Re: [PATCH v2 1/3] vmalloc: add __GFP_SKIP_KASAN support

[Ryan Roberts]

On 24/03/2026 13:26, Muhammad Usama Anjum wrote:
> For allocations that will be accessed only with match-all pointers
> (e.g., kernel stacks), setting tags is wasted work. If the caller
> already set __GFP_SKIP_KASAN, don’t skip zeroing the pages and
> don’t set KASAN_VMALLOC_PROT_NORMAL so kasan_unpoison_vmalloc()
> returns early without tagging.
> 
> Before this patch, __GFP_SKIP_KASAN wasn't being used with vmalloc
> APIs. So it wasn't being checked. Now its being checked and acted
> upon. Other KASAN modes are unchanged because __GFP_SKIP_KASAN isn't
> defined there.
> 
> This is a preparatory patch for optimizing kernel stack allocations.
> 
> Signed-off-by: Muhammad Usama Anjum <usama.anjum@xxxxxxx>
> ---
> Changes since v1:
> - Simplify skip conditions based on the fact that __GFP_SKIP_KASAN
>   is zero in non-hw-tags mode.
> - Add __GFP_SKIP_KASAN to GFP_VMALLOC_SUPPORTED list of flags
> ---
>  mm/vmalloc.c | 11 ++++++++---
>  1 file changed, 8 insertions(+), 3 deletions(-)
> 
> diff --git a/mm/vmalloc.c b/mm/vmalloc.c
> index c607307c657a6..69ae205effb46 100644
> --- a/mm/vmalloc.c
> +++ b/mm/vmalloc.c
> @@ -3939,7 +3939,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
>  				__GFP_NOFAIL | __GFP_ZERO |\
>  				__GFP_NORETRY | __GFP_RETRY_MAYFAIL |\
>  				GFP_NOFS | GFP_NOIO | GFP_KERNEL_ACCOUNT |\
> -				GFP_USER | __GFP_NOLOCKDEP)
> +				GFP_USER | __GFP_NOLOCKDEP | __GFP_SKIP_KASAN)
>  
>  static gfp_t vmalloc_fix_flags(gfp_t flags)
>  {
> @@ -3980,6 +3980,8 @@ static gfp_t vmalloc_fix_flags(gfp_t flags)
>   *
>   * %__GFP_NOWARN can be used to suppress failure messages.
>   *
> + * %__GFP_SKIP_KASAN can be used to skip poisoning

You mean skip *un*poisoning, I think? But you would only want this to apply to
the actaul pages mapped by vmalloc. You wouldn't want to skip unpoisoning for
any allocated meta data; I think that is currently possible since the gfp_flags
that are passed into __vmalloc_node_range_noprof() are passed down to
__get_vm_area_node() unmdified. You probably want to explicitly ensure
__GFP_SKIP_KASAN is clear for that internal call?

> + *
>   * Can not be called from interrupt nor NMI contexts.
>   * Return: the address of the area or %NULL on failure
>   */
> @@ -4041,7 +4043,9 @@ void *__vmalloc_node_range_noprof(unsigned long size, unsigned long align,
>  	 * kasan_unpoison_vmalloc().
>  	 */
>  	if (pgprot_val(prot) == pgprot_val(PAGE_KERNEL)) {
> -		if (kasan_hw_tags_enabled()) {
> +		bool skip_kasan = gfp_mask & __GFP_SKIP_KASAN;
> +
> +		if (kasan_hw_tags_enabled() && !skip_kasan) {
>  			/*
>  			 * Modify protection bits to allow tagging.
>  			 * This must be done before mapping.
> @@ -4057,7 +4061,8 @@ void *__vmalloc_node_range_noprof(unsigned long size, unsigned long align,
>  		}
>  
>  		/* Take note that the mapping is PAGE_KERNEL. */
> -		kasan_flags |= KASAN_VMALLOC_PROT_NORMAL;
> +		if (!skip_kasan)
> +			kasan_flags |= KASAN_VMALLOC_PROT_NORMAL;

It's pretty ugly to use the absence of this flag to rely on
kasan_unpoison_vmalloc() not unpoisoning. Perhaps it is preferable to just not
call kasan_unpoison_vmalloc() for the skip_kasan case?

>  	}
>  
>  	/* Allocate physical pages and map them into vmalloc space. */

Perhaps something like this would work:

---8<---
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index c31a8615a8328..c340db141df57 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -3979,6 +3979,8 @@ static gfp_t vmalloc_fix_flags(gfp_t flags)
  * under moderate memory pressure.
  *
  * %__GFP_NOWARN can be used to suppress failure messages.
+
+ * %__GFP_SKIP_KASAN skip unpoisoning of mapped pages (when prot=PAGE_KERNEL).
  *
  * Can not be called from interrupt nor NMI contexts.
  * Return: the address of the area or %NULL on failure
@@ -3993,6 +3995,9 @@ void *__vmalloc_node_range_noprof(unsigned long size,
unsigned long align,
 	kasan_vmalloc_flags_t kasan_flags = KASAN_VMALLOC_NONE;
 	unsigned long original_align = align;
 	unsigned int shift = PAGE_SHIFT;
+	bool skip_kasan = gfp_mask & __GFP_SKIP_KASAN;
+
+	gfp_mask &= ~__GFP_SKIP_KASAN;
  	if (WARN_ON_ONCE(!size))
 		return NULL;
@@ -4041,7 +4046,7 @@ void *__vmalloc_node_range_noprof(unsigned long size,
unsigned long align,
 	 * kasan_unpoison_vmalloc().
 	 */
 	if (pgprot_val(prot) == pgprot_val(PAGE_KERNEL)) {
-		if (kasan_hw_tags_enabled()) {
+		if (kasan_hw_tags_enabled() && !skip_kasan) {
 			/*
 			 * Modify protection bits to allow tagging.
 			 * This must be done before mapping.
@@ -4054,6 +4059,12 @@ void *__vmalloc_node_range_noprof(unsigned long size,
unsigned long align,
 			 * poisoned and zeroed by kasan_unpoison_vmalloc().
 			 */
 			gfp_mask |= __GFP_SKIP_KASAN | __GFP_SKIP_ZERO;
+		} else if (skip_kasan) {
+			/*
+			 * Skip page_alloc unpoisoning physical pages backing
+			 * VM_ALLOC mapping, as requested by caller.
+			 */
+			gfp_mask |= __GFP_SKIP_KASAN;
 		}
  		/* Take note that the mapping is PAGE_KERNEL. */
@@ -4078,7 +4089,8 @@ void *__vmalloc_node_range_noprof(unsigned long size,
unsigned long align,
 	    (gfp_mask & __GFP_SKIP_ZERO))
 		kasan_flags |= KASAN_VMALLOC_INIT;
 	/* KASAN_VMALLOC_PROT_NORMAL already set if required. */
-	area->addr = kasan_unpoison_vmalloc(area->addr, size, kasan_flags);
+	if (!skip_kasan)
+		area->addr = kasan_unpoison_vmalloc(area->addr, size, kasan_flags);
  	/*
 	 * In this function, newly allocated vm_struct has VM_UNINITIALIZED

---8<---

Thanks,
Ryan