[PATCH] 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@xxxxxxxxxx>
Signed-off-by: Breno Leitao <leitao@xxxxxxxxxx>
---
 include/linux/mm.h  |  6 ++++++
 kernel/kexec_core.c | 10 ++++++++++
 kernel/kexec_file.c | 14 ++++++++++++++
 mm/memory-failure.c | 18 ++++++++++++++++++
 4 files changed, 48 insertions(+)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 7fabe6c66b4b7..a89108bcc3f90 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);
+bool range_contains_hwpoison(phys_addr_t start, unsigned long size);
 #else
 static inline void memory_failure_queue(unsigned long pfn, int flags)
 {
@@ -5204,6 +5205,11 @@ 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)
+{
+	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..18793f925835f 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))
+			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..cd77350f12f85 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -504,6 +504,13 @@ static int locate_mem_hole_top_down(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)) {
+			temp_start = temp_start - PAGE_SIZE;
+			continue;
+		}
+
 		/* We found a suitable memory range */
 		break;
 	} while (1);
@@ -546,6 +553,13 @@ 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)) {
+			temp_start = temp_start + 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..032bb23db7566 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -96,6 +96,24 @@ void num_poisoned_pages_sub(unsigned long pfn, long i)
 		memblk_nr_poison_sub(pfn, i);
 }
 
+/*
+ * Check if any page in [start, start + size) has hardware-poisoned segments
+ */
+bool range_contains_hwpoison(phys_addr_t start, unsigned long size)
+{
+	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++) {
+		if (pfn_valid(pfn) && PageHWPoison(pfn_to_page(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 <leitao@xxxxxxxxxx>