-----BEGIN PGP SIGNATURE-----

iQIcBAABAgAGBQJaZ0sNAAoJEPMMOL0/L7480bQP/i5QO0c4MrXJ7VaEa1u6ubfv
 AELpodvD6hm0qDT8OIH/4g1PRFZvB1OGg1wd8sZg/aLLbxfiKQ0kR+6Kq+W6LLJY
 qD4xddVZnBVlcSDwGn6Rg3bStgISOBr+Z7fAOtLOFc6BJz5JryU4PSPLXIb4gxtX
 0DXPXnSSTj+yZUjoG408aqAAlFRgbbXcY9Yhx3hblEO3ZJWAv7qrtoL67PEgB4kh
 j2t/6SSpEvsrmsb1g4N0/NMb6csOAwcA3kiTiOE2fGhc6vS7hUpcQPDQi/FHfkWD
 Q9Qe5y1TUE+JCc1VAdjWy3+42yH+IFpJo8lshJZw0tSGk3GCXeRUI6jlsawMphq/
 Xo9zrIcXcTY/1ZWB9FWypr0orFLMphQPY6cwEu/60QvzQA8coeJk27zqXgL/G78y
 7bNqLhMVz1JkKO4uCkRGQVJuijLo3aO3OeFSEnl8QoZInoOaPd+aVh/FCs57hV3r
 mcXT+ab9lbNrx0BTMI8Cr4HzvHH5cAfNg8hK/hh9rVHkAopLGvHkNJWOLbtAawds
 MulpKlLMnuntU/LGfAVU+ccttWt8Hfd5vRwS3Ex99sTIU/yBYh8iSAHh0lweE00p
 RmGMuVn+aXwcnDAsTXR6+8Zn5GzK+o9eifwlFdhI7AkCPwhra4fVodi0d/0imvGE
 XHLy02hVBGUp+Hoyf0/r
 =2ycl
 -----END PGP SIGNATURE-----

Merge remote-tracking branch 'remotes/vivier2/tags/linux-user-for-2.12-pull-request' into staging

# gpg: Signature made Tue 23 Jan 2018 14:47:41 GMT
# gpg:                using RSA key 0xF30C38BD3F2FBE3C
# gpg: Good signature from "Laurent Vivier <lvivier@redhat.com>"
# gpg:                 aka "Laurent Vivier <laurent@vivier.eu>"
# gpg:                 aka "Laurent Vivier (Red Hat) <lvivier@redhat.com>"
# Primary key fingerprint: CD2F 75DD C8E3 A4DC 2E4F  5173 F30C 38BD 3F2F BE3C

* remotes/vivier2/tags/linux-user-for-2.12-pull-request:
  linux-user: implement renameat2
  page_unprotect(): handle calls to pages that are PAGE_WRITE
  linux-user: Propagate siginfo_t through to handle_cpu_signal()
  linux-user: remove nmi.c and fw-path-provider.c
  linux-user: Add getcpu() support
  linux-user: Add AT_SECURE auxval
  linux-user: Fix sched_get/setaffinity conversion
  linux-user/mmap.c: Avoid choosing NULL as start address
  linux-user: Translate flags argument to dup3 syscall
  linux-user: Don't use CMSG_ALIGN(sizeof struct cmsghdr)
  linux-user: Fix length calculations in host_to_target_cmsg()
  linux-user: wrap fork() in a start/end exclusive section
  linux-user: Fix locking order in fork_start()

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

accel/tcg/translate-all.c

@@ -2181,29 +2181,41 @@ int page_unprotect(target_ulong address, uintptr_t pc)
 
     /* if the page was really writable, then we change its
        protection back to writable */
-    if ((p->flags & PAGE_WRITE_ORG) && !(p->flags & PAGE_WRITE)) {
+    if (p->flags & PAGE_WRITE_ORG) {
-        host_start = address & qemu_host_page_mask;
-        host_end = host_start + qemu_host_page_size;
-
-        prot = 0;
         current_tb_invalidated = false;
-        for (addr = host_start ; addr < host_end ; addr += TARGET_PAGE_SIZE) {
+        if (p->flags & PAGE_WRITE) {
-            p = page_find(addr >> TARGET_PAGE_BITS);
+            /* If the page is actually marked WRITE then assume this is because
-            p->flags |= PAGE_WRITE;
+             * this thread raced with another one which got here first and
-            prot |= p->flags;
+             * set the page to PAGE_WRITE and did the TB invalidate for us.
-
+             */
-            /* and since the content will be modified, we must invalidate
+#ifdef TARGET_HAS_PRECISE_SMC
-               the corresponding translated code. */
+            TranslationBlock *current_tb = tb_find_pc(pc);
-            current_tb_invalidated |= tb_invalidate_phys_page(addr, pc);
+            if (current_tb) {
-#ifdef CONFIG_USER_ONLY
+                current_tb_invalidated = tb_cflags(current_tb) & CF_INVALID;
-            if (DEBUG_TB_CHECK_GATE) {
-                tb_invalidate_check(addr);
             }
 #endif
-        }
+        } else {
-        mprotect((void *)g2h(host_start), qemu_host_page_size,
+            host_start = address & qemu_host_page_mask;
-                 prot & PAGE_BITS);
+            host_end = host_start + qemu_host_page_size;
 
+            prot = 0;
+            for (addr = host_start; addr < host_end; addr += TARGET_PAGE_SIZE) {
+                p = page_find(addr >> TARGET_PAGE_BITS);
+                p->flags |= PAGE_WRITE;
+                prot |= p->flags;
+
+                /* and since the content will be modified, we must invalidate
+                   the corresponding translated code. */
+                current_tb_invalidated |= tb_invalidate_phys_page(addr, pc);
+#ifdef CONFIG_USER_ONLY
+                if (DEBUG_TB_CHECK_GATE) {
+                    tb_invalidate_check(addr);
+                }
+#endif
+            }
+            mprotect((void *)g2h(host_start), qemu_host_page_size,
+                     prot & PAGE_BITS);
+        }
         mmap_unlock();
         /* If current TB was invalidated return to main loop */
         return current_tb_invalidated ? 2 : 1;

accel/tcg/user-exec.c

@@ -57,12 +57,13 @@ static void cpu_exit_tb_from_sighandler(CPUState *cpu, sigset_t *old_set)
    the effective address of the memory exception. 'is_write' is 1 if a
    write caused the exception and otherwise 0'. 'old_set' is the
    signal set which should be restored */
-static inline int handle_cpu_signal(uintptr_t pc, unsigned long address,
+static inline int handle_cpu_signal(uintptr_t pc, siginfo_t *info,
                                     int is_write, sigset_t *old_set)
 {
     CPUState *cpu = current_cpu;
     CPUClass *cc;
     int ret;
+    unsigned long address = (unsigned long)info->si_addr;
 
     /* We must handle PC addresses from two different sources:
      * a call return address and a signal frame address.
@@ -103,7 +104,18 @@ static inline int handle_cpu_signal(uintptr_t pc, unsigned long address,
            pc, address, is_write, *(unsigned long *)old_set);
 #endif
     /* XXX: locking issue */
-    if (is_write && h2g_valid(address)) {
+    /* Note that it is important that we don't call page_unprotect() unless
+     * this is really a "write to nonwriteable page" fault, because
+     * page_unprotect() assumes that if it is called for an access to
+     * a page that's writeable this means we had two threads racing and
+     * another thread got there first and already made the page writeable;
+     * so we will retry the access. If we were to call page_unprotect()
+     * for some other kind of fault that should really be passed to the
+     * guest, we'd end up in an infinite loop of retrying the faulting
+     * access.
+     */
+    if (is_write && info->si_signo == SIGSEGV && info->si_code == SEGV_ACCERR &&
+        h2g_valid(address)) {
         switch (page_unprotect(h2g(address), pc)) {
         case 0:
             /* Fault not caused by a page marked unwritable to protect
@@ -215,9 +227,8 @@ int cpu_signal_handler(int host_signum, void *pinfo,
 #endif
     pc = EIP_sig(uc);
     trapno = TRAP_sig(uc);
-    return handle_cpu_signal(pc, (unsigned long)info->si_addr,
+    return handle_cpu_signal(pc, info,
-                             trapno == 0xe ?
+                             trapno == 0xe ? (ERROR_sig(uc) >> 1) & 1 : 0,
-                             (ERROR_sig(uc) >> 1) & 1 : 0,
                              &MASK_sig(uc));
 }
 
@@ -261,9 +272,8 @@ int cpu_signal_handler(int host_signum, void *pinfo,
 #endif
 
     pc = PC_sig(uc);
-    return handle_cpu_signal(pc, (unsigned long)info->si_addr,
+    return handle_cpu_signal(pc, info,
-                             TRAP_sig(uc) == 0xe ?
+                             TRAP_sig(uc) == 0xe ? (ERROR_sig(uc) >> 1) & 1 : 0,
-                             (ERROR_sig(uc) >> 1) & 1 : 0,
                              &MASK_sig(uc));
 }
 
@@ -341,8 +351,7 @@ int cpu_signal_handler(int host_signum, void *pinfo,
         is_write = 1;
     }
 #endif
-    return handle_cpu_signal(pc, (unsigned long)info->si_addr,
+    return handle_cpu_signal(pc, info, is_write, &uc->uc_sigmask);
-                             is_write, &uc->uc_sigmask);
 }
 
 #elif defined(__alpha__)
@@ -372,8 +381,7 @@ int cpu_signal_handler(int host_signum, void *pinfo,
         is_write = 1;
     }
 
-    return handle_cpu_signal(pc, (unsigned long)info->si_addr,
+    return handle_cpu_signal(pc, info, is_write, &uc->uc_sigmask);
-                             is_write, &uc->uc_sigmask);
 }
 #elif defined(__sparc__)
 
@@ -432,8 +440,7 @@ int cpu_signal_handler(int host_signum, void *pinfo,
             break;
         }
     }
-    return handle_cpu_signal(pc, (unsigned long)info->si_addr,
+    return handle_cpu_signal(pc, info, is_write, sigmask);
-                             is_write, sigmask);
 }
 
 #elif defined(__arm__)
@@ -466,9 +473,7 @@ int cpu_signal_handler(int host_signum, void *pinfo,
      * later processor; on v5 we will always report this as a read).
      */
     is_write = extract32(uc->uc_mcontext.error_code, 11, 1);
-    return handle_cpu_signal(pc, (unsigned long)info->si_addr,
+    return handle_cpu_signal(pc, info, is_write, &uc->uc_sigmask);
-                             is_write,
-                             &uc->uc_sigmask);
 }
 
 #elif defined(__aarch64__)
@@ -495,8 +500,7 @@ int cpu_signal_handler(int host_signum, void *pinfo, void *puc)
                 /* Ignore bits 23 & 24, controlling indexing.  */
                 || (insn & 0x3a400000) == 0x28000000); /* C3.3.7,14-16 */
 
-    return handle_cpu_signal(pc, (uintptr_t)info->si_addr,
+    return handle_cpu_signal(pc, info, is_write, &uc->uc_sigmask);
-                             is_write, &uc->uc_sigmask);
 }
 
 #elif defined(__ia64)
@@ -529,9 +533,7 @@ int cpu_signal_handler(int host_signum, void *pinfo, void *puc)
     default:
         break;
     }
-    return handle_cpu_signal(ip, (unsigned long)info->si_addr,
+    return handle_cpu_signal(ip, info, is_write, (sigset_t *)&uc->uc_sigmask);
-                             is_write,
-                             (sigset_t *)&uc->uc_sigmask);
 }
 
 #elif defined(__s390__)
@@ -583,8 +585,7 @@ int cpu_signal_handler(int host_signum, void *pinfo,
         }
         break;
     }
-    return handle_cpu_signal(pc, (unsigned long)info->si_addr,
+    return handle_cpu_signal(pc, info, is_write, &uc->uc_sigmask);
-                             is_write, &uc->uc_sigmask);
 }
 
 #elif defined(__mips__)
@@ -599,8 +600,7 @@ int cpu_signal_handler(int host_signum, void *pinfo,
 
     /* XXX: compute is_write */
     is_write = 0;
-    return handle_cpu_signal(pc, (unsigned long)info->si_addr,
+    return handle_cpu_signal(pc, info, is_write, &uc->uc_sigmask);
-                             is_write, &uc->uc_sigmask);
 }
 
 #else

hw/core/Makefile.objs

@@ -1,11 +1,12 @@
 # core qdev-related obj files, also used by *-user:
 common-obj-y += qdev.o qdev-properties.o
 common-obj-y += bus.o reset.o
-common-obj-y += fw-path-provider.o
+common-obj-$(CONFIG_SOFTMMU) += qdev-fw.o
+common-obj-$(CONFIG_SOFTMMU) += fw-path-provider.o
 # irq.o needed for qdev GPIO handling:
 common-obj-y += irq.o
 common-obj-y += hotplug.o
-common-obj-y += nmi.o
+common-obj-$(CONFIG_SOFTMMU) += nmi.o
 
 common-obj-$(CONFIG_EMPTY_SLOT) += empty_slot.o
 common-obj-$(CONFIG_XILINX_AXI) += stream.o

hw/core/qdev-fw.c

@@ -0,0 +1,96 @@
+/*
+ *  qdev fw helpers
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License,
+ *  or (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "qemu/osdep.h"
+#include "hw/qdev.h"
+#include "hw/fw-path-provider.h"
+
+const char *qdev_fw_name(DeviceState *dev)
+{
+    DeviceClass *dc = DEVICE_GET_CLASS(dev);
+
+    if (dc->fw_name) {
+        return dc->fw_name;
+    }
+
+    return object_get_typename(OBJECT(dev));
+}
+
+static char *bus_get_fw_dev_path(BusState *bus, DeviceState *dev)
+{
+    BusClass *bc = BUS_GET_CLASS(bus);
+
+    if (bc->get_fw_dev_path) {
+        return bc->get_fw_dev_path(dev);
+    }
+
+    return NULL;
+}
+
+static char *qdev_get_fw_dev_path_from_handler(BusState *bus, DeviceState *dev)
+{
+    Object *obj = OBJECT(dev);
+    char *d = NULL;
+
+    while (!d && obj->parent) {
+        obj = obj->parent;
+        d = fw_path_provider_try_get_dev_path(obj, bus, dev);
+    }
+    return d;
+}
+
+char *qdev_get_own_fw_dev_path_from_handler(BusState *bus, DeviceState *dev)
+{
+    Object *obj = OBJECT(dev);
+
+    return fw_path_provider_try_get_dev_path(obj, bus, dev);
+}
+
+static int qdev_get_fw_dev_path_helper(DeviceState *dev, char *p, int size)
+{
+    int l = 0;
+
+    if (dev && dev->parent_bus) {
+        char *d;
+        l = qdev_get_fw_dev_path_helper(dev->parent_bus->parent, p, size);
+        d = qdev_get_fw_dev_path_from_handler(dev->parent_bus, dev);
+        if (!d) {
+            d = bus_get_fw_dev_path(dev->parent_bus, dev);
+        }
+        if (d) {
+            l += snprintf(p + l, size - l, "%s", d);
+            g_free(d);
+        } else {
+            return l;
+        }
+    }
+    l += snprintf(p + l , size - l, "/");
+
+    return l;
+}
+
+char *qdev_get_fw_dev_path(DeviceState *dev)
+{
+    char path[128];
+    int l;
+
+    l = qdev_get_fw_dev_path_helper(dev, path, 128);
+
+    path[l - 1] = '\0';
+
+    return g_strdup(path);
+}

hw/core/qdev.c

@@ -27,7 +27,6 @@
 
 #include "qemu/osdep.h"
 #include "hw/qdev.h"
-#include "hw/fw-path-provider.h"
 #include "sysemu/sysemu.h"
 #include "qapi/qmp/qerror.h"
 #include "qapi/visitor.h"
@@ -48,17 +47,6 @@ const VMStateDescription *qdev_get_vmsd(DeviceState *dev)
     return dc->vmsd;
 }
 
-const char *qdev_fw_name(DeviceState *dev)
-{
-    DeviceClass *dc = DEVICE_GET_CLASS(dev);
-
-    if (dc->fw_name) {
-        return dc->fw_name;
-    }
-
-    return object_get_typename(OBJECT(dev));
-}
-
 static void bus_remove_child(BusState *bus, DeviceState *child)
 {
     BusChild *kid;
@@ -631,71 +619,6 @@ DeviceState *qdev_find_recursive(BusState *bus, const char *id)
     return NULL;
 }
 
-static char *bus_get_fw_dev_path(BusState *bus, DeviceState *dev)
-{
-    BusClass *bc = BUS_GET_CLASS(bus);
-
-    if (bc->get_fw_dev_path) {
-        return bc->get_fw_dev_path(dev);
-    }
-
-    return NULL;
-}
-
-static char *qdev_get_fw_dev_path_from_handler(BusState *bus, DeviceState *dev)
-{
-    Object *obj = OBJECT(dev);
-    char *d = NULL;
-
-    while (!d && obj->parent) {
-        obj = obj->parent;
-        d = fw_path_provider_try_get_dev_path(obj, bus, dev);
-    }
-    return d;
-}
-
-char *qdev_get_own_fw_dev_path_from_handler(BusState *bus, DeviceState *dev)
-{
-    Object *obj = OBJECT(dev);
-
-    return fw_path_provider_try_get_dev_path(obj, bus, dev);
-}
-
-static int qdev_get_fw_dev_path_helper(DeviceState *dev, char *p, int size)
-{
-    int l = 0;
-
-    if (dev && dev->parent_bus) {
-        char *d;
-        l = qdev_get_fw_dev_path_helper(dev->parent_bus->parent, p, size);
-        d = qdev_get_fw_dev_path_from_handler(dev->parent_bus, dev);
-        if (!d) {
-            d = bus_get_fw_dev_path(dev->parent_bus, dev);
-        }
-        if (d) {
-            l += snprintf(p + l, size - l, "%s", d);
-            g_free(d);
-        } else {
-            return l;
-        }
-    }
-    l += snprintf(p + l , size - l, "/");
-
-    return l;
-}
-
-char* qdev_get_fw_dev_path(DeviceState *dev)
-{
-    char path[128];
-    int l;
-
-    l = qdev_get_fw_dev_path_helper(dev, path, 128);
-
-    path[l-1] = '\0';
-
-    return g_strdup(path);
-}
-
 char *qdev_get_dev_path(DeviceState *dev)
 {
     BusClass *bc;

linux-user/elfload.c

@@ -1354,7 +1354,7 @@ struct exec
                                  ~(abi_ulong)(TARGET_ELF_EXEC_PAGESIZE-1))
 #define TARGET_ELF_PAGEOFFSET(_v) ((_v) & (TARGET_ELF_EXEC_PAGESIZE-1))
 
-#define DLINFO_ITEMS 14
+#define DLINFO_ITEMS 15
 
 static inline void memcpy_fromfs(void * to, const void * from, unsigned long n)
 {
@@ -1786,6 +1786,7 @@ static abi_ulong create_elf_tables(abi_ulong p, int argc, int envc,
     NEW_AUX_ENT(AT_HWCAP, (abi_ulong) ELF_HWCAP);
     NEW_AUX_ENT(AT_CLKTCK, (abi_ulong) sysconf(_SC_CLK_TCK));
     NEW_AUX_ENT(AT_RANDOM, (abi_ulong) u_rand_bytes);
+    NEW_AUX_ENT(AT_SECURE, (abi_ulong) qemu_getauxval(AT_SECURE));
 
 #ifdef ELF_HWCAP2
     NEW_AUX_ENT(AT_HWCAP2, (abi_ulong) ELF_HWCAP2);

linux-user/main.c

@@ -127,9 +127,10 @@ int cpu_get_pic_interrupt(CPUX86State *env)
 /* Make sure everything is in a consistent state for calling fork().  */
 void fork_start(void)
 {
-    cpu_list_lock();
+    start_exclusive();
-    qemu_mutex_lock(&tb_ctx.tb_lock);
     mmap_fork_start();
+    qemu_mutex_lock(&tb_ctx.tb_lock);
+    cpu_list_lock();
 }
 
 void fork_end(int child)
@@ -147,9 +148,13 @@ void fork_end(int child)
         qemu_mutex_init(&tb_ctx.tb_lock);
         qemu_init_cpu_list();
         gdbserver_fork(thread_cpu);
+        /* qemu_init_cpu_list() takes care of reinitializing the
+         * exclusive state, so we don't need to end_exclusive() here.
+         */
     } else {
         qemu_mutex_unlock(&tb_ctx.tb_lock);
         cpu_list_unlock();
+        end_exclusive();
     }
 }
 

linux-user/mmap.c

@@ -234,7 +234,7 @@ static abi_ulong mmap_find_vma_reserved(abi_ulong start, abi_ulong size)
         if (prot) {
             end_addr = addr;
         }
-        if (addr + size == end_addr) {
+        if (addr && addr + size == end_addr) {
             break;
         }
         addr -= qemu_host_page_size;

linux-user/syscall.c

@@ -296,6 +296,8 @@ _syscall3(int, sys_sched_getaffinity, pid_t, pid, unsigned int, len,
 #define __NR_sys_sched_setaffinity __NR_sched_setaffinity
 _syscall3(int, sys_sched_setaffinity, pid_t, pid, unsigned int, len,
           unsigned long *, user_mask_ptr);
+#define __NR_sys_getcpu __NR_getcpu
+_syscall3(int, sys_getcpu, unsigned *, cpu, unsigned *, node, void *, tcache);
 _syscall4(int, reboot, int, magic1, int, magic2, unsigned int, cmd,
           void *, arg);
 _syscall2(int, capget, struct __user_cap_header_struct *, header,
@@ -598,6 +600,24 @@ static int sys_utimensat(int dirfd, const char *pathname,
 #endif
 #endif /* TARGET_NR_utimensat */
 
+#ifdef TARGET_NR_renameat2
+#if defined(__NR_renameat2)
+#define __NR_sys_renameat2 __NR_renameat2
+_syscall5(int, sys_renameat2, int, oldfd, const char *, old, int, newfd,
+          const char *, new, unsigned int, flags)
+#else
+static int sys_renameat2(int oldfd, const char *old,
+                         int newfd, const char *new, int flags)
+{
+    if (flags == 0) {
+        return renameat(oldfd, old, newfd, new);
+    }
+    errno = ENOSYS;
+    return -1;
+}
+#endif
+#endif /* TARGET_NR_renameat2 */
+
 #ifdef CONFIG_INOTIFY
 #include <sys/inotify.h>
 
@@ -1692,7 +1712,7 @@ static inline abi_long target_to_host_cmsg(struct msghdr *msgh,
         void *target_data = TARGET_CMSG_DATA(target_cmsg);
 
         int len = tswapal(target_cmsg->cmsg_len)
-                  - TARGET_CMSG_ALIGN(sizeof (struct target_cmsghdr));
+            - sizeof(struct target_cmsghdr);
 
         space += CMSG_SPACE(len);
         if (space > msgh->msg_controllen) {
@@ -1773,7 +1793,7 @@ static inline abi_long host_to_target_cmsg(struct target_msghdr *target_msgh,
         void *data = CMSG_DATA(cmsg);
         void *target_data = TARGET_CMSG_DATA(target_cmsg);
 
-        int len = cmsg->cmsg_len - CMSG_ALIGN(sizeof (struct cmsghdr));
+        int len = cmsg->cmsg_len - sizeof(struct cmsghdr);
         int tgt_len, tgt_space;
 
         /* We never copy a half-header but may copy half-data;
@@ -1782,7 +1802,7 @@ static inline abi_long host_to_target_cmsg(struct target_msghdr *target_msgh,
          * to the guest via the CTRUNC bit), unlike truncation
          * in target_to_host_cmsg, which is a QEMU bug.
          */
-        if (msg_controllen < sizeof(struct cmsghdr)) {
+        if (msg_controllen < sizeof(struct target_cmsghdr)) {
             target_msgh->msg_flags |= tswap32(MSG_CTRUNC);
             break;
         }
@@ -1794,8 +1814,6 @@ static inline abi_long host_to_target_cmsg(struct target_msghdr *target_msgh,
         }
         target_cmsg->cmsg_type = tswap32(cmsg->cmsg_type);
 
-        tgt_len = TARGET_CMSG_LEN(len);
-
         /* Payload types which need a different size of payload on
          * the target must adjust tgt_len here.
          */
@@ -1809,12 +1827,13 @@ static inline abi_long host_to_target_cmsg(struct target_msghdr *target_msgh,
                 break;
             }
         default:
+            tgt_len = len;
             break;
         }
 
-        if (msg_controllen < tgt_len) {
+        if (msg_controllen < TARGET_CMSG_LEN(tgt_len)) {
             target_msgh->msg_flags |= tswap32(MSG_CTRUNC);
-            tgt_len = msg_controllen;
+            tgt_len = msg_controllen - sizeof(struct target_cmsghdr);
         }
 
         /* We must now copy-and-convert len bytes of payload
@@ -1875,6 +1894,10 @@ static inline abi_long host_to_target_cmsg(struct target_msghdr *target_msgh,
                 uint32_t *v = (uint32_t *)data;
                 uint32_t *t_int = (uint32_t *)target_data;
 
+                if (len != sizeof(uint32_t) ||
+                    tgt_len != sizeof(uint32_t)) {
+                    goto unimplemented;
+                }
                 __put_user(*v, t_int);
                 break;
             }
@@ -1888,6 +1911,10 @@ static inline abi_long host_to_target_cmsg(struct target_msghdr *target_msgh,
                 struct errhdr_t *target_errh =
                     (struct errhdr_t *)target_data;
 
+                if (len != sizeof(struct errhdr_t) ||
+                    tgt_len != sizeof(struct errhdr_t)) {
+                    goto unimplemented;
+                }
                 __put_user(errh->ee.ee_errno, &target_errh->ee.ee_errno);
                 __put_user(errh->ee.ee_origin, &target_errh->ee.ee_origin);
                 __put_user(errh->ee.ee_type,  &target_errh->ee.ee_type);
@@ -1911,6 +1938,10 @@ static inline abi_long host_to_target_cmsg(struct target_msghdr *target_msgh,
                 uint32_t *v = (uint32_t *)data;
                 uint32_t *t_int = (uint32_t *)target_data;
 
+                if (len != sizeof(uint32_t) ||
+                    tgt_len != sizeof(uint32_t)) {
+                    goto unimplemented;
+                }
                 __put_user(*v, t_int);
                 break;
             }
@@ -1924,6 +1955,10 @@ static inline abi_long host_to_target_cmsg(struct target_msghdr *target_msgh,
                 struct errhdr6_t *target_errh =
                     (struct errhdr6_t *)target_data;
 
+                if (len != sizeof(struct errhdr6_t) ||
+                    tgt_len != sizeof(struct errhdr6_t)) {
+                    goto unimplemented;
+                }
                 __put_user(errh->ee.ee_errno, &target_errh->ee.ee_errno);
                 __put_user(errh->ee.ee_origin, &target_errh->ee.ee_origin);
                 __put_user(errh->ee.ee_type,  &target_errh->ee.ee_type);
@@ -1950,8 +1985,8 @@ static inline abi_long host_to_target_cmsg(struct target_msghdr *target_msgh,
             }
         }
 
-        target_cmsg->cmsg_len = tswapal(tgt_len);
+        target_cmsg->cmsg_len = tswapal(TARGET_CMSG_LEN(tgt_len));
-        tgt_space = TARGET_CMSG_SPACE(len);
+        tgt_space = TARGET_CMSG_SPACE(tgt_len);
         if (msg_controllen < tgt_space) {
             tgt_space = msg_controllen;
         }
@@ -7716,6 +7751,73 @@ static TargetFdTrans target_inotify_trans = {
 };
 #endif
 
+static int target_to_host_cpu_mask(unsigned long *host_mask,
+                                   size_t host_size,
+                                   abi_ulong target_addr,
+                                   size_t target_size)
+{
+    unsigned target_bits = sizeof(abi_ulong) * 8;
+    unsigned host_bits = sizeof(*host_mask) * 8;
+    abi_ulong *target_mask;
+    unsigned i, j;
+
+    assert(host_size >= target_size);
+
+    target_mask = lock_user(VERIFY_READ, target_addr, target_size, 1);
+    if (!target_mask) {
+        return -TARGET_EFAULT;
+    }
+    memset(host_mask, 0, host_size);
+
+    for (i = 0 ; i < target_size / sizeof(abi_ulong); i++) {
+        unsigned bit = i * target_bits;
+        abi_ulong val;
+
+        __get_user(val, &target_mask[i]);
+        for (j = 0; j < target_bits; j++, bit++) {
+            if (val & (1UL << j)) {
+                host_mask[bit / host_bits] |= 1UL << (bit % host_bits);
+            }
+        }
+    }
+
+    unlock_user(target_mask, target_addr, 0);
+    return 0;
+}
+
+static int host_to_target_cpu_mask(const unsigned long *host_mask,
+                                   size_t host_size,
+                                   abi_ulong target_addr,
+                                   size_t target_size)
+{
+    unsigned target_bits = sizeof(abi_ulong) * 8;
+    unsigned host_bits = sizeof(*host_mask) * 8;
+    abi_ulong *target_mask;
+    unsigned i, j;
+
+    assert(host_size >= target_size);
+
+    target_mask = lock_user(VERIFY_WRITE, target_addr, target_size, 0);
+    if (!target_mask) {
+        return -TARGET_EFAULT;
+    }
+
+    for (i = 0 ; i < target_size / sizeof(abi_ulong); i++) {
+        unsigned bit = i * target_bits;
+        abi_ulong val = 0;
+
+        for (j = 0; j < target_bits; j++, bit++) {
+            if (host_mask[bit / host_bits] & (1UL << (bit % host_bits))) {
+                val |= 1UL << j;
+            }
+        }
+        __put_user(val, &target_mask[i]);
+    }
+
+    unlock_user(target_mask, target_addr, target_size);
+    return 0;
+}
+
 /* do_syscall() should always have a single exit point at the end so
    that actions, such as logging of syscall results, can be performed.
    All errnos that do_syscall() returns must be -TARGET_<errcode>. */
@@ -8342,6 +8444,22 @@ abi_long do_syscall(void *cpu_env, int num, abi_long arg1,
         }
         break;
 #endif
+#if defined(TARGET_NR_renameat2)
+    case TARGET_NR_renameat2:
+        {
+            void *p2;
+            p  = lock_user_string(arg2);
+            p2 = lock_user_string(arg4);
+            if (!p || !p2) {
+                ret = -TARGET_EFAULT;
+            } else {
+                ret = get_errno(sys_renameat2(arg1, p, arg3, p2, arg5));
+            }
+            unlock_user(p2, arg4, 0);
+            unlock_user(p, arg2, 0);
+        }
+        break;
+#endif
 #ifdef TARGET_NR_mkdir
     case TARGET_NR_mkdir:
         if (!(p = lock_user_string(arg1)))
@@ -8475,11 +8593,19 @@ abi_long do_syscall(void *cpu_env, int num, abi_long arg1,
 #endif
 #if defined(CONFIG_DUP3) && defined(TARGET_NR_dup3)
     case TARGET_NR_dup3:
-        ret = get_errno(dup3(arg1, arg2, arg3));
+    {
+        int host_flags;
+
+        if ((arg3 & ~TARGET_O_CLOEXEC) != 0) {
+            return -EINVAL;
+        }
+        host_flags = target_to_host_bitmask(arg3, fcntl_flags_tbl);
+        ret = get_errno(dup3(arg1, arg2, host_flags));
         if (ret >= 0) {
             fd_trans_dup(arg1, arg2);
         }
         break;
+    }
 #endif
 #ifdef TARGET_NR_getppid /* not on alpha */
     case TARGET_NR_getppid:
@@ -10353,6 +10479,7 @@ abi_long do_syscall(void *cpu_env, int num, abi_long arg1,
             mask_size = (arg2 + (sizeof(*mask) - 1)) & ~(sizeof(*mask) - 1);
 
             mask = alloca(mask_size);
+            memset(mask, 0, mask_size);
             ret = get_errno(sys_sched_getaffinity(arg1, mask_size, mask));
 
             if (!is_error(ret)) {
@@ -10372,9 +10499,7 @@ abi_long do_syscall(void *cpu_env, int num, abi_long arg1,
                     ret = arg2;
                 }
 
-                if (copy_to_user(arg3, mask, ret)) {
+                ret = host_to_target_cpu_mask(mask, mask_size, arg3, arg2);
-                    goto efault;
-                }
             }
         }
         break;
@@ -10392,17 +10517,33 @@ abi_long do_syscall(void *cpu_env, int num, abi_long arg1,
                 break;
             }
             mask_size = (arg2 + (sizeof(*mask) - 1)) & ~(sizeof(*mask) - 1);
-
             mask = alloca(mask_size);
-            if (!lock_user_struct(VERIFY_READ, p, arg3, 1)) {
+
-                goto efault;
+            ret = target_to_host_cpu_mask(mask, mask_size, arg3, arg2);
+            if (ret) {
+                break;
             }
-            memcpy(mask, p, arg2);
-            unlock_user_struct(p, arg2, 0);
 
             ret = get_errno(sys_sched_setaffinity(arg1, mask_size, mask));
         }
         break;
+    case TARGET_NR_getcpu:
+        {
+            unsigned cpu, node;
+            ret = get_errno(sys_getcpu(arg1 ? &cpu : NULL,
+                                       arg2 ? &node : NULL,
+                                       NULL));
+            if (is_error(ret)) {
+                goto fail;
+            }
+            if (arg1 && put_user_u32(cpu, arg1)) {
+                goto efault;
+            }
+            if (arg2 && put_user_u32(node, arg2)) {
+                goto efault;
+            }
+        }
+        break;
     case TARGET_NR_sched_setparam:
         {
             struct sched_param *target_schp;

linux-user/syscall_defs.h

@@ -303,9 +303,9 @@ struct target_cmsghdr {
                                __target_cmsg_nxthdr(mhdr, cmsg, cmsg_start)
 #define TARGET_CMSG_ALIGN(len) (((len) + sizeof (abi_long) - 1) \
                                & (size_t) ~(sizeof (abi_long) - 1))
-#define TARGET_CMSG_SPACE(len) (TARGET_CMSG_ALIGN (len) \
+#define TARGET_CMSG_SPACE(len) (sizeof(struct target_cmsghdr) + \
-                               + TARGET_CMSG_ALIGN (sizeof (struct target_cmsghdr)))
+                                TARGET_CMSG_ALIGN(len))
-#define TARGET_CMSG_LEN(len)   (TARGET_CMSG_ALIGN (sizeof (struct target_cmsghdr)) + (len))
+#define TARGET_CMSG_LEN(len) (sizeof(struct target_cmsghdr) + (len))
 
 static __inline__ struct target_cmsghdr *
 __target_cmsg_nxthdr(struct target_msghdr *__mhdr,