Commit f627c2f5 authored by Kirill A. Shutemov's avatar Kirill A. Shutemov Committed by Linus Torvalds
Browse files

memcg: adjust to support new THP refcounting 



As with rmap, with new refcounting we cannot rely on PageTransHuge() to
check if we need to charge size of huge page form the cgroup.  We need
to get information from caller to know whether it was mapped with PMD or
PTE.

We do uncharge when last reference on the page gone.  At that point if
we see PageTransHuge() it means we need to unchange whole huge page.

The tricky part is partial unmap -- when we try to unmap part of huge
page.  We don't do a special handing of this situation, meaning we don't
uncharge the part of huge page unless last user is gone or
split_huge_page() is triggered.  In case of cgroup memory pressure
happens the partial unmapped page will be split through shrinker.  This
should be good enough.

Signed-off-by: default avatarKirill A. Shutemov <kirill.shutemov@linux.intel.com>
Tested-by: default avatarSasha Levin <sasha.levin@oracle.com>
Tested-by: default avatarAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: default avatarVlastimil Babka <vbabka@suse.cz>
Acked-by: default avatarJerome Marchand <jmarchan@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Steve Capper <steve.capper@linaro.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent d281ee61

include/linux/memcontrol.h

+10 −6
Original line number Diff line number Diff line
@@ -280,10 +280,12 @@ static inline void mem_cgroup_events(struct mem_cgroup *memcg, 
bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg);



int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,

			  gfp_t gfp_mask, struct mem_cgroup **memcgp);

			  gfp_t gfp_mask, struct mem_cgroup **memcgp,

			  bool compound);

void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg,

			      bool lrucare);

void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg);

			      bool lrucare, bool compound);

void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg,

		bool compound);

void mem_cgroup_uncharge(struct page *page);

void mem_cgroup_uncharge_list(struct list_head *page_list);
@@ -515,7 +517,8 @@ static inline bool mem_cgroup_low(struct mem_cgroup *root, 


static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,

					gfp_t gfp_mask,

					struct mem_cgroup **memcgp)

					struct mem_cgroup **memcgp,

					bool compound)

{

	*memcgp = NULL;

	return 0;
@@ -523,12 +526,13 @@ static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, 


static inline void mem_cgroup_commit_charge(struct page *page,

					    struct mem_cgroup *memcg,

					    bool lrucare)

					    bool lrucare, bool compound)

{

}



static inline void mem_cgroup_cancel_charge(struct page *page,

					    struct mem_cgroup *memcg)

					    struct mem_cgroup *memcg,

					    bool compound)

{

}

kernel/events/uprobes.c

+4 −3
Original line number Diff line number Diff line
@@ -161,7 +161,8 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, 
	const unsigned long mmun_end   = addr + PAGE_SIZE;

	struct mem_cgroup *memcg;



	err = mem_cgroup_try_charge(kpage, vma->vm_mm, GFP_KERNEL, &memcg);

	err = mem_cgroup_try_charge(kpage, vma->vm_mm, GFP_KERNEL, &memcg,

			false);

	if (err)

		return err;
@@ -176,7 +177,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, 


	get_page(kpage);

	page_add_new_anon_rmap(kpage, vma, addr, false);

	mem_cgroup_commit_charge(kpage, memcg, false);

	mem_cgroup_commit_charge(kpage, memcg, false, false);

	lru_cache_add_active_or_unevictable(kpage, vma);



	if (!PageAnon(page)) {
@@ -199,7 +200,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, 


	err = 0;

 unlock:

	mem_cgroup_cancel_charge(kpage, memcg);

	mem_cgroup_cancel_charge(kpage, memcg, false);

	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);

	unlock_page(page);

	return err;

mm/filemap.c

+4 −4
Original line number Diff line number Diff line
@@ -618,7 +618,7 @@ static int __add_to_page_cache_locked(struct page *page, 


	if (!huge) {

		error = mem_cgroup_try_charge(page, current->mm,

					      gfp_mask, &memcg);

					      gfp_mask, &memcg, false);

		if (error)

			return error;

	}
@@ -626,7 +626,7 @@ static int __add_to_page_cache_locked(struct page *page, 
	error = radix_tree_maybe_preload(gfp_mask & ~__GFP_HIGHMEM);

	if (error) {

		if (!huge)

			mem_cgroup_cancel_charge(page, memcg);

			mem_cgroup_cancel_charge(page, memcg, false);

		return error;

	}
@@ -645,7 +645,7 @@ static int __add_to_page_cache_locked(struct page *page, 
		__inc_zone_page_state(page, NR_FILE_PAGES);

	spin_unlock_irq(&mapping->tree_lock);

	if (!huge)

		mem_cgroup_commit_charge(page, memcg, false);

		mem_cgroup_commit_charge(page, memcg, false, false);

	trace_mm_filemap_add_to_page_cache(page);

	return 0;

err_insert:
@@ -653,7 +653,7 @@ err_insert: 
	/* Leave page->index set: truncation relies upon it */

	spin_unlock_irq(&mapping->tree_lock);

	if (!huge)

		mem_cgroup_cancel_charge(page, memcg);

		mem_cgroup_cancel_charge(page, memcg, false);

	page_cache_release(page);

	return error;

}

mm/huge_memory.c

+17 −15
Original line number Diff line number Diff line
@@ -751,7 +751,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, 


	VM_BUG_ON_PAGE(!PageCompound(page), page);



	if (mem_cgroup_try_charge(page, mm, gfp, &memcg)) {

	if (mem_cgroup_try_charge(page, mm, gfp, &memcg, true)) {

		put_page(page);

		count_vm_event(THP_FAULT_FALLBACK);

		return VM_FAULT_FALLBACK;
@@ -759,7 +759,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, 


	pgtable = pte_alloc_one(mm, haddr);

	if (unlikely(!pgtable)) {

		mem_cgroup_cancel_charge(page, memcg);

		mem_cgroup_cancel_charge(page, memcg, true);

		put_page(page);

		return VM_FAULT_OOM;

	}
@@ -775,7 +775,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, 
	ptl = pmd_lock(mm, pmd);

	if (unlikely(!pmd_none(*pmd))) {

		spin_unlock(ptl);

		mem_cgroup_cancel_charge(page, memcg);

		mem_cgroup_cancel_charge(page, memcg, true);

		put_page(page);

		pte_free(mm, pgtable);

	} else {
@@ -786,7 +786,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, 
			int ret;



			spin_unlock(ptl);

			mem_cgroup_cancel_charge(page, memcg);

			mem_cgroup_cancel_charge(page, memcg, true);

			put_page(page);

			pte_free(mm, pgtable);

			ret = handle_userfault(vma, address, flags,
@@ -798,7 +798,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, 
		entry = mk_huge_pmd(page, vma->vm_page_prot);

		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);

		page_add_new_anon_rmap(page, vma, haddr, true);

		mem_cgroup_commit_charge(page, memcg, false);

		mem_cgroup_commit_charge(page, memcg, false, true);

		lru_cache_add_active_or_unevictable(page, vma);

		pgtable_trans_huge_deposit(mm, pmd, pgtable);

		set_pmd_at(mm, haddr, pmd, entry);
@@ -1095,13 +1095,14 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, 
					       vma, address, page_to_nid(page));

		if (unlikely(!pages[i] ||

			     mem_cgroup_try_charge(pages[i], mm, GFP_KERNEL,

						   &memcg))) {

						   &memcg, false))) {

			if (pages[i])

				put_page(pages[i]);

			while (--i >= 0) {

				memcg = (void *)page_private(pages[i]);

				set_page_private(pages[i], 0);

				mem_cgroup_cancel_charge(pages[i], memcg);

				mem_cgroup_cancel_charge(pages[i], memcg,

						false);

				put_page(pages[i]);

			}

			kfree(pages);
@@ -1140,7 +1141,7 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, 
		memcg = (void *)page_private(pages[i]);

		set_page_private(pages[i], 0);

		page_add_new_anon_rmap(pages[i], vma, haddr, false);

		mem_cgroup_commit_charge(pages[i], memcg, false);

		mem_cgroup_commit_charge(pages[i], memcg, false, false);

		lru_cache_add_active_or_unevictable(pages[i], vma);

		pte = pte_offset_map(&_pmd, haddr);

		VM_BUG_ON(!pte_none(*pte));
@@ -1168,7 +1169,7 @@ out_free_pages: 
	for (i = 0; i < HPAGE_PMD_NR; i++) {

		memcg = (void *)page_private(pages[i]);

		set_page_private(pages[i], 0);

		mem_cgroup_cancel_charge(pages[i], memcg);

		mem_cgroup_cancel_charge(pages[i], memcg, false);

		put_page(pages[i]);

	}

	kfree(pages);
@@ -1234,7 +1235,8 @@ alloc: 
		goto out;

	}



	if (unlikely(mem_cgroup_try_charge(new_page, mm, huge_gfp, &memcg))) {

	if (unlikely(mem_cgroup_try_charge(new_page, mm, huge_gfp, &memcg,

					   true))) {

		put_page(new_page);

		if (page) {

			split_huge_page(page);
@@ -1263,7 +1265,7 @@ alloc: 
		put_user_huge_page(page);

	if (unlikely(!pmd_same(*pmd, orig_pmd))) {

		spin_unlock(ptl);

		mem_cgroup_cancel_charge(new_page, memcg);

		mem_cgroup_cancel_charge(new_page, memcg, true);

		put_page(new_page);

		goto out_mn;

	} else {
@@ -1272,7 +1274,7 @@ alloc: 
		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);

		pmdp_huge_clear_flush_notify(vma, haddr, pmd);

		page_add_new_anon_rmap(new_page, vma, haddr, true);

		mem_cgroup_commit_charge(new_page, memcg, false);

		mem_cgroup_commit_charge(new_page, memcg, false, true);

		lru_cache_add_active_or_unevictable(new_page, vma);

		set_pmd_at(mm, haddr, pmd, entry);

		update_mmu_cache_pmd(vma, address, pmd);
@@ -2583,7 +2585,7 @@ static void collapse_huge_page(struct mm_struct *mm, 
		goto out_nolock;

	}



	if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg))) {

	if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg, true))) {

		result = SCAN_CGROUP_CHARGE_FAIL;

		goto out_nolock;

	}
@@ -2683,7 +2685,7 @@ static void collapse_huge_page(struct mm_struct *mm, 
	spin_lock(pmd_ptl);

	BUG_ON(!pmd_none(*pmd));

	page_add_new_anon_rmap(new_page, vma, address, true);

	mem_cgroup_commit_charge(new_page, memcg, false);

	mem_cgroup_commit_charge(new_page, memcg, false, true);

	lru_cache_add_active_or_unevictable(new_page, vma);

	pgtable_trans_huge_deposit(mm, pmd, pgtable);

	set_pmd_at(mm, address, pmd, _pmd);
@@ -2703,7 +2705,7 @@ out_nolock: 
	trace_mm_collapse_huge_page(mm, isolated, result);

	return;

out:

	mem_cgroup_cancel_charge(new_page, memcg);

	mem_cgroup_cancel_charge(new_page, memcg, true);

	goto out_up_write;

}

mm/memcontrol.c

+23 −39
Original line number Diff line number Diff line
@@ -647,7 +647,7 @@ static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg, 


static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,

					 struct page *page,

					 int nr_pages)

					 bool compound, int nr_pages)

{

	/*

	 * Here, RSS means 'mapped anon' and anon's SwapCache. Shmem/tmpfs is
@@ -660,9 +660,11 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, 
		__this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_CACHE],

				nr_pages);



	if (PageTransHuge(page))

	if (compound) {

		VM_BUG_ON_PAGE(!PageTransHuge(page), page);

		__this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_RSS_HUGE],

				nr_pages);

	}



	/* pagein of a big page is an event. So, ignore page size */

	if (nr_pages > 0)
@@ -4513,30 +4515,24 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma, 
 * from old cgroup.

 */

static int mem_cgroup_move_account(struct page *page,

				   unsigned int nr_pages,

				   bool compound,

				   struct mem_cgroup *from,

				   struct mem_cgroup *to)

{

	unsigned long flags;

	unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1;

	int ret;

	bool anon;



	VM_BUG_ON(from == to);

	VM_BUG_ON_PAGE(PageLRU(page), page);

	/*

	 * The page is isolated from LRU. So, collapse function

	 * will not handle this page. But page splitting can happen.

	 * Do this check under compound_page_lock(). The caller should

	 * hold it.

	 */

	ret = -EBUSY;

	if (nr_pages > 1 && !PageTransHuge(page))

		goto out;

	VM_BUG_ON(compound && !PageTransHuge(page));



	/*

	 * Prevent mem_cgroup_replace_page() from looking at

	 * page->mem_cgroup of its source page while we change it.

	 */

	ret = -EBUSY;

	if (!trylock_page(page))

		goto out;
@@ -4591,9 +4587,9 @@ static int mem_cgroup_move_account(struct page *page, 
	ret = 0;



	local_irq_disable();

	mem_cgroup_charge_statistics(to, page, nr_pages);

	mem_cgroup_charge_statistics(to, page, compound, nr_pages);

	memcg_check_events(to, page);

	mem_cgroup_charge_statistics(from, page, -nr_pages);

	mem_cgroup_charge_statistics(from, page, compound, -nr_pages);

	memcg_check_events(from, page);

	local_irq_enable();

out_unlock:
@@ -4890,7 +4886,7 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd, 
		if (target_type == MC_TARGET_PAGE) {

			page = target.page;

			if (!isolate_lru_page(page)) {

				if (!mem_cgroup_move_account(page, HPAGE_PMD_NR,

				if (!mem_cgroup_move_account(page, true,

							     mc.from, mc.to)) {

					mc.precharge -= HPAGE_PMD_NR;

					mc.moved_charge += HPAGE_PMD_NR;
@@ -4919,7 +4915,8 @@ retry: 
			page = target.page;

			if (isolate_lru_page(page))

				goto put;

			if (!mem_cgroup_move_account(page, 1, mc.from, mc.to)) {

			if (!mem_cgroup_move_account(page, false,

						mc.from, mc.to)) {

				mc.precharge--;

				/* we uncharge from mc.from later. */

				mc.moved_charge++;
@@ -5258,10 +5255,11 @@ bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg) 
 * with mem_cgroup_cancel_charge() in case page instantiation fails.

 */

int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,

			  gfp_t gfp_mask, struct mem_cgroup **memcgp)

			  gfp_t gfp_mask, struct mem_cgroup **memcgp,

			  bool compound)

{

	struct mem_cgroup *memcg = NULL;

	unsigned int nr_pages = 1;

	unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1;

	int ret = 0;



	if (mem_cgroup_disabled())
@@ -5291,11 +5289,6 @@ int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, 
		}

	}



	if (PageTransHuge(page)) {

		nr_pages <<= compound_order(page);

		VM_BUG_ON_PAGE(!PageTransHuge(page), page);

	}



	if (!memcg)

		memcg = get_mem_cgroup_from_mm(mm);
@@ -5324,9 +5317,9 @@ out: 
 * Use mem_cgroup_cancel_charge() to cancel the transaction instead.

 */

void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg,

			      bool lrucare)

			      bool lrucare, bool compound)

{

	unsigned int nr_pages = 1;

	unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1;



	VM_BUG_ON_PAGE(!page->mapping, page);

	VM_BUG_ON_PAGE(PageLRU(page) && !lrucare, page);
@@ -5343,13 +5336,8 @@ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, 


	commit_charge(page, memcg, lrucare);



	if (PageTransHuge(page)) {

		nr_pages <<= compound_order(page);

		VM_BUG_ON_PAGE(!PageTransHuge(page), page);

	}



	local_irq_disable();

	mem_cgroup_charge_statistics(memcg, page, nr_pages);

	mem_cgroup_charge_statistics(memcg, page, compound, nr_pages);

	memcg_check_events(memcg, page);

	local_irq_enable();
@@ -5371,9 +5359,10 @@ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, 
 *

 * Cancel a charge transaction started by mem_cgroup_try_charge().

 */

void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg)

void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg,

		bool compound)

{

	unsigned int nr_pages = 1;

	unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1;



	if (mem_cgroup_disabled())

		return;
@@ -5385,11 +5374,6 @@ void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg) 
	if (!memcg)

		return;



	if (PageTransHuge(page)) {

		nr_pages <<= compound_order(page);

		VM_BUG_ON_PAGE(!PageTransHuge(page), page);

	}



	cancel_charge(memcg, nr_pages);

}
@@ -5750,7 +5734,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) 
	 * only synchronisation we have for udpating the per-CPU variables.

	 */

	VM_BUG_ON(!irqs_disabled());

	mem_cgroup_charge_statistics(memcg, page, -1);

	mem_cgroup_charge_statistics(memcg, page, false, -1);

	memcg_check_events(memcg, page);

}

CRA Git | Maintained and supported by SUSTech CRA and CCSE