ARM: 7169/1: topdown mmap support

Similar to other architectures, this adds topdown mmap support in user
process address space allocation policy. This allows mmap sizes greater
than 2GB. This support is largely copied from MIPS and the generic
implementations.

The address space randomization is moved into arch_pick_mmap_layout.

Tested on V-Express with ubuntu and a mmap test from here:
https://bugs.launchpad.net/bugs/861296

Signed-off-by: Rob Herring <rob.herring@calxeda.com>
Acked-by: Nicolas Pitre <nico@linaro.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

1 files changed, 168 insertions, 5 deletions

diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c
index 44b628e..ce8cb19 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