diff mbox series

[14/16] target/arm: Reuse sve_probe_page for scatter stores

Message ID 20200311064420.30606-15-richard.henderson@linaro.org
State Superseded
Headers show
Series target/arm: sve load/store improvements | expand

Commit Message

Richard Henderson March 11, 2020, 6:44 a.m. UTC 
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

---
 target/arm/sve_helper.c | 182 ++++++++++++++++++++++++----------------
 1 file changed, 111 insertions(+), 71 deletions(-)

-- 
2.20.1

Comments

Peter Maydell April 16, 2020, 2:25 p.m. UTC | #1 
On Wed, 11 Mar 2020 at 06:44, Richard Henderson
<richard.henderson@linaro.org> wrote:
>

> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

> ---

>  target/arm/sve_helper.c | 182 ++++++++++++++++++++++++----------------

>  1 file changed, 111 insertions(+), 71 deletions(-)

>


Reviewed-by: Peter Maydell <peter.maydell@linaro.org>


thanks
-- PMM
diff mbox series

Patch

diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index a33699adf8..e8b8f2560d 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -5414,94 +5414,134 @@  DO_LDFF1_ZPZ_D(dd_be, zd, MO_64)
 
 /* Stores with a vector index.  */
 
-static void sve_st1_zs(CPUARMState *env, void *vd, void *vg, void *vm,
-                       target_ulong base, uint32_t desc, uintptr_t ra,
-                       zreg_off_fn *off_fn, sve_ldst1_tlb_fn *tlb_fn)
+static inline QEMU_ALWAYS_INLINE
+void sve_st1_z(CPUARMState *env, void *vd, uint64_t *vg, void *vm,
+               target_ulong base, uint32_t desc, uintptr_t retaddr,
+               int esize, int msize, zreg_off_fn *off_fn,
+               sve_ldst1_host_fn *host_fn,
+               sve_ldst1_tlb_fn *tlb_fn)
 {
     const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2);
-    intptr_t i, oprsz = simd_oprsz(desc);
+    const int mmu_idx = cpu_mmu_index(env, false);
+    const intptr_t reg_max = simd_oprsz(desc);
+    void *host[ARM_MAX_VQ * 4];
+    intptr_t reg_off, i;
+    SVEHostPage info, info2;
 
-    for (i = 0; i < oprsz; ) {
-        uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
+    /*
+     * Probe all of the elements for host addresses and flags.
+     */
+    i = reg_off = 0;
+    do {
+        uint64_t pg = vg[reg_off >> 6];
         do {
-            if (likely(pg & 1)) {
-                target_ulong off = off_fn(vm, i);
-                tlb_fn(env, vd, i, base + (off << scale), ra);
+            target_ulong addr = base + (off_fn(vm, reg_off) << scale);
+            target_ulong in_page = -(addr | TARGET_PAGE_MASK);
+
+            host[i] = NULL;
+            if (likely((pg >> (reg_off & 63)) & 1)) {
+                if (likely(in_page >= msize)) {
+                    sve_probe_page(&info, false, env, addr, 0, MMU_DATA_STORE,
+                                   mmu_idx, retaddr);
+                    host[i] = info.host;
+                } else {
+                    /*
+                     * Element crosses the page boundary.
+                     * Probe both pages, but do not record the host address,
+                     * so that we use the slow path.
+                     */
+                    sve_probe_page(&info, false, env, addr, 0,
+                                   MMU_DATA_STORE, mmu_idx, retaddr);
+                    sve_probe_page(&info2, false, env, addr + in_page, 0,
+                                   MMU_DATA_STORE, mmu_idx, retaddr);
+                    info.flags |= info2.flags;
+                }
+
+                if (unlikely(info.flags & TLB_WATCHPOINT)) {
+                    cpu_check_watchpoint(env_cpu(env), addr, msize,
+                                         info.attrs, BP_MEM_WRITE, retaddr);
+                }
+                /* TODO: MTE check. */
             }
-            i += 4, pg >>= 4;
-        } while (i & 15);
-    }
-}
+            i += 1;
+            reg_off += esize;
+        } while (reg_off & 63);
+    } while (reg_off < reg_max);
 
-static void sve_st1_zd(CPUARMState *env, void *vd, void *vg, void *vm,
-                       target_ulong base, uint32_t desc, uintptr_t ra,
-                       zreg_off_fn *off_fn, sve_ldst1_tlb_fn *tlb_fn)
-{
-    const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2);
-    intptr_t i, oprsz = simd_oprsz(desc) / 8;
-
-    for (i = 0; i < oprsz; i++) {
-        uint8_t pg = *(uint8_t *)(vg + H1(i));
-        if (likely(pg & 1)) {
-            target_ulong off = off_fn(vm, i * 8);
-            tlb_fn(env, vd, i * 8, base + (off << scale), ra);
+    /*
+     * Now that we have recognized all exceptions except SyncExternal
+     * (from TLB_MMIO), which we cannot avoid, perform all of the stores.
+     *
+     * Note for the common case of an element in RAM, not crossing a page
+     * boundary, we have stored the host address in host[].  This doubles
+     * as a first-level check against the predicate, since only enabled
+     * elements have non-null host addresses.
+     */
+    i = reg_off = 0;
+    do {
+        void *h = host[i];
+        if (likely(h != NULL)) {
+            host_fn(vd, reg_off, h);
+        } else if ((vg[reg_off >> 6] >> (reg_off & 63)) & 1) {
+            target_ulong addr = base + (off_fn(vm, reg_off) << scale);
+            tlb_fn(env, vd, reg_off, addr, retaddr);
         }
-    }
+        i += 1;
+        reg_off += esize;
+    } while (reg_off < reg_max);
 }
 
-#define DO_ST1_ZPZ_S(MEM, OFS) \
-void QEMU_FLATTEN HELPER(sve_st##MEM##_##OFS) \
-    (CPUARMState *env, void *vd, void *vg, void *vm,         \
-     target_ulong base, uint32_t desc)                       \
-{                                                            \
-    sve_st1_zs(env, vd, vg, vm, base, desc, GETPC(),         \
-              off_##OFS##_s, sve_st1##MEM##_tlb);            \
+#define DO_ST1_ZPZ_S(MEM, OFS, MSZ) \
+void HELPER(sve_st##MEM##_##OFS)(CPUARMState *env, void *vd, void *vg,       \
+                                 void *vm, target_ulong base, uint32_t desc) \
+{                                                                            \
+    sve_st1_z(env, vd, vg, vm, base, desc, GETPC(), 4, 1 << MSZ,             \
+              off_##OFS##_s, sve_st1##MEM##_host, sve_st1##MEM##_tlb);       \
 }
 
-#define DO_ST1_ZPZ_D(MEM, OFS) \
-void QEMU_FLATTEN HELPER(sve_st##MEM##_##OFS) \
-    (CPUARMState *env, void *vd, void *vg, void *vm,         \
-     target_ulong base, uint32_t desc)                       \
-{                                                            \
-    sve_st1_zd(env, vd, vg, vm, base, desc, GETPC(),         \
-               off_##OFS##_d, sve_st1##MEM##_tlb);           \
+#define DO_ST1_ZPZ_D(MEM, OFS, MSZ) \
+void HELPER(sve_st##MEM##_##OFS)(CPUARMState *env, void *vd, void *vg,       \
+                                 void *vm, target_ulong base, uint32_t desc) \
+{                                                                            \
+    sve_st1_z(env, vd, vg, vm, base, desc, GETPC(), 8, 1 << MSZ,             \
+              off_##OFS##_d, sve_st1##MEM##_host, sve_st1##MEM##_tlb);       \
 }
 
-DO_ST1_ZPZ_S(bs, zsu)
-DO_ST1_ZPZ_S(hs_le, zsu)
-DO_ST1_ZPZ_S(hs_be, zsu)
-DO_ST1_ZPZ_S(ss_le, zsu)
-DO_ST1_ZPZ_S(ss_be, zsu)
+DO_ST1_ZPZ_S(bs, zsu, MO_8)
+DO_ST1_ZPZ_S(hs_le, zsu, MO_16)
+DO_ST1_ZPZ_S(hs_be, zsu, MO_16)
+DO_ST1_ZPZ_S(ss_le, zsu, MO_32)
+DO_ST1_ZPZ_S(ss_be, zsu, MO_32)
 
-DO_ST1_ZPZ_S(bs, zss)
-DO_ST1_ZPZ_S(hs_le, zss)
-DO_ST1_ZPZ_S(hs_be, zss)
-DO_ST1_ZPZ_S(ss_le, zss)
-DO_ST1_ZPZ_S(ss_be, zss)
+DO_ST1_ZPZ_S(bs, zss, MO_8)
+DO_ST1_ZPZ_S(hs_le, zss, MO_16)
+DO_ST1_ZPZ_S(hs_be, zss, MO_16)
+DO_ST1_ZPZ_S(ss_le, zss, MO_32)
+DO_ST1_ZPZ_S(ss_be, zss, MO_32)
 
-DO_ST1_ZPZ_D(bd, zsu)
-DO_ST1_ZPZ_D(hd_le, zsu)
-DO_ST1_ZPZ_D(hd_be, zsu)
-DO_ST1_ZPZ_D(sd_le, zsu)
-DO_ST1_ZPZ_D(sd_be, zsu)
-DO_ST1_ZPZ_D(dd_le, zsu)
-DO_ST1_ZPZ_D(dd_be, zsu)
+DO_ST1_ZPZ_D(bd, zsu, MO_8)
+DO_ST1_ZPZ_D(hd_le, zsu, MO_16)
+DO_ST1_ZPZ_D(hd_be, zsu, MO_16)
+DO_ST1_ZPZ_D(sd_le, zsu, MO_32)
+DO_ST1_ZPZ_D(sd_be, zsu, MO_32)
+DO_ST1_ZPZ_D(dd_le, zsu, MO_64)
+DO_ST1_ZPZ_D(dd_be, zsu, MO_64)
 
-DO_ST1_ZPZ_D(bd, zss)
-DO_ST1_ZPZ_D(hd_le, zss)
-DO_ST1_ZPZ_D(hd_be, zss)
-DO_ST1_ZPZ_D(sd_le, zss)
-DO_ST1_ZPZ_D(sd_be, zss)
-DO_ST1_ZPZ_D(dd_le, zss)
-DO_ST1_ZPZ_D(dd_be, zss)
+DO_ST1_ZPZ_D(bd, zss, MO_8)
+DO_ST1_ZPZ_D(hd_le, zss, MO_16)
+DO_ST1_ZPZ_D(hd_be, zss, MO_16)
+DO_ST1_ZPZ_D(sd_le, zss, MO_32)
+DO_ST1_ZPZ_D(sd_be, zss, MO_32)
+DO_ST1_ZPZ_D(dd_le, zss, MO_64)
+DO_ST1_ZPZ_D(dd_be, zss, MO_64)
 
-DO_ST1_ZPZ_D(bd, zd)
-DO_ST1_ZPZ_D(hd_le, zd)
-DO_ST1_ZPZ_D(hd_be, zd)
-DO_ST1_ZPZ_D(sd_le, zd)
-DO_ST1_ZPZ_D(sd_be, zd)
-DO_ST1_ZPZ_D(dd_le, zd)
-DO_ST1_ZPZ_D(dd_be, zd)
+DO_ST1_ZPZ_D(bd, zd, MO_8)
+DO_ST1_ZPZ_D(hd_le, zd, MO_16)
+DO_ST1_ZPZ_D(hd_be, zd, MO_16)
+DO_ST1_ZPZ_D(sd_le, zd, MO_32)
+DO_ST1_ZPZ_D(sd_be, zd, MO_32)
+DO_ST1_ZPZ_D(dd_le, zd, MO_64)
+DO_ST1_ZPZ_D(dd_be, zd, MO_64)
 
 #undef DO_ST1_ZPZ_S
 #undef DO_ST1_ZPZ_D