mm/mmu_notifier: contextual information for event triggering invalidation

CPU page table update can happens for many reasons, not only as a result
of a syscall (munmap(), mprotect(), mremap(), madvise(), ...) but also as
a result of kernel activities (memory compression, reclaim, migration,
...).

Users of mmu notifier API track changes to the CPU page table and take
specific action for them.  While current API only provide range of virtual
address affected by the change, not why the changes is happening.

This patchset do the initial mechanical convertion of all the places that
calls mmu_notifier_range_init to also provide the default MMU_NOTIFY_UNMAP
event as well as the vma if it is know (most invalidation happens against
a given vma).  Passing down the vma allows the users of mmu notifier to
inspect the new vma page protection.

The MMU_NOTIFY_UNMAP is always the safe default as users of mmu notifier
should assume that every for the range is going away when that event
happens.  A latter patch do convert mm call path to use a more appropriate
events for each call.

This is done as 2 patches so that no call site is forgotten especialy
as it uses this following coccinelle patch:

%<----------------------------------------------------------------------
@@
identifier I1, I2, I3, I4;
@@
static inline void mmu_notifier_range_init(struct mmu_notifier_range *I1,
+enum mmu_notifier_event event,
+unsigned flags,
+struct vm_area_struct *vma,
struct mm_struct *I2, unsigned long I3, unsigned long I4) { ... }

@@
@@
-#define mmu_notifier_range_init(range, mm, start, end)
+#define mmu_notifier_range_init(range, event, flags, vma, mm, start, end)

@@
expression E1, E3, E4;
identifier I1;
@@
<...
mmu_notifier_range_init(E1,
+MMU_NOTIFY_UNMAP, 0, I1,
I1->vm_mm, E3, E4)
...>

@@
expression E1, E2, E3, E4;
identifier FN, VMA;
@@
FN(..., struct vm_area_struct *VMA, ...) {
<...
mmu_notifier_range_init(E1,
+MMU_NOTIFY_UNMAP, 0, VMA,
E2, E3, E4)
...> }

@@
expression E1, E2, E3, E4;
identifier FN, VMA;
@@
FN(...) {
struct vm_area_struct *VMA;
<...
mmu_notifier_range_init(E1,
+MMU_NOTIFY_UNMAP, 0, VMA,
E2, E3, E4)
...> }

@@
expression E1, E2, E3, E4;
identifier FN;
@@
FN(...) {
<...
mmu_notifier_range_init(E1,
+MMU_NOTIFY_UNMAP, 0, NULL,
E2, E3, E4)
...> }
---------------------------------------------------------------------->%

Applied with:
spatch --all-includes --sp-file mmu-notifier.spatch fs/proc/task_mmu.c --in-place
spatch --sp-file mmu-notifier.spatch --dir kernel/events/ --in-place
spatch --sp-file mmu-notifier.spatch --dir mm --in-place

Link: http://lkml.kernel.org/r/20190326164747.24405-6-jglisse@redhat.com
Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Felix Kuehling <Felix.Kuehling@amd.com>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: Ross Zwisler <zwisler@kernel.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krcmar <rkrcmar@redhat.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Christian Koenig <christian.koenig@amd.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 95ca1fe..ea464f2 100644 (file)
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1169,7 +1169,8 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
                                break;
                        }
 
-                       mmu_notifier_range_init(&range, mm, 0, -1UL);
+                       mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0,
+                                               NULL, mm, 0, -1UL);
                        mmu_notifier_invalidate_range_start(&range);
                }
                walk_page_range(0, mm->highest_vm_end, &clear_refs_walk);

diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index 2386e71..62f94cd 100644 (file)
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -356,6 +356,9 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm)
 
 
 static inline void mmu_notifier_range_init(struct mmu_notifier_range *range,
+                                          enum mmu_notifier_event event,
+                                          unsigned flags,
+                                          struct vm_area_struct *vma,
                                           struct mm_struct *mm,
                                           unsigned long start,
                                           unsigned long end)
@@ -491,7 +494,7 @@ static inline void _mmu_notifier_range_init(struct mmu_notifier_range *range,
        range->end = end;
 }
 
-#define mmu_notifier_range_init(range, mm, start, end) \
+#define mmu_notifier_range_init(range,event,flags,vma,mm,start,end)  \
        _mmu_notifier_range_init(range, start, end)
 
 static inline bool

diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 4ca7364..e34b699 100644 (file)
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -161,7 +161,8 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
        struct mmu_notifier_range range;
        struct mem_cgroup *memcg;
 
-       mmu_notifier_range_init(&range, mm, addr, addr + PAGE_SIZE);
+       mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, mm, addr,
+                               addr + PAGE_SIZE);
 
        VM_BUG_ON_PAGE(PageTransHuge(old_page), old_page);
 

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 50c665b..428b579 100644 (file)
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1224,7 +1224,8 @@ static vm_fault_t do_huge_pmd_wp_page_fallback(struct vm_fault *vmf,
                cond_resched();
        }
 
-       mmu_notifier_range_init(&range, vma->vm_mm, haddr,
+       mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm,
+                               haddr,
                                haddr + HPAGE_PMD_SIZE);
        mmu_notifier_invalidate_range_start(&range);
 
@@ -1388,7 +1389,8 @@ alloc:
                                    vma, HPAGE_PMD_NR);
        __SetPageUptodate(new_page);
 
-       mmu_notifier_range_init(&range, vma->vm_mm, haddr,
+       mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm,
+                               haddr,
                                haddr + HPAGE_PMD_SIZE);
        mmu_notifier_invalidate_range_start(&range);
 
@@ -2064,7 +2066,8 @@ void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud,
        spinlock_t *ptl;
        struct mmu_notifier_range range;
 
-       mmu_notifier_range_init(&range, vma->vm_mm, address & HPAGE_PUD_MASK,
+       mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm,
+                               address & HPAGE_PUD_MASK,
                                (address & HPAGE_PUD_MASK) + HPAGE_PUD_SIZE);
        mmu_notifier_invalidate_range_start(&range);
        ptl = pud_lock(vma->vm_mm, pud);
@@ -2282,7 +2285,8 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
        spinlock_t *ptl;
        struct mmu_notifier_range range;
 
-       mmu_notifier_range_init(&range, vma->vm_mm, address & HPAGE_PMD_MASK,
+       mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm,
+                               address & HPAGE_PMD_MASK,
                                (address & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE);
        mmu_notifier_invalidate_range_start(&range);
        ptl = pmd_lock(vma->vm_mm, pmd);

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 98a3c7c..89d206d 100644 (file)
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3294,7 +3294,8 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
        cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
 
        if (cow) {
-               mmu_notifier_range_init(&range, src, vma->vm_start,
+               mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, src,
+                                       vma->vm_start,
                                        vma->vm_end);
                mmu_notifier_invalidate_range_start(&range);
        }
@@ -3406,7 +3407,8 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
        /*
         * If sharing possible, alert mmu notifiers of worst case.
         */
-       mmu_notifier_range_init(&range, mm, start, end);
+       mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, mm, start,
+                               end);
        adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end);
        mmu_notifier_invalidate_range_start(&range);
        address = start;
@@ -3673,7 +3675,8 @@ retry_avoidcopy:
                            pages_per_huge_page(h));
        __SetPageUptodate(new_page);
 
-       mmu_notifier_range_init(&range, mm, haddr, haddr + huge_page_size(h));
+       mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, mm, haddr,
+                               haddr + huge_page_size(h));
        mmu_notifier_invalidate_range_start(&range);
 
        /*
@@ -4408,7 +4411,8 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
         * start/end.  Set range.start/range.end to cover the maximum possible
         * range if PMD sharing is possible.
         */
-       mmu_notifier_range_init(&range, mm, start, end);
+       mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, mm, start,
+                               end);
        adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end);
 
        BUG_ON(address >= end);

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 7ba7a1e..14581db 100644 (file)
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1016,7 +1016,8 @@ static void collapse_huge_page(struct mm_struct *mm,
        pte = pte_offset_map(pmd, address);
        pte_ptl = pte_lockptr(mm, pmd);
 
-       mmu_notifier_range_init(&range, mm, address, address + HPAGE_PMD_SIZE);
+       mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, NULL, mm,
+                               address, address + HPAGE_PMD_SIZE);
        mmu_notifier_invalidate_range_start(&range);
        pmd_ptl = pmd_lock(mm, pmd); /* probably unnecessary */
        /*

diff --git a/mm/ksm.c b/mm/ksm.c
index fc64874..01f5fe2 100644 (file)
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -1066,7 +1066,8 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page,
 
        BUG_ON(PageTransCompound(page));
 
-       mmu_notifier_range_init(&range, mm, pvmw.address,
+       mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, mm,
+                               pvmw.address,
                                pvmw.address + PAGE_SIZE);
        mmu_notifier_invalidate_range_start(&range);
 
@@ -1154,7 +1155,8 @@ static int replace_page(struct vm_area_struct *vma, struct page *page,
        if (!pmd)
                goto out;
 
-       mmu_notifier_range_init(&range, mm, addr, addr + PAGE_SIZE);
+       mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, mm, addr,
+                               addr + PAGE_SIZE);
        mmu_notifier_invalidate_range_start(&range);
 
        ptep = pte_offset_map_lock(mm, pmd, addr, &ptl);

diff --git a/mm/madvise.c b/mm/madvise.c
index bb3a455..1c52bdf 100644 (file)
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -472,7 +472,8 @@ static int madvise_free_single_vma(struct vm_area_struct *vma,
        range.end = min(vma->vm_end, end_addr);
        if (range.end <= vma->vm_start)
                return -EINVAL;
-       mmu_notifier_range_init(&range, mm, range.start, range.end);
+       mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, mm,
+                               range.start, range.end);
 
        lru_add_drain();
        tlb_gather_mmu(&tlb, mm, range.start, range.end);

diff --git a/mm/memory.c b/mm/memory.c
index f7d962d..9067267 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1010,7 +1010,8 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
        is_cow = is_cow_mapping(vma->vm_flags);
 
        if (is_cow) {
-               mmu_notifier_range_init(&range, src_mm, addr, end);
+               mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma,
+                                       src_mm, addr, end);
                mmu_notifier_invalidate_range_start(&range);
        }
 
@@ -1334,7 +1335,8 @@ void unmap_vmas(struct mmu_gather *tlb,
 {
        struct mmu_notifier_range range;
 
-       mmu_notifier_range_init(&range, vma->vm_mm, start_addr, end_addr);
+       mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm,
+                               start_addr, end_addr);
        mmu_notifier_invalidate_range_start(&range);
        for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next)
                unmap_single_vma(tlb, vma, start_addr, end_addr, NULL);
@@ -1356,7 +1358,8 @@ void zap_page_range(struct vm_area_struct *vma, unsigned long start,
        struct mmu_gather tlb;
 
        lru_add_drain();
-       mmu_notifier_range_init(&range, vma->vm_mm, start, start + size);
+       mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm,
+                               start, start + size);
        tlb_gather_mmu(&tlb, vma->vm_mm, start, range.end);
        update_hiwater_rss(vma->vm_mm);
        mmu_notifier_invalidate_range_start(&range);
@@ -1382,7 +1385,8 @@ static void zap_page_range_single(struct vm_area_struct *vma, unsigned long addr
        struct mmu_gather tlb;
 
        lru_add_drain();
-       mmu_notifier_range_init(&range, vma->vm_mm, address, address + size);
+       mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm,
+                               address, address + size);
        tlb_gather_mmu(&tlb, vma->vm_mm, address, range.end);
        update_hiwater_rss(vma->vm_mm);
        mmu_notifier_invalidate_range_start(&range);
@@ -2279,7 +2283,8 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 
        __SetPageUptodate(new_page);
 
-       mmu_notifier_range_init(&range, mm, vmf->address & PAGE_MASK,
+       mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, mm,
+                               vmf->address & PAGE_MASK,
                                (vmf->address & PAGE_MASK) + PAGE_SIZE);
        mmu_notifier_invalidate_range_start(&range);
 
@@ -4104,8 +4109,9 @@ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address,
                        goto out;
 
                if (range) {
-                       mmu_notifier_range_init(range, mm, address & PMD_MASK,
-                                            (address & PMD_MASK) + PMD_SIZE);
+                       mmu_notifier_range_init(range, MMU_NOTIFY_UNMAP, 0,
+                                               NULL, mm, address & PMD_MASK,
+                                               (address & PMD_MASK) + PMD_SIZE);
                        mmu_notifier_invalidate_range_start(range);
                }
                *ptlp = pmd_lock(mm, pmd);
@@ -4122,8 +4128,9 @@ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address,
                goto out;
 
        if (range) {
-               mmu_notifier_range_init(range, mm, address & PAGE_MASK,
-                                    (address & PAGE_MASK) + PAGE_SIZE);
+               mmu_notifier_range_init(range, MMU_NOTIFY_UNMAP, 0, NULL, mm,
+                                       address & PAGE_MASK,
+                                       (address & PAGE_MASK) + PAGE_SIZE);
                mmu_notifier_invalidate_range_start(range);
        }
        ptep = pte_offset_map_lock(mm, pmd, address, ptlp);

diff --git a/mm/migrate.c b/mm/migrate.c
index a177040..855bdb3 100644 (file)
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -2356,7 +2356,8 @@ static void migrate_vma_collect(struct migrate_vma *migrate)
        mm_walk.mm = migrate->vma->vm_mm;
        mm_walk.private = migrate;
 
-       mmu_notifier_range_init(&range, mm_walk.mm, migrate->start,
+       mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, NULL, mm_walk.mm,
+                               migrate->start,
                                migrate->end);
        mmu_notifier_invalidate_range_start(&range);
        walk_page_range(migrate->start, migrate->end, &mm_walk);
@@ -2764,6 +2765,8 @@ static void migrate_vma_pages(struct migrate_vma *migrate)
                                notified = true;
 
                                mmu_notifier_range_init(&range,
+                                                       MMU_NOTIFY_UNMAP, 0,
+                                                       NULL,
                                                        migrate->vma->vm_mm,
                                                        addr, migrate->end);
                                mmu_notifier_invalidate_range_start(&range);

diff --git a/mm/mprotect.c b/mm/mprotect.c
index 028c724..b109840 100644 (file)
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -185,7 +185,8 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 
                /* invoke the mmu notifier if the pmd is populated */
                if (!range.start) {
-                       mmu_notifier_range_init(&range, vma->vm_mm, addr, end);
+                       mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0,
+                                               vma, vma->vm_mm, addr, end);
                        mmu_notifier_invalidate_range_start(&range);
                }
 

diff --git a/mm/mremap.c b/mm/mremap.c
index e3edef6..fc241d2 100644 (file)
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -249,7 +249,8 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
        old_end = old_addr + len;
        flush_cache_range(vma, old_addr, old_end);
 
-       mmu_notifier_range_init(&range, vma->vm_mm, old_addr, old_end);
+       mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm,
+                               old_addr, old_end);
        mmu_notifier_invalidate_range_start(&range);
 
        for (; old_addr < old_end; old_addr += extent, new_addr += extent) {

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 3a24848..539c91d 100644 (file)
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -531,7 +531,8 @@ bool __oom_reap_task_mm(struct mm_struct *mm)
                        struct mmu_notifier_range range;
                        struct mmu_gather tlb;
 
-                       mmu_notifier_range_init(&range, mm, vma->vm_start,
+                       mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0,
+                                               vma, mm, vma->vm_start,
                                                vma->vm_end);
                        tlb_gather_mmu(&tlb, mm, range.start, range.end);
                        if (mmu_notifier_invalidate_range_start_nonblock(&range)) {

diff --git a/mm/rmap.c b/mm/rmap.c
index 76c8dfd..288e636 100644 (file)
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -896,7 +896,8 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma,
         * We have to assume the worse case ie pmd for invalidation. Note that
         * the page can not be free from this function.
         */
-       mmu_notifier_range_init(&range, vma->vm_mm, address,
+       mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm,
+                               address,
                                min(vma->vm_end, address +
                                    (PAGE_SIZE << compound_order(page))));
        mmu_notifier_invalidate_range_start(&range);
@@ -1371,7 +1372,8 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
         * Note that the page can not be free in this function as call of
         * try_to_unmap() must hold a reference on the page.
         */
-       mmu_notifier_range_init(&range, vma->vm_mm, address,
+       mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm,
+                               address,
                                min(vma->vm_end, address +
                                    (PAGE_SIZE << compound_order(page))));
        if (PageHuge(page)) {