* You should have received a copy of the GNU Lesser General Public
* License along with this library; if not, see <http://www.gnu.org/licenses/>.
*/
+
#include "qemu/osdep.h"
#include "cpu.h"
#include "exec/exec-all.h"
#include "qemu/host-utils.h"
+#include "qemu/main-loop.h"
#include "exec/helper-proto.h"
-
#include "helper_regs.h"
#include "exec/cpu_ldst.h"
+#include "tcg.h"
+#include "internal.h"
+#include "qemu/atomic128.h"
-//#define DEBUG_OP
+/* #define DEBUG_OP */
static inline bool needs_byteswap(const CPUPPCState *env)
{
do_lsw(env, addr, nb, reg, GETPC());
}
-/* PPC32 specification says we must generate an exception if
- * rA is in the range of registers to be loaded.
- * In an other hand, IBM says this is valid, but rA won't be loaded.
- * For now, I'll follow the spec...
+/*
+ * PPC32 specification says we must generate an exception if rA is in
+ * the range of registers to be loaded. In an other hand, IBM says
+ * this is valid, but rA won't be loaded. For now, I'll follow the
+ * spec...
*/
void helper_lswx(CPUPPCState *env, target_ulong addr, uint32_t reg,
uint32_t ra, uint32_t rb)
{
if (likely(xer_bc != 0)) {
- int num_used_regs = (xer_bc + 3) / 4;
+ int num_used_regs = DIV_ROUND_UP(xer_bc, 4);
if (unlikely((ra != 0 && lsw_reg_in_range(reg, num_used_regs, ra)) ||
lsw_reg_in_range(reg, num_used_regs, rb))) {
raise_exception_err_ra(env, POWERPC_EXCP_PROGRAM,
}
}
-void helper_dcbz(CPUPPCState *env, target_ulong addr, uint32_t opcode)
+static void dcbz_common(CPUPPCState *env, target_ulong addr,
+ uint32_t opcode, bool epid, uintptr_t retaddr)
{
target_ulong mask, dcbz_size = env->dcache_line_size;
uint32_t i;
void *haddr;
+ int mmu_idx = epid ? PPC_TLB_EPID_STORE : env->dmmu_idx;
#if defined(TARGET_PPC64)
/* Check for dcbz vs dcbzl on 970 */
}
/* Try fast path translate */
- haddr = tlb_vaddr_to_host(env, addr, MMU_DATA_STORE, env->dmmu_idx);
+ haddr = tlb_vaddr_to_host(env, addr, MMU_DATA_STORE, mmu_idx);
if (haddr) {
memset(haddr, 0, dcbz_size);
} else {
/* Slow path */
for (i = 0; i < dcbz_size; i += 8) {
- cpu_stq_data_ra(env, addr + i, 0, GETPC());
+ if (epid) {
+#if !defined(CONFIG_USER_ONLY)
+ /* Does not make sense on USER_ONLY config */
+ cpu_stq_eps_ra(env, addr + i, 0, retaddr);
+#endif
+ } else {
+ cpu_stq_data_ra(env, addr + i, 0, retaddr);
+ }
}
}
}
+void helper_dcbz(CPUPPCState *env, target_ulong addr, uint32_t opcode)
+{
+ dcbz_common(env, addr, opcode, false, GETPC());
+}
+
+void helper_dcbzep(CPUPPCState *env, target_ulong addr, uint32_t opcode)
+{
+ dcbz_common(env, addr, opcode, true, GETPC());
+}
+
void helper_icbi(CPUPPCState *env, target_ulong addr)
{
addr &= ~(env->dcache_line_size - 1);
- /* Invalidate one cache line :
+ /*
+ * Invalidate one cache line :
* PowerPC specification says this is to be treated like a load
* (not a fetch) by the MMU. To be sure it will be so,
* do the load "by hand".
cpu_ldl_data_ra(env, addr, GETPC());
}
+void helper_icbiep(CPUPPCState *env, target_ulong addr)
+{
+#if !defined(CONFIG_USER_ONLY)
+ /* See comments above */
+ addr &= ~(env->dcache_line_size - 1);
+ cpu_ldl_epl_ra(env, addr, GETPC());
+#endif
+}
+
/* XXX: to be tested */
target_ulong helper_lscbx(CPUPPCState *env, target_ulong addr, uint32_t reg,
uint32_t ra, uint32_t rb)
return i;
}
+#ifdef TARGET_PPC64
+uint64_t helper_lq_le_parallel(CPUPPCState *env, target_ulong addr,
+ uint32_t opidx)
+{
+ Int128 ret;
+
+ /* We will have raised EXCP_ATOMIC from the translator. */
+ assert(HAVE_ATOMIC128);
+ ret = helper_atomic_ldo_le_mmu(env, addr, opidx, GETPC());
+ env->retxh = int128_gethi(ret);
+ return int128_getlo(ret);
+}
+
+uint64_t helper_lq_be_parallel(CPUPPCState *env, target_ulong addr,
+ uint32_t opidx)
+{
+ Int128 ret;
+
+ /* We will have raised EXCP_ATOMIC from the translator. */
+ assert(HAVE_ATOMIC128);
+ ret = helper_atomic_ldo_be_mmu(env, addr, opidx, GETPC());
+ env->retxh = int128_gethi(ret);
+ return int128_getlo(ret);
+}
+
+void helper_stq_le_parallel(CPUPPCState *env, target_ulong addr,
+ uint64_t lo, uint64_t hi, uint32_t opidx)
+{
+ Int128 val;
+
+ /* We will have raised EXCP_ATOMIC from the translator. */
+ assert(HAVE_ATOMIC128);
+ val = int128_make128(lo, hi);
+ helper_atomic_sto_le_mmu(env, addr, val, opidx, GETPC());
+}
+
+void helper_stq_be_parallel(CPUPPCState *env, target_ulong addr,
+ uint64_t lo, uint64_t hi, uint32_t opidx)
+{
+ Int128 val;
+
+ /* We will have raised EXCP_ATOMIC from the translator. */
+ assert(HAVE_ATOMIC128);
+ val = int128_make128(lo, hi);
+ helper_atomic_sto_be_mmu(env, addr, val, opidx, GETPC());
+}
+
+uint32_t helper_stqcx_le_parallel(CPUPPCState *env, target_ulong addr,
+ uint64_t new_lo, uint64_t new_hi,
+ uint32_t opidx)
+{
+ bool success = false;
+
+ /* We will have raised EXCP_ATOMIC from the translator. */
+ assert(HAVE_CMPXCHG128);
+
+ if (likely(addr == env->reserve_addr)) {
+ Int128 oldv, cmpv, newv;
+
+ cmpv = int128_make128(env->reserve_val2, env->reserve_val);
+ newv = int128_make128(new_lo, new_hi);
+ oldv = helper_atomic_cmpxchgo_le_mmu(env, addr, cmpv, newv,
+ opidx, GETPC());
+ success = int128_eq(oldv, cmpv);
+ }
+ env->reserve_addr = -1;
+ return env->so + success * CRF_EQ_BIT;
+}
+
+uint32_t helper_stqcx_be_parallel(CPUPPCState *env, target_ulong addr,
+ uint64_t new_lo, uint64_t new_hi,
+ uint32_t opidx)
+{
+ bool success = false;
+
+ /* We will have raised EXCP_ATOMIC from the translator. */
+ assert(HAVE_CMPXCHG128);
+
+ if (likely(addr == env->reserve_addr)) {
+ Int128 oldv, cmpv, newv;
+
+ cmpv = int128_make128(env->reserve_val2, env->reserve_val);
+ newv = int128_make128(new_lo, new_hi);
+ oldv = helper_atomic_cmpxchgo_be_mmu(env, addr, cmpv, newv,
+ opidx, GETPC());
+ success = int128_eq(oldv, cmpv);
+ }
+ env->reserve_addr = -1;
+ return env->so + success * CRF_EQ_BIT;
+}
+#endif
+
/*****************************************************************************/
/* Altivec extension helpers */
#if defined(HOST_WORDS_BIGENDIAN)
#define LO_IDX 0
#endif
-/* We use msr_le to determine index ordering in a vector. However,
- byteswapping is not simply controlled by msr_le. We also need to take
- into account endianness of the target. This is done for the little-endian
- PPC64 user-mode target. */
+/*
+ * We use msr_le to determine index ordering in a vector. However,
+ * byteswapping is not simply controlled by msr_le. We also need to
+ * take into account endianness of the target. This is done for the
+ * little-endian PPC64 user-mode target.
+ */
#define LVE(name, access, swap, element) \
void helper_##name(CPUPPCState *env, ppc_avr_t *r, \
target_ulong addr) \
{ \
size_t n_elems = ARRAY_SIZE(r->element); \
- int adjust = HI_IDX*(n_elems - 1); \
+ int adjust = HI_IDX * (n_elems - 1); \
int sh = sizeof(r->element[0]) >> 1; \
int index = (addr & 0xf) >> sh; \
if (msr_le) { \
#undef I
#undef LVE
+#ifdef TARGET_PPC64
+#define GET_NB(rb) ((rb >> 56) & 0xFF)
+
+#define VSX_LXVL(name, lj) \
+void helper_##name(CPUPPCState *env, target_ulong addr, \
+ ppc_vsr_t *xt, target_ulong rb) \
+{ \
+ ppc_vsr_t t; \
+ uint64_t nb = GET_NB(rb); \
+ int i; \
+ \
+ t.s128 = int128_zero(); \
+ if (nb) { \
+ nb = (nb >= 16) ? 16 : nb; \
+ if (msr_le && !lj) { \
+ for (i = 16; i > 16 - nb; i--) { \
+ t.VsrB(i - 1) = cpu_ldub_data_ra(env, addr, GETPC()); \
+ addr = addr_add(env, addr, 1); \
+ } \
+ } else { \
+ for (i = 0; i < nb; i++) { \
+ t.VsrB(i) = cpu_ldub_data_ra(env, addr, GETPC()); \
+ addr = addr_add(env, addr, 1); \
+ } \
+ } \
+ } \
+ *xt = t; \
+}
+
+VSX_LXVL(lxvl, 0)
+VSX_LXVL(lxvll, 1)
+#undef VSX_LXVL
+
+#define VSX_STXVL(name, lj) \
+void helper_##name(CPUPPCState *env, target_ulong addr, \
+ ppc_vsr_t *xt, target_ulong rb) \
+{ \
+ target_ulong nb = GET_NB(rb); \
+ int i; \
+ \
+ if (!nb) { \
+ return; \
+ } \
+ \
+ nb = (nb >= 16) ? 16 : nb; \
+ if (msr_le && !lj) { \
+ for (i = 16; i > 16 - nb; i--) { \
+ cpu_stb_data_ra(env, addr, xt->VsrB(i - 1), GETPC()); \
+ addr = addr_add(env, addr, 1); \
+ } \
+ } else { \
+ for (i = 0; i < nb; i++) { \
+ cpu_stb_data_ra(env, addr, xt->VsrB(i), GETPC()); \
+ addr = addr_add(env, addr, 1); \
+ } \
+ } \
+}
+
+VSX_STXVL(stxvl, 0)
+VSX_STXVL(stxvll, 1)
+#undef VSX_STXVL
+#undef GET_NB
+#endif /* TARGET_PPC64 */
+
#undef HI_IDX
#undef LO_IDX
void helper_tbegin(CPUPPCState *env)
{
- /* As a degenerate implementation, always fail tbegin. The reason
+ /*
+ * As a degenerate implementation, always fail tbegin. The reason
* given is "Nesting overflow". The "persistent" bit is set,
* providing a hint to the error handler to not retry. The TFIAR
* captures the address of the failure, which is this tbegin
- * instruction. Instruction execution will continue with the
- * next instruction in memory, which is precisely what we want.
+ * instruction. Instruction execution will continue with the next
+ * instruction in memory, which is precisely what we want.
*/
env->spr[SPR_TEXASR] =