[PATCH v3] kexec: keep the next kernel off hardware-poisoned pages

[Breno Leitao]

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 <kas at kernel.org>
Signed-off-by: Breno Leitao <leitao at debian.org>
---
Tested on x86_64 under virtme-ng, poisoning frames through
/sys/kernel/debug/hwpoison/corrupt-pfn:

 - kexec_file_load(): poisoning a page inside the range the previous load
   picked moves the kernel from 0x13b000000 to 0x138000000, and moves the
   crash kernel's elfcorehdr, the only bottom-up user on x86, from
   0xaf000000 to 0xaf001000.
 - kexec_load(): a one page segment aimed at a poisoned frame fails with
   EADDRNOTAVAIL, while the same segment on a clean frame still loads.
 - No splat with CONFIG_DEBUG_ATOMIC_SLEEP=y, and the box kexecs into the
   relocated kernel.
---
Changes in v3:
- Return the address of the last poisoned page in the range, or
  PHYS_ADDR_MAX when it is clean, instead of a bool plus an output
  parameter. Renamed to range_last_hwpoison(). (Pratyush Yadav)
- Add cond_resched() to the scan loop, as a segment can span half of
  memory. (Sashiko)
- Link to v2: https://patch.msgid.link/20260730-kexec_posioned-v2-1-f92d18551f64@debian.org

Changes in v2:
- Change from pfn_to_page() to pfn_to_online_page(). (Miaohe Lin)
- Return the poisoned address once we find a hit, to avoid the O(n^2)
  rescan. (Sashiko)
- Link to v1: https://patch.msgid.link/20260728-kexec_posioned-v1-1-160c81d180fe@debian.org

To: Andrew Morton <akpm at linux-foundation.org>
To: David Hildenbrand <david at kernel.org>
To: Lorenzo Stoakes <ljs at kernel.org>
To: "Liam R. Howlett" <liam at infradead.org>
To: Vlastimil Babka <vbabka at kernel.org>
To: Mike Rapoport <rppt at kernel.org>
To: Suren Baghdasaryan <surenb at google.com>
To: Michal Hocko <mhocko at suse.com>
To: Baoquan He <baoquan.he at linux.dev>
To: Pasha Tatashin <pasha.tatashin at soleen.com>
To: Pratyush Yadav <pratyush at kernel.org>
To: Miaohe Lin <linmiaohe at huawei.com>
To: Naoya Horiguchi <nao.horiguchi at gmail.com>
Cc: linux-mm at kvack.org
Cc: linux-kernel at vger.kernel.org
Cc: kexec at lists.infradead.org
---
 include/linux/mm.h  |  7 +++++++
 kernel/kexec_core.c | 13 +++++++++++++
 kernel/kexec_file.c | 18 ++++++++++++++++++
 mm/memory-failure.c | 25 +++++++++++++++++++++++++
 4 files changed, 63 insertions(+)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 7fabe6c66b4b7..fa4f55eff2415 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -5192,6 +5192,7 @@ 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);
+phys_addr_t range_last_hwpoison(phys_addr_t start, unsigned long size);
 #else
 static inline void memory_failure_queue(unsigned long pfn, int flags)
 {
@@ -5204,6 +5205,12 @@ static inline void num_poisoned_pages_inc(unsigned long pfn)
 static inline void num_poisoned_pages_sub(unsigned long pfn, long i)
 {
 }
+
+static inline phys_addr_t range_last_hwpoison(phys_addr_t start,
+					      unsigned long size)
+{
+	return PHYS_ADDR_MAX;
+}
 #endif
 
 #if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG)
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index dc770b9a6d053..f2a519a4a6d93 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -212,6 +212,19 @@ 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++) {
+		phys_addr_t poison;
+
+		poison = range_last_hwpoison(image->segment[i].mem,
+					     image->segment[i].memsz);
+		if (poison != PHYS_ADDR_MAX)
+			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..530c919412a92 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 poison;
 
 	temp_end = min(end, kbuf->buf_max);
 	temp_start = temp_end - kbuf->memsz + 1;
@@ -504,6 +505,15 @@ static int locate_mem_hole_top_down(unsigned long start, unsigned long end,
 			continue;
 		}
 
+		poison = range_last_hwpoison(temp_start, kbuf->memsz);
+		if (poison != PHYS_ADDR_MAX) {
+			/* we hit a poisoned page */
+			if (poison < kbuf->memsz)
+				return 0;
+			temp_start = poison - kbuf->memsz;
+			continue;
+		}
+
 		/* We found a suitable memory range */
 		break;
 	} while (1);
@@ -520,6 +530,7 @@ 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 poison;
 
 	temp_start = max(start, kbuf->buf_min);
 
@@ -546,6 +557,13 @@ static int locate_mem_hole_bottom_up(unsigned long start, unsigned long end,
 			continue;
 		}
 
+		poison = range_last_hwpoison(temp_start, kbuf->memsz);
+		if (poison != PHYS_ADDR_MAX) {
+			/* we hit a poisoned page */
+			temp_start = poison + 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..ef0e989c25d93 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -96,6 +96,31 @@ void num_poisoned_pages_sub(unsigned long pfn, long i)
 		memblk_nr_poison_sub(pfn, i);
 }
 
+/*
+ * Return the address of the last hardware-poisoned online page in
+ * [start, start + size), or PHYS_ADDR_MAX if the range is clean.
+ */
+phys_addr_t range_last_hwpoison(phys_addr_t start, unsigned long size)
+{
+	phys_addr_t poison = PHYS_ADDR_MAX;
+	unsigned long pfn, end_pfn;
+
+	if (!size || !atomic_long_read(&num_poisoned_pages))
+		return poison;
+
+	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))
+			poison = PFN_PHYS(pfn);
+
+		cond_resched();
+	}
+
+	return poison;
+}
+
 /**
  * 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 <leitao at debian.org>