Merge branches 'fixes' and 'misc' into for-linus

3 files changed, 218 insertions, 24 deletions

diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index aa33949fef6..4aabeaec25d 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -231,7 +231,7 @@ 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;
@@ -253,18 +253,7 @@ 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))
@@ -279,6 +268,9 @@ 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;
@@ -305,6 +297,7 @@ 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 {
 		/*
@@ -320,14 +313,41 @@ 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
diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c
index 44b628e4d6e..ce8cb1970d7 100644
--- a/arch/arm/mm/mmap.c
+++ b/arch/arm/mm/mmap.c
@@ -11,10 +11,49 @@
 #include <linux/random.h>
 #include <asm/cachetype.h>
 
+static inline unsigned long COLOUR_ALIGN_DOWN(unsigned long addr,
+					      unsigned long pgoff)
+{
+	unsigned long base = addr & ~(SHMLBA-1);
+	unsigned long off = (pgoff << PAGE_SHIFT) & (SHMLBA-1);
+
+	if (base + off <= addr)
+		return base + off;
+
+	return base - off;
+}
+
 #define COLOUR_ALIGN(addr,pgoff)		\
 	((((addr)+SHMLBA-1)&~(SHMLBA-1)) +	\
 	 (((pgoff)<<PAGE_SHIFT) & (SHMLBA-1)))
 
+/* gap between mmap and stack */
+#define MIN_GAP (128*1024*1024UL)
+#define MAX_GAP ((TASK_SIZE)/6*5)
+
+static int mmap_is_legacy(void)
+{
+	if (current->personality & ADDR_COMPAT_LAYOUT)
+		return 1;
+
+	if (rlimit(RLIMIT_STACK) == RLIM_INFINITY)
+		return 1;
+
+	return sysctl_legacy_va_layout;
+}
+
+static unsigned long mmap_base(unsigned long rnd)
+{
+	unsigned long gap = rlimit(RLIMIT_STACK);
+
+	if (gap < MIN_GAP)
+		gap = MIN_GAP;
+	else if (gap > MAX_GAP)
+		gap = MAX_GAP;
+
+	return PAGE_ALIGN(TASK_SIZE - gap - rnd);
+}
+
 /*
  * We need to ensure that shared mappings are correctly aligned to
  * avoid aliasing issues with VIPT caches.  We need to ensure that
@@ -68,13 +107,9 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	if (len > mm->cached_hole_size) {
 	        start_addr = addr = mm->free_area_cache;
 	} else {
-	        start_addr = addr = TASK_UNMAPPED_BASE;
+	        start_addr = addr = mm->mmap_base;
 	        mm->cached_hole_size = 0;
 	}
-	/* 8 bits of randomness in 20 address space bits */
-	if ((current->flags & PF_RANDOMIZE) &&
-	    !(current->personality & ADDR_NO_RANDOMIZE))
-		addr += (get_random_int() % (1 << 8)) << PAGE_SHIFT;
 
 full_search:
 	if (do_align)
@@ -111,6 +146,134 @@ full_search:
 	}
 }
 
+unsigned long
+arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
+			const unsigned long len, const unsigned long pgoff,
+			const unsigned long flags)
+{
+	struct vm_area_struct *vma;
+	struct mm_struct *mm = current->mm;
+	unsigned long addr = addr0;
+	int do_align = 0;
+	int aliasing = cache_is_vipt_aliasing();
+
+	/*
+	 * We only need to do colour alignment if either the I or D
+	 * caches alias.
+	 */
+	if (aliasing)
+		do_align = filp || (flags & MAP_SHARED);
+
+	/* requested length too big for entire address space */
+	if (len > TASK_SIZE)
+		return -ENOMEM;
+
+	if (flags & MAP_FIXED) {
+		if (aliasing && flags & MAP_SHARED &&
+		    (addr - (pgoff << PAGE_SHIFT)) & (SHMLBA - 1))
+			return -EINVAL;
+		return addr;
+	}
+
+	/* requesting a specific address */
+	if (addr) {
+		if (do_align)
+			addr = COLOUR_ALIGN(addr, pgoff);
+		else
+			addr = PAGE_ALIGN(addr);
+		vma = find_vma(mm, addr);
+		if (TASK_SIZE - len >= addr &&
+				(!vma || addr + len <= vma->vm_start))
+			return addr;
+	}
+
+	/* check if free_area_cache is useful for us */
+	if (len <= mm->cached_hole_size) {
+		mm->cached_hole_size = 0;
+		mm->free_area_cache = mm->mmap_base;
+	}
+
+	/* either no address requested or can't fit in requested address hole */
+	addr = mm->free_area_cache;
+	if (do_align) {
+		unsigned long base = COLOUR_ALIGN_DOWN(addr - len, pgoff);
+		addr = base + len;
+	}
+
+	/* make sure it can fit in the remaining address space */
+	if (addr > len) {
+		vma = find_vma(mm, addr-len);
+		if (!vma || addr <= vma->vm_start)
+			/* remember the address as a hint for next time */
+			return (mm->free_area_cache = addr-len);
+	}
+
+	if (mm->mmap_base < len)
+		goto bottomup;
+
+	addr = mm->mmap_base - len;
+	if (do_align)
+		addr = COLOUR_ALIGN_DOWN(addr, pgoff);
+
+	do {
+		/*
+		 * Lookup failure means no vma is above this address,
+		 * else if new region fits below vma->vm_start,
+		 * return with success:
+		 */
+		vma = find_vma(mm, addr);
+		if (!vma || addr+len <= vma->vm_start)
+			/* remember the address as a hint for next time */
+			return (mm->free_area_cache = addr);
+
+		/* remember the largest hole we saw so far */
+		if (addr + mm->cached_hole_size < vma->vm_start)
+			mm->cached_hole_size = vma->vm_start - addr;
+
+		/* try just below the current vma->vm_start */
+		addr = vma->vm_start - len;
+		if (do_align)
+			addr = COLOUR_ALIGN_DOWN(addr, pgoff);
+	} while (len < vma->vm_start);
+
+bottomup:
+	/*
+	 * A failed mmap() very likely causes application failure,
+	 * so fall back to the bottom-up function here. This scenario
+	 * can happen with large stack limits and large mmap()
+	 * allocations.
+	 */
+	mm->cached_hole_size = ~0UL;
+	mm->free_area_cache = TASK_UNMAPPED_BASE;
+	addr = arch_get_unmapped_area(filp, addr0, len, pgoff, flags);
+	/*
+	 * Restore the topdown base:
+	 */
+	mm->free_area_cache = mm->mmap_base;
+	mm->cached_hole_size = ~0UL;
+
+	return addr;
+}
+
+void arch_pick_mmap_layout(struct mm_struct *mm)
+{
+	unsigned long random_factor = 0UL;
+
+	/* 8 bits of randomness in 20 address space bits */
+	if ((current->flags & PF_RANDOMIZE) &&
+	    !(current->personality & ADDR_NO_RANDOMIZE))
+		random_factor = (get_random_int() % (1 << 8)) << PAGE_SHIFT;
+
+	if (mmap_is_legacy()) {
+		mm->mmap_base = TASK_UNMAPPED_BASE + random_factor;
+		mm->get_unmapped_area = arch_get_unmapped_area;
+		mm->unmap_area = arch_unmap_area;
+	} else {
+		mm->mmap_base = mmap_base(random_factor);
+		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
+		mm->unmap_area = arch_unmap_area_topdown;
+	}
+}
 
 /*
  * You really shouldn't be using read() or write() on /dev/mem.  This
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index e70a73731ea..69a98a4204a 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -284,6 +284,7 @@ __v7_ca5mp_setup:
 __v7_ca9mp_setup:
 	mov	r10, #(1 << 0)			@ TLB ops broadcasting
 	b	1f
+__v7_ca7mp_setup:
 __v7_ca15mp_setup:
 	mov	r10, #0
 1:
@@ -465,6 +466,16 @@ __v7_ca5mp_proc_info:
 	.size	__v7_ca5mp_proc_info, . - __v7_ca5mp_proc_info
 
 	/*
+	 * ARM Ltd. Cortex A7 processor.
+	 */
+	.type	__v7_ca7mp_proc_info, #object
+__v7_ca7mp_proc_info:
+	.long	0x410fc070
+	.long	0xff0ffff0
+	__v7_proc __v7_ca7mp_setup, hwcaps = HWCAP_IDIV
+	.size	__v7_ca7mp_proc_info, . - __v7_ca7mp_proc_info
+
+	/*
 	 * ARM Ltd. Cortex A9 processor.
 	 */
 	.type   __v7_ca9mp_proc_info, #object