[PATCH v4 17/18] target/arm: Reuse sve_probe_page for gather loads

[Richard Henderson]

Reviewed-by: Peter Maydell <address@hidden>
Signed-off-by: Richard Henderson <address@hidden>
---
 target/arm/sve_helper.c | 208 +++++++++++++++++++++-------------------
 1 file changed, 109 insertions(+), 99 deletions(-)

diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index ad7e10f1e7..f1870aabc2 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -5124,130 +5124,140 @@ static target_ulong off_zd_d(void *reg, intptr_t 
reg_ofs)
     return *(uint64_t *)(reg + reg_ofs);
 }
 
-static void sve_ld1_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_ld1_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);
-    ARMVectorReg scratch = { };
+    const int mmu_idx = cpu_mmu_index(env, false);
+    const intptr_t reg_max = simd_oprsz(desc);
+    ARMVectorReg scratch;
+    intptr_t reg_off;
+    SVEHostPage info, info2;
 
-    for (i = 0; i < oprsz; ) {
-        uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
+    memset(&scratch, 0, reg_max);
+    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, &scratch, i, base + (off << scale), ra);
+                target_ulong addr = base + (off_fn(vm, reg_off) << scale);
+                target_ulong in_page = -(addr | TARGET_PAGE_MASK);
+
+                sve_probe_page(&info, false, env, addr, 0, MMU_DATA_LOAD,
+                               mmu_idx, retaddr);
+
+                if (likely(in_page >= msize)) {
+                    if (unlikely(info.flags & TLB_WATCHPOINT)) {
+                        cpu_check_watchpoint(env_cpu(env), addr, msize,
+                                             info.attrs, BP_MEM_READ, retaddr);
+                    }
+                    /* TODO: MTE check */
+                    host_fn(&scratch, reg_off, info.host);
+                } else {
+                    /* Element crosses the page boundary. */
+                    sve_probe_page(&info2, false, env, addr + in_page, 0,
+                                   MMU_DATA_LOAD, mmu_idx, retaddr);
+                    if (unlikely((info.flags | info2.flags) & TLB_WATCHPOINT)) 
{
+                        cpu_check_watchpoint(env_cpu(env), addr,
+                                             msize, info.attrs,
+                                             BP_MEM_READ, retaddr);
+                    }
+                    /* TODO: MTE check */
+                    tlb_fn(env, &scratch, reg_off, addr, retaddr);
+                }
             }
-            i += 4, pg >>= 4;
-        } while (i & 15);
-    }
+            reg_off += esize;
+            pg >>= esize;
+        } while (reg_off & 63);
+    } while (reg_off < reg_max);
 
     /* Wait until all exceptions have been raised to write back.  */
-    memcpy(vd, &scratch, oprsz);
+    memcpy(vd, &scratch, reg_max);
 }
 
-static void sve_ld1_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;
-    ARMVectorReg scratch = { };
-
-    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, &scratch, i * 8, base + (off << scale), ra);
-        }
-    }
-
-    /* Wait until all exceptions have been raised to write back.  */
-    memcpy(vd, &scratch, oprsz * 8);
+#define DO_LD1_ZPZ_S(MEM, OFS, MSZ) \
+void HELPER(sve_ld##MEM##_##OFS)(CPUARMState *env, void *vd, void *vg,       \
+                                 void *vm, target_ulong base, uint32_t desc) \
+{                                                                            \
+    sve_ld1_z(env, vd, vg, vm, base, desc, GETPC(), 4, 1 << MSZ,             \
+              off_##OFS##_s, sve_ld1##MEM##_host, sve_ld1##MEM##_tlb);       \
 }
 
-#define DO_LD1_ZPZ_S(MEM, OFS) \
-void QEMU_FLATTEN HELPER(sve_ld##MEM##_##OFS) \
-    (CPUARMState *env, void *vd, void *vg, void *vm,         \
-     target_ulong base, uint32_t desc)                       \
-{                                                            \
-    sve_ld1_zs(env, vd, vg, vm, base, desc, GETPC(),         \
-              off_##OFS##_s, sve_ld1##MEM##_tlb);            \
+#define DO_LD1_ZPZ_D(MEM, OFS, MSZ) \
+void HELPER(sve_ld##MEM##_##OFS)(CPUARMState *env, void *vd, void *vg,       \
+                                 void *vm, target_ulong base, uint32_t desc) \
+{                                                                            \
+    sve_ld1_z(env, vd, vg, vm, base, desc, GETPC(), 8, 1 << MSZ,             \
+              off_##OFS##_d, sve_ld1##MEM##_host, sve_ld1##MEM##_tlb);       \
 }
 
-#define DO_LD1_ZPZ_D(MEM, OFS) \
-void QEMU_FLATTEN HELPER(sve_ld##MEM##_##OFS) \
-    (CPUARMState *env, void *vd, void *vg, void *vm,         \
-     target_ulong base, uint32_t desc)                       \
-{                                                            \
-    sve_ld1_zd(env, vd, vg, vm, base, desc, GETPC(),         \
-               off_##OFS##_d, sve_ld1##MEM##_tlb);           \
-}
+DO_LD1_ZPZ_S(bsu, zsu, MO_8)
+DO_LD1_ZPZ_S(bsu, zss, MO_8)
+DO_LD1_ZPZ_D(bdu, zsu, MO_8)
+DO_LD1_ZPZ_D(bdu, zss, MO_8)
+DO_LD1_ZPZ_D(bdu, zd, MO_8)
 
-DO_LD1_ZPZ_S(bsu, zsu)
-DO_LD1_ZPZ_S(bsu, zss)
-DO_LD1_ZPZ_D(bdu, zsu)
-DO_LD1_ZPZ_D(bdu, zss)
-DO_LD1_ZPZ_D(bdu, zd)
+DO_LD1_ZPZ_S(bss, zsu, MO_8)
+DO_LD1_ZPZ_S(bss, zss, MO_8)
+DO_LD1_ZPZ_D(bds, zsu, MO_8)
+DO_LD1_ZPZ_D(bds, zss, MO_8)
+DO_LD1_ZPZ_D(bds, zd, MO_8)
 
-DO_LD1_ZPZ_S(bss, zsu)
-DO_LD1_ZPZ_S(bss, zss)
-DO_LD1_ZPZ_D(bds, zsu)
-DO_LD1_ZPZ_D(bds, zss)
-DO_LD1_ZPZ_D(bds, zd)
+DO_LD1_ZPZ_S(hsu_le, zsu, MO_16)
+DO_LD1_ZPZ_S(hsu_le, zss, MO_16)
+DO_LD1_ZPZ_D(hdu_le, zsu, MO_16)
+DO_LD1_ZPZ_D(hdu_le, zss, MO_16)
+DO_LD1_ZPZ_D(hdu_le, zd, MO_16)
 
-DO_LD1_ZPZ_S(hsu_le, zsu)
-DO_LD1_ZPZ_S(hsu_le, zss)
-DO_LD1_ZPZ_D(hdu_le, zsu)
-DO_LD1_ZPZ_D(hdu_le, zss)
-DO_LD1_ZPZ_D(hdu_le, zd)
+DO_LD1_ZPZ_S(hsu_be, zsu, MO_16)
+DO_LD1_ZPZ_S(hsu_be, zss, MO_16)
+DO_LD1_ZPZ_D(hdu_be, zsu, MO_16)
+DO_LD1_ZPZ_D(hdu_be, zss, MO_16)
+DO_LD1_ZPZ_D(hdu_be, zd, MO_16)
 
-DO_LD1_ZPZ_S(hsu_be, zsu)
-DO_LD1_ZPZ_S(hsu_be, zss)
-DO_LD1_ZPZ_D(hdu_be, zsu)
-DO_LD1_ZPZ_D(hdu_be, zss)
-DO_LD1_ZPZ_D(hdu_be, zd)
+DO_LD1_ZPZ_S(hss_le, zsu, MO_16)
+DO_LD1_ZPZ_S(hss_le, zss, MO_16)
+DO_LD1_ZPZ_D(hds_le, zsu, MO_16)
+DO_LD1_ZPZ_D(hds_le, zss, MO_16)
+DO_LD1_ZPZ_D(hds_le, zd, MO_16)
 
-DO_LD1_ZPZ_S(hss_le, zsu)
-DO_LD1_ZPZ_S(hss_le, zss)
-DO_LD1_ZPZ_D(hds_le, zsu)
-DO_LD1_ZPZ_D(hds_le, zss)
-DO_LD1_ZPZ_D(hds_le, zd)
+DO_LD1_ZPZ_S(hss_be, zsu, MO_16)
+DO_LD1_ZPZ_S(hss_be, zss, MO_16)
+DO_LD1_ZPZ_D(hds_be, zsu, MO_16)
+DO_LD1_ZPZ_D(hds_be, zss, MO_16)
+DO_LD1_ZPZ_D(hds_be, zd, MO_16)
 
-DO_LD1_ZPZ_S(hss_be, zsu)
-DO_LD1_ZPZ_S(hss_be, zss)
-DO_LD1_ZPZ_D(hds_be, zsu)
-DO_LD1_ZPZ_D(hds_be, zss)
-DO_LD1_ZPZ_D(hds_be, zd)
+DO_LD1_ZPZ_S(ss_le, zsu, MO_32)
+DO_LD1_ZPZ_S(ss_le, zss, MO_32)
+DO_LD1_ZPZ_D(sdu_le, zsu, MO_32)
+DO_LD1_ZPZ_D(sdu_le, zss, MO_32)
+DO_LD1_ZPZ_D(sdu_le, zd, MO_32)
 
-DO_LD1_ZPZ_S(ss_le, zsu)
-DO_LD1_ZPZ_S(ss_le, zss)
-DO_LD1_ZPZ_D(sdu_le, zsu)
-DO_LD1_ZPZ_D(sdu_le, zss)
-DO_LD1_ZPZ_D(sdu_le, zd)
+DO_LD1_ZPZ_S(ss_be, zsu, MO_32)
+DO_LD1_ZPZ_S(ss_be, zss, MO_32)
+DO_LD1_ZPZ_D(sdu_be, zsu, MO_32)
+DO_LD1_ZPZ_D(sdu_be, zss, MO_32)
+DO_LD1_ZPZ_D(sdu_be, zd, MO_32)
 
-DO_LD1_ZPZ_S(ss_be, zsu)
-DO_LD1_ZPZ_S(ss_be, zss)
-DO_LD1_ZPZ_D(sdu_be, zsu)
-DO_LD1_ZPZ_D(sdu_be, zss)
-DO_LD1_ZPZ_D(sdu_be, zd)
+DO_LD1_ZPZ_D(sds_le, zsu, MO_32)
+DO_LD1_ZPZ_D(sds_le, zss, MO_32)
+DO_LD1_ZPZ_D(sds_le, zd, MO_32)
 
-DO_LD1_ZPZ_D(sds_le, zsu)
-DO_LD1_ZPZ_D(sds_le, zss)
-DO_LD1_ZPZ_D(sds_le, zd)
+DO_LD1_ZPZ_D(sds_be, zsu, MO_32)
+DO_LD1_ZPZ_D(sds_be, zss, MO_32)
+DO_LD1_ZPZ_D(sds_be, zd, MO_32)
 
-DO_LD1_ZPZ_D(sds_be, zsu)
-DO_LD1_ZPZ_D(sds_be, zss)
-DO_LD1_ZPZ_D(sds_be, zd)
+DO_LD1_ZPZ_D(dd_le, zsu, MO_64)
+DO_LD1_ZPZ_D(dd_le, zss, MO_64)
+DO_LD1_ZPZ_D(dd_le, zd, MO_64)
 
-DO_LD1_ZPZ_D(dd_le, zsu)
-DO_LD1_ZPZ_D(dd_le, zss)
-DO_LD1_ZPZ_D(dd_le, zd)
-
-DO_LD1_ZPZ_D(dd_be, zsu)
-DO_LD1_ZPZ_D(dd_be, zss)
-DO_LD1_ZPZ_D(dd_be, zd)
+DO_LD1_ZPZ_D(dd_be, zsu, MO_64)
+DO_LD1_ZPZ_D(dd_be, zss, MO_64)
+DO_LD1_ZPZ_D(dd_be, zd, MO_64)
 
 #undef DO_LD1_ZPZ_S
 #undef DO_LD1_ZPZ_D
-- 
2.20.1