February 2024 - Linux-stable-mirror

[PATCH 6.1.y] fs: dlm: don't put dlm_local_addrs on heap

by Jordan Rife

From: Alexander Aring <aahringo(a)redhat.com> commit c51c9cd8addcfbdc097dbefd59f022402183644b upstream This patch removes to allocate the dlm_local_addr[] pointers on the heap. Instead we directly store the type of "struct sockaddr_storage". This removes function deinit_local() because it was freeing memory only. Backport e11dea8 ("dlm: use kernel_connect() and kernel_bind()") to Linux stable 6.1 caused a regression. The original patch expected dlm_local_addrs[0] to be of type sockaddr_storage, because c51c9cd ("fs: dlm: don't put dlm_local_addrs on heap") changed its type from sockaddr_storage* to sockaddr_storage in Linux 6.5+ while in older Linux versions this is still the original sockaddr_storage*. Signed-off-by: Alexander Aring <aahringo(a)redhat.com> Signed-off-by: David Teigland <teigland(a)redhat.com> Signed-off-by: Jordan Rife <jrife(a)google.com> Tested-by: Valentin Kleibel <valentin(a)vrvis.at> Fixes: e11dea8f5033 ("dlm: use kernel_connect() and kernel_bind()") Closes: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=1063338 Link: https://lore.kernel.org/stable/20240209162658.70763-2-jrife@google.com/T/#u Cc: <stable(a)vger.kernel.org> # 6.1.x --- fs/dlm/lowcomms.c | 36 +++++++++++------------------------- 1 file changed, 11 insertions(+), 25 deletions(-) diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index 72f34f96d0155..e26af8c23aa80 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -174,7 +174,7 @@ static LIST_HEAD(dlm_node_addrs); static DEFINE_SPINLOCK(dlm_node_addrs_spin); static struct listen_connection listen_con; -static struct sockaddr_storage *dlm_local_addr[DLM_MAX_ADDR_COUNT]; +static struct sockaddr_storage dlm_local_addr[DLM_MAX_ADDR_COUNT]; static int dlm_local_count; int dlm_allow_conn; @@ -398,7 +398,7 @@ static int nodeid_to_addr(int nodeid, struct sockaddr_storage *sas_out, if (!sa_out) return 0; - if (dlm_local_addr[0]->ss_family == AF_INET) { + if (dlm_local_addr[0].ss_family == AF_INET) { struct sockaddr_in *in4 = (struct sockaddr_in *) &sas; struct sockaddr_in *ret4 = (struct sockaddr_in *) sa_out; ret4->sin_addr.s_addr = in4->sin_addr.s_addr; @@ -727,7 +727,7 @@ static void add_sock(struct socket *sock, struct connection *con) static void make_sockaddr(struct sockaddr_storage *saddr, uint16_t port, int *addr_len) { - saddr->ss_family = dlm_local_addr[0]->ss_family; + saddr->ss_family = dlm_local_addr[0].ss_family; if (saddr->ss_family == AF_INET) { struct sockaddr_in *in4_addr = (struct sockaddr_in *)saddr; in4_addr->sin_port = cpu_to_be16(port); @@ -1167,7 +1167,7 @@ static int sctp_bind_addrs(struct socket *sock, uint16_t port) int i, addr_len, result = 0; for (i = 0; i < dlm_local_count; i++) { - memcpy(&localaddr, dlm_local_addr[i], sizeof(localaddr)); + memcpy(&localaddr, &dlm_local_addr[i], sizeof(localaddr)); make_sockaddr(&localaddr, port, &addr_len); if (!i) @@ -1187,7 +1187,7 @@ static int sctp_bind_addrs(struct socket *sock, uint16_t port) /* Get local addresses */ static void init_local(void) { - struct sockaddr_storage sas, *addr; + struct sockaddr_storage sas; int i; dlm_local_count = 0; @@ -1195,21 +1195,10 @@ static void init_local(void) if (dlm_our_addr(&sas, i)) break; - addr = kmemdup(&sas, sizeof(*addr), GFP_NOFS); - if (!addr) - break; - dlm_local_addr[dlm_local_count++] = addr; + memcpy(&dlm_local_addr[dlm_local_count++], &sas, sizeof(sas)); } } -static void deinit_local(void) -{ - int i; - - for (i = 0; i < dlm_local_count; i++) - kfree(dlm_local_addr[i]); -} - static struct writequeue_entry *new_writequeue_entry(struct connection *con) { struct writequeue_entry *entry; @@ -1575,7 +1564,7 @@ static void dlm_connect(struct connection *con) } /* Create a socket to communicate with */ - result = sock_create_kern(&init_net, dlm_local_addr[0]->ss_family, + result = sock_create_kern(&init_net, dlm_local_addr[0].ss_family, SOCK_STREAM, dlm_proto_ops->proto, &sock); if (result < 0) goto socket_err; @@ -1786,7 +1775,6 @@ void dlm_lowcomms_stop(void) foreach_conn(free_conn); srcu_read_unlock(&connections_srcu, idx); work_stop(); - deinit_local(); dlm_proto_ops = NULL; } @@ -1803,7 +1791,7 @@ static int dlm_listen_for_all(void) if (result < 0) return result; - result = sock_create_kern(&init_net, dlm_local_addr[0]->ss_family, + result = sock_create_kern(&init_net, dlm_local_addr[0].ss_family, SOCK_STREAM, dlm_proto_ops->proto, &sock); if (result < 0) { log_print("Can't create comms socket: %d", result); @@ -1842,7 +1830,7 @@ static int dlm_tcp_bind(struct socket *sock) /* Bind to our cluster-known address connecting to avoid * routing problems. */ - memcpy(&src_addr, dlm_local_addr[0], sizeof(src_addr)); + memcpy(&src_addr, &dlm_local_addr[0], sizeof(src_addr)); make_sockaddr(&src_addr, 0, &addr_len); result = kernel_bind(sock, (struct sockaddr *)&src_addr, @@ -1899,7 +1887,7 @@ static int dlm_tcp_listen_bind(struct socket *sock) int addr_len; /* Bind to our port */ - make_sockaddr(dlm_local_addr[0], dlm_config.ci_tcp_port, &addr_len); + make_sockaddr(&dlm_local_addr[0], dlm_config.ci_tcp_port, &addr_len); return kernel_bind(sock, (struct sockaddr *)&dlm_local_addr[0], addr_len); } @@ -1992,7 +1980,7 @@ int dlm_lowcomms_start(void) error = work_start(); if (error) - goto fail_local; + goto fail; dlm_allow_conn = 1; @@ -2022,8 +2010,6 @@ int dlm_lowcomms_start(void) fail_proto_ops: dlm_allow_conn = 0; work_stop(); -fail_local: - deinit_local(); fail: return error; } -- 2.43.0.687.g38aa6559b0-goog

1 year, 2 months

1
0
0 0

[PATCH 05/10] arm64: dts: qcom: sc8280xp-x13s: limit pcie4 link speed

by Johan Hovold

Limit the WiFi PCIe link speed to Gen2 speed (500 GB/s), which is the speed that the boot firmware has brought up the link at (and that Windows uses). This is specifically needed to avoid a large amount of link errors when restarting the link during boot (but which are currently not reported). This may potentially also help with intermittent failures to download the ath11k firmware during boot which can be seen when there is a longer delay between restarting the link and loading the WiFi driver (e.g. when using full disk encryption). Fixes: 123b30a75623 ("arm64: dts: qcom: sc8280xp-x13s: enable WiFi controller") Cc: stable(a)vger.kernel.org # 6.2 Signed-off-by: Johan Hovold <johan+linaro(a)kernel.org> --- arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts b/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts index 511d53d9c5a1..ff4b896b1bbf 100644 --- a/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts +++ b/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts @@ -863,6 +863,8 @@ &pcie3a_phy { }; &pcie4 { + max-link-speed = <2>; + perst-gpios = <&tlmm 141 GPIO_ACTIVE_LOW>; wake-gpios = <&tlmm 139 GPIO_ACTIVE_LOW>; -- 2.43.0

1 year, 2 months

1
0
0 0

[PATCH 03/10] arm64: dts: qcom: sc8280xp: add missing PCIe minimum OPP

by Johan Hovold

Add the missing PCIe CX performance level votes to avoid relying on other drivers (e.g. USB or UFS) to maintain the nominal performance level required for Gen3 speeds. Fixes: 813e83157001 ("arm64: dts: qcom: sc8280xp/sa8540p: add PCIe2-4 nodes") Cc: stable(a)vger.kernel.org # 6.2 Signed-off-by: Johan Hovold <johan+linaro(a)kernel.org> --- arch/arm64/boot/dts/qcom/sc8280xp.dtsi | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi index ae41b3051819..36382b1bd965 100644 --- a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi +++ b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi @@ -1780,6 +1780,7 @@ pcie4: pcie@1c00000 { reset-names = "pci"; power-domains = <&gcc PCIE_4_GDSC>; + required-opps = <&rpmhpd_opp_nom>; phys = <&pcie4_phy>; phy-names = "pciephy"; @@ -1878,6 +1879,7 @@ pcie3b: pcie@1c08000 { reset-names = "pci"; power-domains = <&gcc PCIE_3B_GDSC>; + required-opps = <&rpmhpd_opp_nom>; phys = <&pcie3b_phy>; phy-names = "pciephy"; @@ -1976,6 +1978,7 @@ pcie3a: pcie@1c10000 { reset-names = "pci"; power-domains = <&gcc PCIE_3A_GDSC>; + required-opps = <&rpmhpd_opp_nom>; phys = <&pcie3a_phy>; phy-names = "pciephy"; @@ -2077,6 +2080,7 @@ pcie2b: pcie@1c18000 { reset-names = "pci"; power-domains = <&gcc PCIE_2B_GDSC>; + required-opps = <&rpmhpd_opp_nom>; phys = <&pcie2b_phy>; phy-names = "pciephy"; @@ -2175,6 +2179,7 @@ pcie2a: pcie@1c20000 { reset-names = "pci"; power-domains = <&gcc PCIE_2A_GDSC>; + required-opps = <&rpmhpd_opp_nom>; phys = <&pcie2a_phy>; phy-names = "pciephy"; -- 2.43.0

1 year, 2 months

1
0
0 0

Re: [syzbot] [ext4?] KASAN: out-of-bounds Read in ext4_ext_remove_space

by syzbot

syzbot suspects this issue was fixed by commit: commit 6f861765464f43a71462d52026fbddfc858239a5 Author: Jan Kara <jack(a)suse.cz> Date: Wed Nov 1 17:43:10 2023 +0000 fs: Block writes to mounted block devices bisection log: https://syzkaller.appspot.com/x/bisect.txt?x=1764f648180000 start commit: e6fda526d9db Merge tag 'arm64-fixes' of git://git.kernel.o.. git tree: upstream kernel config: https://syzkaller.appspot.com/x/.config?x=1e3d5175079af5a4 dashboard link: https://syzkaller.appspot.com/bug?extid=6e5f2db05775244c73b7 syz repro: https://syzkaller.appspot.com/x/repro.syz?x=16a56679a80000 C reproducer: https://syzkaller.appspot.com/x/repro.c?x=14d76b5da80000 If the result looks correct, please mark the issue as fixed by replying with: #syz fix: fs: Block writes to mounted block devices For information about bisection process see: https://goo.gl/tpsmEJ#bisection

1 year, 2 months

2
1
0 0

[PATCH 0/2] Bluetooth: SCO: possible deadlock in sco_conn_del

by oficerovas＠altlinux.org

From: Alexander Ofitserov <oficerovas(a)altlinux.org> Syzkaller hit 'possible deadlock in sco_conn_del' bug. This bug is not a vulnerability and is reproduced only when running with root privileges for stable 6.1 kernel. This series of patches is fix for this particular bug. Both of these patches were taken from upstream and applied clearly without any conflicts. First one is the fix for the problem and another one is for fix first patch. Bluetooth: hci3: unexpected cc 0x0c38 length: 249 > 2 Bluetooth: hci2: unexpected cc 0x0c38 length: 249 > 2 ====================================================== WARNING: possible circular locking dependency detected 6.1.55-un-def-alt1 #1 Not tainted ------------------------------------------------------ syz-executor272/377 is trying to acquire lock: ffff888115b93130 (sk_lock-AF_BLUETOOTH-BTPROTO_SCO){+.+.}-{0:0}, at: sco_conn_del+0x121/0x2c0 [bluetooth] but task is already holding lock: ffffffffc12bce28 (hci_cb_list_lock){+.+.}-{3:3}, at: hci_conn_hash_flush+0xcc/0x2a0 [bluetooth] which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (hci_cb_list_lock){+.+.}-{3:3}: __mutex_lock_common kernel/locking/mutex.c:603 [inline] __mutex_lock+0x12f/0x18f0 kernel/locking/mutex.c:747 hci_remote_features_evt+0x45b/0x950 [bluetooth] hci_event_packet+0x91e/0xf60 [bluetooth] hci_rx_work+0xa68/0x10f0 [bluetooth] process_one_work+0xa18/0x1570 kernel/workqueue.c:2292 worker_thread+0x63a/0x1260 kernel/workqueue.c:2439 kthread+0x2ec/0x3b0 kernel/kthread.c:376 ret_from_fork+0x22/0x30 arch/x86/entry/entry_64.S:306 -> #1 (&hdev->lock){+.+.}-{3:3}: __mutex_lock_common kernel/locking/mutex.c:603 [inline] __mutex_lock+0x12f/0x18f0 kernel/locking/mutex.c:747 sco_sock_connect+0x1e9/0xa60 [bluetooth] __sys_connect_file+0x15a/0x1a0 net/socket.c:1976 __sys_connect+0x16a/0x1a0 net/socket.c:1993 __do_sys_connect net/socket.c:2003 [inline] __se_sys_connect net/socket.c:2000 [inline] __x64_sys_connect+0x74/0xb0 net/socket.c:2000 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x5c/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x64/0xce -> #0 (sk_lock-AF_BLUETOOTH-BTPROTO_SCO){+.+.}-{0:0}: check_prev_add kernel/locking/lockdep.c:3090 [inline] check_prevs_add kernel/locking/lockdep.c:3209 [inline] validate_chain kernel/locking/lockdep.c:3824 [inline] __lock_acquire+0x28c2/0x5350 kernel/locking/lockdep.c:5048 lock_acquire kernel/locking/lockdep.c:5661 [inline] lock_acquire+0x1fb/0x580 kernel/locking/lockdep.c:5626 lock_sock_nested+0x42/0x100 net/core/sock.c:3475 sco_conn_del+0x121/0x2c0 [bluetooth] sco_disconn_cfm+0x67/0x80 [bluetooth] hci_conn_hash_flush+0x11e/0x2a0 [bluetooth] hci_dev_close_sync+0x51d/0xf70 [bluetooth] hci_rfkill_set_block+0x17c/0x1c0 [bluetooth] rfkill_set_block+0x202/0x550 [rfkill] rfkill_fop_write+0x2b8/0x540 [rfkill] vfs_write+0x2d7/0xdd0 fs/read_write.c:582 ksys_write+0x1f5/0x260 fs/read_write.c:637 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x5c/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x64/0xce other info that might help us debug this: Chain exists of: sk_lock-AF_BLUETOOTH-BTPROTO_SCO --> &hdev->lock --> hci_cb_list_lock Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(hci_cb_list_lock); lock(&hdev->lock); lock(hci_cb_list_lock); lock(sk_lock-AF_BLUETOOTH-BTPROTO_SCO); *** DEADLOCK *** 4 locks held by syz-executor272/377: #0: ffffffffc0d83688 (rfkill_global_mutex){+.+.}-{3:3}, at: rfkill_fop_write+0x162/0x540 [rfkill] #1: ffff888100de90b8 (&hdev->req_lock){+.+.}-{3:3}, at: hci_rfkill_set_block+0x174/0x1c0 [bluetooth] #2: ffff888100de8078 (&hdev->lock){+.+.}-{3:3}, at: hci_dev_close_sync+0x2e1/0xf70 [bluetooth] #3: ffffffffc12bce28 (hci_cb_list_lock){+.+.}-{3:3}, at: hci_conn_hash_flush+0xcc/0x2a0 [bluetooth] stack backtrace: CPU: 1 PID: 377 Comm: syz-executor272 Not tainted 6.1.55-un-def-alt1 #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.0-alt1 04/01/2014 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x14f/0x1be lib/dump_stack.c:106 check_noncircular+0x263/0x2e0 kernel/locking/lockdep.c:2170 check_prev_add kernel/locking/lockdep.c:3090 [inline] check_prevs_add kernel/locking/lockdep.c:3209 [inline] validate_chain kernel/locking/lockdep.c:3824 [inline] __lock_acquire+0x28c2/0x5350 kernel/locking/lockdep.c:5048 lock_acquire kernel/locking/lockdep.c:5661 [inline] lock_acquire+0x1fb/0x580 kernel/locking/lockdep.c:5626 lock_sock_nested+0x42/0x100 net/core/sock.c:3475 sco_conn_del+0x121/0x2c0 [bluetooth] sco_disconn_cfm+0x67/0x80 [bluetooth] hci_conn_hash_flush+0x11e/0x2a0 [bluetooth] hci_dev_close_sync+0x51d/0xf70 [bluetooth] hci_rfkill_set_block+0x17c/0x1c0 [bluetooth] rfkill_set_block+0x202/0x550 [rfkill] rfkill_fop_write+0x2b8/0x540 [rfkill] vfs_write+0x2d7/0xdd0 fs/read_write.c:582 ksys_write+0x1f5/0x260 fs/read_write.c:637 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x5c/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x64/0xce RIP: 0033:0x7fa908ef7d49 Code: 00 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d ef 70 0d 00 f7 d8 64 89 01 48 RSP: 002b:00007fa9085f7e18 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 000055a2e59de080 RCX: 00007fa908ef7d49 RDX: 0000000000000008 RSI: 0000000020000040 RDI: 0000000000000003 RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007ffdb3f52d1e R13: 00007ffdb3f52d1f R14: 000055a2e59de088 R15: 00007fa9085f8640 // autogenerated by syzkaller (https://github.com/google/syzkaller) #define _GNU_SOURCE #include <dirent.h> #include <endian.h> #include <errno.h> #include <fcntl.h> #include <pthread.h> #include <sched.h> #include <signal.h> #include <stdarg.h> #include <stdbool.h> #include <stdint.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <sys/epoll.h> #include <sys/ioctl.h> #include <sys/mount.h> #include <sys/prctl.h> #include <sys/resource.h> #include <sys/socket.h> #include <sys/stat.h> #include <sys/syscall.h> #include <sys/time.h> #include <sys/types.h> #include <sys/uio.h> #include <sys/wait.h> #include <time.h> #include <unistd.h> #include <linux/capability.h> #include <linux/futex.h> #include <linux/rfkill.h> static unsigned long long procid; 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 = 0; for (; 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, 1000000); } 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_ACQUIRE)) 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; } const int kInitNetNsFd = 201; #define MAX_FDS 30 static long syz_init_net_socket(volatile long domain, volatile long type, volatile long proto) { int netns = open("/proc/self/ns/net", O_RDONLY); if (netns == -1) return netns; if (setns(kInitNetNsFd, 0)) return -1; int sock = syscall(__NR_socket, domain, type, proto); int err = errno; if (setns(netns, 0)) exit(1); close(netns); errno = err; return sock; } #define BTPROTO_HCI 1 #define ACL_LINK 1 #define SCAN_PAGE 2 typedef struct { uint8_t b[6]; } __attribute__((packed)) bdaddr_t; #define HCI_COMMAND_PKT 1 #define HCI_EVENT_PKT 4 #define HCI_VENDOR_PKT 0xff struct hci_command_hdr { uint16_t opcode; uint8_t plen; } __attribute__((packed)); struct hci_event_hdr { uint8_t evt; uint8_t plen; } __attribute__((packed)); #define HCI_EV_CONN_COMPLETE 0x03 struct hci_ev_conn_complete { uint8_t status; uint16_t handle; bdaddr_t bdaddr; uint8_t link_type; uint8_t encr_mode; } __attribute__((packed)); #define HCI_EV_CONN_REQUEST 0x04 struct hci_ev_conn_request { bdaddr_t bdaddr; uint8_t dev_class[3]; uint8_t link_type; } __attribute__((packed)); #define HCI_EV_REMOTE_FEATURES 0x0b struct hci_ev_remote_features { uint8_t status; uint16_t handle; uint8_t features[8]; } __attribute__((packed)); #define HCI_EV_CMD_COMPLETE 0x0e struct hci_ev_cmd_complete { uint8_t ncmd; uint16_t opcode; } __attribute__((packed)); #define HCI_OP_WRITE_SCAN_ENABLE 0x0c1a #define HCI_OP_READ_BUFFER_SIZE 0x1005 struct hci_rp_read_buffer_size { uint8_t status; uint16_t acl_mtu; uint8_t sco_mtu; uint16_t acl_max_pkt; uint16_t sco_max_pkt; } __attribute__((packed)); #define HCI_OP_READ_BD_ADDR 0x1009 struct hci_rp_read_bd_addr { uint8_t status; bdaddr_t bdaddr; } __attribute__((packed)); #define HCI_EV_LE_META 0x3e struct hci_ev_le_meta { uint8_t subevent; } __attribute__((packed)); #define HCI_EV_LE_CONN_COMPLETE 0x01 struct hci_ev_le_conn_complete { uint8_t status; uint16_t handle; uint8_t role; uint8_t bdaddr_type; bdaddr_t bdaddr; uint16_t interval; uint16_t latency; uint16_t supervision_timeout; uint8_t clk_accurancy; } __attribute__((packed)); struct hci_dev_req { uint16_t dev_id; uint32_t dev_opt; }; struct vhci_vendor_pkt { uint8_t type; uint8_t opcode; uint16_t id; }; #define HCIDEVUP _IOW('H', 201, int) #define HCISETSCAN _IOW('H', 221, int) static int vhci_fd = -1; static void rfkill_unblock_all() { int fd = open("/dev/rfkill", O_WRONLY); if (fd < 0) exit(1); struct rfkill_event event = {0}; event.idx = 0; event.type = RFKILL_TYPE_ALL; event.op = RFKILL_OP_CHANGE_ALL; event.soft = 0; event.hard = 0; if (write(fd, &event, sizeof(event)) < 0) exit(1); close(fd); } static void hci_send_event_packet(int fd, uint8_t evt, void* data, size_t data_len) { struct iovec iv[3]; struct hci_event_hdr hdr; hdr.evt = evt; hdr.plen = data_len; uint8_t type = HCI_EVENT_PKT; iv[0].iov_base = &type; iv[0].iov_len = sizeof(type); iv[1].iov_base = &hdr; iv[1].iov_len = sizeof(hdr); iv[2].iov_base = data; iv[2].iov_len = data_len; if (writev(fd, iv, sizeof(iv) / sizeof(struct iovec)) < 0) exit(1); } static void hci_send_event_cmd_complete(int fd, uint16_t opcode, void* data, size_t data_len) { struct iovec iv[4]; struct hci_event_hdr hdr; hdr.evt = HCI_EV_CMD_COMPLETE; hdr.plen = sizeof(struct hci_ev_cmd_complete) + data_len; struct hci_ev_cmd_complete evt_hdr; evt_hdr.ncmd = 1; evt_hdr.opcode = opcode; uint8_t type = HCI_EVENT_PKT; iv[0].iov_base = &type; iv[0].iov_len = sizeof(type); iv[1].iov_base = &hdr; iv[1].iov_len = sizeof(hdr); iv[2].iov_base = &evt_hdr; iv[2].iov_len = sizeof(evt_hdr); iv[3].iov_base = data; iv[3].iov_len = data_len; if (writev(fd, iv, sizeof(iv) / sizeof(struct iovec)) < 0) exit(1); } static bool process_command_pkt(int fd, char* buf, ssize_t buf_size) { struct hci_command_hdr* hdr = (struct hci_command_hdr*)buf; if (buf_size < (ssize_t)sizeof(struct hci_command_hdr) || hdr->plen != buf_size - sizeof(struct hci_command_hdr)) exit(1); switch (hdr->opcode) { case HCI_OP_WRITE_SCAN_ENABLE: { uint8_t status = 0; hci_send_event_cmd_complete(fd, hdr->opcode, &status, sizeof(status)); return true; } case HCI_OP_READ_BD_ADDR: { struct hci_rp_read_bd_addr rp = {0}; rp.status = 0; memset(&rp.bdaddr, 0xaa, 6); hci_send_event_cmd_complete(fd, hdr->opcode, &rp, sizeof(rp)); return false; } case HCI_OP_READ_BUFFER_SIZE: { struct hci_rp_read_buffer_size rp = {0}; rp.status = 0; rp.acl_mtu = 1021; rp.sco_mtu = 96; rp.acl_max_pkt = 4; rp.sco_max_pkt = 6; hci_send_event_cmd_complete(fd, hdr->opcode, &rp, sizeof(rp)); return false; } } char dummy[0xf9] = {0}; hci_send_event_cmd_complete(fd, hdr->opcode, dummy, sizeof(dummy)); return false; } static void* event_thread(void* arg) { while (1) { char buf[1024] = {0}; ssize_t buf_size = read(vhci_fd, buf, sizeof(buf)); if (buf_size < 0) exit(1); if (buf_size > 0 && buf[0] == HCI_COMMAND_PKT) { if (process_command_pkt(vhci_fd, buf + 1, buf_size - 1)) break; } } return NULL; } #define HCI_HANDLE_1 200 #define HCI_HANDLE_2 201 static void initialize_vhci() { int hci_sock = socket(AF_BLUETOOTH, SOCK_RAW, BTPROTO_HCI); if (hci_sock < 0) exit(1); vhci_fd = open("/dev/vhci", O_RDWR); if (vhci_fd == -1) exit(1); const int kVhciFd = 202; if (dup2(vhci_fd, kVhciFd) < 0) exit(1); close(vhci_fd); vhci_fd = kVhciFd; struct vhci_vendor_pkt vendor_pkt; if (read(vhci_fd, &vendor_pkt, sizeof(vendor_pkt)) != sizeof(vendor_pkt)) exit(1); if (vendor_pkt.type != HCI_VENDOR_PKT) exit(1); pthread_t th; if (pthread_create(&th, NULL, event_thread, NULL)) exit(1); int ret = ioctl(hci_sock, HCIDEVUP, vendor_pkt.id); if (ret) { if (errno == ERFKILL) { rfkill_unblock_all(); ret = ioctl(hci_sock, HCIDEVUP, vendor_pkt.id); } if (ret && errno != EALREADY) exit(1); } struct hci_dev_req dr = {0}; dr.dev_id = vendor_pkt.id; dr.dev_opt = SCAN_PAGE; if (ioctl(hci_sock, HCISETSCAN, &dr)) exit(1); struct hci_ev_conn_request request; memset(&request, 0, sizeof(request)); memset(&request.bdaddr, 0xaa, 6); *(uint8_t*)&request.bdaddr.b[5] = 0x10; request.link_type = ACL_LINK; hci_send_event_packet(vhci_fd, HCI_EV_CONN_REQUEST, &request, sizeof(request)); struct hci_ev_conn_complete complete; memset(&complete, 0, sizeof(complete)); complete.status = 0; complete.handle = HCI_HANDLE_1; memset(&complete.bdaddr, 0xaa, 6); *(uint8_t*)&complete.bdaddr.b[5] = 0x10; complete.link_type = ACL_LINK; complete.encr_mode = 0; hci_send_event_packet(vhci_fd, HCI_EV_CONN_COMPLETE, &complete, sizeof(complete)); struct hci_ev_remote_features features; memset(&features, 0, sizeof(features)); features.status = 0; features.handle = HCI_HANDLE_1; hci_send_event_packet(vhci_fd, HCI_EV_REMOTE_FEATURES, &features, sizeof(features)); struct { struct hci_ev_le_meta le_meta; struct hci_ev_le_conn_complete le_conn; } le_conn; memset(&le_conn, 0, sizeof(le_conn)); le_conn.le_meta.subevent = HCI_EV_LE_CONN_COMPLETE; memset(&le_conn.le_conn.bdaddr, 0xaa, 6); *(uint8_t*)&le_conn.le_conn.bdaddr.b[5] = 0x11; le_conn.le_conn.role = 1; le_conn.le_conn.handle = HCI_HANDLE_2; hci_send_event_packet(vhci_fd, HCI_EV_LE_META, &le_conn, sizeof(le_conn)); pthread_join(th, NULL); close(hci_sock); } static void setup_common() { if (mount(0, "/sys/fs/fuse/connections", "fusectl", 0, 0)) { } } static void setup_binderfs() { if (mkdir("/dev/binderfs", 0777)) { } if (mount("binder", "/dev/binderfs", "binder", 0, NULL)) { } if (symlink("/dev/binderfs", "./binderfs")) { } } static void loop(); static void sandbox_common() { prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0); setsid(); int netns = open("/proc/self/ns/net", O_RDONLY); if (netns == -1) exit(1); if (dup2(netns, kInitNetNsFd) < 0) exit(1); close(netns); struct rlimit rlim; rlim.rlim_cur = rlim.rlim_max = (200 << 20); setrlimit(RLIMIT_AS, &rlim); rlim.rlim_cur = rlim.rlim_max = 32 << 20; setrlimit(RLIMIT_MEMLOCK, &rlim); rlim.rlim_cur = rlim.rlim_max = 136 << 20; setrlimit(RLIMIT_FSIZE, &rlim); rlim.rlim_cur = rlim.rlim_max = 1 << 20; setrlimit(RLIMIT_STACK, &rlim); rlim.rlim_cur = rlim.rlim_max = 0; setrlimit(RLIMIT_CORE, &rlim); rlim.rlim_cur = rlim.rlim_max = 256; setrlimit(RLIMIT_NOFILE, &rlim); if (unshare(CLONE_NEWNS)) { } if (mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, NULL)) { } if (unshare(CLONE_NEWIPC)) { } if (unshare(0x02000000)) { } if (unshare(CLONE_NEWUTS)) { } if (unshare(CLONE_SYSVSEM)) { } typedef struct { const char* name; const char* value; } sysctl_t; static const sysctl_t sysctls[] = { {"/proc/sys/kernel/shmmax", "16777216"}, {"/proc/sys/kernel/shmall", "536870912"}, {"/proc/sys/kernel/shmmni", "1024"}, {"/proc/sys/kernel/msgmax", "8192"}, {"/proc/sys/kernel/msgmni", "1024"}, {"/proc/sys/kernel/msgmnb", "1024"}, {"/proc/sys/kernel/sem", "1024 1048576 500 1024"}, }; unsigned i; for (i = 0; i < sizeof(sysctls) / sizeof(sysctls[0]); i++) write_file(sysctls[i].name, sysctls[i].value); } static int wait_for_loop(int pid) { if (pid < 0) exit(1); int status = 0; while (waitpid(-1, &status, __WALL) != pid) { } return WEXITSTATUS(status); } static void drop_caps(void) { struct __user_cap_header_struct cap_hdr = {}; struct __user_cap_data_struct cap_data[2] = {}; cap_hdr.version = _LINUX_CAPABILITY_VERSION_3; cap_hdr.pid = getpid(); if (syscall(SYS_capget, &cap_hdr, &cap_data)) exit(1); const int drop = (1 << CAP_SYS_PTRACE) | (1 << CAP_SYS_NICE); cap_data[0].effective &= ~drop; cap_data[0].permitted &= ~drop; cap_data[0].inheritable &= ~drop; if (syscall(SYS_capset, &cap_hdr, &cap_data)) exit(1); } static int do_sandbox_none(void) { if (unshare(CLONE_NEWPID)) { } int pid = fork(); if (pid != 0) return wait_for_loop(pid); setup_common(); initialize_vhci(); sandbox_common(); drop_caps(); if (unshare(CLONE_NEWNET)) { } setup_binderfs(); loop(); exit(1); } static void kill_and_wait(int pid, int* status) { kill(-pid, SIGKILL); kill(pid, SIGKILL); for (int 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) { } } static void setup_test() { prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0); setpgrp(); write_file("/proc/self/oom_score_adj", "1000"); } static void close_fds() { for (int fd = 3; fd < MAX_FDS; fd++) close(fd); } 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 < 4; 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, 50); break; } } for (i = 0; i < 100 && __atomic_load_n(&running, __ATOMIC_RELAXED); i++) sleep_ms(1); close_fds(); } static void execute_one(void); #define WAIT_FLAGS __WALL static void loop(void) { int iter = 0; for (;; 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 < 5000) continue; kill_and_wait(pid, &status); break; } } } uint64_t r[2] = {0xffffffffffffffff, 0xffffffffffffffff}; void execute_call(int call) { intptr_t res = 0; switch (call) { case 0: memcpy((void*)0x20000000, "/dev/rfkill\000", 12); res = syscall(__NR_openat, 0xffffffffffffff9cul, 0x20000000ul, 0x100001ul, 0ul); if (res != -1) r[0] = res; break; case 1: *(uint32_t*)0x20000040 = 0; *(uint8_t*)0x20000044 = 0; *(uint8_t*)0x20000045 = 3; *(uint8_t*)0x20000046 = 1; *(uint8_t*)0x20000047 = 0; syscall(__NR_write, r[0], 0x20000040ul, 8ul); break; case 2: res = -1; res = syz_init_net_socket(0x1f, 5, 2); if (res != -1) r[1] = res; break; case 3: *(uint16_t*)0x20000040 = 0x1f; *(uint16_t*)0x20000042 = 0; memset((void*)0x20000044, 255, 6); *(uint16_t*)0x2000004a = 0; *(uint8_t*)0x2000004c = 0; syscall(__NR_connect, r[1], 0x20000040ul, 0xeul); break; } } int main(void) { syscall(__NR_mmap, 0x1ffff000ul, 0x1000ul, 0ul, 0x32ul, -1, 0ul); syscall(__NR_mmap, 0x20000000ul, 0x1000000ul, 7ul, 0x32ul, -1, 0ul); syscall(__NR_mmap, 0x21000000ul, 0x1000ul, 0ul, 0x32ul, -1, 0ul); for (procid = 0; procid < 4; procid++) { if (fork() == 0) { do_sandbox_none(); } } sleep(1000000); return 0; } [PATCH 1/2] Bluetooth: SCO: Fix possible circular locking dependency [PATCH 2/2] Bluetooth: SCO: fix sco_conn related locking and validity -- 2.42.1

1 year, 2 months

2
3
0 0

[PATCH v3] fs, USB gadget: Remove libaio I/O cancellation support

by Bart Van Assche

Originally io_cancel() only supported cancelling USB reads and writes. If I/O was cancelled successfully, information about the cancelled I/O operation was copied to the data structure the io_cancel() 'result' argument points at. Commit 63b05203af57 ("[PATCH] AIO: retry infrastructure fixes and enhancements") changed the io_cancel() behavior from reporting status information via the 'result' argument into reporting status information on the completion ring. Commit 41003a7bcfed ("aio: remove retry-based AIO") accidentally changed the behavior into not reporting a completion event on the completion ring for cancelled requests. This is a bug because successful cancellation leads to an iocb leak in user space. Since this bug was introduced more than ten years ago and since nobody has complained since then, remove support for I/O cancellation. Keep support for cancellation of IOCB_CMD_POLL requests. Calling kiocb_set_cancel_fn() without knowing whether the caller submitted a struct kiocb or a struct aio_kiocb is unsafe. The following call trace illustrates that without this patch an out-of-bounds write happens if I/O is submitted by io_uring (from a phone with an ARM CPU and kernel 6.1): WARNING: CPU: 3 PID: 368 at fs/aio.c:598 kiocb_set_cancel_fn+0x9c/0xa8 Call trace: kiocb_set_cancel_fn+0x9c/0xa8 ffs_epfile_read_iter+0x144/0x1d0 io_read+0x19c/0x498 io_issue_sqe+0x118/0x27c io_submit_sqes+0x25c/0x5fc __arm64_sys_io_uring_enter+0x104/0xab0 invoke_syscall+0x58/0x11c el0_svc_common+0xb4/0xf4 do_el0_svc+0x2c/0xb0 el0_svc+0x2c/0xa4 el0t_64_sync_handler+0x68/0xb4 el0t_64_sync+0x1a4/0x1a8 Cc: Christoph Hellwig <hch(a)lst.de> Cc: Avi Kivity <avi(a)scylladb.com> Cc: Sandeep Dhavale <dhavale(a)google.com> Cc: Jens Axboe <axboe(a)kernel.dk> Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Fixes: 63b05203af57 ("[PATCH] AIO: retry infrastructure fixes and enhancements") Cc: <stable(a)vger.kernel.org> Signed-off-by: Bart Van Assche <bvanassche(a)acm.org> --- drivers/usb/gadget/function/f_fs.c | 25 ------------------- drivers/usb/gadget/legacy/inode.c | 20 --------------- fs/aio.c | 39 +++++------------------------- include/linux/aio.h | 9 ------- 4 files changed, 6 insertions(+), 87 deletions(-) diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 6bff6cb93789..59789292f4f7 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -1157,25 +1157,6 @@ ffs_epfile_open(struct inode *inode, struct file *file) return stream_open(inode, file); } -static int ffs_aio_cancel(struct kiocb *kiocb) -{ - struct ffs_io_data *io_data = kiocb->private; - struct ffs_epfile *epfile = kiocb->ki_filp->private_data; - unsigned long flags; - int value; - - spin_lock_irqsave(&epfile->ffs->eps_lock, flags); - - if (io_data && io_data->ep && io_data->req) - value = usb_ep_dequeue(io_data->ep, io_data->req); - else - value = -EINVAL; - - spin_unlock_irqrestore(&epfile->ffs->eps_lock, flags); - - return value; -} - static ssize_t ffs_epfile_write_iter(struct kiocb *kiocb, struct iov_iter *from) { struct ffs_io_data io_data, *p = &io_data; @@ -1198,9 +1179,6 @@ static ssize_t ffs_epfile_write_iter(struct kiocb *kiocb, struct iov_iter *from) kiocb->private = p; - if (p->aio) - kiocb_set_cancel_fn(kiocb, ffs_aio_cancel); - res = ffs_epfile_io(kiocb->ki_filp, p); if (res == -EIOCBQUEUED) return res; @@ -1242,9 +1220,6 @@ static ssize_t ffs_epfile_read_iter(struct kiocb *kiocb, struct iov_iter *to) kiocb->private = p; - if (p->aio) - kiocb_set_cancel_fn(kiocb, ffs_aio_cancel); - res = ffs_epfile_io(kiocb->ki_filp, p); if (res == -EIOCBQUEUED) return res; diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index 03179b1880fd..99b7366d77af 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -446,25 +446,6 @@ struct kiocb_priv { unsigned actual; }; -static int ep_aio_cancel(struct kiocb *iocb) -{ - struct kiocb_priv *priv = iocb->private; - struct ep_data *epdata; - int value; - - local_irq_disable(); - epdata = priv->epdata; - // spin_lock(&epdata->dev->lock); - if (likely(epdata && epdata->ep && priv->req)) - value = usb_ep_dequeue (epdata->ep, priv->req); - else - value = -EINVAL; - // spin_unlock(&epdata->dev->lock); - local_irq_enable(); - - return value; -} - static void ep_user_copy_worker(struct work_struct *work) { struct kiocb_priv *priv = container_of(work, struct kiocb_priv, work); @@ -537,7 +518,6 @@ static ssize_t ep_aio(struct kiocb *iocb, iocb->private = priv; priv->iocb = iocb; - kiocb_set_cancel_fn(iocb, ep_aio_cancel); get_ep(epdata); priv->epdata = epdata; priv->actual = 0; diff --git a/fs/aio.c b/fs/aio.c index bb2ff48991f3..c20946d5fcf3 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -203,7 +203,7 @@ struct aio_kiocb { }; struct kioctx *ki_ctx; - kiocb_cancel_fn *ki_cancel; + int (*ki_cancel)(struct kiocb *); struct io_event ki_res; @@ -587,22 +587,6 @@ static int aio_setup_ring(struct kioctx *ctx, unsigned int nr_events) #define AIO_EVENTS_FIRST_PAGE ((PAGE_SIZE - sizeof(struct aio_ring)) / sizeof(struct io_event)) #define AIO_EVENTS_OFFSET (AIO_EVENTS_PER_PAGE - AIO_EVENTS_FIRST_PAGE) -void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel) -{ - struct aio_kiocb *req = container_of(iocb, struct aio_kiocb, rw); - struct kioctx *ctx = req->ki_ctx; - unsigned long flags; - - if (WARN_ON_ONCE(!list_empty(&req->ki_list))) - return; - - spin_lock_irqsave(&ctx->ctx_lock, flags); - list_add_tail(&req->ki_list, &ctx->active_reqs); - req->ki_cancel = cancel; - spin_unlock_irqrestore(&ctx->ctx_lock, flags); -} -EXPORT_SYMBOL(kiocb_set_cancel_fn); - /* * free_ioctx() should be RCU delayed to synchronize against the RCU * protected lookup_ioctx() and also needs process context to call @@ -2158,13 +2142,11 @@ COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id, #endif /* sys_io_cancel: - * Attempts to cancel an iocb previously passed to io_submit. If - * the operation is successfully cancelled, the resulting event is - * copied into the memory pointed to by result without being placed - * into the completion queue and 0 is returned. May fail with - * -EFAULT if any of the data structures pointed to are invalid. - * May fail with -EINVAL if aio_context specified by ctx_id is - * invalid. May fail with -EAGAIN if the iocb specified was not + * Attempts to cancel an IOCB_CMD_POLL iocb previously passed to + * io_submit(). If the operation is successfully cancelled 0 is returned. + * May fail with -EFAULT if any of the data structures pointed to are + * invalid. May fail with -EINVAL if aio_context specified by ctx_id is + * invalid. May fail with -EINPROGRESS if the iocb specified was not * cancelled. Will fail with -ENOSYS if not implemented. */ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, @@ -2196,15 +2178,6 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, } spin_unlock_irq(&ctx->ctx_lock); - if (!ret) { - /* - * The result argument is no longer used - the io_event is - * always delivered via the ring buffer. -EINPROGRESS indicates - * cancellation is progress: - */ - ret = -EINPROGRESS; - } - percpu_ref_put(&ctx->users); return ret; diff --git a/include/linux/aio.h b/include/linux/aio.h index 86892a4fe7c8..9aabca4a0eed 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -2,22 +2,13 @@ #ifndef __LINUX__AIO_H #define __LINUX__AIO_H -#include <linux/aio_abi.h> - -struct kioctx; -struct kiocb; struct mm_struct; -typedef int (kiocb_cancel_fn)(struct kiocb *); - /* prototypes */ #ifdef CONFIG_AIO extern void exit_aio(struct mm_struct *mm); -void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel); #else static inline void exit_aio(struct mm_struct *mm) { } -static inline void kiocb_set_cancel_fn(struct kiocb *req, - kiocb_cancel_fn *cancel) { } #endif /* CONFIG_AIO */ #endif /* __LINUX__AIO_H */

1 year, 2 months

4
5
0 0

[PATCH net 0/7] mptcp: locking cleanup & misc. fixes

by Matthieu Baerts (NGI0)

Patches 1-4 are fixes for issues found by Paolo while working on adding TCP_NOTSENT_LOWAT support. The latter will need to track more states under the msk data lock. Since the locking msk locking schema is already quite complex, do a long awaited clean-up step by moving several confusing lockless initialization under the relevant locks. Note that it is unlikely a real race could happen even prior to such patches as the MPTCP-level state machine implicitly ensures proper serialization of the write accesses, even lacking explicit lock. But still, simplification is welcome and this will help for the maintenance. This can be backported up to v5.6. Patch 5 is a fix for the userspace PM, not to add new local address entries if the address is already in the list. This behaviour can be seen since v5.19. Patch 6 fixes an issue when Fastopen is used. The issue can happen since v6.2. A previous fix has already been applied, but not taking care of all cases according to syzbot. Patch 7 updates Geliang's email address in the MAINTAINERS file. Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> --- Geliang Tang (2): mptcp: check addrs list in userspace_pm_get_local_id MAINTAINERS: update Geliang's email address Paolo Abeni (5): mptcp: drop the push_pending field mptcp: fix rcv space initialization mptcp: fix more tx path fields initialization mptcp: corner case locking for rx path fields initialization mptcp: really cope with fastopen race .mailmap | 9 +++--- MAINTAINERS | 2 +- net/mptcp/fastopen.c | 6 ++-- net/mptcp/options.c | 9 +++--- net/mptcp/pm_userspace.c | 13 ++++++++- net/mptcp/protocol.c | 31 +++++++++++---------- net/mptcp/protocol.h | 16 ++++++----- net/mptcp/subflow.c | 71 ++++++++++++++++++++++++++++++------------------ 8 files changed, 95 insertions(+), 62 deletions(-) --- base-commit: 335bac1daae3fd9070d0f9f34d7d7ba708729256 change-id: 20240202-upstream-net-20240202-locking-cleanup-misc-5f2ee79d8356 Best regards, -- Matthieu Baerts (NGI0) <matttbe(a)kernel.org>

1 year, 2 months

2
7
0 0

[PATCH] comedi: comedi_8255: Correct error in subdevice initialization

by Frej Drejhammar

The refactoring done in commit 5c57b1ccecc7 ("comedi: comedi_8255: Rework subdevice initialization functions") to the initialization of the io field of struct subdev_8255_private broke all cards using the drivers/comedi/drivers/comedi_8255.c module. Prior to 5c57b1ccecc7, __subdev_8255_init() initialized the io field in the newly allocated struct subdev_8255_private to the non-NULL callback given to the function, otherwise it used a flag parameter to select between subdev_8255_mmio and subdev_8255_io. The refactoring removed that logic and the flag, as subdev_8255_mm_init() and subdev_8255_io_init() now explicitly pass subdev_8255_mmio and subdev_8255_io respectively to __subdev_8255_init(), only __subdev_8255_init() never sets spriv->io to the supplied callback. That spriv->io is NULL leads to a later BUG: BUG: kernel NULL pointer dereference, address: 0000000000000000 PGD 0 P4D 0 Oops: 0010 [#1] SMP PTI CPU: 1 PID: 1210 Comm: systemd-udevd Not tainted 6.7.3-x86_64 #1 Hardware name: XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX RIP: 0010:0x0 Code: Unable to access opcode bytes at 0xffffffffffffffd6. RSP: 0018:ffffa3f1c02d7b78 EFLAGS: 00010202 RAX: 0000000000000000 RBX: ffff91f847aefd00 RCX: 000000000000009b RDX: 0000000000000003 RSI: 0000000000000001 RDI: ffff91f840f6fc00 RBP: ffff91f840f6fc00 R08: 0000000000000000 R09: 0000000000000001 R10: 0000000000000000 R11: 000000000000005f R12: 0000000000000000 R13: 0000000000000000 R14: ffffffffc0102498 R15: ffff91f847ce6ba8 FS: 00007f72f4e8f500(0000) GS:ffff91f8d5c80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffffffffffd6 CR3: 000000010540e000 CR4: 00000000000406f0 Call Trace: <TASK> ? __die_body+0x15/0x57 ? page_fault_oops+0x2ef/0x33c ? insert_vmap_area.constprop.0+0xb6/0xd5 ? alloc_vmap_area+0x529/0x5ee ? exc_page_fault+0x15a/0x489 ? asm_exc_page_fault+0x22/0x30 __subdev_8255_init+0x79/0x8d [comedi_8255] pci_8255_auto_attach+0x11a/0x139 [8255_pci] comedi_auto_config+0xac/0x117 [comedi] ? __pfx___driver_attach+0x10/0x10 pci_device_probe+0x88/0xf9 really_probe+0x101/0x248 __driver_probe_device+0xbb/0xed driver_probe_device+0x1a/0x72 __driver_attach+0xd4/0xed bus_for_each_dev+0x76/0xb8 bus_add_driver+0xbe/0x1be driver_register+0x9a/0xd8 comedi_pci_driver_register+0x28/0x48 [comedi_pci] ? __pfx_pci_8255_driver_init+0x10/0x10 [8255_pci] do_one_initcall+0x72/0x183 do_init_module+0x5b/0x1e8 init_module_from_file+0x86/0xac __do_sys_finit_module+0x151/0x218 do_syscall_64+0x72/0xdb entry_SYSCALL_64_after_hwframe+0x6e/0x76 RIP: 0033:0x7f72f50a0cb9 Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 47 71 0c 00 f7 d8 64 89 01 48 RSP: 002b:00007ffd47e512d8 EFLAGS: 00000246 ORIG_RAX: 0000000000000139 RAX: ffffffffffffffda RBX: 0000562dd06ae070 RCX: 00007f72f50a0cb9 RDX: 0000000000000000 RSI: 00007f72f52d32df RDI: 000000000000000e RBP: 0000000000000000 R08: 00007f72f5168b20 R09: 0000000000000000 R10: 0000000000000050 R11: 0000000000000246 R12: 00007f72f52d32df R13: 0000000000020000 R14: 0000562dd06785c0 R15: 0000562dcfd0e9a8 </TASK> Modules linked in: 8255_pci(+) comedi_8255 comedi_pci comedi intel_gtt e100(+) acpi_cpufreq rtc_cmos usbhid CR2: 0000000000000000 ---[ end trace 0000000000000000 ]--- RIP: 0010:0x0 Code: Unable to access opcode bytes at 0xffffffffffffffd6. RSP: 0018:ffffa3f1c02d7b78 EFLAGS: 00010202 RAX: 0000000000000000 RBX: ffff91f847aefd00 RCX: 000000000000009b RDX: 0000000000000003 RSI: 0000000000000001 RDI: ffff91f840f6fc00 RBP: ffff91f840f6fc00 R08: 0000000000000000 R09: 0000000000000001 R10: 0000000000000000 R11: 000000000000005f R12: 0000000000000000 R13: 0000000000000000 R14: ffffffffc0102498 R15: ffff91f847ce6ba8 FS: 00007f72f4e8f500(0000) GS:ffff91f8d5c80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffffffffffd6 CR3: 000000010540e000 CR4: 00000000000406f0 This patch simply corrects the above mistake by initializing spriv->io to the given io callback. Fixes: 5c57b1ccecc7 ("comedi: comedi_8255: Rework subdevice initialization functions") Signed-off-by: Frej Drejhammar <frej.drejhammar(a)gmail.com> Cc: <stable(a)vger.kernel.org> --- drivers/comedi/drivers/comedi_8255.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/comedi/drivers/comedi_8255.c b/drivers/comedi/drivers/comedi_8255.c index e4974b508328..a933ef53845a 100644 --- a/drivers/comedi/drivers/comedi_8255.c +++ b/drivers/comedi/drivers/comedi_8255.c @@ -159,6 +159,7 @@ static int __subdev_8255_init(struct comedi_device *dev, return -ENOMEM; spriv->context = context; + spriv->io = io; s->type = COMEDI_SUBD_DIO; s->subdev_flags = SDF_READABLE | SDF_WRITABLE; -- 2.43.0

1 year, 2 months

2
1
0 0

[PATCH] scsi: elx: efct: adjust error handling inside efct_hw_setup_io

by Fedor Pchelkin

IO and WQE buffers are allocated once per HW and can be reused later. If WQE buffers allocation fails then the whole allocation is marked as failed but already created IO array internal objects are not freed. hw->io is freed but not nullified in that specific case - it may become a problem later as efct_hw_setup_io() is supposed to be reusable for the same HW. While at it, use kcalloc instead of kmalloc_array/memset-zero combination and get rid of some needless NULL assignments: nullifying hw->io[i] elements just before freeing hw->io is not really useful. Found by Linux Verification Center (linuxtesting.org). Fixes: 4df84e846624 ("scsi: elx: efct: Driver initialization routines") Cc: stable(a)vger.kernel.org Signed-off-by: Fedor Pchelkin <pchelkin(a)ispras.ru> --- drivers/scsi/elx/efct/efct_hw.c | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) diff --git a/drivers/scsi/elx/efct/efct_hw.c b/drivers/scsi/elx/efct/efct_hw.c index 5a5525054d71..e5486e6949f9 100644 --- a/drivers/scsi/elx/efct/efct_hw.c +++ b/drivers/scsi/elx/efct/efct_hw.c @@ -487,12 +487,10 @@ efct_hw_setup_io(struct efct_hw *hw) struct efct *efct = hw->os; if (!hw->io) { - hw->io = kmalloc_array(hw->config.n_io, sizeof(io), GFP_KERNEL); + hw->io = kcalloc(hw->config.n_io, sizeof(io), GFP_KERNEL); if (!hw->io) return -ENOMEM; - memset(hw->io, 0, hw->config.n_io * sizeof(io)); - for (i = 0; i < hw->config.n_io; i++) { hw->io[i] = kzalloc(sizeof(*io), GFP_KERNEL); if (!hw->io[i]) @@ -502,10 +500,8 @@ efct_hw_setup_io(struct efct_hw *hw) /* Create WQE buffs for IO */ hw->wqe_buffs = kzalloc((hw->config.n_io * hw->sli.wqe_size), GFP_KERNEL); - if (!hw->wqe_buffs) { - kfree(hw->io); - return -ENOMEM; - } + if (!hw->wqe_buffs) + goto error; } else { /* re-use existing IOs, including SGLs */ @@ -586,10 +582,8 @@ efct_hw_setup_io(struct efct_hw *hw) return 0; error: - for (i = 0; i < hw->config.n_io && hw->io[i]; i++) { + for (i = 0; i < hw->config.n_io && hw->io[i]; i++) kfree(hw->io[i]); - hw->io[i] = NULL; - } kfree(hw->io); hw->io = NULL; -- 2.39.2

1 year, 2 months

2
3
0 0

[PATCH stable 5.4 v2] net: bcmgenet: Fix EEE implementation

by Florian Fainelli

commit a9f31047baca57d47440c879cf259b86f900260c upstream We had a number of short comings: - EEE must be re-evaluated whenever the state machine detects a link change as wight be switching from a link partner with EEE enabled/disabled - tx_lpi_enabled controls whether EEE should be enabled/disabled for the transmit path, which applies to the TBUF block - We do not need to forcibly enable EEE upon system resume, as the PHY state machine will trigger a link event that will do that, too Fixes: 6ef398ea60d9 ("net: bcmgenet: add EEE support") Signed-off-by: Florian Fainelli <florian.fainelli(a)broadcom.com> Reviewed-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk> Link: https://lore.kernel.org/r/20230606214348.2408018-1-florian.fainelli@broadco… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Florian Fainelli <florian.fainelli(a)broadcom.com> --- Changes in v2: - removed Changed-id .../net/ethernet/broadcom/genet/bcmgenet.c | 22 +++++++------------ .../net/ethernet/broadcom/genet/bcmgenet.h | 3 +++ drivers/net/ethernet/broadcom/genet/bcmmii.c | 6 +++++ 3 files changed, 17 insertions(+), 14 deletions(-) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index eeadeeec17ba..380bf7a328ba 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1018,7 +1018,8 @@ static void bcmgenet_get_ethtool_stats(struct net_device *dev, } } -static void bcmgenet_eee_enable_set(struct net_device *dev, bool enable) +void bcmgenet_eee_enable_set(struct net_device *dev, bool enable, + bool tx_lpi_enabled) { struct bcmgenet_priv *priv = netdev_priv(dev); u32 off = priv->hw_params->tbuf_offset + TBUF_ENERGY_CTRL; @@ -1038,7 +1039,7 @@ static void bcmgenet_eee_enable_set(struct net_device *dev, bool enable) /* Enable EEE and switch to a 27Mhz clock automatically */ reg = bcmgenet_readl(priv->base + off); - if (enable) + if (tx_lpi_enabled) reg |= TBUF_EEE_EN | TBUF_PM_EN; else reg &= ~(TBUF_EEE_EN | TBUF_PM_EN); @@ -1059,6 +1060,7 @@ static void bcmgenet_eee_enable_set(struct net_device *dev, bool enable) priv->eee.eee_enabled = enable; priv->eee.eee_active = enable; + priv->eee.tx_lpi_enabled = tx_lpi_enabled; } static int bcmgenet_get_eee(struct net_device *dev, struct ethtool_eee *e) @@ -1074,6 +1076,7 @@ static int bcmgenet_get_eee(struct net_device *dev, struct ethtool_eee *e) e->eee_enabled = p->eee_enabled; e->eee_active = p->eee_active; + e->tx_lpi_enabled = p->tx_lpi_enabled; e->tx_lpi_timer = bcmgenet_umac_readl(priv, UMAC_EEE_LPI_TIMER); return phy_ethtool_get_eee(dev->phydev, e); @@ -1083,7 +1086,6 @@ static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_eee *e) { struct bcmgenet_priv *priv = netdev_priv(dev); struct ethtool_eee *p = &priv->eee; - int ret = 0; if (GENET_IS_V1(priv)) return -EOPNOTSUPP; @@ -1094,16 +1096,11 @@ static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_eee *e) p->eee_enabled = e->eee_enabled; if (!p->eee_enabled) { - bcmgenet_eee_enable_set(dev, false); + bcmgenet_eee_enable_set(dev, false, false); } else { - ret = phy_init_eee(dev->phydev, 0); - if (ret) { - netif_err(priv, hw, dev, "EEE initialization failed\n"); - return ret; - } - + p->eee_active = phy_init_eee(dev->phydev, false) >= 0; bcmgenet_umac_writel(priv, e->tx_lpi_timer, UMAC_EEE_LPI_TIMER); - bcmgenet_eee_enable_set(dev, true); + bcmgenet_eee_enable_set(dev, p->eee_active, e->tx_lpi_enabled); } return phy_ethtool_set_eee(dev->phydev, e); @@ -3688,9 +3685,6 @@ static int bcmgenet_resume(struct device *d) if (!device_may_wakeup(d)) phy_resume(dev->phydev); - if (priv->eee.eee_enabled) - bcmgenet_eee_enable_set(dev, true); - bcmgenet_netif_start(dev); netif_device_attach(dev); diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h index 5b7c2f9241d0..29bf256d13f6 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h @@ -736,4 +736,7 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv, void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv, enum bcmgenet_power_mode mode); +void bcmgenet_eee_enable_set(struct net_device *dev, bool enable, + bool tx_lpi_enabled); + #endif /* __BCMGENET_H__ */ diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 2fbec2acb606..026f00ccaa0c 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -25,6 +25,7 @@ #include "bcmgenet.h" + /* setup netdev link state when PHY link status change and * update UMAC and RGMII block when link up */ @@ -96,6 +97,11 @@ void bcmgenet_mii_setup(struct net_device *dev) CMD_RX_PAUSE_IGNORE | CMD_TX_PAUSE_IGNORE); reg |= cmd_bits; bcmgenet_umac_writel(priv, reg, UMAC_CMD); + + priv->eee.eee_active = phy_init_eee(phydev, 0) >= 0; + bcmgenet_eee_enable_set(dev, + priv->eee.eee_enabled && priv->eee.eee_active, + priv->eee.tx_lpi_enabled); } else { /* done if nothing has changed */ if (!status_changed) -- 2.34.1

1 year, 2 months

2
3
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror February 2024