[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-devel] [RFC 1/6] (XXX) cputlb: separate MMU allocation + run-time
From: |
Emilio G. Cota |
Subject: |
[Qemu-devel] [RFC 1/6] (XXX) cputlb: separate MMU allocation + run-time sizing |
Date: |
Sat, 6 Oct 2018 17:45:03 -0400 |
No dynamic sizing yet, but the indirection is there.
XXX:
- convert other TCG backends
Signed-off-by: Emilio G. Cota <address@hidden>
---
accel/tcg/softmmu_template.h | 14 +++++----
include/exec/cpu-defs.h | 14 ++++++---
include/exec/cpu_ldst.h | 2 +-
include/exec/cpu_ldst_template.h | 6 ++--
accel/tcg/cputlb.c | 49 +++++++++++++++++++++-----------
tcg/i386/tcg-target.inc.c | 26 ++++++++---------
6 files changed, 68 insertions(+), 43 deletions(-)
diff --git a/accel/tcg/softmmu_template.h b/accel/tcg/softmmu_template.h
index 1e50263871..3f5a0d4017 100644
--- a/accel/tcg/softmmu_template.h
+++ b/accel/tcg/softmmu_template.h
@@ -112,7 +112,7 @@ WORD_TYPE helper_le_ld_name(CPUArchState *env, target_ulong
addr,
TCGMemOpIdx oi, uintptr_t retaddr)
{
unsigned mmu_idx = get_mmuidx(oi);
- int index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
+ int index = (addr >> TARGET_PAGE_BITS) & (env->tlb_desc[mmu_idx].size - 1);
target_ulong tlb_addr = env->tlb_table[mmu_idx][index].ADDR_READ;
unsigned a_bits = get_alignment_bits(get_memop(oi));
uintptr_t haddr;
@@ -180,7 +180,7 @@ WORD_TYPE helper_be_ld_name(CPUArchState *env, target_ulong
addr,
TCGMemOpIdx oi, uintptr_t retaddr)
{
unsigned mmu_idx = get_mmuidx(oi);
- int index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
+ int index = (addr >> TARGET_PAGE_BITS) & (env->tlb_desc[mmu_idx].size - 1);
target_ulong tlb_addr = env->tlb_table[mmu_idx][index].ADDR_READ;
unsigned a_bits = get_alignment_bits(get_memop(oi));
uintptr_t haddr;
@@ -276,7 +276,7 @@ void helper_le_st_name(CPUArchState *env, target_ulong
addr, DATA_TYPE val,
TCGMemOpIdx oi, uintptr_t retaddr)
{
unsigned mmu_idx = get_mmuidx(oi);
- int index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
+ int index = (addr >> TARGET_PAGE_BITS) & (env->tlb_desc[mmu_idx].size - 1);
target_ulong tlb_addr =
atomic_read(&env->tlb_table[mmu_idx][index].addr_write);
unsigned a_bits = get_alignment_bits(get_memop(oi));
@@ -322,7 +322,8 @@ void helper_le_st_name(CPUArchState *env, target_ulong
addr, DATA_TYPE val,
is already guaranteed to be filled, and that the second page
cannot evict the first. */
page2 = (addr + DATA_SIZE) & TARGET_PAGE_MASK;
- index2 = (page2 >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
+ index2 = (page2 >> TARGET_PAGE_BITS) &
+ (env->tlb_desc[mmu_idx].size - 1);
tlb_addr2 = atomic_read(&env->tlb_table[mmu_idx][index2].addr_write);
if (!tlb_hit_page(tlb_addr2, page2)
&& !VICTIM_TLB_HIT(addr_write, page2)) {
@@ -355,7 +356,7 @@ void helper_be_st_name(CPUArchState *env, target_ulong
addr, DATA_TYPE val,
TCGMemOpIdx oi, uintptr_t retaddr)
{
unsigned mmu_idx = get_mmuidx(oi);
- int index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
+ int index = (addr >> TARGET_PAGE_BITS) & (env->tlb_desc[mmu_idx].size - 1);
target_ulong tlb_addr =
atomic_read(&env->tlb_table[mmu_idx][index].addr_write);
unsigned a_bits = get_alignment_bits(get_memop(oi));
@@ -401,7 +402,8 @@ void helper_be_st_name(CPUArchState *env, target_ulong
addr, DATA_TYPE val,
is already guaranteed to be filled, and that the second page
cannot evict the first. */
page2 = (addr + DATA_SIZE) & TARGET_PAGE_MASK;
- index2 = (page2 >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
+ index2 = (page2 >> TARGET_PAGE_BITS) &
+ (env->tlb_desc[mmu_idx].size - 1);
tlb_addr2 = atomic_read(&env->tlb_table[mmu_idx][index2].addr_write);
if (!tlb_hit_page(tlb_addr2, page2)
&& !VICTIM_TLB_HIT(addr_write, page2)) {
diff --git a/include/exec/cpu-defs.h b/include/exec/cpu-defs.h
index 4ff62f32bf..fa95a4257e 100644
--- a/include/exec/cpu-defs.h
+++ b/include/exec/cpu-defs.h
@@ -141,13 +141,19 @@ typedef struct CPUIOTLBEntry {
MemTxAttrs attrs;
} CPUIOTLBEntry;
-#define CPU_COMMON_TLB \
+typedef struct CPUTLBDesc {
+ size_t size;
+ size_t mask; /* (.size - 1) << CPU_TLB_ENTRY_BITS for TLB fast path */
+} CPUTLBDesc;
+
+#define CPU_COMMON_TLB \
/* The meaning of the MMU modes is defined in the target code. */ \
- /* tlb_lock serializes updates to tlb_table and tlb_v_table */ \
+ /* tlb_lock serializes updates to tlb_desc, tlb_table and tlb_v_table */ \
QemuSpin tlb_lock; \
- CPUTLBEntry tlb_table[NB_MMU_MODES][CPU_TLB_SIZE]; \
+ CPUTLBDesc tlb_desc[NB_MMU_MODES]; \
+ CPUTLBEntry *tlb_table[NB_MMU_MODES]; \
CPUTLBEntry tlb_v_table[NB_MMU_MODES][CPU_VTLB_SIZE]; \
- CPUIOTLBEntry iotlb[NB_MMU_MODES][CPU_TLB_SIZE]; \
+ CPUIOTLBEntry *iotlb[NB_MMU_MODES]; \
CPUIOTLBEntry iotlb_v[NB_MMU_MODES][CPU_VTLB_SIZE]; \
size_t tlb_flush_count; \
target_ulong tlb_flush_addr; \
diff --git a/include/exec/cpu_ldst.h b/include/exec/cpu_ldst.h
index 9581587ce1..df452f5977 100644
--- a/include/exec/cpu_ldst.h
+++ b/include/exec/cpu_ldst.h
@@ -416,7 +416,7 @@ static inline void *tlb_vaddr_to_host(CPUArchState *env,
abi_ptr addr,
#if defined(CONFIG_USER_ONLY)
return g2h(addr);
#else
- int index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
+ int index = (addr >> TARGET_PAGE_BITS) & (env->tlb_desc[mmu_idx].size - 1);
CPUTLBEntry *tlbentry = &env->tlb_table[mmu_idx][index];
abi_ptr tlb_addr;
uintptr_t haddr;
diff --git a/include/exec/cpu_ldst_template.h b/include/exec/cpu_ldst_template.h
index ba7a11123c..6ab9909f46 100644
--- a/include/exec/cpu_ldst_template.h
+++ b/include/exec/cpu_ldst_template.h
@@ -94,8 +94,8 @@ glue(glue(glue(cpu_ld, USUFFIX), MEMSUFFIX),
_ra)(CPUArchState *env,
#endif
addr = ptr;
- page_index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
mmu_idx = CPU_MMU_INDEX;
+ page_index = (addr >> TARGET_PAGE_BITS) & (env->tlb_desc[mmu_idx].size -
1);
if (unlikely(env->tlb_table[mmu_idx][page_index].ADDR_READ !=
(addr & (TARGET_PAGE_MASK | (DATA_SIZE - 1))))) {
oi = make_memop_idx(SHIFT, mmu_idx);
@@ -132,8 +132,8 @@ glue(glue(glue(cpu_lds, SUFFIX), MEMSUFFIX),
_ra)(CPUArchState *env,
#endif
addr = ptr;
- page_index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
mmu_idx = CPU_MMU_INDEX;
+ page_index = (addr >> TARGET_PAGE_BITS) & (env->tlb_desc[mmu_idx].size -
1);
if (unlikely(env->tlb_table[mmu_idx][page_index].ADDR_READ !=
(addr & (TARGET_PAGE_MASK | (DATA_SIZE - 1))))) {
oi = make_memop_idx(SHIFT, mmu_idx);
@@ -174,8 +174,8 @@ glue(glue(glue(cpu_st, SUFFIX), MEMSUFFIX),
_ra)(CPUArchState *env,
#endif
addr = ptr;
- page_index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
mmu_idx = CPU_MMU_INDEX;
+ page_index = (addr >> TARGET_PAGE_BITS) & (env->tlb_desc[mmu_idx].size -
1);
if (unlikely(atomic_read(&env->tlb_table[mmu_idx][page_index].addr_write)
!=
(addr & (TARGET_PAGE_MASK | (DATA_SIZE - 1))))) {
oi = make_memop_idx(SHIFT, mmu_idx);
diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c
index c7608ccdf8..0b51efc374 100644
--- a/accel/tcg/cputlb.c
+++ b/accel/tcg/cputlb.c
@@ -76,8 +76,17 @@ QEMU_BUILD_BUG_ON(NB_MMU_MODES > 16);
void tlb_init(CPUState *cpu)
{
CPUArchState *env = cpu->env_ptr;
+ int i;
qemu_spin_init(&env->tlb_lock);
+ for (i = 0; i < NB_MMU_MODES; i++) {
+ CPUTLBDesc *desc = &env->tlb_desc[i];
+
+ desc->size = CPU_TLB_SIZE;
+ desc->mask = (desc->size - 1) << CPU_TLB_ENTRY_BITS;
+ env->tlb_table[i] = g_new(CPUTLBEntry, desc->size);
+ env->iotlb[i] = g_new0(CPUIOTLBEntry, desc->size);
+ }
}
/* flush_all_helper: run fn across all cpus
@@ -120,6 +129,7 @@ size_t tlb_flush_count(void)
static void tlb_flush_nocheck(CPUState *cpu)
{
CPUArchState *env = cpu->env_ptr;
+ int i;
/* The QOM tests will trigger tlb_flushes without setting up TCG
* so we bug out here in that case.
@@ -139,7 +149,10 @@ static void tlb_flush_nocheck(CPUState *cpu)
* that do not hold the lock are performed by the same owner thread.
*/
qemu_spin_lock(&env->tlb_lock);
- memset(env->tlb_table, -1, sizeof(env->tlb_table));
+ for (i = 0; i < NB_MMU_MODES; i++) {
+ memset(env->tlb_table[i], -1,
+ env->tlb_desc[i].size * sizeof(CPUTLBEntry));
+ }
memset(env->tlb_v_table, -1, sizeof(env->tlb_v_table));
qemu_spin_unlock(&env->tlb_lock);
@@ -200,7 +213,8 @@ static void tlb_flush_by_mmuidx_async_work(CPUState *cpu,
run_on_cpu_data data)
if (test_bit(mmu_idx, &mmu_idx_bitmask)) {
tlb_debug("%d\n", mmu_idx);
- memset(env->tlb_table[mmu_idx], -1, sizeof(env->tlb_table[0]));
+ memset(env->tlb_table[mmu_idx], -1,
+ env->tlb_desc[mmu_idx].size * sizeof(CPUTLBEntry));
memset(env->tlb_v_table[mmu_idx], -1, sizeof(env->tlb_v_table[0]));
}
}
@@ -286,7 +300,6 @@ static void tlb_flush_page_async_work(CPUState *cpu,
run_on_cpu_data data)
{
CPUArchState *env = cpu->env_ptr;
target_ulong addr = (target_ulong) data.target_ptr;
- int i;
int mmu_idx;
assert_cpu_is_self(cpu);
@@ -304,9 +317,10 @@ static void tlb_flush_page_async_work(CPUState *cpu,
run_on_cpu_data data)
}
addr &= TARGET_PAGE_MASK;
- i = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
qemu_spin_lock(&env->tlb_lock);
for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) {
+ int i = (addr >> TARGET_PAGE_BITS) & (env->tlb_desc[mmu_idx].size - 1);
+
tlb_flush_entry_locked(&env->tlb_table[mmu_idx][i], addr);
tlb_flush_vtlb_page_locked(env, mmu_idx, addr);
}
@@ -339,16 +353,17 @@ static void tlb_flush_page_by_mmuidx_async_work(CPUState
*cpu,
target_ulong addr_and_mmuidx = (target_ulong) data.target_ptr;
target_ulong addr = addr_and_mmuidx & TARGET_PAGE_MASK;
unsigned long mmu_idx_bitmap = addr_and_mmuidx & ALL_MMUIDX_BITS;
- int page = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
int mmu_idx;
assert_cpu_is_self(cpu);
- tlb_debug("page:%d addr:"TARGET_FMT_lx" mmu_idx:0x%lx\n",
- page, addr, mmu_idx_bitmap);
+ tlb_debug("addr: "TARGET_FMT_lx" mmu_idx:0x%lx\n", addr, mmu_idx_bitmap);
qemu_spin_lock(&env->tlb_lock);
for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) {
+ int page;
+
+ page = (addr >> TARGET_PAGE_BITS) & (env->tlb_desc[mmu_idx].size - 1);
if (test_bit(mmu_idx, &mmu_idx_bitmap)) {
tlb_flush_entry_locked(&env->tlb_table[mmu_idx][page], addr);
tlb_flush_vtlb_page_locked(env, mmu_idx, addr);
@@ -524,7 +539,7 @@ void tlb_reset_dirty(CPUState *cpu, ram_addr_t start1,
ram_addr_t length)
for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) {
unsigned int i;
- for (i = 0; i < CPU_TLB_SIZE; i++) {
+ for (i = 0; i < env->tlb_desc[mmu_idx].size; i++) {
tlb_reset_dirty_range_locked(&env->tlb_table[mmu_idx][i], start1,
length);
}
@@ -551,15 +566,15 @@ static inline void tlb_set_dirty1_locked(CPUTLBEntry
*tlb_entry,
void tlb_set_dirty(CPUState *cpu, target_ulong vaddr)
{
CPUArchState *env = cpu->env_ptr;
- int i;
int mmu_idx;
assert_cpu_is_self(cpu);
vaddr &= TARGET_PAGE_MASK;
- i = (vaddr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
qemu_spin_lock(&env->tlb_lock);
for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) {
+ int i = (vaddr >> TARGET_PAGE_BITS) & (env->tlb_desc[mmu_idx].size -
1);
+
tlb_set_dirty1_locked(&env->tlb_table[mmu_idx][i], vaddr);
}
@@ -660,7 +675,8 @@ void tlb_set_page_with_attrs(CPUState *cpu, target_ulong
vaddr,
iotlb = memory_region_section_get_iotlb(cpu, section, vaddr_page,
paddr_page, xlat, prot, &address);
- index = (vaddr_page >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
+ index = (vaddr_page >> TARGET_PAGE_BITS) &
+ (env->tlb_desc[mmu_idx].size - 1);
te = &env->tlb_table[mmu_idx][index];
/*
@@ -788,7 +804,7 @@ static uint64_t io_readx(CPUArchState *env, CPUIOTLBEntry
*iotlbentry,
tlb_fill(cpu, addr, size, MMU_DATA_LOAD, mmu_idx, retaddr);
- index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
+ index = (addr >> TARGET_PAGE_BITS) & (env->tlb_desc[mmu_idx].size - 1);
tlb_addr = env->tlb_table[mmu_idx][index].addr_read;
if (!(tlb_addr & ~(TARGET_PAGE_MASK | TLB_RECHECK))) {
/* RAM access */
@@ -855,7 +871,7 @@ static void io_writex(CPUArchState *env, CPUIOTLBEntry
*iotlbentry,
tlb_fill(cpu, addr, size, MMU_DATA_STORE, mmu_idx, retaddr);
- index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
+ index = (addr >> TARGET_PAGE_BITS) & (env->tlb_desc[mmu_idx].size - 1);
tlb_addr = atomic_read(&env->tlb_table[mmu_idx][index].addr_write);
if (!(tlb_addr & ~(TARGET_PAGE_MASK | TLB_RECHECK))) {
/* RAM access */
@@ -943,8 +959,8 @@ tb_page_addr_t get_page_addr_code(CPUArchState *env,
target_ulong addr)
int mmu_idx, index;
void *p;
- index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
mmu_idx = cpu_mmu_index(env, true);
+ index = (addr >> TARGET_PAGE_BITS) & (env->tlb_desc[mmu_idx].size - 1);
if (unlikely(!tlb_hit(env->tlb_table[mmu_idx][index].addr_code, addr))) {
if (!VICTIM_TLB_HIT(addr_code, addr)) {
tlb_fill(ENV_GET_CPU(env), addr, 0, MMU_INST_FETCH, mmu_idx, 0);
@@ -978,7 +994,7 @@ tb_page_addr_t get_page_addr_code(CPUArchState *env,
target_ulong addr)
void probe_write(CPUArchState *env, target_ulong addr, int size, int mmu_idx,
uintptr_t retaddr)
{
- int index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
+ int index = (addr >> TARGET_PAGE_BITS) & (env->tlb_desc[mmu_idx].size - 1);
target_ulong tlb_addr =
atomic_read(&env->tlb_table[mmu_idx][index].addr_write);
@@ -998,7 +1014,8 @@ static void *atomic_mmu_lookup(CPUArchState *env,
target_ulong addr,
NotDirtyInfo *ndi)
{
size_t mmu_idx = get_mmuidx(oi);
- size_t index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
+ size_t index = (addr >> TARGET_PAGE_BITS) &
+ (env->tlb_desc[mmu_idx].size - 1);
CPUTLBEntry *tlbe = &env->tlb_table[mmu_idx][index];
target_ulong tlb_addr = atomic_read(&tlbe->addr_write);
TCGMemOp mop = get_memop(oi);
diff --git a/tcg/i386/tcg-target.inc.c b/tcg/i386/tcg-target.inc.c
index 436195894b..fce6a94e22 100644
--- a/tcg/i386/tcg-target.inc.c
+++ b/tcg/i386/tcg-target.inc.c
@@ -330,6 +330,7 @@ static inline int tcg_target_const_match(tcg_target_long
val, TCGType type,
#define OPC_ARITH_GvEv (0x03) /* ... plus (ARITH_FOO << 3) */
#define OPC_ANDN (0xf2 | P_EXT38)
#define OPC_ADD_GvEv (OPC_ARITH_GvEv | (ARITH_ADD << 3))
+#define OPC_AND_GvEv (OPC_ARITH_GvEv | (ARITH_AND << 3))
#define OPC_BLENDPS (0x0c | P_EXT3A | P_DATA16)
#define OPC_BSF (0xbc | P_EXT)
#define OPC_BSR (0xbd | P_EXT)
@@ -1633,6 +1634,15 @@ static inline void tcg_out_tlb_load(TCGContext *s,
TCGReg addrlo, TCGReg addrhi,
}
tcg_out_mov(s, tlbtype, r0, addrlo);
+ tcg_out_shifti(s, SHIFT_SHR + tlbrexw, r0,
+ TARGET_PAGE_BITS - CPU_TLB_ENTRY_BITS);
+
+ tcg_out_modrm_offset(s, OPC_AND_GvEv + trexw, r0, TCG_AREG0,
+ offsetof(CPUArchState, tlb_desc[mem_index].mask));
+
+ tcg_out_modrm_offset(s, OPC_ADD_GvEv + hrexw, r0, TCG_AREG0,
+ offsetof(CPUArchState, tlb_table[mem_index]));
+
/* If the required alignment is at least as large as the access, simply
copy the address and mask. For lesser alignments, check that we don't
cross pages for the complete access. */
@@ -1642,20 +1652,10 @@ static inline void tcg_out_tlb_load(TCGContext *s,
TCGReg addrlo, TCGReg addrhi,
tcg_out_modrm_offset(s, OPC_LEA + trexw, r1, addrlo, s_mask - a_mask);
}
tlb_mask = (target_ulong)TARGET_PAGE_MASK | a_mask;
-
- tcg_out_shifti(s, SHIFT_SHR + tlbrexw, r0,
- TARGET_PAGE_BITS - CPU_TLB_ENTRY_BITS);
-
tgen_arithi(s, ARITH_AND + trexw, r1, tlb_mask, 0);
- tgen_arithi(s, ARITH_AND + tlbrexw, r0,
- (CPU_TLB_SIZE - 1) << CPU_TLB_ENTRY_BITS, 0);
-
- tcg_out_modrm_sib_offset(s, OPC_LEA + hrexw, r0, TCG_AREG0, r0, 0,
- offsetof(CPUArchState, tlb_table[mem_index][0])
- + which);
/* cmp 0(r0), r1 */
- tcg_out_modrm_offset(s, OPC_CMP_GvEv + trexw, r1, r0, 0);
+ tcg_out_modrm_offset(s, OPC_CMP_GvEv + trexw, r1, r0, which);
/* Prepare for both the fast path add of the tlb addend, and the slow
path function argument setup. There are two cases worth note:
@@ -1672,7 +1672,7 @@ static inline void tcg_out_tlb_load(TCGContext *s, TCGReg
addrlo, TCGReg addrhi,
if (TARGET_LONG_BITS > TCG_TARGET_REG_BITS) {
/* cmp 4(r0), addrhi */
- tcg_out_modrm_offset(s, OPC_CMP_GvEv, addrhi, r0, 4);
+ tcg_out_modrm_offset(s, OPC_CMP_GvEv, addrhi, r0, which + 4);
/* jne slow_path */
tcg_out_opc(s, OPC_JCC_long + JCC_JNE, 0, 0, 0);
@@ -1684,7 +1684,7 @@ static inline void tcg_out_tlb_load(TCGContext *s, TCGReg
addrlo, TCGReg addrhi,
/* add addend(r0), r1 */
tcg_out_modrm_offset(s, OPC_ADD_GvEv + hrexw, r1, r0,
- offsetof(CPUTLBEntry, addend) - which);
+ offsetof(CPUTLBEntry, addend));
}
/*
--
2.17.1
[Qemu-devel] [RFC 1/6] (XXX) cputlb: separate MMU allocation + run-time sizing,
Emilio G. Cota <=