I am adding another patch here to disable page offlining in case the firmware starts acting up.
Thanks, Naveen -- Add a sysctl memory_failure_soft_offline to control what is done on receipt of firmware ghes notification for a corrected error. By default, kernel tries to soft-offline the page immediately. If set to 0, no action is taken. Signed-off-by: Naveen N. Rao <[email protected]> --- Documentation/sysctl/vm.txt | 12 ++++++++++++ include/linux/mm.h | 1 + kernel/sysctl.c | 9 +++++++++ mm/memory-failure.c | 10 +++++++--- 4 files changed, 29 insertions(+), 3 deletions(-) diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index dcc75a9..6d0fcba 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -375,6 +375,18 @@ Enable memory failure recovery (when supported by the platform) ============================================================== +memory_failure_soft_offline + +Control soft-offlining of pages on receipt of appropriate firmware error +report through GHES. Note that this does not affect user-space initiated +soft-offlining. + +1: Attempt soft-offlining. + +0: No action. + +============================================================== + min_free_kbytes: This is used to force the Linux VM to keep a minimum number diff --git a/include/linux/mm.h b/include/linux/mm.h index 958e9efd..2c16ca4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1791,6 +1791,7 @@ extern void memory_failure_queue(unsigned long pfn, int trapno, int flags); extern int unpoison_memory(unsigned long pfn); extern int sysctl_memory_failure_early_kill; extern int sysctl_memory_failure_recovery; +extern int sysctl_memory_failure_soft_offline; extern void shake_page(struct page *p, int access); extern atomic_long_t num_poisoned_pages; extern int soft_offline_page(struct page *page, int flags); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index b0a1f99..cc4b794 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1427,6 +1427,15 @@ static struct ctl_table vm_table[] = { .extra1 = &zero, .extra2 = &one, }, + { + .procname = "memory_failure_soft_offline", + .data = &sysctl_memory_failure_soft_offline, + .maxlen = sizeof(sysctl_memory_failure_soft_offline), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, #endif { .procname = "user_reserve_kbytes", diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 0d6717e..ec4851c 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -61,6 +61,8 @@ int sysctl_memory_failure_early_kill __read_mostly = 0; int sysctl_memory_failure_recovery __read_mostly = 1; +int sysctl_memory_failure_soft_offline __read_mostly = 1; + atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0); #if defined(CONFIG_HWPOISON_INJECT) || defined(CONFIG_HWPOISON_INJECT_MODULE) @@ -1286,9 +1288,11 @@ static void memory_failure_work_func(struct work_struct *work) spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); if (!gotten) break; - if (entry.flags & MF_SOFT_OFFLINE) - soft_offline_page(pfn_to_page(entry.pfn), entry.flags); - else + if (entry.flags & MF_SOFT_OFFLINE) { + if (sysctl_memory_failure_soft_offline) + soft_offline_page(pfn_to_page(entry.pfn), + entry.flags); + } else memory_failure(entry.pfn, entry.trapno, entry.flags); } } -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
