Merge remote-tracking branch 'remotes/rth-gitlab/tags/pull-tcg-20210306' into staging

TCI build fix and cleanup
Streamline tb_lookup
Fixes for tcg/aarch64

# gpg: Signature made Sat 06 Mar 2021 21:34:46 GMT
# gpg:                using RSA key 7A481E78868B4DB6A85A05C064DF38E8AF7E215F
# gpg:                issuer "richard.henderson@linaro.org"
# gpg: Good signature from "Richard Henderson <richard.henderson@linaro.org>" [full]
# Primary key fingerprint: 7A48 1E78 868B 4DB6 A85A  05C0 64DF 38E8 AF7E 215F

* remotes/rth-gitlab/tags/pull-tcg-20210306: (27 commits)
  accel/tcg: Precompute curr_cflags into cpu->tcg_cflags
  include/exec: lightly re-arrange TranslationBlock
  accel/tcg: drop the use of CF_HASH_MASK and rename params
  accel/tcg: move CF_CLUSTER calculation to curr_cflags
  accel/tcg: rename tb_lookup__cpu_state and hoist state extraction
  tcg/tci: Merge mov, not and neg operations
  tcg/tci: Merge bswap operations
  tcg/tci: Merge extension operations
  tcg/tci: Merge basic arithmetic operations
  tcg/tci: Reduce use of tci_read_r64
  tcg/tci: Remove tci_read_r32s
  tcg/tci: Remove tci_read_r32
  tcg/tci: Remove tci_read_r16s
  tcg/tci: Remove tci_read_r16
  tcg/tci: Remove tci_read_r8s
  tcg/tci: Remove tci_read_r8
  tcg/tci: Merge identical cases in generation (load/store opcodes)
  tcg/tci: Merge identical cases in generation (conditional opcodes)
  tcg/tci: Merge identical cases in generation (deposit opcode)
  tcg/tci: Merge identical cases in generation (exchange opcodes)
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

3 files changed, 25 insertions, 25 deletions

diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h
index b7b3c0ef12..6b036cae8f 100644
--- a/include/exec/exec-all.h
+++ b/include/exec/exec-all.h
@@ -448,9 +448,6 @@ struct TranslationBlock {
     target_ulong pc;   /* simulated PC corresponding to this block (EIP + CS base) */
     target_ulong cs_base; /* CS base for this block */
     uint32_t flags; /* flags defining in which context the code was generated */
-    uint16_t size;      /* size of target code for this block (1 <=
-                           size <= TARGET_PAGE_SIZE) */
-    uint16_t icount;
     uint32_t cflags;    /* compile flags */
 #define CF_COUNT_MASK  0x00007fff
 #define CF_LAST_IO     0x00008000 /* Last insn may be an IO access.  */
@@ -460,12 +457,18 @@ struct TranslationBlock {
 #define CF_PARALLEL    0x00080000 /* Generate code for a parallel context */
 #define CF_CLUSTER_MASK 0xff000000 /* Top 8 bits are cluster ID */
 #define CF_CLUSTER_SHIFT 24
-/* cflags' mask for hashing/comparison, basically ignore CF_INVALID */
-#define CF_HASH_MASK   (~CF_INVALID)
 
     /* Per-vCPU dynamic tracing state used to generate this TB */
     uint32_t trace_vcpu_dstate;
 
+    /*
+     * Above fields used for comparing
+     */
+
+    /* size of target code for this block (1 <= size <= TARGET_PAGE_SIZE) */
+    uint16_t size;
+    uint16_t icount;
+
     struct tb_tc tc;
 
     /* first and second physical page containing code. The lower bit
@@ -510,8 +513,6 @@ struct TranslationBlock {
     uintptr_t jmp_dest[2];
 };
 
-extern bool parallel_cpus;
-
 /* Hide the qatomic_read to make code a little easier on the eyes */
 static inline uint32_t tb_cflags(const TranslationBlock *tb)
 {
@@ -519,10 +520,9 @@ static inline uint32_t tb_cflags(const TranslationBlock *tb)
 }
 
 /* current cflags for hashing/comparison */
-static inline uint32_t curr_cflags(void)
+static inline uint32_t curr_cflags(CPUState *cpu)
 {
-    return (parallel_cpus ? CF_PARALLEL : 0)
-         | (icount_enabled() ? CF_USE_ICOUNT : 0);
+    return cpu->tcg_cflags;
 }
 
 /* TranslationBlock invalidate API */
@@ -536,7 +536,7 @@ void tb_flush(CPUState *cpu);
 void tb_phys_invalidate(TranslationBlock *tb, tb_page_addr_t page_addr);
 TranslationBlock *tb_htable_lookup(CPUState *cpu, target_ulong pc,
                                    target_ulong cs_base, uint32_t flags,
-                                   uint32_t cf_mask);
+                                   uint32_t cflags);
 void tb_set_jmp_target(TranslationBlock *tb, int n, uintptr_t addr);
 
 /* GETPC is the true target of the return instruction that we'll execute.  */
diff --git a/include/exec/tb-lookup.h b/include/exec/tb-lookup.h
index 9cf475bb03..29d61ceb34 100644
--- a/include/exec/tb-lookup.h
+++ b/include/exec/tb-lookup.h
@@ -17,30 +17,28 @@
 #include "exec/tb-hash.h"
 
 /* Might cause an exception, so have a longjmp destination ready */
-static inline TranslationBlock *
-tb_lookup__cpu_state(CPUState *cpu, target_ulong *pc, target_ulong *cs_base,
-                     uint32_t *flags, uint32_t cf_mask)
+static inline TranslationBlock *tb_lookup(CPUState *cpu, target_ulong pc,
+                                          target_ulong cs_base,
+                                          uint32_t flags, uint32_t cflags)
 {
-    CPUArchState *env = (CPUArchState *)cpu->env_ptr;
     TranslationBlock *tb;
     uint32_t hash;
 
-    cpu_get_tb_cpu_state(env, pc, cs_base, flags);
-    hash = tb_jmp_cache_hash_func(*pc);
-    tb = qatomic_rcu_read(&cpu->tb_jmp_cache[hash]);
+    /* we should never be trying to look up an INVALID tb */
+    tcg_debug_assert(!(cflags & CF_INVALID));
 
-    cf_mask &= ~CF_CLUSTER_MASK;
-    cf_mask |= cpu->cluster_index << CF_CLUSTER_SHIFT;
+    hash = tb_jmp_cache_hash_func(pc);
+    tb = qatomic_rcu_read(&cpu->tb_jmp_cache[hash]);
 
     if (likely(tb &&
-               tb->pc == *pc &&
-               tb->cs_base == *cs_base &&
-               tb->flags == *flags &&
+               tb->pc == pc &&
+               tb->cs_base == cs_base &&
+               tb->flags == flags &&
                tb->trace_vcpu_dstate == *cpu->trace_dstate &&
-               (tb_cflags(tb) & (CF_HASH_MASK | CF_INVALID)) == cf_mask)) {
+               tb_cflags(tb) == cflags)) {
         return tb;
     }
-    tb = tb_htable_lookup(cpu, *pc, *cs_base, *flags, cf_mask);
+    tb = tb_htable_lookup(cpu, pc, cs_base, flags, cflags);
     if (tb == NULL) {
         return NULL;
     }
diff --git a/include/hw/core/cpu.h b/include/hw/core/cpu.h
index c005d3dc2d..c68bc3ba8a 100644
--- a/include/hw/core/cpu.h
+++ b/include/hw/core/cpu.h
@@ -282,6 +282,7 @@ struct qemu_work_item;
  *   to a cluster this will be UNASSIGNED_CLUSTER_INDEX; otherwise it will
  *   be the same as the cluster-id property of the CPU object's TYPE_CPU_CLUSTER
  *   QOM parent.
+ * @tcg_cflags: Pre-computed cflags for this cpu.
  * @nr_cores: Number of cores within this CPU package.
  * @nr_threads: Number of threads within this CPU.
  * @running: #true if CPU is currently running (lockless).
@@ -412,6 +413,7 @@ struct CPUState {
     /* TODO Move common fields from CPUArchState here. */
     int cpu_index;
     int cluster_index;
+    uint32_t tcg_cflags;
     uint32_t halted;
     uint32_t can_do_io;
     int32_t exception_index;