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>
Acked-by: David Hildenbrand <david@redhat.com>
---
system/physmem.c | 58 ++++++++++++++++++++++++++++++------------------
1 file changed, 36 insertions(+), 22 deletions(-)
diff --git a/system/physmem.c b/system/physmem.c
index 3dd2adde73..e8ff930bc9 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 +2216,24 @@ 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) {
+ error_report("Could not remap RAM %s:%" PRIx64 "+%"
+ PRIx64 " +%zx", block->idstr, offset,
+ block->fd_offset, page_size);
+ exit(1);
+ }
+ if (qemu_ram_remap_mmap(block, offset, page_size) != 0) {
+ error_report("Could not remap RAM %s:%" PRIx64 " +%zx",
+ block->idstr, offset, page_size);
+ exit(1);
+ }
}
memory_try_enable_merging(vaddr, page_size);
qemu_ram_setup_dump(vaddr, page_size);
--
2.43.5On Sat, Feb 01, 2025 at 09:57:22AM +0000, “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>
> Acked-by: David Hildenbrand <david@redhat.com>
> ---
> system/physmem.c | 58 ++++++++++++++++++++++++++++++------------------
> 1 file changed, 36 insertions(+), 22 deletions(-)
>
> diff --git a/system/physmem.c b/system/physmem.c
> index 3dd2adde73..e8ff930bc9 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 +2216,24 @@ void qemu_ram_remap(ram_addr_t addr)
> ;
> } else if (xen_enabled()) {
> abort();
> - } else {
Do we need to keep this line? Otherwise it looks to me the new code won't
be executed at all in !xen..
> - 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) {
> + error_report("Could not remap RAM %s:%" PRIx64 "+%"
> + PRIx64 " +%zx", block->idstr, offset,
> + block->fd_offset, page_size);
> + exit(1);
> + }
> + if (qemu_ram_remap_mmap(block, offset, page_size) != 0) {
> + error_report("Could not remap RAM %s:%" PRIx64 " +%zx",
> + block->idstr, offset, page_size);
> + exit(1);
> + }
> }
> memory_try_enable_merging(vaddr, page_size);
> qemu_ram_setup_dump(vaddr, page_size);
> --
> 2.43.5
>
--
Peter Xu
On 2/4/25 18:09, Peter Xu wrote:
> On Sat, Feb 01, 2025 at 09:57:22AM +0000, “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>
>> Acked-by: David Hildenbrand <david@redhat.com>
>> ---
>> system/physmem.c | 58 ++++++++++++++++++++++++++++++------------------
>> 1 file changed, 36 insertions(+), 22 deletions(-)
>>
>> diff --git a/system/physmem.c b/system/physmem.c
>> index 3dd2adde73..e8ff930bc9 100644
>> --- a/system/physmem.c
>> +++ b/system/physmem.c
>> ...
>> /*
>> * 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 +2216,24 @@ void qemu_ram_remap(ram_addr_t addr)
>> ;
>> } else if (xen_enabled()) {
>> abort();
>> - } else {
>
> Do we need to keep this line? Otherwise it looks to me the new code won't
> be executed at all in !xen..
Very true, this is a mistake I made in a very recent version - sorry!
I'll fix it with my next version.
Thanks.
© 2016 - 2025 Red Hat, Inc.