From d833049bd20570cbbadeb5228c579f9f3aaa4e03 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill@shutemov.name>
Date: Thu, 12 Apr 2012 12:49:11 -0700
Subject: memcg: fix broken boolen expression

action != CPU_DEAD || action != CPU_DEAD_FROZEN is always true.

Signed-off-by: Kirill A. Shutemov <kirill@shutemov.name>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/memcontrol.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'mm')

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 7d698df4a067..ea1e879b2db6 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2165,7 +2165,7 @@ static int __cpuinit memcg_cpu_hotplug_callback(struct notifier_block *nb,
 	if (action == CPU_ONLINE)
 		return NOTIFY_OK;
 
-	if ((action != CPU_DEAD) || action != CPU_DEAD_FROZEN)
+	if (action != CPU_DEAD && action != CPU_DEAD_FROZEN)
 		return NOTIFY_OK;
 
 	for_each_mem_cgroup(iter)
-- 
cgit v1.2.3


From 569530fb1b40ab2d2ca147ee79898ac807ebdf90 Mon Sep 17 00:00:00 2001
From: Glauber Costa <glommer@parallels.com>
Date: Thu, 12 Apr 2012 12:49:13 -0700
Subject: memcg: do not open code accesses to res_counter members

We should use the accessor res_counter_read_u64 for that.

Although a purely cosmetic change is sometimes better delayed, to avoid
conflicting with other people's work, we are starting to have people
touching this code as well, and reproducing the open code behavior
because that's the standard =)

Time to fix it, then.

Signed-off-by: Glauber Costa <glommer@parallels.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/memcontrol.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'mm')

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ea1e879b2db6..a7165a60d0a7 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3763,7 +3763,7 @@ move_account:
 			goto try_to_free;
 		cond_resched();
 	/* "ret" should also be checked to ensure all lists are empty. */
-	} while (memcg->res.usage > 0 || ret);
+	} while (res_counter_read_u64(&memcg->res, RES_USAGE) > 0 || ret);
 out:
 	css_put(&memcg->css);
 	return ret;
@@ -3778,7 +3778,7 @@ try_to_free:
 	lru_add_drain_all();
 	/* try to free all pages in this cgroup */
 	shrink = 1;
-	while (nr_retries && memcg->res.usage > 0) {
+	while (nr_retries && res_counter_read_u64(&memcg->res, RES_USAGE) > 0) {
 		int progress;
 
 		if (signal_pending(current)) {
-- 
cgit v1.2.3


From 66aebce747eaf9bc456bf1f1b217d8db843031d0 Mon Sep 17 00:00:00 2001
From: Chris Metcalf <cmetcalf@tilera.com>
Date: Thu, 12 Apr 2012 12:49:15 -0700
Subject: hugetlb: fix race condition in hugetlb_fault()

The race is as follows:

Suppose a multi-threaded task forks a new process (on cpu A), thus
bumping up the ref count on all the pages.  While the fork is occurring
(and thus we have marked all the PTEs as read-only), another thread in
the original process (on cpu B) tries to write to a huge page, taking an
access violation from the write-protect and calling hugetlb_cow().  Now,
suppose the fork() fails.  It will undo the COW and decrement the ref
count on the pages, so the ref count on the huge page drops back to 1.
Meanwhile hugetlb_cow() also decrements the ref count by one on the
original page, since the original address space doesn't need it any
more, having copied a new page to replace the original page.  This
leaves the ref count at zero, and when we call unlock_page(), we panic.

	fork on CPU A				fault on CPU B
	=============				==============
	...
	down_write(&parent->mmap_sem);
	down_write_nested(&child->mmap_sem);
	...
	while duplicating vmas
		if error
			break;
	...
	up_write(&child->mmap_sem);
	up_write(&parent->mmap_sem);		...
						down_read(&parent->mmap_sem);
						...
						lock_page(page);
						handle COW
						page_mapcount(old_page) == 2
						alloc and prepare new_page
	...
	handle error
	page_remove_rmap(page);
	put_page(page);
	...
						fold new_page into pte
						page_remove_rmap(page);
						put_page(page);
						...
				oops ==>	unlock_page(page);
						up_read(&parent->mmap_sem);

The solution is to take an extra reference to the page while we are
holding the lock on it.

Signed-off-by: Chris Metcalf <cmetcalf@tilera.com>
Cc: Hillf Danton <dhillf@gmail.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/hugetlb.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'mm')

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index b8ce6f450956..cd65cb19c941 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2791,6 +2791,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * so no worry about deadlock.
 	 */
 	page = pte_page(entry);
+	get_page(page);
 	if (page != pagecache_page)
 		lock_page(page);
 
@@ -2822,6 +2823,7 @@ out_page_table_lock:
 	}
 	if (page != pagecache_page)
 		unlock_page(page);
+	put_page(page);
 
 out_mutex:
 	mutex_unlock(&hugetlb_instantiation_mutex);
-- 
cgit v1.2.3


From 41c93088127df2579e8ca64010929ec9e41d5543 Mon Sep 17 00:00:00 2001
From: Ying Han <yinghan@google.com>
Date: Thu, 12 Apr 2012 12:49:16 -0700
Subject: Revert "mm: vmscan: fix misused nr_reclaimed in
 shrink_mem_cgroup_zone()"

This reverts commit c38446cc65e1f2b3eb8630c53943b94c4f65f670.

Before the commit, the code makes senses to me but not after the commit.
The "nr_reclaimed" is the number of pages reclaimed by scanning through
the memcg's lru lists.  The "nr_to_reclaim" is the target value for the
whole function.  For example, we like to early break the reclaim if
reclaimed 32 pages under direct reclaim (not DEF_PRIORITY).

After the reverted commit, the target "nr_to_reclaim" is decremented each
time by "nr_reclaimed" but we still use it to compare the "nr_reclaimed".
It just doesn't make sense to me...

Signed-off-by: Ying Han <yinghan@google.com>
Acked-by: Hugh Dickins <hughd@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Hillf Danton <dhillf@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/vmscan.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

(limited to 'mm')

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 33c332bbab73..1a518684a32f 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2107,12 +2107,7 @@ restart:
 		 * with multiple processes reclaiming pages, the total
 		 * freeing target can get unreasonably large.
 		 */
-		if (nr_reclaimed >= nr_to_reclaim)
-			nr_to_reclaim = 0;
-		else
-			nr_to_reclaim -= nr_reclaimed;
-
-		if (!nr_to_reclaim && priority < DEF_PRIORITY)
+		if (nr_reclaimed >= nr_to_reclaim && priority < DEF_PRIORITY)
 			break;
 	}
 	blk_finish_plug(&plug);
-- 
cgit v1.2.3


From 9b7f43afd417a6feb80841d30ced4051c362eb5d Mon Sep 17 00:00:00 2001
From: Hugh Dickins <hughd@google.com>
Date: Wed, 18 Apr 2012 23:34:46 -0700
Subject: memcg: fix Bad page state after replace_page_cache

My 9ce70c0240d0 "memcg: fix deadlock by inverting lrucare nesting" put a
nasty little bug into v3.3's version of mem_cgroup_replace_page_cache(),
sometimes used for FUSE.  Replacing __mem_cgroup_commit_charge_lrucare()
by __mem_cgroup_commit_charge(), I used the "pc" pointer set up earlier:
but it's for oldpage, and needs now to be for newpage.  Once oldpage was
freed, its PageCgroupUsed bit (cleared above but set again here) caused
"Bad page state" messages - and perhaps worse, being missed from newpage.
(I didn't find this by using FUSE, but in reusing the function for tmpfs.)

Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: stable@vger.kernel.org [v3.3 only]
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/memcontrol.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'mm')

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index a7165a60d0a7..b868def9bcc1 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3392,6 +3392,7 @@ void mem_cgroup_replace_page_cache(struct page *oldpage,
 	 * the newpage may be on LRU(or pagevec for LRU) already. We lock
 	 * LRU while we overwrite pc->mem_cgroup.
 	 */
+	pc = lookup_page_cgroup(newpage);
 	__mem_cgroup_commit_charge(memcg, newpage, 1, pc, type, true);
 }
 
-- 
cgit v1.2.3


From b3dc627cabb33fc95f93da78457770c1b2a364d2 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Fri, 20 Apr 2012 08:31:34 -0700
Subject: memblock: memblock should be able to handle zero length operations

Commit 24aa07882b ("memblock, x86: Replace memblock_x86_reserve/
free_range() with generic ones") replaced x86 specific memblock
operations with the generic ones; unfortunately, it lost zero length
operation handling in the process making the kernel panic if somebody
tries to reserve zero length area.

There isn't much to be gained by being cranky to zero length operations
and panicking is almost the worst response.  Drop the BUG_ON() in
memblock_reserve() and update memblock_add_region/isolate_range() so
that all zero length operations are handled as noops.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: stable@vger.kernel.org
Reported-by: Valere Monseur <valere.monseur@ymail.com>
Bisected-by: Joseph Freeman <jfree143dev@gmail.com>
Tested-by: Joseph Freeman <jfree143dev@gmail.com>
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=43098
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/memblock.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

(limited to 'mm')

diff --git a/mm/memblock.c b/mm/memblock.c
index 99f285599501..a44eab3157f8 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -330,6 +330,9 @@ static int __init_memblock memblock_add_region(struct memblock_type *type,
 	phys_addr_t end = base + memblock_cap_size(base, &size);
 	int i, nr_new;
 
+	if (!size)
+		return 0;
+
 	/* special case for empty array */
 	if (type->regions[0].size == 0) {
 		WARN_ON(type->cnt != 1 || type->total_size);
@@ -430,6 +433,9 @@ static int __init_memblock memblock_isolate_range(struct memblock_type *type,
 
 	*start_rgn = *end_rgn = 0;
 
+	if (!size)
+		return 0;
+
 	/* we'll create at most two more regions */
 	while (type->cnt + 2 > type->max)
 		if (memblock_double_array(type) < 0)
@@ -514,7 +520,6 @@ int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size)
 		     (unsigned long long)base,
 		     (unsigned long long)base + size,
 		     (void *)_RET_IP_);
-	BUG_ON(0 == size);
 
 	return memblock_add_region(_rgn, base, size, MAX_NUMNODES);
 }
-- 
cgit v1.2.3


From e4eb1ff61b323d6141614e5458a1f53c7046ff8e Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Fri, 20 Apr 2012 15:35:40 -0700
Subject: VM: add "vm_brk()" helper function

It does the same thing as "do_brk()", except it handles the VM locking
too.

It turns out that all external callers want that anyway, so we can make
do_brk() static to just mm/mmap.c while at it.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/ia32/ia32_aout.c | 20 +++++---------------
 fs/binfmt_aout.c          | 20 +++++---------------
 fs/binfmt_elf.c           | 15 ++++-----------
 include/linux/mm.h        |  3 ++-
 mm/mmap.c                 | 16 ++++++++++++++--
 mm/nommu.c                |  2 +-
 6 files changed, 31 insertions(+), 45 deletions(-)

(limited to 'mm')

diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index d511d951a052..b6817ee9033f 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -119,9 +119,7 @@ static void set_brk(unsigned long start, unsigned long end)
 	end = PAGE_ALIGN(end);
 	if (end <= start)
 		return;
-	down_write(&current->mm->mmap_sem);
-	do_brk(start, end - start);
-	up_write(&current->mm->mmap_sem);
+	vm_brk(start, end - start);
 }
 
 #ifdef CORE_DUMP
@@ -332,9 +330,7 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 		pos = 32;
 		map_size = ex.a_text+ex.a_data;
 
-		down_write(&current->mm->mmap_sem);
-		error = do_brk(text_addr & PAGE_MASK, map_size);
-		up_write(&current->mm->mmap_sem);
+		error = vm_brk(text_addr & PAGE_MASK, map_size);
 
 		if (error != (text_addr & PAGE_MASK)) {
 			send_sig(SIGKILL, current, 0);
@@ -373,9 +369,7 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 		if (!bprm->file->f_op->mmap || (fd_offset & ~PAGE_MASK) != 0) {
 			loff_t pos = fd_offset;
 
-			down_write(&current->mm->mmap_sem);
-			do_brk(N_TXTADDR(ex), ex.a_text+ex.a_data);
-			up_write(&current->mm->mmap_sem);
+			vm_brk(N_TXTADDR(ex), ex.a_text+ex.a_data);
 			bprm->file->f_op->read(bprm->file,
 					(char __user *)N_TXTADDR(ex),
 					ex.a_text+ex.a_data, &pos);
@@ -476,9 +470,7 @@ static int load_aout_library(struct file *file)
 			error_time = jiffies;
 		}
 #endif
-		down_write(&current->mm->mmap_sem);
-		do_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss);
-		up_write(&current->mm->mmap_sem);
+		vm_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss);
 
 		file->f_op->read(file, (char __user *)start_addr,
 			ex.a_text + ex.a_data, &pos);
@@ -503,9 +495,7 @@ static int load_aout_library(struct file *file)
 	len = PAGE_ALIGN(ex.a_text + ex.a_data);
 	bss = ex.a_text + ex.a_data + ex.a_bss;
 	if (bss > len) {
-		down_write(&current->mm->mmap_sem);
-		error = do_brk(start_addr + len, bss - len);
-		up_write(&current->mm->mmap_sem);
+		error = vm_brk(start_addr + len, bss - len);
 		retval = error;
 		if (error != start_addr + len)
 			goto out;
diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c
index 2eb12f13593d..88527492b917 100644
--- a/fs/binfmt_aout.c
+++ b/fs/binfmt_aout.c
@@ -50,9 +50,7 @@ static int set_brk(unsigned long start, unsigned long end)
 	end = PAGE_ALIGN(end);
 	if (end > start) {
 		unsigned long addr;
-		down_write(&current->mm->mmap_sem);
-		addr = do_brk(start, end - start);
-		up_write(&current->mm->mmap_sem);
+		addr = vm_brk(start, end - start);
 		if (BAD_ADDR(addr))
 			return addr;
 	}
@@ -280,9 +278,7 @@ static int load_aout_binary(struct linux_binprm * bprm, struct pt_regs * regs)
 		pos = 32;
 		map_size = ex.a_text+ex.a_data;
 #endif
-		down_write(&current->mm->mmap_sem);
-		error = do_brk(text_addr & PAGE_MASK, map_size);
-		up_write(&current->mm->mmap_sem);
+		error = vm_brk(text_addr & PAGE_MASK, map_size);
 		if (error != (text_addr & PAGE_MASK)) {
 			send_sig(SIGKILL, current, 0);
 			return error;
@@ -313,9 +309,7 @@ static int load_aout_binary(struct linux_binprm * bprm, struct pt_regs * regs)
 
 		if (!bprm->file->f_op->mmap||((fd_offset & ~PAGE_MASK) != 0)) {
 			loff_t pos = fd_offset;
-			down_write(&current->mm->mmap_sem);
-			do_brk(N_TXTADDR(ex), ex.a_text+ex.a_data);
-			up_write(&current->mm->mmap_sem);
+			vm_brk(N_TXTADDR(ex), ex.a_text+ex.a_data);
 			bprm->file->f_op->read(bprm->file,
 					(char __user *)N_TXTADDR(ex),
 					ex.a_text+ex.a_data, &pos);
@@ -412,9 +406,7 @@ static int load_aout_library(struct file *file)
 			       "N_TXTOFF is not page aligned. Please convert library: %s\n",
 			       file->f_path.dentry->d_name.name);
 		}
-		down_write(&current->mm->mmap_sem);
-		do_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss);
-		up_write(&current->mm->mmap_sem);
+		vm_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss);
 		
 		file->f_op->read(file, (char __user *)start_addr,
 			ex.a_text + ex.a_data, &pos);
@@ -438,9 +430,7 @@ static int load_aout_library(struct file *file)
 	len = PAGE_ALIGN(ex.a_text + ex.a_data);
 	bss = ex.a_text + ex.a_data + ex.a_bss;
 	if (bss > len) {
-		down_write(&current->mm->mmap_sem);
-		error = do_brk(start_addr + len, bss - len);
-		up_write(&current->mm->mmap_sem);
+		error = vm_brk(start_addr + len, bss - len);
 		retval = error;
 		if (error != start_addr + len)
 			goto out;
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 48ffb3dc610a..0708a0bf0ba9 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -82,9 +82,7 @@ static int set_brk(unsigned long start, unsigned long end)
 	end = ELF_PAGEALIGN(end);
 	if (end > start) {
 		unsigned long addr;
-		down_write(&current->mm->mmap_sem);
-		addr = do_brk(start, end - start);
-		up_write(&current->mm->mmap_sem);
+		addr = vm_brk(start, end - start);
 		if (BAD_ADDR(addr))
 			return addr;
 	}
@@ -514,9 +512,7 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
 		elf_bss = ELF_PAGESTART(elf_bss + ELF_MIN_ALIGN - 1);
 
 		/* Map the last of the bss segment */
-		down_write(&current->mm->mmap_sem);
-		error = do_brk(elf_bss, last_bss - elf_bss);
-		up_write(&current->mm->mmap_sem);
+		error = vm_brk(elf_bss, last_bss - elf_bss);
 		if (BAD_ADDR(error))
 			goto out_close;
 	}
@@ -1072,11 +1068,8 @@ static int load_elf_library(struct file *file)
 	len = ELF_PAGESTART(eppnt->p_filesz + eppnt->p_vaddr +
 			    ELF_MIN_ALIGN - 1);
 	bss = eppnt->p_memsz + eppnt->p_vaddr;
-	if (bss > len) {
-		down_write(&current->mm->mmap_sem);
-		do_brk(len, bss - len);
-		up_write(&current->mm->mmap_sem);
-	}
+	if (bss > len)
+		vm_brk(len, bss - len);
 	error = 0;
 
 out_free_ph:
diff --git a/include/linux/mm.h b/include/linux/mm.h
index d8738a464b94..bfee4ad6680b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1415,7 +1415,8 @@ out:
 
 extern int do_munmap(struct mm_struct *, unsigned long, size_t);
 
-extern unsigned long do_brk(unsigned long, unsigned long);
+/* These take the mm semaphore themselves */
+extern unsigned long vm_brk(unsigned long, unsigned long);
 
 /* truncate.c */
 extern void truncate_inode_pages(struct address_space *, loff_t);
diff --git a/mm/mmap.c b/mm/mmap.c
index a7bf6a31c9f6..df51891c8646 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -240,6 +240,8 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma)
 	return next;
 }
 
+static unsigned long do_brk(unsigned long addr, unsigned long len);
+
 SYSCALL_DEFINE1(brk, unsigned long, brk)
 {
 	unsigned long rlim, retval;
@@ -2136,7 +2138,7 @@ static inline void verify_mm_writelocked(struct mm_struct *mm)
  *  anonymous maps.  eventually we may be able to do some
  *  brk-specific accounting here.
  */
-unsigned long do_brk(unsigned long addr, unsigned long len)
+static unsigned long do_brk(unsigned long addr, unsigned long len)
 {
 	struct mm_struct * mm = current->mm;
 	struct vm_area_struct * vma, * prev;
@@ -2232,7 +2234,17 @@ out:
 	return addr;
 }
 
-EXPORT_SYMBOL(do_brk);
+unsigned long vm_brk(unsigned long addr, unsigned long len)
+{
+	struct mm_struct *mm = current->mm;
+	unsigned long ret;
+
+	down_write(&mm->mmap_sem);
+	ret = do_brk(addr, len);
+	up_write(&mm->mmap_sem);
+	return ret;
+}
+EXPORT_SYMBOL(vm_brk);
 
 /* Release all mmaps. */
 void exit_mmap(struct mm_struct *mm)
diff --git a/mm/nommu.c b/mm/nommu.c
index f59e170fceb4..634193324a6b 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1744,7 +1744,7 @@ void exit_mmap(struct mm_struct *mm)
 	kleave("");
 }
 
-unsigned long do_brk(unsigned long addr, unsigned long len)
+unsigned long vm_brk(unsigned long addr, unsigned long len)
 {
 	return -ENOMEM;
 }
-- 
cgit v1.2.3


From a46ef99d80817a167477ed1c8b4d90ee0c2e726f Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Fri, 20 Apr 2012 16:20:01 -0700
Subject: VM: add "vm_munmap()" helper function

Like the vm_brk() function, this is the same as "do_munmap()", except it
does the VM locking for the caller.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/ia64/kernel/perfmon.c       | 11 +++--------
 arch/sparc/kernel/sys_sparc_64.c |  7 +------
 arch/x86/kvm/x86.c               |  4 +---
 drivers/gpu/drm/i810/i810_dma.c  |  4 +---
 fs/aio.c                         |  7 ++-----
 include/linux/mm.h               |  1 +
 mm/mmap.c                        | 15 +++++++++------
 mm/nommu.c                       |  9 +++++++--
 8 files changed, 25 insertions(+), 33 deletions(-)

(limited to 'mm')

diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index 9d0fd7d5bb82..2777310b698b 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -605,9 +605,9 @@ pfm_unprotect_ctx_ctxsw(pfm_context_t *x, unsigned long f)
 }
 
 static inline unsigned int
-pfm_do_munmap(struct mm_struct *mm, unsigned long addr, size_t len, int acct)
+pfm_vm_munmap(struct mm_struct *mm, unsigned long addr, size_t len)
 {
-	return do_munmap(mm, addr, len);
+	return vm_munmap(mm, addr, len);
 }
 
 static inline unsigned long 
@@ -1473,13 +1473,8 @@ pfm_remove_smpl_mapping(struct task_struct *task, void *vaddr, unsigned long siz
 	/*
 	 * does the actual unmapping
 	 */
-	down_write(&task->mm->mmap_sem);
-
-	DPRINT(("down_write done smpl_vaddr=%p size=%lu\n", vaddr, size));
+	r = pfm_vm_munmap(task->mm, (unsigned long)vaddr, size);
 
-	r = pfm_do_munmap(task->mm, (unsigned long)vaddr, size, 0);
-
-	up_write(&task->mm->mmap_sem);
 	if (r !=0) {
 		printk(KERN_ERR "perfmon: [%d] unable to unmap sampling buffer @%p size=%lu\n", task_pid_nr(task), vaddr, size);
 	}
diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c
index 232df9949530..022e57aadf5d 100644
--- a/arch/sparc/kernel/sys_sparc_64.c
+++ b/arch/sparc/kernel/sys_sparc_64.c
@@ -566,15 +566,10 @@ out:
 
 SYSCALL_DEFINE2(64_munmap, unsigned long, addr, size_t, len)
 {
-	long ret;
-
 	if (invalid_64bit_range(addr, len))
 		return -EINVAL;
 
-	down_write(&current->mm->mmap_sem);
-	ret = do_munmap(current->mm, addr, len);
-	up_write(&current->mm->mmap_sem);
-	return ret;
+	return vm_munmap(current->mm, addr, len);
 }
 
 extern unsigned long do_mremap(unsigned long addr,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 4044ce0bf7c1..8beb9ce79364 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6366,10 +6366,8 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 	if (!user_alloc && !old.user_alloc && old.rmap && !npages) {
 		int ret;
 
-		down_write(&current->mm->mmap_sem);
-		ret = do_munmap(current->mm, old.userspace_addr,
+		ret = vm_munmap(current->mm, old.userspace_addr,
 				old.npages * PAGE_SIZE);
-		up_write(&current->mm->mmap_sem);
 		if (ret < 0)
 			printk(KERN_WARNING
 			       "kvm_vm_ioctl_set_memory_region: "
diff --git a/drivers/gpu/drm/i810/i810_dma.c b/drivers/gpu/drm/i810/i810_dma.c
index 2c8a60c3b98e..b85337f06fbf 100644
--- a/drivers/gpu/drm/i810/i810_dma.c
+++ b/drivers/gpu/drm/i810/i810_dma.c
@@ -157,11 +157,9 @@ static int i810_unmap_buffer(struct drm_buf *buf)
 	if (buf_priv->currently_mapped != I810_BUF_MAPPED)
 		return -EINVAL;
 
-	down_write(&current->mm->mmap_sem);
-	retcode = do_munmap(current->mm,
+	retcode = vm_munmap(current->mm,
 			    (unsigned long)buf_priv->virtual,
 			    (size_t) buf->total);
-	up_write(&current->mm->mmap_sem);
 
 	buf_priv->currently_mapped = I810_BUF_UNMAPPED;
 	buf_priv->virtual = NULL;
diff --git a/fs/aio.c b/fs/aio.c
index da887604dfc5..99bd790e8cd2 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -92,11 +92,8 @@ static void aio_free_ring(struct kioctx *ctx)
 	for (i=0; i<info->nr_pages; i++)
 		put_page(info->ring_pages[i]);
 
-	if (info->mmap_size) {
-		down_write(&ctx->mm->mmap_sem);
-		do_munmap(ctx->mm, info->mmap_base, info->mmap_size);
-		up_write(&ctx->mm->mmap_sem);
-	}
+	if (info->mmap_size)
+		vm_munmap(ctx->mm, info->mmap_base, info->mmap_size);
 
 	if (info->ring_pages && info->ring_pages != info->internal_pages)
 		kfree(info->ring_pages);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index bfee4ad6680b..cb61950a3aa1 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1417,6 +1417,7 @@ extern int do_munmap(struct mm_struct *, unsigned long, size_t);
 
 /* These take the mm semaphore themselves */
 extern unsigned long vm_brk(unsigned long, unsigned long);
+extern int vm_munmap(struct mm_struct *, unsigned long, size_t);
 
 /* truncate.c */
 extern void truncate_inode_pages(struct address_space *, loff_t);
diff --git a/mm/mmap.c b/mm/mmap.c
index df51891c8646..4af45f519f19 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2107,21 +2107,24 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
 
 	return 0;
 }
-
 EXPORT_SYMBOL(do_munmap);
 
-SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len)
+int vm_munmap(struct mm_struct *mm, unsigned long start, size_t len)
 {
 	int ret;
-	struct mm_struct *mm = current->mm;
-
-	profile_munmap(addr);
 
 	down_write(&mm->mmap_sem);
-	ret = do_munmap(mm, addr, len);
+	ret = do_munmap(mm, start, len);
 	up_write(&mm->mmap_sem);
 	return ret;
 }
+EXPORT_SYMBOL(vm_munmap);
+
+SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len)
+{
+	profile_munmap(addr);
+	return vm_munmap(current->mm, addr, len);
+}
 
 static inline void verify_mm_writelocked(struct mm_struct *mm)
 {
diff --git a/mm/nommu.c b/mm/nommu.c
index 634193324a6b..11a69b22bd4b 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1709,16 +1709,21 @@ erase_whole_vma:
 }
 EXPORT_SYMBOL(do_munmap);
 
-SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len)
+int vm_munmap(struct mm_struct *mm, unsigned long addr, size_t len)
 {
 	int ret;
-	struct mm_struct *mm = current->mm;
 
 	down_write(&mm->mmap_sem);
 	ret = do_munmap(mm, addr, len);
 	up_write(&mm->mmap_sem);
 	return ret;
 }
+EXPORT_SYMBOL(vm_munmap);
+
+SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len)
+{
+	return vm_munmap(current->mm, addr, len);
+}
 
 /*
  * release all the mappings made in a process's VM space
-- 
cgit v1.2.3


From 6be5ceb02e98eaf6cfc4f8b12a896d04023f340d Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Fri, 20 Apr 2012 17:13:58 -0700
Subject: VM: add "vm_mmap()" helper function

This continues the theme started with vm_brk() and vm_munmap():
vm_mmap() does the same thing as do_mmap(), but additionally does the
required VM locking.

This uninlines (and rewrites it to be clearer) do_mmap(), which sadly
duplicates it in mm/mmap.c and mm/nommu.c.  But that way we don't have
to export our internal do_mmap_pgoff() function.

Some day we hopefully don't have to export do_mmap() either, if all
modular users can become the simpler vm_mmap() instead.  We're actually
very close to that already, with the notable exception of the (broken)
use in i810, and a couple of stragglers in binfmt_elf.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/tile/kernel/single_step.c          |  4 +---
 arch/x86/ia32/ia32_aout.c               | 12 +++---------
 arch/x86/kvm/x86.c                      |  4 +---
 drivers/gpu/drm/drm_bufs.c              | 12 ++++--------
 drivers/gpu/drm/exynos/exynos_drm_gem.c |  4 +---
 drivers/gpu/drm/i810/i810_dma.c         |  1 +
 drivers/gpu/drm/i915/i915_gem.c         |  4 +---
 fs/binfmt_aout.c                        | 12 +++---------
 fs/binfmt_elf.c                         |  8 ++------
 fs/binfmt_elf_fdpic.c                   | 18 ++++--------------
 fs/binfmt_flat.c                        | 12 +++---------
 fs/binfmt_som.c                         | 12 +++---------
 include/linux/mm.h                      | 23 ++++++-----------------
 mm/mmap.c                               | 29 +++++++++++++++++++++++++++--
 mm/nommu.c                              | 29 +++++++++++++++++++++++++++--
 15 files changed, 87 insertions(+), 97 deletions(-)

(limited to 'mm')

diff --git a/arch/tile/kernel/single_step.c b/arch/tile/kernel/single_step.c
index 9efbc1391b3c..89529c9f0605 100644
--- a/arch/tile/kernel/single_step.c
+++ b/arch/tile/kernel/single_step.c
@@ -346,12 +346,10 @@ void single_step_once(struct pt_regs *regs)
 		}
 
 		/* allocate a cache line of writable, executable memory */
-		down_write(&current->mm->mmap_sem);
-		buffer = (void __user *) do_mmap(NULL, 0, 64,
+		buffer = (void __user *) vm_mmap(NULL, 0, 64,
 					  PROT_EXEC | PROT_READ | PROT_WRITE,
 					  MAP_PRIVATE | MAP_ANONYMOUS,
 					  0);
-		up_write(&current->mm->mmap_sem);
 
 		if (IS_ERR((void __force *)buffer)) {
 			kfree(state);
diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index b6817ee9033f..4824fb45560f 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -379,26 +379,22 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 			goto beyond_if;
 		}
 
-		down_write(&current->mm->mmap_sem);
-		error = do_mmap(bprm->file, N_TXTADDR(ex), ex.a_text,
+		error = vm_mmap(bprm->file, N_TXTADDR(ex), ex.a_text,
 				PROT_READ | PROT_EXEC,
 				MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE |
 				MAP_EXECUTABLE | MAP_32BIT,
 				fd_offset);
-		up_write(&current->mm->mmap_sem);
 
 		if (error != N_TXTADDR(ex)) {
 			send_sig(SIGKILL, current, 0);
 			return error;
 		}
 
-		down_write(&current->mm->mmap_sem);
-		error = do_mmap(bprm->file, N_DATADDR(ex), ex.a_data,
+		error = vm_mmap(bprm->file, N_DATADDR(ex), ex.a_data,
 				PROT_READ | PROT_WRITE | PROT_EXEC,
 				MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE |
 				MAP_EXECUTABLE | MAP_32BIT,
 				fd_offset + ex.a_text);
-		up_write(&current->mm->mmap_sem);
 		if (error != N_DATADDR(ex)) {
 			send_sig(SIGKILL, current, 0);
 			return error;
@@ -482,12 +478,10 @@ static int load_aout_library(struct file *file)
 		goto out;
 	}
 	/* Now use mmap to map the library into memory. */
-	down_write(&current->mm->mmap_sem);
-	error = do_mmap(file, start_addr, ex.a_text + ex.a_data,
+	error = vm_mmap(file, start_addr, ex.a_text + ex.a_data,
 			PROT_READ | PROT_WRITE | PROT_EXEC,
 			MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_32BIT,
 			N_TXTOFF(ex));
-	up_write(&current->mm->mmap_sem);
 	retval = error;
 	if (error != start_addr)
 		goto out;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 8beb9ce79364..1457be305fb1 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6336,13 +6336,11 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 		if (npages && !old.rmap) {
 			unsigned long userspace_addr;
 
-			down_write(&current->mm->mmap_sem);
-			userspace_addr = do_mmap(NULL, 0,
+			userspace_addr = vm_mmap(NULL, 0,
 						 npages * PAGE_SIZE,
 						 PROT_READ | PROT_WRITE,
 						 map_flags,
 						 0);
-			up_write(&current->mm->mmap_sem);
 
 			if (IS_ERR((void *)userspace_addr))
 				return PTR_ERR((void *)userspace_addr);
diff --git a/drivers/gpu/drm/drm_bufs.c b/drivers/gpu/drm/drm_bufs.c
index 30372f7b2d45..348b367debeb 100644
--- a/drivers/gpu/drm/drm_bufs.c
+++ b/drivers/gpu/drm/drm_bufs.c
@@ -1510,8 +1510,8 @@ int drm_freebufs(struct drm_device *dev, void *data,
  * \param arg pointer to a drm_buf_map structure.
  * \return zero on success or a negative number on failure.
  *
- * Maps the AGP, SG or PCI buffer region with do_mmap(), and copies information
- * about each buffer into user space. For PCI buffers, it calls do_mmap() with
+ * Maps the AGP, SG or PCI buffer region with vm_mmap(), and copies information
+ * about each buffer into user space. For PCI buffers, it calls vm_mmap() with
  * offset equal to 0, which drm_mmap() interpretes as PCI buffers and calls
  * drm_mmap_dma().
  */
@@ -1553,18 +1553,14 @@ int drm_mapbufs(struct drm_device *dev, void *data,
 				retcode = -EINVAL;
 				goto done;
 			}
-			down_write(&current->mm->mmap_sem);
-			virtual = do_mmap(file_priv->filp, 0, map->size,
+			virtual = vm_mmap(file_priv->filp, 0, map->size,
 					  PROT_READ | PROT_WRITE,
 					  MAP_SHARED,
 					  token);
-			up_write(&current->mm->mmap_sem);
 		} else {
-			down_write(&current->mm->mmap_sem);
-			virtual = do_mmap(file_priv->filp, 0, dma->byte_count,
+			virtual = vm_mmap(file_priv->filp, 0, dma->byte_count,
 					  PROT_READ | PROT_WRITE,
 					  MAP_SHARED, 0);
-			up_write(&current->mm->mmap_sem);
 		}
 		if (virtual > -1024UL) {
 			/* Real error */
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c
index 26d51979116b..392ce71ed6a1 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c
@@ -581,10 +581,8 @@ int exynos_drm_gem_mmap_ioctl(struct drm_device *dev, void *data,
 	obj->filp->f_op = &exynos_drm_gem_fops;
 	obj->filp->private_data = obj;
 
-	down_write(&current->mm->mmap_sem);
-	addr = do_mmap(obj->filp, 0, args->size,
+	addr = vm_mmap(obj->filp, 0, args->size,
 			PROT_READ | PROT_WRITE, MAP_SHARED, 0);
-	up_write(&current->mm->mmap_sem);
 
 	drm_gem_object_unreference_unlocked(obj);
 
diff --git a/drivers/gpu/drm/i810/i810_dma.c b/drivers/gpu/drm/i810/i810_dma.c
index b85337f06fbf..a4ba453b3d27 100644
--- a/drivers/gpu/drm/i810/i810_dma.c
+++ b/drivers/gpu/drm/i810/i810_dma.c
@@ -129,6 +129,7 @@ static int i810_map_buffer(struct drm_buf *buf, struct drm_file *file_priv)
 	if (buf_priv->currently_mapped == I810_BUF_MAPPED)
 		return -EINVAL;
 
+	/* This is all entirely broken */
 	down_write(&current->mm->mmap_sem);
 	old_fops = file_priv->filp->f_op;
 	file_priv->filp->f_op = &i810_buffer_fops;
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 0e3c6acde955..0d1e4b7b4b99 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1087,11 +1087,9 @@ i915_gem_mmap_ioctl(struct drm_device *dev, void *data,
 	if (obj == NULL)
 		return -ENOENT;
 
-	down_write(&current->mm->mmap_sem);
-	addr = do_mmap(obj->filp, 0, args->size,
+	addr = vm_mmap(obj->filp, 0, args->size,
 		       PROT_READ | PROT_WRITE, MAP_SHARED,
 		       args->offset);
-	up_write(&current->mm->mmap_sem);
 	drm_gem_object_unreference_unlocked(obj);
 	if (IS_ERR((void *)addr))
 		return addr;
diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c
index 88527492b917..d146e181d10d 100644
--- a/fs/binfmt_aout.c
+++ b/fs/binfmt_aout.c
@@ -319,24 +319,20 @@ static int load_aout_binary(struct linux_binprm * bprm, struct pt_regs * regs)
 			goto beyond_if;
 		}
 
-		down_write(&current->mm->mmap_sem);
-		error = do_mmap(bprm->file, N_TXTADDR(ex), ex.a_text,
+		error = vm_mmap(bprm->file, N_TXTADDR(ex), ex.a_text,
 			PROT_READ | PROT_EXEC,
 			MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE,
 			fd_offset);
-		up_write(&current->mm->mmap_sem);
 
 		if (error != N_TXTADDR(ex)) {
 			send_sig(SIGKILL, current, 0);
 			return error;
 		}
 
-		down_write(&current->mm->mmap_sem);
- 		error = do_mmap(bprm->file, N_DATADDR(ex), ex.a_data,
+		error = vm_mmap(bprm->file, N_DATADDR(ex), ex.a_data,
 				PROT_READ | PROT_WRITE | PROT_EXEC,
 				MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE,
 				fd_offset + ex.a_text);
-		up_write(&current->mm->mmap_sem);
 		if (error != N_DATADDR(ex)) {
 			send_sig(SIGKILL, current, 0);
 			return error;
@@ -417,12 +413,10 @@ static int load_aout_library(struct file *file)
 		goto out;
 	}
 	/* Now use mmap to map the library into memory. */
-	down_write(&current->mm->mmap_sem);
-	error = do_mmap(file, start_addr, ex.a_text + ex.a_data,
+	error = vm_mmap(file, start_addr, ex.a_text + ex.a_data,
 			PROT_READ | PROT_WRITE | PROT_EXEC,
 			MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE,
 			N_TXTOFF(ex));
-	up_write(&current->mm->mmap_sem);
 	retval = error;
 	if (error != start_addr)
 		goto out;
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 0708a0bf0ba9..16f735417072 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -958,10 +958,8 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 		   and some applications "depend" upon this behavior.
 		   Since we do not have the power to recompile these, we
 		   emulate the SVr4 behavior. Sigh. */
-		down_write(&current->mm->mmap_sem);
-		error = do_mmap(NULL, 0, PAGE_SIZE, PROT_READ | PROT_EXEC,
+		error = vm_mmap(NULL, 0, PAGE_SIZE, PROT_READ | PROT_EXEC,
 				MAP_FIXED | MAP_PRIVATE, 0);
-		up_write(&current->mm->mmap_sem);
 	}
 
 #ifdef ELF_PLAT_INIT
@@ -1046,8 +1044,7 @@ static int load_elf_library(struct file *file)
 		eppnt++;
 
 	/* Now use mmap to map the library into memory. */
-	down_write(&current->mm->mmap_sem);
-	error = do_mmap(file,
+	error = vm_mmap(file,
 			ELF_PAGESTART(eppnt->p_vaddr),
 			(eppnt->p_filesz +
 			 ELF_PAGEOFFSET(eppnt->p_vaddr)),
@@ -1055,7 +1052,6 @@ static int load_elf_library(struct file *file)
 			MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE,
 			(eppnt->p_offset -
 			 ELF_PAGEOFFSET(eppnt->p_vaddr)));
-	up_write(&current->mm->mmap_sem);
 	if (error != ELF_PAGESTART(eppnt->p_vaddr))
 		goto out_free_ph;
 
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 9bd5612a8224..d390a0fffc65 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -390,21 +390,17 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm,
 	    (executable_stack == EXSTACK_DEFAULT && VM_STACK_FLAGS & VM_EXEC))
 		stack_prot |= PROT_EXEC;
 
-	down_write(&current->mm->mmap_sem);
-	current->mm->start_brk = do_mmap(NULL, 0, stack_size, stack_prot,
+	current->mm->start_brk = vm_mmap(NULL, 0, stack_size, stack_prot,
 					 MAP_PRIVATE | MAP_ANONYMOUS |
 					 MAP_UNINITIALIZED | MAP_GROWSDOWN,
 					 0);
 
 	if (IS_ERR_VALUE(current->mm->start_brk)) {
-		up_write(&current->mm->mmap_sem);
 		retval = current->mm->start_brk;
 		current->mm->start_brk = 0;
 		goto error_kill;
 	}
 
-	up_write(&current->mm->mmap_sem);
-
 	current->mm->brk = current->mm->start_brk;
 	current->mm->context.end_brk = current->mm->start_brk;
 	current->mm->context.end_brk +=
@@ -955,10 +951,8 @@ static int elf_fdpic_map_file_constdisp_on_uclinux(
 	if (params->flags & ELF_FDPIC_FLAG_EXECUTABLE)
 		mflags |= MAP_EXECUTABLE;
 
-	down_write(&mm->mmap_sem);
-	maddr = do_mmap(NULL, load_addr, top - base,
+	maddr = vm_mmap(NULL, load_addr, top - base,
 			PROT_READ | PROT_WRITE | PROT_EXEC, mflags, 0);
-	up_write(&mm->mmap_sem);
 	if (IS_ERR_VALUE(maddr))
 		return (int) maddr;
 
@@ -1096,10 +1090,8 @@ static int elf_fdpic_map_file_by_direct_mmap(struct elf_fdpic_params *params,
 
 		/* create the mapping */
 		disp = phdr->p_vaddr & ~PAGE_MASK;
-		down_write(&mm->mmap_sem);
-		maddr = do_mmap(file, maddr, phdr->p_memsz + disp, prot, flags,
+		maddr = vm_mmap(file, maddr, phdr->p_memsz + disp, prot, flags,
 				phdr->p_offset - disp);
-		up_write(&mm->mmap_sem);
 
 		kdebug("mmap[%d] <file> sz=%lx pr=%x fl=%x of=%lx --> %08lx",
 		       loop, phdr->p_memsz + disp, prot, flags,
@@ -1143,10 +1135,8 @@ static int elf_fdpic_map_file_by_direct_mmap(struct elf_fdpic_params *params,
 			unsigned long xmaddr;
 
 			flags |= MAP_FIXED | MAP_ANONYMOUS;
-			down_write(&mm->mmap_sem);
-			xmaddr = do_mmap(NULL, xaddr, excess - excess1,
+			xmaddr = vm_mmap(NULL, xaddr, excess - excess1,
 					 prot, flags, 0);
-			up_write(&mm->mmap_sem);
 
 			kdebug("mmap[%d] <anon>"
 			       " ad=%lx sz=%lx pr=%x fl=%x of=0 --> %08lx",
diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
index 024d20ee3ca3..6b2daf99fab8 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -542,10 +542,8 @@ static int load_flat_file(struct linux_binprm * bprm,
 		 */
 		DBG_FLT("BINFMT_FLAT: ROM mapping of file (we hope)\n");
 
-		down_write(&current->mm->mmap_sem);
-		textpos = do_mmap(bprm->file, 0, text_len, PROT_READ|PROT_EXEC,
+		textpos = vm_mmap(bprm->file, 0, text_len, PROT_READ|PROT_EXEC,
 				  MAP_PRIVATE|MAP_EXECUTABLE, 0);
-		up_write(&current->mm->mmap_sem);
 		if (!textpos || IS_ERR_VALUE(textpos)) {
 			if (!textpos)
 				textpos = (unsigned long) -ENOMEM;
@@ -556,10 +554,8 @@ static int load_flat_file(struct linux_binprm * bprm,
 
 		len = data_len + extra + MAX_SHARED_LIBS * sizeof(unsigned long);
 		len = PAGE_ALIGN(len);
-		down_write(&current->mm->mmap_sem);
-		realdatastart = do_mmap(0, 0, len,
+		realdatastart = vm_mmap(0, 0, len,
 			PROT_READ|PROT_WRITE|PROT_EXEC, MAP_PRIVATE, 0);
-		up_write(&current->mm->mmap_sem);
 
 		if (realdatastart == 0 || IS_ERR_VALUE(realdatastart)) {
 			if (!realdatastart)
@@ -603,10 +599,8 @@ static int load_flat_file(struct linux_binprm * bprm,
 
 		len = text_len + data_len + extra + MAX_SHARED_LIBS * sizeof(unsigned long);
 		len = PAGE_ALIGN(len);
-		down_write(&current->mm->mmap_sem);
-		textpos = do_mmap(0, 0, len,
+		textpos = vm_mmap(0, 0, len,
 			PROT_READ | PROT_EXEC | PROT_WRITE, MAP_PRIVATE, 0);
-		up_write(&current->mm->mmap_sem);
 
 		if (!textpos || IS_ERR_VALUE(textpos)) {
 			if (!textpos)
diff --git a/fs/binfmt_som.c b/fs/binfmt_som.c
index e4fc746629a7..4517aaff61b4 100644
--- a/fs/binfmt_som.c
+++ b/fs/binfmt_som.c
@@ -147,10 +147,8 @@ static int map_som_binary(struct file *file,
 	code_size = SOM_PAGEALIGN(hpuxhdr->exec_tsize);
 	current->mm->start_code = code_start;
 	current->mm->end_code = code_start + code_size;
-	down_write(&current->mm->mmap_sem);
-	retval = do_mmap(file, code_start, code_size, prot,
+	retval = vm_mmap(file, code_start, code_size, prot,
 			flags, SOM_PAGESTART(hpuxhdr->exec_tfile));
-	up_write(&current->mm->mmap_sem);
 	if (retval < 0 && retval > -1024)
 		goto out;
 
@@ -158,20 +156,16 @@ static int map_som_binary(struct file *file,
 	data_size = SOM_PAGEALIGN(hpuxhdr->exec_dsize);
 	current->mm->start_data = data_start;
 	current->mm->end_data = bss_start = data_start + data_size;
-	down_write(&current->mm->mmap_sem);
-	retval = do_mmap(file, data_start, data_size,
+	retval = vm_mmap(file, data_start, data_size,
 			prot | PROT_WRITE, flags,
 			SOM_PAGESTART(hpuxhdr->exec_dfile));
-	up_write(&current->mm->mmap_sem);
 	if (retval < 0 && retval > -1024)
 		goto out;
 
 	som_brk = bss_start + SOM_PAGEALIGN(hpuxhdr->exec_bsize);
 	current->mm->start_brk = current->mm->brk = som_brk;
-	down_write(&current->mm->mmap_sem);
-	retval = do_mmap(NULL, bss_start, som_brk - bss_start,
+	retval = vm_mmap(NULL, bss_start, som_brk - bss_start,
 			prot | PROT_WRITE, MAP_FIXED | MAP_PRIVATE, 0);
-	up_write(&current->mm->mmap_sem);
 	if (retval > 0 || retval < -1024)
 		retval = 0;
 out:
diff --git a/include/linux/mm.h b/include/linux/mm.h
index cb61950a3aa1..86a692c3b238 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1393,31 +1393,20 @@ extern int install_special_mapping(struct mm_struct *mm,
 
 extern unsigned long get_unmapped_area(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
 
-extern unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
-	unsigned long len, unsigned long prot,
-	unsigned long flag, unsigned long pgoff);
 extern unsigned long mmap_region(struct file *file, unsigned long addr,
 	unsigned long len, unsigned long flags,
 	vm_flags_t vm_flags, unsigned long pgoff);
-
-static inline unsigned long do_mmap(struct file *file, unsigned long addr,
-	unsigned long len, unsigned long prot,
-	unsigned long flag, unsigned long offset)
-{
-	unsigned long ret = -EINVAL;
-	if ((offset + PAGE_ALIGN(len)) < offset)
-		goto out;
-	if (!(offset & ~PAGE_MASK))
-		ret = do_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT);
-out:
-	return ret;
-}
-
+extern unsigned long do_mmap(struct file *, unsigned long,
+        unsigned long, unsigned long,
+        unsigned long, unsigned long);
 extern int do_munmap(struct mm_struct *, unsigned long, size_t);
 
 /* These take the mm semaphore themselves */
 extern unsigned long vm_brk(unsigned long, unsigned long);
 extern int vm_munmap(struct mm_struct *, unsigned long, size_t);
+extern unsigned long vm_mmap(struct file *, unsigned long,
+        unsigned long, unsigned long,
+        unsigned long, unsigned long);
 
 /* truncate.c */
 extern void truncate_inode_pages(struct address_space *, loff_t);
diff --git a/mm/mmap.c b/mm/mmap.c
index 4af45f519f19..b38b47ef1f77 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -953,7 +953,7 @@ static inline unsigned long round_hint_to_min(unsigned long hint)
  * The caller must hold down_write(&current->mm->mmap_sem).
  */
 
-unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
+static unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 			unsigned long len, unsigned long prot,
 			unsigned long flags, unsigned long pgoff)
 {
@@ -1089,7 +1089,32 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 
 	return mmap_region(file, addr, len, flags, vm_flags, pgoff);
 }
-EXPORT_SYMBOL(do_mmap_pgoff);
+
+unsigned long do_mmap(struct file *file, unsigned long addr,
+	unsigned long len, unsigned long prot,
+	unsigned long flag, unsigned long offset)
+{
+	if (unlikely(offset + PAGE_ALIGN(len) < offset))
+		return -EINVAL;
+	if (unlikely(offset & ~PAGE_MASK))
+		return -EINVAL;
+	return do_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT);
+}
+EXPORT_SYMBOL(do_mmap);
+
+unsigned long vm_mmap(struct file *file, unsigned long addr,
+	unsigned long len, unsigned long prot,
+	unsigned long flag, unsigned long offset)
+{
+	unsigned long ret;
+	struct mm_struct *mm = current->mm;
+
+	down_write(&mm->mmap_sem);
+	ret = do_mmap(file, addr, len, prot, flag, offset);
+	up_write(&mm->mmap_sem);
+	return ret;
+}
+EXPORT_SYMBOL(vm_mmap);
 
 SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
 		unsigned long, prot, unsigned long, flags,
diff --git a/mm/nommu.c b/mm/nommu.c
index 11a69b22bd4b..dd00383be2d9 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1233,7 +1233,7 @@ enomem:
 /*
  * handle mapping creation for uClinux
  */
-unsigned long do_mmap_pgoff(struct file *file,
+static unsigned long do_mmap_pgoff(struct file *file,
 			    unsigned long addr,
 			    unsigned long len,
 			    unsigned long prot,
@@ -1470,7 +1470,32 @@ error_getting_region:
 	show_free_areas(0);
 	return -ENOMEM;
 }
-EXPORT_SYMBOL(do_mmap_pgoff);
+
+unsigned long do_mmap(struct file *file, unsigned long addr,
+	unsigned long len, unsigned long prot,
+	unsigned long flag, unsigned long offset)
+{
+	if (unlikely(offset + PAGE_ALIGN(len) < offset))
+		return -EINVAL;
+	if (unlikely(offset & ~PAGE_MASK))
+		return -EINVAL;
+	return do_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT);
+}
+EXPORT_SYMBOL(do_mmap);
+
+unsigned long vm_mmap(struct file *file, unsigned long addr,
+	unsigned long len, unsigned long prot,
+	unsigned long flag, unsigned long offset)
+{
+	unsigned long ret;
+	struct mm_struct *mm = current->mm;
+
+	down_write(&mm->mmap_sem);
+	ret = do_mmap(file, addr, len, prot, flag, offset);
+	up_write(&mm->mmap_sem);
+	return ret;
+}
+EXPORT_SYMBOL(vm_mmap);
 
 SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
 		unsigned long, prot, unsigned long, flags,
-- 
cgit v1.2.3


From bfce281c287a427d0841fadf5d59242757b4e620 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 20 Apr 2012 21:57:04 -0400
Subject: kill mm argument of vm_munmap()

it's always current->mm

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/ia64/kernel/perfmon.c       | 2 +-
 arch/sparc/kernel/sys_sparc_64.c | 2 +-
 arch/x86/kvm/x86.c               | 2 +-
 drivers/gpu/drm/i810/i810_dma.c  | 3 +--
 fs/aio.c                         | 2 +-
 include/linux/mm.h               | 2 +-
 mm/mmap.c                        | 5 +++--
 mm/nommu.c                       | 5 +++--
 8 files changed, 12 insertions(+), 11 deletions(-)

(limited to 'mm')

diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index 899c0fa5b498..f00ba025375d 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -1468,7 +1468,7 @@ pfm_remove_smpl_mapping(void *vaddr, unsigned long size)
 	/*
 	 * does the actual unmapping
 	 */
-	r = vm_munmap(current->mm, (unsigned long)vaddr, size);
+	r = vm_munmap((unsigned long)vaddr, size);
 
 	if (r !=0) {
 		printk(KERN_ERR "perfmon: [%d] unable to unmap sampling buffer @%p size=%lu\n", task_pid_nr(task), vaddr, size);
diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c
index 022e57aadf5d..3ee51f189a55 100644
--- a/arch/sparc/kernel/sys_sparc_64.c
+++ b/arch/sparc/kernel/sys_sparc_64.c
@@ -569,7 +569,7 @@ SYSCALL_DEFINE2(64_munmap, unsigned long, addr, size_t, len)
 	if (invalid_64bit_range(addr, len))
 		return -EINVAL;
 
-	return vm_munmap(current->mm, addr, len);
+	return vm_munmap(addr, len);
 }
 
 extern unsigned long do_mremap(unsigned long addr,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1457be305fb1..91a5e989abcf 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6364,7 +6364,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 	if (!user_alloc && !old.user_alloc && old.rmap && !npages) {
 		int ret;
 
-		ret = vm_munmap(current->mm, old.userspace_addr,
+		ret = vm_munmap(old.userspace_addr,
 				old.npages * PAGE_SIZE);
 		if (ret < 0)
 			printk(KERN_WARNING
diff --git a/drivers/gpu/drm/i810/i810_dma.c b/drivers/gpu/drm/i810/i810_dma.c
index a4ba453b3d27..f920fb5e42b6 100644
--- a/drivers/gpu/drm/i810/i810_dma.c
+++ b/drivers/gpu/drm/i810/i810_dma.c
@@ -158,8 +158,7 @@ static int i810_unmap_buffer(struct drm_buf *buf)
 	if (buf_priv->currently_mapped != I810_BUF_MAPPED)
 		return -EINVAL;
 
-	retcode = vm_munmap(current->mm,
-			    (unsigned long)buf_priv->virtual,
+	retcode = vm_munmap((unsigned long)buf_priv->virtual,
 			    (size_t) buf->total);
 
 	buf_priv->currently_mapped = I810_BUF_UNMAPPED;
diff --git a/fs/aio.c b/fs/aio.c
index 976e33d97413..67a6db3e1b6f 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -94,7 +94,7 @@ static void aio_free_ring(struct kioctx *ctx)
 
 	if (info->mmap_size) {
 		BUG_ON(ctx->mm != current->mm);
-		vm_munmap(ctx->mm, info->mmap_base, info->mmap_size);
+		vm_munmap(info->mmap_base, info->mmap_size);
 	}
 
 	if (info->ring_pages && info->ring_pages != info->internal_pages)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 86a692c3b238..74aa71bea1e4 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1403,7 +1403,7 @@ extern int do_munmap(struct mm_struct *, unsigned long, size_t);
 
 /* These take the mm semaphore themselves */
 extern unsigned long vm_brk(unsigned long, unsigned long);
-extern int vm_munmap(struct mm_struct *, unsigned long, size_t);
+extern int vm_munmap(unsigned long, size_t);
 extern unsigned long vm_mmap(struct file *, unsigned long,
         unsigned long, unsigned long,
         unsigned long, unsigned long);
diff --git a/mm/mmap.c b/mm/mmap.c
index b38b47ef1f77..848ef52d9603 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2134,9 +2134,10 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
 }
 EXPORT_SYMBOL(do_munmap);
 
-int vm_munmap(struct mm_struct *mm, unsigned long start, size_t len)
+int vm_munmap(unsigned long start, size_t len)
 {
 	int ret;
+	struct mm_struct *mm = current->mm;
 
 	down_write(&mm->mmap_sem);
 	ret = do_munmap(mm, start, len);
@@ -2148,7 +2149,7 @@ EXPORT_SYMBOL(vm_munmap);
 SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len)
 {
 	profile_munmap(addr);
-	return vm_munmap(current->mm, addr, len);
+	return vm_munmap(addr, len);
 }
 
 static inline void verify_mm_writelocked(struct mm_struct *mm)
diff --git a/mm/nommu.c b/mm/nommu.c
index dd00383be2d9..bb8f4f004a82 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1734,8 +1734,9 @@ erase_whole_vma:
 }
 EXPORT_SYMBOL(do_munmap);
 
-int vm_munmap(struct mm_struct *mm, unsigned long addr, size_t len)
+int vm_munmap(unsigned long addr, size_t len)
 {
+	struct mm_struct *mm = current->mm;
 	int ret;
 
 	down_write(&mm->mmap_sem);
@@ -1747,7 +1748,7 @@ EXPORT_SYMBOL(vm_munmap);
 
 SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len)
 {
-	return vm_munmap(current->mm, addr, len);
+	return vm_munmap(addr, len);
 }
 
 /*
-- 
cgit v1.2.3