Merge tag 'linux-user-for-7.0-pull-request' of https://gitlab.com/laurent_vivier/qemu into staging

linux-user pull request 20220324

Fix MIPS n32
Fix ppoll, epoll_wait, pselect
Fix error message in elfload.c
Implement ARM __kernel_memory_barrier/__kernel_cmpxchg/__kernel_cmpxchg64

# gpg: Signature made Thu 24 Mar 2022 08:19:57 GMT
# gpg:                using RSA key CD2F75DDC8E3A4DC2E4F5173F30C38BD3F2FBE3C
# gpg:                issuer "laurent@vivier.eu"
# gpg: Good signature from "Laurent Vivier <lvivier@redhat.com>" [full]
# gpg:                 aka "Laurent Vivier <laurent@vivier.eu>" [full]
# gpg:                 aka "Laurent Vivier (Red Hat) <lvivier@redhat.com>" [full]
# Primary key fingerprint: CD2F 75DD C8E3 A4DC 2E4F  5173 F30C 38BD 3F2F BE3C

* tag 'linux-user-for-7.0-pull-request' of https://gitlab.com/laurent_vivier/qemu:
  linux-user/arm: Implement __kernel_cmpxchg64 with host atomics
  linux-user/arm: Implement __kernel_cmpxchg with host atomics
  linux-user/arm: Implement __kernel_memory_barrier
  linux-user: Fix missing space in error message
  linux-user: Properly handle sigset arg to ppoll
  linux-user: Properly handle sigset arg to epoll_pwait
  linux-user: Properly handle sigset arg to pselect
  linux-user: Split out helpers for sigsuspend
  linux-user/alpha: Fix sigsuspend for big-endian hosts
  linux-user: Fix syscall parameter handling for MIPS n32

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

6 files changed, 195 insertions, 145 deletions

diff --git a/linux-user/arm/cpu_loop.c b/linux-user/arm/cpu_loop.c
index 032e1ff..aae375d 100644
--- a/linux-user/arm/cpu_loop.c
+++ b/linux-user/arm/cpu_loop.c
@@ -75,10 +75,70 @@
         put_user_u16(__x, (gaddr));                     \
     })
 
-/* Commpage handling -- there is no commpage for AArch64 */
+/*
+ * Similar to code in accel/tcg/user-exec.c, but outside the execution loop.
+ * Must be called with mmap_lock.
+ * We get the PC of the entry address - which is as good as anything,
+ * on a real kernel what you get depends on which mode it uses.
+ */
+static void *atomic_mmu_lookup(CPUArchState *env, uint32_t addr, int size)
+{
+    int need_flags = PAGE_READ | PAGE_WRITE_ORG | PAGE_VALID;
+    int page_flags;
+
+    /* Enforce guest required alignment.  */
+    if (unlikely(addr & (size - 1))) {
+        force_sig_fault(TARGET_SIGBUS, TARGET_BUS_ADRALN, addr);
+        return NULL;
+    }
+
+    page_flags = page_get_flags(addr);
+    if (unlikely((page_flags & need_flags) != need_flags)) {
+        force_sig_fault(TARGET_SIGSEGV,
+                        page_flags & PAGE_VALID ?
+                        TARGET_SEGV_ACCERR : TARGET_SEGV_MAPERR, addr);
+        return NULL;
+    }
+
+    return g2h(env_cpu(env), addr);
+}
+
+/*
+ * See the Linux kernel's Documentation/arm/kernel_user_helpers.rst
+ * Input:
+ * r0 = oldval
+ * r1 = newval
+ * r2 = pointer to target value
+ *
+ * Output:
+ * r0 = 0 if *ptr was changed, non-0 if no exchange happened
+ * C set if *ptr was changed, clear if no exchange happened
+ */
+static void arm_kernel_cmpxchg32_helper(CPUARMState *env)
+{
+    uint32_t oldval, newval, val, addr, cpsr, *host_addr;
+
+    oldval = env->regs[0];
+    newval = env->regs[1];
+    addr = env->regs[2];
+
+    mmap_lock();
+    host_addr = atomic_mmu_lookup(env, addr, 4);
+    if (!host_addr) {
+        mmap_unlock();
+        return;
+    }
+
+    val = qatomic_cmpxchg__nocheck(host_addr, oldval, newval);
+    mmap_unlock();
+
+    cpsr = (val == oldval) * CPSR_C;
+    cpsr_write(env, cpsr, CPSR_C, CPSRWriteByInstr);
+    env->regs[0] = cpsr ? 0 : -1;
+}
 
 /*
- * See the Linux kernel's Documentation/arm/kernel_user_helpers.txt
+ * See the Linux kernel's Documentation/arm/kernel_user_helpers.rst
  * Input:
  * r0 = pointer to oldval
  * r1 = pointer to newval
@@ -95,57 +155,54 @@ static void arm_kernel_cmpxchg64_helper(CPUARMState *env)
 {
     uint64_t oldval, newval, val;
     uint32_t addr, cpsr;
+    uint64_t *host_addr;
 
-    /* Based on the 32 bit code in do_kernel_trap */
-
-    /* XXX: This only works between threads, not between processes.
-       It's probably possible to implement this with native host
-       operations. However things like ldrex/strex are much harder so
-       there's not much point trying.  */
-    start_exclusive();
-    cpsr = cpsr_read(env);
-    addr = env->regs[2];
-
-    if (get_user_u64(oldval, env->regs[0])) {
-        env->exception.vaddress = env->regs[0];
+    addr = env->regs[0];
+    if (get_user_u64(oldval, addr)) {
         goto segv;
-    };
+    }
 
-    if (get_user_u64(newval, env->regs[1])) {
-        env->exception.vaddress = env->regs[1];
+    addr = env->regs[1];
+    if (get_user_u64(newval, addr)) {
         goto segv;
-    };
+    }
 
-    if (get_user_u64(val, addr)) {
-        env->exception.vaddress = addr;
-        goto segv;
+    mmap_lock();
+    addr = env->regs[2];
+    host_addr = atomic_mmu_lookup(env, addr, 8);
+    if (!host_addr) {
+        mmap_unlock();
+        return;
     }
 
+#ifdef CONFIG_ATOMIC64
+    val = qatomic_cmpxchg__nocheck(host_addr, oldval, newval);
+    cpsr = (val == oldval) * CPSR_C;
+#else
+    /*
+     * This only works between threads, not between processes, but since
+     * the host has no 64-bit cmpxchg, it is the best that we can do.
+     */
+    start_exclusive();
+    val = *host_addr;
     if (val == oldval) {
-        val = newval;
-
-        if (put_user_u64(val, addr)) {
-            env->exception.vaddress = addr;
-            goto segv;
-        };
-
-        env->regs[0] = 0;
-        cpsr |= CPSR_C;
+        *host_addr = newval;
+        cpsr = CPSR_C;
     } else {
-        env->regs[0] = -1;
-        cpsr &= ~CPSR_C;
+        cpsr = 0;
     }
-    cpsr_write(env, cpsr, CPSR_C, CPSRWriteByInstr);
     end_exclusive();
+#endif
+    mmap_unlock();
+
+    cpsr_write(env, cpsr, CPSR_C, CPSRWriteByInstr);
+    env->regs[0] = cpsr ? 0 : -1;
     return;
 
-segv:
-    end_exclusive();
-    /* We get the PC of the entry address - which is as good as anything,
-       on a real kernel what you get depends on which mode it uses. */
-    /* XXX: check env->error_code */
-    force_sig_fault(TARGET_SIGSEGV, TARGET_SEGV_MAPERR,
-                    env->exception.vaddress);
+ segv:
+    force_sig_fault(TARGET_SIGSEGV,
+                    page_get_flags(addr) & PAGE_VALID ?
+                    TARGET_SEGV_ACCERR : TARGET_SEGV_MAPERR, addr);
 }
 
 /* Handle a jump to the kernel code page.  */
@@ -153,36 +210,13 @@ static int
 do_kernel_trap(CPUARMState *env)
 {
     uint32_t addr;
-    uint32_t cpsr;
-    uint32_t val;
 
     switch (env->regs[15]) {
     case 0xffff0fa0: /* __kernel_memory_barrier */
-        /* ??? No-op. Will need to do better for SMP.  */
+        smp_mb();
         break;
     case 0xffff0fc0: /* __kernel_cmpxchg */
-         /* XXX: This only works between threads, not between processes.
-            It's probably possible to implement this with native host
-            operations. However things like ldrex/strex are much harder so
-            there's not much point trying.  */
-        start_exclusive();
-        cpsr = cpsr_read(env);
-        addr = env->regs[2];
-        /* FIXME: This should SEGV if the access fails.  */
-        if (get_user_u32(val, addr))
-            val = ~env->regs[0];
-        if (val == env->regs[0]) {
-            val = env->regs[1];
-            /* FIXME: Check for segfaults.  */
-            put_user_u32(val, addr);
-            env->regs[0] = 0;
-            cpsr |= CPSR_C;
-        } else {
-            env->regs[0] = -1;
-            cpsr &= ~CPSR_C;
-        }
-        cpsr_write(env, cpsr, CPSR_C, CPSRWriteByInstr);
-        end_exclusive();
+        arm_kernel_cmpxchg32_helper(env);
         break;
     case 0xffff0fe0: /* __kernel_get_tls */
         env->regs[0] = cpu_get_tls(env);
diff --git a/linux-user/elfload.c b/linux-user/elfload.c
index 9628a38..c45da4d 100644
--- a/linux-user/elfload.c
+++ b/linux-user/elfload.c
@@ -2504,7 +2504,7 @@ static void pgb_reserved_va(const char *image_name, abi_ulong guest_loaddr,
     addr = mmap(test, reserved_va, PROT_NONE, flags, -1, 0);
     if (addr == MAP_FAILED || addr != test) {
         error_report("Unable to reserve 0x%lx bytes of virtual address "
-                     "space at %p (%s) for use as guest address space (check your"
+                     "space at %p (%s) for use as guest address space (check your "
                      "virtual memory ulimit setting, min_mmap_addr or reserve less "
                      "using -R option)", reserved_va, test, strerror(errno));
         exit(EXIT_FAILURE);
diff --git a/linux-user/signal-common.h b/linux-user/signal-common.h
index 2113165..6a7e4a9 100644
--- a/linux-user/signal-common.h
+++ b/linux-user/signal-common.h
@@ -92,4 +92,30 @@ abi_long do_swapcontext(CPUArchState *env, abi_ulong uold_ctx,
  */
 int block_signals(void); /* Returns non zero if signal pending */
 
+/**
+ * process_sigsuspend_mask: read and apply syscall-local signal mask
+ *
+ * Read the guest signal mask from @sigset, length @sigsize.
+ * Convert that to a host signal mask and save it to sigpending_mask.
+ *
+ * Return value: negative target errno, or zero;
+ *               store &sigpending_mask into *pset on success.
+ */
+int process_sigsuspend_mask(sigset_t **pset, target_ulong sigset,
+                            target_ulong sigsize);
+
+/**
+ * finish_sigsuspend_mask: finish a sigsuspend-like syscall
+ *
+ * Set in_sigsuspend if we need to use the modified sigset
+ * during process_pending_signals.
+ */
+static inline void finish_sigsuspend_mask(int ret)
+{
+    if (ret != -QEMU_ERESTARTSYS) {
+        TaskState *ts = (TaskState *)thread_cpu->opaque;
+        ts->in_sigsuspend = 1;
+    }
+}
+
 #endif
diff --git a/linux-user/signal.c b/linux-user/signal.c
index 2a3f3cc..092e70b 100644
--- a/linux-user/signal.c
+++ b/linux-user/signal.c
@@ -1199,3 +1199,26 @@ void process_pending_signals(CPUArchState *cpu_env)
     }
     ts->in_sigsuspend = 0;
 }
+
+int process_sigsuspend_mask(sigset_t **pset, target_ulong sigset,
+                            target_ulong sigsize)
+{
+    TaskState *ts = (TaskState *)thread_cpu->opaque;
+    sigset_t *host_set = &ts->sigsuspend_mask;
+    target_sigset_t *target_sigset;
+
+    if (sigsize != sizeof(*target_sigset)) {
+        /* Like the kernel, we enforce correct size sigsets */
+        return -TARGET_EINVAL;
+    }
+
+    target_sigset = lock_user(VERIFY_READ, sigset, sigsize, 1);
+    if (!target_sigset) {
+        return -TARGET_EFAULT;
+    }
+    target_to_host_sigset(host_set, target_sigset);
+    unlock_user(target_sigset, sigset, 0);
+
+    *pset = host_set;
+    return 0;
+}
diff --git a/linux-user/syscall.c b/linux-user/syscall.c
index 75ed71e..f65045e 100644
--- a/linux-user/syscall.c
+++ b/linux-user/syscall.c
@@ -1391,14 +1391,12 @@ static abi_long do_pselect6(abi_long arg1, abi_long arg2, abi_long arg3,
      * The 6th arg is actually two args smashed together,
      * so we cannot use the C library.
      */
-    sigset_t set;
     struct {
         sigset_t *set;
         size_t size;
     } sig, *sig_ptr;
 
     abi_ulong arg_sigset, arg_sigsize, *arg7;
-    target_sigset_t *target_sigset;
 
     n = arg1;
     rfd_addr = arg2;
@@ -1439,10 +1437,8 @@ static abi_long do_pselect6(abi_long arg1, abi_long arg2, abi_long arg3,
     }
 
     /* Extract the two packed args for the sigset */
+    sig_ptr = NULL;
     if (arg6) {
-        sig_ptr = &sig;
-        sig.size = SIGSET_T_SIZE;
-
         arg7 = lock_user(VERIFY_READ, arg6, sizeof(*arg7) * 2, 1);
         if (!arg7) {
             return -TARGET_EFAULT;
@@ -1452,28 +1448,22 @@ static abi_long do_pselect6(abi_long arg1, abi_long arg2, abi_long arg3,
         unlock_user(arg7, arg6, 0);
 
         if (arg_sigset) {
-            sig.set = &set;
-            if (arg_sigsize != sizeof(*target_sigset)) {
-                /* Like the kernel, we enforce correct size sigsets */
-                return -TARGET_EINVAL;
-            }
-            target_sigset = lock_user(VERIFY_READ, arg_sigset,
-                                      sizeof(*target_sigset), 1);
-            if (!target_sigset) {
-                return -TARGET_EFAULT;
+            ret = process_sigsuspend_mask(&sig.set, arg_sigset, arg_sigsize);
+            if (ret != 0) {
+                return ret;
             }
-            target_to_host_sigset(&set, target_sigset);
-            unlock_user(target_sigset, arg_sigset, 0);
-        } else {
-            sig.set = NULL;
+            sig_ptr = &sig;
+            sig.size = SIGSET_T_SIZE;
         }
-    } else {
-        sig_ptr = NULL;
     }
 
     ret = get_errno(safe_pselect6(n, rfds_ptr, wfds_ptr, efds_ptr,
                                   ts_ptr, sig_ptr));
 
+    if (sig_ptr) {
+        finish_sigsuspend_mask(ret);
+    }
+
     if (!is_error(ret)) {
         if (rfd_addr && copy_to_user_fdset(rfd_addr, &rfds, n)) {
             return -TARGET_EFAULT;
@@ -1529,8 +1519,7 @@ static abi_long do_ppoll(abi_long arg1, abi_long arg2, abi_long arg3,
     }
     if (ppoll) {
         struct timespec _timeout_ts, *timeout_ts = &_timeout_ts;
-        target_sigset_t *target_set;
-        sigset_t _set, *set = &_set;
+        sigset_t *set = NULL;
 
         if (arg3) {
             if (time64) {
@@ -1549,25 +1538,19 @@ static abi_long do_ppoll(abi_long arg1, abi_long arg2, abi_long arg3,
         }
 
         if (arg4) {
-            if (arg5 != sizeof(target_sigset_t)) {
-                unlock_user(target_pfd, arg1, 0);
-                return -TARGET_EINVAL;
-            }
-
-            target_set = lock_user(VERIFY_READ, arg4,
-                                   sizeof(target_sigset_t), 1);
-            if (!target_set) {
+            ret = process_sigsuspend_mask(&set, arg4, arg5);
+            if (ret != 0) {
                 unlock_user(target_pfd, arg1, 0);
-                return -TARGET_EFAULT;
+                return ret;
             }
-            target_to_host_sigset(set, target_set);
-        } else {
-            set = NULL;
         }
 
         ret = get_errno(safe_ppoll(pfd, nfds, timeout_ts,
                                    set, SIGSET_T_SIZE));
 
+        if (set) {
+            finish_sigsuspend_mask(ret);
+        }
         if (!is_error(ret) && arg3) {
             if (time64) {
                 if (host_to_target_timespec64(arg3, timeout_ts)) {
@@ -1579,9 +1562,6 @@ static abi_long do_ppoll(abi_long arg1, abi_long arg2, abi_long arg3,
                 }
             }
         }
-        if (arg4) {
-            unlock_user(target_set, arg4, 0);
-        }
     } else {
           struct timespec ts, *pts;
 
@@ -9557,40 +9537,35 @@ static abi_long do_syscall1(void *cpu_env, int num, abi_long arg1,
 #ifdef TARGET_NR_sigsuspend
     case TARGET_NR_sigsuspend:
         {
-            TaskState *ts = cpu->opaque;
+            sigset_t *set;
+
 #if defined(TARGET_ALPHA)
-            abi_ulong mask = arg1;
-            target_to_host_old_sigset(&ts->sigsuspend_mask, &mask);
+            TaskState *ts = cpu->opaque;
+            /* target_to_host_old_sigset will bswap back */
+            abi_ulong mask = tswapal(arg1);
+            set = &ts->sigsuspend_mask;
+            target_to_host_old_sigset(set, &mask);
 #else
-            if (!(p = lock_user(VERIFY_READ, arg1, sizeof(target_sigset_t), 1)))
-                return -TARGET_EFAULT;
-            target_to_host_old_sigset(&ts->sigsuspend_mask, p);
-            unlock_user(p, arg1, 0);
-#endif
-            ret = get_errno(safe_rt_sigsuspend(&ts->sigsuspend_mask,
-                                               SIGSET_T_SIZE));
-            if (ret != -QEMU_ERESTARTSYS) {
-                ts->in_sigsuspend = 1;
+            ret = process_sigsuspend_mask(&set, arg1, sizeof(target_sigset_t));
+            if (ret != 0) {
+                return ret;
             }
+#endif
+            ret = get_errno(safe_rt_sigsuspend(set, SIGSET_T_SIZE));
+            finish_sigsuspend_mask(ret);
         }
         return ret;
 #endif
     case TARGET_NR_rt_sigsuspend:
         {
-            TaskState *ts = cpu->opaque;
+            sigset_t *set;
 
-            if (arg2 != sizeof(target_sigset_t)) {
-                return -TARGET_EINVAL;
-            }
-            if (!(p = lock_user(VERIFY_READ, arg1, sizeof(target_sigset_t), 1)))
-                return -TARGET_EFAULT;
-            target_to_host_sigset(&ts->sigsuspend_mask, p);
-            unlock_user(p, arg1, 0);
-            ret = get_errno(safe_rt_sigsuspend(&ts->sigsuspend_mask,
-                                               SIGSET_T_SIZE));
-            if (ret != -QEMU_ERESTARTSYS) {
-                ts->in_sigsuspend = 1;
+            ret = process_sigsuspend_mask(&set, arg1, arg2);
+            if (ret != 0) {
+                return ret;
             }
+            ret = get_errno(safe_rt_sigsuspend(set, SIGSET_T_SIZE));
+            finish_sigsuspend_mask(ret);
         }
         return ret;
 #ifdef TARGET_NR_rt_sigtimedwait
@@ -12709,29 +12684,21 @@ static abi_long do_syscall1(void *cpu_env, int num, abi_long arg1,
 #if defined(TARGET_NR_epoll_pwait)
         case TARGET_NR_epoll_pwait:
         {
-            target_sigset_t *target_set;
-            sigset_t _set, *set = &_set;
+            sigset_t *set = NULL;
 
             if (arg5) {
-                if (arg6 != sizeof(target_sigset_t)) {
-                    ret = -TARGET_EINVAL;
-                    break;
-                }
-
-                target_set = lock_user(VERIFY_READ, arg5,
-                                       sizeof(target_sigset_t), 1);
-                if (!target_set) {
-                    ret = -TARGET_EFAULT;
+                ret = process_sigsuspend_mask(&set, arg5, arg6);
+                if (ret != 0) {
                     break;
                 }
-                target_to_host_sigset(set, target_set);
-                unlock_user(target_set, arg5, 0);
-            } else {
-                set = NULL;
             }
 
             ret = get_errno(safe_epoll_pwait(epfd, ep, maxevents, timeout,
                                              set, SIGSET_T_SIZE));
+
+            if (set) {
+                finish_sigsuspend_mask(ret);
+            }
             break;
         }
 #endif
diff --git a/linux-user/user-internals.h b/linux-user/user-internals.h
index a8fdd69..ee152cc 100644
--- a/linux-user/user-internals.h
+++ b/linux-user/user-internals.h
@@ -112,7 +112,7 @@ static inline int is_error(abi_long ret)
     return (abi_ulong)ret >= (abi_ulong)(-4096);
 }
 
-#if TARGET_ABI_BITS == 32
+#if (TARGET_ABI_BITS == 32) && !defined(TARGET_ABI_MIPSN32)
 static inline uint64_t target_offset64(uint32_t word0, uint32_t word1)
 {
 #ifdef TARGET_WORDS_BIGENDIAN
@@ -121,7 +121,7 @@ static inline uint64_t target_offset64(uint32_t word0, uint32_t word1)
     return ((uint64_t)word1 << 32) | word0;
 #endif
 }
-#else /* TARGET_ABI_BITS == 32 */
+#else /* TARGET_ABI_BITS == 32 && !defined(TARGET_ABI_MIPSN32) */
 static inline uint64_t target_offset64(uint64_t word0, uint64_t word1)
 {
     return word0;
@@ -136,7 +136,7 @@ static inline int regpairs_aligned(void *cpu_env, int num)
 {
     return ((((CPUARMState *)cpu_env)->eabi) == 1) ;
 }
-#elif defined(TARGET_MIPS) && (TARGET_ABI_BITS == 32)
+#elif defined(TARGET_MIPS) && defined(TARGET_ABI_MIPSO32)
 static inline int regpairs_aligned(void *cpu_env, int num) { return 1; }
 #elif defined(TARGET_PPC) && !defined(TARGET_PPC64)
 /*