@nxtedition/rocksdb 7.0.2 → 7.0.5

package/deps/liburing/liburing/README

@@ -0,0 +1,46 @@
+liburing
+--------
+
+This is the io_uring library, liburing. liburing provides helpers to setup and
+teardown io_uring instances, and also a simplified interface for
+applications that don't need (or want) to deal with the full kernel
+side implementation.
+
+For more info on io_uring, please see:
+
+https://kernel.dk/io_uring.pdf
+
+Subscribe to io-uring@vger.kernel.org for io_uring related discussions
+and development for both kernel and userspace. The list is archived here:
+
+https://lore.kernel.org/io-uring/
+
+
+ulimit settings
+---------------
+
+io_uring accounts memory it needs under the rlimit memlocked option, which
+can be quite low on some setups (64K). The default is usually enough for
+most use cases, but bigger rings or things like registered buffers deplete
+it quickly. root isn't under this restriction, but regular users are. Going
+into detail on how to bump the limit on various systems is beyond the scope
+of this little blurb, but check /etc/security/limits.conf for user specific
+settings, or /etc/systemd/user.conf and /etc/systemd/system.conf for systemd
+setups.
+
+Regressions tests
+-----------------
+
+The bulk of liburing is actually regression/unit tests for both liburing and
+the kernel io_uring support. Please note that this suite isn't expected to
+pass on older kernels, and may even crash or hang older kernels!
+
+License
+-------
+
+All software contained within this repo is dual licensed LGPL and MIT, see
+COPYING and LICENSE, except for a header coming from the kernel which is
+dual licensed GPL with a Linux-syscall-note exception and MIT, see
+COPYING.GPL and <https://spdx.org/licenses/Linux-syscall-note.html>.
+
+Jens Axboe 2020-01-20

package/deps/liburing/liburing/test/232c93d07b74-test.c

@@ -0,0 +1,305 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Test case for socket read/write through IORING_OP_READV and
+ * IORING_OP_WRITEV, using both TCP and sockets and blocking and
+ * non-blocking IO.
+ *
+ * Heavily based on a test case from Hrvoje Zeba <zeba.hrvoje@gmail.com>
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdint.h>
+#include <assert.h>
+
+#include <pthread.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <sys/socket.h>
+#include <sys/un.h>
+#include <netinet/tcp.h>
+#include <netinet/in.h>
+
+#include "liburing.h"
+
+#define RECV_BUFF_SIZE 2
+#define SEND_BUFF_SIZE 3
+
+#define PORT	0x1235
+
+struct params {
+	int tcp;
+	int non_blocking;
+};
+
+pthread_mutex_t mutex = PTHREAD_MUTEX_INITIALIZER;
+pthread_cond_t cond = PTHREAD_COND_INITIALIZER;
+int rcv_ready = 0;
+
+static void set_rcv_ready(void)
+{
+	pthread_mutex_lock(&mutex);
+
+	rcv_ready = 1;
+	pthread_cond_signal(&cond);
+
+	pthread_mutex_unlock(&mutex);
+}
+
+static void wait_for_rcv_ready(void)
+{
+	pthread_mutex_lock(&mutex);
+
+	while (!rcv_ready)
+		pthread_cond_wait(&cond, &mutex);
+
+	pthread_mutex_unlock(&mutex);
+}
+
+static void *rcv(void *arg)
+{
+	struct params *p = arg;
+	int s0;
+	int res;
+
+	if (p->tcp) {
+		int val = 1;
+                
+
+		s0 = socket(AF_INET, SOCK_STREAM | SOCK_CLOEXEC, IPPROTO_TCP);
+		res = setsockopt(s0, SOL_SOCKET, SO_REUSEPORT, &val, sizeof(val));
+		assert(res != -1);
+		res = setsockopt(s0, SOL_SOCKET, SO_REUSEADDR, &val, sizeof(val));
+		assert(res != -1);
+
+		struct sockaddr_in addr;
+
+		addr.sin_family = AF_INET;
+		addr.sin_port = PORT;
+		addr.sin_addr.s_addr = 0x0100007fU;
+		res = bind(s0, (struct sockaddr *) &addr, sizeof(addr));
+		assert(res != -1);
+	} else {
+		s0 = socket(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0);
+		assert(s0 != -1);
+
+		struct sockaddr_un addr;
+		memset(&addr, 0, sizeof(addr));
+
+		addr.sun_family = AF_UNIX;
+		memcpy(addr.sun_path, "\0sock", 6);
+		res = bind(s0, (struct sockaddr *) &addr, sizeof(addr));
+		assert(res != -1);
+	}
+	res = listen(s0, 128);
+	assert(res != -1);
+
+	set_rcv_ready();
+
+	int s1 = accept(s0, NULL, NULL);
+	assert(s1 != -1);
+
+	if (p->non_blocking) {
+		int flags = fcntl(s1, F_GETFL, 0);
+		assert(flags != -1);
+
+		flags |= O_NONBLOCK;
+		res = fcntl(s1, F_SETFL, flags);
+		assert(res != -1);
+	}
+
+	struct io_uring m_io_uring;
+	void *ret = NULL;
+
+	res = io_uring_queue_init(32, &m_io_uring, 0);
+	assert(res >= 0);
+
+	int bytes_read = 0;
+	int expected_byte = 0;
+	int done = 0;
+
+	while (!done && bytes_read != 33) {
+		char buff[RECV_BUFF_SIZE];
+		struct iovec iov;
+
+		iov.iov_base = buff;
+		iov.iov_len = sizeof(buff);
+
+		struct io_uring_sqe *sqe = io_uring_get_sqe(&m_io_uring);
+		assert(sqe != NULL);
+
+		io_uring_prep_readv(sqe, s1, &iov, 1, 0);
+
+		res = io_uring_submit(&m_io_uring);
+		assert(res != -1);
+
+		struct io_uring_cqe *cqe;
+		unsigned head;
+		unsigned count = 0;
+
+		while (!done && count != 1) {
+			io_uring_for_each_cqe(&m_io_uring, head, cqe) {
+				if (cqe->res < 0)
+					assert(cqe->res == -EAGAIN);
+				else {
+					int i;
+
+					for (i = 0; i < cqe->res; i++) {
+						if (buff[i] != expected_byte) {
+							fprintf(stderr,
+								"Received %d, wanted %d\n",
+								buff[i], expected_byte);
+							ret++;
+							done = 1;
+						 }
+						 expected_byte++;
+					}
+					bytes_read += cqe->res;
+				}
+
+				count++;
+			}
+
+			assert(count <= 1);
+			io_uring_cq_advance(&m_io_uring, count);
+		}
+	}
+
+	shutdown(s1, SHUT_RDWR);
+	close(s1);
+	close(s0);
+	io_uring_queue_exit(&m_io_uring);
+	return ret;
+}
+
+static void *snd(void *arg)
+{
+	struct params *p = arg;
+	int s0;
+	int ret;
+
+	wait_for_rcv_ready();
+
+	if (p->tcp) {
+		int val = 1;
+
+		s0 = socket(AF_INET, SOCK_STREAM | SOCK_CLOEXEC, IPPROTO_TCP);
+		ret = setsockopt(s0, IPPROTO_TCP, TCP_NODELAY, &val, sizeof(val));
+		assert(ret != -1);
+
+		struct sockaddr_in addr;
+
+		addr.sin_family = AF_INET;
+		addr.sin_port = PORT;
+		addr.sin_addr.s_addr = 0x0100007fU;
+		ret = connect(s0, (struct sockaddr*) &addr, sizeof(addr));
+		assert(ret != -1);
+	} else {
+		s0 = socket(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0);
+		assert(s0 != -1);
+
+		struct sockaddr_un addr;
+		memset(&addr, 0, sizeof(addr));
+
+		addr.sun_family = AF_UNIX;
+		memcpy(addr.sun_path, "\0sock", 6);
+		ret = connect(s0, (struct sockaddr*) &addr, sizeof(addr));
+		assert(ret != -1);
+	}
+
+	if (p->non_blocking) {
+		int flags = fcntl(s0, F_GETFL, 0);
+		assert(flags != -1);
+
+		flags |= O_NONBLOCK;
+		ret = fcntl(s0, F_SETFL, flags);
+		assert(ret != -1);
+	}
+
+	struct io_uring m_io_uring;
+
+	ret = io_uring_queue_init(32, &m_io_uring, 0);
+	assert(ret >= 0);
+
+	int bytes_written = 0;
+	int done = 0;
+
+	while (!done && bytes_written != 33) {
+		char buff[SEND_BUFF_SIZE];
+		int i;
+
+		for (i = 0; i < SEND_BUFF_SIZE; i++)
+			buff[i] = i + bytes_written;
+
+		struct iovec iov;
+
+		iov.iov_base = buff;
+		iov.iov_len = sizeof(buff);
+
+		struct io_uring_sqe *sqe = io_uring_get_sqe(&m_io_uring);
+		assert(sqe != NULL);
+
+		io_uring_prep_writev(sqe, s0, &iov, 1, 0);
+
+		ret = io_uring_submit(&m_io_uring);
+		assert(ret != -1);
+
+		struct io_uring_cqe *cqe;
+		unsigned head;
+		unsigned count = 0;
+
+		while (!done && count != 1) {
+			io_uring_for_each_cqe(&m_io_uring, head, cqe) {
+				if (cqe->res < 0) {
+					if (cqe->res == -EPIPE) {
+						done = 1;
+						break;
+					}
+					assert(cqe->res == -EAGAIN);
+				} else {
+					bytes_written += cqe->res;
+				}
+
+				count++;
+			}
+
+			assert(count <= 1);
+			io_uring_cq_advance(&m_io_uring, count);
+		}
+		usleep(100000);
+	}
+
+	shutdown(s0, SHUT_RDWR);
+	close(s0);
+	io_uring_queue_exit(&m_io_uring);
+	return NULL;
+}
+
+int main(int argc, char *argv[])
+{
+	struct params p;
+	pthread_t t1, t2;
+	void *res1, *res2;
+	int i, exit_val = 0;
+
+	if (argc > 1)
+		return 0;
+
+	for (i = 0; i < 4; i++) {
+		p.tcp = i & 1;
+		p.non_blocking = (i & 2) >> 1;
+
+		rcv_ready = 0;
+
+		pthread_create(&t1, NULL, rcv, &p);
+		pthread_create(&t2, NULL, snd, &p);
+		pthread_join(t1, &res1);
+		pthread_join(t2, &res2);
+		if (res1 || res2) {
+			fprintf(stderr, "Failed tcp=%d, non_blocking=%d\n", p.tcp, p.non_blocking);
+			exit_val = 1;
+		}
+	}
+
+	return exit_val;
+}

package/deps/liburing/liburing/test/35fa71a030ca-test.c

@@ -0,0 +1,329 @@
+/* SPDX-License-Identifier: MIT */
+// autogenerated by syzkaller (https://github.com/google/syzkaller)
+
+#include <dirent.h>
+#include <endian.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <pthread.h>
+#include <signal.h>
+#include <stdarg.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/prctl.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <time.h>
+#include <unistd.h>
+#include <sys/mman.h>
+
+#include <linux/futex.h>
+
+#include "liburing.h"
+#include "../src/syscall.h"
+
+#if !defined(SYS_futex) && defined(SYS_futex_time64)
+# define SYS_futex SYS_futex_time64
+#endif
+
+static void sleep_ms(uint64_t ms)
+{
+  usleep(ms * 1000);
+}
+
+static uint64_t current_time_ms(void)
+{
+  struct timespec ts;
+  if (clock_gettime(CLOCK_MONOTONIC, &ts))
+    exit(1);
+  return (uint64_t)ts.tv_sec * 1000 + (uint64_t)ts.tv_nsec / 1000000;
+}
+
+static void thread_start(void* (*fn)(void*), void* arg)
+{
+  pthread_t th;
+  pthread_attr_t attr;
+  pthread_attr_init(&attr);
+  pthread_attr_setstacksize(&attr, 128 << 10);
+  int i;
+  for (i = 0; i < 100; i++) {
+    if (pthread_create(&th, &attr, fn, arg) == 0) {
+      pthread_attr_destroy(&attr);
+      return;
+    }
+    if (errno == EAGAIN) {
+      usleep(50);
+      continue;
+    }
+    break;
+  }
+  exit(1);
+}
+
+typedef struct {
+  int state;
+} event_t;
+
+static void event_init(event_t* ev)
+{
+  ev->state = 0;
+}
+
+static void event_reset(event_t* ev)
+{
+  ev->state = 0;
+}
+
+static void event_set(event_t* ev)
+{
+  if (ev->state)
+    exit(1);
+  __atomic_store_n(&ev->state, 1, __ATOMIC_RELEASE);
+  syscall(SYS_futex, &ev->state, FUTEX_WAKE | FUTEX_PRIVATE_FLAG);
+}
+
+static void event_wait(event_t* ev)
+{
+  while (!__atomic_load_n(&ev->state, __ATOMIC_ACQUIRE))
+    syscall(SYS_futex, &ev->state, FUTEX_WAIT | FUTEX_PRIVATE_FLAG, 0, 0);
+}
+
+static int event_isset(event_t* ev)
+{
+  return __atomic_load_n(&ev->state, __ATOMIC_ACQUIRE);
+}
+
+static int event_timedwait(event_t* ev, uint64_t timeout)
+{
+  uint64_t start = current_time_ms();
+  uint64_t now = start;
+  for (;;) {
+    uint64_t remain = timeout - (now - start);
+    struct timespec ts;
+    ts.tv_sec = remain / 1000;
+    ts.tv_nsec = (remain % 1000) * 1000 * 1000;
+    syscall(SYS_futex, &ev->state, FUTEX_WAIT | FUTEX_PRIVATE_FLAG, 0, &ts);
+    if (__atomic_load_n(&ev->state, __ATOMIC_RELAXED))
+      return 1;
+    now = current_time_ms();
+    if (now - start > timeout)
+      return 0;
+  }
+}
+
+static bool write_file(const char* file, const char* what, ...)
+{
+  char buf[1024];
+  va_list args;
+  va_start(args, what);
+  vsnprintf(buf, sizeof(buf), what, args);
+  va_end(args);
+  buf[sizeof(buf) - 1] = 0;
+  int len = strlen(buf);
+  int fd = open(file, O_WRONLY | O_CLOEXEC);
+  if (fd == -1)
+    return false;
+  if (write(fd, buf, len) != len) {
+    int err = errno;
+    close(fd);
+    errno = err;
+    return false;
+  }
+  close(fd);
+  return true;
+}
+
+static void kill_and_wait(int pid, int* status)
+{
+  kill(-pid, SIGKILL);
+  kill(pid, SIGKILL);
+  int i;
+  for (i = 0; i < 100; i++) {
+    if (waitpid(-1, status, WNOHANG | __WALL) == pid)
+      return;
+    usleep(1000);
+  }
+  DIR* dir = opendir("/sys/fs/fuse/connections");
+  if (dir) {
+    for (;;) {
+      struct dirent* ent = readdir(dir);
+      if (!ent)
+        break;
+      if (strcmp(ent->d_name, ".") == 0 || strcmp(ent->d_name, "..") == 0)
+        continue;
+      char abort[300];
+      snprintf(abort, sizeof(abort), "/sys/fs/fuse/connections/%s/abort",
+               ent->d_name);
+      int fd = open(abort, O_WRONLY);
+      if (fd == -1) {
+        continue;
+      }
+      if (write(fd, abort, 1) < 0) {
+      }
+      close(fd);
+    }
+    closedir(dir);
+  } else {
+  }
+  while (waitpid(-1, status, __WALL) != pid) {
+  }
+}
+
+#define SYZ_HAVE_SETUP_TEST 1
+static void setup_test()
+{
+  prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0);
+  setpgrp();
+  write_file("/proc/self/oom_score_adj", "1000");
+}
+
+struct thread_t {
+  int created, call;
+  event_t ready, done;
+};
+
+static struct thread_t threads[16];
+static void execute_call(int call);
+static int running;
+
+static void* thr(void* arg)
+{
+  struct thread_t* th = (struct thread_t*)arg;
+  for (;;) {
+    event_wait(&th->ready);
+    event_reset(&th->ready);
+    execute_call(th->call);
+    __atomic_fetch_sub(&running, 1, __ATOMIC_RELAXED);
+    event_set(&th->done);
+  }
+  return 0;
+}
+
+static void execute_one(void)
+{
+  int i, call, thread;
+  for (call = 0; call < 3; call++) {
+    for (thread = 0; thread < (int)(sizeof(threads) / sizeof(threads[0]));
+         thread++) {
+      struct thread_t* th = &threads[thread];
+      if (!th->created) {
+        th->created = 1;
+        event_init(&th->ready);
+        event_init(&th->done);
+        event_set(&th->done);
+        thread_start(thr, th);
+      }
+      if (!event_isset(&th->done))
+        continue;
+      event_reset(&th->done);
+      th->call = call;
+      __atomic_fetch_add(&running, 1, __ATOMIC_RELAXED);
+      event_set(&th->ready);
+      event_timedwait(&th->done, 45);
+      break;
+    }
+  }
+  for (i = 0; i < 100 && __atomic_load_n(&running, __ATOMIC_RELAXED); i++)
+    sleep_ms(1);
+}
+
+static void execute_one(void);
+
+#define WAIT_FLAGS __WALL
+
+static void loop(void)
+{
+  int iter;
+  for (iter = 0;; iter++) {
+    int pid = fork();
+    if (pid < 0)
+      exit(1);
+    if (pid == 0) {
+      setup_test();
+      execute_one();
+      exit(0);
+    }
+    int status = 0;
+    uint64_t start = current_time_ms();
+    for (;;) {
+      if (waitpid(-1, &status, WNOHANG | WAIT_FLAGS) == pid)
+        break;
+      sleep_ms(1);
+      if (current_time_ms() - start < 5 * 1000)
+        continue;
+      kill_and_wait(pid, &status);
+      break;
+    }
+  }
+}
+
+uint64_t r[1] = {0xffffffffffffffff};
+
+void execute_call(int call)
+{
+  long res;
+  switch (call) {
+  case 0:
+    *(uint32_t*)0x20000040 = 0;
+    *(uint32_t*)0x20000044 = 0;
+    *(uint32_t*)0x20000048 = 0;
+    *(uint32_t*)0x2000004c = 0;
+    *(uint32_t*)0x20000050 = 0;
+    *(uint32_t*)0x20000054 = 0;
+    *(uint32_t*)0x20000058 = 0;
+    *(uint32_t*)0x2000005c = 0;
+    *(uint32_t*)0x20000060 = 0;
+    *(uint32_t*)0x20000064 = 0;
+    *(uint32_t*)0x20000068 = 0;
+    *(uint32_t*)0x2000006c = 0;
+    *(uint32_t*)0x20000070 = 0;
+    *(uint32_t*)0x20000074 = 0;
+    *(uint32_t*)0x20000078 = 0;
+    *(uint32_t*)0x2000007c = 0;
+    *(uint32_t*)0x20000080 = 0;
+    *(uint32_t*)0x20000084 = 0;
+    *(uint64_t*)0x20000088 = 0;
+    *(uint32_t*)0x20000090 = 0;
+    *(uint32_t*)0x20000094 = 0;
+    *(uint32_t*)0x20000098 = 0;
+    *(uint32_t*)0x2000009c = 0;
+    *(uint32_t*)0x200000a0 = 0;
+    *(uint32_t*)0x200000a4 = 0;
+    *(uint32_t*)0x200000a8 = 0;
+    *(uint32_t*)0x200000ac = 0;
+    *(uint64_t*)0x200000b0 = 0;
+    res = __sys_io_uring_setup(0x64, (struct io_uring_params *) 0x20000040UL);
+    if (res != -1)
+      r[0] = res;
+    break;
+  case 1:
+    __sys_io_uring_register((long)r[0], 0, 0, 0);
+    break;
+  case 2:
+    __sys_io_uring_register((long)r[0], 0, 0, 0);
+    break;
+  }
+}
+
+static void sig_int(int sig)
+{
+	exit(0);
+}
+
+int main(int argc, char *argv[])
+{
+	if (argc > 1)
+		return 0;
+	signal(SIGINT, sig_int);
+	mmap((void *) 0x20000000, 0x1000000, 3, 0x32, -1, 0);
+	signal(SIGALRM, sig_int);
+	alarm(5);
+
+	loop();
+	return 0;
+}