exec: [tcg] Use different TBs according to the vCPU's dynamic tracing state

Every vCPU now uses a separate set of TBs for each set of dynamic
tracing event state values. Each set of TBs can be used by any number of
vCPUs to maximize TB reuse when vCPUs have the same tracing state.

This feature is later used by tracetool to optimize tracing of guest
code events.

The maximum number of TB sets is defined as 2^E, where E is the number
of events that have the 'vcpu' property (their state is stored in
CPUState->trace_dstate).

For this to work, a change on the dynamic tracing state of a vCPU will
force it to flush its virtual TB cache (which is only indexed by
address), and fall back to the physical TB cache (which now contains the
vCPU's dynamic tracing state as part of the hashing function).

Signed-off-by: Lluís Vilanova <vilanova@ac.upc.edu>
Reviewed-by: Richard Henderson <rth@twiddle.net>
Reviewed-by: Emilio G. Cota <cota@braap.org>
Signed-off-by: Emilio G. Cota <cota@braap.org>
Message-id: 149915775266.6295.10060144081246467690.stgit@frigg.lan
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

2 files changed, 15 insertions, 4 deletions

diff --git a/accel/tcg/cpu-exec.c b/accel/tcg/cpu-exec.c
index 3581618bc0..d84b01d1b8 100644
--- a/accel/tcg/cpu-exec.c
+++ b/accel/tcg/cpu-exec.c
@@ -280,6 +280,7 @@ struct tb_desc {
     CPUArchState *env;
     tb_page_addr_t phys_page1;
     uint32_t flags;
+    uint32_t trace_vcpu_dstate;
 };
 
 static bool tb_cmp(const void *p, const void *d)
@@ -291,6 +292,7 @@ static bool tb_cmp(const void *p, const void *d)
         tb->page_addr[0] == desc->phys_page1 &&
         tb->cs_base == desc->cs_base &&
         tb->flags == desc->flags &&
+        tb->trace_vcpu_dstate == desc->trace_vcpu_dstate &&
         !atomic_read(&tb->invalid)) {
         /* check next page if needed */
         if (tb->page_addr[1] == -1) {
@@ -319,10 +321,11 @@ TranslationBlock *tb_htable_lookup(CPUState *cpu, target_ulong pc,
     desc.env = (CPUArchState *)cpu->env_ptr;
     desc.cs_base = cs_base;
     desc.flags = flags;
+    desc.trace_vcpu_dstate = *cpu->trace_dstate;
     desc.pc = pc;
     phys_pc = get_page_addr_code(desc.env, pc);
     desc.phys_page1 = phys_pc & TARGET_PAGE_MASK;
-    h = tb_hash_func(phys_pc, pc, flags);
+    h = tb_hash_func(phys_pc, pc, flags, *cpu->trace_dstate);
     return qht_lookup(&tcg_ctx.tb_ctx.htable, tb_cmp, &desc, h);
 }
 
@@ -342,7 +345,8 @@ static inline TranslationBlock *tb_find(CPUState *cpu,
     cpu_get_tb_cpu_state(env, &pc, &cs_base, &flags);
     tb = atomic_rcu_read(&cpu->tb_jmp_cache[tb_jmp_cache_hash_func(pc)]);
     if (unlikely(!tb || tb->pc != pc || tb->cs_base != cs_base ||
-                 tb->flags != flags)) {
+                 tb->flags != flags ||
+                 tb->trace_vcpu_dstate != *cpu->trace_dstate)) {
         tb = tb_htable_lookup(cpu, pc, cs_base, flags);
         if (!tb) {
 
diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c
index 4e1831cbb9..090ebad0a7 100644
--- a/accel/tcg/translate-all.c
+++ b/accel/tcg/translate-all.c
@@ -54,6 +54,7 @@
 #include "exec/tb-hash.h"
 #include "translate-all.h"
 #include "qemu/bitmap.h"
+#include "qemu/error-report.h"
 #include "qemu/timer.h"
 #include "qemu/main-loop.h"
 #include "exec/log.h"
@@ -112,6 +113,11 @@ typedef struct PageDesc {
 #define V_L2_BITS 10
 #define V_L2_SIZE (1 << V_L2_BITS)
 
+/* Make sure all possible CPU event bits fit in tb->trace_vcpu_dstate */
+QEMU_BUILD_BUG_ON(CPU_TRACE_DSTATE_MAX_EVENTS >
+                  sizeof(((TranslationBlock *)0)->trace_vcpu_dstate)
+                  * BITS_PER_BYTE);
+
 /*
  * L1 Mapping properties
  */
@@ -1071,7 +1077,7 @@ void tb_phys_invalidate(TranslationBlock *tb, tb_page_addr_t page_addr)
 
     /* remove the TB from the hash list */
     phys_pc = tb->page_addr[0] + (tb->pc & ~TARGET_PAGE_MASK);
-    h = tb_hash_func(phys_pc, tb->pc, tb->flags);
+    h = tb_hash_func(phys_pc, tb->pc, tb->flags, tb->trace_vcpu_dstate);
     qht_remove(&tcg_ctx.tb_ctx.htable, tb, h);
 
     /* remove the TB from the page list */
@@ -1216,7 +1222,7 @@ static void tb_link_page(TranslationBlock *tb, tb_page_addr_t phys_pc,
     }
 
     /* add in the hash table */
-    h = tb_hash_func(phys_pc, tb->pc, tb->flags);
+    h = tb_hash_func(phys_pc, tb->pc, tb->flags, tb->trace_vcpu_dstate);
     qht_insert(&tcg_ctx.tb_ctx.htable, tb, h);
 
 #ifdef DEBUG_TB_CHECK
@@ -1262,6 +1268,7 @@ 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->invalid = false;
 
 #ifdef CONFIG_PROFILER