[PATCH v5 02/32] x86/mm/hotplug: Don't remove PGD entries in remove_pagetable()

[PATCH v5 02/32] x86/mm/hotplug: Don't remove PGD entries in remove_pagetable()

[Andy Lutomirski]

From: Ingo Molnar <mingo@kernel.org>

So when memory hotplug removes a piece of physical memory from pagetable
mappings, it also frees the underlying PGD entry.

This complicates PGD management, so don't do this. We can keep the
PGD mapped and the PUD table all clear - it's only a single 4K page
per 512 GB of memory hotplugged.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Waiman Long <Waiman.Long@hp.com>
Cc: linux-mm@kvack.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Message-Id: <1442903021-3893-4-git-send-email-mingo@kernel.org>
---
 arch/x86/mm/init_64.c | 27 ---------------------------
 1 file changed, 27 deletions(-)

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index bce2e5d9edd4..c7465453d64e 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -702,27 +702,6 @@ static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud)
 	spin_unlock(&init_mm.page_table_lock);
 }
 
-/* Return true if pgd is changed, otherwise return false. */
-static bool __meminit free_pud_table(pud_t *pud_start, pgd_t *pgd)
-{
-	pud_t *pud;
-	int i;
-
-	for (i = 0; i < PTRS_PER_PUD; i++) {
-		pud = pud_start + i;
-		if (pud_val(*pud))
-			return false;
-	}
-
-	/* free a pud table */
-	free_pagetable(pgd_page(*pgd), 0);
-	spin_lock(&init_mm.page_table_lock);
-	pgd_clear(pgd);
-	spin_unlock(&init_mm.page_table_lock);
-
-	return true;
-}
-
 static void __meminit
 remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end,
 		 bool direct)
@@ -913,7 +892,6 @@ remove_pagetable(unsigned long start, unsigned long end, bool direct)
 	unsigned long addr;
 	pgd_t *pgd;
 	pud_t *pud;
-	bool pgd_changed = false;
 
 	for (addr = start; addr < end; addr = next) {
 		next = pgd_addr_end(addr, end);
@@ -924,13 +902,8 @@ remove_pagetable(unsigned long start, unsigned long end, bool direct)
 
 		pud = (pud_t *)pgd_page_vaddr(*pgd);
 		remove_pud_table(pud, addr, next, direct);
-		if (free_pud_table(pud, pgd))
-			pgd_changed = true;
 	}
 
-	if (pgd_changed)
-		sync_global_pgds(start, end - 1, 1);
-
 	flush_tlb_all();
 }
 
-- 
2.7.4

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH v5 05/32] 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

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH v5 06/32] 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

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>