From f86268549f424f83b9eb0963989270e14fbfc3de Mon Sep 17 00:00:00 2001 From: Andrey Vagin Date: Wed, 9 Mar 2011 15:22:23 -0800 Subject: x86/mm: Handle mm_fault_error() in kernel space mm_fault_error() should not execute oom-killer, if page fault occurs in kernel space. E.g. in copy_from_user()/copy_to_user(). This would happen if we find ourselves in OOM on a copy_to_user(), or a copy_from_user() which faults. Without this patch, the kernels hangs up in copy_from_user(), because OOM killer sends SIG_KILL to current process, but it can't handle a signal while in syscall, then the kernel returns to copy_from_user(), reexcute current command and provokes page_fault again. With this patch the kernel return -EFAULT from copy_from_user(). The code, which checks that page fault occurred in kernel space, has been copied from do_sigbus(). This situation is handled by the same way on powerpc, xtensa, tile, ... Signed-off-by: Andrey Vagin Signed-off-by: Andrew Morton Cc: "H. Peter Anvin" Cc: Linus Torvalds Cc: LKML-Reference: <201103092322.p29NMNPH001682@imap1.linux-foundation.org> Signed-off-by: Ingo Molnar --- arch/x86/mm/fault.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'arch/x86/mm/fault.c') diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 7d90ceb882a4..ffc7be104fc2 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -828,6 +828,13 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, unsigned long address, unsigned int fault) { 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; + } + out_of_memory(regs, error_code, address); } else { if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON| -- cgit v1.2.3 From a79e53d85683c6dd9f99c90511028adc2043031f Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Wed, 16 Feb 2011 15:45:22 -0800 Subject: x86/mm: Fix pgd_lock deadlock It's forbidden to take the page_table_lock with the irq disabled or if there's contention the IPIs (for tlb flushes) sent with the page_table_lock held will never run leading to a deadlock. Nobody takes the pgd_lock from irq context so the _irqsave can be removed. Signed-off-by: Andrea Arcangeli Acked-by: Rik van Riel Tested-by: Konrad Rzeszutek Wilk Signed-off-by: Andrew Morton Cc: Peter Zijlstra Cc: Linus Torvalds Cc: LKML-Reference: <201102162345.p1GNjMjm021738@imap1.linux-foundation.org> Signed-off-by: Ingo Molnar --- arch/x86/mm/fault.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'arch/x86/mm/fault.c') diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index ffc7be104fc2..20e3f8702d1e 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -229,15 +229,14 @@ void vmalloc_sync_all(void) for (address = VMALLOC_START & PMD_MASK; address >= TASK_SIZE && address < FIXADDR_TOP; address += PMD_SIZE) { - - unsigned long flags; struct page *page; - spin_lock_irqsave(&pgd_lock, flags); + spin_lock(&pgd_lock); list_for_each_entry(page, &pgd_list, lru) { spinlock_t *pgt_lock; pmd_t *ret; + /* the pgt_lock only for Xen */ pgt_lock = &pgd_page_get_mm(page)->page_table_lock; spin_lock(pgt_lock); @@ -247,7 +246,7 @@ void vmalloc_sync_all(void) if (!ret) break; } - spin_unlock_irqrestore(&pgd_lock, flags); + spin_unlock(&pgd_lock); } } -- cgit v1.2.3