@@ -148,9 +148,14 @@ typedef enum {
#define TCG_TARGET_DEFAULT_MO (0)
#define TCG_TARGET_HAS_MEMORY_BSWAP 1
-static inline void flush_icache_range(uintptr_t start, uintptr_t stop)
+/* Flush the dcache at RW, and the icache at RX, as necessary. */
+static inline void flush_idcache_range(uintptr_t rx, uintptr_t rw, size_t len)
{
- __builtin___clear_cache((char *)start, (char *)stop);
+ /* TODO: Copy this from gcc to avoid 4 loops instead of 2. */
+ if (rw != rx) {
+ __builtin___clear_cache((char *)rw, (char *)(rw + len));
+ }
+ __builtin___clear_cache((char *)rx, (char *)(rx + len));
}
void tb_target_set_jmp_target(uintptr_t, uintptr_t, uintptr_t);
@@ -134,9 +134,13 @@ enum {
#define TCG_TARGET_DEFAULT_MO (0)
#define TCG_TARGET_HAS_MEMORY_BSWAP 1
-static inline void flush_icache_range(uintptr_t start, uintptr_t stop)
+/* Flush the dcache at RW, and the icache at RX, as necessary. */
+static inline void flush_idcache_range(uintptr_t rx, uintptr_t rw, size_t len)
{
- __builtin___clear_cache((char *) start, (char *) stop);
+ if (rw != rx) {
+ __builtin___clear_cache((char *)rw, (char *)(rw + len));
+ }
+ __builtin___clear_cache((char *)rx, (char *)(rx + len));
}
/* not defined -- call should be eliminated at compile time */
@@ -206,7 +206,8 @@ extern bool have_avx2;
#define TCG_TARGET_extract_i64_valid(ofs, len) \
(((ofs) == 8 && (len) == 8) || ((ofs) + (len)) == 32)
-static inline void flush_icache_range(uintptr_t start, uintptr_t stop)
+/* Flush the dcache at RW, and the icache at RX, as necessary. */
+static inline void flush_idcache_range(uintptr_t rx, uintptr_t rw, size_t len)
{
}
@@ -207,9 +207,13 @@ extern bool use_mips32r2_instructions;
#define TCG_TARGET_DEFAULT_MO (0)
#define TCG_TARGET_HAS_MEMORY_BSWAP 1
-static inline void flush_icache_range(uintptr_t start, uintptr_t stop)
+/* Flush the dcache at RW, and the icache at RX, as necessary. */
+static inline void flush_idcache_range(uintptr_t rx, uintptr_t rw, size_t len)
{
- cacheflush ((void *)start, stop-start, ICACHE);
+ if (rx != rw) {
+ cacheflush((void *)rw, len, DCACHE);
+ }
+ cacheflush((void *)rx, len, ICACHE);
}
void tb_target_set_jmp_target(uintptr_t, uintptr_t, uintptr_t);
@@ -175,7 +175,7 @@ extern bool have_vsx;
#define TCG_TARGET_HAS_bitsel_vec have_vsx
#define TCG_TARGET_HAS_cmpsel_vec 0
-void flush_icache_range(uintptr_t start, uintptr_t stop);
+void flush_idcache_range(uintptr_t rx, uintptr_t rw, size_t len);
void tb_target_set_jmp_target(uintptr_t, uintptr_t, uintptr_t);
#define TCG_TARGET_DEFAULT_MO (0)
@@ -159,9 +159,13 @@ typedef enum {
#define TCG_TARGET_HAS_mulsh_i64 1
#endif
-static inline void flush_icache_range(uintptr_t start, uintptr_t stop)
+/* Flush the dcache at RW, and the icache at RX, as necessary. */
+static inline void flush_idcache_range(uintptr_t rx, uintptr_t rw, size_t len)
{
- __builtin___clear_cache((char *)start, (char *)stop);
+ if (rx != rw) {
+ __builtin___clear_cache((char *)rw, (char *)(rw + len));
+ }
+ __builtin___clear_cache((char *)rx, (char *)(rx + len));
}
/* not defined -- call should be eliminated at compile time */
@@ -145,7 +145,8 @@ enum {
TCG_AREG0 = TCG_REG_R10,
};
-static inline void flush_icache_range(uintptr_t start, uintptr_t stop)
+/* Flush the dcache at RW, and the icache at RX, as necessary. */
+static inline void flush_idcache_range(uintptr_t rx, uintptr_t rw, size_t len)
{
}
@@ -168,10 +168,12 @@ extern bool use_vis3_instructions;
#define TCG_TARGET_DEFAULT_MO (0)
#define TCG_TARGET_HAS_MEMORY_BSWAP 1
-static inline void flush_icache_range(uintptr_t start, uintptr_t stop)
+/* Flush the dcache at RW, and the icache at RX, as necessary. */
+static inline void flush_idcache_range(uintptr_t rx, uintptr_t rw, size_t len)
{
- uintptr_t p;
- for (p = start & -8; p < ((stop + 7) & -8); p += 8) {
+ /* No additional data flush to the RW virtual address required. */
+ uintptr_t p, end = (rx + len + 7) & -8;
+ for (p = rx & -8; p < end; p += 8) {
__asm__ __volatile__("flush\t%0" : : "r" (p));
}
}
@@ -191,7 +191,8 @@ void tci_disas(uint8_t opc);
#define HAVE_TCG_QEMU_TB_EXEC
-static inline void flush_icache_range(uintptr_t start, uintptr_t stop)
+/* Flush the dcache at RW, and the icache at RX, as necessary. */
+static inline void flush_idcache_range(uintptr_t rx, uintptr_t rw, size_t len)
{
}
@@ -2946,7 +2946,14 @@ static inline MemTxResult address_space_write_rom_internal(AddressSpace *as,
invalidate_and_set_dirty(mr, addr1, l);
break;
case FLUSH_CACHE:
- flush_icache_range((uintptr_t)ram_ptr, (uintptr_t)ram_ptr + l);
+ /*
+ * FIXME: This function is currently located in tcg/host/,
+ * but we never come here when tcg is enabled; only for
+ * real hardware acceleration. This can actively fail
+ * when TCI is configured, since that function is a nop.
+ * We should move this to util/ or something.
+ */
+ flush_idcache_range((uintptr_t)ram_ptr, (uintptr_t)ram_ptr, l);
break;
}
}
@@ -1077,7 +1077,8 @@ void tcg_prologue_init(TCGContext *s)
#endif
buf1 = s->code_ptr;
- flush_icache_range((uintptr_t)buf0, (uintptr_t)buf1);
+ flush_idcache_range((uintptr_t)buf0, (uintptr_t)buf0,
+ tcg_ptr_byte_diff(buf1, buf0));
/* Deduct the prologue from the buffer. */
prologue_size = tcg_current_code_size(s);
@@ -4320,7 +4321,8 @@ int tcg_gen_code(TCGContext *s, TranslationBlock *tb)
}
/* flush instruction cache */
- flush_icache_range((uintptr_t)s->code_buf, (uintptr_t)s->code_ptr);
+ flush_idcache_range((uintptr_t)s->code_buf, (uintptr_t)s->code_buf,
+ tcg_ptr_byte_diff(s->code_ptr, s->code_buf));
return tcg_current_code_size(s);
}
@@ -1363,7 +1363,7 @@ void tb_target_set_jmp_target(uintptr_t tc_ptr, uintptr_t jmp_addr,
}
pair = (uint64_t)i2 << 32 | i1;
qatomic_set((uint64_t *)jmp_addr, pair);
- flush_icache_range(jmp_addr, jmp_addr + 8);
+ flush_idcache_range(jmp_addr, jmp_addr, 8);
}
static inline void tcg_out_goto_label(TCGContext *s, TCGLabel *l)
@@ -2660,7 +2660,7 @@ void tb_target_set_jmp_target(uintptr_t tc_ptr, uintptr_t jmp_addr,
uintptr_t addr)
{
qatomic_set((uint32_t *)jmp_addr, deposit32(OPC_J, 0, 26, addr >> 2));
- flush_icache_range(jmp_addr, jmp_addr + 4);
+ flush_idcache_range(jmp_addr, jmp_addr, 4);
}
typedef struct {
@@ -1753,12 +1753,12 @@ void tb_target_set_jmp_target(uintptr_t tc_ptr, uintptr_t jmp_addr,
/* As per the enclosing if, this is ppc64. Avoid the _Static_assert
within qatomic_set that would fail to build a ppc32 host. */
qatomic_set__nocheck((uint64_t *)jmp_addr, pair);
- flush_icache_range(jmp_addr, jmp_addr + 8);
+ flush_idcache_range(jmp_addr, jmp_addr, 8);
} else {
intptr_t diff = addr - jmp_addr;
tcg_debug_assert(in_range_b(diff));
qatomic_set((uint32_t *)jmp_addr, B | (diff & 0x3fffffc));
- flush_icache_range(jmp_addr, jmp_addr + 4);
+ flush_idcache_range(jmp_addr, jmp_addr, 4);
}
}
@@ -3864,22 +3864,23 @@ void tcg_register_jit(void *buf, size_t buf_size)
}
#endif /* __ELF__ */
-void flush_icache_range(uintptr_t start, uintptr_t stop)
+/* Flush the dcache at RW, and the icache at RX, as necessary. */
+void flush_idcache_range(uintptr_t rx, uintptr_t rw, uintptr_t len)
{
- uintptr_t p, start1, stop1;
+ uintptr_t p, start, stop;
size_t dsize = qemu_dcache_linesize;
size_t isize = qemu_icache_linesize;
- start1 = start & ~(dsize - 1);
- stop1 = (stop + dsize - 1) & ~(dsize - 1);
- for (p = start1; p < stop1; p += dsize) {
+ start = rw & ~(dsize - 1);
+ stop = (rw + len + dsize - 1) & ~(dsize - 1);
+ for (p = start; p < stop; p += dsize) {
asm volatile ("dcbst 0,%0" : : "r"(p) : "memory");
}
asm volatile ("sync" : : : "memory");
- start &= start & ~(isize - 1);
- stop1 = (stop + isize - 1) & ~(isize - 1);
- for (p = start1; p < stop1; p += isize) {
+ start = rx & ~(isize - 1);
+ stop = (rx + len + isize - 1) & ~(isize - 1);
+ for (p = start; p < stop; p += isize) {
asm volatile ("icbi 0,%0" : : "r"(p) : "memory");
}
asm volatile ("sync" : : : "memory");
@@ -1836,7 +1836,7 @@ void tb_target_set_jmp_target(uintptr_t tc_ptr, uintptr_t jmp_addr,
if (!USE_REG_TB) {
qatomic_set((uint32_t *)jmp_addr,
deposit32(CALL, 0, 30, br_disp >> 2));
- flush_icache_range(jmp_addr, jmp_addr + 4);
+ flush_idcache_range(jmp_addr, jmp_addr, 4);
return;
}
@@ -1860,5 +1860,5 @@ void tb_target_set_jmp_target(uintptr_t tc_ptr, uintptr_t jmp_addr,
}
qatomic_set((uint64_t *)jmp_addr, deposit64(i2, 32, 32, i1));
- flush_icache_range(jmp_addr, jmp_addr + 8);
+ flush_idcache_range(jmp_addr, jmp_addr, 8);
}
We are shortly going to have a split rw/rx jit buffer. Depending on the host, we need to flush the dcache at the rw data pointer and flush the icache at the rx code pointer. For now, the two passed pointers are identical, so there is no effective change in behaviour. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/aarch64/tcg-target.h | 9 +++++++-- tcg/arm/tcg-target.h | 8 ++++++-- tcg/i386/tcg-target.h | 3 ++- tcg/mips/tcg-target.h | 8 ++++++-- tcg/ppc/tcg-target.h | 2 +- tcg/riscv/tcg-target.h | 8 ++++++-- tcg/s390/tcg-target.h | 3 ++- tcg/sparc/tcg-target.h | 8 +++++--- tcg/tci/tcg-target.h | 3 ++- softmmu/physmem.c | 9 ++++++++- tcg/tcg.c | 6 ++++-- tcg/aarch64/tcg-target.c.inc | 2 +- tcg/mips/tcg-target.c.inc | 2 +- tcg/ppc/tcg-target.c.inc | 21 +++++++++++---------- tcg/sparc/tcg-target.c.inc | 4 ++-- 15 files changed, 64 insertions(+), 32 deletions(-)