mm/gup: cache dev_pagemap while pinning pages

Getting pages from ZONE_DEVICE memory needs to check the backing device's
live-ness, which is tracked in the device's dev_pagemap metadata.  This
metadata is stored in a radix tree and looking it up adds measurable
software overhead.

This patch avoids repeating this relatively costly operation when
dev_pagemap is used by caching the last dev_pagemap while getting user
pages.  The gup_benchmark kernel self test reports this reduces time to
get user pages to as low as 1/3 of the previous time.

Link: http://lkml.kernel.org/r/20181012173040.15669-1-keith.busch@intel.com
Signed-off-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

5 files changed, 79 insertions, 73 deletions

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index fdcb45999b26..4663ee96cf59 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -213,9 +213,9 @@ static inline int hpage_nr_pages(struct page *page)
 }
 
 struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
-                pmd_t *pmd, int flags);
+                pmd_t *pmd, int flags, struct dev_pagemap **pgmap);
 struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr,
-                pud_t *pud, int flags);
+                pud_t *pud, int flags, struct dev_pagemap **pgmap);
 
 extern vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd);
 
@@ -344,13 +344,13 @@ static inline void mm_put_huge_zero_page(struct mm_struct *mm)
 }
 
 static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma,
-                unsigned long addr, pmd_t *pmd, int flags)
+        unsigned long addr, pmd_t *pmd, int flags, struct dev_pagemap **pgmap)
 {
         return NULL;
 }
 
 static inline struct page *follow_devmap_pud(struct vm_area_struct *vma,
-                unsigned long addr, pud_t *pud, int flags)
+        unsigned long addr, pud_t *pud, int flags, struct dev_pagemap **pgmap)
 {
         return NULL;
 }
diff --git a/include/linux/mm.h b/include/linux/mm.h
index a023c5ce71fa..1e52b8fd1685 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2536,16 +2536,8 @@ static inline vm_fault_t vmf_error(int err)
         return VM_FAULT_SIGBUS;
 }
 
-struct page *follow_page_mask(struct vm_area_struct *vma,
-                              unsigned long address, unsigned int foll_flags,
-                              unsigned int *page_mask);
-
-static inline struct page *follow_page(struct vm_area_struct *vma,
-                unsigned long address, unsigned int foll_flags)
-{
-        unsigned int unused_page_mask;
-        return follow_page_mask(vma, address, foll_flags, &unused_page_mask);
-}
+struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
+                         unsigned int foll_flags);
 
 #define FOLL_WRITE      0x01    /* check pte is writable */
 #define FOLL_TOUCH      0x02    /* mark page accessed */
diff --git a/mm/gup.c b/mm/gup.c
index 08eb350e0f35..841d7ef53591 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -20,6 +20,11 @@
 
 #include "internal.h"
 
+struct follow_page_context {
+        struct dev_pagemap *pgmap;
+        unsigned int page_mask;
+};
+
 static struct page *no_page_table(struct vm_area_struct *vma,
                 unsigned int flags)
 {
@@ -71,10 +76,10 @@ static inline bool can_follow_write_pte(pte_t pte, unsigned int flags)
 }
 
 static struct page *follow_page_pte(struct vm_area_struct *vma,
-                unsigned long address, pmd_t *pmd, unsigned int flags)
+                unsigned long address, pmd_t *pmd, unsigned int flags,
+                struct dev_pagemap **pgmap)
 {
         struct mm_struct *mm = vma->vm_mm;
-        struct dev_pagemap *pgmap = NULL;
         struct page *page;
         spinlock_t *ptl;
         pte_t *ptep, pte;
@@ -116,8 +121,8 @@ retry:
                  * Only return device mapping pages in the FOLL_GET case since
                  * they are only valid while holding the pgmap reference.
                  */
-                pgmap = get_dev_pagemap(pte_pfn(pte), NULL);
-                if (pgmap)
+                *pgmap = get_dev_pagemap(pte_pfn(pte), *pgmap);
+                if (*pgmap)
                         page = pte_page(pte);
                 else
                         goto no_page;
@@ -152,15 +157,8 @@ retry:
                 goto retry;
         }
 
-        if (flags & FOLL_GET) {
+        if (flags & FOLL_GET)
                 get_page(page);
-
-                /* drop the pgmap reference now that we hold the page */
-                if (pgmap) {
-                        put_dev_pagemap(pgmap);
-                        pgmap = NULL;
-                }
-        }
         if (flags & FOLL_TOUCH) {
                 if ((flags & FOLL_WRITE) &&
                     !pte_dirty(pte) && !PageDirty(page))
@@ -210,7 +208,8 @@ no_page:
 
 static struct page *follow_pmd_mask(struct vm_area_struct *vma,
                                     unsigned long address, pud_t *pudp,
-                                    unsigned int flags, unsigned int *page_mask)
+                                    unsigned int flags,
+                                    struct follow_page_context *ctx)
 {
         pmd_t *pmd, pmdval;
         spinlock_t *ptl;
@@ -258,13 +257,13 @@ retry:
         }
         if (pmd_devmap(pmdval)) {
                 ptl = pmd_lock(mm, pmd);
-                page = follow_devmap_pmd(vma, address, pmd, flags);
+                page = follow_devmap_pmd(vma, address, pmd, flags, &ctx->pgmap);
                 spin_unlock(ptl);
                 if (page)
                         return page;
         }
         if (likely(!pmd_trans_huge(pmdval)))
-                return follow_page_pte(vma, address, pmd, flags);
+                return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
 
         if ((flags & FOLL_NUMA) && pmd_protnone(pmdval))
                 return no_page_table(vma, flags);
@@ -284,7 +283,7 @@ retry_locked:
         }
         if (unlikely(!pmd_trans_huge(*pmd))) {
                 spin_unlock(ptl);
-                return follow_page_pte(vma, address, pmd, flags);
+                return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
         }
         if (flags & FOLL_SPLIT) {
                 int ret;
@@ -307,18 +306,18 @@ retry_locked:
                 }
 
                 return ret ? ERR_PTR(ret) :
-                        follow_page_pte(vma, address, pmd, flags);
+                        follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
         }
         page = follow_trans_huge_pmd(vma, address, pmd, flags);
         spin_unlock(ptl);
-        *page_mask = HPAGE_PMD_NR - 1;
+        ctx->page_mask = HPAGE_PMD_NR - 1;
         return page;
 }
 
-
 static struct page *follow_pud_mask(struct vm_area_struct *vma,
                                     unsigned long address, p4d_t *p4dp,
-                                    unsigned int flags, unsigned int *page_mask)
+                                    unsigned int flags,
+                                    struct follow_page_context *ctx)
 {
         pud_t *pud;
         spinlock_t *ptl;
@@ -344,7 +343,7 @@ static struct page *follow_pud_mask(struct vm_area_struct *vma,
         }
         if (pud_devmap(*pud)) {
                 ptl = pud_lock(mm, pud);
-                page = follow_devmap_pud(vma, address, pud, flags);
+                page = follow_devmap_pud(vma, address, pud, flags, &ctx->pgmap);
                 spin_unlock(ptl);
                 if (page)
                         return page;
@@ -352,13 +351,13 @@ static struct page *follow_pud_mask(struct vm_area_struct *vma,
         if (unlikely(pud_bad(*pud)))