* [v3 PATCH 1/7] mm: memory: add orig_pmd to struct vm_fault
2021-05-18 20:07 [v3 PATCH 0/7] mm: thp: use generic THP migration for NUMA hinting fault Yang Shi
@ 2021-05-18 20:07 ` Yang Shi
2021-05-19 8:13 ` Mel Gorman
2021-05-18 20:07 ` [v3 PATCH 2/7] mm: memory: make numa_migrate_prep() non-static Yang Shi
` (5 subsequent siblings)
6 siblings, 1 reply; 9+ messages in thread
From: Yang Shi @ 2021-05-18 20:07 UTC (permalink / raw)
To: mgorman, kirill.shutemov, ziy, ying.huang, mhocko, hughd,
gerald.schaefer, hca, gor, borntraeger, akpm
Cc: shy828301, linux-mm, linux-s390, linux-kernel
Add orig_pmd to struct vm_fault so the "orig_pmd" parameter used by huge page
fault could be removed, just like its PTE counterpart does.
Signed-off-by: Yang Shi <shy828301@gmail.com>
---
include/linux/huge_mm.h | 9 ++++-----
include/linux/mm.h | 7 ++++++-
mm/huge_memory.c | 9 ++++++---
mm/memory.c | 26 +++++++++++++-------------
4 files changed, 29 insertions(+), 22 deletions(-)
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 60dad7c88d72..77d6d454df90 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -11,7 +11,7 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf);
int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma);
-void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd);
+void huge_pmd_set_accessed(struct vm_fault *vmf);
int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pud_t *dst_pud, pud_t *src_pud, unsigned long addr,
struct vm_area_struct *vma);
@@ -24,7 +24,7 @@ static inline void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud)
}
#endif
-vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd);
+vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf);
struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
unsigned long addr, pmd_t *pmd,
unsigned int flags);
@@ -283,7 +283,7 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr,
pud_t *pud, int flags, struct dev_pagemap **pgmap);
-vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd);
+vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf);
extern struct page *huge_zero_page;
@@ -429,8 +429,7 @@ static inline spinlock_t *pud_trans_huge_lock(pud_t *pud,
return NULL;
}
-static inline vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf,
- pmd_t orig_pmd)
+static inline vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
{
return 0;
}
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 6ce7bac74530..b3a4b405364b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -550,7 +550,12 @@ struct vm_fault {
pud_t *pud; /* Pointer to pud entry matching
* the 'address'
*/
- pte_t orig_pte; /* Value of PTE at the time of fault */
+ union {
+ pte_t orig_pte; /* Value of PTE at the time of fault */
+ pmd_t orig_pmd; /* Value of PMD at the time of fault,
+ * used by PMD fault only.
+ */
+ };
struct page *cow_page; /* Page handler may use for COW fault */
struct page *page; /* ->fault handlers should return a
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 19195fca1aee..692788988530 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1245,11 +1245,12 @@ void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud)
}
#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
-void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd)
+void huge_pmd_set_accessed(struct vm_fault *vmf)
{
pmd_t entry;
unsigned long haddr;
bool write = vmf->flags & FAULT_FLAG_WRITE;
+ pmd_t orig_pmd = vmf->orig_pmd;
vmf->ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd);
if (unlikely(!pmd_same(*vmf->pmd, orig_pmd)))
@@ -1266,11 +1267,12 @@ void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd)
spin_unlock(vmf->ptl);
}
-vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd)
+vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
struct page *page;
unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
+ pmd_t orig_pmd = vmf->orig_pmd;
vmf->ptl = pmd_lockptr(vma->vm_mm, vmf->pmd);
VM_BUG_ON_VMA(!vma->anon_vma, vma);
@@ -1406,9 +1408,10 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
}
/* NUMA hinting page fault entry point for trans huge pmds */
-vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd)
+vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
+ pmd_t pmd = vmf->orig_pmd;
struct anon_vma *anon_vma = NULL;
struct page *page;
unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
diff --git a/mm/memory.c b/mm/memory.c
index 97ca3e51cf85..f9df3ab12813 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4252,12 +4252,12 @@ static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf)
}
/* `inline' is required to avoid gcc 4.1.2 build error */
-static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd)
+static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf)
{
if (vma_is_anonymous(vmf->vma)) {
- if (userfaultfd_huge_pmd_wp(vmf->vma, orig_pmd))
+ if (userfaultfd_huge_pmd_wp(vmf->vma, vmf->orig_pmd))
return handle_userfault(vmf, VM_UFFD_WP);
- return do_huge_pmd_wp_page(vmf, orig_pmd);
+ return do_huge_pmd_wp_page(vmf);
}
if (vmf->vma->vm_ops->huge_fault) {
vm_fault_t ret = vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD);
@@ -4484,26 +4484,26 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
if (!(ret & VM_FAULT_FALLBACK))
return ret;
} else {
- pmd_t orig_pmd = *vmf.pmd;
+ vmf.orig_pmd = *vmf.pmd;
barrier();
- if (unlikely(is_swap_pmd(orig_pmd))) {
+ if (unlikely(is_swap_pmd(vmf.orig_pmd))) {
VM_BUG_ON(thp_migration_supported() &&
- !is_pmd_migration_entry(orig_pmd));
- if (is_pmd_migration_entry(orig_pmd))
+ !is_pmd_migration_entry(vmf.orig_pmd));
+ if (is_pmd_migration_entry(vmf.orig_pmd))
pmd_migration_entry_wait(mm, vmf.pmd);
return 0;
}
- if (pmd_trans_huge(orig_pmd) || pmd_devmap(orig_pmd)) {
- if (pmd_protnone(orig_pmd) && vma_is_accessible(vma))
- return do_huge_pmd_numa_page(&vmf, orig_pmd);
+ if (pmd_trans_huge(vmf.orig_pmd) || pmd_devmap(vmf.orig_pmd)) {
+ if (pmd_protnone(vmf.orig_pmd) && vma_is_accessible(vma))
+ return do_huge_pmd_numa_page(&vmf);
- if (dirty && !pmd_write(orig_pmd)) {
- ret = wp_huge_pmd(&vmf, orig_pmd);
+ if (dirty && !pmd_write(vmf.orig_pmd)) {
+ ret = wp_huge_pmd(&vmf);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
} else {
- huge_pmd_set_accessed(&vmf, orig_pmd);
+ huge_pmd_set_accessed(&vmf);
return 0;
}
}
--
2.26.2
^ permalink raw reply related [flat|nested] 9+ messages in thread
* Re: [v3 PATCH 1/7] mm: memory: add orig_pmd to struct vm_fault
2021-05-18 20:07 ` [v3 PATCH 1/7] mm: memory: add orig_pmd to struct vm_fault Yang Shi
@ 2021-05-19 8:13 ` Mel Gorman
0 siblings, 0 replies; 9+ messages in thread
From: Mel Gorman @ 2021-05-19 8:13 UTC (permalink / raw)
To: Yang Shi
Cc: kirill.shutemov, ziy, ying.huang, mhocko, hughd, gerald.schaefer,
hca, gor, borntraeger, akpm, linux-mm, linux-s390, linux-kernel
On Tue, May 18, 2021 at 01:07:55PM -0700, Yang Shi wrote:
> Add orig_pmd to struct vm_fault so the "orig_pmd" parameter used by huge page
> fault could be removed, just like its PTE counterpart does.
>
> Signed-off-by: Yang Shi <shy828301@gmail.com>
Acked-by: Mel Gorman <mgorman@suse.de>
--
Mel Gorman
SUSE Labs
^ permalink raw reply [flat|nested] 9+ messages in thread
* [v3 PATCH 2/7] mm: memory: make numa_migrate_prep() non-static
2021-05-18 20:07 [v3 PATCH 0/7] mm: thp: use generic THP migration for NUMA hinting fault Yang Shi
2021-05-18 20:07 ` [v3 PATCH 1/7] mm: memory: add orig_pmd to struct vm_fault Yang Shi
@ 2021-05-18 20:07 ` Yang Shi
2021-05-18 20:07 ` [v3 PATCH 3/7] mm: thp: refactor NUMA fault handling Yang Shi
` (4 subsequent siblings)
6 siblings, 0 replies; 9+ messages in thread
From: Yang Shi @ 2021-05-18 20:07 UTC (permalink / raw)
To: mgorman, kirill.shutemov, ziy, ying.huang, mhocko, hughd,
gerald.schaefer, hca, gor, borntraeger, akpm
Cc: shy828301, linux-mm, linux-s390, linux-kernel
The numa_migrate_prep() will be used by huge NUMA fault as well in the following
patch, make it non-static.
Acked-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Yang Shi <shy828301@gmail.com>
---
mm/internal.h | 3 +++
mm/memory.c | 5 ++---
2 files changed, 5 insertions(+), 3 deletions(-)
diff --git a/mm/internal.h b/mm/internal.h
index 8a176d1d0176..28fc471b4669 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -653,4 +653,7 @@ int vmap_pages_range_noflush(unsigned long addr, unsigned long end,
void vunmap_range_noflush(unsigned long start, unsigned long end);
+int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
+ unsigned long addr, int page_nid, int *flags);
+
#endif /* __MM_INTERNAL_H */
diff --git a/mm/memory.c b/mm/memory.c
index f9df3ab12813..a2f2c2a8d28e 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4129,9 +4129,8 @@ static vm_fault_t do_fault(struct vm_fault *vmf)
return ret;
}
-static int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
- unsigned long addr, int page_nid,
- int *flags)
+int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
+ unsigned long addr, int page_nid, int *flags)
{
get_page(page);
--
2.26.2
^ permalink raw reply related [flat|nested] 9+ messages in thread
* [v3 PATCH 3/7] mm: thp: refactor NUMA fault handling
2021-05-18 20:07 [v3 PATCH 0/7] mm: thp: use generic THP migration for NUMA hinting fault Yang Shi
2021-05-18 20:07 ` [v3 PATCH 1/7] mm: memory: add orig_pmd to struct vm_fault Yang Shi
2021-05-18 20:07 ` [v3 PATCH 2/7] mm: memory: make numa_migrate_prep() non-static Yang Shi
@ 2021-05-18 20:07 ` Yang Shi
2021-05-18 20:07 ` [v3 PATCH 4/7] mm: migrate: account THP NUMA migration counters correctly Yang Shi
` (3 subsequent siblings)
6 siblings, 0 replies; 9+ messages in thread
From: Yang Shi @ 2021-05-18 20:07 UTC (permalink / raw)
To: mgorman, kirill.shutemov, ziy, ying.huang, mhocko, hughd,
gerald.schaefer, hca, gor, borntraeger, akpm
Cc: shy828301, linux-mm, linux-s390, linux-kernel
When the THP NUMA fault support was added THP migration was not supported yet.
So the ad hoc THP migration was implemented in NUMA fault handling. Since v4.14
THP migration has been supported so it doesn't make too much sense to still keep
another THP migration implementation rather than using the generic migration
code.
This patch reworked the NUMA fault handling to use generic migration implementation
to migrate misplaced page. There is no functional change.
After the refactor the flow of NUMA fault handling looks just like its
PTE counterpart:
Acquire ptl
Prepare for migration (elevate page refcount)
Release ptl
Isolate page from lru and elevate page refcount
Migrate the misplaced THP
If migration is failed just restore the old normal PMD.
In the old code anon_vma lock was needed to serialize THP migration
against THP split, but since then the THP code has been reworked a lot,
it seems anon_vma lock is not required anymore to avoid the race.
The page refcount elevation when holding ptl should prevent from THP
split.
Use migrate_misplaced_page() for both base page and THP NUMA hinting
fault and remove all the dead and duplicate code.
Acked-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Yang Shi <shy828301@gmail.com>
---
include/linux/migrate.h | 23 ------
mm/huge_memory.c | 147 +++++++++++----------------------
mm/internal.h | 18 ----
mm/migrate.c | 177 ++++++++--------------------------------
4 files changed, 79 insertions(+), 286 deletions(-)
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 4bb4e519e3f5..163d6f2b03d1 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -95,14 +95,9 @@ static inline void __ClearPageMovable(struct page *page)
#endif
#ifdef CONFIG_NUMA_BALANCING
-extern bool pmd_trans_migrating(pmd_t pmd);
extern int migrate_misplaced_page(struct page *page,
struct vm_area_struct *vma, int node);
#else
-static inline bool pmd_trans_migrating(pmd_t pmd)
-{
- return false;
-}
static inline int migrate_misplaced_page(struct page *page,
struct vm_area_struct *vma, int node)
{
@@ -110,24 +105,6 @@ static inline int migrate_misplaced_page(struct page *page,
}
#endif /* CONFIG_NUMA_BALANCING */
-#if defined(CONFIG_NUMA_BALANCING) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
-extern int migrate_misplaced_transhuge_page(struct mm_struct *mm,
- struct vm_area_struct *vma,
- pmd_t *pmd, pmd_t entry,
- unsigned long address,
- struct page *page, int node);
-#else
-static inline int migrate_misplaced_transhuge_page(struct mm_struct *mm,
- struct vm_area_struct *vma,
- pmd_t *pmd, pmd_t entry,
- unsigned long address,
- struct page *page, int node)
-{
- return -EAGAIN;
-}
-#endif /* CONFIG_NUMA_BALANCING && CONFIG_TRANSPARENT_HUGEPAGE*/
-
-
#ifdef CONFIG_MIGRATION
/*
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 692788988530..b8526b9b041a 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1411,94 +1411,22 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
- pmd_t pmd = vmf->orig_pmd;
- struct anon_vma *anon_vma = NULL;
+ pmd_t oldpmd = vmf->orig_pmd;
+ pmd_t pmd;
struct page *page;
unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
- int page_nid = NUMA_NO_NODE, this_nid = numa_node_id();
+ int page_nid = NUMA_NO_NODE;
int target_nid, last_cpupid = -1;
- bool page_locked;
bool migrated = false;
- bool was_writable;
+ bool was_writable = pmd_savedwrite(oldpmd);
int flags = 0;
vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
- if (unlikely(!pmd_same(pmd, *vmf->pmd)))
- goto out_unlock;
-
- /*
- * If there are potential migrations, wait for completion and retry
- * without disrupting NUMA hinting information. Do not relock and
- * check_same as the page may no longer be mapped.
- */
- if (unlikely(pmd_trans_migrating(*vmf->pmd))) {
- page = pmd_page(*vmf->pmd);
- if (!get_page_unless_zero(page))
- goto out_unlock;
+ if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) {
spin_unlock(vmf->ptl);
- put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE);
goto out;
}
- page = pmd_page(pmd);
- BUG_ON(is_huge_zero_page(page));
- page_nid = page_to_nid(page);
- last_cpupid = page_cpupid_last(page);
- count_vm_numa_event(NUMA_HINT_FAULTS);
- if (page_nid == this_nid) {
- count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
- flags |= TNF_FAULT_LOCAL;
- }
-
- /* See similar comment in do_numa_page for explanation */
- if (!pmd_savedwrite(pmd))
- flags |= TNF_NO_GROUP;
-
- /*
- * Acquire the page lock to serialise THP migrations but avoid dropping
- * page_table_lock if at all possible
- */
- page_locked = trylock_page(page);
- target_nid = mpol_misplaced(page, vma, haddr);
- /* Migration could have started since the pmd_trans_migrating check */
- if (!page_locked) {
- page_nid = NUMA_NO_NODE;
- if (!get_page_unless_zero(page))
- goto out_unlock;
- spin_unlock(vmf->ptl);
- put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE);
- goto out;
- } else if (target_nid == NUMA_NO_NODE) {
- /* There are no parallel migrations and page is in the right
- * node. Clear the numa hinting info in this pmd.
- */
- goto clear_pmdnuma;
- }
-
- /*
- * Page is misplaced. Page lock serialises migrations. Acquire anon_vma
- * to serialises splits
- */
- get_page(page);
- spin_unlock(vmf->ptl);
- anon_vma = page_lock_anon_vma_read(page);
-
- /* Confirm the PMD did not change while page_table_lock was released */
- spin_lock(vmf->ptl);
- if (unlikely(!pmd_same(pmd, *vmf->pmd))) {
- unlock_page(page);
- put_page(page);
- page_nid = NUMA_NO_NODE;
- goto out_unlock;
- }
-
- /* Bail if we fail to protect against THP splits for any reason */
- if (unlikely(!anon_vma)) {
- put_page(page);
- page_nid = NUMA_NO_NODE;
- goto clear_pmdnuma;
- }
-
/*
* Since we took the NUMA fault, we must have observed the !accessible
* bit. Make sure all other CPUs agree with that, to avoid them
@@ -1525,43 +1453,60 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
haddr + HPAGE_PMD_SIZE);
}
- /*
- * Migrate the THP to the requested node, returns with page unlocked
- * and access rights restored.
- */
+ pmd = pmd_modify(oldpmd, vma->vm_page_prot);
+ page = vm_normal_page_pmd(vma, haddr, pmd);
+ if (!page) {
+ spin_unlock(vmf->ptl);
+ goto out_map;
+ }
+
+ /* See similar comment in do_numa_page for explanation */
+ if (!was_writable)
+ flags |= TNF_NO_GROUP;
+
+ page_nid = page_to_nid(page);
+ last_cpupid = page_cpupid_last(page);
+ target_nid = numa_migrate_prep(page, vma, haddr, page_nid,
+ &flags);
+
+ if (target_nid == NUMA_NO_NODE) {
+ put_page(page);
+ goto out_map;
+ }
+
spin_unlock(vmf->ptl);
- migrated = migrate_misplaced_transhuge_page(vma->vm_mm, vma,
- vmf->pmd, pmd, vmf->address, page, target_nid);
+ migrated = migrate_misplaced_page(page, vma, target_nid);
if (migrated) {
flags |= TNF_MIGRATED;
page_nid = target_nid;
- } else
+ } else {
flags |= TNF_MIGRATE_FAIL;
-
- goto out;
-clear_pmdnuma:
- BUG_ON(!PageLocked(page));
- was_writable = pmd_savedwrite(pmd);
- pmd = pmd_modify(pmd, vma->vm_page_prot);
- pmd = pmd_mkyoung(pmd);
- if (was_writable)
- pmd = pmd_mkwrite(pmd);
- set_pmd_at(vma->vm_mm, haddr, vmf->pmd, pmd);
- update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
- unlock_page(page);
-out_unlock:
- spin_unlock(vmf->ptl);
+ vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
+ if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) {
+ spin_unlock(vmf->ptl);
+ goto out;
+ }
+ goto out_map;
+ }
out:
- if (anon_vma)
- page_unlock_anon_vma_read(anon_vma);
-
if (page_nid != NUMA_NO_NODE)
task_numa_fault(last_cpupid, page_nid, HPAGE_PMD_NR,
flags);
return 0;
+
+out_map:
+ /* Restore the PMD */
+ pmd = pmd_modify(oldpmd, vma->vm_page_prot);
+ pmd = pmd_mkyoung(pmd);
+ if (was_writable)
+ pmd = pmd_mkwrite(pmd);
+ set_pmd_at(vma->vm_mm, haddr, vmf->pmd, pmd);
+ update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
+ spin_unlock(vmf->ptl);
+ goto out;
}
/*
diff --git a/mm/internal.h b/mm/internal.h
index 28fc471b4669..d9a5d00bee1a 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -375,23 +375,6 @@ extern int mlock_future_check(struct mm_struct *mm, unsigned long flags,
*/
extern void clear_page_mlock(struct page *page);
-/*
- * mlock_migrate_page - called only from migrate_misplaced_transhuge_page()
- * (because that does not go through the full procedure of migration ptes):
- * to migrate the Mlocked page flag; update statistics.
- */
-static inline void mlock_migrate_page(struct page *newpage, struct page *page)
-{
- if (TestClearPageMlocked(page)) {
- int nr_pages = thp_nr_pages(page);
-
- /* Holding pmd lock, no change in irq context: __mod is safe */
- __mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages);
- SetPageMlocked(newpage);
- __mod_zone_page_state(page_zone(newpage), NR_MLOCK, nr_pages);
- }
-}
-
extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma);
/*
@@ -442,7 +425,6 @@ static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf,
#else /* !CONFIG_MMU */
static inline void clear_page_mlock(struct page *page) { }
static inline void mlock_vma_page(struct page *page) { }
-static inline void mlock_migrate_page(struct page *new, struct page *old) { }
static inline void vunmap_range_noflush(unsigned long start, unsigned long end)
{
}
diff --git a/mm/migrate.c b/mm/migrate.c
index e7a173da74ec..4e0c2644256a 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -2045,6 +2045,23 @@ static struct page *alloc_misplaced_dst_page(struct page *page,
return newpage;
}
+static struct page *alloc_misplaced_dst_page_thp(struct page *page,
+ unsigned long data)
+{
+ int nid = (int) data;
+ struct page *newpage;
+
+ newpage = alloc_pages_node(nid, (GFP_TRANSHUGE_LIGHT | __GFP_THISNODE),
+ HPAGE_PMD_ORDER);
+ if (!newpage)
+ goto out;
+
+ prep_transhuge_page(newpage);
+
+out:
+ return newpage;
+}
+
static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
{
int page_lru;
@@ -2083,12 +2100,6 @@ static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
return 1;
}
-bool pmd_trans_migrating(pmd_t pmd)
-{
- struct page *page = pmd_page(pmd);
- return PageLocked(page);
-}
-
/*
* Attempt to migrate a misplaced page to the specified destination
* node. Caller is expected to have an elevated reference count on
@@ -2101,6 +2112,20 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
int isolated;
int nr_remaining;
LIST_HEAD(migratepages);
+ new_page_t *new;
+ bool compound;
+
+ /*
+ * PTE mapped THP or HugeTLB page can't reach here so the page could
+ * be either base page or THP. And it must be head page if it is
+ * THP.
+ */
+ compound = PageTransHuge(page);
+
+ if (compound)
+ new = alloc_misplaced_dst_page_thp;
+ else
+ new = alloc_misplaced_dst_page;
/*
* Don't migrate file pages that are mapped in multiple processes
@@ -2122,9 +2147,8 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
goto out;
list_add(&page->lru, &migratepages);
- nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_page,
- NULL, node, MIGRATE_ASYNC,
- MR_NUMA_MISPLACED);
+ nr_remaining = migrate_pages(&migratepages, *new, NULL, node,
+ MIGRATE_ASYNC, MR_NUMA_MISPLACED);
if (nr_remaining) {
if (!list_empty(&migratepages)) {
list_del(&page->lru);
@@ -2143,141 +2167,6 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
return 0;
}
#endif /* CONFIG_NUMA_BALANCING */
-
-#if defined(CONFIG_NUMA_BALANCING) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
-/*
- * Migrates a THP to a given target node. page must be locked and is unlocked
- * before returning.
- */
-int migrate_misplaced_transhuge_page(struct mm_struct *mm,
- struct vm_area_struct *vma,
- pmd_t *pmd, pmd_t entry,
- unsigned long address,
- struct page *page, int node)
-{
- spinlock_t *ptl;
- pg_data_t *pgdat = NODE_DATA(node);
- int isolated = 0;
- struct page *new_page = NULL;
- int page_lru = page_is_file_lru(page);
- unsigned long start = address & HPAGE_PMD_MASK;
-
- new_page = alloc_pages_node(node,
- (GFP_TRANSHUGE_LIGHT | __GFP_THISNODE),
- HPAGE_PMD_ORDER);
- if (!new_page)
- goto out_fail;
- prep_transhuge_page(new_page);
-
- isolated = numamigrate_isolate_page(pgdat, page);
- if (!isolated) {
- put_page(new_page);
- goto out_fail;
- }
-
- /* Prepare a page as a migration target */
- __SetPageLocked(new_page);
- if (PageSwapBacked(page))
- __SetPageSwapBacked(new_page);
-
- /* anon mapping, we can simply copy page->mapping to the new page: */
- new_page->mapping = page->mapping;
- new_page->index = page->index;
- /* flush the cache before copying using the kernel virtual address */
- flush_cache_range(vma, start, start + HPAGE_PMD_SIZE);
- migrate_page_copy(new_page, page);
- WARN_ON(PageLRU(new_page));
-
- /* Recheck the target PMD */
- ptl = pmd_lock(mm, pmd);
- if (unlikely(!pmd_same(*pmd, entry) || !page_ref_freeze(page, 2))) {
- spin_unlock(ptl);
-
- /* Reverse changes made by migrate_page_copy() */
- if (TestClearPageActive(new_page))
- SetPageActive(page);
- if (TestClearPageUnevictable(new_page))
- SetPageUnevictable(page);
-
- unlock_page(new_page);
- put_page(new_page); /* Free it */
-
- /* Retake the callers reference and putback on LRU */
- get_page(page);
- putback_lru_page(page);
- mod_node_page_state(page_pgdat(page),
- NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR);
-
- goto out_unlock;
- }
-
- entry = mk_huge_pmd(new_page, vma->vm_page_prot);
- entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
-
- /*
- * Overwrite the old entry under pagetable lock and establish
- * the new PTE. Any parallel GUP will either observe the old
- * page blocking on the page lock, block on the page table
- * lock or observe the new page. The SetPageUptodate on the
- * new page and page_add_new_anon_rmap guarantee the copy is
- * visible before the pagetable update.
- */
- page_add_anon_rmap(new_page, vma, start, true);
- /*
- * At this point the pmd is numa/protnone (i.e. non present) and the TLB
- * has already been flushed globally. So no TLB can be currently
- * caching this non present pmd mapping. There's no need to clear the
- * pmd before doing set_pmd_at(), nor to flush the TLB after
- * set_pmd_at(). Clearing the pmd here would introduce a race
- * condition against MADV_DONTNEED, because MADV_DONTNEED only holds the
- * mmap_lock for reading. If the pmd is set to NULL at any given time,
- * MADV_DONTNEED won't wait on the pmd lock and it'll skip clearing this
- * pmd.
- */
- set_pmd_at(mm, start, pmd, entry);
- update_mmu_cache_pmd(vma, address, &entry);
-
- page_ref_unfreeze(page, 2);
- mlock_migrate_page(new_page, page);
- page_remove_rmap(page, true);
- set_page_owner_migrate_reason(new_page, MR_NUMA_MISPLACED);
-
- spin_unlock(ptl);
-
- /* Take an "isolate" reference and put new page on the LRU. */
- get_page(new_page);
- putback_lru_page(new_page);
-
- unlock_page(new_page);
- unlock_page(page);
- put_page(page); /* Drop the rmap reference */
- put_page(page); /* Drop the LRU isolation reference */
-
- count_vm_events(PGMIGRATE_SUCCESS, HPAGE_PMD_NR);
- count_vm_numa_events(NUMA_PAGE_MIGRATE, HPAGE_PMD_NR);
-
- mod_node_page_state(page_pgdat(page),
- NR_ISOLATED_ANON + page_lru,
- -HPAGE_PMD_NR);
- return isolated;
-
-out_fail:
- count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
- ptl = pmd_lock(mm, pmd);
- if (pmd_same(*pmd, entry)) {
- entry = pmd_modify(entry, vma->vm_page_prot);
- set_pmd_at(mm, start, pmd, entry);
- update_mmu_cache_pmd(vma, address, &entry);
- }
- spin_unlock(ptl);
-
-out_unlock:
- unlock_page(page);
- put_page(page);
- return 0;
-}
-#endif /* CONFIG_NUMA_BALANCING */
-
#endif /* CONFIG_NUMA */
#ifdef CONFIG_DEVICE_PRIVATE
--
2.26.2
^ permalink raw reply related [flat|nested] 9+ messages in thread
* [v3 PATCH 4/7] mm: migrate: account THP NUMA migration counters correctly
2021-05-18 20:07 [v3 PATCH 0/7] mm: thp: use generic THP migration for NUMA hinting fault Yang Shi
` (2 preceding siblings ...)
2021-05-18 20:07 ` [v3 PATCH 3/7] mm: thp: refactor NUMA fault handling Yang Shi
@ 2021-05-18 20:07 ` Yang Shi
2021-05-18 20:07 ` [v3 PATCH 5/7] mm: migrate: don't split THP for misplaced NUMA page Yang Shi
` (2 subsequent siblings)
6 siblings, 0 replies; 9+ messages in thread
From: Yang Shi @ 2021-05-18 20:07 UTC (permalink / raw)
To: mgorman, kirill.shutemov, ziy, ying.huang, mhocko, hughd,
gerald.schaefer, hca, gor, borntraeger, akpm
Cc: shy828301, linux-mm, linux-s390, linux-kernel
Now both base page and THP NUMA migration is done via migrate_misplaced_page(),
keep the counters correctly for THP.
Acked-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Yang Shi <shy828301@gmail.com>
---
mm/migrate.c | 7 ++++---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/mm/migrate.c b/mm/migrate.c
index 4e0c2644256a..26f79f516100 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -2114,6 +2114,7 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
LIST_HEAD(migratepages);
new_page_t *new;
bool compound;
+ unsigned int nr_pages = thp_nr_pages(page);
/*
* PTE mapped THP or HugeTLB page can't reach here so the page could
@@ -2152,13 +2153,13 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
if (nr_remaining) {
if (!list_empty(&migratepages)) {
list_del(&page->lru);
- dec_node_page_state(page, NR_ISOLATED_ANON +
- page_is_file_lru(page));
+ mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON +
+ page_is_file_lru(page), -nr_pages);
putback_lru_page(page);
}
isolated = 0;
} else
- count_vm_numa_event(NUMA_PAGE_MIGRATE);
+ count_vm_numa_events(NUMA_PAGE_MIGRATE, nr_pages);
BUG_ON(!list_empty(&migratepages));
return isolated;
--
2.26.2
^ permalink raw reply related [flat|nested] 9+ messages in thread
* [v3 PATCH 5/7] mm: migrate: don't split THP for misplaced NUMA page
2021-05-18 20:07 [v3 PATCH 0/7] mm: thp: use generic THP migration for NUMA hinting fault Yang Shi
` (3 preceding siblings ...)
2021-05-18 20:07 ` [v3 PATCH 4/7] mm: migrate: account THP NUMA migration counters correctly Yang Shi
@ 2021-05-18 20:07 ` Yang Shi
2021-05-18 20:08 ` [v3 PATCH 6/7] mm: migrate: check mapcount for THP instead of refcount Yang Shi
2021-05-18 20:08 ` [v3 PATCH 7/7] mm: thp: skip make PMD PROT_NONE if THP migration is not supported Yang Shi
6 siblings, 0 replies; 9+ messages in thread
From: Yang Shi @ 2021-05-18 20:07 UTC (permalink / raw)
To: mgorman, kirill.shutemov, ziy, ying.huang, mhocko, hughd,
gerald.schaefer, hca, gor, borntraeger, akpm
Cc: shy828301, linux-mm, linux-s390, linux-kernel
The old behavior didn't split THP if migration is failed due to lack of
memory on the target node. But the THP migration does split THP, so keep
the old behavior for misplaced NUMA page migration.
Acked-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Yang Shi <shy828301@gmail.com>
---
mm/migrate.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/mm/migrate.c b/mm/migrate.c
index 26f79f516100..035daaec1ca0 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1420,6 +1420,7 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
int swapwrite = current->flags & PF_SWAPWRITE;
int rc, nr_subpages;
LIST_HEAD(ret_pages);
+ bool nosplit = (reason == MR_NUMA_MISPLACED);
trace_mm_migrate_pages_start(mode, reason);
@@ -1491,8 +1492,9 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
/*
* When memory is low, don't bother to try to migrate
* other pages, just exit.
+ * THP NUMA faulting doesn't split THP to retry.
*/
- if (is_thp) {
+ if (is_thp && !nosplit) {
if (!try_split_thp(page, &page2, from)) {
nr_thp_split++;
goto retry;
--
2.26.2
^ permalink raw reply related [flat|nested] 9+ messages in thread
* [v3 PATCH 6/7] mm: migrate: check mapcount for THP instead of refcount
2021-05-18 20:07 [v3 PATCH 0/7] mm: thp: use generic THP migration for NUMA hinting fault Yang Shi
` (4 preceding siblings ...)
2021-05-18 20:07 ` [v3 PATCH 5/7] mm: migrate: don't split THP for misplaced NUMA page Yang Shi
@ 2021-05-18 20:08 ` Yang Shi
2021-05-18 20:08 ` [v3 PATCH 7/7] mm: thp: skip make PMD PROT_NONE if THP migration is not supported Yang Shi
6 siblings, 0 replies; 9+ messages in thread
From: Yang Shi @ 2021-05-18 20:08 UTC (permalink / raw)
To: mgorman, kirill.shutemov, ziy, ying.huang, mhocko, hughd,
gerald.schaefer, hca, gor, borntraeger, akpm
Cc: shy828301, linux-mm, linux-s390, linux-kernel
The generic migration path will check refcount, so no need check refcount here.
But the old code actually prevents from migrating shared THP (mapped by multiple
processes), so bail out early if mapcount is > 1 to keep the behavior.
Signed-off-by: Yang Shi <shy828301@gmail.com>
---
mm/migrate.c | 16 ++++------------
1 file changed, 4 insertions(+), 12 deletions(-)
diff --git a/mm/migrate.c b/mm/migrate.c
index 035daaec1ca0..77215f28502b 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -2070,6 +2070,10 @@ static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
VM_BUG_ON_PAGE(compound_order(page) && !PageTransHuge(page), page);
+ /* Do not migrate THP mapped by multiple processes */
+ if (PageTransHuge(page) && total_mapcount(page) > 1)
+ return 0;
+
/* Avoid migrating to a node that is nearly full */
if (!migrate_balanced_pgdat(pgdat, compound_nr(page)))
return 0;
@@ -2077,18 +2081,6 @@ static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
if (isolate_lru_page(page))
return 0;
- /*
- * migrate_misplaced_transhuge_page() skips page migration's usual
- * check on page_count(), so we must do it here, now that the page
- * has been isolated: a GUP pin, or any other pin, prevents migration.
- * The expected page count is 3: 1 for page's mapcount and 1 for the
- * caller's pin and 1 for the reference taken by isolate_lru_page().
- */
- if (PageTransHuge(page) && page_count(page) != 3) {
- putback_lru_page(page);
- return 0;
- }
-
page_lru = page_is_file_lru(page);
mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + page_lru,
thp_nr_pages(page));
--
2.26.2
^ permalink raw reply related [flat|nested] 9+ messages in thread
* [v3 PATCH 7/7] mm: thp: skip make PMD PROT_NONE if THP migration is not supported
2021-05-18 20:07 [v3 PATCH 0/7] mm: thp: use generic THP migration for NUMA hinting fault Yang Shi
` (5 preceding siblings ...)
2021-05-18 20:08 ` [v3 PATCH 6/7] mm: migrate: check mapcount for THP instead of refcount Yang Shi
@ 2021-05-18 20:08 ` Yang Shi
6 siblings, 0 replies; 9+ messages in thread
From: Yang Shi @ 2021-05-18 20:08 UTC (permalink / raw)
To: mgorman, kirill.shutemov, ziy, ying.huang, mhocko, hughd,
gerald.schaefer, hca, gor, borntraeger, akpm
Cc: shy828301, linux-mm, linux-s390, linux-kernel
A quick grep shows x86_64, PowerPC (book3s), ARM64 and S390 support both
NUMA balancing and THP. But S390 doesn't support THP migration so NUMA
balancing actually can't migrate any misplaced pages.
Skip make PMD PROT_NONE for such case otherwise CPU cycles may be wasted
by pointless NUMA hinting faults on S390.
Acked-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Yang Shi <shy828301@gmail.com>
---
mm/huge_memory.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index b8526b9b041a..fb984ef5a761 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1735,6 +1735,7 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
* Returns
* - 0 if PMD could not be locked
* - 1 if PMD was locked but protections unchanged and TLB flush unnecessary
+ * or if prot_numa but THP migration is not supported
* - HPAGE_PMD_NR if protections changed and TLB flush necessary
*/
int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
@@ -1749,6 +1750,9 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
bool uffd_wp = cp_flags & MM_CP_UFFD_WP;
bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE;
+ if (prot_numa && !thp_migration_supported())
+ return 1;
+
ptl = __pmd_trans_huge_lock(pmd, vma);
if (!ptl)
return 0;
--
2.26.2
^ permalink raw reply related [flat|nested] 9+ messages in thread