[PATCH v5 11/12] system/physmem: make ram_block_discard_range() handle guest_memfd

Most callers of ram_block_discard_range() want to discard both the
shared and guest_memfd backing. Only kvm_convert_memory() intentionally
discards a single plane during private/shared conversions.

Rename the current implementation to ram_block_discard_shared_range()
and make ram_block_discard_range() a composite that also discards
guest_memfd when present (rb->guest_memfd >= 0). This ensures callers
like virtio-mem, virtio-balloon, hv-balloon, migration.. reclaim
private pages on discard.

Update kvm_convert_memory() to use the plane-specific
ram_block_discard_shared_range() since it only needs to discard
the shared backing when converting to private.

Likewise, after TDVF image copy, use ram_block_discard_shared_range().

Reviewed-by: Peter Xu <[email protected]>
Reviewed-by: Xiaoyao Li <[email protected]>
Signed-off-by: Marc-André Lureau <[email protected]>
---
 include/system/ramblock.h |  3 ++-
 accel/kvm/kvm-all.c       |  2 +-
 system/physmem.c          | 25 +++++++++++++++++++++----
 target/i386/kvm/tdx.c     |  2 +-
 system/trace-events       |  2 +-
 5 files changed, 26 insertions(+), 8 deletions(-)

diff --git a/include/system/ramblock.h b/include/system/ramblock.h
index 2b38718fe5f..f0639287bf0 100644
--- a/include/system/ramblock.h
+++ b/include/system/ramblock.h
@@ -103,7 +103,8 @@ struct RamBlockAttributes {
 
 /* @offset: the offset within the RAMBlock */
 int ram_block_discard_range(RAMBlock *rb, uint64_t offset, size_t length);
-/* @offset: the offset within the RAMBlock */
+int ram_block_discard_shared_range(RAMBlock *rb, uint64_t offset,
+                                   size_t length);
 int ram_block_discard_guest_memfd_range(RAMBlock *rb, uint64_t offset,
                                         size_t length);
 
diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index 96f90ebb240..dcfb99cdf74 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -3426,7 +3426,7 @@ int kvm_convert_memory(hwaddr start, hwaddr size, bool to_private)
              */
             goto out_unref;
         }
-        ret = ram_block_discard_range(rb, offset, size);
+        ret = ram_block_discard_shared_range(rb, offset, size);
     } else {
         ret = ram_block_discard_guest_memfd_range(rb, offset, size);
     }
diff --git a/system/physmem.c b/system/physmem.c
index ddb67ba2359..0ff80a74917 100644
--- a/system/physmem.c
+++ b/system/physmem.c
@@ -4095,7 +4095,7 @@ int qemu_ram_foreach_block(RAMBlockIterFunc func, void *opaque)
  * Returns: 0 on success, none-0 on failure
  *
  */
-int ram_block_discard_range(RAMBlock *rb, uint64_t offset, size_t length)
+int ram_block_discard_shared_range(RAMBlock *rb, uint64_t offset, size_t length)
 {
     int ret = -1;
 
@@ -4144,7 +4144,7 @@ int ram_block_discard_range(RAMBlock *rb, uint64_t offset, size_t length)
              * have a MAP_PRIVATE mapping, possibly messing with other
              * MAP_PRIVATE/MAP_SHARED mappings. There is no easy way to
              * change that behavior whithout violating the promised
-             * semantics of ram_block_discard_range().
+             * semantics of ram_block_discard_shared_range().
              *
              * Only warn, because it works as long as nobody else uses that
              * file.
@@ -4200,8 +4200,9 @@ int ram_block_discard_range(RAMBlock *rb, uint64_t offset, size_t length)
             goto err;
 #endif
         }
-        trace_ram_block_discard_range(rb->idstr, host_startaddr, length,
-                                      need_madvise, need_fallocate, ret);
+        trace_ram_block_discard_shared_range(rb->idstr, host_startaddr, length,
+                                             need_madvise, need_fallocate,
+                                             ret);
     } else {
         error_report("%s: Overrun block '%s' (%" PRIu64 "/%zx/" RAM_ADDR_FMT")",
                      __func__, rb->idstr, offset, length, rb->max_length);
@@ -4211,6 +4212,22 @@ err:
     return ret;
 }
 
+int ram_block_discard_range(RAMBlock *rb, uint64_t offset, size_t length)
+{
+    int ret;
+
+    ret = ram_block_discard_shared_range(rb, offset, length);
+    if (ret) {
+        return ret;
+    }
+
+    if (rb->guest_memfd >= 0) {
+        ret = ram_block_discard_guest_memfd_range(rb, offset, length);
+    }
+
+    return ret;
+}
+
 int ram_block_discard_guest_memfd_range(RAMBlock *rb, uint64_t offset,
                                         size_t length)
 {
diff --git a/target/i386/kvm/tdx.c b/target/i386/kvm/tdx.c
index 4714c9d514e..fcb11aa67e4 100644
--- a/target/i386/kvm/tdx.c
+++ b/target/i386/kvm/tdx.c
@@ -385,7 +385,7 @@ static void tdx_finalize_vm(Notifier *notifier, void *unused)
      * KVM_MEMORY_MAPPING. It becomes useless.
      */
     ram_block = tdx_guest->tdvf_mr->ram_block;
-    ram_block_discard_range(ram_block, 0, ram_block->max_length);
+    ram_block_discard_shared_range(ram_block, 0, ram_block->max_length);
 
     tdx_vm_ioctl(KVM_TDX_FINALIZE_VM, 0, NULL, &error_fatal);
     CONFIDENTIAL_GUEST_SUPPORT(tdx_guest)->ready = true;
diff --git a/system/trace-events b/system/trace-events
index e6e1b612798..51b4a4679a2 100644
--- a/system/trace-events
+++ b/system/trace-events
@@ -32,7 +32,7 @@ global_dirty_changed(unsigned int bitmask) "bitmask 0x%"PRIx32
 address_space_map(void *as, uint64_t addr, uint64_t len, bool is_write, uint32_t attrs) "as:%p addr 0x%"PRIx64":%"PRIx64" write:%d attrs:0x%x"
 find_ram_offset(uint64_t size, uint64_t offset) "size: 0x%" PRIx64 " @ 0x%" PRIx64
 find_ram_offset_loop(uint64_t size, uint64_t candidate, uint64_t offset, uint64_t next, uint64_t mingap) "trying size: 0x%" PRIx64 " @ 0x%" PRIx64 ", offset: 0x%" PRIx64" next: 0x%" PRIx64 " mingap: 0x%" PRIx64
-ram_block_discard_range(const char *rbname, void *hva, size_t length, bool need_madvise, bool need_fallocate, int ret) "%s@%p + 0x%zx: madvise: %d fallocate: %d ret: %d"
+ram_block_discard_shared_range(const char *rbname, void *hva, size_t length, bool need_madvise, bool need_fallocate, int ret) "%s@%p + 0x%zx: madvise: %d fallocate: %d ret: %d"
 qemu_ram_alloc_shared(const char *name, size_t size, size_t max_size, int fd, void *host) "%s size %zu max_size %zu fd %d host %p"
 
 subpage_register(void *subpage, uint32_t start, uint32_t end, int idx, int eidx, uint16_t section) "subpage %p start 0x%08x end 0x%08x idx 0x%08x eidx 0x%08x section %u"

-- 
2.54.0