mm: always expand the stack with the mmap write lock held

This finishes the job of always holding the mmap write lock when
extending the user stack vma, and removes the 'write_locked' argument
from the vm helper functions again.

For some cases, we just avoid expanding the stack at all: drivers and
page pinning really shouldn't be extending any stacks.  Let's see if any
strange users really wanted that.

It's worth noting that architectures that weren't converted to the new
lock_mm_and_find_vma() helper function are left using the legacy
"expand_stack()" function, but it has been changed to drop the mmap_lock
and take it for writing while expanding the vma.  This makes it fairly
straightforward to convert the remaining architectures.

As a result of dropping and re-taking the lock, the calling conventions
for this function have also changed, since the old vma may no longer be
valid.  So it will now return the new vma if successful, and NULL - and
the lock dropped - if the area could not be extended.

Tested-by: Vegard Nossum <vegard.nossum@oracle.com>
Tested-by: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de> # ia64
Tested-by: Frank Scheiner <frank.scheiner@web.de> # ia64
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

8 files changed, 43 insertions, 59 deletions

diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c
index 85c4d9ac8686..5458b52b4009 100644
--- a/arch/ia64/mm/fault.c
+++ b/arch/ia64/mm/fault.c
@@ -110,10 +110,12 @@ retry:
          * register backing store that needs to expand upwards, in
          * this case vma will be null, but prev_vma will ne non-null
          */
-        if (( !vma && prev_vma ) || (address < vma->vm_start) )
-		goto check_expansion;
+        if (( !vma && prev_vma ) || (address < vma->vm_start) ) {
+		vma = expand_stack(mm, address);
+		if (!vma)
+			goto bad_area_nosemaphore;
+	}
 
-  good_area:
 	code = SEGV_ACCERR;
 
 	/* OK, we've got a good vm_area for this memory area.  Check the access permissions: */
@@ -177,35 +179,9 @@ retry:
 	mmap_read_unlock(mm);
 	return;
 
-  check_expansion:
-	if (!(prev_vma && (prev_vma->vm_flags & VM_GROWSUP) && (address == prev_vma->vm_end))) {
-		if (!vma)
-			goto bad_area;
-		if (!(vma->vm_flags & VM_GROWSDOWN))
-			goto bad_area;
-		if (REGION_NUMBER(address) != REGION_NUMBER(vma->vm_start)
-		    || REGION_OFFSET(address) >= RGN_MAP_LIMIT)
-			goto bad_area;
-		if (expand_stack(vma, address))
-			goto bad_area;
-	} else {
-		vma = prev_vma;
-		if (REGION_NUMBER(address) != REGION_NUMBER(vma->vm_start)
-		    || REGION_OFFSET(address) >= RGN_MAP_LIMIT)
-			goto bad_area;
-		/*
-		 * Since the register backing store is accessed sequentially,
-		 * we disallow growing it by more than a page at a time.
-		 */
-		if (address > vma->vm_end + PAGE_SIZE - sizeof(long))
-			goto bad_area;
-		if (expand_upwards(vma, address))
-			goto bad_area;
-	}
-	goto good_area;
-
   bad_area:
 	mmap_read_unlock(mm);
+  bad_area_nosemaphore:
 	if ((isr & IA64_ISR_SP)
 	    || ((isr & IA64_ISR_NA) && (isr & IA64_ISR_CODE_MASK) == IA64_ISR_CODE_LFETCH))
 	{
diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index 228128e45c67..c290c5c0cfb9 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -105,8 +105,9 @@ retry:
 		if (address + 256 < rdusp())
 			goto map_err;
 	}
-	if (expand_stack(vma, address))
-		goto map_err;
+	vma = expand_stack(mm, address);
+	if (!vma)
+		goto map_err_nosemaphore;
 
 /*
  * Ok, we have a good vm_area for this memory access, so
@@ -196,10 +197,12 @@ bus_err:
 	goto send_sig;
 
 map_err:
+	mmap_read_unlock(mm);
+map_err_nosemaphore:
 	current->thread.signo = SIGSEGV;
 	current->thread.code = SEGV_MAPERR;
 	current->thread.faddr = address;
-	goto send_sig;
+	return send_fault_sig(regs);
 
 acc_err:
 	current->thread.signo = SIGSEGV;
diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c
index 687714db6f4d..d3c3c33b73a6 100644
--- a/arch/microblaze/mm/fault.c
+++ b/arch/microblaze/mm/fault.c
@@ -192,8 +192,9 @@ retry:
 			&& (kernel_mode(regs) || !store_updates_sp(regs)))
 				goto bad_area;
 	}
-	if (expand_stack(vma, address))
-		goto bad_area;
+	vma = expand_stack(mm, address);
+	if (!vma)
+		goto bad_area_nosemaphore;
 
 good_area:
 	code = SEGV_ACCERR;
diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c
index 6734fee3134f..a9dcd4381d1a 100644
--- a/arch/openrisc/mm/fault.c
+++ b/arch/openrisc/mm/fault.c
@@ -127,8 +127,9 @@ retry:
 		if (address + PAGE_SIZE < regs->sp)
 			goto bad_area;
 	}
-	if (expand_stack(vma, address))
-		goto bad_area;
+	vma = expand_stack(mm, address);
+	if (!vma)
+		goto bad_area_nosemaphore;
 
 	/*
 	 * Ok, we have a good vm_area for this memory access, so
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index 6941fdbf2517..6e894afa4249 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -288,15 +288,19 @@ void do_page_fault(struct pt_regs *regs, unsigned long code,
 retry:
 	mmap_read_lock(mm);
 	vma = find_vma_prev(mm, address, &prev_vma);
-	if (!vma || address < vma->vm_start)
-		goto check_expansion;
+	if (!vma || address < vma->vm_start) {
+		if (!prev || !(prev->vm_flags & VM_GROWSUP))
+			goto bad_area;
+		vma = expand_stack(mm, address);
+		if (!vma)
+			goto bad_area_nosemaphore;
+	}
+
 /*
  * Ok, we have a good vm_area for this memory access. We still need to
  * check the access permissions.
  */
 
-good_area:
-
 	if ((vma->vm_flags & acc_type) != acc_type)
 		goto bad_area;
 
@@ -347,17 +351,13 @@ good_area:
 	mmap_read_unlock(mm);
 	return;
 
-check_expansion:
-	vma = prev_vma;
-	if (vma && (expand_stack(vma, address) == 0))
-		goto good_area;
-
 /*
  * Something tried to access memory that isn't in our memory map..
  */
 bad_area:
 	mmap_read_unlock(mm);
 
+bad_area_nosemaphore:
 	if (user_mode(regs)) {
 		int signo, si_code;
 
@@ -449,7 +449,7 @@ handle_nadtlb_fault(struct pt_regs *regs)
 {
 	unsigned long insn = regs->iir;
 	int breg, treg, xreg, val = 0;
-	struct vm_area_struct *vma, *prev_vma;
+	struct vm_area_struct *vma;
 	struct task_struct *tsk;
 	struct mm_struct *mm;
 	unsigned long address;
@@ -485,7 +485,7 @@ handle_nadtlb_fault(struct pt_regs *regs)
 				/* Search for VMA */
 				address = regs->ior;
 				mmap_read_lock(mm);
-				vma = find_vma_prev(mm, address, &prev_vma);
+				vma = vma_lookup(mm, address);
 				mmap_read_unlock(mm);
 
 				/*
@@ -494,7 +494,6 @@ handle_nadtlb_fault(struct pt_regs *regs)
 				 */
 				acc_type = (insn & 0x40) ? VM_WRITE : VM_READ;
 				if (vma
-				    && address >= vma->vm_start
 				    && (vma->vm_flags & acc_type) == acc_type)
 					val = 1;
 			}
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index b65144c392b0..dbe8394234e2 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -457,8 +457,9 @@ retry:
 	if (unlikely(vma->vm_start > address)) {
 		if (!(vma->vm_flags & VM_GROWSDOWN))
 			goto out_up;
-		if (expand_stack(vma, address))
-			goto out_up;
+		vma = expand_stack(mm, address);
+		if (!vma)
+			goto out;
 	}
 
 	/*
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index d91305de694c..69ff07bc6c07 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -383,8 +383,9 @@ continue_fault:
 				goto bad_area;
 		}
 	}
-	if (expand_stack(vma, address))
-		goto bad_area;
+	vma = expand_stack(mm, address);
+	if (!vma)
+		goto bad_area_nosemaphore;
 	/*
 	 * Ok, we have a good vm_area for this memory access, so
 	 * we can handle it..
@@ -487,8 +488,9 @@ exit_exception:
 	 * Fix it, but check if it's kernel or user first..
 	 */
 bad_area:
-	insn = get_fault_insn(regs, insn);
 	mmap_read_unlock(mm);
+bad_area_nosemaphore:
+	insn = get_fault_insn(regs, insn);
 
 handle_kernel_fault:
 	do_kernel_fault(regs, si_code, fault_code, insn, address);
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index d3ce21c4ca32..6d8ae86ae978 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -47,14 +47,15 @@ retry:
 	vma = find_vma(mm, address);
 	if (!vma)
 		goto out;
-	else if (vma->vm_start <= address)
+	if (vma->vm_start <= address)
 		goto good_area;
-	else if (!(vma->vm_flags & VM_GROWSDOWN))
+	if (!(vma->vm_flags & VM_GROWSDOWN))
 		goto out;
-	else if (is_user && !ARCH_IS_STACKGROW(address))
-		goto out;
-	else if (expand_stack(vma, address))
+	if (is_user && !ARCH_IS_STACKGROW(address))
 		goto out;
+	vma = expand_stack(mm, address);
+	if (!vma)
+		goto out_nosemaphore;
 
 good_area:
 	*code_out = SEGV_ACCERR;