public inbox for kvm@vger.kernel.org
 help / color / mirror / Atom feed
From: "“William Roche" <william.roche@oracle.com>
To: david@redhat.com, kvm@vger.kernel.org, qemu-devel@nongnu.org,
	qemu-arm@nongnu.org
Cc: william.roche@oracle.com, peterx@redhat.com, pbonzini@redhat.com,
	richard.henderson@linaro.org, philmd@linaro.org,
	peter.maydell@linaro.org, mtosatti@redhat.com,
	imammedo@redhat.com, eduardo@habkost.net,
	marcel.apfelbaum@gmail.com, wangyanan55@huawei.com,
	zhao1.liu@intel.com, joao.m.martins@oracle.com
Subject: [PATCH v4 3/7] accel/kvm: Report the loss of a large memory page
Date: Sat, 14 Dec 2024 13:45:51 +0000	[thread overview]
Message-ID: <20241214134555.440097-4-william.roche@oracle.com> (raw)
In-Reply-To: <20241214134555.440097-1-william.roche@oracle.com>

From: William Roche <william.roche@oracle.com>

In case of a large page impacted by a memory error, enhance
the existing Qemu error message which indicates that the error
is injected in the VM, adding "on lost large page SIZE@ADDR".

Include also a similar message to the ARM platform.

In the case of a large page impacted, we now report:
...Memory Error at QEMU addr X and GUEST addr Y on lost large page SIZE@ADDR of type...

Signed-off-by: William Roche <william.roche@oracle.com>
---
 accel/kvm/kvm-all.c   |  4 ----
 target/arm/kvm.c      | 13 +++++++++++++
 target/i386/kvm/kvm.c | 18 ++++++++++++++----
 3 files changed, 27 insertions(+), 8 deletions(-)

diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index 24c0c4ce3f..8a47aa7258 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -1286,10 +1286,6 @@ static void kvm_unpoison_all(void *param)
 void kvm_hwpoison_page_add(ram_addr_t ram_addr)
 {
     HWPoisonPage *page;
-    size_t page_size = qemu_ram_pagesize_from_addr(ram_addr);
-
-    if (page_size > TARGET_PAGE_SIZE)
-        ram_addr = QEMU_ALIGN_DOWN(ram_addr, page_size);
 
     QLIST_FOREACH(page, &hwpoison_page_list, list) {
         if (page->ram_addr == ram_addr) {
diff --git a/target/arm/kvm.c b/target/arm/kvm.c
index 7b6812c0de..db234f79cc 100644
--- a/target/arm/kvm.c
+++ b/target/arm/kvm.c
@@ -2366,6 +2366,8 @@ void kvm_arch_on_sigbus_vcpu(CPUState *c, int code, void *addr)
 {
     ram_addr_t ram_addr;
     hwaddr paddr;
+    size_t page_size;
+    char lp_msg[54];
 
     assert(code == BUS_MCEERR_AR || code == BUS_MCEERR_AO);
 
@@ -2373,6 +2375,14 @@ 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)) {
+            page_size = qemu_ram_pagesize_from_addr(ram_addr);
+            if (page_size > TARGET_PAGE_SIZE) {
+                ram_addr = ROUND_DOWN(ram_addr, page_size);
+                snprintf(lp_msg, sizeof(lp_msg), " on lost large page "
+                    RAM_ADDR_FMT "@" RAM_ADDR_FMT "", page_size, ram_addr);
+            } else {
+                lp_msg[0] = '\0';
+            }
             kvm_hwpoison_page_add(ram_addr);
             /*
              * If this is a BUS_MCEERR_AR, we know we have been called
@@ -2389,6 +2399,9 @@ void kvm_arch_on_sigbus_vcpu(CPUState *c, int code, void *addr)
                 kvm_cpu_synchronize_state(c);
                 if (!acpi_ghes_record_errors(ACPI_HEST_SRC_ID_SEA, paddr)) {
                     kvm_inject_arm_sea(c);
+                    error_report("Guest Memory Error at QEMU addr %p and "
+                        "GUEST addr 0x%" HWADDR_PRIx "%s of type %s injected",
+                        addr, paddr, lp_msg, "BUS_MCEERR_AR");
                 } else {
                     error_report("failed to record the error");
                     abort();
diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
index 8e17942c3b..336646ed61 100644
--- a/target/i386/kvm/kvm.c
+++ b/target/i386/kvm/kvm.c
@@ -741,6 +741,8 @@ void kvm_arch_on_sigbus_vcpu(CPUState *c, int code, void *addr)
     CPUX86State *env = &cpu->env;
     ram_addr_t ram_addr;
     hwaddr paddr;
+    size_t page_size;
+    char lp_msg[54];
 
     /* If we get an action required MCE, it has been injected by KVM
      * while the VM was running.  An action optional MCE instead should
@@ -753,6 +755,14 @@ 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)) {
+            page_size = qemu_ram_pagesize_from_addr(ram_addr);
+            if (page_size > TARGET_PAGE_SIZE) {
+                ram_addr = ROUND_DOWN(ram_addr, page_size);
+                snprintf(lp_msg, sizeof(lp_msg), " on lost large page "
+                        RAM_ADDR_FMT "@" RAM_ADDR_FMT "", page_size, ram_addr);
+            } else {
+                lp_msg[0] = '\0';
+            }
             kvm_hwpoison_page_add(ram_addr);
             kvm_mce_inject(cpu, paddr, code);
 
@@ -763,12 +773,12 @@ void kvm_arch_on_sigbus_vcpu(CPUState *c, int code, void *addr)
              */
             if (code == BUS_MCEERR_AR) {
                 error_report("Guest MCE Memory Error at QEMU addr %p and "
-                    "GUEST addr 0x%" HWADDR_PRIx " of type %s injected",
-                    addr, paddr, "BUS_MCEERR_AR");
+                    "GUEST addr 0x%" HWADDR_PRIx "%s of type %s injected",
+                    addr, paddr, lp_msg, "BUS_MCEERR_AR");
             } else {
                  warn_report("Guest MCE Memory Error at QEMU addr %p and "
-                     "GUEST addr 0x%" HWADDR_PRIx " of type %s injected",
-                     addr, paddr, "BUS_MCEERR_AO");
+                     "GUEST addr 0x%" HWADDR_PRIx "%s of type %s injected",
+                     addr, paddr, lp_msg, "BUS_MCEERR_AO");
             }
 
             return;
-- 
2.43.5


  parent reply	other threads:[~2024-12-14 13:46 UTC|newest]

Thread overview: 111+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <20240910090747.2741475-1-william.roche@oracle.com>
2024-09-10 10:02 ` [RFC RESEND 0/6] hugetlbfs largepage RAS project “William Roche
2024-09-10 10:02   ` [RFC RESEND 1/6] accel/kvm: SIGBUS handler should also deal with si_addr_lsb “William Roche
2024-09-10 10:02   ` [RFC RESEND 2/6] accel/kvm: Keep track of the HWPoisonPage sizes “William Roche
2024-09-10 10:02   ` [RFC RESEND 3/6] system/physmem: Remap memory pages on reset based on the page size “William Roche
2024-09-10 10:02   ` [RFC RESEND 4/6] system: Introducing hugetlbfs largepage RAS feature “William Roche
2024-09-10 10:02   ` [RFC RESEND 5/6] system/hugetlb_ras: Handle madvise SIGBUS signal on listener “William Roche
2024-09-10 10:02   ` [RFC RESEND 6/6] system/hugetlb_ras: Replay lost BUS_MCEERR_AO signals on VM resume “William Roche
2024-09-10 11:36   ` [RFC RESEND 0/6] hugetlbfs largepage RAS project David Hildenbrand
2024-09-10 16:24     ` William Roche
2024-09-11 22:07       ` David Hildenbrand
2024-09-12 17:07         ` William Roche
2024-09-19 16:52           ` William Roche
2024-10-09 15:45             ` Peter Xu
2024-10-10 20:35               ` William Roche
2024-10-22 21:34               ` [PATCH v1 0/4] hugetlbfs memory HW error fixes “William Roche
2024-10-22 21:35                 ` [PATCH v1 1/4] accel/kvm: SIGBUS handler should also deal with si_addr_lsb “William Roche
2024-10-22 21:35                 ` [PATCH v1 2/4] accel/kvm: Keep track of the HWPoisonPage page_size “William Roche
2024-10-23  7:28                   ` David Hildenbrand
2024-10-25 23:30                     ` William Roche
     [not found]                     ` <9b17600d-4473-4bb6-841f-00f93d86f720@oracle.com>
2024-10-28 16:42                       ` David Hildenbrand
2024-10-30  1:56                         ` William Roche
2024-11-04 14:10                           ` David Hildenbrand
2024-10-22 21:35                 ` [PATCH v1 3/4] system/physmem: Largepage punch hole before reset of memory pages “William Roche
2024-10-23  7:30                   ` David Hildenbrand
2024-10-25 23:27                     ` William Roche
2024-10-28 17:01                       ` David Hildenbrand
2024-10-30  1:56                         ` William Roche
2024-11-04 13:30                           ` David Hildenbrand
2024-11-07 10:21                             ` [PATCH v2 0/7] hugetlbfs memory HW error fixes “William Roche
2024-11-07 10:21                               ` [PATCH v2 1/7] accel/kvm: Keep track of the HWPoisonPage page_size “William Roche
2024-11-12 10:30                                 ` David Hildenbrand
2024-11-12 18:17                                   ` William Roche
2024-11-12 21:35                                     ` David Hildenbrand
2024-11-07 10:21                               ` [PATCH v2 2/7] system/physmem: poisoned memory discard on reboot “William Roche
2024-11-12 11:07                                 ` David Hildenbrand
2024-11-12 18:17                                   ` William Roche
2024-11-12 22:06                                     ` David Hildenbrand
2024-11-07 10:21                               ` [PATCH v2 3/7] accel/kvm: Report the loss of a large memory page “William Roche
2024-11-12 11:13                                 ` David Hildenbrand
2024-11-12 18:17                                   ` William Roche
2024-11-12 22:22                                     ` David Hildenbrand
2024-11-15 21:03                                       ` William Roche
2024-11-18  9:45                                         ` David Hildenbrand
2024-11-07 10:21                               ` [PATCH v2 4/7] numa: Introduce and use ram_block_notify_remap() “William Roche
2024-11-07 10:21                               ` [PATCH v2 5/7] hostmem: Factor out applying settings “William Roche
2024-11-07 10:21                               ` [PATCH v2 6/7] hostmem: Handle remapping of RAM “William Roche
2024-11-12 13:45                                 ` David Hildenbrand
2024-11-12 18:17                                   ` William Roche
2024-11-12 22:24                                     ` David Hildenbrand
2024-11-07 10:21                               ` [PATCH v2 7/7] system/physmem: Memory settings applied on remap notification “William Roche
2024-10-22 21:35                 ` [PATCH v1 4/4] accel/kvm: Report the loss of a large memory page “William Roche
2024-10-28 16:32             ` [RFC RESEND 0/6] hugetlbfs largepage RAS project David Hildenbrand
2024-11-25 14:27         ` [PATCH v3 0/7] hugetlbfs memory HW error fixes “William Roche
2024-11-25 14:27           ` [PATCH v3 1/7] hwpoison_page_list and qemu_ram_remap are based of pages “William Roche
2024-11-25 14:27           ` [PATCH v3 2/7] system/physmem: poisoned memory discard on reboot “William Roche
2024-11-25 14:27           ` [PATCH v3 3/7] accel/kvm: Report the loss of a large memory page “William Roche
2024-11-25 14:27           ` [PATCH v3 4/7] numa: Introduce and use ram_block_notify_remap() “William Roche
2024-11-25 14:27           ` [PATCH v3 5/7] hostmem: Factor out applying settings “William Roche
2024-11-25 14:27           ` [PATCH v3 6/7] hostmem: Handle remapping of RAM “William Roche
2024-11-25 14:27           ` [PATCH v3 7/7] system/physmem: Memory settings applied on remap notification “William Roche
2024-12-02 15:41           ` [PATCH v3 0/7] hugetlbfs memory HW error fixes William Roche
2024-12-02 16:00             ` David Hildenbrand
2024-12-03  0:15               ` William Roche
2024-12-03 14:08                 ` David Hildenbrand
2024-12-03 14:39                   ` William Roche
2024-12-03 15:00                     ` David Hildenbrand
2024-12-06 18:26                       ` William Roche
2024-12-09 21:25                         ` David Hildenbrand
2024-12-14 13:45         ` [PATCH v4 0/7] Poisoned memory recovery on reboot “William Roche
2024-12-14 13:45           ` [PATCH v4 1/7] hwpoison_page_list and qemu_ram_remap are based on pages “William Roche
2025-01-08 21:34             ` David Hildenbrand
2025-01-10 20:56               ` William Roche
2025-01-14 13:56                 ` David Hildenbrand
2024-12-14 13:45           ` [PATCH v4 2/7] system/physmem: poisoned memory discard on reboot “William Roche
2025-01-08 21:44             ` David Hildenbrand
2025-01-10 20:56               ` William Roche
2025-01-14 14:00                 ` David Hildenbrand
2025-01-27 21:15                   ` William Roche
2024-12-14 13:45           ` “William Roche [this message]
2024-12-14 13:45           ` [PATCH v4 4/7] numa: Introduce and use ram_block_notify_remap() “William Roche
2024-12-14 13:45           ` [PATCH v4 5/7] hostmem: Factor out applying settings “William Roche
2025-01-08 21:58             ` David Hildenbrand
2025-01-10 20:56               ` William Roche
2024-12-14 13:45           ` [PATCH v4 6/7] hostmem: Handle remapping of RAM “William Roche
2025-01-08 21:51             ` [PATCH v4 6/7] c David Hildenbrand
2025-01-10 20:57               ` [PATCH v4 6/7] hostmem: Handle remapping of RAM William Roche
2024-12-14 13:45           ` [PATCH v4 7/7] system/physmem: Memory settings applied on remap notification “William Roche
2025-01-08 21:53             ` David Hildenbrand
2025-01-10 20:57               ` William Roche
2025-01-14 14:01                 ` David Hildenbrand
2025-01-08 21:22           ` [PATCH v4 0/7] Poisoned memory recovery on reboot David Hildenbrand
2025-01-10 20:55             ` William Roche
2025-01-10 21:13         ` [PATCH v5 0/6] " “William Roche
2025-01-10 21:14           ` [PATCH v5 1/6] system/physmem: handle hugetlb correctly in qemu_ram_remap() “William Roche
2025-01-14 14:02             ` David Hildenbrand
2025-01-27 21:16               ` William Roche
2025-01-28 18:41                 ` David Hildenbrand
2025-01-10 21:14           ` [PATCH v5 2/6] system/physmem: poisoned memory discard on reboot “William Roche
2025-01-14 14:07             ` David Hildenbrand
2025-01-27 21:16               ` William Roche
2025-01-10 21:14           ` [PATCH v5 3/6] accel/kvm: Report the loss of a large memory page “William Roche
2025-01-14 14:09             ` David Hildenbrand
2025-01-27 21:16               ` William Roche
2025-01-28 18:45                 ` David Hildenbrand
2025-01-10 21:14           ` [PATCH v5 4/6] numa: Introduce and use ram_block_notify_remap() “William Roche
2025-01-10 21:14           ` [PATCH v5 5/6] hostmem: Factor out applying settings “William Roche
2025-01-10 21:14           ` [PATCH v5 6/6] hostmem: Handle remapping of RAM “William Roche
2025-01-14 14:11             ` David Hildenbrand
2025-01-27 21:16               ` William Roche
2025-01-14 14:12           ` [PATCH v5 0/6] Poisoned memory recovery on reboot David Hildenbrand
2025-01-27 21:16             ` William Roche

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20241214134555.440097-4-william.roche@oracle.com \
    --to=william.roche@oracle.com \
    --cc=david@redhat.com \
    --cc=eduardo@habkost.net \
    --cc=imammedo@redhat.com \
    --cc=joao.m.martins@oracle.com \
    --cc=kvm@vger.kernel.org \
    --cc=marcel.apfelbaum@gmail.com \
    --cc=mtosatti@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=peter.maydell@linaro.org \
    --cc=peterx@redhat.com \
    --cc=philmd@linaro.org \
    --cc=qemu-arm@nongnu.org \
    --cc=qemu-devel@nongnu.org \
    --cc=richard.henderson@linaro.org \
    --cc=wangyanan55@huawei.com \
    --cc=zhao1.liu@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox