Merge tag 'pull-tcg-20220621' of https://gitlab.com/rth7680/qemu into staging

Speed empty timer list in qemu_clock_deadline_ns_all.
Implement remainder for Power3.1 hosts.
Optimize ppc host icache flushing.
Cleanups to tcg_accel_ops_init.
Fix mmio crash accessing unmapped physical memory.

# -----BEGIN PGP SIGNATURE-----
#
# iQFRBAABCgA7FiEEekgeeIaLTbaoWgXAZN846K9+IV8FAmKyLesdHHJpY2hhcmQu
# aGVuZGVyc29uQGxpbmFyby5vcmcACgkQZN846K9+IV8O1wf5AW6JeeUTs2r3owsK
# UpVaRqjlLpNeuktoOQoG8lbVzm1ulEv7zgXYJTZg4cc/83WQZ2G8WzTj3W+Qr/S9
# ECRd73Kou+fK3jTo8I+wPLQjLjkIV4xSABMGz/onxhoAeyS+xcAI4qGuSGrtIg2r
# sQ61V4fWCwvQJdHMyG756Xsh8Xjf18mrNQZ5PLGkyn/e9UIAc4KH6FsgWJdinGEs
# V/oibY20kCXpLxN0ajNmx3x4/NFs/ymMtn1z9fdhVGjAVPY0N6YsxjsGqd/WP/5U
# ui/x0wAhl/VNK2M2+z3hVGfNlMpkzTVG2A3ndD+tYI3nofwTYb/UiakhID7ZX1cQ
# yKDyAw==
# =3Rhw
# -----END PGP SIGNATURE-----
# gpg: Signature made Tue 21 Jun 2022 01:45:31 PM PDT
# gpg:                using RSA key 7A481E78868B4DB6A85A05C064DF38E8AF7E215F
# gpg:                issuer "richard.henderson@linaro.org"
# gpg: Good signature from "Richard Henderson <richard.henderson@linaro.org>" [ultimate]

* tag 'pull-tcg-20220621' of https://gitlab.com/rth7680/qemu:
  util/cacheflush: Optimize flushing when ppc host has coherent icache
  util/cacheflush: Merge aarch64 ctr_el0 usage
  util: Merge cacheflush.c and cacheinfo.c
  softmmu: Always initialize xlat in address_space_translate_for_iotlb
  qemu-timer: Skip empty timer lists before locking in qemu_clock_deadline_ns_all
  accel/tcg: Reorganize tcg_accel_ops_init()
  accel/tcg: Init TCG cflags in vCPU thread handler
  target/avr: Drop avr_cpu_memory_rw_debug()
  tcg/ppc: implement rem[u]_i{32,64} with mod[su][wd]

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

4 files changed, 235 insertions, 217 deletions

diff --git a/util/cacheflush.c b/util/cacheflush.c
index 4b57186d89..2c2c73e085 100644
--- a/util/cacheflush.c
+++ b/util/cacheflush.c
@@ -1,5 +1,5 @@
 /*
- * Flush the host cpu caches.
+ * Info about, and flushing the host cpu caches.
  *
  * This work is licensed under the terms of the GNU GPL, version 2 or later.
  * See the COPYING file in the top-level directory.
@@ -9,8 +9,218 @@
 #include "qemu/cacheflush.h"
 #include "qemu/cacheinfo.h"
 #include "qemu/bitops.h"
+#include "qemu/host-utils.h"
+#include "qemu/atomic.h"
 
 
+int qemu_icache_linesize = 0;
+int qemu_icache_linesize_log;
+int qemu_dcache_linesize = 0;
+int qemu_dcache_linesize_log;
+
+/*
+ * Operating system specific cache detection mechanisms.
+ */
+
+#if defined(_WIN32)
+
+static void sys_cache_info(int *isize, int *dsize)
+{
+    SYSTEM_LOGICAL_PROCESSOR_INFORMATION *buf;
+    DWORD size = 0;
+    BOOL success;
+    size_t i, n;
+
+    /*
+     * Check for the required buffer size first.  Note that if the zero
+     * size we use for the probe results in success, then there is no
+     * data available; fail in that case.
+     */
+    success = GetLogicalProcessorInformation(0, &size);
+    if (success || GetLastError() != ERROR_INSUFFICIENT_BUFFER) {
+        return;
+    }
+
+    n = size / sizeof(SYSTEM_LOGICAL_PROCESSOR_INFORMATION);
+    size = n * sizeof(SYSTEM_LOGICAL_PROCESSOR_INFORMATION);
+    buf = g_new0(SYSTEM_LOGICAL_PROCESSOR_INFORMATION, n);
+    if (!GetLogicalProcessorInformation(buf, &size)) {
+        goto fail;
+    }
+
+    for (i = 0; i < n; i++) {
+        if (buf[i].Relationship == RelationCache
+            && buf[i].Cache.Level == 1) {
+            switch (buf[i].Cache.Type) {
+            case CacheUnified:
+                *isize = *dsize = buf[i].Cache.LineSize;
+                break;
+            case CacheInstruction:
+                *isize = buf[i].Cache.LineSize;
+                break;
+            case CacheData:
+                *dsize = buf[i].Cache.LineSize;
+                break;
+            default:
+                break;
+            }
+        }
+    }
+ fail:
+    g_free(buf);
+}
+
+#elif defined(CONFIG_DARWIN)
+# include <sys/sysctl.h>
+static void sys_cache_info(int *isize, int *dsize)
+{
+    /* There's only a single sysctl for both I/D cache line sizes.  */
+    long size;
+    size_t len = sizeof(size);
+    if (!sysctlbyname("hw.cachelinesize", &size, &len, NULL, 0)) {
+        *isize = *dsize = size;
+    }
+}
+#elif defined(__FreeBSD__) || defined(__FreeBSD_kernel__)
+# include <sys/sysctl.h>
+static void sys_cache_info(int *isize, int *dsize)
+{
+    /* There's only a single sysctl for both I/D cache line sizes.  */
+    int size;
+    size_t len = sizeof(size);
+    if (!sysctlbyname("machdep.cacheline_size", &size, &len, NULL, 0)) {
+        *isize = *dsize = size;
+    }
+}
+#else
+/* POSIX */
+
+static void sys_cache_info(int *isize, int *dsize)
+{
+# ifdef _SC_LEVEL1_ICACHE_LINESIZE
+    int tmp_isize = (int) sysconf(_SC_LEVEL1_ICACHE_LINESIZE);
+    if (tmp_isize > 0) {
+        *isize = tmp_isize;
+    }
+# endif
+# ifdef _SC_LEVEL1_DCACHE_LINESIZE
+    int tmp_dsize = (int) sysconf(_SC_LEVEL1_DCACHE_LINESIZE);
+    if (tmp_dsize > 0) {
+        *dsize = tmp_dsize;
+    }
+# endif
+}
+#endif /* sys_cache_info */
+
+
+/*
+ * Architecture (+ OS) specific cache detection mechanisms.
+ */
+
+#if defined(__powerpc__)
+static bool have_coherent_icache;
+#endif
+
+#if defined(__aarch64__) && !defined(CONFIG_DARWIN)
+/* Apple does not expose CTR_EL0, so we must use system interfaces. */
+static uint64_t save_ctr_el0;
+static void arch_cache_info(int *isize, int *dsize)
+{
+    uint64_t ctr;
+
+    /*
+     * The real cache geometry is in CCSIDR_EL1/CLIDR_EL1/CSSELR_EL1,
+     * but (at least under Linux) these are marked protected by the
+     * kernel.  However, CTR_EL0 contains the minimum linesize in the
+     * entire hierarchy, and is used by userspace cache flushing.
+     *
+     * We will also use this value in flush_idcache_range.
+     */
+    asm volatile("mrs\t%0, ctr_el0" : "=r"(ctr));
+    save_ctr_el0 = ctr;
+
+    if (*isize == 0 || *dsize == 0) {
+        if (*isize == 0) {
+            *isize = 4 << (ctr & 0xf);
+        }
+        if (*dsize == 0) {
+            *dsize = 4 << ((ctr >> 16) & 0xf);
+        }
+    }
+}
+
+#elif defined(_ARCH_PPC) && defined(__linux__)
+# include "elf.h"
+
+static void arch_cache_info(int *isize, int *dsize)
+{
+    if (*isize == 0) {
+        *isize = qemu_getauxval(AT_ICACHEBSIZE);
+    }
+    if (*dsize == 0) {
+        *dsize = qemu_getauxval(AT_DCACHEBSIZE);
+    }
+    have_coherent_icache = qemu_getauxval(AT_HWCAP) & PPC_FEATURE_ICACHE_SNOOP;
+}
+
+#else
+static void arch_cache_info(int *isize, int *dsize) { }
+#endif /* arch_cache_info */
+
+/*
+ * ... and if all else fails ...
+ */
+
+static void fallback_cache_info(int *isize, int *dsize)
+{
+    /* If we can only find one of the two, assume they're the same.  */
+    if (*isize) {
+        if (*dsize) {
+            /* Success! */
+        } else {
+            *dsize = *isize;
+        }
+    } else if (*dsize) {
+        *isize = *dsize;
+    } else {
+#if defined(_ARCH_PPC)
+        /*
+         * For PPC, we're going to use the cache sizes computed for
+         * flush_idcache_range.  Which means that we must use the
+         * architecture minimum.
+         */
+        *isize = *dsize = 16;
+#else
+        /* Otherwise, 64 bytes is not uncommon.  */
+        *isize = *dsize = 64;
+#endif
+    }
+}
+
+static void __attribute__((constructor)) init_cache_info(void)
+{
+    int isize = 0, dsize = 0;
+
+    sys_cache_info(&isize, &dsize);
+    arch_cache_info(&isize, &dsize);
+    fallback_cache_info(&isize, &dsize);
+
+    assert((isize & (isize - 1)) == 0);
+    assert((dsize & (dsize - 1)) == 0);
+
+    qemu_icache_linesize = isize;
+    qemu_icache_linesize_log = ctz32(isize);
+    qemu_dcache_linesize = dsize;
+    qemu_dcache_linesize_log = ctz32(dsize);
+
+    qatomic64_init();
+}
+
+
+/*
+ * Architecture (+ OS) specific cache flushing mechanisms.
+ */
+
 #if defined(__i386__) || defined(__x86_64__) || defined(__s390__)
 
 /* Caches are coherent and do not require flushing; symbol inline. */
@@ -29,17 +239,6 @@ void flush_idcache_range(uintptr_t rx, uintptr_t rw, size_t len)
 #else
 
 /*
- * TODO: unify this with cacheinfo.c.
- * We want to save the whole contents of CTR_EL0, so that we
- * have more than the linesize, but also IDC and DIC.
- */
-static uint64_t save_ctr_el0;
-static void __attribute__((constructor)) init_ctr_el0(void)
-{
-    asm volatile("mrs\t%0, ctr_el0" : "=r"(save_ctr_el0));
-}
-
-/*
  * This is a copy of gcc's __aarch64_sync_cache_range, modified
  * to fit this three-operand interface.
  */
@@ -48,8 +247,8 @@ void flush_idcache_range(uintptr_t rx, uintptr_t rw, size_t len)
     const unsigned CTR_IDC = 1u << 28;
     const unsigned CTR_DIC = 1u << 29;
     const uint64_t ctr_el0 = save_ctr_el0;
-    const uintptr_t icache_lsize = 4 << extract64(ctr_el0, 0, 4);
-    const uintptr_t dcache_lsize = 4 << extract64(ctr_el0, 16, 4);
+    const uintptr_t icache_lsize = qemu_icache_linesize;
+    const uintptr_t dcache_lsize = qemu_dcache_linesize;
     uintptr_t p;
 
     /*
@@ -104,8 +303,24 @@ void flush_idcache_range(uintptr_t rx, uintptr_t rw, size_t len)
 void flush_idcache_range(uintptr_t rx, uintptr_t rw, size_t len)
 {
     uintptr_t p, b, e;
-    size_t dsize = qemu_dcache_linesize;
-    size_t isize = qemu_icache_linesize;
+    size_t dsize, isize;
+
+    /*
+     * Some processors have coherent caches and support a simplified
+     * flushing procedure.  See
+     *   POWER9 UM, 4.6.2.2 Instruction Cache Block Invalidate (icbi) 
+     *   https://ibm.ent.box.com/s/tmklq90ze7aj8f4n32er1mu3sy9u8k3k
+     */
+    if (have_coherent_icache) {
+        asm volatile ("sync\n\t"
+                      "icbi 0,%0\n\t"
+                      "isync"
+                      : : "r"(rx) : "memory");
+        return;
+    }
+
+    dsize = qemu_dcache_linesize;
+    isize = qemu_icache_linesize;
 
     b = rw & ~(dsize - 1);
     e = (rw + len + dsize - 1) & ~(dsize - 1);
diff --git a/util/cacheinfo.c b/util/cacheinfo.c
deleted file mode 100644
index ab1644d490..0000000000
--- a/util/cacheinfo.c
+++ /dev/null
@@ -1,200 +0,0 @@
-/*
- * cacheinfo.c - helpers to query the host about its caches
- *
- * Copyright (C) 2017, Emilio G. Cota <cota@braap.org>
- * License: GNU GPL, version 2 or later.
- *   See the COPYING file in the top-level directory.
- */
-
-#include "qemu/osdep.h"
-#include "qemu/host-utils.h"
-#include "qemu/atomic.h"
-#include "qemu/cacheinfo.h"
-
-int qemu_icache_linesize = 0;
-int qemu_icache_linesize_log;
-int qemu_dcache_linesize = 0;
-int qemu_dcache_linesize_log;
-
-/*
- * Operating system specific detection mechanisms.
- */
-
-#if defined(_WIN32)
-
-static void sys_cache_info(int *isize, int *dsize)
-{
-    SYSTEM_LOGICAL_PROCESSOR_INFORMATION *buf;
-    DWORD size = 0;
-    BOOL success;
-    size_t i, n;
-
-    /* Check for the required buffer size first.  Note that if the zero
-       size we use for the probe results in success, then there is no
-       data available; fail in that case.  */
-    success = GetLogicalProcessorInformation(0, &size);
-    if (success || GetLastError() != ERROR_INSUFFICIENT_BUFFER) {
-        return;
-    }
-
-    n = size / sizeof(SYSTEM_LOGICAL_PROCESSOR_INFORMATION);
-    size = n * sizeof(SYSTEM_LOGICAL_PROCESSOR_INFORMATION);
-    buf = g_new0(SYSTEM_LOGICAL_PROCESSOR_INFORMATION, n);
-    if (!GetLogicalProcessorInformation(buf, &size)) {
-        goto fail;
-    }
-
-    for (i = 0; i < n; i++) {
-        if (buf[i].Relationship == RelationCache
-            && buf[i].Cache.Level == 1) {
-            switch (buf[i].Cache.Type) {
-            case CacheUnified:
-                *isize = *dsize = buf[i].Cache.LineSize;
-                break;
-            case CacheInstruction:
-                *isize = buf[i].Cache.LineSize;
-                break;
-            case CacheData:
-                *dsize = buf[i].Cache.LineSize;
-                break;
-            default:
-                break;
-            }
-        }
-    }
- fail:
-    g_free(buf);
-}
-
-#elif defined(__APPLE__)
-# include <sys/sysctl.h>
-static void sys_cache_info(int *isize, int *dsize)
-{
-    /* There's only a single sysctl for both I/D cache line sizes.  */
-    long size;
-    size_t len = sizeof(size);
-    if (!sysctlbyname("hw.cachelinesize", &size, &len, NULL, 0)) {
-        *isize = *dsize = size;
-    }
-}
-#elif defined(__FreeBSD__) || defined(__FreeBSD_kernel__)
-# include <sys/sysctl.h>
-static void sys_cache_info(int *isize, int *dsize)
-{
-    /* There's only a single sysctl for both I/D cache line sizes.  */
-    int size;
-    size_t len = sizeof(size);
-    if (!sysctlbyname("machdep.cacheline_size", &size, &len, NULL, 0)) {
-        *isize = *dsize = size;
-    }
-}
-#else
-/* POSIX */
-
-static void sys_cache_info(int *isize, int *dsize)
-{
-# ifdef _SC_LEVEL1_ICACHE_LINESIZE
-    int tmp_isize = (int) sysconf(_SC_LEVEL1_ICACHE_LINESIZE);
-    if (tmp_isize > 0) {
-        *isize = tmp_isize;
-    }
-# endif
-# ifdef _SC_LEVEL1_DCACHE_LINESIZE
-    int tmp_dsize = (int) sysconf(_SC_LEVEL1_DCACHE_LINESIZE);
-    if (tmp_dsize > 0) {
-        *dsize = tmp_dsize;
-    }
-# endif
-}
-#endif /* sys_cache_info */
-
-/*
- * Architecture (+ OS) specific detection mechanisms.
- */
-
-#if defined(__aarch64__)
-
-static void arch_cache_info(int *isize, int *dsize)
-{
-    if (*isize == 0 || *dsize == 0) {
-        uint64_t ctr;
-
-        /* The real cache geometry is in CCSIDR_EL1/CLIDR_EL1/CSSELR_EL1,
-           but (at least under Linux) these are marked protected by the
-           kernel.  However, CTR_EL0 contains the minimum linesize in the
-           entire hierarchy, and is used by userspace cache flushing.  */
-        asm volatile("mrs\t%0, ctr_el0" : "=r"(ctr));
-        if (*isize == 0) {
-            *isize = 4 << (ctr & 0xf);
-        }
-        if (*dsize == 0) {
-            *dsize = 4 << ((ctr >> 16) & 0xf);
-        }
-    }
-}
-
-#elif defined(_ARCH_PPC) && defined(__linux__)
-# include "elf.h"
-
-static void arch_cache_info(int *isize, int *dsize)
-{
-    if (*isize == 0) {
-        *isize = qemu_getauxval(AT_ICACHEBSIZE);
-    }
-    if (*dsize == 0) {
-        *dsize = qemu_getauxval(AT_DCACHEBSIZE);
-    }
-}
-
-#else
-static void arch_cache_info(int *isize, int *dsize) { }
-#endif /* arch_cache_info */
-
-/*
- * ... and if all else fails ...
- */
-
-static void fallback_cache_info(int *isize, int *dsize)
-{
-    /* If we can only find one of the two, assume they're the same.  */
-    if (*isize) {
-        if (*dsize) {
-            /* Success! */
-        } else {
-            *dsize = *isize;
-        }
-    } else if (*dsize) {
-        *isize = *dsize;
-    } else {
-#if defined(_ARCH_PPC)
-        /*
-         * For PPC, we're going to use the cache sizes computed for
-         * flush_idcache_range.  Which means that we must use the
-         * architecture minimum.
-         */
-        *isize = *dsize = 16;
-#else
-        /* Otherwise, 64 bytes is not uncommon.  */
-        *isize = *dsize = 64;
-#endif
-    }
-}
-
-static void __attribute__((constructor)) init_cache_info(void)
-{
-    int isize = 0, dsize = 0;
-
-    sys_cache_info(&isize, &dsize);
-    arch_cache_info(&isize, &dsize);
-    fallback_cache_info(&isize, &dsize);
-
-    assert((isize & (isize - 1)) == 0);
-    assert((dsize & (dsize - 1)) == 0);
-
-    qemu_icache_linesize = isize;
-    qemu_icache_linesize_log = ctz32(isize);
-    qemu_dcache_linesize = dsize;
-    qemu_dcache_linesize_log = ctz32(dsize);
-
-    qatomic64_init();
-}
diff --git a/util/meson.build b/util/meson.build
index 8f16018cd4..4939b0b91c 100644
--- a/util/meson.build
+++ b/util/meson.build
@@ -27,7 +27,7 @@ util_ss.add(files('envlist.c', 'path.c', 'module.c'))
 util_ss.add(files('host-utils.c'))
 util_ss.add(files('bitmap.c', 'bitops.c'))
 util_ss.add(files('fifo8.c'))
-util_ss.add(files('cacheinfo.c', 'cacheflush.c'))
+util_ss.add(files('cacheflush.c'))
 util_ss.add(files('error.c', 'error-report.c'))
 util_ss.add(files('qemu-print.c'))
 util_ss.add(files('id.c'))
diff --git a/util/qemu-timer.c b/util/qemu-timer.c
index a670a57881..6a0de33dd2 100644
--- a/util/qemu-timer.c
+++ b/util/qemu-timer.c
@@ -261,6 +261,9 @@ int64_t qemu_clock_deadline_ns_all(QEMUClockType type, int attr_mask)
     }
 
     QLIST_FOREACH(timer_list, &clock->timerlists, list) {
+        if (!qatomic_read(&timer_list->active_timers)) {
+            continue;
+        }
         qemu_mutex_lock(&timer_list->active_timers_lock);
         ts = timer_list->active_timers;
         /* Skip all external timers */