accel/tcg: include cs_base in our hash calculations

We weren't using cs_base in the hash calculations before. Since the
arm front end moved a chunk of flags in a378206a20 (target/arm: Move
mode specific TB flags to tb->cs_base) they comprise of an important
part of the execution state.

Widen the tb_hash_func to include cs_base and expand to qemu_xxhash8()
to accommodate it.

My initial benchmark shows very little difference in the
runtime.

Before:

armhf

➜  hyperfine -w 2 -m 20 "./arm-softmmu/qemu-system-arm -cpu cortex-a15 -machine type=virt,highmem=off -display none -m 2048 -serial mon:stdio -netdev user,id=unet,hostfwd=tcp::2222-:22 -device virtio-net-pci,netdev=unet -device virtio-scsi-pci -blockdev driver=raw,node-name=hd,discard=unmap,file.driver=host_device,file.filename=/dev/zen-disk/debian-bullseye-armhf -device scsi-hd,drive=hd -smp 4 -kernel /home/alex/lsrc/linux.git/builds/arm/arch/arm/boot/zImage -append 'console=ttyAMA0 root=/dev/sda2 systemd.unit=benchmark.service' -snapshot"
Benchmark 1: ./arm-softmmu/qemu-system-arm -cpu cortex-a15 -machine type=virt,highmem=off -display none -m 2048 -serial mon:stdio -netdev user,id=unet,hostfwd=tcp::2222-:22 -device virtio-net-pci,netdev=unet -device virtio-scsi-pci -blockdev driver=raw,node-name=hd,discard=unmap,file.driver=host_device,file.filename=/dev/zen-disk/debian-bullseye-armhf -device scsi-hd,drive=hd -smp 4 -kernel /home/alex/lsrc/linux.git/builds/arm/arch/arm/boot/zImage -append 'console=ttyAMA0 root=/dev/sda2 systemd.unit=benchmark.service' -snapshot
  Time (mean ± σ):     24.627 s ±  2.708 s    [User: 34.309 s, System: 1.797 s]
  Range (min … max):   22.345 s … 29.864 s    20 runs

arm64

➜  hyperfine -w 2 -n 20 "./qemu-system-aarch64 -cpu max,pauth-impdef=on -machine type=virt,virtualization=on,gic-version=3 -display none -serial mon:stdio -netdev user,id=unet,hostfwd=tcp::2222-:22,hostfwd=tcp::1234-:1234 -device virtio-net-pci,netdev=unet -device virtio-scsi-pci -blockdev driver=raw,node-name=hd,discard=unmap,file.driver=host_device,file.filename=/dev/zen-disk/debian-bullseye-arm64 -device scsi-hd,drive=hd -smp 4 -kernel ~/lsrc/linux.git/builds/arm64/arch/arm64/boot/Image.gz -append 'console=ttyAMA0 root=/dev/sda2 systemd.unit=benchmark-pigz.service' -snapshot"
Benchmark 1: 20
  Time (mean ± σ):     62.559 s ±  2.917 s    [User: 189.115 s, System: 4.089 s]
  Range (min … max):   59.997 s … 70.153 s    10 runs

After:

armhf

Benchmark 1: ./arm-softmmu/qemu-system-arm -cpu cortex-a15 -machine type=virt,highmem=off -display none -m 2048 -serial mon:stdio -netdev user,id=unet,hostfwd=tcp::2222-:22 -device virtio-net-pci,netdev=unet -device virtio-scsi-pci -blockdev driver=raw,node-name=hd,discard=unmap,file.driver=host_device,file.filename=/dev/zen-disk/debian-bullseye-armhf -device scsi-hd,drive=hd -smp 4 -kernel /home/alex/lsrc/linux.git/builds/arm/arch/arm/boot/zImage -append 'console=ttyAMA0 root=/dev/sda2 systemd.unit=benchmark.service' -snapshot
  Time (mean ± σ):     24.223 s ±  2.151 s    [User: 34.284 s, System: 1.906 s]
  Range (min … max):   22.000 s … 28.476 s    20 runs

arm64

hyperfine -w 2 -n 20 "./qemu-system-aarch64 -cpu max,pauth-impdef=on -machine type=virt,virtualization=on,gic-version=3 -display none -serial mon:stdio -netdev user,id=unet,hostfwd=tcp::2222-:22,hostfwd=tcp::1234-:1234 -device virtio-net-pci,netdev=unet -device virtio-scsi-pci -blockdev driver=raw,node-name=hd,discard=unmap,file.driver=host_device,file.filename=/dev/zen-disk/debian-bullseye-arm64 -device scsi-hd,drive=hd -smp 4 -kernel ~/lsrc/linux.git/builds/arm64/arch/arm64/boot/Image.gz -append 'console=ttyAMA0 root=/dev/sda2 systemd.unit=benchmark-pigz.service' -snapshot"
Benchmark 1: 20
  Time (mean ± σ):     62.769 s ±  1.978 s    [User: 188.431 s, System: 5.269 s]
  Range (min … max):   60.285 s … 66.868 s    10 runs

Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20230526165401.574474-12-alex.bennee@linaro.org
Message-Id: <20230524133952.3971948-11-alex.bennee@linaro.org>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

3 files changed, 5 insertions, 5 deletions

diff --git a/accel/tcg/cpu-exec.c b/accel/tcg/cpu-exec.c
index 4a1dce98ff..60ca9e229e 100644
--- a/accel/tcg/cpu-exec.c
+++ b/accel/tcg/cpu-exec.c
@@ -233,7 +233,7 @@ static TranslationBlock *tb_htable_lookup(CPUState *cpu, target_ulong pc,
     }
     desc.page_addr0 = phys_pc;
     h = tb_hash_func(phys_pc, (cflags & CF_PCREL ? 0 : pc),
-                     flags, cflags);
+                     flags, cs_base, cflags);
     return qht_lookup_custom(&tb_ctx.htable, &desc, h, tb_lookup_cmp);
 }
 
diff --git a/accel/tcg/tb-hash.h b/accel/tcg/tb-hash.h
index 1d19c69caa..2ba2193731 100644
--- a/accel/tcg/tb-hash.h
+++ b/accel/tcg/tb-hash.h
@@ -62,9 +62,9 @@ static inline unsigned int tb_jmp_cache_hash_func(target_ulong pc)
 
 static inline
 uint32_t tb_hash_func(tb_page_addr_t phys_pc, target_ulong pc,
-                      uint32_t flags, uint32_t cf_mask)
+                      uint32_t flags, uint64_t flags2, uint32_t cf_mask)
 {
-    return qemu_xxhash6(phys_pc, pc, flags, cf_mask);
+    return qemu_xxhash8(phys_pc, pc, flags2, flags, cf_mask);
 }
 
 #endif
diff --git a/accel/tcg/tb-maint.c b/accel/tcg/tb-maint.c
index bc1961ea55..892eecda2d 100644
--- a/accel/tcg/tb-maint.c
+++ b/accel/tcg/tb-maint.c
@@ -887,7 +887,7 @@ static void do_tb_phys_invalidate(TranslationBlock *tb, bool rm_from_page_list)
     /* remove the TB from the hash list */
     phys_pc = tb_page_addr0(tb);
     h = tb_hash_func(phys_pc, (orig_cflags & CF_PCREL ? 0 : tb->pc),
-                     tb->flags, orig_cflags);
+                     tb->flags, tb->cs_base, orig_cflags);
     if (!qht_remove(&tb_ctx.htable, tb, h)) {
         return;
     }
@@ -968,7 +968,7 @@ TranslationBlock *tb_link_page(TranslationBlock *tb, tb_page_addr_t phys_pc,
 
     /* add in the hash table */
     h = tb_hash_func(phys_pc, (tb->cflags & CF_PCREL ? 0 : tb->pc),
-                     tb->flags, tb->cflags);
+                     tb->flags, tb->cs_base, tb->cflags);
     qht_insert(&tb_ctx.htable, tb, h, &existing_tb);
 
     /* remove TB from the page(s) if we couldn't insert it */