@@ -2001,6 +2001,16 @@ void qemu_ram_unset_migratable(RAMBlock *rb)
rb->flags &= ~RAM_MIGRATABLE;
}
+bool qemu_ram_is_resizeable(RAMBlock *rb)
+{
+ return rb->flags & RAM_RESIZEABLE;
+}
+
+bool qemu_ram_is_resizeable_alloc(RAMBlock *rb)
+{
+ return rb->flags & RAM_RESIZEABLE_ALLOC;
+}
+
/* Called with iothread lock held. */
void qemu_ram_set_idstr(RAMBlock *new_block, const char *name, DeviceState *dev)
{
@@ -2094,6 +2104,7 @@ static void qemu_ram_apply_settings(void *host, size_t length)
*/
int qemu_ram_resize(RAMBlock *block, ram_addr_t newsize, Error **errp)
{
+ const bool shared = block->flags & RAM_SHARED;
const ram_addr_t oldsize = block->used_length;
assert(block);
@@ -2104,7 +2115,7 @@ int qemu_ram_resize(RAMBlock *block, ram_addr_t newsize, Error **errp)
return 0;
}
- if (!(block->flags & RAM_RESIZEABLE)) {
+ if (!qemu_ram_is_resizeable(block)) {
error_setg_errno(errp, EINVAL,
"Length mismatch: %s: 0x" RAM_ADDR_FMT
" in != 0x" RAM_ADDR_FMT, block->idstr,
@@ -2120,6 +2131,15 @@ int qemu_ram_resize(RAMBlock *block, ram_addr_t newsize, Error **errp)
return -EINVAL;
}
+ if (oldsize < newsize && qemu_ram_is_resizeable_alloc(block)) {
+ if (!qemu_anon_ram_resize(block->host, oldsize, newsize, shared)) {
+ error_setg_errno(errp, -ENOMEM, "Cannot allocate enough memory.");
+ return -ENOMEM;
+ }
+ /* apply settings for the newly accessible memory */
+ qemu_ram_apply_settings(block->host + oldsize, newsize - oldsize);
+ }
+
/* Notify before modifying the ram block and touching the bitmaps. */
if (block->host) {
ram_block_notify_resize(block->host, oldsize, newsize);
@@ -2133,6 +2153,16 @@ int qemu_ram_resize(RAMBlock *block, ram_addr_t newsize, Error **errp)
if (block->resized) {
block->resized(block->idstr, newsize, block->host);
}
+
+ /*
+ * Shrinking will only fail in rare scenarios (e.g., maximum number of
+ * mappings reached), and can be ignored. Warn only.
+ */
+ if (newsize < oldsize && qemu_ram_is_resizeable_alloc(block) &&
+ !qemu_anon_ram_resize(block->host, oldsize, newsize, shared)) {
+ warn_report("Shrinking memory allocation failed.");
+ }
+
return 0;
}
@@ -2211,6 +2241,28 @@ static void dirty_memory_extend(ram_addr_t old_ram_size,
}
}
+static void ram_block_alloc_ram(RAMBlock *rb)
+{
+ const bool shared = qemu_ram_is_shared(rb);
+
+ /*
+ * If we can, try to allocate actually resizeable ram. Will also fail
+ * if qemu_anon_ram_alloc_resizeable() is not implemented.
+ */
+ if (phys_mem_alloc == qemu_anon_ram_alloc &&
+ qemu_ram_is_resizeable(rb) &&
+ ram_block_notifiers_support_resize()) {
+ rb->host = qemu_anon_ram_alloc_resizeable(rb->used_length,
+ rb->max_length,
+ &rb->mr->align, shared);
+ if (rb->host) {
+ rb->flags |= RAM_RESIZEABLE_ALLOC;
+ return;
+ }
+ }
+ rb->host = phys_mem_alloc(rb->max_length, &rb->mr->align, shared);
+}
+
static void ram_block_add(RAMBlock *new_block, Error **errp)
{
RAMBlock *block;
@@ -2233,9 +2285,7 @@ static void ram_block_add(RAMBlock *new_block, Error **errp)
return;
}
} else {
- new_block->host = phys_mem_alloc(new_block->max_length,
- &new_block->mr->align,
- qemu_ram_is_shared(new_block));
+ ram_block_alloc_ram(new_block);
if (!new_block->host) {
error_setg_errno(errp, errno,
"cannot set up guest memory '%s'",
@@ -2280,7 +2330,11 @@ static void ram_block_add(RAMBlock *new_block, Error **errp)
DIRTY_CLIENTS_ALL);
if (new_block->host) {
- qemu_ram_apply_settings(new_block->host, new_block->max_length);
+ if (qemu_ram_is_resizeable_alloc(new_block)) {
+ qemu_ram_apply_settings(new_block->host, new_block->used_length);
+ } else {
+ qemu_ram_apply_settings(new_block->host, new_block->max_length);
+ }
ram_block_notify_add(new_block->host, new_block->used_length,
new_block->max_length);
}
@@ -862,6 +862,13 @@ static int ram_block_notify_add_single(RAMBlock *rb, void *opaque)
RAMBlockNotifier *notifier = opaque;
if (host) {
+ /*
+ * Dynamically adding notifiers that don't support resizes is forbidden
+ * when dealing with resizeable ram blocks that have actually resizeable
+ * allocations.
+ */
+ g_assert(!qemu_ram_is_resizeable_alloc(rb) ||
+ notifier->ram_block_resized);
notifier->ram_block_added(notifier, host, size, max_size);
}
return 0;
@@ -66,6 +66,8 @@ void qemu_ram_set_uf_zeroable(RAMBlock *rb);
bool qemu_ram_is_migratable(RAMBlock *rb);
void qemu_ram_set_migratable(RAMBlock *rb);
void qemu_ram_unset_migratable(RAMBlock *rb);
+bool qemu_ram_is_resizeable(RAMBlock *rb);
+bool qemu_ram_is_resizeable_alloc(RAMBlock *rb);
size_t qemu_ram_pagesize(RAMBlock *block);
size_t qemu_ram_pagesize_largest(void);
@@ -129,6 +129,14 @@ typedef struct IOMMUNotifier IOMMUNotifier;
/* RAM is a persistent kind memory */
#define RAM_PMEM (1 << 5)
+/*
+ * Implies RAM_RESIZEABLE. Memory beyond the used_length is inaccessible
+ * (esp. initially and after resizing). For such memory blocks, only the
+ * used_length is reserved in the OS - resizing might fail. Will only be
+ * used with host OS support and if all ram block notifiers support resizing.
+ */
+#define RAM_RESIZEABLE_ALLOC (1 << 6)
+
static inline void iommu_notifier_init(IOMMUNotifier *n, IOMMUNotify fn,
IOMMUNotifierFlag flags,
hwaddr start, hwaddr end,
We can now make use of resizeable anonymous allocations to implement actually resizeable ram blocks. Resizeable anonymous allocations are not implemented under WIN32 yet and are not available when using alternative allocators. Fall back to the existing handling. We also have to fallback to the existing handling in case any ram block notifier does not support resizing (esp., AMD SEV, HAX) yet. Remember in RAM_RESIZEABLE_ALLOC if we are using resizeable anonymous allocations. Try to grow early, as that can easily fail if out of memory. Shrink late and ignore errors (nothing will actually break). Warn only. The benefit of actually resizeable ram blocks is that e.g., under Linux, only the actual size will be reserved (even if "/proc/sys/vm/overcommit_memory" is set to "never"). Additional memory will be reserved when trying to resize, which allows to have ram blocks that start small but can theoretically grow very large. Note1: We are not able to create resizeable ram blocks with pre-allocated memory yet, so prealloc is not affected. Note2: mlock should work as it used to as os_mlock() does a mlockall(MCL_CURRENT | MCL_FUTURE), which includes future mappings. Note3: Nobody should access memory beyond used_length. Memory notifiers already properly take care of this, only ram block notifiers violate this constraint and, therefore, have to be special-cased. Especially, any ram block notifier that might dynamically register at runtime (e.g., vfio) has to support resizes. Add an assert for that. Both, HAX and SEV register early, so they are fine. Cc: Richard Henderson <rth@twiddle.net> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com> Cc: Eduardo Habkost <ehabkost@redhat.com> Cc: Marcel Apfelbaum <marcel.apfelbaum@gmail.com> Cc: Stefan Weil <sw@weilnetz.de> Cc: Igor Mammedov <imammedo@redhat.com> Cc: Shameerali Kolothum Thodi <shameerali.kolothum.thodi@huawei.com> Signed-off-by: David Hildenbrand <david@redhat.com> --- exec.c | 64 ++++++++++++++++++++++++++++++++++++--- hw/core/numa.c | 7 +++++ include/exec/cpu-common.h | 2 ++ include/exec/memory.h | 8 +++++ 4 files changed, 76 insertions(+), 5 deletions(-)