mm: memcontrol: convert anon and file-thp to new mem_cgroup_charge() API
With the page->mapping requirement gone from memcg, we can charge anon and
file-thp pages in one single step, right after they're allocated.
This removes two out of three API calls - especially the tricky commit
step that needed to happen at just the right time between when the page is
"set up" and when it's "published" - somewhat vague and fluid concepts
that varied by page type. All we need is a freshly allocated page and a
memcg context to charge.
v2: prevent double charges on pre-allocated hugepages in khugepaged
[hannes@cmpxchg.org: Fix crash - *hpage could be ERR_PTR instead of NULL]
Link: http://lkml.kernel.org/r/20200512215813.GA487759@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Alex Shi <alex.shi@linux.alibaba.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: Qian Cai <cai@lca.pw>
Link: http://lkml.kernel.org/r/20200508183105.225460-13-hannes@cmpxchg.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/mm/memory.c b/mm/memory.c
index 543e41b..27e225b 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2645,7 +2645,6 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
struct page *new_page = NULL;
pte_t entry;
int page_copied = 0;
- struct mem_cgroup *memcg;
struct mmu_notifier_range range;
if (unlikely(anon_vma_prepare(vma)))
@@ -2676,8 +2675,9 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
}
}
- if (mem_cgroup_try_charge_delay(new_page, mm, GFP_KERNEL, &memcg))
+ if (mem_cgroup_charge(new_page, mm, GFP_KERNEL, false))
goto oom_free_new;
+ cgroup_throttle_swaprate(new_page, GFP_KERNEL);
__SetPageUptodate(new_page);
@@ -2710,7 +2710,6 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
* thread doing COW.
*/
ptep_clear_flush_notify(vma, vmf->address, vmf->pte);
- mem_cgroup_commit_charge(new_page, memcg, false);
page_add_new_anon_rmap(new_page, vma, vmf->address, false);
lru_cache_add_active_or_unevictable(new_page, vma);
/*
@@ -2749,8 +2748,6 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
/* Free the old page.. */
new_page = old_page;
page_copied = 1;
- } else {
- mem_cgroup_cancel_charge(new_page, memcg);
}
if (new_page)
@@ -3088,7 +3085,6 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
struct page *page = NULL, *swapcache;
- struct mem_cgroup *memcg;
swp_entry_t entry;
pte_t pte;
int locked;
@@ -3193,10 +3189,11 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
goto out_page;
}
- if (mem_cgroup_try_charge_delay(page, vma->vm_mm, GFP_KERNEL, &memcg)) {
+ if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL, true)) {
ret = VM_FAULT_OOM;
goto out_page;
}
+ cgroup_throttle_swaprate(page, GFP_KERNEL);
/*
* Back out if somebody else already faulted in this pte.
@@ -3243,11 +3240,9 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
/* ksm created a completely new copy */
if (unlikely(page != swapcache && swapcache)) {
- mem_cgroup_commit_charge(page, memcg, false);
page_add_new_anon_rmap(page, vma, vmf->address, false);
lru_cache_add_active_or_unevictable(page, vma);
} else {
- mem_cgroup_commit_charge(page, memcg, true);
do_page_add_anon_rmap(page, vma, vmf->address, exclusive);
activate_page(page);
}
@@ -3284,7 +3279,6 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
out:
return ret;
out_nomap:
- mem_cgroup_cancel_charge(page, memcg);
pte_unmap_unlock(vmf->pte, vmf->ptl);
out_page:
unlock_page(page);
@@ -3305,7 +3299,6 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
- struct mem_cgroup *memcg;
struct page *page;
vm_fault_t ret = 0;
pte_t entry;
@@ -3358,8 +3351,9 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
if (!page)
goto oom;
- if (mem_cgroup_try_charge_delay(page, vma->vm_mm, GFP_KERNEL, &memcg))
+ if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL, false))
goto oom_free_page;
+ cgroup_throttle_swaprate(page, GFP_KERNEL);
/*
* The memory barrier inside __SetPageUptodate makes sure that
@@ -3384,13 +3378,11 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
/* Deliver the page fault to userland, check inside PT lock */
if (userfaultfd_missing(vma)) {
pte_unmap_unlock(vmf->pte, vmf->ptl);
- mem_cgroup_cancel_charge(page, memcg);
put_page(page);
return handle_userfault(vmf, VM_UFFD_MISSING);
}
inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
- mem_cgroup_commit_charge(page, memcg, false);
page_add_new_anon_rmap(page, vma, vmf->address, false);
lru_cache_add_active_or_unevictable(page, vma);
setpte:
@@ -3402,7 +3394,6 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
pte_unmap_unlock(vmf->pte, vmf->ptl);
return ret;
release:
- mem_cgroup_cancel_charge(page, memcg);
put_page(page);
goto unlock;
oom_free_page:
@@ -3607,7 +3598,6 @@ static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
* mapping. If needed, the fucntion allocates page table or use pre-allocated.
*
* @vmf: fault environment
- * @memcg: memcg to charge page (only for private mappings)
* @page: page to map
*
* Caller must take care of unlocking vmf->ptl, if vmf->pte is non-NULL on
@@ -3618,8 +3608,7 @@ static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
*
* Return: %0 on success, %VM_FAULT_ code in case of error.
*/
-vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg,
- struct page *page)
+vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page)
{
struct vm_area_struct *vma = vmf->vma;
bool write = vmf->flags & FAULT_FLAG_WRITE;
@@ -3627,9 +3616,6 @@ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg,
vm_fault_t ret;
if (pmd_none(*vmf->pmd) && PageTransCompound(page)) {
- /* THP on COW? */
- VM_BUG_ON_PAGE(memcg, page);
-
ret = do_set_pmd(vmf, page);
if (ret != VM_FAULT_FALLBACK)
return ret;
@@ -3652,7 +3638,6 @@ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg,
/* copy-on-write page */
if (write && !(vma->vm_flags & VM_SHARED)) {
inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
- mem_cgroup_commit_charge(page, memcg, false);
page_add_new_anon_rmap(page, vma, vmf->address, false);
lru_cache_add_active_or_unevictable(page, vma);
} else {
@@ -3702,7 +3687,7 @@ vm_fault_t finish_fault(struct vm_fault *vmf)
if (!(vmf->vma->vm_flags & VM_SHARED))
ret = check_stable_address_space(vmf->vma->vm_mm);
if (!ret)
- ret = alloc_set_pte(vmf, vmf->memcg, page);
+ ret = alloc_set_pte(vmf, page);
if (vmf->pte)
pte_unmap_unlock(vmf->pte, vmf->ptl);
return ret;
@@ -3862,11 +3847,11 @@ static vm_fault_t do_cow_fault(struct vm_fault *vmf)
if (!vmf->cow_page)
return VM_FAULT_OOM;
- if (mem_cgroup_try_charge_delay(vmf->cow_page, vma->vm_mm,
- GFP_KERNEL, &vmf->memcg)) {
+ if (mem_cgroup_charge(vmf->cow_page, vma->vm_mm, GFP_KERNEL, false)) {
put_page(vmf->cow_page);
return VM_FAULT_OOM;
}
+ cgroup_throttle_swaprate(vmf->cow_page, GFP_KERNEL);
ret = __do_fault(vmf);
if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
@@ -3884,7 +3869,6 @@ static vm_fault_t do_cow_fault(struct vm_fault *vmf)
goto uncharge_out;
return ret;
uncharge_out:
- mem_cgroup_cancel_charge(vmf->cow_page, vmf->memcg);
put_page(vmf->cow_page);
return ret;
}