From f28fa729149c8b39699f7995ce5fff34c5145a9d Mon Sep 17 00:00:00 2001 From: Kautuk Consul Date: Thu, 14 Jun 2012 13:11:37 -0700 Subject: [PATCH 1/2] [IA64] Port OOM changes to ia64_do_page_fault Commit d065bd810b6deb67d4897a14bfe21f8eb526ba99 (mm: retry page fault when blocking on disk transfer) and commit 37b23e0525d393d48a7d59f870b3bc061a30ccdb (x86,mm: make pagefault killable) The above commits introduced changes into the x86 pagefault handler for making the page fault handler retryable as well as killable. These changes reduce the mmap_sem hold time, which is crucial during OOM killer invocation. Port these changes to ia64. Signed-off-by: Kautuk Consul Signed-off-by: Tony Luck --- arch/ia64/mm/fault.c | 46 ++++++++++++++++++++++++++++++++------------ 1 file changed, 34 insertions(+), 12 deletions(-) diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index 02d29c2a132a..8443daf4f515 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -72,6 +72,10 @@ mapped_kernel_page_is_present (unsigned long address) return pte_present(pte); } +# define VM_READ_BIT 0 +# define VM_WRITE_BIT 1 +# define VM_EXEC_BIT 2 + void __kprobes ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *regs) { @@ -81,6 +85,12 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re struct siginfo si; unsigned long mask; int fault; + unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + + mask = ((((isr >> IA64_ISR_X_BIT) & 1UL) << VM_EXEC_BIT) + | (((isr >> IA64_ISR_W_BIT) & 1UL) << VM_WRITE_BIT)); + + flags |= ((mask & VM_WRITE) ? FAULT_FLAG_WRITE : 0); /* mmap_sem is performance critical.... */ prefetchw(&mm->mmap_sem); @@ -109,6 +119,7 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re if (notify_page_fault(regs, TRAP_BRKPT)) return; +retry: down_read(&mm->mmap_sem); vma = find_vma_prev(mm, address, &prev_vma); @@ -130,10 +141,6 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re /* OK, we've got a good vm_area for this memory area. Check the access permissions: */ -# define VM_READ_BIT 0 -# define VM_WRITE_BIT 1 -# define VM_EXEC_BIT 2 - # if (((1 << VM_READ_BIT) != VM_READ || (1 << VM_WRITE_BIT) != VM_WRITE) \ || (1 << VM_EXEC_BIT) != VM_EXEC) # error File is out of sync with . Please update. @@ -142,9 +149,6 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re if (((isr >> IA64_ISR_R_BIT) & 1UL) && (!(vma->vm_flags & (VM_READ | VM_WRITE)))) goto bad_area; - mask = ( (((isr >> IA64_ISR_X_BIT) & 1UL) << VM_EXEC_BIT) - | (((isr >> IA64_ISR_W_BIT) & 1UL) << VM_WRITE_BIT)); - if ((vma->vm_flags & mask) != mask) goto bad_area; @@ -153,7 +157,11 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re * sure we exit gracefully rather than endlessly redo the * fault. */ - fault = handle_mm_fault(mm, vma, address, (mask & VM_WRITE) ? FAULT_FLAG_WRITE : 0); + fault = handle_mm_fault(mm, vma, address, flags); + + if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { /* * We ran out of memory, or some other thing happened @@ -168,10 +176,24 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re } BUG(); } - if (fault & VM_FAULT_MAJOR) - current->maj_flt++; - else - current->min_flt++; + + if (flags & FAULT_FLAG_ALLOW_RETRY) { + if (fault & VM_FAULT_MAJOR) + current->maj_flt++; + else + current->min_flt++; + if (fault & VM_FAULT_RETRY) { + flags &= ~FAULT_FLAG_ALLOW_RETRY; + + /* No need to up_read(&mm->mmap_sem) as we would + * have already released it in __lock_page_or_retry + * in mm/filemap.c. + */ + + goto retry; + } + } + up_read(&mm->mmap_sem); return; From e9c31b32f1cc6d3aa190119103622fb8e4c257b1 Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Wed, 18 Jul 2012 10:35:05 -0700 Subject: [PATCH 2/2] debug: Do not permit CONFIG_DEBUG_STACK_USAGE=y on IA64 or PARISC The stack_not_used() function in assumes that stacks grow downwards. This is not true on IA64 or PARISC, so this function would walk off in the wrong direction and into the weeds. Found on IA64 because of a compilation failure with recursive dependencies on IA64_TASKSIZE and IA64_THREAD_INFO_SIZE. Fixing the code is possible, but should be combined with other infrastructure additions to set up the "canary" at the end of the stack. Reported-by: Fengguang Wu (failed allmodconfig build) Signed-off-by: Tony Luck --- lib/Kconfig.debug | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index a42d3ae39648..5d3e3288438f 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -694,7 +694,7 @@ config STACKTRACE config DEBUG_STACK_USAGE bool "Stack utilization instrumentation" - depends on DEBUG_KERNEL + depends on DEBUG_KERNEL && !IA64 && !PARISC help Enables the display of the minimum amount of free stack which each task has ever had available in the sysrq-T and sysrq-P debug output.