clear(&nfsi->nfs_page_tree, req->wb_index, tag); - nfs_list_add_request(req, dst); + list = pnfs_choose_commit_list(req, dst); + nfs_list_add_request(req, list); res++; if (res == INT_MAX) goto out; diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index f38813a0a295..d9ab97269ce6 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -259,6 +259,7 @@ put_lseg(struct pnfs_layout_segment *lseg) pnfs_free_lseg_list(&free_me); } } +EXPORT_SYMBOL_GPL(put_lseg); static bool should_free_lseg(u32 lseg_iomode, u32 recall_iomode) @@ -471,6 +472,9 @@ send_layoutget(struct pnfs_layout_hdr *lo, struct nfs_server *server = NFS_SERVER(ino); struct nfs4_layoutget *lgp; struct pnfs_layout_segment *lseg = NULL; + struct page **pages = NULL; + int i; + u32 max_resp_sz, max_pages; dprintk("--> %s\n", __func__); @@ -478,6 +482,21 @@ send_layoutget(struct pnfs_layout_hdr *lo, lgp = kzalloc(sizeof(*lgp), GFP_KERNEL); if (lgp == NULL) return NULL; + + /* allocate pages for xdr post processing */ + max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz; + max_pages = max_resp_sz >> PAGE_SHIFT; + + pages = kzalloc(max_pages * sizeof(struct page *), GFP_KERNEL); + if (!pages) + goto out_err_free; + + for (i = 0; i < max_pages; i++) { + pages[i] = alloc_page(GFP_KERNEL); + if (!pages[i]) + goto out_err_free; + } + lgp->args.minlength = NFS4_MAX_UINT64; lgp->args.maxcount = PNFS_LAYOUT_MAXSIZE; lgp->args.range.iomode = iomode; @@ -486,6 +505,8 @@ send_layoutget(struct pnfs_layout_hdr *lo, lgp->args.type = server->pnfs_curr_ld->id; lgp->args.inode = ino; lgp->args.ctx = get_nfs_open_context(ctx); + lgp->args.layout.pages = pages; + lgp->args.layout.pglen = max_pages * PAGE_SIZE; lgp->lsegpp = &lseg; /* Synchronously retrieve layout information from server and @@ -496,7 +517,26 @@ send_layoutget(struct pnfs_layout_hdr *lo, /* remember that LAYOUTGET failed and suspend trying */ set_bit(lo_fail_bit(iomode), &lo->plh_flags); } + + /* free xdr pages */ + for (i = 0; i < max_pages; i++) + __free_page(pages[i]); + kfree(pages); + return lseg; + +out_err_free: + /* free any allocated xdr pages, lgp as it's not used */ + if (pages) { + for (i = 0; i < max_pages; i++) { + if (!pages[i]) + break; + __free_page(pages[i]); + } + kfree(pages); + } + kfree(lgp); + return NULL; } bool pnfs_roc(struct inode *ino) @@ -945,3 +985,105 @@ pnfs_try_to_read_data(struct nfs_read_data *rdata, dprintk("%s End (trypnfs:%d)\n", __func__, trypnfs); return trypnfs; } + +/* + * Currently there is only one (whole file) write lseg. + */ +static struct pnfs_layout_segment *pnfs_list_write_lseg(struct inode *inode) +{ + struct pnfs_layout_segment *lseg, *rv = NULL; + + list_for_each_entry(lseg, &NFS_I(inode)->layout->plh_segs, pls_list) + if (lseg->pls_range.iomode == IOMODE_RW) + rv = lseg; + return rv; +} + +void +pnfs_set_layoutcommit(struct nfs_write_data *wdata) +{ + struct nfs_inode *nfsi = NFS_I(wdata->inode); + loff_t end_pos = wdata->args.offset + wdata->res.count; + + spin_lock(&nfsi->vfs_inode.i_lock); + if (!test_and_set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) { + /* references matched in nfs4_layoutcommit_release */ + get_lseg(wdata->lseg); + wdata->lseg->pls_lc_cred = + get_rpccred(wdata->args.context->state->owner->so_cred); + mark_inode_dirty_sync(wdata->inode); + dprintk("%s: Set layoutcommit for inode %lu ", + __func__, wdata->inode->i_ino); + } + if (end_pos > wdata->lseg->pls_end_pos) + wdata->lseg->pls_end_pos = end_pos; + spin_unlock(&nfsi->vfs_inode.i_lock); +} +EXPORT_SYMBOL_GPL(pnfs_set_layoutcommit); + +/* + * For the LAYOUT4_NFSV4_1_FILES layout type, NFS_DATA_SYNC WRITEs and + * NFS_UNSTABLE WRITEs with a COMMIT to data servers must store enough + * data to disk to allow the server to recover the data if it crashes. + * LAYOUTCOMMIT is only needed when the NFL4_UFLG_COMMIT_THRU_MDS flag + * is off, and a COMMIT is sent to a data server, or + * if WRITEs to a data server return NFS_DATA_SYNC. + */ +int +pnfs_layoutcommit_inode(struct inode *inode, bool sync) +{ + struct nfs4_layoutcommit_data *data; + struct nfs_inode *nfsi = NFS_I(inode); + struct pnfs_layout_segment *lseg; + struct rpc_cred *cred; + loff_t end_pos; + int status = 0; + + dprintk("--> %s inode %lu\n", __func__, inode->i_ino); + + if (!test_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) + return 0; + + /* Note kzalloc ensures data->res.seq_res.sr_slot == NULL */ + data = kzalloc(sizeof(*data), GFP_NOFS); + if (!data) { + mark_inode_dirty_sync(inode); + status = -ENOMEM; + goto out; + } + + spin_lock(&inode->i_lock); + if (!test_and_clear_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) { + spin_unlock(&inode->i_lock); + kfree(data); + goto out; + } + /* + * Currently only one (whole file) write lseg which is referenced + * in pnfs_set_layoutcommit and will be found. + */ + lseg = pnfs_list_write_lseg(inode); + + end_pos = lseg->pls_end_pos; + cred = lseg->pls_lc_cred; + lseg->pls_end_pos = 0; + lseg->pls_lc_cred = NULL; + + memcpy(&data->args.stateid.data, nfsi->layout->plh_stateid.data, + sizeof(nfsi->layout->plh_stateid.data)); + spin_unlock(&inode->i_lock); + + data->args.inode = inode; + data->lseg = lseg; + data->cred = cred; + nfs_fattr_init(&data->fattr); + data->args.bitmask = NFS_SERVER(inode)->cache_consistency_bitmask; + data->res.fattr = &data->fattr; + data->args.lastbytewritten = end_pos - 1; + data->res.server = NFS_SERVER(inode); + + status = nfs4_proc_layoutcommit(data, sync); +out: + dprintk("<-- %s status %d\n", __func__, status); + return status; +} diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 6380b9405bcd..bc4827202e7a 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -43,6 +43,8 @@ struct pnfs_layout_segment { atomic_t pls_refcount; unsigned long pls_flags; struct pnfs_layout_hdr *pls_layout; + struct rpc_cred *pls_lc_cred; /* LAYOUTCOMMIT credential */ + loff_t pls_end_pos; /* LAYOUTCOMMIT write end */ }; enum pnfs_try_status { @@ -74,6 +76,13 @@ struct pnfs_layoutdriver_type { /* test for nfs page cache coalescing */ int (*pg_test)(struct nfs_pageio_descriptor *, struct nfs_page *, struct nfs_page *); + /* Returns true if layoutdriver wants to divert this request to + * driver's commit routine. + */ + bool (*mark_pnfs_commit)(struct pnfs_layout_segment *lseg); + struct list_head * (*choose_commit_list) (struct nfs_page *req); + int (*commit_pagelist)(struct inode *inode, struct list_head *mds_pages, int how); + /* * Return PNFS_ATTEMPTED to indicate the layout code has attempted * I/O, else return PNFS_NOT_ATTEMPTED to fall back to normal NFS @@ -100,7 +109,6 @@ struct pnfs_device { unsigned int layout_type; unsigned int mincount; struct page **pages; - void *area; unsigned int pgbase; unsigned int pglen; }; @@ -145,7 +153,8 @@ bool pnfs_roc(struct inode *ino); void pnfs_roc_release(struct inode *ino); void pnfs_roc_set_barrier(struct inode *ino, u32 barrier); bool pnfs_roc_drain(struct inode *ino, u32 *barrier); - +void pnfs_set_layoutcommit(struct nfs_write_data *wdata); +int pnfs_layoutcommit_inode(struct inode *inode, bool sync); static inline int lo_fail_bit(u32 iomode) { @@ -169,6 +178,51 @@ static inline int pnfs_enabled_sb(struct nfs_server *nfss) return nfss->pnfs_curr_ld != NULL; } +static inline void +pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg) +{ + if (lseg) { + struct pnfs_layoutdriver_type *ld; + + ld = NFS_SERVER(req->wb_page->mapping->host)->pnfs_curr_ld; + if (ld->mark_pnfs_commit && ld->mark_pnfs_commit(lseg)) { + set_bit(PG_PNFS_COMMIT, &req->wb_flags); + req->wb_commit_lseg = get_lseg(lseg); + } + } +} + +static inline int +pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how) +{ + if (!test_and_clear_bit(NFS_INO_PNFS_COMMIT, &NFS_I(inode)->flags)) + return PNFS_NOT_ATTEMPTED; + return NFS_SERVER(inode)->pnfs_curr_ld->commit_pagelist(inode, mds_pages, how); +} + +static inline struct list_head * +pnfs_choose_commit_list(struct nfs_page *req, struct list_head *mds) +{ + struct list_head *rv; + + if (test_and_clear_bit(PG_PNFS_COMMIT, &req->wb_flags)) { + struct inode *inode = req->wb_commit_lseg->pls_layout->plh_inode; + + set_bit(NFS_INO_PNFS_COMMIT, &NFS_I(inode)->flags); + rv = NFS_SERVER(inode)->pnfs_curr_ld->choose_commit_list(req); + /* matched by ref taken when PG_PNFS_COMMIT is set */ + put_lseg(req->wb_commit_lseg); + } else + rv = mds; + return rv; +} + +static inline void pnfs_clear_request_commit(struct nfs_page *req) +{ + if (test_and_clear_bit(PG_PNFS_COMMIT, &req->wb_flags)) + put_lseg(req->wb_commit_lseg); +} + #else /* CONFIG_NFS_V4_1 */ static inline void pnfs_destroy_all_layouts(struct nfs_client *clp) @@ -252,6 +306,31 @@ pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *ino) pgio->pg_test = NULL; } +static inline void +pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg) +{ +} + +static inline int +pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how) +{ + return PNFS_NOT_ATTEMPTED; +} + +static inline struct list_head * +pnfs_choose_commit_list(struct nfs_page *req, struct list_head *mds) +{ + return mds; +} + +static inline void pnfs_clear_request_commit(struct nfs_page *req) +{ +} + +static inline int pnfs_layoutcommit_inode(struct inode *inode, bool sync) +{ + return 0; +} #endif /* CONFIG_NFS_V4_1 */ #endif /* FS_NFS_PNFS_H */ diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index b8ec170f2a0f..ac40b8535d7e 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -177,7 +177,7 @@ nfs_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr, } static int -nfs_proc_lookup(struct inode *dir, struct qstr *name, +nfs_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, struct qstr *name, struct nfs_fh *fhandle, struct nfs_fattr *fattr) { struct nfs_diropargs arg = { diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 47a3ad63e0d5..85d75254328e 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -59,6 +59,7 @@ struct nfs_write_data *nfs_commitdata_alloc(void) } return p; } +EXPORT_SYMBOL_GPL(nfs_commitdata_alloc); void nfs_commit_free(struct nfs_write_data *p) { @@ -66,6 +67,7 @@ void nfs_commit_free(struct nfs_write_data *p) kfree(p->pagevec); mempool_free(p, nfs_commit_mempool); } +EXPORT_SYMBOL_GPL(nfs_commit_free); struct nfs_write_data *nfs_writedata_alloc(unsigned int pagecount) { @@ -179,8 +181,8 @@ static int wb_priority(struct writeback_control *wbc) if (wbc->for_reclaim) return FLUSH_HIGHPRI | FLUSH_STABLE; if (wbc->for_kupdate || wbc->for_background) - return FLUSH_LOWPRI; - return 0; + return FLUSH_LOWPRI | FLUSH_COND_STABLE; + return FLUSH_COND_STABLE; } /* @@ -441,7 +443,7 @@ nfs_mark_request_dirty(struct nfs_page *req) * Add a request to the inode's commit list. */ static void -nfs_mark_request_commit(struct nfs_page *req) +nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg) { struct inode *inode = req->wb_context->path.dentry->d_inode; struct nfs_inode *nfsi = NFS_I(inode); @@ -453,6 +455,7 @@ nfs_mark_request_commit(struct nfs_page *req) NFS_PAGE_TAG_COMMIT); nfsi->ncommit++; spin_unlock(&inode->i_lock); + pnfs_mark_request_commit(req, lseg); inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS); inc_bdi_stat(req->wb_page->mapping->backing_dev_info, BDI_RECLAIMABLE); __mark_inode_dirty(inode, I_DIRTY_DATASYNC); @@ -474,14 +477,18 @@ nfs_clear_request_commit(struct nfs_page *req) static inline int nfs_write_need_commit(struct nfs_write_data *data) { - return data->verf.committed != NFS_FILE_SYNC; + if (data->verf.committed == NFS_DATA_SYNC) + return data->lseg == NULL; + else + return data->verf.committed != NFS_FILE_SYNC; } static inline -int nfs_reschedule_unstable_write(struct nfs_page *req) +int nfs_reschedule_unstable_write(struct nfs_page *req, + struct nfs_write_data *data) { if (test_and_clear_bit(PG_NEED_COMMIT, &req->wb_flags)) { - nfs_mark_request_commit(req); + nfs_mark_request_commit(req, data->lseg); return 1; } if (test_and_clear_bit(PG_NEED_RESCHED, &req->wb_flags)) { @@ -492,7 +499,7 @@ int nfs_reschedule_unstable_write(struct nfs_page *req) } #else static inline void -nfs_mark_request_commit(struct nfs_page *req) +nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg) { } @@ -509,7 +516,8 @@ int nfs_write_need_commit(struct nfs_write_data *data) } static inline -int nfs_reschedule_unstable_write(struct nfs_page *req) +int nfs_reschedule_unstable_write(struct nfs_page *req, + struct nfs_write_data *data) { return 0; } @@ -612,9 +620,11 @@ static struct nfs_page *nfs_try_to_update_request(struct inode *inode, } if (nfs_clear_request_commit(req) && - radix_tree_tag_clear(&NFS_I(inode)->nfs_page_tree, - req->wb_index, NFS_PAGE_TAG_COMMIT) != NULL) + radix_tree_tag_clear(&NFS_I(inode)->nfs_page_tree, + req->wb_index, NFS_PAGE_TAG_COMMIT) != NULL) { NFS_I(inode)->ncommit--; + pnfs_clear_request_commit(req); + } /* Okay, the request matches. Update the region */ if (offset < req->wb_offset) { @@ -762,11 +772,12 @@ int nfs_updatepage(struct file *file, struct page *page, return status; } -static void nfs_writepage_release(struct nfs_page *req) +static void nfs_writepage_release(struct nfs_page *req, + struct nfs_write_data *data) { struct page *page = req->wb_page; - if (PageError(req->wb_page) || !nfs_reschedule_unstable_write(req)) + if (PageError(req->wb_page) || !nfs_reschedule_unstable_write(req, data)) nfs_inode_remove_request(req); nfs_clear_page_tag_locked(req); nfs_end_page_writeback(page); @@ -863,7 +874,7 @@ static int nfs_write_rpcsetup(struct nfs_page *req, data->args.context = get_nfs_open_context(req->wb_context); data->args.lock_context = req->wb_lock_context; data->args.stable = NFS_UNSTABLE; - if (how & FLUSH_STABLE) { + if (how & (FLUSH_STABLE | FLUSH_COND_STABLE)) { data->args.stable = NFS_DATA_SYNC; if (!nfs_need_commit(NFS_I(inode))) data->args.stable = NFS_FILE_SYNC; @@ -912,6 +923,12 @@ static int nfs_flush_multi(struct nfs_pageio_descriptor *desc) nfs_list_remove_request(req); + if ((desc->pg_ioflags & FLUSH_COND_STABLE) && + (desc->pg_moreio || NFS_I(desc->pg_inode)->ncommit || + desc->pg_count > wsize)) + desc->pg_ioflags &= ~FLUSH_COND_STABLE; + + nbytes = desc->pg_count; do { size_t len = min(nbytes, wsize); @@ -1002,6 +1019,10 @@ static int nfs_flush_one(struct nfs_pageio_descriptor *desc) if ((!lseg) && list_is_singular(&data->pages)) lseg = pnfs_update_layout(desc->pg_inode, req->wb_context, IOMODE_RW); + if ((desc->pg_ioflags & FLUSH_COND_STABLE) && + (desc->pg_moreio || NFS_I(desc->pg_inode)->ncommit)) + desc->pg_ioflags &= ~FLUSH_COND_STABLE; + /* Set up the argument struct */ ret = nfs_write_rpcsetup(req, data, &nfs_write_full_ops, desc->pg_count, 0, lseg, desc->pg_ioflags); out: @@ -1074,7 +1095,7 @@ static void nfs_writeback_release_partial(void *calldata) out: if (atomic_dec_and_test(&req->wb_complete)) - nfs_writepage_release(req); + nfs_writepage_release(req, data); nfs_writedata_release(calldata); } @@ -1141,7 +1162,7 @@ static void nfs_writeback_release_full(void *calldata) if (nfs_write_need_commit(data)) { memcpy(&req->wb_verf, &data->verf, sizeof(req->wb_verf)); - nfs_mark_request_commit(req); + nfs_mark_request_commit(req, data->lseg); dprintk(" marked for commit\n"); goto next; } @@ -1251,57 +1272,82 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data) #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4) static int nfs_commit_set_lock(struct nfs_inode *nfsi, int may_wait) { + int ret; + if (!test_and_set_bit(NFS_INO_COMMIT, &nfsi->flags)) return 1; - if (may_wait && !out_of_line_wait_on_bit_lock(&nfsi->flags, - NFS_INO_COMMIT, nfs_wait_bit_killable, - TASK_KILLABLE)) - return 1; - return 0; + if (!may_wait) + return 0; + ret = out_of_line_wait_on_bit_lock(&nfsi->flags, + NFS_INO_COMMIT, + nfs_wait_bit_killable, + TASK_KILLABLE); + return (ret < 0) ? ret : 1; } -static void nfs_commit_clear_lock(struct nfs_inode *nfsi) +void nfs_commit_clear_lock(struct nfs_inode *nfsi) { clear_bit(NFS_INO_COMMIT, &nfsi->flags); smp_mb__after_clear_bit(); wake_up_bit(&nfsi->flags, NFS_INO_COMMIT); } +EXPORT_SYMBOL_GPL(nfs_commit_clear_lock); - -static void nfs_commitdata_release(void *data) +void nfs_commitdata_release(void *data) { struct nfs_write_data *wdata = data; + put_lseg(wdata->lseg); put_nfs_open_context(wdata->args.context); nfs_commit_free(wdata); } +EXPORT_SYMBOL_GPL(nfs_commitdata_release); -/* - * Set up the argument/result storage required for the RPC call. - */ -static int nfs_commit_rpcsetup(struct list_head *head, - struct nfs_write_data *data, - int how) +int nfs_initiate_commit(struct nfs_write_data *data, struct rpc_clnt *clnt, + const struct rpc_call_ops *call_ops, + int how) { - struct nfs_page *first = nfs_list_entry(head->next); - struct inode *inode = first->wb_context->path.dentry->d_inode; - int priority = flush_task_priority(how); struct rpc_task *task; + int priority = flush_task_priority(how); struct rpc_message msg = { .rpc_argp = &data->args, .rpc_resp = &data->res, - .rpc_cred = first->wb_context->cred, + .rpc_cred = data->cred, }; struct rpc_task_setup task_setup_data = { .task = &data->task, - .rpc_client = NFS_CLIENT(inode), + .rpc_client = clnt, .rpc_message = &msg, - .callback_ops = &nfs_commit_ops, + .callback_ops = call_ops, .callback_data = data, .workqueue = nfsiod_workqueue, .flags = RPC_TASK_ASYNC, .priority = priority, }; + /* Set up the initial task struct. */ + NFS_PROTO(data->inode)->commit_setup(data, &msg); + + dprintk("NFS: %5u initiated commit call\n", data->task.tk_pid); + + task = rpc_run_task(&task_setup_data); + if (IS_ERR(task)) + return PTR_ERR(task); + if (how & FLUSH_SYNC) + rpc_wait_for_completion_task(task); + rpc_put_task(task); + return 0; +} +EXPORT_SYMBOL_GPL(nfs_initiate_commit); + +/* + * Set up the argument/result storage required for the RPC call. + */ +void nfs_init_commit(struct nfs_write_data *data, + struct list_head *head, + struct pnfs_layout_segment *lseg) +{ + struct nfs_page *first = nfs_list_entry(head->next); + struct inode *inode = first->wb_context->path.dentry->d_inode; /* Set up the RPC argument and reply structs * NB: take care not to mess about with data->commit et al. */ @@ -1309,7 +1355,9 @@ static int nfs_commit_rpcsetup(struct list_head *head, list_splice_init(head, &data->pages); data->inode = inode; - data->cred = msg.rpc_cred; + data->cred = first->wb_context->cred; + data->lseg = lseg; /* reference transferred */ + data->mds_ops = &nfs_commit_ops; data->args.fh = NFS_FH(data->inode); /* Note: we always request a commit of the entire inode */ @@ -1320,20 +1368,25 @@ static int nfs_commit_rpcsetup(struct list_head *head, data->res.fattr = &data->fattr; data->res.verf = &data->verf; nfs_fattr_init(&data->fattr); +} +EXPORT_SYMBOL_GPL(nfs_init_commit); - /* Set up the initial task struct. */ - NFS_PROTO(inode)->commit_setup(data, &msg); - - dprintk("NFS: %5u initiated commit call\n", data->task.tk_pid); +void nfs_retry_commit(struct list_head *page_list, + struct pnfs_layout_segment *lseg) +{ + struct nfs_page *req; - task = rpc_run_task(&task_setup_data); - if (IS_ERR(task)) - return PTR_ERR(task); - if (how & FLUSH_SYNC) - rpc_wait_for_completion_task(task); - rpc_put_task(task); - return 0; + while (!list_empty(page_list)) { + req = nfs_list_entry(page_list->next); + nfs_list_remove_request(req); + nfs_mark_request_commit(req, lseg); + dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS); + dec_bdi_stat(req->wb_page->mapping->backing_dev_info, + BDI_RECLAIMABLE); + nfs_clear_page_tag_locked(req); + } } +EXPORT_SYMBOL_GPL(nfs_retry_commit); /* * Commit dirty pages @@ -1342,7 +1395,6 @@ static int nfs_commit_list(struct inode *inode, struct list_head *head, int how) { struct nfs_write_data *data; - struct nfs_page *req; data = nfs_commitdata_alloc(); @@ -1350,17 +1402,10 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how) goto out_bad; /* Set up the argument struct */ - return nfs_commit_rpcsetup(head, data, how); + nfs_init_commit(data, head, NULL); + return nfs_initiate_commit(data, NFS_CLIENT(inode), data->mds_ops, how); out_bad: - while (!list_empty(head)) { - req = nfs_list_entry(head->next); - nfs_list_remove_request(req); - nfs_mark_request_commit(req); - dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS); - dec_bdi_stat(req->wb_page->mapping->backing_dev_info, - BDI_RECLAIMABLE); - nfs_clear_page_tag_locked(req); - } + nfs_retry_commit(head, NULL); nfs_commit_clear_lock(NFS_I(inode)); return -ENOMEM; } @@ -1380,10 +1425,9 @@ static void nfs_commit_done(struct rpc_task *task, void *calldata) return; } -static void nfs_commit_release(void *calldata) +void nfs_commit_release_pages(struct nfs_write_data *data) { - struct nfs_write_data *data = calldata; - struct nfs_page *req; + struct nfs_page *req; int status = data->task.tk_status; while (!list_empty(&data->pages)) { @@ -1417,6 +1461,14 @@ static void nfs_commit_release(void *calldata) next: nfs_clear_page_tag_locked(req); } +} +EXPORT_SYMBOL_GPL(nfs_commit_release_pages); + +static void nfs_commit_release(void *calldata) +{ + struct nfs_write_data *data = calldata; + + nfs_commit_release_pages(data); nfs_commit_clear_lock(NFS_I(data->inode)); nfs_commitdata_release(calldata); } @@ -1433,23 +1485,30 @@ int nfs_commit_inode(struct inode *inode, int how) { LIST_HEAD(head); int may_wait = how & FLUSH_SYNC; - int res = 0; + int res; - if (!nfs_commit_set_lock(NFS_I(inode), may_wait)) + res = nfs_commit_set_lock(NFS_I(inode), may_wait); + if (res <= 0) goto out_mark_dirty; spin_lock(&inode->i_lock); res = nfs_scan_commit(inode, &head, 0, 0); spin_unlock(&inode->i_lock); if (res) { - int error = nfs_commit_list(inode, &head, how); + int error; + + error = pnfs_commit_list(inode, &head, how); + if (error == PNFS_NOT_ATTEMPTED) + error = nfs_commit_list(inode, &head, how); if (error < 0) return error; - if (may_wait) - wait_on_bit(&NFS_I(inode)->flags, NFS_INO_COMMIT, - nfs_wait_bit_killable, - TASK_KILLABLE); - else + if (!may_wait) goto out_mark_dirty; + error = wait_on_bit(&NFS_I(inode)->flags, + NFS_INO_COMMIT, + nfs_wait_bit_killable, + TASK_KILLABLE); + if (error < 0) + return error; } else nfs_commit_clear_lock(NFS_I(inode)); return res; @@ -1503,7 +1562,22 @@ static int nfs_commit_unstable_pages(struct inode *inode, struct writeback_contr int nfs_write_inode(struct inode *inode, struct writeback_control *wbc) { - return nfs_commit_unstable_pages(inode, wbc); + int ret; + + ret = nfs_commit_unstable_pages(inode, wbc); + if (ret >= 0 && test_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(inode)->flags)) { + int status; + bool sync = true; + + if (wbc->sync_mode == WB_SYNC_NONE || wbc->nonblocking || + wbc->for_background) + sync = false; + + status = pnfs_layoutcommit_inode(inode, sync); + if (status < 0) + return status; + } + return ret; } /* diff --git a/fs/nfs_common/nfsacl.c b/fs/nfs_common/nfsacl.c index 84c27d69d421..ec0f277be7f5 100644 --- a/fs/nfs_common/nfsacl.c +++ b/fs/nfs_common/nfsacl.c @@ -117,7 +117,6 @@ int nfsacl_encode(struct xdr_buf *buf, unsigned int base, struct inode *inode, * invoked in contexts where a memory allocation failure is * fatal. Fortunately this fake ACL is small enough to * construct on the stack. */ - memset(acl2, 0, sizeof(acl2)); posix_acl_init(acl2, 4); /* Insert entries in canonical order: other orders seem diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 27e79c27ba08..a32dcaec04e1 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -432,13 +432,35 @@ struct jbd2_journal_handle int h_err; /* Flags [no locking] */ - unsigned int h_sync: 1; /* sync-on-close */ - unsigned int h_jdata: 1; /* force data journaling */ - unsigned int h_aborted: 1; /* fatal error on handle */ + unsigned int h_sync:1; /* sync-on-close */ + unsigned int h_jdata:1; /* force data journaling */ + unsigned int h_aborted:1; /* fatal error on handle */ + unsigned int h_cowing:1; /* COWing block to snapshot */ + + /* Number of buffers requested by user: + * (before adding the COW credits factor) */ + unsigned int h_base_credits:14; + + /* Number of buffers the user is allowed to dirty: + * (counts only buffers dirtied when !h_cowing) */ + unsigned int h_user_credits:14; + #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map h_lockdep_map; #endif + +#ifdef CONFIG_JBD2_DEBUG + /* COW debugging counters: */ + unsigned int h_cow_moved; /* blocks moved to snapshot */ + unsigned int h_cow_copied; /* blocks copied to snapshot */ + unsigned int h_cow_ok_jh; /* blocks already COWed during current + transaction */ + unsigned int h_cow_ok_bitmap; /* blocks not set in COW bitmap */ + unsigned int h_cow_ok_mapped;/* blocks already mapped in snapshot */ + unsigned int h_cow_bitmaps; /* COW bitmaps created */ + unsigned int h_cow_excluded; /* blocks set in exclude bitmap */ +#endif }; diff --git a/include/linux/journal-head.h b/include/linux/journal-head.h index 525aac3c97df..44e95d0a721f 100644 --- a/include/linux/journal-head.h +++ b/include/linux/journal-head.h @@ -41,6 +41,13 @@ struct journal_head { unsigned b_modified; /* + * This feild tracks the last transaction id in which this buffer + * has been cowed + * [jbd_lock_bh_state()] + */ + unsigned b_cow_tid; + + /* * Copy of the buffer data frozen for writing to the log. * [jbd_lock_bh_state()] */ diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 134716e5e350..b528f6d4b860 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -550,6 +550,7 @@ enum { NFSPROC4_CLNT_SETACL, NFSPROC4_CLNT_FS_LOCATIONS, NFSPROC4_CLNT_RELEASE_LOCKOWNER, + NFSPROC4_CLNT_SECINFO, /* nfs41 */ NFSPROC4_CLNT_EXCHANGE_ID, @@ -560,6 +561,7 @@ enum { NFSPROC4_CLNT_RECLAIM_COMPLETE, NFSPROC4_CLNT_LAYOUTGET, NFSPROC4_CLNT_GETDEVICEINFO, + NFSPROC4_CLNT_LAYOUTCOMMIT, }; /* nfs41 types */ diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index f88522b10a38..1b93b9c60e55 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -33,6 +33,8 @@ #define FLUSH_STABLE 4 /* commit to stable storage */ #define FLUSH_LOWPRI 8 /* low priority background flush */ #define FLUSH_HIGHPRI 16 /* high priority memory reclaim flush */ +#define FLUSH_COND_STABLE 32 /* conditional stable write - only stable + * if everything fits in one RPC */ #ifdef __KERNEL__ @@ -93,8 +95,13 @@ struct nfs_open_context { int error; struct list_head list; +}; +struct nfs_open_dir_context { + struct rpc_cred *cred; __u64 dir_cookie; + __u64 dup_cookie; + int duped; }; /* @@ -191,6 +198,7 @@ struct nfs_inode { /* pNFS layout information */ struct pnfs_layout_hdr *layout; + atomic_t commits_outstanding; #endif /* CONFIG_NFS_V4*/ #ifdef CONFIG_NFS_FSCACHE struct fscache_cookie *fscache; @@ -219,6 +227,8 @@ struct nfs_inode { #define NFS_INO_FSCACHE (5) /* inode can be cached by FS-Cache */ #define NFS_INO_FSCACHE_LOCK (6) /* FS-Cache cookie management lock */ #define NFS_INO_COMMIT (7) /* inode is committing unstable writes */ +#define NFS_INO_PNFS_COMMIT (8) /* use pnfs code for commit */ +#define NFS_INO_LAYOUTCOMMIT (9) /* layoutcommit required */ static inline struct nfs_inode *NFS_I(const struct inode *inode) { diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 90907ada6d52..8023e4e25133 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -33,11 +33,15 @@ enum { PG_CLEAN, PG_NEED_COMMIT, PG_NEED_RESCHED, + PG_PNFS_COMMIT, }; struct nfs_inode; struct nfs_page { - struct list_head wb_list; /* Defines state of page: */ + union { + struct list_head wb_list; /* Defines state of page: */ + struct pnfs_layout_segment *wb_commit_lseg; /* Used when PG_PNFS_COMMIT set */ + }; struct page *wb_page; /* page to read in/write out */ struct nfs_open_context *wb_context; /* File state context info */ struct nfs_lock_context *wb_lock_context; /* lock context info */ @@ -57,6 +61,7 @@ struct nfs_pageio_descriptor { size_t pg_count; size_t pg_bsize; unsigned int pg_base; + char pg_moreio; struct inode *pg_inode; int (*pg_doio)(struct nfs_pageio_descriptor *); diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 2c2c67d2eb42..78b101e487ea 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -3,6 +3,7 @@ #include <linux/nfsacl.h> #include <linux/nfs3.h> +#include <linux/sunrpc/gss_api.h> /* * To change the maximum rsize and wsize supported by the NFS client, adjust @@ -14,6 +15,9 @@ #define NFS_DEF_FILE_IO_SIZE (4096U) #define NFS_MIN_FILE_IO_SIZE (1024U) +/* Forward declaration for NFS v3 */ +struct nfs4_secinfo_flavors; + struct nfs_fsid { uint64_t major; uint64_t minor; @@ -78,6 +82,7 @@ struct nfs_fattr { #define NFS_ATTR_FATTR_CHANGE (1U << 17) #define NFS_ATTR_FATTR_PRECHANGE (1U << 18) #define NFS_ATTR_FATTR_V4_REFERRAL (1U << 19) /* NFSv4 referral */ +#define NFS_ATTR_FATTR_MOUNTPOINT (1U << 20) /* Treat as mountpoint */ #define NFS_ATTR_FATTR (NFS_ATTR_FATTR_TYPE \ | NFS_ATTR_FATTR_MODE \ @@ -190,8 +195,9 @@ struct nfs4_get_lease_time_res { #define PNFS_LAYOUT_MAXSIZE 4096 struct nfs4_layoutdriver_data { + struct page **pages; + __u32 pglen; __u32 len; - void *buf; }; struct pnfs_layout_range { @@ -209,6 +215,7 @@ struct nfs4_layoutget_args { struct nfs_open_context *ctx; struct nfs4_sequence_args seq_args; nfs4_stateid stateid; + struct nfs4_layoutdriver_data layout; }; struct nfs4_layoutget_res { @@ -216,8 +223,8 @@ struct nfs4_layoutget_res { struct pnfs_layout_range range; __u32 type; nfs4_stateid stateid; - struct nfs4_layoutdriver_data layout; struct nfs4_sequence_res seq_res; + struct nfs4_layoutdriver_data *layoutp; }; struct nfs4_layoutget { @@ -236,6 +243,29 @@ struct nfs4_getdeviceinfo_res { struct nfs4_sequence_res seq_res; }; +struct nfs4_layoutcommit_args { + nfs4_stateid stateid; + __u64 lastbytewritten; + struct inode *inode; + const u32 *bitmask; + struct nfs4_sequence_args seq_args; +}; + +struct nfs4_layoutcommit_res { + struct nfs_fattr *fattr; + const struct nfs_server *server; + struct nfs4_sequence_res seq_res; +}; + +struct nfs4_layoutcommit_data { + struct rpc_task task; + struct nfs_fattr fattr; + struct pnfs_layout_segment *lseg; + struct rpc_cred *cred; + struct nfs4_layoutcommit_args args; + struct nfs4_layoutcommit_res res; +}; + /* * Arguments to the open call. */ @@ -936,6 +966,38 @@ struct nfs4_fs_locations_res { struct nfs4_sequence_res seq_res; }; +struct nfs4_secinfo_oid { + unsigned int len; + char data[GSS_OID_MAX_LEN]; +}; + +struct nfs4_secinfo_gss { + struct nfs4_secinfo_oid sec_oid4; + unsigned int qop4; + unsigned int service; +}; + +struct nfs4_secinfo_flavor { + unsigned int flavor; + struct nfs4_secinfo_gss gss; +}; + +struct nfs4_secinfo_flavors { + unsigned int num_flavors; + struct nfs4_secinfo_flavor flavors[0]; +}; + +struct nfs4_secinfo_arg { + const struct nfs_fh *dir_fh; + const struct qstr *name; + struct nfs4_sequence_args seq_args; +}; + +struct nfs4_secinfo_res { + struct nfs4_secinfo_flavors *flavors; + struct nfs4_sequence_res seq_res; +}; + #endif /* CONFIG_NFS_V4 */ struct nfstime4 { @@ -1040,6 +1102,7 @@ struct nfs_write_data { struct nfs_writeres res; /* result struct */ struct pnfs_layout_segment *lseg; struct nfs_client *ds_clp; /* pNFS data server */ + int ds_commit_index; const struct rpc_call_ops *mds_ops; int (*write_done_cb) (struct rpc_task *task, struct nfs_write_data *data); #ifdef CONFIG_NFS_V4 @@ -1071,7 +1134,7 @@ struct nfs_rpc_ops { struct nfs_fattr *); int (*setattr) (struct dentry *, struct nfs_fattr *, struct iattr *); - int (*lookup) (struct inode *, struct qstr *, + int (*lookup) (struct rpc_clnt *clnt, struct inode *, struct qstr *, struct nfs_fh *, struct nfs_fattr *); int (*access) (struct inode *, struct nfs_access_entry *); int (*readlink)(struct inode *, struct page *, unsigned int, @@ -1118,6 +1181,7 @@ struct nfs_rpc_ops { struct iattr *iattr); int (*init_client) (struct nfs_client *, const struct rpc_timeout *, const char *, rpc_authflavor_t, int); + int (*secinfo)(struct inode *, const struct qstr *, struct nfs4_secinfo_flavors *); }; /* diff --git a/include/linux/sunrpc/gss_api.h b/include/linux/sunrpc/gss_api.h index 5d8048beb051..332da61cf8b7 100644 --- a/include/linux/sunrpc/gss_api.h +++ b/include/linux/sunrpc/gss_api.h @@ -126,6 +126,9 @@ struct gss_api_mech *gss_mech_get_by_name(const char *); /* Similar, but get by pseudoflavor. */ struct gss_api_mech *gss_mech_get_by_pseudoflavor(u32); +/* Fill in an array with a list of supported pseudoflavors */ +int gss_mech_list_pseudoflavors(u32 *); + /* Just increments the mechanism's reference count and returns its input: */ struct gss_api_mech * gss_mech_get(struct gss_api_mech *); diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index e5e345fb2a5c..e09592d2f916 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -21,8 +21,7 @@ TRACE_EVENT(ext4_free_inode, TP_ARGS(inode), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( umode_t, mode ) __field( uid_t, uid ) @@ -31,8 +30,7 @@ TRACE_EVENT(ext4_free_inode, ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->mode = inode->i_mode; __entry->uid = inode->i_uid; @@ -41,9 +39,9 @@ TRACE_EVENT(ext4_free_inode, ), TP_printk("dev %d,%d ino %lu mode 0%o uid %u gid %u blocks %llu", - __entry->dev_major, __entry->dev_minor, - (unsigned long) __entry->ino, __entry->mode, - __entry->uid, __entry->gid, + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + __entry->mode, __entry->uid, __entry->gid, (unsigned long long) __entry->blocks) ); @@ -53,21 +51,19 @@ TRACE_EVENT(ext4_request_inode, TP_ARGS(dir, mode), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, dir ) __field( umode_t, mode ) ), TP_fast_assign( - __entry->dev_major = MAJOR(dir->i_sb->s_dev); - __entry->dev_minor = MINOR(dir->i_sb->s_dev); + __entry->dev = dir->i_sb->s_dev; __entry->dir = dir->i_ino; __entry->mode = mode; ), TP_printk("dev %d,%d dir %lu mode 0%o", - __entry->dev_major, __entry->dev_minor, + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->dir, __entry->mode) ); @@ -77,23 +73,21 @@ TRACE_EVENT(ext4_allocate_inode, TP_ARGS(inode, dir, mode), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( ino_t, dir ) __field( umode_t, mode ) ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->dir = dir->i_ino; __entry->mode = mode; ), TP_printk("dev %d,%d ino %lu dir %lu mode 0%o", - __entry->dev_major, __entry->dev_minor, + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned long) __entry->dir, __entry->mode) ); @@ -104,21 +98,19 @@ TRACE_EVENT(ext4_evict_inode, TP_ARGS(inode), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( int, nlink ) ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->nlink = inode->i_nlink; ), TP_printk("dev %d,%d ino %lu nlink %d", - __entry->dev_major, __entry->dev_minor, + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->nlink) ); @@ -128,21 +120,19 @@ TRACE_EVENT(ext4_drop_inode, TP_ARGS(inode, drop), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( int, drop ) ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->drop = drop; ), TP_printk("dev %d,%d ino %lu drop %d", - __entry->dev_major, __entry->dev_minor, + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->drop) ); @@ -152,21 +142,19 @@ TRACE_EVENT(ext4_mark_inode_dirty, TP_ARGS(inode, IP), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field(unsigned long, ip ) ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->ip = IP; ), TP_printk("dev %d,%d ino %lu caller %pF", - __entry->dev_major, __entry->dev_minor, + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (void *)__entry->ip) ); @@ -176,21 +164,19 @@ TRACE_EVENT(ext4_begin_ordered_truncate, TP_ARGS(inode, new_size), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( loff_t, new_size ) ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->new_size = new_size; ), TP_printk("dev %d,%d ino %lu new_size %lld", - __entry->dev_major, __entry->dev_minor, + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (long long) __entry->new_size) ); @@ -203,8 +189,7 @@ DECLARE_EVENT_CLASS(ext4__write_begin, TP_ARGS(inode, pos, len, flags), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( loff_t, pos ) __field( unsigned int, len ) @@ -212,8 +197,7 @@ DECLARE_EVENT_CLASS(ext4__write_begin, ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->pos = pos; __entry->len = len; @@ -221,7 +205,7 @@ DECLARE_EVENT_CLASS(ext4__write_begin, ), TP_printk("dev %d,%d ino %lu pos %llu len %u flags %u", - __entry->dev_major, __entry->dev_minor, + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->pos, __entry->len, __entry->flags) ); @@ -249,8 +233,7 @@ DECLARE_EVENT_CLASS(ext4__write_end, TP_ARGS(inode, pos, len, copied), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( loff_t, pos ) __field( unsigned int, len ) @@ -258,8 +241,7 @@ DECLARE_EVENT_CLASS(ext4__write_end, ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->pos = pos; __entry->len = len; @@ -267,9 +249,9 @@ DECLARE_EVENT_CLASS(ext4__write_end, ), TP_printk("dev %d,%d ino %lu pos %llu len %u copied %u", - __entry->dev_major, __entry->dev_minor, - (unsigned long) __entry->ino, __entry->pos, - __entry->len, __entry->copied) + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + __entry->pos, __entry->len, __entry->copied) ); DEFINE_EVENT(ext4__write_end, ext4_ordered_write_end, @@ -310,22 +292,20 @@ TRACE_EVENT(ext4_writepage, TP_ARGS(inode, page), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( pgoff_t, index ) ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->index = page->index; ), TP_printk("dev %d,%d ino %lu page_index %lu", - __entry->dev_major, __entry->dev_minor, + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->index) ); @@ -335,43 +315,39 @@ TRACE_EVENT(ext4_da_writepages, TP_ARGS(inode, wbc), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( long, nr_to_write ) __field( long, pages_skipped ) __field( loff_t, range_start ) __field( loff_t, range_end ) + __field( int, sync_mode ) __field( char, for_kupdate ) - __field( char, for_reclaim ) __field( char, range_cyclic ) __field( pgoff_t, writeback_index ) ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->nr_to_write = wbc->nr_to_write; __entry->pages_skipped = wbc->pages_skipped; __entry->range_start = wbc->range_start; __entry->range_end = wbc->range_end; + __entry->sync_mode = wbc->sync_mode; __entry->for_kupdate = wbc->for_kupdate; - __entry->for_reclaim = wbc->for_reclaim; __entry->range_cyclic = wbc->range_cyclic; __entry->writeback_index = inode->i_mapping->writeback_index; ), TP_printk("dev %d,%d ino %lu nr_to_write %ld pages_skipped %ld " - "range_start %llu range_end %llu " - "for_kupdate %d for_reclaim %d " - "range_cyclic %d writeback_index %lu", - __entry->dev_major, __entry->dev_minor, + "range_start %llu range_end %llu sync_mode %d" + "for_kupdate %d range_cyclic %d writeback_index %lu", + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->nr_to_write, __entry->pages_skipped, __entry->range_start, - __entry->range_end, - __entry->for_kupdate, __entry->for_reclaim, - __entry->range_cyclic, + __entry->range_end, __entry->sync_mode, + __entry->for_kupdate, __entry->range_cyclic, (unsigned long) __entry->writeback_index) ); @@ -381,8 +357,7 @@ TRACE_EVENT(ext4_da_write_pages, TP_ARGS(inode, mpd), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, b_blocknr ) __field( __u32, b_size ) @@ -390,11 +365,11 @@ TRACE_EVENT(ext4_da_write_pages, __field( unsigned long, first_page ) __field( int, io_done ) __field( int, pages_written ) + __field( int, sync_mode ) ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->b_blocknr = mpd->b_blocknr; __entry->b_size = mpd->b_size; @@ -402,14 +377,18 @@ TRACE_EVENT(ext4_da_write_pages, __entry->first_page = mpd->first_page; __entry->io_done = mpd->io_done; __entry->pages_written = mpd->pages_written; + __entry->sync_mode = mpd->wbc->sync_mode; ), - TP_printk("dev %d,%d ino %lu b_blocknr %llu b_size %u b_state 0x%04x first_page %lu io_done %d pages_written %d", - __entry->dev_major, __entry->dev_minor, + TP_printk("dev %d,%d ino %lu b_blocknr %llu b_size %u b_state 0x%04x " + "first_page %lu io_done %d pages_written %d sync_mode %d", + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->b_blocknr, __entry->b_size, __entry->b_state, __entry->first_page, - __entry->io_done, __entry->pages_written) + __entry->io_done, __entry->pages_written, + __entry->sync_mode + ) ); TRACE_EVENT(ext4_da_writepages_result, @@ -419,35 +398,100 @@ TRACE_EVENT(ext4_da_writepages_result, TP_ARGS(inode, wbc, ret, pages_written), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( int, ret ) __field( int, pages_written ) __field( long, pages_skipped ) + __field( int, sync_mode ) __field( char, more_io ) __field( pgoff_t, writeback_index ) ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->ret = ret; __entry->pages_written = pages_written; __entry->pages_skipped = wbc->pages_skipped; + __entry->sync_mode = wbc->sync_mode; __entry->more_io = wbc->more_io; __entry->writeback_index = inode->i_mapping->writeback_index; ), - TP_printk("dev %d,%d ino %lu ret %d pages_written %d pages_skipped %ld more_io %d writeback_index %lu", - __entry->dev_major, __entry->dev_minor, + TP_printk("dev %d,%d ino %lu ret %d pages_written %d pages_skipped %ld " + " more_io %d sync_mode %d writeback_index %lu", + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->ret, __entry->pages_written, __entry->pages_skipped, - __entry->more_io, + __entry->more_io, __entry->sync_mode, (unsigned long) __entry->writeback_index) ); +DECLARE_EVENT_CLASS(ext4__page_op, + TP_PROTO(struct page *page), + + TP_ARGS(page), + + TP_STRUCT__entry( + __field( pgoff_t, index ) + __field( ino_t, ino ) + __field( dev_t, dev ) + + ), + + TP_fast_assign( + __entry->index = page->index; + __entry->ino = page->mapping->host->i_ino; + __entry->dev = page->mapping->host->i_sb->s_dev; + ), + + TP_printk("dev %d,%d ino %lu page_index %lu", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + __entry->index) +); + +DEFINE_EVENT(ext4__page_op, ext4_readpage, + + TP_PROTO(struct page *page), + + TP_ARGS(page) +); + +DEFINE_EVENT(ext4__page_op, ext4_releasepage, + + TP_PROTO(struct page *page), + + TP_ARGS(page) +); + +TRACE_EVENT(ext4_invalidatepage, + TP_PROTO(struct page *page, unsigned long offset), + + TP_ARGS(page, offset), + + TP_STRUCT__entry( + __field( pgoff_t, index ) + __field( unsigned long, offset ) + __field( ino_t, ino ) + __field( dev_t, dev ) + + ), + + TP_fast_assign( + __entry->index = page->index; + __entry->offset = offset; + __entry->ino = page->mapping->host->i_ino; + __entry->dev = page->mapping->host->i_sb->s_dev; + ), + + TP_printk("dev %d,%d ino %lu page_index %lu offset %lu", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + __entry->index, __entry->offset) +); + TRACE_EVENT(ext4_discard_blocks, TP_PROTO(struct super_block *sb, unsigned long long blk, unsigned long long count), @@ -455,22 +499,20 @@ TRACE_EVENT(ext4_discard_blocks, TP_ARGS(sb, blk, count), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( __u64, blk ) __field( __u64, count ) ), TP_fast_assign( - __entry->dev_major = MAJOR(sb->s_dev); - __entry->dev_minor = MINOR(sb->s_dev); + __entry->dev = sb->s_dev; __entry->blk = blk; __entry->count = count; ), TP_printk("dev %d,%d blk %llu count %llu", - __entry->dev_major, __entry->dev_minor, + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->blk, __entry->count) ); @@ -481,8 +523,7 @@ DECLARE_EVENT_CLASS(ext4__mb_new_pa, TP_ARGS(ac, pa), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, pa_pstart ) __field( __u32, pa_len ) @@ -491,8 +532,7 @@ DECLARE_EVENT_CLASS(ext4__mb_new_pa, ), TP_fast_assign( - __entry->dev_major = MAJOR(ac->ac_sb->s_dev); - __entry->dev_minor = MINOR(ac->ac_sb->s_dev); + __entry->dev = ac->ac_sb->s_dev; __entry->ino = ac->ac_inode->i_ino; __entry->pa_pstart = pa->pa_pstart; __entry->pa_len = pa->pa_len; @@ -500,9 +540,9 @@ DECLARE_EVENT_CLASS(ext4__mb_new_pa, ), TP_printk("dev %d,%d ino %lu pstart %llu len %u lstart %llu", - __entry->dev_major, __entry->dev_minor, - (unsigned long) __entry->ino, __entry->pa_pstart, - __entry->pa_len, __entry->pa_lstart) + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + __entry->pa_pstart, __entry->pa_len, __entry->pa_lstart) ); DEFINE_EVENT(ext4__mb_new_pa, ext4_mb_new_inode_pa, @@ -530,8 +570,7 @@ TRACE_EVENT(ext4_mb_release_inode_pa, TP_ARGS(sb, inode, pa, block, count), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, block ) __field( __u32, count ) @@ -539,16 +578,16 @@ TRACE_EVENT(ext4_mb_release_inode_pa, ), TP_fast_assign( - __entry->dev_major = MAJOR(sb->s_dev); - __entry->dev_minor = MINOR(sb->s_dev); + __entry->dev = sb->s_dev; __entry->ino = inode->i_ino; __entry->block = block; __entry->count = count; ), TP_printk("dev %d,%d ino %lu block %llu count %u", - __entry->dev_major, __entry->dev_minor, - (unsigned long) __entry->ino, __entry->block, __entry->count) + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + __entry->block, __entry->count) ); TRACE_EVENT(ext4_mb_release_group_pa, @@ -558,22 +597,20 @@ TRACE_EVENT(ext4_mb_release_group_pa, TP_ARGS(sb, pa), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( __u64, pa_pstart ) __field( __u32, pa_len ) ), TP_fast_assign( - __entry->dev_major = MAJOR(sb->s_dev); - __entry->dev_minor = MINOR(sb->s_dev); + __entry->dev = sb->s_dev; __entry->pa_pstart = pa->pa_pstart; __entry->pa_len = pa->pa_len; ), TP_printk("dev %d,%d pstart %llu len %u", - __entry->dev_major, __entry->dev_minor, + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->pa_pstart, __entry->pa_len) ); @@ -583,20 +620,18 @@ TRACE_EVENT(ext4_discard_preallocations, TP_ARGS(inode), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; ), TP_printk("dev %d,%d ino %lu", - __entry->dev_major, __entry->dev_minor, + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino) ); @@ -606,20 +641,19 @@ TRACE_EVENT(ext4_mb_discard_preallocations, TP_ARGS(sb, needed), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( int, needed ) ), TP_fast_assign( - __entry->dev_major = MAJOR(sb->s_dev); - __entry->dev_minor = MINOR(sb->s_dev); + __entry->dev = sb->s_dev; __entry->needed = needed; ), TP_printk("dev %d,%d needed %d", - __entry->dev_major, __entry->dev_minor, __entry->needed) + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->needed) ); TRACE_EVENT(ext4_request_blocks, @@ -628,8 +662,7 @@ TRACE_EVENT(ext4_request_blocks, TP_ARGS(ar), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( unsigned int, flags ) __field( unsigned int, len ) @@ -642,8 +675,7 @@ TRACE_EVENT(ext4_request_blocks, ), TP_fast_assign( - __entry->dev_major = MAJOR(ar->inode->i_sb->s_dev); - __entry->dev_minor = MINOR(ar->inode->i_sb->s_dev); + __entry->dev = ar->inode->i_sb->s_dev; __entry->ino = ar->inode->i_ino; __entry->flags = ar->flags; __entry->len = ar->len; @@ -655,8 +687,9 @@ TRACE_EVENT(ext4_request_blocks, __entry->pright = ar->pright; ), - TP_printk("dev %d,%d ino %lu flags %u len %u lblk %llu goal %llu lleft %llu lright %llu pleft %llu pright %llu ", - __entry->dev_major, __entry->dev_minor, + TP_printk("dev %d,%d ino %lu flags %u len %u lblk %llu goal %llu " + "lleft %llu lright %llu pleft %llu pright %llu ", + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->flags, __entry->len, (unsigned long long) __entry->logical, @@ -673,8 +706,7 @@ TRACE_EVENT(ext4_allocate_blocks, TP_ARGS(ar, block), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, block ) __field( unsigned int, flags ) @@ -688,8 +720,7 @@ TRACE_EVENT(ext4_allocate_blocks, ), TP_fast_assign( - __entry->dev_major = MAJOR(ar->inode->i_sb->s_dev); - __entry->dev_minor = MINOR(ar->inode->i_sb->s_dev); + __entry->dev = ar->inode->i_sb->s_dev; __entry->ino = ar->inode->i_ino; __entry->block = block; __entry->flags = ar->flags; @@ -702,10 +733,11 @@ TRACE_EVENT(ext4_allocate_blocks, __entry->pright = ar->pright; ), - TP_printk("dev %d,%d ino %lu flags %u len %u block %llu lblk %llu goal %llu lleft %llu lright %llu pleft %llu pright %llu ", - __entry->dev_major, __entry->dev_minor, - (unsigned long) __entry->ino, __entry->flags, - __entry->len, __entry->block, + TP_printk("dev %d,%d ino %lu flags %u len %u block %llu lblk %llu " + "goal %llu lleft %llu lright %llu pleft %llu pright %llu", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + __entry->flags, __entry->len, __entry->block, (unsigned long long) __entry->logical, (unsigned long long) __entry->goal, (unsigned long long) __entry->lleft, @@ -721,8 +753,7 @@ TRACE_EVENT(ext4_free_blocks, TP_ARGS(inode, block, count, flags), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( umode_t, mode ) __field( __u64, block ) @@ -731,8 +762,7 @@ TRACE_EVENT(ext4_free_blocks, ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->mode = inode->i_mode; __entry->block = block; @@ -741,20 +771,19 @@ TRACE_EVENT(ext4_free_blocks, ), TP_printk("dev %d,%d ino %lu mode 0%o block %llu count %lu flags %d", - __entry->dev_major, __entry->dev_minor, + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->mode, __entry->block, __entry->count, __entry->flags) ); -TRACE_EVENT(ext4_sync_file, +TRACE_EVENT(ext4_sync_file_enter, TP_PROTO(struct file *file, int datasync), TP_ARGS(file, datasync), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( ino_t, parent ) __field( int, datasync ) @@ -763,39 +792,60 @@ TRACE_EVENT(ext4_sync_file, TP_fast_assign( struct dentry *dentry = file->f_path.dentry; - __entry->dev_major = MAJOR(dentry->d_inode->i_sb->s_dev); - __entry->dev_minor = MINOR(dentry->d_inode->i_sb->s_dev); + __entry->dev = dentry->d_inode->i_sb->s_dev; __entry->ino = dentry->d_inode->i_ino; __entry->datasync = datasync; __entry->parent = dentry->d_parent->d_inode->i_ino; ), TP_printk("dev %d,%d ino %ld parent %ld datasync %d ", - __entry->dev_major, __entry->dev_minor, + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned long) __entry->parent, __entry->datasync) ); +TRACE_EVENT(ext4_sync_file_exit, + TP_PROTO(struct inode *inode, int ret), + + TP_ARGS(inode, ret), + + TP_STRUCT__entry( + __field( int, ret ) + __field( ino_t, ino ) + __field( dev_t, dev ) + ), + + TP_fast_assign( + __entry->ret = ret; + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + ), + + TP_printk("dev %d,%d ino %ld ret %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + __entry->ret) +); + TRACE_EVENT(ext4_sync_fs, TP_PROTO(struct super_block *sb, int wait), TP_ARGS(sb, wait), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( int, wait ) ), TP_fast_assign( - __entry->dev_major = MAJOR(sb->s_dev); - __entry->dev_minor = MINOR(sb->s_dev); + __entry->dev = sb->s_dev; __entry->wait = wait; ), - TP_printk("dev %d,%d wait %d", __entry->dev_major, - __entry->dev_minor, __entry->wait) + TP_printk("dev %d,%d wait %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->wait) ); TRACE_EVENT(ext4_alloc_da_blocks, @@ -804,23 +854,21 @@ TRACE_EVENT(ext4_alloc_da_blocks, TP_ARGS(inode), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( unsigned int, data_blocks ) __field( unsigned int, meta_blocks ) ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->data_blocks = EXT4_I(inode)->i_reserved_data_blocks; __entry->meta_blocks = EXT4_I(inode)->i_reserved_meta_blocks; ), TP_printk("dev %d,%d ino %lu data_blocks %u meta_blocks %u", - __entry->dev_major, __entry->dev_minor, + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->data_blocks, __entry->meta_blocks) ); @@ -831,8 +879,7 @@ TRACE_EVENT(ext4_mballoc_alloc, TP_ARGS(ac), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( __u16, found ) __field( __u16, groups ) @@ -855,8 +902,7 @@ TRACE_EVENT(ext4_mballoc_alloc, ), TP_fast_assign( - __entry->dev_major = MAJOR(ac->ac_inode->i_sb->s_dev); - __entry->dev_minor = MINOR(ac->ac_inode->i_sb->s_dev); + __entry->dev = ac->ac_inode->i_sb->s_dev; __entry->ino = ac->ac_inode->i_ino; __entry->found = ac->ac_found; __entry->flags = ac->ac_flags; @@ -881,7 +927,7 @@ TRACE_EVENT(ext4_mballoc_alloc, TP_printk("dev %d,%d inode %lu orig %u/%d/%u@%u goal %u/%d/%u@%u " "result %u/%d/%u@%u blks %u grps %u cr %u flags 0x%04x " "tail %u broken %u", - __entry->dev_major, __entry->dev_minor, + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->orig_group, __entry->orig_start, __entry->orig_len, __entry->orig_logical, @@ -900,8 +946,7 @@ TRACE_EVENT(ext4_mballoc_prealloc, TP_ARGS(ac), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( __u32, orig_logical ) __field( int, orig_start ) @@ -914,8 +959,7 @@ TRACE_EVENT(ext4_mballoc_prealloc, ), TP_fast_assign( - __entry->dev_major = MAJOR(ac->ac_inode->i_sb->s_dev); - __entry->dev_minor = MINOR(ac->ac_inode->i_sb->s_dev); + __entry->dev = ac->ac_inode->i_sb->s_dev; __entry->ino = ac->ac_inode->i_ino; __entry->orig_logical = ac->ac_o_ex.fe_logical; __entry->orig_start = ac->ac_o_ex.fe_start; @@ -928,7 +972,7 @@ TRACE_EVENT(ext4_mballoc_prealloc, ), TP_printk("dev %d,%d inode %lu orig %u/%d/%u@%u result %u/%d/%u@%u", - __entry->dev_major, __entry->dev_minor, + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->orig_group, __entry->orig_start, __entry->orig_len, __entry->orig_logical, @@ -946,8 +990,7 @@ DECLARE_EVENT_CLASS(ext4__mballoc, TP_ARGS(sb, inode, group, start, len), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( int, result_start ) __field( __u32, result_group ) @@ -955,8 +998,7 @@ DECLARE_EVENT_CLASS(ext4__mballoc, ), TP_fast_assign( - __entry->dev_major = MAJOR(sb->s_dev); - __entry->dev_minor = MINOR(sb->s_dev); + __entry->dev = sb->s_dev; __entry->ino = inode ? inode->i_ino : 0; __entry->result_start = start; __entry->result_group = group; @@ -964,7 +1006,7 @@ DECLARE_EVENT_CLASS(ext4__mballoc, ), TP_printk("dev %d,%d inode %lu extent %u/%d/%u ", - __entry->dev_major, __entry->dev_minor, + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->result_group, __entry->result_start, __entry->result_len) @@ -998,8 +1040,7 @@ TRACE_EVENT(ext4_forget, TP_ARGS(inode, is_metadata, block), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( umode_t, mode ) __field( int, is_metadata ) @@ -1007,8 +1048,7 @@ TRACE_EVENT(ext4_forget, ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->mode = inode->i_mode; __entry->is_metadata = is_metadata; @@ -1016,9 +1056,9 @@ TRACE_EVENT(ext4_forget, ), TP_printk("dev %d,%d ino %lu mode 0%o is_metadata %d block %llu", - __entry->dev_major, __entry->dev_minor, - (unsigned long) __entry->ino, __entry->mode, - __entry->is_metadata, __entry->block) + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + __entry->mode, __entry->is_metadata, __entry->block) ); TRACE_EVENT(ext4_da_update_reserve_space, @@ -1027,8 +1067,7 @@ TRACE_EVENT(ext4_da_update_reserve_space, TP_ARGS(inode, used_blocks), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( umode_t, mode ) __field( __u64, i_blocks ) @@ -1039,8 +1078,7 @@ TRACE_EVENT(ext4_da_update_reserve_space, ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->mode = inode->i_mode; __entry->i_blocks = inode->i_blocks; @@ -1050,10 +1088,12 @@ TRACE_EVENT(ext4_da_update_reserve_space, __entry->allocated_meta_blocks = EXT4_I(inode)->i_allocated_meta_blocks; ), - TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu used_blocks %d reserved_data_blocks %d reserved_meta_blocks %d allocated_meta_blocks %d", - __entry->dev_major, __entry->dev_minor, - (unsigned long) __entry->ino, __entry->mode, - (unsigned long long) __entry->i_blocks, + TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu used_blocks %d " + "reserved_data_blocks %d reserved_meta_blocks %d " + "allocated_meta_blocks %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + __entry->mode, (unsigned long long) __entry->i_blocks, __entry->used_blocks, __entry->reserved_data_blocks, __entry->reserved_meta_blocks, __entry->allocated_meta_blocks) ); @@ -1064,8 +1104,7 @@ TRACE_EVENT(ext4_da_reserve_space, TP_ARGS(inode, md_needed), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( umode_t, mode ) __field( __u64, i_blocks ) @@ -1075,8 +1114,7 @@ TRACE_EVENT(ext4_da_reserve_space, ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->mode = inode->i_mode; __entry->i_blocks = inode->i_blocks; @@ -1085,8 +1123,9 @@ TRACE_EVENT(ext4_da_reserve_space, __entry->reserved_meta_blocks = EXT4_I(inode)->i_reserved_meta_blocks; ), - TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu md_needed %d reserved_data_blocks %d reserved_meta_blocks %d", - __entry->dev_major, __entry->dev_minor, + TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu md_needed %d " + "reserved_data_blocks %d reserved_meta_blocks %d", + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->mode, (unsigned long long) __entry->i_blocks, __entry->md_needed, __entry->reserved_data_blocks, @@ -1099,8 +1138,7 @@ TRACE_EVENT(ext4_da_release_space, TP_ARGS(inode, freed_blocks), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( umode_t, mode ) __field( __u64, i_blocks ) @@ -1111,8 +1149,7 @@ TRACE_EVENT(ext4_da_release_space, ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->mode = inode->i_mode; __entry->i_blocks = inode->i_blocks; @@ -1122,8 +1159,10 @@ TRACE_EVENT(ext4_da_release_space, __entry->allocated_meta_blocks = EXT4_I(inode)->i_allocated_meta_blocks; ), - TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu freed_blocks %d reserved_data_blocks %d reserved_meta_blocks %d allocated_meta_blocks %d", - __entry->dev_major, __entry->dev_minor, + TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu freed_blocks %d " + "reserved_data_blocks %d reserved_meta_blocks %d " + "allocated_meta_blocks %d", + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->mode, (unsigned long long) __entry->i_blocks, __entry->freed_blocks, __entry->reserved_data_blocks, @@ -1136,20 +1175,19 @@ DECLARE_EVENT_CLASS(ext4__bitmap_load, TP_ARGS(sb, group), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( __u32, group ) ), TP_fast_assign( - __entry->dev_major = MAJOR(sb->s_dev); - __entry->dev_minor = MINOR(sb->s_dev); + __entry->dev = sb->s_dev; __entry->group = group; ), TP_printk("dev %d,%d group %u", - __entry->dev_major, __entry->dev_minor, __entry->group) + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->group) ); DEFINE_EVENT(ext4__bitmap_load, ext4_mb_bitmap_load, @@ -1166,6 +1204,349 @@ DEFINE_EVENT(ext4__bitmap_load, ext4_mb_buddy_bitmap_load, TP_ARGS(sb, group) ); +DEFINE_EVENT(ext4__bitmap_load, ext4_read_block_bitmap_load, + + TP_PROTO(struct super_block *sb, unsigned long group), + + TP_ARGS(sb, group) +); + +DEFINE_EVENT(ext4__bitmap_load, ext4_load_inode_bitmap, + + TP_PROTO(struct super_block *sb, unsigned long group), + + TP_ARGS(sb, group) +); + +TRACE_EVENT(ext4_direct_IO_enter, + TP_PROTO(struct inode *inode, loff_t offset, unsigned long len, int rw), + + TP_ARGS(inode, offset, len, rw), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( loff_t, pos ) + __field( unsigned long, len ) + __field( int, rw ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->pos = offset; + __entry->len = len; + __entry->rw = rw; + ), + + TP_printk("dev %d,%d ino %lu pos %llu len %lu rw %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned long long) __entry->pos, __entry->len, __entry->rw) +); + +TRACE_EVENT(ext4_direct_IO_exit, + TP_PROTO(struct inode *inode, loff_t offset, unsigned long len, int rw, int ret), + + TP_ARGS(inode, offset, len, rw, ret), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( loff_t, pos ) + __field( unsigned long, len ) + __field( int, rw ) + __field( int, ret ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->pos = offset; + __entry->len = len; + __entry->rw = rw; + __entry->ret = ret; + ), + + TP_printk("dev %d,%d ino %lu pos %llu len %lu rw %d ret %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned long long) __entry->pos, __entry->len, + __entry->rw, __entry->ret) +); + +TRACE_EVENT(ext4_fallocate_enter, + TP_PROTO(struct inode *inode, loff_t offset, loff_t len, int mode), + + TP_ARGS(inode, offset, len, mode), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( loff_t, pos ) + __field( loff_t, len ) + __field( int, mode ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->pos = offset; + __entry->len = len; + __entry->mode = mode; + ), + + TP_printk("dev %d,%d ino %ld pos %llu len %llu mode %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned long long) __entry->pos, + (unsigned long long) __entry->len, __entry->mode) +); + +TRACE_EVENT(ext4_fallocate_exit, + TP_PROTO(struct inode *inode, loff_t offset, unsigned int max_blocks, int ret), + + TP_ARGS(inode, offset, max_blocks, ret), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( loff_t, pos ) + __field( unsigned, blocks ) + __field( int, ret ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->pos = offset; + __entry->blocks = max_blocks; + __entry->ret = ret; + ), + + TP_printk("dev %d,%d ino %ld pos %llu blocks %d ret %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned long long) __entry->pos, __entry->blocks, + __entry->ret) +); + +TRACE_EVENT(ext4_unlink_enter, + TP_PROTO(struct inode *parent, struct dentry *dentry), + + TP_ARGS(parent, dentry), + + TP_STRUCT__entry( + __field( ino_t, parent ) + __field( ino_t, ino ) + __field( loff_t, size ) + __field( dev_t, dev ) + ), + + TP_fast_assign( + __entry->parent = parent->i_ino; + __entry->ino = dentry->d_inode->i_ino; + __entry->size = dentry->d_inode->i_size; + __entry->dev = dentry->d_inode->i_sb->s_dev; + ), + + TP_printk("dev %d,%d ino %ld size %lld parent %ld", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, __entry->size, + (unsigned long) __entry->parent) +); + +TRACE_EVENT(ext4_unlink_exit, + TP_PROTO(struct dentry *dentry, int ret), + + TP_ARGS(dentry, ret), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( int, ret ) + ), + + TP_fast_assign( + __entry->ino = dentry->d_inode->i_ino; + __entry->dev = dentry->d_inode->i_sb->s_dev; + __entry->ret = ret; + ), + + TP_printk("dev %d,%d ino %ld ret %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + __entry->ret) +); + +DECLARE_EVENT_CLASS(ext4__truncate, + TP_PROTO(struct inode *inode), + + TP_ARGS(inode), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( blkcnt_t, blocks ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->blocks = inode->i_blocks; + ), + + TP_printk("dev %d,%d ino %lu blocks %lu", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, (unsigned long) __entry->blocks) +); + +DEFINE_EVENT(ext4__truncate, ext4_truncate_enter, + + TP_PROTO(struct inode *inode), + + TP_ARGS(inode) +); + +DEFINE_EVENT(ext4__truncate, ext4_truncate_exit, + + TP_PROTO(struct inode *inode), + + TP_ARGS(inode) +); + +DECLARE_EVENT_CLASS(ext4__map_blocks_enter, + TP_PROTO(struct inode *inode, ext4_lblk_t lblk, + unsigned len, unsigned flags), + + TP_ARGS(inode, lblk, len, flags), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( ext4_lblk_t, lblk ) + __field( unsigned, len ) + __field( unsigned, flags ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->lblk = lblk; + __entry->len = len; + __entry->flags = flags; + ), + + TP_printk("dev %d,%d ino %lu lblk %u len %u flags %u", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned) __entry->lblk, __entry->len, __entry->flags) +); + +DEFINE_EVENT(ext4__map_blocks_enter, ext4_ext_map_blocks_enter, + TP_PROTO(struct inode *inode, ext4_lblk_t lblk, + unsigned len, unsigned flags), + + TP_ARGS(inode, lblk, len, flags) +); + +DEFINE_EVENT(ext4__map_blocks_enter, ext4_ind_map_blocks_enter, + TP_PROTO(struct inode *inode, ext4_lblk_t lblk, + unsigned len, unsigned flags), + + TP_ARGS(inode, lblk, len, flags) +); + +DECLARE_EVENT_CLASS(ext4__map_blocks_exit, + TP_PROTO(struct inode *inode, ext4_lblk_t lblk, + ext4_fsblk_t pblk, unsigned len, int ret), + + TP_ARGS(inode, lblk, pblk, len, ret), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( ext4_lblk_t, lblk ) + __field( ext4_fsblk_t, pblk ) + __field( unsigned, len ) + __field( int, ret ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->lblk = lblk; + __entry->pblk = pblk; + __entry->len = len; + __entry->ret = ret; + ), + + TP_printk("dev %d,%d ino %lu lblk %u pblk %llu len %u ret %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned) __entry->lblk, (unsigned long long) __entry->pblk, + __entry->len, __entry->ret) +); + +DEFINE_EVENT(ext4__map_blocks_exit, ext4_ext_map_blocks_exit, + TP_PROTO(struct inode *inode, ext4_lblk_t lblk, + ext4_fsblk_t pblk, unsigned len, int ret), + + TP_ARGS(inode, lblk, pblk, len, ret) +); + +DEFINE_EVENT(ext4__map_blocks_exit, ext4_ind_map_blocks_exit, + TP_PROTO(struct inode *inode, ext4_lblk_t lblk, + ext4_fsblk_t pblk, unsigned len, int ret), + + TP_ARGS(inode, lblk, pblk, len, ret) +); + +TRACE_EVENT(ext4_ext_load_extent, + TP_PROTO(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk), + + TP_ARGS(inode, lblk, pblk), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( ext4_lblk_t, lblk ) + __field( ext4_fsblk_t, pblk ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->lblk = lblk; + __entry->pblk = pblk; + ), + + TP_printk("dev %d,%d ino %lu lblk %u pblk %llu", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned) __entry->lblk, (unsigned long long) __entry->pblk) +); + +TRACE_EVENT(ext4_load_inode, + TP_PROTO(struct inode *inode), + + TP_ARGS(inode), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + ), + + TP_printk("dev %d,%d ino %ld", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino) +); + #endif /* _TRACE_EXT4_H */ /* This part must be outside protection */ diff --git a/include/trace/events/jbd2.h b/include/trace/events/jbd2.h index 7447ea9305b5..bf16545cc977 100644 --- a/include/trace/events/jbd2.h +++ b/include/trace/events/jbd2.h @@ -17,19 +17,17 @@ TRACE_EVENT(jbd2_checkpoint, TP_ARGS(journal, result), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( int, result ) ), TP_fast_assign( - __entry->dev_major = MAJOR(journal->j_fs_dev->bd_dev); - __entry->dev_minor = MINOR(journal->j_fs_dev->bd_dev); + __entry->dev = journal->j_fs_dev->bd_dev; __entry->result = result; ), - TP_printk("dev %d,%d result %d", - __entry->dev_major, __entry->dev_minor, __entry->result) + TP_printk("dev %s result %d", + jbd2_dev_to_name(__entry->dev), __entry->result) ); DECLARE_EVENT_CLASS(jbd2_commit, @@ -39,22 +37,20 @@ DECLARE_EVENT_CLASS(jbd2_commit, TP_ARGS(journal, commit_transaction), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( char, sync_commit ) __field( int, transaction ) ), TP_fast_assign( - __entry->dev_major = MAJOR(journal->j_fs_dev->bd_dev); - __entry->dev_minor = MINOR(journal->j_fs_dev->bd_dev); + __entry->dev = journal->j_fs_dev->bd_dev; __entry->sync_commit = commit_transaction->t_synchronous_commit; __entry->transaction = commit_transaction->t_tid; ), - TP_printk("dev %d,%d transaction %d sync %d", - __entry->dev_major, __entry->dev_minor, - __entry->transaction, __entry->sync_commit) + TP_printk("dev %s transaction %d sync %d", + jbd2_dev_to_name(__entry->dev), __entry->transaction, + __entry->sync_commit) ); DEFINE_EVENT(jbd2_commit, jbd2_start_commit, @@ -91,24 +87,22 @@ TRACE_EVENT(jbd2_end_commit, TP_ARGS(journal, commit_transaction), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( char, sync_commit ) __field( int, transaction ) __field( int, head ) ), TP_fast_assign( - __entry->dev_major = MAJOR(journal->j_fs_dev->bd_dev); - __entry->dev_minor = MINOR(journal->j_fs_dev->bd_dev); + __entry->dev = journal->j_fs_dev->bd_dev; __entry->sync_commit = commit_transaction->t_synchronous_commit; __entry->transaction = commit_transaction->t_tid; __entry->head = journal->j_tail_sequence; ), - TP_printk("dev %d,%d transaction %d sync %d head %d", - __entry->dev_major, __entry->dev_minor, - __entry->transaction, __entry->sync_commit, __entry->head) + TP_printk("dev %s transaction %d sync %d head %d", + jbd2_dev_to_name(__entry->dev), __entry->transaction, + __entry->sync_commit, __entry->head) ); TRACE_EVENT(jbd2_submit_inode_data, @@ -117,20 +111,17 @@ TRACE_EVENT(jbd2_submit_inode_data, TP_ARGS(inode), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; ), - TP_printk("dev %d,%d ino %lu", - __entry->dev_major, __entry->dev_minor, - (unsigned long) __entry->ino) + TP_printk("dev %s ino %lu", + jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino) ); TRACE_EVENT(jbd2_run_stats, @@ -140,8 +131,7 @@ TRACE_EVENT(jbd2_run_stats, TP_ARGS(dev, tid, stats), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( unsigned long, tid ) __field( unsigned long, wait ) __field( unsigned long, running ) @@ -154,8 +144,7 @@ TRACE_EVENT(jbd2_run_stats, ), TP_fast_assign( - __entry->dev_major = MAJOR(dev); - __entry->dev_minor = MINOR(dev); + __entry->dev = dev; __entry->tid = tid; __entry->wait = stats->rs_wait; __entry->running = stats->rs_running; @@ -167,9 +156,9 @@ TRACE_EVENT(jbd2_run_stats, __entry->blocks_logged = stats->rs_blocks_logged; ), - TP_printk("dev %d,%d tid %lu wait %u running %u locked %u flushing %u " + TP_printk("dev %s tid %lu wait %u running %u locked %u flushing %u " "logging %u handle_count %u blocks %u blocks_logged %u", - __entry->dev_major, __entry->dev_minor, __entry->tid, + jbd2_dev_to_name(__entry->dev), __entry->tid, jiffies_to_msecs(__entry->wait), jiffies_to_msecs(__entry->running), jiffies_to_msecs(__entry->locked), @@ -186,8 +175,7 @@ TRACE_EVENT(jbd2_checkpoint_stats, TP_ARGS(dev, tid, stats), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( unsigned long, tid ) __field( unsigned long, chp_time ) __field( __u32, forced_to_close ) @@ -196,8 +184,7 @@ TRACE_EVENT(jbd2_checkpoint_stats, ), TP_fast_assign( - __entry->dev_major = MAJOR(dev); - __entry->dev_minor = MINOR(dev); + __entry->dev = dev; __entry->tid = tid; __entry->chp_time = stats->cs_chp_time; __entry->forced_to_close= stats->cs_forced_to_close; @@ -205,9 +192,9 @@ TRACE_EVENT(jbd2_checkpoint_stats, __entry->dropped = stats->cs_dropped; ), - TP_printk("dev %d,%d tid %lu chp_time %u forced_to_close %u " + TP_printk("dev %s tid %lu chp_time %u forced_to_close %u " "written %u dropped %u", - __entry->dev_major, __entry->dev_minor, __entry->tid, + jbd2_dev_to_name(__entry->dev), __entry->tid, jiffies_to_msecs(__entry->chp_time), __entry->forced_to_close, __entry->written, __entry->dropped) ); @@ -220,8 +207,7 @@ TRACE_EVENT(jbd2_cleanup_journal_tail, TP_ARGS(journal, first_tid, block_nr, freed), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( tid_t, tail_sequence ) __field( tid_t, first_tid ) __field(unsigned long, block_nr ) @@ -229,18 +215,16 @@ TRACE_EVENT(jbd2_cleanup_journal_tail, ), TP_fast_assign( - __entry->dev_major = MAJOR(journal->j_fs_dev->bd_dev); - __entry->dev_minor = MINOR(journal->j_fs_dev->bd_dev); + __entry->dev = journal->j_fs_dev->bd_dev; __entry->tail_sequence = journal->j_tail_sequence; __entry->first_tid = first_tid; __entry->block_nr = block_nr; __entry->freed = freed; ), - TP_printk("dev %d,%d from %u to %u offset %lu freed %lu", - __entry->dev_major, __entry->dev_minor, - __entry->tail_sequence, __entry->first_tid, - __entry->block_nr, __entry->freed) + TP_printk("dev %s from %u to %u offset %lu freed %lu", + jbd2_dev_to_name(__entry->dev), __entry->tail_sequence, + __entry->first_tid, __entry->block_nr, __entry->freed) ); #endif /* _TRACE_JBD2_H */ diff --git a/ipc/namespace.c b/ipc/namespace.c index 3c3e5223e7e5..8054c8e5faf1 100644 --- a/ipc/namespace.c +++ b/ipc/namespace.c @@ -104,7 +104,6 @@ static void free_ipc_ns(struct ipc_namespace *ns) sem_exit_ns(ns); msg_exit_ns(ns); shm_exit_ns(ns); - kfree(ns); atomic_dec(&nr_ipc_ns); /* @@ -113,6 +112,7 @@ static void free_ipc_ns(struct ipc_namespace *ns) */ ipcns_notify(IPCNS_REMOVED); put_user_ns(ns->user_ns); + kfree(ns); } /* diff --git a/net/sunrpc/auth_gss/gss_mech_switch.c b/net/sunrpc/auth_gss/gss_mech_switch.c index 8b4061049d76..e3c36a274412 100644 --- a/net/sunrpc/auth_gss/gss_mech_switch.c +++ b/net/sunrpc/auth_gss/gss_mech_switch.c @@ -160,6 +160,28 @@ gss_mech_get_by_name(const char *name) EXPORT_SYMBOL_GPL(gss_mech_get_by_name); +struct gss_api_mech * +gss_mech_get_by_OID(struct xdr_netobj *obj) +{ + struct gss_api_mech *pos, *gm = NULL; + + spin_lock(®istered_mechs_lock); + list_for_each_entry(pos, ®istered_mechs, gm_list) { + if (obj->len == pos->gm_oid.len) { + if (0 == memcmp(obj->data, pos->gm_oid.data, obj->len)) { + if (try_module_get(pos->gm_owner)) + gm = pos; + break; + } + } + } + spin_unlock(®istered_mechs_lock); + return gm; + +} + +EXPORT_SYMBOL_GPL(gss_mech_get_by_OID); + static inline int mech_supports_pseudoflavor(struct gss_api_mech *gm, u32 pseudoflavor) { @@ -193,6 +215,22 @@ gss_mech_get_by_pseudoflavor(u32 pseudoflavor) EXPORT_SYMBOL_GPL(gss_mech_get_by_pseudoflavor); +int gss_mech_list_pseudoflavors(rpc_authflavor_t *array_ptr) +{ + struct gss_api_mech *pos = NULL; + int i = 0; + + spin_lock(®istered_mechs_lock); + list_for_each_entry(pos, ®istered_mechs, gm_list) { + array_ptr[i] = pos->gm_pfs->pseudoflavor; + i++; + } + spin_unlock(®istered_mechs_lock); + return i; +} + +EXPORT_SYMBOL_GPL(gss_mech_list_pseudoflavors); + u32 gss_svc_to_pseudoflavor(struct gss_api_mech *gm, u32 service) { diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index be96d429b475..1e336a06d3e6 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -710,6 +710,8 @@ static void xs_reset_transport(struct sock_xprt *transport) if (sk == NULL) return; + transport->srcport = 0; + write_lock_bh(&sk->sk_callback_lock); transport->inet = NULL; transport->sock = NULL; |