Re: [PATCH v2] kexec: keep the next kernel off hardware-poisoned pages

On Thu, Jul 30 2026, Breno Leitao wrote:

> Memory failures (such as unrecoverable ECCs errors) are getting more and
> more common. The kernel knows how to handle it while running, marking it
> as poisoned (and SIGBUS user tasks).
>
> Poisoned memory is removed from the buddy allocator, but, not from
> other places. A current problem is that kexec will load new kernel
> on top of a bad/poisoned memory, which is undesirable.
>
> If the next kernel's image, initrd or purgatory lands on poisoned frame,
> the relocation copy writes to the bad memory and the machine checks
> during the kexec.
>
> Skip hardware-poisoned frames when placing segments: check them in the
> kexec_file hole finder so it lays the next kernel down on good memory,
> and reject a poisoned destination in sanity_check_segment_list() for
> the kexec_load path, which cannot relocate.
>
> Suggested-by: Kiryl Shutsemau <[email protected]>
> Signed-off-by: Breno Leitao <[email protected]>
> ---
> Changes in v2:
> - EDITME: describe what is new in this series revision.
> - EDITME: use bulletpoints and terse descriptions.
> - Link to v1: https://patch.msgid.link/[email protected]
> ---
>  include/linux/mm.h  |  8 ++++++++
>  kernel/kexec_core.c | 10 ++++++++++
>  kernel/kexec_file.c | 19 +++++++++++++++++++
>  mm/memory-failure.c | 28 ++++++++++++++++++++++++++++
>  4 files changed, 65 insertions(+)
>
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 7fabe6c66b4b7..48cad9a519d08 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -5192,6 +5192,8 @@ extern const struct attribute_group memory_failure_attr_group;
>  extern void memory_failure_queue(unsigned long pfn, int flags);
>  void num_poisoned_pages_inc(unsigned long pfn);
>  void num_poisoned_pages_sub(unsigned long pfn, long i);
> +bool range_contains_hwpoison(phys_addr_t start, unsigned long size,
> +			     phys_addr_t *poison);
>  #else
>  static inline void memory_failure_queue(unsigned long pfn, int flags)
>  {
> @@ -5204,6 +5206,12 @@ static inline void num_poisoned_pages_inc(unsigned long pfn)
>  static inline void num_poisoned_pages_sub(unsigned long pfn, long i)
>  {
>  }
> +
> +static inline bool range_contains_hwpoison(phys_addr_t start, unsigned long size,
> +					   phys_addr_t *poison)
> +{
> +	return false;
> +}
>  #endif
>  
>  #if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG)
> diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
> index dc770b9a6d053..9f6ed3c04299b 100644
> --- a/kernel/kexec_core.c
> +++ b/kernel/kexec_core.c
> @@ -212,6 +212,16 @@ int sanity_check_segment_list(struct kimage *image)
>  	}
>  #endif
>  
> +	/*
> +	 * Reject destinations that land on hardware-poisoned memory: the
> +	 * relocation copy would machine-check on the bad frame.
> +	 */
> +	for (i = 0; i < nr_segments; i++) {
> +		if (range_contains_hwpoison(image->segment[i].mem,
> +					    image->segment[i].memsz, NULL))
> +			return -EADDRNOTAVAIL;
> +	}
> +
>  	/*
>  	 * The destination addresses are searched from system RAM rather than
>  	 * being allocated from the buddy allocator, so they are not guaranteed
> diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
> index 59fb9d71e9d86..95cc981a557be 100644
> --- a/kernel/kexec_file.c
> +++ b/kernel/kexec_file.c
> @@ -475,6 +475,7 @@ static int locate_mem_hole_top_down(unsigned long start, unsigned long end,
>  {
>  	struct kimage *image = kbuf->image;
>  	unsigned long temp_start, temp_end;
> +	phys_addr_t poisoned_addr;
>  
>  	temp_end = min(end, kbuf->buf_max);
>  	temp_start = temp_end - kbuf->memsz + 1;
> @@ -504,6 +505,14 @@ static int locate_mem_hole_top_down(unsigned long start, unsigned long end,
>  			continue;
>  		}
>  
> +		if (range_contains_hwpoison(temp_start, temp_end - temp_start + 1,
> +					    &poisoned_addr)) {
> +			if (poisoned_addr < kbuf->memsz)
> +				return 0;
> +			temp_start = poisoned_addr - kbuf->memsz;
> +			continue;
> +		}
> +
>  		/* We found a suitable memory range */
>  		break;
>  	} while (1);
> @@ -520,6 +529,7 @@ static int locate_mem_hole_bottom_up(unsigned long start, unsigned long end,
>  {
>  	struct kimage *image = kbuf->image;
>  	unsigned long temp_start, temp_end;
> +	phys_addr_t poisoned_addr;
>  
>  	temp_start = max(start, kbuf->buf_min);
>  
> @@ -546,6 +556,15 @@ static int locate_mem_hole_bottom_up(unsigned long start, unsigned long end,
>  			continue;
>  		}
>  
> +		/*
> +		 * Avoid placing the next kernel on hardware-poisoned memory.
> +		 */
> +		if (range_contains_hwpoison(temp_start, temp_end - temp_start + 1,
> +					    &poisoned_addr)) {
> +			temp_start = poisoned_addr + PAGE_SIZE;
> +			continue;
> +		}
> +
>  		/* We found a suitable memory range */
>  		break;
>  	} while (1);
> diff --git a/mm/memory-failure.c b/mm/memory-failure.c
> index a8b03e2920ba8..04a1883d51fda 100644
> --- a/mm/memory-failure.c
> +++ b/mm/memory-failure.c
> @@ -96,6 +96,34 @@ void num_poisoned_pages_sub(unsigned long pfn, long i)
>  		memblk_nr_poison_sub(pfn, i);
>  }
>  
> +/*
> + * Return true if any online page in [start, start + size) is hardware
> + * poisoned.  On a hit, when @poison is not NULL, @poison is set to the
> + * address of the first poisoned page, which is ugly, but I cannot only

Won't the last page be better? If two poisoned pages land in the range,
you'd like to search past the last one.

> + * return phys_addr_t, thus this "extra" parameter, instead of returning
> + * the hit.
> + */
> +bool range_contains_hwpoison(phys_addr_t start, unsigned long size,
> +			     phys_addr_t *poison)

Perhaps

    phys_addr_t range_last_hwpoison(phys_addr_t start, unsigned long size)  ?

And if no poisoned page lands here then a default of 0 or ~0UL?

> +{
> +	unsigned long pfn, end_pfn;
> +
> +	if (!size || !atomic_long_read(&num_poisoned_pages))
> +		return false;
> +
> +	end_pfn = PHYS_PFN(start + size - 1);
> +	for (pfn = PHYS_PFN(start); pfn <= end_pfn; pfn++) {
> +		struct page *page = pfn_to_online_page(pfn);
> +
> +		if (page && PageHWPoison(page)) {
> +			if (poison)
> +				*poison = PFN_PHYS(pfn);
> +			return true;
> +		}
> +	}
> +	return false;
> +}
> +
>  /**
>   * MF_ATTR_RO - Create sysfs entry for each memory failure statistics.
>   * @_name: name of the file in the per NUMA sysfs directory.
>
> ---
> base-commit: c5e32e86ca02b003f86e095d379b38148999293d
> change-id: 20260727-kexec_posioned-72bb0a4143a0
>
> Best regards,
> --  
>
> Breno Leitao <[email protected]>
>

-- 
Regards,
Pratyush Yadav