On Mon, Dec 02, 2024 at 05:19:54AM -0800, Steve Sistare wrote:
@@ -2089,13 +2154,23 @@ RAMBlock *qemu_ram_alloc_internal(ram_addr_t size,
ram_addr_t max_size,
new_block->page_size = qemu_real_host_page_size();
new_block->host = host;
new_block->flags = ram_flags;
+
+ if (!host && !xen_enabled()) {
Adding one more xen check is unnecessary. This patch needed it could mean
that the patch can be refactored.. because we have xen checks in both
ram_block_add() and also in the fd allocation path.
At the meantime, see:
qemu_ram_alloc_from_fd():
if (kvm_enabled() && !kvm_has_sync_mmu()) {
error_setg(errp,
"host lacks kvm mmu notifiers, -mem-path unsupported");
return NULL;
}
I don't think any decent kernel could hit this, but that could be another
sign that this patch duplicated some file allocations.
+ if ((new_block->flags & RAM_SHARED) &&
+ !qemu_ram_alloc_shared(new_block, &local_err)) {
+ goto err;
+ }
+ }
+
ram_block_add(new_block, &local_err);
- if (local_err) {
- g_free(new_block);
- error_propagate(errp, local_err);
- return NULL;
+ if (!local_err) {
+ return new_block;
}
- return new_block;
+
+err:
+ g_free(new_block);
+ error_propagate(errp, local_err);
+ return NULL;
}
IIUC we only need to conditionally convert an anon-allocation into an
fd-allocation, and then we don't need to mostly duplicate
qemu_ram_alloc_from_fd(), instead we reuse it.
I do have a few other comments elsewhere, but when I was trying to comment.
E.g., we either shouldn't need to bother caching qemu_memfd_check()
results, or do it in qemu_memfd_check() directly.. and some more.
===8<===
From a90119131a972b0b4f15770fe0b431770456e447 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Mon, 9 Dec 2024 13:38:06 -0500
Subject: [PATCH] physmem: Try to always allocate anon and shared memory with
fd
qemu_ram_alloc_internal() is the memory API QEMU uses to allocate anonymous
memory. It allows RAM_SHARED too on top of anonymous.
It might be always beneficial to allocate memory with fd attached whenever
possible because fd is normally more flexible comparing to the virtual
mapping alone. For example, CPR can use it to pass over fds between
processes to share memory, especially useful when the memory can be pinned.
Since there's no harm when it's possible, do it unconditionally for all
such anonymous & shared memory allocations where the memory is to be
allocated. Provide fallbacks when it can fail, e.g., when none of the
memory attached fd is available.
Two extra ERRP_GUARD()s are needed in the used functions, as we will not
care about error even if it happened, so it's easier to allow passing NULL
into them.
Signed-off-by: Peter Xu <peterx@redhat.com>
---
system/physmem.c | 38 ++++++++++++++++++++++++++++++++++++++
util/memfd.c | 2 ++
util/oslib-posix.c | 2 ++
3 files changed, 42 insertions(+)
diff --git a/system/physmem.c b/system/physmem.c
index dc1db3a384..4e795aefa0 100644
--- a/system/physmem.c
+++ b/system/physmem.c
@@ -47,6 +47,7 @@
#include "qemu/qemu-print.h"
#include "qemu/log.h"
#include "qemu/memalign.h"
+#include "qemu/memfd.h"
#include "exec/memory.h"
#include "exec/ioport.h"
#include "sysemu/dma.h"
@@ -2057,6 +2058,24 @@ RAMBlock *qemu_ram_alloc_from_file(ram_addr_t size,
MemoryRegion *mr,
}
#endif
+/*
+ * Try to allocate a zero-sized anonymous fd for shared memory allocations.
+ * Returns >=0 if succeeded, <0 otherwise.
+ *
+ * Prioritize memfd, as it doesn't have the same /dev/shm size limitation
+ * v.s. POSIX shm_open().
+ */
+static int qemu_ram_alloc_anonymous_fd(void)
+{
+ if (qemu_memfd_check(0)) {
+ return qemu_memfd_create("anon-memfd", 0, 0, 0, 0, NULL);
+ } else if (qemu_shm_available()) {
+ return qemu_shm_alloc(0, NULL);
+ } else {
+ return -1;
+ }
+}
+
static
RAMBlock *qemu_ram_alloc_internal(ram_addr_t size, ram_addr_t max_size,
void (*resized)(const char*,
@@ -2073,6 +2092,25 @@ RAMBlock *qemu_ram_alloc_internal(ram_addr_t size,
ram_addr_t max_size,
RAM_NORESERVE | RAM_GUEST_MEMFD)) == 0);
assert(!host ^ (ram_flags & RAM_PREALLOC));
+ /*
+ * Try to use fd-based allocation for anonymous and shared memory,
+ * because fd is normally more flexible (e.g. on memory sharing between
+ * processes). We can still fallback to old ways if it fails.
+ */
+ if (!host && (ram_flags & RAM_SHARED)) {
+ int fd = qemu_ram_alloc_anonymous_fd();
+
+ if (fd >= 0) {
+ new_block = qemu_ram_alloc_from_fd(size, mr, ram_flags,
+ fd, 0, errp);
+ if (new_block) {
+ return new_block;
+ }
+ close(fd);
+ }
+ /* Either fd or ramblock allocation failed, fallback */
+ }
+
align = qemu_real_host_page_size();
align = MAX(align, TARGET_PAGE_SIZE);
size = ROUND_UP(size, align);
diff --git a/util/memfd.c b/util/memfd.c
index 8a2e906962..0dc15b2f44 100644
--- a/util/memfd.c
+++ b/util/memfd.c
@@ -52,6 +52,8 @@ int qemu_memfd_create(const char *name, size_t size, bool
hugetlb,
{
int htsize = hugetlbsize ? ctz64(hugetlbsize) : 0;
+ ERRP_GUARD();
+
if (htsize && 1ULL << htsize != hugetlbsize) {
error_setg(errp, "Hugepage size must be a power of 2");
return -1;
diff --git a/util/oslib-posix.c b/util/oslib-posix.c
index f8c3724e68..6ca3e994fc 100644
--- a/util/oslib-posix.c
+++ b/util/oslib-posix.c
@@ -944,6 +944,8 @@ int qemu_shm_alloc(size_t size, Error **errp)
static int sequence;
mode_t mode;
+ ERRP_GUARD();
+
cur_sequence = qatomic_fetch_inc(&sequence);
/*