From: William Roche <william.roche@oracle.com>
The list of hwpoison pages used to remap the memory on reset
is based on the backend real page size. When dealing with
hugepages, we create a single entry for the entire page.
Co-developed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: William Roche <william.roche@oracle.com>
---
accel/kvm/kvm-all.c | 6 +++++-
include/exec/cpu-common.h | 3 ++-
system/physmem.c | 32 ++++++++++++++++++++++++++------
3 files changed, 33 insertions(+), 8 deletions(-)
diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index 801cff16a5..24c0c4ce3f 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -1278,7 +1278,7 @@ static void kvm_unpoison_all(void *param)
QLIST_FOREACH_SAFE(page, &hwpoison_page_list, list, next_page) {
QLIST_REMOVE(page, list);
- qemu_ram_remap(page->ram_addr, TARGET_PAGE_SIZE);
+ qemu_ram_remap(page->ram_addr);
g_free(page);
}
}
@@ -1286,6 +1286,10 @@ 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/include/exec/cpu-common.h b/include/exec/cpu-common.h
index 638dc806a5..59fbb324fa 100644
--- a/include/exec/cpu-common.h
+++ b/include/exec/cpu-common.h
@@ -67,7 +67,7 @@ typedef uintptr_t ram_addr_t;
/* memory API */
-void qemu_ram_remap(ram_addr_t addr, ram_addr_t length);
+void qemu_ram_remap(ram_addr_t addr);
/* This should not be used by devices. */
ram_addr_t qemu_ram_addr_from_host(void *ptr);
ram_addr_t qemu_ram_addr_from_host_nofail(void *ptr);
@@ -108,6 +108,7 @@ bool qemu_ram_is_named_file(RAMBlock *rb);
int qemu_ram_get_fd(RAMBlock *rb);
size_t qemu_ram_pagesize(RAMBlock *block);
+size_t qemu_ram_pagesize_from_addr(ram_addr_t addr);
size_t qemu_ram_pagesize_largest(void);
/**
diff --git a/system/physmem.c b/system/physmem.c
index dc1db3a384..2c90cc2d78 100644
--- a/system/physmem.c
+++ b/system/physmem.c
@@ -1665,6 +1665,19 @@ size_t qemu_ram_pagesize(RAMBlock *rb)
return rb->page_size;
}
+/* Return backend real page size used for the given ram_addr */
+size_t qemu_ram_pagesize_from_addr(ram_addr_t addr)
+{
+ RAMBlock *rb;
+
+ RCU_READ_LOCK_GUARD();
+ rb = qemu_get_ram_block(addr);
+ if (!rb) {
+ return TARGET_PAGE_SIZE;
+ }
+ return qemu_ram_pagesize(rb);
+}
+
/* Returns the largest size of page in use */
size_t qemu_ram_pagesize_largest(void)
{
@@ -2167,17 +2180,22 @@ void qemu_ram_free(RAMBlock *block)
}
#ifndef _WIN32
-void qemu_ram_remap(ram_addr_t addr, ram_addr_t length)
+void qemu_ram_remap(ram_addr_t addr)
{
RAMBlock *block;
ram_addr_t offset;
int flags;
void *area, *vaddr;
int prot;
+ size_t page_size;
RAMBLOCK_FOREACH(block) {
offset = addr - block->offset;
if (offset < block->max_length) {
+ /* Respect the pagesize of our RAMBlock */
+ page_size = qemu_ram_pagesize(block);
+ offset = QEMU_ALIGN_DOWN(offset, page_size);
+
vaddr = ramblock_ptr(block, offset);
if (block->flags & RAM_PREALLOC) {
;
@@ -2191,21 +2209,23 @@ void qemu_ram_remap(ram_addr_t addr, ram_addr_t length)
prot = PROT_READ;
prot |= block->flags & RAM_READONLY ? 0 : PROT_WRITE;
if (block->fd >= 0) {
- area = mmap(vaddr, length, prot, flags, block->fd,
+ area = mmap(vaddr, page_size, prot, flags, block->fd,
offset + block->fd_offset);
} else {
flags |= MAP_ANONYMOUS;
- area = mmap(vaddr, length, prot, flags, -1, 0);
+ area = mmap(vaddr, page_size, prot, flags, -1, 0);
}
if (area != vaddr) {
error_report("Could not remap addr: "
RAM_ADDR_FMT "@" RAM_ADDR_FMT "",
- length, addr);
+ page_size, addr);
exit(1);
}
- memory_try_enable_merging(vaddr, length);
- qemu_ram_setup_dump(vaddr, length);
+ memory_try_enable_merging(vaddr, page_size);
+ qemu_ram_setup_dump(vaddr, page_size);
}
+
+ break;
}
}
}
--
2.43.5On 14.12.24 14:45, “William Roche wrote:
> From: William Roche <william.roche@oracle.com>
Subject should likely start with "system/physmem:".
Maybe
"system/physmem: handle hugetlb correctly in qemu_ram_remap()"
>
> The list of hwpoison pages used to remap the memory on reset
> is based on the backend real page size. When dealing with
> hugepages, we create a single entry for the entire page.
Maybe add something like:
"To correctly handle hugetlb, we must mmap(MAP_FIXED) a complete hugetlb
page; hugetlb pages cannot be partially mapped."
>
> Co-developed-by: David Hildenbrand <david@redhat.com>
> Signed-off-by: William Roche <william.roche@oracle.com>
> ---
> accel/kvm/kvm-all.c | 6 +++++-
> include/exec/cpu-common.h | 3 ++-
> system/physmem.c | 32 ++++++++++++++++++++++++++------
> 3 files changed, 33 insertions(+), 8 deletions(-)
>
> diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
> index 801cff16a5..24c0c4ce3f 100644
> --- a/accel/kvm/kvm-all.c
> +++ b/accel/kvm/kvm-all.c
> @@ -1278,7 +1278,7 @@ static void kvm_unpoison_all(void *param)
>
> QLIST_FOREACH_SAFE(page, &hwpoison_page_list, list, next_page) {
> QLIST_REMOVE(page, list);
> - qemu_ram_remap(page->ram_addr, TARGET_PAGE_SIZE);
> + qemu_ram_remap(page->ram_addr);
> g_free(page);
> }
> }
> @@ -1286,6 +1286,10 @@ 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);
Is that part still required? I thought it would be sufficient (at least
in the context of this patch) to handle it all in qemu_ram_remap().
qemu_ram_remap() will calculate the range to process based on the
RAMBlock page size. IOW, the QEMU_ALIGN_DOWN() we do now in
qemu_ram_remap().
Or am I missing something?
(sorry if we discussed that already; if there is a good reason it might
make sense to state it in the patch description)
--
Cheers,
David / dhildenb
On 1/8/25 22:34, David Hildenbrand wrote:
> On 14.12.24 14:45, “William Roche wrote:
>> From: William Roche <william.roche@oracle.com>
>
> Subject should likely start with "system/physmem:".
>
> Maybe
>
> "system/physmem: handle hugetlb correctly in qemu_ram_remap()"
I updated the commit title
>
>>
>> The list of hwpoison pages used to remap the memory on reset
>> is based on the backend real page size. When dealing with
>> hugepages, we create a single entry for the entire page.
>
> Maybe add something like:
>
> "To correctly handle hugetlb, we must mmap(MAP_FIXED) a complete hugetlb
> page; hugetlb pages cannot be partially mapped."
>
Updated into the commit message
>>
>> Co-developed-by: David Hildenbrand <david@redhat.com>
>> Signed-off-by: William Roche <william.roche@oracle.com>
>> ---
>> accel/kvm/kvm-all.c | 6 +++++-
>> include/exec/cpu-common.h | 3 ++-
>> system/physmem.c | 32 ++++++++++++++++++++++++++------
>> 3 files changed, 33 insertions(+), 8 deletions(-)
>>
>> diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
>> index 801cff16a5..24c0c4ce3f 100644
>> --- a/accel/kvm/kvm-all.c
>> +++ b/accel/kvm/kvm-all.c
>> @@ -1278,7 +1278,7 @@ static void kvm_unpoison_all(void *param)
>> QLIST_FOREACH_SAFE(page, &hwpoison_page_list, list, next_page) {
>> QLIST_REMOVE(page, list);
>> - qemu_ram_remap(page->ram_addr, TARGET_PAGE_SIZE);
>> + qemu_ram_remap(page->ram_addr);
>> g_free(page);
>> }
>> }
>> @@ -1286,6 +1286,10 @@ 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);
>
> Is that part still required? I thought it would be sufficient (at least
> in the context of this patch) to handle it all in qemu_ram_remap().
>
> qemu_ram_remap() will calculate the range to process based on the
> RAMBlock page size. IOW, the QEMU_ALIGN_DOWN() we do now in
> qemu_ram_remap().
>
> Or am I missing something?
>
> (sorry if we discussed that already; if there is a good reason it might
> make sense to state it in the patch description)
You are right, but at this patch level we still need to round up the
address and doing it here is small enough.
Of course, the code changes on patch 3/7 where we change both x86 and
ARM versions of the code to align the memory pointer correctly in both
cases.
On 10.01.25 21:56, William Roche wrote:
> On 1/8/25 22:34, David Hildenbrand wrote:
>> On 14.12.24 14:45, “William Roche wrote:
>>> From: William Roche <william.roche@oracle.com>
>>
>> Subject should likely start with "system/physmem:".
>>
>> Maybe
>>
>> "system/physmem: handle hugetlb correctly in qemu_ram_remap()"
>
> I updated the commit title
>
>>
>>>
>>> The list of hwpoison pages used to remap the memory on reset
>>> is based on the backend real page size. When dealing with
>>> hugepages, we create a single entry for the entire page.
>>
>> Maybe add something like:
>>
>> "To correctly handle hugetlb, we must mmap(MAP_FIXED) a complete hugetlb
>> page; hugetlb pages cannot be partially mapped."
>>
>
> Updated into the commit message
>
>>>
>>> Co-developed-by: David Hildenbrand <david@redhat.com>
>>> Signed-off-by: William Roche <william.roche@oracle.com>
>>> ---
>>> accel/kvm/kvm-all.c | 6 +++++-
>>> include/exec/cpu-common.h | 3 ++-
>>> system/physmem.c | 32 ++++++++++++++++++++++++++------
>>> 3 files changed, 33 insertions(+), 8 deletions(-)
>>>
>>> diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
>>> index 801cff16a5..24c0c4ce3f 100644
>>> --- a/accel/kvm/kvm-all.c
>>> +++ b/accel/kvm/kvm-all.c
>>> @@ -1278,7 +1278,7 @@ static void kvm_unpoison_all(void *param)
>>> QLIST_FOREACH_SAFE(page, &hwpoison_page_list, list, next_page) {
>>> QLIST_REMOVE(page, list);
>>> - qemu_ram_remap(page->ram_addr, TARGET_PAGE_SIZE);
>>> + qemu_ram_remap(page->ram_addr);
>>> g_free(page);
>>> }
>>> }
>>> @@ -1286,6 +1286,10 @@ 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);
>>
>> Is that part still required? I thought it would be sufficient (at least
>> in the context of this patch) to handle it all in qemu_ram_remap().
>>
>> qemu_ram_remap() will calculate the range to process based on the
>> RAMBlock page size. IOW, the QEMU_ALIGN_DOWN() we do now in
>> qemu_ram_remap().
>>
>> Or am I missing something?
>>
>> (sorry if we discussed that already; if there is a good reason it might
>> make sense to state it in the patch description)
>
> You are right, but at this patch level we still need to round up the
s/round up/align_down/
> address and doing it here is small enough.
Let me explain.
qemu_ram_remap() in this patch here doesn't need an aligned addr. It
will compute the offset into the block and align that down.
The only case where we need the addr besides from that is the
error_report(), where I am not 100% sure if that is actually what we
want to print. We want to print something like ram_block_discard_range().
Note that ram_addr_t is a weird, separate address space. The alignment
does not have any guarantees / semantics there.
See ram_block_add() where we set
new_block->offset = find_ram_offset(new_block->max_length);
independent of any other RAMBlock properties.
The only alignment we do is
candidate = ROUND_UP(candidate, BITS_PER_LONG << TARGET_PAGE_BITS);
There is no guarantee that new_block->offset will be aligned to 1 GiB with
a 1 GiB hugetlb mapping.
Note that there is another conceptual issue in this function: offset
should be of type uint64_t, it's not really ram_addr_t, but an
offset into the RAMBlock.
> Of course, the code changes on patch 3/7 where we change both x86 and
> ARM versions of the code to align the memory pointer correctly in both
> cases.
Thinking about it more, we should never try aligning ram_addr_t, only
the offset into the memory block or the virtual address.
So please remove this from this ram_addr_t alignment from this patch, and look into
aligning the virtual address / offset for the other user. Again, aligning
ram_addr_t is not guaranteed to work correctly.
So the patch itself should probably be (- patch description):
diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index 801cff16a5..8a47aa7258 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -1278,7 +1278,7 @@ static void kvm_unpoison_all(void *param)
QLIST_FOREACH_SAFE(page, &hwpoison_page_list, list, next_page) {
QLIST_REMOVE(page, list);
- qemu_ram_remap(page->ram_addr, TARGET_PAGE_SIZE);
+ qemu_ram_remap(page->ram_addr);
g_free(page);
}
}
diff --git a/include/exec/cpu-common.h b/include/exec/cpu-common.h
index 638dc806a5..50a829d31f 100644
--- a/include/exec/cpu-common.h
+++ b/include/exec/cpu-common.h
@@ -67,7 +67,7 @@ typedef uintptr_t ram_addr_t;
/* memory API */
-void qemu_ram_remap(ram_addr_t addr, ram_addr_t length);
+void qemu_ram_remap(ram_addr_t addr);
/* This should not be used by devices. */
ram_addr_t qemu_ram_addr_from_host(void *ptr);
ram_addr_t qemu_ram_addr_from_host_nofail(void *ptr);
diff --git a/system/physmem.c b/system/physmem.c
index 03d3618039..355588f5d5 100644
--- a/system/physmem.c
+++ b/system/physmem.c
@@ -2167,17 +2167,35 @@ void qemu_ram_free(RAMBlock *block)
}
#ifndef _WIN32
-void qemu_ram_remap(ram_addr_t addr, ram_addr_t length)
+/*
+ * qemu_ram_remap - remap a single RAM page
+ *
+ * @addr: address in ram_addr_t address space.
+ *
+ * This function will try remapping a single page of guest RAM identified by
+ * @addr, essentially discarding memory to recover from previously poisoned
+ * memory (MCE). The page size depends on the RAMBlock (i.e., hugetlb). @addr
+ * does not have to point at the start of the page.
+ *
+ * This function is only to be used during system resets; it will kill the
+ * VM if remapping failed.
+ */
+void qemu_ram_remap(ram_addr_t addr)
{
RAMBlock *block;
- ram_addr_t offset;
+ uint64_t offset;
int flags;
void *area, *vaddr;
int prot;
+ size_t page_size;
RAMBLOCK_FOREACH(block) {
offset = addr - block->offset;
if (offset < block->max_length) {
+ /* Respect the pagesize of our RAMBlock */
+ page_size = qemu_ram_pagesize(block);
+ offset = QEMU_ALIGN_DOWN(offset, page_size);
+
vaddr = ramblock_ptr(block, offset);
if (block->flags & RAM_PREALLOC) {
;
@@ -2191,21 +2209,22 @@ void qemu_ram_remap(ram_addr_t addr, ram_addr_t length)
prot = PROT_READ;
prot |= block->flags & RAM_READONLY ? 0 : PROT_WRITE;
if (block->fd >= 0) {
- area = mmap(vaddr, length, prot, flags, block->fd,
+ area = mmap(vaddr, page_size, prot, flags, block->fd,
offset + block->fd_offset);
} else {
flags |= MAP_ANONYMOUS;
- area = mmap(vaddr, length, prot, flags, -1, 0);
+ area = mmap(vaddr, page_size, prot, flags, -1, 0);
}
if (area != vaddr) {
- error_report("Could not remap addr: "
- RAM_ADDR_FMT "@" RAM_ADDR_FMT "",
- length, addr);
+ error_report("Could not remap RAM %s:%" PRIx64 " +%zx",
+ block->idstr, offset, page_size);
exit(1);
}
- memory_try_enable_merging(vaddr, length);
- qemu_ram_setup_dump(vaddr, length);
+ memory_try_enable_merging(vaddr, page_size);
+ qemu_ram_setup_dump(vaddr, page_size);
}
+
+ break;
}
}
}
--
2.47.1
--
Cheers,
David / dhildenb
© 2016 - 2025 Red Hat, Inc.