Merge tag 'pull-misc-20240408' of https://gitlab.com/rth7680/qemu int…

…o staging

util/bufferiszero: Optimizations and cleanups, esp code removal
target/m68k: Semihosting for non-coldfire cpus
target/m68k: Fix fp accrued exception reporting
target/hppa: Fix IIAOQ, IIASQ for pa2.0
target/sh4: Fixes to mac.l and mac.w saturation
target/sh4: Fixes to illegal delay slot reporting
linux-user: Cleanups for do_setsockopt
linux-user: Add FITRIM ioctl
linux-user: Fix waitid return of siginfo_t and rusage
tcg/optimize: Do not attempt to constant fold neg_vec
accel/tcg: Improve can_do_io management, mmio bug fix

# -----BEGIN PGP SIGNATURE-----
#
# iQFRBAABCgA7FiEEekgeeIaLTbaoWgXAZN846K9+IV8FAmYULZgdHHJpY2hhcmQu
# aGVuZGVyc29uQGxpbmFyby5vcmcACgkQZN846K9+IV+gIAgAqhtlPsZbnoXwqCNs
# fafa/lTvpZYHl2kMJVRYtMmU661HD2HGARe3XCc7/5ZldvEXeQKPde9VrhmasIe8
# EChS3xh1U3J2zEUbnHHgnC9DDVE7uvG0lTazXQRe6WESTaRuBz5d6a0GZtSkH6F4
# AFp0lyKAxX4cn07aBFg0MJ/oPe21Ay9tTQv+5Ox2JOSvaK+FbW7hXisyReF5MVwq
# WPQSELCSppdowxAcsHCD5Q8t/nwGfBbHKOjxLJCgf9xX1+9Wv3Ab8kMjRqaJWdXu
# CvvJ/DigLZiHWbU2TxR2dPOIFSNZOIJY/BJ92aCHw7q9a4Ii2tkTPoJoM/qqlBq8
# 0oLPXg==
# =00NK
# -----END PGP SIGNATURE-----
# gpg: Signature made Mon 08 Apr 2024 18:47:04 BST
# gpg:                using RSA key 7A481E78868B4DB6A85A05C064DF38E8AF7E215F
# gpg:                issuer "richard.henderson@linaro.org"
# gpg: Good signature from "Richard Henderson <richard.henderson@linaro.org>" [full]
# Primary key fingerprint: 7A48 1E78 868B 4DB6 A85A  05C0 64DF 38E8 AF7E 215F

* tag 'pull-misc-20240408' of https://gitlab.com/rth7680/qemu: (35 commits)
  util/bufferiszero: Simplify test_buffer_is_zero_next_accel
  util/bufferiszero: Introduce biz_accel_fn typedef
  util/bufferiszero: Improve scalar variant
  util/bufferiszero: Optimize SSE2 and AVX2 variants
  util/bufferiszero: Remove useless prefetches
  util/bufferiszero: Reorganize for early test for acceleration
  util/bufferiszero: Remove AVX512 variant
  util/bufferiszero: Remove SSE4.1 variant
  accel/tcg: Improve can_do_io management
  target/s390x: Use insn_start from DisasContextBase
  target/riscv: Use insn_start from DisasContextBase
  target/microblaze: Use insn_start from DisasContextBase
  target/i386: Preserve DisasContextBase.insn_start across rewind
  target/hppa: Use insn_start from DisasContextBase
  target/arm: Use insn_start from DisasContextBase
  accel/tcg: Add insn_start to DisasContextBase
  tcg: Add TCGContext.emit_before_op
  target/m68k: Support semihosting on non-ColdFire targets
  target/m68k: Perform the semihosting test during translate
  target/m68k: Pass semihosting arg to exit
  ...

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

accel/tcg/translator.c

@@ -18,20 +18,14 @@
 
 static void set_can_do_io(DisasContextBase *db, bool val)
 {
-    if (db->saved_can_do_io != val) {
-        db->saved_can_do_io = val;
-
-        QEMU_BUILD_BUG_ON(sizeof_field(CPUState, neg.can_do_io) != 1);
-        tcg_gen_st8_i32(tcg_constant_i32(val), tcg_env,
-                        offsetof(ArchCPU, parent_obj.neg.can_do_io) -
-                        offsetof(ArchCPU, env));
-    }
+    QEMU_BUILD_BUG_ON(sizeof_field(CPUState, neg.can_do_io) != 1);
+    tcg_gen_st8_i32(tcg_constant_i32(val), tcg_env,
+                    offsetof(ArchCPU, parent_obj.neg.can_do_io) -
+                    offsetof(ArchCPU, env));
 }
 
 bool translator_io_start(DisasContextBase *db)
 {
-    set_can_do_io(db, true);
-
     /*
      * Ensure that this instruction will be the last in the TB.
      * The target may override this to something more forceful.
@@ -84,13 +78,6 @@ static TCGOp *gen_tb_start(DisasContextBase *db, uint32_t cflags)
                          - offsetof(ArchCPU, env));
     }
 
-    /*
-     * cpu->neg.can_do_io is set automatically here at the beginning of
-     * each translation block.  The cost is minimal, plus it would be
-     * very easy to forget doing it in the translator.
-     */
-    set_can_do_io(db, db->max_insns == 1);
-
     return icount_start_insn;
 }
 
@@ -129,6 +116,7 @@ void translator_loop(CPUState *cpu, TranslationBlock *tb, int *max_insns,
 {
     uint32_t cflags = tb_cflags(tb);
     TCGOp *icount_start_insn;
+    TCGOp *first_insn_start = NULL;
     bool plugin_enabled;
 
     /* Initialize DisasContext */
@@ -139,7 +127,7 @@ void translator_loop(CPUState *cpu, TranslationBlock *tb, int *max_insns,
     db->num_insns = 0;
     db->max_insns = *max_insns;
     db->singlestep_enabled = cflags & CF_SINGLE_STEP;
-    db->saved_can_do_io = -1;
+    db->insn_start = NULL;
     db->host_addr[0] = host_pc;
     db->host_addr[1] = NULL;
 
@@ -157,6 +145,10 @@ void translator_loop(CPUState *cpu, TranslationBlock *tb, int *max_insns,
     while (true) {
         *max_insns = ++db->num_insns;
         ops->insn_start(db, cpu);
+        db->insn_start = tcg_last_op();
+        if (first_insn_start == NULL) {
+            first_insn_start = db->insn_start;
+        }
         tcg_debug_assert(db->is_jmp == DISAS_NEXT);  /* no early exit */
 
         if (plugin_enabled) {
@@ -169,10 +161,6 @@ void translator_loop(CPUState *cpu, TranslationBlock *tb, int *max_insns,
          * done next -- either exiting this loop or locate the start of
          * the next instruction.
          */
-        if (db->num_insns == db->max_insns) {
-            /* Accept I/O on the last instruction.  */
-            set_can_do_io(db, true);
-        }
         ops->translate_insn(db, cpu);
 
         /*
@@ -205,6 +193,21 @@ void translator_loop(CPUState *cpu, TranslationBlock *tb, int *max_insns,
     ops->tb_stop(db, cpu);
     gen_tb_end(tb, cflags, icount_start_insn, db->num_insns);
 
+    /*
+     * Manage can_do_io for the translation block: set to false before
+     * the first insn and set to true before the last insn.
+     */
+    if (db->num_insns == 1) {
+        tcg_debug_assert(first_insn_start == db->insn_start);
+    } else {
+        tcg_debug_assert(first_insn_start != db->insn_start);
+        tcg_ctx->emit_before_op = first_insn_start;
+        set_can_do_io(db, false);
+    }
+    tcg_ctx->emit_before_op = db->insn_start;
+    set_can_do_io(db, true);
+    tcg_ctx->emit_before_op = NULL;
+
     if (plugin_enabled) {
         plugin_gen_tb_end(cpu, db->num_insns);
     }

include/exec/translator.h

@@ -74,6 +74,8 @@ typedef enum DisasJumpType {
  * @singlestep_enabled: "Hardware" single stepping enabled.
  * @saved_can_do_io: Known value of cpu->neg.can_do_io, or -1 for unknown.
  * @plugin_enabled: TCG plugin enabled in this TB.
+ * @insn_start: The last op emitted by the insn_start hook,
+ *              which is expected to be INDEX_op_insn_start.
  *
  * Architecture-agnostic disassembly context.
  */
@@ -85,8 +87,8 @@ typedef struct DisasContextBase {
     int num_insns;
     int max_insns;
     bool singlestep_enabled;
-    int8_t saved_can_do_io;
     bool plugin_enabled;
+    struct TCGOp *insn_start;
     void *host_addr[2];
 } DisasContextBase;
 

include/qemu/cutils.h

@@ -187,9 +187,39 @@ char *freq_to_str(uint64_t freq_hz);
 /* used to print char* safely */
 #define STR_OR_NULL(str) ((str) ? (str) : "null")
 
-bool buffer_is_zero(const void *buf, size_t len);
+/*
+ * Check if a buffer is all zeroes.
+ */
+
+bool buffer_is_zero_ool(const void *vbuf, size_t len);
+bool buffer_is_zero_ge256(const void *vbuf, size_t len);
 bool test_buffer_is_zero_next_accel(void);
 
+static inline bool buffer_is_zero_sample3(const char *buf, size_t len)
+{
+    /*
+     * For any reasonably sized buffer, these three samples come from
+     * three different cachelines.  In qemu-img usage, we find that
+     * each byte eliminates more than half of all buffer testing.
+     * It is therefore critical to performance that the byte tests
+     * short-circuit, so that we do not pull in additional cache lines.
+     * Do not "optimize" this to !(a | b | c).
+     */
+    return !buf[0] && !buf[len - 1] && !buf[len / 2];
+}
+
+#ifdef __OPTIMIZE__
+static inline bool buffer_is_zero(const void *buf, size_t len)
+{
+    return (__builtin_constant_p(len) && len >= 256
+            ? buffer_is_zero_sample3(buf, len) &&
+              buffer_is_zero_ge256(buf, len)
+            : buffer_is_zero_ool(buf, len));
+}
+#else
+#define buffer_is_zero  buffer_is_zero_ool
+#endif
+
 /*
  * Implementation of ULEB128 (http://en.wikipedia.org/wiki/LEB128)
  * Input is limited to 14-bit numbers

include/tcg/tcg.h

@@ -553,6 +553,12 @@ struct TCGContext {
     QTAILQ_HEAD(, TCGOp) ops, free_ops;
     QSIMPLEQ_HEAD(, TCGLabel) labels;
 
+    /*
+     * When clear, new ops are added to the tail of @ops.
+     * When set, new ops are added in front of @emit_before_op.
+     */
+    TCGOp *emit_before_op;
+
     /* Tells which temporary holds a given register.
        It does not take into account fixed registers */
     TCGTemp *reg_to_temp[TCG_TARGET_NB_REGS];

linux-user/ioctls.h

@@ -140,6 +140,9 @@
 #ifdef FITHAW
      IOCTL(FITHAW, IOC_W | IOC_R, TYPE_INT)
 #endif
+#ifdef FITRIM
+     IOCTL(FITRIM, IOC_W | IOC_R, MK_PTR(MK_STRUCT(STRUCT_fstrim_range)))
+#endif
 
      IOCTL(FIGETBSZ, IOC_R, MK_PTR(TYPE_LONG))
 #ifdef CONFIG_FIEMAP

linux-user/main.c

@@ -928,11 +928,7 @@ int main(int argc, char **argv, char **envp)
      * Prepare copy of argv vector for target.
      */
     target_argc = argc - optind;
-    target_argv = calloc(target_argc + 1, sizeof (char *));
-    if (target_argv == NULL) {
-        (void) fprintf(stderr, "Unable to allocate memory for target_argv\n");
-        exit(EXIT_FAILURE);
-    }
+    target_argv = g_new0(char *, target_argc + 1);
 
     /*
      * If argv0 is specified (using '-0' switch) we replace

linux-user/syscall.c

@@ -1615,24 +1615,6 @@ static abi_long do_pipe(CPUArchState *cpu_env, abi_ulong pipedes,
     return get_errno(ret);
 }
 
-static inline abi_long target_to_host_ip_mreq(struct ip_mreqn *mreqn,
-                                              abi_ulong target_addr,
-                                              socklen_t len)
-{
-    struct target_ip_mreqn *target_smreqn;
-
-    target_smreqn = lock_user(VERIFY_READ, target_addr, len, 1);
-    if (!target_smreqn)
-        return -TARGET_EFAULT;
-    mreqn->imr_multiaddr.s_addr = target_smreqn->imr_multiaddr.s_addr;
-    mreqn->imr_address.s_addr = target_smreqn->imr_address.s_addr;
-    if (len == sizeof(struct target_ip_mreqn))
-        mreqn->imr_ifindex = tswapal(target_smreqn->imr_ifindex);
-    unlock_user(target_smreqn, target_addr, 0);
-
-    return 0;
-}
-
 static inline abi_long target_to_host_sockaddr(int fd, struct sockaddr *addr,
                                                abi_ulong target_addr,
                                                socklen_t len)
@@ -2067,8 +2049,6 @@ static abi_long do_setsockopt(int sockfd, int level, int optname,
 {
     abi_long ret;
     int val;
-    struct ip_mreqn *ip_mreq;
-    struct ip_mreq_source *ip_mreq_source;
 
     switch(level) {
     case SOL_TCP:
@@ -2111,19 +2091,40 @@ static abi_long do_setsockopt(int sockfd, int level, int optname,
             break;
         case IP_ADD_MEMBERSHIP:
         case IP_DROP_MEMBERSHIP:
+        {
+            struct ip_mreqn ip_mreq;
+            struct target_ip_mreqn *target_smreqn;
+
+            QEMU_BUILD_BUG_ON(sizeof(struct ip_mreq) !=
+                              sizeof(struct target_ip_mreq));
+
             if (optlen < sizeof (struct target_ip_mreq) ||
-                optlen > sizeof (struct target_ip_mreqn))
+                optlen > sizeof (struct target_ip_mreqn)) {
                 return -TARGET_EINVAL;
+            }
 
-            ip_mreq = (struct ip_mreqn *) alloca(optlen);
-            target_to_host_ip_mreq(ip_mreq, optval_addr, optlen);
-            ret = get_errno(setsockopt(sockfd, level, optname, ip_mreq, optlen));
-            break;
+            target_smreqn = lock_user(VERIFY_READ, optval_addr, optlen, 1);
+            if (!target_smreqn) {
+                return -TARGET_EFAULT;
+            }
+            ip_mreq.imr_multiaddr.s_addr = target_smreqn->imr_multiaddr.s_addr;
+            ip_mreq.imr_address.s_addr = target_smreqn->imr_address.s_addr;
+            if (optlen == sizeof(struct target_ip_mreqn)) {
+                ip_mreq.imr_ifindex = tswapal(target_smreqn->imr_ifindex);
+                optlen = sizeof(struct ip_mreqn);
+            }
+            unlock_user(target_smreqn, optval_addr, 0);
 
+            ret = get_errno(setsockopt(sockfd, level, optname, &ip_mreq, optlen));
+            break;
+        }
         case IP_BLOCK_SOURCE:
         case IP_UNBLOCK_SOURCE:
         case IP_ADD_SOURCE_MEMBERSHIP:
         case IP_DROP_SOURCE_MEMBERSHIP:
+        {
+            struct ip_mreq_source *ip_mreq_source;
+
             if (optlen != sizeof (struct target_ip_mreq_source))
                 return -TARGET_EINVAL;
 
@@ -2134,7 +2135,7 @@ static abi_long do_setsockopt(int sockfd, int level, int optname,
             ret = get_errno(setsockopt(sockfd, level, optname, ip_mreq_source, optlen));
             unlock_user (ip_mreq_source, optval_addr, 0);
             break;
-
+        }
         default:
             goto unimplemented;
         }
@@ -2277,18 +2278,13 @@ static abi_long do_setsockopt(int sockfd, int level, int optname,
         switch (optname) {
         case ALG_SET_KEY:
         {
-            char *alg_key = g_malloc(optlen);
-
+            char *alg_key = lock_user(VERIFY_READ, optval_addr, optlen, 1);
             if (!alg_key) {
-                return -TARGET_ENOMEM;
-            }
-            if (copy_from_user(alg_key, optval_addr, optlen)) {
-                g_free(alg_key);
                 return -TARGET_EFAULT;
             }
             ret = get_errno(setsockopt(sockfd, level, optname,
                                        alg_key, optlen));
-            g_free(alg_key);
+            unlock_user(alg_key, optval_addr, optlen);
             break;
         }
         case ALG_SET_AEAD_AUTHSIZE:
@@ -2305,12 +2301,10 @@ static abi_long do_setsockopt(int sockfd, int level, int optname,
     case TARGET_SOL_SOCKET:
         switch (optname) {
         case TARGET_SO_RCVTIMEO:
+        case TARGET_SO_SNDTIMEO:
         {
                 struct timeval tv;
 
-                optname = SO_RCVTIMEO;
-
-set_timeout:
                 if (optlen != sizeof(struct target_timeval)) {
                     return -TARGET_EINVAL;
                 }
@@ -2319,13 +2313,12 @@ static abi_long do_setsockopt(int sockfd, int level, int optname,
                     return -TARGET_EFAULT;
                 }
 
-                ret = get_errno(setsockopt(sockfd, SOL_SOCKET, optname,
+                ret = get_errno(setsockopt(sockfd, SOL_SOCKET,
+                                optname == TARGET_SO_RCVTIMEO ?
+                                    SO_RCVTIMEO : SO_SNDTIMEO,
                                 &tv, sizeof(tv)));
                 return ret;
         }
-        case TARGET_SO_SNDTIMEO:
-                optname = SO_SNDTIMEO;
-                goto set_timeout;
         case TARGET_SO_ATTACH_FILTER:
         {
                 struct target_sock_fprog *tfprog;
@@ -9272,14 +9265,24 @@ static abi_long do_syscall1(CPUArchState *cpu_env, int num, abi_long arg1,
 #ifdef TARGET_NR_waitid
     case TARGET_NR_waitid:
         {
+            struct rusage ru;
             siginfo_t info;
-            info.si_pid = 0;
-            ret = get_errno(safe_waitid(arg1, arg2, &info, arg4, NULL));
-            if (!is_error(ret) && arg3 && info.si_pid != 0) {
-                if (!(p = lock_user(VERIFY_WRITE, arg3, sizeof(target_siginfo_t), 0)))
+
+            ret = get_errno(safe_waitid(arg1, arg2, (arg3 ? &info : NULL),
+                                        arg4, (arg5 ? &ru : NULL)));
+            if (!is_error(ret)) {
+                if (arg3) {
+                    p = lock_user(VERIFY_WRITE, arg3,
+                                  sizeof(target_siginfo_t), 0);
+                    if (!p) {
+                        return -TARGET_EFAULT;
+                    }
+                    host_to_target_siginfo(p, &info);
+                    unlock_user(p, arg3, sizeof(target_siginfo_t));
+                }
+                if (arg5 && host_to_target_rusage(arg5, &ru)) {
                     return -TARGET_EFAULT;
-                host_to_target_siginfo(p, &info);
-                unlock_user(p, arg3, sizeof(target_siginfo_t));
+                }
             }
         }
         return ret;

linux-user/syscall_defs.h

@@ -945,6 +945,7 @@ struct target_rtc_pll_info {
 
 #define TARGET_FIFREEZE    TARGET_IOWR('X', 119, abi_int)
 #define TARGET_FITHAW    TARGET_IOWR('X', 120, abi_int)
+#define TARGET_FITRIM    TARGET_IOWR('X', 121, struct fstrim_range)
 
 /*
  * Note that the ioctl numbers for FS_IOC_<GET|SET><FLAGS|VERSION>

linux-user/syscall_types.h

@@ -341,6 +341,11 @@ STRUCT(file_clone_range,
        TYPE_ULONGLONG, /* src_length */
        TYPE_ULONGLONG) /* dest_offset */
 
+STRUCT(fstrim_range,
+       TYPE_ULONGLONG, /* start */
+       TYPE_ULONGLONG, /* len */
+       TYPE_ULONGLONG) /* minlen */
+
 STRUCT(fiemap_extent,
        TYPE_ULONGLONG, /* fe_logical */
        TYPE_ULONGLONG, /* fe_physical */

target/arm/tcg/translate-a64.c

@@ -14179,7 +14179,7 @@ static void aarch64_tr_insn_start(DisasContextBase *dcbase, CPUState *cpu)
         pc_arg &= ~TARGET_PAGE_MASK;
     }
     tcg_gen_insn_start(pc_arg, 0, 0);
-    dc->insn_start = tcg_last_op();
+    dc->insn_start_updated = false;
 }
 
 static void aarch64_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu)