diff mbox series

[v6,2/6] system/physmem: poisoned memory discard on reboot

Message ID 20250127213107.3454680-3-william.roche@oracle.com (mailing list archive)
State New
Headers show
Series Poisoned memory recovery on reboot | expand

Commit Message

“William Roche Jan. 27, 2025, 9:31 p.m. UTC
From: William Roche <william.roche@oracle.com>

Repair poisoned memory location(s), calling ram_block_discard_range():
punching a hole in the backend file when necessary and regenerating
a usable memory.
If the kernel doesn't support the madvise calls used by this function
and we are dealing with anonymous memory, fall back to remapping the
location(s).

Signed-off-by: William Roche <william.roche@oracle.com>
---
 system/physmem.c | 54 ++++++++++++++++++++++++++++--------------------
 1 file changed, 32 insertions(+), 22 deletions(-)

Comments

David Hildenbrand Jan. 30, 2025, 10:08 a.m. UTC | #1
On 27.01.25 22:31, “William Roche wrote:
> From: William Roche <william.roche@oracle.com>
> 
> Repair poisoned memory location(s), calling ram_block_discard_range():
> punching a hole in the backend file when necessary and regenerating
> a usable memory.
> If the kernel doesn't support the madvise calls used by this function
> and we are dealing with anonymous memory, fall back to remapping the
> location(s).
> 
> Signed-off-by: William Roche <william.roche@oracle.com>
> ---
>   system/physmem.c | 54 ++++++++++++++++++++++++++++--------------------
>   1 file changed, 32 insertions(+), 22 deletions(-)
> 
> diff --git a/system/physmem.c b/system/physmem.c
> index 3dd2adde73..3dc10ae27b 100644
> --- a/system/physmem.c
> +++ b/system/physmem.c
> @@ -2167,6 +2167,23 @@ void qemu_ram_free(RAMBlock *block)
>   }
>   
>   #ifndef _WIN32
> +/* Simply remap the given VM memory location from start to start+length */
> +static int qemu_ram_remap_mmap(RAMBlock *block, uint64_t start, size_t length)
> +{
> +    int flags, prot;
> +    void *area;
> +    void *host_startaddr = block->host + start;
> +
> +    assert(block->fd < 0);
> +    flags = MAP_FIXED | MAP_ANONYMOUS;
> +    flags |= block->flags & RAM_SHARED ? MAP_SHARED : MAP_PRIVATE;
> +    flags |= block->flags & RAM_NORESERVE ? MAP_NORESERVE : 0;
> +    prot = PROT_READ;
> +    prot |= block->flags & RAM_READONLY ? 0 : PROT_WRITE;
> +    area = mmap(host_startaddr, length, prot, flags, -1, 0);
> +    return area != host_startaddr ? -errno : 0;
> +}
> +
>   /*
>    * qemu_ram_remap - remap a single RAM page
>    *
> @@ -2184,9 +2201,7 @@ void qemu_ram_remap(ram_addr_t addr)
>   {
>       RAMBlock *block;
>       uint64_t offset;
> -    int flags;
> -    void *area, *vaddr;
> -    int prot;
> +    void *vaddr;
>       size_t page_size;
>   
>       RAMBLOCK_FOREACH(block) {
> @@ -2201,25 +2216,20 @@ void qemu_ram_remap(ram_addr_t addr)
>                   ;
>               } else if (xen_enabled()) {
>                   abort();
> -            } else {
> -                flags = MAP_FIXED;
> -                flags |= block->flags & RAM_SHARED ?
> -                         MAP_SHARED : MAP_PRIVATE;
> -                flags |= block->flags & RAM_NORESERVE ? MAP_NORESERVE : 0;
> -                prot = PROT_READ;
> -                prot |= block->flags & RAM_READONLY ? 0 : PROT_WRITE;
> -                if (block->fd >= 0) {
> -                    area = mmap(vaddr, page_size, prot, flags, block->fd,
> -                                offset + block->fd_offset);
> -                } else {
> -                    flags |= MAP_ANONYMOUS;
> -                    area = mmap(vaddr, page_size, prot, flags, -1, 0);
> -                }
> -                if (area != vaddr) {
> -                    error_report("Could not remap RAM %s:%" PRIx64 "+%" PRIx64
> -                                 " +%zx", block->idstr, offset,
> -                                 block->fd_offset, page_size);
> -                    exit(1);
> +                if (ram_block_discard_range(block, offset, page_size) != 0) {
> +                    /*
> +                     * Fall back to using mmap() only for anonymous mapping,
> +                     * as if a backing file is associated we may not be able
> +                     * to recover the memory in all cases.
> +                     * So don't take the risk of using only mmap and fail now.
> +                     */
> +                    if (block->fd >= 0 ||
> +                        qemu_ram_remap_mmap(block, offset, page_size) != 0) {
> +                        error_report("Could not remap RAM %s:%" PRIx64 "+%"
> +                                     PRIx64 " +%zx", block->idstr, offset,
> +                                     block->fd_offset, page_size);
> +                        exit(1);
> +                    }
>                   }
>                   memory_try_enable_merging(vaddr, page_size);
>                   qemu_ram_setup_dump(vaddr, page_size);


Acked-by: David Hildenbrand <david@redhat.com>
diff mbox series

Patch

diff --git a/system/physmem.c b/system/physmem.c
index 3dd2adde73..3dc10ae27b 100644
--- a/system/physmem.c
+++ b/system/physmem.c
@@ -2167,6 +2167,23 @@  void qemu_ram_free(RAMBlock *block)
 }
 
 #ifndef _WIN32
+/* Simply remap the given VM memory location from start to start+length */
+static int qemu_ram_remap_mmap(RAMBlock *block, uint64_t start, size_t length)
+{
+    int flags, prot;
+    void *area;
+    void *host_startaddr = block->host + start;
+
+    assert(block->fd < 0);
+    flags = MAP_FIXED | MAP_ANONYMOUS;
+    flags |= block->flags & RAM_SHARED ? MAP_SHARED : MAP_PRIVATE;
+    flags |= block->flags & RAM_NORESERVE ? MAP_NORESERVE : 0;
+    prot = PROT_READ;
+    prot |= block->flags & RAM_READONLY ? 0 : PROT_WRITE;
+    area = mmap(host_startaddr, length, prot, flags, -1, 0);
+    return area != host_startaddr ? -errno : 0;
+}
+
 /*
  * qemu_ram_remap - remap a single RAM page
  *
@@ -2184,9 +2201,7 @@  void qemu_ram_remap(ram_addr_t addr)
 {
     RAMBlock *block;
     uint64_t offset;
-    int flags;
-    void *area, *vaddr;
-    int prot;
+    void *vaddr;
     size_t page_size;
 
     RAMBLOCK_FOREACH(block) {
@@ -2201,25 +2216,20 @@  void qemu_ram_remap(ram_addr_t addr)
                 ;
             } else if (xen_enabled()) {
                 abort();
-            } else {
-                flags = MAP_FIXED;
-                flags |= block->flags & RAM_SHARED ?
-                         MAP_SHARED : MAP_PRIVATE;
-                flags |= block->flags & RAM_NORESERVE ? MAP_NORESERVE : 0;
-                prot = PROT_READ;
-                prot |= block->flags & RAM_READONLY ? 0 : PROT_WRITE;
-                if (block->fd >= 0) {
-                    area = mmap(vaddr, page_size, prot, flags, block->fd,
-                                offset + block->fd_offset);
-                } else {
-                    flags |= MAP_ANONYMOUS;
-                    area = mmap(vaddr, page_size, prot, flags, -1, 0);
-                }
-                if (area != vaddr) {
-                    error_report("Could not remap RAM %s:%" PRIx64 "+%" PRIx64
-                                 " +%zx", block->idstr, offset,
-                                 block->fd_offset, page_size);
-                    exit(1);
+                if (ram_block_discard_range(block, offset, page_size) != 0) {
+                    /*
+                     * Fall back to using mmap() only for anonymous mapping,
+                     * as if a backing file is associated we may not be able
+                     * to recover the memory in all cases.
+                     * So don't take the risk of using only mmap and fail now.
+                     */
+                    if (block->fd >= 0 ||
+                        qemu_ram_remap_mmap(block, offset, page_size) != 0) {
+                        error_report("Could not remap RAM %s:%" PRIx64 "+%"
+                                     PRIx64 " +%zx", block->idstr, offset,
+                                     block->fd_offset, page_size);
+                        exit(1);
+                    }
                 }
                 memory_try_enable_merging(vaddr, page_size);
                 qemu_ram_setup_dump(vaddr, page_size);