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: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Michal 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: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

arch/alpha/mm/fault.c

@@ -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 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 	} 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

@@ -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 @@ void do_page_fault(struct pt_regs *regs, unsigned long address)
 	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

@@ -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

@@ -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

@@ -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);
 

arch/cris/mm/fault.c

@@ -58,8 +58,7 @@ do_page_fault(unsigned long address, struct pt_regs *regs,
 	struct vm_area_struct * vma;
 	siginfo_t info;
 	int fault;
-	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-				((writeaccess & 1) ? FAULT_FLAG_WRITE : 0);
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	D(printk(KERN_DEBUG
 		 "Page fault for %lX on %X at %lX, prot %d write %d\n",
@@ -117,6 +116,8 @@ do_page_fault(unsigned long address, struct pt_regs *regs,
 	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);
@@ -155,6 +156,7 @@ do_page_fault(unsigned long address, struct pt_regs *regs,
 	} else if (writeaccess == 1) {
 		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/frv/mm/fault.c

@@ -34,11 +34,11 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
 	struct vm_area_struct *vma;
 	struct mm_struct *mm;
 	unsigned long _pme, lrai, lrad, fixup;
+	unsigned long flags = 0;
 	siginfo_t info;
 	pgd_t *pge;
 	pud_t *pue;
 	pte_t *pte;
-	int write;
 	int fault;
 
 #if 0
@@ -81,6 +81,9 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
 	if (in_atomic() || !mm)
 		goto no_context;
 
+	if (user_mode(__frame))
+		flags |= FAULT_FLAG_USER;
+
 	down_read(&mm->mmap_sem);
 
 	vma = find_vma(mm, ear0);
@@ -129,7 +132,6 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
  */
  good_area:
 	info.si_code = SEGV_ACCERR;
-	write = 0;
 	switch (esr0 & ESR0_ATXC) {
 	default:
 		/* handle write to write protected page */
@@ -140,7 +142,7 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
 #endif
 		if (!(vma->vm_flags & VM_WRITE))
 			goto bad_area;
-		write = 1;
+		flags |= FAULT_FLAG_WRITE;
 		break;
 
 		 /* handle read from protected page */
@@ -162,7 +164,7 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(mm, vma, ear0, write ? FAULT_FLAG_WRITE : 0);
+	fault = handle_mm_fault(mm, vma, ear0, flags);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;

arch/hexagon/mm/vm_fault.c

@@ -53,8 +53,7 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs)
 	int si_code = SEGV_MAPERR;
 	int fault;
 	const struct exception_table_entry *fixup;
-	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;
 
 	/*
 	 * If we're in an interrupt or have no user context,
@@ -65,6 +64,8 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs)
 
 	local_irq_enable();
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
 retry:
 	down_read(&mm->mmap_sem);
 	vma = find_vma(mm, address);
@@ -96,6 +97,7 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs)
 	case FLT_STORE:
 		if (!(vma->vm_flags & VM_WRITE))
 			goto bad_area;
+		flags |= FAULT_FLAG_WRITE;
 		break;
 	}
 

arch/ia64/mm/fault.c

@@ -90,8 +90,6 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
 	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);
 
@@ -119,6 +117,10 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
 	if (notify_page_fault(regs, TRAP_BRKPT))
 		return;
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
+	if (mask & VM_WRITE)
+		flags |= FAULT_FLAG_WRITE;
 retry:
 	down_read(&mm->mmap_sem);
 

arch/m32r/mm/fault.c

@@ -78,7 +78,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code,
 	struct mm_struct *mm;
 	struct vm_area_struct * vma;
 	unsigned long page, addr;
-	int write;
+	unsigned long flags = 0;
 	int fault;
 	siginfo_t info;
 
@@ -117,6 +117,9 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code,
 	if (in_atomic() || !mm)
 		goto bad_area_nosemaphore;
 
+	if (error_code & ACE_USERMODE)
+		flags |= FAULT_FLAG_USER;
+
 	/* When running in the kernel we expect faults to occur only to
 	 * addresses in user space.  All other faults represent errors in the
 	 * kernel and should generate an OOPS.  Unfortunately, in the case of an
@@ -166,14 +169,13 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code,
  */
 good_area:
 	info.si_code = SEGV_ACCERR;
-	write = 0;
 	switch (error_code & (ACE_WRITE|ACE_PROTECTION)) {
 		default:	/* 3: write, present */
 			/* fall through */
 		case ACE_WRITE:	/* write, not present */
 			if (!(vma->vm_flags & VM_WRITE))
 				goto bad_area;
-			write++;
+			flags |= FAULT_FLAG_WRITE;
 			break;
 		case ACE_PROTECTION:	/* read, present */
 		case 0:		/* read, not present */
@@ -194,7 +196,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code,
 	 */
 	addr = (address & PAGE_MASK);
 	set_thread_fault_code(error_code);
-	fault = handle_mm_fault(mm, vma, addr, write ? FAULT_FLAG_WRITE : 0);
+	fault = handle_mm_fault(mm, vma, addr, flags);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;

arch/m68k/mm/fault.c

@@ -88,6 +88,8 @@ int 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);
 

arch/metag/mm/fault.c

@@ -53,8 +53,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
 	struct vm_area_struct *vma, *prev_vma;
 	siginfo_t info;
 	int fault;
-	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-				(write_access ? FAULT_FLAG_WRITE : 0);
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	tsk = current;
 
@@ -109,6 +108,8 @@ int 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);
 
@@ -121,6 +122,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
 	if (write_access) {
 		if (!(vma->vm_flags & VM_WRITE))
 			goto bad_area;
+		flags |= FAULT_FLAG_WRITE;
 	} else {
 		if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
 			goto bad_area;

arch/microblaze/mm/fault.c

@@ -92,8 +92,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
 	int code = SEGV_MAPERR;
 	int is_write = error_code & ESR_S;
 	int fault;
-	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-					 (is_write ? FAULT_FLAG_WRITE : 0);
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	regs->ear = address;
 	regs->esr = error_code;
@@ -121,6 +120,9 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
 		die("Weird page fault", regs, SIGSEGV);
 	}
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
+
 	/* When running in the kernel we expect faults to occur only to
 	 * addresses in user space.  All other faults represent errors in the
 	 * kernel and should generate an OOPS.  Unfortunately, in the case of an
@@ -199,6 +201,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
 	if (unlikely(is_write)) {
 		if (unlikely(!(vma->vm_flags & VM_WRITE)))
 			goto bad_area;
+		flags |= FAULT_FLAG_WRITE;
 	/* a read */
 	} else {
 		/* protection fault */

arch/mips/mm/fault.c

@@ -42,8 +42,7 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write,
 	const int field = sizeof(unsigned long) * 2;
 	siginfo_t info;
 	int fault;
-	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 0
 	printk("Cpu%d[%s:%d:%0*lx:%ld:%0*lx]\n", raw_smp_processor_id(),
@@ -93,6 +92,8 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write,
 	if (in_atomic() || !mm)
 		goto bad_area_nosemaphore;
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
 retry:
 	down_read(&mm->mmap_sem);
 	vma = find_vma(mm, address);
@@ -114,6 +115,7 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write,
 	if (write) {
 		if (!(vma->vm_flags & VM_WRITE))
 			goto bad_area;
+		flags |= FAULT_FLAG_WRITE;
 	} else {
 		if (cpu_has_rixi) {
 			if (address == regs->cp0_epc && !(vma->vm_flags & VM_EXEC)) {

arch/mn10300/mm/fault.c

@@ -171,6 +171,8 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long fault_code,
 	if (in_atomic() || !mm)
 		goto no_context;
 
+	if ((fault_code & MMUFCR_xFC_ACCESS) == MMUFCR_xFC_ACCESS_USR)
+		flags |= FAULT_FLAG_USER;
 retry:
 	down_read(&mm->mmap_sem);
 

arch/openrisc/mm/fault.c

@@ -86,6 +86,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address,
 	if (user_mode(regs)) {
 		/* Exception was in userspace: reenable interrupts */
 		local_irq_enable();
+		flags |= FAULT_FLAG_USER;
 	} else {
 		/* If exception was in a syscall, then IRQ's may have
 		 * been enabled or disabled.  If they were enabled,