summaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2023-08-25 11:44:43 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2023-08-25 11:44:43 -0700
commit6f0edbb833ec16ab2042073af4846152b455104d (patch)
tree5295baa2ada00c7b5eb45c79b2a0d82f130b4f50 /include
parent4942fed84b98cfb71d3cdff1a3df0072a57bbdfa (diff)
parente5548f85b4527c4c803b7eae7887c10bf8f90c97 (diff)
Merge tag 'mm-hotfixes-stable-2023-08-25-11-07' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull misc fixes from Andrew Morton: "18 hotfixes. 13 are cc:stable and the remainder pertain to post-6.4 issues or aren't considered suitable for a -stable backport" * tag 'mm-hotfixes-stable-2023-08-25-11-07' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: shmem: fix smaps BUG sleeping while atomic selftests: cachestat: catch failing fsync test on tmpfs selftests: cachestat: test for cachestat availability maple_tree: disable mas_wr_append() when other readers are possible madvise:madvise_free_pte_range(): don't use mapcount() against large folio for sharing check madvise:madvise_free_huge_pmd(): don't use mapcount() against large folio for sharing check madvise:madvise_cold_or_pageout_pte_range(): don't use mapcount() against large folio for sharing check mm: multi-gen LRU: don't spin during memcg release mm: memory-failure: fix unexpected return value in soft_offline_page() radix tree: remove unused variable mm: add a call to flush_cache_vmap() in vmap_pfn() selftests/mm: FOLL_LONGTERM need to be updated to 0x100 nilfs2: fix general protection fault in nilfs_lookup_dirty_data_buffers() mm/gup: handle cont-PTE hugetlb pages correctly in gup_must_unshare() via GUP-fast selftests: cgroup: fix test_kmem_basic less than error mm: enable page walking API to lock vmas during the walk smaps: use vm_normal_page_pmd() instead of follow_trans_huge_pmd() mm/gup: reintroduce FOLL_NUMA as FOLL_HONOR_NUMA_FAULT
Diffstat (limited to 'include')
-rw-r--r--include/linux/huge_mm.h3
-rw-r--r--include/linux/mm.h21
-rw-r--r--include/linux/mm_types.h9
-rw-r--r--include/linux/pagewalk.h11
4 files changed, 35 insertions, 9 deletions
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 20284387b841..e718dbe928ba 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -25,9 +25,6 @@ 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);
-struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
- unsigned long addr, pmd_t *pmd,
- unsigned int flags);
bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
pmd_t *pmd, unsigned long addr, unsigned long next);
int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 406ab9ea818f..34f9dba17c1a 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3421,15 +3421,24 @@ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags)
* Indicates whether GUP can follow a PROT_NONE mapped page, or whether
* a (NUMA hinting) fault is required.
*/
-static inline bool gup_can_follow_protnone(unsigned int flags)
+static inline bool gup_can_follow_protnone(struct vm_area_struct *vma,
+ unsigned int flags)
{
/*
- * FOLL_FORCE has to be able to make progress even if the VMA is
- * inaccessible. Further, FOLL_FORCE access usually does not represent
- * application behaviour and we should avoid triggering NUMA hinting
- * faults.
+ * If callers don't want to honor NUMA hinting faults, no need to
+ * determine if we would actually have to trigger a NUMA hinting fault.
*/
- return flags & FOLL_FORCE;
+ if (!(flags & FOLL_HONOR_NUMA_FAULT))
+ return true;
+
+ /*
+ * NUMA hinting faults don't apply in inaccessible (PROT_NONE) VMAs.
+ *
+ * Requiring a fault here even for inaccessible VMAs would mean that
+ * FOLL_FORCE cannot make any progress, because handle_mm_fault()
+ * refuses to process NUMA hinting faults in inaccessible VMAs.
+ */
+ return !vma_is_accessible(vma);
}
typedef int (*pte_fn_t)(pte_t *pte, unsigned long addr, void *data);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 5e74ce4a28cd..7d30dc4ff0ff 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -1286,6 +1286,15 @@ enum {
FOLL_PCI_P2PDMA = 1 << 10,
/* allow interrupts from generic signals */
FOLL_INTERRUPTIBLE = 1 << 11,
+ /*
+ * Always honor (trigger) NUMA hinting faults.
+ *
+ * FOLL_WRITE implicitly honors NUMA hinting faults because a
+ * PROT_NONE-mapped page is not writable (exceptions with FOLL_FORCE
+ * apply). get_user_pages_fast_only() always implicitly honors NUMA
+ * hinting faults.
+ */
+ FOLL_HONOR_NUMA_FAULT = 1 << 12,
/* See also internal only FOLL flags in mm/internal.h */
};
diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h
index 27a6df448ee5..27cd1e59ccf7 100644
--- a/include/linux/pagewalk.h
+++ b/include/linux/pagewalk.h
@@ -6,6 +6,16 @@
struct mm_walk;
+/* Locking requirement during a page walk. */
+enum page_walk_lock {
+ /* mmap_lock should be locked for read to stabilize the vma tree */
+ PGWALK_RDLOCK = 0,
+ /* vma will be write-locked during the walk */
+ PGWALK_WRLOCK = 1,
+ /* vma is expected to be already write-locked during the walk */
+ PGWALK_WRLOCK_VERIFY = 2,
+};
+
/**
* struct mm_walk_ops - callbacks for walk_page_range
* @pgd_entry: if set, called for each non-empty PGD (top-level) entry
@@ -66,6 +76,7 @@ struct mm_walk_ops {
int (*pre_vma)(unsigned long start, unsigned long end,
struct mm_walk *walk);
void (*post_vma)(struct mm_walk *walk);
+ enum page_walk_lock walk_lock;
};
/*