*/
#ifdef _WIN32
#include <windows.h>
-#else
-#include <sys/mman.h>
#endif
#include "qemu/osdep.h"
#define V_L2_BITS 10
#define V_L2_SIZE (1 << V_L2_BITS)
-/* The bits remaining after N lower levels of page tables. */
-#define V_L1_BITS_REM \
- ((L1_MAP_ADDR_SPACE_BITS - TARGET_PAGE_BITS) % V_L2_BITS)
-
-#if V_L1_BITS_REM < 4
-#define V_L1_BITS (V_L1_BITS_REM + V_L2_BITS)
-#else
-#define V_L1_BITS V_L1_BITS_REM
-#endif
-
-#define V_L1_SIZE ((target_ulong)1 << V_L1_BITS)
-
-#define V_L1_SHIFT (L1_MAP_ADDR_SPACE_BITS - TARGET_PAGE_BITS - V_L1_BITS)
-
uintptr_t qemu_host_page_size;
intptr_t qemu_host_page_mask;
-/* The bottom level has pointers to PageDesc */
-static void *l1_map[V_L1_SIZE];
+/*
+ * L1 Mapping properties
+ */
+static int v_l1_size;
+static int v_l1_shift;
+static int v_l2_levels;
+
+/* The bottom level has pointers to PageDesc, and is indexed by
+ * anything from 4 to (V_L2_BITS + 3) bits, depending on target page size.
+ */
+#define V_L1_MIN_BITS 4
+#define V_L1_MAX_BITS (V_L2_BITS + 3)
+#define V_L1_MAX_SIZE (1 << V_L1_MAX_BITS)
+
+static void *l1_map[V_L1_MAX_SIZE];
/* code generation context */
TCGContext tcg_ctx;
+bool parallel_cpus;
/* translation block context */
#ifdef CONFIG_USER_ONLY
__thread int have_tb_lock;
#endif
+static void page_table_config_init(void)
+{
+ uint32_t v_l1_bits;
+
+ assert(TARGET_PAGE_BITS);
+ /* The bits remaining after N lower levels of page tables. */
+ v_l1_bits = (L1_MAP_ADDR_SPACE_BITS - TARGET_PAGE_BITS) % V_L2_BITS;
+ if (v_l1_bits < V_L1_MIN_BITS) {
+ v_l1_bits += V_L2_BITS;
+ }
+
+ v_l1_size = 1 << v_l1_bits;
+ v_l1_shift = L1_MAP_ADDR_SPACE_BITS - TARGET_PAGE_BITS - v_l1_bits;
+ v_l2_levels = v_l1_shift / V_L2_BITS - 1;
+
+ assert(v_l1_bits <= V_L1_MAX_BITS);
+ assert(v_l1_shift % V_L2_BITS == 0);
+ assert(v_l2_levels >= 0);
+}
+
void tb_lock(void)
{
#ifdef CONFIG_USER_ONLY
int64_t ti = profile_getclock();
#endif
+ searched_pc -= GETPC_ADJ;
+
if (searched_pc < host_pc) {
return -1;
}
static void page_init(void)
{
page_size_init();
+ page_table_config_init();
+
#if defined(CONFIG_BSD) && defined(CONFIG_USER_ONLY)
{
#ifdef HAVE_KINFO_GETVMMAP
int i;
/* Level 1. Always allocated. */
- lp = l1_map + ((index >> V_L1_SHIFT) & (V_L1_SIZE - 1));
+ lp = l1_map + ((index >> v_l1_shift) & (v_l1_size - 1));
/* Level 2..N-1. */
- for (i = V_L1_SHIFT / V_L2_BITS - 1; i > 0; i--) {
+ for (i = v_l2_levels; i > 0; i--) {
void **p = atomic_rcu_read(lp);
if (p == NULL) {
tb = &tcg_ctx.tb_ctx.tbs[tcg_ctx.tb_ctx.nb_tbs++];
tb->pc = pc;
tb->cflags = 0;
+ tb->invalid = false;
return tb;
}
static void page_flush_tb(void)
{
- int i;
+ int i, l1_sz = v_l1_size;
- for (i = 0; i < V_L1_SIZE; i++) {
- page_flush_tb_1(V_L1_SHIFT / V_L2_BITS - 1, l1_map + i);
+ for (i = 0; i < l1_sz; i++) {
+ page_flush_tb_1(v_l2_levels, l1_map + i);
}
}
/* flush all the translation blocks */
-/* XXX: tb_flush is currently not thread safe */
-void tb_flush(CPUState *cpu)
+static void do_tb_flush(CPUState *cpu, void *data)
{
+ unsigned tb_flush_req = (unsigned) (uintptr_t) data;
+
+ tb_lock();
+
+ /* If it's already been done on request of another CPU,
+ * just retry.
+ */
+ if (tcg_ctx.tb_ctx.tb_flush_count != tb_flush_req) {
+ goto done;
+ }
+
#if defined(DEBUG_FLUSH)
printf("qemu: flush code_size=%ld nb_tbs=%d avg_tb_size=%ld\n",
(unsigned long)(tcg_ctx.code_gen_ptr - tcg_ctx.code_gen_buffer),
> tcg_ctx.code_gen_buffer_size) {
cpu_abort(cpu, "Internal error: code buffer overflow\n");
}
- tcg_ctx.tb_ctx.nb_tbs = 0;
CPU_FOREACH(cpu) {
- memset(cpu->tb_jmp_cache, 0, sizeof(cpu->tb_jmp_cache));
- cpu->tb_flushed = true;
+ int i;
+
+ for (i = 0; i < TB_JMP_CACHE_SIZE; ++i) {
+ atomic_set(&cpu->tb_jmp_cache[i], NULL);
+ }
}
+ tcg_ctx.tb_ctx.nb_tbs = 0;
qht_reset_size(&tcg_ctx.tb_ctx.htable, CODE_GEN_HTABLE_SIZE);
page_flush_tb();
tcg_ctx.code_gen_ptr = tcg_ctx.code_gen_buffer;
/* XXX: flush processor icache at this point if cache flush is
expensive */
- tcg_ctx.tb_ctx.tb_flush_count++;
+ atomic_mb_set(&tcg_ctx.tb_ctx.tb_flush_count,
+ tcg_ctx.tb_ctx.tb_flush_count + 1);
+
+done:
+ tb_unlock();
+}
+
+void tb_flush(CPUState *cpu)
+{
+ if (tcg_enabled()) {
+ uintptr_t tb_flush_req = atomic_mb_read(&tcg_ctx.tb_ctx.tb_flush_count);
+ async_safe_run_on_cpu(cpu, do_tb_flush, (void *) tb_flush_req);
+ }
}
#ifdef DEBUG_TB_CHECK
uint32_t h;
tb_page_addr_t phys_pc;
+ atomic_set(&tb->invalid, true);
+
/* 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);
/* remove the TB from the hash list */
h = tb_jmp_cache_hash_func(tb->pc);
CPU_FOREACH(cpu) {
- if (cpu->tb_jmp_cache[h] == tb) {
- cpu->tb_jmp_cache[h] = NULL;
+ if (atomic_read(&cpu->tb_jmp_cache[h]) == tb) {
+ atomic_set(&cpu->tb_jmp_cache[h], NULL);
}
}
{
uint32_t h;
- /* add in the hash table */
- h = tb_hash_func(phys_pc, tb->pc, tb->flags);
- qht_insert(&tcg_ctx.tb_ctx.htable, tb, h);
-
/* add in the page list */
tb_alloc_page(tb, 0, phys_pc & TARGET_PAGE_MASK);
if (phys_page2 != -1) {
tb->page_addr[1] = -1;
}
+ /* add in the hash table */
+ h = tb_hash_func(phys_pc, tb->pc, tb->flags);
+ qht_insert(&tcg_ctx.tb_ctx.htable, tb, h);
+
#ifdef DEBUG_TB_CHECK
tb_page_check();
#endif
buffer_overflow:
/* flush must be done */
tb_flush(cpu);
- /* cannot fail at this point */
- tb = tb_alloc(pc);
- assert(tb != NULL);
+ mmap_unlock();
+ cpu_loop_exit(cpu);
}
gen_code_buf = tcg_ctx.code_gen_ptr;
tcg_func_start(&tcg_ctx);
+ tcg_ctx.cpu = ENV_GET_CPU(env);
gen_intermediate_code(env, tb);
+ tcg_ctx.cpu = NULL;
trace_translate_block(tb, tb->pc, tb->tc_ptr);
TB_JMP_PAGE_SIZE * sizeof(TranslationBlock *));
}
+static void print_qht_statistics(FILE *f, fprintf_function cpu_fprintf,
+ struct qht_stats hst)
+{
+ uint32_t hgram_opts;
+ size_t hgram_bins;
+ char *hgram;
+
+ if (!hst.head_buckets) {
+ return;
+ }
+ cpu_fprintf(f, "TB hash buckets %zu/%zu (%0.2f%% head buckets used)\n",
+ hst.used_head_buckets, hst.head_buckets,
+ (double)hst.used_head_buckets / hst.head_buckets * 100);
+
+ hgram_opts = QDIST_PR_BORDER | QDIST_PR_LABELS;
+ hgram_opts |= QDIST_PR_100X | QDIST_PR_PERCENT;
+ if (qdist_xmax(&hst.occupancy) - qdist_xmin(&hst.occupancy) == 1) {
+ hgram_opts |= QDIST_PR_NODECIMAL;
+ }
+ hgram = qdist_pr(&hst.occupancy, 10, hgram_opts);
+ cpu_fprintf(f, "TB hash occupancy %0.2f%% avg chain occ. Histogram: %s\n",
+ qdist_avg(&hst.occupancy) * 100, hgram);
+ g_free(hgram);
+
+ hgram_opts = QDIST_PR_BORDER | QDIST_PR_LABELS;
+ hgram_bins = qdist_xmax(&hst.chain) - qdist_xmin(&hst.chain);
+ if (hgram_bins > 10) {
+ hgram_bins = 10;
+ } else {
+ hgram_bins = 0;
+ hgram_opts |= QDIST_PR_NODECIMAL | QDIST_PR_NOBINRANGE;
+ }
+ hgram = qdist_pr(&hst.chain, hgram_bins, hgram_opts);
+ cpu_fprintf(f, "TB hash avg chain %0.3f buckets. Histogram: %s\n",
+ qdist_avg(&hst.chain), hgram);
+ g_free(hgram);
+}
+
void dump_exec_info(FILE *f, fprintf_function cpu_fprintf)
{
int i, target_code_size, max_target_code_size;
int direct_jmp_count, direct_jmp2_count, cross_page;
TranslationBlock *tb;
struct qht_stats hst;
- uint32_t hgram_opts;
- size_t hgram_bins;
- char *hgram;
target_code_size = 0;
max_target_code_size = 0;
tcg_ctx.tb_ctx.nb_tbs : 0);
qht_statistics_init(&tcg_ctx.tb_ctx.htable, &hst);
-
- cpu_fprintf(f, "TB hash buckets %zu/%zu (%0.2f%% head buckets used)\n",
- hst.used_head_buckets, hst.head_buckets,
- (double)hst.used_head_buckets / hst.head_buckets * 100);
-
- hgram_opts = QDIST_PR_BORDER | QDIST_PR_LABELS;
- hgram_opts |= QDIST_PR_100X | QDIST_PR_PERCENT;
- if (qdist_xmax(&hst.occupancy) - qdist_xmin(&hst.occupancy) == 1) {
- hgram_opts |= QDIST_PR_NODECIMAL;
- }
- hgram = qdist_pr(&hst.occupancy, 10, hgram_opts);
- cpu_fprintf(f, "TB hash occupancy %0.2f%% avg chain occ. Histogram: %s\n",
- qdist_avg(&hst.occupancy) * 100, hgram);
- g_free(hgram);
-
- hgram_opts = QDIST_PR_BORDER | QDIST_PR_LABELS;
- hgram_bins = qdist_xmax(&hst.chain) - qdist_xmin(&hst.chain);
- if (hgram_bins > 10) {
- hgram_bins = 10;
- } else {
- hgram_bins = 0;
- hgram_opts |= QDIST_PR_NODECIMAL | QDIST_PR_NOBINRANGE;
- }
- hgram = qdist_pr(&hst.chain, hgram_bins, hgram_opts);
- cpu_fprintf(f, "TB hash avg chain %0.3f buckets. Histogram: %s\n",
- qdist_avg(&hst.chain), hgram);
- g_free(hgram);
-
+ print_qht_statistics(f, cpu_fprintf, hst);
qht_statistics_destroy(&hst);
cpu_fprintf(f, "\nStatistics:\n");
- cpu_fprintf(f, "TB flush count %d\n", tcg_ctx.tb_ctx.tb_flush_count);
+ cpu_fprintf(f, "TB flush count %u\n",
+ atomic_read(&tcg_ctx.tb_ctx.tb_flush_count));
cpu_fprintf(f, "TB invalidate count %d\n",
tcg_ctx.tb_ctx.tb_phys_invalidate_count);
cpu_fprintf(f, "TLB flush count %d\n", tlb_flush_count);
int walk_memory_regions(void *priv, walk_memory_regions_fn fn)
{
struct walk_memory_regions_data data;
- uintptr_t i;
+ uintptr_t i, l1_sz = v_l1_size;
data.fn = fn;
data.priv = priv;
data.start = -1u;
data.prot = 0;
- for (i = 0; i < V_L1_SIZE; i++) {
- int rc = walk_memory_regions_1(&data, (target_ulong)i << (V_L1_SHIFT + TARGET_PAGE_BITS),
- V_L1_SHIFT / V_L2_BITS - 1, l1_map + i);
+ for (i = 0; i < l1_sz; i++) {
+ target_ulong base = i << (v_l1_shift + TARGET_PAGE_BITS);
+ int rc = walk_memory_regions_1(&data, base, v_l2_levels, l1_map + i);
if (rc != 0) {
return rc;
}
int page_unprotect(target_ulong address, uintptr_t pc)
{
unsigned int prot;
+ bool current_tb_invalidated;
PageDesc *p;
target_ulong host_start, host_end, addr;
host_end = host_start + qemu_host_page_size;
prot = 0;
+ current_tb_invalidated = false;
for (addr = host_start ; addr < host_end ; addr += TARGET_PAGE_SIZE) {
p = page_find(addr >> TARGET_PAGE_BITS);
p->flags |= PAGE_WRITE;
/* and since the content will be modified, we must invalidate
the corresponding translated code. */
- if (tb_invalidate_phys_page(addr, pc)) {
- mmap_unlock();
- return 2;
- }
+ current_tb_invalidated |= tb_invalidate_phys_page(addr, pc);
#ifdef DEBUG_TB_CHECK
tb_invalidate_check(addr);
#endif
prot & PAGE_BITS);
mmap_unlock();
- return 1;
+ /* If current TB was invalidated return to main loop */
+ return current_tb_invalidated ? 2 : 1;
}
mmap_unlock();
return 0;
projects / mirror_qemu.git / blobdiff