From 268bb0ce3e87872cb9290c322b0d35bce230d88f Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 20 May 2011 12:50:29 -0700 Subject: sanitize usage Commit e66eed651fd1 ("list: remove prefetching from regular list iterators") removed the include of prefetch.h from list.h, which uncovered several cases that had apparently relied on that rather obscure header file dependency. So this fixes things up a bit, using grep -L linux/prefetch.h $(git grep -l '[^a-z_]prefetchw*(' -- '*.[ch]') grep -L 'prefetchw*(' $(git grep -l 'linux/prefetch.h' -- '*.[ch]') to guide us in finding files that either need inclusion, or have it despite not needing it. There are more of them around (mostly network drivers), but this gets many core ones. Reported-by: Stephen Rothwell Signed-off-by: Linus Torvalds --- arch/x86/mm/fault.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86/mm/fault.c') diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 20e3f8702d1e..bcb394dfbb35 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -12,6 +12,7 @@ #include /* kmmio_handler, ... */ #include /* perf_sw_event */ #include /* hstate_index_to_shift */ +#include /* prefetchw */ #include /* dotraplinkage, ... */ #include /* pgd_*(), ... */ -- cgit v1.2.3 From 37b23e0525d393d48a7d59f870b3bc061a30ccdb Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Tue, 24 May 2011 17:11:30 -0700 Subject: x86,mm: make pagefault killable When an oom killing occurs, almost all processes are getting stuck at the following two points. 1) __alloc_pages_nodemask 2) __lock_page_or_retry 1) is not very problematic because TIF_MEMDIE leads to an allocation failure and getting out from page allocator. 2) is more problematic. In an OOM situation, zones typically don't have page cache at all and memory starvation might lead to greatly reduced IO performance. When a fork bomb occurs, TIF_MEMDIE tasks don't die quickly, meaning that a fork bomb may create new process quickly rather than the oom-killer killing it. Then, the system may become livelocked. This patch makes the pagefault interruptible by SIGKILL. Signed-off-by: KOSAKI Motohiro Reviewed-by: KAMEZAWA Hiroyuki Cc: Minchan Kim Cc: Matthew Wilcox Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/mm/fault.c | 12 +++++++++++- include/linux/mm.h | 1 + mm/filemap.c | 31 ++++++++++++++++++++++++------- 3 files changed, 36 insertions(+), 8 deletions(-) (limited to 'arch/x86/mm/fault.c') diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index bcb394dfbb35..f7a2a054a3c0 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -965,7 +965,7 @@ do_page_fault(struct pt_regs *regs, unsigned long error_code) struct mm_struct *mm; int fault; int write = error_code & PF_WRITE; - unsigned int flags = FAULT_FLAG_ALLOW_RETRY | + unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE | (write ? FAULT_FLAG_WRITE : 0); tsk = current; @@ -1138,6 +1138,16 @@ good_area: return; } + /* + * Pagefault was interrupted by SIGKILL. We have no reason to + * continue pagefault. + */ + if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) { + if (!(error_code & PF_USER)) + no_context(regs, error_code, address); + return; + } + /* * Major/minor page fault accounting is only done on the * initial attempt. If we go through a retry, it is extremely diff --git a/include/linux/mm.h b/include/linux/mm.h index 1746f67c33de..57d3d5fade16 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -153,6 +153,7 @@ extern pgprot_t protection_map[16]; #define FAULT_FLAG_MKWRITE 0x04 /* Fault was mkwrite of existing pte */ #define FAULT_FLAG_ALLOW_RETRY 0x08 /* Retry fault if blocking */ #define FAULT_FLAG_RETRY_NOWAIT 0x10 /* Don't drop mmap_sem and wait when retrying */ +#define FAULT_FLAG_KILLABLE 0x20 /* The fault task is in SIGKILL killable region */ /* * This interface is used by x86 PAT code to identify a pfn mapping that is diff --git a/mm/filemap.c b/mm/filemap.c index dea8a38bb2bb..8144f87dcbb4 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -654,15 +654,32 @@ EXPORT_SYMBOL_GPL(__lock_page_killable); int __lock_page_or_retry(struct page *page, struct mm_struct *mm, unsigned int flags) { - if (!(flags & FAULT_FLAG_ALLOW_RETRY)) { - __lock_page(page); - return 1; - } else { - if (!(flags & FAULT_FLAG_RETRY_NOWAIT)) { - up_read(&mm->mmap_sem); + if (flags & FAULT_FLAG_ALLOW_RETRY) { + /* + * CAUTION! In this case, mmap_sem is not released + * even though return 0. + */ + if (flags & FAULT_FLAG_RETRY_NOWAIT) + return 0; + + up_read(&mm->mmap_sem); + if (flags & FAULT_FLAG_KILLABLE) + wait_on_page_locked_killable(page); + else wait_on_page_locked(page); - } return 0; + } else { + if (flags & FAULT_FLAG_KILLABLE) { + int ret; + + ret = __lock_page_killable(page); + if (ret) { + up_read(&mm->mmap_sem); + return 0; + } + } else + __lock_page(page); + return 1; } } -- cgit v1.2.3 From b80ef10e84d85a06bcd0b3a24a752ec32d0e0e40 Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Thu, 26 May 2011 17:12:12 +0900 Subject: x86: Move do_page_fault()'s error path under unlikely() Ingo suggested SIGKILL check should be moved into slowpath function. This will reduce the page fault fastpath impact of this recent commit: 37b23e0525d3: x86,mm: make pagefault killable Suggested-by: Ingo Molnar Signed-off-by: KOSAKI Motohiro Cc: kamezawa.hiroyu@jp.fujitsu.com Cc: minchan.kim@gmail.com Cc: willy@linux.intel.com Cc: Andrew Morton Cc: Linus Torvalds Link: http://lkml.kernel.org/r/4DDE0B5C.9050907@jp.fujitsu.com Signed-off-by: Ingo Molnar --- arch/x86/mm/fault.c | 35 ++++++++++++++++++++--------------- 1 file changed, 20 insertions(+), 15 deletions(-) (limited to 'arch/x86/mm/fault.c') diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index f7a2a054a3c0..2dbf6bf4c7e5 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -823,16 +823,30 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address, force_sig_info_fault(SIGBUS, code, address, tsk, fault); } -static noinline void +static noinline int mm_fault_error(struct pt_regs *regs, unsigned long error_code, unsigned long address, unsigned int fault) { + /* + * Pagefault was interrupted by SIGKILL. We have no reason to + * continue pagefault. + */ + if (fatal_signal_pending(current)) { + if (!(fault & VM_FAULT_RETRY)) + up_read(¤t->mm->mmap_sem); + if (!(error_code & PF_USER)) + no_context(regs, error_code, address); + return 1; + } + if (!(fault & VM_FAULT_ERROR)) + return 0; + if (fault & VM_FAULT_OOM) { /* Kernel mode? Handle exceptions or die: */ if (!(error_code & PF_USER)) { up_read(¤t->mm->mmap_sem); no_context(regs, error_code, address); - return; + return 1; } out_of_memory(regs, error_code, address); @@ -843,6 +857,7 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, else BUG(); } + return 1; } static int spurious_fault_check(unsigned long error_code, pte_t *pte) @@ -1133,19 +1148,9 @@ good_area: */ fault = handle_mm_fault(mm, vma, address, flags); - if (unlikely(fault & VM_FAULT_ERROR)) { - mm_fault_error(regs, error_code, address, fault); - return; - } - - /* - * Pagefault was interrupted by SIGKILL. We have no reason to - * continue pagefault. - */ - if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) { - if (!(error_code & PF_USER)) - no_context(regs, error_code, address); - return; + if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) { + if (mm_fault_error(regs, error_code, address, fault)) + return; } /* -- cgit v1.2.3