[PATCH v3 08/10] tcg: remove the final vestiges of dstate

["Alex Bennée" <alex.bennee@linaro.org>]

Now we no longer have dynamic state affecting things we can remove the
additional fields in cpu.h and simplify the TB hash calculation.

For the benchmark:

    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"

It has a marginal effect on runtime, before:

  Time (mean ± σ):     26.279 s ±  2.438 s    [User: 41.113 s, System: 1.843 s]
  Range (min … max):   24.420 s … 32.565 s    20 runs

after:

  Time (mean ± σ):     24.440 s ±  2.885 s    [User: 34.474 s, System: 2.028 s]
  Range (min … max):   21.663 s … 29.937 s    20 runs

Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1358
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-Id: <20230503091756.1453057-9-alex.bennee@linaro.org>
---
 accel/tcg/tb-hash.h       | 6 +++---
 include/exec/exec-all.h   | 3 ---
 include/hw/core/cpu.h     | 5 -----
 accel/tcg/cpu-exec.c      | 7 +------
 accel/tcg/tb-maint.c      | 5 ++---
 accel/tcg/translate-all.c | 6 ------
 6 files changed, 6 insertions(+), 26 deletions(-)

diff --git a/accel/tcg/tb-hash.h b/accel/tcg/tb-hash.h
index 83dc610e4c..1d19c69caa 100644
--- a/accel/tcg/tb-hash.h
+++ b/accel/tcg/tb-hash.h
@@ -61,10 +61,10 @@ static inline unsigned int tb_jmp_cache_hash_func(target_ulong pc)
 #endif /* CONFIG_SOFTMMU */
 
 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 trace_vcpu_dstate)
+uint32_t tb_hash_func(tb_page_addr_t phys_pc, target_ulong pc,
+                      uint32_t flags, uint32_t cf_mask)
 {
-    return qemu_xxhash7(phys_pc, pc, flags, cf_mask, trace_vcpu_dstate);
+    return qemu_xxhash6(phys_pc, pc, flags, cf_mask);
 }
 
 #endif
diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h
index ecded1f112..3ee76af28b 100644
--- a/include/exec/exec-all.h
+++ b/include/exec/exec-all.h
@@ -548,9 +548,6 @@ struct TranslationBlock {
 #define CF_CLUSTER_MASK  0xff000000 /* Top 8 bits are cluster ID */
 #define CF_CLUSTER_SHIFT 24
 
-    /* Per-vCPU dynamic tracing state used to generate this TB */
-    uint32_t trace_vcpu_dstate;
-
     /*
      * Above fields used for comparing
      */
diff --git a/include/hw/core/cpu.h b/include/hw/core/cpu.h
index 397fd3ac68..4b399643d0 100644
--- a/include/hw/core/cpu.h
+++ b/include/hw/core/cpu.h
@@ -262,7 +262,6 @@ typedef void (*run_on_cpu_func)(CPUState *cpu, run_on_cpu_data data);
 struct qemu_work_item;
 
 #define CPU_UNSET_NUMA_NODE_ID -1
-#define CPU_TRACE_DSTATE_MAX_EVENTS 32
 
 /**
  * CPUState:
@@ -403,10 +402,6 @@ struct CPUState {
     /* Use by accel-block: CPU is executing an ioctl() */
     QemuLockCnt in_ioctl_lock;
 
-    /* Used for events with 'vcpu' and *without* the 'disabled' properties */
-    DECLARE_BITMAP(trace_dstate_delayed, CPU_TRACE_DSTATE_MAX_EVENTS);
-    DECLARE_BITMAP(trace_dstate, CPU_TRACE_DSTATE_MAX_EVENTS);
-
     DECLARE_BITMAP(plugin_mask, QEMU_PLUGIN_EV_MAX);
 
 #ifdef CONFIG_PLUGIN
diff --git a/accel/tcg/cpu-exec.c b/accel/tcg/cpu-exec.c
index bc0e1c3299..973da2a434 100644
--- a/accel/tcg/cpu-exec.c
+++ b/accel/tcg/cpu-exec.c
@@ -175,7 +175,6 @@ struct tb_desc {
     tb_page_addr_t page_addr0;
     uint32_t flags;
     uint32_t cflags;
-    uint32_t trace_vcpu_dstate;
 };
 
 static bool tb_lookup_cmp(const void *p, const void *d)
@@ -187,7 +186,6 @@ static bool tb_lookup_cmp(const void *p, const void *d)
         tb_page_addr0(tb) == desc->page_addr0 &&
         tb->cs_base == desc->cs_base &&
         tb->flags == desc->flags &&
-        tb->trace_vcpu_dstate == desc->trace_vcpu_dstate &&
         tb_cflags(tb) == desc->cflags) {
         /* check next page if needed */
         tb_page_addr_t tb_phys_page1 = tb_page_addr1(tb);
@@ -228,7 +226,6 @@ static TranslationBlock *tb_htable_lookup(CPUState *cpu, target_ulong pc,
     desc.cs_base = cs_base;
     desc.flags = flags;
     desc.cflags = cflags;
-    desc.trace_vcpu_dstate = *cpu->trace_dstate;
     desc.pc = pc;
     phys_pc = get_page_addr_code(desc.env, pc);
     if (phys_pc == -1) {
@@ -236,7 +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, *cpu->trace_dstate);
+                     flags, cflags);
     return qht_lookup_custom(&tb_ctx.htable, &desc, h, tb_lookup_cmp);
 }
 
@@ -263,7 +260,6 @@ static inline TranslationBlock *tb_lookup(CPUState *cpu, target_ulong pc,
                    jc->array[hash].pc == pc &&
                    tb->cs_base == cs_base &&
                    tb->flags == flags &&
-                   tb->trace_vcpu_dstate == *cpu->trace_dstate &&
                    tb_cflags(tb) == cflags)) {
             return tb;
         }
@@ -282,7 +278,6 @@ static inline TranslationBlock *tb_lookup(CPUState *cpu, target_ulong pc,
                    tb->pc == pc &&
                    tb->cs_base == cs_base &&
                    tb->flags == flags &&
-                   tb->trace_vcpu_dstate == *cpu->trace_dstate &&
                    tb_cflags(tb) == cflags)) {
             return tb;
         }
diff --git a/accel/tcg/tb-maint.c b/accel/tcg/tb-maint.c
index cb1f806f00..432a0cffdb 100644
--- a/accel/tcg/tb-maint.c
+++ b/accel/tcg/tb-maint.c
@@ -50,7 +50,6 @@ static bool tb_cmp(const void *ap, const void *bp)
             a->cs_base == b->cs_base &&
             a->flags == b->flags &&
             (tb_cflags(a) & ~CF_INVALID) == (tb_cflags(b) & ~CF_INVALID) &&
-            a->trace_vcpu_dstate == b->trace_vcpu_dstate &&
             tb_page_addr0(a) == tb_page_addr0(b) &&
             tb_page_addr1(a) == tb_page_addr1(b));
 }
@@ -888,7 +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->trace_vcpu_dstate);
+                     tb->flags, orig_cflags);
     if (!qht_remove(&tb_ctx.htable, tb, h)) {
         return;
     }
@@ -969,7 +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->trace_vcpu_dstate);
+                     tb->flags, tb->cflags);
     qht_insert(&tb_ctx.htable, tb, h, &existing_tb);
 
     /* remove TB from the page(s) if we couldn't insert it */
diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c
index 5b13281119..2ea42970e1 100644
--- a/accel/tcg/translate-all.c
+++ b/accel/tcg/translate-all.c
@@ -65,11 +65,6 @@
 #include "internal.h"
 #include "perf.h"
 
-/* Make sure all possible CPU event bits fit in tb->trace_vcpu_dstate */
-QEMU_BUILD_BUG_ON(CPU_TRACE_DSTATE_MAX_EVENTS >
-                  sizeof_field(TranslationBlock, trace_vcpu_dstate)
-                  * BITS_PER_BYTE);
-
 TBContext tb_ctx;
 
 /* Encode VAL as a signed leb128 sequence at P.
@@ -348,7 +343,6 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
     tb->cs_base = cs_base;
     tb->flags = flags;
     tb->cflags = cflags;
-    tb->trace_vcpu_dstate = *cpu->trace_dstate;
     tb_set_page_addr0(tb, phys_pc);
     tb_set_page_addr1(tb, -1);
     tcg_ctx->gen_tb = tb;
-- 
2.39.2