linux-user pull request 20220928-v2

use 'max' instead of 'qemu32' / 'qemu64'
 add  pidfd_open(), pidfd_send_signal() and pidfd_getfd()
 Improve madvise(MADV_DONTNEED)
 futex syscal rework
 strace improvement
 HP/PA fixes and improvement
 Misc fixes
 -----BEGIN PGP SIGNATURE-----
 
 iQJGBAABCAAwFiEEzS913cjjpNwuT1Fz8ww4vT8vvjwFAmM0riISHGxhdXJlbnRA
 dml2aWVyLmV1AAoJEPMMOL0/L748gH4P/2wesXJKPMY2zQzP3Rld4iyefoPGG/Yp
 mdq59BbjO2jQMR8GBss/nl9l84cIzzkYRQIogaKsjljtZYm/OO5xRefqrzJY6apD
 eidxv20dAVjuaXHAIdGhbFlxot1ctExbZs9atB4uj5DWxfYGD6e/stoBy5/pSmr4
 M5EbGHhyrRI7tRbHGtVQVvG6AT6XGE0pT9tzT5JLaApF8UPMkgJwmez16PNWvcMm
 v8GEvKm/vEVS8CCpzLV4kfwVeo3f54VAOrEBDi29ph2Yo50IA21k8BvoRZaSp+Kn
 G6TMnnly/DkMspAs5EOVfat+kv3TziNNdDH7EnVU1vV1yTDdZgW/1204Uy/JY0Pw
 WotwAFuO9FYeHKmjY0CfnIIZZHYZpDYUOZ8M6dESD/O0EjoB8LMf5p9cbYlze4DE
 csJZCsVcz19HDv6QZXi5mvvDcJ83B2IDb8/PUAzSc0n62lXL9qjYD0wdb0QsLdAT
 I25qLDge1HCmQfCIKcaoHYvE0pDmvkF6ftuQUXLtIwtaV0Z/N5wDf2PEHikjOYHM
 gD2izz23/2wQx6KP/9ZNnCJ5QEBkEgm5wpHncsvjzSzi1uIdNlHyzJJwGTAcc5qZ
 hOeoJ7dT0D6g0BGnvOdg2W/bDx18KW65mNDxE4d+W0uzn0YmQtArk2YsnhKQNO46
 12/0ltPFnSV/
 =DIzQ
 -----END PGP SIGNATURE-----

Merge tag 'linux-user-for-7.2-pull-request' of https://gitlab.com/laurent_vivier/qemu into staging

linux-user pull request 20220928-v2

use 'max' instead of 'qemu32' / 'qemu64'
add  pidfd_open(), pidfd_send_signal() and pidfd_getfd()
Improve madvise(MADV_DONTNEED)
futex syscal rework
strace improvement
HP/PA fixes and improvement
Misc fixes

# -----BEGIN PGP SIGNATURE-----
#
# iQJGBAABCAAwFiEEzS913cjjpNwuT1Fz8ww4vT8vvjwFAmM0riISHGxhdXJlbnRA
# dml2aWVyLmV1AAoJEPMMOL0/L748gH4P/2wesXJKPMY2zQzP3Rld4iyefoPGG/Yp
# mdq59BbjO2jQMR8GBss/nl9l84cIzzkYRQIogaKsjljtZYm/OO5xRefqrzJY6apD
# eidxv20dAVjuaXHAIdGhbFlxot1ctExbZs9atB4uj5DWxfYGD6e/stoBy5/pSmr4
# M5EbGHhyrRI7tRbHGtVQVvG6AT6XGE0pT9tzT5JLaApF8UPMkgJwmez16PNWvcMm
# v8GEvKm/vEVS8CCpzLV4kfwVeo3f54VAOrEBDi29ph2Yo50IA21k8BvoRZaSp+Kn
# G6TMnnly/DkMspAs5EOVfat+kv3TziNNdDH7EnVU1vV1yTDdZgW/1204Uy/JY0Pw
# WotwAFuO9FYeHKmjY0CfnIIZZHYZpDYUOZ8M6dESD/O0EjoB8LMf5p9cbYlze4DE
# csJZCsVcz19HDv6QZXi5mvvDcJ83B2IDb8/PUAzSc0n62lXL9qjYD0wdb0QsLdAT
# I25qLDge1HCmQfCIKcaoHYvE0pDmvkF6ftuQUXLtIwtaV0Z/N5wDf2PEHikjOYHM
# gD2izz23/2wQx6KP/9ZNnCJ5QEBkEgm5wpHncsvjzSzi1uIdNlHyzJJwGTAcc5qZ
# hOeoJ7dT0D6g0BGnvOdg2W/bDx18KW65mNDxE4d+W0uzn0YmQtArk2YsnhKQNO46
# 12/0ltPFnSV/
# =DIzQ
# -----END PGP SIGNATURE-----
# gpg: Signature made Wed 28 Sep 2022 16:27:14 EDT
# 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-7.2-pull-request' of https://gitlab.com/laurent_vivier/qemu: (37 commits)
  linux-user: Add parameters of getrandom() syscall for strace
  linux-user: Lock log around strace
  linux-user: Update print_futex_op
  linux-user: Implement PI futexes
  linux-user: Convert signal number for FUTEX_FD
  linux-user: Implement FUTEX_WAKE_BITSET
  linux-user: Sink call to do_safe_futex
  linux-user: Combine do_futex and do_futex_time64
  linux-user: Set ELF_BASE_PLATFORM for MIPS
  linux-user: Introduce stubs for ELF AT_BASE_PLATFORM
  linux-user/s390x: Save/restore fpc when handling a signal
  linux-user: Don't assume 0 is not a valid host timer_t value
  linux-user: fix bug about missing signum convert of sigqueue
  linux-user/hppa: Fix setup_sigcontext()
  linux-user/hppa: Allow PROT_GROWSUP and PROT_GROWSDOWN in mprotect()
  linux-user/hppa: Increase guest stack size to 80MB for hppa target
  linux-user/hppa: Drop stack guard page on hppa target
  linux-user/hppa: Add signal trampoline for hppa target
  linux-user: Add proper strace format strings for getdents()/getdents64()
  linux-user: Fix TARGET_PROT_SEM for XTENSA
  ...

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

accel/tcg/translate-all.c

@@ -2258,7 +2258,7 @@ int page_get_flags(target_ulong address)
 #ifndef PAGE_TARGET_STICKY
 #define PAGE_TARGET_STICKY  0
 #endif
-#define PAGE_STICKY  (PAGE_ANON | PAGE_TARGET_STICKY)
+#define PAGE_STICKY  (PAGE_ANON | PAGE_PASSTHROUGH | PAGE_TARGET_STICKY)
 
 /* Modify the flags of a page and invalidate the code if necessary.
    The flag PAGE_WRITE_ORG is positioned automatically depending

include/exec/cpu-all.h

@@ -262,6 +262,12 @@ extern const TargetPageBits target_page;
 #define PAGE_TARGET_1  0x0200
 #define PAGE_TARGET_2  0x0400
 
+/*
+ * For linux-user, indicates that the page is mapped with the same semantics
+ * in both guest and host.
+ */
+#define PAGE_PASSTHROUGH 0x0800
+
 #if defined(CONFIG_USER_ONLY)
 void page_dump(FILE *f);
 

linux-user/aarch64/target_mman.h

@@ -0,0 +1 @@
+#include "../generic/target_mman.h"

linux-user/alpha/target_mman.h

@@ -0,0 +1,8 @@
+#ifndef ALPHA_TARGET_MMAN_H
+#define ALPHA_TARGET_MMAN_H
+
+#define TARGET_MADV_DONTNEED 6
+
+#include "../generic/target_mman.h"
+
+#endif

linux-user/arm/target_mman.h

@@ -0,0 +1 @@
+#include "../generic/target_mman.h"

linux-user/cpu_loop-common.h

@@ -27,9 +27,11 @@
 do {                                                                    \
     CPUState *cs = env_cpu(env);                                        \
     fprintf(stderr, fmt , ## __VA_ARGS__);                              \
+    fprintf(stderr, "Failing executable: %s\n", exec_path);             \
     cpu_dump_state(cs, stderr, 0);                                      \
     if (qemu_log_separate()) {                                          \
         qemu_log(fmt, ## __VA_ARGS__);                                  \
+        qemu_log("Failing executable: %s\n", exec_path);                \
         log_cpu_state(cs, 0);                                           \
     }                                                                   \
 } while (0)

linux-user/cris/target_mman.h

@@ -0,0 +1 @@
+#include "../generic/target_mman.h"

linux-user/elfload.c

@@ -1080,6 +1080,37 @@ static uint32_t get_elf_hwcap(void)
 #define elf_check_abi(x) (!((x) & EF_MIPS_ABI2))
 #endif
 
+#define ELF_BASE_PLATFORM get_elf_base_platform()
+
+#define MATCH_PLATFORM_INSN(_flags, _base_platform)      \
+    do { if ((cpu->env.insn_flags & (_flags)) == _flags) \
+    { return _base_platform; } } while (0)
+
+static const char *get_elf_base_platform(void)
+{
+    MIPSCPU *cpu = MIPS_CPU(thread_cpu);
+
+    /* 64 bit ISAs goes first */
+    MATCH_PLATFORM_INSN(CPU_MIPS64R6, "mips64r6");
+    MATCH_PLATFORM_INSN(CPU_MIPS64R5, "mips64r5");
+    MATCH_PLATFORM_INSN(CPU_MIPS64R2, "mips64r2");
+    MATCH_PLATFORM_INSN(CPU_MIPS64R1, "mips64");
+    MATCH_PLATFORM_INSN(CPU_MIPS5, "mips5");
+    MATCH_PLATFORM_INSN(CPU_MIPS4, "mips4");
+    MATCH_PLATFORM_INSN(CPU_MIPS3, "mips3");
+
+    /* 32 bit ISAs */
+    MATCH_PLATFORM_INSN(CPU_MIPS32R6, "mips32r6");
+    MATCH_PLATFORM_INSN(CPU_MIPS32R5, "mips32r5");
+    MATCH_PLATFORM_INSN(CPU_MIPS32R2, "mips32r2");
+    MATCH_PLATFORM_INSN(CPU_MIPS32R1, "mips32");
+    MATCH_PLATFORM_INSN(CPU_MIPS2, "mips2");
+
+    /* Fallback */
+    return "mips";
+}
+#undef MATCH_PLATFORM_INSN
+
 static inline void init_thread(struct target_pt_regs *regs,
                                struct image_info *infop)
 {
@@ -1776,6 +1807,10 @@ static inline void init_thread(struct target_pt_regs *regs,
 
 #endif /* TARGET_HEXAGON */
 
+#ifndef ELF_BASE_PLATFORM
+#define ELF_BASE_PLATFORM (NULL)
+#endif
+
 #ifndef ELF_PLATFORM
 #define ELF_PLATFORM (NULL)
 #endif
@@ -2096,10 +2131,16 @@ static abi_ulong setup_arg_pages(struct linux_binprm *bprm,
     if (size < STACK_LOWER_LIMIT) {
         size = STACK_LOWER_LIMIT;
     }
+
+    if (STACK_GROWS_DOWN) {
         guard = TARGET_PAGE_SIZE;
         if (guard < qemu_real_host_page_size()) {
             guard = qemu_real_host_page_size();
         }
+    } else {
+        /* no guard page for hppa target where stack grows upwards. */
+        guard = 0;
+    }
 
     prot = PROT_READ | PROT_WRITE;
     if (info->exec_stack) {
@@ -2118,7 +2159,6 @@ static abi_ulong setup_arg_pages(struct linux_binprm *bprm,
         info->stack_limit = error + guard;
         return info->stack_limit + size - sizeof(void *);
     } else {
-        target_mprotect(error + size, guard, PROT_NONE);
         info->stack_limit = error + size;
         return error;
     }
@@ -2215,8 +2255,8 @@ static abi_ulong create_elf_tables(abi_ulong p, int argc, int envc,
     int i;
     abi_ulong u_rand_bytes;
     uint8_t k_rand_bytes[16];
-    abi_ulong u_platform;
+    abi_ulong u_platform, u_base_platform;
-    const char *k_platform;
+    const char *k_platform, *k_base_platform;
     const int n = sizeof(elf_addr_t);
 
     sp = p;
@@ -2238,6 +2278,22 @@ static abi_ulong create_elf_tables(abi_ulong p, int argc, int envc,
         }
     }
 
+    u_base_platform = 0;
+    k_base_platform = ELF_BASE_PLATFORM;
+    if (k_base_platform) {
+        size_t len = strlen(k_base_platform) + 1;
+        if (STACK_GROWS_DOWN) {
+            sp -= (len + n - 1) & ~(n - 1);
+            u_base_platform = sp;
+            /* FIXME - check return value of memcpy_to_target() for failure */
+            memcpy_to_target(sp, k_base_platform, len);
+        } else {
+            memcpy_to_target(sp, k_base_platform, len);
+            u_base_platform = sp;
+            sp += len + 1;
+        }
+    }
+
     u_platform = 0;
     k_platform = ELF_PLATFORM;
     if (k_platform) {
@@ -2279,6 +2335,8 @@ static abi_ulong create_elf_tables(abi_ulong p, int argc, int envc,
     }
 
     size = (DLINFO_ITEMS + 1) * 2;
+    if (k_base_platform)
+        size += 2;
     if (k_platform)
         size += 2;
 #ifdef DLINFO_ARCH_ITEMS
@@ -2356,6 +2414,9 @@ static abi_ulong create_elf_tables(abi_ulong p, int argc, int envc,
     NEW_AUX_ENT(AT_HWCAP2, (abi_ulong) ELF_HWCAP2);
 #endif
 
+    if (u_base_platform) {
+        NEW_AUX_ENT(AT_BASE_PLATFORM, u_base_platform);
+    }
     if (u_platform) {
         NEW_AUX_ENT(AT_PLATFORM, u_platform);
     }

linux-user/generic/target_mman.h

@@ -0,0 +1,92 @@
+#ifndef LINUX_USER_TARGET_MMAN_H
+#define LINUX_USER_TARGET_MMAN_H
+
+#ifndef TARGET_MADV_NORMAL
+#define TARGET_MADV_NORMAL 0
+#endif
+
+#ifndef TARGET_MADV_RANDOM
+#define TARGET_MADV_RANDOM 1
+#endif
+
+#ifndef TARGET_MADV_SEQUENTIAL
+#define TARGET_MADV_SEQUENTIAL 2
+#endif
+
+#ifndef TARGET_MADV_WILLNEED
+#define TARGET_MADV_WILLNEED 3
+#endif
+
+#ifndef TARGET_MADV_DONTNEED
+#define TARGET_MADV_DONTNEED 4
+#endif
+
+#ifndef TARGET_MADV_FREE
+#define TARGET_MADV_FREE 8
+#endif
+
+#ifndef TARGET_MADV_REMOVE
+#define TARGET_MADV_REMOVE 9
+#endif
+
+#ifndef TARGET_MADV_DONTFORK
+#define TARGET_MADV_DONTFORK 10
+#endif
+
+#ifndef TARGET_MADV_DOFORK
+#define TARGET_MADV_DOFORK 11
+#endif
+
+#ifndef TARGET_MADV_MERGEABLE
+#define TARGET_MADV_MERGEABLE 12
+#endif
+
+#ifndef TARGET_MADV_UNMERGEABLE
+#define TARGET_MADV_UNMERGEABLE 13
+#endif
+
+#ifndef TARGET_MADV_HUGEPAGE
+#define TARGET_MADV_HUGEPAGE 14
+#endif
+
+#ifndef TARGET_MADV_NOHUGEPAGE
+#define TARGET_MADV_NOHUGEPAGE 15
+#endif
+
+#ifndef TARGET_MADV_DONTDUMP
+#define TARGET_MADV_DONTDUMP 16
+#endif
+
+#ifndef TARGET_MADV_DODUMP
+#define TARGET_MADV_DODUMP 17
+#endif
+
+#ifndef TARGET_MADV_WIPEONFORK
+#define TARGET_MADV_WIPEONFORK 18
+#endif
+
+#ifndef TARGET_MADV_KEEPONFORK
+#define TARGET_MADV_KEEPONFORK 19
+#endif
+
+#ifndef TARGET_MADV_COLD
+#define TARGET_MADV_COLD 20
+#endif
+
+#ifndef TARGET_MADV_PAGEOUT
+#define TARGET_MADV_PAGEOUT 21
+#endif
+
+#ifndef TARGET_MADV_POPULATE_READ
+#define TARGET_MADV_POPULATE_READ 22
+#endif
+
+#ifndef TARGET_MADV_POPULATE_WRITE
+#define TARGET_MADV_POPULATE_WRITE 23
+#endif
+
+#ifndef TARGET_MADV_DONTNEED_LOCKED
+#define TARGET_MADV_DONTNEED_LOCKED 24
+#endif
+
+#endif

linux-user/hexagon/target_mman.h

@@ -0,0 +1 @@
+#include "../generic/target_mman.h"

linux-user/hppa/cpu_loop.c

@@ -147,12 +147,15 @@ void cpu_loop(CPUHPPAState *env)
             force_sig_fault(TARGET_SIGSEGV, TARGET_SEGV_MAPERR, env->iaoq_f);
             break;
         case EXCP_ILL:
+            EXCP_DUMP(env, "qemu: got CPU exception 0x%x - aborting\n", trapnr);
             force_sig_fault(TARGET_SIGILL, TARGET_ILL_ILLOPN, env->iaoq_f);
             break;
         case EXCP_PRIV_OPR:
+            EXCP_DUMP(env, "qemu: got CPU exception 0x%x - aborting\n", trapnr);
             force_sig_fault(TARGET_SIGILL, TARGET_ILL_PRVOPC, env->iaoq_f);
             break;
         case EXCP_PRIV_REG:
+            EXCP_DUMP(env, "qemu: got CPU exception 0x%x - aborting\n", trapnr);
             force_sig_fault(TARGET_SIGILL, TARGET_ILL_PRVREG, env->iaoq_f);
             break;
         case EXCP_OVERFLOW:
@@ -171,7 +174,8 @@ void cpu_loop(CPUHPPAState *env)
             /* just indicate that signals should be handled asap */
             break;
         default:
-            g_assert_not_reached();
+            EXCP_DUMP(env, "qemu: unhandled CPU exception 0x%x - aborting\n", trapnr);
+            abort();
         }
         process_pending_signals(env);
     }

linux-user/hppa/signal.c

@@ -41,7 +41,7 @@ struct target_ucontext {
 };
 
 struct target_rt_sigframe {
-    abi_uint tramp[9];
+    abi_uint tramp[2];  /* syscall restart return address */
     target_siginfo_t info;
     struct target_ucontext uc;
     /* hidden location of upper halves of pa2.0 64-bit gregs */
@@ -49,23 +49,13 @@ struct target_rt_sigframe {
 
 static void setup_sigcontext(struct target_sigcontext *sc, CPUArchState *env)
 {
-    int flags = 0;
     int i;
 
-    /* ??? if on_sig_stack, flags |= 1 (PARISC_SC_FLAG_ONSTACK).  */
-
-    if (env->iaoq_f < TARGET_PAGE_SIZE) {
-        /* In the gateway page, executing a syscall.  */
-        flags |= 2; /* PARISC_SC_FLAG_IN_SYSCALL */
-        __put_user(env->gr[31], &sc->sc_iaoq[0]);
-        __put_user(env->gr[31] + 4, &sc->sc_iaoq[1]);
-    } else {
     __put_user(env->iaoq_f, &sc->sc_iaoq[0]);
     __put_user(env->iaoq_b, &sc->sc_iaoq[1]);
-    }
     __put_user(0, &sc->sc_iasq[0]);
     __put_user(0, &sc->sc_iasq[1]);
-    __put_user(flags, &sc->sc_flags);
+    __put_user(0, &sc->sc_flags);
 
     __put_user(cpu_hppa_get_psw(env), &sc->sc_gr[0]);
     for (i = 1; i < 32; ++i) {
@@ -101,9 +91,15 @@ static void restore_sigcontext(CPUArchState *env, struct target_sigcontext *sc)
     __get_user(env->cr[CR_SAR], &sc->sc_sar);
 }
 
-/* No, this doesn't look right, but it's copied straight from the kernel.  */
+#if TARGET_ABI_BITS == 32
+#define SIGFRAME                64
+#define FUNCTIONCALLFRAME       48
+#else
+#define SIGFRAME                128
+#define FUNCTIONCALLFRAME       96
+#endif
 #define PARISC_RT_SIGFRAME_SIZE32 \
-    ((sizeof(struct target_rt_sigframe) + 48 + 64) & -64)
+    ((sizeof(struct target_rt_sigframe) + FUNCTIONCALLFRAME + SIGFRAME) & -SIGFRAME)
 
 void setup_rt_frame(int sig, struct target_sigaction *ka,
                     target_siginfo_t *info,
@@ -118,7 +114,7 @@ void setup_rt_frame(int sig, struct target_sigaction *ka,
     if ((ka->sa_flags & TARGET_SA_ONSTACK) && !sas_ss_flags(sp)) {
         sp = (ts->sigaltstack_used.ss_sp + 0x7f) & ~0x3f;
     }
-    frame_addr = QEMU_ALIGN_UP(sp, 64);
+    frame_addr = QEMU_ALIGN_UP(sp, SIGFRAME);
     sp = frame_addr + PARISC_RT_SIGFRAME_SIZE32;
 
     trace_user_setup_rt_frame(env, frame_addr);
@@ -139,14 +135,9 @@ void setup_rt_frame(int sig, struct target_sigaction *ka,
 
     setup_sigcontext(&frame->uc.tuc_mcontext, env);
 
-    __put_user(0x34190000, frame->tramp + 0); /* ldi 0,%r25 */
-    __put_user(0x3414015a, frame->tramp + 1); /* ldi __NR_rt_sigreturn,%r20 */
-    __put_user(0xe4008200, frame->tramp + 2); /* be,l 0x100(%sr2,%r0) */
-    __put_user(0x08000240, frame->tramp + 3); /* nop */
-
     unlock_user_struct(frame, frame_addr, 1);
 
-    env->gr[2] = h2g(frame->tramp);
+    env->gr[2] = default_rt_sigreturn;
     env->gr[30] = sp;
     env->gr[26] = sig;
     env->gr[25] = h2g(&frame->info);
@@ -197,3 +188,23 @@ long do_rt_sigreturn(CPUArchState *env)
     force_sig(TARGET_SIGSEGV);
     return -QEMU_ESIGRETURN;
 }
+
+void setup_sigtramp(abi_ulong sigtramp_page)
+{
+    uint32_t *tramp = lock_user(VERIFY_WRITE, sigtramp_page, 6*4, 0);
+    abi_ulong SIGFRAME_CONTEXT_REGS32;
+    assert(tramp != NULL);
+
+    SIGFRAME_CONTEXT_REGS32 = offsetof(struct target_rt_sigframe, uc.tuc_mcontext);
+    SIGFRAME_CONTEXT_REGS32 -= PARISC_RT_SIGFRAME_SIZE32;
+
+    __put_user(SIGFRAME_CONTEXT_REGS32, tramp + 0);
+    __put_user(0x08000240, tramp + 1);  /* nop - b/c dwarf2 unwind routines */
+    __put_user(0x34190000, tramp + 2);  /* ldi 0, %r25 (in_syscall=0) */
+    __put_user(0x3414015a, tramp + 3);  /* ldi __NR_rt_sigreturn, %r20 */
+    __put_user(0xe4008200, tramp + 4);  /* ble 0x100(%sr2, %r0) */
+    __put_user(0x08000240, tramp + 5);  /* nop */
+
+    default_rt_sigreturn = (sigtramp_page + 8) | 3;
+    unlock_user(tramp, sigtramp_page, 6*4);
+}

linux-user/hppa/target_mman.h

@@ -0,0 +1,15 @@
+#ifndef HPPA_TARGET_MMAN_H
+#define HPPA_TARGET_MMAN_H
+
+#define TARGET_MADV_MERGEABLE 65
+#define TARGET_MADV_UNMERGEABLE 66
+#define TARGET_MADV_HUGEPAGE 67
+#define TARGET_MADV_NOHUGEPAGE 68
+#define TARGET_MADV_DONTDUMP 69
+#define TARGET_MADV_DODUMP 70
+#define TARGET_MADV_WIPEONFORK 71
+#define TARGET_MADV_KEEPONFORK 72
+
+#include "../generic/target_mman.h"
+
+#endif

linux-user/hppa/target_signal.h

@@ -70,18 +70,6 @@ typedef struct target_sigaltstack {
 /* mask for all SS_xxx flags */
 #define TARGET_SS_FLAG_BITS  TARGET_SS_AUTODISARM
 
-/*
+#define TARGET_ARCH_HAS_SIGTRAMP_PAGE 1
- * We cannot use a bare sigtramp page for hppa-linux.
- *
- * Unlike other guests where we use the instructions at PC to validate
- * an offset from SP, the hppa libgcc signal frame fallback unwinding uses
- * the PC address itself to find the frame.  This is due to the fact that
- * the hppa grows the stack upward, and the frame is of unknown size.
- *
- * TODO: We should be able to use a VDSO to address this, by providing
- * proper unwind info for the sigtramp code, at which point the fallback
- * unwinder will not be used.
- */
-#define TARGET_ARCH_HAS_SIGTRAMP_PAGE 0
 
 #endif /* HPPA_TARGET_SIGNAL_H */

linux-user/hppa/target_syscall.h

@@ -26,4 +26,6 @@ struct target_pt_regs {
 #define TARGET_MCL_FUTURE  2
 #define TARGET_MCL_ONFAULT 4
 
+#define TARGET_DEFAULT_STACK_SIZE	80 * 1024 * 1024UL
+
 #endif /* HPPA_TARGET_SYSCALL_H */

linux-user/i386/target_elf.h

@@ -9,6 +9,6 @@
 #define I386_TARGET_ELF_H
 static inline const char *cpu_get_model(uint32_t eflags)
 {
-    return "qemu32";
+    return "max";
 }
 #endif

linux-user/i386/target_mman.h

@@ -0,0 +1 @@
+#include "../generic/target_mman.h"

linux-user/loongarch64/target_mman.h

@@ -0,0 +1 @@
+#include "../generic/target_mman.h"

linux-user/m68k/target_mman.h

@@ -0,0 +1 @@
+#include "../generic/target_mman.h"

linux-user/main.c

@@ -124,10 +124,14 @@ static void usage(int exitcode);
 static const char *interp_prefix = CONFIG_QEMU_INTERP_PREFIX;
 const char *qemu_uname_release;
 
+#if !defined(TARGET_DEFAULT_STACK_SIZE)
 /* XXX: on x86 MAP_GROWSDOWN only works if ESP <= address + 32, so
    we allocate a bigger stack. Need a better solution, for example
    by remapping the process stack directly at the right place */
-unsigned long guest_stack_size = 8 * 1024 * 1024UL;
+#define TARGET_DEFAULT_STACK_SIZE	8 * 1024 * 1024UL
+#endif
+
+unsigned long guest_stack_size = TARGET_DEFAULT_STACK_SIZE;
 
 /***********************************************************/
 /* Helper routines for implementing atomic operations.  */
@@ -668,7 +672,8 @@ int main(int argc, char **argv, char **envp)
         struct rlimit lim;
         if (getrlimit(RLIMIT_STACK, &lim) == 0
             && lim.rlim_cur != RLIM_INFINITY
-            && lim.rlim_cur == (target_long)lim.rlim_cur) {
+            && lim.rlim_cur == (target_long)lim.rlim_cur
+            && lim.rlim_cur > guest_stack_size) {
             guest_stack_size = lim.rlim_cur;
         }
     }

linux-user/microblaze/target_mman.h

@@ -0,0 +1 @@
+#include "../generic/target_mman.h"

linux-user/mips/target_mman.h

@@ -0,0 +1 @@
+#include "../generic/target_mman.h"

linux-user/mips64/target_mman.h

@@ -0,0 +1 @@
+#include "../generic/target_mman.h"

linux-user/mmap.c

@@ -22,6 +22,7 @@
 #include "qemu.h"
 #include "user-internals.h"
 #include "user-mmap.h"
+#include "target_mman.h"
 
 static pthread_mutex_t mmap_mutex = PTHREAD_MUTEX_INITIALIZER;
 static __thread int mmap_lock_count;
@@ -105,6 +106,8 @@ static int validate_prot_to_pageflags(int *host_prot, int prot)
             page_flags |= PAGE_MTE;
         }
     }
+#elif defined(TARGET_HPPA)
+    valid |= PROT_GROWSDOWN | PROT_GROWSUP;
 #endif
 
     return prot & ~valid ? 0 : page_flags;
@@ -253,8 +256,12 @@ static int mmap_frag(abi_ulong real_start,
 # define TASK_UNMAPPED_BASE  (1ul << 38)
 #endif
 #else
+#ifdef TARGET_HPPA
+# define TASK_UNMAPPED_BASE  0xfa000000
+#else
 # define TASK_UNMAPPED_BASE  0x40000000
 #endif
+#endif
 abi_ulong mmap_next_start = TASK_UNMAPPED_BASE;
 
 unsigned long last_brk;
@@ -426,7 +433,8 @@ abi_ulong mmap_find_vma(abi_ulong start, abi_ulong size, abi_ulong align)
 abi_long target_mmap(abi_ulong start, abi_ulong len, int target_prot,
                      int flags, int fd, abi_ulong offset)
 {
-    abi_ulong ret, end, real_start, real_end, retaddr, host_offset, host_len;
+    abi_ulong ret, end, real_start, real_end, retaddr, host_offset, host_len,
+              passthrough_start = -1, passthrough_end = -1;
     int page_flags, host_prot;
 
     mmap_lock();
@@ -539,6 +547,8 @@ abi_long target_mmap(abi_ulong start, abi_ulong len, int target_prot,
             host_start += offset - host_offset;
         }
         start = h2g(host_start);
+        passthrough_start = start;
+        passthrough_end = start + len;
     } else {
         if (start & ~TARGET_PAGE_MASK) {
             errno = EINVAL;
@@ -621,6 +631,8 @@ abi_long target_mmap(abi_ulong start, abi_ulong len, int target_prot,
                      host_prot, flags, fd, offset1);
             if (p == MAP_FAILED)
                 goto fail;
+            passthrough_start = real_start;
+            passthrough_end = real_end;
         }
     }
  the_end1:
@@ -628,7 +640,18 @@ abi_long target_mmap(abi_ulong start, abi_ulong len, int target_prot,
         page_flags |= PAGE_ANON;
     }
     page_flags |= PAGE_RESET;
+    if (passthrough_start == passthrough_end) {
         page_set_flags(start, start + len, page_flags);
+    } else {
+        if (start < passthrough_start) {
+            page_set_flags(start, passthrough_start, page_flags);
+        }
+        page_set_flags(passthrough_start, passthrough_end,
+                       page_flags | PAGE_PASSTHROUGH);
+        if (passthrough_end < start + len) {
+            page_set_flags(passthrough_end, start + len, page_flags);
+        }
+    }
  the_end:
     trace_target_mmap_complete(start);
     if (qemu_loglevel_mask(CPU_LOG_PAGE)) {
@@ -847,7 +870,7 @@ static bool can_passthrough_madv_dontneed(abi_ulong start, abi_ulong end)
     }
 
     for (addr = start; addr < end; addr += TARGET_PAGE_SIZE) {
-        if (!(page_get_flags(addr) & PAGE_ANON)) {
+        if (!(page_get_flags(addr) & PAGE_PASSTHROUGH)) {
             return false;
         }
     }
@@ -889,11 +912,12 @@ abi_long target_madvise(abi_ulong start, abi_ulong len_in, int advice)
      * This is a hint, so ignoring and returning success is ok.
      *
      * This breaks MADV_DONTNEED, completely implementing which is quite
-     * complicated. However, there is one low-hanging fruit: host-page-aligned
+     * complicated. However, there is one low-hanging fruit: mappings that are
-     * anonymous mappings. In this case passthrough is safe, so do it.
+     * known to have the same semantics in the host and the guest. In this case
+     * passthrough is safe, so do it.
      */
     mmap_lock();
-    if (advice == MADV_DONTNEED &&
+    if (advice == TARGET_MADV_DONTNEED &&
         can_passthrough_madv_dontneed(start, end)) {
         ret = get_errno(madvise(g2h_untagged(start), len, MADV_DONTNEED));
         if (ret == 0) {

linux-user/nios2/target_mman.h

@@ -0,0 +1 @@
+#include "../generic/target_mman.h"

linux-user/openrisc/target_mman.h

@@ -0,0 +1 @@
+#include "../generic/target_mman.h"

linux-user/ppc/target_mman.h

@@ -0,0 +1 @@
+#include "../generic/target_mman.h"

linux-user/riscv/target_mman.h

@@ -0,0 +1 @@
+#include "../generic/target_mman.h"

linux-user/s390x/signal.c

@@ -146,6 +146,7 @@ static void save_sigregs(CPUS390XState *env, target_sigregs *sregs)
      * We have to store the fp registers to current->thread.fp_regs
      * to merge them with the emulated registers.
      */
+    __put_user(env->fpc, &sregs->fpregs.fpc);
     for (i = 0; i < 16; i++) {
         __put_user(*get_freg(env, i), &sregs->fpregs.fprs[i]);
     }
@@ -331,6 +332,7 @@ static void restore_sigregs(CPUS390XState *env, target_sigregs *sc)
     for (i = 0; i < 16; i++) {
         __get_user(env->aregs[i], &sc->regs.acrs[i]);
     }
+    __get_user(env->fpc, &sc->fpregs.fpc);
     for (i = 0; i < 16; i++) {
         __get_user(*get_freg(env, i), &sc->fpregs.fprs[i]);
     }

linux-user/s390x/target_mman.h

@@ -0,0 +1 @@
+#include "../generic/target_mman.h"

linux-user/sh4/target_mman.h

@@ -0,0 +1 @@
+#include "../generic/target_mman.h"

linux-user/signal-common.h

@@ -118,4 +118,50 @@ static inline void finish_sigsuspend_mask(int ret)
     }
 }
 
+#if defined(SIGSTKFLT) && defined(TARGET_SIGSTKFLT)
+#define MAKE_SIG_ENTRY_SIGSTKFLT        MAKE_SIG_ENTRY(SIGSTKFLT)
+#else
+#define MAKE_SIG_ENTRY_SIGSTKFLT
+#endif
+
+#if defined(SIGIOT) && defined(TARGET_SIGIOT)
+#define MAKE_SIG_ENTRY_SIGIOT           MAKE_SIG_ENTRY(SIGIOT)
+#else
+#define MAKE_SIG_ENTRY_SIGIOT
+#endif
+
+#define MAKE_SIGNAL_LIST \
+        MAKE_SIG_ENTRY(SIGHUP) \
+        MAKE_SIG_ENTRY(SIGINT) \
+        MAKE_SIG_ENTRY(SIGQUIT) \
+        MAKE_SIG_ENTRY(SIGILL) \
+        MAKE_SIG_ENTRY(SIGTRAP) \
+        MAKE_SIG_ENTRY(SIGABRT) \
+        MAKE_SIG_ENTRY(SIGBUS) \
+        MAKE_SIG_ENTRY(SIGFPE) \
+        MAKE_SIG_ENTRY(SIGKILL) \
+        MAKE_SIG_ENTRY(SIGUSR1) \
+        MAKE_SIG_ENTRY(SIGSEGV) \
+        MAKE_SIG_ENTRY(SIGUSR2) \
+        MAKE_SIG_ENTRY(SIGPIPE) \
+        MAKE_SIG_ENTRY(SIGALRM) \
+        MAKE_SIG_ENTRY(SIGTERM) \
+        MAKE_SIG_ENTRY(SIGCHLD) \
+        MAKE_SIG_ENTRY(SIGCONT) \
+        MAKE_SIG_ENTRY(SIGSTOP) \
+        MAKE_SIG_ENTRY(SIGTSTP) \
+        MAKE_SIG_ENTRY(SIGTTIN) \
+        MAKE_SIG_ENTRY(SIGTTOU) \
+        MAKE_SIG_ENTRY(SIGURG) \
+        MAKE_SIG_ENTRY(SIGXCPU) \
+        MAKE_SIG_ENTRY(SIGXFSZ) \
+        MAKE_SIG_ENTRY(SIGVTALRM) \
+        MAKE_SIG_ENTRY(SIGPROF) \
+        MAKE_SIG_ENTRY(SIGWINCH) \
+        MAKE_SIG_ENTRY(SIGIO) \
+        MAKE_SIG_ENTRY(SIGPWR) \
+        MAKE_SIG_ENTRY(SIGSYS) \
+        MAKE_SIG_ENTRY_SIGSTKFLT \
+        MAKE_SIG_ENTRY_SIGIOT
+
 #endif

linux-user/signal.c

@@ -53,40 +53,9 @@ abi_ulong default_rt_sigreturn;
 QEMU_BUILD_BUG_ON(__SIGRTMAX + 1 != _NSIG);
 #endif
 static uint8_t host_to_target_signal_table[_NSIG] = {
-    [SIGHUP] = TARGET_SIGHUP,
+#define MAKE_SIG_ENTRY(sig)     [sig] = TARGET_##sig,
-    [SIGINT] = TARGET_SIGINT,
+        MAKE_SIGNAL_LIST
-    [SIGQUIT] = TARGET_SIGQUIT,
+#undef MAKE_SIG_ENTRY
-    [SIGILL] = TARGET_SIGILL,
-    [SIGTRAP] = TARGET_SIGTRAP,
-    [SIGABRT] = TARGET_SIGABRT,
-/*    [SIGIOT] = TARGET_SIGIOT,*/
-    [SIGBUS] = TARGET_SIGBUS,
-    [SIGFPE] = TARGET_SIGFPE,
-    [SIGKILL] = TARGET_SIGKILL,
-    [SIGUSR1] = TARGET_SIGUSR1,
-    [SIGSEGV] = TARGET_SIGSEGV,
-    [SIGUSR2] = TARGET_SIGUSR2,
-    [SIGPIPE] = TARGET_SIGPIPE,
-    [SIGALRM] = TARGET_SIGALRM,
-    [SIGTERM] = TARGET_SIGTERM,
-#ifdef SIGSTKFLT
-    [SIGSTKFLT] = TARGET_SIGSTKFLT,
-#endif
-    [SIGCHLD] = TARGET_SIGCHLD,
-    [SIGCONT] = TARGET_SIGCONT,
-    [SIGSTOP] = TARGET_SIGSTOP,
-    [SIGTSTP] = TARGET_SIGTSTP,
-    [SIGTTIN] = TARGET_SIGTTIN,
-    [SIGTTOU] = TARGET_SIGTTOU,
-    [SIGURG] = TARGET_SIGURG,
-    [SIGXCPU] = TARGET_SIGXCPU,
-    [SIGXFSZ] = TARGET_SIGXFSZ,
-    [SIGVTALRM] = TARGET_SIGVTALRM,
-    [SIGPROF] = TARGET_SIGPROF,
-    [SIGWINCH] = TARGET_SIGWINCH,
-    [SIGIO] = TARGET_SIGIO,
-    [SIGPWR] = TARGET_SIGPWR,
-    [SIGSYS] = TARGET_SIGSYS,
     /* next signals stay the same */
 };
 

linux-user/sparc/target_mman.h

@@ -0,0 +1 @@
+#include "../generic/target_mman.h"

linux-user/strace.c

@@ -17,6 +17,8 @@
 #include "qemu.h"
 #include "user-internals.h"
 #include "strace.h"
+#include "signal-common.h"
+#include "target_mman.h"
 
 struct syscallname {
     int nr;
@@ -81,6 +83,7 @@ UNUSED static void print_buf(abi_long addr, abi_long len, int last);
 UNUSED static void print_raw_param(const char *, abi_long, int);
 UNUSED static void print_timeval(abi_ulong, int);
 UNUSED static void print_timespec(abi_ulong, int);
+UNUSED static void print_timespec64(abi_ulong, int);
 UNUSED static void print_timezone(abi_ulong, int);
 UNUSED static void print_itimerval(abi_ulong, int);
 UNUSED static void print_number(abi_long, int);
@@ -141,30 +144,21 @@ if( cmd == val ) { \
     qemu_log("%d", cmd);
 }
 
+static const char * const target_signal_name[] = {
+#define MAKE_SIG_ENTRY(sig)     [TARGET_##sig] = #sig,
+        MAKE_SIGNAL_LIST
+#undef MAKE_SIG_ENTRY
+};
+
 static void
 print_signal(abi_ulong arg, int last)
 {
     const char *signal_name = NULL;
-    switch(arg) {
+
-    case TARGET_SIGHUP: signal_name = "SIGHUP"; break;
+    if (arg < ARRAY_SIZE(target_signal_name)) {
-    case TARGET_SIGINT: signal_name = "SIGINT"; break;
+        signal_name = target_signal_name[arg];
-    case TARGET_SIGQUIT: signal_name = "SIGQUIT"; break;
-    case TARGET_SIGILL: signal_name = "SIGILL"; break;
-    case TARGET_SIGABRT: signal_name = "SIGABRT"; break;
-    case TARGET_SIGFPE: signal_name = "SIGFPE"; break;
-    case TARGET_SIGKILL: signal_name = "SIGKILL"; break;
-    case TARGET_SIGSEGV: signal_name = "SIGSEGV"; break;
-    case TARGET_SIGPIPE: signal_name = "SIGPIPE"; break;
-    case TARGET_SIGALRM: signal_name = "SIGALRM"; break;
-    case TARGET_SIGTERM: signal_name = "SIGTERM"; break;
-    case TARGET_SIGUSR1: signal_name = "SIGUSR1"; break;
-    case TARGET_SIGUSR2: signal_name = "SIGUSR2"; break;
-    case TARGET_SIGCHLD: signal_name = "SIGCHLD"; break;
-    case TARGET_SIGCONT: signal_name = "SIGCONT"; break;
-    case TARGET_SIGSTOP: signal_name = "SIGSTOP"; break;
-    case TARGET_SIGTTIN: signal_name = "SIGTTIN"; break;
-    case TARGET_SIGTTOU: signal_name = "SIGTTOU"; break;
     }
+
     if (signal_name == NULL) {
         print_raw_param("%ld", arg, last);
         return;
@@ -803,6 +797,24 @@ print_syscall_ret_clock_gettime(CPUArchState *cpu_env, const struct syscallname
 #define print_syscall_ret_clock_getres     print_syscall_ret_clock_gettime
 #endif
 
+#if defined(TARGET_NR_clock_gettime64)
+static void
+print_syscall_ret_clock_gettime64(CPUArchState *cpu_env, const struct syscallname *name,
+                                abi_long ret, abi_long arg0, abi_long arg1,
+                                abi_long arg2, abi_long arg3, abi_long arg4,
+                                abi_long arg5)
+{
+    if (!print_syscall_err(ret)) {
+        qemu_log(TARGET_ABI_FMT_ld, ret);
+        qemu_log(" (");
+        print_timespec64(arg1, 1);
+        qemu_log(")");
+    }
+
+    qemu_log("\n");
+}
+#endif
+
 #ifdef TARGET_NR_gettimeofday
 static void
 print_syscall_ret_gettimeofday(CPUArchState *cpu_env, const struct syscallname *name,
@@ -1494,6 +1506,11 @@ print_file_mode(abi_long mode, int last)
     const char *sep = "";
     const struct flags *m;
 
+    if (mode == 0) {
+        qemu_log("000%s", get_comma(last));
+        return;
+    }
+
     for (m = &mode_flags[0]; m->f_string != NULL; m++) {
         if ((m->f_value & mode) == m->f_value) {
             qemu_log("%s%s", m->f_string, sep);
@@ -1660,6 +1677,27 @@ print_timespec(abi_ulong ts_addr, int last)
     }
 }
 
+static void
+print_timespec64(abi_ulong ts_addr, int last)
+{
+    if (ts_addr) {
+        struct target__kernel_timespec *ts;
+
+        ts = lock_user(VERIFY_READ, ts_addr, sizeof(*ts), 1);
+        if (!ts) {
+            print_pointer(ts_addr, last);
+            return;
+        }
+        qemu_log("{tv_sec = %lld"
+                 ",tv_nsec = %lld}%s",
+                 (long long)tswap64(ts->tv_sec), (long long)tswap64(ts->tv_nsec),
+                 get_comma(last));
+        unlock_user(ts, ts_addr, 0);
+    } else {
+        qemu_log("NULL%s", get_comma(last));
+    }
+}
+
 static void
 print_timezone(abi_ulong tz_addr, int last)
 {
@@ -2275,6 +2313,19 @@ print_clock_gettime(CPUArchState *cpu_env, const struct syscallname *name,
 #define print_clock_getres     print_clock_gettime
 #endif
 
+#if defined(TARGET_NR_clock_gettime64)
+static void
+print_clock_gettime64(CPUArchState *cpu_env, const struct syscallname *name,
+                    abi_long arg0, abi_long arg1, abi_long arg2,
+                    abi_long arg3, abi_long arg4, abi_long arg5)
+{
+    print_syscall_prologue(name);
+    print_enums(clockids, arg0, 0);
+    print_pointer(arg1, 1);
+    print_syscall_epilogue(name);
+}
+#endif
+
 #ifdef TARGET_NR_clock_settime
 static void
 print_clock_settime(CPUArchState *cpu_env, const struct syscallname *name,
@@ -2969,6 +3020,46 @@ print_stat(CPUArchState *cpu_env, const struct syscallname *name,
 #define print_lstat64   print_stat
 #endif
 
+#if defined(TARGET_NR_madvise)
+static struct enums madvise_advice[] = {
+    ENUM_TARGET(MADV_NORMAL),
+    ENUM_TARGET(MADV_RANDOM),
+    ENUM_TARGET(MADV_SEQUENTIAL),
+    ENUM_TARGET(MADV_WILLNEED),
+    ENUM_TARGET(MADV_DONTNEED),
+    ENUM_TARGET(MADV_FREE),
+    ENUM_TARGET(MADV_REMOVE),
+    ENUM_TARGET(MADV_DONTFORK),
+    ENUM_TARGET(MADV_DOFORK),
+    ENUM_TARGET(MADV_MERGEABLE),
+    ENUM_TARGET(MADV_UNMERGEABLE),
+    ENUM_TARGET(MADV_HUGEPAGE),
+    ENUM_TARGET(MADV_NOHUGEPAGE),
+    ENUM_TARGET(MADV_DONTDUMP),
+    ENUM_TARGET(MADV_DODUMP),
+    ENUM_TARGET(MADV_WIPEONFORK),
+    ENUM_TARGET(MADV_KEEPONFORK),
+    ENUM_TARGET(MADV_COLD),
+    ENUM_TARGET(MADV_PAGEOUT),
+    ENUM_TARGET(MADV_POPULATE_READ),
+    ENUM_TARGET(MADV_POPULATE_WRITE),
+    ENUM_TARGET(MADV_DONTNEED_LOCKED),
+    ENUM_END,
+};
+
+static void
+print_madvise(CPUArchState *cpu_env, const struct syscallname *name,
+              abi_long arg0, abi_long arg1, abi_long arg2,
+              abi_long arg3, abi_long arg4, abi_long arg5)
+{
+    print_syscall_prologue(name);
+    print_pointer(arg0, 0);
+    print_raw_param("%d", arg1, 0);
+    print_enums(madvise_advice, arg2, 1);
+    print_syscall_epilogue(name);
+}
+#endif
+
 #if defined(TARGET_NR_fstat) || defined(TARGET_NR_fstat64)
 static void
 print_fstat(CPUArchState *cpu_env, const struct syscallname *name,
@@ -3272,6 +3363,34 @@ print_openat(CPUArchState *cpu_env, const struct syscallname *name,
 }
 #endif
 
+#ifdef TARGET_NR_pidfd_send_signal
+static void
+print_pidfd_send_signal(CPUArchState *cpu_env, const struct syscallname *name,
+                abi_long arg0, abi_long arg1, abi_long arg2,
+                abi_long arg3, abi_long arg4, abi_long arg5)
+{
+    void *p;
+    target_siginfo_t uinfo;
+
+    print_syscall_prologue(name);
+    print_raw_param("%d", arg0, 0);
+    print_signal(arg1, 0);
+
+    p = lock_user(VERIFY_READ, arg2, sizeof(target_siginfo_t), 1);
+    if (p) {
+        get_target_siginfo(&uinfo, p);
+        print_siginfo(&uinfo);
+
+        unlock_user(p, arg2, 0);
+    } else {
+        print_pointer(arg2, 1);
+    }
+
+    print_raw_param("%u", arg3, 0);
+    print_syscall_epilogue(name);
+}
+#endif
+
 #ifdef TARGET_NR_mq_unlink
 static void
 print_mq_unlink(CPUArchState *cpu_env, const struct syscallname *name,
@@ -3489,6 +3608,21 @@ print_unshare(CPUArchState *cpu_env, const struct syscallname *name,
 }
 #endif
 
+#ifdef TARGET_NR_clock_nanosleep
+static void
+print_clock_nanosleep(CPUArchState *cpu_env, const struct syscallname *name,
+                abi_long arg0, abi_long arg1, abi_long arg2,
+                abi_long arg3, abi_long arg4, abi_long arg5)
+{
+    print_syscall_prologue(name);
+    print_enums(clockids, arg0, 0);
+    print_raw_param("%d", arg1, 0);
+    print_timespec(arg2, 0);
+    print_timespec(arg3, 1);
+    print_syscall_epilogue(name);
+}
+#endif
+
 #ifdef TARGET_NR_utime
 static void
 print_utime(CPUArchState *cpu_env, const struct syscallname *name,
@@ -3576,44 +3710,37 @@ print_munmap(CPUArchState *cpu_env, const struct syscallname *name,
 #endif
 
 #ifdef TARGET_NR_futex
-static void print_futex_op(abi_long tflag, int last)
+static void print_futex_op(int cmd, int last)
 {
-#define print_op(val) \
+    static const char * const futex_names[] = {
-if( cmd == val ) { \
+#define NAME(X)  [X] = #X
-    qemu_log(#val); \
+        NAME(FUTEX_WAIT),
-    return; \
+        NAME(FUTEX_WAKE),
-}
+        NAME(FUTEX_FD),
+        NAME(FUTEX_REQUEUE),
+        NAME(FUTEX_CMP_REQUEUE),
+        NAME(FUTEX_WAKE_OP),
+        NAME(FUTEX_LOCK_PI),
+        NAME(FUTEX_UNLOCK_PI),
+        NAME(FUTEX_TRYLOCK_PI),
+        NAME(FUTEX_WAIT_BITSET),
+        NAME(FUTEX_WAKE_BITSET),
+        NAME(FUTEX_WAIT_REQUEUE_PI),
+        NAME(FUTEX_CMP_REQUEUE_PI),
+        NAME(FUTEX_LOCK_PI2),
+#undef NAME
+    };
 
-    int cmd = (int)tflag;
+    unsigned base_cmd = cmd & FUTEX_CMD_MASK;
-#ifdef FUTEX_PRIVATE_FLAG
+
-    if (cmd & FUTEX_PRIVATE_FLAG) {
+    if (base_cmd < ARRAY_SIZE(futex_names)) {
-        qemu_log("FUTEX_PRIVATE_FLAG|");
+        qemu_log("%s%s%s",
-        cmd &= ~FUTEX_PRIVATE_FLAG;
+                 (cmd & FUTEX_PRIVATE_FLAG ? "FUTEX_PRIVATE_FLAG|" : ""),
+                 (cmd & FUTEX_CLOCK_REALTIME ? "FUTEX_CLOCK_REALTIME|" : ""),
+                 futex_names[base_cmd]);
+    } else {
+        qemu_log("0x%x", cmd);
     }
-#endif
-#ifdef FUTEX_CLOCK_REALTIME
-    if (cmd & FUTEX_CLOCK_REALTIME) {
-        qemu_log("FUTEX_CLOCK_REALTIME|");
-        cmd &= ~FUTEX_CLOCK_REALTIME;
-    }
-#endif
-    print_op(FUTEX_WAIT)
-    print_op(FUTEX_WAKE)
-    print_op(FUTEX_FD)
-    print_op(FUTEX_REQUEUE)
-    print_op(FUTEX_CMP_REQUEUE)
-    print_op(FUTEX_WAKE_OP)
-    print_op(FUTEX_LOCK_PI)
-    print_op(FUTEX_UNLOCK_PI)
-    print_op(FUTEX_TRYLOCK_PI)
-#ifdef FUTEX_WAIT_BITSET
-    print_op(FUTEX_WAIT_BITSET)
-#endif
-#ifdef FUTEX_WAKE_BITSET
-    print_op(FUTEX_WAKE_BITSET)
-#endif
-    /* unknown values */
-    qemu_log("%d", cmd);
 }
 
 static void
@@ -3621,11 +3748,23 @@ print_futex(CPUArchState *cpu_env, const struct syscallname *name,
             abi_long arg0, abi_long arg1, abi_long arg2,
             abi_long arg3, abi_long arg4, abi_long arg5)
 {
+    abi_long op = arg1 & FUTEX_CMD_MASK;
     print_syscall_prologue(name);
     print_pointer(arg0, 0);
     print_futex_op(arg1, 0);
     print_raw_param(",%d", arg2, 0);
-    print_pointer(arg3, 0); /* struct timespec */
+    switch (op) {
+        case FUTEX_WAIT:
+        case FUTEX_WAIT_BITSET:
+        case FUTEX_LOCK_PI:
+        case FUTEX_LOCK_PI2:
+        case FUTEX_WAIT_REQUEUE_PI:
+            print_timespec(arg3, 0);
+            break;
+        default:
+            print_pointer(arg3, 0);
+            break;
+    }
     print_pointer(arg4, 0);
     print_raw_param("%d", arg4, 1);
     print_syscall_epilogue(name);
@@ -3780,26 +3919,37 @@ print_syscall(CPUArchState *cpu_env, int num,
               abi_long arg4, abi_long arg5, abi_long arg6)
 {
     int i;
-    const char *format="%s(" TARGET_ABI_FMT_ld "," TARGET_ABI_FMT_ld "," TARGET_ABI_FMT_ld "," TARGET_ABI_FMT_ld "," TARGET_ABI_FMT_ld "," TARGET_ABI_FMT_ld ")";
+    FILE *f;
+    const char *format = "%s(" TARGET_ABI_FMT_ld "," TARGET_ABI_FMT_ld ","
+                               TARGET_ABI_FMT_ld "," TARGET_ABI_FMT_ld ","
+                               TARGET_ABI_FMT_ld "," TARGET_ABI_FMT_ld ")";
 
-    qemu_log("%d ", getpid());
+    f = qemu_log_trylock();
+    if (!f) {
+        return;
+    }
+    fprintf(f, "%d ", getpid());
 
-    for(i=0;i<nsyscalls;i++)
+    for (i = 0; i < nsyscalls; i++) {
-        if( scnames[i].nr == num ) {
+        if (scnames[i].nr == num) {
-            if( scnames[i].call != NULL ) {
+            if (scnames[i].call != NULL) {
-                scnames[i].call(
+                scnames[i].call(cpu_env, &scnames[i], arg1, arg2, arg3,
-                    cpu_env, &scnames[i], arg1, arg2, arg3, arg4, arg5, arg6);
+                                arg4, arg5, arg6);
             } else {
                 /* XXX: this format system is broken because it uses
                    host types and host pointers for strings */
-                if( scnames[i].format != NULL )
+                if (scnames[i].format != NULL) {
                     format = scnames[i].format;
-                qemu_log(format,
-                         scnames[i].name, arg1, arg2, arg3, arg4, arg5, arg6);
                 }
+                fprintf(f, format, scnames[i].name, arg1, arg2,
+                        arg3, arg4, arg5, arg6);
+            }
+            qemu_log_unlock(f);
             return;
         }
-    qemu_log("Unknown syscall %d\n", num);
+    }
+    fprintf(f, "Unknown syscall %d\n", num);
+    qemu_log_unlock(f);
 }
 
 
@@ -3809,21 +3959,29 @@ print_syscall_ret(CPUArchState *cpu_env, int num, abi_long ret,
                   abi_long arg4, abi_long arg5, abi_long arg6)
 {
     int i;
+    FILE *f;
 
-    for(i=0;i<nsyscalls;i++)
+    f = qemu_log_trylock();
-        if( scnames[i].nr == num ) {
+    if (!f) {
-            if( scnames[i].result != NULL ) {
+        return;
+    }
+
+    for (i = 0; i < nsyscalls; i++) {
+        if (scnames[i].nr == num) {
+            if (scnames[i].result != NULL) {
                 scnames[i].result(cpu_env, &scnames[i], ret,
                                   arg1, arg2, arg3,
                                   arg4, arg5, arg6);
             } else {
                 if (!print_syscall_err(ret)) {
-                    qemu_log(TARGET_ABI_FMT_ld, ret);
+                    fprintf(f, TARGET_ABI_FMT_ld, ret);
                 }
-                qemu_log("\n");
+                fprintf(f, "\n");
             }
             break;
         }
+    }
+    qemu_log_unlock(f);
 }
 
 void print_taken_signal(int target_signum, const target_siginfo_t *tinfo)
@@ -3831,9 +3989,17 @@ void print_taken_signal(int target_signum, const target_siginfo_t *tinfo)
     /* Print the strace output for a signal being taken:
      * --- SIGSEGV {si_signo=SIGSEGV, si_code=SI_KERNEL, si_addr=0} ---
      */
-    qemu_log("--- ");
+    FILE *f;
+
+    f = qemu_log_trylock();
+    if (!f) {
+        return;
+    }
+
+    fprintf(f, "--- ");
     print_signal(target_signum, 1);
-    qemu_log(" ");
+    fprintf(f, " ");
     print_siginfo(tinfo);
-    qemu_log(" ---\n");
+    fprintf(f, " ---\n");
+    qemu_log_unlock(f);
 }

linux-user/strace.list

@@ -91,7 +91,8 @@
                            print_syscall_ret_clock_gettime },
 #endif
 #ifdef TARGET_NR_clock_nanosleep
-{ TARGET_NR_clock_nanosleep, "clock_nanosleep" , NULL, NULL, NULL },
+{ TARGET_NR_clock_nanosleep, "clock_nanosleep" , NULL, print_clock_nanosleep,
+                            NULL },
 #endif
 #ifdef TARGET_NR_clock_settime
 { TARGET_NR_clock_settime, "clock_settime" , NULL, print_clock_settime, NULL },
@@ -278,10 +279,10 @@
 { TARGET_NR_getcwd, "getcwd" , "%s(%p,%d)", NULL, NULL },
 #endif
 #ifdef TARGET_NR_getdents
-{ TARGET_NR_getdents, "getdents" , NULL, NULL, NULL },
+{ TARGET_NR_getdents, "getdents" , "%s(%d,%p,%u)", NULL, NULL },
 #endif
 #ifdef TARGET_NR_getdents64
-{ TARGET_NR_getdents64, "getdents64" , NULL, NULL, NULL },
+{ TARGET_NR_getdents64, "getdents64" , "%s(%d,%p,%u)", NULL, NULL },
 #endif
 #ifdef TARGET_NR_getdomainname
 { TARGET_NR_getdomainname, "getdomainname" , NULL, NULL, NULL },
@@ -351,7 +352,7 @@
 { TARGET_NR_getpriority, "getpriority", "%s(%#x,%#x)", NULL, NULL },
 #endif
 #ifdef TARGET_NR_getrandom
-{ TARGET_NR_getrandom, "getrandom", NULL, NULL, NULL },
+{ TARGET_NR_getrandom, "getrandom", "%s(%p,%u,%u)", NULL, NULL },
 #endif
 #ifdef TARGET_NR_getresgid
 { TARGET_NR_getresgid, "getresgid" , NULL, NULL, NULL },
@@ -541,7 +542,7 @@
 { TARGET_NR_lstat64, "lstat64" , NULL, print_lstat64, NULL },
 #endif
 #ifdef TARGET_NR_madvise
-{ TARGET_NR_madvise, "madvise" , NULL, NULL, NULL },
+{ TARGET_NR_madvise, "madvise" , NULL, print_madvise, NULL },
 #endif
 #ifdef TARGET_NR_madvise1
 { TARGET_NR_madvise1, "madvise1" , NULL, NULL, NULL },
@@ -1664,6 +1665,15 @@
 #ifdef TARGET_NR_pipe2
 { TARGET_NR_pipe2, "pipe2", NULL, NULL, NULL },
 #endif
+#ifdef TARGET_NR_pidfd_open
+{ TARGET_NR_pidfd_open, "pidfd_open", "%s(%d,%u)", NULL, NULL },
+#endif
+#ifdef TARGET_NR_pidfd_send_signal
+{ TARGET_NR_pidfd_send_signal, "pidfd_send_signal", NULL, print_pidfd_send_signal, NULL },
+#endif
+#ifdef TARGET_NR_pidfd_getfd
+{ TARGET_NR_pidfd_getfd, "pidfd_getfd", "%s(%d,%d,%u)", NULL, NULL },
+#endif
 #ifdef TARGET_NR_atomic_cmpxchg_32
 { TARGET_NR_atomic_cmpxchg_32, "atomic_cmpxchg_32", NULL, NULL, NULL },
 #endif
@@ -1676,3 +1686,7 @@
 #ifdef TARGET_NR_copy_file_range
 { TARGET_NR_copy_file_range, "copy_file_range", "%s(%d,%p,%d,%p,"TARGET_ABI_FMT_lu",%u)", NULL, NULL },
 #endif
+#ifdef TARGET_NR_clock_gettime64
+{ TARGET_NR_clock_gettime64, "clock_gettime64" , NULL, print_clock_gettime64,
+                           print_syscall_ret_clock_gettime64 },
+#endif

linux-user/syscall.c

@@ -346,6 +346,16 @@ _syscall6(int,sys_futex,int *,uaddr,int,op,int,val,
 _syscall6(int,sys_futex_time64,int *,uaddr,int,op,int,val,
           const struct timespec *,timeout,int *,uaddr2,int,val3)
 #endif
+#if defined(__NR_pidfd_open) && defined(TARGET_NR_pidfd_open)
+_syscall2(int, pidfd_open, pid_t, pid, unsigned int, flags);
+#endif
+#if defined(__NR_pidfd_send_signal) && defined(TARGET_NR_pidfd_send_signal)
+_syscall4(int, pidfd_send_signal, int, pidfd, int, sig, siginfo_t *, info,
+                             unsigned int, flags);
+#endif
+#if defined(__NR_pidfd_getfd) && defined(TARGET_NR_pidfd_getfd)
+_syscall3(int, pidfd_getfd, int, pidfd, int, targetfd, unsigned int, flags);
+#endif
 #define __NR_sys_sched_getaffinity __NR_sched_getaffinity
 _syscall3(int, sys_sched_getaffinity, pid_t, pid, unsigned int, len,
           unsigned long *, user_mask_ptr);
@@ -515,20 +525,25 @@ _syscall4(int, sys_prlimit64, pid_t, pid, int, resource,
 
 #if defined(TARGET_NR_timer_create)
 /* Maximum of 32 active POSIX timers allowed at any one time. */
-static timer_t g_posix_timers[32] = { 0, } ;
+#define GUEST_TIMER_MAX 32
+static timer_t g_posix_timers[GUEST_TIMER_MAX];
+static int g_posix_timer_allocated[GUEST_TIMER_MAX];
 
 static inline int next_free_host_timer(void)
 {
-    int k ;
+    int k;
-    /* FIXME: Does finding the next free slot require a lock? */
+    for (k = 0; k < ARRAY_SIZE(g_posix_timer_allocated); k++) {
-    for (k = 0; k < ARRAY_SIZE(g_posix_timers); k++) {
+        if (qatomic_xchg(g_posix_timer_allocated + k, 1) == 0) {
-        if (g_posix_timers[k] == 0) {
-            g_posix_timers[k] = (timer_t) 1;
             return k;
         }
     }
     return -1;
 }
+
+static inline void free_host_timer_slot(int id)
+{
+    qatomic_store_release(g_posix_timer_allocated + id, 0);
+}
 #endif
 
 static inline int host_to_target_errno(int host_errno)
@@ -7753,65 +7768,16 @@ static int do_safe_futex(int *uaddr, int op, int val,
    futexes locally would make futexes shared between multiple processes
    tricky.  However they're probably useless because guest atomic
    operations won't work either.  */
-#if defined(TARGET_NR_futex)
+#if defined(TARGET_NR_futex) || defined(TARGET_NR_futex_time64)
-static int do_futex(CPUState *cpu, target_ulong uaddr, int op, int val,
+static int do_futex(CPUState *cpu, bool time64, target_ulong uaddr,
-                    target_ulong timeout, target_ulong uaddr2, int val3)
+                    int op, int val, target_ulong timeout,
-{
-    struct timespec ts, *pts;
-    int base_op;
-
-    /* ??? We assume FUTEX_* constants are the same on both host
-       and target.  */
-#ifdef FUTEX_CMD_MASK
-    base_op = op & FUTEX_CMD_MASK;
-#else
-    base_op = op;
-#endif
-    switch (base_op) {
-    case FUTEX_WAIT:
-    case FUTEX_WAIT_BITSET:
-        if (timeout) {
-            pts = &ts;
-            target_to_host_timespec(pts, timeout);
-        } else {
-            pts = NULL;
-        }
-        return do_safe_futex(g2h(cpu, uaddr),
-                             op, tswap32(val), pts, NULL, val3);
-    case FUTEX_WAKE:
-        return do_safe_futex(g2h(cpu, uaddr),
-                             op, val, NULL, NULL, 0);
-    case FUTEX_FD:
-        return do_safe_futex(g2h(cpu, uaddr),
-                             op, val, NULL, NULL, 0);
-    case FUTEX_REQUEUE:
-    case FUTEX_CMP_REQUEUE:
-    case FUTEX_WAKE_OP:
-        /* For FUTEX_REQUEUE, FUTEX_CMP_REQUEUE, and FUTEX_WAKE_OP, the
-           TIMEOUT parameter is interpreted as a uint32_t by the kernel.
-           But the prototype takes a `struct timespec *'; insert casts
-           to satisfy the compiler.  We do not need to tswap TIMEOUT
-           since it's not compared to guest memory.  */
-        pts = (struct timespec *)(uintptr_t) timeout;
-        return do_safe_futex(g2h(cpu, uaddr), op, val, pts, g2h(cpu, uaddr2),
-                             (base_op == FUTEX_CMP_REQUEUE
-                              ? tswap32(val3) : val3));
-    default:
-        return -TARGET_ENOSYS;
-    }
-}
-#endif
-
-#if defined(TARGET_NR_futex_time64)
-static int do_futex_time64(CPUState *cpu, target_ulong uaddr, int op,
-                           int val, target_ulong timeout,
                     target_ulong uaddr2, int val3)
 {
-    struct timespec ts, *pts;
+    struct timespec ts, *pts = NULL;
+    void *haddr2 = NULL;
     int base_op;
 
-    /* ??? We assume FUTEX_* constants are the same on both host
+    /* We assume FUTEX_* constants are the same on both host and target. */
-       and target.  */
 #ifdef FUTEX_CMD_MASK
     base_op = op & FUTEX_CMD_MASK;
 #else
@@ -7820,35 +7786,53 @@ static int do_futex_time64(CPUState *cpu, target_ulong uaddr, int op,
     switch (base_op) {
     case FUTEX_WAIT:
     case FUTEX_WAIT_BITSET:
-        if (timeout) {
+        val = tswap32(val);
-            pts = &ts;
+        break;
-            if (target_to_host_timespec64(pts, timeout)) {
+    case FUTEX_WAIT_REQUEUE_PI:
-                return -TARGET_EFAULT;
+        val = tswap32(val);
-            }
+        haddr2 = g2h(cpu, uaddr2);
-        } else {
+        break;
-            pts = NULL;
+    case FUTEX_LOCK_PI:
-        }
+    case FUTEX_LOCK_PI2:
-        return do_safe_futex(g2h(cpu, uaddr), op,
+        break;
-                             tswap32(val), pts, NULL, val3);
     case FUTEX_WAKE:
-        return do_safe_futex(g2h(cpu, uaddr), op, val, NULL, NULL, 0);
+    case FUTEX_WAKE_BITSET:
+    case FUTEX_TRYLOCK_PI:
+    case FUTEX_UNLOCK_PI:
+        timeout = 0;
+        break;
     case FUTEX_FD:
-        return do_safe_futex(g2h(cpu, uaddr), op, val, NULL, NULL, 0);
+        val = target_to_host_signal(val);
-    case FUTEX_REQUEUE:
+        timeout = 0;
+        break;
     case FUTEX_CMP_REQUEUE:
+    case FUTEX_CMP_REQUEUE_PI:
+        val3 = tswap32(val3);
+        /* fall through */
+    case FUTEX_REQUEUE:
     case FUTEX_WAKE_OP:
-        /* For FUTEX_REQUEUE, FUTEX_CMP_REQUEUE, and FUTEX_WAKE_OP, the
+        /*
-           TIMEOUT parameter is interpreted as a uint32_t by the kernel.
+         * For these, the 4th argument is not TIMEOUT, but VAL2.
-           But the prototype takes a `struct timespec *'; insert casts
+         * But the prototype of do_safe_futex takes a pointer, so
-           to satisfy the compiler.  We do not need to tswap TIMEOUT
+         * insert casts to satisfy the compiler.  We do not need
-           since it's not compared to guest memory.  */
+         * to tswap VAL2 since it's not compared to guest memory.
-        pts = (struct timespec *)(uintptr_t) timeout;
+          */
-        return do_safe_futex(g2h(cpu, uaddr), op, val, pts, g2h(cpu, uaddr2),
+        pts = (struct timespec *)(uintptr_t)timeout;
-                             (base_op == FUTEX_CMP_REQUEUE
+        timeout = 0;
-                              ? tswap32(val3) : val3));
+        haddr2 = g2h(cpu, uaddr2);
+        break;
     default:
         return -TARGET_ENOSYS;
     }
+    if (timeout) {
+        pts = &ts;
+        if (time64
+            ? target_to_host_timespec64(pts, timeout)
+            : target_to_host_timespec(pts, timeout)) {
+            return -TARGET_EFAULT;
+        }
+    }
+    return do_safe_futex(g2h(cpu, uaddr), op, val, pts, haddr2, val3);
 }
 #endif
 
@@ -8026,7 +8010,11 @@ static int open_self_maps(CPUArchState *cpu_env, int fd)
                 continue;
             }
 
+#ifdef TARGET_HPPA
+            if (h2g(max) == ts->info->stack_limit) {
+#else
             if (h2g(min) == ts->info->stack_limit) {
+#endif
                 path = "[stack]";
             } else {
                 path = e->path;
@@ -8683,6 +8671,30 @@ static abi_long do_syscall1(CPUArchState *cpu_env, int num, abi_long arg1,
         ret = do_open_by_handle_at(arg1, arg2, arg3);
         fd_trans_unregister(ret);
         return ret;
+#endif
+#if defined(__NR_pidfd_open) && defined(TARGET_NR_pidfd_open)
+    case TARGET_NR_pidfd_open:
+        return get_errno(pidfd_open(arg1, arg2));
+#endif
+#if defined(__NR_pidfd_send_signal) && defined(TARGET_NR_pidfd_send_signal)
+    case TARGET_NR_pidfd_send_signal:
+        {
+            siginfo_t uinfo;
+
+            p = lock_user(VERIFY_READ, arg3, sizeof(target_siginfo_t), 1);
+            if (!p) {
+                return -TARGET_EFAULT;
+            }
+            target_to_host_siginfo(&uinfo, p);
+            unlock_user(p, arg3, 0);
+            ret = get_errno(pidfd_send_signal(arg1, target_to_host_signal(arg2),
+                &uinfo, arg4));
+        }
+        return ret;
+#endif
+#if defined(__NR_pidfd_getfd) && defined(TARGET_NR_pidfd_getfd)
+    case TARGET_NR_pidfd_getfd:
+        return get_errno(pidfd_getfd(arg1, arg2, arg3));
 #endif
     case TARGET_NR_close:
         fd_trans_unregister(arg1);
@@ -9690,7 +9702,7 @@ static abi_long do_syscall1(CPUArchState *cpu_env, int num, abi_long arg1,
             }
             target_to_host_siginfo(&uinfo, p);
             unlock_user(p, arg3, 0);
-            ret = get_errno(sys_rt_sigqueueinfo(arg1, arg2, &uinfo));
+            ret = get_errno(sys_rt_sigqueueinfo(arg1, target_to_host_signal(arg2), &uinfo));
         }
         return ret;
     case TARGET_NR_rt_tgsigqueueinfo:
@@ -9703,7 +9715,7 @@ static abi_long do_syscall1(CPUArchState *cpu_env, int num, abi_long arg1,
             }
             target_to_host_siginfo(&uinfo, p);
             unlock_user(p, arg4, 0);
-            ret = get_errno(sys_rt_tgsigqueueinfo(arg1, arg2, arg3, &uinfo));
+            ret = get_errno(sys_rt_tgsigqueueinfo(arg1, arg2, target_to_host_signal(arg3), &uinfo));
         }
         return ret;
 #ifdef TARGET_NR_sigreturn
@@ -9912,11 +9924,22 @@ static abi_long do_syscall1(CPUArchState *cpu_env, int num, abi_long arg1,
             p2 = lock_user(VERIFY_WRITE, arg3, arg4, 0);
             if (!p || !p2) {
                 ret = -TARGET_EFAULT;
+            } else if (!arg4) {
+                /* Short circuit this for the magic exe check. */
+                ret = -TARGET_EINVAL;
             } else if (is_proc_myself((const char *)p, "exe")) {
                 char real[PATH_MAX], *temp;
                 temp = realpath(exec_path, real);
-                ret = temp == NULL ? get_errno(-1) : strlen(real) ;
+                /* Return value is # of bytes that we wrote to the buffer. */
-                snprintf((char *)p2, arg4, "%s", real);
+                if (temp == NULL) {
+                    ret = get_errno(-1);
+                } else {
+                    /* Don't worry about sign mismatch as earlier mapping
+                     * logic would have thrown a bad address error. */
+                    ret = MIN(strlen(real), arg4);
+                    /* We cannot NUL terminate the string. */
+                    memcpy(p2, real, ret);
+                }
             } else {
                 ret = get_errno(readlinkat(arg1, path(p), p2, arg4));
             }
@@ -12318,11 +12341,11 @@ static abi_long do_syscall1(CPUArchState *cpu_env, int num, abi_long arg1,
 #endif
 #ifdef TARGET_NR_futex
     case TARGET_NR_futex:
-        return do_futex(cpu, arg1, arg2, arg3, arg4, arg5, arg6);
+        return do_futex(cpu, false, arg1, arg2, arg3, arg4, arg5, arg6);
 #endif
 #ifdef TARGET_NR_futex_time64
     case TARGET_NR_futex_time64:
-        return do_futex_time64(cpu, arg1, arg2, arg3, arg4, arg5, arg6);
+        return do_futex(cpu, true, arg1, arg2, arg3, arg4, arg5, arg6);
 #endif
 #ifdef CONFIG_INOTIFY
 #if defined(TARGET_NR_inotify_init)
@@ -12847,15 +12870,18 @@ static abi_long do_syscall1(CPUArchState *cpu_env, int num, abi_long arg1,
                 phost_sevp = &host_sevp;
                 ret = target_to_host_sigevent(phost_sevp, arg2);
                 if (ret != 0) {
+                    free_host_timer_slot(timer_index);
                     return ret;
                 }
             }
 
             ret = get_errno(timer_create(clkid, phost_sevp, phtimer));
             if (ret) {
-                phtimer = NULL;
+                free_host_timer_slot(timer_index);
             } else {
                 if (put_user(TIMER_MAGIC | timer_index, arg3, target_timer_t)) {
+                    timer_delete(*phtimer);
+                    free_host_timer_slot(timer_index);
                     return -TARGET_EFAULT;
                 }
             }
@@ -12991,7 +13017,7 @@ static abi_long do_syscall1(CPUArchState *cpu_env, int num, abi_long arg1,
         } else {
             timer_t htimer = g_posix_timers[timerid];
             ret = get_errno(timer_delete(htimer));
-            g_posix_timers[timerid] = 0;
+            free_host_timer_slot(timerid);
         }
         return ret;
     }

linux-user/syscall_defs.h

@@ -1246,7 +1246,7 @@ struct target_winsize {
 
 #include "termbits.h"
 
-#if defined(TARGET_MIPS)
+#if defined(TARGET_MIPS) || defined(TARGET_XTENSA)
 #define TARGET_PROT_SEM         0x10
 #else
 #define TARGET_PROT_SEM         0x08
@@ -2699,6 +2699,9 @@ struct target_drm_i915_getparam {
 #define FUTEX_TRYLOCK_PI        8
 #define FUTEX_WAIT_BITSET       9
 #define FUTEX_WAKE_BITSET       10
+#define FUTEX_WAIT_REQUEUE_PI   11
+#define FUTEX_CMP_REQUEUE_PI    12
+#define FUTEX_LOCK_PI2          13
 
 #define FUTEX_PRIVATE_FLAG      128
 #define FUTEX_CLOCK_REALTIME    256

linux-user/x86_64/target_elf.h

@@ -9,6 +9,6 @@
 #define X86_64_TARGET_ELF_H
 static inline const char *cpu_get_model(uint32_t eflags)
 {
-    return "qemu64";
+    return "max";
 }
 #endif

linux-user/x86_64/target_mman.h

@@ -0,0 +1 @@
+#include "../generic/target_mman.h"

linux-user/xtensa/target_mman.h

@@ -0,0 +1 @@
+#include "../generic/target_mman.h"

target/hppa/helper.c

@@ -85,9 +85,11 @@ void hppa_cpu_dump_state(CPUState *cs, FILE *f, int flags)
     char psw_c[20];
     int i;
 
-    qemu_fprintf(f, "IA_F " TARGET_FMT_lx " IA_B " TARGET_FMT_lx "\n",
+    qemu_fprintf(f, "IA_F " TARGET_FMT_lx " IA_B " TARGET_FMT_lx
+                 " IIR " TREG_FMT_lx  "\n",
                  hppa_form_gva_psw(psw, env->iasq_f, env->iaoq_f),
-                 hppa_form_gva_psw(psw, env->iasq_b, env->iaoq_b));
+                 hppa_form_gva_psw(psw, env->iasq_b, env->iaoq_b),
+                 env->cr[CR_IIR]);
 
     psw_c[0]  = (psw & PSW_W ? 'W' : '-');
     psw_c[1]  = (psw & PSW_E ? 'E' : '-');

tests/tcg/multiarch/linux/linux-madvise.c

@@ -0,0 +1,70 @@
+#include <assert.h>
+#include <stdlib.h>
+#include <sys/mman.h>
+#include <unistd.h>
+
+static void test_anonymous(void)
+{
+    int pagesize = getpagesize();
+    char *page;
+    int ret;
+
+    page = mmap(NULL, pagesize, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+    assert(page != MAP_FAILED);
+
+    /* Check that mprotect() does not interfere with MADV_DONTNEED. */
+    ret = mprotect(page, pagesize, PROT_READ | PROT_WRITE);
+    assert(ret == 0);
+
+    /* Check that MADV_DONTNEED clears the page. */
+    *page = 42;
+    ret = madvise(page, pagesize, MADV_DONTNEED);
+    assert(ret == 0);
+    assert(*page == 0);
+
+    ret = munmap(page, pagesize);
+    assert(ret == 0);
+}
+
+static void test_file(void)
+{
+    char tempname[] = "/tmp/.cmadviseXXXXXX";
+    int pagesize = getpagesize();
+    ssize_t written;
+    char c = 42;
+    char *page;
+    int ret;
+    int fd;
+
+    fd = mkstemp(tempname);
+    assert(fd != -1);
+    ret = unlink(tempname);
+    assert(ret == 0);
+    written = write(fd, &c, sizeof(c));
+    assert(written == sizeof(c));
+    page = mmap(NULL, pagesize, PROT_READ, MAP_PRIVATE, fd, 0);
+    assert(page != MAP_FAILED);
+
+    /* Check that mprotect() does not interfere with MADV_DONTNEED. */
+    ret = mprotect(page, pagesize, PROT_READ | PROT_WRITE);
+    assert(ret == 0);
+
+    /* Check that MADV_DONTNEED resets the page. */
+    *page = 0;
+    ret = madvise(page, pagesize, MADV_DONTNEED);
+    assert(ret == 0);
+    assert(*page == c);
+
+    ret = munmap(page, pagesize);
+    assert(ret == 0);
+    ret = close(fd);
+    assert(ret == 0);
+}
+
+int main(void)
+{
+    test_anonymous();
+    test_file();
+
+    return EXIT_SUCCESS;
+}