powerpc/mm: Enable mappings above 128TB

Not all user space application is ready to handle wide addresses. It's
known that at least some JIT compilers use higher bits in pointers to
encode their information. It collides with valid pointers with 512TB
addresses and leads to crashes.

To mitigate this, we are not going to allocate virtual address space
above 128TB by default.

But userspace can ask for allocation from full address space by
specifying hint address (with or without MAP_FIXED) above 128TB.

If hint address set above 128TB, but MAP_FIXED is not specified, we try
to look for unmapped area by specified address. If it's already
occupied, we look for unmapped area in *full* address space, rather than
from 128TB window.

This approach helps to easily make application's memory allocator aware
about large address space without manually tracking allocated virtual
address space.

This is going to be a per mmap decision. ie, we can have some mmaps with
larger addresses and other that do not.

A sample memory layout looks like:

  10000000-10010000 r-xp 00000000 fc:00 9057045          /home/max_addr_512TB
  10010000-10020000 r--p 00000000 fc:00 9057045          /home/max_addr_512TB
  10020000-10030000 rw-p 00010000 fc:00 9057045          /home/max_addr_512TB
  10029630000-10029660000 rw-p 00000000 00:00 0          [heap]
  7fff834a0000-7fff834b0000 rw-p 00000000 00:00 0
  7fff834b0000-7fff83670000 r-xp 00000000 fc:00 9177190  /lib/powerpc64le-linux-gnu/libc-2.23.so
  7fff83670000-7fff83680000 r--p 001b0000 fc:00 9177190  /lib/powerpc64le-linux-gnu/libc-2.23.so
  7fff83680000-7fff83690000 rw-p 001c0000 fc:00 9177190  /lib/powerpc64le-linux-gnu/libc-2.23.so
  7fff83690000-7fff836a0000 rw-p 00000000 00:00 0
  7fff836a0000-7fff836c0000 r-xp 00000000 00:00 0        [vdso]
  7fff836c0000-7fff83700000 r-xp 00000000 fc:00 9177193  /lib/powerpc64le-linux-gnu/ld-2.23.so
  7fff83700000-7fff83710000 r--p 00030000 fc:00 9177193  /lib/powerpc64le-linux-gnu/ld-2.23.so
  7fff83710000-7fff83720000 rw-p 00040000 fc:00 9177193  /lib/powerpc64le-linux-gnu/ld-2.23.so
  7fffdccf0000-7fffdcd20000 rw-p 00000000 00:00 0        [stack]
  1000000000000-1000000010000 rw-p 00000000 00:00 0
  1ffff83710000-1ffff83720000 rw-p 00000000 00:00 0

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

1 files changed, 21 insertions, 11 deletions

diff --git a/arch/powerpc/mm/mmap.c b/arch/powerpc/mm/mmap.c
index 6e9fead92969..b2111baa0da6 100644
--- a/arch/powerpc/mm/mmap.c
+++ b/arch/powerpc/mm/mmap.c
@@ -79,7 +79,7 @@ static inline unsigned long mmap_base(unsigned long rnd)
 	else if (gap > MAX_GAP)
 		gap = MAX_GAP;
 
-	return PAGE_ALIGN(TASK_SIZE - gap - rnd);
+	return PAGE_ALIGN(DEFAULT_MAP_WINDOW - gap - rnd);
 }
 
 #ifdef CONFIG_PPC_RADIX_MMU
@@ -97,6 +97,9 @@ radix__arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	struct vm_area_struct *vma;
 	struct vm_unmapped_area_info info;
 
+	if (unlikely(addr > mm->context.addr_limit && addr < TASK_SIZE))
+		mm->context.addr_limit = TASK_SIZE;
+
 	if (len > mm->context.addr_limit - mmap_min_addr)
 		return -ENOMEM;
 
@@ -114,8 +117,13 @@ radix__arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	info.flags = 0;
 	info.length = len;
 	info.low_limit = mm->mmap_base;
-	info.high_limit = mm->context.addr_limit;
 	info.align_mask = 0;
+
+	if (unlikely(addr > DEFAULT_MAP_WINDOW))
+		info.high_limit = mm->context.addr_limit;
+	else
+		info.high_limit = DEFAULT_MAP_WINDOW;
+
 	return vm_unmapped_area(&info);
 }
 
@@ -131,6 +139,9 @@ radix__arch_get_unmapped_area_topdown(struct file *filp,
 	unsigned long addr = addr0;
 	struct vm_unmapped_area_info info;
 
+	if (unlikely(addr > mm->context.addr_limit && addr < TASK_SIZE))
+		mm->context.addr_limit = TASK_SIZE;
+
 	/* requested length too big for entire address space */
 	if (len > mm->context.addr_limit - mmap_min_addr)
 		return -ENOMEM;
@@ -152,7 +163,14 @@ radix__arch_get_unmapped_area_topdown(struct file *filp,
 	info.low_limit = max(PAGE_SIZE, mmap_min_addr);
 	info.high_limit = mm->mmap_base;
 	info.align_mask = 0;
+
+	if (addr > DEFAULT_MAP_WINDOW)
+		info.high_limit += mm->context.addr_limit - DEFAULT_MAP_WINDOW;
+
 	addr = vm_unmapped_area(&info);
+	if (!(addr & ~PAGE_MASK))
+		return addr;
+	VM_BUG_ON(addr != -ENOMEM);
 
 	/*
 	 * A failed mmap() very likely causes application failure,
@@ -160,15 +178,7 @@ radix__arch_get_unmapped_area_topdown(struct file *filp,
 	 * can happen with large stack limits and large mmap()
 	 * allocations.
 	 */
-	if (addr & ~PAGE_MASK) {
-		VM_BUG_ON(addr != -ENOMEM);
-		info.flags = 0;
-		info.low_limit = TASK_UNMAPPED_BASE;
-		info.high_limit = mm->context.addr_limit;
-		addr = vm_unmapped_area(&info);
-	}
-
-	return addr;
+	return radix__arch_get_unmapped_area(filp, addr0, len, pgoff, flags);
 }
 
 static void radix__arch_pick_mmap_layout(struct mm_struct *mm,