kmsan: remove hard-coded GFP_KERNEL flags

kmsan_vmap_pages_range_noflush() allocates its temp s_pages/o_pages arrays
with GFP_KERNEL, which may sleep.  This is inconsistent with vmalloc() as
it will support non-blocking requests later.

Plumb gfp_mask through the kmsan_vmap_pages_range_noflush(), so it can use
it internally for its demand.

Please note, the subsequent __vmap_pages_range_noflush() still uses
GFP_KERNEL and can sleep.  If a caller runs under reclaim constraints,
sleeping is forbidden, it must establish the appropriate memalloc scope
API.

Link: https://lkml.kernel.org/r/20251007122035.56347-8-urezki@gmail.com
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Reviewed-by: Alexander Potapenko <glider@google.com>
Cc: Marco Elver <elver@google.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Michal Hocko <mhocko@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/include/linux/kmsan.h b/include/linux/kmsan.h
index f2fd221107bbaa177a6bfd609f44cfdf74545a9a..7da9fd506b390fd07f8e418ed4d6ba728185d46d 100644 (file)
--- a/include/linux/kmsan.h
+++ b/include/linux/kmsan.h
@@ -133,6 +133,7 @@ void kmsan_kfree_large(const void *ptr);
  * @prot:      page protection flags used for vmap.
  * @pages:     array of pages.
  * @page_shift:        page_shift passed to vmap_range_noflush().
+ * @gfp_mask:  gfp_mask to use internally.
  *
  * KMSAN maps shadow and origin pages of @pages into contiguous ranges in
  * vmalloc metadata address range. Returns 0 on success, callers must check
@@ -142,7 +143,8 @@ int __must_check kmsan_vmap_pages_range_noflush(unsigned long start,
                                                unsigned long end,
                                                pgprot_t prot,
                                                struct page **pages,
-                                               unsigned int page_shift);
+                                               unsigned int page_shift,
+                                               gfp_t gfp_mask);
 
 /**
  * kmsan_vunmap_kernel_range_noflush() - Notify KMSAN about a vunmap.
@@ -347,7 +349,7 @@ static inline void kmsan_kfree_large(const void *ptr)
 
 static inline int __must_check kmsan_vmap_pages_range_noflush(
        unsigned long start, unsigned long end, pgprot_t prot,
-       struct page **pages, unsigned int page_shift)
+       struct page **pages, unsigned int page_shift, gfp_t gfp_mask)
 {
        return 0;
 }

diff --git a/mm/internal.h b/mm/internal.h
index 1561fc2ff5b832e45f7c4131c565614594748a4d..e623c81033588e27b173dfd07066c5d456ed557b 100644 (file)
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1355,7 +1355,7 @@ size_t splice_folio_into_pipe(struct pipe_inode_info *pipe,
 #ifdef CONFIG_MMU
 void __init vmalloc_init(void);
 int __must_check vmap_pages_range_noflush(unsigned long addr, unsigned long end,
-                pgprot_t prot, struct page **pages, unsigned int page_shift);
+       pgprot_t prot, struct page **pages, unsigned int page_shift, gfp_t gfp_mask);
 unsigned int get_vm_area_page_order(struct vm_struct *vm);
 #else
 static inline void vmalloc_init(void)
@@ -1364,7 +1364,7 @@ static inline void vmalloc_init(void)
 
 static inline
 int __must_check vmap_pages_range_noflush(unsigned long addr, unsigned long end,
-                pgprot_t prot, struct page **pages, unsigned int page_shift)
+       pgprot_t prot, struct page **pages, unsigned int page_shift, gfp_t gfp_mask)
 {
        return -EINVAL;
 }

diff --git a/mm/kmsan/shadow.c b/mm/kmsan/shadow.c
index 54f3c3c962f07842587b8cde6f3b7247ca6de8dd..3cd733663100d0845c2e5e02f6fe2b48584d695d 100644 (file)
--- a/mm/kmsan/shadow.c
+++ b/mm/kmsan/shadow.c
@@ -215,7 +215,7 @@ void kmsan_free_page(struct page *page, unsigned int order)
 
 int kmsan_vmap_pages_range_noflush(unsigned long start, unsigned long end,
                                   pgprot_t prot, struct page **pages,
-                                  unsigned int page_shift)
+                                  unsigned int page_shift, gfp_t gfp_mask)
 {
        unsigned long shadow_start, origin_start, shadow_end, origin_end;
        struct page **s_pages, **o_pages;
@@ -230,8 +230,8 @@ int kmsan_vmap_pages_range_noflush(unsigned long start, unsigned long end,
                return 0;
 
        nr = (end - start) / PAGE_SIZE;
-       s_pages = kcalloc(nr, sizeof(*s_pages), GFP_KERNEL);
-       o_pages = kcalloc(nr, sizeof(*o_pages), GFP_KERNEL);
+       s_pages = kcalloc(nr, sizeof(*s_pages), gfp_mask);
+       o_pages = kcalloc(nr, sizeof(*o_pages), gfp_mask);
        if (!s_pages || !o_pages) {
                err = -ENOMEM;
                goto ret;

diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c
index cd69caf6aa8d8eded2395eb4bc4051b78ec6aa33..4f5937090590d87da091ed1502fd792485245a55 100644 (file)
--- a/mm/percpu-vm.c
+++ b/mm/percpu-vm.c
@@ -194,7 +194,7 @@ static int __pcpu_map_pages(unsigned long addr, struct page **pages,
                            int nr_pages)
 {
        return vmap_pages_range_noflush(addr, addr + (nr_pages << PAGE_SHIFT),
-                                       PAGE_KERNEL, pages, PAGE_SHIFT);
+                       PAGE_KERNEL, pages, PAGE_SHIFT, GFP_KERNEL);
 }
 
 /**

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index d8bcd87239b59ab018ffb17506965e0b5ae3f3bf..d7e7049e01f8ff7d6b627dd72730204bb4942096 100644 (file)
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -671,16 +671,28 @@ int __vmap_pages_range_noflush(unsigned long addr, unsigned long end,
 }
 
 int vmap_pages_range_noflush(unsigned long addr, unsigned long end,
-               pgprot_t prot, struct page **pages, unsigned int page_shift)
+               pgprot_t prot, struct page **pages, unsigned int page_shift,
+               gfp_t gfp_mask)
 {
        int ret = kmsan_vmap_pages_range_noflush(addr, end, prot, pages,
-                                                page_shift);
+                                               page_shift, gfp_mask);
 
        if (ret)
                return ret;
        return __vmap_pages_range_noflush(addr, end, prot, pages, page_shift);
 }
 
+static int __vmap_pages_range(unsigned long addr, unsigned long end,
+               pgprot_t prot, struct page **pages, unsigned int page_shift,
+               gfp_t gfp_mask)
+{
+       int err;
+
+       err = vmap_pages_range_noflush(addr, end, prot, pages, page_shift, gfp_mask);
+       flush_cache_vmap(addr, end);
+       return err;
+}
+
 /**
  * vmap_pages_range - map pages to a kernel virtual address
  * @addr: start of the VM area to map
@@ -696,11 +708,7 @@ int vmap_pages_range_noflush(unsigned long addr, unsigned long end,
 int vmap_pages_range(unsigned long addr, unsigned long end,
                pgprot_t prot, struct page **pages, unsigned int page_shift)
 {
-       int err;
-
-       err = vmap_pages_range_noflush(addr, end, prot, pages, page_shift);
-       flush_cache_vmap(addr, end);
-       return err;
+       return __vmap_pages_range(addr, end, prot, pages, page_shift, GFP_KERNEL);
 }
 
 static int check_sparse_vm_area(struct vm_struct *area, unsigned long start,
@@ -3839,8 +3847,8 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
         */
        flags = memalloc_apply_gfp_scope(gfp_mask);
        do {
-               ret = vmap_pages_range(addr, addr + size, prot, area->pages,
-                       page_shift);
+               ret = __vmap_pages_range(addr, addr + size, prot, area->pages,
+                               page_shift, nested_gfp);
                if (nofail && (ret < 0))
                        schedule_timeout_uninterruptible(1);
        } while (nofail && (ret < 0));