Commit b186a942 authored by Uladzislau Rezki (Sony)'s avatar Uladzislau Rezki (Sony) Committed by Andrew Morton
Browse files

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: default avatarUladzislau Rezki (Sony) <urezki@gmail.com>
Reviewed-by: default avatarAlexander 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: default avatarAndrew Morton <akpm@linux-foundation.org>
parent ad435e79

include/linux/kmsan.h

+4 −2
Original line number Diff line number Diff line
@@ -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;

}

mm/internal.h

+2 −2
Original line number Diff line number Diff line
@@ -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;

}

mm/kmsan/shadow.c

+3 −3
Original line number Diff line number Diff line
@@ -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;

mm/percpu-vm.c

+1 −1
Original line number Diff line number Diff line
@@ -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);

}



/**

mm/vmalloc.c

+17 −9
Original line number Diff line number Diff line
@@ -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));