diff options
377 files changed, 6008 insertions, 3448 deletions
diff --git a/Documentation/ABI/testing/sysfs-power b/Documentation/ABI/testing/sysfs-power index 1e0d1dac706b..2f813d644c69 100644 --- a/Documentation/ABI/testing/sysfs-power +++ b/Documentation/ABI/testing/sysfs-power @@ -287,3 +287,17 @@ Description: Writing a "1" to this file enables the debug messages and writing a "0" (default) to it disables them. Reads from this file return the current value. + +What: /sys/power/resume_offset +Date: April 2018 +Contact: Mario Limonciello <mario.limonciello@dell.com> +Description: + This file is used for telling the kernel an offset into a disk + to use when hibernating the system such as with a swap file. + + Reads from this file will display the current offset + the kernel will be using on the next hibernation + attempt. + + Using this sysfs file will override any values that were + set using the kernel command line for disk offset.
\ No newline at end of file diff --git a/Documentation/accelerators/ocxl.rst b/Documentation/accelerators/ocxl.rst index 4f7af841d935..ddcc58d01cfb 100644 --- a/Documentation/accelerators/ocxl.rst +++ b/Documentation/accelerators/ocxl.rst @@ -152,6 +152,11 @@ OCXL_IOCTL_IRQ_SET_FD: Associate an event fd to an AFU interrupt so that the user process can be notified when the AFU sends an interrupt. +OCXL_IOCTL_GET_METADATA: + + Obtains configuration information from the card, such at the size of + MMIO areas, the AFU version, and the PASID for the current context. + mmap ---- diff --git a/Documentation/devicetree/bindings/cpufreq/cpufreq-dt.txt b/Documentation/devicetree/bindings/cpufreq/cpufreq-dt.txt index dd3929e85dec..332aed8f4597 100644 --- a/Documentation/devicetree/bindings/cpufreq/cpufreq-dt.txt +++ b/Documentation/devicetree/bindings/cpufreq/cpufreq-dt.txt @@ -18,8 +18,6 @@ Optional properties: in unit of nanoseconds. - voltage-tolerance: Specify the CPU voltage tolerance in percentage. - #cooling-cells: -- cooling-min-level: -- cooling-max-level: Please refer to Documentation/devicetree/bindings/thermal/thermal.txt. Examples: @@ -40,8 +38,6 @@ cpus { >; clock-latency = <61036>; /* two CLK32 periods */ #cooling-cells = <2>; - cooling-min-level = <0>; - cooling-max-level = <2>; }; cpu@1 { diff --git a/Documentation/devicetree/bindings/cpufreq/cpufreq-mediatek.txt b/Documentation/devicetree/bindings/cpufreq/cpufreq-mediatek.txt index f6403089edcf..d36f07e0a2bb 100644 --- a/Documentation/devicetree/bindings/cpufreq/cpufreq-mediatek.txt +++ b/Documentation/devicetree/bindings/cpufreq/cpufreq-mediatek.txt @@ -21,8 +21,6 @@ Optional properties: flow is handled by hardware, hence no software "voltage tracking" is needed. - #cooling-cells: -- cooling-min-level: -- cooling-max-level: Please refer to Documentation/devicetree/bindings/thermal/thermal.txt for detail. @@ -67,8 +65,6 @@ Example 1 (MT7623 SoC): clock-names = "cpu", "intermediate"; operating-points-v2 = <&cpu_opp_table>; #cooling-cells = <2>; - cooling-min-level = <0>; - cooling-max-level = <7>; }; cpu@1 { device_type = "cpu"; diff --git a/Documentation/devicetree/bindings/dma/mv-xor-v2.txt b/Documentation/devicetree/bindings/dma/mv-xor-v2.txt index 217a90eaabe7..9c38bbe7e6d7 100644 --- a/Documentation/devicetree/bindings/dma/mv-xor-v2.txt +++ b/Documentation/devicetree/bindings/dma/mv-xor-v2.txt @@ -11,7 +11,11 @@ Required properties: interrupts. Optional properties: -- clocks: Optional reference to the clock used by the XOR engine. +- clocks: Optional reference to the clocks used by the XOR engine. +- clock-names: mandatory if there is a second clock, in this case the + name must be "core" for the first clock and "reg" for the second + one + Example: diff --git a/Documentation/devicetree/bindings/net/renesas,ravb.txt b/Documentation/devicetree/bindings/net/renesas,ravb.txt index c902261893b9..92fd4b2f17b2 100644 --- a/Documentation/devicetree/bindings/net/renesas,ravb.txt +++ b/Documentation/devicetree/bindings/net/renesas,ravb.txt @@ -18,6 +18,7 @@ Required properties: - "renesas,etheravb-r8a7795" for the R8A7795 SoC. - "renesas,etheravb-r8a7796" for the R8A7796 SoC. - "renesas,etheravb-r8a77970" for the R8A77970 SoC. + - "renesas,etheravb-r8a77980" for the R8A77980 SoC. - "renesas,etheravb-r8a77995" for the R8A77995 SoC. - "renesas,etheravb-rcar-gen3" as a fallback for the above R-Car Gen3 devices. diff --git a/Documentation/ia64/serial.txt b/Documentation/ia64/serial.txt index 6869c73de4e2..a63d2c54329b 100644 --- a/Documentation/ia64/serial.txt +++ b/Documentation/ia64/serial.txt @@ -111,7 +111,7 @@ TROUBLESHOOTING SERIAL CONSOLE PROBLEMS - If you don't have an HCDP, the kernel doesn't know where your console lives until the driver discovers serial - devices. Use "console=uart, io,0x3f8" (or appropriate + devices. Use "console=uart,io,0x3f8" (or appropriate address for your machine). Kernel and init script output works fine, but no "login:" prompt: diff --git a/Documentation/power/swsusp.txt b/Documentation/power/swsusp.txt index 9f2f942a01cf..cc87adf44c0a 100644 --- a/Documentation/power/swsusp.txt +++ b/Documentation/power/swsusp.txt @@ -24,8 +24,16 @@ Some warnings, first. * see the FAQ below for details. (This is not true for more traditional * power states like "standby", which normally don't turn USB off.) +Swap partition: You need to append resume=/dev/your_swap_partition to kernel command -line. Then you suspend by +line or specify it using /sys/power/resume. + +Swap file: +If using a swapfile you can also specify a resume offset using +resume_offset=<number> on the kernel command line or specify it +in /sys/power/resume_offset. + +After preparing then you suspend by echo shutdown > /sys/power/disk; echo disk > /sys/power/state diff --git a/Documentation/sphinx/kerneldoc.py b/Documentation/sphinx/kerneldoc.py index 39aa9e8697cc..fbedcc39460b 100644 --- a/Documentation/sphinx/kerneldoc.py +++ b/Documentation/sphinx/kerneldoc.py @@ -36,8 +36,7 @@ import glob from docutils import nodes, statemachine from docutils.statemachine import ViewList -from docutils.parsers.rst import directives -from sphinx.util.compat import Directive +from docutils.parsers.rst import directives, Directive from sphinx.ext.autodoc import AutodocReporter __version__ = '1.0' @@ -2,7 +2,7 @@ VERSION = 4 PATCHLEVEL = 16 SUBLEVEL = 0 -EXTRAVERSION = -rc4 +EXTRAVERSION = -rc5 NAME = Fearless Coyote # *DOCUMENTATION* diff --git a/arch/arm/boot/dts/mt7623.dtsi b/arch/arm/boot/dts/mt7623.dtsi index b750da5362f7..8e7c65464c9d 100644 --- a/arch/arm/boot/dts/mt7623.dtsi +++ b/arch/arm/boot/dts/mt7623.dtsi @@ -87,8 +87,6 @@ clock-names = "cpu", "intermediate"; operating-points-v2 = <&cpu_opp_table>; #cooling-cells = <2>; - cooling-min-level = <0>; - cooling-max-level = <7>; clock-frequency = <1300000000>; }; diff --git a/arch/arm/mach-orion5x/Kconfig b/arch/arm/mach-orion5x/Kconfig index 2a7bb6ccdcb7..a810f4dd34b1 100644 --- a/arch/arm/mach-orion5x/Kconfig +++ b/arch/arm/mach-orion5x/Kconfig @@ -58,7 +58,6 @@ config MACH_KUROBOX_PRO config MACH_DNS323 bool "D-Link DNS-323" - select GENERIC_NET_UTILS select I2C_BOARDINFO if I2C help Say 'Y' here if you want your kernel to support the @@ -66,7 +65,6 @@ config MACH_DNS323 config MACH_TS209 bool "QNAP TS-109/TS-209" - select GENERIC_NET_UTILS help Say 'Y' here if you want your kernel to support the QNAP TS-109/TS-209 platform. @@ -101,7 +99,6 @@ config MACH_LINKSTATION_LS_HGL config MACH_TS409 bool "QNAP TS-409" - select GENERIC_NET_UTILS help Say 'Y' here if you want your kernel to support the QNAP TS-409 platform. diff --git a/arch/arm/mach-orion5x/dns323-setup.c b/arch/arm/mach-orion5x/dns323-setup.c index cd483bfb5ca8..d13344b2ddcd 100644 --- a/arch/arm/mach-orion5x/dns323-setup.c +++ b/arch/arm/mach-orion5x/dns323-setup.c @@ -173,10 +173,42 @@ static struct mv643xx_eth_platform_data dns323_eth_data = { .phy_addr = MV643XX_ETH_PHY_ADDR(8), }; +/* dns323_parse_hex_*() taken from tsx09-common.c; should a common copy of these + * functions be kept somewhere? + */ +static int __init dns323_parse_hex_nibble(char n) +{ + if (n >= '0' && n <= '9') + return n - '0'; + + if (n >= 'A' && n <= 'F') + return n - 'A' + 10; + + if (n >= 'a' && n <= 'f') + return n - 'a' + 10; + + return -1; +} + +static int __init dns323_parse_hex_byte(const char *b) +{ + int hi; + int lo; + + hi = dns323_parse_hex_nibble(b[0]); + lo = dns323_parse_hex_nibble(b[1]); + + if (hi < 0 || lo < 0) + return -1; + + return (hi << 4) | lo; +} + static int __init dns323_read_mac_addr(void) { u_int8_t addr[6]; - void __iomem *mac_page; + int i; + char *mac_page; /* MAC address is stored as a regular ol' string in /dev/mtdblock4 * (0x007d0000-0x00800000) starting at offset 196480 (0x2ff80). @@ -185,8 +217,23 @@ static int __init dns323_read_mac_addr(void) if (!mac_page) return -ENOMEM; - if (!mac_pton((__force const char *) mac_page, addr)) - goto error_fail; + /* Sanity check the string we're looking at */ + for (i = 0; i < 5; i++) { + if (*(mac_page + (i * 3) + 2) != ':') { + goto error_fail; + } + } + + for (i = 0; i < 6; i++) { + int byte; + + byte = dns323_parse_hex_byte(mac_page + (i * 3)); + if (byte < 0) { + goto error_fail; + } + + addr[i] = byte; + } iounmap(mac_page); printk("DNS-323: Found ethernet MAC address: %pM\n", addr); diff --git a/arch/arm/mach-orion5x/tsx09-common.c b/arch/arm/mach-orion5x/tsx09-common.c index 89774985d380..905d4f2dd0b8 100644 --- a/arch/arm/mach-orion5x/tsx09-common.c +++ b/arch/arm/mach-orion5x/tsx09-common.c @@ -53,12 +53,53 @@ struct mv643xx_eth_platform_data qnap_tsx09_eth_data = { .phy_addr = MV643XX_ETH_PHY_ADDR(8), }; +static int __init qnap_tsx09_parse_hex_nibble(char n) +{ + if (n >= '0' && n <= '9') + return n - '0'; + + if (n >= 'A' && n <= 'F') + return n - 'A' + 10; + + if (n >= 'a' && n <= 'f') + return n - 'a' + 10; + + return -1; +} + +static int __init qnap_tsx09_parse_hex_byte(const char *b) +{ + int hi; + int lo; + + hi = qnap_tsx09_parse_hex_nibble(b[0]); + lo = qnap_tsx09_parse_hex_nibble(b[1]); + + if (hi < 0 || lo < 0) + return -1; + + return (hi << 4) | lo; +} + static int __init qnap_tsx09_check_mac_addr(const char *addr_str) { u_int8_t addr[6]; + int i; - if (!mac_pton(addr_str, addr)) - return -1; + for (i = 0; i < 6; i++) { + int byte; + + /* + * Enforce "xx:xx:xx:xx:xx:xx\n" format. + */ + if (addr_str[(i * 3) + 2] != ((i < 5) ? ':' : '\n')) + return -1; + + byte = qnap_tsx09_parse_hex_byte(addr_str + (i * 3)); + if (byte < 0) + return -1; + addr[i] = byte; + } printk(KERN_INFO "tsx09: found ethernet mac address %pM\n", addr); @@ -77,12 +118,12 @@ void __init qnap_tsx09_find_mac_addr(u32 mem_base, u32 size) unsigned long addr; for (addr = mem_base; addr < (mem_base + size); addr += 1024) { - void __iomem *nor_page; + char *nor_page; int ret = 0; nor_page = ioremap(addr, 1024); if (nor_page != NULL) { - ret = qnap_tsx09_check_mac_addr((__force const char *)nor_page); + ret = qnap_tsx09_check_mac_addr(nor_page); iounmap(nor_page); } diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 52f15cd896e1..b5a28336c077 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -178,7 +178,7 @@ static int enable_smccc_arch_workaround_1(void *data) case PSCI_CONDUIT_HVC: arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, ARM_SMCCC_ARCH_WORKAROUND_1, &res); - if (res.a0) + if ((int)res.a0 < 0) return 0; cb = call_hvc_arch_workaround_1; smccc_start = __smccc_workaround_1_hvc_start; @@ -188,7 +188,7 @@ static int enable_smccc_arch_workaround_1(void *data) case PSCI_CONDUIT_SMC: arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, ARM_SMCCC_ARCH_WORKAROUND_1, &res); - if (res.a0) + if ((int)res.a0 < 0) return 0; cb = call_smc_arch_workaround_1; smccc_start = __smccc_workaround_1_smc_start; diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 84a019f55022..8c704f1e53c2 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -108,7 +108,7 @@ static bool pgattr_change_is_safe(u64 old, u64 new) * The following mapping attributes may be updated in live * kernel mappings without the need for break-before-make. */ - static const pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE; + static const pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE | PTE_NG; /* creating or taking down mappings is always safe */ if (old == 0 || new == 0) @@ -118,9 +118,9 @@ static bool pgattr_change_is_safe(u64 old, u64 new) if ((old | new) & PTE_CONT) return false; - /* Transitioning from Global to Non-Global is safe */ - if (((old ^ new) == PTE_NG) && (new & PTE_NG)) - return true; + /* Transitioning from Non-Global to Global is unsafe */ + if (old & ~new & PTE_NG) + return false; return ((old ^ new) & ~mask) == 0; } diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h index 762eeb0fcc1d..2524fb60fbc2 100644 --- a/arch/ia64/include/asm/atomic.h +++ b/arch/ia64/include/asm/atomic.h @@ -66,38 +66,35 @@ ATOMIC_OPS(add, +) ATOMIC_OPS(sub, -) #ifdef __OPTIMIZE__ -#define __ia64_atomic_const(i) __builtin_constant_p(i) ? \ +#define __ia64_atomic_const(i) \ + static const int __ia64_atomic_p = __builtin_constant_p(i) ? \ ((i) == 1 || (i) == 4 || (i) == 8 || (i) == 16 || \ - (i) == -1 || (i) == -4 || (i) == -8 || (i) == -16) : 0 + (i) == -1 || (i) == -4 || (i) == -8 || (i) == -16) : 0;\ + __ia64_atomic_p +#else +#define __ia64_atomic_const(i) 0 +#endif -#define atomic_add_return(i, v) \ +#define atomic_add_return(i,v) \ ({ \ - int __i = (i); \ - static const int __ia64_atomic_p = __ia64_atomic_const(i); \ - __ia64_atomic_p ? ia64_fetch_and_add(__i, &(v)->counter) : \ - ia64_atomic_add(__i, v); \ + int __ia64_aar_i = (i); \ + __ia64_atomic_const(i) \ + ? ia64_fetch_and_add(__ia64_aar_i, &(v)->counter) \ + : ia64_atomic_add(__ia64_aar_i, v); \ }) -#define atomic_sub_return(i, v) \ +#define atomic_sub_return(i,v) \ ({ \ - int __i = (i); \ - static const int __ia64_atomic_p = __ia64_atomic_const(i); \ - __ia64_atomic_p ? ia64_fetch_and_add(-__i, &(v)->counter) : \ - ia64_atomic_sub(__i, v); \ + int __ia64_asr_i = (i); \ + __ia64_atomic_const(i) \ + ? ia64_fetch_and_add(-__ia64_asr_i, &(v)->counter) \ + : ia64_atomic_sub(__ia64_asr_i, v); \ }) -#else -#define atomic_add_return(i, v) ia64_atomic_add(i, v) -#define atomic_sub_return(i, v) ia64_atomic_sub(i, v) -#endif #define atomic_fetch_add(i,v) \ ({ \ int __ia64_aar_i = (i); \ - (__builtin_constant_p(i) \ - && ( (__ia64_aar_i == 1) || (__ia64_aar_i == 4) \ - || (__ia64_aar_i == 8) || (__ia64_aar_i == 16) \ - || (__ia64_aar_i == -1) || (__ia64_aar_i == -4) \ - || (__ia64_aar_i == -8) || (__ia64_aar_i == -16))) \ + __ia64_atomic_const(i) \ ? ia64_fetchadd(__ia64_aar_i, &(v)->counter, acq) \ : ia64_atomic_fetch_add(__ia64_aar_i, v); \ }) @@ -105,11 +102,7 @@ ATOMIC_OPS(sub, -) #define atomic_fetch_sub(i,v) \ ({ \ int __ia64_asr_i = (i); \ - (__builtin_constant_p(i) \ - && ( (__ia64_asr_i == 1) || (__ia64_asr_i == 4) \ - || (__ia64_asr_i == 8) || (__ia64_asr_i == 16) \ - || (__ia64_asr_i == -1) || (__ia64_asr_i == -4) \ - || (__ia64_asr_i == -8) || (__ia64_asr_i == -16))) \ + __ia64_atomic_const(i) \ ? ia64_fetchadd(-__ia64_asr_i, &(v)->counter, acq) \ : ia64_atomic_fetch_sub(__ia64_asr_i, v); \ }) @@ -170,11 +163,7 @@ ATOMIC64_OPS(sub, -) #define atomic64_add_return(i,v) \ ({ \ long __ia64_aar_i = (i); \ - (__builtin_constant_p(i) \ - && ( (__ia64_aar_i == 1) || (__ia64_aar_i == 4) \ - || (__ia64_aar_i == 8) || (__ia64_aar_i == 16) \ - || (__ia64_aar_i == -1) || (__ia64_aar_i == -4) \ - || (__ia64_aar_i == -8) || (__ia64_aar_i == -16))) \ + __ia64_atomic_const(i) \ ? ia64_fetch_and_add(__ia64_aar_i, &(v)->counter) \ : ia64_atomic64_add(__ia64_aar_i, v); \ }) @@ -182,11 +171,7 @@ ATOMIC64_OPS(sub, -) #define atomic64_sub_return(i,v) \ ({ \ long __ia64_asr_i = (i); \ - (__builtin_constant_p(i) \ - && ( (__ia64_asr_i == 1) || (__ia64_asr_i == 4) \ - || (__ia64_asr_i == 8) || (__ia64_asr_i == 16) \ - || (__ia64_asr_i == -1) || (__ia64_asr_i == -4) \ - || (__ia64_asr_i == -8) || (__ia64_asr_i == -16))) \ + __ia64_atomic_const(i) \ ? ia64_fetch_and_add(-__ia64_asr_i, &(v)->counter) \ : ia64_atomic64_sub(__ia64_asr_i, v); \ }) @@ -194,11 +179,7 @@ ATOMIC64_OPS(sub, -) #define atomic64_fetch_add(i,v) \ ({ \ long __ia64_aar_i = (i); \ - (__builtin_constant_p(i) \ - && ( (__ia64_aar_i == 1) || (__ia64_aar_i == 4) \ - || (__ia64_aar_i == 8) || (__ia64_aar_i == 16) \ - || (__ia64_aar_i == -1) || (__ia64_aar_i == -4) \ - || (__ia64_aar_i == -8) || (__ia64_aar_i == -16))) \ + __ia64_atomic_const(i) \ ? ia64_fetchadd(__ia64_aar_i, &(v)->counter, acq) \ : ia64_atomic64_fetch_add(__ia64_aar_i, v); \ }) @@ -206,11 +187,7 @@ ATOMIC64_OPS(sub, -) #define atomic64_fetch_sub(i,v) \ ({ \ long __ia64_asr_i = (i); \ - (__builtin_constant_p(i) \ - && ( (__ia64_asr_i == 1) || (__ia64_asr_i == 4) \ - || (__ia64_asr_i == 8) || (__ia64_asr_i == 16) \ - || (__ia64_asr_i == -1) || (__ia64_asr_i == -4) \ - || (__ia64_asr_i == -8) || (__ia64_asr_i == -16))) \ + __ia64_atomic_const(i) \ ? ia64_fetchadd(-__ia64_asr_i, &(v)->counter, acq) \ : ia64_atomic64_fetch_sub(__ia64_asr_i, v); \ }) diff --git a/arch/ia64/kernel/err_inject.c b/arch/ia64/kernel/err_inject.c index 85bba43e7d5d..8b5b8e6bc9d9 100644 --- a/arch/ia64/kernel/err_inject.c +++ b/arch/ia64/kernel/err_inject.c @@ -117,7 +117,7 @@ store_call_start(struct device *dev, struct device_attribute *attr, #ifdef ERR_INJ_DEBUG printk(KERN_DEBUG "Returns: status=%d,\n", (int)status[cpu]); - printk(KERN_DEBUG "capapbilities=%lx,\n", capabilities[cpu]); + printk(KERN_DEBUG "capabilities=%lx,\n", capabilities[cpu]); printk(KERN_DEBUG "resources=%lx\n", resources[cpu]); #endif return size; @@ -142,7 +142,7 @@ store_virtual_to_phys(struct device *dev, struct device_attribute *attr, u64 virt_addr=simple_strtoull(buf, NULL, 16); int ret; - ret = get_user_pages(virt_addr, 1, FOLL_WRITE, NULL, NULL); + ret = get_user_pages_fast(virt_addr, 1, FOLL_WRITE, NULL); if (ret<=0) { #ifdef ERR_INJ_DEBUG printk("Virtual address %lx is not existing.\n",virt_addr); diff --git a/arch/ia64/scripts/unwcheck.py b/arch/ia64/scripts/unwcheck.py index 89f3a1480a63..c55276e31b6b 100644 --- a/arch/ia64/scripts/unwcheck.py +++ b/arch/ia64/scripts/unwcheck.py @@ -16,7 +16,7 @@ import re import sys if len(sys.argv) != 2: - print "Usage: %s FILE" % sys.argv[0] + print("Usage: %s FILE" % sys.argv[0]) sys.exit(2) readelf = os.getenv("READELF", "readelf") @@ -29,7 +29,7 @@ def check_func (func, slots, rlen_sum): global num_errors num_errors += 1 if not func: func = "[%#x-%#x]" % (start, end) - print "ERROR: %s: %lu slots, total region length = %lu" % (func, slots, rlen_sum) + print("ERROR: %s: %lu slots, total region length = %lu" % (func, slots, rlen_sum)) return num_funcs = 0 @@ -43,23 +43,23 @@ for line in os.popen("%s -u %s" % (readelf, sys.argv[1])): check_func(func, slots, rlen_sum) func = m.group(1) - start = long(m.group(2), 16) - end = long(m.group(3), 16) + start = int(m.group(2), 16) + end = int(m.group(3), 16) slots = 3 * (end - start) / 16 - rlen_sum = 0L + rlen_sum = 0 num_funcs += 1 else: m = rlen_pattern.match(line) if m: - rlen_sum += long(m.group(1)) + rlen_sum += int(m.group(1)) check_func(func, slots, rlen_sum) if num_errors == 0: - print "No errors detected in %u functions." % num_funcs + print("No errors detected in %u functions." % num_funcs) else: if num_errors > 1: err="errors" else: err="error" - print "%u %s detected in %u functions." % (num_errors, err, num_funcs) + print("%u %s detected in %u functions." % (num_errors, err, num_funcs)) sys.exit(1) diff --git a/arch/mips/ath25/board.c b/arch/mips/ath25/board.c index 9ab48ff80c1c..6d11ae581ea7 100644 --- a/arch/mips/ath25/board.c +++ b/arch/mips/ath25/board.c @@ -135,6 +135,8 @@ int __init ath25_find_config(phys_addr_t base, unsigned long size) } board_data = kzalloc(BOARD_CONFIG_BUFSZ, GFP_KERNEL); + if (!board_data) + goto error; ath25_board.config = (struct ath25_boarddata *)board_data; memcpy_fromio(board_data, bcfg, 0x100); if (broken_boarddata) { diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c index 5b3a3f6a9ad3..d99f5242169e 100644 --- a/arch/mips/cavium-octeon/octeon-irq.c +++ b/arch/mips/cavium-octeon/octeon-irq.c @@ -2277,6 +2277,8 @@ static int __init octeon_irq_init_cib(struct device_node *ciu_node, } host_data = kzalloc(sizeof(*host_data), GFP_KERNEL); + if (!host_data) + return -ENOMEM; raw_spin_lock_init(&host_data->lock); addr = of_get_address(ciu_node, 0, NULL, NULL); diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c index 9d41732a9146..159e83add4bb 100644 --- a/arch/mips/kernel/smp-bmips.c +++ b/arch/mips/kernel/smp-bmips.c @@ -168,11 +168,11 @@ static void bmips_prepare_cpus(unsigned int max_cpus) return; } - if (request_irq(IPI0_IRQ, bmips_ipi_interrupt, IRQF_PERCPU, - "smp_ipi0", NULL)) + if (request_irq(IPI0_IRQ, bmips_ipi_interrupt, + IRQF_PERCPU | IRQF_NO_SUSPEND, "smp_ipi0", NULL)) panic("Can't request IPI0 interrupt"); - if (request_irq(IPI1_IRQ, bmips_ipi_interrupt, IRQF_PERCPU, - "smp_ipi1", NULL)) + if (request_irq(IPI1_IRQ, bmips_ipi_interrupt, + IRQF_PERCPU | IRQF_NO_SUSPEND, "smp_ipi1", NULL)) panic("Can't request IPI1 interrupt"); } diff --git a/arch/mips/loongson64/Kconfig b/arch/mips/loongson64/Kconfig index bc2fdbfa8223..72af0c183969 100644 --- a/arch/mips/loongson64/Kconfig +++ b/arch/mips/loongson64/Kconfig @@ -7,6 +7,8 @@ choice config LEMOTE_FULOONG2E bool "Lemote Fuloong(2e) mini-PC" select ARCH_SPARSEMEM_ENABLE + select ARCH_MIGHT_HAVE_PC_PARPORT + select ARCH_MIGHT_HAVE_PC_SERIO select CEVT_R4K select CSRC_R4K select SYS_HAS_CPU_LOONGSON2E @@ -33,6 +35,8 @@ config LEMOTE_FULOONG2E config LEMOTE_MACH2F bool "Lemote Loongson 2F family machines" select ARCH_SPARSEMEM_ENABLE + select ARCH_MIGHT_HAVE_PC_PARPORT + select ARCH_MIGHT_HAVE_PC_SERIO select BOARD_SCACHE select BOOT_ELF32 select CEVT_R4K if ! MIPS_EXTERNAL_TIMER @@ -62,6 +66,8 @@ config LEMOTE_MACH2F config LOONGSON_MACH3X bool "Generic Loongson 3 family machines" select ARCH_SPARSEMEM_ENABLE + select ARCH_MIGHT_HAVE_PC_PARPORT + select ARCH_MIGHT_HAVE_PC_SERIO select GENERIC_ISA_DMA_SUPPORT_BROKEN select BOOT_ELF32 select BOARD_SCACHE diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index ef6549e57157..26d5d2a5b8e9 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -101,7 +101,8 @@ $(addprefix $(obj)/,$(zlib-y)): \ libfdt := fdt.c fdt_ro.c fdt_wip.c fdt_sw.c fdt_rw.c fdt_strerror.c libfdtheader := fdt.h libfdt.h libfdt_internal.h -$(addprefix $(obj)/,$(libfdt) libfdt-wrapper.o simpleboot.o epapr.o opal.o): \ +$(addprefix $(obj)/,$(libfdt) libfdt-wrapper.o simpleboot.o epapr.o opal.o \ + treeboot-akebono.o treeboot-currituck.o treeboot-iss4xx.o): \ $(addprefix $(obj)/,$(libfdtheader)) src-wlib-y := string.S crt0.S stdio.c decompress.c main.c \ diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index d22c41c26bb3..acf4b2e0530c 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -874,7 +874,6 @@ struct ibm_arch_vec __cacheline_aligned ibm_architecture_vec = { .mmu = 0, .hash_ext = 0, .radix_ext = 0, - .byte22 = 0, }, /* option vector 6: IBM PAPR hints */ diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 0c854816e653..5cb4e4687107 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -195,6 +195,12 @@ static void kvmppc_pte_free(pte_t *ptep) kmem_cache_free(kvm_pte_cache, ptep); } +/* Like pmd_huge() and pmd_large(), but works regardless of config options */ +static inline int pmd_is_leaf(pmd_t pmd) +{ + return !!(pmd_val(pmd) & _PAGE_PTE); +} + static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa, unsigned int level, unsigned long mmu_seq) { @@ -219,7 +225,7 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa, else new_pmd = pmd_alloc_one(kvm->mm, gpa); - if (level == 0 && !(pmd && pmd_present(*pmd))) + if (level == 0 && !(pmd && pmd_present(*pmd) && !pmd_is_leaf(*pmd))) new_ptep = kvmppc_pte_alloc(); /* Check if we might have been invalidated; let the guest retry if so */ @@ -244,12 +250,30 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa, new_pmd = NULL; } pmd = pmd_offset(pud, gpa); - if (pmd_large(*pmd)) { - /* Someone else has instantiated a large page here; retry */ - ret = -EAGAIN; - goto out_unlock; - } - if (level == 1 && !pmd_none(*pmd)) { + if (pmd_is_leaf(*pmd)) { + unsigned long lgpa = gpa & PMD_MASK; + + /* + * If we raced with another CPU which has just put + * a 2MB pte in after we saw a pte page, try again. + */ + if (level == 0 && !new_ptep) { + ret = -EAGAIN; + goto out_unlock; + } + /* Valid 2MB page here already, remove it */ + old = kvmppc_radix_update_pte(kvm, pmdp_ptep(pmd), + ~0UL, 0, lgpa, PMD_SHIFT); + kvmppc_radix_tlbie_page(kvm, lgpa, PMD_SHIFT); + if (old & _PAGE_DIRTY) { + unsigned long gfn = lgpa >> PAGE_SHIFT; + struct kvm_memory_slot *memslot; + memslot = gfn_to_memslot(kvm, gfn); + if (memslot && memslot->dirty_bitmap) + kvmppc_update_dirty_map(memslot, + gfn, PMD_SIZE); + } + } else if (level == 1 && !pmd_none(*pmd)) { /* * There's a page table page here, but we wanted * to install a large page. Tell the caller and let @@ -412,28 +436,24 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, } else { page = pages[0]; pfn = page_to_pfn(page); - if (PageHuge(page)) { - page = compound_head(page); - pte_size <<= compound_order(page); + if (PageCompound(page)) { + pte_size <<= compound_order(compound_head(page)); /* See if we can insert a 2MB large-page PTE here */ if (pte_size >= PMD_SIZE && - (gpa & PMD_MASK & PAGE_MASK) == - (hva & PMD_MASK & PAGE_MASK)) { + (gpa & (PMD_SIZE - PAGE_SIZE)) == + (hva & (PMD_SIZE - PAGE_SIZE))) { level = 1; pfn &= ~((PMD_SIZE >> PAGE_SHIFT) - 1); } } /* See if we can provide write access */ if (writing) { - /* - * We assume gup_fast has set dirty on the host PTE. - */ pgflags |= _PAGE_WRITE; } else { local_irq_save(flags); ptep = find_current_mm_pte(current->mm->pgd, hva, NULL, NULL); - if (ptep && pte_write(*ptep) && pte_dirty(*ptep)) + if (ptep && pte_write(*ptep)) pgflags |= _PAGE_WRITE; local_irq_restore(flags); } @@ -459,18 +479,15 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, pte = pfn_pte(pfn, __pgprot(pgflags)); ret = kvmppc_create_pte(kvm, pte, gpa, level, mmu_seq); } - if (ret == 0 || ret == -EAGAIN) - ret = RESUME_GUEST; if (page) { - /* - * We drop pages[0] here, not page because page might - * have been set to the head page of a compound, but - * we have to drop the reference on the correct tail - * page to match the get inside gup() - */ - put_page(pages[0]); + if (!ret && (pgflags & _PAGE_WRITE)) + set_page_dirty_lock(page); + put_page(page); } + + if (ret == 0 || ret == -EAGAIN) + ret = RESUME_GUEST; return ret; } @@ -644,7 +661,7 @@ void kvmppc_free_radix(struct kvm *kvm) continue; pmd = pmd_offset(pud, 0); for (im = 0; im < PTRS_PER_PMD; ++im, ++pmd) { - if (pmd_huge(*pmd)) { + if (pmd_is_leaf(*pmd)) { pmd_clear(pmd); continue; } diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 89707354c2ef..9cb9448163c4 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -2885,7 +2885,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) */ trace_hardirqs_on(); - guest_enter(); + guest_enter_irqoff(); srcu_idx = srcu_read_lock(&vc->kvm->srcu); @@ -2893,8 +2893,6 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) srcu_read_unlock(&vc->kvm->srcu, srcu_idx); - guest_exit(); - trace_hardirqs_off(); set_irq_happened(trap); @@ -2937,6 +2935,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) kvmppc_set_host_core(pcpu); local_irq_enable(); + guest_exit(); /* Let secondaries go back to the offline loop */ for (i = 0; i < controlled_threads; ++i) { @@ -3656,15 +3655,17 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) goto up_out; psize = vma_kernel_pagesize(vma); - porder = __ilog2(psize); up_read(¤t->mm->mmap_sem); /* We can handle 4k, 64k or 16M pages in the VRMA */ - err = -EINVAL; - if (!(psize == 0x1000 || psize == 0x10000 || - psize == 0x1000000)) - goto out_srcu; + if (psize >= 0x1000000) + psize = 0x1000000; + else if (psize >= 0x10000) + psize = 0x10000; + else + psize = 0x1000; + porder = __ilog2(psize); senc = slb_pgsize_encoding(psize); kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T | diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 403e642c78f5..52c205373986 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -1345,7 +1345,7 @@ static int kvmppc_emulate_mmio_vsx_loadstore(struct kvm_vcpu *vcpu, int kvmppc_handle_load128_by2x64(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned int rt, int is_default_endian) { - enum emulation_result emulated; + enum emulation_result emulated = EMULATE_DONE; while (vcpu->arch.mmio_vmx_copy_nums) { emulated = __kvmppc_handle_load(run, vcpu, rt, 8, @@ -1608,7 +1608,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) kvm_sigset_deactivate(vcpu); +#ifdef CONFIG_ALTIVEC out: +#endif vcpu_put(vcpu); return r; } diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 0a34b0cec7b7..0ef3d9580e98 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -240,6 +240,7 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 * goto out; */ PPC_LWZ(b2p[TMP_REG_1], b2p_bpf_array, offsetof(struct bpf_array, map.max_entries)); + PPC_RLWINM(b2p_index, b2p_index, 0, 0, 31); PPC_CMPLW(b2p_index, b2p[TMP_REG_1]); PPC_BCC(COND_GE, out); diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index 65154eaa3714..6c8ce15cde7b 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -63,6 +63,7 @@ static inline int init_new_context(struct task_struct *tsk, _ASCE_USER_BITS | _ASCE_TYPE_SEGMENT; /* pgd_alloc() did not account this pmd */ mm_inc_nr_pmds(mm); + mm_inc_nr_puds(mm); } crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm)); return 0; diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 13a133a6015c..a5621ea6d123 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -14,6 +14,7 @@ #include <asm/processor.h> #include <asm/cache.h> #include <asm/ctl_reg.h> +#include <asm/dwarf.h> #include <asm/errno.h> #include <asm/ptrace.h> #include <asm/thread_info.h> @@ -230,7 +231,7 @@ _PIF_WORK = (_PIF_PER_TRAP | _PIF_SYSCALL_RESTART) .hidden \name .type \name,@function \name: - .cfi_startproc + CFI_STARTPROC #ifdef CONFIG_HAVE_MARCH_Z10_FEATURES exrl 0,0f #else @@ -239,7 +240,7 @@ _PIF_WORK = (_PIF_PER_TRAP | _PIF_SYSCALL_RESTART) #endif j . 0: br \reg - .cfi_endproc + CFI_ENDPROC .endm GEN_BR_THUNK __s390x_indirect_jump_r1use_r9,%r9,%r1 @@ -426,13 +427,13 @@ ENTRY(system_call) UPDATE_VTIME %r8,%r9,__LC_SYNC_ENTER_TIMER BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP stmg %r0,%r7,__PT_R0(%r11) - # clear user controlled register to prevent speculative use - xgr %r0,%r0 mvc __PT_R8(64,%r11),__LC_SAVE_AREA_SYNC mvc __PT_PSW(16,%r11),__LC_SVC_OLD_PSW mvc __PT_INT_CODE(4,%r11),__LC_SVC_ILC stg %r14,__PT_FLAGS(%r11) .Lsysc_do_svc: + # clear user controlled register to prevent speculative use + xgr %r0,%r0 # load address of system call table lg %r10,__THREAD_sysc_table(%r13,%r12) llgh %r8,__PT_INT_CODE+2(%r11) @@ -1439,6 +1440,7 @@ cleanup_critical: stg %r15,__LC_SYSTEM_TIMER 0: # update accounting time stamp mvc __LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER + BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP # set up saved register r11 lg %r15,__LC_KERNEL_STACK la %r9,STACK_FRAME_OVERHEAD(%r15) diff --git a/arch/s390/kernel/nospec-branch.c b/arch/s390/kernel/nospec-branch.c index 69d7fcf48158..9aff72d3abda 100644 --- a/arch/s390/kernel/nospec-branch.c +++ b/arch/s390/kernel/nospec-branch.c @@ -2,8 +2,8 @@ #include <linux/module.h> #include <asm/nospec-branch.h> -int nospec_call_disable = IS_ENABLED(EXPOLINE_OFF); -int nospec_return_disable = !IS_ENABLED(EXPOLINE_FULL); +int nospec_call_disable = IS_ENABLED(CONFIG_EXPOLINE_OFF); +int nospec_return_disable = !IS_ENABLED(CONFIG_EXPOLINE_FULL); static int __init nospectre_v2_setup_early(char *str) { diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 77d7818130db..339ac0964590 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -86,6 +86,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "deliver_prefix_signal", VCPU_STAT(deliver_prefix_signal) }, { "deliver_restart_signal", VCPU_STAT(deliver_restart_signal) }, { "deliver_program_interruption", VCPU_STAT(deliver_program_int) }, + { "deliver_io_interrupt", VCPU_STAT(deliver_io_int) }, { "exit_wait_state", VCPU_STAT(exit_wait_state) }, { "instruction_epsw", VCPU_STAT(instruction_epsw) }, { "instruction_gs", VCPU_STAT(instruction_gs) }, @@ -2146,6 +2147,7 @@ static void sca_add_vcpu(struct kvm_vcpu *vcpu) /* we still need the basic sca for the ipte control */ vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32); vcpu->arch.sie_block->scaol = (__u32)(__u64)sca; + return; } read_lock(&vcpu->kvm->arch.sca_lock); if (vcpu->kvm->arch.use_esca) { diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index eb7f43f23521..0fa71a78ec99 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2307,7 +2307,7 @@ choice it can be used to assist security vulnerability exploitation. This setting can be changed at boot time via the kernel command - line parameter vsyscall=[native|emulate|none]. + line parameter vsyscall=[emulate|none]. On a system with recent enough glibc (2.14 or newer) and no static binaries, you can say None without a performance penalty @@ -2315,15 +2315,6 @@ choice If unsure, select "Emulate". - config LEGACY_VSYSCALL_NATIVE - bool "Native" - help - Actual executable code is located in the fixed vsyscall - address mapping, implementing time() efficiently. Since - this makes the mapping executable, it can be used during - security vulnerability exploitation (traditionally as - ROP gadgets). This configuration is not recommended. - config LEGACY_VSYSCALL_EMULATE bool "Emulate" help diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index e811dd9c5e99..08425c42f8b7 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -363,9 +363,7 @@ ENTRY(entry_INT80_compat) pushq 2*8(%rdi) /* regs->ip */ pushq 1*8(%rdi) /* regs->orig_ax */ - movq (%rdi), %rdi /* restore %rdi */ - - pushq %rdi /* pt_regs->di */ + pushq (%rdi) /* pt_regs->di */ pushq %rsi /* pt_regs->si */ pushq %rdx /* pt_regs->dx */ pushq %rcx /* pt_regs->cx */ @@ -406,15 +404,3 @@ ENTRY(entry_INT80_compat) TRACE_IRQS_ON jmp swapgs_restore_regs_and_return_to_usermode END(entry_INT80_compat) - -ENTRY(stub32_clone) - /* - * The 32-bit clone ABI is: clone(..., int tls_val, int *child_tidptr). - * The 64-bit clone ABI is: clone(..., int *child_tidptr, int tls_val). - * - * The native 64-bit kernel's sys_clone() implements the latter, - * so we need to swap arguments here before calling it: - */ - xchg %r8, %rcx - jmp sys_clone -ENDPROC(stub32_clone) diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 448ac2161112..2a5e99cff859 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -8,12 +8,12 @@ # 0 i386 restart_syscall sys_restart_syscall 1 i386 exit sys_exit -2 i386 fork sys_fork sys_fork +2 i386 fork sys_fork 3 i386 read sys_read 4 i386 write sys_write 5 i386 open sys_open compat_sys_open 6 i386 close sys_close -7 i386 waitpid sys_waitpid sys32_waitpid +7 i386 waitpid sys_waitpid compat_sys_x86_waitpid 8 i386 creat sys_creat 9 i386 link sys_link 10 i386 unlink sys_unlink @@ -78,7 +78,7 @@ 69 i386 ssetmask sys_ssetmask 70 i386 setreuid sys_setreuid16 71 i386 setregid sys_setregid16 -72 i386 sigsuspend sys_sigsuspend sys_sigsuspend +72 i386 sigsuspend sys_sigsuspend 73 i386 sigpending sys_sigpending compat_sys_sigpending 74 i386 sethostname sys_sethostname 75 i386 setrlimit sys_setrlimit compat_sys_setrlimit @@ -96,7 +96,7 @@ 87 i386 swapon sys_swapon 88 i386 reboot sys_reboot 89 i386 readdir sys_old_readdir compat_sys_old_readdir -90 i386 mmap sys_old_mmap sys32_mmap +90 i386 mmap sys_old_mmap compat_sys_x86_mmap 91 i386 munmap sys_munmap 92 i386 truncate sys_truncate compat_sys_truncate 93 i386 ftruncate sys_ftruncate compat_sys_ftruncate @@ -126,7 +126,7 @@ 117 i386 ipc sys_ipc compat_sys_ipc 118 i386 fsync sys_fsync 119 i386 sigreturn sys_sigreturn sys32_sigreturn -120 i386 clone sys_clone stub32_clone +120 i386 clone sys_clone compat_sys_x86_clone 121 i386 setdomainname sys_setdomainname 122 i386 uname sys_newuname 123 i386 modify_ldt sys_modify_ldt @@ -186,8 +186,8 @@ 177 i386 rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait 178 i386 rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo 179 i386 rt_sigsuspend sys_rt_sigsuspend -180 i386 pread64 sys_pread64 sys32_pread -181 i386 pwrite64 sys_pwrite64 sys32_pwrite +180 i386 pread64 sys_pread64 compat_sys_x86_pread +181 i386 pwrite64 sys_pwrite64 compat_sys_x86_pwrite 182 i386 chown sys_chown16 183 i386 getcwd sys_getcwd 184 i386 capget sys_capget @@ -196,14 +196,14 @@ 187 i386 sendfile sys_sendfile compat_sys_sendfile 188 i386 getpmsg 189 i386 putpmsg -190 i386 vfork sys_vfork sys_vfork +190 i386 vfork sys_vfork 191 i386 ugetrlimit sys_getrlimit compat_sys_getrlimit 192 i386 mmap2 sys_mmap_pgoff -193 i386 truncate64 sys_truncate64 sys32_truncate64 -194 i386 ftruncate64 sys_ftruncate64 sys32_ftruncate64 -195 i386 stat64 sys_stat64 sys32_stat64 -196 i386 lstat64 sys_lstat64 sys32_lstat64 -197 i386 fstat64 sys_fstat64 sys32_fstat64 +193 i386 truncate64 sys_truncate64 compat_sys_x86_truncate64 +194 i386 ftruncate64 sys_ftruncate64 compat_sys_x86_ftruncate64 +195 i386 stat64 sys_stat64 compat_sys_x86_stat64 +196 i386 lstat64 sys_lstat64 compat_sys_x86_lstat64 +197 i386 fstat64 sys_fstat64 compat_sys_x86_fstat64 198 i386 lchown32 sys_lchown 199 i386 getuid32 sys_getuid 200 i386 getgid32 sys_getgid @@ -231,7 +231,7 @@ # 222 is unused # 223 is unused 224 i386 gettid sys_gettid -225 i386 readahead sys_readahead sys32_readahead +225 i386 readahead sys_readahead compat_sys_x86_readahead 226 i386 setxattr sys_setxattr 227 i386 lsetxattr sys_lsetxattr 228 i386 fsetxattr sys_fsetxattr @@ -256,7 +256,7 @@ 247 i386 io_getevents sys_io_getevents compat_sys_io_getevents 248 i386 io_submit sys_io_submit compat_sys_io_submit 249 i386 io_cancel sys_io_cancel -250 i386 fadvise64 sys_fadvise64 sys32_fadvise64 +250 i386 fadvise64 sys_fadvise64 compat_sys_x86_fadvise64 # 251 is available for reuse (was briefly sys_set_zone_reclaim) 252 i386 exit_group sys_exit_group 253 i386 lookup_dcookie sys_lookup_dcookie compat_sys_lookup_dcookie @@ -278,7 +278,7 @@ 269 i386 fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 270 i386 tgkill sys_tgkill 271 i386 utimes sys_utimes compat_sys_utimes -272 i386 fadvise64_64 sys_fadvise64_64 sys32_fadvise64_64 +272 i386 fadvise64_64 sys_fadvise64_64 compat_sys_x86_fadvise64_64 273 i386 vserver 274 i386 mbind sys_mbind 275 i386 get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy @@ -306,7 +306,7 @@ 297 i386 mknodat sys_mknodat 298 i386 fchownat sys_fchownat 299 i386 futimesat sys_futimesat compat_sys_futimesat -300 i386 fstatat64 sys_fstatat64 sys32_fstatat +300 i386 fstatat64 sys_fstatat64 compat_sys_x86_fstatat 301 i386 unlinkat sys_unlinkat 302 i386 renameat sys_renameat 303 i386 linkat sys_linkat @@ -320,7 +320,7 @@ 311 i386 set_robust_list sys_set_robust_list compat_sys_set_robust_list 312 i386 get_robust_list sys_get_robust_list compat_sys_get_robust_list 313 i386 splice sys_splice -314 i386 sync_file_range sys_sync_file_range sys32_sync_file_range +314 i386 sync_file_range sys_sync_file_range compat_sys_x86_sync_file_range 315 i386 tee sys_tee 316 i386 vmsplice sys_vmsplice compat_sys_vmsplice 317 i386 move_pages sys_move_pages compat_sys_move_pages @@ -330,7 +330,7 @@ 321 i386 signalfd sys_signalfd compat_sys_signalfd 322 i386 timerfd_create sys_timerfd_create 323 i386 eventfd sys_eventfd -324 i386 fallocate sys_fallocate sys32_fallocate +324 i386 fallocate sys_fallocate compat_sys_x86_fallocate 325 i386 timerfd_settime sys_timerfd_settime compat_sys_timerfd_settime 326 i386 timerfd_gettime sys_timerfd_gettime compat_sys_timerfd_gettime 327 i386 signalfd4 sys_signalfd4 compat_sys_signalfd4 diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c index 577fa8adb785..8560ef68a9d6 100644 --- a/arch/x86/entry/vsyscall/vsyscall_64.c +++ b/arch/x86/entry/vsyscall/vsyscall_64.c @@ -42,10 +42,8 @@ #define CREATE_TRACE_POINTS #include "vsyscall_trace.h" -static enum { EMULATE, NATIVE, NONE } vsyscall_mode = -#if defined(CONFIG_LEGACY_VSYSCALL_NATIVE) - NATIVE; -#elif defined(CONFIG_LEGACY_VSYSCALL_NONE) +static enum { EMULATE, NONE } vsyscall_mode = +#ifdef CONFIG_LEGACY_VSYSCALL_NONE NONE; #else EMULATE; @@ -56,8 +54,6 @@ static int __init vsyscall_setup(char *str) if (str) { if (!strcmp("emulate", str)) vsyscall_mode = EMULATE; - else if (!strcmp("native", str)) - vsyscall_mode = NATIVE; else if (!strcmp("none", str)) vsyscall_mode = NONE; else @@ -139,10 +135,6 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) WARN_ON_ONCE(address != regs->ip); - /* This should be unreachable in NATIVE mode. */ - if (WARN_ON(vsyscall_mode == NATIVE)) - return false; - if (vsyscall_mode == NONE) { warn_bad_vsyscall(KERN_INFO, regs, "vsyscall attempted with vsyscall=none"); @@ -370,9 +362,7 @@ void __init map_vsyscall(void) if (vsyscall_mode != NONE) { __set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall, - vsyscall_mode == NATIVE - ? PAGE_KERNEL_VSYSCALL - : PAGE_KERNEL_VVAR); + PAGE_KERNEL_VVAR); set_vsyscall_pgtable_user_bits(swapper_pg_dir); } diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 6d8044ab1060..22ec65bc033a 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -3606,7 +3606,7 @@ static struct intel_uncore_type skx_uncore_imc = { }; static struct attribute *skx_upi_uncore_formats_attr[] = { - &format_attr_event_ext.attr, + &format_attr_event.attr, &format_attr_umask_ext.attr, &format_attr_edge.attr, &format_attr_inv.attr, diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index 96cd33bbfc85..6512498bbef6 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -51,15 +51,14 @@ #define AA(__x) ((unsigned long)(__x)) -asmlinkage long sys32_truncate64(const char __user *filename, - unsigned long offset_low, - unsigned long offset_high) +COMPAT_SYSCALL_DEFINE3(x86_truncate64, const char __user *, filename, + unsigned long, offset_low, unsigned long, offset_high) { return sys_truncate(filename, ((loff_t) offset_high << 32) | offset_low); } -asmlinkage long sys32_ftruncate64(unsigned int fd, unsigned long offset_low, - unsigned long offset_high) +COMPAT_SYSCALL_DEFINE3(x86_ftruncate64, unsigned int, fd, + unsigned long, offset_low, unsigned long, offset_high) { return sys_ftruncate(fd, ((loff_t) offset_high << 32) | offset_low); } @@ -96,8 +95,8 @@ static int cp_stat64(struct stat64 __user *ubuf, struct kstat *stat) return 0; } -asmlinkage long sys32_stat64(const char __user *filename, - struct stat64 __user *statbuf) +COMPAT_SYSCALL_DEFINE2(x86_stat64, const char __user *, filename, + struct stat64 __user *, statbuf) { struct kstat stat; int ret = vfs_stat(filename, &stat); @@ -107,8 +106,8 @@ asmlinkage long sys32_stat64(const char __user *filename, return ret; } -asmlinkage long sys32_lstat64(const char __user *filename, - struct stat64 __user *statbuf) +COMPAT_SYSCALL_DEFINE2(x86_lstat64, const char __user *, filename, + struct stat64 __user *, statbuf) { struct kstat stat; int ret = vfs_lstat(filename, &stat); @@ -117,7 +116,8 @@ asmlinkage long sys32_lstat64(const char __user *filename, return ret; } -asmlinkage long sys32_fstat64(unsigned int fd, struct stat64 __user *statbuf) +COMPAT_SYSCALL_DEFINE2(x86_fstat64, unsigned int, fd, + struct stat64 __user *, statbuf) { struct kstat stat; int ret = vfs_fstat(fd, &stat); @@ -126,8 +126,9 @@ asmlinkage long sys32_fstat64(unsigned int fd, struct stat64 __user *statbuf) return ret; } -asmlinkage long sys32_fstatat(unsigned int dfd, const char __user *filename, - struct stat64 __user *statbuf, int flag) +COMPAT_SYSCALL_DEFINE4(x86_fstatat, unsigned int, dfd, + const char __user *, filename, + struct stat64 __user *, statbuf, int, flag) { struct kstat stat; int error; @@ -153,7 +154,7 @@ struct mmap_arg_struct32 { unsigned int offset; }; -asmlinkage long sys32_mmap(struct mmap_arg_struct32 __user *arg) +COMPAT_SYSCALL_DEFINE1(x86_mmap, struct mmap_arg_struct32 __user *, arg) { struct mmap_arg_struct32 a; @@ -167,22 +168,22 @@ asmlinkage long sys32_mmap(struct mmap_arg_struct32 __user *arg) a.offset>>PAGE_SHIFT); } -asmlinkage long sys32_waitpid(compat_pid_t pid, unsigned int __user *stat_addr, - int options) +COMPAT_SYSCALL_DEFINE3(x86_waitpid, compat_pid_t, pid, unsigned int __user *, + stat_addr, int, options) { return compat_sys_wait4(pid, stat_addr, options, NULL); } /* warning: next two assume little endian */ -asmlinkage long sys32_pread(unsigned int fd, char __user *ubuf, u32 count, - u32 poslo, u32 poshi) +COMPAT_SYSCALL_DEFINE5(x86_pread, unsigned int, fd, char __user *, ubuf, + u32, count, u32, poslo, u32, poshi) { return sys_pread64(fd, ubuf, count, ((loff_t)AA(poshi) << 32) | AA(poslo)); } -asmlinkage long sys32_pwrite(unsigned int fd, const char __user *ubuf, - u32 count, u32 poslo, u32 poshi) +COMPAT_SYSCALL_DEFINE5(x86_pwrite, unsigned int, fd, const char __user *, ubuf, + u32, count, u32, poslo, u32, poshi) { return sys_pwrite64(fd, ubuf, count, ((loff_t)AA(poshi) << 32) | AA(poslo)); @@ -193,8 +194,9 @@ asmlinkage long sys32_pwrite(unsigned int fd, const char __user *ubuf, * Some system calls that need sign extended arguments. This could be * done by a generic wrapper. */ -long sys32_fadvise64_64(int fd, __u32 offset_low, __u32 offset_high, - __u32 len_low, __u32 len_high, int advice) +COMPAT_SYSCALL_DEFINE6(x86_fadvise64_64, int, fd, __u32, offset_low, + __u32, offset_high, __u32, len_low, __u32, len_high, + int, advice) { return sys_fadvise64_64(fd, (((u64)offset_high)<<32) | offset_low, @@ -202,31 +204,43 @@ long sys32_fadvise64_64(int fd, __u32 offset_low, __u32 offset_high, advice); } -asmlinkage ssize_t sys32_readahead(int fd, unsigned off_lo, unsigned off_hi, - size_t count) +COMPAT_SYSCALL_DEFINE4(x86_readahead, int, fd, unsigned int, off_lo, + unsigned int, off_hi, size_t, count) { return sys_readahead(fd, ((u64)off_hi << 32) | off_lo, count); } -asmlinkage long sys32_sync_file_range(int fd, unsigned off_low, unsigned off_hi, - unsigned n_low, unsigned n_hi, int flags) +COMPAT_SYSCALL_DEFINE6(x86_sync_file_range, int, fd, unsigned int, off_low, + unsigned int, off_hi, unsigned int, n_low, + unsigned int, n_hi, int, flags) { return sys_sync_file_range(fd, ((u64)off_hi << 32) | off_low, ((u64)n_hi << 32) | n_low, flags); } -asmlinkage long sys32_fadvise64(int fd, unsigned offset_lo, unsigned offset_hi, - size_t len, int advice) +COMPAT_SYSCALL_DEFINE5(x86_fadvise64, int, fd, unsigned int, offset_lo, + unsigned int, offset_hi, size_t, len, int, advice) { return sys_fadvise64_64(fd, ((u64)offset_hi << 32) | offset_lo, len, advice); } -asmlinkage long sys32_fallocate(int fd, int mode, unsigned offset_lo, - unsigned offset_hi, unsigned len_lo, - unsigned len_hi) +COMPAT_SYSCALL_DEFINE6(x86_fallocate, int, fd, int, mode, + unsigned int, offset_lo, unsigned int, offset_hi, + unsigned int, len_lo, unsigned int, len_hi) { return sys_fallocate(fd, mode, ((u64)offset_hi << 32) | offset_lo, ((u64)len_hi << 32) | len_lo); } + +/* + * The 32-bit clone ABI is CONFIG_CLONE_BACKWARDS + */ +COMPAT_SYSCALL_DEFINE5(x86_clone, unsigned long, clone_flags, + unsigned long, newsp, int __user *, parent_tidptr, + unsigned long, tls_val, int __user *, child_tidptr) +{ + return sys_clone(clone_flags, newsp, parent_tidptr, child_tidptr, + tls_val); +} diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 246f15b4e64c..acfe755562a6 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -174,7 +174,6 @@ enum page_cache_mode { #define __PAGE_KERNEL_RO (__PAGE_KERNEL & ~_PAGE_RW) #define __PAGE_KERNEL_RX (__PAGE_KERNEL_EXEC & ~_PAGE_RW) #define __PAGE_KERNEL_NOCACHE (__PAGE_KERNEL | _PAGE_NOCACHE) -#define __PAGE_KERNEL_VSYSCALL (__PAGE_KERNEL_RX | _PAGE_USER) #define __PAGE_KERNEL_VVAR (__PAGE_KERNEL_RO | _PAGE_USER) #define __PAGE_KERNEL_LARGE (__PAGE_KERNEL | _PAGE_PSE) #define __PAGE_KERNEL_LARGE_EXEC (__PAGE_KERNEL_EXEC | _PAGE_PSE) @@ -206,7 +205,6 @@ enum page_cache_mode { #define PAGE_KERNEL_NOCACHE __pgprot(__PAGE_KERNEL_NOCACHE | _PAGE_ENC) #define PAGE_KERNEL_LARGE __pgprot(__PAGE_KERNEL_LARGE | _PAGE_ENC) #define PAGE_KERNEL_LARGE_EXEC __pgprot(__PAGE_KERNEL_LARGE_EXEC | _PAGE_ENC) -#define PAGE_KERNEL_VSYSCALL __pgprot(__PAGE_KERNEL_VSYSCALL | _PAGE_ENC) #define PAGE_KERNEL_VVAR __pgprot(__PAGE_KERNEL_VVAR | _PAGE_ENC) #define PAGE_KERNEL_IO __pgprot(__PAGE_KERNEL_IO) diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h index d6baf23782bc..5c019d23d06b 100644 --- a/arch/x86/include/asm/sections.h +++ b/arch/x86/include/asm/sections.h @@ -10,6 +10,7 @@ extern struct exception_table_entry __stop___ex_table[]; #if defined(CONFIG_X86_64) extern char __end_rodata_hpage_align[]; +extern char __entry_trampoline_start[], __entry_trampoline_end[]; #endif #endif /* _ASM_X86_SECTIONS_H */ diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h index 82c34ee25a65..906794aa034e 100644 --- a/arch/x86/include/asm/sys_ia32.h +++ b/arch/x86/include/asm/sys_ia32.h @@ -20,31 +20,43 @@ #include <asm/ia32.h> /* ia32/sys_ia32.c */ -asmlinkage long sys32_truncate64(const char __user *, unsigned long, unsigned long); -asmlinkage long sys32_ftruncate64(unsigned int, unsigned long, unsigned long); +asmlinkage long compat_sys_x86_truncate64(const char __user *, unsigned long, + unsigned long); +asmlinkage long compat_sys_x86_ftruncate64(unsigned int, unsigned long, + unsigned long); -asmlinkage long sys32_stat64(const char __user *, struct stat64 __user *); -asmlinkage long sys32_lstat64(const char __user *, struct stat64 __user *); -asmlinkage long sys32_fstat64(unsigned int, struct stat64 __user *); -asmlinkage long sys32_fstatat(unsigned int, const char __user *, +asmlinkage long compat_sys_x86_stat64(const char __user *, + struct stat64 __user *); +asmlinkage long compat_sys_x86_lstat64(const char __user *, + struct stat64 __user *); +asmlinkage long compat_sys_x86_fstat64(unsigned int, struct stat64 __user *); +asmlinkage long compat_sys_x86_fstatat(unsigned int, const char __user *, struct stat64 __user *, int); struct mmap_arg_struct32; -asmlinkage long sys32_mmap(struct mmap_arg_struct32 __user *); +asmlinkage long compat_sys_x86_mmap(struct mmap_arg_struct32 __user *); -asmlinkage long sys32_waitpid(compat_pid_t, unsigned int __user *, int); +asmlinkage long compat_sys_x86_waitpid(compat_pid_t, unsigned int __user *, + int); -asmlinkage long sys32_pread(unsigned int, char __user *, u32, u32, u32); -asmlinkage long sys32_pwrite(unsigned int, const char __user *, u32, u32, u32); +asmlinkage long compat_sys_x86_pread(unsigned int, char __user *, u32, u32, + u32); +asmlinkage long compat_sys_x86_pwrite(unsigned int, const char __user *, u32, + u32, u32); -long sys32_fadvise64_64(int, __u32, __u32, __u32, __u32, int); -long sys32_vm86_warning(void); +asmlinkage long compat_sys_x86_fadvise64_64(int, __u32, __u32, __u32, __u32, + int); -asmlinkage ssize_t sys32_readahead(int, unsigned, unsigned, size_t); -asmlinkage long sys32_sync_file_range(int, unsigned, unsigned, - unsigned, unsigned, int); -asmlinkage long sys32_fadvise64(int, unsigned, unsigned, size_t, int); -asmlinkage long sys32_fallocate(int, int, unsigned, - unsigned, unsigned, unsigned); +asmlinkage ssize_t compat_sys_x86_readahead(int, unsigned int, unsigned int, + size_t); +asmlinkage long compat_sys_x86_sync_file_range(int, unsigned int, unsigned int, + unsigned int, unsigned int, + int); +asmlinkage long compat_sys_x86_fadvise64(int, unsigned int, unsigned int, + size_t, int); +asmlinkage long compat_sys_x86_fallocate(int, int, unsigned int, unsigned int, + unsigned int, unsigned int); +asmlinkage long compat_sys_x86_clone(unsigned long, unsigned long, int __user *, + unsigned long, int __user *); /* ia32/ia32_signal.c */ asmlinkage long sys32_sigreturn(void); diff --git a/arch/x86/include/uapi/asm/mce.h b/arch/x86/include/uapi/asm/mce.h index 91723461dc1f..435db58a7bad 100644 --- a/arch/x86/include/uapi/asm/mce.h +++ b/arch/x86/include/uapi/asm/mce.h @@ -30,6 +30,7 @@ struct mce { __u64 synd; /* MCA_SYND MSR: only valid on SMCA systems */ __u64 ipid; /* MCA_IPID MSR: only valid on SMCA systems */ __u64 ppin; /* Protected Processor Inventory Number */ + __u32 microcode;/* Microcode revision */ }; #define MCE_GET_RECORD_LEN _IOR('M', 1, int) diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index d19e903214b4..4aa9fd379390 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -144,6 +144,13 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c) { int i; + /* + * We know that the hypervisor lie to us on the microcode version so + * we may as well hope that it is running the correct version. + */ + if (cpu_has(c, X86_FEATURE_HYPERVISOR)) + return false; + for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) { if (c->x86_model == spectre_bad_microcodes[i].model && c->x86_stepping == spectre_bad_microcodes[i].stepping) diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 8ff94d1e2dce..466f47301334 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -56,6 +56,9 @@ static DEFINE_MUTEX(mce_log_mutex); +/* sysfs synchronization */ +static DEFINE_MUTEX(mce_sysfs_mutex); + #define CREATE_TRACE_POINTS #include <trace/events/mce.h> @@ -130,6 +133,8 @@ void mce_setup(struct mce *m) if (this_cpu_has(X86_FEATURE_INTEL_PPIN)) rdmsrl(MSR_PPIN, m->ppin); + + m->microcode = boot_cpu_data.microcode; } DEFINE_PER_CPU(struct mce, injectm); @@ -262,7 +267,7 @@ static void __print_mce(struct mce *m) */ pr_emerg(HW_ERR "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x microcode %x\n", m->cpuvendor, m->cpuid, m->time, m->socketid, m->apicid, - cpu_data(m->extcpu).microcode); + m->microcode); } static void print_mce(struct mce *m) @@ -2086,6 +2091,7 @@ static ssize_t set_ignore_ce(struct device *s, if (kstrtou64(buf, 0, &new) < 0) return -EINVAL; + mutex_lock(&mce_sysfs_mutex); if (mca_cfg.ignore_ce ^ !!new) { if (new) { /* disable ce features */ @@ -2098,6 +2104,8 @@ static ssize_t set_ignore_ce(struct device *s, on_each_cpu(mce_enable_ce, (void *)1, 1); } } + mutex_unlock(&mce_sysfs_mutex); + return size; } @@ -2110,6 +2118,7 @@ static ssize_t set_cmci_disabled(struct device *s, if (kstrtou64(buf, 0, &new) < 0) return -EINVAL; + mutex_lock(&mce_sysfs_mutex); if (mca_cfg.cmci_disabled ^ !!new) { if (new) { /* disable cmci */ @@ -2121,6 +2130,8 @@ static ssize_t set_cmci_disabled(struct device *s, on_each_cpu(mce_enable_ce, NULL, 1); } } + mutex_unlock(&mce_sysfs_mutex); + return size; } @@ -2128,8 +2139,19 @@ static ssize_t store_int_with_restart(struct device *s, struct device_attribute *attr, const char *buf, size_t size) { - ssize_t ret = device_store_int(s, attr, buf, size); + unsigned long old_check_interval = check_interval; + ssize_t ret = device_store_ulong(s, attr, buf, size); + + if (check_interval == old_check_interval) + return ret; + + if (check_interval < 1) + check_interval = 1; + + mutex_lock(&mce_sysfs_mutex); mce_restart(); + mutex_unlock(&mce_sysfs_mutex); + return ret; } diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index aa1b9a422f2b..70ecbc8099c9 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -22,13 +22,16 @@ #define pr_fmt(fmt) "microcode: " fmt #include <linux/platform_device.h> +#include <linux/stop_machine.h> #include <linux/syscore_ops.h> #include <linux/miscdevice.h> #include <linux/capability.h> #include <linux/firmware.h> #include <linux/kernel.h> +#include <linux/delay.h> #include <linux/mutex.h> #include <linux/cpu.h> +#include <linux/nmi.h> #include <linux/fs.h> #include <linux/mm.h> @@ -64,6 +67,11 @@ LIST_HEAD(microcode_cache); */ static DEFINE_MUTEX(microcode_mutex); +/* + * Serialize late loading so that CPUs get updated one-by-one. + */ +static DEFINE_SPINLOCK(update_lock); + struct ucode_cpu_info ucode_cpu_info[NR_CPUS]; struct cpu_info_ctx { @@ -373,26 +381,23 @@ static int collect_cpu_info(int cpu) return ret; } -struct apply_microcode_ctx { - enum ucode_state err; -}; - static void apply_microcode_local(void *arg) { - struct apply_microcode_ctx *ctx = arg; + enum ucode_state *err = arg; - ctx->err = microcode_ops->apply_microcode(smp_processor_id()); + *err = microcode_ops->apply_microcode(smp_processor_id()); } static int apply_microcode_on_target(int cpu) { - struct apply_microcode_ctx ctx = { .err = 0 }; + enum ucode_state err; int ret; - ret = smp_call_function_single(cpu, apply_microcode_local, &ctx, 1); - if (!ret) - ret = ctx.err; - + ret = smp_call_function_single(cpu, apply_microcode_local, &err, 1); + if (!ret) { + if (err == UCODE_ERROR) + ret = 1; + } return ret; } @@ -489,19 +494,100 @@ static void __exit microcode_dev_exit(void) /* fake device for request_firmware */ static struct platform_device *microcode_pdev; -static enum ucode_state reload_for_cpu(int cpu) +/* + * Late loading dance. Why the heavy-handed stomp_machine effort? + * + * - HT siblings must be idle and not execute other code while the other sibling + * is loading microcode in order to avoid any negative interactions caused by + * the loading. + * + * - In addition, microcode update on the cores must be serialized until this + * requirement can be relaxed in the future. Right now, this is conservative + * and good. + */ +#define SPINUNIT 100 /* 100 nsec */ + +static int check_online_cpus(void) { - struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - enum ucode_state ustate; + if (num_online_cpus() == num_present_cpus()) + return 0; - if (!uci->valid) - return UCODE_OK; + pr_err("Not all CPUs online, aborting microcode update.\n"); + + return -EINVAL; +} + +static atomic_t late_cpus; + +/* + * Returns: + * < 0 - on error + * 0 - no update done + * 1 - microcode was updated + */ +static int __reload_late(void *info) +{ + unsigned int timeout = NSEC_PER_SEC; + int all_cpus = num_online_cpus(); + int cpu = smp_processor_id(); + enum ucode_state err; + int ret = 0; + + atomic_dec(&late_cpus); + + /* + * Wait for all CPUs to arrive. A load will not be attempted unless all + * CPUs show up. + * */ + while (atomic_read(&late_cpus)) { + if (timeout < SPINUNIT) { + pr_err("Timeout while waiting for CPUs rendezvous, remaining: %d\n", + atomic_read(&late_cpus)); + return -1; + } - ustate = microcode_ops->request_microcode_fw(cpu, µcode_pdev->dev, true); - if (ustate != UCODE_OK) - return ustate; + ndelay(SPINUNIT); + timeout -= SPINUNIT; - return apply_microcode_on_target(cpu); + touch_nmi_watchdog(); + } + + spin_lock(&update_lock); + apply_microcode_local(&err); + spin_unlock(&update_lock); + + if (err > UCODE_NFOUND) { + pr_warn("Error reloading microcode on CPU %d\n", cpu); + ret = -1; + } else if (err == UCODE_UPDATED) { + ret = 1; + } + + atomic_inc(&late_cpus); + + while (atomic_read(&late_cpus) != all_cpus) + cpu_relax(); + + return ret; +} + +/* + * Reload microcode late on all CPUs. Wait for a sec until they + * all gather together. + */ +static int microcode_reload_late(void) +{ + int ret; + + atomic_set(&late_cpus, num_online_cpus()); + + ret = stop_machine_cpuslocked(__reload_late, NULL, cpu_online_mask); + if (ret < 0) + return ret; + else if (ret > 0) + microcode_check(); + + return ret; } static ssize_t reload_store(struct device *dev, @@ -509,10 +595,9 @@ static ssize_t reload_store(struct device *dev, const char *buf, size_t size) { enum ucode_state tmp_ret = UCODE_OK; - bool do_callback = false; + int bsp = boot_cpu_data.cpu_index; unsigned long val; ssize_t ret = 0; - int cpu; ret = kstrtoul(buf, 0, &val); if (ret) @@ -521,29 +606,24 @@ static ssize_t reload_store(struct device *dev, if (val != 1) return size; - get_online_cpus(); - mutex_lock(µcode_mutex); - for_each_online_cpu(cpu) { - tmp_ret = reload_for_cpu(cpu); - if (tmp_ret > UCODE_NFOUND) { - pr_warn("Error reloading microcode on CPU %d\n", cpu); - - /* set retval for the first encountered reload error */ - if (!ret) - ret = -EINVAL; - } + tmp_ret = microcode_ops->request_microcode_fw(bsp, µcode_pdev->dev, true); + if (tmp_ret != UCODE_OK) + return size; - if (tmp_ret == UCODE_UPDATED) - do_callback = true; - } + get_online_cpus(); - if (!ret && do_callback) - microcode_check(); + ret = check_online_cpus(); + if (ret) + goto put; + mutex_lock(µcode_mutex); + ret = microcode_reload_late(); mutex_unlock(µcode_mutex); + +put: put_online_cpus(); - if (!ret) + if (ret >= 0) ret = size; return ret; diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 923054a6b760..2aded9db1d42 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -589,6 +589,23 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early) if (!mc) return 0; + /* + * Save us the MSR write below - which is a particular expensive + * operation - when the other hyperthread has updated the microcode + * already. + */ + rev = intel_get_microcode_revision(); + if (rev >= mc->hdr.rev) { + uci->cpu_sig.rev = rev; + return UCODE_OK; + } + + /* + * Writeback and invalidate caches before updating microcode to avoid + * internal issues depending on what the microcode is updating. + */ + native_wbinvd(); + /* write microcode via MSR 0x79 */ native_wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits); @@ -774,9 +791,9 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig) static enum ucode_state apply_microcode_intel(int cpu) { + struct ucode_cpu_info *uci = ucode_cpu_info + cpu; + struct cpuinfo_x86 *c = &cpu_data(cpu); struct microcode_intel *mc; - struct ucode_cpu_info *uci; - struct cpuinfo_x86 *c; static int prev_rev; u32 rev; @@ -784,15 +801,32 @@ static enum ucode_state apply_microcode_intel(int cpu) if (WARN_ON(raw_smp_processor_id() != cpu)) return UCODE_ERROR; - uci = ucode_cpu_info + cpu; - mc = uci->mc; + /* Look for a newer patch in our cache: */ + mc = find_patch(uci); if (!mc) { - /* Look for a newer patch in our cache: */ - mc = find_patch(uci); + mc = uci->mc; if (!mc) return UCODE_NFOUND; } + /* + * Save us the MSR write below - which is a particular expensive + * operation - when the other hyperthread has updated the microcode + * already. + */ + rev = intel_get_microcode_revision(); + if (rev >= mc->hdr.rev) { + uci->cpu_sig.rev = rev; + c->microcode = rev; + return UCODE_OK; + } + + /* + * Writeback and invalidate caches before updating microcode to avoid + * internal issues depending on what the microcode is updating. + */ + native_wbinvd(); + /* write microcode via MSR 0x79 */ wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits); @@ -813,8 +847,6 @@ static enum ucode_state apply_microcode_intel(int cpu) prev_rev = rev; } - c = &cpu_data(cpu); - uci->cpu_sig.rev = rev; c->microcode = rev; diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c index 2f723301eb58..38deafebb21b 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -23,7 +23,7 @@ /* * this changes the io permissions bitmap in the current task. */ -asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on) +SYSCALL_DEFINE3(ioperm, unsigned long, from, unsigned long, num, int, turn_on) { struct thread_struct *t = ¤t->thread; struct tss_struct *tss; diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index bd36f3c33cd0..0715f827607c 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -1168,10 +1168,18 @@ NOKPROBE_SYMBOL(longjmp_break_handler); bool arch_within_kprobe_blacklist(unsigned long addr) { + bool is_in_entry_trampoline_section = false; + +#ifdef CONFIG_X86_64 + is_in_entry_trampoline_section = + (addr >= (unsigned long)__entry_trampoline_start && + addr < (unsigned long)__entry_trampoline_end); +#endif return (addr >= (unsigned long)__kprobes_text_start && addr < (unsigned long)__kprobes_text_end) || (addr >= (unsigned long)__entry_text_start && - addr < (unsigned long)__entry_text_end); + addr < (unsigned long)__entry_text_end) || + is_in_entry_trampoline_section; } int __init arch_init_kprobes(void) diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c index ac057f9b0763..0d930d8987cc 100644 --- a/arch/x86/kernel/signal_compat.c +++ b/arch/x86/kernel/signal_compat.c @@ -43,6 +43,13 @@ static inline void signal_compat_build_tests(void) BUILD_BUG_ON(offsetof(compat_siginfo_t, _sifields) != 3 * sizeof(int)); #define CHECK_CSI_OFFSET(name) BUILD_BUG_ON(_sifields_offset != offsetof(compat_siginfo_t, _sifields.name)) + BUILD_BUG_ON(offsetof(siginfo_t, si_signo) != 0); + BUILD_BUG_ON(offsetof(siginfo_t, si_errno) != 4); + BUILD_BUG_ON(offsetof(siginfo_t, si_code) != 8); + + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_signo) != 0); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_errno) != 4); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_code) != 8); /* * Ensure that the size of each si_field never changes. * If it does, it is a sign that the @@ -63,36 +70,94 @@ static inline void signal_compat_build_tests(void) CHECK_CSI_SIZE (_kill, 2*sizeof(int)); CHECK_SI_SIZE (_kill, 2*sizeof(int)); + BUILD_BUG_ON(offsetof(siginfo_t, si_pid) != 0x10); + BUILD_BUG_ON(offsetof(siginfo_t, si_uid) != 0x14); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pid) != 0xC); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_uid) != 0x10); + CHECK_CSI_OFFSET(_timer); CHECK_CSI_SIZE (_timer, 3*sizeof(int)); CHECK_SI_SIZE (_timer, 6*sizeof(int)); + BUILD_BUG_ON(offsetof(siginfo_t, si_tid) != 0x10); + BUILD_BUG_ON(offsetof(siginfo_t, si_overrun) != 0x14); + BUILD_BUG_ON(offsetof(siginfo_t, si_value) != 0x18); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_tid) != 0x0C); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_overrun) != 0x10); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_value) != 0x14); + CHECK_CSI_OFFSET(_rt); CHECK_CSI_SIZE (_rt, 3*sizeof(int)); CHECK_SI_SIZE (_rt, 4*sizeof(int)); + BUILD_BUG_ON(offsetof(siginfo_t, si_pid) != 0x10); + BUILD_BUG_ON(offsetof(siginfo_t, si_uid) != 0x14); + BUILD_BUG_ON(offsetof(siginfo_t, si_value) != 0x18); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pid) != 0x0C); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_uid) != 0x10); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_value) != 0x14); + CHECK_CSI_OFFSET(_sigchld); CHECK_CSI_SIZE (_sigchld, 5*sizeof(int)); CHECK_SI_SIZE (_sigchld, 8*sizeof(int)); + BUILD_BUG_ON(offsetof(siginfo_t, si_pid) != 0x10); + BUILD_BUG_ON(offsetof(siginfo_t, si_uid) != 0x14); + BUILD_BUG_ON(offsetof(siginfo_t, si_status) != 0x18); + BUILD_BUG_ON(offsetof(siginfo_t, si_utime) != 0x20); + BUILD_BUG_ON(offsetof(siginfo_t, si_stime) != 0x28); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pid) != 0x0C); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_uid) != 0x10); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_status) != 0x14); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_utime) != 0x18); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_stime) != 0x1C); + #ifdef CONFIG_X86_X32_ABI CHECK_CSI_OFFSET(_sigchld_x32); CHECK_CSI_SIZE (_sigchld_x32, 7*sizeof(int)); /* no _sigchld_x32 in the generic siginfo_t */ + BUILD_BUG_ON(offsetof(compat_siginfo_t, _sifields._sigchld_x32._utime) != 0x18); + BUILD_BUG_ON(offsetof(compat_siginfo_t, _sifields._sigchld_x32._stime) != 0x20); #endif CHECK_CSI_OFFSET(_sigfault); CHECK_CSI_SIZE (_sigfault, 4*sizeof(int)); CHECK_SI_SIZE (_sigfault, 8*sizeof(int)); + BUILD_BUG_ON(offsetof(siginfo_t, si_addr) != 0x10); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_addr) != 0x0C); + + BUILD_BUG_ON(offsetof(siginfo_t, si_addr_lsb) != 0x18); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_addr_lsb) != 0x10); + + BUILD_BUG_ON(offsetof(siginfo_t, si_lower) != 0x20); + BUILD_BUG_ON(offsetof(siginfo_t, si_upper) != 0x28); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_lower) != 0x14); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_upper) != 0x18); + + BUILD_BUG_ON(offsetof(siginfo_t, si_pkey) != 0x20); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pkey) != 0x14); + CHECK_CSI_OFFSET(_sigpoll); CHECK_CSI_SIZE (_sigpoll, 2*sizeof(int)); CHECK_SI_SIZE (_sigpoll, 4*sizeof(int)); + BUILD_BUG_ON(offsetof(siginfo_t, si_band) != 0x10); + BUILD_BUG_ON(offsetof(siginfo_t, si_fd) != 0x18); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_band) != 0x0C); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_fd) != 0x10); + CHECK_CSI_OFFSET(_sigsys); CHECK_CSI_SIZE (_sigsys, 3*sizeof(int)); CHECK_SI_SIZE (_sigsys, 4*sizeof(int)); + BUILD_BUG_ON(offsetof(siginfo_t, si_call_addr) != 0x10); + BUILD_BUG_ON(offsetof(siginfo_t, si_syscall) != 0x18); + BUILD_BUG_ON(offsetof(siginfo_t, si_arch) != 0x1C); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_call_addr) != 0x0C); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_syscall) != 0x10); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_arch) != 0x14); + /* any new si_fields should be added here */ } diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 9b138a06c1a4..b854ebf5851b 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -118,9 +118,11 @@ SECTIONS #ifdef CONFIG_X86_64 . = ALIGN(PAGE_SIZE); + VMLINUX_SYMBOL(__entry_trampoline_start) = .; _entry_trampoline = .; *(.entry_trampoline) . = ALIGN(PAGE_SIZE); + VMLINUX_SYMBOL(__entry_trampoline_end) = .; ASSERT(. - _entry_trampoline == PAGE_SIZE, "entry trampoline is too big"); #endif diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index ce38f165489b..631507f0c198 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -332,7 +332,7 @@ static void __init pti_clone_user_shared(void) } /* - * Clone the ESPFIX P4D into the user space visinble page table + * Clone the ESPFIX P4D into the user space visible page table */ static void __init pti_setup_espfix64(void) { diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c index c4d0a1c912f0..3d96e4da2d98 100644 --- a/drivers/acpi/device_pm.c +++ b/drivers/acpi/device_pm.c @@ -543,6 +543,7 @@ static int acpi_dev_pm_get_state(struct device *dev, struct acpi_device *adev, unsigned long long ret; int d_min, d_max; bool wakeup = false; + bool has_sxd = false; acpi_status status; /* @@ -581,6 +582,10 @@ static int acpi_dev_pm_get_state(struct device *dev, struct acpi_device *adev, else return -ENODATA; } + + if (status == AE_OK) + has_sxd = true; + d_min = ret; wakeup = device_may_wakeup(dev) && adev->wakeup.flags.valid && adev->wakeup.sleep_state >= target_state; @@ -599,7 +604,11 @@ static int acpi_dev_pm_get_state(struct device *dev, struct acpi_device *adev, method[3] = 'W'; status = acpi_evaluate_integer(handle, method, NULL, &ret); if (status == AE_NOT_FOUND) { - if (target_state > ACPI_STATE_S0) + /* No _SxW. In this case, the ACPI spec says that we + * must not go into any power state deeper than the + * value returned from _SxD. + */ + if (has_sxd && target_state > ACPI_STATE_S0) d_max = d_min; } else if (ACPI_SUCCESS(status) && ret <= ACPI_STATE_D3_COLD) { /* Fall back to D3cold if ret is not a valid state. */ diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 46cde0912762..4a59c16915c3 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -851,23 +851,25 @@ static void lpi_check_constraints(void) int i; for (i = 0; i < lpi_constraints_table_size; ++i) { + acpi_handle handle = lpi_constraints_table[i].handle; struct acpi_device *adev; - if (acpi_bus_get_device(lpi_constraints_table[i].handle, &adev)) + if (!handle || acpi_bus_get_device(handle, &adev)) continue; - acpi_handle_debug(adev->handle, + acpi_handle_debug(handle, "LPI: required min power state:%s current power state:%s\n", acpi_power_state_string(lpi_constraints_table[i].min_dstate), acpi_power_state_string(adev->power.state)); if (!adev->flags.power_manageable) { - acpi_handle_info(adev->handle, "LPI: Device not power manageble\n"); + acpi_handle_info(handle, "LPI: Device not power manageable\n"); + lpi_constraints_table[i].handle = NULL; continue; } if (adev->power.state < lpi_constraints_table[i].min_dstate) - acpi_handle_info(adev->handle, + acpi_handle_info(handle, "LPI: Constraint not met; min power state:%s current power state:%s\n", acpi_power_state_string(lpi_constraints_table[i].min_dstate), acpi_power_state_string(adev->power.state)); @@ -953,15 +955,8 @@ static int acpi_s2idle_prepare(void) if (lps0_device_handle) { acpi_sleep_run_lps0_dsm(ACPI_LPS0_SCREEN_OFF); acpi_sleep_run_lps0_dsm(ACPI_LPS0_ENTRY); - } else { - /* - * The configuration of GPEs is changed here to avoid spurious - * wakeups, but that should not be necessary if this is a - * "low-power S0" platform and the low-power S0 _DSM is present. - */ - acpi_enable_all_wakeup_gpes(); - acpi_os_wait_events_complete(); } + if (acpi_sci_irq_valid()) enable_irq_wake(acpi_sci_irq); @@ -994,8 +989,9 @@ static void acpi_s2idle_sync(void) * The EC driver uses the system workqueue and an additional special * one, so those need to be flushed too. */ + acpi_os_wait_events_complete(); /* synchronize SCI IRQ handling */ acpi_ec_flush_work(); - acpi_os_wait_events_complete(); + acpi_os_wait_events_complete(); /* synchronize Notify handling */ s2idle_wakeup = false; } @@ -1007,8 +1003,6 @@ static void acpi_s2idle_restore(void) if (lps0_device_handle) { acpi_sleep_run_lps0_dsm(ACPI_LPS0_EXIT); acpi_sleep_run_lps0_dsm(ACPI_LPS0_SCREEN_ON); - } else { - acpi_enable_all_runtime_gpes(); } } diff --git a/drivers/base/core.c b/drivers/base/core.c index 5847364f25d9..b610816eb887 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -196,8 +196,10 @@ struct device_link *device_link_add(struct device *consumer, } list_for_each_entry(link, &supplier->links.consumers, s_node) - if (link->consumer == consumer) + if (link->consumer == consumer) { + kref_get(&link->kref); goto out; + } link = kzalloc(sizeof(*link), GFP_KERNEL); if (!link) @@ -222,6 +224,7 @@ struct device_link *device_link_add(struct device *consumer, link->consumer = consumer; INIT_LIST_HEAD(&link->c_node); link->flags = flags; + kref_init(&link->kref); /* Determine the initial link state. */ if (flags & DL_FLAG_STATELESS) { @@ -292,8 +295,10 @@ static void __device_link_free_srcu(struct rcu_head *rhead) device_link_free(container_of(rhead, struct device_link, rcu_head)); } -static void __device_link_del(struct device_link *link) +static void __device_link_del(struct kref *kref) { + struct device_link *link = container_of(kref, struct device_link, kref); + dev_info(link->consumer, "Dropping the link to %s\n", dev_name(link->supplier)); @@ -305,8 +310,10 @@ static void __device_link_del(struct device_link *link) call_srcu(&device_links_srcu, &link->rcu_head, __device_link_free_srcu); } #else /* !CONFIG_SRCU */ -static void __device_link_del(struct device_link *link) +static void __device_link_del(struct kref *kref) { + struct device_link *link = container_of(kref, struct device_link, kref); + dev_info(link->consumer, "Dropping the link to %s\n", dev_name(link->supplier)); @@ -324,13 +331,15 @@ static void __device_link_del(struct device_link *link) * @link: Device link to delete. * * The caller must ensure proper synchronization of this function with runtime - * PM. + * PM. If the link was added multiple times, it needs to be deleted as often. + * Care is required for hotplugged devices: Their links are purged on removal + * and calling device_link_del() is then no longer allowed. */ void device_link_del(struct device_link *link) { device_links_write_lock(); device_pm_lock(); - __device_link_del(link); + kref_put(&link->kref, __device_link_del); device_pm_unlock(); device_links_write_unlock(); } @@ -444,7 +453,7 @@ static void __device_links_no_driver(struct device *dev) continue; if (link->flags & DL_FLAG_AUTOREMOVE) - __device_link_del(link); + kref_put(&link->kref, __device_link_del); else if (link->status != DL_STATE_SUPPLIER_UNBIND) WRITE_ONCE(link->status, DL_STATE_AVAILABLE); } @@ -597,13 +606,13 @@ static void device_links_purge(struct device *dev) list_for_each_entry_safe_reverse(link, ln, &dev->links.suppliers, c_node) { WARN_ON(link->status == DL_STATE_ACTIVE); - __device_link_del(link); + __device_link_del(&link->kref); } list_for_each_entry_safe_reverse(link, ln, &dev->links.consumers, s_node) { WARN_ON(link->status != DL_STATE_DORMANT && link->status != DL_STATE_NONE); - __device_link_del(link); + __device_link_del(&link->kref); } device_links_write_unlock(); diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h index 21244c53e377..86e67e70b509 100644 --- a/drivers/base/power/power.h +++ b/drivers/base/power/power.h @@ -31,6 +31,7 @@ struct wake_irq { struct device *dev; unsigned int status; int irq; + const char *name; }; extern void dev_pm_arm_wake_irq(struct wake_irq *wirq); diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c index 6637fc319269..b8fa5c0f2d13 100644 --- a/drivers/base/power/wakeirq.c +++ b/drivers/base/power/wakeirq.c @@ -112,6 +112,7 @@ void dev_pm_clear_wake_irq(struct device *dev) free_irq(wirq->irq, wirq); wirq->status &= ~WAKE_IRQ_DEDICATED_MASK; } + kfree(wirq->name); kfree(wirq); } EXPORT_SYMBOL_GPL(dev_pm_clear_wake_irq); @@ -184,6 +185,12 @@ int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq) if (!wirq) return -ENOMEM; + wirq->name = kasprintf(GFP_KERNEL, "%s:wakeup", dev_name(dev)); + if (!wirq->name) { + err = -ENOMEM; + goto err_free; + } + wirq->dev = dev; wirq->irq = irq; irq_set_status_flags(irq, IRQ_NOAUTOEN); @@ -196,9 +203,9 @@ int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq) * so we use a threaded irq. */ err = request_threaded_irq(irq, NULL, handle_threaded_wake_irq, - IRQF_ONESHOT, dev_name(dev), wirq); + IRQF_ONESHOT, wirq->name, wirq); if (err) - goto err_free; + goto err_free_name; err = dev_pm_attach_wake_irq(dev, irq, wirq); if (err) @@ -210,6 +217,8 @@ int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq) err_free_irq: free_irq(irq, wirq); +err_free_name: + kfree(wirq->name); err_free: kfree(wirq); diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 87855b5123a6..ee62d2d517bf 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -266,7 +266,7 @@ static int lo_write_bvec(struct file *file, struct bio_vec *bvec, loff_t *ppos) struct iov_iter i; ssize_t bw; - iov_iter_bvec(&i, ITER_BVEC, bvec, 1, bvec->bv_len); + iov_iter_bvec(&i, ITER_BVEC | WRITE, bvec, 1, bvec->bv_len); file_start_write(file); bw = vfs_iter_write(file, &i, ppos, 0); diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index e126e4cac2ca..92ec1bbece51 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -262,6 +262,7 @@ static DEFINE_SPINLOCK(minor_lock); static int blkfront_setup_indirect(struct blkfront_ring_info *rinfo); static void blkfront_gather_backend_features(struct blkfront_info *info); +static int negotiate_mq(struct blkfront_info *info); static int get_id_from_freelist(struct blkfront_ring_info *rinfo) { @@ -1774,11 +1775,18 @@ static int talk_to_blkback(struct xenbus_device *dev, unsigned int i, max_page_order; unsigned int ring_page_order; + if (!info) + return -ENODEV; + max_page_order = xenbus_read_unsigned(info->xbdev->otherend, "max-ring-page-order", 0); ring_page_order = min(xen_blkif_max_ring_order, max_page_order); info->nr_ring_pages = 1 << ring_page_order; + err = negotiate_mq(info); + if (err) + goto destroy_blkring; + for (i = 0; i < info->nr_rings; i++) { struct blkfront_ring_info *rinfo = &info->rinfo[i]; @@ -1978,11 +1986,6 @@ static int blkfront_probe(struct xenbus_device *dev, } info->xbdev = dev; - err = negotiate_mq(info); - if (err) { - kfree(info); - return err; - } mutex_init(&info->mutex); info->vdevice = vdevice; @@ -2099,10 +2102,6 @@ static int blkfront_resume(struct xenbus_device *dev) blkif_free(info, info->connected == BLKIF_STATE_CONNECTED); - err = negotiate_mq(info); - if (err) - return err; - err = talk_to_blkback(dev, info); if (!err) blk_mq_update_nr_hw_queues(&info->tag_set, info->nr_rings); diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 2a55380ad730..60bf04b8f103 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -21,6 +21,7 @@ * */ +#include <linux/dmi.h> #include <linux/module.h> #include <linux/usb.h> #include <linux/usb/quirks.h> @@ -379,6 +380,21 @@ static const struct usb_device_id blacklist_table[] = { { } /* Terminating entry */ }; +/* The Bluetooth USB module build into some devices needs to be reset on resume, + * this is a problem with the platform (likely shutting off all power) not with + * the module itself. So we use a DMI list to match known broken platforms. + */ +static const struct dmi_system_id btusb_needs_reset_resume_table[] = { + { + /* Lenovo Yoga 920 (QCA Rome device 0cf3:e300) */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo YOGA 920"), + }, + }, + {} +}; + #define BTUSB_MAX_ISOC_FRAMES 10 #define BTUSB_INTR_RUNNING 0 @@ -2945,6 +2961,9 @@ static int btusb_probe(struct usb_interface *intf, hdev->send = btusb_send_frame; hdev->notify = btusb_notify; + if (dmi_check_system(btusb_needs_reset_resume_table)) + interface_to_usbdev(intf)->quirks |= USB_QUIRK_RESET_RESUME; + #ifdef CONFIG_PM err = btusb_config_oob_wake(hdev); if (err) @@ -3031,12 +3050,6 @@ static int btusb_probe(struct usb_interface *intf, if (id->driver_info & BTUSB_QCA_ROME) { data->setup_on_usb = btusb_setup_qca; hdev->set_bdaddr = btusb_set_bdaddr_ath3012; - - /* QCA Rome devices lose their updated firmware over suspend, - * but the USB hub doesn't notice any status change. - * explicitly request a device reset on resume. - */ - interface_to_usbdev(intf)->quirks |= USB_QUIRK_RESET_RESUME; } #ifdef CONFIG_BT_HCIBTUSB_RTL diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c index 0438a64b8185..6314dfb02969 100644 --- a/drivers/bluetooth/hci_bcm.c +++ b/drivers/bluetooth/hci_bcm.c @@ -922,12 +922,13 @@ static int bcm_get_resources(struct bcm_device *dev) dev->clk = devm_clk_get(dev->dev, NULL); - dev->device_wakeup = devm_gpiod_get(dev->dev, "device-wakeup", - GPIOD_OUT_LOW); + dev->device_wakeup = devm_gpiod_get_optional(dev->dev, "device-wakeup", + GPIOD_OUT_LOW); if (IS_ERR(dev->device_wakeup)) return PTR_ERR(dev->device_wakeup); - dev->shutdown = devm_gpiod_get(dev->dev, "shutdown", GPIOD_OUT_LOW); + dev->shutdown = devm_gpiod_get_optional(dev->dev, "shutdown", + GPIOD_OUT_LOW); if (IS_ERR(dev->shutdown)) return PTR_ERR(dev->shutdown); diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig index b3b4ed9b6874..d2e5382821a4 100644 --- a/drivers/clocksource/Kconfig +++ b/drivers/clocksource/Kconfig @@ -386,6 +386,7 @@ config ATMEL_PIT config ATMEL_ST bool "Atmel ST timer support" if COMPILE_TEST + depends on HAS_IOMEM select TIMER_OF select MFD_SYSCON help diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index fb586e09682d..833b5f41f596 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -45,6 +45,7 @@ config ARM_DT_BL_CPUFREQ config ARM_SCPI_CPUFREQ tristate "SCPI based CPUfreq driver" depends on ARM_SCPI_PROTOCOL && COMMON_CLK_SCPI + depends on !CPU_THERMAL || THERMAL help This adds the CPUfreq driver support for ARM platforms using SCPI protocol for CPU power management. diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index d0c34df0529c..9449657d72f0 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -794,15 +794,9 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) valid_states++; } freq_table[valid_states].frequency = CPUFREQ_TABLE_END; + policy->freq_table = freq_table; perf->state = 0; - result = cpufreq_table_validate_and_show(policy, freq_table); - if (result) - goto err_freqfree; - - if (perf->states[0].core_frequency * 1000 != policy->cpuinfo.max_freq) - pr_warn(FW_WARN "P-state 0 is not max freq\n"); - switch (perf->control_register.space_id) { case ACPI_ADR_SPACE_SYSTEM_IO: /* @@ -842,8 +836,6 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) return result; -err_freqfree: - kfree(freq_table); err_unreg: acpi_processor_unregister_performance(cpu); err_free_mask: @@ -871,6 +863,15 @@ static int acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy) return 0; } +static void acpi_cpufreq_cpu_ready(struct cpufreq_policy *policy) +{ + struct acpi_processor_performance *perf = per_cpu_ptr(acpi_perf_data, + policy->cpu); + + if (perf->states[0].core_frequency * 1000 != policy->cpuinfo.max_freq) + pr_warn(FW_WARN "P-state 0 is not max freq\n"); +} + static int acpi_cpufreq_resume(struct cpufreq_policy *policy) { struct acpi_cpufreq_data *data = policy->driver_data; @@ -898,6 +899,7 @@ static struct cpufreq_driver acpi_cpufreq_driver = { .bios_limit = acpi_processor_get_bios_limit, .init = acpi_cpufreq_cpu_init, .exit = acpi_cpufreq_cpu_exit, + .ready = acpi_cpufreq_cpu_ready, .resume = acpi_cpufreq_resume, .name = "acpi-cpufreq", .attr = acpi_cpufreq_attr, diff --git a/drivers/cpufreq/arm_big_little.c b/drivers/cpufreq/arm_big_little.c index c56b57dcfda5..1d7ef5fc1977 100644 --- a/drivers/cpufreq/arm_big_little.c +++ b/drivers/cpufreq/arm_big_little.c @@ -483,14 +483,7 @@ static int bL_cpufreq_init(struct cpufreq_policy *policy) if (ret) return ret; - ret = cpufreq_table_validate_and_show(policy, freq_table[cur_cluster]); - if (ret) { - dev_err(cpu_dev, "CPU %d, cluster: %d invalid freq table\n", - policy->cpu, cur_cluster); - put_cluster_clk_and_freq_table(cpu_dev, policy->cpus); - return ret; - } - + policy->freq_table = freq_table[cur_cluster]; policy->cpuinfo.transition_latency = arm_bL_ops->get_transition_latency(cpu_dev); diff --git a/drivers/cpufreq/brcmstb-avs-cpufreq.c b/drivers/cpufreq/brcmstb-avs-cpufreq.c index 7281a2c19c36..6cdac1aaf23c 100644 --- a/drivers/cpufreq/brcmstb-avs-cpufreq.c +++ b/drivers/cpufreq/brcmstb-avs-cpufreq.c @@ -902,11 +902,7 @@ static int brcm_avs_cpufreq_init(struct cpufreq_policy *policy) return ret; } - ret = cpufreq_table_validate_and_show(policy, freq_table); - if (ret) { - dev_err(dev, "invalid frequency table: %d\n", ret); - return ret; - } + policy->freq_table = freq_table; /* All cores share the same clock and thus the same policy. */ cpumask_setall(policy->cpus); diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c index a1c3025f9df7..8300a9fcb80c 100644 --- a/drivers/cpufreq/cppc_cpufreq.c +++ b/drivers/cpufreq/cppc_cpufreq.c @@ -20,6 +20,7 @@ #include <linux/cpu.h> #include <linux/cpufreq.h> #include <linux/dmi.h> +#include <linux/time.h> #include <linux/vmalloc.h> #include <asm/unaligned.h> @@ -162,6 +163,8 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy) policy->cpuinfo.max_freq = cppc_dmi_max_khz; policy->cpuinfo.transition_latency = cppc_get_transition_latency(cpu_num); + policy->transition_delay_us = cppc_get_transition_latency(cpu_num) / + NSEC_PER_USEC; policy->shared_type = cpu->shared_type; if (policy->shared_type == CPUFREQ_SHARED_TYPE_ANY) @@ -230,8 +233,13 @@ static int __init cppc_cpufreq_init(void) return ret; out: - for_each_possible_cpu(i) - kfree(all_cpu_data[i]); + for_each_possible_cpu(i) { + cpu = all_cpu_data[i]; + if (!cpu) + break; + free_cpumask_var(cpu->shared_cpu_map); + kfree(cpu); + } kfree(all_cpu_data); return -ENODEV; diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c index de3d104c25d7..190ea0dccb79 100644 --- a/drivers/cpufreq/cpufreq-dt.c +++ b/drivers/cpufreq/cpufreq-dt.c @@ -258,16 +258,10 @@ static int cpufreq_init(struct cpufreq_policy *policy) priv->cpu_dev = cpu_dev; policy->driver_data = priv; policy->clk = cpu_clk; + policy->freq_table = freq_table; policy->suspend_freq = dev_pm_opp_get_suspend_opp_freq(cpu_dev) / 1000; - ret = cpufreq_table_validate_and_show(policy, freq_table); - if (ret) { - dev_err(cpu_dev, "%s: invalid frequency table: %d\n", __func__, - ret); - goto out_free_cpufreq_table; - } - /* Support turbo/boost mode */ if (policy_has_boost_freq(policy)) { /* This gets disabled by core on driver unregister */ diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index de33ebf008ad..075d18f6ba7a 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -178,14 +178,7 @@ int cpufreq_generic_init(struct cpufreq_policy *policy, struct cpufreq_frequency_table *table, unsigned int transition_latency) { - int ret; - - ret = cpufreq_table_validate_and_show(policy, table); - if (ret) { - pr_err("%s: invalid frequency table: %d\n", __func__, ret); - return ret; - } - + policy->freq_table = table; policy->cpuinfo.transition_latency = transition_latency; /* @@ -1219,6 +1212,10 @@ static int cpufreq_online(unsigned int cpu) goto out_free_policy; } + ret = cpufreq_table_validate_and_sort(policy); + if (ret) + goto out_exit_policy; + down_write(&policy->rwsem); if (new_policy) { @@ -1249,7 +1246,7 @@ static int cpufreq_online(unsigned int cpu) policy->cur = cpufreq_driver->get(policy->cpu); if (!policy->cur) { pr_err("%s: ->get() failed\n", __func__); - goto out_exit_policy; + goto out_destroy_policy; } } @@ -1296,7 +1293,7 @@ static int cpufreq_online(unsigned int cpu) if (new_policy) { ret = cpufreq_add_dev_interface(policy); if (ret) - goto out_exit_policy; + goto out_destroy_policy; cpufreq_stats_create_table(policy); @@ -1311,7 +1308,7 @@ static int cpufreq_online(unsigned int cpu) __func__, cpu, ret); /* cpufreq_policy_free() will notify based on this */ new_policy = false; - goto out_exit_policy; + goto out_destroy_policy; } up_write(&policy->rwsem); @@ -1326,15 +1323,16 @@ static int cpufreq_online(unsigned int cpu) return 0; -out_exit_policy: +out_destroy_policy: + for_each_cpu(j, policy->real_cpus) + remove_cpu_dev_symlink(policy, get_cpu_device(j)); + up_write(&policy->rwsem); +out_exit_policy: if (cpufreq_driver->exit) cpufreq_driver->exit(policy); - for_each_cpu(j, policy->real_cpus) - remove_cpu_dev_symlink(policy, get_cpu_device(j)); - out_free_policy: cpufreq_policy_free(policy); return ret; diff --git a/drivers/cpufreq/e_powersaver.c b/drivers/cpufreq/e_powersaver.c index cdf097b29862..60bea302abbe 100644 --- a/drivers/cpufreq/e_powersaver.c +++ b/drivers/cpufreq/e_powersaver.c @@ -184,7 +184,6 @@ static int eps_cpu_init(struct cpufreq_policy *policy) struct cpuinfo_x86 *c = &cpu_data(0); struct cpufreq_frequency_table *f_table; int k, step, voltage; - int ret; int states; #if IS_ENABLED(CONFIG_ACPI_PROCESSOR) unsigned int limit; @@ -359,12 +358,7 @@ static int eps_cpu_init(struct cpufreq_policy *policy) } policy->cpuinfo.transition_latency = 140000; /* 844mV -> 700mV in ns */ - - ret = cpufreq_table_validate_and_show(policy, ¢aur->freq_table[0]); - if (ret) { - kfree(centaur); - return ret; - } + policy->freq_table = ¢aur->freq_table[0]; return 0; } diff --git a/drivers/cpufreq/elanfreq.c b/drivers/cpufreq/elanfreq.c index 45e2ca62515e..03419f064752 100644 --- a/drivers/cpufreq/elanfreq.c +++ b/drivers/cpufreq/elanfreq.c @@ -165,7 +165,8 @@ static int elanfreq_cpu_init(struct cpufreq_policy *policy) if (pos->frequency > max_freq) pos->frequency = CPUFREQ_ENTRY_INVALID; - return cpufreq_table_validate_and_show(policy, elanfreq_table); + policy->freq_table = elanfreq_table; + return 0; } diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c index 6d007f824ca7..10e119ae66dd 100644 --- a/drivers/cpufreq/freq_table.c +++ b/drivers/cpufreq/freq_table.c @@ -362,10 +362,24 @@ int cpufreq_table_validate_and_show(struct cpufreq_policy *policy, return ret; policy->freq_table = table; - return set_freq_table_sorted(policy); + return 0; } EXPORT_SYMBOL_GPL(cpufreq_table_validate_and_show); +int cpufreq_table_validate_and_sort(struct cpufreq_policy *policy) +{ + int ret; + + if (!policy->freq_table) + return 0; + + ret = cpufreq_frequency_table_cpuinfo(policy, policy->freq_table); + if (ret) + return ret; + + return set_freq_table_sorted(policy); +} + MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>"); MODULE_DESCRIPTION("CPUfreq frequency table helpers"); MODULE_LICENSE("GPL"); diff --git a/drivers/cpufreq/ia64-acpi-cpufreq.c b/drivers/cpufreq/ia64-acpi-cpufreq.c index a757c0a1e7b5..7974a2fdb760 100644 --- a/drivers/cpufreq/ia64-acpi-cpufreq.c +++ b/drivers/cpufreq/ia64-acpi-cpufreq.c @@ -270,10 +270,7 @@ acpi_cpufreq_cpu_init ( } } - result = cpufreq_table_validate_and_show(policy, freq_table); - if (result) { - goto err_freqfree; - } + policy->freq_table = freq_table; /* notify BIOS that we exist */ acpi_processor_notify_smm(THIS_MODULE); @@ -296,8 +293,6 @@ acpi_cpufreq_cpu_init ( return (result); - err_freqfree: - kfree(freq_table); err_unreg: acpi_processor_unregister_performance(cpu); err_free: diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c index ff67859948b3..83cf631fc9bc 100644 --- a/drivers/cpufreq/imx6q-cpufreq.c +++ b/drivers/cpufreq/imx6q-cpufreq.c @@ -52,6 +52,7 @@ static struct clk_bulk_data clks[] = { static struct device *cpu_dev; static bool free_opp; static struct cpufreq_frequency_table *freq_table; +static unsigned int max_freq; static unsigned int transition_latency; static u32 *imx6_soc_volt; @@ -196,7 +197,7 @@ static int imx6q_cpufreq_init(struct cpufreq_policy *policy) policy->clk = clks[ARM].clk; ret = cpufreq_generic_init(policy, freq_table, transition_latency); - policy->suspend_freq = policy->max; + policy->suspend_freq = max_freq; return ret; } @@ -437,12 +438,12 @@ soc_opp_out: * freq_table initialised from OPP is therefore sorted in the * same order. */ + max_freq = freq_table[--num].frequency; opp = dev_pm_opp_find_freq_exact(cpu_dev, freq_table[0].frequency * 1000, true); min_volt = dev_pm_opp_get_voltage(opp); dev_pm_opp_put(opp); - opp = dev_pm_opp_find_freq_exact(cpu_dev, - freq_table[--num].frequency * 1000, true); + opp = dev_pm_opp_find_freq_exact(cpu_dev, max_freq * 1000, true); max_volt = dev_pm_opp_get_voltage(opp); dev_pm_opp_put(opp); diff --git a/drivers/cpufreq/longhaul.c b/drivers/cpufreq/longhaul.c index f730b6528c18..61a4c5b08219 100644 --- a/drivers/cpufreq/longhaul.c +++ b/drivers/cpufreq/longhaul.c @@ -895,8 +895,9 @@ static int longhaul_cpu_init(struct cpufreq_policy *policy) longhaul_setup_voltagescaling(); policy->transition_delay_us = 200000; /* usec */ + policy->freq_table = longhaul_table; - return cpufreq_table_validate_and_show(policy, longhaul_table); + return 0; } static struct cpufreq_driver longhaul_driver = { diff --git a/drivers/cpufreq/mediatek-cpufreq.c b/drivers/cpufreq/mediatek-cpufreq.c index 8c04dddd3c28..eb8920d39818 100644 --- a/drivers/cpufreq/mediatek-cpufreq.c +++ b/drivers/cpufreq/mediatek-cpufreq.c @@ -460,21 +460,12 @@ static int mtk_cpufreq_init(struct cpufreq_policy *policy) return ret; } - ret = cpufreq_table_validate_and_show(policy, freq_table); - if (ret) { - pr_err("%s: invalid frequency table: %d\n", __func__, ret); - goto out_free_cpufreq_table; - } - cpumask_copy(policy->cpus, &info->cpus); + policy->freq_table = freq_table; policy->driver_data = info; policy->clk = info->cpu_clk; return 0; - -out_free_cpufreq_table: - dev_pm_opp_free_cpufreq_table(info->cpu_dev, &freq_table); - return ret; } static int mtk_cpufreq_exit(struct cpufreq_policy *policy) @@ -578,7 +569,7 @@ static int __init mtk_cpufreq_driver_init(void) match = of_match_node(mtk_cpufreq_machines, np); of_node_put(np); if (!match) { - pr_warn("Machine is not compatible with mtk-cpufreq\n"); + pr_debug("Machine is not compatible with mtk-cpufreq\n"); return -ENODEV; } diff --git a/drivers/cpufreq/p4-clockmod.c b/drivers/cpufreq/p4-clockmod.c index a25741b1281b..911206243050 100644 --- a/drivers/cpufreq/p4-clockmod.c +++ b/drivers/cpufreq/p4-clockmod.c @@ -202,8 +202,9 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy) /* the transition latency is set to be 1 higher than the maximum * transition latency of the ondemand governor */ policy->cpuinfo.transition_latency = 10000001; + policy->freq_table = &p4clockmod_table[0]; - return cpufreq_table_validate_and_show(policy, &p4clockmod_table[0]); + return 0; } diff --git a/drivers/cpufreq/powernow-k6.c b/drivers/cpufreq/powernow-k6.c index dedd2568e852..8a8ea68611a8 100644 --- a/drivers/cpufreq/powernow-k6.c +++ b/drivers/cpufreq/powernow-k6.c @@ -214,8 +214,9 @@ have_busfreq: /* cpuinfo and default policy values */ policy->cpuinfo.transition_latency = 500000; + policy->freq_table = clock_ratio; - return cpufreq_table_validate_and_show(policy, clock_ratio); + return 0; } diff --git a/drivers/cpufreq/powernow-k7.c b/drivers/cpufreq/powernow-k7.c index 302e9ce793a0..d6cb052b0a75 100644 --- a/drivers/cpufreq/powernow-k7.c +++ b/drivers/cpufreq/powernow-k7.c @@ -639,8 +639,9 @@ static int powernow_cpu_init(struct cpufreq_policy *policy) policy->cpuinfo.transition_latency = cpufreq_scale(2000000UL, fsb, latency); + policy->freq_table = powernow_table; - return cpufreq_table_validate_and_show(policy, powernow_table); + return 0; } static int powernow_cpu_exit(struct cpufreq_policy *policy) diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c index b01e31db5f83..fb77b39a4ce3 100644 --- a/drivers/cpufreq/powernow-k8.c +++ b/drivers/cpufreq/powernow-k8.c @@ -122,14 +122,12 @@ static int query_current_values_with_pending_wait(struct powernow_k8_data *data) static void count_off_irt(struct powernow_k8_data *data) { udelay((1 << data->irt) * 10); - return; } /* the voltage stabilization time */ static void count_off_vst(struct powernow_k8_data *data) { udelay(data->vstable * VST_UNITS_20US); - return; } /* need to init the control msr to a safe value (for each cpu) */ @@ -591,10 +589,8 @@ static int fill_powernow_table(struct powernow_k8_data *data, powernow_table = kzalloc((sizeof(*powernow_table) * (data->numps + 1)), GFP_KERNEL); - if (!powernow_table) { - pr_err("powernow_table memory alloc failure\n"); + if (!powernow_table) return -ENOMEM; - } for (j = 0; j < data->numps; j++) { int freq; @@ -760,10 +756,8 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data) /* fill in data->powernow_table */ powernow_table = kzalloc((sizeof(*powernow_table) * (data->acpi_data.state_count + 1)), GFP_KERNEL); - if (!powernow_table) { - pr_debug("powernow_table memory alloc failure\n"); + if (!powernow_table) goto err_out; - } /* fill in data */ data->numps = data->acpi_data.state_count; @@ -1042,10 +1036,8 @@ static int powernowk8_cpu_init(struct cpufreq_policy *pol) return -ENODEV; data = kzalloc(sizeof(*data), GFP_KERNEL); - if (!data) { - pr_err("unable to alloc powernow_k8_data\n"); + if (!data) return -ENOMEM; - } data->cpu = pol->cpu; @@ -1084,15 +1076,7 @@ static int powernowk8_cpu_init(struct cpufreq_policy *pol) cpumask_copy(pol->cpus, topology_core_cpumask(pol->cpu)); data->available_cores = pol->cpus; - - /* min/max the cpu is capable of */ - if (cpufreq_table_validate_and_show(pol, data->powernow_table)) { - pr_err(FW_BUG "invalid powernow_table\n"); - powernow_k8_cpu_exit_acpi(data); - kfree(data->powernow_table); - kfree(data); - return -EINVAL; - } + pol->freq_table = data->powernow_table; pr_debug("cpu_init done, current fid 0x%x, vid 0x%x\n", data->currfid, data->currvid); diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c index 29cdec198657..0591874856d3 100644 --- a/drivers/cpufreq/powernv-cpufreq.c +++ b/drivers/cpufreq/powernv-cpufreq.c @@ -812,7 +812,7 @@ gpstates_done: static int powernv_cpufreq_cpu_init(struct cpufreq_policy *policy) { - int base, i, ret; + int base, i; struct kernfs_node *kn; struct global_pstate_info *gpstates; @@ -848,15 +848,10 @@ static int powernv_cpufreq_cpu_init(struct cpufreq_policy *policy) gpstates->timer.expires = jiffies + msecs_to_jiffies(GPSTATE_TIMER_INTERVAL); spin_lock_init(&gpstates->gpstate_lock); - ret = cpufreq_table_validate_and_show(policy, powernv_freqs); - - if (ret < 0) { - kfree(policy->driver_data); - return ret; - } + policy->freq_table = powernv_freqs; policy->fast_switch_possible = true; - return ret; + return 0; } static int powernv_cpufreq_cpu_exit(struct cpufreq_policy *policy) diff --git a/drivers/cpufreq/ppc_cbe_cpufreq.c b/drivers/cpufreq/ppc_cbe_cpufreq.c index 5a4c5a639f61..41a0f0be3f9f 100644 --- a/drivers/cpufreq/ppc_cbe_cpufreq.c +++ b/drivers/cpufreq/ppc_cbe_cpufreq.c @@ -121,9 +121,8 @@ static int cbe_cpufreq_cpu_init(struct cpufreq_policy *policy) cpumask_copy(policy->cpus, cpu_sibling_mask(policy->cpu)); #endif - /* this ensures that policy->cpuinfo_min - * and policy->cpuinfo_max are set correctly */ - return cpufreq_table_validate_and_show(policy, cbe_freqs); + policy->freq_table = cbe_freqs; + return 0; } static int cbe_cpufreq_target(struct cpufreq_policy *policy, diff --git a/drivers/cpufreq/pxa2xx-cpufreq.c b/drivers/cpufreq/pxa2xx-cpufreq.c index 06b024a3e474..46254e583982 100644 --- a/drivers/cpufreq/pxa2xx-cpufreq.c +++ b/drivers/cpufreq/pxa2xx-cpufreq.c @@ -292,10 +292,10 @@ static int pxa_cpufreq_init(struct cpufreq_policy *policy) pr_info("using %s frequency table\n", pxa255_turbo_table ? "turbo" : "run"); - cpufreq_table_validate_and_show(policy, pxa255_freq_table); + policy->freq_table = pxa255_freq_table; } else if (cpu_is_pxa27x()) { - cpufreq_table_validate_and_show(policy, pxa27x_freq_table); + policy->freq_table = pxa27x_freq_table; } pr_info("frequency change support initialized\n"); diff --git a/drivers/cpufreq/pxa3xx-cpufreq.c b/drivers/cpufreq/pxa3xx-cpufreq.c index a01275900389..7acc7fa4536d 100644 --- a/drivers/cpufreq/pxa3xx-cpufreq.c +++ b/drivers/cpufreq/pxa3xx-cpufreq.c @@ -108,7 +108,9 @@ static int setup_freqs_table(struct cpufreq_policy *policy, pxa3xx_freqs_num = num; pxa3xx_freqs_table = table; - return cpufreq_table_validate_and_show(policy, table); + policy->freq_table = table; + + return 0; } static void __update_core_freq(struct pxa3xx_freq_info *info) diff --git a/drivers/cpufreq/qoriq-cpufreq.c b/drivers/cpufreq/qoriq-cpufreq.c index 0562761a3dec..3d773f64b4df 100644 --- a/drivers/cpufreq/qoriq-cpufreq.c +++ b/drivers/cpufreq/qoriq-cpufreq.c @@ -165,7 +165,7 @@ static void freq_table_sort(struct cpufreq_frequency_table *freq_table, static int qoriq_cpufreq_cpu_init(struct cpufreq_policy *policy) { struct device_node *np; - int i, count, ret; + int i, count; u32 freq; struct clk *clk; const struct clk_hw *hwclk; @@ -192,16 +192,12 @@ static int qoriq_cpufreq_cpu_init(struct cpufreq_policy *policy) count = clk_hw_get_num_parents(hwclk); data->pclk = kcalloc(count, sizeof(struct clk *), GFP_KERNEL); - if (!data->pclk) { - pr_err("%s: no memory\n", __func__); + if (!data->pclk) goto err_nomem2; - } table = kcalloc(count + 1, sizeof(*table), GFP_KERNEL); - if (!table) { - pr_err("%s: no memory\n", __func__); + if (!table) goto err_pclk; - } for (i = 0; i < count; i++) { clk = clk_hw_get_parent_by_index(hwclk, i)->clk; @@ -213,14 +209,7 @@ static int qoriq_cpufreq_cpu_init(struct cpufreq_policy *policy) freq_table_redup(table, count); freq_table_sort(table, count); table[i].frequency = CPUFREQ_TABLE_END; - - /* set the min and max frequency properly */ - ret = cpufreq_table_validate_and_show(policy, table); - if (ret) { - pr_err("invalid frequency table: %d\n", ret); - goto err_nomem1; - } - + policy->freq_table = table; data->table = table; /* update ->cpus if we have cluster, no harm if not */ @@ -236,8 +225,6 @@ static int qoriq_cpufreq_cpu_init(struct cpufreq_policy *policy) return 0; -err_nomem1: - kfree(table); err_pclk: kfree(data->pclk); err_nomem2: diff --git a/drivers/cpufreq/s3c24xx-cpufreq.c b/drivers/cpufreq/s3c24xx-cpufreq.c index 6bebc1f9f55a..909bd6e27639 100644 --- a/drivers/cpufreq/s3c24xx-cpufreq.c +++ b/drivers/cpufreq/s3c24xx-cpufreq.c @@ -351,11 +351,8 @@ struct clk *s3c_cpufreq_clk_get(struct device *dev, const char *name) static int s3c_cpufreq_init(struct cpufreq_policy *policy) { policy->clk = clk_arm; - policy->cpuinfo.transition_latency = cpu_cur.info->latency; - - if (ftab) - return cpufreq_table_validate_and_show(policy, ftab); + policy->freq_table = ftab; return 0; } @@ -479,10 +476,8 @@ int __init s3c_cpufreq_setboard(struct s3c_cpufreq_board *board) * initdata. */ ours = kzalloc(sizeof(*ours), GFP_KERNEL); - if (ours == NULL) { - pr_err("%s: no memory\n", __func__); + if (!ours) return -ENOMEM; - } *ours = *board; cpu_cur.board = ours; @@ -568,10 +563,8 @@ static int s3c_cpufreq_build_freq(void) size++; ftab = kzalloc(sizeof(*ftab) * size, GFP_KERNEL); - if (!ftab) { - pr_err("%s: no memory for tables\n", __func__); + if (!ftab) return -ENOMEM; - } ftab_size = size; diff --git a/drivers/cpufreq/sc520_freq.c b/drivers/cpufreq/sc520_freq.c index 4225501a4b78..abaa75e86148 100644 --- a/drivers/cpufreq/sc520_freq.c +++ b/drivers/cpufreq/sc520_freq.c @@ -83,8 +83,9 @@ static int sc520_freq_cpu_init(struct cpufreq_policy *policy) /* cpuinfo and default policy values */ policy->cpuinfo.transition_latency = 1000000; /* 1ms */ + policy->freq_table = sc520_freq_table; - return cpufreq_table_validate_and_show(policy, sc520_freq_table); + return 0; } diff --git a/drivers/cpufreq/scpi-cpufreq.c b/drivers/cpufreq/scpi-cpufreq.c index d300a163945f..87a98ec77773 100644 --- a/drivers/cpufreq/scpi-cpufreq.c +++ b/drivers/cpufreq/scpi-cpufreq.c @@ -158,13 +158,7 @@ static int scpi_cpufreq_init(struct cpufreq_policy *policy) } policy->driver_data = priv; - - ret = cpufreq_table_validate_and_show(policy, freq_table); - if (ret) { - dev_err(cpu_dev, "%s: invalid frequency table: %d\n", __func__, - ret); - goto out_put_clk; - } + policy->freq_table = freq_table; /* scpi allows DVFS request for any domain from any CPU */ policy->dvfs_possible_from_any_cpu = true; @@ -178,8 +172,6 @@ static int scpi_cpufreq_init(struct cpufreq_policy *policy) policy->fast_switch_possible = false; return 0; -out_put_clk: - clk_put(priv->clk); out_free_cpufreq_table: dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table); out_free_priv: diff --git a/drivers/cpufreq/sfi-cpufreq.c b/drivers/cpufreq/sfi-cpufreq.c index 3779742f86e3..9767afe05da2 100644 --- a/drivers/cpufreq/sfi-cpufreq.c +++ b/drivers/cpufreq/sfi-cpufreq.c @@ -72,8 +72,9 @@ static int sfi_cpufreq_cpu_init(struct cpufreq_policy *policy) { policy->shared_type = CPUFREQ_SHARED_TYPE_HW; policy->cpuinfo.transition_latency = 100000; /* 100us */ + policy->freq_table = freq_table; - return cpufreq_table_validate_and_show(policy, freq_table); + return 0; } static struct cpufreq_driver sfi_cpufreq_driver = { diff --git a/drivers/cpufreq/sh-cpufreq.c b/drivers/cpufreq/sh-cpufreq.c index 28893d435cf5..5096c0ab781b 100644 --- a/drivers/cpufreq/sh-cpufreq.c +++ b/drivers/cpufreq/sh-cpufreq.c @@ -122,11 +122,7 @@ static int sh_cpufreq_cpu_init(struct cpufreq_policy *policy) freq_table = cpuclk->nr_freqs ? cpuclk->freq_table : NULL; if (freq_table) { - int result; - - result = cpufreq_table_validate_and_show(policy, freq_table); - if (result) - return result; + policy->freq_table = freq_table; } else { dev_notice(dev, "no frequency table found, falling back " "to rate rounding.\n"); @@ -137,11 +133,6 @@ static int sh_cpufreq_cpu_init(struct cpufreq_policy *policy) (clk_round_rate(cpuclk, ~0UL) + 500) / 1000; } - dev_info(dev, "CPU Frequencies - Minimum %u.%03u MHz, " - "Maximum %u.%03u MHz.\n", - policy->min / 1000, policy->min % 1000, - policy->max / 1000, policy->max % 1000); - return 0; } @@ -155,6 +146,16 @@ static int sh_cpufreq_cpu_exit(struct cpufreq_policy *policy) return 0; } +static void sh_cpufreq_cpu_ready(struct cpufreq_policy *policy) +{ + struct device *dev = get_cpu_device(policy->cpu); + + dev_info(dev, "CPU Frequencies - Minimum %u.%03u MHz, " + "Maximum %u.%03u MHz.\n", + policy->min / 1000, policy->min % 1000, + policy->max / 1000, policy->max % 1000); +} + static struct cpufreq_driver sh_cpufreq_driver = { .name = "sh", .flags = CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING, @@ -163,6 +164,7 @@ static struct cpufreq_driver sh_cpufreq_driver = { .verify = sh_cpufreq_verify, .init = sh_cpufreq_cpu_init, .exit = sh_cpufreq_cpu_exit, + .ready = sh_cpufreq_cpu_ready, .attr = cpufreq_generic_attr, }; diff --git a/drivers/cpufreq/sparc-us2e-cpufreq.c b/drivers/cpufreq/sparc-us2e-cpufreq.c index 90f33efee5fc..bbd1d1e166b8 100644 --- a/drivers/cpufreq/sparc-us2e-cpufreq.c +++ b/drivers/cpufreq/sparc-us2e-cpufreq.c @@ -292,8 +292,9 @@ static int __init us2e_freq_cpu_init(struct cpufreq_policy *policy) policy->cpuinfo.transition_latency = 0; policy->cur = clock_tick; + policy->freq_table = table; - return cpufreq_table_validate_and_show(policy, table); + return 0; } static int us2e_freq_cpu_exit(struct cpufreq_policy *policy) diff --git a/drivers/cpufreq/sparc-us3-cpufreq.c b/drivers/cpufreq/sparc-us3-cpufreq.c index 30645b0118f9..51e3c6018e74 100644 --- a/drivers/cpufreq/sparc-us3-cpufreq.c +++ b/drivers/cpufreq/sparc-us3-cpufreq.c @@ -136,8 +136,9 @@ static int __init us3_freq_cpu_init(struct cpufreq_policy *policy) policy->cpuinfo.transition_latency = 0; policy->cur = clock_tick; + policy->freq_table = table; - return cpufreq_table_validate_and_show(policy, table); + return 0; } static int us3_freq_cpu_exit(struct cpufreq_policy *policy) diff --git a/drivers/cpufreq/speedstep-centrino.c b/drivers/cpufreq/speedstep-centrino.c index 4fa5adf16c70..a1fb735685db 100644 --- a/drivers/cpufreq/speedstep-centrino.c +++ b/drivers/cpufreq/speedstep-centrino.c @@ -394,9 +394,9 @@ static int centrino_cpu_init(struct cpufreq_policy *policy) policy->cpuinfo.transition_latency = 10000; /* 10uS transition latency */ + policy->freq_table = per_cpu(centrino_model, policy->cpu)->op_points; - return cpufreq_table_validate_and_show(policy, - per_cpu(centrino_model, policy->cpu)->op_points); + return 0; } static int centrino_cpu_exit(struct cpufreq_policy *policy) diff --git a/drivers/cpufreq/speedstep-ich.c b/drivers/cpufreq/speedstep-ich.c index 0412a246a785..fbbcb88db061 100644 --- a/drivers/cpufreq/speedstep-ich.c +++ b/drivers/cpufreq/speedstep-ich.c @@ -304,7 +304,9 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy) if (gf.ret) return gf.ret; - return cpufreq_table_validate_and_show(policy, speedstep_freqs); + policy->freq_table = speedstep_freqs; + + return 0; } diff --git a/drivers/cpufreq/speedstep-smi.c b/drivers/cpufreq/speedstep-smi.c index d23f24ccff38..01fe70dae20b 100644 --- a/drivers/cpufreq/speedstep-smi.c +++ b/drivers/cpufreq/speedstep-smi.c @@ -266,7 +266,9 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy) pr_debug("workaround worked.\n"); } - return cpufreq_table_validate_and_show(policy, speedstep_freqs); + policy->freq_table = speedstep_freqs; + + return 0; } static unsigned int speedstep_get(unsigned int cpu) diff --git a/drivers/cpufreq/tegra186-cpufreq.c b/drivers/cpufreq/tegra186-cpufreq.c index fe7875311d62..1f59966573aa 100644 --- a/drivers/cpufreq/tegra186-cpufreq.c +++ b/drivers/cpufreq/tegra186-cpufreq.c @@ -78,7 +78,8 @@ static int tegra186_cpufreq_init(struct cpufreq_policy *policy) policy->driver_data = data->regs + info->offset + EDVD_CORE_VOLT_FREQ(core); - cpufreq_table_validate_and_show(policy, cluster->table); + policy->freq_table = cluster->table; + break; } policy->cpuinfo.transition_latency = 300 * 1000; diff --git a/drivers/dma/mv_xor_v2.c b/drivers/dma/mv_xor_v2.c index f652a0e0f5a2..3548caa9e933 100644 --- a/drivers/dma/mv_xor_v2.c +++ b/drivers/dma/mv_xor_v2.c @@ -163,6 +163,7 @@ struct mv_xor_v2_device { void __iomem *dma_base; void __iomem *glob_base; struct clk *clk; + struct clk *reg_clk; struct tasklet_struct irq_tasklet; struct list_head free_sw_desc; struct dma_device dmadev; @@ -749,13 +750,26 @@ static int mv_xor_v2_probe(struct platform_device *pdev) if (ret) return ret; + xor_dev->reg_clk = devm_clk_get(&pdev->dev, "reg"); + if (PTR_ERR(xor_dev->reg_clk) != -ENOENT) { + if (!IS_ERR(xor_dev->reg_clk)) { + ret = clk_prepare_enable(xor_dev->reg_clk); + if (ret) + return ret; + } else { + return PTR_ERR(xor_dev->reg_clk); + } + } + xor_dev->clk = devm_clk_get(&pdev->dev, NULL); - if (IS_ERR(xor_dev->clk) && PTR_ERR(xor_dev->clk) == -EPROBE_DEFER) - return -EPROBE_DEFER; + if (IS_ERR(xor_dev->clk) && PTR_ERR(xor_dev->clk) == -EPROBE_DEFER) { + ret = EPROBE_DEFER; + goto disable_reg_clk; + } if (!IS_ERR(xor_dev->clk)) { ret = clk_prepare_enable(xor_dev->clk); if (ret) - return ret; + goto disable_reg_clk; } ret = platform_msi_domain_alloc_irqs(&pdev->dev, 1, @@ -866,8 +880,9 @@ free_hw_desq: free_msi_irqs: platform_msi_domain_free_irqs(&pdev->dev); disable_clk: - if (!IS_ERR(xor_dev->clk)) - clk_disable_unprepare(xor_dev->clk); + clk_disable_unprepare(xor_dev->clk); +disable_reg_clk: + clk_disable_unprepare(xor_dev->reg_clk); return ret; } diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c index e3ff162c03fc..d0cacdb0713e 100644 --- a/drivers/dma/sh/rcar-dmac.c +++ b/drivers/dma/sh/rcar-dmac.c @@ -917,7 +917,7 @@ rcar_dmac_chan_prep_sg(struct rcar_dmac_chan *chan, struct scatterlist *sgl, rcar_dmac_chan_configure_desc(chan, desc); - max_chunk_size = (RCAR_DMATCR_MASK + 1) << desc->xfer_shift; + max_chunk_size = RCAR_DMATCR_MASK << desc->xfer_shift; /* * Allocate and fill the transfer chunk descriptors. We own the only diff --git a/drivers/gpio/gpio-rcar.c b/drivers/gpio/gpio-rcar.c index e76de57dd617..ebaea8b1594b 100644 --- a/drivers/gpio/gpio-rcar.c +++ b/drivers/gpio/gpio-rcar.c @@ -14,7 +14,6 @@ * GNU General Public License for more details. */ -#include <linux/clk.h> #include <linux/err.h> #include <linux/gpio.h> #include <linux/init.h> @@ -37,10 +36,9 @@ struct gpio_rcar_priv { struct platform_device *pdev; struct gpio_chip gpio_chip; struct irq_chip irq_chip; - struct clk *clk; unsigned int irq_parent; + atomic_t wakeup_path; bool has_both_edge_trigger; - bool needs_clk; }; #define IOINTSEL 0x00 /* General IO/Interrupt Switching Register */ @@ -186,13 +184,10 @@ static int gpio_rcar_irq_set_wake(struct irq_data *d, unsigned int on) } } - if (!p->clk) - return 0; - if (on) - clk_enable(p->clk); + atomic_inc(&p->wakeup_path); else - clk_disable(p->clk); + atomic_dec(&p->wakeup_path); return 0; } @@ -330,17 +325,14 @@ static int gpio_rcar_direction_output(struct gpio_chip *chip, unsigned offset, struct gpio_rcar_info { bool has_both_edge_trigger; - bool needs_clk; }; static const struct gpio_rcar_info gpio_rcar_info_gen1 = { .has_both_edge_trigger = false, - .needs_clk = false, }; static const struct gpio_rcar_info gpio_rcar_info_gen2 = { .has_both_edge_trigger = true, - .needs_clk = true, }; static const struct of_device_id gpio_rcar_of_table[] = { @@ -403,7 +395,6 @@ static int gpio_rcar_parse_dt(struct gpio_rcar_priv *p, unsigned int *npins) ret = of_parse_phandle_with_fixed_args(np, "gpio-ranges", 3, 0, &args); *npins = ret == 0 ? args.args[2] : RCAR_MAX_GPIO_PER_BANK; p->has_both_edge_trigger = info->has_both_edge_trigger; - p->needs_clk = info->needs_clk; if (*npins == 0 || *npins > RCAR_MAX_GPIO_PER_BANK) { dev_warn(&p->pdev->dev, @@ -440,16 +431,6 @@ static int gpio_rcar_probe(struct platform_device *pdev) platform_set_drvdata(pdev, p); - p->clk = devm_clk_get(dev, NULL); - if (IS_ERR(p->clk)) { - if (p->needs_clk) { - dev_err(dev, "unable to get clock\n"); - ret = PTR_ERR(p->clk); - goto err0; - } - p->clk = NULL; - } - pm_runtime_enable(dev); irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0); @@ -531,11 +512,24 @@ static int gpio_rcar_remove(struct platform_device *pdev) return 0; } +static int __maybe_unused gpio_rcar_suspend(struct device *dev) +{ + struct gpio_rcar_priv *p = dev_get_drvdata(dev); + + if (atomic_read(&p->wakeup_path)) + device_set_wakeup_path(dev); + + return 0; +} + +static SIMPLE_DEV_PM_OPS(gpio_rcar_pm_ops, gpio_rcar_suspend, NULL); + static struct platform_driver gpio_rcar_device_driver = { .probe = gpio_rcar_probe, .remove = gpio_rcar_remove, .driver = { .name = "gpio_rcar", + .pm = &gpio_rcar_pm_ops, .of_match_table = of_match_ptr(gpio_rcar_of_table), } }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c index 57afad79f55d..8fa850a070e0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c @@ -540,6 +540,9 @@ int amdgpu_acpi_pcie_performance_request(struct amdgpu_device *adev, size_t size; u32 retry = 3; + if (amdgpu_acpi_pcie_notify_device_ready(adev)) + return -EINVAL; + /* Get the device handle */ handle = ACPI_HANDLE(&adev->pdev->dev); if (!handle) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c index 13044e66dcaf..561d3312af32 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c @@ -481,7 +481,7 @@ static ssize_t amdgpu_debugfs_ring_read(struct file *f, char __user *buf, result = 0; if (*pos < 12) { - early[0] = amdgpu_ring_get_rptr(ring); + early[0] = amdgpu_ring_get_rptr(ring) & ring->buf_mask; early[1] = amdgpu_ring_get_wptr(ring) & ring->buf_mask; early[2] = ring->wptr & ring->buf_mask; for (i = *pos / 4; i < 3 && size; i++) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c index b2eae86bf906..5c26a8e806b9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c @@ -299,12 +299,15 @@ int amdgpu_uvd_suspend(struct amdgpu_device *adev) cancel_delayed_work_sync(&adev->uvd.idle_work); - for (i = 0; i < adev->uvd.max_handles; ++i) - if (atomic_read(&adev->uvd.handles[i])) - break; + /* only valid for physical mode */ + if (adev->asic_type < CHIP_POLARIS10) { + for (i = 0; i < adev->uvd.max_handles; ++i) + if (atomic_read(&adev->uvd.handles[i])) + break; - if (i == AMDGPU_MAX_UVD_HANDLES) - return 0; + if (i == adev->uvd.max_handles) + return 0; + } size = amdgpu_bo_size(adev->uvd.vcpu_bo); ptr = adev->uvd.cpu_addr; diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c index bd2c4f727df6..a712f4b285f6 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c @@ -3093,7 +3093,7 @@ static int dce_v6_0_hpd_irq(struct amdgpu_device *adev, tmp |= DC_HPD1_INT_CONTROL__DC_HPD1_INT_ACK_MASK; WREG32(mmDC_HPD1_INT_CONTROL + hpd_offsets[hpd], tmp); schedule_work(&adev->hotplug_work); - DRM_INFO("IH: HPD%d\n", hpd + 1); + DRM_DEBUG("IH: HPD%d\n", hpd + 1); } return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c index a066c5eda135..a4309698e76c 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c @@ -4384,34 +4384,8 @@ static void gfx_v7_0_gpu_early_init(struct amdgpu_device *adev) case CHIP_KAVERI: adev->gfx.config.max_shader_engines = 1; adev->gfx.config.max_tile_pipes = 4; - if ((adev->pdev->device == 0x1304) || - (adev->pdev->device == 0x1305) || - (adev->pdev->device == 0x130C) || - (adev->pdev->device == 0x130F) || - (adev->pdev->device == 0x1310) || - (adev->pdev->device == 0x1311) || - (adev->pdev->device == 0x131C)) { - adev->gfx.config.max_cu_per_sh = 8; - adev->gfx.config.max_backends_per_se = 2; - } else if ((adev->pdev->device == 0x1309) || - (adev->pdev->device == 0x130A) || - (adev->pdev->device == 0x130D) || - (adev->pdev->device == 0x1313) || - (adev->pdev->device == 0x131D)) { - adev->gfx.config.max_cu_per_sh = 6; - adev->gfx.config.max_backends_per_se = 2; - } else if ((adev->pdev->device == 0x1306) || - (adev->pdev->device == 0x1307) || - (adev->pdev->device == 0x130B) || - (adev->pdev->device == 0x130E) || - (adev->pdev->device == 0x1315) || - (adev->pdev->device == 0x131B)) { - adev->gfx.config.max_cu_per_sh = 4; - adev->gfx.config.max_backends_per_se = 1; - } else { - adev->gfx.config.max_cu_per_sh = 3; - adev->gfx.config.max_backends_per_se = 1; - } + adev->gfx.config.max_cu_per_sh = 8; + adev->gfx.config.max_backends_per_se = 2; adev->gfx.config.max_sh_per_se = 1; adev->gfx.config.max_texture_channel_caches = 4; adev->gfx.config.max_gprs = 256; diff --git a/drivers/gpu/drm/amd/amdgpu/si.c b/drivers/gpu/drm/amd/amdgpu/si.c index 543101d5a5ed..2095173aaabf 100644 --- a/drivers/gpu/drm/amd/amdgpu/si.c +++ b/drivers/gpu/drm/amd/amdgpu/si.c @@ -31,6 +31,7 @@ #include "amdgpu_uvd.h" #include "amdgpu_vce.h" #include "atom.h" +#include "amd_pcie.h" #include "amdgpu_powerplay.h" #include "sid.h" #include "si_ih.h" @@ -1461,8 +1462,8 @@ static void si_pcie_gen3_enable(struct amdgpu_device *adev) { struct pci_dev *root = adev->pdev->bus->self; int bridge_pos, gpu_pos; - u32 speed_cntl, mask, current_data_rate; - int ret, i; + u32 speed_cntl, current_data_rate; + int i; u16 tmp16; if (pci_is_root_bus(adev->pdev->bus)) @@ -1474,23 +1475,20 @@ static void si_pcie_gen3_enable(struct amdgpu_device *adev) if (adev->flags & AMD_IS_APU) return; - ret = drm_pcie_get_speed_cap_mask(adev->ddev, &mask); - if (ret != 0) - return; - - if (!(mask & (DRM_PCIE_SPEED_50 | DRM_PCIE_SPEED_80))) + if (!(adev->pm.pcie_gen_mask & (CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2 | + CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3))) return; speed_cntl = RREG32_PCIE_PORT(PCIE_LC_SPEED_CNTL); current_data_rate = (speed_cntl & LC_CURRENT_DATA_RATE_MASK) >> LC_CURRENT_DATA_RATE_SHIFT; - if (mask & DRM_PCIE_SPEED_80) { + if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3) { if (current_data_rate == 2) { DRM_INFO("PCIE gen 3 link speeds already enabled\n"); return; } DRM_INFO("enabling PCIE gen 3 link speeds, disable with amdgpu.pcie_gen2=0\n"); - } else if (mask & DRM_PCIE_SPEED_50) { + } else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2) { if (current_data_rate == 1) { DRM_INFO("PCIE gen 2 link speeds already enabled\n"); return; @@ -1506,7 +1504,7 @@ static void si_pcie_gen3_enable(struct amdgpu_device *adev) if (!gpu_pos) return; - if (mask & DRM_PCIE_SPEED_80) { + if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3) { if (current_data_rate != 2) { u16 bridge_cfg, gpu_cfg; u16 bridge_cfg2, gpu_cfg2; @@ -1589,9 +1587,9 @@ static void si_pcie_gen3_enable(struct amdgpu_device *adev) pci_read_config_word(adev->pdev, gpu_pos + PCI_EXP_LNKCTL2, &tmp16); tmp16 &= ~0xf; - if (mask & DRM_PCIE_SPEED_80) + if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3) tmp16 |= 3; - else if (mask & DRM_PCIE_SPEED_50) + else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2) tmp16 |= 2; else tmp16 |= 1; diff --git a/drivers/gpu/drm/amd/amdgpu/si_dpm.c b/drivers/gpu/drm/amd/amdgpu/si_dpm.c index ce675a7f179a..22f0b7ff3ac9 100644 --- a/drivers/gpu/drm/amd/amdgpu/si_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/si_dpm.c @@ -26,6 +26,7 @@ #include "amdgpu_pm.h" #include "amdgpu_dpm.h" #include "amdgpu_atombios.h" +#include "amd_pcie.h" #include "sid.h" #include "r600_dpm.h" #include "si_dpm.h" @@ -3331,29 +3332,6 @@ static void btc_apply_voltage_delta_rules(struct amdgpu_device *adev, } } -static enum amdgpu_pcie_gen r600_get_pcie_gen_support(struct amdgpu_device *adev, - u32 sys_mask, - enum amdgpu_pcie_gen asic_gen, - enum amdgpu_pcie_gen default_gen) -{ - switch (asic_gen) { - case AMDGPU_PCIE_GEN1: - return AMDGPU_PCIE_GEN1; - case AMDGPU_PCIE_GEN2: - return AMDGPU_PCIE_GEN2; - case AMDGPU_PCIE_GEN3: - return AMDGPU_PCIE_GEN3; - default: - if ((sys_mask & DRM_PCIE_SPEED_80) && (default_gen == AMDGPU_PCIE_GEN3)) - return AMDGPU_PCIE_GEN3; - else if ((sys_mask & DRM_PCIE_SPEED_50) && (default_gen == AMDGPU_PCIE_GEN2)) - return AMDGPU_PCIE_GEN2; - else - return AMDGPU_PCIE_GEN1; - } - return AMDGPU_PCIE_GEN1; -} - static void r600_calculate_u_and_p(u32 i, u32 r_c, u32 p_b, u32 *p, u32 *u) { @@ -5028,10 +5006,11 @@ static int si_populate_smc_acpi_state(struct amdgpu_device *adev, table->ACPIState.levels[0].vddc.index, &table->ACPIState.levels[0].std_vddc); } - table->ACPIState.levels[0].gen2PCIE = (u8)r600_get_pcie_gen_support(adev, - si_pi->sys_pcie_mask, - si_pi->boot_pcie_gen, - AMDGPU_PCIE_GEN1); + table->ACPIState.levels[0].gen2PCIE = + (u8)amdgpu_get_pcie_gen_support(adev, + si_pi->sys_pcie_mask, + si_pi->boot_pcie_gen, + AMDGPU_PCIE_GEN1); if (si_pi->vddc_phase_shed_control) si_populate_phase_shedding_value(adev, @@ -7168,10 +7147,10 @@ static void si_parse_pplib_clock_info(struct amdgpu_device *adev, pl->vddc = le16_to_cpu(clock_info->si.usVDDC); pl->vddci = le16_to_cpu(clock_info->si.usVDDCI); pl->flags = le32_to_cpu(clock_info->si.ulFlags); - pl->pcie_gen = r600_get_pcie_gen_support(adev, - si_pi->sys_pcie_mask, - si_pi->boot_pcie_gen, - clock_info->si.ucPCIEGen); + pl->pcie_gen = amdgpu_get_pcie_gen_support(adev, + si_pi->sys_pcie_mask, + si_pi->boot_pcie_gen, + clock_info->si.ucPCIEGen); /* patch up vddc if necessary */ ret = si_get_leakage_voltage_from_leakage_index(adev, pl->vddc, @@ -7326,7 +7305,6 @@ static int si_dpm_init(struct amdgpu_device *adev) struct si_power_info *si_pi; struct atom_clock_dividers dividers; int ret; - u32 mask; si_pi = kzalloc(sizeof(struct si_power_info), GFP_KERNEL); if (si_pi == NULL) @@ -7336,11 +7314,9 @@ static int si_dpm_init(struct amdgpu_device *adev) eg_pi = &ni_pi->eg; pi = &eg_pi->rv7xx; - ret = drm_pcie_get_speed_cap_mask(adev->ddev, &mask); - if (ret) - si_pi->sys_pcie_mask = 0; - else - si_pi->sys_pcie_mask = mask; + si_pi->sys_pcie_mask = + (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_MASK) >> + CAIL_PCIE_LINK_SPEED_SUPPORT_SHIFT; si_pi->force_pcie_gen = AMDGPU_PCIE_GEN_INVALID; si_pi->boot_pcie_gen = si_get_current_pcie_speed(adev); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 862835dc054e..c345e645f1d7 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1037,6 +1037,10 @@ static void handle_hpd_rx_irq(void *param) !is_mst_root_connector) { /* Downstream Port status changed. */ if (dc_link_detect(dc_link, DETECT_REASON_HPDRX)) { + + if (aconnector->fake_enable) + aconnector->fake_enable = false; + amdgpu_dm_update_connector_after_detect(aconnector); @@ -2012,30 +2016,32 @@ static void update_stream_scaling_settings(const struct drm_display_mode *mode, dst.width = stream->timing.h_addressable; dst.height = stream->timing.v_addressable; - rmx_type = dm_state->scaling; - if (rmx_type == RMX_ASPECT || rmx_type == RMX_OFF) { - if (src.width * dst.height < - src.height * dst.width) { - /* height needs less upscaling/more downscaling */ - dst.width = src.width * - dst.height / src.height; - } else { - /* width needs less upscaling/more downscaling */ - dst.height = src.height * - dst.width / src.width; + if (dm_state) { + rmx_type = dm_state->scaling; + if (rmx_type == RMX_ASPECT || rmx_type == RMX_OFF) { + if (src.width * dst.height < + src.height * dst.width) { + /* height needs less upscaling/more downscaling */ + dst.width = src.width * + dst.height / src.height; + } else { + /* width needs less upscaling/more downscaling */ + dst.height = src.height * + dst.width / src.width; + } + } else if (rmx_type == RMX_CENTER) { + dst = src; } - } else if (rmx_type == RMX_CENTER) { - dst = src; - } - dst.x = (stream->timing.h_addressable - dst.width) / 2; - dst.y = (stream->timing.v_addressable - dst.height) / 2; + dst.x = (stream->timing.h_addressable - dst.width) / 2; + dst.y = (stream->timing.v_addressable - dst.height) / 2; - if (dm_state->underscan_enable) { - dst.x += dm_state->underscan_hborder / 2; - dst.y += dm_state->underscan_vborder / 2; - dst.width -= dm_state->underscan_hborder; - dst.height -= dm_state->underscan_vborder; + if (dm_state->underscan_enable) { + dst.x += dm_state->underscan_hborder / 2; + dst.y += dm_state->underscan_vborder / 2; + dst.width -= dm_state->underscan_hborder; + dst.height -= dm_state->underscan_vborder; + } } stream->src = src; @@ -2360,12 +2366,7 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, if (aconnector == NULL) { DRM_ERROR("aconnector is NULL!\n"); - goto drm_connector_null; - } - - if (dm_state == NULL) { - DRM_ERROR("dm_state is NULL!\n"); - goto dm_state_null; + return stream; } drm_connector = &aconnector->base; @@ -2377,18 +2378,18 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, */ if (aconnector->mst_port) { dm_dp_mst_dc_sink_create(drm_connector); - goto mst_dc_sink_create_done; + return stream; } if (create_fake_sink(aconnector)) - goto stream_create_fail; + return stream; } stream = dc_create_stream_for_sink(aconnector->dc_sink); if (stream == NULL) { DRM_ERROR("Failed to create stream for sink!\n"); - goto stream_create_fail; + return stream; } list_for_each_entry(preferred_mode, &aconnector->base.modes, head) { @@ -2414,9 +2415,12 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, } else { decide_crtc_timing_for_drm_display_mode( &mode, preferred_mode, - dm_state->scaling != RMX_OFF); + dm_state ? (dm_state->scaling != RMX_OFF) : false); } + if (!dm_state) + drm_mode_set_crtcinfo(&mode, 0); + fill_stream_properties_from_drm_display_mode(stream, &mode, &aconnector->base); update_stream_scaling_settings(&mode, dm_state, stream); @@ -2426,10 +2430,8 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, drm_connector, aconnector->dc_sink); -stream_create_fail: -dm_state_null: -drm_connector_null: -mst_dc_sink_create_done: + update_stream_signal(stream); + return stream; } @@ -2497,6 +2499,27 @@ dm_crtc_duplicate_state(struct drm_crtc *crtc) return &state->base; } + +static inline int dm_set_vblank(struct drm_crtc *crtc, bool enable) +{ + enum dc_irq_source irq_source; + struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc); + struct amdgpu_device *adev = crtc->dev->dev_private; + + irq_source = IRQ_TYPE_VBLANK + acrtc->otg_inst; + return dc_interrupt_set(adev->dm.dc, irq_source, enable) ? 0 : -EBUSY; +} + +static int dm_enable_vblank(struct drm_crtc *crtc) +{ + return dm_set_vblank(crtc, true); +} + +static void dm_disable_vblank(struct drm_crtc *crtc) +{ + dm_set_vblank(crtc, false); +} + /* Implemented only the options currently availible for the driver */ static const struct drm_crtc_funcs amdgpu_dm_crtc_funcs = { .reset = dm_crtc_reset_state, @@ -2506,6 +2529,8 @@ static const struct drm_crtc_funcs amdgpu_dm_crtc_funcs = { .page_flip = drm_atomic_helper_page_flip, .atomic_duplicate_state = dm_crtc_duplicate_state, .atomic_destroy_state = dm_crtc_destroy_state, + .enable_vblank = dm_enable_vblank, + .disable_vblank = dm_disable_vblank, }; static enum drm_connector_status @@ -2800,7 +2825,7 @@ int amdgpu_dm_connector_mode_valid(struct drm_connector *connector, goto fail; } - stream = dc_create_stream_for_sink(dc_sink); + stream = create_stream_for_sink(aconnector, mode, NULL); if (stream == NULL) { DRM_ERROR("Failed to create stream for sink!\n"); goto fail; @@ -3060,6 +3085,9 @@ static int dm_plane_atomic_check(struct drm_plane *plane, if (!dm_plane_state->dc_state) return 0; + if (!fill_rects_from_plane_state(state, dm_plane_state->dc_state)) + return -EINVAL; + if (dc_validate_plane(dc, dm_plane_state->dc_state) == DC_OK) return 0; @@ -4632,8 +4660,6 @@ static int dm_update_planes_state(struct dc *dc, bool pflip_needed = !state->allow_modeset; int ret = 0; - if (pflip_needed) - return ret; /* Add new planes */ for_each_oldnew_plane_in_state(state, plane, old_plane_state, new_plane_state, i) { @@ -4648,6 +4674,8 @@ static int dm_update_planes_state(struct dc *dc, /* Remove any changed/removed planes */ if (!enable) { + if (pflip_needed) + continue; if (!old_plane_crtc) continue; @@ -4679,6 +4707,7 @@ static int dm_update_planes_state(struct dc *dc, *lock_and_validation_needed = true; } else { /* Add new planes */ + struct dc_plane_state *dc_new_plane_state; if (drm_atomic_plane_disabling(plane->state, new_plane_state)) continue; @@ -4692,38 +4721,50 @@ static int dm_update_planes_state(struct dc *dc, if (!dm_new_crtc_state->stream) continue; + if (pflip_needed) + continue; WARN_ON(dm_new_plane_state->dc_state); - dm_new_plane_state->dc_state = dc_create_plane_state(dc); - - DRM_DEBUG_DRIVER("Enabling DRM plane: %d on DRM crtc %d\n", - plane->base.id, new_plane_crtc->base.id); - - if (!dm_new_plane_state->dc_state) { + dc_new_plane_state = dc_create_plane_state(dc); + if (!dc_new_plane_state) { ret = -EINVAL; return ret; } + DRM_DEBUG_DRIVER("Enabling DRM plane: %d on DRM crtc %d\n", + plane->base.id, new_plane_crtc->base.id); + ret = fill_plane_attributes( new_plane_crtc->dev->dev_private, - dm_new_plane_state->dc_state, + dc_new_plane_state, new_plane_state, new_crtc_state); - if (ret) + if (ret) { + dc_plane_state_release(dc_new_plane_state); return ret; + } - + /* + * Any atomic check errors that occur after this will + * not need a release. The plane state will be attached + * to the stream, and therefore part of the atomic + * state. It'll be released when the atomic state is + * cleaned. + */ if (!dc_add_plane_to_context( dc, dm_new_crtc_state->stream, - dm_new_plane_state->dc_state, + dc_new_plane_state, dm_state->context)) { + dc_plane_state_release(dc_new_plane_state); ret = -EINVAL; return ret; } + dm_new_plane_state->dc_state = dc_new_plane_state; + /* Tell DC to do a full surface update every time there * is a plane change. Inefficient, but works for now. */ @@ -4737,6 +4778,30 @@ static int dm_update_planes_state(struct dc *dc, return ret; } +static int dm_atomic_check_plane_state_fb(struct drm_atomic_state *state, + struct drm_crtc *crtc) +{ + struct drm_plane *plane; + struct drm_crtc_state *crtc_state; + + WARN_ON(!drm_atomic_get_new_crtc_state(state, crtc)); + + drm_for_each_plane_mask(plane, state->dev, crtc->state->plane_mask) { + struct drm_plane_state *plane_state = + drm_atomic_get_plane_state(state, plane); + + if (IS_ERR(plane_state)) + return -EDEADLK; + + crtc_state = drm_atomic_get_crtc_state(plane_state->state, crtc); + if (crtc->primary == plane && crtc_state->active) { + if (!plane_state->fb) + return -EINVAL; + } + } + return 0; +} + static int amdgpu_dm_atomic_check(struct drm_device *dev, struct drm_atomic_state *state) { @@ -4760,6 +4825,10 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, goto fail; for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { + ret = dm_atomic_check_plane_state_fb(state, crtc); + if (ret) + goto fail; + if (!drm_atomic_crtc_needs_modeset(new_crtc_state) && !new_crtc_state->color_mgmt_changed) continue; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c index 1874b6cee6af..422055080df4 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c @@ -683,10 +683,8 @@ static const struct amdgpu_irq_src_funcs dm_hpd_irq_funcs = { void amdgpu_dm_set_irq_funcs(struct amdgpu_device *adev) { - if (adev->mode_info.num_crtc > 0) - adev->crtc_irq.num_types = AMDGPU_CRTC_IRQ_VLINE1 + adev->mode_info.num_crtc; - else - adev->crtc_irq.num_types = 0; + + adev->crtc_irq.num_types = adev->mode_info.num_crtc; adev->crtc_irq.funcs = &dm_crtc_irq_funcs; adev->pageflip_irq.num_types = adev->mode_info.num_crtc; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index f3d87f418d2e..93421dad21bd 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -189,6 +189,12 @@ void dm_dp_mst_dc_sink_create(struct drm_connector *connector) .link = aconnector->dc_link, .sink_signal = SIGNAL_TYPE_DISPLAY_PORT_MST }; + /* + * TODO: Need to further figure out why ddc.algo is NULL while MST port exists + */ + if (!aconnector->port || !aconnector->port->aux.ddc.algo) + return; + edid = drm_dp_mst_get_edid(connector, &aconnector->mst_port->mst_mgr, aconnector->port); if (!edid) { diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 35e84ed031de..12868c769606 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -1358,13 +1358,13 @@ enum dc_irq_source dc_interrupt_to_irq_source( return dal_irq_service_to_irq_source(dc->res_pool->irqs, src_id, ext_id); } -void dc_interrupt_set(struct dc *dc, enum dc_irq_source src, bool enable) +bool dc_interrupt_set(struct dc *dc, enum dc_irq_source src, bool enable) { if (dc == NULL) - return; + return false; - dal_irq_service_set(dc->res_pool->irqs, src, enable); + return dal_irq_service_set(dc->res_pool->irqs, src, enable); } void dc_interrupt_ack(struct dc *dc, enum dc_irq_source src) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index a37428271573..be5546181fa8 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -1749,8 +1749,7 @@ static void enable_link_hdmi(struct pipe_ctx *pipe_ctx) link->link_enc, pipe_ctx->clock_source->id, display_color_depth, - pipe_ctx->stream->signal == SIGNAL_TYPE_HDMI_TYPE_A, - pipe_ctx->stream->signal == SIGNAL_TYPE_DVI_DUAL_LINK, + pipe_ctx->stream->signal, stream->phy_pix_clk); if (pipe_ctx->stream->signal == SIGNAL_TYPE_HDMI_TYPE_A) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index 95b8dd0e53c6..4d07ffebfd31 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -1360,9 +1360,6 @@ bool dc_is_stream_scaling_unchanged( return true; } -/* Maximum TMDS single link pixel clock 165MHz */ -#define TMDS_MAX_PIXEL_CLOCK_IN_KHZ 165000 - static void update_stream_engine_usage( struct resource_context *res_ctx, const struct resource_pool *pool, diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c index 539c3e0a6292..cd5819789d76 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c @@ -33,8 +33,7 @@ /******************************************************************************* * Private functions ******************************************************************************/ -#define TMDS_MAX_PIXEL_CLOCK_IN_KHZ_UPMOST 297000 -static void update_stream_signal(struct dc_stream_state *stream) +void update_stream_signal(struct dc_stream_state *stream) { struct dc_sink *dc_sink = stream->sink; @@ -45,8 +44,9 @@ static void update_stream_signal(struct dc_stream_state *stream) stream->signal = dc_sink->sink_signal; if (dc_is_dvi_signal(stream->signal)) { - if (stream->timing.pix_clk_khz > TMDS_MAX_PIXEL_CLOCK_IN_KHZ_UPMOST && - stream->sink->sink_signal != SIGNAL_TYPE_DVI_SINGLE_LINK) + if (stream->ctx->dc->caps.dual_link_dvi && + stream->timing.pix_clk_khz > TMDS_MAX_PIXEL_CLOCK && + stream->sink->sink_signal != SIGNAL_TYPE_DVI_SINGLE_LINK) stream->signal = SIGNAL_TYPE_DVI_DUAL_LINK; else stream->signal = SIGNAL_TYPE_DVI_SINGLE_LINK; @@ -193,6 +193,7 @@ bool dc_stream_set_cursor_attributes( core_dc = stream->ctx->dc; res_ctx = &core_dc->current_state->res_ctx; + stream->cursor_attributes = *attributes; for (i = 0; i < MAX_PIPES; i++) { struct pipe_ctx *pipe_ctx = &res_ctx->pipe_ctx[i]; @@ -204,34 +205,8 @@ bool dc_stream_set_cursor_attributes( continue; - if (pipe_ctx->plane_res.ipp->funcs->ipp_cursor_set_attributes != NULL) - pipe_ctx->plane_res.ipp->funcs->ipp_cursor_set_attributes( - pipe_ctx->plane_res.ipp, attributes); - - if (pipe_ctx->plane_res.hubp != NULL && - pipe_ctx->plane_res.hubp->funcs->set_cursor_attributes != NULL) - pipe_ctx->plane_res.hubp->funcs->set_cursor_attributes( - pipe_ctx->plane_res.hubp, attributes); - - if (pipe_ctx->plane_res.mi != NULL && - pipe_ctx->plane_res.mi->funcs->set_cursor_attributes != NULL) - pipe_ctx->plane_res.mi->funcs->set_cursor_attributes( - pipe_ctx->plane_res.mi, attributes); - - - if (pipe_ctx->plane_res.xfm != NULL && - pipe_ctx->plane_res.xfm->funcs->set_cursor_attributes != NULL) - pipe_ctx->plane_res.xfm->funcs->set_cursor_attributes( - pipe_ctx->plane_res.xfm, attributes); - - if (pipe_ctx->plane_res.dpp != NULL && - pipe_ctx->plane_res.dpp->funcs->set_cursor_attributes != NULL) - pipe_ctx->plane_res.dpp->funcs->set_cursor_attributes( - pipe_ctx->plane_res.dpp, attributes->color_format); + core_dc->hwss.set_cursor_attribute(pipe_ctx); } - - stream->cursor_attributes = *attributes; - return true; } @@ -255,21 +230,10 @@ bool dc_stream_set_cursor_position( core_dc = stream->ctx->dc; res_ctx = &core_dc->current_state->res_ctx; + stream->cursor_position = *position; for (i = 0; i < MAX_PIPES; i++) { struct pipe_ctx *pipe_ctx = &res_ctx->pipe_ctx[i]; - struct input_pixel_processor *ipp = pipe_ctx->plane_res.ipp; - struct mem_input *mi = pipe_ctx->plane_res.mi; - struct hubp *hubp = pipe_ctx->plane_res.hubp; - struct dpp *dpp = pipe_ctx->plane_res.dpp; - struct dc_cursor_position pos_cpy = *position; - struct dc_cursor_mi_param param = { - .pixel_clk_khz = stream->timing.pix_clk_khz, - .ref_clk_khz = core_dc->res_pool->ref_clock_inKhz, - .viewport_x_start = pipe_ctx->plane_res.scl_data.viewport.x, - .viewport_width = pipe_ctx->plane_res.scl_data.viewport.width, - .h_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.horz - }; if (pipe_ctx->stream != stream || (!pipe_ctx->plane_res.mi && !pipe_ctx->plane_res.hubp) || @@ -278,33 +242,9 @@ bool dc_stream_set_cursor_position( !pipe_ctx->plane_res.ipp) continue; - if (pipe_ctx->plane_state->address.type - == PLN_ADDR_TYPE_VIDEO_PROGRESSIVE) - pos_cpy.enable = false; - - if (pipe_ctx->top_pipe && pipe_ctx->plane_state != pipe_ctx->top_pipe->plane_state) - pos_cpy.enable = false; - - - if (ipp != NULL && ipp->funcs->ipp_cursor_set_position != NULL) - ipp->funcs->ipp_cursor_set_position(ipp, &pos_cpy, ¶m); - - if (mi != NULL && mi->funcs->set_cursor_position != NULL) - mi->funcs->set_cursor_position(mi, &pos_cpy, ¶m); - - if (!hubp) - continue; - - if (hubp->funcs->set_cursor_position != NULL) - hubp->funcs->set_cursor_position(hubp, &pos_cpy, ¶m); - - if (dpp != NULL && dpp->funcs->set_cursor_position != NULL) - dpp->funcs->set_cursor_position(dpp, &pos_cpy, ¶m, hubp->curs_attr.width); - + core_dc->hwss.set_cursor_position(pipe_ctx); } - stream->cursor_position = *position; - return true; } diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index e2e3c9df79ea..d6d56611604e 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -62,6 +62,7 @@ struct dc_caps { bool dcc_const_color; bool dynamic_audio; bool is_apu; + bool dual_link_dvi; }; struct dc_dcc_surface_param { @@ -672,7 +673,7 @@ enum dc_irq_source dc_interrupt_to_irq_source( struct dc *dc, uint32_t src_id, uint32_t ext_id); -void dc_interrupt_set(struct dc *dc, enum dc_irq_source src, bool enable); +bool dc_interrupt_set(struct dc *dc, enum dc_irq_source src, bool enable); void dc_interrupt_ack(struct dc *dc, enum dc_irq_source src); enum dc_irq_source dc_get_hpd_irq_source_at_index( struct dc *dc, uint32_t link_index); diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h index 01c60f11b2bd..456e4d29eadd 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_stream.h +++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h @@ -237,6 +237,8 @@ enum surface_update_type dc_check_update_surfaces_for_stream( */ struct dc_stream_state *dc_create_stream_for_sink(struct dc_sink *dc_sink); +void update_stream_signal(struct dc_stream_state *stream); + void dc_stream_retain(struct dc_stream_state *dc_stream); void dc_stream_release(struct dc_stream_state *dc_stream); diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h index b73db9e78437..a993279a8f2d 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h @@ -236,6 +236,7 @@ SR(D2VGA_CONTROL), \ SR(D3VGA_CONTROL), \ SR(D4VGA_CONTROL), \ + SR(VGA_TEST_CONTROL), \ SR(DC_IP_REQUEST_CNTL), \ BL_REG_LIST() @@ -337,6 +338,7 @@ struct dce_hwseq_registers { uint32_t D2VGA_CONTROL; uint32_t D3VGA_CONTROL; uint32_t D4VGA_CONTROL; + uint32_t VGA_TEST_CONTROL; /* MMHUB registers. read only. temporary hack */ uint32_t VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32; uint32_t VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_LO32; @@ -493,6 +495,9 @@ struct dce_hwseq_registers { HWS_SF(, DOMAIN6_PG_STATUS, DOMAIN6_PGFSM_PWR_STATUS, mask_sh), \ HWS_SF(, DOMAIN7_PG_STATUS, DOMAIN7_PGFSM_PWR_STATUS, mask_sh), \ HWS_SF(, DC_IP_REQUEST_CNTL, IP_REQUEST_EN, mask_sh), \ + HWS_SF(, D1VGA_CONTROL, D1VGA_MODE_ENABLE, mask_sh),\ + HWS_SF(, VGA_TEST_CONTROL, VGA_TEST_ENABLE, mask_sh),\ + HWS_SF(, VGA_TEST_CONTROL, VGA_TEST_RENDER_START, mask_sh),\ HWS_SF(, LVTMA_PWRSEQ_CNTL, LVTMA_BLON, mask_sh), \ HWS_SF(, LVTMA_PWRSEQ_STATE, LVTMA_PWRSEQ_TARGET_STATE_R, mask_sh) @@ -583,7 +588,10 @@ struct dce_hwseq_registers { type DCFCLK_GATE_DIS; \ type DCHUBBUB_GLOBAL_TIMER_REFDIV; \ type DENTIST_DPPCLK_WDIVIDER; \ - type DENTIST_DISPCLK_WDIVIDER; + type DENTIST_DISPCLK_WDIVIDER; \ + type VGA_TEST_ENABLE; \ + type VGA_TEST_RENDER_START; \ + type D1VGA_MODE_ENABLE; struct dce_hwseq_shift { HWSEQ_REG_FIELD_LIST(uint8_t) diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c index a266e3f5e75f..e4741f1a2b01 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c @@ -82,13 +82,6 @@ #define DCE110_DIG_FE_SOURCE_SELECT_DIGF 0x20 #define DCE110_DIG_FE_SOURCE_SELECT_DIGG 0x40 -/* Minimum pixel clock, in KHz. For TMDS signal is 25.00 MHz */ -#define TMDS_MIN_PIXEL_CLOCK 25000 -/* Maximum pixel clock, in KHz. For TMDS signal is 165.00 MHz */ -#define TMDS_MAX_PIXEL_CLOCK 165000 -/* For current ASICs pixel clock - 600MHz */ -#define MAX_ENCODER_CLOCK 600000 - enum { DP_MST_UPDATE_MAX_RETRY = 50 }; @@ -683,6 +676,7 @@ void dce110_link_encoder_construct( { struct bp_encoder_cap_info bp_cap_info = {0}; const struct dc_vbios_funcs *bp_funcs = init_data->ctx->dc_bios->funcs; + enum bp_result result = BP_RESULT_OK; enc110->base.funcs = &dce110_lnk_enc_funcs; enc110->base.ctx = init_data->ctx; @@ -757,15 +751,24 @@ void dce110_link_encoder_construct( enc110->base.preferred_engine = ENGINE_ID_UNKNOWN; } + /* default to one to mirror Windows behavior */ + enc110->base.features.flags.bits.HDMI_6GB_EN = 1; + + result = bp_funcs->get_encoder_cap_info(enc110->base.ctx->dc_bios, + enc110->base.id, &bp_cap_info); + /* Override features with DCE-specific values */ - if (BP_RESULT_OK == bp_funcs->get_encoder_cap_info( - enc110->base.ctx->dc_bios, enc110->base.id, - &bp_cap_info)) { + if (BP_RESULT_OK == result) { enc110->base.features.flags.bits.IS_HBR2_CAPABLE = bp_cap_info.DP_HBR2_EN; enc110->base.features.flags.bits.IS_HBR3_CAPABLE = bp_cap_info.DP_HBR3_EN; enc110->base.features.flags.bits.HDMI_6GB_EN = bp_cap_info.HDMI_6GB_EN; + } else { + dm_logger_write(enc110->base.ctx->logger, LOG_WARNING, + "%s: Failed to get encoder_cap_info from VBIOS with error code %d!\n", + __func__, + result); } } @@ -904,8 +907,7 @@ void dce110_link_encoder_enable_tmds_output( struct link_encoder *enc, enum clock_source_id clock_source, enum dc_color_depth color_depth, - bool hdmi, - bool dual_link, + enum signal_type signal, uint32_t pixel_clock) { struct dce110_link_encoder *enc110 = TO_DCE110_LINK_ENC(enc); @@ -919,16 +921,12 @@ void dce110_link_encoder_enable_tmds_output( cntl.engine_id = enc->preferred_engine; cntl.transmitter = enc110->base.transmitter; cntl.pll_id = clock_source; - if (hdmi) { - cntl.signal = SIGNAL_TYPE_HDMI_TYPE_A; - cntl.lanes_number = 4; - } else if (dual_link) { - cntl.signal = SIGNAL_TYPE_DVI_DUAL_LINK; + cntl.signal = signal; + if (cntl.signal == SIGNAL_TYPE_DVI_DUAL_LINK) cntl.lanes_number = 8; - } else { - cntl.signal = SIGNAL_TYPE_DVI_SINGLE_LINK; + else cntl.lanes_number = 4; - } + cntl.hpd_sel = enc110->base.hpd_source; cntl.pixel_clock = pixel_clock; diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.h index 8ca9afe47a2b..0ec3433d34b6 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.h @@ -210,8 +210,7 @@ void dce110_link_encoder_enable_tmds_output( struct link_encoder *enc, enum clock_source_id clock_source, enum dc_color_depth color_depth, - bool hdmi, - bool dual_link, + enum signal_type signal, uint32_t pixel_clock); /* enables DP PHY output */ diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c index 3ea43e2a9450..442dd2d93618 100644 --- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c @@ -852,6 +852,7 @@ static bool construct( dc->caps.max_downscale_ratio = 200; dc->caps.i2c_speed_in_khz = 40; dc->caps.max_cursor_size = 128; + dc->caps.dual_link_dvi = true; for (i = 0; i < pool->base.pipe_count; i++) { pool->base.timing_generators[i] = diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index 86cdd7b4811f..6f382a3ac90f 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -688,15 +688,22 @@ void dce110_enable_stream(struct pipe_ctx *pipe_ctx) struct dc_crtc_timing *timing = &pipe_ctx->stream->timing; struct dc_link *link = pipe_ctx->stream->sink->link; - /* 1. update AVI info frame (HDMI, DP) - * we always need to update info frame - */ + uint32_t active_total_with_borders; uint32_t early_control = 0; struct timing_generator *tg = pipe_ctx->stream_res.tg; - /* TODOFPGA may change to hwss.update_info_frame */ + /* For MST, there are multiply stream go to only one link. + * connect DIG back_end to front_end while enable_stream and + * disconnect them during disable_stream + * BY this, it is logic clean to separate stream and link */ + link->link_enc->funcs->connect_dig_be_to_fe(link->link_enc, + pipe_ctx->stream_res.stream_enc->id, true); + + /* update AVI info frame (HDMI, DP)*/ + /* TODO: FPGA may change to hwss.update_info_frame */ dce110_update_info_frame(pipe_ctx); + /* enable early control to avoid corruption on DP monitor*/ active_total_with_borders = timing->h_addressable @@ -717,12 +724,8 @@ void dce110_enable_stream(struct pipe_ctx *pipe_ctx) pipe_ctx->stream_res.stream_enc->funcs->dp_audio_enable(pipe_ctx->stream_res.stream_enc); } - /* For MST, there are multiply stream go to only one link. - * connect DIG back_end to front_end while enable_stream and - * disconnect them during disable_stream - * BY this, it is logic clean to separate stream and link */ - link->link_enc->funcs->connect_dig_be_to_fe(link->link_enc, - pipe_ctx->stream_res.stream_enc->id, true); + + } @@ -1690,9 +1693,13 @@ static void apply_min_clocks( * Check if FBC can be enabled */ static bool should_enable_fbc(struct dc *dc, - struct dc_state *context) + struct dc_state *context, + uint32_t *pipe_idx) { - struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[0]; + uint32_t i; + struct pipe_ctx *pipe_ctx = NULL; + struct resource_context *res_ctx = &context->res_ctx; + ASSERT(dc->fbc_compressor); @@ -1704,6 +1711,14 @@ static bool should_enable_fbc(struct dc *dc, if (context->stream_count != 1) return false; + for (i = 0; i < dc->res_pool->pipe_count; i++) { + if (res_ctx->pipe_ctx[i].stream) { + pipe_ctx = &res_ctx->pipe_ctx[i]; + *pipe_idx = i; + break; + } + } + /* Only supports eDP */ if (pipe_ctx->stream->sink->link->connector_signal != SIGNAL_TYPE_EDP) return false; @@ -1729,11 +1744,14 @@ static bool should_enable_fbc(struct dc *dc, static void enable_fbc(struct dc *dc, struct dc_state *context) { - if (should_enable_fbc(dc, context)) { + uint32_t pipe_idx = 0; + + if (should_enable_fbc(dc, context, &pipe_idx)) { /* Program GRPH COMPRESSED ADDRESS and PITCH */ struct compr_addr_and_pitch_params params = {0, 0, 0}; struct compressor *compr = dc->fbc_compressor; - struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[0]; + struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[pipe_idx]; + params.source_view_width = pipe_ctx->stream->timing.h_addressable; params.source_view_height = pipe_ctx->stream->timing.v_addressable; @@ -2915,6 +2933,49 @@ static void program_csc_matrix(struct pipe_ctx *pipe_ctx, } } +void dce110_set_cursor_position(struct pipe_ctx *pipe_ctx) +{ + struct dc_cursor_position pos_cpy = pipe_ctx->stream->cursor_position; + struct input_pixel_processor *ipp = pipe_ctx->plane_res.ipp; + struct mem_input *mi = pipe_ctx->plane_res.mi; + struct dc_cursor_mi_param param = { + .pixel_clk_khz = pipe_ctx->stream->timing.pix_clk_khz, + .ref_clk_khz = pipe_ctx->stream->ctx->dc->res_pool->ref_clock_inKhz, + .viewport_x_start = pipe_ctx->plane_res.scl_data.viewport.x, + .viewport_width = pipe_ctx->plane_res.scl_data.viewport.width, + .h_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.horz + }; + + if (pipe_ctx->plane_state->address.type + == PLN_ADDR_TYPE_VIDEO_PROGRESSIVE) + pos_cpy.enable = false; + + if (pipe_ctx->top_pipe && pipe_ctx->plane_state != pipe_ctx->top_pipe->plane_state) + pos_cpy.enable = false; + + if (ipp->funcs->ipp_cursor_set_position) + ipp->funcs->ipp_cursor_set_position(ipp, &pos_cpy, ¶m); + if (mi->funcs->set_cursor_position) + mi->funcs->set_cursor_position(mi, &pos_cpy, ¶m); +} + +void dce110_set_cursor_attribute(struct pipe_ctx *pipe_ctx) +{ + struct dc_cursor_attributes *attributes = &pipe_ctx->stream->cursor_attributes; + + if (pipe_ctx->plane_res.ipp->funcs->ipp_cursor_set_attributes) + pipe_ctx->plane_res.ipp->funcs->ipp_cursor_set_attributes( + pipe_ctx->plane_res.ipp, attributes); + + if (pipe_ctx->plane_res.mi->funcs->set_cursor_attributes) + pipe_ctx->plane_res.mi->funcs->set_cursor_attributes( + pipe_ctx->plane_res.mi, attributes); + + if (pipe_ctx->plane_res.xfm->funcs->set_cursor_attributes) + pipe_ctx->plane_res.xfm->funcs->set_cursor_attributes( + pipe_ctx->plane_res.xfm, attributes); +} + static void ready_shared_resources(struct dc *dc, struct dc_state *context) {} static void optimize_shared_resources(struct dc *dc) {} @@ -2957,6 +3018,8 @@ static const struct hw_sequencer_funcs dce110_funcs = { .edp_backlight_control = hwss_edp_backlight_control, .edp_power_control = hwss_edp_power_control, .edp_wait_for_hpd_ready = hwss_edp_wait_for_hpd_ready, + .set_cursor_position = dce110_set_cursor_position, + .set_cursor_attribute = dce110_set_cursor_attribute }; void dce110_hw_sequencer_construct(struct dc *dc) diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c index 7c4779578fb7..00f18c485e1e 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c @@ -846,6 +846,16 @@ static bool dce110_validate_bandwidth( return result; } +enum dc_status dce110_validate_plane(const struct dc_plane_state *plane_state, + struct dc_caps *caps) +{ + if (((plane_state->dst_rect.width * 2) < plane_state->src_rect.width) || + ((plane_state->dst_rect.height * 2) < plane_state->src_rect.height)) + return DC_FAIL_SURFACE_VALIDATE; + + return DC_OK; +} + static bool dce110_validate_surface_sets( struct dc_state *context) { @@ -869,6 +879,13 @@ static bool dce110_validate_surface_sets( plane->src_rect.height > 1080)) return false; + /* we don't have the logic to support underlay + * only yet so block the use case where we get + * NV12 plane as top layer + */ + if (j == 0) + return false; + /* irrespective of plane format, * stream should be RGB encoded */ @@ -1021,6 +1038,7 @@ static const struct resource_funcs dce110_res_pool_funcs = { .link_enc_create = dce110_link_encoder_create, .validate_guaranteed = dce110_validate_guaranteed, .validate_bandwidth = dce110_validate_bandwidth, + .validate_plane = dce110_validate_plane, .acquire_idle_pipe_for_layer = dce110_acquire_underlay, .add_stream_to_ctx = dce110_add_stream_to_ctx, .validate_global = dce110_validate_global diff --git a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c index 663e0a047a4b..98d9cd0109e1 100644 --- a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c @@ -1103,6 +1103,8 @@ static bool construct( dc->caps.max_downscale_ratio = 200; dc->caps.i2c_speed_in_khz = 100; dc->caps.max_cursor_size = 128; + dc->caps.dual_link_dvi = true; + /************************************************* * Create resources * diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c index 57cd67359567..5aab01db28ee 100644 --- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c @@ -835,6 +835,8 @@ static bool construct( dc->caps.max_downscale_ratio = 200; dc->caps.i2c_speed_in_khz = 100; dc->caps.max_cursor_size = 128; + dc->caps.dual_link_dvi = true; + dc->debug = debug_defaults; /************************************************* diff --git a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c index 8f2bd56f3461..25d7eb1567ae 100644 --- a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c @@ -793,6 +793,7 @@ static bool dce80_construct( dc->caps.max_downscale_ratio = 200; dc->caps.i2c_speed_in_khz = 40; dc->caps.max_cursor_size = 128; + dc->caps.dual_link_dvi = true; /************************************************* * Create resources * diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index 82572863acab..072e4485e85e 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -238,10 +238,24 @@ static void enable_power_gating_plane( static void disable_vga( struct dce_hwseq *hws) { + unsigned int in_vga_mode = 0; + + REG_GET(D1VGA_CONTROL, D1VGA_MODE_ENABLE, &in_vga_mode); + + if (in_vga_mode == 0) + return; + REG_WRITE(D1VGA_CONTROL, 0); - REG_WRITE(D2VGA_CONTROL, 0); - REG_WRITE(D3VGA_CONTROL, 0); - REG_WRITE(D4VGA_CONTROL, 0); + + /* HW Engineer's Notes: + * During switch from vga->extended, if we set the VGA_TEST_ENABLE and + * then hit the VGA_TEST_RENDER_START, then the DCHUBP timing gets updated correctly. + * + * Then vBIOS will have it poll for the VGA_TEST_RENDER_DONE and unset + * VGA_TEST_ENABLE, to leave it in the same state as before. + */ + REG_UPDATE(VGA_TEST_CONTROL, VGA_TEST_ENABLE, 1); + REG_UPDATE(VGA_TEST_CONTROL, VGA_TEST_RENDER_START, 1); } static void dpp_pg_control( @@ -1761,6 +1775,11 @@ static void update_dchubp_dpp( &pipe_ctx->plane_res.scl_data.viewport_c); } + if (pipe_ctx->stream->cursor_attributes.address.quad_part != 0) { + dc->hwss.set_cursor_position(pipe_ctx); + dc->hwss.set_cursor_attribute(pipe_ctx); + } + if (plane_state->update_flags.bits.full_update) { /*gamut remap*/ program_gamut_remap(pipe_ctx); @@ -2296,7 +2315,7 @@ static bool dcn10_dummy_display_power_gating( return true; } -void dcn10_update_pending_status(struct pipe_ctx *pipe_ctx) +static void dcn10_update_pending_status(struct pipe_ctx *pipe_ctx) { struct dc_plane_state *plane_state = pipe_ctx->plane_state; struct timing_generator *tg = pipe_ctx->stream_res.tg; @@ -2316,12 +2335,46 @@ void dcn10_update_pending_status(struct pipe_ctx *pipe_ctx) } } -void dcn10_update_dchub(struct dce_hwseq *hws, struct dchub_init_data *dh_data) +static void dcn10_update_dchub(struct dce_hwseq *hws, struct dchub_init_data *dh_data) { if (hws->ctx->dc->res_pool->hubbub != NULL) hubbub1_update_dchub(hws->ctx->dc->res_pool->hubbub, dh_data); } +static void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx) +{ + struct dc_cursor_position pos_cpy = pipe_ctx->stream->cursor_position; + struct hubp *hubp = pipe_ctx->plane_res.hubp; + struct dpp *dpp = pipe_ctx->plane_res.dpp; + struct dc_cursor_mi_param param = { + .pixel_clk_khz = pipe_ctx->stream->timing.pix_clk_khz, + .ref_clk_khz = pipe_ctx->stream->ctx->dc->res_pool->ref_clock_inKhz, + .viewport_x_start = pipe_ctx->plane_res.scl_data.viewport.x, + .viewport_width = pipe_ctx->plane_res.scl_data.viewport.width, + .h_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.horz + }; + + if (pipe_ctx->plane_state->address.type + == PLN_ADDR_TYPE_VIDEO_PROGRESSIVE) + pos_cpy.enable = false; + + if (pipe_ctx->top_pipe && pipe_ctx->plane_state != pipe_ctx->top_pipe->plane_state) + pos_cpy.enable = false; + + hubp->funcs->set_cursor_position(hubp, &pos_cpy, ¶m); + dpp->funcs->set_cursor_position(dpp, &pos_cpy, ¶m, hubp->curs_attr.width); +} + +static void dcn10_set_cursor_attribute(struct pipe_ctx *pipe_ctx) +{ + struct dc_cursor_attributes *attributes = &pipe_ctx->stream->cursor_attributes; + + pipe_ctx->plane_res.hubp->funcs->set_cursor_attributes( + pipe_ctx->plane_res.hubp, attributes); + pipe_ctx->plane_res.dpp->funcs->set_cursor_attributes( + pipe_ctx->plane_res.dpp, attributes->color_format); +} + static const struct hw_sequencer_funcs dcn10_funcs = { .program_gamut_remap = program_gamut_remap, .program_csc_matrix = program_csc_matrix, @@ -2362,6 +2415,8 @@ static const struct hw_sequencer_funcs dcn10_funcs = { .edp_backlight_control = hwss_edp_backlight_control, .edp_power_control = hwss_edp_power_control, .edp_wait_for_hpd_ready = hwss_edp_wait_for_hpd_ready, + .set_cursor_position = dcn10_set_cursor_position, + .set_cursor_attribute = dcn10_set_cursor_attribute }; diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h b/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h index 0fd329deacd8..54d8a1386142 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h @@ -123,8 +123,7 @@ struct link_encoder_funcs { void (*enable_tmds_output)(struct link_encoder *enc, enum clock_source_id clock_source, enum dc_color_depth color_depth, - bool hdmi, - bool dual_link, + enum signal_type signal, uint32_t pixel_clock); void (*enable_dp_output)(struct link_encoder *enc, const struct dc_link_settings *link_settings, diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h index 4c0aa56f7bae..379c6ecd271a 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h @@ -198,6 +198,9 @@ struct hw_sequencer_funcs { bool enable); void (*edp_wait_for_hpd_ready)(struct dc_link *link, bool power_up); + void (*set_cursor_position)(struct pipe_ctx *pipe); + void (*set_cursor_attribute)(struct pipe_ctx *pipe); + }; void color_space_to_black_color( diff --git a/drivers/gpu/drm/amd/display/dc/irq/dce110/irq_service_dce110.c b/drivers/gpu/drm/amd/display/dc/irq/dce110/irq_service_dce110.c index f7e40b292dfb..d3e1923b01a8 100644 --- a/drivers/gpu/drm/amd/display/dc/irq/dce110/irq_service_dce110.c +++ b/drivers/gpu/drm/amd/display/dc/irq/dce110/irq_service_dce110.c @@ -217,7 +217,7 @@ bool dce110_vblank_set( core_dc->current_state->res_ctx.pipe_ctx[pipe_offset].stream_res.tg; if (enable) { - if (!tg->funcs->arm_vert_intr(tg, 2)) { + if (!tg || !tg->funcs->arm_vert_intr(tg, 2)) { DC_ERROR("Failed to get VBLANK!\n"); return false; } diff --git a/drivers/gpu/drm/amd/display/dc/virtual/virtual_link_encoder.c b/drivers/gpu/drm/amd/display/dc/virtual/virtual_link_encoder.c index 57a54a7b89e5..1c079ba37c30 100644 --- a/drivers/gpu/drm/amd/display/dc/virtual/virtual_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/virtual/virtual_link_encoder.c @@ -42,8 +42,7 @@ static void virtual_link_encoder_enable_tmds_output( struct link_encoder *enc, enum clock_source_id clock_source, enum dc_color_depth color_depth, - bool hdmi, - bool dual_link, + enum signal_type signal, uint32_t pixel_clock) {} static void virtual_link_encoder_enable_dp_output( diff --git a/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h b/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h index 7a9b43f84a31..36bbad594267 100644 --- a/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h +++ b/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h @@ -419,11 +419,6 @@ struct bios_event_info { bool backlight_changed; }; -enum { - HDMI_PIXEL_CLOCK_IN_KHZ_297 = 297000, - TMDS_PIXEL_CLOCK_IN_KHZ_165 = 165000 -}; - /* * DFS-bypass flag */ diff --git a/drivers/gpu/drm/amd/display/include/signal_types.h b/drivers/gpu/drm/amd/display/include/signal_types.h index b5ebde642207..199c5db67cbc 100644 --- a/drivers/gpu/drm/amd/display/include/signal_types.h +++ b/drivers/gpu/drm/amd/display/include/signal_types.h @@ -26,6 +26,11 @@ #ifndef __DC_SIGNAL_TYPES_H__ #define __DC_SIGNAL_TYPES_H__ +/* Minimum pixel clock, in KHz. For TMDS signal is 25.00 MHz */ +#define TMDS_MIN_PIXEL_CLOCK 25000 +/* Maximum pixel clock, in KHz. For TMDS signal is 165.00 MHz */ +#define TMDS_MAX_PIXEL_CLOCK 165000 + enum signal_type { SIGNAL_TYPE_NONE = 0L, /* no signal */ SIGNAL_TYPE_DVI_SINGLE_LINK = (1 << 0), diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index dd89abd2263d..66ee9d888d16 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -3205,8 +3205,10 @@ void i915_gem_set_wedged(struct drm_i915_private *i915) * rolling the global seqno forward (since this would complete requests * for which we haven't set the fence error to EIO yet). */ - for_each_engine(engine, i915, id) + for_each_engine(engine, i915, id) { + i915_gem_reset_prepare_engine(engine); engine->submit_request = nop_submit_request; + } /* * Make sure no one is running the old callback before we proceed with @@ -3244,6 +3246,8 @@ void i915_gem_set_wedged(struct drm_i915_private *i915) intel_engine_init_global_seqno(engine, intel_engine_last_submit(engine)); spin_unlock_irqrestore(&engine->timeline->lock, flags); + + i915_gem_reset_finish_engine(engine); } set_bit(I915_WEDGED, &i915->gpu_error.flags); diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 0be50e43507d..f8fe5ffcdcff 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -1303,9 +1303,8 @@ static void i915_oa_stream_destroy(struct i915_perf_stream *stream) */ mutex_lock(&dev_priv->drm.struct_mutex); dev_priv->perf.oa.exclusive_stream = NULL; - mutex_unlock(&dev_priv->drm.struct_mutex); - dev_priv->perf.oa.ops.disable_metric_set(dev_priv); + mutex_unlock(&dev_priv->drm.struct_mutex); free_oa_buffer(dev_priv); @@ -1756,22 +1755,13 @@ static int gen8_switch_to_updated_kernel_context(struct drm_i915_private *dev_pr * Note: it's only the RCS/Render context that has any OA state. */ static int gen8_configure_all_contexts(struct drm_i915_private *dev_priv, - const struct i915_oa_config *oa_config, - bool interruptible) + const struct i915_oa_config *oa_config) { struct i915_gem_context *ctx; int ret; unsigned int wait_flags = I915_WAIT_LOCKED; - if (interruptible) { - ret = i915_mutex_lock_interruptible(&dev_priv->drm); - if (ret) - return ret; - - wait_flags |= I915_WAIT_INTERRUPTIBLE; - } else { - mutex_lock(&dev_priv->drm.struct_mutex); - } + lockdep_assert_held(&dev_priv->drm.struct_mutex); /* Switch away from any user context. */ ret = gen8_switch_to_updated_kernel_context(dev_priv, oa_config); @@ -1819,8 +1809,6 @@ static int gen8_configure_all_contexts(struct drm_i915_private *dev_priv, } out: - mutex_unlock(&dev_priv->drm.struct_mutex); - return ret; } @@ -1863,7 +1851,7 @@ static int gen8_enable_metric_set(struct drm_i915_private *dev_priv, * to make sure all slices/subslices are ON before writing to NOA * registers. */ - ret = gen8_configure_all_contexts(dev_priv, oa_config, true); + ret = gen8_configure_all_contexts(dev_priv, oa_config); if (ret) return ret; @@ -1878,7 +1866,7 @@ static int gen8_enable_metric_set(struct drm_i915_private *dev_priv, static void gen8_disable_metric_set(struct drm_i915_private *dev_priv) { /* Reset all contexts' slices/subslices configurations. */ - gen8_configure_all_contexts(dev_priv, NULL, false); + gen8_configure_all_contexts(dev_priv, NULL); I915_WRITE(GDT_CHICKEN_BITS, (I915_READ(GDT_CHICKEN_BITS) & ~GT_NOA_ENABLE)); @@ -1888,7 +1876,7 @@ static void gen8_disable_metric_set(struct drm_i915_private *dev_priv) static void gen10_disable_metric_set(struct drm_i915_private *dev_priv) { /* Reset all contexts' slices/subslices configurations. */ - gen8_configure_all_contexts(dev_priv, NULL, false); + gen8_configure_all_contexts(dev_priv, NULL); /* Make sure we disable noa to save power. */ I915_WRITE(RPM_CONFIG1, @@ -2138,6 +2126,10 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, if (ret) goto err_oa_buf_alloc; + ret = i915_mutex_lock_interruptible(&dev_priv->drm); + if (ret) + goto err_lock; + ret = dev_priv->perf.oa.ops.enable_metric_set(dev_priv, stream->oa_config); if (ret) @@ -2145,23 +2137,17 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, stream->ops = &i915_oa_stream_ops; - /* Lock device for exclusive_stream access late because - * enable_metric_set() might lock as well on gen8+. - */ - ret = i915_mutex_lock_interruptible(&dev_priv->drm); - if (ret) - goto err_lock; - dev_priv->perf.oa.exclusive_stream = stream; mutex_unlock(&dev_priv->drm.struct_mutex); return 0; -err_lock: +err_enable: dev_priv->perf.oa.ops.disable_metric_set(dev_priv); + mutex_unlock(&dev_priv->drm.struct_mutex); -err_enable: +err_lock: free_oa_buffer(dev_priv); err_oa_buf_alloc: diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index 7ece2f061b9e..e0fca035ff78 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -719,6 +719,8 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine) struct rb_node *rb; unsigned long flags; + GEM_TRACE("%s\n", engine->name); + spin_lock_irqsave(&engine->timeline->lock, flags); /* Cancel the requests on the HW and clear the ELSP tracker. */ @@ -765,6 +767,9 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine) */ clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted); + /* Mark all CS interrupts as complete */ + execlists->active = 0; + spin_unlock_irqrestore(&engine->timeline->lock, flags); } diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c index d3045a371a55..7c73bc7e2f85 100644 --- a/drivers/gpu/drm/radeon/cik.c +++ b/drivers/gpu/drm/radeon/cik.c @@ -3221,35 +3221,8 @@ static void cik_gpu_init(struct radeon_device *rdev) case CHIP_KAVERI: rdev->config.cik.max_shader_engines = 1; rdev->config.cik.max_tile_pipes = 4; - if ((rdev->pdev->device == 0x1304) || - (rdev->pdev->device == 0x1305) || - (rdev->pdev->device == 0x130C) || - (rdev->pdev->device == 0x130F) || - (rdev->pdev->device == 0x1310) || - (rdev->pdev->device == 0x1311) || - (rdev->pdev->device == 0x131C)) { - rdev->config.cik.max_cu_per_sh = 8; - rdev->config.cik.max_backends_per_se = 2; - } else if ((rdev->pdev->device == 0x1309) || - (rdev->pdev->device == 0x130A) || - (rdev->pdev->device == 0x130D) || - (rdev->pdev->device == 0x1313) || - (rdev->pdev->device == 0x131D)) { - rdev->config.cik.max_cu_per_sh = 6; - rdev->config.cik.max_backends_per_se = 2; - } else if ((rdev->pdev->device == 0x1306) || - (rdev->pdev->device == 0x1307) || - (rdev->pdev->device == 0x130B) || - (rdev->pdev->device == 0x130E) || - (rdev->pdev->device == 0x1315) || - (rdev->pdev->device == 0x1318) || - (rdev->pdev->device == 0x131B)) { - rdev->config.cik.max_cu_per_sh = 4; - rdev->config.cik.max_backends_per_se = 1; - } else { - rdev->config.cik.max_cu_per_sh = 3; - rdev->config.cik.max_backends_per_se = 1; - } + rdev->config.cik.max_cu_per_sh = 8; + rdev->config.cik.max_backends_per_se = 2; rdev->config.cik.max_sh_per_se = 1; rdev->config.cik.max_texture_channel_caches = 4; rdev->config.cik.max_gprs = 256; diff --git a/drivers/gpu/drm/sun4i/sun4i_crtc.c b/drivers/gpu/drm/sun4i/sun4i_crtc.c index 5decae0069d0..78cbc3145e44 100644 --- a/drivers/gpu/drm/sun4i/sun4i_crtc.c +++ b/drivers/gpu/drm/sun4i/sun4i_crtc.c @@ -93,6 +93,8 @@ static void sun4i_crtc_atomic_disable(struct drm_crtc *crtc, DRM_DEBUG_DRIVER("Disabling the CRTC\n"); + drm_crtc_vblank_off(crtc); + sun4i_tcon_set_status(scrtc->tcon, encoder, false); if (crtc->state->event && !crtc->state->active) { @@ -113,6 +115,8 @@ static void sun4i_crtc_atomic_enable(struct drm_crtc *crtc, DRM_DEBUG_DRIVER("Enabling the CRTC\n"); sun4i_tcon_set_status(scrtc->tcon, encoder, true); + + drm_crtc_vblank_on(crtc); } static void sun4i_crtc_mode_set_nofb(struct drm_crtc *crtc) diff --git a/drivers/gpu/drm/sun4i/sun4i_dotclock.c b/drivers/gpu/drm/sun4i/sun4i_dotclock.c index 023f39bda633..e36004fbe453 100644 --- a/drivers/gpu/drm/sun4i/sun4i_dotclock.c +++ b/drivers/gpu/drm/sun4i/sun4i_dotclock.c @@ -132,10 +132,13 @@ static int sun4i_dclk_get_phase(struct clk_hw *hw) static int sun4i_dclk_set_phase(struct clk_hw *hw, int degrees) { struct sun4i_dclk *dclk = hw_to_dclk(hw); + u32 val = degrees / 120; + + val <<= 28; regmap_update_bits(dclk->regmap, SUN4I_TCON0_IO_POL_REG, GENMASK(29, 28), - degrees / 120); + val); return 0; } diff --git a/drivers/gpu/drm/sun4i/sun4i_rgb.c b/drivers/gpu/drm/sun4i/sun4i_rgb.c index 832f8f9bc47f..b8da5a50a61d 100644 --- a/drivers/gpu/drm/sun4i/sun4i_rgb.c +++ b/drivers/gpu/drm/sun4i/sun4i_rgb.c @@ -92,6 +92,8 @@ static int sun4i_rgb_mode_valid(struct drm_connector *connector, DRM_DEBUG_DRIVER("Vertical parameters OK\n"); + tcon->dclk_min_div = 6; + tcon->dclk_max_div = 127; rounded_rate = clk_round_rate(tcon->dclk, rate); if (rounded_rate < rate) return MODE_CLOCK_LOW; diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c index b3960118deb9..2de586b7c98b 100644 --- a/drivers/gpu/drm/sun4i/sun4i_tcon.c +++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c @@ -101,10 +101,12 @@ static void sun4i_tcon_channel_set_status(struct sun4i_tcon *tcon, int channel, return; } - if (enabled) + if (enabled) { clk_prepare_enable(clk); - else + } else { + clk_rate_exclusive_put(clk); clk_disable_unprepare(clk); + } } static void sun4i_tcon_lvds_set_status(struct sun4i_tcon *tcon, @@ -873,52 +875,56 @@ static int sun4i_tcon_bind(struct device *dev, struct device *master, return ret; } - /* - * This can only be made optional since we've had DT nodes - * without the LVDS reset properties. - * - * If the property is missing, just disable LVDS, and print a - * warning. - */ - tcon->lvds_rst = devm_reset_control_get_optional(dev, "lvds"); - if (IS_ERR(tcon->lvds_rst)) { - dev_err(dev, "Couldn't get our reset line\n"); - return PTR_ERR(tcon->lvds_rst); - } else if (tcon->lvds_rst) { - has_lvds_rst = true; - reset_control_reset(tcon->lvds_rst); - } else { - has_lvds_rst = false; - } + if (tcon->quirks->supports_lvds) { + /* + * This can only be made optional since we've had DT + * nodes without the LVDS reset properties. + * + * If the property is missing, just disable LVDS, and + * print a warning. + */ + tcon->lvds_rst = devm_reset_control_get_optional(dev, "lvds"); + if (IS_ERR(tcon->lvds_rst)) { + dev_err(dev, "Couldn't get our reset line\n"); + return PTR_ERR(tcon->lvds_rst); + } else if (tcon->lvds_rst) { + has_lvds_rst = true; + reset_control_reset(tcon->lvds_rst); + } else { + has_lvds_rst = false; + } - /* - * This can only be made optional since we've had DT nodes - * without the LVDS reset properties. - * - * If the property is missing, just disable LVDS, and print a - * warning. - */ - if (tcon->quirks->has_lvds_alt) { - tcon->lvds_pll = devm_clk_get(dev, "lvds-alt"); - if (IS_ERR(tcon->lvds_pll)) { - if (PTR_ERR(tcon->lvds_pll) == -ENOENT) { - has_lvds_alt = false; + /* + * This can only be made optional since we've had DT + * nodes without the LVDS reset properties. + * + * If the property is missing, just disable LVDS, and + * print a warning. + */ + if (tcon->quirks->has_lvds_alt) { + tcon->lvds_pll = devm_clk_get(dev, "lvds-alt"); + if (IS_ERR(tcon->lvds_pll)) { + if (PTR_ERR(tcon->lvds_pll) == -ENOENT) { + has_lvds_alt = false; + } else { + dev_err(dev, "Couldn't get the LVDS PLL\n"); + return PTR_ERR(tcon->lvds_pll); + } } else { - dev_err(dev, "Couldn't get the LVDS PLL\n"); - return PTR_ERR(tcon->lvds_pll); + has_lvds_alt = true; } - } else { - has_lvds_alt = true; } - } - if (!has_lvds_rst || (tcon->quirks->has_lvds_alt && !has_lvds_alt)) { - dev_warn(dev, - "Missing LVDS properties, Please upgrade your DT\n"); - dev_warn(dev, "LVDS output disabled\n"); - can_lvds = false; + if (!has_lvds_rst || + (tcon->quirks->has_lvds_alt && !has_lvds_alt)) { + dev_warn(dev, "Missing LVDS properties, Please upgrade your DT\n"); + dev_warn(dev, "LVDS output disabled\n"); + can_lvds = false; + } else { + can_lvds = true; + } } else { - can_lvds = true; + can_lvds = false; } ret = sun4i_tcon_init_clocks(dev, tcon); @@ -1137,7 +1143,7 @@ static const struct sun4i_tcon_quirks sun8i_a33_quirks = { }; static const struct sun4i_tcon_quirks sun8i_a83t_lcd_quirks = { - /* nothing is supported */ + .supports_lvds = true, }; static const struct sun4i_tcon_quirks sun8i_v3s_quirks = { diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.h b/drivers/gpu/drm/sun4i/sun4i_tcon.h index b761c7b823c5..278700c7bf9f 100644 --- a/drivers/gpu/drm/sun4i/sun4i_tcon.h +++ b/drivers/gpu/drm/sun4i/sun4i_tcon.h @@ -175,6 +175,7 @@ struct sun4i_tcon_quirks { bool has_channel_1; /* a33 does not have channel 1 */ bool has_lvds_alt; /* Does the LVDS clock have a parent other than the TCON clock? */ bool needs_de_be_mux; /* sun6i needs mux to select backend */ + bool supports_lvds; /* Does the TCON support an LVDS output? */ /* callback to handle tcon muxing options */ int (*set_mux)(struct sun4i_tcon *, const struct drm_encoder *); diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c index a5b4cf030c11..9183d148d644 100644 --- a/drivers/infiniband/core/addr.c +++ b/drivers/infiniband/core/addr.c @@ -550,18 +550,13 @@ static int addr_resolve(struct sockaddr *src_in, dst_release(dst); } - if (ndev->flags & IFF_LOOPBACK) { - ret = rdma_translate_ip(dst_in, addr); - /* - * Put the loopback device and get the translated - * device instead. - */ + if (ndev) { + if (ndev->flags & IFF_LOOPBACK) + ret = rdma_translate_ip(dst_in, addr); + else + addr->bound_dev_if = ndev->ifindex; dev_put(ndev); - ndev = dev_get_by_index(addr->net, addr->bound_dev_if); - } else { - addr->bound_dev_if = ndev->ifindex; } - dev_put(ndev); return ret; } diff --git a/drivers/infiniband/core/cq.c b/drivers/infiniband/core/cq.c index bc79ca8215d7..af5ad6a56ae4 100644 --- a/drivers/infiniband/core/cq.c +++ b/drivers/infiniband/core/cq.c @@ -17,6 +17,7 @@ /* # of WCs to poll for with a single call to ib_poll_cq */ #define IB_POLL_BATCH 16 +#define IB_POLL_BATCH_DIRECT 8 /* # of WCs to iterate over before yielding */ #define IB_POLL_BUDGET_IRQ 256 @@ -25,18 +26,18 @@ #define IB_POLL_FLAGS \ (IB_CQ_NEXT_COMP | IB_CQ_REPORT_MISSED_EVENTS) -static int __ib_process_cq(struct ib_cq *cq, int budget, struct ib_wc *poll_wc) +static int __ib_process_cq(struct ib_cq *cq, int budget, struct ib_wc *wcs, + int batch) { int i, n, completed = 0; - struct ib_wc *wcs = poll_wc ? : cq->wc; /* * budget might be (-1) if the caller does not * want to bound this call, thus we need unsigned * minimum here. */ - while ((n = ib_poll_cq(cq, min_t(u32, IB_POLL_BATCH, - budget - completed), wcs)) > 0) { + while ((n = ib_poll_cq(cq, min_t(u32, batch, + budget - completed), wcs)) > 0) { for (i = 0; i < n; i++) { struct ib_wc *wc = &wcs[i]; @@ -48,8 +49,7 @@ static int __ib_process_cq(struct ib_cq *cq, int budget, struct ib_wc *poll_wc) completed += n; - if (n != IB_POLL_BATCH || - (budget != -1 && completed >= budget)) + if (n != batch || (budget != -1 && completed >= budget)) break; } @@ -72,9 +72,9 @@ static int __ib_process_cq(struct ib_cq *cq, int budget, struct ib_wc *poll_wc) */ int ib_process_cq_direct(struct ib_cq *cq, int budget) { - struct ib_wc wcs[IB_POLL_BATCH]; + struct ib_wc wcs[IB_POLL_BATCH_DIRECT]; - return __ib_process_cq(cq, budget, wcs); + return __ib_process_cq(cq, budget, wcs, IB_POLL_BATCH_DIRECT); } EXPORT_SYMBOL(ib_process_cq_direct); @@ -88,7 +88,7 @@ static int ib_poll_handler(struct irq_poll *iop, int budget) struct ib_cq *cq = container_of(iop, struct ib_cq, iop); int completed; - completed = __ib_process_cq(cq, budget, NULL); + completed = __ib_process_cq(cq, budget, cq->wc, IB_POLL_BATCH); if (completed < budget) { irq_poll_complete(&cq->iop); if (ib_req_notify_cq(cq, IB_POLL_FLAGS) > 0) @@ -108,7 +108,8 @@ static void ib_cq_poll_work(struct work_struct *work) struct ib_cq *cq = container_of(work, struct ib_cq, work); int completed; - completed = __ib_process_cq(cq, IB_POLL_BUDGET_WORKQUEUE, NULL); + completed = __ib_process_cq(cq, IB_POLL_BUDGET_WORKQUEUE, cq->wc, + IB_POLL_BATCH); if (completed >= IB_POLL_BUDGET_WORKQUEUE || ib_req_notify_cq(cq, IB_POLL_FLAGS) > 0) queue_work(ib_comp_wq, &cq->work); diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index e8010e73a1cf..bb065c9449be 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -536,14 +536,14 @@ int ib_register_device(struct ib_device *device, ret = device->query_device(device, &device->attrs, &uhw); if (ret) { pr_warn("Couldn't query the device attributes\n"); - goto cache_cleanup; + goto cg_cleanup; } ret = ib_device_register_sysfs(device, port_callback); if (ret) { pr_warn("Couldn't register device %s with driver model\n", device->name); - goto cache_cleanup; + goto cg_cleanup; } device->reg_state = IB_DEV_REGISTERED; @@ -559,6 +559,8 @@ int ib_register_device(struct ib_device *device, mutex_unlock(&device_mutex); return 0; +cg_cleanup: + ib_device_unregister_rdmacg(device); cache_cleanup: ib_cache_cleanup_one(device); ib_cache_release_one(device); diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c index 8cf15d4a8ac4..9f029a1ca5ea 100644 --- a/drivers/infiniband/core/sa_query.c +++ b/drivers/infiniband/core/sa_query.c @@ -1291,10 +1291,9 @@ int ib_init_ah_attr_from_path(struct ib_device *device, u8 port_num, resolved_dev = dev_get_by_index(dev_addr.net, dev_addr.bound_dev_if); - if (resolved_dev->flags & IFF_LOOPBACK) { - dev_put(resolved_dev); - resolved_dev = idev; - dev_hold(resolved_dev); + if (!resolved_dev) { + dev_put(idev); + return -ENODEV; } ndev = ib_get_ndev_from_path(rec); rcu_read_lock(); diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index f015f1bf88c9..3a9d0f5b5881 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -1149,6 +1149,9 @@ static ssize_t ucma_init_qp_attr(struct ucma_file *file, if (copy_from_user(&cmd, inbuf, sizeof(cmd))) return -EFAULT; + if (cmd.qp_state > IB_QPS_ERR) + return -EINVAL; + ctx = ucma_get_ctx(file, cmd.id); if (IS_ERR(ctx)) return PTR_ERR(ctx); @@ -1294,6 +1297,9 @@ static ssize_t ucma_set_option(struct ucma_file *file, const char __user *inbuf, if (IS_ERR(ctx)) return PTR_ERR(ctx); + if (unlikely(cmd.optval > KMALLOC_MAX_SIZE)) + return -EINVAL; + optval = memdup_user((void __user *) (unsigned long) cmd.optval, cmd.optlen); if (IS_ERR(optval)) { diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index 643174d949a8..0dd75f449872 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -785,7 +785,7 @@ int bnxt_re_query_ah(struct ib_ah *ib_ah, struct rdma_ah_attr *ah_attr) return 0; } -static unsigned long bnxt_re_lock_cqs(struct bnxt_re_qp *qp) +unsigned long bnxt_re_lock_cqs(struct bnxt_re_qp *qp) __acquires(&qp->scq->cq_lock) __acquires(&qp->rcq->cq_lock) { unsigned long flags; @@ -799,8 +799,8 @@ static unsigned long bnxt_re_lock_cqs(struct bnxt_re_qp *qp) return flags; } -static void bnxt_re_unlock_cqs(struct bnxt_re_qp *qp, - unsigned long flags) +void bnxt_re_unlock_cqs(struct bnxt_re_qp *qp, + unsigned long flags) __releases(&qp->scq->cq_lock) __releases(&qp->rcq->cq_lock) { if (qp->rcq != qp->scq) @@ -1606,6 +1606,7 @@ int bnxt_re_modify_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr, int status; union ib_gid sgid; struct ib_gid_attr sgid_attr; + unsigned int flags; u8 nw_type; qp->qplib_qp.modify_flags = 0; @@ -1634,14 +1635,18 @@ int bnxt_re_modify_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr, dev_dbg(rdev_to_dev(rdev), "Move QP = %p to flush list\n", qp); + flags = bnxt_re_lock_cqs(qp); bnxt_qplib_add_flush_qp(&qp->qplib_qp); + bnxt_re_unlock_cqs(qp, flags); } if (!qp->sumem && qp->qplib_qp.state == CMDQ_MODIFY_QP_NEW_STATE_RESET) { dev_dbg(rdev_to_dev(rdev), "Move QP = %p out of flush list\n", qp); + flags = bnxt_re_lock_cqs(qp); bnxt_qplib_clean_qp(&qp->qplib_qp); + bnxt_re_unlock_cqs(qp, flags); } } if (qp_attr_mask & IB_QP_EN_SQD_ASYNC_NOTIFY) { @@ -2227,10 +2232,13 @@ static int bnxt_re_build_inv_wqe(struct ib_send_wr *wr, wqe->type = BNXT_QPLIB_SWQE_TYPE_LOCAL_INV; wqe->local_inv.inv_l_key = wr->ex.invalidate_rkey; + /* Need unconditional fence for local invalidate + * opcode to work as expected. + */ + wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_UC_FENCE; + if (wr->send_flags & IB_SEND_SIGNALED) wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_SIGNAL_COMP; - if (wr->send_flags & IB_SEND_FENCE) - wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_UC_FENCE; if (wr->send_flags & IB_SEND_SOLICITED) wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_SOLICIT_EVENT; @@ -2251,8 +2259,12 @@ static int bnxt_re_build_reg_wqe(struct ib_reg_wr *wr, wqe->frmr.levels = qplib_frpl->hwq.level + 1; wqe->type = BNXT_QPLIB_SWQE_TYPE_REG_MR; - if (wr->wr.send_flags & IB_SEND_FENCE) - wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_UC_FENCE; + /* Need unconditional fence for reg_mr + * opcode to function as expected. + */ + + wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_UC_FENCE; + if (wr->wr.send_flags & IB_SEND_SIGNALED) wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_SIGNAL_COMP; diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.h b/drivers/infiniband/hw/bnxt_re/ib_verbs.h index b88a48d43a9d..e62b7c2c7da6 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.h +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.h @@ -222,4 +222,7 @@ struct ib_ucontext *bnxt_re_alloc_ucontext(struct ib_device *ibdev, struct ib_udata *udata); int bnxt_re_dealloc_ucontext(struct ib_ucontext *context); int bnxt_re_mmap(struct ib_ucontext *context, struct vm_area_struct *vma); + +unsigned long bnxt_re_lock_cqs(struct bnxt_re_qp *qp); +void bnxt_re_unlock_cqs(struct bnxt_re_qp *qp, unsigned long flags); #endif /* __BNXT_RE_IB_VERBS_H__ */ diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index 33a448036c2e..f6e361750466 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -730,6 +730,13 @@ static int bnxt_re_handle_qp_async_event(struct creq_qp_event *qp_event, struct bnxt_re_qp *qp) { struct ib_event event; + unsigned int flags; + + if (qp->qplib_qp.state == CMDQ_MODIFY_QP_NEW_STATE_ERR) { + flags = bnxt_re_lock_cqs(qp); + bnxt_qplib_add_flush_qp(&qp->qplib_qp); + bnxt_re_unlock_cqs(qp, flags); + } memset(&event, 0, sizeof(event)); if (qp->qplib_qp.srq) { @@ -1416,9 +1423,12 @@ static void bnxt_re_task(struct work_struct *work) switch (re_work->event) { case NETDEV_REGISTER: rc = bnxt_re_ib_reg(rdev); - if (rc) + if (rc) { dev_err(rdev_to_dev(rdev), "Failed to register with IB: %#x", rc); + bnxt_re_remove_one(rdev); + bnxt_re_dev_unreg(rdev); + } break; case NETDEV_UP: bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1, diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index 3ea5b9624f6b..06b42c880fd4 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -88,75 +88,35 @@ static void __bnxt_qplib_add_flush_qp(struct bnxt_qplib_qp *qp) } } -void bnxt_qplib_acquire_cq_locks(struct bnxt_qplib_qp *qp, - unsigned long *flags) - __acquires(&qp->scq->hwq.lock) __acquires(&qp->rcq->hwq.lock) +static void bnxt_qplib_acquire_cq_flush_locks(struct bnxt_qplib_qp *qp, + unsigned long *flags) + __acquires(&qp->scq->flush_lock) __acquires(&qp->rcq->flush_lock) { - spin_lock_irqsave(&qp->scq->hwq.lock, *flags); + spin_lock_irqsave(&qp->scq->flush_lock, *flags); if (qp->scq == qp->rcq) - __acquire(&qp->rcq->hwq.lock); + __acquire(&qp->rcq->flush_lock); else - spin_lock(&qp->rcq->hwq.lock); + spin_lock(&qp->rcq->flush_lock); } -void bnxt_qplib_release_cq_locks(struct bnxt_qplib_qp *qp, - unsigned long *flags) - __releases(&qp->scq->hwq.lock) __releases(&qp->rcq->hwq.lock) +static void bnxt_qplib_release_cq_flush_locks(struct bnxt_qplib_qp *qp, + unsigned long *flags) + __releases(&qp->scq->flush_lock) __releases(&qp->rcq->flush_lock) { if (qp->scq == qp->rcq) - __release(&qp->rcq->hwq.lock); + __release(&qp->rcq->flush_lock); else - spin_unlock(&qp->rcq->hwq.lock); - spin_unlock_irqrestore(&qp->scq->hwq.lock, *flags); -} - -static struct bnxt_qplib_cq *bnxt_qplib_find_buddy_cq(struct bnxt_qplib_qp *qp, - struct bnxt_qplib_cq *cq) -{ - struct bnxt_qplib_cq *buddy_cq = NULL; - - if (qp->scq == qp->rcq) - buddy_cq = NULL; - else if (qp->scq == cq) - buddy_cq = qp->rcq; - else - buddy_cq = qp->scq; - return buddy_cq; -} - -static void bnxt_qplib_lock_buddy_cq(struct bnxt_qplib_qp *qp, - struct bnxt_qplib_cq *cq) - __acquires(&buddy_cq->hwq.lock) -{ - struct bnxt_qplib_cq *buddy_cq = NULL; - - buddy_cq = bnxt_qplib_find_buddy_cq(qp, cq); - if (!buddy_cq) - __acquire(&cq->hwq.lock); - else - spin_lock(&buddy_cq->hwq.lock); -} - -static void bnxt_qplib_unlock_buddy_cq(struct bnxt_qplib_qp *qp, - struct bnxt_qplib_cq *cq) - __releases(&buddy_cq->hwq.lock) -{ - struct bnxt_qplib_cq *buddy_cq = NULL; - - buddy_cq = bnxt_qplib_find_buddy_cq(qp, cq); - if (!buddy_cq) - __release(&cq->hwq.lock); - else - spin_unlock(&buddy_cq->hwq.lock); + spin_unlock(&qp->rcq->flush_lock); + spin_unlock_irqrestore(&qp->scq->flush_lock, *flags); } void bnxt_qplib_add_flush_qp(struct bnxt_qplib_qp *qp) { unsigned long flags; - bnxt_qplib_acquire_cq_locks(qp, &flags); + bnxt_qplib_acquire_cq_flush_locks(qp, &flags); __bnxt_qplib_add_flush_qp(qp); - bnxt_qplib_release_cq_locks(qp, &flags); + bnxt_qplib_release_cq_flush_locks(qp, &flags); } static void __bnxt_qplib_del_flush_qp(struct bnxt_qplib_qp *qp) @@ -177,7 +137,7 @@ void bnxt_qplib_clean_qp(struct bnxt_qplib_qp *qp) { unsigned long flags; - bnxt_qplib_acquire_cq_locks(qp, &flags); + bnxt_qplib_acquire_cq_flush_locks(qp, &flags); __clean_cq(qp->scq, (u64)(unsigned long)qp); qp->sq.hwq.prod = 0; qp->sq.hwq.cons = 0; @@ -186,7 +146,7 @@ void bnxt_qplib_clean_qp(struct bnxt_qplib_qp *qp) qp->rq.hwq.cons = 0; __bnxt_qplib_del_flush_qp(qp); - bnxt_qplib_release_cq_locks(qp, &flags); + bnxt_qplib_release_cq_flush_locks(qp, &flags); } static void bnxt_qpn_cqn_sched_task(struct work_struct *work) @@ -2107,9 +2067,6 @@ void bnxt_qplib_mark_qp_error(void *qp_handle) /* Must block new posting of SQ and RQ */ qp->state = CMDQ_MODIFY_QP_NEW_STATE_ERR; bnxt_qplib_cancel_phantom_processing(qp); - - /* Add qp to flush list of the CQ */ - __bnxt_qplib_add_flush_qp(qp); } /* Note: SQE is valid from sw_sq_cons up to cqe_sq_cons (exclusive) @@ -2285,9 +2242,9 @@ static int bnxt_qplib_cq_process_req(struct bnxt_qplib_cq *cq, sw_sq_cons, cqe->wr_id, cqe->status); cqe++; (*budget)--; - bnxt_qplib_lock_buddy_cq(qp, cq); bnxt_qplib_mark_qp_error(qp); - bnxt_qplib_unlock_buddy_cq(qp, cq); + /* Add qp to flush list of the CQ */ + bnxt_qplib_add_flush_qp(qp); } else { if (swq->flags & SQ_SEND_FLAGS_SIGNAL_COMP) { /* Before we complete, do WA 9060 */ @@ -2403,9 +2360,7 @@ static int bnxt_qplib_cq_process_res_rc(struct bnxt_qplib_cq *cq, if (hwcqe->status != CQ_RES_RC_STATUS_OK) { qp->state = CMDQ_MODIFY_QP_NEW_STATE_ERR; /* Add qp to flush list of the CQ */ - bnxt_qplib_lock_buddy_cq(qp, cq); - __bnxt_qplib_add_flush_qp(qp); - bnxt_qplib_unlock_buddy_cq(qp, cq); + bnxt_qplib_add_flush_qp(qp); } } @@ -2489,9 +2444,7 @@ static int bnxt_qplib_cq_process_res_ud(struct bnxt_qplib_cq *cq, if (hwcqe->status != CQ_RES_RC_STATUS_OK) { qp->state = CMDQ_MODIFY_QP_NEW_STATE_ERR; /* Add qp to flush list of the CQ */ - bnxt_qplib_lock_buddy_cq(qp, cq); - __bnxt_qplib_add_flush_qp(qp); - bnxt_qplib_unlock_buddy_cq(qp, cq); + bnxt_qplib_add_flush_qp(qp); } } done: @@ -2501,11 +2454,9 @@ done: bool bnxt_qplib_is_cq_empty(struct bnxt_qplib_cq *cq) { struct cq_base *hw_cqe, **hw_cqe_ptr; - unsigned long flags; u32 sw_cons, raw_cons; bool rc = true; - spin_lock_irqsave(&cq->hwq.lock, flags); raw_cons = cq->hwq.cons; sw_cons = HWQ_CMP(raw_cons, &cq->hwq); hw_cqe_ptr = (struct cq_base **)cq->hwq.pbl_ptr; @@ -2513,7 +2464,6 @@ bool bnxt_qplib_is_cq_empty(struct bnxt_qplib_cq *cq) /* Check for Valid bit. If the CQE is valid, return false */ rc = !CQE_CMP_VALID(hw_cqe, raw_cons, cq->hwq.max_elements); - spin_unlock_irqrestore(&cq->hwq.lock, flags); return rc; } @@ -2602,9 +2552,7 @@ static int bnxt_qplib_cq_process_res_raweth_qp1(struct bnxt_qplib_cq *cq, if (hwcqe->status != CQ_RES_RC_STATUS_OK) { qp->state = CMDQ_MODIFY_QP_NEW_STATE_ERR; /* Add qp to flush list of the CQ */ - bnxt_qplib_lock_buddy_cq(qp, cq); - __bnxt_qplib_add_flush_qp(qp); - bnxt_qplib_unlock_buddy_cq(qp, cq); + bnxt_qplib_add_flush_qp(qp); } } @@ -2719,9 +2667,7 @@ do_rq: */ /* Add qp to flush list of the CQ */ - bnxt_qplib_lock_buddy_cq(qp, cq); - __bnxt_qplib_add_flush_qp(qp); - bnxt_qplib_unlock_buddy_cq(qp, cq); + bnxt_qplib_add_flush_qp(qp); done: return rc; } @@ -2750,7 +2696,7 @@ int bnxt_qplib_process_flush_list(struct bnxt_qplib_cq *cq, u32 budget = num_cqes; unsigned long flags; - spin_lock_irqsave(&cq->hwq.lock, flags); + spin_lock_irqsave(&cq->flush_lock, flags); list_for_each_entry(qp, &cq->sqf_head, sq_flush) { dev_dbg(&cq->hwq.pdev->dev, "QPLIB: FP: Flushing SQ QP= %p", @@ -2764,7 +2710,7 @@ int bnxt_qplib_process_flush_list(struct bnxt_qplib_cq *cq, qp); __flush_rq(&qp->rq, qp, &cqe, &budget); } - spin_unlock_irqrestore(&cq->hwq.lock, flags); + spin_unlock_irqrestore(&cq->flush_lock, flags); return num_cqes - budget; } @@ -2773,11 +2719,9 @@ int bnxt_qplib_poll_cq(struct bnxt_qplib_cq *cq, struct bnxt_qplib_cqe *cqe, int num_cqes, struct bnxt_qplib_qp **lib_qp) { struct cq_base *hw_cqe, **hw_cqe_ptr; - unsigned long flags; u32 sw_cons, raw_cons; int budget, rc = 0; - spin_lock_irqsave(&cq->hwq.lock, flags); raw_cons = cq->hwq.cons; budget = num_cqes; @@ -2853,20 +2797,15 @@ int bnxt_qplib_poll_cq(struct bnxt_qplib_cq *cq, struct bnxt_qplib_cqe *cqe, bnxt_qplib_arm_cq(cq, DBR_DBR_TYPE_CQ); } exit: - spin_unlock_irqrestore(&cq->hwq.lock, flags); return num_cqes - budget; } void bnxt_qplib_req_notify_cq(struct bnxt_qplib_cq *cq, u32 arm_type) { - unsigned long flags; - - spin_lock_irqsave(&cq->hwq.lock, flags); if (arm_type) bnxt_qplib_arm_cq(cq, arm_type); /* Using cq->arm_state variable to track whether to issue cq handler */ atomic_set(&cq->arm_state, 1); - spin_unlock_irqrestore(&cq->hwq.lock, flags); } void bnxt_qplib_flush_cqn_wq(struct bnxt_qplib_qp *qp) diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.h b/drivers/infiniband/hw/bnxt_re/qplib_fp.h index ca0a2ffa3509..ade9f13c0fd1 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.h @@ -389,6 +389,18 @@ struct bnxt_qplib_cq { struct list_head sqf_head, rqf_head; atomic_t arm_state; spinlock_t compl_lock; /* synch CQ handlers */ +/* Locking Notes: + * QP can move to error state from modify_qp, async error event or error + * CQE as part of poll_cq. When QP is moved to error state, it gets added + * to two flush lists, one each for SQ and RQ. + * Each flush list is protected by qplib_cq->flush_lock. Both scq and rcq + * flush_locks should be acquired when QP is moved to error. The control path + * operations(modify_qp and async error events) are synchronized with poll_cq + * using upper level CQ locks (bnxt_re_cq->cq_lock) of both SCQ and RCQ. + * The qplib_cq->flush_lock is required to synchronize two instances of poll_cq + * of the same QP while manipulating the flush list. + */ + spinlock_t flush_lock; /* QP flush management */ }; #define BNXT_QPLIB_MAX_IRRQE_ENTRY_SIZE sizeof(struct xrrq_irrq) diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c index 8329ec6a7946..80027a494730 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c @@ -305,9 +305,8 @@ static int bnxt_qplib_process_qp_event(struct bnxt_qplib_rcfw *rcfw, err_event->res_err_state_reason); if (!qp) break; - bnxt_qplib_acquire_cq_locks(qp, &flags); bnxt_qplib_mark_qp_error(qp); - bnxt_qplib_release_cq_locks(qp, &flags); + rcfw->aeq_handler(rcfw, qp_event, qp); break; default: /* Command Response */ @@ -460,7 +459,11 @@ int bnxt_qplib_init_rcfw(struct bnxt_qplib_rcfw *rcfw, int rc; RCFW_CMD_PREP(req, INITIALIZE_FW, cmd_flags); - + /* Supply (log-base-2-of-host-page-size - base-page-shift) + * to bono to adjust the doorbell page sizes. + */ + req.log2_dbr_pg_size = cpu_to_le16(PAGE_SHIFT - + RCFW_DBR_BASE_PAGE_SHIFT); /* * VFs need not setup the HW context area, PF * shall setup this area for VF. Skipping the diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h index 6bee6e3636ea..c7cce2e4185e 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h @@ -49,6 +49,7 @@ #define RCFW_COMM_SIZE 0x104 #define RCFW_DBR_PCI_BAR_REGION 2 +#define RCFW_DBR_BASE_PAGE_SHIFT 12 #define RCFW_CMD_PREP(req, CMD, cmd_flags) \ do { \ diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c index 03057983341f..ee98e5efef84 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c @@ -139,7 +139,8 @@ int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw, attr->max_pkey = le32_to_cpu(sb->max_pkeys); attr->max_inline_data = le32_to_cpu(sb->max_inline_data); - attr->l2_db_size = (sb->l2_db_space_size + 1) * PAGE_SIZE; + attr->l2_db_size = (sb->l2_db_space_size + 1) * + (0x01 << RCFW_DBR_BASE_PAGE_SHIFT); attr->max_sgid = le32_to_cpu(sb->max_gid); bnxt_qplib_query_version(rcfw, attr->fw_ver); diff --git a/drivers/infiniband/hw/bnxt_re/roce_hsi.h b/drivers/infiniband/hw/bnxt_re/roce_hsi.h index 2d7ea096a247..3e5a4f760d0e 100644 --- a/drivers/infiniband/hw/bnxt_re/roce_hsi.h +++ b/drivers/infiniband/hw/bnxt_re/roce_hsi.h @@ -1761,7 +1761,30 @@ struct cmdq_initialize_fw { #define CMDQ_INITIALIZE_FW_TIM_PG_SIZE_PG_2M (0x3UL << 4) #define CMDQ_INITIALIZE_FW_TIM_PG_SIZE_PG_8M (0x4UL << 4) #define CMDQ_INITIALIZE_FW_TIM_PG_SIZE_PG_1G (0x5UL << 4) - __le16 reserved16; + /* This value is (log-base-2-of-DBR-page-size - 12). + * 0 for 4KB. HW supported values are enumerated below. + */ + __le16 log2_dbr_pg_size; + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_MASK 0xfUL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_SFT 0 + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_4K 0x0UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_8K 0x1UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_16K 0x2UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_32K 0x3UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_64K 0x4UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_128K 0x5UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_256K 0x6UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_512K 0x7UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_1M 0x8UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_2M 0x9UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_4M 0xaUL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_8M 0xbUL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_16M 0xcUL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_32M 0xdUL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_64M 0xeUL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_128M 0xfUL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_LAST \ + CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_128M __le64 qpc_page_dir; __le64 mrw_page_dir; __le64 srq_page_dir; diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c index 9a566ee3ceff..82adc0d1d30e 100644 --- a/drivers/infiniband/hw/mlx4/cq.c +++ b/drivers/infiniband/hw/mlx4/cq.c @@ -601,6 +601,7 @@ static void use_tunnel_data(struct mlx4_ib_qp *qp, struct mlx4_ib_cq *cq, struct wc->dlid_path_bits = 0; if (is_eth) { + wc->slid = 0; wc->vlan_id = be16_to_cpu(hdr->tun.sl_vid); memcpy(&(wc->smac[0]), (char *)&hdr->tun.mac_31_0, 4); memcpy(&(wc->smac[4]), (char *)&hdr->tun.slid_mac_47_32, 2); @@ -851,7 +852,6 @@ repoll: } } - wc->slid = be16_to_cpu(cqe->rlid); g_mlpath_rqpn = be32_to_cpu(cqe->g_mlpath_rqpn); wc->src_qp = g_mlpath_rqpn & 0xffffff; wc->dlid_path_bits = (g_mlpath_rqpn >> 24) & 0x7f; @@ -860,6 +860,7 @@ repoll: wc->wc_flags |= mlx4_ib_ipoib_csum_ok(cqe->status, cqe->checksum) ? IB_WC_IP_CSUM_OK : 0; if (is_eth) { + wc->slid = 0; wc->sl = be16_to_cpu(cqe->sl_vid) >> 13; if (be32_to_cpu(cqe->vlan_my_qpn) & MLX4_CQE_CVLAN_PRESENT_MASK) { @@ -871,6 +872,7 @@ repoll: memcpy(wc->smac, cqe->smac, ETH_ALEN); wc->wc_flags |= (IB_WC_WITH_VLAN | IB_WC_WITH_SMAC); } else { + wc->slid = be16_to_cpu(cqe->rlid); wc->sl = be16_to_cpu(cqe->sl_vid) >> 12; wc->vlan_id = 0xffff; } diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 8d2ee9322f2e..5a0e4fc4785a 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -219,8 +219,6 @@ static int mlx4_ib_update_gids_v1_v2(struct gid_entry *gids, gid_tbl[i].version = 2; if (!ipv6_addr_v4mapped((struct in6_addr *)&gids[i].gid)) gid_tbl[i].type = 1; - else - memset(&gid_tbl[i].gid, 0, 12); } } @@ -366,8 +364,13 @@ static int mlx4_ib_del_gid(struct ib_device *device, if (!gids) { ret = -ENOMEM; } else { - for (i = 0; i < MLX4_MAX_PORT_GIDS; i++) - memcpy(&gids[i].gid, &port_gid_table->gids[i].gid, sizeof(union ib_gid)); + for (i = 0; i < MLX4_MAX_PORT_GIDS; i++) { + memcpy(&gids[i].gid, + &port_gid_table->gids[i].gid, + sizeof(union ib_gid)); + gids[i].gid_type = + port_gid_table->gids[i].gid_type; + } } } spin_unlock_bh(&iboe->lock); diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c index 5b974fb97611..15457c9569a7 100644 --- a/drivers/infiniband/hw/mlx5/cq.c +++ b/drivers/infiniband/hw/mlx5/cq.c @@ -226,7 +226,6 @@ static void handle_responder(struct ib_wc *wc, struct mlx5_cqe64 *cqe, wc->ex.invalidate_rkey = be32_to_cpu(cqe->imm_inval_pkey); break; } - wc->slid = be16_to_cpu(cqe->slid); wc->src_qp = be32_to_cpu(cqe->flags_rqpn) & 0xffffff; wc->dlid_path_bits = cqe->ml_path; g = (be32_to_cpu(cqe->flags_rqpn) >> 28) & 3; @@ -241,10 +240,12 @@ static void handle_responder(struct ib_wc *wc, struct mlx5_cqe64 *cqe, } if (ll != IB_LINK_LAYER_ETHERNET) { + wc->slid = be16_to_cpu(cqe->slid); wc->sl = (be32_to_cpu(cqe->flags_rqpn) >> 24) & 0xf; return; } + wc->slid = 0; vlan_present = cqe->l4_l3_hdr_type & 0x1; roce_packet_type = (be32_to_cpu(cqe->flags_rqpn) >> 24) & 0x3; if (vlan_present) { @@ -1177,7 +1178,12 @@ static int resize_user(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq, if (ucmd.reserved0 || ucmd.reserved1) return -EINVAL; - umem = ib_umem_get(context, ucmd.buf_addr, entries * ucmd.cqe_size, + /* check multiplication overflow */ + if (ucmd.cqe_size && SIZE_MAX / ucmd.cqe_size <= entries - 1) + return -EINVAL; + + umem = ib_umem_get(context, ucmd.buf_addr, + (size_t)ucmd.cqe_size * entries, IB_ACCESS_LOCAL_WRITE, 1); if (IS_ERR(umem)) { err = PTR_ERR(umem); diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 4236c8086820..033b6af90de9 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -245,12 +245,16 @@ struct mlx5_core_dev *mlx5_ib_get_native_port_mdev(struct mlx5_ib_dev *ibdev, struct mlx5_ib_multiport_info *mpi; struct mlx5_ib_port *port; + if (!mlx5_core_mp_enabled(ibdev->mdev) || + ll != IB_LINK_LAYER_ETHERNET) { + if (native_port_num) + *native_port_num = ib_port_num; + return ibdev->mdev; + } + if (native_port_num) *native_port_num = 1; - if (!mlx5_core_mp_enabled(ibdev->mdev) || ll != IB_LINK_LAYER_ETHERNET) - return ibdev->mdev; - port = &ibdev->port[ib_port_num - 1]; if (!port) return NULL; @@ -3263,7 +3267,7 @@ static void mlx5_ib_handle_event(struct work_struct *_work) struct mlx5_ib_dev *ibdev; struct ib_event ibev; bool fatal = false; - u8 port = 0; + u8 port = (u8)work->param; if (mlx5_core_is_mp_slave(work->dev)) { ibdev = mlx5_ib_get_ibdev_from_mpi(work->context); @@ -3283,8 +3287,6 @@ static void mlx5_ib_handle_event(struct work_struct *_work) case MLX5_DEV_EVENT_PORT_UP: case MLX5_DEV_EVENT_PORT_DOWN: case MLX5_DEV_EVENT_PORT_INITIALIZED: - port = (u8)work->param; - /* In RoCE, port up/down events are handled in * mlx5_netdev_event(). */ @@ -3298,24 +3300,19 @@ static void mlx5_ib_handle_event(struct work_struct *_work) case MLX5_DEV_EVENT_LID_CHANGE: ibev.event = IB_EVENT_LID_CHANGE; - port = (u8)work->param; break; case MLX5_DEV_EVENT_PKEY_CHANGE: ibev.event = IB_EVENT_PKEY_CHANGE; - port = (u8)work->param; - schedule_work(&ibdev->devr.ports[port - 1].pkey_change_work); break; case MLX5_DEV_EVENT_GUID_CHANGE: ibev.event = IB_EVENT_GID_CHANGE; - port = (u8)work->param; break; case MLX5_DEV_EVENT_CLIENT_REREG: ibev.event = IB_EVENT_CLIENT_REREGISTER; - port = (u8)work->param; break; case MLX5_DEV_EVENT_DELAY_DROP_TIMEOUT: schedule_work(&ibdev->delay_drop.delay_drop_work); @@ -3327,7 +3324,7 @@ static void mlx5_ib_handle_event(struct work_struct *_work) ibev.device = &ibdev->ib_dev; ibev.element.port_num = port; - if (port < 1 || port > ibdev->num_ports) { + if (!rdma_is_port_valid(&ibdev->ib_dev, port)) { mlx5_ib_warn(ibdev, "warning: event on port %d\n", port); goto out; } diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 556e015678de..1961c6a45437 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -1816,7 +1816,6 @@ mlx5_ib_sg_to_klms(struct mlx5_ib_mr *mr, mr->ibmr.iova = sg_dma_address(sg) + sg_offset; mr->ibmr.length = 0; - mr->ndescs = sg_nents; for_each_sg(sgl, sg, sg_nents, i) { if (unlikely(i >= mr->max_descs)) @@ -1828,6 +1827,7 @@ mlx5_ib_sg_to_klms(struct mlx5_ib_mr *mr, sg_offset = 0; } + mr->ndescs = i; if (sg_offset_p) *sg_offset_p = sg_offset; diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 39d24bf694a8..36197fbac63a 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -1584,6 +1584,7 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd, u32 uidx = MLX5_IB_DEFAULT_UIDX; struct mlx5_ib_create_qp ucmd; struct mlx5_ib_qp_base *base; + int mlx5_st; void *qpc; u32 *in; int err; @@ -1592,6 +1593,10 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd, spin_lock_init(&qp->sq.lock); spin_lock_init(&qp->rq.lock); + mlx5_st = to_mlx5_st(init_attr->qp_type); + if (mlx5_st < 0) + return -EINVAL; + if (init_attr->rwq_ind_tbl) { if (!udata) return -ENOSYS; @@ -1753,7 +1758,7 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd, qpc = MLX5_ADDR_OF(create_qp_in, in, qpc); - MLX5_SET(qpc, qpc, st, to_mlx5_st(init_attr->qp_type)); + MLX5_SET(qpc, qpc, st, mlx5_st); MLX5_SET(qpc, qpc, pm_state, MLX5_QP_PM_MIGRATED); if (init_attr->qp_type != MLX5_IB_QPT_REG_UMR) @@ -3095,8 +3100,10 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp, goto out; if (mlx5_cur >= MLX5_QP_NUM_STATE || mlx5_new >= MLX5_QP_NUM_STATE || - !optab[mlx5_cur][mlx5_new]) + !optab[mlx5_cur][mlx5_new]) { + err = -EINVAL; goto out; + } op = optab[mlx5_cur][mlx5_new]; optpar = ib_mask_to_mlx5_opt(attr_mask); diff --git a/drivers/infiniband/hw/qedr/qedr_iw_cm.c b/drivers/infiniband/hw/qedr/qedr_iw_cm.c index 478b7317b80a..26dc374787f7 100644 --- a/drivers/infiniband/hw/qedr/qedr_iw_cm.c +++ b/drivers/infiniband/hw/qedr/qedr_iw_cm.c @@ -458,8 +458,7 @@ qedr_addr6_resolve(struct qedr_dev *dev, } return -EINVAL; } - neigh = dst_neigh_lookup(dst, &dst_in); - + neigh = dst_neigh_lookup(dst, &fl6.daddr); if (neigh) { rcu_read_lock(); if (neigh->nud_state & NUD_VALID) { @@ -494,10 +493,14 @@ int qedr_iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) qp = idr_find(&dev->qpidr, conn_param->qpn); - laddr = (struct sockaddr_in *)&cm_id->local_addr; - raddr = (struct sockaddr_in *)&cm_id->remote_addr; - laddr6 = (struct sockaddr_in6 *)&cm_id->local_addr; - raddr6 = (struct sockaddr_in6 *)&cm_id->remote_addr; + laddr = (struct sockaddr_in *)&cm_id->m_local_addr; + raddr = (struct sockaddr_in *)&cm_id->m_remote_addr; + laddr6 = (struct sockaddr_in6 *)&cm_id->m_local_addr; + raddr6 = (struct sockaddr_in6 *)&cm_id->m_remote_addr; + + DP_DEBUG(dev, QEDR_MSG_IWARP, "MAPPED %d %d\n", + ntohs(((struct sockaddr_in *)&cm_id->remote_addr)->sin_port), + ntohs(raddr->sin_port)); DP_DEBUG(dev, QEDR_MSG_IWARP, "Connect source address: %pISpc, remote address: %pISpc\n", @@ -599,8 +602,8 @@ int qedr_iw_create_listen(struct iw_cm_id *cm_id, int backlog) int rc; int i; - laddr = (struct sockaddr_in *)&cm_id->local_addr; - laddr6 = (struct sockaddr_in6 *)&cm_id->local_addr; + laddr = (struct sockaddr_in *)&cm_id->m_local_addr; + laddr6 = (struct sockaddr_in6 *)&cm_id->m_local_addr; DP_DEBUG(dev, QEDR_MSG_IWARP, "Create Listener address: %pISpc\n", &cm_id->local_addr); diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c index 53f00dbf313f..875b17272d65 100644 --- a/drivers/infiniband/hw/qedr/verbs.c +++ b/drivers/infiniband/hw/qedr/verbs.c @@ -3034,6 +3034,11 @@ static int __qedr_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, switch (wr->opcode) { case IB_WR_SEND_WITH_IMM: + if (unlikely(rdma_protocol_iwarp(&dev->ibdev, 1))) { + rc = -EINVAL; + *bad_wr = wr; + break; + } wqe->req_type = RDMA_SQ_REQ_TYPE_SEND_WITH_IMM; swqe = (struct rdma_sq_send_wqe_1st *)wqe; swqe->wqe_size = 2; @@ -3075,6 +3080,11 @@ static int __qedr_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, break; case IB_WR_RDMA_WRITE_WITH_IMM: + if (unlikely(rdma_protocol_iwarp(&dev->ibdev, 1))) { + rc = -EINVAL; + *bad_wr = wr; + break; + } wqe->req_type = RDMA_SQ_REQ_TYPE_RDMA_WR_WITH_IMM; rwqe = (struct rdma_sq_rdma_wqe_1st *)wqe; @@ -3724,7 +3734,7 @@ int qedr_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc) { struct qedr_dev *dev = get_qedr_dev(ibcq->device); struct qedr_cq *cq = get_qedr_cq(ibcq); - union rdma_cqe *cqe = cq->latest_cqe; + union rdma_cqe *cqe; u32 old_cons, new_cons; unsigned long flags; int update = 0; @@ -3741,6 +3751,7 @@ int qedr_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc) return qedr_gsi_poll_cq(ibcq, num_entries, wc); spin_lock_irqsave(&cq->cq_lock, flags); + cqe = cq->latest_cqe; old_cons = qed_chain_get_cons_idx_u32(&cq->pbl); while (num_entries && is_valid_cqe(cq, cqe)) { struct qedr_qp *qp; diff --git a/drivers/input/keyboard/matrix_keypad.c b/drivers/input/keyboard/matrix_keypad.c index 1f316d66e6f7..41614c185918 100644 --- a/drivers/input/keyboard/matrix_keypad.c +++ b/drivers/input/keyboard/matrix_keypad.c @@ -218,8 +218,10 @@ static void matrix_keypad_stop(struct input_dev *dev) { struct matrix_keypad *keypad = input_get_drvdata(dev); + spin_lock_irq(&keypad->lock); keypad->stopped = true; - mb(); + spin_unlock_irq(&keypad->lock); + flush_work(&keypad->work.work); /* * matrix_keypad_scan() will leave IRQs enabled; diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index 3d2e23a0ae39..a246fc686bb7 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -173,7 +173,6 @@ static const char * const smbus_pnp_ids[] = { "LEN0046", /* X250 */ "LEN004a", /* W541 */ "LEN200f", /* T450s */ - "LEN2018", /* T460p */ NULL }; diff --git a/drivers/input/touchscreen/mms114.c b/drivers/input/touchscreen/mms114.c index db4f6bb502e3..a5ab774da4cc 100644 --- a/drivers/input/touchscreen/mms114.c +++ b/drivers/input/touchscreen/mms114.c @@ -1,11 +1,8 @@ -/* - * Copyright (C) 2012 Samsung Electronics Co.Ltd - * Author: Joonyoung Shim <jy0922.shim@samsung.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ +// SPDX-License-Identifier: GPL-2.0 +// Melfas MMS114/MMS152 touchscreen device driver +// +// Copyright (c) 2012 Samsung Electronics Co., Ltd. +// Author: Joonyoung Shim <jy0922.shim@samsung.com> #include <linux/module.h> #include <linux/delay.h> @@ -624,4 +621,4 @@ module_i2c_driver(mms114_driver); /* Module information */ MODULE_AUTHOR("Joonyoung Shim <jy0922.shim@samsung.com>"); MODULE_DESCRIPTION("MELFAS mms114 Touchscreen driver"); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 4d1d8dfb2d2a..f2273143b3cb 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -963,6 +963,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c, uint32_t rtime = cpu_to_le32(get_seconds()); struct uuid_entry *u; char buf[BDEVNAME_SIZE]; + struct cached_dev *exist_dc, *t; bdevname(dc->bdev, buf); @@ -987,6 +988,16 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c, return -EINVAL; } + /* Check whether already attached */ + list_for_each_entry_safe(exist_dc, t, &c->cached_devs, list) { + if (!memcmp(dc->sb.uuid, exist_dc->sb.uuid, 16)) { + pr_err("Tried to attach %s but duplicate UUID already attached", + buf); + + return -EINVAL; + } + } + u = uuid_find(c, dc->sb.uuid); if (u && @@ -1204,7 +1215,7 @@ static void register_bdev(struct cache_sb *sb, struct page *sb_page, return; err: - pr_notice("error opening %s: %s", bdevname(bdev, name), err); + pr_notice("error %s: %s", bdevname(bdev, name), err); bcache_device_stop(&dc->disk); } @@ -1883,6 +1894,8 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page, const char *err = NULL; /* must be set for any error case */ int ret = 0; + bdevname(bdev, name); + memcpy(&ca->sb, sb, sizeof(struct cache_sb)); ca->bdev = bdev; ca->bdev->bd_holder = ca; @@ -1891,11 +1904,12 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page, bio_first_bvec_all(&ca->sb_bio)->bv_page = sb_page; get_page(sb_page); - if (blk_queue_discard(bdev_get_queue(ca->bdev))) + if (blk_queue_discard(bdev_get_queue(bdev))) ca->discard = CACHE_DISCARD(&ca->sb); ret = cache_alloc(ca); if (ret != 0) { + blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL); if (ret == -ENOMEM) err = "cache_alloc(): -ENOMEM"; else @@ -1918,14 +1932,14 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page, goto out; } - pr_info("registered cache device %s", bdevname(bdev, name)); + pr_info("registered cache device %s", name); out: kobject_put(&ca->kobj); err: if (err) - pr_notice("error opening %s: %s", bdevname(bdev, name), err); + pr_notice("error %s: %s", name, err); return ret; } @@ -2014,6 +2028,7 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr, if (err) goto err_close; + err = "failed to register device"; if (SB_IS_BDEV(sb)) { struct cached_dev *dc = kzalloc(sizeof(*dc), GFP_KERNEL); if (!dc) @@ -2028,7 +2043,7 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr, goto err_close; if (register_cache(sb, sb_page, bdev, ca) != 0) - goto err_close; + goto err; } out: if (sb_page) @@ -2041,7 +2056,7 @@ out: err_close: blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL); err: - pr_info("error opening %s: %s", path, err); + pr_info("error %s: %s", path, err); ret = -EINVAL; goto out; } diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 414c9af54ded..aa2032fa80d4 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -386,9 +386,6 @@ static void __cache_size_refresh(void) static void *alloc_buffer_data(struct dm_bufio_client *c, gfp_t gfp_mask, enum data_mode *data_mode) { - unsigned noio_flag; - void *ptr; - if (c->block_size <= DM_BUFIO_BLOCK_SIZE_SLAB_LIMIT) { *data_mode = DATA_MODE_SLAB; return kmem_cache_alloc(DM_BUFIO_CACHE(c), gfp_mask); @@ -412,16 +409,15 @@ static void *alloc_buffer_data(struct dm_bufio_client *c, gfp_t gfp_mask, * all allocations done by this process (including pagetables) are done * as if GFP_NOIO was specified. */ + if (gfp_mask & __GFP_NORETRY) { + unsigned noio_flag = memalloc_noio_save(); + void *ptr = __vmalloc(c->block_size, gfp_mask, PAGE_KERNEL); - if (gfp_mask & __GFP_NORETRY) - noio_flag = memalloc_noio_save(); - - ptr = __vmalloc(c->block_size, gfp_mask, PAGE_KERNEL); - - if (gfp_mask & __GFP_NORETRY) memalloc_noio_restore(noio_flag); + return ptr; + } - return ptr; + return __vmalloc(c->block_size, gfp_mask, PAGE_KERNEL); } /* diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 7d3e572072f5..3fde9e9faddd 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -22,6 +22,7 @@ #include <linux/time.h> #include <linux/workqueue.h> #include <linux/delay.h> +#include <scsi/scsi_device.h> #include <scsi/scsi_dh.h> #include <linux/atomic.h> #include <linux/blk-mq.h> @@ -211,25 +212,13 @@ static int alloc_multipath_stage2(struct dm_target *ti, struct multipath *m) else m->queue_mode = DM_TYPE_REQUEST_BASED; - } else if (m->queue_mode == DM_TYPE_BIO_BASED || - m->queue_mode == DM_TYPE_NVME_BIO_BASED) { + } else if (m->queue_mode == DM_TYPE_BIO_BASED) { INIT_WORK(&m->process_queued_bios, process_queued_bios); - - if (m->queue_mode == DM_TYPE_BIO_BASED) { - /* - * bio-based doesn't support any direct scsi_dh management; - * it just discovers if a scsi_dh is attached. - */ - set_bit(MPATHF_RETAIN_ATTACHED_HW_HANDLER, &m->flags); - } - } - - if (m->queue_mode != DM_TYPE_NVME_BIO_BASED) { - set_bit(MPATHF_QUEUE_IO, &m->flags); - atomic_set(&m->pg_init_in_progress, 0); - atomic_set(&m->pg_init_count, 0); - m->pg_init_delay_msecs = DM_PG_INIT_DELAY_DEFAULT; - init_waitqueue_head(&m->pg_init_wait); + /* + * bio-based doesn't support any direct scsi_dh management; + * it just discovers if a scsi_dh is attached. + */ + set_bit(MPATHF_RETAIN_ATTACHED_HW_HANDLER, &m->flags); } dm_table_set_type(ti->table, m->queue_mode); @@ -337,14 +326,12 @@ static void __switch_pg(struct multipath *m, struct priority_group *pg) { m->current_pg = pg; - if (m->queue_mode == DM_TYPE_NVME_BIO_BASED) - return; - /* Must we initialise the PG first, and queue I/O till it's ready? */ if (m->hw_handler_name) { set_bit(MPATHF_PG_INIT_REQUIRED, &m->flags); set_bit(MPATHF_QUEUE_IO, &m->flags); } else { + /* FIXME: not needed if no scsi_dh is attached */ clear_bit(MPATHF_PG_INIT_REQUIRED, &m->flags); clear_bit(MPATHF_QUEUE_IO, &m->flags); } @@ -385,8 +372,7 @@ static struct pgpath *choose_pgpath(struct multipath *m, size_t nr_bytes) unsigned bypassed = 1; if (!atomic_read(&m->nr_valid_paths)) { - if (m->queue_mode != DM_TYPE_NVME_BIO_BASED) - clear_bit(MPATHF_QUEUE_IO, &m->flags); + clear_bit(MPATHF_QUEUE_IO, &m->flags); goto failed; } @@ -599,7 +585,7 @@ static struct pgpath *__map_bio(struct multipath *m, struct bio *bio) return pgpath; } -static struct pgpath *__map_bio_nvme(struct multipath *m, struct bio *bio) +static struct pgpath *__map_bio_fast(struct multipath *m, struct bio *bio) { struct pgpath *pgpath; unsigned long flags; @@ -634,8 +620,8 @@ static int __multipath_map_bio(struct multipath *m, struct bio *bio, { struct pgpath *pgpath; - if (m->queue_mode == DM_TYPE_NVME_BIO_BASED) - pgpath = __map_bio_nvme(m, bio); + if (!m->hw_handler_name) + pgpath = __map_bio_fast(m, bio); else pgpath = __map_bio(m, bio); @@ -675,8 +661,7 @@ static void process_queued_io_list(struct multipath *m) { if (m->queue_mode == DM_TYPE_MQ_REQUEST_BASED) dm_mq_kick_requeue_list(dm_table_get_md(m->ti->table)); - else if (m->queue_mode == DM_TYPE_BIO_BASED || - m->queue_mode == DM_TYPE_NVME_BIO_BASED) + else if (m->queue_mode == DM_TYPE_BIO_BASED) queue_work(kmultipathd, &m->process_queued_bios); } @@ -838,6 +823,16 @@ retain: */ kfree(m->hw_handler_name); m->hw_handler_name = attached_handler_name; + + /* + * Init fields that are only used when a scsi_dh is attached + */ + if (!test_and_set_bit(MPATHF_QUEUE_IO, &m->flags)) { + atomic_set(&m->pg_init_in_progress, 0); + atomic_set(&m->pg_init_count, 0); + m->pg_init_delay_msecs = DM_PG_INIT_DELAY_DEFAULT; + init_waitqueue_head(&m->pg_init_wait); + } } } @@ -873,6 +868,7 @@ static struct pgpath *parse_path(struct dm_arg_set *as, struct path_selector *ps int r; struct pgpath *p; struct multipath *m = ti->private; + struct scsi_device *sdev; /* we need at least a path arg */ if (as->argc < 1) { @@ -891,7 +887,9 @@ static struct pgpath *parse_path(struct dm_arg_set *as, struct path_selector *ps goto bad; } - if (m->queue_mode != DM_TYPE_NVME_BIO_BASED) { + sdev = scsi_device_from_queue(bdev_get_queue(p->path.dev->bdev)); + if (sdev) { + put_device(&sdev->sdev_gendev); INIT_DELAYED_WORK(&p->activate_path, activate_path_work); r = setup_scsi_dh(p->path.dev->bdev, m, &ti->error); if (r) { @@ -1001,8 +999,7 @@ static int parse_hw_handler(struct dm_arg_set *as, struct multipath *m) if (!hw_argc) return 0; - if (m->queue_mode == DM_TYPE_BIO_BASED || - m->queue_mode == DM_TYPE_NVME_BIO_BASED) { + if (m->queue_mode == DM_TYPE_BIO_BASED) { dm_consume_args(as, hw_argc); DMERR("bio-based multipath doesn't allow hardware handler args"); return 0; @@ -1091,8 +1088,6 @@ static int parse_features(struct dm_arg_set *as, struct multipath *m) if (!strcasecmp(queue_mode_name, "bio")) m->queue_mode = DM_TYPE_BIO_BASED; - else if (!strcasecmp(queue_mode_name, "nvme")) - m->queue_mode = DM_TYPE_NVME_BIO_BASED; else if (!strcasecmp(queue_mode_name, "rq")) m->queue_mode = DM_TYPE_REQUEST_BASED; else if (!strcasecmp(queue_mode_name, "mq")) @@ -1193,7 +1188,7 @@ static int multipath_ctr(struct dm_target *ti, unsigned argc, char **argv) ti->num_discard_bios = 1; ti->num_write_same_bios = 1; ti->num_write_zeroes_bios = 1; - if (m->queue_mode == DM_TYPE_BIO_BASED || m->queue_mode == DM_TYPE_NVME_BIO_BASED) + if (m->queue_mode == DM_TYPE_BIO_BASED) ti->per_io_data_size = multipath_per_bio_data_size(); else ti->per_io_data_size = sizeof(struct dm_mpath_io); @@ -1730,9 +1725,6 @@ static void multipath_status(struct dm_target *ti, status_type_t type, case DM_TYPE_BIO_BASED: DMEMIT("queue_mode bio "); break; - case DM_TYPE_NVME_BIO_BASED: - DMEMIT("queue_mode nvme "); - break; case DM_TYPE_MQ_REQUEST_BASED: DMEMIT("queue_mode mq "); break; diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 7ef469e902c6..c1d1034ff7b7 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3408,9 +3408,10 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery, set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags); } else { - if (test_bit(MD_RECOVERY_NEEDED, &recovery) || - test_bit(MD_RECOVERY_RESHAPE, &recovery) || - test_bit(MD_RECOVERY_RUNNING, &recovery)) + if (!test_bit(MD_RECOVERY_INTR, &recovery) && + (test_bit(MD_RECOVERY_NEEDED, &recovery) || + test_bit(MD_RECOVERY_RESHAPE, &recovery) || + test_bit(MD_RECOVERY_RUNNING, &recovery))) r = mddev->curr_resync_completed; else r = mddev->recovery_cp; diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 5fe7ec356c33..7eb3e2a3c07d 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -942,17 +942,12 @@ static int dm_table_determine_type(struct dm_table *t) if (t->type != DM_TYPE_NONE) { /* target already set the table's type */ - if (t->type == DM_TYPE_BIO_BASED) - return 0; - else if (t->type == DM_TYPE_NVME_BIO_BASED) { - if (!dm_table_does_not_support_partial_completion(t)) { - DMERR("nvme bio-based is only possible with devices" - " that don't support partial completion"); - return -EINVAL; - } - /* Fallthru, also verify all devices are blk-mq */ + if (t->type == DM_TYPE_BIO_BASED) { + /* possibly upgrade to a variant of bio-based */ + goto verify_bio_based; } BUG_ON(t->type == DM_TYPE_DAX_BIO_BASED); + BUG_ON(t->type == DM_TYPE_NVME_BIO_BASED); goto verify_rq_based; } @@ -985,6 +980,7 @@ static int dm_table_determine_type(struct dm_table *t) } if (bio_based) { +verify_bio_based: /* We must use this table as bio-based */ t->type = DM_TYPE_BIO_BASED; if (dm_table_supports_dax(t) || @@ -1755,7 +1751,7 @@ static int device_no_partial_completion(struct dm_target *ti, struct dm_dev *dev char b[BDEVNAME_SIZE]; /* For now, NVMe devices are the only devices of this class */ - return (strncmp(bdevname(dev->bdev, b), "nvme", 3) == 0); + return (strncmp(bdevname(dev->bdev, b), "nvme", 4) == 0); } static bool dm_table_does_not_support_partial_completion(struct dm_table *t) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 68136806d365..45328d8b2859 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -458,9 +458,11 @@ static int dm_blk_getgeo(struct block_device *bdev, struct hd_geometry *geo) return dm_get_geometry(md, geo); } -static int dm_grab_bdev_for_ioctl(struct mapped_device *md, - struct block_device **bdev, - fmode_t *mode) +static char *_dm_claim_ptr = "I belong to device-mapper"; + +static int dm_get_bdev_for_ioctl(struct mapped_device *md, + struct block_device **bdev, + fmode_t *mode) { struct dm_target *tgt; struct dm_table *map; @@ -490,6 +492,10 @@ retry: goto out; bdgrab(*bdev); + r = blkdev_get(*bdev, *mode, _dm_claim_ptr); + if (r < 0) + goto out; + dm_put_live_table(md, srcu_idx); return r; @@ -508,7 +514,7 @@ static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode, struct mapped_device *md = bdev->bd_disk->private_data; int r; - r = dm_grab_bdev_for_ioctl(md, &bdev, &mode); + r = dm_get_bdev_for_ioctl(md, &bdev, &mode); if (r < 0) return r; @@ -528,7 +534,7 @@ static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode, r = __blkdev_driver_ioctl(bdev, mode, cmd, arg); out: - bdput(bdev); + blkdev_put(bdev, mode); return r; } @@ -708,14 +714,13 @@ static void dm_put_live_table_fast(struct mapped_device *md) __releases(RCU) static int open_table_device(struct table_device *td, dev_t dev, struct mapped_device *md) { - static char *_claim_ptr = "I belong to device-mapper"; struct block_device *bdev; int r; BUG_ON(td->dm_dev.bdev); - bdev = blkdev_get_by_dev(dev, td->dm_dev.mode | FMODE_EXCL, _claim_ptr); + bdev = blkdev_get_by_dev(dev, td->dm_dev.mode | FMODE_EXCL, _dm_claim_ptr); if (IS_ERR(bdev)) return PTR_ERR(bdev); @@ -3011,7 +3016,7 @@ static int dm_pr_reserve(struct block_device *bdev, u64 key, enum pr_type type, fmode_t mode; int r; - r = dm_grab_bdev_for_ioctl(md, &bdev, &mode); + r = dm_get_bdev_for_ioctl(md, &bdev, &mode); if (r < 0) return r; @@ -3021,7 +3026,7 @@ static int dm_pr_reserve(struct block_device *bdev, u64 key, enum pr_type type, else r = -EOPNOTSUPP; - bdput(bdev); + blkdev_put(bdev, mode); return r; } @@ -3032,7 +3037,7 @@ static int dm_pr_release(struct block_device *bdev, u64 key, enum pr_type type) fmode_t mode; int r; - r = dm_grab_bdev_for_ioctl(md, &bdev, &mode); + r = dm_get_bdev_for_ioctl(md, &bdev, &mode); if (r < 0) return r; @@ -3042,7 +3047,7 @@ static int dm_pr_release(struct block_device *bdev, u64 key, enum pr_type type) else r = -EOPNOTSUPP; - bdput(bdev); + blkdev_put(bdev, mode); return r; } @@ -3054,7 +3059,7 @@ static int dm_pr_preempt(struct block_device *bdev, u64 old_key, u64 new_key, fmode_t mode; int r; - r = dm_grab_bdev_for_ioctl(md, &bdev, &mode); + r = dm_get_bdev_for_ioctl(md, &bdev, &mode); if (r < 0) return r; @@ -3064,7 +3069,7 @@ static int dm_pr_preempt(struct block_device *bdev, u64 old_key, u64 new_key, else r = -EOPNOTSUPP; - bdput(bdev); + blkdev_put(bdev, mode); return r; } @@ -3075,7 +3080,7 @@ static int dm_pr_clear(struct block_device *bdev, u64 key) fmode_t mode; int r; - r = dm_grab_bdev_for_ioctl(md, &bdev, &mode); + r = dm_get_bdev_for_ioctl(md, &bdev, &mode); if (r < 0) return r; @@ -3085,7 +3090,7 @@ static int dm_pr_clear(struct block_device *bdev, u64 key) else r = -EOPNOTSUPP; - bdput(bdev); + blkdev_put(bdev, mode); return r; } diff --git a/drivers/misc/ocxl/file.c b/drivers/misc/ocxl/file.c index 337462e1569f..038509e5d031 100644 --- a/drivers/misc/ocxl/file.c +++ b/drivers/misc/ocxl/file.c @@ -102,10 +102,32 @@ static long afu_ioctl_attach(struct ocxl_context *ctx, return rc; } +static long afu_ioctl_get_metadata(struct ocxl_context *ctx, + struct ocxl_ioctl_metadata __user *uarg) +{ + struct ocxl_ioctl_metadata arg; + + memset(&arg, 0, sizeof(arg)); + + arg.version = 0; + + arg.afu_version_major = ctx->afu->config.version_major; + arg.afu_version_minor = ctx->afu->config.version_minor; + arg.pasid = ctx->pasid; + arg.pp_mmio_size = ctx->afu->config.pp_mmio_stride; + arg.global_mmio_size = ctx->afu->config.global_mmio_size; + + if (copy_to_user(uarg, &arg, sizeof(arg))) + return -EFAULT; + + return 0; +} + #define CMD_STR(x) (x == OCXL_IOCTL_ATTACH ? "ATTACH" : \ x == OCXL_IOCTL_IRQ_ALLOC ? "IRQ_ALLOC" : \ x == OCXL_IOCTL_IRQ_FREE ? "IRQ_FREE" : \ x == OCXL_IOCTL_IRQ_SET_FD ? "IRQ_SET_FD" : \ + x == OCXL_IOCTL_GET_METADATA ? "GET_METADATA" : \ "UNKNOWN") static long afu_ioctl(struct file *file, unsigned int cmd, @@ -159,6 +181,11 @@ static long afu_ioctl(struct file *file, unsigned int cmd, irq_fd.eventfd); break; + case OCXL_IOCTL_GET_METADATA: + rc = afu_ioctl_get_metadata(ctx, + (struct ocxl_ioctl_metadata __user *) args); + break; + default: rc = -EINVAL; } diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index f5c87bd35fa1..f27f9bae1a4a 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -3063,9 +3063,6 @@ static void gfar_process_frame(struct net_device *ndev, struct sk_buff *skb) if (ndev->features & NETIF_F_RXCSUM) gfar_rx_checksum(skb, fcb); - /* Tell the skb what kind of packet this is */ - skb->protocol = eth_type_trans(skb, ndev); - /* There's need to check for NETIF_F_HW_VLAN_CTAG_RX here. * Even if vlan rx accel is disabled, on some chips * RXFCB_VLN is pseudo randomly set. @@ -3136,13 +3133,15 @@ int gfar_clean_rx_ring(struct gfar_priv_rx_q *rx_queue, int rx_work_limit) continue; } + gfar_process_frame(ndev, skb); + /* Increment the number of packets */ total_pkts++; total_bytes += skb->len; skb_record_rx_queue(skb, rx_queue->qindex); - gfar_process_frame(ndev, skb); + skb->protocol = eth_type_trans(skb, ndev); /* Send the packet up the stack */ napi_gro_receive(&rx_queue->grp->napi_rx, skb); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 0da5aa2c8aba..9fc063af233c 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1888,6 +1888,14 @@ static void ixgbe_dma_sync_frag(struct ixgbe_ring *rx_ring, ixgbe_rx_pg_size(rx_ring), DMA_FROM_DEVICE, IXGBE_RX_DMA_ATTR); + } else if (ring_uses_build_skb(rx_ring)) { + unsigned long offset = (unsigned long)(skb->data) & ~PAGE_MASK; + + dma_sync_single_range_for_cpu(rx_ring->dev, + IXGBE_CB(skb)->dma, + offset, + skb_headlen(skb), + DMA_FROM_DEVICE); } else { struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 21d29f7936f6..d39b0b7011b2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -124,7 +124,7 @@ void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force) trigger_cmd_completions(dev); } - mlx5_core_event(dev, MLX5_DEV_EVENT_SYS_ERROR, 0); + mlx5_core_event(dev, MLX5_DEV_EVENT_SYS_ERROR, 1); mlx5_core_err(dev, "end\n"); unlock: diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h index f6963b0b4a55..122506daa586 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h @@ -107,20 +107,20 @@ static const struct mlxsw_afk_element_info mlxsw_afk_element_infos[] = { MLXSW_AFK_ELEMENT_INFO_U32(VID, 0x10, 8, 12), MLXSW_AFK_ELEMENT_INFO_U32(PCP, 0x10, 20, 3), MLXSW_AFK_ELEMENT_INFO_U32(TCP_FLAGS, 0x10, 23, 9), - MLXSW_AFK_ELEMENT_INFO_U32(IP_TTL_, 0x14, 0, 8), - MLXSW_AFK_ELEMENT_INFO_U32(IP_ECN, 0x14, 9, 2), - MLXSW_AFK_ELEMENT_INFO_U32(IP_DSCP, 0x14, 11, 6), - MLXSW_AFK_ELEMENT_INFO_U32(SRC_IP4, 0x18, 0, 32), - MLXSW_AFK_ELEMENT_INFO_U32(DST_IP4, 0x1C, 0, 32), - MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP6_HI, 0x18, 8), - MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP6_LO, 0x20, 8), - MLXSW_AFK_ELEMENT_INFO_BUF(DST_IP6_HI, 0x28, 8), - MLXSW_AFK_ELEMENT_INFO_BUF(DST_IP6_LO, 0x30, 8), MLXSW_AFK_ELEMENT_INFO_U32(DST_L4_PORT, 0x14, 0, 16), MLXSW_AFK_ELEMENT_INFO_U32(SRC_L4_PORT, 0x14, 16, 16), + MLXSW_AFK_ELEMENT_INFO_U32(IP_TTL_, 0x18, 0, 8), + MLXSW_AFK_ELEMENT_INFO_U32(IP_ECN, 0x18, 9, 2), + MLXSW_AFK_ELEMENT_INFO_U32(IP_DSCP, 0x18, 11, 6), + MLXSW_AFK_ELEMENT_INFO_U32(SRC_IP4, 0x20, 0, 32), + MLXSW_AFK_ELEMENT_INFO_U32(DST_IP4, 0x24, 0, 32), + MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP6_HI, 0x20, 8), + MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP6_LO, 0x28, 8), + MLXSW_AFK_ELEMENT_INFO_BUF(DST_IP6_HI, 0x30, 8), + MLXSW_AFK_ELEMENT_INFO_BUF(DST_IP6_LO, 0x38, 8), }; -#define MLXSW_AFK_ELEMENT_STORAGE_SIZE 0x38 +#define MLXSW_AFK_ELEMENT_STORAGE_SIZE 0x40 struct mlxsw_afk_element_inst { /* element instance in actual block */ const struct mlxsw_afk_element_info *info; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 3dcc58d61506..c7e941aecc2a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -1459,6 +1459,7 @@ mlxsw_sp_port_vlan_create(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid) } mlxsw_sp_port_vlan->mlxsw_sp_port = mlxsw_sp_port; + mlxsw_sp_port_vlan->ref_count = 1; mlxsw_sp_port_vlan->vid = vid; list_add(&mlxsw_sp_port_vlan->list, &mlxsw_sp_port->vlans_list); @@ -1486,8 +1487,10 @@ mlxsw_sp_port_vlan_get(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid) struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan; mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid); - if (mlxsw_sp_port_vlan) + if (mlxsw_sp_port_vlan) { + mlxsw_sp_port_vlan->ref_count++; return mlxsw_sp_port_vlan; + } return mlxsw_sp_port_vlan_create(mlxsw_sp_port, vid); } @@ -1496,6 +1499,9 @@ void mlxsw_sp_port_vlan_put(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan) { struct mlxsw_sp_fid *fid = mlxsw_sp_port_vlan->fid; + if (--mlxsw_sp_port_vlan->ref_count != 0) + return; + if (mlxsw_sp_port_vlan->bridge_port) mlxsw_sp_port_vlan_bridge_leave(mlxsw_sp_port_vlan); else if (fid) @@ -4207,13 +4213,12 @@ static struct devlink_resource_ops mlxsw_sp_resource_kvd_hash_double_ops = { .size_validate = mlxsw_sp_resource_kvd_hash_double_size_validate, }; -static struct devlink_resource_size_params mlxsw_sp_kvd_size_params; -static struct devlink_resource_size_params mlxsw_sp_linear_size_params; -static struct devlink_resource_size_params mlxsw_sp_hash_single_size_params; -static struct devlink_resource_size_params mlxsw_sp_hash_double_size_params; - static void -mlxsw_sp_resource_size_params_prepare(struct mlxsw_core *mlxsw_core) +mlxsw_sp_resource_size_params_prepare(struct mlxsw_core *mlxsw_core, + struct devlink_resource_size_params *kvd_size_params, + struct devlink_resource_size_params *linear_size_params, + struct devlink_resource_size_params *hash_double_size_params, + struct devlink_resource_size_params *hash_single_size_params) { u32 single_size_min = MLXSW_CORE_RES_GET(mlxsw_core, KVD_SINGLE_MIN_SIZE); @@ -4222,37 +4227,35 @@ mlxsw_sp_resource_size_params_prepare(struct mlxsw_core *mlxsw_core) u32 kvd_size = MLXSW_CORE_RES_GET(mlxsw_core, KVD_SIZE); u32 linear_size_min = 0; - /* KVD top resource */ - mlxsw_sp_kvd_size_params.size_min = kvd_size; - mlxsw_sp_kvd_size_params.size_max = kvd_size; - mlxsw_sp_kvd_size_params.size_granularity = MLXSW_SP_KVD_GRANULARITY; - mlxsw_sp_kvd_size_params.unit = DEVLINK_RESOURCE_UNIT_ENTRY; - - /* Linear part init */ - mlxsw_sp_linear_size_params.size_min = linear_size_min; - mlxsw_sp_linear_size_params.size_max = kvd_size - single_size_min - - double_size_min; - mlxsw_sp_linear_size_params.size_granularity = MLXSW_SP_KVD_GRANULARITY; - mlxsw_sp_linear_size_params.unit = DEVLINK_RESOURCE_UNIT_ENTRY; - - /* Hash double part init */ - mlxsw_sp_hash_double_size_params.size_min = double_size_min; - mlxsw_sp_hash_double_size_params.size_max = kvd_size - single_size_min - - linear_size_min; - mlxsw_sp_hash_double_size_params.size_granularity = MLXSW_SP_KVD_GRANULARITY; - mlxsw_sp_hash_double_size_params.unit = DEVLINK_RESOURCE_UNIT_ENTRY; - - /* Hash single part init */ - mlxsw_sp_hash_single_size_params.size_min = single_size_min; - mlxsw_sp_hash_single_size_params.size_max = kvd_size - double_size_min - - linear_size_min; - mlxsw_sp_hash_single_size_params.size_granularity = MLXSW_SP_KVD_GRANULARITY; - mlxsw_sp_hash_single_size_params.unit = DEVLINK_RESOURCE_UNIT_ENTRY; + devlink_resource_size_params_init(kvd_size_params, kvd_size, kvd_size, + MLXSW_SP_KVD_GRANULARITY, + DEVLINK_RESOURCE_UNIT_ENTRY); + devlink_resource_size_params_init(linear_size_params, linear_size_min, + kvd_size - single_size_min - + double_size_min, + MLXSW_SP_KVD_GRANULARITY, + DEVLINK_RESOURCE_UNIT_ENTRY); + devlink_resource_size_params_init(hash_double_size_params, + double_size_min, + kvd_size - single_size_min - + linear_size_min, + MLXSW_SP_KVD_GRANULARITY, + DEVLINK_RESOURCE_UNIT_ENTRY); + devlink_resource_size_params_init(hash_single_size_params, + single_size_min, + kvd_size - double_size_min - + linear_size_min, + MLXSW_SP_KVD_GRANULARITY, + DEVLINK_RESOURCE_UNIT_ENTRY); } static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core) { struct devlink *devlink = priv_to_devlink(mlxsw_core); + struct devlink_resource_size_params hash_single_size_params; + struct devlink_resource_size_params hash_double_size_params; + struct devlink_resource_size_params linear_size_params; + struct devlink_resource_size_params kvd_size_params; u32 kvd_size, single_size, double_size, linear_size; const struct mlxsw_config_profile *profile; int err; @@ -4261,13 +4264,17 @@ static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core) if (!MLXSW_CORE_RES_VALID(mlxsw_core, KVD_SIZE)) return -EIO; - mlxsw_sp_resource_size_params_prepare(mlxsw_core); + mlxsw_sp_resource_size_params_prepare(mlxsw_core, &kvd_size_params, + &linear_size_params, + &hash_double_size_params, + &hash_single_size_params); + kvd_size = MLXSW_CORE_RES_GET(mlxsw_core, KVD_SIZE); err = devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD, true, kvd_size, MLXSW_SP_RESOURCE_KVD, DEVLINK_RESOURCE_ID_PARENT_TOP, - &mlxsw_sp_kvd_size_params, + &kvd_size_params, &mlxsw_sp_resource_kvd_ops); if (err) return err; @@ -4277,7 +4284,7 @@ static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core) false, linear_size, MLXSW_SP_RESOURCE_KVD_LINEAR, MLXSW_SP_RESOURCE_KVD, - &mlxsw_sp_linear_size_params, + &linear_size_params, &mlxsw_sp_resource_kvd_linear_ops); if (err) return err; @@ -4291,7 +4298,7 @@ static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core) false, double_size, MLXSW_SP_RESOURCE_KVD_HASH_DOUBLE, MLXSW_SP_RESOURCE_KVD, - &mlxsw_sp_hash_double_size_params, + &hash_double_size_params, &mlxsw_sp_resource_kvd_hash_double_ops); if (err) return err; @@ -4301,7 +4308,7 @@ static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core) false, single_size, MLXSW_SP_RESOURCE_KVD_HASH_SINGLE, MLXSW_SP_RESOURCE_KVD, - &mlxsw_sp_hash_single_size_params, + &hash_single_size_params, &mlxsw_sp_resource_kvd_hash_single_ops); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index bdd8f94a452c..4ec1ca3c96c8 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -211,6 +211,7 @@ struct mlxsw_sp_port_vlan { struct list_head list; struct mlxsw_sp_port *mlxsw_sp_port; struct mlxsw_sp_fid *fid; + unsigned int ref_count; u16 vid; struct mlxsw_sp_bridge_port *bridge_port; struct list_head bridge_vlan_node; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c index bbd238e50f05..54262af4e98f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c @@ -112,11 +112,11 @@ static const int mlxsw_sp_sfgc_bc_packet_types[MLXSW_REG_SFGC_TYPE_MAX] = { [MLXSW_REG_SFGC_TYPE_UNREGISTERED_MULTICAST_NON_IP] = 1, [MLXSW_REG_SFGC_TYPE_IPV4_LINK_LOCAL] = 1, [MLXSW_REG_SFGC_TYPE_IPV6_ALL_HOST] = 1, + [MLXSW_REG_SFGC_TYPE_UNREGISTERED_MULTICAST_IPV6] = 1, }; static const int mlxsw_sp_sfgc_mc_packet_types[MLXSW_REG_SFGC_TYPE_MAX] = { [MLXSW_REG_SFGC_TYPE_UNREGISTERED_MULTICAST_IPV4] = 1, - [MLXSW_REG_SFGC_TYPE_UNREGISTERED_MULTICAST_IPV6] = 1, }; static const int *mlxsw_sp_packet_type_sfgc_types[] = { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 593ad31be749..161bcdc012f0 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -1203,6 +1203,7 @@ static int __mlxsw_sp_port_fdb_uc_op(struct mlxsw_sp *mlxsw_sp, u8 local_port, bool dynamic) { char *sfd_pl; + u8 num_rec; int err; sfd_pl = kmalloc(MLXSW_REG_SFD_LEN, GFP_KERNEL); @@ -1212,9 +1213,16 @@ static int __mlxsw_sp_port_fdb_uc_op(struct mlxsw_sp *mlxsw_sp, u8 local_port, mlxsw_reg_sfd_pack(sfd_pl, mlxsw_sp_sfd_op(adding), 0); mlxsw_reg_sfd_uc_pack(sfd_pl, 0, mlxsw_sp_sfd_rec_policy(dynamic), mac, fid, action, local_port); + num_rec = mlxsw_reg_sfd_num_rec_get(sfd_pl); err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfd), sfd_pl); - kfree(sfd_pl); + if (err) + goto out; + + if (num_rec != mlxsw_reg_sfd_num_rec_get(sfd_pl)) + err = -EBUSY; +out: + kfree(sfd_pl); return err; } @@ -1239,6 +1247,7 @@ static int mlxsw_sp_port_fdb_uc_lag_op(struct mlxsw_sp *mlxsw_sp, u16 lag_id, bool adding, bool dynamic) { char *sfd_pl; + u8 num_rec; int err; sfd_pl = kmalloc(MLXSW_REG_SFD_LEN, GFP_KERNEL); @@ -1249,9 +1258,16 @@ static int mlxsw_sp_port_fdb_uc_lag_op(struct mlxsw_sp *mlxsw_sp, u16 lag_id, mlxsw_reg_sfd_uc_lag_pack(sfd_pl, 0, mlxsw_sp_sfd_rec_policy(dynamic), mac, fid, MLXSW_REG_SFD_REC_ACTION_NOP, lag_vid, lag_id); + num_rec = mlxsw_reg_sfd_num_rec_get(sfd_pl); err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfd), sfd_pl); - kfree(sfd_pl); + if (err) + goto out; + + if (num_rec != mlxsw_reg_sfd_num_rec_get(sfd_pl)) + err = -EBUSY; +out: + kfree(sfd_pl); return err; } @@ -1296,6 +1312,7 @@ static int mlxsw_sp_port_mdb_op(struct mlxsw_sp *mlxsw_sp, const char *addr, u16 fid, u16 mid_idx, bool adding) { char *sfd_pl; + u8 num_rec; int err; sfd_pl = kmalloc(MLXSW_REG_SFD_LEN, GFP_KERNEL); @@ -1305,7 +1322,15 @@ static int mlxsw_sp_port_mdb_op(struct mlxsw_sp *mlxsw_sp, const char *addr, mlxsw_reg_sfd_pack(sfd_pl, mlxsw_sp_sfd_op(adding), 0); mlxsw_reg_sfd_mc_pack(sfd_pl, 0, addr, fid, MLXSW_REG_SFD_REC_ACTION_NOP, mid_idx); + num_rec = mlxsw_reg_sfd_num_rec_get(sfd_pl); err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfd), sfd_pl); + if (err) + goto out; + + if (num_rec != mlxsw_reg_sfd_num_rec_get(sfd_pl)) + err = -EBUSY; + +out: kfree(sfd_pl); return err; } diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 92dcf8717fc6..14c839bb09e7 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -439,6 +439,17 @@ static void sh_eth_modify(struct net_device *ndev, int enum_index, u32 clear, enum_index); } +static void sh_eth_tsu_write(struct sh_eth_private *mdp, u32 data, + int enum_index) +{ + iowrite32(data, mdp->tsu_addr + mdp->reg_offset[enum_index]); +} + +static u32 sh_eth_tsu_read(struct sh_eth_private *mdp, int enum_index) +{ + return ioread32(mdp->tsu_addr + mdp->reg_offset[enum_index]); +} + static bool sh_eth_is_gether(struct sh_eth_private *mdp) { return mdp->reg_offset == sh_eth_offset_gigabit; diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h index a6753ccba711..e5fe70134690 100644 --- a/drivers/net/ethernet/renesas/sh_eth.h +++ b/drivers/net/ethernet/renesas/sh_eth.h @@ -567,15 +567,4 @@ static inline void *sh_eth_tsu_get_offset(struct sh_eth_private *mdp, return mdp->tsu_addr + mdp->reg_offset[enum_index]; } -static inline void sh_eth_tsu_write(struct sh_eth_private *mdp, u32 data, - int enum_index) -{ - iowrite32(data, mdp->tsu_addr + mdp->reg_offset[enum_index]); -} - -static inline u32 sh_eth_tsu_read(struct sh_eth_private *mdp, int enum_index) -{ - return ioread32(mdp->tsu_addr + mdp->reg_offset[enum_index]); -} - #endif /* #ifndef __SH_ETH_H__ */ diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 17e529af79dc..0265d703eb03 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -852,13 +852,6 @@ int netvsc_send(struct net_device *ndev, if (unlikely(!net_device || net_device->destroy)) return -ENODEV; - /* We may race with netvsc_connect_vsp()/netvsc_init_buf() and get - * here before the negotiation with the host is finished and - * send_section_map may not be allocated yet. - */ - if (unlikely(!net_device->send_section_map)) - return -EAGAIN; - nvchan = &net_device->chan_table[packet->q_idx]; packet->send_buf_index = NETVSC_INVALID_INDEX; packet->cp_partial = false; @@ -866,10 +859,8 @@ int netvsc_send(struct net_device *ndev, /* Send control message directly without accessing msd (Multi-Send * Data) field which may be changed during data packet processing. */ - if (!skb) { - cur_send = packet; - goto send_now; - } + if (!skb) + return netvsc_send_pkt(device, packet, net_device, pb, skb); /* batch packets in send buffer if possible */ msdp = &nvchan->msd; @@ -953,7 +944,6 @@ int netvsc_send(struct net_device *ndev, } } -send_now: if (cur_send) ret = netvsc_send_pkt(device, cur_send, net_device, pb, skb); @@ -1217,9 +1207,10 @@ int netvsc_poll(struct napi_struct *napi, int budget) if (send_recv_completions(ndev, net_device, nvchan) == 0 && work_done < budget && napi_complete_done(napi, work_done) && - hv_end_read(&channel->inbound)) { + hv_end_read(&channel->inbound) && + napi_schedule_prep(napi)) { hv_begin_read(&channel->inbound); - napi_reschedule(napi); + __napi_schedule(napi); } /* Driver may overshoot since multiple packets per descriptor */ @@ -1242,7 +1233,7 @@ void netvsc_channel_cb(void *context) /* disable interupts from host */ hv_begin_read(rbi); - __napi_schedule(&nvchan->napi); + __napi_schedule_irqoff(&nvchan->napi); } } @@ -1296,7 +1287,6 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device, netvsc_channel_cb, net_device->chan_table); if (ret != 0) { - netif_napi_del(&net_device->chan_table[0].napi); netdev_err(ndev, "unable to open channel: %d\n", ret); goto cleanup; } @@ -1306,11 +1296,6 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device, napi_enable(&net_device->chan_table[0].napi); - /* Writing nvdev pointer unlocks netvsc_send(), make sure chn_table is - * populated. - */ - rcu_assign_pointer(net_device_ctx->nvdev, net_device); - /* Connect with the NetVsp */ ret = netvsc_connect_vsp(device, net_device, device_info); if (ret != 0) { @@ -1319,6 +1304,11 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device, goto close; } + /* Writing nvdev pointer unlocks netvsc_send(), make sure chn_table is + * populated. + */ + rcu_assign_pointer(net_device_ctx->nvdev, net_device); + return net_device; close: @@ -1329,6 +1319,7 @@ close: vmbus_close(device->channel); cleanup: + netif_napi_del(&net_device->chan_table[0].napi); free_netvsc_device(&net_device->rcu); return ERR_PTR(ret); diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index c5584c2d440e..cdb78eefab67 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -66,10 +66,36 @@ static int debug = -1; module_param(debug, int, S_IRUGO); MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)"); -static void netvsc_set_multicast_list(struct net_device *net) +static void netvsc_change_rx_flags(struct net_device *net, int change) { - struct net_device_context *net_device_ctx = netdev_priv(net); - struct netvsc_device *nvdev = rtnl_dereference(net_device_ctx->nvdev); + struct net_device_context *ndev_ctx = netdev_priv(net); + struct net_device *vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev); + int inc; + + if (!vf_netdev) + return; + + if (change & IFF_PROMISC) { + inc = (net->flags & IFF_PROMISC) ? 1 : -1; + dev_set_promiscuity(vf_netdev, inc); + } + + if (change & IFF_ALLMULTI) { + inc = (net->flags & IFF_ALLMULTI) ? 1 : -1; + dev_set_allmulti(vf_netdev, inc); + } +} + +static void netvsc_set_rx_mode(struct net_device *net) +{ + struct net_device_context *ndev_ctx = netdev_priv(net); + struct net_device *vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev); + struct netvsc_device *nvdev = rtnl_dereference(ndev_ctx->nvdev); + + if (vf_netdev) { + dev_uc_sync(vf_netdev, net); + dev_mc_sync(vf_netdev, net); + } rndis_filter_update(nvdev); } @@ -91,12 +117,11 @@ static int netvsc_open(struct net_device *net) return ret; } - netif_tx_wake_all_queues(net); - rdev = nvdev->extension; - - if (!rdev->link_state) + if (!rdev->link_state) { netif_carrier_on(net); + netif_tx_wake_all_queues(net); + } if (vf_netdev) { /* Setting synthetic device up transparently sets @@ -299,8 +324,19 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb, rcu_read_lock(); vf_netdev = rcu_dereference(ndc->vf_netdev); if (vf_netdev) { - txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) : 0; - qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb->queue_mapping; + const struct net_device_ops *vf_ops = vf_netdev->netdev_ops; + + if (vf_ops->ndo_select_queue) + txq = vf_ops->ndo_select_queue(vf_netdev, skb, + accel_priv, fallback); + else + txq = fallback(vf_netdev, skb); + + /* Record the queue selected by VF so that it can be + * used for common case where VF has more queues than + * the synthetic device. + */ + qdisc_skb_cb(skb)->slave_dev_queue_mapping = txq; } else { txq = netvsc_pick_tx(ndev, skb); } @@ -1576,7 +1612,8 @@ static const struct net_device_ops device_ops = { .ndo_open = netvsc_open, .ndo_stop = netvsc_close, .ndo_start_xmit = netvsc_start_xmit, - .ndo_set_rx_mode = netvsc_set_multicast_list, + .ndo_change_rx_flags = netvsc_change_rx_flags, + .ndo_set_rx_mode = netvsc_set_rx_mode, .ndo_change_mtu = netvsc_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = netvsc_set_mac_addr, @@ -1807,6 +1844,11 @@ static void __netvsc_vf_setup(struct net_device *ndev, netdev_warn(vf_netdev, "unable to change mtu to %u\n", ndev->mtu); + /* set multicast etc flags on VF */ + dev_change_flags(vf_netdev, ndev->flags | IFF_SLAVE); + dev_uc_sync(vf_netdev, ndev); + dev_mc_sync(vf_netdev, ndev); + if (netif_running(ndev)) { ret = dev_open(vf_netdev); if (ret) diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index c3ca191fea7f..8927c483c217 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -854,15 +854,19 @@ static void rndis_set_multicast(struct work_struct *w) { struct rndis_device *rdev = container_of(w, struct rndis_device, mcast_work); + u32 filter = NDIS_PACKET_TYPE_DIRECTED; + unsigned int flags = rdev->ndev->flags; - if (rdev->ndev->flags & IFF_PROMISC) - rndis_filter_set_packet_filter(rdev, - NDIS_PACKET_TYPE_PROMISCUOUS); - else - rndis_filter_set_packet_filter(rdev, - NDIS_PACKET_TYPE_BROADCAST | - NDIS_PACKET_TYPE_ALL_MULTICAST | - NDIS_PACKET_TYPE_DIRECTED); + if (flags & IFF_PROMISC) { + filter = NDIS_PACKET_TYPE_PROMISCUOUS; + } else { + if (flags & IFF_ALLMULTI) + flags |= NDIS_PACKET_TYPE_ALL_MULTICAST; + if (flags & IFF_BROADCAST) + flags |= NDIS_PACKET_TYPE_BROADCAST; + } + + rndis_filter_set_packet_filter(rdev, filter); } void rndis_filter_update(struct netvsc_device *nvdev) @@ -1340,6 +1344,9 @@ void rndis_filter_device_remove(struct hv_device *dev, { struct rndis_device *rndis_dev = net_dev->extension; + /* Don't try and setup sub channels if about to halt */ + cancel_work_sync(&net_dev->subchan_work); + /* Halt and release the rndis device */ rndis_filter_halt_device(rndis_dev); diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index e3e29c2b028b..a6f924fee584 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -819,7 +819,7 @@ void phy_start(struct phy_device *phydev) break; case PHY_HALTED: /* if phy was suspended, bring the physical link up again */ - phy_resume(phydev); + __phy_resume(phydev); /* make sure interrupts are re-enabled for the PHY */ if (phy_interrupt_is_valid(phydev)) { diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index d39ae77707ef..478405e544cc 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -135,9 +135,7 @@ static int mdio_bus_phy_resume(struct device *dev) if (!mdio_bus_phy_may_suspend(phydev)) goto no_resume; - mutex_lock(&phydev->lock); ret = phy_resume(phydev); - mutex_unlock(&phydev->lock); if (ret < 0) return ret; @@ -1041,9 +1039,7 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, if (err) goto error; - mutex_lock(&phydev->lock); phy_resume(phydev); - mutex_unlock(&phydev->lock); phy_led_triggers_register(phydev); return err; @@ -1172,7 +1168,7 @@ int phy_suspend(struct phy_device *phydev) } EXPORT_SYMBOL(phy_suspend); -int phy_resume(struct phy_device *phydev) +int __phy_resume(struct phy_device *phydev) { struct phy_driver *phydrv = to_phy_driver(phydev->mdio.dev.driver); int ret = 0; @@ -1189,6 +1185,18 @@ int phy_resume(struct phy_device *phydev) return ret; } +EXPORT_SYMBOL(__phy_resume); + +int phy_resume(struct phy_device *phydev) +{ + int ret; + + mutex_lock(&phydev->lock); + ret = __phy_resume(phydev); + mutex_unlock(&phydev->lock); + + return ret; +} EXPORT_SYMBOL(phy_resume); int phy_loopback(struct phy_device *phydev, bool enable) diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 255a5def56e9..fa2a9bdd1866 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -3161,6 +3161,15 @@ ppp_connect_channel(struct channel *pch, int unit) goto outl; ppp_lock(ppp); + spin_lock_bh(&pch->downl); + if (!pch->chan) { + /* Don't connect unregistered channels */ + spin_unlock_bh(&pch->downl); + ppp_unlock(ppp); + ret = -ENOTCONN; + goto outl; + } + spin_unlock_bh(&pch->downl); if (pch->file.hdrlen > ppp->file.hdrlen) ppp->file.hdrlen = pch->file.hdrlen; hdrlen = pch->file.hdrlen + 2; /* for protocol bytes */ diff --git a/drivers/net/tun.c b/drivers/net/tun.c index b52258c327d2..7433bb2e4451 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -181,7 +181,6 @@ struct tun_file { struct tun_struct *detached; struct ptr_ring tx_ring; struct xdp_rxq_info xdp_rxq; - int xdp_pending_pkts; }; struct tun_flow_entry { @@ -1643,6 +1642,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, else *skb_xdp = 0; + preempt_disable(); rcu_read_lock(); xdp_prog = rcu_dereference(tun->xdp_prog); if (xdp_prog && !*skb_xdp) { @@ -1662,11 +1662,12 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, case XDP_REDIRECT: get_page(alloc_frag->page); alloc_frag->offset += buflen; - ++tfile->xdp_pending_pkts; err = xdp_do_redirect(tun->dev, &xdp, xdp_prog); + xdp_do_flush_map(); if (err) goto err_redirect; rcu_read_unlock(); + preempt_enable(); return NULL; case XDP_TX: xdp_xmit = true; @@ -1688,6 +1689,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, skb = build_skb(buf, buflen); if (!skb) { rcu_read_unlock(); + preempt_enable(); return ERR_PTR(-ENOMEM); } @@ -1700,10 +1702,12 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, skb->dev = tun->dev; generic_xdp_tx(skb, xdp_prog); rcu_read_unlock(); + preempt_enable(); return NULL; } rcu_read_unlock(); + preempt_enable(); return skb; @@ -1711,6 +1715,7 @@ err_redirect: put_page(alloc_frag->page); err_xdp: rcu_read_unlock(); + preempt_enable(); this_cpu_inc(tun->pcpu_stats->rx_dropped); return NULL; } @@ -1984,11 +1989,6 @@ static ssize_t tun_chr_write_iter(struct kiocb *iocb, struct iov_iter *from) result = tun_get_user(tun, tfile, NULL, from, file->f_flags & O_NONBLOCK, false); - if (tfile->xdp_pending_pkts) { - tfile->xdp_pending_pkts = 0; - xdp_do_flush_map(); - } - tun_put(tun); return result; } @@ -2325,13 +2325,6 @@ static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) ret = tun_get_user(tun, tfile, m->msg_control, &m->msg_iter, m->msg_flags & MSG_DONTWAIT, m->msg_flags & MSG_MORE); - - if (tfile->xdp_pending_pkts >= NAPI_POLL_WEIGHT || - !(m->msg_flags & MSG_MORE)) { - tfile->xdp_pending_pkts = 0; - xdp_do_flush_map(); - } - tun_put(tun); return ret; } @@ -3163,7 +3156,6 @@ static int tun_chr_open(struct inode *inode, struct file * file) sock_set_flag(&tfile->sk, SOCK_ZEROCOPY); memset(&tfile->tx_ring, 0, sizeof(tfile->tx_ring)); - tfile->xdp_pending_pkts = 0; return 0; } diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index 05dca3e5c93d..fff4b13eece2 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -896,6 +896,12 @@ static const struct usb_device_id products[] = { USB_CDC_PROTO_NONE), .driver_info = (unsigned long)&wwan_info, }, { + /* Cinterion PLS8 modem by GEMALTO */ + USB_DEVICE_AND_INTERFACE_INFO(0x1e2d, 0x0061, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, + USB_CDC_PROTO_NONE), + .driver_info = (unsigned long)&wwan_info, +}, { USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), .driver_info = (unsigned long) &cdc_info, diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 958b2e8b90f6..86f7196f9d91 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -1794,7 +1794,7 @@ static int r8152_tx_agg_fill(struct r8152 *tp, struct tx_agg *agg) tx_data += len; agg->skb_len += len; - agg->skb_num++; + agg->skb_num += skb_shinfo(skb)->gso_segs ?: 1; dev_kfree_skb_any(skb); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 9bb9e562b893..23374603e4d9 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -504,6 +504,7 @@ static struct page *xdp_linearize_page(struct receive_queue *rq, page_off += *len; while (--*num_buf) { + int tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); unsigned int buflen; void *buf; int off; @@ -518,7 +519,7 @@ static struct page *xdp_linearize_page(struct receive_queue *rq, /* guard against a misconfigured or uncooperative backend that * is sending packet larger than the MTU. */ - if ((page_off + buflen) > PAGE_SIZE) { + if ((page_off + buflen + tailroom) > PAGE_SIZE) { put_page(p); goto err_buf; } @@ -690,6 +691,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, unsigned int truesize; unsigned int headroom = mergeable_ctx_to_headroom(ctx); bool sent; + int err; head_skb = NULL; @@ -701,7 +703,12 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, void *data; u32 act; - /* This happens when rx buffer size is underestimated */ + /* This happens when rx buffer size is underestimated + * or headroom is not enough because of the buffer + * was refilled before XDP is set. This should only + * happen for the first several packets, so we don't + * care much about its performance. + */ if (unlikely(num_buf > 1 || headroom < virtnet_get_headroom(vi))) { /* linearize data for XDP */ @@ -736,9 +743,6 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, act = bpf_prog_run_xdp(xdp_prog, &xdp); - if (act != XDP_PASS) - ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len); - switch (act) { case XDP_PASS: /* recalculate offset to account for any header @@ -770,6 +774,18 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, goto err_xdp; rcu_read_unlock(); goto xdp_xmit; + case XDP_REDIRECT: + err = xdp_do_redirect(dev, &xdp, xdp_prog); + if (err) { + if (unlikely(xdp_page != page)) + put_page(xdp_page); + goto err_xdp; + } + *xdp_xmit = true; + if (unlikely(xdp_page != page)) + goto err_xdp; + rcu_read_unlock(); + goto xdp_xmit; default: bpf_warn_invalid_xdp_action(act); case XDP_ABORTED: @@ -1013,13 +1029,18 @@ static int add_recvbuf_big(struct virtnet_info *vi, struct receive_queue *rq, } static unsigned int get_mergeable_buf_len(struct receive_queue *rq, - struct ewma_pkt_len *avg_pkt_len) + struct ewma_pkt_len *avg_pkt_len, + unsigned int room) { const size_t hdr_len = sizeof(struct virtio_net_hdr_mrg_rxbuf); unsigned int len; - len = hdr_len + clamp_t(unsigned int, ewma_pkt_len_read(avg_pkt_len), + if (room) + return PAGE_SIZE - room; + + len = hdr_len + clamp_t(unsigned int, ewma_pkt_len_read(avg_pkt_len), rq->min_buf_len, PAGE_SIZE - hdr_len); + return ALIGN(len, L1_CACHE_BYTES); } @@ -1028,21 +1049,27 @@ static int add_recvbuf_mergeable(struct virtnet_info *vi, { struct page_frag *alloc_frag = &rq->alloc_frag; unsigned int headroom = virtnet_get_headroom(vi); + unsigned int tailroom = headroom ? sizeof(struct skb_shared_info) : 0; + unsigned int room = SKB_DATA_ALIGN(headroom + tailroom); char *buf; void *ctx; int err; unsigned int len, hole; - len = get_mergeable_buf_len(rq, &rq->mrg_avg_pkt_len); - if (unlikely(!skb_page_frag_refill(len + headroom, alloc_frag, gfp))) + /* Extra tailroom is needed to satisfy XDP's assumption. This + * means rx frags coalescing won't work, but consider we've + * disabled GSO for XDP, it won't be a big issue. + */ + len = get_mergeable_buf_len(rq, &rq->mrg_avg_pkt_len, room); + if (unlikely(!skb_page_frag_refill(len + room, alloc_frag, gfp))) return -ENOMEM; buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset; buf += headroom; /* advance address leaving hole at front of pkt */ get_page(alloc_frag->page); - alloc_frag->offset += len + headroom; + alloc_frag->offset += len + room; hole = alloc_frag->size - alloc_frag->offset; - if (hole < len + headroom) { + if (hole < len + room) { /* To avoid internal fragmentation, if there is very likely not * enough space for another buffer, add the remaining space to * the current buffer. @@ -2185,8 +2212,9 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, } /* Make sure NAPI is not using any XDP TX queues for RX. */ - for (i = 0; i < vi->max_queue_pairs; i++) - napi_disable(&vi->rq[i].napi); + if (netif_running(dev)) + for (i = 0; i < vi->max_queue_pairs; i++) + napi_disable(&vi->rq[i].napi); netif_set_real_num_rx_queues(dev, curr_qp + xdp_qp); err = _virtnet_set_queues(vi, curr_qp + xdp_qp); @@ -2205,7 +2233,8 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, } if (old_prog) bpf_prog_put(old_prog); - virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi); + if (netif_running(dev)) + virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi); } return 0; @@ -2576,12 +2605,15 @@ static ssize_t mergeable_rx_buffer_size_show(struct netdev_rx_queue *queue, { struct virtnet_info *vi = netdev_priv(queue->dev); unsigned int queue_index = get_netdev_rx_queue_index(queue); + unsigned int headroom = virtnet_get_headroom(vi); + unsigned int tailroom = headroom ? sizeof(struct skb_shared_info) : 0; struct ewma_pkt_len *avg; BUG_ON(queue_index >= vi->max_queue_pairs); avg = &vi->rq[queue_index].mrg_avg_pkt_len; return sprintf(buf, "%u\n", - get_mergeable_buf_len(&vi->rq[queue_index], avg)); + get_mergeable_buf_len(&vi->rq[queue_index], avg, + SKB_DATA_ALIGN(headroom + tailroom))); } static struct rx_queue_attribute mergeable_rx_buffer_size_attribute = diff --git a/drivers/net/wan/hdlc_ppp.c b/drivers/net/wan/hdlc_ppp.c index afeca6bcdade..ab8b3cbbb205 100644 --- a/drivers/net/wan/hdlc_ppp.c +++ b/drivers/net/wan/hdlc_ppp.c @@ -574,7 +574,10 @@ static void ppp_timer(struct timer_list *t) ppp_cp_event(proto->dev, proto->pid, TO_GOOD, 0, 0, 0, NULL); proto->restart_counter--; - } else + } else if (netif_carrier_ok(proto->dev)) + ppp_cp_event(proto->dev, proto->pid, TO_GOOD, 0, 0, + 0, NULL); + else ppp_cp_event(proto->dev, proto->pid, TO_BAD, 0, 0, 0, NULL); break; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 817e5e2766da..7aeca5db7916 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3033,7 +3033,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) ns->disk->disk_name); nvme_mpath_add_disk(ns->head); - nvme_mpath_add_disk_links(ns); return; out_unlink_ns: mutex_lock(&ctrl->subsys->lock); @@ -3053,7 +3052,6 @@ static void nvme_ns_remove(struct nvme_ns *ns) return; if (ns->disk && ns->disk->flags & GENHD_FL_UP) { - nvme_mpath_remove_disk_links(ns); sysfs_remove_group(&disk_to_dev(ns->disk)->kobj, &nvme_ns_id_attr_group); if (ns->ndev) diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index a1c58e35075e..8f0f34d06d46 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -650,6 +650,11 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, ret = -EINVAL; goto out; } + if (opts->discovery_nqn) { + pr_debug("Ignoring nr_io_queues value for discovery controller\n"); + break; + } + opts->nr_io_queues = min_t(unsigned int, num_online_cpus(), token); break; diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 7f51f8414b97..1dc1387b7134 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -1206,7 +1206,7 @@ nvme_fc_connect_admin_queue(struct nvme_fc_ctrl *ctrl, sizeof(struct fcnvme_lsdesc_cr_assoc_cmd)); assoc_rqst->assoc_cmd.ersp_ratio = cpu_to_be16(ersp_ratio); - assoc_rqst->assoc_cmd.sqsize = cpu_to_be16(qsize); + assoc_rqst->assoc_cmd.sqsize = cpu_to_be16(qsize - 1); /* Linux supports only Dynamic controllers */ assoc_rqst->assoc_cmd.cntlid = cpu_to_be16(0xffff); uuid_copy(&assoc_rqst->assoc_cmd.hostid, &ctrl->ctrl.opts->host->id); @@ -1321,7 +1321,7 @@ nvme_fc_connect_queue(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue, sizeof(struct fcnvme_lsdesc_cr_conn_cmd)); conn_rqst->connect_cmd.ersp_ratio = cpu_to_be16(ersp_ratio); conn_rqst->connect_cmd.qid = cpu_to_be16(queue->qnum); - conn_rqst->connect_cmd.sqsize = cpu_to_be16(qsize); + conn_rqst->connect_cmd.sqsize = cpu_to_be16(qsize - 1); lsop->queue = queue; lsreq->rqstaddr = conn_rqst; @@ -2481,11 +2481,11 @@ nvme_fc_create_io_queues(struct nvme_fc_ctrl *ctrl) goto out_free_tag_set; } - ret = nvme_fc_create_hw_io_queues(ctrl, ctrl->ctrl.opts->queue_size); + ret = nvme_fc_create_hw_io_queues(ctrl, ctrl->ctrl.sqsize + 1); if (ret) goto out_cleanup_blk_queue; - ret = nvme_fc_connect_io_queues(ctrl, ctrl->ctrl.opts->queue_size); + ret = nvme_fc_connect_io_queues(ctrl, ctrl->ctrl.sqsize + 1); if (ret) goto out_delete_hw_queues; @@ -2532,11 +2532,11 @@ nvme_fc_reinit_io_queues(struct nvme_fc_ctrl *ctrl) if (ret) goto out_free_io_queues; - ret = nvme_fc_create_hw_io_queues(ctrl, ctrl->ctrl.opts->queue_size); + ret = nvme_fc_create_hw_io_queues(ctrl, ctrl->ctrl.sqsize + 1); if (ret) goto out_free_io_queues; - ret = nvme_fc_connect_io_queues(ctrl, ctrl->ctrl.opts->queue_size); + ret = nvme_fc_connect_io_queues(ctrl, ctrl->ctrl.sqsize + 1); if (ret) goto out_delete_hw_queues; @@ -2632,13 +2632,12 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) nvme_fc_init_queue(ctrl, 0); ret = __nvme_fc_create_hw_queue(ctrl, &ctrl->queues[0], 0, - NVME_AQ_BLK_MQ_DEPTH); + NVME_AQ_DEPTH); if (ret) goto out_free_queue; ret = nvme_fc_connect_admin_queue(ctrl, &ctrl->queues[0], - NVME_AQ_BLK_MQ_DEPTH, - (NVME_AQ_BLK_MQ_DEPTH / 4)); + NVME_AQ_DEPTH, (NVME_AQ_DEPTH / 4)); if (ret) goto out_delete_hw_queue; @@ -2666,7 +2665,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) } ctrl->ctrl.sqsize = - min_t(int, NVME_CAP_MQES(ctrl->ctrl.cap) + 1, ctrl->ctrl.sqsize); + min_t(int, NVME_CAP_MQES(ctrl->ctrl.cap), ctrl->ctrl.sqsize); ret = nvme_enable_ctrl(&ctrl->ctrl, ctrl->ctrl.cap); if (ret) @@ -2699,6 +2698,14 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) opts->queue_size = ctrl->ctrl.maxcmd; } + if (opts->queue_size > ctrl->ctrl.sqsize + 1) { + /* warn if sqsize is lower than queue_size */ + dev_warn(ctrl->ctrl.device, + "queue_size %zu > ctrl sqsize %u, clamping down\n", + opts->queue_size, ctrl->ctrl.sqsize + 1); + opts->queue_size = ctrl->ctrl.sqsize + 1; + } + ret = nvme_fc_init_aen_ops(ctrl); if (ret) goto out_term_aen_ops; diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index b7e5c6db4d92..060f69e03427 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -210,25 +210,6 @@ void nvme_mpath_add_disk(struct nvme_ns_head *head) mutex_unlock(&head->subsys->lock); } -void nvme_mpath_add_disk_links(struct nvme_ns *ns) -{ - struct kobject *slave_disk_kobj, *holder_disk_kobj; - - if (!ns->head->disk) - return; - - slave_disk_kobj = &disk_to_dev(ns->disk)->kobj; - if (sysfs_create_link(ns->head->disk->slave_dir, slave_disk_kobj, - kobject_name(slave_disk_kobj))) - return; - - holder_disk_kobj = &disk_to_dev(ns->head->disk)->kobj; - if (sysfs_create_link(ns->disk->part0.holder_dir, holder_disk_kobj, - kobject_name(holder_disk_kobj))) - sysfs_remove_link(ns->head->disk->slave_dir, - kobject_name(slave_disk_kobj)); -} - void nvme_mpath_remove_disk(struct nvme_ns_head *head) { if (!head->disk) @@ -243,14 +224,3 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head) blk_cleanup_queue(head->disk->queue); put_disk(head->disk); } - -void nvme_mpath_remove_disk_links(struct nvme_ns *ns) -{ - if (!ns->head->disk) - return; - - sysfs_remove_link(ns->disk->part0.holder_dir, - kobject_name(&disk_to_dev(ns->head->disk)->kobj)); - sysfs_remove_link(ns->head->disk->slave_dir, - kobject_name(&disk_to_dev(ns->disk)->kobj)); -} diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 0521e4707d1c..d733b14ede9d 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -410,9 +410,7 @@ bool nvme_req_needs_failover(struct request *req, blk_status_t error); void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl); int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,struct nvme_ns_head *head); void nvme_mpath_add_disk(struct nvme_ns_head *head); -void nvme_mpath_add_disk_links(struct nvme_ns *ns); void nvme_mpath_remove_disk(struct nvme_ns_head *head); -void nvme_mpath_remove_disk_links(struct nvme_ns *ns); static inline void nvme_mpath_clear_current_path(struct nvme_ns *ns) { @@ -454,12 +452,6 @@ static inline void nvme_mpath_add_disk(struct nvme_ns_head *head) static inline void nvme_mpath_remove_disk(struct nvme_ns_head *head) { } -static inline void nvme_mpath_add_disk_links(struct nvme_ns *ns) -{ -} -static inline void nvme_mpath_remove_disk_links(struct nvme_ns *ns) -{ -} static inline void nvme_mpath_clear_current_path(struct nvme_ns *ns) { } diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 5933a5c732e8..b6f43b738f03 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1153,12 +1153,6 @@ static bool nvme_should_reset(struct nvme_dev *dev, u32 csts) if (!(csts & NVME_CSTS_CFS) && !nssro) return false; - /* If PCI error recovery process is happening, we cannot reset or - * the recovery mechanism will surely fail. - */ - if (pci_channel_offline(to_pci_dev(dev->dev))) - return false; - return true; } @@ -1189,6 +1183,13 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved) struct nvme_command cmd; u32 csts = readl(dev->bar + NVME_REG_CSTS); + /* If PCI error recovery process is happening, we cannot reset or + * the recovery mechanism will surely fail. + */ + mb(); + if (pci_channel_offline(to_pci_dev(dev->dev))) + return BLK_EH_RESET_TIMER; + /* * Reset immediately if the controller is failed */ @@ -1913,7 +1914,7 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) int result, nr_io_queues; unsigned long size; - nr_io_queues = num_present_cpus(); + nr_io_queues = num_possible_cpus(); result = nvme_set_queue_count(&dev->ctrl, &nr_io_queues); if (result < 0) return result; diff --git a/drivers/pci/dwc/pcie-designware-host.c b/drivers/pci/dwc/pcie-designware-host.c index 8de2d5c69b1d..dc9303abda42 100644 --- a/drivers/pci/dwc/pcie-designware-host.c +++ b/drivers/pci/dwc/pcie-designware-host.c @@ -613,7 +613,7 @@ void dw_pcie_setup_rc(struct pcie_port *pp) /* setup bus numbers */ val = dw_pcie_readl_dbi(pci, PCI_PRIMARY_BUS); val &= 0xff000000; - val |= 0x00010100; + val |= 0x00ff0100; dw_pcie_writel_dbi(pci, PCI_PRIMARY_BUS, val); /* setup command register */ diff --git a/drivers/pcmcia/cs.c b/drivers/pcmcia/cs.c index c3b615c94b4b..8c8caec3a72c 100644 --- a/drivers/pcmcia/cs.c +++ b/drivers/pcmcia/cs.c @@ -452,17 +452,20 @@ static int socket_insert(struct pcmcia_socket *skt) static int socket_suspend(struct pcmcia_socket *skt) { - if (skt->state & SOCKET_SUSPEND) + if ((skt->state & SOCKET_SUSPEND) && !(skt->state & SOCKET_IN_RESUME)) return -EBUSY; mutex_lock(&skt->ops_mutex); - skt->suspended_state = skt->state; + /* store state on first suspend, but not after spurious wakeups */ + if (!(skt->state & SOCKET_IN_RESUME)) + skt->suspended_state = skt->state; skt->socket = dead_socket; skt->ops->set_socket(skt, &skt->socket); if (skt->ops->suspend) skt->ops->suspend(skt); skt->state |= SOCKET_SUSPEND; + skt->state &= ~SOCKET_IN_RESUME; mutex_unlock(&skt->ops_mutex); return 0; } @@ -475,6 +478,7 @@ static int socket_early_resume(struct pcmcia_socket *skt) skt->ops->set_socket(skt, &skt->socket); if (skt->state & SOCKET_PRESENT) skt->resume_status = socket_setup(skt, resume_delay); + skt->state |= SOCKET_IN_RESUME; mutex_unlock(&skt->ops_mutex); return 0; } @@ -484,7 +488,7 @@ static int socket_late_resume(struct pcmcia_socket *skt) int ret = 0; mutex_lock(&skt->ops_mutex); - skt->state &= ~SOCKET_SUSPEND; + skt->state &= ~(SOCKET_SUSPEND | SOCKET_IN_RESUME); mutex_unlock(&skt->ops_mutex); if (!(skt->state & SOCKET_PRESENT)) { diff --git a/drivers/pcmcia/cs_internal.h b/drivers/pcmcia/cs_internal.h index 6765beadea95..03ec43802909 100644 --- a/drivers/pcmcia/cs_internal.h +++ b/drivers/pcmcia/cs_internal.h @@ -70,6 +70,7 @@ struct pccard_resource_ops { /* Flags in socket state */ #define SOCKET_PRESENT 0x0008 #define SOCKET_INUSE 0x0010 +#define SOCKET_IN_RESUME 0x0040 #define SOCKET_SUSPEND 0x0080 #define SOCKET_WIN_REQ(i) (0x0100<<(i)) #define SOCKET_CARDBUS 0x8000 diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c index 0c2ed11c0603..f63db346c219 100644 --- a/drivers/perf/arm_pmu.c +++ b/drivers/perf/arm_pmu.c @@ -638,7 +638,7 @@ static int arm_perf_teardown_cpu(unsigned int cpu, struct hlist_node *node) if (irq_is_percpu_devid(irq)) disable_percpu_irq(irq); else - disable_irq(irq); + disable_irq_nosync(irq); } per_cpu(cpu_armpmu, cpu) = NULL; diff --git a/drivers/platform/chrome/chromeos_laptop.c b/drivers/platform/chrome/chromeos_laptop.c index 6dec6ab13300..d8599736a41a 100644 --- a/drivers/platform/chrome/chromeos_laptop.c +++ b/drivers/platform/chrome/chromeos_laptop.c @@ -423,7 +423,7 @@ static int chromeos_laptop_probe(struct platform_device *pdev) return ret; } -static const struct chromeos_laptop samsung_series_5_550 = { +static struct chromeos_laptop samsung_series_5_550 = { .i2c_peripherals = { /* Touchpad. */ { .add = setup_cyapa_tp, I2C_ADAPTER_SMBUS }, @@ -432,14 +432,14 @@ static const struct chromeos_laptop samsung_series_5_550 = { }, }; -static const struct chromeos_laptop samsung_series_5 = { +static struct chromeos_laptop samsung_series_5 = { .i2c_peripherals = { /* Light Sensor. */ { .add = setup_tsl2583_als, I2C_ADAPTER_SMBUS }, }, }; -static const struct chromeos_laptop chromebook_pixel = { +static struct chromeos_laptop chromebook_pixel = { .i2c_peripherals = { /* Touch Screen. */ { .add = setup_atmel_1664s_ts, I2C_ADAPTER_PANEL }, @@ -450,14 +450,14 @@ static const struct chromeos_laptop chromebook_pixel = { }, }; -static const struct chromeos_laptop hp_chromebook_14 = { +static struct chromeos_laptop hp_chromebook_14 = { .i2c_peripherals = { /* Touchpad. */ { .add = setup_cyapa_tp, I2C_ADAPTER_DESIGNWARE_0 }, }, }; -static const struct chromeos_laptop dell_chromebook_11 = { +static struct chromeos_laptop dell_chromebook_11 = { .i2c_peripherals = { /* Touchpad. */ { .add = setup_cyapa_tp, I2C_ADAPTER_DESIGNWARE_0 }, @@ -466,28 +466,28 @@ static const struct chromeos_laptop dell_chromebook_11 = { }, }; -static const struct chromeos_laptop toshiba_cb35 = { +static struct chromeos_laptop toshiba_cb35 = { .i2c_peripherals = { /* Touchpad. */ { .add = setup_cyapa_tp, I2C_ADAPTER_DESIGNWARE_0 }, }, }; -static const struct chromeos_laptop acer_c7_chromebook = { +static struct chromeos_laptop acer_c7_chromebook = { .i2c_peripherals = { /* Touchpad. */ { .add = setup_cyapa_tp, I2C_ADAPTER_SMBUS }, }, }; -static const struct chromeos_laptop acer_ac700 = { +static struct chromeos_laptop acer_ac700 = { .i2c_peripherals = { /* Light Sensor. */ { .add = setup_tsl2563_als, I2C_ADAPTER_SMBUS }, }, }; -static const struct chromeos_laptop acer_c720 = { +static struct chromeos_laptop acer_c720 = { .i2c_peripherals = { /* Touchscreen. */ { .add = setup_atmel_1664s_ts, I2C_ADAPTER_DESIGNWARE_1 }, @@ -500,14 +500,14 @@ static const struct chromeos_laptop acer_c720 = { }, }; -static const struct chromeos_laptop hp_pavilion_14_chromebook = { +static struct chromeos_laptop hp_pavilion_14_chromebook = { .i2c_peripherals = { /* Touchpad. */ { .add = setup_cyapa_tp, I2C_ADAPTER_SMBUS }, }, }; -static const struct chromeos_laptop cr48 = { +static struct chromeos_laptop cr48 = { .i2c_peripherals = { /* Light Sensor. */ { .add = setup_tsl2563_als, I2C_ADAPTER_SMBUS }, diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index 9a8f96465cdc..d10ffe51da24 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -105,31 +105,44 @@ config ASUS_LAPTOP If you have an ACPI-compatible ASUS laptop, say Y or M here. +# +# If the DELL_SMBIOS_SMM feature is enabled, the DELL_SMBIOS driver +# becomes dependent on the DCDBAS driver. The "depends" line prevents a +# configuration where DELL_SMBIOS=y while DCDBAS=m. +# config DELL_SMBIOS - tristate + tristate "Dell SMBIOS driver" + depends on DCDBAS || DCDBAS=n + ---help--- + This provides support for the Dell SMBIOS calling interface. + If you have a Dell computer you should enable this option. + + Be sure to select at least one backend for it to work properly. config DELL_SMBIOS_WMI - tristate "Dell SMBIOS calling interface (WMI implementation)" + bool "Dell SMBIOS driver WMI backend" + default y depends on ACPI_WMI select DELL_WMI_DESCRIPTOR - select DELL_SMBIOS + depends on DELL_SMBIOS ---help--- This provides an implementation for the Dell SMBIOS calling interface communicated over ACPI-WMI. - If you have a Dell computer from >2007 you should say Y or M here. + If you have a Dell computer from >2007 you should say Y here. If you aren't sure and this module doesn't work for your computer it just won't load. config DELL_SMBIOS_SMM - tristate "Dell SMBIOS calling interface (SMM implementation)" + bool "Dell SMBIOS driver SMM backend" + default y depends on DCDBAS - select DELL_SMBIOS + depends on DELL_SMBIOS ---help--- This provides an implementation for the Dell SMBIOS calling interface communicated over SMI/SMM. - If you have a Dell computer from <=2017 you should say Y or M here. + If you have a Dell computer from <=2017 you should say Y here. If you aren't sure and this module doesn't work for your computer it just won't load. diff --git a/drivers/platform/x86/Makefile b/drivers/platform/x86/Makefile index c388608ad2a3..2ba6cb795338 100644 --- a/drivers/platform/x86/Makefile +++ b/drivers/platform/x86/Makefile @@ -13,8 +13,9 @@ obj-$(CONFIG_MSI_LAPTOP) += msi-laptop.o obj-$(CONFIG_ACPI_CMPC) += classmate-laptop.o obj-$(CONFIG_COMPAL_LAPTOP) += compal-laptop.o obj-$(CONFIG_DELL_SMBIOS) += dell-smbios.o -obj-$(CONFIG_DELL_SMBIOS_WMI) += dell-smbios-wmi.o -obj-$(CONFIG_DELL_SMBIOS_SMM) += dell-smbios-smm.o +dell-smbios-objs := dell-smbios-base.o +dell-smbios-$(CONFIG_DELL_SMBIOS_WMI) += dell-smbios-wmi.o +dell-smbios-$(CONFIG_DELL_SMBIOS_SMM) += dell-smbios-smm.o obj-$(CONFIG_DELL_LAPTOP) += dell-laptop.o obj-$(CONFIG_DELL_WMI) += dell-wmi.o obj-$(CONFIG_DELL_WMI_DESCRIPTOR) += dell-wmi-descriptor.o diff --git a/drivers/platform/x86/dell-smbios.c b/drivers/platform/x86/dell-smbios-base.c index 8541cde4cb7d..5bcf8a18f785 100644 --- a/drivers/platform/x86/dell-smbios.c +++ b/drivers/platform/x86/dell-smbios-base.c @@ -36,7 +36,7 @@ static DEFINE_MUTEX(smbios_mutex); struct smbios_device { struct list_head list; struct device *device; - int (*call_fn)(struct calling_interface_buffer *); + int (*call_fn)(struct calling_interface_buffer *arg); }; struct smbios_call { @@ -352,8 +352,10 @@ static void __init parse_da_table(const struct dmi_header *dm) struct calling_interface_structure *table = container_of(dm, struct calling_interface_structure, header); - /* 4 bytes of table header, plus 7 bytes of Dell header, plus at least - 6 bytes of entry */ + /* + * 4 bytes of table header, plus 7 bytes of Dell header + * plus at least 6 bytes of entry + */ if (dm->length < 17) return; @@ -554,7 +556,7 @@ static void free_group(struct platform_device *pdev) static int __init dell_smbios_init(void) { const struct dmi_device *valid; - int ret; + int ret, wmi, smm; valid = dmi_find_device(DMI_DEV_TYPE_OEM_STRING, "Dell System", NULL); if (!valid) { @@ -589,8 +591,24 @@ static int __init dell_smbios_init(void) if (ret) goto fail_create_group; + /* register backends */ + wmi = init_dell_smbios_wmi(); + if (wmi) + pr_debug("Failed to initialize WMI backend: %d\n", wmi); + smm = init_dell_smbios_smm(); + if (smm) + pr_debug("Failed to initialize SMM backend: %d\n", smm); + if (wmi && smm) { + pr_err("No SMBIOS backends available (wmi: %d, smm: %d)\n", + wmi, smm); + goto fail_sysfs; + } + return 0; +fail_sysfs: + free_group(platform_device); + fail_create_group: platform_device_del(platform_device); @@ -607,6 +625,8 @@ fail_platform_driver: static void __exit dell_smbios_exit(void) { + exit_dell_smbios_wmi(); + exit_dell_smbios_smm(); mutex_lock(&smbios_mutex); if (platform_device) { free_group(platform_device); @@ -623,5 +643,6 @@ module_exit(dell_smbios_exit); MODULE_AUTHOR("Matthew Garrett <mjg@redhat.com>"); MODULE_AUTHOR("Gabriele Mazzotta <gabriele.mzt@gmail.com>"); MODULE_AUTHOR("Pali Rohár <pali.rohar@gmail.com>"); +MODULE_AUTHOR("Mario Limonciello <mario.limonciello@dell.com>"); MODULE_DESCRIPTION("Common functions for kernel modules using Dell SMBIOS"); MODULE_LICENSE("GPL"); diff --git a/drivers/platform/x86/dell-smbios-smm.c b/drivers/platform/x86/dell-smbios-smm.c index 89f65c4651a0..e9e9da556318 100644 --- a/drivers/platform/x86/dell-smbios-smm.c +++ b/drivers/platform/x86/dell-smbios-smm.c @@ -58,7 +58,7 @@ static const struct dmi_system_id dell_device_table[] __initconst = { }; MODULE_DEVICE_TABLE(dmi, dell_device_table); -static void __init parse_da_table(const struct dmi_header *dm) +static void parse_da_table(const struct dmi_header *dm) { struct calling_interface_structure *table = container_of(dm, struct calling_interface_structure, header); @@ -73,7 +73,7 @@ static void __init parse_da_table(const struct dmi_header *dm) da_command_code = table->cmdIOCode; } -static void __init find_cmd_address(const struct dmi_header *dm, void *dummy) +static void find_cmd_address(const struct dmi_header *dm, void *dummy) { switch (dm->type) { case 0xda: /* Calling interface */ @@ -128,7 +128,7 @@ static bool test_wsmt_enabled(void) return false; } -static int __init dell_smbios_smm_init(void) +int init_dell_smbios_smm(void) { int ret; /* @@ -176,7 +176,7 @@ fail_platform_device_alloc: return ret; } -static void __exit dell_smbios_smm_exit(void) +void exit_dell_smbios_smm(void) { if (platform_device) { dell_smbios_unregister_device(&platform_device->dev); @@ -184,13 +184,3 @@ static void __exit dell_smbios_smm_exit(void) free_page((unsigned long)buffer); } } - -subsys_initcall(dell_smbios_smm_init); -module_exit(dell_smbios_smm_exit); - -MODULE_AUTHOR("Matthew Garrett <mjg@redhat.com>"); -MODULE_AUTHOR("Gabriele Mazzotta <gabriele.mzt@gmail.com>"); -MODULE_AUTHOR("Pali Rohár <pali.rohar@gmail.com>"); -MODULE_AUTHOR("Mario Limonciello <mario.limonciello@dell.com>"); -MODULE_DESCRIPTION("Dell SMBIOS communications over SMI"); -MODULE_LICENSE("GPL"); diff --git a/drivers/platform/x86/dell-smbios-wmi.c b/drivers/platform/x86/dell-smbios-wmi.c index 609557aa5868..fbefedb1c172 100644 --- a/drivers/platform/x86/dell-smbios-wmi.c +++ b/drivers/platform/x86/dell-smbios-wmi.c @@ -228,7 +228,7 @@ static const struct wmi_device_id dell_smbios_wmi_id_table[] = { { }, }; -static void __init parse_b1_table(const struct dmi_header *dm) +static void parse_b1_table(const struct dmi_header *dm) { struct misc_bios_flags_structure *flags = container_of(dm, struct misc_bios_flags_structure, header); @@ -242,7 +242,7 @@ static void __init parse_b1_table(const struct dmi_header *dm) wmi_supported = 1; } -static void __init find_b1(const struct dmi_header *dm, void *dummy) +static void find_b1(const struct dmi_header *dm, void *dummy) { switch (dm->type) { case 0xb1: /* misc bios flags */ @@ -261,7 +261,7 @@ static struct wmi_driver dell_smbios_wmi_driver = { .filter_callback = dell_smbios_wmi_filter, }; -static int __init init_dell_smbios_wmi(void) +int init_dell_smbios_wmi(void) { dmi_walk(find_b1, NULL); @@ -271,15 +271,9 @@ static int __init init_dell_smbios_wmi(void) return wmi_driver_register(&dell_smbios_wmi_driver); } -static void __exit exit_dell_smbios_wmi(void) +void exit_dell_smbios_wmi(void) { wmi_driver_unregister(&dell_smbios_wmi_driver); } -module_init(init_dell_smbios_wmi); -module_exit(exit_dell_smbios_wmi); - MODULE_ALIAS("wmi:" DELL_WMI_SMBIOS_GUID); -MODULE_AUTHOR("Mario Limonciello <mario.limonciello@dell.com>"); -MODULE_DESCRIPTION("Dell SMBIOS communications over WMI"); -MODULE_LICENSE("GPL"); diff --git a/drivers/platform/x86/dell-smbios.h b/drivers/platform/x86/dell-smbios.h index 138d478d9adc..d8adaf959740 100644 --- a/drivers/platform/x86/dell-smbios.h +++ b/drivers/platform/x86/dell-smbios.h @@ -75,4 +75,29 @@ int dell_laptop_register_notifier(struct notifier_block *nb); int dell_laptop_unregister_notifier(struct notifier_block *nb); void dell_laptop_call_notifier(unsigned long action, void *data); -#endif +/* for the supported backends */ +#ifdef CONFIG_DELL_SMBIOS_WMI +int init_dell_smbios_wmi(void); +void exit_dell_smbios_wmi(void); +#else /* CONFIG_DELL_SMBIOS_WMI */ +static inline int init_dell_smbios_wmi(void) +{ + return -ENODEV; +} +static inline void exit_dell_smbios_wmi(void) +{} +#endif /* CONFIG_DELL_SMBIOS_WMI */ + +#ifdef CONFIG_DELL_SMBIOS_SMM +int init_dell_smbios_smm(void); +void exit_dell_smbios_smm(void); +#else /* CONFIG_DELL_SMBIOS_SMM */ +static inline int init_dell_smbios_smm(void) +{ + return -ENODEV; +} +static inline void exit_dell_smbios_smm(void) +{} +#endif /* CONFIG_DELL_SMBIOS_SMM */ + +#endif /* _DELL_SMBIOS_H_ */ diff --git a/drivers/powercap/intel_rapl.c b/drivers/powercap/intel_rapl.c index 35636e1d8a3d..295d8dcba48c 100644 --- a/drivers/powercap/intel_rapl.c +++ b/drivers/powercap/intel_rapl.c @@ -1162,6 +1162,7 @@ static const struct x86_cpu_id rapl_ids[] __initconst = { RAPL_CPU(INTEL_FAM6_SKYLAKE_X, rapl_defaults_hsw_server), RAPL_CPU(INTEL_FAM6_KABYLAKE_MOBILE, rapl_defaults_core), RAPL_CPU(INTEL_FAM6_KABYLAKE_DESKTOP, rapl_defaults_core), + RAPL_CPU(INTEL_FAM6_CANNONLAKE_MOBILE, rapl_defaults_core), RAPL_CPU(INTEL_FAM6_ATOM_SILVERMONT1, rapl_defaults_byt), RAPL_CPU(INTEL_FAM6_ATOM_AIRMONT, rapl_defaults_cht), diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index dd4708c58480..1fc0c0811da4 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -4310,7 +4310,7 @@ static int _regulator_resume_early(struct device *dev, void *data) rstate = regulator_get_suspend_state(rdev, *state); if (rstate == NULL) - return -EINVAL; + return 0; mutex_lock(&rdev->mutex); diff --git a/drivers/regulator/stm32-vrefbuf.c b/drivers/regulator/stm32-vrefbuf.c index 72c8b3e1022b..e0a9c445ed67 100644 --- a/drivers/regulator/stm32-vrefbuf.c +++ b/drivers/regulator/stm32-vrefbuf.c @@ -51,7 +51,7 @@ static int stm32_vrefbuf_enable(struct regulator_dev *rdev) * arbitrary timeout. */ ret = readl_poll_timeout(priv->base + STM32_VREFBUF_CSR, val, - !(val & STM32_VRR), 650, 10000); + val & STM32_VRR, 650, 10000); if (ret) { dev_err(&rdev->dev, "stm32 vrefbuf timed out!\n"); val = readl_relaxed(priv->base + STM32_VREFBUF_CSR); diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index a7c15f0085e2..ecef8e73d40b 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -2581,8 +2581,6 @@ int dasd_cancel_req(struct dasd_ccw_req *cqr) case DASD_CQR_QUEUED: /* request was not started - just set to cleared */ cqr->status = DASD_CQR_CLEARED; - if (cqr->callback_data == DASD_SLEEPON_START_TAG) - cqr->callback_data = DASD_SLEEPON_END_TAG; break; case DASD_CQR_IN_IO: /* request in IO - terminate IO and release again */ @@ -3902,9 +3900,12 @@ static int dasd_generic_requeue_all_requests(struct dasd_device *device) wait_event(dasd_flush_wq, (cqr->status != DASD_CQR_CLEAR_PENDING)); - /* mark sleepon requests as ended */ - if (cqr->callback_data == DASD_SLEEPON_START_TAG) - cqr->callback_data = DASD_SLEEPON_END_TAG; + /* + * requeue requests to blocklayer will only work + * for block device requests + */ + if (_dasd_requeue_request(cqr)) + continue; /* remove requests from device and block queue */ list_del_init(&cqr->devlist); @@ -3917,13 +3918,6 @@ static int dasd_generic_requeue_all_requests(struct dasd_device *device) cqr = refers; } - /* - * requeue requests to blocklayer will only work - * for block device requests - */ - if (_dasd_requeue_request(cqr)) - continue; - if (cqr->block) list_del_init(&cqr->blocklist); cqr->block->base->discipline->free_cp( @@ -3940,8 +3934,7 @@ static int dasd_generic_requeue_all_requests(struct dasd_device *device) list_splice_tail(&requeue_queue, &device->ccw_queue); spin_unlock_irq(get_ccwdev_lock(device->cdev)); } - /* wake up generic waitqueue for eventually ended sleepon requests */ - wake_up(&generic_waitq); + dasd_schedule_device_bh(device); return rc; } diff --git a/drivers/s390/cio/device_fsm.c b/drivers/s390/cio/device_fsm.c index 1319122e9d12..9169af7dbb43 100644 --- a/drivers/s390/cio/device_fsm.c +++ b/drivers/s390/cio/device_fsm.c @@ -795,6 +795,7 @@ ccw_device_online_timeout(struct ccw_device *cdev, enum dev_event dev_event) ccw_device_set_timeout(cdev, 0); cdev->private->iretry = 255; + cdev->private->async_kill_io_rc = -ETIMEDOUT; ret = ccw_device_cancel_halt_clear(cdev); if (ret == -EBUSY) { ccw_device_set_timeout(cdev, 3*HZ); @@ -871,7 +872,7 @@ ccw_device_killing_irq(struct ccw_device *cdev, enum dev_event dev_event) /* OK, i/o is dead now. Call interrupt handler. */ if (cdev->handler) cdev->handler(cdev, cdev->private->intparm, - ERR_PTR(-EIO)); + ERR_PTR(cdev->private->async_kill_io_rc)); } static void @@ -888,14 +889,16 @@ ccw_device_killing_timeout(struct ccw_device *cdev, enum dev_event dev_event) ccw_device_online_verify(cdev, 0); if (cdev->handler) cdev->handler(cdev, cdev->private->intparm, - ERR_PTR(-EIO)); + ERR_PTR(cdev->private->async_kill_io_rc)); } void ccw_device_kill_io(struct ccw_device *cdev) { int ret; + ccw_device_set_timeout(cdev, 0); cdev->private->iretry = 255; + cdev->private->async_kill_io_rc = -EIO; ret = ccw_device_cancel_halt_clear(cdev); if (ret == -EBUSY) { ccw_device_set_timeout(cdev, 3*HZ); diff --git a/drivers/s390/cio/device_ops.c b/drivers/s390/cio/device_ops.c index 1caf6a398760..75ce12a24dc2 100644 --- a/drivers/s390/cio/device_ops.c +++ b/drivers/s390/cio/device_ops.c @@ -159,7 +159,7 @@ int ccw_device_clear(struct ccw_device *cdev, unsigned long intparm) } /** - * ccw_device_start_key() - start a s390 channel program with key + * ccw_device_start_timeout_key() - start a s390 channel program with timeout and key * @cdev: target ccw device * @cpa: logical start address of channel program * @intparm: user specific interruption parameter; will be presented back to @@ -170,10 +170,15 @@ int ccw_device_clear(struct ccw_device *cdev, unsigned long intparm) * @key: storage key to be used for the I/O * @flags: additional flags; defines the action to be performed for I/O * processing. + * @expires: timeout value in jiffies * * Start a S/390 channel program. When the interrupt arrives, the * IRQ handler is called, either immediately, delayed (dev-end missing, * or sense required) or never (no IRQ handler registered). + * This function notifies the device driver if the channel program has not + * completed during the time specified by @expires. If a timeout occurs, the + * channel program is terminated via xsch, hsch or csch, and the device's + * interrupt handler will be called with an irb containing ERR_PTR(-%ETIMEDOUT). * Returns: * %0, if the operation was successful; * -%EBUSY, if the device is busy, or status pending; @@ -182,9 +187,9 @@ int ccw_device_clear(struct ccw_device *cdev, unsigned long intparm) * Context: * Interrupts disabled, ccw device lock held */ -int ccw_device_start_key(struct ccw_device *cdev, struct ccw1 *cpa, - unsigned long intparm, __u8 lpm, __u8 key, - unsigned long flags) +int ccw_device_start_timeout_key(struct ccw_device *cdev, struct ccw1 *cpa, + unsigned long intparm, __u8 lpm, __u8 key, + unsigned long flags, int expires) { struct subchannel *sch; int ret; @@ -224,6 +229,8 @@ int ccw_device_start_key(struct ccw_device *cdev, struct ccw1 *cpa, switch (ret) { case 0: cdev->private->intparm = intparm; + if (expires) + ccw_device_set_timeout(cdev, expires); break; case -EACCES: case -ENODEV: @@ -234,7 +241,7 @@ int ccw_device_start_key(struct ccw_device *cdev, struct ccw1 *cpa, } /** - * ccw_device_start_timeout_key() - start a s390 channel program with timeout and key + * ccw_device_start_key() - start a s390 channel program with key * @cdev: target ccw device * @cpa: logical start address of channel program * @intparm: user specific interruption parameter; will be presented back to @@ -245,15 +252,10 @@ int ccw_device_start_key(struct ccw_device *cdev, struct ccw1 *cpa, * @key: storage key to be used for the I/O * @flags: additional flags; defines the action to be performed for I/O * processing. - * @expires: timeout value in jiffies * * Start a S/390 channel program. When the interrupt arrives, the * IRQ handler is called, either immediately, delayed (dev-end missing, * or sense required) or never (no IRQ handler registered). - * This function notifies the device driver if the channel program has not - * completed during the time specified by @expires. If a timeout occurs, the - * channel program is terminated via xsch, hsch or csch, and the device's - * interrupt handler will be called with an irb containing ERR_PTR(-%ETIMEDOUT). * Returns: * %0, if the operation was successful; * -%EBUSY, if the device is busy, or status pending; @@ -262,19 +264,12 @@ int ccw_device_start_key(struct ccw_device *cdev, struct ccw1 *cpa, * Context: * Interrupts disabled, ccw device lock held */ -int ccw_device_start_timeout_key(struct ccw_device *cdev, struct ccw1 *cpa, - unsigned long intparm, __u8 lpm, __u8 key, - unsigned long flags, int expires) +int ccw_device_start_key(struct ccw_device *cdev, struct ccw1 *cpa, + unsigned long intparm, __u8 lpm, __u8 key, + unsigned long flags) { - int ret; - - if (!cdev) - return -ENODEV; - ccw_device_set_timeout(cdev, expires); - ret = ccw_device_start_key(cdev, cpa, intparm, lpm, key, flags); - if (ret != 0) - ccw_device_set_timeout(cdev, 0); - return ret; + return ccw_device_start_timeout_key(cdev, cpa, intparm, lpm, key, + flags, 0); } /** @@ -489,18 +484,20 @@ void ccw_device_get_id(struct ccw_device *cdev, struct ccw_dev_id *dev_id) EXPORT_SYMBOL(ccw_device_get_id); /** - * ccw_device_tm_start_key() - perform start function + * ccw_device_tm_start_timeout_key() - perform start function * @cdev: ccw device on which to perform the start function * @tcw: transport-command word to be started * @intparm: user defined parameter to be passed to the interrupt handler * @lpm: mask of paths to use * @key: storage key to use for storage access + * @expires: time span in jiffies after which to abort request * * Start the tcw on the given ccw device. Return zero on success, non-zero * otherwise. */ -int ccw_device_tm_start_key(struct ccw_device *cdev, struct tcw *tcw, - unsigned long intparm, u8 lpm, u8 key) +int ccw_device_tm_start_timeout_key(struct ccw_device *cdev, struct tcw *tcw, + unsigned long intparm, u8 lpm, u8 key, + int expires) { struct subchannel *sch; int rc; @@ -527,37 +524,32 @@ int ccw_device_tm_start_key(struct ccw_device *cdev, struct tcw *tcw, return -EACCES; } rc = cio_tm_start_key(sch, tcw, lpm, key); - if (rc == 0) + if (rc == 0) { cdev->private->intparm = intparm; + if (expires) + ccw_device_set_timeout(cdev, expires); + } return rc; } -EXPORT_SYMBOL(ccw_device_tm_start_key); +EXPORT_SYMBOL(ccw_device_tm_start_timeout_key); /** - * ccw_device_tm_start_timeout_key() - perform start function + * ccw_device_tm_start_key() - perform start function * @cdev: ccw device on which to perform the start function * @tcw: transport-command word to be started * @intparm: user defined parameter to be passed to the interrupt handler * @lpm: mask of paths to use * @key: storage key to use for storage access - * @expires: time span in jiffies after which to abort request * * Start the tcw on the given ccw device. Return zero on success, non-zero * otherwise. */ -int ccw_device_tm_start_timeout_key(struct ccw_device *cdev, struct tcw *tcw, - unsigned long intparm, u8 lpm, u8 key, - int expires) +int ccw_device_tm_start_key(struct ccw_device *cdev, struct tcw *tcw, + unsigned long intparm, u8 lpm, u8 key) { - int ret; - - ccw_device_set_timeout(cdev, expires); - ret = ccw_device_tm_start_key(cdev, tcw, intparm, lpm, key); - if (ret != 0) - ccw_device_set_timeout(cdev, 0); - return ret; + return ccw_device_tm_start_timeout_key(cdev, tcw, intparm, lpm, key, 0); } -EXPORT_SYMBOL(ccw_device_tm_start_timeout_key); +EXPORT_SYMBOL(ccw_device_tm_start_key); /** * ccw_device_tm_start() - perform start function diff --git a/drivers/s390/cio/io_sch.h b/drivers/s390/cio/io_sch.h index af571d8d6925..90e4e3a7841b 100644 --- a/drivers/s390/cio/io_sch.h +++ b/drivers/s390/cio/io_sch.h @@ -157,6 +157,7 @@ struct ccw_device_private { unsigned long intparm; /* user interruption parameter */ struct qdio_irq *qdio_data; struct irb irb; /* device status */ + int async_kill_io_rc; struct senseid senseid; /* SenseID info */ struct pgid pgid[8]; /* path group IDs per chpid*/ struct ccw1 iccws[2]; /* ccws for SNID/SID/SPGID commands */ diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index ca72f3311004..c8b308cfabf1 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -2134,24 +2134,25 @@ int qeth_send_control_data(struct qeth_card *card, int len, } reply->callback = reply_cb; reply->param = reply_param; - if (card->state == CARD_STATE_DOWN) - reply->seqno = QETH_IDX_COMMAND_SEQNO; - else - reply->seqno = card->seqno.ipa++; + init_waitqueue_head(&reply->wait_q); - spin_lock_irqsave(&card->lock, flags); - list_add_tail(&reply->list, &card->cmd_waiter_list); - spin_unlock_irqrestore(&card->lock, flags); while (atomic_cmpxchg(&card->write.irq_pending, 0, 1)) ; - qeth_prepare_control_data(card, len, iob); if (IS_IPA(iob->data)) { cmd = __ipa_cmd(iob); + cmd->hdr.seqno = card->seqno.ipa++; + reply->seqno = cmd->hdr.seqno; event_timeout = QETH_IPA_TIMEOUT; } else { + reply->seqno = QETH_IDX_COMMAND_SEQNO; event_timeout = QETH_TIMEOUT; } + qeth_prepare_control_data(card, len, iob); + + spin_lock_irqsave(&card->lock, flags); + list_add_tail(&reply->list, &card->cmd_waiter_list); + spin_unlock_irqrestore(&card->lock, flags); timeout = jiffies + event_timeout; @@ -2933,7 +2934,7 @@ static void qeth_fill_ipacmd_header(struct qeth_card *card, memset(cmd, 0, sizeof(struct qeth_ipa_cmd)); cmd->hdr.command = command; cmd->hdr.initiator = IPA_CMD_INITIATOR_HOST; - cmd->hdr.seqno = card->seqno.ipa; + /* cmd->hdr.seqno is set by qeth_send_control_data() */ cmd->hdr.adapter_type = qeth_get_ipa_adp_type(card->info.link_type); cmd->hdr.rel_adapter_no = (__u8) card->info.portno; if (card->options.layer2) @@ -3898,10 +3899,12 @@ EXPORT_SYMBOL_GPL(qeth_get_elements_for_frags); int qeth_get_elements_no(struct qeth_card *card, struct sk_buff *skb, int extra_elems, int data_offset) { - int elements = qeth_get_elements_for_range( - (addr_t)skb->data + data_offset, - (addr_t)skb->data + skb_headlen(skb)) + - qeth_get_elements_for_frags(skb); + addr_t end = (addr_t)skb->data + skb_headlen(skb); + int elements = qeth_get_elements_for_frags(skb); + addr_t start = (addr_t)skb->data + data_offset; + + if (start != end) + elements += qeth_get_elements_for_range(start, end); if ((elements + extra_elems) > QETH_MAX_BUFFER_ELEMENTS(card)) { QETH_DBF_MESSAGE(2, "Invalid size of IP packet " diff --git a/drivers/s390/net/qeth_l3.h b/drivers/s390/net/qeth_l3.h index bdd45f4dcace..498fe9af2cdb 100644 --- a/drivers/s390/net/qeth_l3.h +++ b/drivers/s390/net/qeth_l3.h @@ -40,8 +40,40 @@ struct qeth_ipaddr { unsigned int pfxlen; } a6; } u; - }; + +static inline bool qeth_l3_addr_match_ip(struct qeth_ipaddr *a1, + struct qeth_ipaddr *a2) +{ + if (a1->proto != a2->proto) + return false; + if (a1->proto == QETH_PROT_IPV6) + return ipv6_addr_equal(&a1->u.a6.addr, &a2->u.a6.addr); + return a1->u.a4.addr == a2->u.a4.addr; +} + +static inline bool qeth_l3_addr_match_all(struct qeth_ipaddr *a1, + struct qeth_ipaddr *a2) +{ + /* Assumes that the pair was obtained via qeth_l3_addr_find_by_ip(), + * so 'proto' and 'addr' match for sure. + * + * For ucast: + * - 'mac' is always 0. + * - 'mask'/'pfxlen' for RXIP/VIPA is always 0. For NORMAL, matching + * values are required to avoid mixups in takeover eligibility. + * + * For mcast, + * - 'mac' is mapped from the IP, and thus always matches. + * - 'mask'/'pfxlen' is always 0. + */ + if (a1->type != a2->type) + return false; + if (a1->proto == QETH_PROT_IPV6) + return a1->u.a6.pfxlen == a2->u.a6.pfxlen; + return a1->u.a4.mask == a2->u.a4.mask; +} + static inline u64 qeth_l3_ipaddr_hash(struct qeth_ipaddr *addr) { u64 ret = 0; diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index b0c888e86cd4..962a04b68dd2 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -67,6 +67,24 @@ void qeth_l3_ipaddr_to_string(enum qeth_prot_versions proto, const __u8 *addr, qeth_l3_ipaddr6_to_string(addr, buf); } +static struct qeth_ipaddr *qeth_l3_find_addr_by_ip(struct qeth_card *card, + struct qeth_ipaddr *query) +{ + u64 key = qeth_l3_ipaddr_hash(query); + struct qeth_ipaddr *addr; + + if (query->is_multicast) { + hash_for_each_possible(card->ip_mc_htable, addr, hnode, key) + if (qeth_l3_addr_match_ip(addr, query)) + return addr; + } else { + hash_for_each_possible(card->ip_htable, addr, hnode, key) + if (qeth_l3_addr_match_ip(addr, query)) + return addr; + } + return NULL; +} + static void qeth_l3_convert_addr_to_bits(u8 *addr, u8 *bits, int len) { int i, j; @@ -120,34 +138,6 @@ static bool qeth_l3_is_addr_covered_by_ipato(struct qeth_card *card, return rc; } -inline int -qeth_l3_ipaddrs_is_equal(struct qeth_ipaddr *addr1, struct qeth_ipaddr *addr2) -{ - return addr1->proto == addr2->proto && - !memcmp(&addr1->u, &addr2->u, sizeof(addr1->u)) && - ether_addr_equal_64bits(addr1->mac, addr2->mac); -} - -static struct qeth_ipaddr * -qeth_l3_ip_from_hash(struct qeth_card *card, struct qeth_ipaddr *tmp_addr) -{ - struct qeth_ipaddr *addr; - - if (tmp_addr->is_multicast) { - hash_for_each_possible(card->ip_mc_htable, addr, - hnode, qeth_l3_ipaddr_hash(tmp_addr)) - if (qeth_l3_ipaddrs_is_equal(tmp_addr, addr)) - return addr; - } else { - hash_for_each_possible(card->ip_htable, addr, - hnode, qeth_l3_ipaddr_hash(tmp_addr)) - if (qeth_l3_ipaddrs_is_equal(tmp_addr, addr)) - return addr; - } - - return NULL; -} - int qeth_l3_delete_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr) { int rc = 0; @@ -162,23 +152,18 @@ int qeth_l3_delete_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr) QETH_CARD_HEX(card, 4, ((char *)&tmp_addr->u.a6.addr) + 8, 8); } - addr = qeth_l3_ip_from_hash(card, tmp_addr); - if (!addr) + addr = qeth_l3_find_addr_by_ip(card, tmp_addr); + if (!addr || !qeth_l3_addr_match_all(addr, tmp_addr)) return -ENOENT; addr->ref_counter--; - if (addr->ref_counter > 0 && (addr->type == QETH_IP_TYPE_NORMAL || - addr->type == QETH_IP_TYPE_RXIP)) + if (addr->type == QETH_IP_TYPE_NORMAL && addr->ref_counter > 0) return rc; if (addr->in_progress) return -EINPROGRESS; - if (!qeth_card_hw_is_reachable(card)) { - addr->disp_flag = QETH_DISP_ADDR_DELETE; - return 0; - } - - rc = qeth_l3_deregister_addr_entry(card, addr); + if (qeth_card_hw_is_reachable(card)) + rc = qeth_l3_deregister_addr_entry(card, addr); hash_del(&addr->hnode); kfree(addr); @@ -190,6 +175,7 @@ int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr) { int rc = 0; struct qeth_ipaddr *addr; + char buf[40]; QETH_CARD_TEXT(card, 4, "addip"); @@ -200,8 +186,20 @@ int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr) QETH_CARD_HEX(card, 4, ((char *)&tmp_addr->u.a6.addr) + 8, 8); } - addr = qeth_l3_ip_from_hash(card, tmp_addr); - if (!addr) { + addr = qeth_l3_find_addr_by_ip(card, tmp_addr); + if (addr) { + if (tmp_addr->type != QETH_IP_TYPE_NORMAL) + return -EADDRINUSE; + if (qeth_l3_addr_match_all(addr, tmp_addr)) { + addr->ref_counter++; + return 0; + } + qeth_l3_ipaddr_to_string(tmp_addr->proto, (u8 *)&tmp_addr->u, + buf); + dev_warn(&card->gdev->dev, + "Registering IP address %s failed\n", buf); + return -EADDRINUSE; + } else { addr = qeth_l3_get_addr_buffer(tmp_addr->proto); if (!addr) return -ENOMEM; @@ -241,19 +239,15 @@ int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr) (rc == IPA_RC_LAN_OFFLINE)) { addr->disp_flag = QETH_DISP_ADDR_DO_NOTHING; if (addr->ref_counter < 1) { - qeth_l3_delete_ip(card, addr); + qeth_l3_deregister_addr_entry(card, addr); + hash_del(&addr->hnode); kfree(addr); } } else { hash_del(&addr->hnode); kfree(addr); } - } else { - if (addr->type == QETH_IP_TYPE_NORMAL || - addr->type == QETH_IP_TYPE_RXIP) - addr->ref_counter++; } - return rc; } @@ -321,11 +315,7 @@ static void qeth_l3_recover_ip(struct qeth_card *card) spin_lock_bh(&card->ip_lock); hash_for_each_safe(card->ip_htable, i, tmp, addr, hnode) { - if (addr->disp_flag == QETH_DISP_ADDR_DELETE) { - qeth_l3_deregister_addr_entry(card, addr); - hash_del(&addr->hnode); - kfree(addr); - } else if (addr->disp_flag == QETH_DISP_ADDR_ADD) { + if (addr->disp_flag == QETH_DISP_ADDR_ADD) { if (addr->proto == QETH_PROT_IPV4) { addr->in_progress = 1; spin_unlock_bh(&card->ip_lock); @@ -643,12 +633,7 @@ int qeth_l3_add_vipa(struct qeth_card *card, enum qeth_prot_versions proto, return -ENOMEM; spin_lock_bh(&card->ip_lock); - - if (qeth_l3_ip_from_hash(card, ipaddr)) - rc = -EEXIST; - else - rc = qeth_l3_add_ip(card, ipaddr); - + rc = qeth_l3_add_ip(card, ipaddr); spin_unlock_bh(&card->ip_lock); kfree(ipaddr); @@ -713,12 +698,7 @@ int qeth_l3_add_rxip(struct qeth_card *card, enum qeth_prot_versions proto, return -ENOMEM; spin_lock_bh(&card->ip_lock); - - if (qeth_l3_ip_from_hash(card, ipaddr)) - rc = -EEXIST; - else - rc = qeth_l3_add_ip(card, ipaddr); - + rc = qeth_l3_add_ip(card, ipaddr); spin_unlock_bh(&card->ip_lock); kfree(ipaddr); @@ -1239,8 +1219,9 @@ qeth_l3_add_mc_to_hash(struct qeth_card *card, struct in_device *in4_dev) tmp->u.a4.addr = be32_to_cpu(im4->multiaddr); tmp->is_multicast = 1; - ipm = qeth_l3_ip_from_hash(card, tmp); + ipm = qeth_l3_find_addr_by_ip(card, tmp); if (ipm) { + /* for mcast, by-IP match means full match */ ipm->disp_flag = QETH_DISP_ADDR_DO_NOTHING; } else { ipm = qeth_l3_get_addr_buffer(QETH_PROT_IPV4); @@ -1319,8 +1300,9 @@ static void qeth_l3_add_mc6_to_hash(struct qeth_card *card, sizeof(struct in6_addr)); tmp->is_multicast = 1; - ipm = qeth_l3_ip_from_hash(card, tmp); + ipm = qeth_l3_find_addr_by_ip(card, tmp); if (ipm) { + /* for mcast, by-IP match means full match */ ipm->disp_flag = QETH_DISP_ADDR_DO_NOTHING; continue; } @@ -2450,11 +2432,12 @@ static void qeth_tso_fill_header(struct qeth_card *card, static int qeth_l3_get_elements_no_tso(struct qeth_card *card, struct sk_buff *skb, int extra_elems) { - addr_t tcpdptr = (addr_t)tcp_hdr(skb) + tcp_hdrlen(skb); - int elements = qeth_get_elements_for_range( - tcpdptr, - (addr_t)skb->data + skb_headlen(skb)) + - qeth_get_elements_for_frags(skb); + addr_t start = (addr_t)tcp_hdr(skb) + tcp_hdrlen(skb); + addr_t end = (addr_t)skb->data + skb_headlen(skb); + int elements = qeth_get_elements_for_frags(skb); + + if (start != end) + elements += qeth_get_elements_for_range(start, end); if ((elements + extra_elems) > QETH_MAX_BUFFER_ELEMENTS(card)) { QETH_DBF_MESSAGE(2, diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c index 57bf43e34863..dd9464920456 100644 --- a/drivers/scsi/hosts.c +++ b/drivers/scsi/hosts.c @@ -328,8 +328,6 @@ static void scsi_host_dev_release(struct device *dev) if (shost->work_q) destroy_workqueue(shost->work_q); - destroy_rcu_head(&shost->rcu); - if (shost->shost_state == SHOST_CREATED) { /* * Free the shost_dev device name here if scsi_host_alloc() @@ -404,7 +402,6 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize) INIT_LIST_HEAD(&shost->starved_list); init_waitqueue_head(&shost->host_wait); mutex_init(&shost->scan_mutex); - init_rcu_head(&shost->rcu); index = ida_simple_get(&host_index_ida, 0, 0, GFP_KERNEL); if (index < 0) diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c index 073ced07e662..dc8e850fbfd2 100644 --- a/drivers/scsi/megaraid/megaraid_sas_fusion.c +++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c @@ -216,36 +216,30 @@ inline void megasas_return_cmd_fusion(struct megasas_instance *instance, /** * megasas_fire_cmd_fusion - Sends command to the FW * @instance: Adapter soft state - * @req_desc: 32bit or 64bit Request descriptor + * @req_desc: 64bit Request descriptor * - * Perform PCI Write. Ventura supports 32 bit Descriptor. - * Prior to Ventura (12G) MR controller supports 64 bit Descriptor. + * Perform PCI Write. */ static void megasas_fire_cmd_fusion(struct megasas_instance *instance, union MEGASAS_REQUEST_DESCRIPTOR_UNION *req_desc) { - if (instance->adapter_type == VENTURA_SERIES) - writel(le32_to_cpu(req_desc->u.low), - &instance->reg_set->inbound_single_queue_port); - else { #if defined(writeq) && defined(CONFIG_64BIT) - u64 req_data = (((u64)le32_to_cpu(req_desc->u.high) << 32) | - le32_to_cpu(req_desc->u.low)); + u64 req_data = (((u64)le32_to_cpu(req_desc->u.high) << 32) | + le32_to_cpu(req_desc->u.low)); - writeq(req_data, &instance->reg_set->inbound_low_queue_port); + writeq(req_data, &instance->reg_set->inbound_low_queue_port); #else - unsigned long flags; - spin_lock_irqsave(&instance->hba_lock, flags); - writel(le32_to_cpu(req_desc->u.low), - &instance->reg_set->inbound_low_queue_port); - writel(le32_to_cpu(req_desc->u.high), - &instance->reg_set->inbound_high_queue_port); - mmiowb(); - spin_unlock_irqrestore(&instance->hba_lock, flags); + unsigned long flags; + spin_lock_irqsave(&instance->hba_lock, flags); + writel(le32_to_cpu(req_desc->u.low), + &instance->reg_set->inbound_low_queue_port); + writel(le32_to_cpu(req_desc->u.high), + &instance->reg_set->inbound_high_queue_port); + mmiowb(); + spin_unlock_irqrestore(&instance->hba_lock, flags); #endif - } } /** @@ -982,7 +976,6 @@ megasas_ioc_init_fusion(struct megasas_instance *instance) const char *sys_info; MFI_CAPABILITIES *drv_ops; u32 scratch_pad_2; - unsigned long flags; ktime_t time; bool cur_fw_64bit_dma_capable; @@ -1121,14 +1114,7 @@ megasas_ioc_init_fusion(struct megasas_instance *instance) break; } - /* For Ventura also IOC INIT required 64 bit Descriptor write. */ - spin_lock_irqsave(&instance->hba_lock, flags); - writel(le32_to_cpu(req_desc.u.low), - &instance->reg_set->inbound_low_queue_port); - writel(le32_to_cpu(req_desc.u.high), - &instance->reg_set->inbound_high_queue_port); - mmiowb(); - spin_unlock_irqrestore(&instance->hba_lock, flags); + megasas_fire_cmd_fusion(instance, &req_desc); wait_and_poll(instance, cmd, MFI_POLL_TIMEOUT_SECS); diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 59a87ca328d3..0aafbfd1b746 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -6297,14 +6297,14 @@ _base_reset_handler(struct MPT3SAS_ADAPTER *ioc, int reset_phase) } /** - * _wait_for_commands_to_complete - reset controller + * mpt3sas_wait_for_commands_to_complete - reset controller * @ioc: Pointer to MPT_ADAPTER structure * * This function is waiting 10s for all pending commands to complete * prior to putting controller in reset. */ -static void -_wait_for_commands_to_complete(struct MPT3SAS_ADAPTER *ioc) +void +mpt3sas_wait_for_commands_to_complete(struct MPT3SAS_ADAPTER *ioc) { u32 ioc_state; @@ -6377,7 +6377,7 @@ mpt3sas_base_hard_reset_handler(struct MPT3SAS_ADAPTER *ioc, is_fault = 1; } _base_reset_handler(ioc, MPT3_IOC_PRE_RESET); - _wait_for_commands_to_complete(ioc); + mpt3sas_wait_for_commands_to_complete(ioc); _base_mask_interrupts(ioc); r = _base_make_ioc_ready(ioc, type); if (r) diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h index 789bc421424b..99ccf83b8c51 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.h +++ b/drivers/scsi/mpt3sas/mpt3sas_base.h @@ -1433,6 +1433,9 @@ void mpt3sas_base_update_missing_delay(struct MPT3SAS_ADAPTER *ioc, int mpt3sas_port_enable(struct MPT3SAS_ADAPTER *ioc); +void +mpt3sas_wait_for_commands_to_complete(struct MPT3SAS_ADAPTER *ioc); + /* scsih shared API */ struct scsi_cmnd *mpt3sas_scsih_scsi_lookup_get(struct MPT3SAS_ADAPTER *ioc, diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index 74fca184dba9..c2ea13c7e37e 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -2835,7 +2835,8 @@ scsih_abort(struct scsi_cmnd *scmd) _scsih_tm_display_info(ioc, scmd); sas_device_priv_data = scmd->device->hostdata; - if (!sas_device_priv_data || !sas_device_priv_data->sas_target) { + if (!sas_device_priv_data || !sas_device_priv_data->sas_target || + ioc->remove_host) { sdev_printk(KERN_INFO, scmd->device, "device been deleted! scmd(%p)\n", scmd); scmd->result = DID_NO_CONNECT << 16; @@ -2898,7 +2899,8 @@ scsih_dev_reset(struct scsi_cmnd *scmd) _scsih_tm_display_info(ioc, scmd); sas_device_priv_data = scmd->device->hostdata; - if (!sas_device_priv_data || !sas_device_priv_data->sas_target) { + if (!sas_device_priv_data || !sas_device_priv_data->sas_target || + ioc->remove_host) { sdev_printk(KERN_INFO, scmd->device, "device been deleted! scmd(%p)\n", scmd); scmd->result = DID_NO_CONNECT << 16; @@ -2961,7 +2963,8 @@ scsih_target_reset(struct scsi_cmnd *scmd) _scsih_tm_display_info(ioc, scmd); sas_device_priv_data = scmd->device->hostdata; - if (!sas_device_priv_data || !sas_device_priv_data->sas_target) { + if (!sas_device_priv_data || !sas_device_priv_data->sas_target || + ioc->remove_host) { starget_printk(KERN_INFO, starget, "target been deleted! scmd(%p)\n", scmd); scmd->result = DID_NO_CONNECT << 16; @@ -3019,7 +3022,7 @@ scsih_host_reset(struct scsi_cmnd *scmd) ioc->name, scmd); scsi_print_command(scmd); - if (ioc->is_driver_loading) { + if (ioc->is_driver_loading || ioc->remove_host) { pr_info(MPT3SAS_FMT "Blocking the host reset\n", ioc->name); r = FAILED; @@ -4453,7 +4456,7 @@ _scsih_flush_running_cmds(struct MPT3SAS_ADAPTER *ioc) st = scsi_cmd_priv(scmd); mpt3sas_base_clear_st(ioc, st); scsi_dma_unmap(scmd); - if (ioc->pci_error_recovery) + if (ioc->pci_error_recovery || ioc->remove_host) scmd->result = DID_NO_CONNECT << 16; else scmd->result = DID_RESET << 16; @@ -9739,6 +9742,10 @@ static void scsih_remove(struct pci_dev *pdev) unsigned long flags; ioc->remove_host = 1; + + mpt3sas_wait_for_commands_to_complete(ioc); + _scsih_flush_running_cmds(ioc); + _scsih_fw_event_cleanup_queue(ioc); spin_lock_irqsave(&ioc->fw_event_lock, flags); @@ -9815,6 +9822,10 @@ scsih_shutdown(struct pci_dev *pdev) unsigned long flags; ioc->remove_host = 1; + + mpt3sas_wait_for_commands_to_complete(ioc); + _scsih_flush_running_cmds(ioc); + _scsih_fw_event_cleanup_queue(ioc); spin_lock_irqsave(&ioc->fw_event_lock, flags); diff --git a/drivers/scsi/qedi/qedi_fw.c b/drivers/scsi/qedi/qedi_fw.c index 667d7697ba01..d09afe1b567d 100644 --- a/drivers/scsi/qedi/qedi_fw.c +++ b/drivers/scsi/qedi/qedi_fw.c @@ -762,6 +762,11 @@ static void qedi_process_cmd_cleanup_resp(struct qedi_ctx *qedi, iscsi_cid = cqe->conn_id; qedi_conn = qedi->cid_que.conn_cid_tbl[iscsi_cid]; + if (!qedi_conn) { + QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO, + "icid not found 0x%x\n", cqe->conn_id); + return; + } /* Based on this itt get the corresponding qedi_cmd */ spin_lock_bh(&qedi_conn->tmf_work_lock); diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index be7d6824581a..c9689f97c307 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -261,9 +261,9 @@ struct name_list_extended { struct get_name_list_extended *l; dma_addr_t ldma; - struct list_head fcports; /* protect by sess_list */ + struct list_head fcports; + spinlock_t fcports_lock; u32 size; - u8 sent; }; /* * Timeout timer counts in seconds @@ -2217,6 +2217,7 @@ typedef struct { /* FCP-4 types */ #define FC4_TYPE_FCP_SCSI 0x08 +#define FC4_TYPE_NVME 0x28 #define FC4_TYPE_OTHER 0x0 #define FC4_TYPE_UNKNOWN 0xff diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c index 5bf9a59432f6..403fa096f8c8 100644 --- a/drivers/scsi/qla2xxx/qla_gs.c +++ b/drivers/scsi/qla2xxx/qla_gs.c @@ -3179,6 +3179,7 @@ done_free_sp: sp->free(sp); fcport->flags &= ~FCF_ASYNC_SENT; done: + fcport->flags &= ~FCF_ASYNC_ACTIVE; return rval; } @@ -3370,6 +3371,7 @@ done_free_sp: sp->free(sp); fcport->flags &= ~FCF_ASYNC_SENT; done: + fcport->flags &= ~FCF_ASYNC_ACTIVE; return rval; } @@ -3971,6 +3973,9 @@ out: spin_lock_irqsave(&vha->work_lock, flags); vha->scan.scan_flags &= ~SF_SCANNING; spin_unlock_irqrestore(&vha->work_lock, flags); + + if ((fc4type == FC4_TYPE_FCP_SCSI) && vha->flags.nvme_enabled) + qla24xx_async_gpnft(vha, FC4_TYPE_NVME); } static void qla2x00_async_gpnft_gnnft_sp_done(void *s, int res) diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 2dea1129d396..00329dda6179 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -213,6 +213,7 @@ done_free_sp: sp->free(sp); fcport->flags &= ~FCF_ASYNC_SENT; done: + fcport->flags &= ~FCF_ASYNC_ACTIVE; return rval; } @@ -263,7 +264,7 @@ qla2x00_async_logout(struct scsi_qla_host *vha, fc_port_t *fcport) done_free_sp: sp->free(sp); done: - fcport->flags &= ~FCF_ASYNC_SENT; + fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE); return rval; } @@ -271,6 +272,7 @@ void qla2x00_async_prlo_done(struct scsi_qla_host *vha, fc_port_t *fcport, uint16_t *data) { + fcport->flags &= ~FCF_ASYNC_ACTIVE; /* Don't re-login in target mode */ if (!fcport->tgt_session) qla2x00_mark_device_lost(vha, fcport, 1, 0); @@ -284,6 +286,7 @@ qla2x00_async_prlo_sp_done(void *s, int res) struct srb_iocb *lio = &sp->u.iocb_cmd; struct scsi_qla_host *vha = sp->vha; + sp->fcport->flags &= ~FCF_ASYNC_ACTIVE; if (!test_bit(UNLOADING, &vha->dpc_flags)) qla2x00_post_async_prlo_done_work(sp->fcport->vha, sp->fcport, lio->u.logio.data); @@ -322,6 +325,7 @@ qla2x00_async_prlo(struct scsi_qla_host *vha, fc_port_t *fcport) done_free_sp: sp->free(sp); done: + fcport->flags &= ~FCF_ASYNC_ACTIVE; return rval; } @@ -375,6 +379,8 @@ qla2x00_async_adisc_sp_done(void *ptr, int res) "Async done-%s res %x %8phC\n", sp->name, res, sp->fcport->port_name); + sp->fcport->flags &= ~FCF_ASYNC_SENT; + memset(&ea, 0, sizeof(ea)); ea.event = FCME_ADISC_DONE; ea.rc = res; @@ -425,7 +431,7 @@ qla2x00_async_adisc(struct scsi_qla_host *vha, fc_port_t *fcport, done_free_sp: sp->free(sp); done: - fcport->flags &= ~FCF_ASYNC_SENT; + fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE); qla2x00_post_async_adisc_work(vha, fcport, data); return rval; } @@ -643,8 +649,7 @@ qla24xx_async_gnl_sp_done(void *s, int res) (loop_id & 0x7fff)); } - spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags); - vha->gnl.sent = 0; + spin_lock_irqsave(&vha->gnl.fcports_lock, flags); INIT_LIST_HEAD(&h); fcport = tf = NULL; @@ -653,12 +658,16 @@ qla24xx_async_gnl_sp_done(void *s, int res) list_for_each_entry_safe(fcport, tf, &h, gnl_entry) { list_del_init(&fcport->gnl_entry); + spin_lock(&vha->hw->tgt.sess_lock); fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE); + spin_unlock(&vha->hw->tgt.sess_lock); ea.fcport = fcport; qla2x00_fcport_event_handler(vha, &ea); } + spin_unlock_irqrestore(&vha->gnl.fcports_lock, flags); + spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags); /* create new fcport if fw has knowledge of new sessions */ for (i = 0; i < n; i++) { port_id_t id; @@ -710,18 +719,21 @@ int qla24xx_async_gnl(struct scsi_qla_host *vha, fc_port_t *fcport) ql_dbg(ql_dbg_disc, vha, 0x20d9, "Async-gnlist WWPN %8phC \n", fcport->port_name); - spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags); + spin_lock_irqsave(&vha->gnl.fcports_lock, flags); + if (!list_empty(&fcport->gnl_entry)) { + spin_unlock_irqrestore(&vha->gnl.fcports_lock, flags); + rval = QLA_SUCCESS; + goto done; + } + + spin_lock(&vha->hw->tgt.sess_lock); fcport->disc_state = DSC_GNL; fcport->last_rscn_gen = fcport->rscn_gen; fcport->last_login_gen = fcport->login_gen; + spin_unlock(&vha->hw->tgt.sess_lock); list_add_tail(&fcport->gnl_entry, &vha->gnl.fcports); - if (vha->gnl.sent) { - spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags); - return QLA_SUCCESS; - } - vha->gnl.sent = 1; - spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags); + spin_unlock_irqrestore(&vha->gnl.fcports_lock, flags); sp = qla2x00_get_sp(vha, fcport, GFP_KERNEL); if (!sp) @@ -1049,6 +1061,7 @@ void qla24xx_handle_gpdb_event(scsi_qla_host_t *vha, struct event_arg *ea) fc_port_t *fcport = ea->fcport; struct port_database_24xx *pd; struct srb *sp = ea->sp; + uint8_t ls; pd = (struct port_database_24xx *)sp->u.iocb_cmd.u.mbx.in; @@ -1061,7 +1074,12 @@ void qla24xx_handle_gpdb_event(scsi_qla_host_t *vha, struct event_arg *ea) if (fcport->disc_state == DSC_DELETE_PEND) return; - switch (pd->current_login_state) { + if (fcport->fc4f_nvme) + ls = pd->current_login_state >> 4; + else + ls = pd->current_login_state & 0xf; + + switch (ls) { case PDS_PRLI_COMPLETE: __qla24xx_parse_gpdb(vha, fcport, pd); break; @@ -1151,8 +1169,9 @@ int qla24xx_fcport_handle_login(struct scsi_qla_host *vha, fc_port_t *fcport) if (fcport->scan_state != QLA_FCPORT_FOUND) return 0; - if ((fcport->fw_login_state == DSC_LS_PLOGI_PEND) || - (fcport->fw_login_state == DSC_LS_PRLI_PEND)) + if ((fcport->loop_id != FC_NO_LOOP_ID) && + ((fcport->fw_login_state == DSC_LS_PLOGI_PEND) || + (fcport->fw_login_state == DSC_LS_PRLI_PEND))) return 0; if (fcport->fw_login_state == DSC_LS_PLOGI_COMP) { @@ -1527,6 +1546,7 @@ qla24xx_abort_sp_done(void *ptr, int res) srb_t *sp = ptr; struct srb_iocb *abt = &sp->u.iocb_cmd; + del_timer(&sp->u.iocb_cmd.timer); complete(&abt->u.abt.comp); } @@ -1791,6 +1811,7 @@ qla2x00_async_logout_done(struct scsi_qla_host *vha, fc_port_t *fcport, qla2x00_mark_device_lost(vha, fcport, 1, 0); qlt_logo_completion_handler(fcport, data[0]); fcport->login_gen++; + fcport->flags &= ~FCF_ASYNC_ACTIVE; return; } @@ -1798,6 +1819,7 @@ void qla2x00_async_adisc_done(struct scsi_qla_host *vha, fc_port_t *fcport, uint16_t *data) { + fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE); if (data[0] == MBS_COMMAND_COMPLETE) { qla2x00_update_fcport(vha, fcport); @@ -1805,7 +1827,6 @@ qla2x00_async_adisc_done(struct scsi_qla_host *vha, fc_port_t *fcport, } /* Retry login. */ - fcport->flags &= ~FCF_ASYNC_SENT; if (data[1] & QLA_LOGIO_LOGIN_RETRIED) set_bit(RELOGIN_NEEDED, &vha->dpc_flags); else diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index afcb5567998a..285911e81728 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -4577,6 +4577,7 @@ struct scsi_qla_host *qla2x00_create_host(struct scsi_host_template *sht, spin_lock_init(&vha->work_lock); spin_lock_init(&vha->cmd_list_lock); + spin_lock_init(&vha->gnl.fcports_lock); init_waitqueue_head(&vha->fcport_waitQ); init_waitqueue_head(&vha->vref_waitq); @@ -4806,9 +4807,12 @@ void qla24xx_create_new_sess(struct scsi_qla_host *vha, struct qla_work_evt *e) fcport->d_id = e->u.new_sess.id; fcport->flags |= FCF_FABRIC_DEVICE; fcport->fw_login_state = DSC_LS_PLOGI_PEND; - if (e->u.new_sess.fc4_type == FC4_TYPE_FCP_SCSI) + if (e->u.new_sess.fc4_type == FC4_TYPE_FCP_SCSI) { fcport->fc4_type = FC4_TYPE_FCP_SCSI; - + } else if (e->u.new_sess.fc4_type == FC4_TYPE_NVME) { + fcport->fc4_type = FC4_TYPE_OTHER; + fcport->fc4f_nvme = FC4_TYPE_NVME; + } memcpy(fcport->port_name, e->u.new_sess.port_name, WWN_SIZE); } else { @@ -4877,6 +4881,8 @@ void qla24xx_create_new_sess(struct scsi_qla_host *vha, struct qla_work_evt *e) } qlt_plogi_ack_unref(vha, pla); } else { + fc_port_t *dfcp = NULL; + spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags); tfcp = qla2x00_find_fcport_by_nportid(vha, &e->u.new_sess.id, 1); @@ -4899,11 +4905,13 @@ void qla24xx_create_new_sess(struct scsi_qla_host *vha, struct qla_work_evt *e) default: fcport->login_pause = 1; tfcp->conflict = fcport; - qlt_schedule_sess_for_deletion(tfcp); + dfcp = tfcp; break; } } spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags); + if (dfcp) + qlt_schedule_sess_for_deletion(tfcp); wwn = wwn_to_u64(fcport->node_name); diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 896b2d8bd803..b49ac85f3de2 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -1224,10 +1224,10 @@ static void qla24xx_chk_fcp_state(struct fc_port *sess) } } -/* ha->tgt.sess_lock supposed to be held on entry */ void qlt_schedule_sess_for_deletion(struct fc_port *sess) { struct qla_tgt *tgt = sess->tgt; + struct qla_hw_data *ha = sess->vha->hw; unsigned long flags; if (sess->disc_state == DSC_DELETE_PEND) @@ -1244,16 +1244,16 @@ void qlt_schedule_sess_for_deletion(struct fc_port *sess) return; } + spin_lock_irqsave(&ha->tgt.sess_lock, flags); if (sess->deleted == QLA_SESS_DELETED) sess->logout_on_delete = 0; - spin_lock_irqsave(&sess->vha->work_lock, flags); if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) { - spin_unlock_irqrestore(&sess->vha->work_lock, flags); + spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); return; } sess->deleted = QLA_SESS_DELETION_IN_PROGRESS; - spin_unlock_irqrestore(&sess->vha->work_lock, flags); + spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); sess->disc_state = DSC_DELETE_PEND; @@ -1262,13 +1262,10 @@ void qlt_schedule_sess_for_deletion(struct fc_port *sess) ql_dbg(ql_dbg_tgt, sess->vha, 0xe001, "Scheduling sess %p for deletion\n", sess); - /* use cancel to push work element through before re-queue */ - cancel_work_sync(&sess->del_work); INIT_WORK(&sess->del_work, qla24xx_delete_sess_fn); - queue_work(sess->vha->hw->wq, &sess->del_work); + WARN_ON(!queue_work(sess->vha->hw->wq, &sess->del_work)); } -/* ha->tgt.sess_lock supposed to be held on entry */ static void qlt_clear_tgt_db(struct qla_tgt *tgt) { struct fc_port *sess; @@ -1451,8 +1448,8 @@ qlt_fc_port_deleted(struct scsi_qla_host *vha, fc_port_t *fcport, int max_gen) ql_dbg(ql_dbg_tgt_mgt, vha, 0xf008, "qla_tgt_fc_port_deleted %p", sess); sess->local = 1; - qlt_schedule_sess_for_deletion(sess); spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags); + qlt_schedule_sess_for_deletion(sess); } static inline int test_tgt_sess_count(struct qla_tgt *tgt) @@ -1512,10 +1509,8 @@ int qlt_stop_phase1(struct qla_tgt *tgt) * Lock is needed, because we still can get an incoming packet. */ mutex_lock(&vha->vha_tgt.tgt_mutex); - spin_lock_irqsave(&ha->tgt.sess_lock, flags); tgt->tgt_stop = 1; qlt_clear_tgt_db(tgt); - spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); mutex_unlock(&vha->vha_tgt.tgt_mutex); mutex_unlock(&qla_tgt_mutex); diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index d042915ce895..ca53a5f785ee 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -223,7 +223,8 @@ static void scsi_eh_reset(struct scsi_cmnd *scmd) static void scsi_eh_inc_host_failed(struct rcu_head *head) { - struct Scsi_Host *shost = container_of(head, typeof(*shost), rcu); + struct scsi_cmnd *scmd = container_of(head, typeof(*scmd), rcu); + struct Scsi_Host *shost = scmd->device->host; unsigned long flags; spin_lock_irqsave(shost->host_lock, flags); @@ -259,7 +260,7 @@ void scsi_eh_scmd_add(struct scsi_cmnd *scmd) * Ensure that all tasks observe the host state change before the * host_failed change. */ - call_rcu(&shost->rcu, scsi_eh_inc_host_failed); + call_rcu(&scmd->rcu, scsi_eh_inc_host_failed); } /** diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index a86df9ca7d1c..c84f931388f2 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -671,6 +671,7 @@ static bool scsi_end_request(struct request *req, blk_status_t error, if (!blk_rq_is_scsi(req)) { WARN_ON_ONCE(!(cmd->flags & SCMD_INITIALIZED)); cmd->flags &= ~SCMD_INITIALIZED; + destroy_rcu_head(&cmd->rcu); } if (req->mq_ctx) { @@ -720,6 +721,8 @@ static blk_status_t __scsi_error_from_host_byte(struct scsi_cmnd *cmd, int result) { switch (host_byte(result)) { + case DID_OK: + return BLK_STS_OK; case DID_TRANSPORT_FAILFAST: return BLK_STS_TRANSPORT; case DID_TARGET_FAILURE: @@ -1151,6 +1154,7 @@ static void scsi_initialize_rq(struct request *rq) struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq); scsi_req_init(&cmd->req); + init_rcu_head(&cmd->rcu); cmd->jiffies_at_alloc = jiffies; cmd->retries = 0; } diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 6be5ab32c94f..8c51d628b52e 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1311,7 +1311,8 @@ static int storvsc_do_io(struct hv_device *device, */ cpumask_and(&alloced_mask, &stor_device->alloced_cpus, cpumask_of_node(cpu_to_node(q_num))); - for_each_cpu(tgt_cpu, &alloced_mask) { + for_each_cpu_wrap(tgt_cpu, &alloced_mask, + outgoing_channel->target_cpu + 1) { if (tgt_cpu != outgoing_channel->target_cpu) { outgoing_channel = stor_device->stor_chns[tgt_cpu]; diff --git a/drivers/video/fbdev/sbuslib.c b/drivers/video/fbdev/sbuslib.c index af6fc97f4ba4..a436d44f1b7f 100644 --- a/drivers/video/fbdev/sbuslib.c +++ b/drivers/video/fbdev/sbuslib.c @@ -122,7 +122,7 @@ int sbusfb_ioctl_helper(unsigned long cmd, unsigned long arg, unsigned char __user *ured; unsigned char __user *ugreen; unsigned char __user *ublue; - int index, count, i; + unsigned int index, count, i; if (get_user(index, &c->index) || __get_user(count, &c->count) || @@ -161,7 +161,7 @@ int sbusfb_ioctl_helper(unsigned long cmd, unsigned long arg, unsigned char __user *ugreen; unsigned char __user *ublue; struct fb_cmap *cmap = &info->cmap; - int index, count, i; + unsigned int index, count, i; u8 red, green, blue; if (get_user(index, &c->index) || diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index eb30f3e09a47..71458f493cf8 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -428,8 +428,6 @@ unmap_release: i = virtio16_to_cpu(_vq->vdev, vq->vring.desc[i].next); } - vq->vq.num_free += total_sg; - if (indirect) kfree(desc); diff --git a/drivers/watchdog/f71808e_wdt.c b/drivers/watchdog/f71808e_wdt.c index e0678c14480f..3a33c5344bd5 100644 --- a/drivers/watchdog/f71808e_wdt.c +++ b/drivers/watchdog/f71808e_wdt.c @@ -566,7 +566,8 @@ static ssize_t watchdog_write(struct file *file, const char __user *buf, char c; if (get_user(c, buf + i)) return -EFAULT; - expect_close = (c == 'V'); + if (c == 'V') + expect_close = true; } /* Properly order writes across fork()ed processes */ diff --git a/drivers/watchdog/hpwdt.c b/drivers/watchdog/hpwdt.c index f1f00dfc0e68..b0a158073abd 100644 --- a/drivers/watchdog/hpwdt.c +++ b/drivers/watchdog/hpwdt.c @@ -28,16 +28,7 @@ #include <linux/types.h> #include <linux/uaccess.h> #include <linux/watchdog.h> -#ifdef CONFIG_HPWDT_NMI_DECODING -#include <linux/dmi.h> -#include <linux/spinlock.h> -#include <linux/nmi.h> -#include <linux/kdebug.h> -#include <linux/notifier.h> -#include <asm/set_memory.h> -#endif /* CONFIG_HPWDT_NMI_DECODING */ #include <asm/nmi.h> -#include <asm/frame.h> #define HPWDT_VERSION "1.4.0" #define SECS_TO_TICKS(secs) ((secs) * 1000 / 128) @@ -48,6 +39,9 @@ static unsigned int soft_margin = DEFAULT_MARGIN; /* in seconds */ static unsigned int reload; /* the computed soft_margin */ static bool nowayout = WATCHDOG_NOWAYOUT; +#ifdef CONFIG_HPWDT_NMI_DECODING +static unsigned int allow_kdump = 1; +#endif static char expect_release; static unsigned long hpwdt_is_open; @@ -63,373 +57,6 @@ static const struct pci_device_id hpwdt_devices[] = { }; MODULE_DEVICE_TABLE(pci, hpwdt_devices); -#ifdef CONFIG_HPWDT_NMI_DECODING -#define PCI_BIOS32_SD_VALUE 0x5F32335F /* "_32_" */ -#define CRU_BIOS_SIGNATURE_VALUE 0x55524324 -#define PCI_BIOS32_PARAGRAPH_LEN 16 -#define PCI_ROM_BASE1 0x000F0000 -#define ROM_SIZE 0x10000 - -struct bios32_service_dir { - u32 signature; - u32 entry_point; - u8 revision; - u8 length; - u8 checksum; - u8 reserved[5]; -}; - -/* type 212 */ -struct smbios_cru64_info { - u8 type; - u8 byte_length; - u16 handle; - u32 signature; - u64 physical_address; - u32 double_length; - u32 double_offset; -}; -#define SMBIOS_CRU64_INFORMATION 212 - -/* type 219 */ -struct smbios_proliant_info { - u8 type; - u8 byte_length; - u16 handle; - u32 power_features; - u32 omega_features; - u32 reserved; - u32 misc_features; -}; -#define SMBIOS_ICRU_INFORMATION 219 - - -struct cmn_registers { - union { - struct { - u8 ral; - u8 rah; - u16 rea2; - }; - u32 reax; - } u1; - union { - struct { - u8 rbl; - u8 rbh; - u8 reb2l; - u8 reb2h; - }; - u32 rebx; - } u2; - union { - struct { - u8 rcl; - u8 rch; - u16 rec2; - }; - u32 recx; - } u3; - union { - struct { - u8 rdl; - u8 rdh; - u16 red2; - }; - u32 redx; - } u4; - - u32 resi; - u32 redi; - u16 rds; - u16 res; - u32 reflags; -} __attribute__((packed)); - -static unsigned int hpwdt_nmi_decoding; -static unsigned int allow_kdump = 1; -static unsigned int is_icru; -static unsigned int is_uefi; -static DEFINE_SPINLOCK(rom_lock); -static void *cru_rom_addr; -static struct cmn_registers cmn_regs; - -extern asmlinkage void asminline_call(struct cmn_registers *pi86Regs, - unsigned long *pRomEntry); - -#ifdef CONFIG_X86_32 -/* --32 Bit Bios------------------------------------------------------------ */ - -#define HPWDT_ARCH 32 - -asm(".text \n\t" - ".align 4 \n\t" - ".globl asminline_call \n" - "asminline_call: \n\t" - "pushl %ebp \n\t" - "movl %esp, %ebp \n\t" - "pusha \n\t" - "pushf \n\t" - "push %es \n\t" - "push %ds \n\t" - "pop %es \n\t" - "movl 8(%ebp),%eax \n\t" - "movl 4(%eax),%ebx \n\t" - "movl 8(%eax),%ecx \n\t" - "movl 12(%eax),%edx \n\t" - "movl 16(%eax),%esi \n\t" - "movl 20(%eax),%edi \n\t" - "movl (%eax),%eax \n\t" - "push %cs \n\t" - "call *12(%ebp) \n\t" - "pushf \n\t" - "pushl %eax \n\t" - "movl 8(%ebp),%eax \n\t" - "movl %ebx,4(%eax) \n\t" - "movl %ecx,8(%eax) \n\t" - "movl %edx,12(%eax) \n\t" - "movl %esi,16(%eax) \n\t" - "movl %edi,20(%eax) \n\t" - "movw %ds,24(%eax) \n\t" - "movw %es,26(%eax) \n\t" - "popl %ebx \n\t" - "movl %ebx,(%eax) \n\t" - "popl %ebx \n\t" - "movl %ebx,28(%eax) \n\t" - "pop %es \n\t" - "popf \n\t" - "popa \n\t" - "leave \n\t" - "ret \n\t" - ".previous"); - - -/* - * cru_detect - * - * Routine Description: - * This function uses the 32-bit BIOS Service Directory record to - * search for a $CRU record. - * - * Return Value: - * 0 : SUCCESS - * <0 : FAILURE - */ -static int cru_detect(unsigned long map_entry, - unsigned long map_offset) -{ - void *bios32_map; - unsigned long *bios32_entrypoint; - unsigned long cru_physical_address; - unsigned long cru_length; - unsigned long physical_bios_base = 0; - unsigned long physical_bios_offset = 0; - int retval = -ENODEV; - - bios32_map = ioremap(map_entry, (2 * PAGE_SIZE)); - - if (bios32_map == NULL) - return -ENODEV; - - bios32_entrypoint = bios32_map + map_offset; - - cmn_regs.u1.reax = CRU_BIOS_SIGNATURE_VALUE; - - set_memory_x((unsigned long)bios32_map, 2); - asminline_call(&cmn_regs, bios32_entrypoint); - - if (cmn_regs.u1.ral != 0) { - pr_warn("Call succeeded but with an error: 0x%x\n", - cmn_regs.u1.ral); - } else { - physical_bios_base = cmn_regs.u2.rebx; - physical_bios_offset = cmn_regs.u4.redx; - cru_length = cmn_regs.u3.recx; - cru_physical_address = - physical_bios_base + physical_bios_offset; - - /* If the values look OK, then map it in. */ - if ((physical_bios_base + physical_bios_offset)) { - cru_rom_addr = - ioremap(cru_physical_address, cru_length); - if (cru_rom_addr) { - set_memory_x((unsigned long)cru_rom_addr & PAGE_MASK, - (cru_length + PAGE_SIZE - 1) >> PAGE_SHIFT); - retval = 0; - } - } - - pr_debug("CRU Base Address: 0x%lx\n", physical_bios_base); - pr_debug("CRU Offset Address: 0x%lx\n", physical_bios_offset); - pr_debug("CRU Length: 0x%lx\n", cru_length); - pr_debug("CRU Mapped Address: %p\n", &cru_rom_addr); - } - iounmap(bios32_map); - return retval; -} - -/* - * bios_checksum - */ -static int bios_checksum(const char __iomem *ptr, int len) -{ - char sum = 0; - int i; - - /* - * calculate checksum of size bytes. This should add up - * to zero if we have a valid header. - */ - for (i = 0; i < len; i++) - sum += ptr[i]; - - return ((sum == 0) && (len > 0)); -} - -/* - * bios32_present - * - * Routine Description: - * This function finds the 32-bit BIOS Service Directory - * - * Return Value: - * 0 : SUCCESS - * <0 : FAILURE - */ -static int bios32_present(const char __iomem *p) -{ - struct bios32_service_dir *bios_32_ptr; - int length; - unsigned long map_entry, map_offset; - - bios_32_ptr = (struct bios32_service_dir *) p; - - /* - * Search for signature by checking equal to the swizzled value - * instead of calling another routine to perform a strcmp. - */ - if (bios_32_ptr->signature == PCI_BIOS32_SD_VALUE) { - length = bios_32_ptr->length * PCI_BIOS32_PARAGRAPH_LEN; - if (bios_checksum(p, length)) { - /* - * According to the spec, we're looking for the - * first 4KB-aligned address below the entrypoint - * listed in the header. The Service Directory code - * is guaranteed to occupy no more than 2 4KB pages. - */ - map_entry = bios_32_ptr->entry_point & ~(PAGE_SIZE - 1); - map_offset = bios_32_ptr->entry_point - map_entry; - - return cru_detect(map_entry, map_offset); - } - } - return -ENODEV; -} - -static int detect_cru_service(void) -{ - char __iomem *p, *q; - int rc = -1; - - /* - * Search from 0x0f0000 through 0x0fffff, inclusive. - */ - p = ioremap(PCI_ROM_BASE1, ROM_SIZE); - if (p == NULL) - return -ENOMEM; - - for (q = p; q < p + ROM_SIZE; q += 16) { - rc = bios32_present(q); - if (!rc) - break; - } - iounmap(p); - return rc; -} -/* ------------------------------------------------------------------------- */ -#endif /* CONFIG_X86_32 */ -#ifdef CONFIG_X86_64 -/* --64 Bit Bios------------------------------------------------------------ */ - -#define HPWDT_ARCH 64 - -asm(".text \n\t" - ".align 4 \n\t" - ".globl asminline_call \n\t" - ".type asminline_call, @function \n\t" - "asminline_call: \n\t" - FRAME_BEGIN - "pushq %rax \n\t" - "pushq %rbx \n\t" - "pushq %rdx \n\t" - "pushq %r12 \n\t" - "pushq %r9 \n\t" - "movq %rsi, %r12 \n\t" - "movq %rdi, %r9 \n\t" - "movl 4(%r9),%ebx \n\t" - "movl 8(%r9),%ecx \n\t" - "movl 12(%r9),%edx \n\t" - "movl 16(%r9),%esi \n\t" - "movl 20(%r9),%edi \n\t" - "movl (%r9),%eax \n\t" - "call *%r12 \n\t" - "pushfq \n\t" - "popq %r12 \n\t" - "movl %eax, (%r9) \n\t" - "movl %ebx, 4(%r9) \n\t" - "movl %ecx, 8(%r9) \n\t" - "movl %edx, 12(%r9) \n\t" - "movl %esi, 16(%r9) \n\t" - "movl %edi, 20(%r9) \n\t" - "movq %r12, %rax \n\t" - "movl %eax, 28(%r9) \n\t" - "popq %r9 \n\t" - "popq %r12 \n\t" - "popq %rdx \n\t" - "popq %rbx \n\t" - "popq %rax \n\t" - FRAME_END - "ret \n\t" - ".previous"); - -/* - * dmi_find_cru - * - * Routine Description: - * This function checks whether or not a SMBIOS/DMI record is - * the 64bit CRU info or not - */ -static void dmi_find_cru(const struct dmi_header *dm, void *dummy) -{ - struct smbios_cru64_info *smbios_cru64_ptr; - unsigned long cru_physical_address; - - if (dm->type == SMBIOS_CRU64_INFORMATION) { - smbios_cru64_ptr = (struct smbios_cru64_info *) dm; - if (smbios_cru64_ptr->signature == CRU_BIOS_SIGNATURE_VALUE) { - cru_physical_address = - smbios_cru64_ptr->physical_address + - smbios_cru64_ptr->double_offset; - cru_rom_addr = ioremap(cru_physical_address, - smbios_cru64_ptr->double_length); - set_memory_x((unsigned long)cru_rom_addr & PAGE_MASK, - smbios_cru64_ptr->double_length >> PAGE_SHIFT); - } - } -} - -static int detect_cru_service(void) -{ - cru_rom_addr = NULL; - - dmi_walk(dmi_find_cru, NULL); - - /* if cru_rom_addr has been set then we found a CRU service */ - return ((cru_rom_addr != NULL) ? 0 : -ENODEV); -} -/* ------------------------------------------------------------------------- */ -#endif /* CONFIG_X86_64 */ -#endif /* CONFIG_HPWDT_NMI_DECODING */ /* * Watchdog operations @@ -486,30 +113,12 @@ static int hpwdt_my_nmi(void) */ static int hpwdt_pretimeout(unsigned int ulReason, struct pt_regs *regs) { - unsigned long rom_pl; - static int die_nmi_called; - - if (!hpwdt_nmi_decoding) - return NMI_DONE; - if ((ulReason == NMI_UNKNOWN) && !hpwdt_my_nmi()) return NMI_DONE; - spin_lock_irqsave(&rom_lock, rom_pl); - if (!die_nmi_called && !is_icru && !is_uefi) - asminline_call(&cmn_regs, cru_rom_addr); - die_nmi_called = 1; - spin_unlock_irqrestore(&rom_lock, rom_pl); - if (allow_kdump) hpwdt_stop(); - if (!is_icru && !is_uefi) { - if (cmn_regs.u1.ral == 0) { - nmi_panic(regs, "An NMI occurred, but unable to determine source.\n"); - return NMI_HANDLED; - } - } nmi_panic(regs, "An NMI occurred. Depending on your system the reason " "for the NMI is logged in any one of the following " "resources:\n" @@ -675,84 +284,11 @@ static struct miscdevice hpwdt_miscdev = { * Init & Exit */ -#ifdef CONFIG_HPWDT_NMI_DECODING -#ifdef CONFIG_X86_LOCAL_APIC -static void hpwdt_check_nmi_decoding(struct pci_dev *dev) -{ - /* - * If nmi_watchdog is turned off then we can turn on - * our nmi decoding capability. - */ - hpwdt_nmi_decoding = 1; -} -#else -static void hpwdt_check_nmi_decoding(struct pci_dev *dev) -{ - dev_warn(&dev->dev, "NMI decoding is disabled. " - "Your kernel does not support a NMI Watchdog.\n"); -} -#endif /* CONFIG_X86_LOCAL_APIC */ - -/* - * dmi_find_icru - * - * Routine Description: - * This function checks whether or not we are on an iCRU-based server. - * This check is independent of architecture and needs to be made for - * any ProLiant system. - */ -static void dmi_find_icru(const struct dmi_header *dm, void *dummy) -{ - struct smbios_proliant_info *smbios_proliant_ptr; - - if (dm->type == SMBIOS_ICRU_INFORMATION) { - smbios_proliant_ptr = (struct smbios_proliant_info *) dm; - if (smbios_proliant_ptr->misc_features & 0x01) - is_icru = 1; - if (smbios_proliant_ptr->misc_features & 0x1400) - is_uefi = 1; - } -} static int hpwdt_init_nmi_decoding(struct pci_dev *dev) { +#ifdef CONFIG_HPWDT_NMI_DECODING int retval; - - /* - * On typical CRU-based systems we need to map that service in - * the BIOS. For 32 bit Operating Systems we need to go through - * the 32 Bit BIOS Service Directory. For 64 bit Operating - * Systems we get that service through SMBIOS. - * - * On systems that support the new iCRU service all we need to - * do is call dmi_walk to get the supported flag value and skip - * the old cru detect code. - */ - dmi_walk(dmi_find_icru, NULL); - if (!is_icru && !is_uefi) { - - /* - * We need to map the ROM to get the CRU service. - * For 32 bit Operating Systems we need to go through the 32 Bit - * BIOS Service Directory - * For 64 bit Operating Systems we get that service through SMBIOS. - */ - retval = detect_cru_service(); - if (retval < 0) { - dev_warn(&dev->dev, - "Unable to detect the %d Bit CRU Service.\n", - HPWDT_ARCH); - return retval; - } - - /* - * We know this is the only CRU call we need to make so lets keep as - * few instructions as possible once the NMI comes in. - */ - cmn_regs.u1.rah = 0x0D; - cmn_regs.u1.ral = 0x02; - } - /* * Only one function can register for NMI_UNKNOWN */ @@ -780,45 +316,26 @@ error: dev_warn(&dev->dev, "Unable to register a die notifier (err=%d).\n", retval); - if (cru_rom_addr) - iounmap(cru_rom_addr); return retval; +#endif /* CONFIG_HPWDT_NMI_DECODING */ + return 0; } static void hpwdt_exit_nmi_decoding(void) { +#ifdef CONFIG_HPWDT_NMI_DECODING unregister_nmi_handler(NMI_UNKNOWN, "hpwdt"); unregister_nmi_handler(NMI_SERR, "hpwdt"); unregister_nmi_handler(NMI_IO_CHECK, "hpwdt"); - if (cru_rom_addr) - iounmap(cru_rom_addr); -} -#else /* !CONFIG_HPWDT_NMI_DECODING */ -static void hpwdt_check_nmi_decoding(struct pci_dev *dev) -{ -} - -static int hpwdt_init_nmi_decoding(struct pci_dev *dev) -{ - return 0; +#endif } -static void hpwdt_exit_nmi_decoding(void) -{ -} -#endif /* CONFIG_HPWDT_NMI_DECODING */ - static int hpwdt_init_one(struct pci_dev *dev, const struct pci_device_id *ent) { int retval; /* - * Check if we can do NMI decoding or not - */ - hpwdt_check_nmi_decoding(dev); - - /* * First let's find out if we are on an iLO2+ server. We will * not run on a legacy ASM box. * So we only support the G5 ProLiant servers and higher. @@ -922,6 +439,6 @@ MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default=" #ifdef CONFIG_HPWDT_NMI_DECODING module_param(allow_kdump, int, 0); MODULE_PARM_DESC(allow_kdump, "Start a kernel dump after NMI occurs"); -#endif /* !CONFIG_HPWDT_NMI_DECODING */ +#endif /* CONFIG_HPWDT_NMI_DECODING */ module_pci_driver(hpwdt_driver); diff --git a/drivers/watchdog/sbsa_gwdt.c b/drivers/watchdog/sbsa_gwdt.c index 316c2eb122d2..e8bd9887c566 100644 --- a/drivers/watchdog/sbsa_gwdt.c +++ b/drivers/watchdog/sbsa_gwdt.c @@ -50,6 +50,7 @@ */ #include <linux/io.h> +#include <linux/io-64-nonatomic-lo-hi.h> #include <linux/interrupt.h> #include <linux/module.h> #include <linux/moduleparam.h> @@ -159,7 +160,7 @@ static unsigned int sbsa_gwdt_get_timeleft(struct watchdog_device *wdd) !(readl(gwdt->control_base + SBSA_GWDT_WCS) & SBSA_GWDT_WCS_WS0)) timeleft += readl(gwdt->control_base + SBSA_GWDT_WOR); - timeleft += readq(gwdt->control_base + SBSA_GWDT_WCV) - + timeleft += lo_hi_readq(gwdt->control_base + SBSA_GWDT_WCV) - arch_counter_get_cntvct(); do_div(timeleft, gwdt->clk); diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c index 74888cacd0b0..ec9eb4fba59c 100644 --- a/drivers/xen/xenbus/xenbus_probe.c +++ b/drivers/xen/xenbus/xenbus_probe.c @@ -466,8 +466,11 @@ int xenbus_probe_node(struct xen_bus_type *bus, /* Register with generic device framework. */ err = device_register(&xendev->dev); - if (err) + if (err) { + put_device(&xendev->dev); + xendev = NULL; goto fail; + } return 0; fail: diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 86d6a4435c87..51f940e76c5e 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -807,9 +807,6 @@ do_alloc: iomap->length = hole_size(inode, lblock, &mp); else iomap->length = size - pos; - } else { - if (height <= ip->i_height) - iomap->length = hole_size(inode, lblock, &mp); } goto out_release; } diff --git a/fs/overlayfs/Kconfig b/fs/overlayfs/Kconfig index 406e72de88f6..ce6ff5a0a6e4 100644 --- a/fs/overlayfs/Kconfig +++ b/fs/overlayfs/Kconfig @@ -24,6 +24,8 @@ config OVERLAY_FS_REDIRECT_DIR an overlay which has redirects on a kernel that doesn't support this feature will have unexpected results. + If unsure, say N. + config OVERLAY_FS_REDIRECT_ALWAYS_FOLLOW bool "Overlayfs: follow redirects even if redirects are turned off" default y @@ -32,8 +34,13 @@ config OVERLAY_FS_REDIRECT_ALWAYS_FOLLOW Disable this to get a possibly more secure configuration, but that might not be backward compatible with previous kernels. + If backward compatibility is not an issue, then it is safe and + recommended to say N here. + For more information, see Documentation/filesystems/overlayfs.txt + If unsure, say Y. + config OVERLAY_FS_INDEX bool "Overlayfs: turn on inodes index feature by default" depends on OVERLAY_FS @@ -51,6 +58,8 @@ config OVERLAY_FS_INDEX That is, mounting an overlay which has an inodes index on a kernel that doesn't support this feature will have unexpected results. + If unsure, say N. + config OVERLAY_FS_NFS_EXPORT bool "Overlayfs: turn on NFS export feature by default" depends on OVERLAY_FS @@ -72,3 +81,8 @@ config OVERLAY_FS_NFS_EXPORT Note, that the NFS export feature is not backward compatible. That is, mounting an overlay which has a full index on a kernel that doesn't support this feature will have unexpected results. + + Most users should say N here and enable this feature on a case-by- + case basis with the "nfs_export=on" mount option. + + Say N unless you fully understand the consequences. diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c index bb94ce9da5c8..87bd4148f4fb 100644 --- a/fs/overlayfs/export.c +++ b/fs/overlayfs/export.c @@ -19,6 +19,142 @@ #include <linux/ratelimit.h> #include "overlayfs.h" +static int ovl_encode_maybe_copy_up(struct dentry *dentry) +{ + int err; + + if (ovl_dentry_upper(dentry)) + return 0; + + err = ovl_want_write(dentry); + if (!err) { + err = ovl_copy_up(dentry); + ovl_drop_write(dentry); + } + + if (err) { + pr_warn_ratelimited("overlayfs: failed to copy up on encode (%pd2, err=%i)\n", + dentry, err); + } + + return err; +} + +/* + * Before encoding a non-upper directory file handle from real layer N, we need + * to check if it will be possible to reconnect an overlay dentry from the real + * lower decoded dentry. This is done by following the overlay ancestry up to a + * "layer N connected" ancestor and verifying that all parents along the way are + * "layer N connectable". If an ancestor that is NOT "layer N connectable" is + * found, we need to copy up an ancestor, which is "layer N connectable", thus + * making that ancestor "layer N connected". For example: + * + * layer 1: /a + * layer 2: /a/b/c + * + * The overlay dentry /a is NOT "layer 2 connectable", because if dir /a is + * copied up and renamed, upper dir /a will be indexed by lower dir /a from + * layer 1. The dir /a from layer 2 will never be indexed, so the algorithm (*) + * in ovl_lookup_real_ancestor() will not be able to lookup a connected overlay + * dentry from the connected lower dentry /a/b/c. + * + * To avoid this problem on decode time, we need to copy up an ancestor of + * /a/b/c, which is "layer 2 connectable", on encode time. That ancestor is + * /a/b. After copy up (and index) of /a/b, it will become "layer 2 connected" + * and when the time comes to decode the file handle from lower dentry /a/b/c, + * ovl_lookup_real_ancestor() will find the indexed ancestor /a/b and decoding + * a connected overlay dentry will be accomplished. + * + * (*) the algorithm in ovl_lookup_real_ancestor() can be improved to lookup an + * entry /a in the lower layers above layer N and find the indexed dir /a from + * layer 1. If that improvement is made, then the check for "layer N connected" + * will need to verify there are no redirects in lower layers above N. In the + * example above, /a will be "layer 2 connectable". However, if layer 2 dir /a + * is a target of a layer 1 redirect, then /a will NOT be "layer 2 connectable": + * + * layer 1: /A (redirect = /a) + * layer 2: /a/b/c + */ + +/* Return the lowest layer for encoding a connectable file handle */ +static int ovl_connectable_layer(struct dentry *dentry) +{ + struct ovl_entry *oe = OVL_E(dentry); + + /* We can get overlay root from root of any layer */ + if (dentry == dentry->d_sb->s_root) + return oe->numlower; + + /* + * If it's an unindexed merge dir, then it's not connectable with any + * lower layer + */ + if (ovl_dentry_upper(dentry) && + !ovl_test_flag(OVL_INDEX, d_inode(dentry))) + return 0; + + /* We can get upper/overlay path from indexed/lower dentry */ + return oe->lowerstack[0].layer->idx; +} + +/* + * @dentry is "connected" if all ancestors up to root or a "connected" ancestor + * have the same uppermost lower layer as the origin's layer. We may need to + * copy up a "connectable" ancestor to make it "connected". A "connected" dentry + * cannot become non "connected", so cache positive result in dentry flags. + * + * Return the connected origin layer or < 0 on error. + */ +static int ovl_connect_layer(struct dentry *dentry) +{ + struct dentry *next, *parent = NULL; + int origin_layer; + int err = 0; + + if (WARN_ON(dentry == dentry->d_sb->s_root) || + WARN_ON(!ovl_dentry_lower(dentry))) + return -EIO; + + origin_layer = OVL_E(dentry)->lowerstack[0].layer->idx; + if (ovl_dentry_test_flag(OVL_E_CONNECTED, dentry)) + return origin_layer; + + /* Find the topmost origin layer connectable ancestor of @dentry */ + next = dget(dentry); + for (;;) { + parent = dget_parent(next); + if (WARN_ON(parent == next)) { + err = -EIO; + break; + } + + /* + * If @parent is not origin layer connectable, then copy up + * @next which is origin layer connectable and we are done. + */ + if (ovl_connectable_layer(parent) < origin_layer) { + err = ovl_encode_maybe_copy_up(next); + break; + } + + /* If @parent is connected or indexed we are done */ + if (ovl_dentry_test_flag(OVL_E_CONNECTED, parent) || + ovl_test_flag(OVL_INDEX, d_inode(parent))) + break; + + dput(next); + next = parent; + } + + dput(parent); + dput(next); + + if (!err) + ovl_dentry_set_flag(OVL_E_CONNECTED, dentry); + + return err ?: origin_layer; +} + /* * We only need to encode origin if there is a chance that the same object was * encoded pre copy up and then we need to stay consistent with the same @@ -41,73 +177,59 @@ * L = lower file handle * * (*) Connecting an overlay dir from real lower dentry is not always - * possible when there are redirects in lower layers. To mitigate this case, - * we copy up the lower dir first and then encode an upper dir file handle. + * possible when there are redirects in lower layers and non-indexed merge dirs. + * To mitigate those case, we may copy up the lower dir ancestor before encode + * a lower dir file handle. + * + * Return 0 for upper file handle, > 0 for lower file handle or < 0 on error. */ -static bool ovl_should_encode_origin(struct dentry *dentry) +static int ovl_check_encode_origin(struct dentry *dentry) { struct ovl_fs *ofs = dentry->d_sb->s_fs_info; + /* Upper file handle for pure upper */ if (!ovl_dentry_lower(dentry)) - return false; + return 0; /* - * Decoding a merge dir, whose origin's parent is under a redirected - * lower dir is not always possible. As a simple aproximation, we do - * not encode lower dir file handles when overlay has multiple lower - * layers and origin is below the topmost lower layer. + * Upper file handle for non-indexed upper. * - * TODO: copy up only the parent that is under redirected lower. + * Root is never indexed, so if there's an upper layer, encode upper for + * root. */ - if (d_is_dir(dentry) && ofs->upper_mnt && - OVL_E(dentry)->lowerstack[0].layer->idx > 1) - return false; - - /* Decoding a non-indexed upper from origin is not implemented */ if (ovl_dentry_upper(dentry) && !ovl_test_flag(OVL_INDEX, d_inode(dentry))) - return false; - - return true; -} - -static int ovl_encode_maybe_copy_up(struct dentry *dentry) -{ - int err; - - if (ovl_dentry_upper(dentry)) return 0; - err = ovl_want_write(dentry); - if (err) - return err; - - err = ovl_copy_up(dentry); + /* + * Decoding a merge dir, whose origin's ancestor is under a redirected + * lower dir or under a non-indexed upper is not always possible. + * ovl_connect_layer() will try to make origin's layer "connected" by + * copying up a "connectable" ancestor. + */ + if (d_is_dir(dentry) && ofs->upper_mnt) + return ovl_connect_layer(dentry); - ovl_drop_write(dentry); - return err; + /* Lower file handle for indexed and non-upper dir/non-dir */ + return 1; } static int ovl_d_to_fh(struct dentry *dentry, char *buf, int buflen) { - struct dentry *origin = ovl_dentry_lower(dentry); struct ovl_fh *fh = NULL; - int err; + int err, enc_lower; /* - * If we should not encode a lower dir file handle, copy up and encode - * an upper dir file handle. + * Check if we should encode a lower or upper file handle and maybe + * copy up an ancestor to make lower file handle connectable. */ - if (!ovl_should_encode_origin(dentry)) { - err = ovl_encode_maybe_copy_up(dentry); - if (err) - goto fail; - - origin = NULL; - } + err = enc_lower = ovl_check_encode_origin(dentry); + if (enc_lower < 0) + goto fail; - /* Encode an upper or origin file handle */ - fh = ovl_encode_fh(origin ?: ovl_dentry_upper(dentry), !origin); + /* Encode an upper or lower file handle */ + fh = ovl_encode_fh(enc_lower ? ovl_dentry_lower(dentry) : + ovl_dentry_upper(dentry), !enc_lower); err = PTR_ERR(fh); if (IS_ERR(fh)) goto fail; @@ -355,8 +477,8 @@ static struct dentry *ovl_lookup_real_inode(struct super_block *sb, dput(upper); } - if (!this) - return NULL; + if (IS_ERR_OR_NULL(this)) + return this; if (WARN_ON(ovl_dentry_real_at(this, layer->idx) != real)) { dput(this); @@ -498,7 +620,7 @@ static struct dentry *ovl_lookup_real(struct super_block *sb, if (err == -ECHILD) { this = ovl_lookup_real_ancestor(sb, real, layer); - err = IS_ERR(this) ? PTR_ERR(this) : 0; + err = PTR_ERR_OR_ZERO(this); } if (!err) { dput(connected); diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index fcd97b783fa1..3b1bd469accd 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -669,38 +669,59 @@ struct inode *ovl_lookup_inode(struct super_block *sb, struct dentry *real, return inode; } +/* + * Does overlay inode need to be hashed by lower inode? + */ +static bool ovl_hash_bylower(struct super_block *sb, struct dentry *upper, + struct dentry *lower, struct dentry *index) +{ + struct ovl_fs *ofs = sb->s_fs_info; + + /* No, if pure upper */ + if (!lower) + return false; + + /* Yes, if already indexed */ + if (index) + return true; + + /* Yes, if won't be copied up */ + if (!ofs->upper_mnt) + return true; + + /* No, if lower hardlink is or will be broken on copy up */ + if ((upper || !ovl_indexdir(sb)) && + !d_is_dir(lower) && d_inode(lower)->i_nlink > 1) + return false; + + /* No, if non-indexed upper with NFS export */ + if (sb->s_export_op && upper) + return false; + + /* Otherwise, hash by lower inode for fsnotify */ + return true; +} + struct inode *ovl_get_inode(struct super_block *sb, struct dentry *upperdentry, struct dentry *lowerdentry, struct dentry *index, unsigned int numlower) { - struct ovl_fs *ofs = sb->s_fs_info; struct inode *realinode = upperdentry ? d_inode(upperdentry) : NULL; struct inode *inode; - /* Already indexed or could be indexed on copy up? */ - bool indexed = (index || (ovl_indexdir(sb) && !upperdentry)); - struct dentry *origin = indexed ? lowerdentry : NULL; + bool bylower = ovl_hash_bylower(sb, upperdentry, lowerdentry, index); bool is_dir; - if (WARN_ON(upperdentry && indexed && !lowerdentry)) - return ERR_PTR(-EIO); - if (!realinode) realinode = d_inode(lowerdentry); /* - * Copy up origin (lower) may exist for non-indexed non-dir upper, but - * we must not use lower as hash key in that case. - * Hash non-dir that is or could be indexed by origin inode. - * Hash dir that is or could be merged by origin inode. - * Hash pure upper and non-indexed non-dir by upper inode. - * Hash non-indexed dir by upper inode for NFS export. + * Copy up origin (lower) may exist for non-indexed upper, but we must + * not use lower as hash key if this is a broken hardlink. */ is_dir = S_ISDIR(realinode->i_mode); - if (is_dir && (indexed || !sb->s_export_op || !ofs->upper_mnt)) - origin = lowerdentry; - - if (upperdentry || origin) { - struct inode *key = d_inode(origin ?: upperdentry); + if (upperdentry || bylower) { + struct inode *key = d_inode(bylower ? lowerdentry : + upperdentry); unsigned int nlink = is_dir ? 1 : realinode->i_nlink; inode = iget5_locked(sb, (unsigned long) key, @@ -728,6 +749,7 @@ struct inode *ovl_get_inode(struct super_block *sb, struct dentry *upperdentry, nlink = ovl_get_nlink(lowerdentry, upperdentry, nlink); set_nlink(inode, nlink); } else { + /* Lower hardlink that will be broken on copy up */ inode = new_inode(sb); if (!inode) goto out_nomem; diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index de3e6da1d5a5..70fcfcc684cc 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -913,9 +913,6 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, stack[ctr].layer = lower.layer; ctr++; - if (d.stop) - break; - /* * Following redirects can have security consequences: it's like * a symlink into the lower layer without the permission checks. @@ -933,6 +930,9 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, goto out_put; } + if (d.stop) + break; + if (d.redirect && d.redirect[0] == '/' && poe != roe) { poe = roe; /* Find the current layer on the root dentry */ diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 0df25a9c94bd..225ff1171147 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -40,6 +40,7 @@ enum ovl_inode_flag { enum ovl_entry_flag { OVL_E_UPPER_ALIAS, OVL_E_OPAQUE, + OVL_E_CONNECTED, }; /* diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 9ee37c76091d..7c24619ae7fc 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -1359,6 +1359,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) /* Root is always merge -> can have whiteouts */ ovl_set_flag(OVL_WHITEOUTS, d_inode(root_dentry)); + ovl_dentry_set_flag(OVL_E_CONNECTED, root_dentry); ovl_inode_init(d_inode(root_dentry), upperpath.dentry, ovl_dentry_lower(root_dentry)); diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 66e1edbfb2b2..046469fcc1b8 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -955,15 +955,29 @@ static inline bool imap_needs_alloc(struct inode *inode, (IS_DAX(inode) && imap->br_state == XFS_EXT_UNWRITTEN); } +static inline bool needs_cow_for_zeroing(struct xfs_bmbt_irec *imap, int nimaps) +{ + return nimaps && + imap->br_startblock != HOLESTARTBLOCK && + imap->br_state != XFS_EXT_UNWRITTEN; +} + static inline bool need_excl_ilock(struct xfs_inode *ip, unsigned flags) { /* - * COW writes will allocate delalloc space, so we need to make sure - * to take the lock exclusively here. + * COW writes may allocate delalloc space or convert unwritten COW + * extents, so we need to make sure to take the lock exclusively here. */ if (xfs_is_reflink_inode(ip) && (flags & (IOMAP_WRITE | IOMAP_ZERO))) return true; - if ((flags & IOMAP_DIRECT) && (flags & IOMAP_WRITE)) + + /* + * Extents not yet cached requires exclusive access, don't block. + * This is an opencoded xfs_ilock_data_map_shared() to cater for the + * non-blocking behaviour. + */ + if (ip->i_d.di_format == XFS_DINODE_FMT_BTREE && + !(ip->i_df.if_flags & XFS_IFEXTENTS)) return true; return false; } @@ -993,16 +1007,18 @@ xfs_file_iomap_begin( return xfs_file_iomap_begin_delay(inode, offset, length, iomap); } - if (need_excl_ilock(ip, flags)) { + if (need_excl_ilock(ip, flags)) lockmode = XFS_ILOCK_EXCL; - xfs_ilock(ip, XFS_ILOCK_EXCL); - } else { - lockmode = xfs_ilock_data_map_shared(ip); - } + else + lockmode = XFS_ILOCK_SHARED; - if ((flags & IOMAP_NOWAIT) && !(ip->i_df.if_flags & XFS_IFEXTENTS)) { - error = -EAGAIN; - goto out_unlock; + if (flags & IOMAP_NOWAIT) { + if (!(ip->i_df.if_flags & XFS_IFEXTENTS)) + return -EAGAIN; + if (!xfs_ilock_nowait(ip, lockmode)) + return -EAGAIN; + } else { + xfs_ilock(ip, lockmode); } ASSERT(offset <= mp->m_super->s_maxbytes); @@ -1024,7 +1040,9 @@ xfs_file_iomap_begin( goto out_unlock; } - if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) { + if (xfs_is_reflink_inode(ip) && + ((flags & IOMAP_WRITE) || + ((flags & IOMAP_ZERO) && needs_cow_for_zeroing(&imap, nimaps)))) { if (flags & IOMAP_DIRECT) { /* * A reflinked inode will result in CoW alloc. diff --git a/include/linux/compat.h b/include/linux/compat.h index 8a9643857c4a..16c3027074a2 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -17,6 +17,7 @@ #include <linux/if.h> #include <linux/fs.h> #include <linux/aio_abi.h> /* for aio_context_t */ +#include <linux/uaccess.h> #include <linux/unistd.h> #include <asm/compat.h> @@ -229,13 +230,13 @@ typedef struct compat_siginfo { short int _addr_lsb; /* Valid LSB of the reported address. */ /* used when si_code=SEGV_BNDERR */ struct { - short _dummy_bnd; + compat_uptr_t _dummy_bnd; compat_uptr_t _lower; compat_uptr_t _upper; } _addr_bnd; /* used when si_code=SEGV_PKUERR */ struct { - short _dummy_pkey; + compat_uptr_t _dummy_pkey; u32 _pkey; } _addr_pkey; }; @@ -550,8 +551,29 @@ asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv, asmlinkage long compat_sys_adjtimex(struct compat_timex __user *utp); extern int get_compat_sigset(sigset_t *set, const compat_sigset_t __user *compat); -extern int put_compat_sigset(compat_sigset_t __user *compat, - const sigset_t *set, unsigned int size); + +/* + * Defined inline such that size can be compile time constant, which avoids + * CONFIG_HARDENED_USERCOPY complaining about copies from task_struct + */ +static inline int +put_compat_sigset(compat_sigset_t __user *compat, const sigset_t *set, + unsigned int size) +{ + /* size <= sizeof(compat_sigset_t) <= sizeof(sigset_t) */ +#ifdef __BIG_ENDIAN + compat_sigset_t v; + switch (_NSIG_WORDS) { + case 4: v.sig[7] = (set->sig[3] >> 32); v.sig[6] = set->sig[3]; + case 3: v.sig[5] = (set->sig[2] >> 32); v.sig[4] = set->sig[2]; + case 2: v.sig[3] = (set->sig[1] >> 32); v.sig[2] = set->sig[1]; + case 1: v.sig[1] = (set->sig[0] >> 32); v.sig[0] = set->sig[0]; + } + return copy_to_user(compat, &v, size) ? -EFAULT : 0; +#else + return copy_to_user(compat, set, size) ? -EFAULT : 0; +#endif +} asmlinkage long compat_sys_migrate_pages(compat_pid_t pid, compat_ulong_t maxnode, const compat_ulong_t __user *old_nodes, diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 21e8d248d956..1fe49724da9e 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -962,6 +962,7 @@ extern struct freq_attr cpufreq_freq_attr_scaling_boost_freqs; extern struct freq_attr *cpufreq_generic_attr[]; int cpufreq_table_validate_and_show(struct cpufreq_policy *policy, struct cpufreq_frequency_table *table); +int cpufreq_table_validate_and_sort(struct cpufreq_policy *policy); unsigned int cpufreq_generic_get(unsigned int cpu); int cpufreq_generic_init(struct cpufreq_policy *policy, diff --git a/include/linux/device.h b/include/linux/device.h index b093405ed525..abf952c82c6d 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -769,6 +769,7 @@ enum device_link_state { * @status: The state of the link (with respect to the presence of drivers). * @flags: Link flags. * @rpm_active: Whether or not the consumer device is runtime-PM-active. + * @kref: Count repeated addition of the same link. * @rcu_head: An RCU head to use for deferred execution of SRCU callbacks. */ struct device_link { @@ -779,6 +780,7 @@ struct device_link { enum device_link_state status; u32 flags; bool rpm_active; + struct kref kref; #ifdef CONFIG_SRCU struct rcu_head rcu_head; #endif diff --git a/include/linux/of_pci.h b/include/linux/of_pci.h index 88865e0ebf4d..091033a6b836 100644 --- a/include/linux/of_pci.h +++ b/include/linux/of_pci.h @@ -13,7 +13,6 @@ struct device_node; struct device_node *of_pci_find_child_device(struct device_node *parent, unsigned int devfn); int of_pci_get_devfn(struct device_node *np); -int of_irq_parse_and_map_pci(const struct pci_dev *dev, u8 slot, u8 pin); int of_pci_parse_bus_range(struct device_node *node, struct resource *res); int of_get_pci_domain_nr(struct device_node *node); int of_pci_get_max_link_speed(struct device_node *node); @@ -34,12 +33,6 @@ static inline int of_pci_get_devfn(struct device_node *np) } static inline int -of_irq_parse_and_map_pci(const struct pci_dev *dev, u8 slot, u8 pin) -{ - return 0; -} - -static inline int of_pci_parse_bus_range(struct device_node *node, struct resource *res) { return -EINVAL; @@ -67,6 +60,16 @@ of_pci_get_max_link_speed(struct device_node *node) static inline void of_pci_check_probe_only(void) { } #endif +#if IS_ENABLED(CONFIG_OF_IRQ) +int of_irq_parse_and_map_pci(const struct pci_dev *dev, u8 slot, u8 pin); +#else +static inline int +of_irq_parse_and_map_pci(const struct pci_dev *dev, u8 slot, u8 pin) +{ + return 0; +} +#endif + #if defined(CONFIG_OF_ADDRESS) int of_pci_get_host_bridge_resources(struct device_node *dev, unsigned char busno, unsigned char bus_max, diff --git a/include/linux/phy.h b/include/linux/phy.h index 5a0c3e53e7c2..d7069539f351 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -924,6 +924,7 @@ void phy_device_remove(struct phy_device *phydev); int phy_init_hw(struct phy_device *phydev); int phy_suspend(struct phy_device *phydev); int phy_resume(struct phy_device *phydev); +int __phy_resume(struct phy_device *phydev); int phy_loopback(struct phy_device *phydev, bool enable); struct phy_device *phy_attach(struct net_device *dev, const char *bus_id, phy_interface_t interface); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index c1e66bdcf583..ddf77cf4ff2d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3285,8 +3285,7 @@ int skb_zerocopy(struct sk_buff *to, struct sk_buff *from, void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len); int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen); void skb_scrub_packet(struct sk_buff *skb, bool xnet); -unsigned int skb_gso_transport_seglen(const struct sk_buff *skb); -bool skb_gso_validate_mtu(const struct sk_buff *skb, unsigned int mtu); +bool skb_gso_validate_network_len(const struct sk_buff *skb, unsigned int mtu); bool skb_gso_validate_mac_len(const struct sk_buff *skb, unsigned int len); struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features); struct sk_buff *skb_vlan_untag(struct sk_buff *skb); @@ -4104,38 +4103,6 @@ static inline bool skb_head_is_locked(const struct sk_buff *skb) return !skb->head_frag || skb_cloned(skb); } -/** - * skb_gso_network_seglen - Return length of individual segments of a gso packet - * - * @skb: GSO skb - * - * skb_gso_network_seglen is used to determine the real size of the - * individual segments, including Layer3 (IP, IPv6) and L4 headers (TCP/UDP). - * - * The MAC/L2 header is not accounted for. - */ -static inline unsigned int skb_gso_network_seglen(const struct sk_buff *skb) -{ - unsigned int hdr_len = skb_transport_header(skb) - - skb_network_header(skb); - return hdr_len + skb_gso_transport_seglen(skb); -} - -/** - * skb_gso_mac_seglen - Return length of individual segments of a gso packet - * - * @skb: GSO skb - * - * skb_gso_mac_seglen is used to determine the real size of the - * individual segments, including MAC/L2, Layer3 (IP, IPv6) and L4 - * headers (TCP/UDP). - */ -static inline unsigned int skb_gso_mac_seglen(const struct sk_buff *skb) -{ - unsigned int hdr_len = skb_transport_header(skb) - skb_mac_header(skb); - return hdr_len + skb_gso_transport_seglen(skb); -} - /* Local Checksum Offload. * Compute outer checksum based on the assumption that the * inner checksum will be offloaded later. diff --git a/include/net/devlink.h b/include/net/devlink.h index 6545b03e97f7..4de35ed12bcc 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -257,6 +257,18 @@ struct devlink_resource_size_params { enum devlink_resource_unit unit; }; +static inline void +devlink_resource_size_params_init(struct devlink_resource_size_params *size_params, + u64 size_min, u64 size_max, + u64 size_granularity, + enum devlink_resource_unit unit) +{ + size_params->size_min = size_min; + size_params->size_max = size_max; + size_params->size_granularity = size_granularity; + size_params->unit = unit; +} + /** * struct devlink_resource - devlink resource * @name: name of the resource @@ -278,7 +290,7 @@ struct devlink_resource { u64 size_new; bool size_valid; struct devlink_resource *parent; - struct devlink_resource_size_params *size_params; + struct devlink_resource_size_params size_params; struct list_head list; struct list_head resource_list; const struct devlink_resource_ops *resource_ops; @@ -402,7 +414,7 @@ int devlink_resource_register(struct devlink *devlink, u64 resource_size, u64 resource_id, u64 parent_resource_id, - struct devlink_resource_size_params *size_params, + const struct devlink_resource_size_params *size_params, const struct devlink_resource_ops *resource_ops); void devlink_resources_unregister(struct devlink *devlink, struct devlink_resource *resource); @@ -556,7 +568,7 @@ devlink_resource_register(struct devlink *devlink, u64 resource_size, u64 resource_id, u64 parent_resource_id, - struct devlink_resource_size_params *size_params, + const struct devlink_resource_size_params *size_params, const struct devlink_resource_ops *resource_ops) { return 0; diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index d8d4a902a88d..2280b2351739 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -68,6 +68,9 @@ struct scsi_cmnd { struct list_head list; /* scsi_cmnd participates in queue lists */ struct list_head eh_entry; /* entry for the host eh_cmd_q */ struct delayed_work abort_work; + + struct rcu_head rcu; + int eh_eflags; /* Used by error handlr */ /* diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h index 1a1df0d21ee3..a8b7bf879ced 100644 --- a/include/scsi/scsi_host.h +++ b/include/scsi/scsi_host.h @@ -571,8 +571,6 @@ struct Scsi_Host { struct blk_mq_tag_set tag_set; }; - struct rcu_head rcu; - atomic_t host_busy; /* commands actually active on low-level */ atomic_t host_blocked; diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h index 85dc965afd89..99c902e460c2 100644 --- a/include/uapi/asm-generic/siginfo.h +++ b/include/uapi/asm-generic/siginfo.h @@ -102,13 +102,13 @@ typedef struct siginfo { short _addr_lsb; /* LSB of the reported address */ /* used when si_code=SEGV_BNDERR */ struct { - short _dummy_bnd; + void *_dummy_bnd; void __user *_lower; void __user *_upper; } _addr_bnd; /* used when si_code=SEGV_PKUERR */ struct { - short _dummy_pkey; + void *_dummy_pkey; __u32 _pkey; } _addr_pkey; }; diff --git a/include/uapi/misc/ocxl.h b/include/uapi/misc/ocxl.h index 4b0b0b756f3e..0af83d80fb3e 100644 --- a/include/uapi/misc/ocxl.h +++ b/include/uapi/misc/ocxl.h @@ -32,6 +32,22 @@ struct ocxl_ioctl_attach { __u64 reserved3; }; +struct ocxl_ioctl_metadata { + __u16 version; // struct version, always backwards compatible + + // Version 0 fields + __u8 afu_version_major; + __u8 afu_version_minor; + __u32 pasid; // PASID assigned to the current context + + __u64 pp_mmio_size; // Per PASID MMIO size + __u64 global_mmio_size; + + // End version 0 fields + + __u64 reserved[13]; // Total of 16*u64 +}; + struct ocxl_ioctl_irq_fd { __u64 irq_offset; __s32 eventfd; @@ -45,5 +61,6 @@ struct ocxl_ioctl_irq_fd { #define OCXL_IOCTL_IRQ_ALLOC _IOR(OCXL_MAGIC, 0x11, __u64) #define OCXL_IOCTL_IRQ_FREE _IOW(OCXL_MAGIC, 0x12, __u64) #define OCXL_IOCTL_IRQ_SET_FD _IOW(OCXL_MAGIC, 0x13, struct ocxl_ioctl_irq_fd) +#define OCXL_IOCTL_GET_METADATA _IOR(OCXL_MAGIC, 0x14, struct ocxl_ioctl_metadata) #endif /* _UAPI_MISC_OCXL_H */ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 5fb69a85d967..c6eff108aa99 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1356,6 +1356,13 @@ static bool is_ctx_reg(struct bpf_verifier_env *env, int regno) return reg->type == PTR_TO_CTX; } +static bool is_pkt_reg(struct bpf_verifier_env *env, int regno) +{ + const struct bpf_reg_state *reg = cur_regs(env) + regno; + + return type_is_pkt_pointer(reg->type); +} + static int check_pkt_ptr_alignment(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int off, int size, bool strict) @@ -1416,10 +1423,10 @@ static int check_generic_ptr_alignment(struct bpf_verifier_env *env, } static int check_ptr_alignment(struct bpf_verifier_env *env, - const struct bpf_reg_state *reg, - int off, int size) + const struct bpf_reg_state *reg, int off, + int size, bool strict_alignment_once) { - bool strict = env->strict_alignment; + bool strict = env->strict_alignment || strict_alignment_once; const char *pointer_desc = ""; switch (reg->type) { @@ -1576,9 +1583,9 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size) * if t==write && value_regno==-1, some unknown value is stored into memory * if t==read && value_regno==-1, don't care what we read from memory */ -static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regno, int off, - int bpf_size, enum bpf_access_type t, - int value_regno) +static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regno, + int off, int bpf_size, enum bpf_access_type t, + int value_regno, bool strict_alignment_once) { struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = regs + regno; @@ -1590,7 +1597,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn return size; /* alignment checks will add in reg->off themselves */ - err = check_ptr_alignment(env, reg, off, size); + err = check_ptr_alignment(env, reg, off, size, strict_alignment_once); if (err) return err; @@ -1735,21 +1742,23 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins return -EACCES; } - if (is_ctx_reg(env, insn->dst_reg)) { - verbose(env, "BPF_XADD stores into R%d context is not allowed\n", - insn->dst_reg); + if (is_ctx_reg(env, insn->dst_reg) || + is_pkt_reg(env, insn->dst_reg)) { + verbose(env, "BPF_XADD stores into R%d %s is not allowed\n", + insn->dst_reg, is_ctx_reg(env, insn->dst_reg) ? + "context" : "packet"); return -EACCES; } /* check whether atomic_add can read the memory */ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, - BPF_SIZE(insn->code), BPF_READ, -1); + BPF_SIZE(insn->code), BPF_READ, -1, true); if (err) return err; /* check whether atomic_add can write into the same memory */ return check_mem_access(env, insn_idx, insn->dst_reg, insn->off, - BPF_SIZE(insn->code), BPF_WRITE, -1); + BPF_SIZE(insn->code), BPF_WRITE, -1, true); } /* when register 'regno' is passed into function that will read 'access_size' @@ -2388,7 +2397,8 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn * is inferred from register state. */ for (i = 0; i < meta.access_size; i++) { - err = check_mem_access(env, insn_idx, meta.regno, i, BPF_B, BPF_WRITE, -1); + err = check_mem_access(env, insn_idx, meta.regno, i, BPF_B, + BPF_WRITE, -1, false); if (err) return err; } @@ -4632,7 +4642,7 @@ static int do_check(struct bpf_verifier_env *env) */ err = check_mem_access(env, insn_idx, insn->src_reg, insn->off, BPF_SIZE(insn->code), BPF_READ, - insn->dst_reg); + insn->dst_reg, false); if (err) return err; @@ -4684,7 +4694,7 @@ static int do_check(struct bpf_verifier_env *env) /* check that memory (dst_reg + off) is writeable */ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_WRITE, - insn->src_reg); + insn->src_reg, false); if (err) return err; @@ -4719,7 +4729,7 @@ static int do_check(struct bpf_verifier_env *env) /* check that memory (dst_reg + off) is writeable */ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_WRITE, - -1); + -1, false); if (err) return err; diff --git a/kernel/compat.c b/kernel/compat.c index 3247fe761f60..3f5fa8902e7d 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -488,25 +488,6 @@ get_compat_sigset(sigset_t *set, const compat_sigset_t __user *compat) } EXPORT_SYMBOL_GPL(get_compat_sigset); -int -put_compat_sigset(compat_sigset_t __user *compat, const sigset_t *set, - unsigned int size) -{ - /* size <= sizeof(compat_sigset_t) <= sizeof(sigset_t) */ -#ifdef __BIG_ENDIAN - compat_sigset_t v; - switch (_NSIG_WORDS) { - case 4: v.sig[7] = (set->sig[3] >> 32); v.sig[6] = set->sig[3]; - case 3: v.sig[5] = (set->sig[2] >> 32); v.sig[4] = set->sig[2]; - case 2: v.sig[3] = (set->sig[1] >> 32); v.sig[2] = set->sig[1]; - case 1: v.sig[1] = (set->sig[0] >> 32); v.sig[0] = set->sig[0]; - } - return copy_to_user(compat, &v, size) ? -EFAULT : 0; -#else - return copy_to_user(compat, set, size) ? -EFAULT : 0; -#endif -} - #ifdef CONFIG_NUMA COMPAT_SYSCALL_DEFINE6(move_pages, pid_t, pid, compat_ulong_t, nr_pages, compat_uptr_t __user *, pages32, diff --git a/kernel/events/core.c b/kernel/events/core.c index 96db9ae5d5af..4b838470fac4 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2246,7 +2246,7 @@ static void ctx_resched(struct perf_cpu_context *cpuctx, struct perf_event_context *task_ctx, enum event_type_t event_type) { - enum event_type_t ctx_event_type = event_type & EVENT_ALL; + enum event_type_t ctx_event_type; bool cpu_event = !!(event_type & EVENT_CPU); /* @@ -2256,6 +2256,8 @@ static void ctx_resched(struct perf_cpu_context *cpuctx, if (event_type & EVENT_PINNED) event_type |= EVENT_FLEXIBLE; + ctx_event_type = event_type & EVENT_ALL; + perf_pmu_disable(cpuctx->ctx.pmu); if (task_ctx) task_ctx_sched_out(cpuctx, task_ctx, event_type); diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 65cc0cb984e6..940633c63254 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1616,11 +1616,12 @@ bool __sched __rt_mutex_futex_unlock(struct rt_mutex *lock, void __sched rt_mutex_futex_unlock(struct rt_mutex *lock) { DEFINE_WAKE_Q(wake_q); + unsigned long flags; bool postunlock; - raw_spin_lock_irq(&lock->wait_lock); + raw_spin_lock_irqsave(&lock->wait_lock, flags); postunlock = __rt_mutex_futex_unlock(lock, &wake_q); - raw_spin_unlock_irq(&lock->wait_lock); + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); if (postunlock) rt_mutex_postunlock(&wake_q); diff --git a/kernel/panic.c b/kernel/panic.c index 2cfef408fec9..4b794f1d8561 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -640,7 +640,7 @@ device_initcall(register_warn_debugfs); */ __visible void __stack_chk_fail(void) { - panic("stack-protector: Kernel stack is corrupted in: %p\n", + panic("stack-protector: Kernel stack is corrupted in: %pB\n", __builtin_return_address(0)); } EXPORT_SYMBOL(__stack_chk_fail); diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index a5c36e9c56a6..1028ecbb7a06 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -1053,7 +1053,7 @@ static ssize_t resume_store(struct kobject *kobj, struct kobj_attribute *attr, lock_system_sleep(); swsusp_resume_device = res; unlock_system_sleep(); - pr_info("Starting manual resume from disk\n"); + pm_pr_dbg("Configured resume from disk to %u\n", swsusp_resume_device); noresume = 0; software_resume(); return n; @@ -1061,6 +1061,29 @@ static ssize_t resume_store(struct kobject *kobj, struct kobj_attribute *attr, power_attr(resume); +static ssize_t resume_offset_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%llu\n", (unsigned long long)swsusp_resume_block); +} + +static ssize_t resume_offset_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, + size_t n) +{ + unsigned long long offset; + int rc; + + rc = kstrtoull(buf, 0, &offset); + if (rc) + return rc; + swsusp_resume_block = offset; + + return n; +} + +power_attr(resume_offset); + static ssize_t image_size_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { @@ -1106,6 +1129,7 @@ power_attr(reserved_size); static struct attribute * g[] = { &disk_attr.attr, + &resume_offset_attr.attr, &resume_attr.attr, &image_size_attr.attr, &reserved_size_attr.attr, diff --git a/lib/bug.c b/lib/bug.c index c1b0fad31b10..1077366f496b 100644 --- a/lib/bug.c +++ b/lib/bug.c @@ -150,6 +150,8 @@ enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs) return BUG_TRAP_TYPE_NONE; bug = find_bug(bugaddr); + if (!bug) + return BUG_TRAP_TYPE_NONE; file = NULL; line = 0; @@ -191,7 +193,7 @@ enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs) if (file) pr_crit("kernel BUG at %s:%u!\n", file, line); else - pr_crit("Kernel BUG at %p [verbose debug info unavailable]\n", + pr_crit("Kernel BUG at %pB [verbose debug info unavailable]\n", (void *)bugaddr); return BUG_TRAP_TYPE_BUG; diff --git a/lib/test_bpf.c b/lib/test_bpf.c index b4e22345963f..2efb213716fa 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -24,10 +24,11 @@ #include <linux/if_vlan.h> #include <linux/random.h> #include <linux/highmem.h> +#include <linux/sched.h> /* General test specific settings */ #define MAX_SUBTESTS 3 -#define MAX_TESTRUNS 10000 +#define MAX_TESTRUNS 1000 #define MAX_DATA 128 #define MAX_INSNS 512 #define MAX_K 0xffffFFFF @@ -6582,6 +6583,7 @@ static __init int test_bpf(void) struct bpf_prog *fp; int err; + cond_resched(); if (exclude_test(i)) continue; diff --git a/lib/test_kmod.c b/lib/test_kmod.c index e372b97eee13..0e5b7a61460b 100644 --- a/lib/test_kmod.c +++ b/lib/test_kmod.c @@ -1141,7 +1141,7 @@ static struct kmod_test_device *register_test_dev_kmod(void) mutex_lock(®_dev_mutex); /* int should suffice for number of devices, test for wrap */ - if (unlikely(num_test_devs + 1) < 0) { + if (num_test_devs + 1 == INT_MAX) { pr_err("reached limit of number of test devices\n"); goto out; } @@ -516,7 +516,7 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma, } if (ret & VM_FAULT_RETRY) { - if (nonblocking) + if (nonblocking && !(fault_flags & FAULT_FLAG_RETRY_NOWAIT)) *nonblocking = 0; return -EBUSY; } @@ -890,7 +890,10 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk, break; } if (*locked) { - /* VM_FAULT_RETRY didn't trigger */ + /* + * VM_FAULT_RETRY didn't trigger or it was a + * FOLL_NOWAIT. + */ if (!pages_done) pages_done = ret; break; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 7c204e3d132b..a963f2034dfc 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1583,7 +1583,7 @@ static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask, page = NULL; } else { h->surplus_huge_pages++; - h->nr_huge_pages_node[page_to_nid(page)]++; + h->surplus_huge_pages_node[page_to_nid(page)]++; } out_unlock: diff --git a/mm/memblock.c b/mm/memblock.c index 5a9ca2a1751b..b6ba6b7adadc 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1107,7 +1107,7 @@ unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn, struct memblock_type *type = &memblock.memory; unsigned int right = type->cnt; unsigned int mid, left = 0; - phys_addr_t addr = PFN_PHYS(pfn + 1); + phys_addr_t addr = PFN_PHYS(++pfn); do { mid = (right + left) / 2; @@ -1118,15 +1118,15 @@ unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn, type->regions[mid].size)) left = mid + 1; else { - /* addr is within the region, so pfn + 1 is valid */ - return min(pfn + 1, max_pfn); + /* addr is within the region, so pfn is valid */ + return pfn; } } while (left < right); if (right == type->cnt) - return max_pfn; + return -1UL; else - return min(PHYS_PFN(type->regions[right].base), max_pfn); + return PHYS_PFN(type->regions[right].base); } /** diff --git a/mm/page_alloc.c b/mm/page_alloc.c index cb416723538f..3d974cb2a1a1 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5359,9 +5359,14 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, /* * Skip to the pfn preceding the next valid one (or * end_pfn), such that we hit a valid pfn (or end_pfn) - * on our next iteration of the loop. + * on our next iteration of the loop. Note that it needs + * to be pageblock aligned even when the region itself + * is not. move_freepages_block() can shift ahead of + * the valid region but still depends on correct page + * metadata. */ - pfn = memblock_next_valid_pfn(pfn, end_pfn) - 1; + pfn = (memblock_next_valid_pfn(pfn, end_pfn) & + ~(pageblock_nr_pages-1)) - 1; #endif continue; } diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 79e326383726..99abeadf416e 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -157,7 +157,7 @@ static void batadv_iv_ogm_orig_free(struct batadv_orig_node *orig_node) * Return: 0 on success, a negative error code otherwise. */ static int batadv_iv_ogm_orig_add_if(struct batadv_orig_node *orig_node, - int max_if_num) + unsigned int max_if_num) { void *data_ptr; size_t old_size; @@ -201,7 +201,8 @@ unlock: */ static void batadv_iv_ogm_drop_bcast_own_entry(struct batadv_orig_node *orig_node, - int max_if_num, int del_if_num) + unsigned int max_if_num, + unsigned int del_if_num) { size_t chunk_size; size_t if_offset; @@ -239,7 +240,8 @@ batadv_iv_ogm_drop_bcast_own_entry(struct batadv_orig_node *orig_node, */ static void batadv_iv_ogm_drop_bcast_own_sum_entry(struct batadv_orig_node *orig_node, - int max_if_num, int del_if_num) + unsigned int max_if_num, + unsigned int del_if_num) { size_t if_offset; void *data_ptr; @@ -276,7 +278,8 @@ batadv_iv_ogm_drop_bcast_own_sum_entry(struct batadv_orig_node *orig_node, * Return: 0 on success, a negative error code otherwise. */ static int batadv_iv_ogm_orig_del_if(struct batadv_orig_node *orig_node, - int max_if_num, int del_if_num) + unsigned int max_if_num, + unsigned int del_if_num) { spin_lock_bh(&orig_node->bat_iv.ogm_cnt_lock); @@ -311,7 +314,8 @@ static struct batadv_orig_node * batadv_iv_ogm_orig_get(struct batadv_priv *bat_priv, const u8 *addr) { struct batadv_orig_node *orig_node; - int size, hash_added; + int hash_added; + size_t size; orig_node = batadv_orig_hash_find(bat_priv, addr); if (orig_node) @@ -893,7 +897,7 @@ batadv_iv_ogm_slide_own_bcast_window(struct batadv_hard_iface *hard_iface) u32 i; size_t word_index; u8 *w; - int if_num; + unsigned int if_num; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -1023,7 +1027,7 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, struct batadv_neigh_node *tmp_neigh_node = NULL; struct batadv_neigh_node *router = NULL; struct batadv_orig_node *orig_node_tmp; - int if_num; + unsigned int if_num; u8 sum_orig, sum_neigh; u8 *neigh_addr; u8 tq_avg; @@ -1182,7 +1186,7 @@ static bool batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, u8 total_count; u8 orig_eq_count, neigh_rq_count, neigh_rq_inv, tq_own; unsigned int neigh_rq_inv_cube, neigh_rq_max_cube; - int if_num; + unsigned int if_num; unsigned int tq_asym_penalty, inv_asym_penalty; unsigned int combined_tq; unsigned int tq_iface_penalty; @@ -1702,9 +1706,9 @@ static void batadv_iv_ogm_process(const struct sk_buff *skb, int ogm_offset, if (is_my_orig) { unsigned long *word; - int offset; + size_t offset; s32 bit_pos; - s16 if_num; + unsigned int if_num; u8 *weight; orig_neigh_node = batadv_iv_ogm_orig_get(bat_priv, @@ -2729,7 +2733,7 @@ static int batadv_iv_gw_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, struct batadv_neigh_ifinfo *router_ifinfo = NULL; struct batadv_neigh_node *router; struct batadv_gw_node *curr_gw; - int ret = -EINVAL; + int ret = 0; void *hdr; router = batadv_orig_router_get(gw_node->orig_node, BATADV_IF_DEFAULT); diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c index 27e165ac9302..c74f81341dab 100644 --- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -928,7 +928,7 @@ static int batadv_v_gw_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, struct batadv_neigh_ifinfo *router_ifinfo = NULL; struct batadv_neigh_node *router; struct batadv_gw_node *curr_gw; - int ret = -EINVAL; + int ret = 0; void *hdr; router = batadv_orig_router_get(gw_node->orig_node, BATADV_IF_DEFAULT); diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index fad47853ad3c..b1a08374088b 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -2161,22 +2161,25 @@ batadv_bla_claim_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq, { struct batadv_bla_claim *claim; int idx = 0; + int ret = 0; rcu_read_lock(); hlist_for_each_entry_rcu(claim, head, hash_entry) { if (idx++ < *idx_skip) continue; - if (batadv_bla_claim_dump_entry(msg, portid, seq, - primary_if, claim)) { + + ret = batadv_bla_claim_dump_entry(msg, portid, seq, + primary_if, claim); + if (ret) { *idx_skip = idx - 1; goto unlock; } } - *idx_skip = idx; + *idx_skip = 0; unlock: rcu_read_unlock(); - return 0; + return ret; } /** @@ -2391,22 +2394,25 @@ batadv_bla_backbone_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq, { struct batadv_bla_backbone_gw *backbone_gw; int idx = 0; + int ret = 0; rcu_read_lock(); hlist_for_each_entry_rcu(backbone_gw, head, hash_entry) { if (idx++ < *idx_skip) continue; - if (batadv_bla_backbone_dump_entry(msg, portid, seq, - primary_if, backbone_gw)) { + + ret = batadv_bla_backbone_dump_entry(msg, portid, seq, + primary_if, backbone_gw); + if (ret) { *idx_skip = idx - 1; goto unlock; } } - *idx_skip = idx; + *idx_skip = 0; unlock: rcu_read_unlock(); - return 0; + return ret; } /** diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 22dde42fd80e..5afe641ee4b0 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -288,7 +288,8 @@ batadv_frag_merge_packets(struct hlist_head *chain) /* Move the existing MAC header to just before the payload. (Override * the fragment header.) */ - skb_pull_rcsum(skb_out, hdr_size); + skb_pull(skb_out, hdr_size); + skb_out->ip_summed = CHECKSUM_NONE; memmove(skb_out->data - ETH_HLEN, skb_mac_header(skb_out), ETH_HLEN); skb_set_mac_header(skb_out, -ETH_HLEN); skb_reset_network_header(skb_out); diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 5f186bff284a..68b54a39c51d 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -763,6 +763,11 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, hard_iface->soft_iface = soft_iface; bat_priv = netdev_priv(hard_iface->soft_iface); + if (bat_priv->num_ifaces >= UINT_MAX) { + ret = -ENOSPC; + goto err_dev; + } + ret = netdev_master_upper_dev_link(hard_iface->net_dev, soft_iface, NULL, NULL, NULL); if (ret) @@ -876,7 +881,7 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface, batadv_hardif_recalc_extra_skbroom(hard_iface->soft_iface); /* nobody uses this interface anymore */ - if (!bat_priv->num_ifaces) { + if (bat_priv->num_ifaces == 0) { batadv_gw_check_client_stop(bat_priv); if (autodel == BATADV_IF_CLEANUP_AUTO) @@ -912,7 +917,7 @@ batadv_hardif_add_interface(struct net_device *net_dev) if (ret) goto free_if; - hard_iface->if_num = -1; + hard_iface->if_num = 0; hard_iface->net_dev = net_dev; hard_iface->soft_iface = NULL; hard_iface->if_status = BATADV_IF_NOT_IN_USE; diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 58a7d9274435..74782426bb77 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -1569,7 +1569,7 @@ int batadv_orig_dump(struct sk_buff *msg, struct netlink_callback *cb) * Return: 0 on success or negative error number in case of failure */ int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface, - int max_if_num) + unsigned int max_if_num) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); struct batadv_algo_ops *bao = bat_priv->algo_ops; @@ -1611,7 +1611,7 @@ err: * Return: 0 on success or negative error number in case of failure */ int batadv_orig_hash_del_if(struct batadv_hard_iface *hard_iface, - int max_if_num) + unsigned int max_if_num) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); struct batadv_hashtable *hash = bat_priv->orig_hash; diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index 8e543a3cdc6c..15d896b2de6f 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -73,9 +73,9 @@ int batadv_orig_seq_print_text(struct seq_file *seq, void *offset); int batadv_orig_dump(struct sk_buff *msg, struct netlink_callback *cb); int batadv_orig_hardif_seq_print_text(struct seq_file *seq, void *offset); int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface, - int max_if_num); + unsigned int max_if_num); int batadv_orig_hash_del_if(struct batadv_hard_iface *hard_iface, - int max_if_num); + unsigned int max_if_num); struct batadv_orig_node_vlan * batadv_orig_node_vlan_new(struct batadv_orig_node *orig_node, unsigned short vid); diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 900c5ce21cd4..367a81fb785f 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -459,13 +459,7 @@ void batadv_interface_rx(struct net_device *soft_iface, /* skb->dev & skb->pkt_type are set here */ skb->protocol = eth_type_trans(skb, soft_iface); - - /* should not be necessary anymore as we use skb_pull_rcsum() - * TODO: please verify this and remove this TODO - * -- Dec 21st 2009, Simon Wunderlich - */ - - /* skb->ip_summed = CHECKSUM_UNNECESSARY; */ + skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); batadv_inc_counter(bat_priv, BATADV_CNT_RX); batadv_add_counter(bat_priv, BATADV_CNT_RX_BYTES, diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index bb1578410e0c..a5aa6d61f4e2 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -167,7 +167,7 @@ struct batadv_hard_iface { struct list_head list; /** @if_num: identificator of the interface */ - s16 if_num; + unsigned int if_num; /** @if_status: status of the interface for batman-adv */ char if_status; @@ -1596,7 +1596,7 @@ struct batadv_priv { atomic_t batman_queue_left; /** @num_ifaces: number of interfaces assigned to this mesh interface */ - char num_ifaces; + unsigned int num_ifaces; /** @mesh_obj: kobject for sysfs mesh subdirectory */ struct kobject *mesh_obj; @@ -2186,15 +2186,16 @@ struct batadv_algo_orig_ops { * orig_node due to a new hard-interface being added into the mesh * (optional) */ - int (*add_if)(struct batadv_orig_node *orig_node, int max_if_num); + int (*add_if)(struct batadv_orig_node *orig_node, + unsigned int max_if_num); /** * @del_if: ask the routing algorithm to apply the needed changes to the * orig_node due to an hard-interface being removed from the mesh * (optional) */ - int (*del_if)(struct batadv_orig_node *orig_node, int max_if_num, - int del_if_num); + int (*del_if)(struct batadv_orig_node *orig_node, + unsigned int max_if_num, unsigned int del_if_num); #ifdef CONFIG_BATMAN_ADV_DEBUGFS /** @print: print the originator table (optional) */ diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 27f1d4f2114a..9b16eaf33819 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -214,7 +214,7 @@ static int br_validate_ipv4(struct net *net, struct sk_buff *skb) iph = ip_hdr(skb); if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl))) - goto inhdr_error; + goto csum_error; len = ntohs(iph->tot_len); if (skb->len < len) { @@ -236,6 +236,8 @@ static int br_validate_ipv4(struct net *net, struct sk_buff *skb) */ return 0; +csum_error: + __IP_INC_STATS(net, IPSTATS_MIB_CSUMERRORS); inhdr_error: __IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS); drop: diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 51935270c651..9896f4975353 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -168,6 +168,8 @@ static struct net_bridge_vlan *br_vlan_get_master(struct net_bridge *br, u16 vid masterv = br_vlan_find(vg, vid); if (WARN_ON(!masterv)) return NULL; + refcount_set(&masterv->refcnt, 1); + return masterv; } refcount_inc(&masterv->refcnt); diff --git a/net/bridge/netfilter/ebt_among.c b/net/bridge/netfilter/ebt_among.c index ce7152a12bd8..c5afb4232ecb 100644 --- a/net/bridge/netfilter/ebt_among.c +++ b/net/bridge/netfilter/ebt_among.c @@ -172,18 +172,35 @@ ebt_among_mt(const struct sk_buff *skb, struct xt_action_param *par) return true; } +static bool poolsize_invalid(const struct ebt_mac_wormhash *w) +{ + return w && w->poolsize >= (INT_MAX / sizeof(struct ebt_mac_wormhash_tuple)); +} + static int ebt_among_mt_check(const struct xt_mtchk_param *par) { const struct ebt_among_info *info = par->matchinfo; const struct ebt_entry_match *em = container_of(par->matchinfo, const struct ebt_entry_match, data); - int expected_length = sizeof(struct ebt_among_info); + unsigned int expected_length = sizeof(struct ebt_among_info); const struct ebt_mac_wormhash *wh_dst, *wh_src; int err; + if (expected_length > em->match_size) + return -EINVAL; + wh_dst = ebt_among_wh_dst(info); - wh_src = ebt_among_wh_src(info); + if (poolsize_invalid(wh_dst)) + return -EINVAL; + expected_length += ebt_mac_wormhash_size(wh_dst); + if (expected_length > em->match_size) + return -EINVAL; + + wh_src = ebt_among_wh_src(info); + if (poolsize_invalid(wh_src)) + return -EINVAL; + expected_length += ebt_mac_wormhash_size(wh_src); if (em->match_size != EBT_ALIGN(expected_length)) { diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 02c4b409d317..254ef9f49567 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1641,7 +1641,8 @@ static int compat_match_to_user(struct ebt_entry_match *m, void __user **dstptr, int off = ebt_compat_match_offset(match, m->match_size); compat_uint_t msize = m->match_size - off; - BUG_ON(off >= m->match_size); + if (WARN_ON(off >= m->match_size)) + return -EINVAL; if (copy_to_user(cm->u.name, match->name, strlen(match->name) + 1) || put_user(msize, &cm->match_size)) @@ -1671,7 +1672,8 @@ static int compat_target_to_user(struct ebt_entry_target *t, int off = xt_compat_target_offset(target); compat_uint_t tsize = t->target_size - off; - BUG_ON(off >= t->target_size); + if (WARN_ON(off >= t->target_size)) + return -EINVAL; if (copy_to_user(cm->u.name, target->name, strlen(target->name) + 1) || put_user(tsize, &cm->match_size)) @@ -1902,7 +1904,8 @@ static int ebt_buf_add(struct ebt_entries_buf_state *state, if (state->buf_kern_start == NULL) goto count_only; - BUG_ON(state->buf_kern_offset + sz > state->buf_kern_len); + if (WARN_ON(state->buf_kern_offset + sz > state->buf_kern_len)) + return -EINVAL; memcpy(state->buf_kern_start + state->buf_kern_offset, data, sz); @@ -1915,7 +1918,8 @@ static int ebt_buf_add_pad(struct ebt_entries_buf_state *state, unsigned int sz) { char *b = state->buf_kern_start; - BUG_ON(b && state->buf_kern_offset > state->buf_kern_len); + if (WARN_ON(b && state->buf_kern_offset > state->buf_kern_len)) + return -EINVAL; if (b != NULL && sz > 0) memset(b + state->buf_kern_offset, 0, sz); @@ -1992,8 +1996,10 @@ static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt, pad = XT_ALIGN(size_kern) - size_kern; if (pad > 0 && dst) { - BUG_ON(state->buf_kern_len <= pad); - BUG_ON(state->buf_kern_offset - (match_size + off) + size_kern > state->buf_kern_len - pad); + if (WARN_ON(state->buf_kern_len <= pad)) + return -EINVAL; + if (WARN_ON(state->buf_kern_offset - (match_size + off) + size_kern > state->buf_kern_len - pad)) + return -EINVAL; memset(dst + size_kern, 0, pad); } return off + match_size; @@ -2043,7 +2049,8 @@ static int ebt_size_mwt(struct compat_ebt_entry_mwt *match32, if (ret < 0) return ret; - BUG_ON(ret < match32->match_size); + if (WARN_ON(ret < match32->match_size)) + return -EINVAL; growth += ret - match32->match_size; growth += ebt_compat_entry_padsize(); @@ -2053,7 +2060,9 @@ static int ebt_size_mwt(struct compat_ebt_entry_mwt *match32, if (match_kern) match_kern->match_size = ret; - WARN_ON(type == EBT_COMPAT_TARGET && size_left); + if (WARN_ON(type == EBT_COMPAT_TARGET && size_left)) + return -EINVAL; + match32 = (struct compat_ebt_entry_mwt *) buf; } @@ -2109,6 +2118,15 @@ static int size_entry_mwt(struct ebt_entry *entry, const unsigned char *base, * * offsets are relative to beginning of struct ebt_entry (i.e., 0). */ + for (i = 0; i < 4 ; ++i) { + if (offsets[i] >= *total) + return -EINVAL; + if (i == 0) + continue; + if (offsets[i-1] > offsets[i]) + return -EINVAL; + } + for (i = 0, j = 1 ; j < 4 ; j++, i++) { struct compat_ebt_entry_mwt *match32; unsigned int size; @@ -2140,7 +2158,8 @@ static int size_entry_mwt(struct ebt_entry *entry, const unsigned char *base, startoff = state->buf_user_offset - startoff; - BUG_ON(*total < startoff); + if (WARN_ON(*total < startoff)) + return -EINVAL; *total -= startoff; return 0; } @@ -2267,7 +2286,8 @@ static int compat_do_replace(struct net *net, void __user *user, state.buf_kern_len = size64; ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state); - BUG_ON(ret < 0); /* parses same data again */ + if (WARN_ON(ret < 0)) + goto out_unlock; vfree(entries_tmp); tmp.entries_size = size64; diff --git a/net/core/dev.c b/net/core/dev.c index d4362befe7e2..2cedf520cb28 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6396,6 +6396,7 @@ static int __netdev_upper_dev_link(struct net_device *dev, .linking = true, .upper_info = upper_info, }; + struct net_device *master_dev; int ret = 0; ASSERT_RTNL(); @@ -6407,11 +6408,14 @@ static int __netdev_upper_dev_link(struct net_device *dev, if (netdev_has_upper_dev(upper_dev, dev)) return -EBUSY; - if (netdev_has_upper_dev(dev, upper_dev)) - return -EEXIST; - - if (master && netdev_master_upper_dev_get(dev)) - return -EBUSY; + if (!master) { + if (netdev_has_upper_dev(dev, upper_dev)) + return -EEXIST; + } else { + master_dev = netdev_master_upper_dev_get(dev); + if (master_dev) + return master_dev == upper_dev ? -EEXIST : -EBUSY; + } ret = call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, &changeupper_info.info); diff --git a/net/core/devlink.c b/net/core/devlink.c index 18d385ed8237..2f2307d94787 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -1695,10 +1695,11 @@ static int devlink_dpipe_table_put(struct sk_buff *skb, goto nla_put_failure; if (table->resource_valid) { - nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_ID, - table->resource_id, DEVLINK_ATTR_PAD); - nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_UNITS, - table->resource_units, DEVLINK_ATTR_PAD); + if (nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_ID, + table->resource_id, DEVLINK_ATTR_PAD) || + nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_UNITS, + table->resource_units, DEVLINK_ATTR_PAD)) + goto nla_put_failure; } if (devlink_dpipe_matches_put(table, skb)) goto nla_put_failure; @@ -2332,7 +2333,7 @@ devlink_resource_validate_children(struct devlink_resource *resource) list_for_each_entry(child_resource, &resource->resource_list, list) parts_size += child_resource->size_new; - if (parts_size > resource->size) + if (parts_size > resource->size_new) size_valid = false; out: resource->size_valid = size_valid; @@ -2372,20 +2373,22 @@ static int devlink_nl_cmd_resource_set(struct sk_buff *skb, return 0; } -static void +static int devlink_resource_size_params_put(struct devlink_resource *resource, struct sk_buff *skb) { struct devlink_resource_size_params *size_params; - size_params = resource->size_params; - nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_GRAN, - size_params->size_granularity, DEVLINK_ATTR_PAD); - nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_MAX, - size_params->size_max, DEVLINK_ATTR_PAD); - nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_MIN, - size_params->size_min, DEVLINK_ATTR_PAD); - nla_put_u8(skb, DEVLINK_ATTR_RESOURCE_UNIT, size_params->unit); + size_params = &resource->size_params; + if (nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_GRAN, + size_params->size_granularity, DEVLINK_ATTR_PAD) || + nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_MAX, + size_params->size_max, DEVLINK_ATTR_PAD) || + nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_MIN, + size_params->size_min, DEVLINK_ATTR_PAD) || + nla_put_u8(skb, DEVLINK_ATTR_RESOURCE_UNIT, size_params->unit)) + return -EMSGSIZE; + return 0; } static int devlink_resource_put(struct devlink *devlink, struct sk_buff *skb, @@ -2409,10 +2412,12 @@ static int devlink_resource_put(struct devlink *devlink, struct sk_buff *skb, nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_NEW, resource->size_new, DEVLINK_ATTR_PAD); if (resource->resource_ops && resource->resource_ops->occ_get) - nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_OCC, - resource->resource_ops->occ_get(devlink), - DEVLINK_ATTR_PAD); - devlink_resource_size_params_put(resource, skb); + if (nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_OCC, + resource->resource_ops->occ_get(devlink), + DEVLINK_ATTR_PAD)) + goto nla_put_failure; + if (devlink_resource_size_params_put(resource, skb)) + goto nla_put_failure; if (list_empty(&resource->resource_list)) goto out; @@ -3151,7 +3156,7 @@ int devlink_resource_register(struct devlink *devlink, u64 resource_size, u64 resource_id, u64 parent_resource_id, - struct devlink_resource_size_params *size_params, + const struct devlink_resource_size_params *size_params, const struct devlink_resource_ops *resource_ops) { struct devlink_resource *resource; @@ -3194,7 +3199,8 @@ int devlink_resource_register(struct devlink *devlink, resource->id = resource_id; resource->resource_ops = resource_ops; resource->size_valid = true; - resource->size_params = size_params; + memcpy(&resource->size_params, size_params, + sizeof(resource->size_params)); INIT_LIST_HEAD(&resource->resource_list); list_add_tail(&resource->list, resource_list); out: diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 494e6a5d7306..3f89c76d5c24 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -2520,11 +2520,14 @@ static int set_phy_tunable(struct net_device *dev, void __user *useraddr) static int ethtool_get_fecparam(struct net_device *dev, void __user *useraddr) { struct ethtool_fecparam fecparam = { ETHTOOL_GFECPARAM }; + int rc; if (!dev->ethtool_ops->get_fecparam) return -EOPNOTSUPP; - dev->ethtool_ops->get_fecparam(dev, &fecparam); + rc = dev->ethtool_ops->get_fecparam(dev, &fecparam); + if (rc) + return rc; if (copy_to_user(useraddr, &fecparam, sizeof(fecparam))) return -EFAULT; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 09bd89c90a71..0bb0d8877954 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4891,7 +4891,7 @@ EXPORT_SYMBOL_GPL(skb_scrub_packet); * * The MAC/L2 or network (IP, IPv6) headers are not accounted for. */ -unsigned int skb_gso_transport_seglen(const struct sk_buff *skb) +static unsigned int skb_gso_transport_seglen(const struct sk_buff *skb) { const struct skb_shared_info *shinfo = skb_shinfo(skb); unsigned int thlen = 0; @@ -4913,7 +4913,40 @@ unsigned int skb_gso_transport_seglen(const struct sk_buff *skb) */ return thlen + shinfo->gso_size; } -EXPORT_SYMBOL_GPL(skb_gso_transport_seglen); + +/** + * skb_gso_network_seglen - Return length of individual segments of a gso packet + * + * @skb: GSO skb + * + * skb_gso_network_seglen is used to determine the real size of the + * individual segments, including Layer3 (IP, IPv6) and L4 headers (TCP/UDP). + * + * The MAC/L2 header is not accounted for. + */ +static unsigned int skb_gso_network_seglen(const struct sk_buff *skb) +{ + unsigned int hdr_len = skb_transport_header(skb) - + skb_network_header(skb); + + return hdr_len + skb_gso_transport_seglen(skb); +} + +/** + * skb_gso_mac_seglen - Return length of individual segments of a gso packet + * + * @skb: GSO skb + * + * skb_gso_mac_seglen is used to determine the real size of the + * individual segments, including MAC/L2, Layer3 (IP, IPv6) and L4 + * headers (TCP/UDP). + */ +static unsigned int skb_gso_mac_seglen(const struct sk_buff *skb) +{ + unsigned int hdr_len = skb_transport_header(skb) - skb_mac_header(skb); + + return hdr_len + skb_gso_transport_seglen(skb); +} /** * skb_gso_size_check - check the skb size, considering GSO_BY_FRAGS @@ -4955,19 +4988,20 @@ static inline bool skb_gso_size_check(const struct sk_buff *skb, } /** - * skb_gso_validate_mtu - Return in case such skb fits a given MTU + * skb_gso_validate_network_len - Will a split GSO skb fit into a given MTU? * * @skb: GSO skb * @mtu: MTU to validate against * - * skb_gso_validate_mtu validates if a given skb will fit a wanted MTU - * once split. + * skb_gso_validate_network_len validates if a given skb will fit a + * wanted MTU once split. It considers L3 headers, L4 headers, and the + * payload. */ -bool skb_gso_validate_mtu(const struct sk_buff *skb, unsigned int mtu) +bool skb_gso_validate_network_len(const struct sk_buff *skb, unsigned int mtu) { return skb_gso_size_check(skb, skb_gso_network_seglen(skb), mtu); } -EXPORT_SYMBOL_GPL(skb_gso_validate_mtu); +EXPORT_SYMBOL_GPL(skb_gso_validate_network_len); /** * skb_gso_validate_mac_len - Will a split GSO skb fit in a given length? diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 2dd21c3281a1..b54b948b0596 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -55,7 +55,7 @@ static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) if (skb->ignore_df) return false; - if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu)) + if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) return false; return true; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 45d97e9b2759..0901de42ed85 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -970,9 +970,6 @@ static void __gre_tunnel_init(struct net_device *dev) t_hlen = tunnel->hlen + sizeof(struct iphdr); - dev->needed_headroom = LL_MAX_HEADER + t_hlen + 4; - dev->mtu = ETH_DATA_LEN - t_hlen - 4; - dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; @@ -1290,8 +1287,6 @@ static int erspan_tunnel_init(struct net_device *dev) erspan_hdr_len(tunnel->erspan_ver); t_hlen = tunnel->hlen + sizeof(struct iphdr); - dev->needed_headroom = LL_MAX_HEADER + t_hlen + 4; - dev->mtu = ETH_DATA_LEN - t_hlen - 4; dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index e8e675be60ec..66340ab750e6 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -248,7 +248,7 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk, /* common case: seglen is <= mtu */ - if (skb_gso_validate_mtu(skb, mtu)) + if (skb_gso_validate_network_len(skb, mtu)) return ip_finish_output2(net, sk, skb); /* Slowpath - GSO segment length exceeds the egress MTU. diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index d786a8441bce..6d21068f9b55 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -710,16 +710,9 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, } } - if (tunnel->fwmark) { - init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr, - tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link, - tunnel->fwmark); - } - else { - init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr, - tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link, - skb->mark); - } + init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr, + tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link, + tunnel->fwmark); if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0) goto tx_error; diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 4b02ab39ebc5..8a8ae61cea71 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -232,7 +232,6 @@ clusterip_config_init(struct net *net, const struct ipt_clusterip_tgt_info *i, c->hash_mode = i->hash_mode; c->hash_initval = i->hash_initval; refcount_set(&c->refcount, 1); - refcount_set(&c->entries, 1); spin_lock_bh(&cn->lock); if (__clusterip_config_find(net, ip)) { @@ -263,8 +262,10 @@ clusterip_config_init(struct net *net, const struct ipt_clusterip_tgt_info *i, c->notifier.notifier_call = clusterip_netdev_event; err = register_netdevice_notifier(&c->notifier); - if (!err) + if (!err) { + refcount_set(&c->entries, 1); return c; + } #ifdef CONFIG_PROC_FS proc_remove(c->pde); @@ -273,7 +274,7 @@ err: spin_lock_bh(&cn->lock); list_del_rcu(&c->list); spin_unlock_bh(&cn->lock); - kfree(c); + clusterip_config_put(c); return ERR_PTR(err); } @@ -496,12 +497,15 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par) return PTR_ERR(config); } } - cipinfo->config = config; ret = nf_ct_netns_get(par->net, par->family); - if (ret < 0) + if (ret < 0) { pr_info("cannot load conntrack support for proto=%u\n", par->family); + clusterip_config_entry_put(par->net, config); + clusterip_config_put(config); + return ret; + } if (!par->net->xt.clusterip_deprecated_warning) { pr_info("ipt_CLUSTERIP is deprecated and it will removed soon, " @@ -509,6 +513,7 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par) par->net->xt.clusterip_deprecated_warning = true; } + cipinfo->config = config; return ret; } diff --git a/net/ipv4/netfilter/nf_flow_table_ipv4.c b/net/ipv4/netfilter/nf_flow_table_ipv4.c index 25d2975da156..0cd46bffa469 100644 --- a/net/ipv4/netfilter/nf_flow_table_ipv4.c +++ b/net/ipv4/netfilter/nf_flow_table_ipv4.c @@ -111,6 +111,7 @@ static int nf_flow_dnat_ip(const struct flow_offload *flow, struct sk_buff *skb, default: return -1; } + csum_replace4(&iph->check, addr, new_addr); return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr); } @@ -185,7 +186,7 @@ static bool __nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) if ((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) return false; - if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu)) + if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) return false; return true; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index a4f44d815a61..860b3fd2f54b 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -128,10 +128,11 @@ static int ip_rt_redirect_silence __read_mostly = ((HZ / 50) << (9 + 1)); static int ip_rt_error_cost __read_mostly = HZ; static int ip_rt_error_burst __read_mostly = 5 * HZ; static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ; -static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20; +static u32 ip_rt_min_pmtu __read_mostly = 512 + 20 + 20; static int ip_rt_min_advmss __read_mostly = 256; static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; + /* * Interface to generic destination cache. */ @@ -930,14 +931,23 @@ out_put_peer: static int ip_error(struct sk_buff *skb) { - struct in_device *in_dev = __in_dev_get_rcu(skb->dev); struct rtable *rt = skb_rtable(skb); + struct net_device *dev = skb->dev; + struct in_device *in_dev; struct inet_peer *peer; unsigned long now; struct net *net; bool send; int code; + if (netif_is_l3_master(skb->dev)) { + dev = __dev_get_by_index(dev_net(skb->dev), IPCB(skb)->iif); + if (!dev) + goto out; + } + + in_dev = __in_dev_get_rcu(dev); + /* IP on this device is disabled. */ if (!in_dev) goto out; @@ -2818,6 +2828,7 @@ void ip_rt_multicast_event(struct in_device *in_dev) static int ip_rt_gc_interval __read_mostly = 60 * HZ; static int ip_rt_gc_min_interval __read_mostly = HZ / 2; static int ip_rt_gc_elasticity __read_mostly = 8; +static int ip_min_valid_pmtu __read_mostly = IPV4_MIN_MTU; static int ipv4_sysctl_rtcache_flush(struct ctl_table *__ctl, int write, void __user *buffer, @@ -2933,7 +2944,8 @@ static struct ctl_table ipv4_route_table[] = { .data = &ip_rt_min_pmtu, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = &ip_min_valid_pmtu, }, { .procname = "min_adv_mss", diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c index 7c843578f233..faddf4f9a707 100644 --- a/net/ipv4/tcp_illinois.c +++ b/net/ipv4/tcp_illinois.c @@ -6,7 +6,7 @@ * The algorithm is described in: * "TCP-Illinois: A Loss and Delay-Based Congestion Control Algorithm * for High-Speed Networks" - * http://www.ifp.illinois.edu/~srikant/Papers/liubassri06perf.pdf + * http://tamerbasar.csl.illinois.edu/LiuBasarSrikantPerfEvalArtJun2008.pdf * * Implemented from description in paper and ns-2 simulation. * Copyright (C) 2007 Stephen Hemminger <shemminger@linux-foundation.org> diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 575d3c1fb6e8..9a1b3c1c1c14 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1971,11 +1971,6 @@ void tcp_enter_loss(struct sock *sk) /* F-RTO RFC5682 sec 3.1 step 1: retransmit SND.UNA if no previous * loss recovery is underway except recurring timeout(s) on * the same SND.UNA (sec 3.2). Disable F-RTO on path MTU probing - * - * In theory F-RTO can be used repeatedly during loss recovery. - * In practice this interacts badly with broken middle-boxes that - * falsely raise the receive window, which results in repeated - * timeouts and stop-and-go behavior. */ tp->frto = net->ipv4.sysctl_tcp_frto && (new_recovery || icsk->icsk_retransmits) && @@ -2631,18 +2626,14 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack, tcp_try_undo_loss(sk, false)) return; - /* The ACK (s)acks some never-retransmitted data meaning not all - * the data packets before the timeout were lost. Therefore we - * undo the congestion window and state. This is essentially - * the operation in F-RTO (RFC5682 section 3.1 step 3.b). Since - * a retransmitted skb is permantly marked, we can apply such an - * operation even if F-RTO was not used. - */ - if ((flag & FLAG_ORIG_SACK_ACKED) && - tcp_try_undo_loss(sk, tp->undo_marker)) - return; - if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */ + /* Step 3.b. A timeout is spurious if not all data are + * lost, i.e., never-retransmitted data are (s)acked. + */ + if ((flag & FLAG_ORIG_SACK_ACKED) && + tcp_try_undo_loss(sk, true)) + return; + if (after(tp->snd_nxt, tp->high_seq)) { if (flag & FLAG_DATA_SACKED || is_dupack) tp->frto = 0; /* Step 3.a. loss was real */ @@ -4001,6 +3992,7 @@ void tcp_reset(struct sock *sk) /* This barrier is coupled with smp_rmb() in tcp_poll() */ smp_wmb(); + tcp_write_queue_purge(sk); tcp_done(sk); if (!sock_flag(sk, SOCK_DEAD)) diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index 94b8702603bc..be980c195fc5 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -30,7 +30,8 @@ static int xfrm4_tunnel_check_size(struct sk_buff *skb) mtu = dst_mtu(skb_dst(skb)); if ((!skb_is_gso(skb) && skb->len > mtu) || - (skb_is_gso(skb) && skb_gso_network_seglen(skb) > ip_skb_dst_mtu(skb->sk, skb))) { + (skb_is_gso(skb) && + !skb_gso_validate_network_len(skb, ip_skb_dst_mtu(skb->sk, skb)))) { skb->protocol = htons(ETH_P_IP); if (skb->sk) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 997c7f19ad62..a8a919520090 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -412,7 +412,7 @@ static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) if (skb->ignore_df) return false; - if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu)) + if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) return false; return true; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 4b15fe928278..6e0f21eed88a 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1982,14 +1982,14 @@ static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev, { struct net *net = dev_net(dev); struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); - struct ip6_tnl *nt, *t; struct ip_tunnel_encap ipencap; + struct ip6_tnl *nt, *t; + int err; nt = netdev_priv(dev); if (ip6_tnl_netlink_encap_parms(data, &ipencap)) { - int err = ip6_tnl_encap_setup(nt, &ipencap); - + err = ip6_tnl_encap_setup(nt, &ipencap); if (err < 0) return err; } @@ -2005,7 +2005,11 @@ static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev, return -EEXIST; } - return ip6_tnl_create2(dev); + err = ip6_tnl_create2(dev); + if (!err && tb[IFLA_MTU]) + ip6_tnl_change_mtu(dev, nla_get_u32(tb[IFLA_MTU])); + + return err; } static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[], diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index d95ceca7ff8f..531d6957af36 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -21,18 +21,19 @@ int ip6_route_me_harder(struct net *net, struct sk_buff *skb) { const struct ipv6hdr *iph = ipv6_hdr(skb); + struct sock *sk = sk_to_full_sk(skb->sk); unsigned int hh_len; struct dst_entry *dst; struct flowi6 fl6 = { - .flowi6_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0, + .flowi6_oif = sk ? sk->sk_bound_dev_if : 0, .flowi6_mark = skb->mark, - .flowi6_uid = sock_net_uid(net, skb->sk), + .flowi6_uid = sock_net_uid(net, sk), .daddr = iph->daddr, .saddr = iph->saddr, }; int err; - dst = ip6_route_output(net, skb->sk, &fl6); + dst = ip6_route_output(net, sk, &fl6); err = dst->error; if (err) { IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); @@ -50,7 +51,7 @@ int ip6_route_me_harder(struct net *net, struct sk_buff *skb) if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && xfrm_decode_session(skb, flowi6_to_flowi(&fl6), AF_INET6) == 0) { skb_dst_set(skb, NULL); - dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), skb->sk, 0); + dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), sk, 0); if (IS_ERR(dst)) return PTR_ERR(dst); skb_dst_set(skb, dst); diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c index 94deb69bbbda..91ed25a24b79 100644 --- a/net/ipv6/netfilter/ip6t_rpfilter.c +++ b/net/ipv6/netfilter/ip6t_rpfilter.c @@ -48,10 +48,6 @@ static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb, } fl6.flowi6_mark = flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0; - if ((flags & XT_RPFILTER_LOOSE) == 0) { - fl6.flowi6_oif = dev->ifindex; - lookup_flags |= RT6_LOOKUP_F_IFACE; - } rt = (void *) ip6_route_lookup(net, &fl6, lookup_flags); if (rt->dst.error) diff --git a/net/ipv6/netfilter/nf_flow_table_ipv6.c b/net/ipv6/netfilter/nf_flow_table_ipv6.c index d346705d6ee6..207cb35569b1 100644 --- a/net/ipv6/netfilter/nf_flow_table_ipv6.c +++ b/net/ipv6/netfilter/nf_flow_table_ipv6.c @@ -178,7 +178,7 @@ static bool __nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) if (skb->len <= mtu) return false; - if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu)) + if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) return false; return true; diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c index bed57ee65f7b..6b7f075f811f 100644 --- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c @@ -99,6 +99,10 @@ static bool nf_nat_ipv6_manip_pkt(struct sk_buff *skb, !l4proto->manip_pkt(skb, &nf_nat_l3proto_ipv6, iphdroff, hdroff, target, maniptype)) return false; + + /* must reload, offset might have changed */ + ipv6h = (void *)skb->data + iphdroff; + manip_addr: if (maniptype == NF_NAT_MANIP_SRC) ipv6h->saddr = target->src.u3.in6; diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c index cc5174c7254c..62fc84d7bdff 100644 --- a/net/ipv6/netfilter/nft_fib_ipv6.c +++ b/net/ipv6/netfilter/nft_fib_ipv6.c @@ -180,7 +180,6 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, } *dest = 0; - again: rt = (void *)ip6_route_lookup(nft_net(pkt), &fl6, lookup_flags); if (rt->dst.error) goto put_rt_err; @@ -189,15 +188,8 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, if (rt->rt6i_flags & (RTF_REJECT | RTF_ANYCAST | RTF_LOCAL)) goto put_rt_err; - if (oif && oif != rt->rt6i_idev->dev) { - /* multipath route? Try again with F_IFACE */ - if ((lookup_flags & RT6_LOOKUP_F_IFACE) == 0) { - lookup_flags |= RT6_LOOKUP_F_IFACE; - fl6.flowi6_oif = oif->ifindex; - ip6_rt_put(rt); - goto again; - } - } + if (oif && oif != rt->rt6i_idev->dev) + goto put_rt_err; switch (priv->result) { case NFT_FIB_RESULT_OIF: diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 3a1775a62973..0195598f7bb5 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1578,6 +1578,13 @@ static int ipip6_newlink(struct net *src_net, struct net_device *dev, if (err < 0) return err; + if (tb[IFLA_MTU]) { + u32 mtu = nla_get_u32(tb[IFLA_MTU]); + + if (mtu >= IPV6_MIN_MTU && mtu <= 0xFFF8 - dev->hard_header_len) + dev->mtu = mtu; + } + #ifdef CONFIG_IPV6_SIT_6RD if (ipip6_netlink_6rd_parms(data, &ip6rd)) err = ipip6_tunnel_update_6rd(nt, &ip6rd); diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 8ae87d4ec5ff..5959ce9620eb 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -82,7 +82,7 @@ static int xfrm6_tunnel_check_size(struct sk_buff *skb) if ((!skb_is_gso(skb) && skb->len > mtu) || (skb_is_gso(skb) && - skb_gso_network_seglen(skb) > ip6_skb_dst_mtu(skb))) { + !skb_gso_validate_network_len(skb, ip6_skb_dst_mtu(skb)))) { skb->dev = dst->dev; skb->protocol = htons(ETH_P_IPV6); diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 194a7483bb93..83421c6f0bef 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -136,51 +136,6 @@ l2tp_session_id_hash_2(struct l2tp_net *pn, u32 session_id) } -/* Lookup the tunnel socket, possibly involving the fs code if the socket is - * owned by userspace. A struct sock returned from this function must be - * released using l2tp_tunnel_sock_put once you're done with it. - */ -static struct sock *l2tp_tunnel_sock_lookup(struct l2tp_tunnel *tunnel) -{ - int err = 0; - struct socket *sock = NULL; - struct sock *sk = NULL; - - if (!tunnel) - goto out; - - if (tunnel->fd >= 0) { - /* Socket is owned by userspace, who might be in the process - * of closing it. Look the socket up using the fd to ensure - * consistency. - */ - sock = sockfd_lookup(tunnel->fd, &err); - if (sock) - sk = sock->sk; - } else { - /* Socket is owned by kernelspace */ - sk = tunnel->sock; - sock_hold(sk); - } - -out: - return sk; -} - -/* Drop a reference to a tunnel socket obtained via. l2tp_tunnel_sock_put */ -static void l2tp_tunnel_sock_put(struct sock *sk) -{ - struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk); - if (tunnel) { - if (tunnel->fd >= 0) { - /* Socket is owned by userspace */ - sockfd_put(sk->sk_socket); - } - sock_put(sk); - } - sock_put(sk); -} - /* Session hash list. * The session_id SHOULD be random according to RFC2661, but several * L2TP implementations (Cisco and Microsoft) use incrementing @@ -193,6 +148,13 @@ l2tp_session_id_hash(struct l2tp_tunnel *tunnel, u32 session_id) return &tunnel->session_hlist[hash_32(session_id, L2TP_HASH_BITS)]; } +void l2tp_tunnel_free(struct l2tp_tunnel *tunnel) +{ + sock_put(tunnel->sock); + /* the tunnel is freed in the socket destructor */ +} +EXPORT_SYMBOL(l2tp_tunnel_free); + /* Lookup a tunnel. A new reference is held on the returned tunnel. */ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id) { @@ -345,13 +307,11 @@ int l2tp_session_register(struct l2tp_session *session, } l2tp_tunnel_inc_refcount(tunnel); - sock_hold(tunnel->sock); hlist_add_head_rcu(&session->global_hlist, g_head); spin_unlock_bh(&pn->l2tp_session_hlist_lock); } else { l2tp_tunnel_inc_refcount(tunnel); - sock_hold(tunnel->sock); } hlist_add_head(&session->hlist, head); @@ -969,7 +929,7 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct l2tp_tunnel *tunnel; - tunnel = l2tp_sock_to_tunnel(sk); + tunnel = l2tp_tunnel(sk); if (tunnel == NULL) goto pass_up; @@ -977,13 +937,10 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) tunnel->name, skb->len); if (l2tp_udp_recv_core(tunnel, skb, tunnel->recv_payload_hook)) - goto pass_up_put; + goto pass_up; - sock_put(sk); return 0; -pass_up_put: - sock_put(sk); pass_up: return 1; } @@ -1207,14 +1164,12 @@ EXPORT_SYMBOL_GPL(l2tp_xmit_skb); static void l2tp_tunnel_destruct(struct sock *sk) { struct l2tp_tunnel *tunnel = l2tp_tunnel(sk); - struct l2tp_net *pn; if (tunnel == NULL) goto end; l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: closing...\n", tunnel->name); - /* Disable udp encapsulation */ switch (tunnel->encap) { case L2TP_ENCAPTYPE_UDP: @@ -1231,18 +1186,11 @@ static void l2tp_tunnel_destruct(struct sock *sk) sk->sk_destruct = tunnel->old_sk_destruct; sk->sk_user_data = NULL; - /* Remove the tunnel struct from the tunnel list */ - pn = l2tp_pernet(tunnel->l2tp_net); - spin_lock_bh(&pn->l2tp_tunnel_list_lock); - list_del_rcu(&tunnel->list); - spin_unlock_bh(&pn->l2tp_tunnel_list_lock); - - tunnel->sock = NULL; - l2tp_tunnel_dec_refcount(tunnel); - /* Call the original destructor */ if (sk->sk_destruct) (*sk->sk_destruct)(sk); + + kfree_rcu(tunnel, rcu); end: return; } @@ -1303,49 +1251,43 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_closeall); /* Tunnel socket destroy hook for UDP encapsulation */ static void l2tp_udp_encap_destroy(struct sock *sk) { - struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk); - if (tunnel) { - l2tp_tunnel_closeall(tunnel); - sock_put(sk); - } + struct l2tp_tunnel *tunnel = l2tp_tunnel(sk); + + if (tunnel) + l2tp_tunnel_delete(tunnel); } /* Workqueue tunnel deletion function */ static void l2tp_tunnel_del_work(struct work_struct *work) { - struct l2tp_tunnel *tunnel = NULL; - struct socket *sock = NULL; - struct sock *sk = NULL; - - tunnel = container_of(work, struct l2tp_tunnel, del_work); + struct l2tp_tunnel *tunnel = container_of(work, struct l2tp_tunnel, + del_work); + struct sock *sk = tunnel->sock; + struct socket *sock = sk->sk_socket; + struct l2tp_net *pn; l2tp_tunnel_closeall(tunnel); - sk = l2tp_tunnel_sock_lookup(tunnel); - if (!sk) - goto out; - - sock = sk->sk_socket; - - /* If the tunnel socket was created by userspace, then go through the - * inet layer to shut the socket down, and let userspace close it. - * Otherwise, if we created the socket directly within the kernel, use + /* If the tunnel socket was created within the kernel, use * the sk API to release it here. - * In either case the tunnel resources are freed in the socket - * destructor when the tunnel socket goes away. */ - if (tunnel->fd >= 0) { - if (sock) - inet_shutdown(sock, 2); - } else { + if (tunnel->fd < 0) { if (sock) { kernel_sock_shutdown(sock, SHUT_RDWR); sock_release(sock); } } - l2tp_tunnel_sock_put(sk); -out: + /* Remove the tunnel struct from the tunnel list */ + pn = l2tp_pernet(tunnel->l2tp_net); + spin_lock_bh(&pn->l2tp_tunnel_list_lock); + list_del_rcu(&tunnel->list); + spin_unlock_bh(&pn->l2tp_tunnel_list_lock); + + /* drop initial ref */ + l2tp_tunnel_dec_refcount(tunnel); + + /* drop workqueue ref */ l2tp_tunnel_dec_refcount(tunnel); } @@ -1598,13 +1540,22 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 sk->sk_user_data = tunnel; } + /* Bump the reference count. The tunnel context is deleted + * only when this drops to zero. A reference is also held on + * the tunnel socket to ensure that it is not released while + * the tunnel is extant. Must be done before sk_destruct is + * set. + */ + refcount_set(&tunnel->ref_count, 1); + sock_hold(sk); + tunnel->sock = sk; + tunnel->fd = fd; + /* Hook on the tunnel socket destructor so that we can cleanup * if the tunnel socket goes away. */ tunnel->old_sk_destruct = sk->sk_destruct; sk->sk_destruct = &l2tp_tunnel_destruct; - tunnel->sock = sk; - tunnel->fd = fd; lockdep_set_class_and_name(&sk->sk_lock.slock, &l2tp_socket_class, "l2tp_sock"); sk->sk_allocation = GFP_ATOMIC; @@ -1614,11 +1565,6 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 /* Add tunnel to our list */ INIT_LIST_HEAD(&tunnel->list); - - /* Bump the reference count. The tunnel context is deleted - * only when this drops to zero. Must be done before list insertion - */ - refcount_set(&tunnel->ref_count, 1); spin_lock_bh(&pn->l2tp_tunnel_list_lock); list_add_rcu(&tunnel->list, &pn->l2tp_tunnel_list); spin_unlock_bh(&pn->l2tp_tunnel_list_lock); @@ -1659,8 +1605,6 @@ void l2tp_session_free(struct l2tp_session *session) if (tunnel) { BUG_ON(tunnel->magic != L2TP_TUNNEL_MAGIC); - sock_put(tunnel->sock); - session->tunnel = NULL; l2tp_tunnel_dec_refcount(tunnel); } diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 9bbee90e9963..a1aa9550f04e 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -214,27 +214,8 @@ static inline void *l2tp_session_priv(struct l2tp_session *session) return &session->priv[0]; } -static inline struct l2tp_tunnel *l2tp_sock_to_tunnel(struct sock *sk) -{ - struct l2tp_tunnel *tunnel; - - if (sk == NULL) - return NULL; - - sock_hold(sk); - tunnel = (struct l2tp_tunnel *)(sk->sk_user_data); - if (tunnel == NULL) { - sock_put(sk); - goto out; - } - - BUG_ON(tunnel->magic != L2TP_TUNNEL_MAGIC); - -out: - return tunnel; -} - struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id); +void l2tp_tunnel_free(struct l2tp_tunnel *tunnel); struct l2tp_session *l2tp_session_get(const struct net *net, struct l2tp_tunnel *tunnel, @@ -283,7 +264,7 @@ static inline void l2tp_tunnel_inc_refcount(struct l2tp_tunnel *tunnel) static inline void l2tp_tunnel_dec_refcount(struct l2tp_tunnel *tunnel) { if (refcount_dec_and_test(&tunnel->ref_count)) - kfree_rcu(tunnel, rcu); + l2tp_tunnel_free(tunnel); } /* Session reference counts. Incremented when code obtains a reference diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index ff61124fdf59..3428fba6f2b7 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -234,17 +234,13 @@ static void l2tp_ip_close(struct sock *sk, long timeout) static void l2tp_ip_destroy_sock(struct sock *sk) { struct sk_buff *skb; - struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk); + struct l2tp_tunnel *tunnel = sk->sk_user_data; while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL) kfree_skb(skb); - if (tunnel) { - l2tp_tunnel_closeall(tunnel); - sock_put(sk); - } - - sk_refcnt_debug_dec(sk); + if (tunnel) + l2tp_tunnel_delete(tunnel); } static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 192344688c06..6f009eaa5fbe 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -248,16 +248,14 @@ static void l2tp_ip6_close(struct sock *sk, long timeout) static void l2tp_ip6_destroy_sock(struct sock *sk) { - struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk); + struct l2tp_tunnel *tunnel = sk->sk_user_data; lock_sock(sk); ip6_flush_pending_frames(sk); release_sock(sk); - if (tunnel) { - l2tp_tunnel_closeall(tunnel); - sock_put(sk); - } + if (tunnel) + l2tp_tunnel_delete(tunnel); inet6_destroy_sock(sk); } diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 59f246d7b290..3b02f24ea9ec 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -416,20 +416,28 @@ abort: * Session (and tunnel control) socket create/destroy. *****************************************************************************/ +static void pppol2tp_put_sk(struct rcu_head *head) +{ + struct pppol2tp_session *ps; + + ps = container_of(head, typeof(*ps), rcu); + sock_put(ps->__sk); +} + /* Called by l2tp_core when a session socket is being closed. */ static void pppol2tp_session_close(struct l2tp_session *session) { - struct sock *sk; - - BUG_ON(session->magic != L2TP_SESSION_MAGIC); + struct pppol2tp_session *ps; - sk = pppol2tp_session_get_sock(session); - if (sk) { - if (sk->sk_socket) - inet_shutdown(sk->sk_socket, SEND_SHUTDOWN); - sock_put(sk); - } + ps = l2tp_session_priv(session); + mutex_lock(&ps->sk_lock); + ps->__sk = rcu_dereference_protected(ps->sk, + lockdep_is_held(&ps->sk_lock)); + RCU_INIT_POINTER(ps->sk, NULL); + if (ps->__sk) + call_rcu(&ps->rcu, pppol2tp_put_sk); + mutex_unlock(&ps->sk_lock); } /* Really kill the session socket. (Called from sock_put() if @@ -449,14 +457,6 @@ static void pppol2tp_session_destruct(struct sock *sk) } } -static void pppol2tp_put_sk(struct rcu_head *head) -{ - struct pppol2tp_session *ps; - - ps = container_of(head, typeof(*ps), rcu); - sock_put(ps->__sk); -} - /* Called when the PPPoX socket (session) is closed. */ static int pppol2tp_release(struct socket *sock) @@ -480,26 +480,17 @@ static int pppol2tp_release(struct socket *sock) sock_orphan(sk); sock->sk = NULL; + /* If the socket is associated with a session, + * l2tp_session_delete will call pppol2tp_session_close which + * will drop the session's ref on the socket. + */ session = pppol2tp_sock_to_session(sk); - - if (session != NULL) { - struct pppol2tp_session *ps; - + if (session) { l2tp_session_delete(session); - - ps = l2tp_session_priv(session); - mutex_lock(&ps->sk_lock); - ps->__sk = rcu_dereference_protected(ps->sk, - lockdep_is_held(&ps->sk_lock)); - RCU_INIT_POINTER(ps->sk, NULL); - mutex_unlock(&ps->sk_lock); - call_rcu(&ps->rcu, pppol2tp_put_sk); - - /* Rely on the sock_put() call at the end of the function for - * dropping the reference held by pppol2tp_sock_to_session(). - * The last reference will be dropped by pppol2tp_put_sk(). - */ + /* drop the ref obtained by pppol2tp_sock_to_session */ + sock_put(sk); } + release_sock(sk); /* This will delete the session context via @@ -796,6 +787,7 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, out_no_ppp: /* This is how we get the session context from the socket. */ + sock_hold(sk); sk->sk_user_data = session; rcu_assign_pointer(ps->sk, sk); mutex_unlock(&ps->sk_lock); diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index fd580614085b..56fe16b07538 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -3921,7 +3921,7 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx, if ((hdr->frame_control & cpu_to_le16(IEEE80211_FCTL_FROMDS | IEEE80211_FCTL_TODS)) != fast_rx->expected_ds_bits) - goto drop; + return false; /* assign the key to drop unencrypted frames (later) * and strip the IV/MIC if necessary diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 25904af38839..69722504e3e1 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -3574,6 +3574,14 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, if (!IS_ERR_OR_NULL(sta)) { struct ieee80211_fast_tx *fast_tx; + /* We need a bit of data queued to build aggregates properly, so + * instruct the TCP stack to allow more than a single ms of data + * to be queued in the stack. The value is a bit-shift of 1 + * second, so 8 is ~4ms of queued data. Only affects local TCP + * sockets. + */ + sk_pacing_shift_update(skb->sk, 8); + fast_tx = rcu_dereference(sta->fast_tx); if (fast_tx && diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index e545a3c9365f..7a4de6d618b1 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -122,7 +122,7 @@ bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) if (skb->len <= mtu) return false; - if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu)) + if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) return false; return true; diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index 3e17d32b629d..58d5d05aec24 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -260,7 +260,7 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, buf_len = strlen(buf); ct = nf_ct_get(skb, &ctinfo); - if (ct && (ct->status & IPS_NAT_MASK)) { + if (ct) { bool mangled; /* If mangling fails this function will return 0 diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 8b9fe30de0cd..558593e6a0a3 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5037,9 +5037,9 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); const struct nf_flowtable_type *type; + struct nft_flowtable *flowtable, *ft; u8 genmask = nft_genmask_next(net); int family = nfmsg->nfgen_family; - struct nft_flowtable *flowtable; struct nft_table *table; struct nft_ctx ctx; int err, i, k; @@ -5099,6 +5099,22 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, goto err3; for (i = 0; i < flowtable->ops_len; i++) { + if (!flowtable->ops[i].dev) + continue; + + list_for_each_entry(ft, &table->flowtables, list) { + for (k = 0; k < ft->ops_len; k++) { + if (!ft->ops[k].dev) + continue; + + if (flowtable->ops[i].dev == ft->ops[k].dev && + flowtable->ops[i].pf == ft->ops[k].pf) { + err = -EBUSY; + goto err4; + } + } + } + err = nf_register_net_hook(net, &flowtable->ops[i]); if (err < 0) goto err4; @@ -5120,7 +5136,7 @@ err5: i = flowtable->ops_len; err4: for (k = i - 1; k >= 0; k--) - nf_unregister_net_hook(net, &flowtable->ops[i]); + nf_unregister_net_hook(net, &flowtable->ops[k]); kfree(flowtable->ops); err3: @@ -5145,6 +5161,11 @@ static int nf_tables_delflowtable(struct net *net, struct sock *nlsk, struct nft_table *table; struct nft_ctx ctx; + if (!nla[NFTA_FLOWTABLE_TABLE] || + (!nla[NFTA_FLOWTABLE_NAME] && + !nla[NFTA_FLOWTABLE_HANDLE])) + return -EINVAL; + table = nf_tables_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE], family, genmask); if (IS_ERR(table)) diff --git a/net/qrtr/smd.c b/net/qrtr/smd.c index 50615d5efac1..9cf089b9754e 100644 --- a/net/qrtr/smd.c +++ b/net/qrtr/smd.c @@ -114,5 +114,6 @@ static struct rpmsg_driver qcom_smd_qrtr_driver = { module_rpmsg_driver(qcom_smd_qrtr_driver); +MODULE_ALIAS("rpmsg:IPCRTR"); MODULE_DESCRIPTION("Qualcomm IPC-Router SMD interface driver"); MODULE_LICENSE("GPL v2"); diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index c061d6eb465d..22571189f21e 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2006 Oracle. All rights reserved. + * Copyright (c) 2006, 2018 Oracle. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU @@ -142,12 +142,20 @@ int rds_tcp_accept_one(struct socket *sock) if (ret) goto out; - new_sock->type = sock->type; - new_sock->ops = sock->ops; ret = sock->ops->accept(sock, new_sock, O_NONBLOCK, true); if (ret < 0) goto out; + /* sock_create_lite() does not get a hold on the owner module so we + * need to do it here. Note that sock_release() uses sock->ops to + * determine if it needs to decrement the reference count. So set + * sock->ops after calling accept() in case that fails. And there's + * no need to do try_module_get() as the listener should have a hold + * already. + */ + new_sock->ops = sock->ops; + __module_get(new_sock->ops->owner); + ret = rds_tcp_keepalive(new_sock); if (ret < 0) goto out; diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 229172d509cc..03225a8df973 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -188,7 +188,8 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch, int ret; if (qdisc_pkt_len(skb) > q->max_size) { - if (skb_is_gso(skb) && skb_gso_mac_seglen(skb) <= q->max_size) + if (skb_is_gso(skb) && + skb_gso_validate_mac_len(skb, q->max_size)) return tbf_segment(skb, sch, to_free); return qdisc_drop(skb, sch, to_free); } diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index da1a5cdefd13..8cc97834d4f6 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -1406,8 +1406,10 @@ static int smc_create(struct net *net, struct socket *sock, int protocol, smc->use_fallback = false; /* assume rdma capability first */ rc = sock_create_kern(net, PF_INET, SOCK_STREAM, IPPROTO_TCP, &smc->clcsock); - if (rc) + if (rc) { sk_common_release(sk); + goto out; + } smc->sk.sk_sndbuf = max(smc->clcsock->sk->sk_sndbuf, SMC_BUF_MIN_SIZE); smc->sk.sk_rcvbuf = max(smc->clcsock->sk->sk_rcvbuf, SMC_BUF_MIN_SIZE); diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index 3cd086e5bd28..b42395d24cba 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -269,7 +269,7 @@ static void smc_cdc_rx_handler(struct ib_wc *wc, void *buf) if (wc->byte_len < offsetof(struct smc_cdc_msg, reserved)) return; /* short message */ - if (cdc->len != sizeof(*cdc)) + if (cdc->len != SMC_WR_TX_SIZE) return; /* invalid message */ smc_cdc_msg_recv(cdc, link, wc->wr_id); } diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 2424c7100aaf..645dd226177b 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -177,6 +177,7 @@ static int smc_lgr_create(struct smc_sock *smc, __be32 peer_in_addr, lnk = &lgr->lnk[SMC_SINGLE_LINK]; /* initialize link */ + lnk->link_id = SMC_SINGLE_LINK; lnk->smcibdev = smcibdev; lnk->ibport = ibport; lnk->path_mtu = smcibdev->pattr[ibport - 1].active_mtu; @@ -465,7 +466,7 @@ create: rc = smc_link_determine_gid(conn->lgr); } conn->local_tx_ctrl.common.type = SMC_CDC_MSG_TYPE; - conn->local_tx_ctrl.len = sizeof(struct smc_cdc_msg); + conn->local_tx_ctrl.len = SMC_WR_TX_SIZE; #ifndef KERNEL_HAS_ATOMIC64 spin_lock_init(&conn->acurs_lock); #endif diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index 92fe4cc8c82c..b4aa4fcedb96 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -92,7 +92,7 @@ int smc_llc_send_confirm_link(struct smc_link *link, u8 mac[], memcpy(confllc->sender_mac, mac, ETH_ALEN); memcpy(confllc->sender_gid, gid, SMC_GID_SIZE); hton24(confllc->sender_qp_num, link->roce_qp->qp_num); - /* confllc->link_num = SMC_SINGLE_LINK; already done by memset above */ + confllc->link_num = link->link_id; memcpy(confllc->link_uid, lgr->id, SMC_LGR_ID_SIZE); confllc->max_links = SMC_LINKS_PER_LGR_MAX; /* send llc message */ diff --git a/net/tipc/group.c b/net/tipc/group.c index 122162a31816..04e516d18054 100644 --- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -189,6 +189,7 @@ struct tipc_group *tipc_group_create(struct net *net, u32 portid, grp->loopback = mreq->flags & TIPC_GROUP_LOOPBACK; grp->events = mreq->flags & TIPC_GROUP_MEMBER_EVTS; grp->open = group_is_open; + *grp->open = false; filter |= global ? TIPC_SUB_CLUSTER_SCOPE : TIPC_SUB_NODE_SCOPE; if (tipc_topsrv_kern_subscr(net, portid, type, 0, ~0, filter, &grp->subid)) diff --git a/net/tipc/socket.c b/net/tipc/socket.c index b0323ec7971e..7dfa9fc99ec3 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -473,6 +473,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock, sk->sk_write_space = tipc_write_space; sk->sk_destruct = tipc_sock_destruct; tsk->conn_timeout = CONN_TIMEOUT_DEFAULT; + tsk->group_is_open = true; atomic_set(&tsk->dupl_rcvcnt, 0); /* Start out with safe limits until we receive an advertised window */ diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index e9b4b53ab53e..d824d548447e 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -46,16 +46,26 @@ MODULE_DESCRIPTION("Transport Layer Security Support"); MODULE_LICENSE("Dual BSD/GPL"); enum { + TLSV4, + TLSV6, + TLS_NUM_PROTS, +}; + +enum { TLS_BASE_TX, TLS_SW_TX, TLS_NUM_CONFIG, }; -static struct proto tls_prots[TLS_NUM_CONFIG]; +static struct proto *saved_tcpv6_prot; +static DEFINE_MUTEX(tcpv6_prot_mutex); +static struct proto tls_prots[TLS_NUM_PROTS][TLS_NUM_CONFIG]; static inline void update_sk_prot(struct sock *sk, struct tls_context *ctx) { - sk->sk_prot = &tls_prots[ctx->tx_conf]; + int ip_ver = sk->sk_family == AF_INET6 ? TLSV6 : TLSV4; + + sk->sk_prot = &tls_prots[ip_ver][ctx->tx_conf]; } int wait_on_pending_writer(struct sock *sk, long *timeo) @@ -453,8 +463,21 @@ static int tls_setsockopt(struct sock *sk, int level, int optname, return do_tls_setsockopt(sk, optname, optval, optlen); } +static void build_protos(struct proto *prot, struct proto *base) +{ + prot[TLS_BASE_TX] = *base; + prot[TLS_BASE_TX].setsockopt = tls_setsockopt; + prot[TLS_BASE_TX].getsockopt = tls_getsockopt; + prot[TLS_BASE_TX].close = tls_sk_proto_close; + + prot[TLS_SW_TX] = prot[TLS_BASE_TX]; + prot[TLS_SW_TX].sendmsg = tls_sw_sendmsg; + prot[TLS_SW_TX].sendpage = tls_sw_sendpage; +} + static int tls_init(struct sock *sk) { + int ip_ver = sk->sk_family == AF_INET6 ? TLSV6 : TLSV4; struct inet_connection_sock *icsk = inet_csk(sk); struct tls_context *ctx; int rc = 0; @@ -479,6 +502,17 @@ static int tls_init(struct sock *sk) ctx->getsockopt = sk->sk_prot->getsockopt; ctx->sk_proto_close = sk->sk_prot->close; + /* Build IPv6 TLS whenever the address of tcpv6_prot changes */ + if (ip_ver == TLSV6 && + unlikely(sk->sk_prot != smp_load_acquire(&saved_tcpv6_prot))) { + mutex_lock(&tcpv6_prot_mutex); + if (likely(sk->sk_prot != saved_tcpv6_prot)) { + build_protos(tls_prots[TLSV6], sk->sk_prot); + smp_store_release(&saved_tcpv6_prot, sk->sk_prot); + } + mutex_unlock(&tcpv6_prot_mutex); + } + ctx->tx_conf = TLS_BASE_TX; update_sk_prot(sk, ctx); out: @@ -493,21 +527,9 @@ static struct tcp_ulp_ops tcp_tls_ulp_ops __read_mostly = { .init = tls_init, }; -static void build_protos(struct proto *prot, struct proto *base) -{ - prot[TLS_BASE_TX] = *base; - prot[TLS_BASE_TX].setsockopt = tls_setsockopt; - prot[TLS_BASE_TX].getsockopt = tls_getsockopt; - prot[TLS_BASE_TX].close = tls_sk_proto_close; - - prot[TLS_SW_TX] = prot[TLS_BASE_TX]; - prot[TLS_SW_TX].sendmsg = tls_sw_sendmsg; - prot[TLS_SW_TX].sendpage = tls_sw_sendpage; -} - static int __init tls_register(void) { - build_protos(tls_prots, &tcp_prot); + build_protos(tls_prots[TLSV4], &tcp_prot); tcp_register_ulp(&tcp_tls_ulp_ops); diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig index 1abcc4fc4df1..41722046b937 100644 --- a/net/wireless/Kconfig +++ b/net/wireless/Kconfig @@ -34,9 +34,10 @@ config CFG80211 When built as a module it will be called cfg80211. +if CFG80211 + config NL80211_TESTMODE bool "nl80211 testmode command" - depends on CFG80211 help The nl80211 testmode command helps implementing things like factory calibration or validation tools for wireless chips. @@ -51,7 +52,6 @@ config NL80211_TESTMODE config CFG80211_DEVELOPER_WARNINGS bool "enable developer warnings" - depends on CFG80211 default n help This option enables some additional warnings that help @@ -68,7 +68,7 @@ config CFG80211_DEVELOPER_WARNINGS config CFG80211_CERTIFICATION_ONUS bool "cfg80211 certification onus" - depends on CFG80211 && EXPERT + depends on EXPERT default n ---help--- You should disable this option unless you are both capable @@ -159,7 +159,6 @@ config CFG80211_REG_RELAX_NO_IR config CFG80211_DEFAULT_PS bool "enable powersave by default" - depends on CFG80211 default y help This option enables powersave mode by default. @@ -170,7 +169,6 @@ config CFG80211_DEFAULT_PS config CFG80211_DEBUGFS bool "cfg80211 DebugFS entries" - depends on CFG80211 depends on DEBUG_FS ---help--- You can enable this if you want debugfs entries for cfg80211. @@ -180,7 +178,6 @@ config CFG80211_DEBUGFS config CFG80211_CRDA_SUPPORT bool "support CRDA" if EXPERT default y - depends on CFG80211 help You should enable this option unless you know for sure you have no need for it, for example when using internal regdb (above) or the @@ -190,7 +187,6 @@ config CFG80211_CRDA_SUPPORT config CFG80211_WEXT bool "cfg80211 wireless extensions compatibility" if !CFG80211_WEXT_EXPORT - depends on CFG80211 select WEXT_CORE default y if CFG80211_WEXT_EXPORT help @@ -199,11 +195,12 @@ config CFG80211_WEXT config CFG80211_WEXT_EXPORT bool - depends on CFG80211 help Drivers should select this option if they require cfg80211's wext compatibility symbols to be exported. +endif # CFG80211 + config LIB80211 tristate default n diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 8e70291e586a..e87d6c4dd5b6 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -217,7 +217,7 @@ bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x) if (skb->len <= mtu) goto ok; - if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu)) + if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) goto ok; } diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index 5589bae34af6..a6f538b31ad6 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -297,11 +297,11 @@ cmd_dt_S_dtb= \ echo '\#include <asm-generic/vmlinux.lds.h>'; \ echo '.section .dtb.init.rodata,"a"'; \ echo '.balign STRUCT_ALIGNMENT'; \ - echo '.global __dtb_$(*F)_begin'; \ - echo '__dtb_$(*F)_begin:'; \ + echo '.global __dtb_$(subst -,_,$(*F))_begin'; \ + echo '__dtb_$(subst -,_,$(*F))_begin:'; \ echo '.incbin "$<" '; \ - echo '__dtb_$(*F)_end:'; \ - echo '.global __dtb_$(*F)_end'; \ + echo '__dtb_$(subst -,_,$(*F))_end:'; \ + echo '.global __dtb_$(subst -,_,$(*F))_end'; \ echo '.balign STRUCT_ALIGNMENT'; \ ) > $@ diff --git a/scripts/basic/fixdep.c b/scripts/basic/fixdep.c index fa3d39b6f23b..449b68c4c90c 100644 --- a/scripts/basic/fixdep.c +++ b/scripts/basic/fixdep.c @@ -93,14 +93,6 @@ * (Note: it'd be easy to port over the complete mkdep state machine, * but I don't think the added complexity is worth it) */ -/* - * Note 2: if somebody writes HELLO_CONFIG_BOOM in a file, it will depend onto - * CONFIG_BOOM. This could seem a bug (not too hard to fix), but please do not - * fix it! Some UserModeLinux files (look at arch/um/) call CONFIG_BOOM as - * UML_CONFIG_BOOM, to avoid conflicts with /usr/include/linux/autoconf.h, - * through arch/um/include/uml-config.h; this fixdep "bug" makes sure that - * those files will have correct dependencies. - */ #include <sys/types.h> #include <sys/stat.h> @@ -233,8 +225,13 @@ static int str_ends_with(const char *s, int slen, const char *sub) static void parse_config_file(const char *p) { const char *q, *r; + const char *start = p; while ((p = strstr(p, "CONFIG_"))) { + if (p > start && (isalnum(p[-1]) || p[-1] == '_')) { + p += 7; + continue; + } p += 7; q = p; while (*q && (isalnum(*q) || *q == '_')) @@ -286,8 +283,6 @@ static int is_ignored_file(const char *s, int len) { return str_ends_with(s, len, "include/generated/autoconf.h") || str_ends_with(s, len, "include/generated/autoksyms.h") || - str_ends_with(s, len, "arch/um/include/uml-config.h") || - str_ends_with(s, len, "include/linux/kconfig.h") || str_ends_with(s, len, ".ver"); } diff --git a/scripts/bloat-o-meter b/scripts/bloat-o-meter index 94b664817ad9..d84a5674e95e 100755 --- a/scripts/bloat-o-meter +++ b/scripts/bloat-o-meter @@ -15,7 +15,7 @@ signal(SIGPIPE, SIG_DFL) if len(sys.argv) < 3: sys.stderr.write("usage: %s [option] file1 file2\n" % sys.argv[0]) sys.stderr.write("The options are:\n") - sys.stderr.write("-c cateogrize output based on symbole type\n") + sys.stderr.write("-c categorize output based on symbol type\n") sys.stderr.write("-d Show delta of Data Section\n") sys.stderr.write("-t Show delta of text Section\n") sys.exit(-1) diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 04d4db44fae5..918338dea5b9 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -910,7 +910,8 @@ int snd_seq_dispatch_event(struct snd_seq_event_cell *cell, int atomic, int hop) static int snd_seq_client_enqueue_event(struct snd_seq_client *client, struct snd_seq_event *event, struct file *file, int blocking, - int atomic, int hop) + int atomic, int hop, + struct mutex *mutexp) { struct snd_seq_event_cell *cell; int err; @@ -948,7 +949,8 @@ static int snd_seq_client_enqueue_event(struct snd_seq_client *client, return -ENXIO; /* queue is not allocated */ /* allocate an event cell */ - err = snd_seq_event_dup(client->pool, event, &cell, !blocking || atomic, file); + err = snd_seq_event_dup(client->pool, event, &cell, !blocking || atomic, + file, mutexp); if (err < 0) return err; @@ -1017,12 +1019,11 @@ static ssize_t snd_seq_write(struct file *file, const char __user *buf, return -ENXIO; /* allocate the pool now if the pool is not allocated yet */ + mutex_lock(&client->ioctl_mutex); if (client->pool->size > 0 && !snd_seq_write_pool_allocated(client)) { - mutex_lock(&client->ioctl_mutex); err = snd_seq_pool_init(client->pool); - mutex_unlock(&client->ioctl_mutex); if (err < 0) - return -ENOMEM; + goto out; } /* only process whole events */ @@ -1073,7 +1074,7 @@ static ssize_t snd_seq_write(struct file *file, const char __user *buf, /* ok, enqueue it */ err = snd_seq_client_enqueue_event(client, &event, file, !(file->f_flags & O_NONBLOCK), - 0, 0); + 0, 0, &client->ioctl_mutex); if (err < 0) break; @@ -1084,6 +1085,8 @@ static ssize_t snd_seq_write(struct file *file, const char __user *buf, written += len; } + out: + mutex_unlock(&client->ioctl_mutex); return written ? written : err; } @@ -1838,9 +1841,11 @@ static int snd_seq_ioctl_set_client_pool(struct snd_seq_client *client, (! snd_seq_write_pool_allocated(client) || info->output_pool != client->pool->size)) { if (snd_seq_write_pool_allocated(client)) { + /* is the pool in use? */ + if (atomic_read(&client->pool->counter)) + return -EBUSY; /* remove all existing cells */ snd_seq_pool_mark_closing(client->pool); - snd_seq_queue_client_leave_cells(client->number); snd_seq_pool_done(client->pool); } client->pool->size = info->output_pool; @@ -2260,7 +2265,8 @@ static int kernel_client_enqueue(int client, struct snd_seq_event *ev, if (! cptr->accept_output) result = -EPERM; else /* send it */ - result = snd_seq_client_enqueue_event(cptr, ev, file, blocking, atomic, hop); + result = snd_seq_client_enqueue_event(cptr, ev, file, blocking, + atomic, hop, NULL); snd_seq_client_unlock(cptr); return result; diff --git a/sound/core/seq/seq_fifo.c b/sound/core/seq/seq_fifo.c index a8c2822e0198..72c0302a55d2 100644 --- a/sound/core/seq/seq_fifo.c +++ b/sound/core/seq/seq_fifo.c @@ -125,7 +125,7 @@ int snd_seq_fifo_event_in(struct snd_seq_fifo *f, return -EINVAL; snd_use_lock_use(&f->use_lock); - err = snd_seq_event_dup(f->pool, event, &cell, 1, NULL); /* always non-blocking */ + err = snd_seq_event_dup(f->pool, event, &cell, 1, NULL, NULL); /* always non-blocking */ if (err < 0) { if ((err == -ENOMEM) || (err == -EAGAIN)) atomic_inc(&f->overflow); diff --git a/sound/core/seq/seq_memory.c b/sound/core/seq/seq_memory.c index f763682584a8..ab1112e90f88 100644 --- a/sound/core/seq/seq_memory.c +++ b/sound/core/seq/seq_memory.c @@ -220,7 +220,8 @@ void snd_seq_cell_free(struct snd_seq_event_cell * cell) */ static int snd_seq_cell_alloc(struct snd_seq_pool *pool, struct snd_seq_event_cell **cellp, - int nonblock, struct file *file) + int nonblock, struct file *file, + struct mutex *mutexp) { struct snd_seq_event_cell *cell; unsigned long flags; @@ -244,7 +245,11 @@ static int snd_seq_cell_alloc(struct snd_seq_pool *pool, set_current_state(TASK_INTERRUPTIBLE); add_wait_queue(&pool->output_sleep, &wait); spin_unlock_irq(&pool->lock); + if (mutexp) + mutex_unlock(mutexp); schedule(); + if (mutexp) + mutex_lock(mutexp); spin_lock_irq(&pool->lock); remove_wait_queue(&pool->output_sleep, &wait); /* interrupted? */ @@ -287,7 +292,7 @@ __error: */ int snd_seq_event_dup(struct snd_seq_pool *pool, struct snd_seq_event *event, struct snd_seq_event_cell **cellp, int nonblock, - struct file *file) + struct file *file, struct mutex *mutexp) { int ncells, err; unsigned int extlen; @@ -304,7 +309,7 @@ int snd_seq_event_dup(struct snd_seq_pool *pool, struct snd_seq_event *event, if (ncells >= pool->total_elements) return -ENOMEM; - err = snd_seq_cell_alloc(pool, &cell, nonblock, file); + err = snd_seq_cell_alloc(pool, &cell, nonblock, file, mutexp); if (err < 0) return err; @@ -330,7 +335,8 @@ int snd_seq_event_dup(struct snd_seq_pool *pool, struct snd_seq_event *event, int size = sizeof(struct snd_seq_event); if (len < size) size = len; - err = snd_seq_cell_alloc(pool, &tmp, nonblock, file); + err = snd_seq_cell_alloc(pool, &tmp, nonblock, file, + mutexp); if (err < 0) goto __error; if (cell->event.data.ext.ptr == NULL) diff --git a/sound/core/seq/seq_memory.h b/sound/core/seq/seq_memory.h index 32f959c17786..3abe306c394a 100644 --- a/sound/core/seq/seq_memory.h +++ b/sound/core/seq/seq_memory.h @@ -66,7 +66,8 @@ struct snd_seq_pool { void snd_seq_cell_free(struct snd_seq_event_cell *cell); int snd_seq_event_dup(struct snd_seq_pool *pool, struct snd_seq_event *event, - struct snd_seq_event_cell **cellp, int nonblock, struct file *file); + struct snd_seq_event_cell **cellp, int nonblock, + struct file *file, struct mutex *mutexp); /* return number of unused (free) cells */ static inline int snd_seq_unused_cells(struct snd_seq_pool *pool) diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index 37e1cf8218ff..5b4dbcec6de8 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -957,6 +957,8 @@ static const struct snd_pci_quirk cxt5066_fixups[] = { SND_PCI_QUIRK(0x1025, 0x054c, "Acer Aspire 3830TG", CXT_FIXUP_ASPIRE_DMIC), SND_PCI_QUIRK(0x1025, 0x054f, "Acer Aspire 4830T", CXT_FIXUP_ASPIRE_DMIC), SND_PCI_QUIRK(0x103c, 0x8079, "HP EliteBook 840 G3", CXT_FIXUP_HP_DOCK), + SND_PCI_QUIRK(0x103c, 0x807C, "HP EliteBook 820 G3", CXT_FIXUP_HP_DOCK), + SND_PCI_QUIRK(0x103c, 0x80FD, "HP ProBook 640 G2", CXT_FIXUP_HP_DOCK), SND_PCI_QUIRK(0x103c, 0x8174, "HP Spectre x360", CXT_FIXUP_HP_SPECTRE), SND_PCI_QUIRK(0x103c, 0x8115, "HP Z1 Gen3", CXT_FIXUP_HP_GATE_MIC), SND_PCI_QUIRK(0x103c, 0x814f, "HP ZBook 15u G3", CXT_FIXUP_MUTE_LED_GPIO), diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index b9c93fa0a51c..9af301c6bba2 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -5274,6 +5274,16 @@ static void alc298_fixup_speaker_volume(struct hda_codec *codec, } } +/* disable DAC3 (0x06) selection on NID 0x17 as it has no volume amp control */ +static void alc295_fixup_disable_dac3(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + if (action == HDA_FIXUP_ACT_PRE_PROBE) { + hda_nid_t conn[2] = { 0x02, 0x03 }; + snd_hda_override_conn_list(codec, 0x17, 2, conn); + } +} + /* Hook to update amp GPIO4 for automute */ static void alc280_hp_gpio4_automute_hook(struct hda_codec *codec, struct hda_jack_callback *jack) @@ -5466,6 +5476,7 @@ enum { ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY, ALC255_FIXUP_DELL_SPK_NOISE, ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, + ALC295_FIXUP_DISABLE_DAC3, ALC280_FIXUP_HP_HEADSET_MIC, ALC221_FIXUP_HP_FRONT_MIC, ALC292_FIXUP_TPT460, @@ -5480,10 +5491,12 @@ enum { ALC233_FIXUP_EAPD_COEF_AND_MIC_NO_PRESENCE, ALC233_FIXUP_LENOVO_MULTI_CODECS, ALC294_FIXUP_LENOVO_MIC_LOCATION, + ALC225_FIXUP_DELL_WYSE_MIC_NO_PRESENCE, ALC700_FIXUP_INTEL_REFERENCE, ALC274_FIXUP_DELL_BIND_DACS, ALC274_FIXUP_DELL_AIO_LINEOUT_VERB, ALC298_FIXUP_TPT470_DOCK, + ALC255_FIXUP_DUMMY_LINEOUT_VERB, }; static const struct hda_fixup alc269_fixups[] = { @@ -6198,6 +6211,10 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC298_FIXUP_DELL_AIO_MIC_NO_PRESENCE, }, + [ALC295_FIXUP_DISABLE_DAC3] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc295_fixup_disable_dac3, + }, [ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -6283,6 +6300,18 @@ static const struct hda_fixup alc269_fixups[] = { { } }, }, + [ALC225_FIXUP_DELL_WYSE_MIC_NO_PRESENCE] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x16, 0x0101102f }, /* Rear Headset HP */ + { 0x19, 0x02a1913c }, /* use as Front headset mic, without its own jack detect */ + { 0x1a, 0x01a19030 }, /* Rear Headset MIC */ + { 0x1b, 0x02011020 }, + { } + }, + .chained = true, + .chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC + }, [ALC700_FIXUP_INTEL_REFERENCE] = { .type = HDA_FIXUP_VERBS, .v.verbs = (const struct hda_verb[]) { @@ -6319,6 +6348,15 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC293_FIXUP_LENOVO_SPK_NOISE }, + [ALC255_FIXUP_DUMMY_LINEOUT_VERB] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x14, 0x0201101f }, + { } + }, + .chained = true, + .chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -6367,10 +6405,13 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0725, "Dell Inspiron 3162", ALC255_FIXUP_DELL_SPK_NOISE), SND_PCI_QUIRK(0x1028, 0x075b, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE), SND_PCI_QUIRK(0x1028, 0x075d, "Dell AIO", ALC298_FIXUP_SPK_VOLUME), + SND_PCI_QUIRK(0x1028, 0x07b0, "Dell Precision 7520", ALC295_FIXUP_DISABLE_DAC3), SND_PCI_QUIRK(0x1028, 0x0798, "Dell Inspiron 17 7000 Gaming", ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER), + SND_PCI_QUIRK(0x1028, 0x080c, "Dell WYSE", ALC225_FIXUP_DELL_WYSE_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x082a, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE), SND_PCI_QUIRK(0x1028, 0x084b, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB), SND_PCI_QUIRK(0x1028, 0x084e, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB), + SND_PCI_QUIRK(0x1028, 0x0873, "Dell Precision 3930", ALC255_FIXUP_DUMMY_LINEOUT_VERB), SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2), @@ -6508,9 +6549,11 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x2245, "Thinkpad T470", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x2246, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x2247, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), + SND_PCI_QUIRK(0x17aa, 0x2249, "Thinkpad", ALC292_FIXUP_TPT460), SND_PCI_QUIRK(0x17aa, 0x224b, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x224c, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x224d, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), + SND_PCI_QUIRK(0x17aa, 0x225d, "Thinkpad T480", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), SND_PCI_QUIRK(0x17aa, 0x310c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION), @@ -6872,7 +6915,7 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x12, 0x90a60120}, {0x14, 0x90170110}, {0x21, 0x0321101f}), - SND_HDA_PIN_QUIRK(0x10ec0289, 0x1028, "Dell", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, + SND_HDA_PIN_QUIRK(0x10ec0289, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE, {0x12, 0xb7a60130}, {0x14, 0x90170110}, {0x21, 0x04211020}), diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 0dfe4d3f74e2..f41079da38c5 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -213,6 +213,7 @@ #define X86_FEATURE_SEV ( 7*32+20) /* AMD Secure Encrypted Virtualization */ #define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ +#define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* "" Use IBRS during runtime firmware calls */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 0fb5ef939732..7b26d4b0b052 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -761,6 +761,7 @@ struct kvm_ppc_resize_hpt { #define KVM_TRACE_PAUSE __KVM_DEPRECATED_MAIN_0x07 #define KVM_TRACE_DISABLE __KVM_DEPRECATED_MAIN_0x08 #define KVM_GET_EMULATED_CPUID _IOWR(KVMIO, 0x09, struct kvm_cpuid2) +#define KVM_GET_MSR_FEATURE_INDEX_LIST _IOWR(KVMIO, 0x0a, struct kvm_msr_list) /* * Extension capability list. @@ -934,6 +935,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_AIS_MIGRATION 150 #define KVM_CAP_PPC_GET_CPU_CHAR 151 #define KVM_CAP_S390_BPB 152 +#define KVM_CAP_GET_MSR_FEATURES 153 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 46c1d239cc1b..92b6a2c21631 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -1116,42 +1116,29 @@ static int read_unwind_hints(struct objtool_file *file) static int read_retpoline_hints(struct objtool_file *file) { - struct section *sec, *relasec; + struct section *sec; struct instruction *insn; struct rela *rela; - int i; - sec = find_section_by_name(file->elf, ".discard.retpoline_safe"); + sec = find_section_by_name(file->elf, ".rela.discard.retpoline_safe"); if (!sec) return 0; - relasec = sec->rela; - if (!relasec) { - WARN("missing .rela.discard.retpoline_safe section"); - return -1; - } - - if (sec->len % sizeof(unsigned long)) { - WARN("retpoline_safe size mismatch: %d %ld", sec->len, sizeof(unsigned long)); - return -1; - } - - for (i = 0; i < sec->len / sizeof(unsigned long); i++) { - rela = find_rela_by_dest(sec, i * sizeof(unsigned long)); - if (!rela) { - WARN("can't find rela for retpoline_safe[%d]", i); + list_for_each_entry(rela, &sec->rela_list, list) { + if (rela->sym->type != STT_SECTION) { + WARN("unexpected relocation symbol type in %s", sec->name); return -1; } insn = find_insn(file, rela->sym->sec, rela->addend); if (!insn) { - WARN("can't find insn for retpoline_safe[%d]", i); + WARN("bad .discard.retpoline_safe entry"); return -1; } if (insn->type != INSN_JUMP_DYNAMIC && insn->type != INSN_CALL_DYNAMIC) { - WARN_FUNC("retpoline_safe hint not a indirect jump/call", + WARN_FUNC("retpoline_safe hint not an indirect jump/call", insn->sec, insn->offset); return -1; } diff --git a/tools/perf/Documentation/perf-kallsyms.txt b/tools/perf/Documentation/perf-kallsyms.txt index 954ea9e21236..cf9f4040ea5c 100644 --- a/tools/perf/Documentation/perf-kallsyms.txt +++ b/tools/perf/Documentation/perf-kallsyms.txt @@ -8,7 +8,7 @@ perf-kallsyms - Searches running kernel for symbols SYNOPSIS -------- [verse] -'perf kallsyms <options> symbol_name[,symbol_name...]' +'perf kallsyms' [<options>] symbol_name[,symbol_name...] DESCRIPTION ----------- diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index bf4ca749d1ac..a217623fec2e 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -881,6 +881,15 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) } } + /* + * If we have just single event and are sending data + * through pipe, we need to force the ids allocation, + * because we synthesize event name through the pipe + * and need the id for that. + */ + if (data->is_pipe && rec->evlist->nr_entries == 1) + rec->opts.sample_id = true; + if (record__open(rec) != 0) { err = -1; goto out_child; diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 98bf9d32f222..54a4c152edb3 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -917,7 +917,7 @@ static void print_metric_csv(void *ctx, char buf[64], *vals, *ends; if (unit == NULL || fmt == NULL) { - fprintf(out, "%s%s%s%s", csv_sep, csv_sep, csv_sep, csv_sep); + fprintf(out, "%s%s", csv_sep, csv_sep); return; } snprintf(buf, sizeof(buf), fmt, val); diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index b7c823ba8374..35ac016fcb98 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -991,7 +991,7 @@ static int perf_top_overwrite_fallback(struct perf_top *top, evlist__for_each_entry(evlist, counter) counter->attr.write_backward = false; opts->overwrite = false; - ui__warning("fall back to non-overwrite mode\n"); + pr_debug2("fall back to non-overwrite mode\n"); return 1; } diff --git a/tools/perf/perf.h b/tools/perf/perf.h index cfe46236a5e5..57b9b342d533 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -61,6 +61,7 @@ struct record_opts { bool tail_synthesize; bool overwrite; bool ignore_missing_thread; + bool sample_id; unsigned int freq; unsigned int mmap_pages; unsigned int auxtrace_mmap_pages; diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index 286427975112..fbf927cf775d 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -327,7 +327,32 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser) if (!disasm_line__is_valid_jump(cursor, sym)) return; + /* + * This first was seen with a gcc function, _cpp_lex_token, that + * has the usual jumps: + * + * │1159e6c: ↓ jne 115aa32 <_cpp_lex_token@@Base+0xf92> + * + * I.e. jumps to a label inside that function (_cpp_lex_token), and + * those works, but also this kind: + * + * │1159e8b: ↓ jne c469be <cpp_named_operator2name@@Base+0xa72> + * + * I.e. jumps to another function, outside _cpp_lex_token, which + * are not being correctly handled generating as a side effect references + * to ab->offset[] entries that are set to NULL, so to make this code + * more robust, check that here. + * + * A proper fix for will be put in place, looking at the function + * name right after the '<' token and probably treating this like a + * 'call' instruction. + */ target = ab->offsets[cursor->ops.target.offset]; + if (target == NULL) { + ui_helpline__printf("WARN: jump target inconsistency, press 'o', ab->offsets[%#x] = NULL\n", + cursor->ops.target.offset); + return; + } bcursor = browser_line(&cursor->al); btarget = browser_line(target); diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index 9faf3b5367db..6470ea2aa25e 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -60,6 +60,12 @@ #include "sane_ctype.h" #include "symbol/kallsyms.h" +static bool auxtrace__dont_decode(struct perf_session *session) +{ + return !session->itrace_synth_opts || + session->itrace_synth_opts->dont_decode; +} + int auxtrace_mmap__mmap(struct auxtrace_mmap *mm, struct auxtrace_mmap_params *mp, void *userpg, int fd) @@ -762,6 +768,9 @@ int auxtrace_queues__process_index(struct auxtrace_queues *queues, size_t i; int err; + if (auxtrace__dont_decode(session)) + return 0; + list_for_each_entry(auxtrace_index, &session->auxtrace_index, list) { for (i = 0; i < auxtrace_index->nr; i++) { ent = &auxtrace_index->entries[i]; @@ -892,12 +901,6 @@ out_free: return err; } -static bool auxtrace__dont_decode(struct perf_session *session) -{ - return !session->itrace_synth_opts || - session->itrace_synth_opts->dont_decode; -} - int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_session *session) diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index 1e97937b03a9..6f09e4962dad 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -137,6 +137,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts, struct perf_evsel *evsel; bool use_sample_identifier = false; bool use_comm_exec; + bool sample_id = opts->sample_id; /* * Set the evsel leader links before we configure attributes, @@ -163,8 +164,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts, * match the id. */ use_sample_identifier = perf_can_sample_identifier(); - evlist__for_each_entry(evlist, evsel) - perf_evsel__set_sample_id(evsel, use_sample_identifier); + sample_id = true; } else if (evlist->nr_entries > 1) { struct perf_evsel *first = perf_evlist__first(evlist); @@ -174,6 +174,10 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts, use_sample_identifier = perf_can_sample_identifier(); break; } + sample_id = true; + } + + if (sample_id) { evlist__for_each_entry(evlist, evsel) perf_evsel__set_sample_id(evsel, use_sample_identifier); } diff --git a/tools/perf/util/trigger.h b/tools/perf/util/trigger.h index 370138e7e35c..88223bc7c82b 100644 --- a/tools/perf/util/trigger.h +++ b/tools/perf/util/trigger.h @@ -12,7 +12,7 @@ * States and transits: * * - * OFF--(on)--> READY --(hit)--> HIT + * OFF--> ON --> READY --(hit)--> HIT * ^ | * | (ready) * | | @@ -27,8 +27,9 @@ struct trigger { volatile enum { TRIGGER_ERROR = -2, TRIGGER_OFF = -1, - TRIGGER_READY = 0, - TRIGGER_HIT = 1, + TRIGGER_ON = 0, + TRIGGER_READY = 1, + TRIGGER_HIT = 2, } state; const char *name; }; @@ -50,7 +51,7 @@ static inline bool trigger_is_error(struct trigger *t) static inline void trigger_on(struct trigger *t) { TRIGGER_WARN_ONCE(t, TRIGGER_OFF); - t->state = TRIGGER_READY; + t->state = TRIGGER_ON; } static inline void trigger_ready(struct trigger *t) diff --git a/tools/power/pm-graph/Makefile b/tools/power/pm-graph/Makefile index 4e1e999e7b05..c1899cd72c80 100644 --- a/tools/power/pm-graph/Makefile +++ b/tools/power/pm-graph/Makefile @@ -7,11 +7,24 @@ all: install : uninstall install -d $(DESTDIR)$(PREFIX)/lib/pm-graph - install analyze_suspend.py $(DESTDIR)$(PREFIX)/lib/pm-graph - install analyze_boot.py $(DESTDIR)$(PREFIX)/lib/pm-graph + install sleepgraph.py $(DESTDIR)$(PREFIX)/lib/pm-graph + install bootgraph.py $(DESTDIR)$(PREFIX)/lib/pm-graph + install -d $(DESTDIR)$(PREFIX)/lib/pm-graph/config + install -m 644 config/cgskip.txt $(DESTDIR)$(PREFIX)/lib/pm-graph/config + install -m 644 config/freeze-callgraph.cfg $(DESTDIR)$(PREFIX)/lib/pm-graph/config + install -m 644 config/freeze.cfg $(DESTDIR)$(PREFIX)/lib/pm-graph/config + install -m 644 config/freeze-dev.cfg $(DESTDIR)$(PREFIX)/lib/pm-graph/config + install -m 644 config/standby-callgraph.cfg $(DESTDIR)$(PREFIX)/lib/pm-graph/config + install -m 644 config/standby.cfg $(DESTDIR)$(PREFIX)/lib/pm-graph/config + install -m 644 config/standby-dev.cfg $(DESTDIR)$(PREFIX)/lib/pm-graph/config + install -m 644 config/suspend-callgraph.cfg $(DESTDIR)$(PREFIX)/lib/pm-graph/config + install -m 644 config/suspend.cfg $(DESTDIR)$(PREFIX)/lib/pm-graph/config + install -m 644 config/suspend-dev.cfg $(DESTDIR)$(PREFIX)/lib/pm-graph/config + install -m 644 config/suspend-x2-proc.cfg $(DESTDIR)$(PREFIX)/lib/pm-graph/config - ln -s $(DESTDIR)$(PREFIX)/lib/pm-graph/analyze_boot.py $(DESTDIR)$(PREFIX)/bin/bootgraph - ln -s $(DESTDIR)$(PREFIX)/lib/pm-graph/analyze_suspend.py $(DESTDIR)$(PREFIX)/bin/sleepgraph + install -d $(DESTDIR)$(PREFIX)/bin + ln -s $(DESTDIR)$(PREFIX)/lib/pm-graph/bootgraph.py $(DESTDIR)$(PREFIX)/bin/bootgraph + ln -s $(DESTDIR)$(PREFIX)/lib/pm-graph/sleepgraph.py $(DESTDIR)$(PREFIX)/bin/sleepgraph install -d $(DESTDIR)$(PREFIX)/share/man/man8 install bootgraph.8 $(DESTDIR)$(PREFIX)/share/man/man8 @@ -24,9 +37,11 @@ uninstall : rm -f $(DESTDIR)$(PREFIX)/bin/bootgraph rm -f $(DESTDIR)$(PREFIX)/bin/sleepgraph - rm -f $(DESTDIR)$(PREFIX)/lib/pm-graph/analyze_boot.py - rm -f $(DESTDIR)$(PREFIX)/lib/pm-graph/analyze_suspend.py - rm -f $(DESTDIR)$(PREFIX)/lib/pm-graph/*.pyc + rm -f $(DESTDIR)$(PREFIX)/lib/pm-graph/config/* + if [ -d $(DESTDIR)$(PREFIX)/lib/pm-graph/config ] ; then \ + rmdir $(DESTDIR)$(PREFIX)/lib/pm-graph/config; \ + fi; + rm -f $(DESTDIR)$(PREFIX)/lib/pm-graph/* if [ -d $(DESTDIR)$(PREFIX)/lib/pm-graph ] ; then \ rmdir $(DESTDIR)$(PREFIX)/lib/pm-graph; \ fi; diff --git a/tools/power/pm-graph/bootgraph.8 b/tools/power/pm-graph/bootgraph.8 index dbdafcf546df..64d513f80a2a 100644 --- a/tools/power/pm-graph/bootgraph.8 +++ b/tools/power/pm-graph/bootgraph.8 @@ -37,6 +37,9 @@ Print the current tool version Add the dmesg log to the html output. It will be viewable by clicking a button in the timeline. .TP +\fB-result \fIfile\fR +Export a results table to a text file for parsing. +.TP \fB-o \fIname\fR Overrides the output subdirectory name when running a new test. Use {date}, {time}, {hostname} for current values. @@ -44,14 +47,14 @@ Use {date}, {time}, {hostname} for current values. e.g. boot-{hostname}-{date}-{time} .SS "advanced" .TP -\fB-f\fR -Use ftrace to add function detail (default: disabled) -.TP -\fB-callgraph\fR +\fB-f or -callgraph\fR Use ftrace to create initcall callgraphs (default: disabled). If -func is not used there will be one callgraph per initcall. This can produce very large outputs, i.e. 10MB - 100MB. .TP +\fB-fstat\fR +Use ftrace to add function detail (default: disabled) +.TP \fB-maxdepth \fIlevel\fR limit the callgraph trace depth to \fIlevel\fR (default: 2). This is the best way to limit the output size when using -callgraph. @@ -67,6 +70,13 @@ Reduce callgraph output in the timeline by limiting it to a list of calls. The argument can be a single function name or a comma delimited list. (default: none) .TP +\fB-cgskip \fIfile\fR +Reduce callgraph output in the timeline by skipping over uninteresting +functions in the trace, e.g. printk or console_unlock. The functions listed +in this file will show up as empty leaves in the callgraph with only the start/end +times displayed. +(default: none) +.TP \fB-timeprec \fIn\fR Number of significant digits in timestamps (0:S, 3:ms, [6:us]) .TP diff --git a/tools/power/pm-graph/analyze_boot.py b/tools/power/pm-graph/bootgraph.py index e83df141a597..abb4c38f029b 100755 --- a/tools/power/pm-graph/analyze_boot.py +++ b/tools/power/pm-graph/bootgraph.py @@ -32,7 +32,7 @@ import platform import shutil from datetime import datetime, timedelta from subprocess import call, Popen, PIPE -import analyze_suspend as aslib +import sleepgraph as aslib # ----------------- CLASSES -------------------- @@ -42,23 +42,18 @@ import analyze_suspend as aslib # store system values and test parameters class SystemValues(aslib.SystemValues): title = 'BootGraph' - version = '2.1' + version = '2.2' hostname = 'localhost' testtime = '' kernel = '' dmesgfile = '' ftracefile = '' htmlfile = 'bootgraph.html' - outfile = '' testdir = '' - testdirprefix = 'boot' - embedded = False - testlog = False - dmesglog = False - ftracelog = False + kparams = '' + result = '' useftrace = False usecallgraph = False - usedevsrc = True suspendmode = 'boot' max_graph_depth = 2 graph_filter = 'do_one_initcall' @@ -69,11 +64,6 @@ class SystemValues(aslib.SystemValues): bootloader = 'grub' blexec = [] def __init__(self): - if('LOG_FILE' in os.environ and 'TEST_RESULTS_IDENTIFIER' in os.environ): - self.embedded = True - self.dmesglog = True - self.outfile = os.environ['LOG_FILE'] - self.htmlfile = os.environ['LOG_FILE'] self.hostname = platform.node() self.testtime = datetime.now().strftime('%Y-%m-%d_%H:%M:%S') if os.path.exists('/proc/version'): @@ -148,11 +138,18 @@ class SystemValues(aslib.SystemValues): cmdline = '%s -cronjob' % os.path.abspath(sys.argv[0]) args = iter(sys.argv[1:]) for arg in args: - if arg in ['-h', '-v', '-cronjob', '-reboot']: + if arg in ['-h', '-v', '-cronjob', '-reboot', '-verbose']: continue elif arg in ['-o', '-dmesg', '-ftrace', '-func']: args.next() continue + elif arg == '-result': + cmdline += ' %s "%s"' % (arg, os.path.abspath(args.next())) + continue + elif arg == '-cgskip': + file = self.configFile(args.next()) + cmdline += ' %s "%s"' % (arg, os.path.abspath(file)) + continue cmdline += ' '+arg if self.graph_filter != 'do_one_initcall': cmdline += ' -func "%s"' % self.graph_filter @@ -166,14 +163,6 @@ class SystemValues(aslib.SystemValues): print '3. After reboot, re-run this tool with the same arguments but no command (w/o -reboot or -manual).\n' print 'CMDLINE="%s"' % cmdline sys.exit() - def getExec(self, cmd): - dirlist = ['/sbin', '/bin', '/usr/sbin', '/usr/bin', - '/usr/local/sbin', '/usr/local/bin'] - for path in dirlist: - cmdfull = os.path.join(path, cmd) - if os.path.exists(cmdfull): - return cmdfull - return '' def blGrub(self): blcmd = '' for cmd in ['update-grub', 'grub-mkconfig', 'grub2-mkconfig']: @@ -199,6 +188,14 @@ class SystemValues(aslib.SystemValues): self.blGrub() else: doError('unknown boot loader: %s' % self.bootloader) + def writeDatafileHeader(self, filename): + self.kparams = open('/proc/cmdline', 'r').read().strip() + fp = open(filename, 'w') + fp.write(self.teststamp+'\n') + fp.write(self.sysstamp+'\n') + fp.write('# command | %s\n' % self.cmdline) + fp.write('# kparams | %s\n' % self.kparams) + fp.close() sysvals = SystemValues() @@ -249,7 +246,7 @@ class Data(aslib.Data): return name def deviceMatch(self, pid, cg): if cg.end - cg.start == 0: - return True + return '' for p in data.phases: list = self.dmesg[p]['list'] for devname in list: @@ -260,14 +257,25 @@ class Data(aslib.Data): if(cg.start <= dev['start'] and cg.end >= dev['end'] and dev['length'] > 0): dev['ftrace'] = cg self.do_one_initcall = True - return True + return devname else: if(cg.start > dev['start'] and cg.end < dev['end']): if 'ftraces' not in dev: dev['ftraces'] = [] dev['ftraces'].append(cg) - return True - return False + return devname + return '' + def printDetails(self): + sysvals.vprint('Timeline Details:') + sysvals.vprint(' Host: %s' % sysvals.hostname) + sysvals.vprint(' Kernel: %s' % sysvals.kernel) + sysvals.vprint(' Test time: %s' % sysvals.testtime) + sysvals.vprint(' Boot time: %s' % self.boottime) + for phase in self.phases: + dc = len(self.dmesg[phase]['list']) + sysvals.vprint('%9s mode: %.3f - %.3f (%d initcalls)' % (phase, + self.dmesg[phase]['start']*1000, + self.dmesg[phase]['end']*1000, dc)) # ----------------- FUNCTIONS -------------------- @@ -275,6 +283,8 @@ class Data(aslib.Data): # Description: # parse a kernel log for boot data def parseKernelLog(): + sysvals.vprint('Analyzing the dmesg data (%s)...' % \ + os.path.basename(sysvals.dmesgfile)) phase = 'kernel' data = Data(0) data.dmesg['kernel']['start'] = data.start = ktime = 0.0 @@ -298,6 +308,12 @@ def parseKernelLog(): elif re.match(tp.sysinfofmt, line): tp.sysinfo = line continue + elif re.match(tp.cmdlinefmt, line): + tp.cmdline = line + continue + elif re.match(tp.kparamsfmt, line): + tp.kparams = line + continue idx = line.find('[') if idx > 1: line = line[idx:] @@ -353,6 +369,17 @@ def parseKernelLog(): # Description: # Check if trace is available and copy to a temp file def parseTraceLog(data): + sysvals.vprint('Analyzing the ftrace data (%s)...' % \ + os.path.basename(sysvals.ftracefile)) + # if available, calculate cgfilter allowable ranges + cgfilter = [] + if len(sysvals.cgfilter) > 0: + for p in data.phases: + list = data.dmesg[p]['list'] + for i in sysvals.cgfilter: + if i in list: + cgfilter.append([list[i]['start']-0.0001, + list[i]['end']+0.0001]) # parse the trace log ftemp = dict() tp = aslib.TestProps() @@ -366,7 +393,16 @@ def parseTraceLog(data): continue m_time, m_proc, m_pid, m_msg, m_dur = \ m.group('time', 'proc', 'pid', 'msg', 'dur') - if float(m_time) > data.end: + t = float(m_time) + if len(cgfilter) > 0: + allow = False + for r in cgfilter: + if t >= r[0] and t < r[1]: + allow = True + break + if not allow: + continue + if t > data.end: break if(m_time and m_pid and m_msg): t = aslib.FTraceLine(m_time, m_msg, m_dur) @@ -378,24 +414,36 @@ def parseTraceLog(data): key = (m_proc, pid) if(key not in ftemp): ftemp[key] = [] - ftemp[key].append(aslib.FTraceCallGraph(pid)) + ftemp[key].append(aslib.FTraceCallGraph(pid, sysvals)) cg = ftemp[key][-1] - if(cg.addLine(t)): - ftemp[key].append(aslib.FTraceCallGraph(pid)) + res = cg.addLine(t) + if(res != 0): + ftemp[key].append(aslib.FTraceCallGraph(pid, sysvals)) + if(res == -1): + ftemp[key][-1].addLine(t) + tf.close() # add the callgraph data to the device hierarchy for key in ftemp: proc, pid = key for cg in ftemp[key]: - if len(cg.list) < 1 or cg.invalid: + if len(cg.list) < 1 or cg.invalid or (cg.end - cg.start == 0): continue if(not cg.postProcess()): print('Sanity check failed for %s-%d' % (proc, pid)) continue # match cg data to devices - if not data.deviceMatch(pid, cg): - print ' BAD: %s %s-%d [%f - %f]' % (cg.name, proc, pid, cg.start, cg.end) + devname = data.deviceMatch(pid, cg) + if not devname: + kind = 'Orphan' + if cg.partial: + kind = 'Partial' + sysvals.vprint('%s callgraph found for %s %s-%d [%f - %f]' %\ + (kind, cg.name, proc, pid, cg.start, cg.end)) + elif len(cg.list) > 1000000: + print 'WARNING: the callgraph found for %s is massive! (%d lines)' %\ + (devname, len(cg.list)) # Function: retrieveLogs # Description: @@ -473,7 +521,7 @@ def createBootGraph(data): devtl = aslib.Timeline(100, 20) # write the test title and general info header - devtl.createHeader(sysvals) + devtl.createHeader(sysvals, sysvals.stamp) # Generate the header for this timeline t0 = data.start @@ -574,12 +622,9 @@ def createBootGraph(data): data.dmesg[phase]['color'], phase+'_mode', phase[0]) devtl.html += '</div>\n' - if(sysvals.outfile == sysvals.htmlfile): - hf = open(sysvals.htmlfile, 'a') - else: - hf = open(sysvals.htmlfile, 'w') + hf = open(sysvals.htmlfile, 'w') - # add the css if this is not an embedded run + # add the css extra = '\ .c1 {background:rgba(209,0,0,0.4);}\n\ .c2 {background:rgba(255,102,34,0.4);}\n\ @@ -597,8 +642,7 @@ def createBootGraph(data): .fstat td {text-align:left;width:35px;}\n\ .srccall {position:absolute;font-size:10px;z-index:7;overflow:hidden;color:black;text-align:center;white-space:nowrap;border-radius:5px;border:1px solid black;background:linear-gradient(to bottom right,#CCC,#969696);}\n\ .srccall:hover {color:white;font-weight:bold;border:1px solid white;}\n' - if(not sysvals.embedded): - aslib.addCSS(hf, sysvals, 1, False, extra) + aslib.addCSS(hf, sysvals, 1, False, extra) # write the device timeline hf.write(devtl.html) @@ -631,6 +675,9 @@ def createBootGraph(data): if(sysvals.usecallgraph): aslib.addCallgraphs(sysvals, hf, data) + # add the test log as a hidden div + if sysvals.testlog and sysvals.logmsg: + hf.write('<div id="testlog" style="display:none;">\n'+sysvals.logmsg+'</div>\n') # add the dmesg log as a hidden div if sysvals.dmesglog: hf.write('<div id="dmesglog" style="display:none;">\n') @@ -639,14 +686,9 @@ def createBootGraph(data): hf.write(line) hf.write('</div>\n') - if(not sysvals.embedded): - # write the footer and close - aslib.addScriptCode(hf, [data]) - hf.write('</body>\n</html>\n') - else: - # embedded out will be loaded in a page, skip the js - hf.write('<div id=bounds style=display:none>%f,%f</div>' % \ - (data.start*1000, data.end*1000)) + # write the footer and close + aslib.addScriptCode(hf, [data]) + hf.write('</body>\n</html>\n') hf.close() return True @@ -780,6 +822,7 @@ def doError(msg, help=False): if help == True: printHelp() print 'ERROR: %s\n' % msg + sysvals.outputResult({'error':msg}) sys.exit() # Function: printHelp @@ -806,18 +849,21 @@ def printHelp(): print('Options:') print(' -h Print this help text') print(' -v Print the current tool version') + print(' -verbose Print extra information during execution and analysis') print(' -addlogs Add the dmesg log to the html output') + print(' -result fn Export a results table to a text file for parsing.') print(' -o name Overrides the output subdirectory name when running a new test') print(' default: boot-{date}-{time}') print(' [advanced]') - print(' -f Use ftrace to add function detail (default: disabled)') - print(' -callgraph Add callgraph detail, can be very large (default: disabled)') + print(' -fstat Use ftrace to add function detail and statistics (default: disabled)') + print(' -f/-callgraph Add callgraph detail, can be very large (default: disabled)') print(' -maxdepth N limit the callgraph data to N call levels (default: 2)') print(' -mincg ms Discard all callgraphs shorter than ms milliseconds (e.g. 0.001 for us)') print(' -timeprec N Number of significant digits in timestamps (0:S, 3:ms, [6:us])') print(' -expandcg pre-expand the callgraph data in the html output (default: disabled)') print(' -func list Limit ftrace to comma-delimited list of functions (default: do_one_initcall)') print(' -cgfilter S Filter the callgraph output in the timeline') + print(' -cgskip file Callgraph functions to skip, off to disable (default: cgskip.txt)') print(' -bl name Use the following boot loader for kernel params (default: grub)') print(' -reboot Reboot the machine automatically and generate a new timeline') print(' -manual Show the steps to generate a new timeline manually (used with -reboot)') @@ -837,8 +883,13 @@ if __name__ == '__main__': # loop through the command line arguments cmd = '' testrun = True + switchoff = ['disable', 'off', 'false', '0'] simplecmds = ['-sysinfo', '-kpupdate', '-flistall', '-checkbl'] + cgskip = '' + if '-f' in sys.argv: + cgskip = sysvals.configFile('cgskip.txt') args = iter(sys.argv[1:]) + mdset = False for arg in args: if(arg == '-h'): printHelp() @@ -846,13 +897,17 @@ if __name__ == '__main__': elif(arg == '-v'): print("Version %s" % sysvals.version) sys.exit() + elif(arg == '-verbose'): + sysvals.verbose = True elif(arg in simplecmds): cmd = arg[1:] - elif(arg == '-f'): + elif(arg == '-fstat'): sysvals.useftrace = True - elif(arg == '-callgraph'): + elif(arg == '-callgraph' or arg == '-f'): sysvals.useftrace = True sysvals.usecallgraph = True + elif(arg == '-cgdump'): + sysvals.cgdump = True elif(arg == '-mincg'): sysvals.mincglen = aslib.getArgFloat('-mincg', args, 0.0, 10000.0) elif(arg == '-cgfilter'): @@ -860,7 +915,18 @@ if __name__ == '__main__': val = args.next() except: doError('No callgraph functions supplied', True) - sysvals.setDeviceFilter(val) + sysvals.setCallgraphFilter(val) + elif(arg == '-cgskip'): + try: + val = args.next() + except: + doError('No file supplied', True) + if val.lower() in switchoff: + cgskip = '' + else: + cgskip = sysvals.configFile(val) + if(not cgskip): + doError('%s does not exist' % cgskip) elif(arg == '-bl'): try: val = args.next() @@ -872,6 +938,7 @@ if __name__ == '__main__': elif(arg == '-timeprec'): sysvals.setPrecision(aslib.getArgInt('-timeprec', args, 0, 6)) elif(arg == '-maxdepth'): + mdset = True sysvals.max_graph_depth = aslib.getArgInt('-maxdepth', args, 0, 1000) elif(arg == '-func'): try: @@ -902,8 +969,6 @@ if __name__ == '__main__': doError('No dmesg file supplied', True) if(os.path.exists(val) == False): doError('%s does not exist' % val) - if(sysvals.htmlfile == val or sysvals.outfile == val): - doError('Output filename collision') testrun = False sysvals.dmesgfile = val elif(arg == '-o'): @@ -912,6 +977,12 @@ if __name__ == '__main__': except: doError('No subdirectory name supplied', True) sysvals.testdir = sysvals.setOutputFolder(val) + elif(arg == '-result'): + try: + val = args.next() + except: + doError('No result file supplied', True) + sysvals.result = val elif(arg == '-reboot'): sysvals.reboot = True elif(arg == '-manual'): @@ -947,7 +1018,7 @@ if __name__ == '__main__': sysvals.getBootLoader() print 'Boot Loader: %s\n%s' % (sysvals.bootloader, sysvals.blexec) elif(cmd == 'sysinfo'): - sysvals.printSystemInfo() + sysvals.printSystemInfo(True) sys.exit() # reboot: update grub, setup a cronjob, and reboot @@ -963,6 +1034,10 @@ if __name__ == '__main__': sysvals.manualRebootRequired() sys.exit() + if sysvals.usecallgraph and cgskip: + sysvals.vprint('Using cgskip file: %s' % cgskip) + sysvals.setCallgraphBlacklist(cgskip) + # cronjob: remove the cronjob, grub changes, and disable ftrace if sysvals.iscronjob: updateCron(True) @@ -980,29 +1055,23 @@ if __name__ == '__main__': # process the log data if sysvals.dmesgfile: + if not mdset: + sysvals.max_graph_depth = 0 data = parseKernelLog() if(not data.valid): doError('No initcall data found in %s' % sysvals.dmesgfile) if sysvals.useftrace and sysvals.ftracefile: parseTraceLog(data) + if sysvals.cgdump: + data.debugPrint() + sys.exit() else: doError('dmesg file required') - print(' Host: %s' % sysvals.hostname) - print(' Test time: %s' % sysvals.testtime) - print(' Boot time: %s' % data.boottime) - print('Kernel Version: %s' % sysvals.kernel) - print(' Kernel start: %.3f' % (data.start * 1000)) - print('Usermode start: %.3f' % (data.tUserMode * 1000)) - print('Last Init Call: %.3f' % (data.end * 1000)) - - # handle embedded output logs - if(sysvals.outfile and sysvals.embedded): - fp = open(sysvals.outfile, 'w') - fp.write('pass %s initstart %.3f end %.3f boot %s\n' % - (data.valid, data.tUserMode*1000, data.end*1000, data.boottime)) - fp.close() - + sysvals.vprint('Creating the html timeline (%s)...' % sysvals.htmlfile) + sysvals.vprint('Command:\n %s' % sysvals.cmdline) + sysvals.vprint('Kernel parameters:\n %s' % sysvals.kparams) + data.printDetails() createBootGraph(data) # if running as root, change output dir owner to sudo_user @@ -1010,3 +1079,7 @@ if __name__ == '__main__': os.getuid() == 0 and 'SUDO_USER' in os.environ: cmd = 'chown -R {0}:{0} {1} > /dev/null 2>&1' call(cmd.format(os.environ['SUDO_USER'], sysvals.testdir), shell=True) + + sysvals.stamp['boot'] = (data.tUserMode - data.start) * 1000 + sysvals.stamp['lastinit'] = data.end * 1000 + sysvals.outputResult(sysvals.stamp) diff --git a/tools/power/pm-graph/config/cgskip.txt b/tools/power/pm-graph/config/cgskip.txt new file mode 100644 index 000000000000..e48d588fbfb4 --- /dev/null +++ b/tools/power/pm-graph/config/cgskip.txt @@ -0,0 +1,65 @@ +# ----------------------------------------------- +# CallGraph function skip list +# +# This file contains a list of functions which are +# meant to be skipped in the callgraph trace. It reduces +# the callgraph html file size by treating these functions +# as leaves with no child calls. It can be editted by +# adding or removing function symbol names. +# +# The sleepgraph tool automatically pulls this file in when +# it is found in the config folder. It can be ignored if +# the tool is called with "-cgskip off". +# ----------------------------------------------- + +# low level scheduling and timing +up +down_timeout +mutex_lock +down_read +complete_all +schedule_timeout +wake_up_process +msleep +__udelay +ktime_get + +# console calls +printk +dev_printk +console_unlock + +# memory handling +__kmalloc +__kmalloc_track_caller +kmem_cache_alloc +kmem_cache_alloc_trace +kmem_cache_free +kstrdup +kstrdup_const +kmalloc_slab +new_slab +__slab_alloc +__slab_free +raw_pci_read +pci_read +alloc_pages_current + +# debugfs and sysfs setup +debugfs_remove_recursive +debugfs_create_dir +debugfs_create_files +debugfs_create_dir +debugfs_get_inode +sysfs_add_file_mode_ns +sysfs_add_file +sysfs_create_dir_ns +sysfs_create_link +sysfs_create_group +sysfs_create_groups +sysfs_create_bin_file +dpm_sysfs_add +sysfs_create_file_ns +sysfs_merge_group +sysfs_add_link_to_group +sysfs_create_link_sd diff --git a/tools/power/pm-graph/config/custom-timeline-functions.cfg b/tools/power/pm-graph/config/custom-timeline-functions.cfg new file mode 100644 index 000000000000..4f80ad7d7275 --- /dev/null +++ b/tools/power/pm-graph/config/custom-timeline-functions.cfg @@ -0,0 +1,205 @@ +# +# This is the configuration file for sleepgraph. It contains +# all the tool arguments so that they don't have to be given on the +# command line. It also includes advanced settings for functions +# and kprobes. It is run like this +# +# sudo ./sleepgraph.py -config thisfile.txt +# + +[Settings] + +# Verbosity +# print verbose messages (default: false) +verbose: false + +# Suspend Mode +# e.g. standby, mem, freeze, disk (default: mem) +mode: mem + +# Automatic Wakeup +# Use rtcwake to autoresume after X seconds, or off to disable (default: 15) +rtcwake: 15 + +# Add Logs +# add the dmesg and ftrace log to the html output (default: false) +addlogs: false + +# Display function calls +# graph source functions in the timeline (default: false) +dev: true + +# Callgraph +# gather detailed ftrace callgraph data on all timeline events (default: false) +callgraph: false + +# Back to Back Suspend/Resume +# Run two suspend/resumes back to back (default: false) +x2: false + +# Back to Back Suspend Delay +# Time delay between the two test runs in ms (default: 0 ms) +x2delay: 0 + +# Minimum Device Length +# graph only devices longer than min in the timeline (default: 0.001 ms) +mindev: 1 + +# Minimum Callgraph Length +# provide callgraph data for blocks longer than min (default: 0.001 ms) +mincg: 1 + +# Suspend/Resume Gap +# insert a small visible gap between suspend and resume on the timeline (default: false) +srgap: false + +# Output Directory Format +# output folder for html, ftrace, and dmesg. Use {date} and {time} for current values +output-dir: suspend-{hostname}-{date}-{time}-custom + +# Override default timeline entries +# Do not use the internal default functions for timeline entries (default: false) +# Set this to true if you intend to only use the ones defined in this config +override-timeline-functions: true + +# Override default dev timeline entries +# Do not use the internal default functions for dev timeline entries (default: false) +# Set this to true if you intend to only use the ones defined in this config +override-dev-timeline-functions: true + +[timeline_functions_x86_64] +# +# Function calls to display in the timeline alongside device callbacks. +# The tool has an internal set of these functions which should cover the +# whole of kernel execution, but you can append or override here. +# +# This is a list of kprobes which use both symbol data and function arg data. +# The function calls are displayed on the timeline alongside the device blocks. +# The args are pulled directly from the stack using this architecture's registers +# and stack formatting. Three pieces of info are required. The function name, +# a format string, and an argument list +# +# Entry format: +# +# function: format{fn_arg1}_{fn_arg2} fn_arg1 fn_arg2 ... [color=purple] +# +# Required Arguments: +# +# function: The symbol name for the function you want probed, this is the +# minimum required for an entry, it will show up as the function +# name with no arguments. +# +# example: _cpu_up: +# +# Optional Arguments: +# +# format: The format to display the data on the timeline in. Use braces to +# enclose the arg names. +# +# example: CPU_ON[{cpu}] +# +# color: The color of the entry block in the timeline. The default color is +# transparent, so the entry shares the phase color. The color is an +# html color string, either a word, or an RGB. +# +# example: [color=#CC00CC] +# +# arglist: A list of arguments from registers/stack addresses. See URL: +# https://www.kernel.org/doc/Documentation/trace/kprobetrace.txt +# +# example: cpu=%di:s32 +# +# Example: Display cpu resume in the timeline +# +# _cpu_up: CPU_ON[{cpu}] cpu=%di:s32 [color=orange] +# +_cpu_down: CPU_OFF[{cpu}] cpu=%di:s32 +_cpu_up: CPU_ON[{cpu}] cpu=%di:s32 +sys_sync: +pm_prepare_console: +pm_notifier_call_chain: +freeze_processes: +freeze_kernel_threads: +pm_restrict_gfp_mask: +acpi_suspend_begin: +suspend_console: +acpi_pm_prepare: +syscore_suspend: +arch_enable_nonboot_cpus_end: +syscore_resume: +acpi_pm_finish: +resume_console: +acpi_pm_end: +pm_restore_gfp_mask: +thaw_processes: +pm_restore_console: + +[dev_timeline_functions_x86_64] +# +# Dev mode function calls to display inside timeline entries +# +# This is a list of kprobes which use both symbol data and function arg data. +# The function calls are displayed on the timeline alongside the device blocks. +# The args are pulled directly from the stack using this architecture's registers +# and stack formatting. Three pieces of info are required. The function name, +# a format string, and an argument list +# +# Entry format: +# +# function: format{fn_arg1}_{fn_arg2} fn_arg1 fn_arg2 ... [color=purple] +# +# Required Arguments: +# +# function: The symbol name for the function you want probed, this is the +# minimum required for an entry, it will show up as the function +# name with no arguments. +# +# example: ata_eh_recover: +# +# Optional Arguments: +# +# format: The format to display the data on the timeline in. Use braces to +# enclose the arg names. +# +# example: ata{port}_port_reset +# +# color: The color of the entry block in the timeline. The default color is +# transparent, so the entry shares the phase color. The color is an +# html color string, either a word, or an RGB. +# +# example: [color=#CC00CC] +# +# arglist: A list of arguments from registers/stack addresses. See URL: +# https://www.kernel.org/doc/Documentation/trace/kprobetrace.txt +# +# example: port=+36(%di):s32 +# +# Example: Display ATA port reset as ataN_port_reset in the timeline +# +# ata_eh_recover: ata{port}_port_reset port=+36(%di):s32 +# +msleep: msleep time=%di:s32 +schedule_timeout_uninterruptible: schedule_timeout_uninterruptible timeout=%di:s32 +schedule_timeout: schedule_timeout timeout=%di:s32 +usleep_range: usleep_range min=%di:s32 max=%si:s32 +__const_udelay: udelay loops=%di:s32 +__mutex_lock_slowpath: mutex_lock_slowpath +ata_eh_recover: ata_eh_recover port=+36(%di):s32 +acpi_os_stall: +acpi_resume_power_resources: +acpi_ps_parse_aml: +ext4_sync_fs: +i915_gem_resume: +i915_restore_state: +intel_opregion_setup: +g4x_pre_enable_dp: +vlv_pre_enable_dp: +chv_pre_enable_dp: +g4x_enable_dp: +vlv_enable_dp: +intel_hpd_init: +intel_opregion_register: +intel_dp_detect: +intel_hdmi_detect: +intel_opregion_init: +intel_fbdev_set_suspend: diff --git a/tools/power/pm-graph/config/example.cfg b/tools/power/pm-graph/config/example.cfg new file mode 100644 index 000000000000..05b2efb9bb54 --- /dev/null +++ b/tools/power/pm-graph/config/example.cfg @@ -0,0 +1,133 @@ +# +# Generic S3 (Suspend to Mem) test +# +# This is the configuration file for sleepgraph. It contains +# all the tool arguments so that they don't have to be given on the +# command line. It also includes advanced settings for functions +# and kprobes. It is run like this +# +# sudo ./sleepgraph.py -config config/example.cfg +# + +[Settings] + +# ---- General Options ---- + +# Verbosity +# print verbose messages (default: false) +verbose: false + +# Suspend Mode +# e.g. standby, mem, freeze, disk (default: mem) +mode: mem + +# Output Directory Format +# output folder for html, ftrace, and dmesg. Use {date} and {time} for current values +output-dir: suspend-{hostname}-{date}-{time} + +# Automatic Wakeup +# Use rtcwake to autoresume after X seconds, or off to disable (default: 15) +rtcwake: 15 + +# Add Logs +# add the dmesg and ftrace log to the html output (default: false) +addlogs: true + +# Suspend/Resume Gap +# insert a small visible gap between suspend and resume on the timeline (default: false) +srgap: false + +# Skip HTML generation +# Only capture the logs, don't generate the html timeline (default: false) +skiphtml: false + +# Sync filesystem before suspend +# run sync before the test, minimizes sys_sync call time (default: false) +sync: true + +# Runtime suspend enable/disable +# Enable/disable runtime suspend for all devices, restore all after test (default: no-action) +# rs: disable + +# Turn display on/off for test +# Switch the display on/off for the test using xset (default: no-action) +# display: on + +# Print results to text file +# Print the status of the test run in the given file (default: no-action) +result: result.txt + +# Gzip the log files to save space +# Gzip the generated log files, and read gzipped log files (default: false) +gzip: true + +# ---- Advanced Options ---- + +# Command to execute in lieu of suspend (default: "") +# command: echo mem > /sys/power/state + +# Display user processes +# graph user processes and cpu usage in the timeline (default: false) +proc: false + +# Display function calls +# graph source functions in the timeline (default: false) +dev: false + +# Multiple test runs +# Run N tests D seconds apart, generates separate outputs with a summary (default: false) +# multi: 3 5 + +# Back to Back Suspend/Resume +# Run two suspend/resumes back to back and display in the same timeline (default: false) +x2: false + +# Back to Back Suspend Delay +# Time delay between the two test runs in ms (default: 0 ms) +x2delay: 0 + +# Pre Suspend Delay +# Include an N ms delay before (1st) suspend (default: 0 ms) +predelay: 0 + +# Post Resume Delay +# Include an N ms delay after (last) resume (default: 0 ms) +postdelay: 0 + +# Minimum Device Length +# graph only devices longer than min in the timeline (default: 0.001 ms) +mindev: 0.001 + +# ---- Debug Options ---- + +# Callgraph +# gather detailed ftrace callgraph data on all timeline events (default: false) +callgraph: false + +# Callgraph phase filter +# Only enable callgraphs for one phase, i.e. resume_noirq (default: all) +cgphase: suspend + +# Callgraph x2 test filter +# Only enable callgraphs test 0 or 1 when using -x2 (default: 1) +cgtest: 0 + +# Expand Callgraph +# pre-expand the callgraph data in the html output (default: disabled) +expandcg: false + +# Minimum Callgraph Length +# provide callgraph data for blocks longer than min (default: 0.001 ms) +mincg: 1 + +# Timestamp Precision +# Number of significant digits in timestamps (0:S, [3:ms], 6:us) +timeprec: 6 + +# Device Filter +# show only devices whose name/driver includes one of these strings +# devicefilter: _cpu_up,_cpu_down,i915,usb + +# Add kprobe functions to the timeline +# Add functions to the timeline from a text file (default: no-action) +# fadd: file.txt diff --git a/tools/power/pm-graph/config/freeze-callgraph.cfg b/tools/power/pm-graph/config/freeze-callgraph.cfg new file mode 100644 index 000000000000..f692821c4828 --- /dev/null +++ b/tools/power/pm-graph/config/freeze-callgraph.cfg @@ -0,0 +1,94 @@ +# +# Full Callgraph for S2 (Freeze) test +# +# This is the configuration file for sleepgraph. It contains +# all the tool arguments so that they don't have to be given on the +# command line. It also includes advanced settings for functions +# and kprobes. It is run like this +# +# sudo ./sleepgraph.py -config config/freeze-callgraph.cfg +# +# NOTE: the output of this test is very large (> 30MB) + +[Settings] + +# ---- General Options ---- + +# Verbosity +# print verbose messages (default: false) +verbose: false + +# Suspend Mode +# e.g. standby, mem, freeze, disk (default: mem) +mode: freeze + +# Output Directory Format +# output folder for html, ftrace, and dmesg. Use {date} and {time} for current values +output-dir: freeze-{hostname}-{date}-{time}-cg + +# Automatic Wakeup +# Use rtcwake to autoresume after X seconds, or off to disable (default: 15) +rtcwake: 15 + +# Add Logs +# add the dmesg and ftrace log to the html output (default: false) +addlogs: false + +# Suspend/Resume Gap +# insert a small visible gap between suspend and resume on the timeline (default: false) +srgap: false + +# ---- Advanced Options ---- + +# Command to execute in lieu of freeze (default: "") +# command: echo freeze > /sys/power/state + +# Display user processes +# graph user processes and cpu usage in the timeline (default: false) +proc: false + +# Display function calls +# graph source functions in the timeline (default: false) +dev: false + +# Back to Back Suspend/Resume +# Run two suspend/resumes back to back (default: false) +x2: false + +# Back to Back Suspend Delay +# Time delay between the two test runs in ms (default: 0 ms) +x2delay: 0 + +# Pre Suspend Delay +# Include an N ms delay before (1st) suspend (default: 0 ms) +predelay: 0 + +# Post Resume Delay +# Include an N ms delay after (last) resume (default: 0 ms) +postdelay: 0 + +# Minimum Device Length +# graph only devices longer than min in the timeline (default: 0.001 ms) +mindev: 1 + +# ---- Debug Options ---- + +# Callgraph +# gather detailed ftrace callgraph data on all timeline events (default: false) +callgraph: true + +# Expand Callgraph +# pre-expand the callgraph data in the html output (default: disabled) +expandcg: false + +# Minimum Callgraph Length +# provide callgraph data for blocks longer than min (default: 0.001 ms) +mincg: 1 + +# Timestamp Precision +# Number of significant digits in timestamps (0:S, [3:ms], 6:us) +timeprec: 6 + +# Device Filter +# show only devs whose name/driver includes one of these strings +# devicefilter: _cpu_up,_cpu_down,i915,usb diff --git a/tools/power/pm-graph/config/freeze-dev.cfg b/tools/power/pm-graph/config/freeze-dev.cfg new file mode 100644 index 000000000000..c4ad5cea3cbf --- /dev/null +++ b/tools/power/pm-graph/config/freeze-dev.cfg @@ -0,0 +1,93 @@ +# +# Dev S2 (Freeze) test - includes src calls / kernel threads +# +# This is the configuration file for sleepgraph. It contains +# all the tool arguments so that they don't have to be given on the +# command line. It also includes advanced settings for functions +# and kprobes. It is run like this +# +# sudo ./sleepgraph.py -config config/freeze-dev.cfg +# + +[Settings] + +# ---- General Options ---- + +# Verbosity +# print verbose messages (default: false) +verbose: false + +# Suspend Mode +# e.g. standby, mem, freeze, disk (default: mem) +mode: freeze + +# Output Directory Format +# output folder for html, ftrace, and dmesg. Use {date} and {time} for current values +output-dir: freeze-{hostname}-{date}-{time}-dev + +# Automatic Wakeup +# Use rtcwake to autoresume after X seconds, or off to disable (default: 15) +rtcwake: 15 + +# Add Logs +# add the dmesg and ftrace log to the html output (default: false) +addlogs: false + +# Suspend/Resume Gap +# insert a small visible gap between suspend and resume on the timeline (default: false) +srgap: false + +# ---- Advanced Options ---- + +# Command to execute in lieu of freeze (default: "") +# command: echo freeze > /sys/power/state + +# Display user processes +# graph user processes and cpu usage in the timeline (default: false) +proc: false + +# Display function calls +# graph source functions in the timeline (default: false) +dev: true + +# Back to Back Suspend/Resume +# Run two suspend/resumes back to back (default: false) +x2: false + +# Back to Back Suspend Delay +# Time delay between the two test runs in ms (default: 0 ms) +x2delay: 0 + +# Pre Suspend Delay +# Include an N ms delay before (1st) suspend (default: 0 ms) +predelay: 0 + +# Post Resume Delay +# Include an N ms delay after (last) resume (default: 0 ms) +postdelay: 0 + +# Minimum Device Length +# graph only devices longer than min in the timeline (default: 0.001 ms) +mindev: 1 + +# ---- Debug Options ---- + +# Callgraph +# gather detailed ftrace callgraph data on all timeline events (default: false) +callgraph: false + +# Expand Callgraph +# pre-expand the callgraph data in the html output (default: disabled) +expandcg: false + +# Minimum Callgraph Length +# provide callgraph data for blocks longer than min (default: 0.001 ms) +mincg: 1 + +# Timestamp Precision +# Number of significant digits in timestamps (0:S, [3:ms], 6:us) +timeprec: 3 + +# Device Filter +# show only devs whose name/driver includes one of these strings +# devicefilter: _cpu_up,_cpu_down,i915,usb diff --git a/tools/power/pm-graph/config/freeze.cfg b/tools/power/pm-graph/config/freeze.cfg new file mode 100644 index 000000000000..0b70e0b74527 --- /dev/null +++ b/tools/power/pm-graph/config/freeze.cfg @@ -0,0 +1,93 @@ +# +# Generic S2 (Freeze) test +# +# This is the configuration file for sleepgraph. It contains +# all the tool arguments so that they don't have to be given on the +# command line. It also includes advanced settings for functions +# and kprobes. It is run like this +# +# sudo ./sleepgraph.py -config config/freeze.cfg +# + +[Settings] + +# ---- General Options ---- + +# Verbosity +# print verbose messages (default: false) +verbose: false + +# Suspend Mode +# e.g. standby, mem, freeze, disk (default: mem) +mode: freeze + +# Output Directory Format +# output folder for html, ftrace, and dmesg. Use {date} and {time} for current values +output-dir: freeze-{hostname}-{date}-{time} + +# Automatic Wakeup +# Use rtcwake to autoresume after X seconds, or off to disable (default: 15) +rtcwake: 15 + +# Add Logs +# add the dmesg and ftrace log to the html output (default: false) +addlogs: false + +# Suspend/Resume Gap +# insert a small visible gap between suspend and resume on the timeline (default: false) +srgap: false + +# ---- Advanced Options ---- + +# Command to execute in lieu of freeze (default: "") +# command: echo freeze > /sys/power/state + +# Display user processes +# graph user processes and cpu usage in the timeline (default: false) +proc: false + +# Display function calls +# graph source functions in the timeline (default: false) +dev: false + +# Back to Back Suspend/Resume +# Run two suspend/resumes back to back (default: false) +x2: false + +# Back to Back Suspend Delay +# Time delay between the two test runs in ms (default: 0 ms) +x2delay: 0 + +# Pre Suspend Delay +# Include an N ms delay before (1st) suspend (default: 0 ms) +predelay: 0 + +# Post Resume Delay +# Include an N ms delay after (last) resume (default: 0 ms) +postdelay: 0 + +# Minimum Device Length +# graph only devices longer than min in the timeline (default: 0.001 ms) +mindev: 0.001 + +# ---- Debug Options ---- + +# Callgraph +# gather detailed ftrace callgraph data on all timeline events (default: false) +callgraph: false + +# Expand Callgraph +# pre-expand the callgraph data in the html output (default: disabled) +expandcg: false + +# Minimum Callgraph Length +# provide callgraph data for blocks longer than min (default: 0.001 ms) +mincg: 1 + +# Timestamp Precision +# Number of significant digits in timestamps (0:S, [3:ms], 6:us) +timeprec: 3 + +# Device Filter +# show only devs whose name/driver includes one of these strings +# devicefilter: _cpu_up,_cpu_down,i915,usb diff --git a/tools/power/pm-graph/config/standby-callgraph.cfg b/tools/power/pm-graph/config/standby-callgraph.cfg new file mode 100644 index 000000000000..f52a6b9d5c32 --- /dev/null +++ b/tools/power/pm-graph/config/standby-callgraph.cfg @@ -0,0 +1,94 @@ +# +# Full Callgraph for S1 (Standby) test +# +# This is the configuration file for sleepgraph. It contains +# all the tool arguments so that they don't have to be given on the +# command line. It also includes advanced settings for functions +# and kprobes. It is run like this +# +# sudo ./sleepgraph.py -config config/standby-callgraph.cfg +# +# NOTE: the output of this test is very large (> 30MB) + +[Settings] + +# ---- General Options ---- + +# Verbosity +# print verbose messages (default: false) +verbose: false + +# Suspend Mode +# e.g. standby, mem, freeze, disk (default: mem) +mode: standby + +# Output Directory Format +# output folder for html, ftrace, and dmesg. Use {date} and {time} for current values +output-dir: standby-{hostname}-{date}-{time}-cg + +# Automatic Wakeup +# Use rtcwake to autoresume after X seconds, or off to disable (default: 15) +rtcwake: 15 + +# Add Logs +# add the dmesg and ftrace log to the html output (default: false) +addlogs: false + +# Suspend/Resume Gap +# insert a small visible gap between suspend and resume on the timeline (default: false) +srgap: false + +# ---- Advanced Options ---- + +# Command to execute in lieu of standby (default: "") +# command: echo standby > /sys/power/state + +# Display user processes +# graph user processes and cpu usage in the timeline (default: false) +proc: false + +# Display function calls +# graph source functions in the timeline (default: false) +dev: false + +# Back to Back Suspend/Resume +# Run two suspend/resumes back to back (default: false) +x2: false + +# Back to Back Suspend Delay +# Time delay between the two test runs in ms (default: 0 ms) +x2delay: 0 + +# Pre Suspend Delay +# Include an N ms delay before (1st) suspend (default: 0 ms) +predelay: 0 + +# Post Resume Delay +# Include an N ms delay after (last) resume (default: 0 ms) +postdelay: 0 + +# Minimum Device Length +# graph only devices longer than min in the timeline (default: 0.001 ms) +mindev: 1 + +# ---- Debug Options ---- + +# Callgraph +# gather detailed ftrace callgraph data on all timeline events (default: false) +callgraph: true + +# Expand Callgraph +# pre-expand the callgraph data in the html output (default: disabled) +expandcg: false + +# Minimum Callgraph Length +# provide callgraph data for blocks longer than min (default: 0.001 ms) +mincg: 1 + +# Timestamp Precision +# Number of significant digits in timestamps (0:S, [3:ms], 6:us) +timeprec: 6 + +# Device Filter +# show only devs whose name/driver includes one of these strings +# devicefilter: _cpu_up,_cpu_down,i915,usb diff --git a/tools/power/pm-graph/config/standby-dev.cfg b/tools/power/pm-graph/config/standby-dev.cfg new file mode 100644 index 000000000000..a5498ece3def --- /dev/null +++ b/tools/power/pm-graph/config/standby-dev.cfg @@ -0,0 +1,93 @@ +# +# Dev S1 (Standby) test - includes src calls / kernel threads +# +# This is the configuration file for sleepgraph. It contains +# all the tool arguments so that they don't have to be given on the +# command line. It also includes advanced settings for functions +# and kprobes. It is run like this +# +# sudo ./sleepgraph.py -config config/standby-dev.cfg +# + +[Settings] + +# ---- General Options ---- + +# Verbosity +# print verbose messages (default: false) +verbose: false + +# Suspend Mode +# e.g. standby, mem, freeze, disk (default: mem) +mode: standby + +# Output Directory Format +# output folder for html, ftrace, and dmesg. Use {date} and {time} for current values +output-dir: standby-{hostname}-{date}-{time}-dev + +# Automatic Wakeup +# Use rtcwake to autoresume after X seconds, or off to disable (default: 15) +rtcwake: 15 + +# Add Logs +# add the dmesg and ftrace log to the html output (default: false) +addlogs: false + +# Suspend/Resume Gap +# insert a small visible gap between suspend and resume on the timeline (default: false) +srgap: false + +# ---- Advanced Options ---- + +# Command to execute in lieu of standby (default: "") +# command: echo standby > /sys/power/state + +# Display user processes +# graph user processes and cpu usage in the timeline (default: false) +proc: false + +# Display function calls +# graph source functions in the timeline (default: false) +dev: true + +# Back to Back Suspend/Resume +# Run two suspend/resumes back to back (default: false) +x2: false + +# Back to Back Suspend Delay +# Time delay between the two test runs in ms (default: 0 ms) +x2delay: 0 + +# Pre Suspend Delay +# Include an N ms delay before (1st) suspend (default: 0 ms) +predelay: 0 + +# Post Resume Delay +# Include an N ms delay after (last) resume (default: 0 ms) +postdelay: 0 + +# Minimum Device Length +# graph only devices longer than min in the timeline (default: 0.001 ms) +mindev: 1 + +# ---- Debug Options ---- + +# Callgraph +# gather detailed ftrace callgraph data on all timeline events (default: false) +callgraph: false + +# Expand Callgraph +# pre-expand the callgraph data in the html output (default: disabled) +expandcg: false + +# Minimum Callgraph Length +# provide callgraph data for blocks longer than min (default: 0.001 ms) +mincg: 1 + +# Timestamp Precision +# Number of significant digits in timestamps (0:S, [3:ms], 6:us) +timeprec: 3 + +# Device Filter +# show only devs whose name/driver includes one of these strings +# devicefilter: _cpu_up,_cpu_down,i915,usb diff --git a/tools/power/pm-graph/config/standby.cfg b/tools/power/pm-graph/config/standby.cfg new file mode 100644 index 000000000000..f0dd264dfeff --- /dev/null +++ b/tools/power/pm-graph/config/standby.cfg @@ -0,0 +1,93 @@ +# +# Generic S1 (Standby) test +# +# This is the configuration file for sleepgraph. It contains +# all the tool arguments so that they don't have to be given on the +# command line. It also includes advanced settings for functions +# and kprobes. It is run like this +# +# sudo ./sleepgraph.py -config config/standby.cfg +# + +[Settings] + +# ---- General Options ---- + +# Verbosity +# print verbose messages (default: false) +verbose: false + +# Suspend Mode +# e.g. standby, mem, freeze, disk (default: mem) +mode: standby + +# Output Directory Format +# output folder for html, ftrace, and dmesg. Use {date} and {time} for current values +output-dir: standby-{hostname}-{date}-{time} + +# Automatic Wakeup +# Use rtcwake to autoresume after X seconds, or off to disable (default: 15) +rtcwake: 15 + +# Add Logs +# add the dmesg and ftrace log to the html output (default: false) +addlogs: false + +# Suspend/Resume Gap +# insert a small visible gap between suspend and resume on the timeline (default: false) +srgap: false + +# ---- Advanced Options ---- + +# Command to execute in lieu of standby (default: "") +# command: echo standby > /sys/power/state + +# Display user processes +# graph user processes and cpu usage in the timeline (default: false) +proc: false + +# Display function calls +# graph source functions in the timeline (default: false) +dev: false + +# Back to Back Suspend/Resume +# Run two suspend/resumes back to back (default: false) +x2: false + +# Back to Back Suspend Delay +# Time delay between the two test runs in ms (default: 0 ms) +x2delay: 0 + +# Pre Suspend Delay +# Include an N ms delay before (1st) suspend (default: 0 ms) +predelay: 0 + +# Post Resume Delay +# Include an N ms delay after (last) resume (default: 0 ms) +postdelay: 0 + +# Minimum Device Length +# graph only devices longer than min in the timeline (default: 0.001 ms) +mindev: 0.001 + +# ---- Debug Options ---- + +# Callgraph +# gather detailed ftrace callgraph data on all timeline events (default: false) +callgraph: false + +# Expand Callgraph +# pre-expand the callgraph data in the html output (default: disabled) +expandcg: false + +# Minimum Callgraph Length +# provide callgraph data for blocks longer than min (default: 0.001 ms) +mincg: 1 + +# Timestamp Precision +# Number of significant digits in timestamps (0:S, [3:ms], 6:us) +timeprec: 3 + +# Device Filter +# show only devs whose name/driver includes one of these strings +# devicefilter: _cpu_up,_cpu_down,i915,usb diff --git a/tools/power/pm-graph/config/suspend-callgraph.cfg b/tools/power/pm-graph/config/suspend-callgraph.cfg new file mode 100644 index 000000000000..11b8cbc12d34 --- /dev/null +++ b/tools/power/pm-graph/config/suspend-callgraph.cfg @@ -0,0 +1,98 @@ +# +# Full Callgraph for S3 (Suspend to Mem) test +# +# This is the configuration file for sleepgraph. It contains +# all the tool arguments so that they don't have to be given on the +# command line. It also includes advanced settings for functions +# and kprobes. It is run like this +# +# sudo ./sleepgraph.py -config config/suspend.cfg +# +# NOTE: the output of this test is very large (> 30MB) + +[Settings] + +# ---- General Options ---- + +# Verbosity +# print verbose messages (default: false) +verbose: false + +# Suspend Mode +# e.g. standby, mem, freeze, disk (default: mem) +mode: mem + +# Output Directory Format +# output folder for html, ftrace, and dmesg. Use {date} and {time} for current values +output-dir: suspend-{hostname}-{date}-{time}-cg + +# Automatic Wakeup +# Use rtcwake to autoresume after X seconds, or off to disable (default: 15) +rtcwake: 15 + +# Add Logs +# add the dmesg and ftrace log to the html output (default: false) +addlogs: false + +# Suspend/Resume Gap +# insert a small visible gap between suspend and resume on the timeline (default: false) +srgap: false + +# ---- Advanced Options ---- + +# Command to execute in lieu of suspend (default: "") +# command: echo mem > /sys/power/state + +# Display user processes +# graph user processes and cpu usage in the timeline (default: false) +proc: false + +# Display function calls +# graph source functions in the timeline (default: false) +dev: false + +# Back to Back Suspend/Resume +# Run two suspend/resumes back to back (default: false) +x2: false + +# Back to Back Suspend Delay +# Time delay between the two test runs in ms (default: 0 ms) +x2delay: 0 + +# Pre Suspend Delay +# Include an N ms delay before (1st) suspend (default: 0 ms) +predelay: 0 + +# Post Resume Delay +# Include an N ms delay after (last) resume (default: 0 ms) +postdelay: 0 + +# Minimum Device Length +# graph only devices longer than min in the timeline (default: 0.001 ms) +mindev: 0.001 + +# ---- Debug Options ---- + +# Callgraph +# gather detailed ftrace callgraph data on all timeline events (default: false) +callgraph: true + +# Max graph depth +# limit the callgraph trace to this depth (default: 0 = all) +maxdepth: 5 + +# Expand Callgraph +# pre-expand the callgraph data in the html output (default: disabled) +expandcg: false + +# Minimum Callgraph Length +# provide callgraph data for blocks longer than min (default: 0.001 ms) +mincg: 1 + +# Timestamp Precision +# Number of significant digits in timestamps (0:S, [3:ms], 6:us) +timeprec: 6 + +# Device Filter +# show only devs whose name/driver includes one of these strings +# devicefilter: _cpu_up,_cpu_down,i915,usb diff --git a/tools/power/pm-graph/config/suspend-dev.cfg b/tools/power/pm-graph/config/suspend-dev.cfg new file mode 100644 index 000000000000..56f1d21cc79b --- /dev/null +++ b/tools/power/pm-graph/config/suspend-dev.cfg @@ -0,0 +1,93 @@ +# +# Dev S3 (Suspend to Mem) test - includes src calls / kernel threads +# +# This is the configuration file for sleepgraph. It contains +# all the tool arguments so that they don't have to be given on the +# command line. It also includes advanced settings for functions +# and kprobes. It is run like this +# +# sudo ./sleepgraph.py -config config/suspend-dev.cfg +# + +[Settings] + +# ---- General Options ---- + +# Verbosity +# print verbose messages (default: false) +verbose: false + +# Suspend Mode +# e.g. standby, mem, freeze, disk (default: mem) +mode: mem + +# Output Directory Format +# output folder for html, ftrace, and dmesg. Use {date} and {time} for current values +output-dir: suspend-{hostname}-{date}-{time}-dev + +# Automatic Wakeup +# Use rtcwake to autoresume after X seconds, or off to disable (default: 15) +rtcwake: 15 + +# Add Logs +# add the dmesg and ftrace log to the html output (default: false) +addlogs: false + +# Suspend/Resume Gap +# insert a small visible gap between suspend and resume on the timeline (default: false) +srgap: false + +# ---- Advanced Options ---- + +# Command to execute in lieu of suspend (default: "") +# command: echo mem > /sys/power/state + +# Display user processes +# graph user processes and cpu usage in the timeline (default: false) +proc: false + +# Display function calls +# graph source functions in the timeline (default: false) +dev: true + +# Back to Back Suspend/Resume +# Run two suspend/resumes back to back (default: false) +x2: false + +# Back to Back Suspend Delay +# Time delay between the two test runs in ms (default: 0 ms) +x2delay: 0 + +# Pre Suspend Delay +# Include an N ms delay before (1st) suspend (default: 0 ms) +predelay: 0 + +# Post Resume Delay +# Include an N ms delay after (last) resume (default: 0 ms) +postdelay: 0 + +# Minimum Device Length +# graph only devices longer than min in the timeline (default: 0.001 ms) +mindev: 1 + +# ---- Debug Options ---- + +# Callgraph +# gather detailed ftrace callgraph data on all timeline events (default: false) +callgraph: false + +# Expand Callgraph +# pre-expand the callgraph data in the html output (default: disabled) +expandcg: false + +# Minimum Callgraph Length +# provide callgraph data for blocks longer than min (default: 0.001 ms) +mincg: 1 + +# Timestamp Precision +# Number of significant digits in timestamps (0:S, [3:ms], 6:us) +timeprec: 3 + +# Device Filter +# show only devs whose name/driver includes one of these strings +# devicefilter: _cpu_up,_cpu_down,i915,usb diff --git a/tools/power/pm-graph/config/suspend-x2-proc.cfg b/tools/power/pm-graph/config/suspend-x2-proc.cfg new file mode 100644 index 000000000000..0ecca0ede138 --- /dev/null +++ b/tools/power/pm-graph/config/suspend-x2-proc.cfg @@ -0,0 +1,93 @@ +# +# Proc S3 (Suspend to Mem) x2 test - includes user processes +# +# This is the configuration file for sleepgraph. It contains +# all the tool arguments so that they don't have to be given on the +# command line. It also includes advanced settings for functions +# and kprobes. It is run like this +# +# sudo ./sleepgraph.py -config config/suspend-proc.cfg +# + +[Settings] + +# ---- General Options ---- + +# Verbosity +# print verbose messages (default: false) +verbose: false + +# Suspend Mode +# e.g. standby, mem, freeze, disk (default: mem) +mode: mem + +# Output Directory Format +# output folder for html, ftrace, and dmesg. Use {date} and {time} for current values +output-dir: suspend-{hostname}-{date}-{time}-x2-proc + +# Automatic Wakeup +# Use rtcwake to autoresume after X seconds, or off to disable (default: 15) +rtcwake: 15 + +# Add Logs +# add the dmesg and ftrace log to the html output (default: false) +addlogs: false + +# Suspend/Resume Gap +# insert a small visible gap between suspend and resume on the timeline (default: false) +srgap: false + +# ---- Advanced Options ---- + +# Command to execute in lieu of suspend (default: "") +# command: echo mem > /sys/power/state + +# Display user processes +# graph user processes and cpu usage in the timeline (default: false) +proc: true + +# Display function calls +# graph source functions in the timeline (default: false) +dev: false + +# Back to Back Suspend/Resume +# Run two suspend/resumes back to back (default: false) +x2: true + +# Back to Back Suspend Delay +# Time delay between the two test runs in ms (default: 0 ms) +x2delay: 1000 + +# Pre Suspend Delay +# Include an N ms delay before (1st) suspend (default: 0 ms) +predelay: 1000 + +# Post Resume Delay +# Include an N ms delay after (last) resume (default: 0 ms) +postdelay: 1000 + +# Minimum Device Length +# graph only devices longer than min in the timeline (default: 0.001 ms) +mindev: 1 + +# ---- Debug Options ---- + +# Callgraph +# gather detailed ftrace callgraph data on all timeline events (default: false) +callgraph: false + +# Expand Callgraph +# pre-expand the callgraph data in the html output (default: disabled) +expandcg: false + +# Minimum Callgraph Length +# provide callgraph data for blocks longer than min (default: 0.001 ms) +mincg: 1 + +# Timestamp Precision +# Number of significant digits in timestamps (0:S, [3:ms], 6:us) +timeprec: 3 + +# Device Filter +# show only devs whose name/driver includes one of these strings +# devicefilter: _cpu_up,_cpu_down,i915,usb diff --git a/tools/power/pm-graph/config/suspend.cfg b/tools/power/pm-graph/config/suspend.cfg new file mode 100644 index 000000000000..70d293231b06 --- /dev/null +++ b/tools/power/pm-graph/config/suspend.cfg @@ -0,0 +1,93 @@ +# +# Generic S3 (Suspend to Mem) test +# +# This is the configuration file for sleepgraph. It contains +# all the tool arguments so that they don't have to be given on the +# command line. It also includes advanced settings for functions +# and kprobes. It is run like this +# +# sudo ./sleepgraph.py -config config/suspend.cfg +# + +[Settings] + +# ---- General Options ---- + +# Verbosity +# print verbose messages (default: false) +verbose: false + +# Suspend Mode +# e.g. standby, mem, freeze, disk (default: mem) +mode: mem + +# Output Directory Format +# output folder for html, ftrace, and dmesg. Use {date} and {time} for current values +output-dir: suspend-{hostname}-{date}-{time} + +# Automatic Wakeup +# Use rtcwake to autoresume after X seconds, or off to disable (default: 15) +rtcwake: 15 + +# Add Logs +# add the dmesg and ftrace log to the html output (default: false) +addlogs: false + +# Suspend/Resume Gap +# insert a small visible gap between suspend and resume on the timeline (default: false) +srgap: false + +# ---- Advanced Options ---- + +# Command to execute in lieu of suspend (default: "") +# command: echo mem > /sys/power/state + +# Display user processes +# graph user processes and cpu usage in the timeline (default: false) +proc: false + +# Display function calls +# graph source functions in the timeline (default: false) +dev: false + +# Back to Back Suspend/Resume +# Run two suspend/resumes back to back (default: false) +x2: false + +# Back to Back Suspend Delay +# Time delay between the two test runs in ms (default: 0 ms) +x2delay: 0 + +# Pre Suspend Delay +# Include an N ms delay before (1st) suspend (default: 0 ms) +predelay: 0 + +# Post Resume Delay +# Include an N ms delay after (last) resume (default: 0 ms) +postdelay: 0 + +# Minimum Device Length +# graph only devices longer than min in the timeline (default: 0.001 ms) +mindev: 0.001 + +# ---- Debug Options ---- + +# Callgraph +# gather detailed ftrace callgraph data on all timeline events (default: false) +callgraph: false + +# Expand Callgraph +# pre-expand the callgraph data in the html output (default: disabled) +expandcg: false + +# Minimum Callgraph Length +# provide callgraph data for blocks longer than min (default: 0.001 ms) +mincg: 1 + +# Timestamp Precision +# Number of significant digits in timestamps (0:S, [3:ms], 6:us) +timeprec: 3 + +# Device Filter +# show only devs whose name/driver includes one of these strings +# devicefilter: _cpu_up,_cpu_down,i915,usb diff --git a/tools/power/pm-graph/sleepgraph.8 b/tools/power/pm-graph/sleepgraph.8 index fbe7bd3eae8e..18baaf6300c9 100644 --- a/tools/power/pm-graph/sleepgraph.8 +++ b/tools/power/pm-graph/sleepgraph.8 @@ -52,9 +52,32 @@ disable rtcwake and require a user keypress to resume. \fB-addlogs\fR Add the dmesg and ftrace logs to the html output. They will be viewable by clicking buttons in the timeline. +.TP +\fB-result \fIfile\fR +Export a results table to a text file for parsing. +.TP +\fB-sync\fR +Sync the filesystems before starting the test. This reduces the size of +the sys_sync call which happens in the suspend_prepare phase. +.TP +\fB-rs \fIenable/disable\fR +During test, enable/disable runtime suspend for all devices. The test is delayed +by 5 seconds to allow runtime suspend changes to occur. The settings are restored +after the test is complete. +.TP +\fB-display \fIon/off\fR +Turn the display on or off for the test using the xset command. This helps +maintain the consistecy of test data for better comparison. +.TP +\fB-skiphtml\fR +Run the test and capture the trace logs, but skip the timeline generation. .SS "advanced" .TP +\fB-gzip\fR +Gzip the trace and dmesg logs to save space. The tool can also read in gzipped +logs for processing. +.TP \fB-cmd \fIstr\fR Run the timeline over a custom suspend command, e.g. pm-suspend. By default the tool forces suspend via /sys/power/state so this allows testing over @@ -114,6 +137,18 @@ This reduces the html file size as there can be many tiny callgraphs which are barely visible in the timeline. The value is a float: e.g. 0.001 represents 1 us. .TP +\fB-cgfilter \fI"func1,func2,..."\fR +Reduce callgraph output in the timeline by limiting it to a list of calls. The +argument can be a single function name or a comma delimited list. +(default: none) +.TP +\fB-cgskip \fIfile\fR +Reduce callgraph timeline size by skipping over uninteresting functions +in the trace, e.g. printk or console_unlock. The functions listed +in this file will show up as empty leaves in the callgraph with only the start/end +times displayed. cgskip.txt is used automatically if found in the path, so +use "off" to disable completely (default: cgskip.txt) +.TP \fB-cgphase \fIp\fR Only show callgraph data for phase \fIp\fR (e.g. suspend_late). .TP @@ -122,6 +157,9 @@ In an x2 run, only show callgraph data for test \fIn\fR (e.g. 0 or 1). .TP \fB-timeprec \fIn\fR Number of significant digits in timestamps (0:S, [3:ms], 6:us). +.TP +\fB-bufsize \fIN\fR +Set trace buffer size to N kilo-bytes (default: all of free memory up to 3GB) .SH COMMANDS .TP @@ -144,11 +182,8 @@ Print out the contents of the ACPI Firmware Performance Data Table. \fB-sysinfo\fR Print out system info extracted from BIOS. Reads /dev/mem directly instead of going through dmidecode. .TP -\fB-usbtopo\fR -Print out the current USB topology with power info. -.TP -\fB-usbauto\fR -Enable autosuspend for all connected USB devices. +\fB-devinfo\fR +Print out the pm settings of all devices which support runtime suspend. .TP \fB-flist\fR Print the list of ftrace functions currently being captured. Functions @@ -198,7 +233,7 @@ Execute a mem suspend with a 15 second wakeup. Include the logs in the html. .PP Execute a standby with a 15 second wakeup. Change the output folder name. .IP -\f(CW$ sudo sleepgraph -m standby -rtcwake 15 -o "standby-{hostname}-{date}-{time}"\fR +\f(CW$ sudo sleepgraph -m standby -rtcwake 15 -o "standby-{host}-{date}-{time}"\fR .PP Execute a freeze with no wakeup (require keypress). Change output folder name. .IP diff --git a/tools/power/pm-graph/analyze_suspend.py b/tools/power/pm-graph/sleepgraph.py index 1b60fe203741..266409fb27ae 100755 --- a/tools/power/pm-graph/analyze_suspend.py +++ b/tools/power/pm-graph/sleepgraph.py @@ -19,7 +19,7 @@ # Home Page # https://01.org/suspendresume # Source repo -# https://github.com/01org/pm-graph +# git@github.com:01org/pm-graph # # Description: # This tool is designed to assist kernel and OS developers in optimizing @@ -57,6 +57,7 @@ import platform from datetime import datetime import struct import ConfigParser +import gzip from threading import Thread from subprocess import call, Popen, PIPE @@ -68,8 +69,12 @@ from subprocess import call, Popen, PIPE # store system values and test parameters class SystemValues: title = 'SleepGraph' - version = '4.7' + version = '5.0' ansi = False + rs = 0 + display = 0 + gzip = False + sync = False verbose = False testlog = True dmesglog = False @@ -78,14 +83,19 @@ class SystemValues: mincglen = 0.0 cgphase = '' cgtest = -1 + cgskip = '' + multitest = {'run': False, 'count': 0, 'delay': 0} max_graph_depth = 0 callloopmaxgap = 0.0001 callloopmaxlen = 0.005 + bufsize = 0 cpucount = 0 memtotal = 204800 + memfree = 204800 srgap = 0 cgexp = False testdir = '' + outdir = '' tpath = '/sys/kernel/debug/tracing/' fpdtpath = '/sys/firmware/acpi/tables/FPDT' epath = '/sys/kernel/debug/tracing/events/power/' @@ -109,22 +119,24 @@ class SystemValues: dmesgfile = '' ftracefile = '' htmlfile = 'output.html' - embedded = False + result = '' rtcwake = True rtcwaketime = 15 rtcpath = '' devicefilter = [] + cgfilter = [] stamp = 0 execcount = 1 x2delay = 0 + skiphtml = False usecallgraph = False usetraceevents = False - usetraceeventsonly = False usetracemarkers = True usekprobes = True usedevsrc = False useprocmon = False notestrun = False + cgdump = False mixedphaseheight = True devprops = dict() predelay = 0 @@ -134,24 +146,33 @@ class SystemValues: tracertypefmt = '# tracer: (?P<t>.*)' firmwarefmt = '# fwsuspend (?P<s>[0-9]*) fwresume (?P<r>[0-9]*)$' tracefuncs = { - 'sys_sync': dict(), - 'pm_prepare_console': dict(), - 'pm_notifier_call_chain': dict(), - 'freeze_processes': dict(), - 'freeze_kernel_threads': dict(), - 'pm_restrict_gfp_mask': dict(), - 'acpi_suspend_begin': dict(), - 'suspend_console': dict(), - 'acpi_pm_prepare': dict(), - 'syscore_suspend': dict(), - 'arch_enable_nonboot_cpus_end': dict(), - 'syscore_resume': dict(), - 'acpi_pm_finish': dict(), - 'resume_console': dict(), - 'acpi_pm_end': dict(), - 'pm_restore_gfp_mask': dict(), - 'thaw_processes': dict(), - 'pm_restore_console': dict(), + 'sys_sync': {}, + '__pm_notifier_call_chain': {}, + 'pm_prepare_console': {}, + 'pm_notifier_call_chain': {}, + 'freeze_processes': {}, + 'freeze_kernel_threads': {}, + 'pm_restrict_gfp_mask': {}, + 'acpi_suspend_begin': {}, + 'acpi_hibernation_begin': {}, + 'acpi_hibernation_enter': {}, + 'acpi_hibernation_leave': {}, + 'acpi_pm_freeze': {}, + 'acpi_pm_thaw': {}, + 'hibernate_preallocate_memory': {}, + 'create_basic_memory_bitmaps': {}, + 'swsusp_write': {}, + 'suspend_console': {}, + 'acpi_pm_prepare': {}, + 'syscore_suspend': {}, + 'arch_enable_nonboot_cpus_end': {}, + 'syscore_resume': {}, + 'acpi_pm_finish': {}, + 'resume_console': {}, + 'acpi_pm_end': {}, + 'pm_restore_gfp_mask': {}, + 'thaw_processes': {}, + 'pm_restore_console': {}, 'CPU_OFF': { 'func':'_cpu_down', 'args_x86_64': {'cpu':'%di:s32'}, @@ -173,56 +194,54 @@ class SystemValues: 'mutex_lock_slowpath': { 'func':'__mutex_lock_slowpath', 'ub': 1 }, 'acpi_os_stall': {'ub': 1}, # ACPI - 'acpi_resume_power_resources': dict(), - 'acpi_ps_parse_aml': dict(), + 'acpi_resume_power_resources': {}, + 'acpi_ps_parse_aml': {}, # filesystem - 'ext4_sync_fs': dict(), + 'ext4_sync_fs': {}, # 80211 - 'iwlagn_mac_start': dict(), - 'iwlagn_alloc_bcast_station': dict(), - 'iwl_trans_pcie_start_hw': dict(), - 'iwl_trans_pcie_start_fw': dict(), - 'iwl_run_init_ucode': dict(), - 'iwl_load_ucode_wait_alive': dict(), - 'iwl_alive_start': dict(), - 'iwlagn_mac_stop': dict(), - 'iwlagn_mac_suspend': dict(), - 'iwlagn_mac_resume': dict(), - 'iwlagn_mac_add_interface': dict(), - 'iwlagn_mac_remove_interface': dict(), - 'iwlagn_mac_change_interface': dict(), - 'iwlagn_mac_config': dict(), - 'iwlagn_configure_filter': dict(), - 'iwlagn_mac_hw_scan': dict(), - 'iwlagn_bss_info_changed': dict(), - 'iwlagn_mac_channel_switch': dict(), - 'iwlagn_mac_flush': dict(), + 'iwlagn_mac_start': {}, + 'iwlagn_alloc_bcast_station': {}, + 'iwl_trans_pcie_start_hw': {}, + 'iwl_trans_pcie_start_fw': {}, + 'iwl_run_init_ucode': {}, + 'iwl_load_ucode_wait_alive': {}, + 'iwl_alive_start': {}, + 'iwlagn_mac_stop': {}, + 'iwlagn_mac_suspend': {}, + 'iwlagn_mac_resume': {}, + 'iwlagn_mac_add_interface': {}, + 'iwlagn_mac_remove_interface': {}, + 'iwlagn_mac_change_interface': {}, + 'iwlagn_mac_config': {}, + 'iwlagn_configure_filter': {}, + 'iwlagn_mac_hw_scan': {}, + 'iwlagn_bss_info_changed': {}, + 'iwlagn_mac_channel_switch': {}, + 'iwlagn_mac_flush': {}, # ATA 'ata_eh_recover': { 'args_x86_64': {'port':'+36(%di):s32'} }, # i915 - 'i915_gem_resume': dict(), - 'i915_restore_state': dict(), - 'intel_opregion_setup': dict(), - 'g4x_pre_enable_dp': dict(), - 'vlv_pre_enable_dp': dict(), - 'chv_pre_enable_dp': dict(), - 'g4x_enable_dp': dict(), - 'vlv_enable_dp': dict(), - 'intel_hpd_init': dict(), - 'intel_opregion_register': dict(), - 'intel_dp_detect': dict(), - 'intel_hdmi_detect': dict(), - 'intel_opregion_init': dict(), - 'intel_fbdev_set_suspend': dict(), + 'i915_gem_resume': {}, + 'i915_restore_state': {}, + 'intel_opregion_setup': {}, + 'g4x_pre_enable_dp': {}, + 'vlv_pre_enable_dp': {}, + 'chv_pre_enable_dp': {}, + 'g4x_enable_dp': {}, + 'vlv_enable_dp': {}, + 'intel_hpd_init': {}, + 'intel_opregion_register': {}, + 'intel_dp_detect': {}, + 'intel_hdmi_detect': {}, + 'intel_opregion_init': {}, + 'intel_fbdev_set_suspend': {}, } + cgblacklist = [] kprobes = dict() timeformat = '%.3f' + cmdline = '%s %s' % \ + (os.path.basename(sys.argv[0]), string.join(sys.argv[1:], ' ')) def __init__(self): - # if this is a phoronix test run, set some default options - if('LOG_FILE' in os.environ and 'TEST_RESULTS_IDENTIFIER' in os.environ): - self.embedded = True - self.dmesglog = self.ftracelog = True - self.htmlfile = os.environ['LOG_FILE'] self.archargs = 'args_'+platform.machine() self.hostname = platform.node() if(self.hostname == ''): @@ -237,18 +256,36 @@ class SystemValues: if (hasattr(sys.stdout, 'isatty') and sys.stdout.isatty()): self.ansi = True self.testdir = datetime.now().strftime('suspend-%y%m%d-%H%M%S') + def vprint(self, msg): + self.logmsg += msg+'\n' + if(self.verbose): + print(msg) def rootCheck(self, fatal=True): if(os.access(self.powerfile, os.W_OK)): return True if fatal: - doError('This command requires sysfs mount and root access') + msg = 'This command requires sysfs mount and root access' + print('ERROR: %s\n') % msg + self.outputResult({'error':msg}) + sys.exit() return False def rootUser(self, fatal=False): if 'USER' in os.environ and os.environ['USER'] == 'root': return True if fatal: - doError('This command must be run as root') + msg = 'This command must be run as root' + print('ERROR: %s\n') % msg + self.outputResult({'error':msg}) + sys.exit() return False + def getExec(self, cmd): + dirlist = ['/sbin', '/bin', '/usr/sbin', '/usr/bin', + '/usr/local/sbin', '/usr/local/bin'] + for path in dirlist: + cmdfull = os.path.join(path, cmd) + if os.path.exists(cmdfull): + return cmdfull + return '' def setPrecision(self, num): if num < 0 or num > 6: return @@ -258,15 +295,15 @@ class SystemValues: n = datetime.now() args['date'] = n.strftime('%y%m%d') args['time'] = n.strftime('%H%M%S') - args['hostname'] = self.hostname + args['hostname'] = args['host'] = self.hostname return value.format(**args) def setOutputFile(self): if self.dmesgfile != '': - m = re.match('(?P<name>.*)_dmesg\.txt$', self.dmesgfile) + m = re.match('(?P<name>.*)_dmesg\.txt.*', self.dmesgfile) if(m): self.htmlfile = m.group('name')+'.html' if self.ftracefile != '': - m = re.match('(?P<name>.*)_ftrace\.txt$', self.ftracefile) + m = re.match('(?P<name>.*)_ftrace\.txt.*', self.ftracefile) if(m): self.htmlfile = m.group('name')+'.html' def systemInfo(self, info): @@ -283,16 +320,19 @@ class SystemValues: c = info['processor-version'] if 'bios-version' in info: b = info['bios-version'] - self.sysstamp = '# sysinfo | man:%s | plat:%s | cpu:%s | bios:%s | numcpu:%d | memsz:%d' % \ - (m, p, c, b, self.cpucount, self.memtotal) - def printSystemInfo(self): + self.sysstamp = '# sysinfo | man:%s | plat:%s | cpu:%s | bios:%s | numcpu:%d | memsz:%d | memfr:%d' % \ + (m, p, c, b, self.cpucount, self.memtotal, self.memfree) + def printSystemInfo(self, fatal=False): self.rootCheck(True) - out = dmidecode(self.mempath, True) + out = dmidecode(self.mempath, fatal) + if len(out) < 1: + return fmt = '%-24s: %s' for name in sorted(out): print fmt % (name, out[name]) print fmt % ('cpucount', ('%d' % self.cpucount)) print fmt % ('memtotal', ('%d kB' % self.memtotal)) + print fmt % ('memfree', ('%d kB' % self.memfree)) def cpuInfo(self): self.cpucount = 0 fp = open('/proc/cpuinfo', 'r') @@ -305,7 +345,9 @@ class SystemValues: m = re.match('^MemTotal:[ \t]*(?P<sz>[0-9]*) *kB', line) if m: self.memtotal = int(m.group('sz')) - break + m = re.match('^MemFree:[ \t]*(?P<sz>[0-9]*) *kB', line) + if m: + self.memfree = int(m.group('sz')) fp.close() def initTestOutput(self, name): self.prefix = self.hostname @@ -315,39 +357,34 @@ class SystemValues: testtime = datetime.now().strftime(fmt) self.teststamp = \ '# '+testtime+' '+self.prefix+' '+self.suspendmode+' '+kver - if(self.embedded): - self.dmesgfile = \ - '/tmp/'+testtime+'_'+self.suspendmode+'_dmesg.txt' - self.ftracefile = \ - '/tmp/'+testtime+'_'+self.suspendmode+'_ftrace.txt' - return + ext = '' + if self.gzip: + ext = '.gz' self.dmesgfile = \ - self.testdir+'/'+self.prefix+'_'+self.suspendmode+'_dmesg.txt' + self.testdir+'/'+self.prefix+'_'+self.suspendmode+'_dmesg.txt'+ext self.ftracefile = \ - self.testdir+'/'+self.prefix+'_'+self.suspendmode+'_ftrace.txt' + self.testdir+'/'+self.prefix+'_'+self.suspendmode+'_ftrace.txt'+ext self.htmlfile = \ self.testdir+'/'+self.prefix+'_'+self.suspendmode+'.html' if not os.path.isdir(self.testdir): os.mkdir(self.testdir) + def getValueList(self, value): + out = [] + for i in value.split(','): + if i.strip(): + out.append(i.strip()) + return out def setDeviceFilter(self, value): - self.devicefilter = [] - if value: - value = value.split(',') - for i in value: - self.devicefilter.append(i.strip()) + self.devicefilter = self.getValueList(value) + def setCallgraphFilter(self, value): + self.cgfilter = self.getValueList(value) + def setCallgraphBlacklist(self, file): + self.cgblacklist = self.listFromFile(file) def rtcWakeAlarmOn(self): call('echo 0 > '+self.rtcpath+'/wakealarm', shell=True) - outD = open(self.rtcpath+'/date', 'r').read().strip() - outT = open(self.rtcpath+'/time', 'r').read().strip() - mD = re.match('^(?P<y>[0-9]*)-(?P<m>[0-9]*)-(?P<d>[0-9]*)', outD) - mT = re.match('^(?P<h>[0-9]*):(?P<m>[0-9]*):(?P<s>[0-9]*)', outT) - if(mD and mT): - # get the current time from hardware - utcoffset = int((datetime.now() - datetime.utcnow()).total_seconds()) - dt = datetime(\ - int(mD.group('y')), int(mD.group('m')), int(mD.group('d')), - int(mT.group('h')), int(mT.group('m')), int(mT.group('s'))) - nowtime = int(dt.strftime('%s')) + utcoffset + nowtime = open(self.rtcpath+'/since_epoch', 'r').read().strip() + if nowtime: + nowtime = int(nowtime) else: # if hardware time fails, use the software time nowtime = int(datetime.now().strftime('%s')) @@ -369,10 +406,10 @@ class SystemValues: ktime = m.group('ktime') fp.close() self.dmesgstart = float(ktime) - def getdmesg(self): + def getdmesg(self, fwdata=[]): + op = self.writeDatafileHeader(sysvals.dmesgfile, fwdata) # store all new dmesg lines since initdmesg was called fp = Popen('dmesg', stdout=PIPE).stdout - op = open(self.dmesgfile, 'a') for line in fp: line = line.replace('\r\n', '') idx = line.find('[') @@ -386,11 +423,17 @@ class SystemValues: op.write(line) fp.close() op.close() - def addFtraceFilterFunctions(self, file): + def listFromFile(self, file): + list = [] fp = open(file) - list = fp.read().split('\n') + for i in fp.read().split('\n'): + i = i.strip() + if i and i[0] != '#': + list.append(i) fp.close() - for i in list: + return list + def addFtraceFilterFunctions(self, file): + for i in self.listFromFile(file): if len(i) < 2: continue self.tracefuncs[i] = dict() @@ -399,9 +442,7 @@ class SystemValues: if not current: call('cat '+self.tpath+'available_filter_functions', shell=True) return - fp = open(self.tpath+'available_filter_functions') - master = fp.read().split('\n') - fp.close() + master = self.listFromFile(self.tpath+'available_filter_functions') for i in self.tracefuncs: if 'func' in self.tracefuncs[i]: i = self.tracefuncs[i]['func'] @@ -410,9 +451,7 @@ class SystemValues: else: print self.colorText(i) def setFtraceFilterFunctions(self, list): - fp = open(self.tpath+'available_filter_functions') - master = fp.read().split('\n') - fp.close() + master = self.listFromFile(self.tpath+'available_filter_functions') flist = '' for i in list: if i not in master: @@ -501,6 +540,7 @@ class SystemValues: rejects = [] # sort kprobes: trace, ub-dev, custom, dev kpl = [[], [], [], []] + linesout = len(self.kprobes) for name in sorted(self.kprobes): res = self.colorText('YES', 32) if not self.testKprobe(name, self.kprobes[name]): @@ -528,17 +568,10 @@ class SystemValues: for kp in kplist: kprobeevents += self.kprobeText(kp, self.kprobes[kp]) self.fsetVal(kprobeevents, 'kprobe_events') - # verify that the kprobes were set as ordered - check = self.fgetVal('kprobe_events') - linesout = len(kprobeevents.split('\n')) - 1 - linesack = len(check.split('\n')) - 1 if output: - res = '%d/%d' % (linesack, linesout) - if linesack < linesout: - res = self.colorText(res, 31) - else: - res = self.colorText(res, 32) - print(' working kprobe functions enabled: %s' % res) + check = self.fgetVal('kprobe_events') + linesack = (len(check.split('\n')) - 1) / 2 + print(' kprobe functions enabled: %d/%d' % (linesack, linesout)) self.fsetVal('1', 'events/kprobes/enable') def testKprobe(self, kname, kprobe): self.fsetVal('0', 'events/kprobes/enable') @@ -555,8 +588,7 @@ class SystemValues: if linesack < linesout: return False return True - def fsetVal(self, val, path, mode='w'): - file = self.tpath+path + def setVal(self, val, file, mode='w'): if not os.path.exists(file): return False try: @@ -567,8 +599,9 @@ class SystemValues: except: return False return True - def fgetVal(self, path): - file = self.tpath+path + def fsetVal(self, val, path, mode='w'): + return self.setVal(val, self.tpath+path, mode) + def getVal(self, file): res = '' if not os.path.exists(file): return res @@ -579,10 +612,13 @@ class SystemValues: except: pass return res + def fgetVal(self, path): + return self.getVal(self.tpath+path) def cleanupFtrace(self): - if(self.usecallgraph or self.usetraceevents): + if(self.usecallgraph or self.usetraceevents or self.usedevsrc): self.fsetVal('0', 'events/kprobes/enable') self.fsetVal('', 'kprobe_events') + self.fsetVal('1024', 'buffer_size_kb') def setupAllKprobes(self): for name in self.tracefuncs: self.defaultKprobe(name, self.tracefuncs[name]) @@ -599,7 +635,8 @@ class SystemValues: if name == f: return True return False - def initFtrace(self, testing=False): + def initFtrace(self): + self.printSystemInfo(False) print('INITIALIZING FTRACE...') # turn trace off self.fsetVal('0', 'tracing_on') @@ -607,17 +644,21 @@ class SystemValues: # set the trace clock to global self.fsetVal('global', 'trace_clock') self.fsetVal('nop', 'current_tracer') - # set trace buffer to a huge value - if self.usecallgraph or self.usedevsrc: - tgtsize = min(self.memtotal / 2, 2*1024*1024) - maxbuf = '%d' % (tgtsize / max(1, self.cpucount)) - if self.cpucount < 1 or not self.fsetVal(maxbuf, 'buffer_size_kb'): - self.fsetVal('131072', 'buffer_size_kb') + # set trace buffer to an appropriate value + cpus = max(1, self.cpucount) + if self.bufsize > 0: + tgtsize = self.bufsize + elif self.usecallgraph or self.usedevsrc: + tgtsize = min(self.memfree, 3*1024*1024) else: - self.fsetVal('16384', 'buffer_size_kb') - # go no further if this is just a status check - if testing: - return + tgtsize = 65536 + while not self.fsetVal('%d' % (tgtsize / cpus), 'buffer_size_kb'): + # if the size failed to set, lower it and keep trying + tgtsize -= 65536 + if tgtsize < 65536: + tgtsize = int(self.fgetVal('buffer_size_kb')) * cpus + break + print 'Setting trace buffers to %d kB (%d kB per cpu)' % (tgtsize, tgtsize/cpus) # initialize the callgraph trace if(self.usecallgraph): # set trace type @@ -635,7 +676,7 @@ class SystemValues: self.fsetVal('graph-time', 'trace_options') self.fsetVal('%d' % self.max_graph_depth, 'max_graph_depth') cf = ['dpm_run_callback'] - if(self.usetraceeventsonly): + if(self.usetraceevents): cf += ['dpm_prepare', 'dpm_complete'] for fn in self.tracefuncs: if 'func' in self.tracefuncs[fn]: @@ -688,16 +729,65 @@ class SystemValues: return str return '\x1B[%d;40m%s\x1B[m' % (color, str) def writeDatafileHeader(self, filename, fwdata=[]): - fp = open(filename, 'w') - fp.write(self.teststamp+'\n') - fp.write(self.sysstamp+'\n') + fp = self.openlog(filename, 'w') + fp.write('%s\n%s\n# command | %s\n' % (self.teststamp, self.sysstamp, self.cmdline)) if(self.suspendmode == 'mem' or self.suspendmode == 'command'): for fw in fwdata: if(fw): fp.write('# fwsuspend %u fwresume %u\n' % (fw[0], fw[1])) + return fp + def sudouser(self, dir): + if os.path.exists(dir) and os.getuid() == 0 and \ + 'SUDO_USER' in os.environ: + cmd = 'chown -R {0}:{0} {1} > /dev/null 2>&1' + call(cmd.format(os.environ['SUDO_USER'], dir), shell=True) + def outputResult(self, testdata, num=0): + if not self.result: + return + n = '' + if num > 0: + n = '%d' % num + fp = open(self.result, 'a') + if 'error' in testdata: + fp.write('result%s: fail\n' % n) + fp.write('error%s: %s\n' % (n, testdata['error'])) + else: + fp.write('result%s: pass\n' % n) + for v in ['suspend', 'resume', 'boot', 'lastinit']: + if v in testdata: + fp.write('%s%s: %.3f\n' % (v, n, testdata[v])) + for v in ['fwsuspend', 'fwresume']: + if v in testdata: + fp.write('%s%s: %.3f\n' % (v, n, testdata[v] / 1000000.0)) + if 'bugurl' in testdata: + fp.write('url%s: %s\n' % (n, testdata['bugurl'])) fp.close() + self.sudouser(self.result) + def configFile(self, file): + dir = os.path.dirname(os.path.realpath(__file__)) + if os.path.exists(file): + return file + elif os.path.exists(dir+'/'+file): + return dir+'/'+file + elif os.path.exists(dir+'/config/'+file): + return dir+'/config/'+file + return '' + def openlog(self, filename, mode): + isgz = self.gzip + if mode == 'r': + try: + with gzip.open(filename, mode+'b') as fp: + test = fp.read(64) + isgz = True + except: + isgz = False + if isgz: + return gzip.open(filename, mode+'b') + return open(filename, mode) sysvals = SystemValues() +switchvalues = ['enable', 'disable', 'on', 'off', 'true', 'false', '1', '0'] +switchoff = ['disable', 'off', 'false', '0'] suspendmodename = { 'freeze': 'Freeze (S0)', 'standby': 'Standby (S1)', @@ -826,34 +916,65 @@ class Data: for phase in self.phases: self.devicegroups.append([phase]) self.errorinfo = {'suspend':[],'resume':[]} - def extractErrorInfo(self, dmesg): - error = '' - tm = 0.0 - for i in range(len(dmesg)): - if 'Call Trace:' in dmesg[i]: - m = re.match('[ \t]*(\[ *)(?P<ktime>[0-9\.]*)(\]) .*', dmesg[i]) - if not m: - continue - tm = float(m.group('ktime')) - if tm < self.start or tm > self.end: - continue - for j in range(i-10, i+1): - error += dmesg[j] + def extractErrorInfo(self): + lf = sysvals.openlog(sysvals.dmesgfile, 'r') + i = 0 + list = [] + # sl = start line, et = error time, el = error line + type = 'ERROR' + sl = et = el = -1 + for line in lf: + i += 1 + m = re.match('[ \t]*(\[ *)(?P<ktime>[0-9\.]*)(\]) (?P<msg>.*)', line) + if not m: continue - if error: - m = re.match('[ \t]*\[ *[0-9\.]*\] \[\<[0-9a-fA-F]*\>\] .*', dmesg[i]) - if m: - error += dmesg[i] - else: - if tm < self.tSuspended: - dir = 'suspend' - else: - dir = 'resume' - error = error.replace('<', '<').replace('>', '>') - vprint('kernel error found in %s at %f' % (dir, tm)) - self.errorinfo[dir].append((tm, error)) + t = float(m.group('ktime')) + if t < self.start or t > self.end: + continue + if t < self.tSuspended: + dir = 'suspend' + else: + dir = 'resume' + msg = m.group('msg') + if re.match('-*\[ *cut here *\]-*', msg): + type = 'WARNING' + sl = i + elif re.match('genirq: .*', msg): + type = 'IRQ' + sl = i + elif re.match('BUG: .*', msg) or re.match('kernel BUG .*', msg): + type = 'BUG' + sl = i + elif re.match('-*\[ *end trace .*\]-*', msg) or \ + re.match('R13: .*', msg): + if et >= 0 and sl >= 0: + list.append((type, dir, et, sl, i)) self.kerror = True - error = '' + sl = et = el = -1 + type = 'ERROR' + elif 'Call Trace:' in msg: + if el >= 0 and et >= 0: + list.append((type, dir, et, el, el)) + self.kerror = True + et, el = t, i + if sl < 0 or type == 'BUG': + slval = i + if sl >= 0: + slval = sl + list.append((type, dir, et, slval, i)) + self.kerror = True + sl = et = el = -1 + type = 'ERROR' + if el >= 0 and et >= 0: + list.append((type, dir, et, el, el)) + self.kerror = True + for e in list: + type, dir, t, idx1, idx2 = e + sysvals.vprint('kernel %s found in %s at %f' % (type, dir, t)) + self.errorinfo[dir].append((type, t, idx1, idx2)) + if self.kerror: + sysvals.dmesglog = True + lf.close() def setStart(self, time): self.start = time def setEnd(self, time): @@ -867,6 +988,14 @@ class Data: time < d['end']): return False return True + def phaseCollision(self, phase, isbegin, line): + key = 'end' + if isbegin: + key = 'start' + if self.dmesg[phase][key] >= 0: + sysvals.vprint('IGNORE: %s' % line.strip()) + return True + return False def sourcePhase(self, start): for phase in self.phases: pend = self.dmesg[phase]['end'] @@ -918,7 +1047,7 @@ class Data: return self.addDeviceFunctionCall(displayname, kprobename, proc, pid, start, end, cdata, rdata) # this should not happen if not tgtdev: - vprint('[%f - %f] %s-%d %s %s %s' % \ + sysvals.vprint('[%f - %f] %s-%d %s %s %s' % \ (start, end, proc, pid, kprobename, cdata, rdata)) return False # place the call data inside the src element of the tgtdev @@ -1054,6 +1183,13 @@ class Data: if('src' in d): for e in d['src']: e.time = self.trimTimeVal(e.time, t0, dT, left) + for dir in ['suspend', 'resume']: + list = [] + for e in self.errorinfo[dir]: + type, tm, idx1, idx2 = e + tm = self.trimTimeVal(tm, t0, dT, left) + list.append((type, tm, idx1, idx2)) + self.errorinfo[dir] = list def normalizeTime(self, tZero): # trim out any standby or freeze clock time if(self.tSuspended != self.tResumed): @@ -1100,7 +1236,7 @@ class Data: if self.dmesg[p]['end'] > dev['start']: dev['end'] = self.dmesg[p]['end'] break - vprint('%s (%s): callback didnt return' % (devname, phase)) + sysvals.vprint('%s (%s): callback didnt return' % (devname, phase)) def deviceFilter(self, devicefilter): for phase in self.phases: list = self.dmesg[phase]['list'] @@ -1200,15 +1336,15 @@ class Data: devlist.append(child) return devlist def printDetails(self): - vprint('Timeline Details:') - vprint(' test start: %f' % self.start) - vprint('kernel suspend start: %f' % self.tKernSus) + sysvals.vprint('Timeline Details:') + sysvals.vprint(' test start: %f' % self.start) + sysvals.vprint('kernel suspend start: %f' % self.tKernSus) for phase in self.phases: dc = len(self.dmesg[phase]['list']) - vprint(' %16s: %f - %f (%d devices)' % (phase, \ + sysvals.vprint(' %16s: %f - %f (%d devices)' % (phase, \ self.dmesg[phase]['start'], self.dmesg[phase]['end'], dc)) - vprint(' kernel resume end: %f' % self.tKernRes) - vprint(' test end: %f' % self.end) + sysvals.vprint(' kernel resume end: %f' % self.tKernRes) + sysvals.vprint(' test end: %f' % self.end) def deviceChildrenAllPhases(self, devname): devlist = [] for phase in self.phases: @@ -1358,14 +1494,21 @@ class Data: tres.append(t) # process the events for suspend and resume if len(proclist) > 0: - vprint('Process Execution:') + sysvals.vprint('Process Execution:') for ps in proclist: c = self.addProcessUsageEvent(ps, tsus) if c > 0: - vprint('%25s (sus): %d' % (ps, c)) + sysvals.vprint('%25s (sus): %d' % (ps, c)) c = self.addProcessUsageEvent(ps, tres) if c > 0: - vprint('%25s (res): %d' % (ps, c)) + sysvals.vprint('%25s (res): %d' % (ps, c)) + def debugPrint(self): + for p in self.phases: + list = self.dmesg[p]['list'] + for devname in list: + dev = list[devname] + if 'ftrace' in dev: + dev['ftrace'].debugPrint(' [%s]' % devname) # Class: DevFunction # Description: @@ -1504,18 +1647,24 @@ class FTraceLine: # something else (possibly a trace marker) else: self.name = m + def isCall(self): + return self.fcall and not self.freturn + def isReturn(self): + return self.freturn and not self.fcall + def isLeaf(self): + return self.fcall and self.freturn def getDepth(self, str): return len(str)/2 - def debugPrint(self, dev=''): - if(self.freturn and self.fcall): - print('%s -- %f (%02d): %s(); (%.3f us)' % (dev, self.time, \ - self.depth, self.name, self.length*1000000)) - elif(self.freturn): - print('%s -- %f (%02d): %s} (%.3f us)' % (dev, self.time, \ - self.depth, self.name, self.length*1000000)) + def debugPrint(self, info=''): + if self.isLeaf(): + print(' -- %12.6f (depth=%02d): %s(); (%.3f us) %s' % (self.time, \ + self.depth, self.name, self.length*1000000, info)) + elif self.freturn: + print(' -- %12.6f (depth=%02d): %s} (%.3f us) %s' % (self.time, \ + self.depth, self.name, self.length*1000000, info)) else: - print('%s -- %f (%02d): %s() { (%.3f us)' % (dev, self.time, \ - self.depth, self.name, self.length*1000000)) + print(' -- %12.6f (depth=%02d): %s() { (%.3f us) %s' % (self.time, \ + self.depth, self.name, self.length*1000000, info)) def startMarker(self): # Is this the starting line of a suspend? if not self.fevent: @@ -1558,107 +1707,160 @@ class FTraceCallGraph: depth = 0 pid = 0 name = '' - def __init__(self, pid): + partial = False + vfname = 'missing_function_name' + ignore = False + sv = 0 + def __init__(self, pid, sv): self.start = -1.0 self.end = -1.0 self.list = [] self.depth = 0 self.pid = pid - def addLine(self, line, debug=False): + self.sv = sv + def addLine(self, line): # if this is already invalid, just leave if(self.invalid): - return False - # invalidate on too much data or bad depth - if(len(self.list) >= 1000000 or self.depth < 0): + if(line.depth == 0 and line.freturn): + return 1 + return 0 + # invalidate on bad depth + if(self.depth < 0): self.invalidate(line) - return False + return 0 + # ignore data til we return to the current depth + if self.ignore: + if line.depth > self.depth: + return 0 + else: + self.list[-1].freturn = True + self.list[-1].length = line.time - self.list[-1].time + self.ignore = False + # if this is a return at self.depth, no more work is needed + if line.depth == self.depth and line.isReturn(): + if line.depth == 0: + self.end = line.time + return 1 + return 0 # compare current depth with this lines pre-call depth prelinedep = line.depth - if(line.freturn and not line.fcall): + if line.isReturn(): prelinedep += 1 last = 0 lasttime = line.time - virtualfname = 'missing_function_name' if len(self.list) > 0: last = self.list[-1] lasttime = last.time + if last.isLeaf(): + lasttime += last.length # handle low misalignments by inserting returns - if prelinedep < self.depth: - if debug and last: - print '-------- task %d --------' % self.pid - last.debugPrint() + mismatch = prelinedep - self.depth + warning = self.sv.verbose and abs(mismatch) > 1 + info = [] + if mismatch < 0: idx = 0 # add return calls to get the depth down while prelinedep < self.depth: - if debug: - print 'MISALIGN LOW (add returns): C%d - eC%d' % (self.depth, prelinedep) self.depth -= 1 - if idx == 0 and last and last.fcall and not last.freturn: + if idx == 0 and last and last.isCall(): # special case, turn last call into a leaf last.depth = self.depth last.freturn = True last.length = line.time - last.time - if debug: - last.debugPrint() + if warning: + info.append(('[make leaf]', last)) else: vline = FTraceLine(lasttime) vline.depth = self.depth - vline.name = virtualfname + vline.name = self.vfname vline.freturn = True self.list.append(vline) - if debug: - vline.debugPrint() + if warning: + if idx == 0: + info.append(('', last)) + info.append(('[add return]', vline)) idx += 1 - if debug: - line.debugPrint() - print '' + if warning: + info.append(('', line)) # handle high misalignments by inserting calls - elif prelinedep > self.depth: - if debug and last: - print '-------- task %d --------' % self.pid - last.debugPrint() + elif mismatch > 0: idx = 0 + if warning: + info.append(('', last)) # add calls to get the depth up while prelinedep > self.depth: - if debug: - print 'MISALIGN HIGH (add calls): C%d - eC%d' % (self.depth, prelinedep) - if idx == 0 and line.freturn and not line.fcall: + if idx == 0 and line.isReturn(): # special case, turn this return into a leaf line.fcall = True prelinedep -= 1 + if warning: + info.append(('[make leaf]', line)) else: vline = FTraceLine(lasttime) vline.depth = self.depth - vline.name = virtualfname + vline.name = self.vfname vline.fcall = True - if debug: - vline.debugPrint() self.list.append(vline) self.depth += 1 if not last: self.start = vline.time + if warning: + info.append(('[add call]', vline)) idx += 1 - if debug: - line.debugPrint() - print '' + if warning and ('[make leaf]', line) not in info: + info.append(('', line)) + if warning: + print 'WARNING: ftrace data missing, corrections made:' + for i in info: + t, obj = i + if obj: + obj.debugPrint(t) # process the call and set the new depth - if(line.fcall and not line.freturn): - self.depth += 1 - elif(line.freturn and not line.fcall): + skipadd = False + md = self.sv.max_graph_depth + if line.isCall(): + # ignore blacklisted/overdepth funcs + if (md and self.depth >= md - 1) or (line.name in self.sv.cgblacklist): + self.ignore = True + else: + self.depth += 1 + elif line.isReturn(): self.depth -= 1 + # remove blacklisted/overdepth/empty funcs that slipped through + if (last and last.isCall() and last.depth == line.depth) or \ + (md and last and last.depth >= md) or \ + (line.name in self.sv.cgblacklist): + while len(self.list) > 0 and self.list[-1].depth > line.depth: + self.list.pop(-1) + if len(self.list) == 0: + self.invalid = True + return 1 + self.list[-1].freturn = True + self.list[-1].length = line.time - self.list[-1].time + self.list[-1].name = line.name + skipadd = True if len(self.list) < 1: self.start = line.time - self.list.append(line) + # check for a mismatch that returned all the way to callgraph end + res = 1 + if mismatch < 0 and self.list[-1].depth == 0 and self.list[-1].freturn: + line = self.list[-1] + skipadd = True + res = -1 + if not skipadd: + self.list.append(line) if(line.depth == 0 and line.freturn): if(self.start < 0): self.start = line.time self.end = line.time if line.fcall: self.end += line.length - if self.list[0].name == virtualfname: + if self.list[0].name == self.vfname: self.invalid = True - return True - return False + if res == -1: + self.partial = True + return res + return 0 def invalidate(self, line): if(len(self.list) > 0): first = self.list[0] @@ -1668,29 +1870,30 @@ class FTraceCallGraph: id = 'task %s' % (self.pid) window = '(%f - %f)' % (self.start, line.time) if(self.depth < 0): - vprint('Too much data for '+id+\ + print('Data misalignment for '+id+\ ' (buffer overflow), ignoring this callback') else: - vprint('Too much data for '+id+\ + print('Too much data for '+id+\ ' '+window+', ignoring this callback') - def slice(self, t0, tN): - minicg = FTraceCallGraph(0) - count = -1 - firstdepth = 0 + def slice(self, dev): + minicg = FTraceCallGraph(dev['pid'], self.sv) + minicg.name = self.name + mydepth = -1 + good = False for l in self.list: - if(l.time < t0 or l.time > tN): + if(l.time < dev['start'] or l.time > dev['end']): continue - if(count < 0): - if(not l.fcall or l.name == 'dev_driver_string'): - continue - firstdepth = l.depth - count = 0 - l.depth -= firstdepth - minicg.addLine(l) - if((count == 0 and l.freturn and l.fcall) or - (count > 0 and l.depth <= 0)): + if mydepth < 0: + if l.name == 'mutex_lock' and l.freturn: + mydepth = l.depth + continue + elif l.depth == mydepth and l.name == 'mutex_unlock' and l.fcall: + good = True break - count += 1 + l.depth -= mydepth + minicg.addLine(l) + if not good or len(minicg.list) < 1: + return 0 return minicg def repair(self, enddepth): # bring the depth back to 0 with additional returns @@ -1701,11 +1904,11 @@ class FTraceCallGraph: t.depth = i t.freturn = True fixed = self.addLine(t) - if fixed: + if fixed != 0: self.end = last.time return True return False - def postProcess(self, debug=False): + def postProcess(self): if len(self.list) > 0: self.name = self.list[0].name stack = dict() @@ -1714,20 +1917,23 @@ class FTraceCallGraph: for l in self.list: # ftrace bug: reported duration is not reliable # check each leaf and clip it at max possible length - if(last and last.freturn and last.fcall): + if last and last.isLeaf(): if last.length > l.time - last.time: last.length = l.time - last.time - if(l.fcall and not l.freturn): + if l.isCall(): stack[l.depth] = l cnt += 1 - elif(l.freturn and not l.fcall): + elif l.isReturn(): if(l.depth not in stack): - if debug: + if self.sv.verbose: print 'Post Process Error: Depth missing' l.debugPrint() return False # calculate call length from call/return lines - stack[l.depth].length = l.time - stack[l.depth].time + cl = stack[l.depth] + cl.length = l.time - cl.time + if cl.name == self.vfname: + cl.name = l.name stack.pop(l.depth) l.length = 0 cnt -= 1 @@ -1736,13 +1942,13 @@ class FTraceCallGraph: # trace caught the whole call tree return True elif(cnt < 0): - if debug: + if self.sv.verbose: print 'Post Process Error: Depth is less than 0' return False # trace ended before call tree finished return self.repair(cnt) def deviceMatch(self, pid, data): - found = False + found = '' # add the callgraph data to the device hierarchy borderphase = { 'dpm_prepare': 'suspend_prepare', @@ -1756,8 +1962,10 @@ class FTraceCallGraph: if(pid == dev['pid'] and self.start <= dev['start'] and self.end >= dev['end']): - dev['ftrace'] = self.slice(dev['start'], dev['end']) - found = True + cg = self.slice(dev) + if cg: + dev['ftrace'] = cg + found = devname return found for p in data.phases: if(data.dmesg[p]['start'] <= self.start and @@ -1769,7 +1977,7 @@ class FTraceCallGraph: self.start <= dev['start'] and self.end >= dev['end']): dev['ftrace'] = self - found = True + found = devname break break return found @@ -1793,18 +2001,20 @@ class FTraceCallGraph: if out: phase, myname = out data.dmesg[phase]['list'][myname]['ftrace'] = self - def debugPrint(self): - print('[%f - %f] %s (%d)') % (self.start, self.end, self.name, self.pid) + def debugPrint(self, info=''): + print('%s pid=%d [%f - %f] %.3f us') % \ + (self.name, self.pid, self.start, self.end, + (self.end - self.start)*1000000) for l in self.list: - if(l.freturn and l.fcall): - print('%f (%02d): %s(); (%.3f us)' % (l.time, \ - l.depth, l.name, l.length*1000000)) - elif(l.freturn): - print('%f (%02d): %s} (%.3f us)' % (l.time, \ - l.depth, l.name, l.length*1000000)) + if l.isLeaf(): + print('%f (%02d): %s(); (%.3f us)%s' % (l.time, \ + l.depth, l.name, l.length*1000000, info)) + elif l.freturn: + print('%f (%02d): %s} (%.3f us)%s' % (l.time, \ + l.depth, l.name, l.length*1000000, info)) else: - print('%f (%02d): %s() { (%.3f us)' % (l.time, \ - l.depth, l.name, l.length*1000000)) + print('%f (%02d): %s() { (%.3f us)%s' % (l.time, \ + l.depth, l.name, l.length*1000000, info)) print(' ') class DevItem: @@ -1839,8 +2049,8 @@ class Timeline: self.rowH = rowheight self.scaleH = scaleheight self.html = '' - def createHeader(self, sv): - if(not sv.stamp['time']): + def createHeader(self, sv, stamp): + if(not stamp['time']): return self.html += '<div class="version"><a href="https://01.org/suspendresume">%s v%s</a></div>' \ % (sv.title, sv.version) @@ -1851,12 +2061,12 @@ class Timeline: if sv.ftracelog: self.html += '<button id="showftrace" class="logbtn btnfmt">ftrace</button>' headline_stamp = '<div class="stamp">{0} {1} {2} {3}</div>\n' - self.html += headline_stamp.format(sv.stamp['host'], sv.stamp['kernel'], - sv.stamp['mode'], sv.stamp['time']) - if 'man' in sv.stamp and 'plat' in sv.stamp and 'cpu' in sv.stamp: + self.html += headline_stamp.format(stamp['host'], stamp['kernel'], + stamp['mode'], stamp['time']) + if 'man' in stamp and 'plat' in stamp and 'cpu' in stamp and \ + stamp['man'] and stamp['plat'] and stamp['cpu']: headline_sysinfo = '<div class="stamp sysinfo">{0} {1} <i>with</i> {2}</div>\n' - self.html += headline_sysinfo.format(sv.stamp['man'], - sv.stamp['plat'], sv.stamp['cpu']) + self.html += headline_sysinfo.format(stamp['man'], stamp['plat'], stamp['cpu']) # Function: getDeviceRows # Description: @@ -2067,12 +2277,16 @@ class Timeline: class TestProps: stamp = '' sysinfo = '' + cmdline = '' + kparams = '' S0i3 = False fwdata = [] stampfmt = '# [a-z]*-(?P<m>[0-9]{2})(?P<d>[0-9]{2})(?P<y>[0-9]{2})-'+\ '(?P<H>[0-9]{2})(?P<M>[0-9]{2})(?P<S>[0-9]{2})'+\ ' (?P<host>.*) (?P<mode>.*) (?P<kernel>.*)$' sysinfofmt = '^# sysinfo .*' + cmdlinefmt = '^# command \| (?P<cmd>.*)' + kparamsfmt = '^# kparams \| (?P<kp>.*)' ftrace_line_fmt_fg = \ '^ *(?P<time>[0-9\.]*) *\| *(?P<cpu>[0-9]*)\)'+\ ' *(?P<proc>.*)-(?P<pid>[0-9]*) *\|'+\ @@ -2116,13 +2330,20 @@ class TestProps: sv.hostname = data.stamp['host'] sv.suspendmode = data.stamp['mode'] if sv.suspendmode == 'command' and sv.ftracefile != '': - modes = ['on', 'freeze', 'standby', 'mem'] - out = Popen(['grep', 'suspend_enter', sv.ftracefile], + modes = ['on', 'freeze', 'standby', 'mem', 'disk'] + out = Popen(['grep', 'machine_suspend', sv.ftracefile], stderr=PIPE, stdout=PIPE).stdout.read() - m = re.match('.* suspend_enter\[(?P<mode>.*)\]', out) - if m and m.group('mode') in ['1', '2', '3']: + m = re.match('.* machine_suspend\[(?P<mode>.*)\]', out) + if m and m.group('mode') in ['1', '2', '3', '4']: sv.suspendmode = modes[int(m.group('mode'))] data.stamp['mode'] = sv.suspendmode + m = re.match(self.cmdlinefmt, self.cmdline) + if m: + sv.cmdline = m.group('cmd') + if self.kparams: + m = re.match(self.kparamsfmt, self.kparams) + if m: + sv.kparams = m.group('kp') if not sv.stamp: sv.stamp = data.stamp @@ -2186,47 +2407,43 @@ class ProcessMonitor: # ----------------- FUNCTIONS -------------------- -# Function: vprint -# Description: -# verbose print (prints only with -verbose option) -# Arguments: -# msg: the debug/log message to print -def vprint(msg): - sysvals.logmsg += msg+'\n' - if(sysvals.verbose): - print(msg) - # Function: doesTraceLogHaveTraceEvents # Description: -# Quickly determine if the ftrace log has some or all of the trace events -# required for primary parsing. Set the usetraceevents and/or -# usetraceeventsonly flags in the global sysvals object +# Quickly determine if the ftrace log has all of the trace events, +# markers, and/or kprobes required for primary parsing. def doesTraceLogHaveTraceEvents(): - # check for kprobes + kpcheck = ['_cal: (', '_cpu_down()'] + techeck = sysvals.traceevents[:] + tmcheck = ['SUSPEND START', 'RESUME COMPLETE'] sysvals.usekprobes = False - out = call('grep -q "_cal: (" '+sysvals.ftracefile, shell=True) - if(out == 0): - sysvals.usekprobes = True - # check for callgraph data on trace event blocks - out = call('grep -q "_cpu_down()" '+sysvals.ftracefile, shell=True) - if(out == 0): - sysvals.usekprobes = True - out = Popen(['head', '-1', sysvals.ftracefile], - stderr=PIPE, stdout=PIPE).stdout.read().replace('\n', '') - # figure out what level of trace events are supported - sysvals.usetraceeventsonly = True - sysvals.usetraceevents = False - for e in sysvals.traceevents: - out = call('grep -q "'+e+': " '+sysvals.ftracefile, shell=True) - if(out != 0): - sysvals.usetraceeventsonly = False - if(e == 'suspend_resume' and out == 0): - sysvals.usetraceevents = True - # determine is this log is properly formatted - for e in ['SUSPEND START', 'RESUME COMPLETE']: - out = call('grep -q "'+e+'" '+sysvals.ftracefile, shell=True) - if(out != 0): - sysvals.usetracemarkers = False + fp = sysvals.openlog(sysvals.ftracefile, 'r') + for line in fp: + # check for kprobes + if not sysvals.usekprobes: + for i in kpcheck: + if i in line: + sysvals.usekprobes = True + # check for all necessary trace events + check = techeck[:] + for i in techeck: + if i in line: + check.remove(i) + techeck = check + # check for all necessary trace markers + check = tmcheck[:] + for i in tmcheck: + if i in line: + check.remove(i) + tmcheck = check + fp.close() + if len(techeck) == 0: + sysvals.usetraceevents = True + else: + sysvals.usetraceevents = False + if len(tmcheck) == 0: + sysvals.usetracemarkers = True + else: + sysvals.usetracemarkers = False # Function: appendIncompleteTraceLog # Description: @@ -2247,9 +2464,10 @@ def appendIncompleteTraceLog(testruns): testrun.append(TestRun(data)) # extract the callgraph and traceevent data - vprint('Analyzing the ftrace data...') + sysvals.vprint('Analyzing the ftrace data (%s)...' % \ + os.path.basename(sysvals.ftracefile)) tp = TestProps() - tf = open(sysvals.ftracefile, 'r') + tf = sysvals.openlog(sysvals.ftracefile, 'r') data = 0 for line in tf: # remove any latent carriage returns @@ -2261,6 +2479,9 @@ def appendIncompleteTraceLog(testruns): elif re.match(tp.sysinfofmt, line): tp.sysinfo = line continue + elif re.match(tp.cmdlinefmt, line): + tp.cmdline = line + continue # determine the trace data type (required for further parsing) m = re.match(sysvals.tracertypefmt, line) if(m): @@ -2393,11 +2614,14 @@ def appendIncompleteTraceLog(testruns): # create a callgraph object for the data if(pid not in testrun[testidx].ftemp): testrun[testidx].ftemp[pid] = [] - testrun[testidx].ftemp[pid].append(FTraceCallGraph(pid)) + testrun[testidx].ftemp[pid].append(FTraceCallGraph(pid, sysvals)) # when the call is finished, see which device matches it cg = testrun[testidx].ftemp[pid][-1] - if(cg.addLine(t)): - testrun[testidx].ftemp[pid].append(FTraceCallGraph(pid)) + res = cg.addLine(t) + if(res != 0): + testrun[testidx].ftemp[pid].append(FTraceCallGraph(pid, sysvals)) + if(res == -1): + testrun[testidx].ftemp[pid][-1].addLine(t) tf.close() for test in testrun: @@ -2410,11 +2634,11 @@ def appendIncompleteTraceLog(testruns): # add the callgraph data to the device hierarchy for pid in test.ftemp: for cg in test.ftemp[pid]: - if len(cg.list) < 1 or cg.invalid: + if len(cg.list) < 1 or cg.invalid or (cg.end - cg.start == 0): continue if(not cg.postProcess()): id = 'task %s cpu %s' % (pid, m.group('cpu')) - vprint('Sanity check failed for '+\ + sysvals.vprint('Sanity check failed for '+\ id+', ignoring this callback') continue callstart = cg.start @@ -2431,8 +2655,6 @@ def appendIncompleteTraceLog(testruns): dev['ftrace'] = cg break - test.data.printDetails() - # Function: parseTraceLog # Description: # Analyze an ftrace log output file generated from this app during @@ -2441,12 +2663,13 @@ def appendIncompleteTraceLog(testruns): # The ftrace filename is taken from sysvals # Output: # An array of Data objects -def parseTraceLog(): - vprint('Analyzing the ftrace data...') +def parseTraceLog(live=False): + sysvals.vprint('Analyzing the ftrace data (%s)...' % \ + os.path.basename(sysvals.ftracefile)) if(os.path.exists(sysvals.ftracefile) == False): doError('%s does not exist' % sysvals.ftracefile) - - sysvals.setupAllKprobes() + if not live: + sysvals.setupAllKprobes() tracewatch = [] if sysvals.usekprobes: tracewatch += ['sync_filesystems', 'freeze_processes', 'syscore_suspend', @@ -2458,7 +2681,7 @@ def parseTraceLog(): testdata = [] testrun = 0 data = 0 - tf = open(sysvals.ftracefile, 'r') + tf = sysvals.openlog(sysvals.ftracefile, 'r') phase = 'suspend_prepare' for line in tf: # remove any latent carriage returns @@ -2470,6 +2693,9 @@ def parseTraceLog(): elif re.match(tp.sysinfofmt, line): tp.sysinfo = line continue + elif re.match(tp.cmdlinefmt, line): + tp.cmdline = line + continue # firmware line: pull out any firmware data m = re.match(sysvals.firmwarefmt, line) if(m): @@ -2591,6 +2817,8 @@ def parseTraceLog(): phase = 'suspend_prepare' if(not isbegin): data.dmesg[phase]['end'] = t.time + if data.dmesg[phase]['start'] < 0: + data.dmesg[phase]['start'] = data.start continue # suspend start elif(re.match('dpm_suspend\[.*', t.name)): @@ -2604,6 +2832,8 @@ def parseTraceLog(): continue # suspend_noirq start elif(re.match('dpm_suspend_noirq\[.*', t.name)): + if data.phaseCollision('suspend_noirq', isbegin, line): + continue phase = 'suspend_noirq' data.setPhase(phase, t.time, isbegin) if(not isbegin): @@ -2636,6 +2866,8 @@ def parseTraceLog(): continue # resume_noirq start elif(re.match('dpm_resume_noirq\[.*', t.name)): + if data.phaseCollision('resume_noirq', isbegin, line): + continue phase = 'resume_noirq' data.setPhase(phase, t.time, isbegin) if(isbegin): @@ -2742,11 +2974,14 @@ def parseTraceLog(): key = (m_proc, pid) if(key not in testrun.ftemp): testrun.ftemp[key] = [] - testrun.ftemp[key].append(FTraceCallGraph(pid)) + testrun.ftemp[key].append(FTraceCallGraph(pid, sysvals)) # when the call is finished, see which device matches it cg = testrun.ftemp[key][-1] - if(cg.addLine(t)): - testrun.ftemp[key].append(FTraceCallGraph(pid)) + res = cg.addLine(t) + if(res != 0): + testrun.ftemp[key].append(FTraceCallGraph(pid, sysvals)) + if(res == -1): + testrun.ftemp[key][-1].addLine(t) tf.close() if sysvals.suspendmode == 'command': @@ -2812,28 +3047,31 @@ def parseTraceLog(): for key in test.ftemp: proc, pid = key for cg in test.ftemp[key]: - if len(cg.list) < 1 or cg.invalid: + if len(cg.list) < 1 or cg.invalid or (cg.end - cg.start == 0): continue if(not cg.postProcess()): id = 'task %s' % (pid) - vprint('Sanity check failed for '+\ + sysvals.vprint('Sanity check failed for '+\ id+', ignoring this callback') continue # match cg data to devices - if sysvals.suspendmode == 'command' or not cg.deviceMatch(pid, data): + devname = '' + if sysvals.suspendmode != 'command': + devname = cg.deviceMatch(pid, data) + if not devname: sortkey = '%f%f%d' % (cg.start, cg.end, pid) sortlist[sortkey] = cg + elif len(cg.list) > 1000000: + print 'WARNING: the callgraph for %s is massive (%d lines)' %\ + (devname, len(cg.list)) # create blocks for orphan cg data for sortkey in sorted(sortlist): cg = sortlist[sortkey] name = cg.name if sysvals.isCallgraphFunc(name): - vprint('Callgraph found for task %d: %.3fms, %s' % (cg.pid, (cg.end - cg.start)*1000, name)) + sysvals.vprint('Callgraph found for task %d: %.3fms, %s' % (cg.pid, (cg.end - cg.start)*1000, name)) cg.newActionFromFunction(data) - if sysvals.suspendmode == 'command': - for data in testdata: - data.printDetails() return testdata # fill in any missing phases @@ -2841,7 +3079,7 @@ def parseTraceLog(): lp = data.phases[0] for p in data.phases: if(data.dmesg[p]['start'] < 0 and data.dmesg[p]['end'] < 0): - vprint('WARNING: phase "%s" is missing!' % p) + sysvals.vprint('WARNING: phase "%s" is missing!' % p) if(data.dmesg[p]['start'] < 0): data.dmesg[p]['start'] = data.dmesg[lp]['end'] if(p == 'resume_machine'): @@ -2859,7 +3097,6 @@ def parseTraceLog(): data.fixupInitcallsThatDidntReturn() if sysvals.usedevsrc: data.optimizeDevSrc() - data.printDetails() # x2: merge any overlapping devices between test runs if sysvals.usedevsrc and len(testdata) > 1: @@ -2878,19 +3115,18 @@ def parseTraceLog(): # The dmesg filename is taken from sysvals # Output: # An array of empty Data objects with only their dmesgtext attributes set -def loadKernelLog(justtext=False): - vprint('Analyzing the dmesg data...') +def loadKernelLog(): + sysvals.vprint('Analyzing the dmesg data (%s)...' % \ + os.path.basename(sysvals.dmesgfile)) if(os.path.exists(sysvals.dmesgfile) == False): doError('%s does not exist' % sysvals.dmesgfile) - if justtext: - dmesgtext = [] # there can be multiple test runs in a single file tp = TestProps() tp.stamp = datetime.now().strftime('# suspend-%m%d%y-%H%M%S localhost mem unknown') testruns = [] data = 0 - lf = open(sysvals.dmesgfile, 'r') + lf = sysvals.openlog(sysvals.dmesgfile, 'r') for line in lf: line = line.replace('\r\n', '') idx = line.find('[') @@ -2903,6 +3139,9 @@ def loadKernelLog(justtext=False): elif re.match(tp.sysinfofmt, line): tp.sysinfo = line continue + elif re.match(tp.cmdlinefmt, line): + tp.cmdline = line + continue m = re.match(sysvals.firmwarefmt, line) if(m): tp.fwdata.append((int(m.group('s')), int(m.group('r')))) @@ -2911,9 +3150,6 @@ def loadKernelLog(justtext=False): if(not m): continue msg = m.group("msg") - if justtext: - dmesgtext.append(line) - continue if(re.match('PM: Syncing filesystems.*', msg)): if(data): testruns.append(data) @@ -2934,8 +3170,6 @@ def loadKernelLog(justtext=False): data.dmesgtext.append(line) lf.close() - if justtext: - return dmesgtext if data: testruns.append(data) if len(testruns) < 1: @@ -2975,7 +3209,7 @@ def parseKernelLog(data): phase = 'suspend_runtime' if(data.fwValid): - vprint('Firmware Suspend = %u ns, Firmware Resume = %u ns' % \ + sysvals.vprint('Firmware Suspend = %u ns, Firmware Resume = %u ns' % \ (data.fwSuspend, data.fwResume)) # dmesg phase match table @@ -3201,7 +3435,6 @@ def parseKernelLog(data): for event in actions[name]: data.newActionGlobal(name, event['begin'], event['end']) - data.printDetails() if(len(sysvals.devicefilter) > 0): data.deviceFilter(sysvals.devicefilter) data.fixupInitcallsThatDidntReturn() @@ -3230,9 +3463,9 @@ def callgraphHTML(sv, hf, num, cg, title, color, devid): else: fmt = '<n>(%.3f ms @ '+sv.timeformat+')</n>' flen = fmt % (line.length*1000, line.time) - if(line.freturn and line.fcall): + if line.isLeaf(): hf.write(html_func_leaf.format(line.name, flen)) - elif(line.freturn): + elif line.freturn: hf.write(html_func_end) else: hf.write(html_func_start.format(num, line.name, flen)) @@ -3249,7 +3482,7 @@ def addCallgraphs(sv, hf, data): continue list = data.dmesg[p]['list'] for devname in data.sortedDevices(p): - if len(sv.devicefilter) > 0 and devname not in sv.devicefilter: + if len(sv.cgfilter) > 0 and devname not in sv.cgfilter: continue dev = list[devname] color = 'white' @@ -3270,7 +3503,6 @@ def addCallgraphs(sv, hf, data): for cg in dev['ftraces']: num = callgraphHTML(sv, hf, num, cg, name+' → '+cg.name, color, dev['id']) - hf.write('\n\n </section>\n') # Function: createHTMLSummarySimple @@ -3311,7 +3543,7 @@ def createHTMLSummarySimple(testruns, htmlfile, folder): sTimeAvg = rTimeAvg = 0.0 mode = '' num = 0 - for data in sorted(testruns, key=lambda v:(v['mode'], v['host'], v['kernel'])): + for data in sorted(testruns, key=lambda v:(v['mode'], v['host'], v['kernel'], v['time'])): if mode != data['mode']: # test average line if(num > 0): @@ -3387,7 +3619,7 @@ def createHTML(testruns): data.normalizeTime(testruns[-1].tSuspended) # html function templates - html_error = '<div id="{1}" title="kernel error/warning" class="err" style="right:{0}%">ERROR→</div>\n' + html_error = '<div id="{1}" title="kernel error/warning" class="err" style="right:{0}%">{2}→</div>\n' html_traceevent = '<div title="{0}" class="traceevent{6}" style="left:{1}%;top:{2}px;height:{3}px;width:{4}%;line-height:{3}px;{7}">{5}</div>\n' html_cpuexec = '<div class="jiffie" style="left:{0}%;top:{1}px;height:{2}px;width:{3}%;background:{4};"></div>\n' html_timetotal = '<table class="time1">\n<tr>'\ @@ -3416,20 +3648,17 @@ def createHTML(testruns): scaleH = 40 # device timeline - vprint('Creating Device Timeline...') - devtl = Timeline(30, scaleH) # write the test title and general info header - devtl.createHeader(sysvals) + devtl.createHeader(sysvals, testruns[0].stamp) # Generate the header for this timeline for data in testruns: tTotal = data.end - data.start sktime, rktime = data.getTimeValues() if(tTotal == 0): - print('ERROR: No timeline data') - sys.exit() + doError('No timeline data') if(data.tLow > 0): low_time = '%.0f'%(data.tLow*1000) if sysvals.suspendmode == 'command': @@ -3567,9 +3796,10 @@ def createHTML(testruns): data.dmesg[b]['color'], '') for e in data.errorinfo[dir]: # draw red lines for any kernel errors found - t, err = e + type, t, idx1, idx2 = e + id = '%d_%d' % (idx1, idx2) right = '%f' % (((mMax-t)*100.0)/mTotal) - devtl.html += html_error.format(right, err) + devtl.html += html_error.format(right, id, type) for b in sorted(phases[dir]): # draw the devices for this phase phaselist = data.dmesg[b]['list'] @@ -3663,14 +3893,7 @@ def createHTML(testruns): devtl.html += '</div>\n' hf = open(sysvals.htmlfile, 'w') - - # no header or css if its embedded - if(sysvals.embedded): - hf.write('pass True tSus %.3f tRes %.3f tLow %.3f fwvalid %s tSus %.3f tRes %.3f\n' % - (data.tSuspended-data.start, data.end-data.tSuspended, data.tLow, data.fwValid, \ - data.fwSuspend/1000000, data.fwResume/1000000)) - else: - addCSS(hf, sysvals, len(testruns), kerror) + addCSS(hf, sysvals, len(testruns), kerror) # write the device timeline hf.write(devtl.html) @@ -3701,7 +3924,7 @@ def createHTML(testruns): data = testruns[sysvals.cgtest] else: data = testruns[-1] - if(sysvals.usecallgraph and not sysvals.embedded): + if sysvals.usecallgraph: addCallgraphs(sysvals, hf, data) # add the test log as a hidden div @@ -3710,7 +3933,7 @@ def createHTML(testruns): # add the dmesg log as a hidden div if sysvals.dmesglog and sysvals.dmesgfile: hf.write('<div id="dmesglog" style="display:none;">\n') - lf = open(sysvals.dmesgfile, 'r') + lf = sysvals.openlog(sysvals.dmesgfile, 'r') for line in lf: line = line.replace('<', '<').replace('>', '>') hf.write(line) @@ -3719,28 +3942,15 @@ def createHTML(testruns): # add the ftrace log as a hidden div if sysvals.ftracelog and sysvals.ftracefile: hf.write('<div id="ftracelog" style="display:none;">\n') - lf = open(sysvals.ftracefile, 'r') + lf = sysvals.openlog(sysvals.ftracefile, 'r') for line in lf: hf.write(line) lf.close() hf.write('</div>\n') - if(not sysvals.embedded): - # write the footer and close - addScriptCode(hf, testruns) - hf.write('</body>\n</html>\n') - else: - # embedded out will be loaded in a page, skip the js - t0 = (testruns[0].start - testruns[-1].tSuspended) * 1000 - tMax = (testruns[-1].end - testruns[-1].tSuspended) * 1000 - # add js code in a div entry for later evaluation - detail = 'var bounds = [%f,%f];\n' % (t0, tMax) - detail += 'var devtable = [\n' - for data in testruns: - topo = data.deviceTopology() - detail += '\t"%s",\n' % (topo) - detail += '];\n' - hf.write('<div id=customcode style=display:none>\n'+detail+'</div>\n') + # write the footer and close + addScriptCode(hf, testruns) + hf.write('</body>\n</html>\n') hf.close() return True @@ -4149,9 +4359,25 @@ def addScriptCode(hf, testruns): ' win.document.write(html+dt);\n'\ ' }\n'\ ' function errWindow() {\n'\ - ' var text = this.id;\n'\ + ' var range = this.id.split("_");\n'\ + ' var idx1 = parseInt(range[0]);\n'\ + ' var idx2 = parseInt(range[1]);\n'\ ' var win = window.open();\n'\ - ' win.document.write("<pre>"+text+"</pre>");\n'\ + ' var log = document.getElementById("dmesglog");\n'\ + ' var title = "<title>dmesg log</title>";\n'\ + ' var text = log.innerHTML.split("\\n");\n'\ + ' var html = "";\n'\ + ' for(var i = 0; i < text.length; i++) {\n'\ + ' if(i == idx1) {\n'\ + ' html += "<e id=target>"+text[i]+"</e>\\n";\n'\ + ' } else if(i > idx1 && i <= idx2) {\n'\ + ' html += "<e>"+text[i]+"</e>\\n";\n'\ + ' } else {\n'\ + ' html += text[i]+"\\n";\n'\ + ' }\n'\ + ' }\n'\ + ' win.document.write("<style>e{color:red}</style>"+title+"<pre>"+html+"</pre>");\n'\ + ' win.location.hash = "#target";\n'\ ' win.document.close();\n'\ ' }\n'\ ' function logWindow(e) {\n'\ @@ -4219,6 +4445,30 @@ def addScriptCode(hf, testruns): '</script>\n' hf.write(script_code); +def setRuntimeSuspend(before=True): + global sysvals + sv = sysvals + if sv.rs == 0: + return + if before: + # runtime suspend disable or enable + if sv.rs > 0: + sv.rstgt, sv.rsval, sv.rsdir = 'on', 'auto', 'enabled' + else: + sv.rstgt, sv.rsval, sv.rsdir = 'auto', 'on', 'disabled' + print('CONFIGURING RUNTIME SUSPEND...') + sv.rslist = deviceInfo(sv.rstgt) + for i in sv.rslist: + sv.setVal(sv.rsval, i) + print('runtime suspend %s on all devices (%d changed)' % (sv.rsdir, len(sv.rslist))) + print('waiting 5 seconds...') + time.sleep(5) + else: + # runtime suspend re-enable or re-disable + for i in sv.rslist: + sv.setVal(sv.rstgt, i) + print('runtime suspend settings restored on %d devices' % len(sv.rslist)) + # Function: executeSuspend # Description: # Execute system suspend through the sysfs interface, then copy the output @@ -4227,6 +4477,19 @@ def executeSuspend(): pm = ProcessMonitor() tp = sysvals.tpath fwdata = [] + # run these commands to prepare the system for suspend + if sysvals.display: + if sysvals.display > 0: + print('TURN DISPLAY ON') + call('xset -d :0.0 dpms force suspend', shell=True) + call('xset -d :0.0 dpms force on', shell=True) + else: + print('TURN DISPLAY OFF') + call('xset -d :0.0 dpms force suspend', shell=True) + time.sleep(1) + if sysvals.sync: + print('SYNCING FILESYSTEMS') + call('sync', shell=True) # mark the start point in the kernel ring buffer just as we start sysvals.initdmesg() # start ftrace @@ -4298,47 +4561,22 @@ def executeSuspend(): pm.stop() sysvals.fsetVal('0', 'tracing_on') print('CAPTURING TRACE') - sysvals.writeDatafileHeader(sysvals.ftracefile, fwdata) - call('cat '+tp+'trace >> '+sysvals.ftracefile, shell=True) + op = sysvals.writeDatafileHeader(sysvals.ftracefile, fwdata) + fp = open(tp+'trace', 'r') + for line in fp: + op.write(line) + op.close() sysvals.fsetVal('', 'trace') devProps() # grab a copy of the dmesg output print('CAPTURING DMESG') - sysvals.writeDatafileHeader(sysvals.dmesgfile, fwdata) - sysvals.getdmesg() + sysvals.getdmesg(fwdata) -# Function: setUSBDevicesAuto -# Description: -# Set the autosuspend control parameter of all USB devices to auto -# This can be dangerous, so use at your own risk, most devices are set -# to always-on since the kernel cant determine if the device can -# properly autosuspend -def setUSBDevicesAuto(): - sysvals.rootCheck(True) - for dirname, dirnames, filenames in os.walk('/sys/devices'): - if(re.match('.*/usb[0-9]*.*', dirname) and - 'idVendor' in filenames and 'idProduct' in filenames): - call('echo auto > %s/power/control' % dirname, shell=True) - name = dirname.split('/')[-1] - desc = Popen(['cat', '%s/product' % dirname], - stderr=PIPE, stdout=PIPE).stdout.read().replace('\n', '') - ctrl = Popen(['cat', '%s/power/control' % dirname], - stderr=PIPE, stdout=PIPE).stdout.read().replace('\n', '') - print('control is %s for %6s: %s' % (ctrl, name, desc)) - -# Function: yesno -# Description: -# Print out an equivalent Y or N for a set of known parameter values -# Output: -# 'Y', 'N', or ' ' if the value is unknown -def yesno(val): - yesvals = ['auto', 'enabled', 'active', '1'] - novals = ['on', 'disabled', 'suspended', 'forbidden', 'unsupported'] - if val in yesvals: - return 'Y' - elif val in novals: - return 'N' - return ' ' +def readFile(file): + if os.path.islink(file): + return os.readlink(file).split('/')[-1] + else: + return sysvals.getVal(file).strip() # Function: ms2nice # Description: @@ -4346,69 +4584,81 @@ def yesno(val): # Output: # The time string, e.g. "1901m16s" def ms2nice(val): - ms = 0 - try: - ms = int(val) - except: - return 0.0 - m = ms / 60000 - s = (ms / 1000) - (m * 60) - return '%3dm%2ds' % (m, s) + val = int(val) + h = val / 3600000 + m = (val / 60000) % 60 + s = (val / 1000) % 60 + if h > 0: + return '%d:%02d:%02d' % (h, m, s) + if m > 0: + return '%02d:%02d' % (m, s) + return '%ds' % s -# Function: detectUSB +def yesno(val): + list = {'enabled':'A', 'disabled':'S', 'auto':'E', 'on':'D', + 'active':'A', 'suspended':'S', 'suspending':'S'} + if val not in list: + return ' ' + return list[val] + +# Function: deviceInfo # Description: # Detect all the USB hosts and devices currently connected and add # a list of USB device names to sysvals for better timeline readability -def detectUSB(): - field = {'idVendor':'', 'idProduct':'', 'product':'', 'speed':''} - power = {'async':'', 'autosuspend':'', 'autosuspend_delay_ms':'', - 'control':'', 'persist':'', 'runtime_enabled':'', - 'runtime_status':'', 'runtime_usage':'', - 'runtime_active_time':'', - 'runtime_suspended_time':'', - 'active_duration':'', - 'connected_duration':''} - - print('LEGEND') - print('---------------------------------------------------------------------------------------------') - print(' A = async/sync PM queue Y/N D = autosuspend delay (seconds)') - print(' S = autosuspend Y/N rACTIVE = runtime active (min/sec)') - print(' P = persist across suspend Y/N rSUSPEN = runtime suspend (min/sec)') - print(' E = runtime suspend enabled/forbidden Y/N ACTIVE = active duration (min/sec)') - print(' R = runtime status active/suspended Y/N CONNECT = connected duration (min/sec)') - print(' U = runtime usage count') - print('---------------------------------------------------------------------------------------------') - print(' NAME ID DESCRIPTION SPEED A S P E R U D rACTIVE rSUSPEN ACTIVE CONNECT') - print('---------------------------------------------------------------------------------------------') - +def deviceInfo(output=''): + if not output: + print('LEGEND') + print('---------------------------------------------------------------------------------------------') + print(' A = async/sync PM queue (A/S) C = runtime active children') + print(' R = runtime suspend enabled/disabled (E/D) rACTIVE = runtime active (min/sec)') + print(' S = runtime status active/suspended (A/S) rSUSPEND = runtime suspend (min/sec)') + print(' U = runtime usage count') + print('---------------------------------------------------------------------------------------------') + print('DEVICE NAME A R S U C rACTIVE rSUSPEND') + print('---------------------------------------------------------------------------------------------') + + res = [] + tgtval = 'runtime_status' + lines = dict() for dirname, dirnames, filenames in os.walk('/sys/devices'): - if(re.match('.*/usb[0-9]*.*', dirname) and - 'idVendor' in filenames and 'idProduct' in filenames): - for i in field: - field[i] = Popen(['cat', '%s/%s' % (dirname, i)], - stderr=PIPE, stdout=PIPE).stdout.read().replace('\n', '') - name = dirname.split('/')[-1] - for i in power: - power[i] = Popen(['cat', '%s/power/%s' % (dirname, i)], - stderr=PIPE, stdout=PIPE).stdout.read().replace('\n', '') - if(re.match('usb[0-9]*', name)): - first = '%-8s' % name - else: - first = '%8s' % name - print('%s [%s:%s] %-20s %-4s %1s %1s %1s %1s %1s %1s %1s %s %s %s %s' % \ - (first, field['idVendor'], field['idProduct'], \ - field['product'][0:20], field['speed'], \ - yesno(power['async']), \ - yesno(power['control']), \ - yesno(power['persist']), \ - yesno(power['runtime_enabled']), \ - yesno(power['runtime_status']), \ - power['runtime_usage'], \ - power['autosuspend'], \ - ms2nice(power['runtime_active_time']), \ - ms2nice(power['runtime_suspended_time']), \ - ms2nice(power['active_duration']), \ - ms2nice(power['connected_duration']))) + if(not re.match('.*/power', dirname) or + 'control' not in filenames or + tgtval not in filenames): + continue + name = '' + dirname = dirname[:-6] + device = dirname.split('/')[-1] + power = dict() + power[tgtval] = readFile('%s/power/%s' % (dirname, tgtval)) + # only list devices which support runtime suspend + if power[tgtval] not in ['active', 'suspended', 'suspending']: + continue + for i in ['product', 'driver', 'subsystem']: + file = '%s/%s' % (dirname, i) + if os.path.exists(file): + name = readFile(file) + break + for i in ['async', 'control', 'runtime_status', 'runtime_usage', + 'runtime_active_kids', 'runtime_active_time', + 'runtime_suspended_time']: + if i in filenames: + power[i] = readFile('%s/power/%s' % (dirname, i)) + if output: + if power['control'] == output: + res.append('%s/power/control' % dirname) + continue + lines[dirname] = '%-26s %-26s %1s %1s %1s %1s %1s %10s %10s' % \ + (device[:26], name[:26], + yesno(power['async']), \ + yesno(power['control']), \ + yesno(power['runtime_status']), \ + power['runtime_usage'], \ + power['runtime_active_kids'], \ + ms2nice(power['runtime_active_time']), \ + ms2nice(power['runtime_suspended_time'])) + for i in sorted(lines): + print lines[i] + return res # Function: devProps # Description: @@ -4444,7 +4694,7 @@ def devProps(data=0): msghead = 'Additional data added by AnalyzeSuspend' alreadystamped = False tp = TestProps() - tf = open(sysvals.ftracefile, 'r') + tf = sysvals.openlog(sysvals.ftracefile, 'r') for line in tf: if msghead in line: alreadystamped = True @@ -4469,7 +4719,7 @@ def devProps(data=0): if not alreadystamped and sysvals.suspendmode == 'command': out = '#\n# '+msghead+'\n# Device Properties: ' out += 'testcommandstring,%s,0;' % (sysvals.testcommand) - with open(sysvals.ftracefile, 'a') as fp: + with sysvals.openlog(sysvals.ftracefile, 'a') as fp: fp.write(out+'\n') sysvals.devprops = props return @@ -4526,7 +4776,7 @@ def devProps(data=0): out = '#\n# '+msghead+'\n# Device Properties: ' for dev in sorted(props): out += props[dev].out(dev) - with open(sysvals.ftracefile, 'a') as fp: + with sysvals.openlog(sysvals.ftracefile, 'a') as fp: fp.write(out+'\n') sysvals.devprops = props @@ -4869,20 +5119,12 @@ def statusCheck(probecheck=False): # what data source are we using res = 'DMESG' if(ftgood): - sysvals.usetraceeventsonly = True - sysvals.usetraceevents = False + sysvals.usetraceevents = True for e in sysvals.traceevents: - check = False - if(os.path.exists(sysvals.epath+e)): - check = True - if(not check): - sysvals.usetraceeventsonly = False - if(e == 'suspend_resume' and check): - sysvals.usetraceevents = True - if(sysvals.usetraceevents and sysvals.usetraceeventsonly): + if not os.path.exists(sysvals.epath+e): + sysvals.usetraceevents = False + if(sysvals.usetraceevents): res = 'FTRACE (all trace events found)' - elif(sysvals.usetraceevents): - res = 'DMESG and FTRACE (suspend_resume trace event found)' print(' timeline data source: %s' % res) # check if rtcwake @@ -4917,6 +5159,7 @@ def doError(msg, help=False): if(help == True): printHelp() print('ERROR: %s\n') % msg + sysvals.outputResult({'error':msg}) sys.exit() # Function: getArgInt @@ -4957,22 +5200,36 @@ def getArgFloat(name, args, min, max, main=True): doError(name+': value should be between %f and %f' % (min, max), True) return val -def processData(): +def processData(live=False): print('PROCESSING DATA') - if(sysvals.usetraceeventsonly): - testruns = parseTraceLog() + if(sysvals.usetraceevents): + testruns = parseTraceLog(live) if sysvals.dmesgfile: - dmesgtext = loadKernelLog(True) for data in testruns: - data.extractErrorInfo(dmesgtext) + data.extractErrorInfo() else: testruns = loadKernelLog() for data in testruns: parseKernelLog(data) if(sysvals.ftracefile and (sysvals.usecallgraph or sysvals.usetraceevents)): appendIncompleteTraceLog(testruns) + sysvals.vprint('Command:\n %s' % sysvals.cmdline) + for data in testruns: + data.printDetails() + if sysvals.cgdump: + for data in testruns: + data.debugPrint() + sys.exit() + + sysvals.vprint('Creating the html timeline (%s)...' % sysvals.htmlfile) createHTML(testruns) - return testruns + print('DONE') + data = testruns[0] + stamp = data.stamp + stamp['suspend'], stamp['resume'] = data.getTimeValues() + if data.fwValid: + stamp['fwsuspend'], stamp['fwresume'] = data.fwSuspend, data.fwResume + return (testruns, stamp) # Function: rerunTest # Description: @@ -4980,37 +5237,36 @@ def processData(): def rerunTest(): if sysvals.ftracefile: doesTraceLogHaveTraceEvents() - if not sysvals.dmesgfile and not sysvals.usetraceeventsonly: + if not sysvals.dmesgfile and not sysvals.usetraceevents: doError('recreating this html output requires a dmesg file') sysvals.setOutputFile() - vprint('Output file: %s' % sysvals.htmlfile) if os.path.exists(sysvals.htmlfile): if not os.path.isfile(sysvals.htmlfile): doError('a directory already exists with this name: %s' % sysvals.htmlfile) elif not os.access(sysvals.htmlfile, os.W_OK): doError('missing permission to write to %s' % sysvals.htmlfile) - return processData() + testruns, stamp = processData(False) + return stamp # Function: runTest # Description: # execute a suspend/resume, gather the logs, and generate the output -def runTest(): +def runTest(n=0): # prepare for the test sysvals.initFtrace() sysvals.initTestOutput('suspend') - vprint('Output files:\n\t%s\n\t%s\n\t%s' % \ - (sysvals.dmesgfile, sysvals.ftracefile, sysvals.htmlfile)) # execute the test executeSuspend() sysvals.cleanupFtrace() - processData() - - # if running as root, change output dir owner to sudo_user - if os.path.isdir(sysvals.testdir) and os.getuid() == 0 and \ - 'SUDO_USER' in os.environ: - cmd = 'chown -R {0}:{0} {1} > /dev/null 2>&1' - call(cmd.format(os.environ['SUDO_USER'], sysvals.testdir), shell=True) + if sysvals.skiphtml: + sysvals.sudouser(sysvals.testdir) + return + testruns, stamp = processData(True) + for data in testruns: + del data + sysvals.sudouser(sysvals.testdir) + sysvals.outputResult(stamp, n) def find_in_html(html, strs, div=False): for str in strs: @@ -5072,10 +5328,12 @@ def runSummary(subdir, local=True): # Function: checkArgBool # Description: # check if a boolean string value is true or false -def checkArgBool(value): - yes = ['1', 'true', 'yes', 'on'] - if value.lower() in yes: +def checkArgBool(name, value): + if value in switchvalues: + if value in switchoff: + return False return True + doError('invalid boolean --> (%s: %s), use "true/false" or "1/0"' % (name, value), True) return False # Function: configFromFile @@ -5091,60 +5349,116 @@ def configFromFile(file): if 'Settings' in sections: for opt in Config.options('Settings'): value = Config.get('Settings', opt).lower() - if(opt.lower() == 'verbose'): - sysvals.verbose = checkArgBool(value) - elif(opt.lower() == 'addlogs'): - sysvals.dmesglog = sysvals.ftracelog = checkArgBool(value) - elif(opt.lower() == 'dev'): - sysvals.usedevsrc = checkArgBool(value) - elif(opt.lower() == 'proc'): - sysvals.useprocmon = checkArgBool(value) - elif(opt.lower() == 'x2'): - if checkArgBool(value): + option = opt.lower() + if(option == 'verbose'): + sysvals.verbose = checkArgBool(option, value) + elif(option == 'addlogs'): + sysvals.dmesglog = sysvals.ftracelog = checkArgBool(option, value) + elif(option == 'dev'): + sysvals.usedevsrc = checkArgBool(option, value) + elif(option == 'proc'): + sysvals.useprocmon = checkArgBool(option, value) + elif(option == 'x2'): + if checkArgBool(option, value): sysvals.execcount = 2 - elif(opt.lower() == 'callgraph'): - sysvals.usecallgraph = checkArgBool(value) - elif(opt.lower() == 'override-timeline-functions'): - overridekprobes = checkArgBool(value) - elif(opt.lower() == 'override-dev-timeline-functions'): - overridedevkprobes = checkArgBool(value) - elif(opt.lower() == 'devicefilter'): + elif(option == 'callgraph'): + sysvals.usecallgraph = checkArgBool(option, value) + elif(option == 'override-timeline-functions'): + overridekprobes = checkArgBool(option, value) + elif(option == 'override-dev-timeline-functions'): + overridedevkprobes = checkArgBool(option, value) + elif(option == 'skiphtml'): + sysvals.skiphtml = checkArgBool(option, value) + elif(option == 'sync'): + sysvals.sync = checkArgBool(option, value) + elif(option == 'rs' or option == 'runtimesuspend'): + if value in switchvalues: + if value in switchoff: + sysvals.rs = -1 + else: + sysvals.rs = 1 + else: + doError('invalid value --> (%s: %s), use "enable/disable"' % (option, value), True) + elif(option == 'display'): + if value in switchvalues: + if value in switchoff: + sysvals.display = -1 + else: + sysvals.display = 1 + else: + doError('invalid value --> (%s: %s), use "on/off"' % (option, value), True) + elif(option == 'gzip'): + sysvals.gzip = checkArgBool(option, value) + elif(option == 'cgfilter'): + sysvals.setCallgraphFilter(value) + elif(option == 'cgskip'): + if value in switchoff: + sysvals.cgskip = '' + else: + sysvals.cgskip = sysvals.configFile(val) + if(not sysvals.cgskip): + doError('%s does not exist' % sysvals.cgskip) + elif(option == 'cgtest'): + sysvals.cgtest = getArgInt('cgtest', value, 0, 1, False) + elif(option == 'cgphase'): + d = Data(0) + if value not in d.phases: + doError('invalid phase --> (%s: %s), valid phases are %s'\ + % (option, value, d.phases), True) + sysvals.cgphase = value + elif(option == 'fadd'): + file = sysvals.configFile(value) + if(not file): + doError('%s does not exist' % value) + sysvals.addFtraceFilterFunctions(file) + elif(option == 'result'): + sysvals.result = value + elif(option == 'multi'): + nums = value.split() + if len(nums) != 2: + doError('multi requires 2 integers (exec_count and delay)', True) + sysvals.multitest['run'] = True + sysvals.multitest['count'] = getArgInt('multi: n d (exec count)', nums[0], 2, 1000000, False) + sysvals.multitest['delay'] = getArgInt('multi: n d (delay between tests)', nums[1], 0, 3600, False) + elif(option == 'devicefilter'): sysvals.setDeviceFilter(value) - elif(opt.lower() == 'expandcg'): - sysvals.cgexp = checkArgBool(value) - elif(opt.lower() == 'srgap'): - if checkArgBool(value): + elif(option == 'expandcg'): + sysvals.cgexp = checkArgBool(option, value) + elif(option == 'srgap'): + if checkArgBool(option, value): sysvals.srgap = 5 - elif(opt.lower() == 'mode'): + elif(option == 'mode'): sysvals.suspendmode = value - elif(opt.lower() == 'command'): + elif(option == 'command' or option == 'cmd'): sysvals.testcommand = value - elif(opt.lower() == 'x2delay'): - sysvals.x2delay = getArgInt('-x2delay', value, 0, 60000, False) - elif(opt.lower() == 'predelay'): - sysvals.predelay = getArgInt('-predelay', value, 0, 60000, False) - elif(opt.lower() == 'postdelay'): - sysvals.postdelay = getArgInt('-postdelay', value, 0, 60000, False) - elif(opt.lower() == 'maxdepth'): - sysvals.max_graph_depth = getArgInt('-maxdepth', value, 0, 1000, False) - elif(opt.lower() == 'rtcwake'): - if value.lower() == 'off': + elif(option == 'x2delay'): + sysvals.x2delay = getArgInt('x2delay', value, 0, 60000, False) + elif(option == 'predelay'): + sysvals.predelay = getArgInt('predelay', value, 0, 60000, False) + elif(option == 'postdelay'): + sysvals.postdelay = getArgInt('postdelay', value, 0, 60000, False) + elif(option == 'maxdepth'): + sysvals.max_graph_depth = getArgInt('maxdepth', value, 0, 1000, False) + elif(option == 'rtcwake'): + if value in switchoff: sysvals.rtcwake = False else: sysvals.rtcwake = True - sysvals.rtcwaketime = getArgInt('-rtcwake', value, 0, 3600, False) - elif(opt.lower() == 'timeprec'): - sysvals.setPrecision(getArgInt('-timeprec', value, 0, 6, False)) - elif(opt.lower() == 'mindev'): - sysvals.mindevlen = getArgFloat('-mindev', value, 0.0, 10000.0, False) - elif(opt.lower() == 'callloop-maxgap'): - sysvals.callloopmaxgap = getArgFloat('-callloop-maxgap', value, 0.0, 1.0, False) - elif(opt.lower() == 'callloop-maxlen'): - sysvals.callloopmaxgap = getArgFloat('-callloop-maxlen', value, 0.0, 1.0, False) - elif(opt.lower() == 'mincg'): - sysvals.mincglen = getArgFloat('-mincg', value, 0.0, 10000.0, False) - elif(opt.lower() == 'output-dir'): - sysvals.testdir = sysvals.setOutputFolder(value) + sysvals.rtcwaketime = getArgInt('rtcwake', value, 0, 3600, False) + elif(option == 'timeprec'): + sysvals.setPrecision(getArgInt('timeprec', value, 0, 6, False)) + elif(option == 'mindev'): + sysvals.mindevlen = getArgFloat('mindev', value, 0.0, 10000.0, False) + elif(option == 'callloop-maxgap'): + sysvals.callloopmaxgap = getArgFloat('callloop-maxgap', value, 0.0, 1.0, False) + elif(option == 'callloop-maxlen'): + sysvals.callloopmaxgap = getArgFloat('callloop-maxlen', value, 0.0, 1.0, False) + elif(option == 'mincg'): + sysvals.mincglen = getArgFloat('mincg', value, 0.0, 10000.0, False) + elif(option == 'bufsize'): + sysvals.bufsize = getArgInt('bufsize', value, 1, 1024*1024*8, False) + elif(option == 'output-dir'): + sysvals.outdir = sysvals.setOutputFolder(value) if sysvals.suspendmode == 'command' and not sysvals.testcommand: doError('No command supplied for mode "command"') @@ -5259,7 +5573,14 @@ def printHelp(): print(' -rtcwake t Wakeup t seconds after suspend, set t to "off" to disable (default: 15)') print(' -addlogs Add the dmesg and ftrace logs to the html output') print(' -srgap Add a visible gap in the timeline between sus/res (default: disabled)') + print(' -skiphtml Run the test and capture the trace logs, but skip the timeline (default: disabled)') + print(' -result fn Export a results table to a text file for parsing.') + print(' [testprep]') + print(' -sync Sync the filesystems before starting the test') + print(' -rs on/off Enable/disable runtime suspend for all devices, restore all after test') + print(' -display on/off Turn the display on or off for the test') print(' [advanced]') + print(' -gzip Gzip the trace and dmesg logs to save space') print(' -cmd {s} Run the timeline over a custom command, e.g. "sync -d"') print(' -proc Add usermode process info into the timeline (default: disabled)') print(' -dev Add kernel function calls and threads to the timeline (default: disabled)') @@ -5280,14 +5601,16 @@ def printHelp(): print(' -cgphase P Only show callgraph data for phase P (e.g. suspend_late)') print(' -cgtest N Only show callgraph data for test N (e.g. 0 or 1 in an x2 run)') print(' -timeprec N Number of significant digits in timestamps (0:S, [3:ms], 6:us)') + print(' -cgfilter S Filter the callgraph output in the timeline') + print(' -cgskip file Callgraph functions to skip, off to disable (default: cgskip.txt)') + print(' -bufsize N Set trace buffer size to N kilo-bytes (default: all of free memory)') print('') print('Other commands:') print(' -modes List available suspend modes') print(' -status Test to see if the system is enabled to run this tool') print(' -fpdt Print out the contents of the ACPI Firmware Performance Data Table') print(' -sysinfo Print out system info extracted from BIOS') - print(' -usbtopo Print out the current USB topology with power info') - print(' -usbauto Enable autosuspend for all connected USB devices') + print(' -devinfo Print out the pm settings of all devices which support runtime suspend') print(' -flist Print the list of functions currently being captured in ftrace') print(' -flistall Print all functions capable of being captured in ftrace') print(' -summary directory Create a summary of all test in this dir') @@ -5301,9 +5624,9 @@ def printHelp(): # exec start (skipped if script is loaded as library) if __name__ == '__main__': cmd = '' - outdir = '' - multitest = {'run': False, 'count': 0, 'delay': 0} - simplecmds = ['-sysinfo', '-modes', '-fpdt', '-flist', '-flistall', '-usbtopo', '-usbauto', '-status'] + simplecmds = ['-sysinfo', '-modes', '-fpdt', '-flist', '-flistall', '-devinfo', '-status'] + if '-f' in sys.argv: + sysvals.cgskip = sysvals.configFile('cgskip.txt') # loop through the command line arguments args = iter(sys.argv[1:]) for arg in args: @@ -5333,6 +5656,10 @@ if __name__ == '__main__': sysvals.postdelay = getArgInt('-postdelay', args, 0, 60000) elif(arg == '-f'): sysvals.usecallgraph = True + elif(arg == '-skiphtml'): + sysvals.skiphtml = True + elif(arg == '-cgdump'): + sysvals.cgdump = True elif(arg == '-addlogs'): sysvals.dmesglog = sysvals.ftracelog = True elif(arg == '-verbose'): @@ -5341,6 +5668,34 @@ if __name__ == '__main__': sysvals.useprocmon = True elif(arg == '-dev'): sysvals.usedevsrc = True + elif(arg == '-sync'): + sysvals.sync = True + elif(arg == '-gzip'): + sysvals.gzip = True + elif(arg == '-rs'): + try: + val = args.next() + except: + doError('-rs requires "enable" or "disable"', True) + if val.lower() in switchvalues: + if val.lower() in switchoff: + sysvals.rs = -1 + else: + sysvals.rs = 1 + else: + doError('invalid option: %s, use "enable/disable" or "on/off"' % val, True) + elif(arg == '-display'): + try: + val = args.next() + except: + doError('-display requires "on" or "off"', True) + if val.lower() in switchvalues: + if val.lower() in switchoff: + sysvals.display = -1 + else: + sysvals.display = 1 + else: + doError('invalid option: %s, use "on/off"' % val, True) elif(arg == '-maxdepth'): sysvals.max_graph_depth = getArgInt('-maxdepth', args, 0, 1000) elif(arg == '-rtcwake'): @@ -5348,7 +5703,7 @@ if __name__ == '__main__': val = args.next() except: doError('No rtcwake time supplied', True) - if val.lower() == 'off': + if val.lower() in switchoff: sysvals.rtcwake = False else: sysvals.rtcwake = True @@ -5359,6 +5714,8 @@ if __name__ == '__main__': sysvals.mindevlen = getArgFloat('-mindev', args, 0.0, 10000.0) elif(arg == '-mincg'): sysvals.mincglen = getArgFloat('-mincg', args, 0.0, 10000.0) + elif(arg == '-bufsize'): + sysvals.bufsize = getArgInt('-bufsize', args, 1, 1024*1024*8) elif(arg == '-cgtest'): sysvals.cgtest = getArgInt('-cgtest', args, 0, 1) elif(arg == '-cgphase'): @@ -5368,8 +5725,26 @@ if __name__ == '__main__': doError('No phase name supplied', True) d = Data(0) if val not in d.phases: - doError('Invalid phase, valid phaess are %s' % d.phases, True) + doError('invalid phase --> (%s: %s), valid phases are %s'\ + % (arg, val, d.phases), True) sysvals.cgphase = val + elif(arg == '-cgfilter'): + try: + val = args.next() + except: + doError('No callgraph functions supplied', True) + sysvals.setCallgraphFilter(val) + elif(arg == '-cgskip'): + try: + val = args.next() + except: + doError('No file supplied', True) + if val.lower() in switchoff: + sysvals.cgskip = '' + else: + sysvals.cgskip = sysvals.configFile(val) + if(not sysvals.cgskip): + doError('%s does not exist' % sysvals.cgskip) elif(arg == '-callloop-maxgap'): sysvals.callloopmaxgap = getArgFloat('-callloop-maxgap', args, 0.0, 1.0) elif(arg == '-callloop-maxlen'): @@ -5386,31 +5761,33 @@ if __name__ == '__main__': elif(arg == '-srgap'): sysvals.srgap = 5 elif(arg == '-multi'): - multitest['run'] = True - multitest['count'] = getArgInt('-multi n (exec count)', args, 2, 1000000) - multitest['delay'] = getArgInt('-multi d (delay between tests)', args, 0, 3600) + sysvals.multitest['run'] = True + sysvals.multitest['count'] = getArgInt('-multi n d (exec count)', args, 2, 1000000) + sysvals.multitest['delay'] = getArgInt('-multi n d (delay between tests)', args, 0, 3600) elif(arg == '-o'): try: val = args.next() except: doError('No subdirectory name supplied', True) - outdir = sysvals.setOutputFolder(val) + sysvals.outdir = sysvals.setOutputFolder(val) elif(arg == '-config'): try: val = args.next() except: doError('No text file supplied', True) - if(os.path.exists(val) == False): + file = sysvals.configFile(val) + if(not file): doError('%s does not exist' % val) - configFromFile(val) + configFromFile(file) elif(arg == '-fadd'): try: val = args.next() except: doError('No text file supplied', True) - if(os.path.exists(val) == False): + file = sysvals.configFile(val) + if(not file): doError('%s does not exist' % val) - sysvals.addFtraceFilterFunctions(val) + sysvals.addFtraceFilterFunctions(file) elif(arg == '-dmesg'): try: val = args.next() @@ -5435,7 +5812,7 @@ if __name__ == '__main__': except: doError('No directory supplied', True) cmd = 'summary' - outdir = val + sysvals.outdir = val sysvals.notestrun = True if(os.path.isdir(val) == False): doError('%s is not accesible' % val) @@ -5445,6 +5822,12 @@ if __name__ == '__main__': except: doError('No devnames supplied', True) sysvals.setDeviceFilter(val) + elif(arg == '-result'): + try: + val = args.next() + except: + doError('No result file supplied', True) + sysvals.result = val else: doError('Invalid argument: '+arg, True) @@ -5454,42 +5837,48 @@ if __name__ == '__main__': if(sysvals.usecallgraph and sysvals.useprocmon): doError('-proc is not compatible with -f') + if sysvals.usecallgraph and sysvals.cgskip: + sysvals.vprint('Using cgskip file: %s' % sysvals.cgskip) + sysvals.setCallgraphBlacklist(sysvals.cgskip) + # callgraph size cannot exceed device size if sysvals.mincglen < sysvals.mindevlen: sysvals.mincglen = sysvals.mindevlen - # just run a utility command and exit + # remove existing buffers before calculating memory + if(sysvals.usecallgraph or sysvals.usedevsrc): + sysvals.fsetVal('16', 'buffer_size_kb') sysvals.cpuInfo() + + # just run a utility command and exit if(cmd != ''): if(cmd == 'status'): statusCheck(True) elif(cmd == 'fpdt'): getFPDT(True) elif(cmd == 'sysinfo'): - sysvals.printSystemInfo() - elif(cmd == 'usbtopo'): - detectUSB() + sysvals.printSystemInfo(True) + elif(cmd == 'devinfo'): + deviceInfo() elif(cmd == 'modes'): print getModes() elif(cmd == 'flist'): sysvals.getFtraceFilterFunctions(True) elif(cmd == 'flistall'): sysvals.getFtraceFilterFunctions(False) - elif(cmd == 'usbauto'): - setUSBDevicesAuto() elif(cmd == 'summary'): - runSummary(outdir, True) + runSummary(sysvals.outdir, True) sys.exit() # if instructed, re-analyze existing data files if(sysvals.notestrun): - rerunTest() + stamp = rerunTest() + sysvals.outputResult(stamp) sys.exit() # verify that we can run a test if(not statusCheck()): - print('Check FAILED, aborting the test run!') - sys.exit() + doError('Check FAILED, aborting the test run!') # extract mem modes and convert mode = sysvals.suspendmode @@ -5509,25 +5898,35 @@ if __name__ == '__main__': sysvals.systemInfo(dmidecode(sysvals.mempath)) - if multitest['run']: + setRuntimeSuspend(True) + if sysvals.display: + call('xset -d :0.0 dpms 0 0 0', shell=True) + call('xset -d :0.0 s off', shell=True) + if sysvals.multitest['run']: # run multiple tests in a separate subdirectory - if not outdir: - s = 'suspend-x%d' % multitest['count'] - outdir = datetime.now().strftime(s+'-%y%m%d-%H%M%S') - if not os.path.isdir(outdir): - os.mkdir(outdir) - for i in range(multitest['count']): + if not sysvals.outdir: + s = 'suspend-x%d' % sysvals.multitest['count'] + sysvals.outdir = datetime.now().strftime(s+'-%y%m%d-%H%M%S') + if not os.path.isdir(sysvals.outdir): + os.mkdir(sysvals.outdir) + for i in range(sysvals.multitest['count']): if(i != 0): - print('Waiting %d seconds...' % (multitest['delay'])) - time.sleep(multitest['delay']) - print('TEST (%d/%d) START' % (i+1, multitest['count'])) + print('Waiting %d seconds...' % (sysvals.multitest['delay'])) + time.sleep(sysvals.multitest['delay']) + print('TEST (%d/%d) START' % (i+1, sysvals.multitest['count'])) fmt = 'suspend-%y%m%d-%H%M%S' - sysvals.testdir = os.path.join(outdir, datetime.now().strftime(fmt)) - runTest() - print('TEST (%d/%d) COMPLETE' % (i+1, multitest['count'])) - runSummary(outdir, False) + sysvals.testdir = os.path.join(sysvals.outdir, datetime.now().strftime(fmt)) + runTest(i+1) + print('TEST (%d/%d) COMPLETE' % (i+1, sysvals.multitest['count'])) + sysvals.logmsg = '' + if not sysvals.skiphtml: + runSummary(sysvals.outdir, False) + sysvals.sudouser(sysvals.outdir) else: - if outdir: - sysvals.testdir = outdir + if sysvals.outdir: + sysvals.testdir = sysvals.outdir # run the test in the current directory runTest() + if sysvals.display: + call('xset -d :0.0 s reset', shell=True) + setRuntimeSuspend(False) diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index c73592fa3d41..437c0b1c9d21 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -11163,6 +11163,64 @@ static struct bpf_test tests[] = { .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, + { + "xadd/w check unaligned stack", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + BPF_STX_XADD(BPF_W, BPF_REG_10, BPF_REG_0, -7), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "misaligned stack access off", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "xadd/w check unaligned map", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_1, 1), + BPF_STX_XADD(BPF_W, BPF_REG_0, BPF_REG_1, 3), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 3), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .result = REJECT, + .errstr = "misaligned value access off", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "xadd/w check unaligned pkt", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 2), + BPF_MOV64_IMM(BPF_REG_0, 99), + BPF_JMP_IMM(BPF_JA, 0, 0, 6), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0), + BPF_ST_MEM(BPF_W, BPF_REG_2, 3, 0), + BPF_STX_XADD(BPF_W, BPF_REG_2, BPF_REG_0, 1), + BPF_STX_XADD(BPF_W, BPF_REG_2, BPF_REG_0, 2), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 1), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "BPF_XADD stores into R2 packet", + .prog_type = BPF_PROG_TYPE_XDP, + }, }; static int probe_filter_length(const struct bpf_insn *fp) diff --git a/tools/testing/selftests/memory-hotplug/Makefile b/tools/testing/selftests/memory-hotplug/Makefile index 183b46883875..686da510f989 100644 --- a/tools/testing/selftests/memory-hotplug/Makefile +++ b/tools/testing/selftests/memory-hotplug/Makefile @@ -5,7 +5,8 @@ include ../lib.mk TEST_PROGS := mem-on-off-test.sh override RUN_TESTS := @./mem-on-off-test.sh -r 2 && echo "selftests: memory-hotplug [PASS]" || echo "selftests: memory-hotplug [FAIL]" -override EMIT_TESTS := echo "$(RUN_TESTS)" + +override EMIT_TESTS := echo "$(subst @,,$(RUN_TESTS))" run_full_test: @/bin/bash ./mem-on-off-test.sh && echo "memory-hotplug selftests: [PASS]" || echo "memory-hotplug selftests: [FAIL]" diff --git a/tools/testing/selftests/powerpc/mm/subpage_prot.c b/tools/testing/selftests/powerpc/mm/subpage_prot.c index 35ade7406dcd..3ae77ba93208 100644 --- a/tools/testing/selftests/powerpc/mm/subpage_prot.c +++ b/tools/testing/selftests/powerpc/mm/subpage_prot.c @@ -135,6 +135,16 @@ static int run_test(void *addr, unsigned long size) return 0; } +static int syscall_available(void) +{ + int rc; + + errno = 0; + rc = syscall(__NR_subpage_prot, 0, 0, 0); + + return rc == 0 || (errno != ENOENT && errno != ENOSYS); +} + int test_anon(void) { unsigned long align; @@ -145,6 +155,8 @@ int test_anon(void) void *mallocblock; unsigned long mallocsize; + SKIP_IF(!syscall_available()); + if (getpagesize() != 0x10000) { fprintf(stderr, "Kernel page size must be 64K!\n"); return 1; @@ -180,6 +192,8 @@ int test_file(void) off_t filesize; int fd; + SKIP_IF(!syscall_available()); + fd = open(file_name, O_RDWR); if (fd == -1) { perror("failed to open file"); diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile index a23453943ad2..5c72ff978f27 100644 --- a/tools/testing/selftests/powerpc/tm/Makefile +++ b/tools/testing/selftests/powerpc/tm/Makefile @@ -16,7 +16,7 @@ $(OUTPUT)/tm-syscall: tm-syscall-asm.S $(OUTPUT)/tm-syscall: CFLAGS += -I../../../../../usr/include $(OUTPUT)/tm-tmspr: CFLAGS += -pthread $(OUTPUT)/tm-vmx-unavail: CFLAGS += -pthread -m64 -$(OUTPUT)/tm-resched-dscr: ../pmu/lib.o +$(OUTPUT)/tm-resched-dscr: ../pmu/lib.c $(OUTPUT)/tm-unavailable: CFLAGS += -O0 -pthread -m64 -Wno-error=uninitialized -mvsx $(OUTPUT)/tm-trap: CFLAGS += -O0 -pthread -m64 diff --git a/tools/testing/selftests/powerpc/tm/tm-trap.c b/tools/testing/selftests/powerpc/tm/tm-trap.c index 5d92c23ee6cb..179d592f0073 100644 --- a/tools/testing/selftests/powerpc/tm/tm-trap.c +++ b/tools/testing/selftests/powerpc/tm/tm-trap.c @@ -255,6 +255,8 @@ int tm_trap_test(void) struct sigaction trap_sa; + SKIP_IF(!have_htm()); + trap_sa.sa_flags = SA_SIGINFO; trap_sa.sa_sigaction = trap_signal_handler; sigaction(SIGTRAP, &trap_sa, NULL); diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json index e34075059c26..90bba48c3f07 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json @@ -315,7 +315,7 @@ "cmdUnderTest": "$TC actions ls action skbmod", "expExitCode": "0", "verifyCmd": "$TC actions get action skbmod index 4", - "matchPattern": "action order [0-9]*: skbmod pipe set etype 0x0031", + "matchPattern": "action order [0-9]*: skbmod pipe set etype 0x31", "matchCount": "1", "teardown": [ "$TC actions flush action skbmod" diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests index d2561895a021..22d564673830 100755 --- a/tools/testing/selftests/vm/run_vmtests +++ b/tools/testing/selftests/vm/run_vmtests @@ -2,25 +2,33 @@ # SPDX-License-Identifier: GPL-2.0 #please run as root -#we need 256M, below is the size in kB -needmem=262144 mnt=./huge exitcode=0 -#get pagesize and freepages from /proc/meminfo +#get huge pagesize and freepages from /proc/meminfo while read name size unit; do if [ "$name" = "HugePages_Free:" ]; then freepgs=$size fi if [ "$name" = "Hugepagesize:" ]; then - pgsize=$size + hpgsize_KB=$size fi done < /proc/meminfo +# Simple hugetlbfs tests have a hardcoded minimum requirement of +# huge pages totaling 256MB (262144KB) in size. The userfaultfd +# hugetlb test requires a minimum of 2 * nr_cpus huge pages. Take +# both of these requirements into account and attempt to increase +# number of huge pages available. +nr_cpus=$(nproc) +hpgsize_MB=$((hpgsize_KB / 1024)) +half_ufd_size_MB=$((((nr_cpus * hpgsize_MB + 127) / 128) * 128)) +needmem_KB=$((half_ufd_size_MB * 2 * 1024)) + #set proper nr_hugepages -if [ -n "$freepgs" ] && [ -n "$pgsize" ]; then +if [ -n "$freepgs" ] && [ -n "$hpgsize_KB" ]; then nr_hugepgs=`cat /proc/sys/vm/nr_hugepages` - needpgs=`expr $needmem / $pgsize` + needpgs=$((needmem_KB / hpgsize_KB)) tries=2 while [ $tries -gt 0 ] && [ $freepgs -lt $needpgs ]; do lackpgs=$(( $needpgs - $freepgs )) @@ -107,8 +115,9 @@ fi echo "---------------------------" echo "running userfaultfd_hugetlb" echo "---------------------------" -# 256MB total huge pages == 128MB src and 128MB dst -./userfaultfd hugetlb 128 32 $mnt/ufd_test_file +# Test requires source and destination huge pages. Size of source +# (half_ufd_size_MB) is passed as argument to test. +./userfaultfd hugetlb $half_ufd_size_MB 32 $mnt/ufd_test_file if [ $? -ne 0 ]; then echo "[FAIL]" exitcode=1 diff --git a/tools/testing/selftests/x86/test_vsyscall.c b/tools/testing/selftests/x86/test_vsyscall.c index be81621446f0..0b4f1cc2291c 100644 --- a/tools/testing/selftests/x86/test_vsyscall.c +++ b/tools/testing/selftests/x86/test_vsyscall.c @@ -450,7 +450,7 @@ static void sigtrap(int sig, siginfo_t *info, void *ctx_void) num_vsyscall_traps++; } -static int test_native_vsyscall(void) +static int test_emulation(void) { time_t tmp; bool is_native; @@ -458,7 +458,7 @@ static int test_native_vsyscall(void) if (!vtime) return 0; - printf("[RUN]\tchecking for native vsyscall\n"); + printf("[RUN]\tchecking that vsyscalls are emulated\n"); sethandler(SIGTRAP, sigtrap, 0); set_eflags(get_eflags() | X86_EFLAGS_TF); vtime(&tmp); @@ -474,11 +474,12 @@ static int test_native_vsyscall(void) */ is_native = (num_vsyscall_traps > 1); - printf("\tvsyscalls are %s (%d instructions in vsyscall page)\n", + printf("[%s]\tvsyscalls are %s (%d instructions in vsyscall page)\n", + (is_native ? "FAIL" : "OK"), (is_native ? "native" : "emulated"), (int)num_vsyscall_traps); - return 0; + return is_native; } #endif @@ -498,7 +499,7 @@ int main(int argc, char **argv) nerrs += test_vsys_r(); #ifdef __x86_64__ - nerrs += test_native_vsyscall(); + nerrs += test_emulation(); #endif return nerrs ? 1 : 0; |