#define TCG_H
#include "qemu-common.h"
+#include "cpu.h"
+#include "exec/tb-context.h"
#include "qemu/bitops.h"
#include "tcg-target.h"
+/* XXX: make safe guess about sizes */
+#define MAX_OP_PER_INSTR 266
+
+#if HOST_LONG_BITS == 32
+#define MAX_OPC_PARAM_PER_ARG 2
+#else
+#define MAX_OPC_PARAM_PER_ARG 1
+#endif
+#define MAX_OPC_PARAM_IARGS 5
+#define MAX_OPC_PARAM_OARGS 1
+#define MAX_OPC_PARAM_ARGS (MAX_OPC_PARAM_IARGS + MAX_OPC_PARAM_OARGS)
+
+/* A Call op needs up to 4 + 2N parameters on 32-bit archs,
+ * and up to 4 + N parameters on 64-bit archs
+ * (N = number of input arguments + output arguments). */
+#define MAX_OPC_PARAM (4 + (MAX_OPC_PARAM_PER_ARG * MAX_OPC_PARAM_ARGS))
+#define OPC_BUF_SIZE 640
+#define OPC_MAX_SIZE (OPC_BUF_SIZE - MAX_OP_PER_INSTR)
+
+#define OPPARAM_BUF_SIZE (OPC_BUF_SIZE * MAX_OPC_PARAM)
+
#define CPU_TEMP_BUF_NLONGS 128
/* Default target word size to pointer size. */
#endif
+#if defined CONFIG_DEBUG_TCG || defined QEMU_STATIC_ANALYSIS
+# define tcg_debug_assert(X) do { assert(X); } while (0)
+#elif QEMU_GNUC_PREREQ(4, 5)
+# define tcg_debug_assert(X) \
+ do { if (!(X)) { __builtin_unreachable(); } } while (0)
+#else
+# define tcg_debug_assert(X) do { (void)(X); } while (0)
+#endif
+
typedef struct TCGRelocation {
struct TCGRelocation *next;
int type;
#endif
/* MO_UNALN accesses are never checked for alignment.
- MO_ALIGN accesses will result in a call to the CPU's
- do_unaligned_access hook if the guest address is not aligned.
- The default depends on whether the target CPU defines ALIGNED_ONLY. */
- MO_AMASK = 16,
+ * MO_ALIGN accesses will result in a call to the CPU's
+ * do_unaligned_access hook if the guest address is not aligned.
+ * The default depends on whether the target CPU defines ALIGNED_ONLY.
+ * Some architectures (e.g. ARMv8) need the address which is aligned
+ * to a size more than the size of the memory access.
+ * To support such check it's enough the current costless alignment
+ * check implementation in QEMU, but we need to support
+ * an alignment size specifying.
+ * MO_ALIGN supposes a natural alignment
+ * (i.e. the alignment size is the size of a memory access).
+ * Note that an alignment size must be equal or greater
+ * than an access size.
+ * There are three options:
+ * - an alignment to the size of an access (MO_ALIGN);
+ * - an alignment to the specified size that is equal or greater than
+ * an access size (MO_ALIGN_x where 'x' is a size in bytes);
+ * - unaligned access permitted (MO_UNALN).
+ */
+ MO_ASHIFT = 4,
+ MO_AMASK = 7 << MO_ASHIFT,
#ifdef ALIGNED_ONLY
MO_ALIGN = 0,
MO_UNALN = MO_AMASK,
MO_ALIGN = MO_AMASK,
MO_UNALN = 0,
#endif
+ MO_ALIGN_2 = 1 << MO_ASHIFT,
+ MO_ALIGN_4 = 2 << MO_ASHIFT,
+ MO_ALIGN_8 = 3 << MO_ASHIFT,
+ MO_ALIGN_16 = 4 << MO_ASHIFT,
+ MO_ALIGN_32 = 5 << MO_ASHIFT,
+ MO_ALIGN_64 = 6 << MO_ASHIFT,
/* Combinations of the above, for ease of use. */
MO_UB = MO_8,
MO_SSIZE = MO_SIZE | MO_SIGN,
} TCGMemOp;
+/**
+ * get_alignment_bits
+ * @memop: TCGMemOp value
+ *
+ * Extract the alignment size from the memop.
+ *
+ * Returns: 0 in case of byte access (which is always aligned);
+ * positive value - number of alignment bits;
+ * negative value if unaligned access enabled
+ * and this is not a byte access.
+ */
+static inline int get_alignment_bits(TCGMemOp memop)
+{
+ int a = memop & MO_AMASK;
+ int s = memop & MO_SIZE;
+ int r;
+
+ if (a == MO_UNALN) {
+ /* Negative value if unaligned access enabled,
+ * or zero value in case of byte access.
+ */
+ return -s;
+ } else if (a == MO_ALIGN) {
+ /* A natural alignment: return a number of access size bits */
+ r = s;
+ } else {
+ /* Specific alignment size. It must be equal or greater
+ * than the access size.
+ */
+ r = a >> MO_ASHIFT;
+ tcg_debug_assert(r >= s);
+ }
+#if defined(CONFIG_SOFTMMU)
+ /* The requested alignment cannot overlap the TLB flags. */
+ tcg_debug_assert((TLB_FLAGS_MASK & ((1 << r) - 1)) == 0);
+#endif
+ return r;
+}
+
typedef tcg_target_ulong TCGArg;
/* Define a type and accessor macros for variables. Using pointer types
unsigned long l[BITS_TO_LONGS(TCG_MAX_TEMPS)];
} TCGTempSet;
+/* While we limit helpers to 6 arguments, for 32-bit hosts, with padding,
+ this imples a max of 6*2 (64-bit in) + 2 (64-bit out) = 14 operands.
+ There are never more than 2 outputs, which means that we can store all
+ dead + sync data within 16 bits. */
+#define DEAD_ARG 4
+#define SYNC_ARG 1
+typedef uint16_t TCGLifeData;
+
+/* The layout here is designed to avoid crossing of a 32-bit boundary.
+ If we do so, gcc adds padding, expanding the size to 12. */
typedef struct TCGOp {
- TCGOpcode opc : 8;
+ TCGOpcode opc : 8; /* 8 */
+
+ /* Index of the prev/next op, or 0 for the end of the list. */
+ unsigned prev : 10; /* 18 */
+ unsigned next : 10; /* 28 */
/* The number of out and in parameter for a call. */
- unsigned callo : 2;
- unsigned calli : 6;
+ unsigned calli : 4; /* 32 */
+ unsigned callo : 2; /* 34 */
- /* Index of the arguments for this op, or -1 for zero-operand ops. */
- signed args : 16;
+ /* Index of the arguments for this op, or 0 for zero-operand ops. */
+ unsigned args : 14; /* 48 */
- /* Index of the prex/next op, or -1 for the end of the list. */
- signed prev : 16;
- signed next : 16;
+ /* Lifetime data of the operands. */
+ unsigned life : 16; /* 64 */
} TCGOp;
-QEMU_BUILD_BUG_ON(NB_OPS > 0xff);
-QEMU_BUILD_BUG_ON(OPC_BUF_SIZE >= 0x7fff);
-QEMU_BUILD_BUG_ON(OPPARAM_BUF_SIZE >= 0x7fff);
+/* Make sure operands fit in the bitfields above. */
+QEMU_BUILD_BUG_ON(NB_OPS > (1 << 8));
+QEMU_BUILD_BUG_ON(OPC_BUF_SIZE > (1 << 10));
+QEMU_BUILD_BUG_ON(OPPARAM_BUF_SIZE > (1 << 14));
+
+/* Make sure that we don't overflow 64 bits without noticing. */
+QEMU_BUILD_BUG_ON(sizeof(TCGOp) > 8);
struct TCGContext {
uint8_t *pool_cur, *pool_end;
int nb_labels;
int nb_globals;
int nb_temps;
+ int nb_indirects;
/* goto_tb support */
tcg_insn_unit *code_buf;
- uintptr_t *tb_next;
- uint16_t *tb_next_offset;
- uint16_t *tb_jmp_offset; /* != NULL if USE_DIRECT_JUMP */
-
- /* liveness analysis */
- uint16_t *op_dead_args; /* for each operation, each bit tells if the
- corresponding argument is dead */
- uint8_t *op_sync_args; /* for each operation, each bit tells if the
- corresponding output argument needs to be
- sync to memory. */
-
+ uint16_t *tb_jmp_reset_offset; /* tb->jmp_reset_offset */
+ uint16_t *tb_jmp_insn_offset; /* tb->jmp_insn_offset if USE_DIRECT_JUMP */
+ uintptr_t *tb_jmp_target_addr; /* tb->jmp_target_addr if !USE_DIRECT_JUMP */
+
TCGRegSet reserved_regs;
intptr_t current_frame_offset;
intptr_t frame_start;
int goto_tb_issue_mask;
#endif
- int gen_first_op_idx;
- int gen_last_op_idx;
int gen_next_op_idx;
int gen_next_parm_idx;
TBContext tb_ctx;
+ /* Track which vCPU triggers events */
+ CPUState *cpu; /* *_trans */
+ TCGv_env tcg_env; /* *_exec */
+
/* The TCGBackendData structure is private to tcg-target.inc.c. */
struct TCGBackendData *be;
extern TCGContext tcg_ctx;
+static inline void tcg_set_insn_param(int op_idx, int arg, TCGArg v)
+{
+ int op_argi = tcg_ctx.gen_op_buf[op_idx].args;
+ tcg_ctx.gen_opparam_buf[op_argi + arg] = v;
+}
+
/* The number of opcodes emitted so far. */
static inline int tcg_op_buf_count(void)
{
void *tcg_malloc_internal(TCGContext *s, int size);
void tcg_pool_reset(TCGContext *s);
-void tcg_pool_delete(TCGContext *s);
void tb_lock(void);
void tb_unlock(void);
abort();\
} while (0)
-#ifdef CONFIG_DEBUG_TCG
-# define tcg_debug_assert(X) do { assert(X); } while (0)
-#elif QEMU_GNUC_PREREQ(4, 5)
-# define tcg_debug_assert(X) \
- do { if (!(X)) { __builtin_unreachable(); } } while (0)
-#else
-# define tcg_debug_assert(X) do { (void)(X); } while (0)
-#endif
-
void tcg_add_target_add_op_defs(const TCGTargetOpDef *tdefs);
#if UINTPTR_MAX == UINT32_MAX
TCGArg ret, int nargs, TCGArg *args);
void tcg_op_remove(TCGContext *s, TCGOp *op);
+TCGOp *tcg_op_insert_before(TCGContext *s, TCGOp *op, TCGOpcode opc, int narg);
+TCGOp *tcg_op_insert_after(TCGContext *s, TCGOp *op, TCGOpcode opc, int narg);
+
void tcg_optimize(TCGContext *s);
/* only used for debugging purposes */
void tcg_dump_ops(TCGContext *s);
-void dump_ops(const uint16_t *opc_buf, const TCGArg *opparam_buf);
TCGv_i32 tcg_const_i32(int32_t val);
TCGv_i64 tcg_const_i64(int64_t val);
TCGv_i32 tcg_const_local_i32(int32_t val);
/**
* tcg_qemu_tb_exec:
- * @env: CPUArchState * for the CPU
+ * @env: pointer to CPUArchState for the CPU
* @tb_ptr: address of generated code for the TB to execute
*
* Start executing code from a given translation block.
* which has not yet been directly linked, or an asynchronous
* event such as an interrupt needs handling.
*
- * The return value is a pointer to the next TB to execute
- * (if known; otherwise zero). This pointer is assumed to be
- * 4-aligned, and the bottom two bits are used to return further
- * information:
+ * Return: The return value is the value passed to the corresponding
+ * tcg_gen_exit_tb() at translation time of the last TB attempted to execute.
+ * The value is either zero or a 4-byte aligned pointer to that TB combined
+ * with additional information in its two least significant bits. The
+ * additional information is encoded as follows:
* 0, 1: the link between this TB and the next is via the specified
* TB index (0 or 1). That is, we left the TB via (the equivalent
* of) "goto_tb <index>". The main loop uses this to determine
* how to link the TB just executed to the next.
* 2: we are using instruction counting code generation, and we
* did not start executing this TB because the instruction counter
- * would hit zero midway through it. In this case the next-TB pointer
+ * would hit zero midway through it. In this case the pointer
* returned is the TB we were about to execute, and the caller must
* arrange to execute the remaining count of instructions.
* 3: we stopped because the CPU's exit_request flag was set
* (usually meaning that there is an interrupt that needs to be
- * handled). The next-TB pointer returned is the TB we were
- * about to execute when we noticed the pending exit request.
+ * handled). The pointer returned is the TB we were about to execute
+ * when we noticed the pending exit request.
*
* If the bottom two bits indicate an exit-via-index then the CPU
* state is correctly synchronised and ready for execution of the next
* TB (and in particular the guest PC is the address to execute next).
* Otherwise, we gave up on execution of this TB before it started, and
* the caller must fix up the CPU state by calling the CPU's
- * synchronize_from_tb() method with the next-TB pointer we return (falling
+ * synchronize_from_tb() method with the TB pointer we return (falling
* back to calling the CPU's set_pc method with tb->pb if no
* synchronize_from_tb() method exists).
*
projects / qemu.git / blobdiff