diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2011-08-03 21:53:27 -1000 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2011-08-03 21:53:27 -1000 |
commit | c0c770e610cc4cdcd66c7e939bdf89cc3e72f79d (patch) | |
tree | 7cf6807258fef2a85a2ff212f4f4eb6d9dc336c6 /mm | |
parent | a9e4e6e14c322e08d1c615afc8f504fb415f9613 (diff) | |
parent | d0e323b47057f4492b8fa22345f38d80a469bf8d (diff) | |
download | linux-c0c770e610cc4cdcd66c7e939bdf89cc3e72f79d.tar.bz2 |
Merge branch 'apei-release' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux-acpi-2.6
* 'apei-release' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux-acpi-2.6:
ACPI, APEI, EINJ Param support is disabled by default
APEI GHES: 32-bit buildfix
ACPI: APEI build fix
ACPI, APEI, GHES: Add hardware memory error recovery support
HWPoison: add memory_failure_queue()
ACPI, APEI, GHES, Error records content based throttle
ACPI, APEI, GHES, printk support for recoverable error via NMI
lib, Make gen_pool memory allocator lockless
lib, Add lock-less NULL terminated single list
Add Kconfig option ARCH_HAVE_NMI_SAFE_CMPXCHG
ACPI, APEI, Add WHEA _OSC support
ACPI, APEI, Add APEI bit support in generic _OSC call
ACPI, APEI, GHES, Support disable GHES at boot time
ACPI, APEI, GHES, Prevent GHES to be built as module
ACPI, APEI, Use apei_exec_run_optional in APEI EINJ and ERST
ACPI, APEI, Add apei_exec_run_optional
ACPI, APEI, GHES, Do not ratelimit fatal error printk before panic
ACPI, APEI, ERST, Fix erst-dbg long record reading issue
ACPI, APEI, ERST, Prevent erst_dbg from loading if ERST is disabled
Diffstat (limited to 'mm')
-rw-r--r-- | mm/memory-failure.c | 92 |
1 files changed, 92 insertions, 0 deletions
diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 740c4f52059c..2b43ba051ac9 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -53,6 +53,7 @@ #include <linux/hugetlb.h> #include <linux/memory_hotplug.h> #include <linux/mm_inline.h> +#include <linux/kfifo.h> #include "internal.h" int sysctl_memory_failure_early_kill __read_mostly = 0; @@ -1178,6 +1179,97 @@ void memory_failure(unsigned long pfn, int trapno) __memory_failure(pfn, trapno, 0); } +#define MEMORY_FAILURE_FIFO_ORDER 4 +#define MEMORY_FAILURE_FIFO_SIZE (1 << MEMORY_FAILURE_FIFO_ORDER) + +struct memory_failure_entry { + unsigned long pfn; + int trapno; + int flags; +}; + +struct memory_failure_cpu { + DECLARE_KFIFO(fifo, struct memory_failure_entry, + MEMORY_FAILURE_FIFO_SIZE); + spinlock_t lock; + struct work_struct work; +}; + +static DEFINE_PER_CPU(struct memory_failure_cpu, memory_failure_cpu); + +/** + * memory_failure_queue - Schedule handling memory failure of a page. + * @pfn: Page Number of the corrupted page + * @trapno: Trap number reported in the signal to user space. + * @flags: Flags for memory failure handling + * + * This function is called by the low level hardware error handler + * when it detects hardware memory corruption of a page. It schedules + * the recovering of error page, including dropping pages, killing + * processes etc. + * + * The function is primarily of use for corruptions that + * happen outside the current execution context (e.g. when + * detected by a background scrubber) + * + * Can run in IRQ context. + */ +void memory_failure_queue(unsigned long pfn, int trapno, int flags) +{ + struct memory_failure_cpu *mf_cpu; + unsigned long proc_flags; + struct memory_failure_entry entry = { + .pfn = pfn, + .trapno = trapno, + .flags = flags, + }; + + mf_cpu = &get_cpu_var(memory_failure_cpu); + spin_lock_irqsave(&mf_cpu->lock, proc_flags); + if (kfifo_put(&mf_cpu->fifo, &entry)) + schedule_work_on(smp_processor_id(), &mf_cpu->work); + else + pr_err("Memory failure: buffer overflow when queuing memory failure at 0x%#lx\n", + pfn); + spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); + put_cpu_var(memory_failure_cpu); +} +EXPORT_SYMBOL_GPL(memory_failure_queue); + +static void memory_failure_work_func(struct work_struct *work) +{ + struct memory_failure_cpu *mf_cpu; + struct memory_failure_entry entry = { 0, }; + unsigned long proc_flags; + int gotten; + + mf_cpu = &__get_cpu_var(memory_failure_cpu); + for (;;) { + spin_lock_irqsave(&mf_cpu->lock, proc_flags); + gotten = kfifo_get(&mf_cpu->fifo, &entry); + spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); + if (!gotten) + break; + __memory_failure(entry.pfn, entry.trapno, entry.flags); + } +} + +static int __init memory_failure_init(void) +{ + struct memory_failure_cpu *mf_cpu; + int cpu; + + for_each_possible_cpu(cpu) { + mf_cpu = &per_cpu(memory_failure_cpu, cpu); + spin_lock_init(&mf_cpu->lock); + INIT_KFIFO(mf_cpu->fifo); + INIT_WORK(&mf_cpu->work, memory_failure_work_func); + } + + return 0; +} +core_initcall(memory_failure_init); + /** * unpoison_memory - Unpoison a previously poisoned page * @pfn: Page number of the to be unpoisoned page |