[PATCH 0/4] Virtually mapped stack prep for -mm

[PATCH 0/4] Virtually mapped stack prep for -mm

[Andy Lutomirski]

Hi akpm-

We're delaying virtually mapped stacks to 4.9.  These four patches
are simple and seem like -mm material.  Could you apply them for
4.8 so we can get the easy core bits in place?

Thanks,
Andy

Andy Lutomirski (4):
  mm: Track NR_KERNEL_STACK in KiB instead of number of stacks
  mm: Fix memcg stack accounting for sub-page stacks
  kdb: Use task_cpu() instead of task_thread_info()->cpu
  printk: When dumping regs, show the stack, not thread_info

 drivers/base/node.c        |  3 +--
 fs/proc/meminfo.c          |  2 +-
 include/linux/kdb.h        |  2 +-
 include/linux/memcontrol.h |  2 +-
 include/linux/mmzone.h     |  2 +-
 kernel/fork.c              | 20 +++++++++-----------
 kernel/printk/printk.c     |  5 ++---
 mm/memcontrol.c            |  2 +-
 mm/page_alloc.c            |  3 +--
 9 files changed, 18 insertions(+), 23 deletions(-)

-- 
2.7.4

[PATCH 1/4] mm: Track NR_KERNEL_STACK in KiB instead of number of stacks

[Andy Lutomirski]

Currently, NR_KERNEL_STACK tracks the number of kernel stacks in a
zone.  This only makes sense if each kernel stack exists entirely in
one zone, and allowing vmapped stacks could break this assumption.

Since frv has THREAD_SIZE < PAGE_SIZE, we need to track kernel stack
allocations in a unit that divides both THREAD_SIZE and PAGE_SIZE on
all architectures.  Keep it simple and use KiB.

Cc: Vladimir Davydov <vdavydov@virtuozzo.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: linux-mm@kvack.org
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Reviewed-by: Vladimir Davydov <vdavydov@virtuozzo.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Andy Lutomirski <luto@kernel.org>
---
 drivers/base/node.c    | 3 +--
 fs/proc/meminfo.c      | 2 +-
 include/linux/mmzone.h | 2 +-
 kernel/fork.c          | 3 ++-
 mm/page_alloc.c        | 3 +--
 5 files changed, 6 insertions(+), 7 deletions(-)

diff --git a/drivers/base/node.c b/drivers/base/node.c
index 560751bad294..27dc68a0ed2d 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -121,8 +121,7 @@ static ssize_t node_read_meminfo(struct device *dev,
 		       nid, K(node_page_state(nid, NR_FILE_MAPPED)),
 		       nid, K(node_page_state(nid, NR_ANON_PAGES)),
 		       nid, K(i.sharedram),
-		       nid, node_page_state(nid, NR_KERNEL_STACK) *
-				THREAD_SIZE / 1024,
+		       nid, node_page_state(nid, NR_KERNEL_STACK_KB),
 		       nid, K(node_page_state(nid, NR_PAGETABLE)),
 		       nid, K(node_page_state(nid, NR_UNSTABLE_NFS)),
 		       nid, K(node_page_state(nid, NR_BOUNCE)),
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 83720460c5bc..239b5a06cee0 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -145,7 +145,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 				global_page_state(NR_SLAB_UNRECLAIMABLE)),
 		K(global_page_state(NR_SLAB_RECLAIMABLE)),
 		K(global_page_state(NR_SLAB_UNRECLAIMABLE)),
-		global_page_state(NR_KERNEL_STACK) * THREAD_SIZE / 1024,
+		global_page_state(NR_KERNEL_STACK_KB),
 		K(global_page_state(NR_PAGETABLE)),
 #ifdef CONFIG_QUICKLIST
 		K(quicklist_total_size()),
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 02069c23486d..63f05a7efb54 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -127,7 +127,7 @@ enum zone_stat_item {
 	NR_SLAB_RECLAIMABLE,
 	NR_SLAB_UNRECLAIMABLE,
 	NR_PAGETABLE,		/* used for pagetables */
-	NR_KERNEL_STACK,
+	NR_KERNEL_STACK_KB,	/* measured in KiB */
 	/* Second 128 byte cacheline */
 	NR_UNSTABLE_NFS,	/* NFS unstable pages */
 	NR_BOUNCE,
diff --git a/kernel/fork.c b/kernel/fork.c
index 4a7ec0c6c88c..466ba8febe3b 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -225,7 +225,8 @@ static void account_kernel_stack(unsigned long *stack, int account)
 {
 	struct zone *zone = page_zone(virt_to_page(stack));
 
-	mod_zone_page_state(zone, NR_KERNEL_STACK, account);
+	mod_zone_page_state(zone, NR_KERNEL_STACK_KB,
+			    THREAD_SIZE / 1024 * account);
 }
 
 void free_task(struct task_struct *tsk)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 6903b695ebae..a277dea926c9 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4457,8 +4457,7 @@ void show_free_areas(unsigned int filter)
 			K(zone_page_state(zone, NR_SHMEM)),
 			K(zone_page_state(zone, NR_SLAB_RECLAIMABLE)),
 			K(zone_page_state(zone, NR_SLAB_UNRECLAIMABLE)),
-			zone_page_state(zone, NR_KERNEL_STACK) *
-				THREAD_SIZE / 1024,
+			zone_page_state(zone, NR_KERNEL_STACK_KB),
 			K(zone_page_state(zone, NR_PAGETABLE)),
 			K(zone_page_state(zone, NR_UNSTABLE_NFS)),
 			K(zone_page_state(zone, NR_BOUNCE)),
-- 
2.7.4

[PATCH 2/4] mm: Fix memcg stack accounting for sub-page stacks

[Andy Lutomirski]

We should account for stacks regardless of stack size, and we need
to account in sub-page units if THREAD_SIZE < PAGE_SIZE.  Change the
units to kilobytes and Move it into account_kernel_stack().

Fixes: 12580e4b54ba8 ("mm: memcontrol: report kernel stack usage in cgroup2 memory.stat")
Cc: Vladimir Davydov <vdavydov@virtuozzo.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: linux-mm@kvack.org
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Reviewed-by: Vladimir Davydov <vdavydov@virtuozzo.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Andy Lutomirski <luto@kernel.org>
---
 include/linux/memcontrol.h |  2 +-
 kernel/fork.c              | 19 ++++++++-----------
 mm/memcontrol.c            |  2 +-
 3 files changed, 10 insertions(+), 13 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index a805474df4ab..3b653b86bb8f 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -52,7 +52,7 @@ enum mem_cgroup_stat_index {
 	MEM_CGROUP_STAT_SWAP,		/* # of pages, swapped out */
 	MEM_CGROUP_STAT_NSTATS,
 	/* default hierarchy stats */
-	MEMCG_KERNEL_STACK = MEM_CGROUP_STAT_NSTATS,
+	MEMCG_KERNEL_STACK_KB = MEM_CGROUP_STAT_NSTATS,
 	MEMCG_SLAB_RECLAIMABLE,
 	MEMCG_SLAB_UNRECLAIMABLE,
 	MEMCG_SOCK,
diff --git a/kernel/fork.c b/kernel/fork.c
index 466ba8febe3b..146c9840c079 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -165,20 +165,12 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk,
 	struct page *page = alloc_kmem_pages_node(node, THREADINFO_GFP,
 						  THREAD_SIZE_ORDER);
 
-	if (page)
-		memcg_kmem_update_page_stat(page, MEMCG_KERNEL_STACK,
-					    1 << THREAD_SIZE_ORDER);
-
 	return page ? page_address(page) : NULL;
 }
 
 static inline void free_thread_stack(unsigned long *stack)
 {
-	struct page *page = virt_to_page(stack);
-
-	memcg_kmem_update_page_stat(page, MEMCG_KERNEL_STACK,
-				    -(1 << THREAD_SIZE_ORDER));
-	__free_kmem_pages(page, THREAD_SIZE_ORDER);
+	free_kmem_pages((unsigned long)stack, THREAD_SIZE_ORDER);
 }
 # else
 static struct kmem_cache *thread_stack_cache;
@@ -223,10 +215,15 @@ static struct kmem_cache *mm_cachep;
 
 static void account_kernel_stack(unsigned long *stack, int account)
 {
-	struct zone *zone = page_zone(virt_to_page(stack));
+	/* All stack pages are in the same zone and belong to the same memcg. */
+	struct page *first_page = virt_to_page(stack);
 
-	mod_zone_page_state(zone, NR_KERNEL_STACK_KB,
+	mod_zone_page_state(page_zone(first_page), NR_KERNEL_STACK_KB,
 			    THREAD_SIZE / 1024 * account);
+
+	memcg_kmem_update_page_stat(
+		first_page, MEMCG_KERNEL_STACK_KB,
+		account * (THREAD_SIZE / 1024));
 }
 
 void free_task(struct task_struct *tsk)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ac8664db3823..ee44afc1f2d0 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5133,7 +5133,7 @@ static int memory_stat_show(struct seq_file *m, void *v)
 	seq_printf(m, "file %llu\n",
 		   (u64)stat[MEM_CGROUP_STAT_CACHE] * PAGE_SIZE);
 	seq_printf(m, "kernel_stack %llu\n",
-		   (u64)stat[MEMCG_KERNEL_STACK] * PAGE_SIZE);
+		   (u64)stat[MEMCG_KERNEL_STACK_KB] * 1024);
 	seq_printf(m, "slab %llu\n",
 		   (u64)(stat[MEMCG_SLAB_RECLAIMABLE] +
 			 stat[MEMCG_SLAB_UNRECLAIMABLE]) * PAGE_SIZE);
-- 
2.7.4

[PATCH 3/4] kdb: Use task_cpu() instead of task_thread_info()->cpu

[Andy Lutomirski]

We'll need this cleanup to make the cpu field in thread_info be
optional.

Cc: Jason Wessel <jason.wessel@windriver.com>
Signed-off-by: Andy Lutomirski <luto@kernel.org>
---
 include/linux/kdb.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/kdb.h b/include/linux/kdb.h
index a19bcf9e762e..410decacff8f 100644
--- a/include/linux/kdb.h
+++ b/include/linux/kdb.h
@@ -177,7 +177,7 @@ extern int kdb_get_kbd_char(void);
 static inline
 int kdb_process_cpu(const struct task_struct *p)
 {
-	unsigned int cpu = task_thread_info(p)->cpu;
+	unsigned int cpu = task_cpu(p);
 	if (cpu > num_possible_cpus())
 		cpu = 0;
 	return cpu;
-- 
2.7.4

[PATCH 4/4] printk: When dumping regs, show the stack, not thread_info

[Andy Lutomirski]

We currently show:

  task: <current> ti: <current_thread_info()> task.ti: <task_thread_info(current)>"

"ti" and "task.ti" are redundant, and neither is actually what we
want to show, which the the base of the thread stack.  Change the
display to show the stack pointer explicitly.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
---
 kernel/printk/printk.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 60cdf6386763..d4de33934dac 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -3177,9 +3177,8 @@ void show_regs_print_info(const char *log_lvl)
 {
 	dump_stack_print_info(log_lvl);
 
-	printk("%stask: %p ti: %p task.ti: %p\n",
-	       log_lvl, current, current_thread_info(),
-	       task_thread_info(current));
+	printk("%stask: %p task.stack: %p\n",
+	       log_lvl, current, task_stack_page(current));
 }
 
 #endif
-- 
2.7.4

Re: [PATCH 1/4] mm: Track NR_KERNEL_STACK in KiB instead of number of stacks

[Johannes Weiner]

On Thu, Jul 14, 2016 at 12:14:10PM -0700, Andy Lutomirski wrote:
> Currently, NR_KERNEL_STACK tracks the number of kernel stacks in a
> zone.  This only makes sense if each kernel stack exists entirely in
> one zone, and allowing vmapped stacks could break this assumption.
> 
> Since frv has THREAD_SIZE < PAGE_SIZE, we need to track kernel stack
> allocations in a unit that divides both THREAD_SIZE and PAGE_SIZE on
> all architectures.  Keep it simple and use KiB.
> 
> Cc: Vladimir Davydov <vdavydov@virtuozzo.com>
> Cc: Johannes Weiner <hannes@cmpxchg.org>
> Cc: Michal Hocko <mhocko@kernel.org>
> Cc: linux-mm@kvack.org
> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
> Reviewed-by: Vladimir Davydov <vdavydov@virtuozzo.com>
> Acked-by: Michal Hocko <mhocko@suse.com>
> Signed-off-by: Andy Lutomirski <luto@kernel.org>

Acked-by: Johannes Weiner <hannes@cmpxchg.org>

Re: [PATCH 2/4] mm: Fix memcg stack accounting for sub-page stacks

[Johannes Weiner]

On Thu, Jul 14, 2016 at 12:14:11PM -0700, Andy Lutomirski wrote:
> We should account for stacks regardless of stack size, and we need
> to account in sub-page units if THREAD_SIZE < PAGE_SIZE.  Change the
> units to kilobytes and Move it into account_kernel_stack().
> 
> Fixes: 12580e4b54ba8 ("mm: memcontrol: report kernel stack usage in cgroup2 memory.stat")
> Cc: Vladimir Davydov <vdavydov@virtuozzo.com>
> Cc: Johannes Weiner <hannes@cmpxchg.org>
> Cc: Michal Hocko <mhocko@kernel.org>
> Cc: linux-mm@kvack.org
> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
> Reviewed-by: Vladimir Davydov <vdavydov@virtuozzo.com>
> Acked-by: Michal Hocko <mhocko@suse.com>
> Signed-off-by: Andy Lutomirski <luto@kernel.org>

Acked-by: Johannes Weiner <hannes@cmpxchg.org>

Re: [PATCH 2/4] mm: Fix memcg stack accounting for sub-page stacks

[Andrew Morton]

On Thu, 14 Jul 2016 12:14:11 -0700 Andy Lutomirski <luto@kernel.org> wrote:

> We should account for stacks regardless of stack size, and we need
> to account in sub-page units if THREAD_SIZE < PAGE_SIZE.  Change the
> units to kilobytes and Move it into account_kernel_stack().

I queued this patch after
http://ozlabs.org/~akpm/mmotm/broken-out/mm-charge-uncharge-kmemcg-from-generic-page-allocator-paths.patch
so some changes are needed.  (patching mainline when we're at -rc7 was
optimistic!)

> --- a/kernel/fork.c
> +++ b/kernel/fork.c
> @@ -165,20 +165,12 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk,
>  	struct page *page = alloc_kmem_pages_node(node, THREADINFO_GFP,
>  						  THREAD_SIZE_ORDER);
>  
> -	if (page)
> -		memcg_kmem_update_page_stat(page, MEMCG_KERNEL_STACK,
> -					    1 << THREAD_SIZE_ORDER);
> -
>  	return page ? page_address(page) : NULL;
>  }
>  
>  static inline void free_thread_stack(unsigned long *stack)
>  {
> -	struct page *page = virt_to_page(stack);
> -
> -	memcg_kmem_update_page_stat(page, MEMCG_KERNEL_STACK,
> -				    -(1 << THREAD_SIZE_ORDER));
> -	__free_kmem_pages(page, THREAD_SIZE_ORDER);
> +	free_kmem_pages((unsigned long)stack, THREAD_SIZE_ORDER);
>  }

Here's what I ended up with:

static unsigned long *alloc_thread_stack_node(struct task_struct *tsk,
						  int node)
{
	struct page *page = alloc_pages_node(node, THREADINFO_GFP,
					     THREAD_SIZE_ORDER);

	return page ? page_address(page) : NULL;
}

static inline void free_thread_stack(unsigned long *stack)
{
	__free_pages(virt_to_page(stack), THREAD_SIZE_ORDER);
}