Revision a835429cda91621fca915d80672a157b47738afb authored by Sean Christopherson on 25 March 2021, 20:01:17 UTC, committed by Paolo Bonzini on 30 March 2021, 17:19:55 UTC
When flushing a range of GFNs across multiple roots, ensure any pending
flush from a previous root is honored before yielding while walking the
tables of the current root.
Note, kvm_tdp_mmu_zap_gfn_range() now intentionally overwrites its local
"flush" with the result to avoid redundant flushes. zap_gfn_range()
preserves and return the incoming "flush", unless of course the flush was
performed prior to yielding and no new flush was triggered.
Fixes: 1af4a96025b3 ("KVM: x86/mmu: Yield in TDU MMU iter even if no SPTES changed")
Cc: stable@vger.kernel.org
Reviewed-by: Ben Gardon <bgardon@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210325200119.1359384-2-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
1 parent 1e28eed
| File | Mode | Size |
|---|---|---|
| Kconfig | -rw-r--r-- | 2.3 KB |
| Makefile | -rw-r--r-- | 414 bytes |
| cache.c | -rw-r--r-- | 10.6 KB |
| cookie.c | -rw-r--r-- | 25.2 KB |
| fsdef.c | -rw-r--r-- | 2.9 KB |
| histogram.c | -rw-r--r-- | 2.2 KB |
| internal.h | -rw-r--r-- | 13.5 KB |
| main.c | -rw-r--r-- | 4.6 KB |
| netfs.c | -rw-r--r-- | 1.9 KB |
| object-list.c | -rw-r--r-- | 11.3 KB |
| object.c | -rw-r--r-- | 32.9 KB |
| operation.c | -rw-r--r-- | 17.0 KB |
| page.c | -rw-r--r-- | 33.0 KB |
| proc.c | -rw-r--r-- | 1.7 KB |
| stats.c | -rw-r--r-- | 9.9 KB |
Computing file changes ...
