* [PATCH v8 1/4] mm/cma: Add PF flag to force non cma alloc
2019-02-27 14:47 [PATCH v8 0/4] mm/kvm/vfio/ppc64: Migrate compound pages out of CMA region Aneesh Kumar K.V
@ 2019-02-27 14:47 ` Aneesh Kumar K.V
2019-02-28 12:20 ` Vlastimil Babka
2019-02-27 14:47 ` [PATCH v8 2/4] mm: Update get_user_pages_longterm to migrate pages allocated from CMA region Aneesh Kumar K.V
` (2 subsequent siblings)
3 siblings, 1 reply; 7+ messages in thread
From: Aneesh Kumar K.V @ 2019-02-27 14:47 UTC (permalink / raw)
To: akpm, Michal Hocko, Alexey Kardashevskiy, David Gibson,
Andrea Arcangeli, mpe
Cc: linux-mm, linux-kernel, linuxppc-dev, Aneesh Kumar K.V
This patch adds PF_MEMALLOC_NOCMA which make sure any allocation in that context
is marked non-movable and hence cannot be satisfied by CMA region.
This is useful with get_user_pages_longterm where we want to take a page pin by
migrating pages from CMA region. Marking the section PF_MEMALLOC_NOCMA ensures
that we avoid unnecessary page migration later.
Suggested-by: Andrea Arcangeli <aarcange@redhat.com>
Reviewed-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
include/linux/sched.h | 1 +
include/linux/sched/mm.h | 48 +++++++++++++++++++++++++++++++++-------
2 files changed, 41 insertions(+), 8 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index f9b43c989577..dfa90088ba08 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1403,6 +1403,7 @@ extern struct pid *cad_pid;
#define PF_UMH 0x02000000 /* I'm an Usermodehelper process */
#define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */
#define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */
+#define PF_MEMALLOC_NOCMA 0x10000000 /* All allocation request will have _GFP_MOVABLE cleared */
#define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */
#define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */
#define PF_SUSPEND_TASK 0x80000000 /* This thread called freeze_processes() and should not be frozen */
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 3bfa6a0cbba4..0cd9f10423fb 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -148,17 +148,25 @@ static inline bool in_vfork(struct task_struct *tsk)
* Applies per-task gfp context to the given allocation flags.
* PF_MEMALLOC_NOIO implies GFP_NOIO
* PF_MEMALLOC_NOFS implies GFP_NOFS
+ * PF_MEMALLOC_NOCMA implies no allocation from CMA region.
*/
static inline gfp_t current_gfp_context(gfp_t flags)
{
- /*
- * NOIO implies both NOIO and NOFS and it is a weaker context
- * so always make sure it makes precedence
- */
- if (unlikely(current->flags & PF_MEMALLOC_NOIO))
- flags &= ~(__GFP_IO | __GFP_FS);
- else if (unlikely(current->flags & PF_MEMALLOC_NOFS))
- flags &= ~__GFP_FS;
+ if (unlikely(current->flags &
+ (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS | PF_MEMALLOC_NOCMA))) {
+ /*
+ * NOIO implies both NOIO and NOFS and it is a weaker context
+ * so always make sure it makes precedence
+ */
+ if (current->flags & PF_MEMALLOC_NOIO)
+ flags &= ~(__GFP_IO | __GFP_FS);
+ else if (current->flags & PF_MEMALLOC_NOFS)
+ flags &= ~__GFP_FS;
+#ifdef CONFIG_CMA
+ if (current->flags & PF_MEMALLOC_NOCMA)
+ flags &= ~__GFP_MOVABLE;
+#endif
+ }
return flags;
}
@@ -248,6 +256,30 @@ static inline void memalloc_noreclaim_restore(unsigned int flags)
current->flags = (current->flags & ~PF_MEMALLOC) | flags;
}
+#ifdef CONFIG_CMA
+static inline unsigned int memalloc_nocma_save(void)
+{
+ unsigned int flags = current->flags & PF_MEMALLOC_NOCMA;
+
+ current->flags |= PF_MEMALLOC_NOCMA;
+ return flags;
+}
+
+static inline void memalloc_nocma_restore(unsigned int flags)
+{
+ current->flags = (current->flags & ~PF_MEMALLOC_NOCMA) | flags;
+}
+#else
+static inline unsigned int memalloc_nocma_save(void)
+{
+ return 0;
+}
+
+static inline void memalloc_nocma_restore(unsigned int flags)
+{
+}
+#endif
+
#ifdef CONFIG_MEMCG
/**
* memalloc_use_memcg - Starts the remote memcg charging scope.
--
2.20.1
^ permalink raw reply related [flat|nested] 7+ messages in thread
* Re: [PATCH v8 1/4] mm/cma: Add PF flag to force non cma alloc
2019-02-27 14:47 ` [PATCH v8 1/4] mm/cma: Add PF flag to force non cma alloc Aneesh Kumar K.V
@ 2019-02-28 12:20 ` Vlastimil Babka
2019-02-28 14:34 ` Michal Hocko
0 siblings, 1 reply; 7+ messages in thread
From: Vlastimil Babka @ 2019-02-28 12:20 UTC (permalink / raw)
To: Aneesh Kumar K.V, akpm, Michal Hocko, Alexey Kardashevskiy,
David Gibson, Andrea Arcangeli, mpe
Cc: linux-mm, linux-kernel, linuxppc-dev, Ingo Molnar,
Peter Zijlstra, Matthew Wilcox
On 2/27/19 3:47 PM, Aneesh Kumar K.V wrote:
> This patch adds PF_MEMALLOC_NOCMA which make sure any allocation in that context
> is marked non-movable and hence cannot be satisfied by CMA region.
>
> This is useful with get_user_pages_longterm where we want to take a page pin by
> migrating pages from CMA region. Marking the section PF_MEMALLOC_NOCMA ensures
> that we avoid unnecessary page migration later.
>
> Suggested-by: Andrea Arcangeli <aarcange@redhat.com>
> Reviewed-by: Andrea Arcangeli <aarcange@redhat.com>
> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
+CC scheduler guys
Do we really take the last available PF flag just so that "we avoid
unnecessary page migration later"?
If yes, that's a third PF_MEMALLOC flag, should we get separate variable
for gfp context at this point?
Also I don't like the name PF_MEMALLOC_NOCMA, as it's unnecessarily tied
to CMA. If anything it should be e.g. PF_MEMALLOC_NOMOVABLE.
Thanks.
> ---
> include/linux/sched.h | 1 +
> include/linux/sched/mm.h | 48 +++++++++++++++++++++++++++++++++-------
> 2 files changed, 41 insertions(+), 8 deletions(-)
>
> diff --git a/include/linux/sched.h b/include/linux/sched.h
> index f9b43c989577..dfa90088ba08 100644
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -1403,6 +1403,7 @@ extern struct pid *cad_pid;
> #define PF_UMH 0x02000000 /* I'm an Usermodehelper process */
> #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */
> #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */
> +#define PF_MEMALLOC_NOCMA 0x10000000 /* All allocation request will have _GFP_MOVABLE cleared */
> #define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */
> #define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */
> #define PF_SUSPEND_TASK 0x80000000 /* This thread called freeze_processes() and should not be frozen */
> diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
> index 3bfa6a0cbba4..0cd9f10423fb 100644
> --- a/include/linux/sched/mm.h
> +++ b/include/linux/sched/mm.h
> @@ -148,17 +148,25 @@ static inline bool in_vfork(struct task_struct *tsk)
> * Applies per-task gfp context to the given allocation flags.
> * PF_MEMALLOC_NOIO implies GFP_NOIO
> * PF_MEMALLOC_NOFS implies GFP_NOFS
> + * PF_MEMALLOC_NOCMA implies no allocation from CMA region.
> */
> static inline gfp_t current_gfp_context(gfp_t flags)
> {
> - /*
> - * NOIO implies both NOIO and NOFS and it is a weaker context
> - * so always make sure it makes precedence
> - */
> - if (unlikely(current->flags & PF_MEMALLOC_NOIO))
> - flags &= ~(__GFP_IO | __GFP_FS);
> - else if (unlikely(current->flags & PF_MEMALLOC_NOFS))
> - flags &= ~__GFP_FS;
> + if (unlikely(current->flags &
> + (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS | PF_MEMALLOC_NOCMA))) {
> + /*
> + * NOIO implies both NOIO and NOFS and it is a weaker context
> + * so always make sure it makes precedence
> + */
> + if (current->flags & PF_MEMALLOC_NOIO)
> + flags &= ~(__GFP_IO | __GFP_FS);
> + else if (current->flags & PF_MEMALLOC_NOFS)
> + flags &= ~__GFP_FS;
> +#ifdef CONFIG_CMA
> + if (current->flags & PF_MEMALLOC_NOCMA)
> + flags &= ~__GFP_MOVABLE;
> +#endif
> + }
> return flags;
> }
>
> @@ -248,6 +256,30 @@ static inline void memalloc_noreclaim_restore(unsigned int flags)
> current->flags = (current->flags & ~PF_MEMALLOC) | flags;
> }
>
> +#ifdef CONFIG_CMA
> +static inline unsigned int memalloc_nocma_save(void)
> +{
> + unsigned int flags = current->flags & PF_MEMALLOC_NOCMA;
> +
> + current->flags |= PF_MEMALLOC_NOCMA;
> + return flags;
> +}
> +
> +static inline void memalloc_nocma_restore(unsigned int flags)
> +{
> + current->flags = (current->flags & ~PF_MEMALLOC_NOCMA) | flags;
> +}
> +#else
> +static inline unsigned int memalloc_nocma_save(void)
> +{
> + return 0;
> +}
> +
> +static inline void memalloc_nocma_restore(unsigned int flags)
> +{
> +}
> +#endif
> +
> #ifdef CONFIG_MEMCG
> /**
> * memalloc_use_memcg - Starts the remote memcg charging scope.
>
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [PATCH v8 1/4] mm/cma: Add PF flag to force non cma alloc
2019-02-28 12:20 ` Vlastimil Babka
@ 2019-02-28 14:34 ` Michal Hocko
0 siblings, 0 replies; 7+ messages in thread
From: Michal Hocko @ 2019-02-28 14:34 UTC (permalink / raw)
To: Vlastimil Babka
Cc: Aneesh Kumar K.V, akpm, Alexey Kardashevskiy, David Gibson,
Andrea Arcangeli, mpe, linux-mm, linux-kernel, linuxppc-dev,
Ingo Molnar, Peter Zijlstra, Matthew Wilcox
On Thu 28-02-19 13:20:03, Vlastimil Babka wrote:
> On 2/27/19 3:47 PM, Aneesh Kumar K.V wrote:
> > This patch adds PF_MEMALLOC_NOCMA which make sure any allocation in that context
> > is marked non-movable and hence cannot be satisfied by CMA region.
> >
> > This is useful with get_user_pages_longterm where we want to take a page pin by
> > migrating pages from CMA region. Marking the section PF_MEMALLOC_NOCMA ensures
> > that we avoid unnecessary page migration later.
> >
> > Suggested-by: Andrea Arcangeli <aarcange@redhat.com>
> > Reviewed-by: Andrea Arcangeli <aarcange@redhat.com>
> > Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
>
> +CC scheduler guys
>
> Do we really take the last available PF flag just so that "we avoid
> unnecessary page migration later"?
> If yes, that's a third PF_MEMALLOC flag, should we get separate variable
> for gfp context at this point?
Yes, that sounds like a reasonable thing to do. Just note that xfs still
uses current_{set,restore}* api to handle PF_MEMALLOC_NOFS so that would
have to be moved over to the memalloc_nofs_{save,restore} API.
--
Michal Hocko
^ permalink raw reply [flat|nested] 7+ messages in thread
* [PATCH v8 2/4] mm: Update get_user_pages_longterm to migrate pages allocated from CMA region
2019-02-27 14:47 [PATCH v8 0/4] mm/kvm/vfio/ppc64: Migrate compound pages out of CMA region Aneesh Kumar K.V
2019-02-27 14:47 ` [PATCH v8 1/4] mm/cma: Add PF flag to force non cma alloc Aneesh Kumar K.V
@ 2019-02-27 14:47 ` Aneesh Kumar K.V
2019-02-27 14:47 ` [PATCH v8 3/4] powerpc/mm/iommu: Allow migration of cma allocated pages during mm_iommu_do_alloc Aneesh Kumar K.V
2019-02-27 14:47 ` [PATCH v8 4/4] powerpc/mm/iommu: Allow large IOMMU page size only for hugetlb backing Aneesh Kumar K.V
3 siblings, 0 replies; 7+ messages in thread
From: Aneesh Kumar K.V @ 2019-02-27 14:47 UTC (permalink / raw)
To: akpm, Michal Hocko, Alexey Kardashevskiy, David Gibson,
Andrea Arcangeli, mpe
Cc: linux-mm, linux-kernel, linuxppc-dev, Aneesh Kumar K.V
This patch updates get_user_pages_longterm to migrate pages allocated out
of CMA region. This makes sure that we don't keep non-movable pages (due to page
reference count) in the CMA area.
This will be used by ppc64 in a later patch to avoid pinning pages in the CMA
region. ppc64 uses CMA region for allocation of the hardware page table (hash page
table) and not able to migrate pages out of CMA region results in page table
allocation failures.
One case where we hit this easy is when a guest using a VFIO passthrough device.
VFIO locks all the guest's memory and if the guest memory is backed by CMA
region, it becomes unmovable resulting in fragmenting the CMA and possibly
preventing other guests from allocation a large enough hash page table.
NOTE: We allocate the new page without using __GFP_THISNODE
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
include/linux/hugetlb.h | 2 +
include/linux/mm.h | 3 +-
mm/gup.c | 200 +++++++++++++++++++++++++++++++++++-----
mm/hugetlb.c | 4 +-
4 files changed, 182 insertions(+), 27 deletions(-)
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 087fd5f48c91..1eed0cdaec0e 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -371,6 +371,8 @@ struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
nodemask_t *nmask);
struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma,
unsigned long address);
+struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
+ int nid, nodemask_t *nmask);
int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
pgoff_t idx);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 80bb6408fe73..20ec56f8e2bb 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1536,7 +1536,8 @@ long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
unsigned int gup_flags, struct page **pages, int *locked);
long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
struct page **pages, unsigned int gup_flags);
-#ifdef CONFIG_FS_DAX
+
+#if defined(CONFIG_FS_DAX) || defined(CONFIG_CMA)
long get_user_pages_longterm(unsigned long start, unsigned long nr_pages,
unsigned int gup_flags, struct page **pages,
struct vm_area_struct **vmas);
diff --git a/mm/gup.c b/mm/gup.c
index 75029649baca..22291db50013 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -13,6 +13,9 @@
#include <linux/sched/signal.h>
#include <linux/rwsem.h>
#include <linux/hugetlb.h>
+#include <linux/migrate.h>
+#include <linux/mm_inline.h>
+#include <linux/sched/mm.h>
#include <asm/mmu_context.h>
#include <asm/pgtable.h>
@@ -1126,7 +1129,167 @@ long get_user_pages(unsigned long start, unsigned long nr_pages,
}
EXPORT_SYMBOL(get_user_pages);
+#if defined(CONFIG_FS_DAX) || defined (CONFIG_CMA)
+
#ifdef CONFIG_FS_DAX
+static bool check_dax_vmas(struct vm_area_struct **vmas, long nr_pages)
+{
+ long i;
+ struct vm_area_struct *vma_prev = NULL;
+
+ for (i = 0; i < nr_pages; i++) {
+ struct vm_area_struct *vma = vmas[i];
+
+ if (vma == vma_prev)
+ continue;
+
+ vma_prev = vma;
+
+ if (vma_is_fsdax(vma))
+ return true;
+ }
+ return false;
+}
+#else
+static inline bool check_dax_vmas(struct vm_area_struct **vmas, long nr_pages)
+{
+ return false;
+}
+#endif
+
+#ifdef CONFIG_CMA
+static struct page *new_non_cma_page(struct page *page, unsigned long private)
+{
+ /*
+ * We want to make sure we allocate the new page from the same node
+ * as the source page.
+ */
+ int nid = page_to_nid(page);
+ /*
+ * Trying to allocate a page for migration. Ignore allocation
+ * failure warnings. We don't force __GFP_THISNODE here because
+ * this node here is the node where we have CMA reservation and
+ * in some case these nodes will have really less non movable
+ * allocation memory.
+ */
+ gfp_t gfp_mask = GFP_USER | __GFP_NOWARN;
+
+ if (PageHighMem(page))
+ gfp_mask |= __GFP_HIGHMEM;
+
+#ifdef CONFIG_HUGETLB_PAGE
+ if (PageHuge(page)) {
+ struct hstate *h = page_hstate(page);
+ /*
+ * We don't want to dequeue from the pool because pool pages will
+ * mostly be from the CMA region.
+ */
+ return alloc_migrate_huge_page(h, gfp_mask, nid, NULL);
+ }
+#endif
+ if (PageTransHuge(page)) {
+ struct page *thp;
+ /*
+ * ignore allocation failure warnings
+ */
+ gfp_t thp_gfpmask = GFP_TRANSHUGE | __GFP_NOWARN;
+
+ /*
+ * Remove the movable mask so that we don't allocate from
+ * CMA area again.
+ */
+ thp_gfpmask &= ~__GFP_MOVABLE;
+ thp = __alloc_pages_node(nid, thp_gfpmask, HPAGE_PMD_ORDER);
+ if (!thp)
+ return NULL;
+ prep_transhuge_page(thp);
+ return thp;
+ }
+
+ return __alloc_pages_node(nid, gfp_mask, 0);
+}
+
+static long check_and_migrate_cma_pages(unsigned long start, long nr_pages,
+ unsigned int gup_flags,
+ struct page **pages,
+ struct vm_area_struct **vmas)
+{
+ long i;
+ bool drain_allow = true;
+ bool migrate_allow = true;
+ LIST_HEAD(cma_page_list);
+
+check_again:
+ for (i = 0; i < nr_pages; i++) {
+ /*
+ * If we get a page from the CMA zone, since we are going to
+ * be pinning these entries, we might as well move them out
+ * of the CMA zone if possible.
+ */
+ if (is_migrate_cma_page(pages[i])) {
+
+ struct page *head = compound_head(pages[i]);
+
+ if (PageHuge(head)) {
+ isolate_huge_page(head, &cma_page_list);
+ } else {
+ if (!PageLRU(head) && drain_allow) {
+ lru_add_drain_all();
+ drain_allow = false;
+ }
+
+ if (!isolate_lru_page(head)) {
+ list_add_tail(&head->lru, &cma_page_list);
+ mod_node_page_state(page_pgdat(head),
+ NR_ISOLATED_ANON +
+ page_is_file_cache(head),
+ hpage_nr_pages(head));
+ }
+ }
+ }
+ }
+
+ if (!list_empty(&cma_page_list)) {
+ /*
+ * drop the above get_user_pages reference.
+ */
+ for (i = 0; i < nr_pages; i++)
+ put_page(pages[i]);
+
+ if (migrate_pages(&cma_page_list, new_non_cma_page,
+ NULL, 0, MIGRATE_SYNC, MR_CONTIG_RANGE)) {
+ /*
+ * some of the pages failed migration. Do get_user_pages
+ * without migration.
+ */
+ migrate_allow = false;
+
+ if (!list_empty(&cma_page_list))
+ putback_movable_pages(&cma_page_list);
+ }
+ /*
+ * We did migrate all the pages, Try to get the page references again
+ * migrating any new CMA pages which we failed to isolate earlier.
+ */
+ nr_pages = get_user_pages(start, nr_pages, gup_flags, pages, vmas);
+ if ((nr_pages > 0) && migrate_allow) {
+ drain_allow = true;
+ goto check_again;
+ }
+ }
+
+ return nr_pages;
+}
+#else
+static inline long check_and_migrate_cma_pages(unsigned long start, long nr_pages,
+ unsigned int gup_flags,
+ struct page **pages,
+ struct vm_area_struct **vmas)
+{
+ return nr_pages;
+}
+#endif
+
/*
* This is the same as get_user_pages() in that it assumes we are
* operating on the current task's mm, but it goes further to validate
@@ -1140,11 +1303,11 @@ EXPORT_SYMBOL(get_user_pages);
* Contrast this to iov_iter_get_pages() usages which are transient.
*/
long get_user_pages_longterm(unsigned long start, unsigned long nr_pages,
- unsigned int gup_flags, struct page **pages,
- struct vm_area_struct **vmas_arg)
+ unsigned int gup_flags, struct page **pages,
+ struct vm_area_struct **vmas_arg)
{
struct vm_area_struct **vmas = vmas_arg;
- struct vm_area_struct *vma_prev = NULL;
+ unsigned long flags;
long rc, i;
if (!pages)
@@ -1157,31 +1320,20 @@ long get_user_pages_longterm(unsigned long start, unsigned long nr_pages,
return -ENOMEM;
}
+ flags = memalloc_nocma_save();
rc = get_user_pages(start, nr_pages, gup_flags, pages, vmas);
+ memalloc_nocma_restore(flags);
+ if (rc < 0)
+ goto out;
- for (i = 0; i < rc; i++) {
- struct vm_area_struct *vma = vmas[i];
-
- if (vma == vma_prev)
- continue;
-
- vma_prev = vma;
-
- if (vma_is_fsdax(vma))
- break;
- }
-
- /*
- * Either get_user_pages() failed, or the vma validation
- * succeeded, in either case we don't need to put_page() before
- * returning.
- */
- if (i >= rc)
+ if (check_dax_vmas(vmas, rc)) {
+ for (i = 0; i < rc; i++)
+ put_page(pages[i]);
+ rc = -EOPNOTSUPP;
goto out;
+ }
- for (i = 0; i < rc; i++)
- put_page(pages[i]);
- rc = -EOPNOTSUPP;
+ rc = check_and_migrate_cma_pages(start, rc, gup_flags, pages, vmas);
out:
if (vmas != vmas_arg)
kfree(vmas);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index afef61656c1e..c80f0c16a226 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1586,8 +1586,8 @@ static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask,
return page;
}
-static struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
- int nid, nodemask_t *nmask)
+struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
+ int nid, nodemask_t *nmask)
{
struct page *page;
--
2.20.1
^ permalink raw reply related [flat|nested] 7+ messages in thread
* [PATCH v8 3/4] powerpc/mm/iommu: Allow migration of cma allocated pages during mm_iommu_do_alloc
2019-02-27 14:47 [PATCH v8 0/4] mm/kvm/vfio/ppc64: Migrate compound pages out of CMA region Aneesh Kumar K.V
2019-02-27 14:47 ` [PATCH v8 1/4] mm/cma: Add PF flag to force non cma alloc Aneesh Kumar K.V
2019-02-27 14:47 ` [PATCH v8 2/4] mm: Update get_user_pages_longterm to migrate pages allocated from CMA region Aneesh Kumar K.V
@ 2019-02-27 14:47 ` Aneesh Kumar K.V
2019-02-27 14:47 ` [PATCH v8 4/4] powerpc/mm/iommu: Allow large IOMMU page size only for hugetlb backing Aneesh Kumar K.V
3 siblings, 0 replies; 7+ messages in thread
From: Aneesh Kumar K.V @ 2019-02-27 14:47 UTC (permalink / raw)
To: akpm, Michal Hocko, Alexey Kardashevskiy, David Gibson,
Andrea Arcangeli, mpe
Cc: linux-mm, linux-kernel, linuxppc-dev, Aneesh Kumar K.V
The current code doesn't do page migration if the page allocated is a compound page.
With HugeTLB migration support, we can end up allocating hugetlb pages from
CMA region. Also, THP pages can be allocated from CMA region. This patch updates
the code to handle compound pages correctly. The patch also switches to a single
get_user_pages with the right count, instead of doing one get_user_pages per page.
That avoids reading page table multiple times. This is done by using
get_user_pages_longterm, because that also takes care of DAX backed pages.
DAX pages lifetime is dictated by file system rules and as such, we need
to make sure that we free these pages on operations like truncate and
punch hole. If we have long term pin on these pages, which are mostly
return to userspace with elevated page count, the entity holding the
long term pin may not be aware of the fact that file got truncated and
the file system blocks possibly got reused. That can result in corruption.
The patch also converts the hpas member of mm_iommu_table_group_mem_t to a union.
We use the same storage location to store pointers to struct page. We cannot
update all the code path use struct page *, because we access hpas in real mode
and we can't do that struct page * to pfn conversion in real mode.
Reviewed-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
arch/powerpc/mm/mmu_context_iommu.c | 125 +++++++++-------------------
1 file changed, 38 insertions(+), 87 deletions(-)
diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index a712a650a8b6..85b4e9f5c615 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -21,6 +21,7 @@
#include <linux/sizes.h>
#include <asm/mmu_context.h>
#include <asm/pte-walk.h>
+#include <linux/mm_inline.h>
static DEFINE_MUTEX(mem_list_mutex);
@@ -34,8 +35,18 @@ struct mm_iommu_table_group_mem_t {
atomic64_t mapped;
unsigned int pageshift;
u64 ua; /* userspace address */
- u64 entries; /* number of entries in hpas[] */
- u64 *hpas; /* vmalloc'ed */
+ u64 entries; /* number of entries in hpas/hpages[] */
+ /*
+ * in mm_iommu_get we temporarily use this to store
+ * struct page address.
+ *
+ * We need to convert ua to hpa in real mode. Make it
+ * simpler by storing physical address.
+ */
+ union {
+ struct page **hpages; /* vmalloc'ed */
+ phys_addr_t *hpas;
+ };
#define MM_IOMMU_TABLE_INVALID_HPA ((uint64_t)-1)
u64 dev_hpa; /* Device memory base address */
};
@@ -80,64 +91,15 @@ bool mm_iommu_preregistered(struct mm_struct *mm)
}
EXPORT_SYMBOL_GPL(mm_iommu_preregistered);
-/*
- * Taken from alloc_migrate_target with changes to remove CMA allocations
- */
-struct page *new_iommu_non_cma_page(struct page *page, unsigned long private)
-{
- gfp_t gfp_mask = GFP_USER;
- struct page *new_page;
-
- if (PageCompound(page))
- return NULL;
-
- if (PageHighMem(page))
- gfp_mask |= __GFP_HIGHMEM;
-
- /*
- * We don't want the allocation to force an OOM if possibe
- */
- new_page = alloc_page(gfp_mask | __GFP_NORETRY | __GFP_NOWARN);
- return new_page;
-}
-
-static int mm_iommu_move_page_from_cma(struct page *page)
-{
- int ret = 0;
- LIST_HEAD(cma_migrate_pages);
-
- /* Ignore huge pages for now */
- if (PageCompound(page))
- return -EBUSY;
-
- lru_add_drain();
- ret = isolate_lru_page(page);
- if (ret)
- return ret;
-
- list_add(&page->lru, &cma_migrate_pages);
- put_page(page); /* Drop the gup reference */
-
- ret = migrate_pages(&cma_migrate_pages, new_iommu_non_cma_page,
- NULL, 0, MIGRATE_SYNC, MR_CONTIG_RANGE);
- if (ret) {
- if (!list_empty(&cma_migrate_pages))
- putback_movable_pages(&cma_migrate_pages);
- }
-
- return 0;
-}
-
static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
- unsigned long entries, unsigned long dev_hpa,
- struct mm_iommu_table_group_mem_t **pmem)
+ unsigned long entries, unsigned long dev_hpa,
+ struct mm_iommu_table_group_mem_t **pmem)
{
struct mm_iommu_table_group_mem_t *mem;
- long i, j, ret = 0, locked_entries = 0;
+ long i, ret, locked_entries = 0;
unsigned int pageshift;
unsigned long flags;
unsigned long cur_ua;
- struct page *page = NULL;
mutex_lock(&mem_list_mutex);
@@ -187,41 +149,25 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
goto unlock_exit;
}
+ down_read(&mm->mmap_sem);
+ ret = get_user_pages_longterm(ua, entries, FOLL_WRITE, mem->hpages, NULL);
+ up_read(&mm->mmap_sem);
+ if (ret != entries) {
+ /* free the reference taken */
+ for (i = 0; i < ret; i++)
+ put_page(mem->hpages[i]);
+
+ vfree(mem->hpas);
+ kfree(mem);
+ ret = -EFAULT;
+ goto unlock_exit;
+ }
+
+ pageshift = PAGE_SHIFT;
for (i = 0; i < entries; ++i) {
+ struct page *page = mem->hpages[i];
+
cur_ua = ua + (i << PAGE_SHIFT);
- if (1 != get_user_pages_fast(cur_ua,
- 1/* pages */, 1/* iswrite */, &page)) {
- ret = -EFAULT;
- for (j = 0; j < i; ++j)
- put_page(pfn_to_page(mem->hpas[j] >>
- PAGE_SHIFT));
- vfree(mem->hpas);
- kfree(mem);
- goto unlock_exit;
- }
- /*
- * If we get a page from the CMA zone, since we are going to
- * be pinning these entries, we might as well move them out
- * of the CMA zone if possible. NOTE: faulting in + migration
- * can be expensive. Batching can be considered later
- */
- if (is_migrate_cma_page(page)) {
- if (mm_iommu_move_page_from_cma(page))
- goto populate;
- if (1 != get_user_pages_fast(cur_ua,
- 1/* pages */, 1/* iswrite */,
- &page)) {
- ret = -EFAULT;
- for (j = 0; j < i; ++j)
- put_page(pfn_to_page(mem->hpas[j] >>
- PAGE_SHIFT));
- vfree(mem->hpas);
- kfree(mem);
- goto unlock_exit;
- }
- }
-populate:
- pageshift = PAGE_SHIFT;
if (mem->pageshift > PAGE_SHIFT && PageCompound(page)) {
pte_t *pte;
struct page *head = compound_head(page);
@@ -239,10 +185,15 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
local_irq_restore(flags);
}
mem->pageshift = min(mem->pageshift, pageshift);
+ /*
+ * We don't need struct page reference any more, switch
+ * to physical address.
+ */
mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT;
}
good_exit:
+ ret = 0;
atomic64_set(&mem->mapped, 1);
mem->used = 1;
mem->ua = ua;
--
2.20.1
^ permalink raw reply related [flat|nested] 7+ messages in thread
* [PATCH v8 4/4] powerpc/mm/iommu: Allow large IOMMU page size only for hugetlb backing
2019-02-27 14:47 [PATCH v8 0/4] mm/kvm/vfio/ppc64: Migrate compound pages out of CMA region Aneesh Kumar K.V
` (2 preceding siblings ...)
2019-02-27 14:47 ` [PATCH v8 3/4] powerpc/mm/iommu: Allow migration of cma allocated pages during mm_iommu_do_alloc Aneesh Kumar K.V
@ 2019-02-27 14:47 ` Aneesh Kumar K.V
3 siblings, 0 replies; 7+ messages in thread
From: Aneesh Kumar K.V @ 2019-02-27 14:47 UTC (permalink / raw)
To: akpm, Michal Hocko, Alexey Kardashevskiy, David Gibson,
Andrea Arcangeli, mpe
Cc: linux-mm, linux-kernel, linuxppc-dev, Aneesh Kumar K.V
THP pages can get split during different code paths. An incremented reference
count does imply we will not split the compound page. But the pmd entry can be
converted to level 4 pte entries. Keep the code simpler by allowing large
IOMMU page size only if the guest ram is backed by hugetlb pages.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
arch/powerpc/mm/mmu_context_iommu.c | 24 +++++++-----------------
1 file changed, 7 insertions(+), 17 deletions(-)
diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index 85b4e9f5c615..e7a9c4f6bfca 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -98,8 +98,6 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
struct mm_iommu_table_group_mem_t *mem;
long i, ret, locked_entries = 0;
unsigned int pageshift;
- unsigned long flags;
- unsigned long cur_ua;
mutex_lock(&mem_list_mutex);
@@ -167,22 +165,14 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
for (i = 0; i < entries; ++i) {
struct page *page = mem->hpages[i];
- cur_ua = ua + (i << PAGE_SHIFT);
- if (mem->pageshift > PAGE_SHIFT && PageCompound(page)) {
- pte_t *pte;
+ /*
+ * Allow to use larger than 64k IOMMU pages. Only do that
+ * if we are backed by hugetlb.
+ */
+ if ((mem->pageshift > PAGE_SHIFT) && PageHuge(page)) {
struct page *head = compound_head(page);
- unsigned int compshift = compound_order(head);
- unsigned int pteshift;
-
- local_irq_save(flags); /* disables as well */
- pte = find_linux_pte(mm->pgd, cur_ua, NULL, &pteshift);
-
- /* Double check it is still the same pinned page */
- if (pte && pte_page(*pte) == head &&
- pteshift == compshift + PAGE_SHIFT)
- pageshift = max_t(unsigned int, pteshift,
- PAGE_SHIFT);
- local_irq_restore(flags);
+
+ pageshift = compound_order(head) + PAGE_SHIFT;
}
mem->pageshift = min(mem->pageshift, pageshift);
/*
--
2.20.1
^ permalink raw reply related [flat|nested] 7+ messages in thread