[v2,3/7] accel/kvm: Report the loss of a large memory page

Commit Message

“William Roche Nov. 7, 2024, 10:21 a.m. UTC

From: William Roche <[e-mail]>

When an entire large page is impacted by an error (hugetlbfs case),
report better the size and location of this large memory hole, so
give a warning message when this page is first hit:
Memory error: Loosing a large page (size: X) at QEMU addr Y and GUEST addr Z

Signed-off-by: William Roche <[e-mail]>
---
 accel/kvm/kvm-all.c      | 9 ++++++++-
 include/sysemu/kvm_int.h | 4 +++-
 target/arm/kvm.c         | 2 +-
 target/i386/kvm/kvm.c    | 2 +-
 4 files changed, 13 insertions(+), 4 deletions(-)

Patch

diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index 6dd06f5edf..a572437115 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -1284,7 +1284,7 @@  static void kvm_unpoison_all(void *param)
     }
 }
 
-void kvm_hwpoison_page_add(ram_addr_t ram_addr)
+void kvm_hwpoison_page_add(ram_addr_t ram_addr, void *ha, hwaddr gpa)
 {
     HWPoisonPage *page;
     size_t sz = qemu_ram_pagesize_from_addr(ram_addr);
@@ -1301,6 +1301,13 @@  void kvm_hwpoison_page_add(ram_addr_t ram_addr)
     page->ram_addr = ram_addr;
     page->page_size = sz;
     QLIST_INSERT_HEAD(&hwpoison_page_list, page, list);
+
+    if (sz > TARGET_PAGE_SIZE) {
+        gpa = ROUND_DOWN(gpa, sz);
+        ha = (void *)ROUND_DOWN((uint64_t)ha, sz);
+        warn_report("Memory error: Loosing a large page (size: %zu) "
+            "at QEMU addr %p and GUEST addr 0x%" HWADDR_PRIx, sz, ha, gpa);
+    }
 }
 
 bool kvm_hwpoisoned_mem(void)
diff --git a/include/sysemu/kvm_int.h b/include/sysemu/kvm_int.h
index a1e72763da..ee34f1d225 100644
--- a/include/sysemu/kvm_int.h
+++ b/include/sysemu/kvm_int.h
@@ -178,10 +178,12 @@  void kvm_set_max_memslot_size(hwaddr max_slot_size);
  *
  * Parameters:
  *  @ram_addr: the address in the RAM for the poisoned page
+ *  @hva: host virtual address aka QEMU addr
+ *  @gpa: guest physical address aka GUEST addr
  *
  * Add a poisoned page to the list
  *
  * Return: None.
  */
-void kvm_hwpoison_page_add(ram_addr_t ram_addr);
+void kvm_hwpoison_page_add(ram_addr_t ram_addr, void *hva, hwaddr gpa);
 #endif
diff --git a/target/arm/kvm.c b/target/arm/kvm.c
index f1f1b5b375..aae66dba41 100644
--- a/target/arm/kvm.c
+++ b/target/arm/kvm.c
@@ -2359,7 +2359,7 @@  void kvm_arch_on_sigbus_vcpu(CPUState *c, int code, void *addr)
         ram_addr = qemu_ram_addr_from_host(addr);
         if (ram_addr != RAM_ADDR_INVALID &&
             kvm_physical_memory_addr_from_host(c->kvm_state, addr, &paddr)) {
-            kvm_hwpoison_page_add(ram_addr);
+            kvm_hwpoison_page_add(ram_addr, addr, paddr);
             /*
              * If this is a BUS_MCEERR_AR, we know we have been called
              * synchronously from the vCPU thread, so we can easily
diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
index fd9f198892..fd7cd7008e 100644
--- a/target/i386/kvm/kvm.c
+++ b/target/i386/kvm/kvm.c
@@ -753,7 +753,7 @@  void kvm_arch_on_sigbus_vcpu(CPUState *c, int code, void *addr)
         ram_addr = qemu_ram_addr_from_host(addr);
         if (ram_addr != RAM_ADDR_INVALID &&
             kvm_physical_memory_addr_from_host(c->kvm_state, addr, &paddr)) {
-            kvm_hwpoison_page_add(ram_addr);
+            kvm_hwpoison_page_add(ram_addr, addr, paddr);
             kvm_mce_inject(cpu, paddr, code);
 
             /*