readahead: fault retry breaks mmap file read random detection

.fault now can retry. The retry can break state machine of .fault. In filemap_fault, if page is miss, ra->mmap_miss is increased. In the second try, since the page is in page cache now, ra->mmap_miss is decreased. And these are done in one fault, so we can't detect random mmap file access. Add a new flag to indicate .fault is tried once. In the second try, skip ra->mmap_miss decreasing. The filemap_fault state machine is ok with it. I only tested x86, didn't test other archs, but looks the change for other archs is obvious, but who knows :) Signed-off-by: Shaohua Li <[email protected]> Cc: Rik van Riel <[email protected]> Cc: Wu Fengguang <[email protected]> Signed-off-by: Andrew Morton <[email protected]> Signed-off-by: Linus Torvalds <[email protected]>
mrcheets · Oct 9, 2012 · 45cac65 · 45cac65
1 parent e79bee2
commit 45cac65
Show file tree

Hide file tree

Showing 20 changed files with 21 additions and 2 deletions.
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
@@ -336,6 +336,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 			/* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
 			* of starvation. */
 			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+			flags |= FAULT_FLAG_TRIED;
 			goto retry;
 		}
 	}

diff --git a/arch/avr32/mm/fault.c b/arch/avr32/mm/fault.c
@@ -152,6 +152,7 @@ asmlinkage void do_page_fault(unsigned long ecr, struct pt_regs *regs)
 			tsk->min_flt++;
 		if (fault & VM_FAULT_RETRY) {
 			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+			flags |= FAULT_FLAG_TRIED;
 
 			/*
 			 * No need to up_read(&mm->mmap_sem) as we would have

diff --git a/arch/cris/mm/fault.c b/arch/cris/mm/fault.c
@@ -186,6 +186,7 @@ do_page_fault(unsigned long address, struct pt_regs *regs,
 			tsk->min_flt++;
 		if (fault & VM_FAULT_RETRY) {
 			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+			flags |= FAULT_FLAG_TRIED;
 
 			/*
 			 * No need to up_read(&mm->mmap_sem) as we would

diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c
@@ -113,6 +113,7 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs)
 				current->min_flt++;
 			if (fault & VM_FAULT_RETRY) {
 				flags &= ~FAULT_FLAG_ALLOW_RETRY;
+				flags |= FAULT_FLAG_TRIED;
 				goto retry;
 			}
 		}

diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c
@@ -184,6 +184,7 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
 			current->min_flt++;
 		if (fault & VM_FAULT_RETRY) {
 			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+			flags |= FAULT_FLAG_TRIED;
 
 			 /* No need to up_read(&mm->mmap_sem) as we would
 			 * have already released it in __lock_page_or_retry

diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
@@ -170,6 +170,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
 			/* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
 			 * of starvation. */
 			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+			flags |= FAULT_FLAG_TRIED;
 
 			/*
 			 * No need to up_read(&mm->mmap_sem) as we would

diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c
@@ -233,6 +233,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
 			current->min_flt++;
 		if (fault & VM_FAULT_RETRY) {
 			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+			flags |= FAULT_FLAG_TRIED;
 
 			/*
 			 * No need to up_read(&mm->mmap_sem) as we would

diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
@@ -171,6 +171,7 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs, unsigned long writ
 		}
 		if (fault & VM_FAULT_RETRY) {
 			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+			flags |= FAULT_FLAG_TRIED;
 
 			/*
 			 * No need to up_read(&mm->mmap_sem) as we would

diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c
@@ -183,6 +183,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address,
 			tsk->min_flt++;
 		if (fault & VM_FAULT_RETRY) {
 			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+			flags |= FAULT_FLAG_TRIED;
 
 			 /* No need to up_read(&mm->mmap_sem) as we would
 			 * have already released it in __lock_page_or_retry

diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
@@ -451,6 +451,7 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 			/* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
 			 * of starvation. */
 			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+			flags |= FAULT_FLAG_TRIED;
 			goto retry;
 		}
 	}

diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
@@ -367,6 +367,7 @@ static inline int do_exception(struct pt_regs *regs, int access)
 			/* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
 			 * of starvation. */
 			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+			flags |= FAULT_FLAG_TRIED;
 			down_read(&mm->mmap_sem);
 			goto retry;
 		}

diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c
@@ -504,6 +504,7 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
 		}
 		if (fault & VM_FAULT_RETRY) {
 			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+			flags |= FAULT_FLAG_TRIED;
 
 			/*
 			 * No need to up_read(&mm->mmap_sem) as we would

diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
@@ -265,6 +265,7 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
 		}
 		if (fault & VM_FAULT_RETRY) {
 			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+			flags |= FAULT_FLAG_TRIED;
 
 			/* No need to up_read(&mm->mmap_sem) as we would
 			 * have already released it in __lock_page_or_retry

diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
@@ -452,6 +452,7 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
 		}
 		if (fault & VM_FAULT_RETRY) {
 			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+			flags |= FAULT_FLAG_TRIED;
 
 			/* No need to up_read(&mm->mmap_sem) as we would
 			 * have already released it in __lock_page_or_retry

diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c
@@ -454,6 +454,7 @@ static int handle_page_fault(struct pt_regs *regs,
 			tsk->min_flt++;
 		if (fault & VM_FAULT_RETRY) {
 			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+			flags |= FAULT_FLAG_TRIED;
 
 			 /*
 			  * No need to up_read(&mm->mmap_sem) as we would

diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
@@ -89,6 +89,7 @@ int handle_page_fault(unsigned long address, unsigned long ip,
 				current->min_flt++;
 			if (fault & VM_FAULT_RETRY) {
 				flags &= ~FAULT_FLAG_ALLOW_RETRY;
+				flags |= FAULT_FLAG_TRIED;
 
 				goto retry;
 			}

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
@@ -1220,6 +1220,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
 			/* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
 			 * of starvation. */
 			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+			flags |= FAULT_FLAG_TRIED;
 			goto retry;
 		}
 	}

diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
@@ -126,6 +126,7 @@ void do_page_fault(struct pt_regs *regs)
 			current->min_flt++;
 		if (fault & VM_FAULT_RETRY) {
 			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+			flags |= FAULT_FLAG_TRIED;
 
 			 /* No need to up_read(&mm->mmap_sem) as we would
 			 * have already released it in __lock_page_or_retry

diff --git a/include/linux/mm.h b/include/linux/mm.h
@@ -161,6 +161,7 @@ extern pgprot_t protection_map[16];
 #define FAULT_FLAG_ALLOW_RETRY	0x08	/* Retry fault if blocking */
 #define FAULT_FLAG_RETRY_NOWAIT	0x10	/* Don't drop mmap_sem and wait when retrying */
 #define FAULT_FLAG_KILLABLE	0x20	/* The fault task is in SIGKILL killable region */
+#define FAULT_FLAG_TRIED	0x40	/* second try */
 
 /*
  * vm_fault is filled by the the pagefault handler and passed to the vma's

diff --git a/mm/filemap.c b/mm/filemap.c
@@ -1607,13 +1607,13 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	 * Do we have something in the page cache already?
 	 */
 	page = find_get_page(mapping, offset);
-	if (likely(page)) {
+	if (likely(page) && !(vmf->flags & FAULT_FLAG_TRIED)) {
 		/*
 		 * We found the page, so try async readahead before
 		 * waiting for the lock.
 		 */
 		do_async_mmap_readahead(vma, ra, file, page, offset);
-	} else {
+	} else if (!page) {
 		/* No page in the page cache at all */
 		do_sync_mmap_readahead(vma, ra, file, offset);
 		count_vm_event(PGMAJFAULT);