arm: fault.c: Port OOM changes into 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 ARM.

Without these changes, my ARM board encounters many hang and livelock
scenarios.
After applying this patch, OOM feature performance improves according to
my testing.

Signed-off-by: Kautuk Consul <consul.kautuk@gmail.com>
"I think this is fine"-by Russell King - ARM Linux <linux@arm.linux.org.uk>
Signed-off-by: Nicolas Pitre <nicolas.pitre@linaro.org>

1 files changed, 39 insertions, 19 deletions

diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 05588bc1d22..0a7d73fc984 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -219,7 +219,7 @@ static inline bool access_error(unsigned int fsr, struct vm_area_struct *vma)
 
 static int __kprobes
 __do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr,
-		struct task_struct *tsk)
+		unsigned int flags, struct task_struct *tsk)
 {
 	struct vm_area_struct *vma;
 	int fault;
@@ -241,18 +241,7 @@ good_area:
 		goto out;
 	}
 
-	/*
-	 * If for any reason at all we couldn't handle the fault, make
-	 * sure we exit gracefully rather than endlessly redo the fault.
-	 */
-	fault = handle_mm_fault(mm, vma, addr & PAGE_MASK, (fsr & FSR_WRITE) ? FAULT_FLAG_WRITE : 0);
-	if (unlikely(fault & VM_FAULT_ERROR))
-		return fault;
-	if (fault & VM_FAULT_MAJOR)
-		tsk->maj_flt++;
-	else
-		tsk->min_flt++;
-	return fault;
+	return handle_mm_fault(mm, vma, addr & PAGE_MASK, flags);
 
 check_stack:
 	if (vma->vm_flags & VM_GROWSDOWN && !expand_stack(vma, addr))
@@ -267,6 +256,9 @@ 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);
 
 	if (notify_page_fault(regs, fsr))
 		return 0;
@@ -293,6 +285,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	if (!down_read_trylock(&mm->mmap_sem)) {
 		if (!user_mode(regs) && !search_exception_tables(regs->ARM_pc))
 			goto no_context;
+retry:
 		down_read(&mm->mmap_sem);
 	} else {
 		/*
@@ -308,14 +301,41 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 #endif
 	}
 
-	fault = __do_page_fault(mm, addr, fsr, tsk);
-	up_read(&mm->mmap_sem);
+	fault = __do_page_fault(mm, addr, fsr, flags, tsk);
+
+	/* If we need to retry but a fatal signal is pending, handle the
+	 * signal first. We do not need to release the mmap_sem because
+	 * it would already be released in __lock_page_or_retry in
+	 * mm/filemap.c. */
+	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+		return 0;
+
+	/*
+	 * Major/minor page fault accounting is only done on the
+	 * initial attempt. If we go through a retry, it is extremely
+	 * likely that the page will be found in page cache at that point.
+	 */
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
-	if (fault & VM_FAULT_MAJOR)
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, addr);
-	else if (fault & VM_FAULT_MINOR)
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, addr);
+	if (flags & FAULT_FLAG_ALLOW_RETRY) {
+		if (fault & VM_FAULT_MAJOR) {
+			tsk->maj_flt++;
+			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
+					regs, addr);
+		} else {
+			tsk->min_flt++;
+			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
+					regs, addr);
+		}
+		if (fault & VM_FAULT_RETRY) {
+			/* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
+			* of starvation. */
+			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+			goto retry;
+		}
+	}
+
+	up_read(&mm->mmap_sem);
 
 	/*
 	 * Handle the "normal" case first - VM_FAULT_MAJOR / VM_FAULT_MINOR