Commit 759496ba authored by Johannes Weiner's avatar Johannes Weiner Committed by Linus Torvalds
Browse files

arch: mm: pass userspace fault flag to generic fault handler 



Unlike global OOM handling, memory cgroup code will invoke the OOM killer
in any OOM situation because it has no way of telling faults occuring in
kernel context - which could be handled more gracefully - from
user-triggered faults.

Pass a flag that identifies faults originating in user space from the
architecture-specific fault handlers to generic code so that memcg OOM
handling can be improved.

Signed-off-by: default avatarJohannes Weiner <hannes@cmpxchg.org>
Reviewed-by: default avatarMichal Hocko <mhocko@suse.cz>
Cc: David Rientjes <rientjes@google.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: azurIt <azurit@pobox.sk>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 87134102

arch/alpha/mm/fault.c

+4 −3
Original line number Diff line number Diff line
@@ -89,8 +89,7 @@ do_page_fault(unsigned long address, unsigned long mmcsr, 
	const struct exception_table_entry *fixup;

	int fault, si_code = SEGV_MAPERR;

	siginfo_t info;

	unsigned int flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |

			      (cause > 0 ? FAULT_FLAG_WRITE : 0));

	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;



	/* As of EV6, a load into $31/$f31 is a prefetch, and never faults

	   (or is suppressed by the PALcode).  Support that for older CPUs
@@ -115,7 +114,8 @@ do_page_fault(unsigned long address, unsigned long mmcsr, 
	if (address >= TASK_SIZE)

		goto vmalloc_fault;

#endif



	if (user_mode(regs))

		flags |= FAULT_FLAG_USER;

retry:

	down_read(&mm->mmap_sem);

	vma = find_vma(mm, address);
@@ -142,6 +142,7 @@ retry: 
	} else {

		if (!(vma->vm_flags & VM_WRITE))

			goto bad_area;

		flags |= FAULT_FLAG_WRITE;

	}



	/* If for any reason at all we couldn't handle the fault,

arch/arc/mm/fault.c

+4 −2
Original line number Diff line number Diff line
@@ -60,8 +60,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long address) 
	siginfo_t info;

	int fault, ret;

	int write = regs->ecr_cause & ECR_C_PROTV_STORE;  /* ST/EX */

	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |

				(write ? FAULT_FLAG_WRITE : 0);

	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;



	/*

	 * We fault-in kernel-space virtual memory on-demand. The
@@ -89,6 +88,8 @@ void do_page_fault(struct pt_regs *regs, unsigned long address) 
	if (in_atomic() || !mm)

		goto no_context;



	if (user_mode(regs))

		flags |= FAULT_FLAG_USER;

retry:

	down_read(&mm->mmap_sem);

	vma = find_vma(mm, address);
@@ -117,6 +118,7 @@ good_area: 
	if (write) {

		if (!(vma->vm_flags & VM_WRITE))

			goto bad_area;

		flags |= FAULT_FLAG_WRITE;

	} else {

		if (!(vma->vm_flags & (VM_READ | VM_EXEC)))

			goto bad_area;

arch/arm/mm/fault.c

+6 −3
Original line number Diff line number Diff line
@@ -261,9 +261,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) 
	struct task_struct *tsk;

	struct mm_struct *mm;

	int fault, sig, code;

	int write = fsr & FSR_WRITE;

	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |

				(write ? FAULT_FLAG_WRITE : 0);

	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;



	if (notify_page_fault(regs, fsr))

		return 0;
@@ -282,6 +280,11 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) 
	if (in_atomic() || !mm)

		goto no_context;



	if (user_mode(regs))

		flags |= FAULT_FLAG_USER;

	if (fsr & FSR_WRITE)

		flags |= FAULT_FLAG_WRITE;



	/*

	 * As per x86, we may deadlock here.  However, since the kernel only

	 * validly references user space from well defined areas of the code,

arch/arm64/mm/fault.c

+10 −7
Original line number Diff line number Diff line
@@ -199,13 +199,6 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, 
	unsigned long vm_flags = VM_READ | VM_WRITE | VM_EXEC;

	unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;



	if (esr & ESR_LNX_EXEC) {

		vm_flags = VM_EXEC;

	} else if ((esr & ESR_WRITE) && !(esr & ESR_CM)) {

		vm_flags = VM_WRITE;

		mm_flags |= FAULT_FLAG_WRITE;

	}



	tsk = current;

	mm  = tsk->mm;
@@ -220,6 +213,16 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, 
	if (in_atomic() || !mm)

		goto no_context;



	if (user_mode(regs))

		mm_flags |= FAULT_FLAG_USER;



	if (esr & ESR_LNX_EXEC) {

		vm_flags = VM_EXEC;

	} else if ((esr & ESR_WRITE) && !(esr & ESR_CM)) {

		vm_flags = VM_WRITE;

		mm_flags |= FAULT_FLAG_WRITE;

	}



	/*

	 * As per x86, we may deadlock here. However, since the kernel only

	 * validly references user space from well defined areas of the code,

arch/avr32/mm/fault.c

+2 −0
Original line number Diff line number Diff line
@@ -86,6 +86,8 @@ asmlinkage void do_page_fault(unsigned long ecr, struct pt_regs *regs) 


	local_irq_enable();



	if (user_mode(regs))

		flags |= FAULT_FLAG_USER;

retry:

	down_read(&mm->mmap_sem);

CRA Git | Maintained and supported by SUSTech CRA and CCSE