From 672cde9ef80ffde9e76d38f7aa2b287c4a18de9a Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Fri, 21 Apr 2023 08:46:11 +0300 Subject: iio: fix doc for iio_gts_find_sel_by_int_time The kerneldoc for iio_gts_find_sel_by_int_time() has an error. Documentation states that function is searching a selector for a HW-gain while it is searching a selector for an integration time. Fix the documentation by saying the function is looking for a selector for an integration time. Fixes: 38416c28e168 ("iio: light: Add gain-time-scale helpers") Signed-off-by: Matti Vaittinen Link: https://lore.kernel.org/r/ZEIjI4YUzqPZk/9X@fedora Signed-off-by: Jonathan Cameron --- include/linux/iio/iio-gts-helper.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/iio/iio-gts-helper.h b/include/linux/iio/iio-gts-helper.h index dd64e544a3da..9cb6c80dea71 100644 --- a/include/linux/iio/iio-gts-helper.h +++ b/include/linux/iio/iio-gts-helper.h @@ -135,7 +135,7 @@ static inline int iio_gts_find_int_time_by_sel(struct iio_gts *gts, int sel) /** * iio_gts_find_sel_by_int_time - find selector matching integration time * @gts: Gain time scale descriptor - * @gain: HW-gain for which matching selector is searched for + * @time: Integration time for which matching selector is searched for * * Return: a selector matching given integration time or -EINVAL if * selector was not found. -- cgit v1.2.3 From 13247018d68f21e7132924b9853f7e2c423588b6 Mon Sep 17 00:00:00 2001 From: Maurizio Lombardi Date: Mon, 8 May 2023 18:22:17 +0200 Subject: scsi: target: iscsi: Fix hang in the iSCSI login code If the initiator suddenly stops sending data during a login while keeping the TCP connection open, the login_work won't be scheduled and will never release the login semaphore; concurrent login operations will therefore get stuck and fail. The bug is due to the inability of the login timeout code to properly handle this particular case. Fix the problem by replacing the old per-NP login timer with a new per-connection timer. The timer is started when an initiator connects to the target; if it expires, it sends a SIGINT signal to the thread pointed at by the conn->login_kworker pointer. conn->login_kworker is set by calling the iscsit_set_login_timer_kworker() helper, initially it will point to the np thread; When the login operation's control is in the process of being passed from the NP-thread to login_work, the conn->login_worker pointer is set to NULL. Finally, login_kworker will be changed to point to the worker thread executing the login_work job. If conn->login_kworker is NULL when the timer expires, it means that the login operation hasn't been completed yet but login_work isn't running, in this case the timer will mark the login process as failed and will schedule login_work so the latter will be forced to free the resources it holds. Signed-off-by: Maurizio Lombardi Link: https://lore.kernel.org/r/20230508162219.1731964-2-mlombard@redhat.com Reviewed-by: Mike Christie Signed-off-by: Martin K. Petersen --- drivers/target/iscsi/iscsi_target.c | 2 - drivers/target/iscsi/iscsi_target_login.c | 63 +++------------------------- drivers/target/iscsi/iscsi_target_nego.c | 70 +++++++++++++++++-------------- drivers/target/iscsi/iscsi_target_util.c | 51 ++++++++++++++++++++++ drivers/target/iscsi/iscsi_target_util.h | 4 ++ include/target/iscsi/iscsi_target_core.h | 6 ++- 6 files changed, 103 insertions(+), 93 deletions(-) (limited to 'include') diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 834cce50f9b0..b516c2893420 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -364,8 +364,6 @@ struct iscsi_np *iscsit_add_np( init_completion(&np->np_restart_comp); INIT_LIST_HEAD(&np->np_list); - timer_setup(&np->np_login_timer, iscsi_handle_login_thread_timeout, 0); - ret = iscsi_target_setup_login_socket(np, sockaddr); if (ret != 0) { kfree(np); diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index 274bdd7845ca..90b870f234f0 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -811,59 +811,6 @@ void iscsi_post_login_handler( iscsit_dec_conn_usage_count(conn); } -void iscsi_handle_login_thread_timeout(struct timer_list *t) -{ - struct iscsi_np *np = from_timer(np, t, np_login_timer); - - spin_lock_bh(&np->np_thread_lock); - pr_err("iSCSI Login timeout on Network Portal %pISpc\n", - &np->np_sockaddr); - - if (np->np_login_timer_flags & ISCSI_TF_STOP) { - spin_unlock_bh(&np->np_thread_lock); - return; - } - - if (np->np_thread) - send_sig(SIGINT, np->np_thread, 1); - - np->np_login_timer_flags &= ~ISCSI_TF_RUNNING; - spin_unlock_bh(&np->np_thread_lock); -} - -static void iscsi_start_login_thread_timer(struct iscsi_np *np) -{ - /* - * This used the TA_LOGIN_TIMEOUT constant because at this - * point we do not have access to ISCSI_TPG_ATTRIB(tpg)->login_timeout - */ - spin_lock_bh(&np->np_thread_lock); - np->np_login_timer_flags &= ~ISCSI_TF_STOP; - np->np_login_timer_flags |= ISCSI_TF_RUNNING; - mod_timer(&np->np_login_timer, jiffies + TA_LOGIN_TIMEOUT * HZ); - - pr_debug("Added timeout timer to iSCSI login request for" - " %u seconds.\n", TA_LOGIN_TIMEOUT); - spin_unlock_bh(&np->np_thread_lock); -} - -static void iscsi_stop_login_thread_timer(struct iscsi_np *np) -{ - spin_lock_bh(&np->np_thread_lock); - if (!(np->np_login_timer_flags & ISCSI_TF_RUNNING)) { - spin_unlock_bh(&np->np_thread_lock); - return; - } - np->np_login_timer_flags |= ISCSI_TF_STOP; - spin_unlock_bh(&np->np_thread_lock); - - del_timer_sync(&np->np_login_timer); - - spin_lock_bh(&np->np_thread_lock); - np->np_login_timer_flags &= ~ISCSI_TF_RUNNING; - spin_unlock_bh(&np->np_thread_lock); -} - int iscsit_setup_np( struct iscsi_np *np, struct sockaddr_storage *sockaddr) @@ -1123,10 +1070,13 @@ static struct iscsit_conn *iscsit_alloc_conn(struct iscsi_np *np) spin_lock_init(&conn->nopin_timer_lock); spin_lock_init(&conn->response_queue_lock); spin_lock_init(&conn->state_lock); + spin_lock_init(&conn->login_worker_lock); + spin_lock_init(&conn->login_timer_lock); timer_setup(&conn->nopin_response_timer, iscsit_handle_nopin_response_timeout, 0); timer_setup(&conn->nopin_timer, iscsit_handle_nopin_timeout, 0); + timer_setup(&conn->login_timer, iscsit_login_timeout, 0); if (iscsit_conn_set_transport(conn, np->np_transport) < 0) goto free_conn; @@ -1304,7 +1254,7 @@ static int __iscsi_target_login_thread(struct iscsi_np *np) goto new_sess_out; } - iscsi_start_login_thread_timer(np); + iscsit_start_login_timer(conn, current); pr_debug("Moving to TARG_CONN_STATE_XPT_UP.\n"); conn->conn_state = TARG_CONN_STATE_XPT_UP; @@ -1417,8 +1367,6 @@ static int __iscsi_target_login_thread(struct iscsi_np *np) if (ret < 0) goto new_sess_out; - iscsi_stop_login_thread_timer(np); - if (ret == 1) { tpg_np = conn->tpg_np; @@ -1434,7 +1382,7 @@ static int __iscsi_target_login_thread(struct iscsi_np *np) new_sess_out: new_sess = true; old_sess_out: - iscsi_stop_login_thread_timer(np); + iscsit_stop_login_timer(conn); tpg_np = conn->tpg_np; iscsi_target_login_sess_out(conn, zero_tsih, new_sess); new_sess = false; @@ -1448,7 +1396,6 @@ old_sess_out: return 1; exit: - iscsi_stop_login_thread_timer(np); spin_lock_bh(&np->np_thread_lock); np->np_thread_state = ISCSI_NP_THREAD_EXIT; spin_unlock_bh(&np->np_thread_lock); diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c index 24040c118e49..e3a5644a70b3 100644 --- a/drivers/target/iscsi/iscsi_target_nego.c +++ b/drivers/target/iscsi/iscsi_target_nego.c @@ -535,25 +535,6 @@ static void iscsi_target_login_drop(struct iscsit_conn *conn, struct iscsi_login iscsi_target_login_sess_out(conn, zero_tsih, true); } -struct conn_timeout { - struct timer_list timer; - struct iscsit_conn *conn; -}; - -static void iscsi_target_login_timeout(struct timer_list *t) -{ - struct conn_timeout *timeout = from_timer(timeout, t, timer); - struct iscsit_conn *conn = timeout->conn; - - pr_debug("Entering iscsi_target_login_timeout >>>>>>>>>>>>>>>>>>>\n"); - - if (conn->login_kworker) { - pr_debug("Sending SIGINT to conn->login_kworker %s/%d\n", - conn->login_kworker->comm, conn->login_kworker->pid); - send_sig(SIGINT, conn->login_kworker, 1); - } -} - static void iscsi_target_do_login_rx(struct work_struct *work) { struct iscsit_conn *conn = container_of(work, @@ -562,12 +543,15 @@ static void iscsi_target_do_login_rx(struct work_struct *work) struct iscsi_np *np = login->np; struct iscsi_portal_group *tpg = conn->tpg; struct iscsi_tpg_np *tpg_np = conn->tpg_np; - struct conn_timeout timeout; int rc, zero_tsih = login->zero_tsih; bool state; pr_debug("entering iscsi_target_do_login_rx, conn: %p, %s:%d\n", conn, current->comm, current->pid); + + spin_lock(&conn->login_worker_lock); + set_bit(LOGIN_FLAGS_WORKER_RUNNING, &conn->login_flags); + spin_unlock(&conn->login_worker_lock); /* * If iscsi_target_do_login_rx() has been invoked by ->sk_data_ready() * before initial PDU processing in iscsi_target_start_negotiation() @@ -597,19 +581,16 @@ static void iscsi_target_do_login_rx(struct work_struct *work) goto err; } - conn->login_kworker = current; allow_signal(SIGINT); - - timeout.conn = conn; - timer_setup_on_stack(&timeout.timer, iscsi_target_login_timeout, 0); - mod_timer(&timeout.timer, jiffies + TA_LOGIN_TIMEOUT * HZ); - pr_debug("Starting login timer for %s/%d\n", current->comm, current->pid); + rc = iscsit_set_login_timer_kworker(conn, current); + if (rc < 0) { + /* The login timer has already expired */ + pr_debug("iscsi_target_do_login_rx, login failed\n"); + goto err; + } rc = conn->conn_transport->iscsit_get_login_rx(conn, login); - del_timer_sync(&timeout.timer); - destroy_timer_on_stack(&timeout.timer); flush_signals(current); - conn->login_kworker = NULL; if (rc < 0) goto err; @@ -646,7 +627,17 @@ static void iscsi_target_do_login_rx(struct work_struct *work) if (iscsi_target_sk_check_and_clear(conn, LOGIN_FLAGS_WRITE_ACTIVE)) goto err; + + /* + * Set the login timer thread pointer to NULL to prevent the + * login process from getting stuck if the initiator + * stops sending data. + */ + rc = iscsit_set_login_timer_kworker(conn, NULL); + if (rc < 0) + goto err; } else if (rc == 1) { + iscsit_stop_login_timer(conn); cancel_delayed_work(&conn->login_work); iscsi_target_nego_release(conn); iscsi_post_login_handler(np, conn, zero_tsih); @@ -656,6 +647,7 @@ static void iscsi_target_do_login_rx(struct work_struct *work) err: iscsi_target_restore_sock_callbacks(conn); + iscsit_stop_login_timer(conn); cancel_delayed_work(&conn->login_work); iscsi_target_login_drop(conn, login); iscsit_deaccess_np(np, tpg, tpg_np); @@ -1368,14 +1360,30 @@ int iscsi_target_start_negotiation( * and perform connection cleanup now. */ ret = iscsi_target_do_login(conn, login); - if (!ret && iscsi_target_sk_check_and_clear(conn, LOGIN_FLAGS_INITIAL_PDU)) - ret = -1; + if (!ret) { + spin_lock(&conn->login_worker_lock); + + if (iscsi_target_sk_check_and_clear(conn, LOGIN_FLAGS_INITIAL_PDU)) + ret = -1; + else if (!test_bit(LOGIN_FLAGS_WORKER_RUNNING, &conn->login_flags)) { + if (iscsit_set_login_timer_kworker(conn, NULL) < 0) { + /* + * The timeout has expired already. + * Schedule login_work to perform the cleanup. + */ + schedule_delayed_work(&conn->login_work, 0); + } + } + + spin_unlock(&conn->login_worker_lock); + } if (ret < 0) { iscsi_target_restore_sock_callbacks(conn); iscsi_remove_failed_auth_entry(conn); } if (ret != 0) { + iscsit_stop_login_timer(conn); cancel_delayed_work_sync(&conn->login_work); iscsi_target_nego_release(conn); } diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c index 26dc8ed3045b..b14835fcb033 100644 --- a/drivers/target/iscsi/iscsi_target_util.c +++ b/drivers/target/iscsi/iscsi_target_util.c @@ -1040,6 +1040,57 @@ void iscsit_stop_nopin_timer(struct iscsit_conn *conn) spin_unlock_bh(&conn->nopin_timer_lock); } +void iscsit_login_timeout(struct timer_list *t) +{ + struct iscsit_conn *conn = from_timer(conn, t, login_timer); + struct iscsi_login *login = conn->login; + + pr_debug("Entering iscsi_target_login_timeout >>>>>>>>>>>>>>>>>>>\n"); + + spin_lock_bh(&conn->login_timer_lock); + login->login_failed = 1; + + if (conn->login_kworker) { + pr_debug("Sending SIGINT to conn->login_kworker %s/%d\n", + conn->login_kworker->comm, conn->login_kworker->pid); + send_sig(SIGINT, conn->login_kworker, 1); + } else { + schedule_delayed_work(&conn->login_work, 0); + } + spin_unlock_bh(&conn->login_timer_lock); +} + +void iscsit_start_login_timer(struct iscsit_conn *conn, struct task_struct *kthr) +{ + pr_debug("Login timer started\n"); + + conn->login_kworker = kthr; + mod_timer(&conn->login_timer, jiffies + TA_LOGIN_TIMEOUT * HZ); +} + +int iscsit_set_login_timer_kworker(struct iscsit_conn *conn, struct task_struct *kthr) +{ + struct iscsi_login *login = conn->login; + int ret = 0; + + spin_lock_bh(&conn->login_timer_lock); + if (login->login_failed) { + /* The timer has already expired */ + ret = -1; + } else { + conn->login_kworker = kthr; + } + spin_unlock_bh(&conn->login_timer_lock); + + return ret; +} + +void iscsit_stop_login_timer(struct iscsit_conn *conn) +{ + pr_debug("Login timer stopped\n"); + timer_delete_sync(&conn->login_timer); +} + int iscsit_send_tx_data( struct iscsit_cmd *cmd, struct iscsit_conn *conn, diff --git a/drivers/target/iscsi/iscsi_target_util.h b/drivers/target/iscsi/iscsi_target_util.h index 33ea799a0850..24b8e577575a 100644 --- a/drivers/target/iscsi/iscsi_target_util.h +++ b/drivers/target/iscsi/iscsi_target_util.h @@ -56,6 +56,10 @@ extern void iscsit_handle_nopin_timeout(struct timer_list *t); extern void __iscsit_start_nopin_timer(struct iscsit_conn *); extern void iscsit_start_nopin_timer(struct iscsit_conn *); extern void iscsit_stop_nopin_timer(struct iscsit_conn *); +extern void iscsit_login_timeout(struct timer_list *t); +extern void iscsit_start_login_timer(struct iscsit_conn *, struct task_struct *kthr); +extern void iscsit_stop_login_timer(struct iscsit_conn *); +extern int iscsit_set_login_timer_kworker(struct iscsit_conn *, struct task_struct *kthr); extern int iscsit_send_tx_data(struct iscsit_cmd *, struct iscsit_conn *, int); extern int iscsit_fe_sendpage_sg(struct iscsit_cmd *, struct iscsit_conn *); extern int iscsit_tx_login_rsp(struct iscsit_conn *, u8, u8); diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h index 229118156a1f..42f4a4c0c100 100644 --- a/include/target/iscsi/iscsi_target_core.h +++ b/include/target/iscsi/iscsi_target_core.h @@ -562,12 +562,14 @@ struct iscsit_conn { #define LOGIN_FLAGS_READ_ACTIVE 2 #define LOGIN_FLAGS_WRITE_ACTIVE 3 #define LOGIN_FLAGS_CLOSED 4 +#define LOGIN_FLAGS_WORKER_RUNNING 5 unsigned long login_flags; struct delayed_work login_work; struct iscsi_login *login; struct timer_list nopin_timer; struct timer_list nopin_response_timer; struct timer_list transport_timer; + struct timer_list login_timer; struct task_struct *login_kworker; /* Spinlock used for add/deleting cmd's from conn_cmd_list */ spinlock_t cmd_lock; @@ -576,6 +578,8 @@ struct iscsit_conn { spinlock_t nopin_timer_lock; spinlock_t response_queue_lock; spinlock_t state_lock; + spinlock_t login_timer_lock; + spinlock_t login_worker_lock; /* libcrypto RX and TX contexts for crc32c */ struct ahash_request *conn_rx_hash; struct ahash_request *conn_tx_hash; @@ -792,7 +796,6 @@ struct iscsi_np { enum np_thread_state_table np_thread_state; bool enabled; atomic_t np_reset_count; - enum iscsi_timer_flags_table np_login_timer_flags; u32 np_exports; enum np_flags_table np_flags; spinlock_t np_thread_lock; @@ -800,7 +803,6 @@ struct iscsi_np { struct socket *np_socket; struct sockaddr_storage np_sockaddr; struct task_struct *np_thread; - struct timer_list np_login_timer; void *np_context; struct iscsit_transport *np_transport; struct list_head np_list; -- cgit v1.2.3 From 98a8c2bf938a5973716f280da618077a3d255976 Mon Sep 17 00:00:00 2001 From: Maurizio Lombardi Date: Mon, 8 May 2023 18:22:18 +0200 Subject: scsi: target: iscsi: Remove unused transport_timer Signed-off-by: Maurizio Lombardi Link: https://lore.kernel.org/r/20230508162219.1731964-3-mlombard@redhat.com Reviewed-by: Mike Christie Signed-off-by: Martin K. Petersen --- include/target/iscsi/iscsi_target_core.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h index 42f4a4c0c100..4c15420e8965 100644 --- a/include/target/iscsi/iscsi_target_core.h +++ b/include/target/iscsi/iscsi_target_core.h @@ -568,7 +568,6 @@ struct iscsit_conn { struct iscsi_login *login; struct timer_list nopin_timer; struct timer_list nopin_response_timer; - struct timer_list transport_timer; struct timer_list login_timer; struct task_struct *login_kworker; /* Spinlock used for add/deleting cmd's from conn_cmd_list */ -- cgit v1.2.3 From fd936fd8ac105ba3eb764185e8ba483c789c893e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 23 May 2023 21:01:30 +0200 Subject: efi: fix missing prototype warnings The cper.c file needs to include an extra header, and efi_zboot_entry needs an extern declaration to avoid these 'make W=1' warnings: drivers/firmware/efi/libstub/zboot.c:65:1: error: no previous prototype for 'efi_zboot_entry' [-Werror=missing-prototypes] drivers/firmware/efi/efi.c:176:16: error: no previous prototype for 'efi_attr_is_visible' [-Werror=missing-prototypes] drivers/firmware/efi/cper.c:626:6: error: no previous prototype for 'cper_estatus_print' [-Werror=missing-prototypes] drivers/firmware/efi/cper.c:649:5: error: no previous prototype for 'cper_estatus_check_header' [-Werror=missing-prototypes] drivers/firmware/efi/cper.c:662:5: error: no previous prototype for 'cper_estatus_check' [-Werror=missing-prototypes] To make this easier, move the cper specific declarations to include/linux/cper.h. Signed-off-by: Arnd Bergmann Acked-by: Rafael J. Wysocki Signed-off-by: Ard Biesheuvel --- drivers/acpi/apei/apei-internal.h | 6 ------ drivers/acpi/apei/bert.c | 1 + drivers/firmware/efi/libstub/efistub.h | 3 +++ include/linux/cper.h | 6 ++++++ include/linux/efi.h | 2 ++ 5 files changed, 12 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/acpi/apei/apei-internal.h b/drivers/acpi/apei/apei-internal.h index 1d6ef9654725..67c2c3b959e1 100644 --- a/drivers/acpi/apei/apei-internal.h +++ b/drivers/acpi/apei/apei-internal.h @@ -7,7 +7,6 @@ #ifndef APEI_INTERNAL_H #define APEI_INTERNAL_H -#include #include struct apei_exec_context; @@ -130,10 +129,5 @@ static inline u32 cper_estatus_len(struct acpi_hest_generic_status *estatus) return sizeof(*estatus) + estatus->data_length; } -void cper_estatus_print(const char *pfx, - const struct acpi_hest_generic_status *estatus); -int cper_estatus_check_header(const struct acpi_hest_generic_status *estatus); -int cper_estatus_check(const struct acpi_hest_generic_status *estatus); - int apei_osc_setup(void); #endif diff --git a/drivers/acpi/apei/bert.c b/drivers/acpi/apei/bert.c index c23eb75866d0..7514e38d5640 100644 --- a/drivers/acpi/apei/bert.c +++ b/drivers/acpi/apei/bert.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include "apei-internal.h" diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h index 67d5a20802e0..54a2822cae77 100644 --- a/drivers/firmware/efi/libstub/efistub.h +++ b/drivers/firmware/efi/libstub/efistub.h @@ -1133,4 +1133,7 @@ const u8 *__efi_get_smbios_string(const struct efi_smbios_record *record, void efi_remap_image(unsigned long image_base, unsigned alloc_size, unsigned long code_size); +asmlinkage efi_status_t __efiapi +efi_zboot_entry(efi_handle_t handle, efi_system_table_t *systab); + #endif diff --git a/include/linux/cper.h b/include/linux/cper.h index eacb7dd7b3af..c1a7dc325121 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -572,4 +572,10 @@ void cper_print_proc_ia(const char *pfx, int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg); int cper_dimm_err_location(struct cper_mem_err_compact *mem, char *msg); +struct acpi_hest_generic_status; +void cper_estatus_print(const char *pfx, + const struct acpi_hest_generic_status *estatus); +int cper_estatus_check_header(const struct acpi_hest_generic_status *estatus); +int cper_estatus_check(const struct acpi_hest_generic_status *estatus); + #endif diff --git a/include/linux/efi.h b/include/linux/efi.h index 7aa62c92185f..571d1a6e1b74 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1338,4 +1338,6 @@ bool efi_config_table_is_usable(const efi_guid_t *guid, unsigned long table) return xen_efi_config_table_is_usable(guid, table); } +umode_t efi_attr_is_visible(struct kobject *kobj, struct attribute *attr, int n); + #endif /* _LINUX_EFI_H */ -- cgit v1.2.3 From 36e4fc57fc1619f462e669e939209c45763bc8f5 Mon Sep 17 00:00:00 2001 From: Akihiro Suda Date: Sun, 28 May 2023 19:36:02 +0200 Subject: efi: Bump stub image version for macOS HVF compatibility The macOS hypervisor framework includes a host-side VMM called VZLinuxBootLoader [1] which implements native support for booting the Linux kernel inside a guest directly (instead of, e.g., via GRUB installed inside the guest). On x86, it incorporates a BIOS style loader that does not implement or expose EFI to the loaded kernel. However, this loader appears to fail when the 'image minor version' field in the kernel image's PE/COFF header (which is generally only used by EFI based bootloaders) is set to any value other than 0x0. [2] Commit e346bebbd36b1576 ("efi: libstub: Always enable initrd command line loader and bump version") incremented the EFI stub image minor version to convey that all EFI stub kernels now implement support for the initrd= command line option, and do so in a way where it can load initrd images from any filesystem known to the EFI firmware (as opposed to prior implementations that could only load initrds from the same volume that the kernel image was loaded from). Unfortunately, bumping the version to v1.1 triggers this issue in VZLinuxBootLoader, breaking the boot on x86. So let's keep the image minor version at 0x0, and bump the image major version instead. While at it, convert this field to a bit field, so that individual features are discoverable from it, as suggested by Linus. So let's bump the major version to v3, and document the initrd= command line loading feature as being represented by bit 1 in the mask. Note that, due to the prior interpretation as a monotonically increasing version field, loaders are still permitted to assume that the LoadFile2 initrd loading feature is supported for any major version value >= 1, even if bit 0 is not set. [1] https://developer.apple.com/documentation/virtualization/vzlinuxbootloader [2] https://lore.kernel.org/linux-efi/CAG8fp8Teu4G9JuenQrqGndFt2Gy+V4YgJ=hN1xX7AD940YKf3A@mail.gmail.com/ Fixes: e346bebbd36b1576 ("efi: libstub: Always enable initrd command ...") Closes: https://bugzilla.kernel.org/show_bug.cgi?id=217485 Signed-off-by: Akihiro Suda [ardb: rewrite comment and commit log] Signed-off-by: Ard Biesheuvel --- include/linux/pe.h | 25 +++++++++++++------------ 1 file changed, 13 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/pe.h b/include/linux/pe.h index 5e1e11540870..fdf9c95709ba 100644 --- a/include/linux/pe.h +++ b/include/linux/pe.h @@ -11,25 +11,26 @@ #include /* - * Linux EFI stub v1.0 adds the following functionality: - * - Loading initrd from the LINUX_EFI_INITRD_MEDIA_GUID device path, - * - Loading/starting the kernel from firmware that targets a different - * machine type, via the entrypoint exposed in the .compat PE/COFF section. + * Starting from version v3.0, the major version field should be interpreted as + * a bit mask of features supported by the kernel's EFI stub: + * - 0x1: initrd loading from the LINUX_EFI_INITRD_MEDIA_GUID device path, + * - 0x2: initrd loading using the initrd= command line option, where the file + * may be specified using device path notation, and is not required to + * reside on the same volume as the loaded kernel image. * * The recommended way of loading and starting v1.0 or later kernels is to use * the LoadImage() and StartImage() EFI boot services, and expose the initrd * via the LINUX_EFI_INITRD_MEDIA_GUID device path. * - * Versions older than v1.0 support initrd loading via the image load options - * (using initrd=, limited to the volume from which the kernel itself was - * loaded), or via arch specific means (bootparams, DT, etc). + * Versions older than v1.0 may support initrd loading via the image load + * options (using initrd=, limited to the volume from which the kernel itself + * was loaded), or only via arch specific means (bootparams, DT, etc). * - * On x86, LoadImage() and StartImage() can be omitted if the EFI handover - * protocol is implemented, which can be inferred from the version, - * handover_offset and xloadflags fields in the bootparams structure. + * The minor version field must remain 0x0. + * (https://lore.kernel.org/all/efd6f2d4-547c-1378-1faa-53c044dbd297@gmail.com/) */ -#define LINUX_EFISTUB_MAJOR_VERSION 0x1 -#define LINUX_EFISTUB_MINOR_VERSION 0x1 +#define LINUX_EFISTUB_MAJOR_VERSION 0x3 +#define LINUX_EFISTUB_MINOR_VERSION 0x0 /* * LINUX_PE_MAGIC appears at offset 0x38 into the MS-DOS header of EFI bootable -- cgit v1.2.3 From 0143d148d1e882fb1538dc9974c94d63961719b9 Mon Sep 17 00:00:00 2001 From: Ruihan Li Date: Mon, 15 May 2023 21:09:55 +0800 Subject: usb: usbfs: Enforce page requirements for mmap The current implementation of usbdev_mmap uses usb_alloc_coherent to allocate memory pages that will later be mapped into the user space. Meanwhile, usb_alloc_coherent employs three different methods to allocate memory, as outlined below: * If hcd->localmem_pool is non-null, it uses gen_pool_dma_alloc to allocate memory; * If DMA is not available, it uses kmalloc to allocate memory; * Otherwise, it uses dma_alloc_coherent. However, it should be noted that gen_pool_dma_alloc does not guarantee that the resulting memory will be page-aligned. Furthermore, trying to map slab pages (i.e., memory allocated by kmalloc) into the user space is not resonable and can lead to problems, such as a type confusion bug when PAGE_TABLE_CHECK=y [1]. To address these issues, this patch introduces hcd_alloc_coherent_pages, which addresses the above two problems. Specifically, hcd_alloc_coherent_pages uses gen_pool_dma_alloc_align instead of gen_pool_dma_alloc to ensure that the memory is page-aligned. To replace kmalloc, hcd_alloc_coherent_pages directly allocates pages by calling __get_free_pages. Reported-by: syzbot+fcf1a817ceb50935ce99@syzkaller.appspotmail.comm Closes: https://lore.kernel.org/lkml/000000000000258e5e05fae79fc1@google.com/ [1] Fixes: f7d34b445abc ("USB: Add support for usbfs zerocopy.") Fixes: ff2437befd8f ("usb: host: Fix excessive alignment restriction for local memory allocations") Cc: stable@vger.kernel.org Signed-off-by: Ruihan Li Acked-by: Alan Stern Link: https://lore.kernel.org/r/20230515130958.32471-2-lrh2000@pku.edu.cn Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/buffer.c | 41 +++++++++++++++++++++++++++++++++++++++++ drivers/usb/core/devio.c | 9 +++++---- include/linux/usb/hcd.h | 5 +++++ 3 files changed, 51 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/usb/core/buffer.c b/drivers/usb/core/buffer.c index fbb087b728dc..268ccbec88f9 100644 --- a/drivers/usb/core/buffer.c +++ b/drivers/usb/core/buffer.c @@ -172,3 +172,44 @@ void hcd_buffer_free( } dma_free_coherent(hcd->self.sysdev, size, addr, dma); } + +void *hcd_buffer_alloc_pages(struct usb_hcd *hcd, + size_t size, gfp_t mem_flags, dma_addr_t *dma) +{ + if (size == 0) + return NULL; + + if (hcd->localmem_pool) + return gen_pool_dma_alloc_align(hcd->localmem_pool, + size, dma, PAGE_SIZE); + + /* some USB hosts just use PIO */ + if (!hcd_uses_dma(hcd)) { + *dma = DMA_MAPPING_ERROR; + return (void *)__get_free_pages(mem_flags, + get_order(size)); + } + + return dma_alloc_coherent(hcd->self.sysdev, + size, dma, mem_flags); +} + +void hcd_buffer_free_pages(struct usb_hcd *hcd, + size_t size, void *addr, dma_addr_t dma) +{ + if (!addr) + return; + + if (hcd->localmem_pool) { + gen_pool_free(hcd->localmem_pool, + (unsigned long)addr, size); + return; + } + + if (!hcd_uses_dma(hcd)) { + free_pages((unsigned long)addr, get_order(size)); + return; + } + + dma_free_coherent(hcd->self.sysdev, size, addr, dma); +} diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index e501a03d6c70..3936ca7f7d2f 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -186,6 +186,7 @@ static int connected(struct usb_dev_state *ps) static void dec_usb_memory_use_count(struct usb_memory *usbm, int *count) { struct usb_dev_state *ps = usbm->ps; + struct usb_hcd *hcd = bus_to_hcd(ps->dev->bus); unsigned long flags; spin_lock_irqsave(&ps->lock, flags); @@ -194,8 +195,8 @@ static void dec_usb_memory_use_count(struct usb_memory *usbm, int *count) list_del(&usbm->memlist); spin_unlock_irqrestore(&ps->lock, flags); - usb_free_coherent(ps->dev, usbm->size, usbm->mem, - usbm->dma_handle); + hcd_buffer_free_pages(hcd, usbm->size, + usbm->mem, usbm->dma_handle); usbfs_decrease_memory_usage( usbm->size + sizeof(struct usb_memory)); kfree(usbm); @@ -247,8 +248,8 @@ static int usbdev_mmap(struct file *file, struct vm_area_struct *vma) goto error_decrease_mem; } - mem = usb_alloc_coherent(ps->dev, size, GFP_USER | __GFP_NOWARN, - &dma_handle); + mem = hcd_buffer_alloc_pages(hcd, + size, GFP_USER | __GFP_NOWARN, &dma_handle); if (!mem) { ret = -ENOMEM; goto error_free_usbm; diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 094c77eaf455..0c7eff91adf4 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -501,6 +501,11 @@ void *hcd_buffer_alloc(struct usb_bus *bus, size_t size, void hcd_buffer_free(struct usb_bus *bus, size_t size, void *addr, dma_addr_t dma); +void *hcd_buffer_alloc_pages(struct usb_hcd *hcd, + size_t size, gfp_t mem_flags, dma_addr_t *dma); +void hcd_buffer_free_pages(struct usb_hcd *hcd, + size_t size, void *addr, dma_addr_t dma); + /* generic bus glue, needed for host controllers that don't use PCI */ extern irqreturn_t usb_hcd_irq(int irq, void *__hcd); -- cgit v1.2.3 From 44d0fb387b53e56c8a050bac5c7d460e21eb226f Mon Sep 17 00:00:00 2001 From: Ruihan Li Date: Mon, 15 May 2023 21:09:58 +0800 Subject: mm: page_table_check: Ensure user pages are not slab pages The current uses of PageAnon in page table check functions can lead to type confusion bugs between struct page and slab [1], if slab pages are accidentally mapped into the user space. This is because slab reuses the bits in struct page to store its internal states, which renders PageAnon ineffective on slab pages. Since slab pages are not expected to be mapped into the user space, this patch adds BUG_ON(PageSlab(page)) checks to make sure that slab pages are not inadvertently mapped. Otherwise, there must be some bugs in the kernel. Reported-by: syzbot+fcf1a817ceb50935ce99@syzkaller.appspotmail.com Closes: https://lore.kernel.org/lkml/000000000000258e5e05fae79fc1@google.com/ [1] Fixes: df4e817b7108 ("mm: page table check") Cc: # 5.17 Signed-off-by: Ruihan Li Acked-by: Pasha Tatashin Link: https://lore.kernel.org/r/20230515130958.32471-5-lrh2000@pku.edu.cn Signed-off-by: Greg Kroah-Hartman --- include/linux/page-flags.h | 6 ++++++ mm/page_table_check.c | 6 ++++++ 2 files changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 1c68d67b832f..92a2063a0a23 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -617,6 +617,12 @@ PAGEFLAG_FALSE(VmemmapSelfHosted, vmemmap_self_hosted) * Please note that, confusingly, "page_mapping" refers to the inode * address_space which maps the page from disk; whereas "page_mapped" * refers to user virtual address space into which the page is mapped. + * + * For slab pages, since slab reuses the bits in struct page to store its + * internal states, the page->mapping does not exist as such, nor do these + * flags below. So in order to avoid testing non-existent bits, please + * make sure that PageSlab(page) actually evaluates to false before calling + * the following functions (e.g., PageAnon). See mm/slab.h. */ #define PAGE_MAPPING_ANON 0x1 #define PAGE_MAPPING_MOVABLE 0x2 diff --git a/mm/page_table_check.c b/mm/page_table_check.c index 25d8610c0042..f2baf97d5f38 100644 --- a/mm/page_table_check.c +++ b/mm/page_table_check.c @@ -71,6 +71,8 @@ static void page_table_check_clear(struct mm_struct *mm, unsigned long addr, page = pfn_to_page(pfn); page_ext = page_ext_get(page); + + BUG_ON(PageSlab(page)); anon = PageAnon(page); for (i = 0; i < pgcnt; i++) { @@ -107,6 +109,8 @@ static void page_table_check_set(struct mm_struct *mm, unsigned long addr, page = pfn_to_page(pfn); page_ext = page_ext_get(page); + + BUG_ON(PageSlab(page)); anon = PageAnon(page); for (i = 0; i < pgcnt; i++) { @@ -133,6 +137,8 @@ void __page_table_check_zero(struct page *page, unsigned int order) struct page_ext *page_ext; unsigned long i; + BUG_ON(PageSlab(page)); + page_ext = page_ext_get(page); BUG_ON(!page_ext); for (i = 0; i < (1ul << order); i++) { -- cgit v1.2.3 From ed08d937eaa4f18aa26e47fe6b937205a4745045 Mon Sep 17 00:00:00 2001 From: Maximilian Luz Date: Thu, 25 May 2023 22:50:41 +0200 Subject: platform/surface: aggregator: Make to_ssam_device_driver() respect constness Make to_ssam_device_driver() a bit safer by replacing container_of() with container_of_const() to respect the constness of the passed in pointer, instead of silently discarding any const specifications. This change also makes it more similar to to_ssam_device(), which already uses container_of_const(). Signed-off-by: Maximilian Luz Link: https://lore.kernel.org/r/20230525205041.2774947-1-luzmaximilian@gmail.com Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede --- include/linux/surface_aggregator/device.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/surface_aggregator/device.h b/include/linux/surface_aggregator/device.h index df81043b9e71..42b249b4c24b 100644 --- a/include/linux/surface_aggregator/device.h +++ b/include/linux/surface_aggregator/device.h @@ -243,11 +243,7 @@ static inline bool is_ssam_device(struct device *d) * Return: Returns the pointer to the &struct ssam_device_driver wrapping the * given device driver @d. */ -static inline -struct ssam_device_driver *to_ssam_device_driver(struct device_driver *d) -{ - return container_of(d, struct ssam_device_driver, driver); -} +#define to_ssam_device_driver(d) container_of_const(d, struct ssam_device_driver, driver) const struct ssam_device_id *ssam_device_id_match(const struct ssam_device_id *table, const struct ssam_device_uid uid); -- cgit v1.2.3 From c034203b6a9dae6751ef4371c18cb77983e30c28 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 29 May 2023 14:35:55 +0300 Subject: nfsd: fix double fget() bug in __write_ports_addfd() The bug here is that you cannot rely on getting the same socket from multiple calls to fget() because userspace can influence that. This is a kind of double fetch bug. The fix is to delete the svc_alien_sock() function and instead do the checking inside the svc_addsock() function. Fixes: 3064639423c4 ("nfsd: check passed socket's net matches NFSd superblock's one") Signed-off-by: Dan Carpenter Reviewed-by: NeilBrown Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever --- fs/nfsd/nfsctl.c | 7 +------ include/linux/sunrpc/svcsock.h | 7 +++---- net/sunrpc/svcsock.c | 24 ++++++------------------ 3 files changed, 10 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index c159817d1282..b4fd7a7062d5 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -690,16 +690,11 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred if (err != 0 || fd < 0) return -EINVAL; - if (svc_alien_sock(net, fd)) { - printk(KERN_ERR "%s: socket net is different to NFSd's one\n", __func__); - return -EINVAL; - } - err = nfsd_create_serv(net); if (err != 0) return err; - err = svc_addsock(nn->nfsd_serv, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred); + err = svc_addsock(nn->nfsd_serv, net, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred); if (err >= 0 && !nn->nfsd_serv->sv_nrthreads && !xchg(&nn->keep_active, 1)) diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h index d16ae621782c..a7116048a4d4 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -61,10 +61,9 @@ int svc_recv(struct svc_rqst *, long); void svc_send(struct svc_rqst *rqstp); void svc_drop(struct svc_rqst *); void svc_sock_update_bufs(struct svc_serv *serv); -bool svc_alien_sock(struct net *net, int fd); -int svc_addsock(struct svc_serv *serv, const int fd, - char *name_return, const size_t len, - const struct cred *cred); +int svc_addsock(struct svc_serv *serv, struct net *net, + const int fd, char *name_return, const size_t len, + const struct cred *cred); void svc_init_xprt_sock(void); void svc_cleanup_xprt_sock(void); struct svc_xprt *svc_sock_create(struct svc_serv *serv, int prot); diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 63fe7a338992..f77cebe2c071 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1480,25 +1480,10 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, return svsk; } -bool svc_alien_sock(struct net *net, int fd) -{ - int err; - struct socket *sock = sockfd_lookup(fd, &err); - bool ret = false; - - if (!sock) - goto out; - if (sock_net(sock->sk) != net) - ret = true; - sockfd_put(sock); -out: - return ret; -} -EXPORT_SYMBOL_GPL(svc_alien_sock); - /** * svc_addsock - add a listener socket to an RPC service * @serv: pointer to RPC service to which to add a new listener + * @net: caller's network namespace * @fd: file descriptor of the new listener * @name_return: pointer to buffer to fill in with name of listener * @len: size of the buffer @@ -1508,8 +1493,8 @@ EXPORT_SYMBOL_GPL(svc_alien_sock); * Name is terminated with '\n'. On error, returns a negative errno * value. */ -int svc_addsock(struct svc_serv *serv, const int fd, char *name_return, - const size_t len, const struct cred *cred) +int svc_addsock(struct svc_serv *serv, struct net *net, const int fd, + char *name_return, const size_t len, const struct cred *cred) { int err = 0; struct socket *so = sockfd_lookup(fd, &err); @@ -1520,6 +1505,9 @@ int svc_addsock(struct svc_serv *serv, const int fd, char *name_return, if (!so) return err; + err = -EINVAL; + if (sock_net(so->sk) != net) + goto out; err = -EAFNOSUPPORT; if ((so->sk->sk_family != PF_INET) && (so->sk->sk_family != PF_INET6)) goto out; -- cgit v1.2.3 From ed779fe4c9b5a20b4ab4fd6f3e19807445bb78c7 Mon Sep 17 00:00:00 2001 From: Qingfang DENG Date: Thu, 1 Jun 2023 09:54:32 +0800 Subject: neighbour: fix unaligned access to pneigh_entry After the blamed commit, the member key is longer 4-byte aligned. On platforms that do not support unaligned access, e.g., MIPS32R2 with unaligned_action set to 1, this will trigger a crash when accessing an IPv6 pneigh_entry, as the key is cast to an in6_addr pointer. Change the type of the key to u32 to make it aligned. Fixes: 62dd93181aaa ("[IPV6] NDISC: Set per-entry is_router flag in Proxy NA.") Signed-off-by: Qingfang DENG Link: https://lore.kernel.org/r/20230601015432.159066-1-dqfext@gmail.com Signed-off-by: Jakub Kicinski --- include/net/neighbour.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 3fa5774bddac..f6a8ecc6b1fa 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -180,7 +180,7 @@ struct pneigh_entry { netdevice_tracker dev_tracker; u32 flags; u8 protocol; - u8 key[]; + u32 key[]; }; /* -- cgit v1.2.3 From e209fee4118fe9a449d4d805361eb2de6796be39 Mon Sep 17 00:00:00 2001 From: Akihiro Suda Date: Thu, 1 Jun 2023 12:13:05 +0900 Subject: net/ipv4: ping_group_range: allow GID from 2147483648 to 4294967294 With this commit, all the GIDs ("0 4294967294") can be written to the "net.ipv4.ping_group_range" sysctl. Note that 4294967295 (0xffffffff) is an invalid GID (see gid_valid() in include/linux/uidgid.h), and an attempt to register this number will cause -EINVAL. Prior to this commit, only up to GID 2147483647 could be covered. Documentation/networking/ip-sysctl.rst had "0 4294967295" as an example value, but this example was wrong and causing -EINVAL. Fixes: c319b4d76b9e ("net: ipv4: add IPPROTO_ICMP socket kind") Co-developed-by: Kuniyuki Iwashima Signed-off-by: Kuniyuki Iwashima Signed-off-by: Akihiro Suda Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.rst | 4 ++-- include/net/ping.h | 6 +----- net/ipv4/sysctl_net_ipv4.c | 8 ++++---- 3 files changed, 7 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 6ec06a33688a..80b8f73a0244 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -1352,8 +1352,8 @@ ping_group_range - 2 INTEGERS Restrict ICMP_PROTO datagram sockets to users in the group range. The default is "1 0", meaning, that nobody (not even root) may create ping sockets. Setting it to "100 100" would grant permissions - to the single group. "0 4294967295" would enable it for the world, "100 - 4294967295" would enable it for the users, but not daemons. + to the single group. "0 4294967294" would enable it for the world, "100 + 4294967294" would enable it for the users, but not daemons. tcp_early_demux - BOOLEAN Enable early demux for established TCP sockets. diff --git a/include/net/ping.h b/include/net/ping.h index 9233ad3de0ad..bc7779262e60 100644 --- a/include/net/ping.h +++ b/include/net/ping.h @@ -16,11 +16,7 @@ #define PING_HTABLE_SIZE 64 #define PING_HTABLE_MASK (PING_HTABLE_SIZE-1) -/* - * gid_t is either uint or ushort. We want to pass it to - * proc_dointvec_minmax(), so it must not be larger than MAX_INT - */ -#define GID_T_MAX (((gid_t)~0U) >> 1) +#define GID_T_MAX (((gid_t)~0U) - 1) /* Compatibility glue so we can support IPv6 when it's compiled as a module */ struct pingv6_ops { diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 40fe70fc2015..88dfe51e68f3 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -34,8 +34,8 @@ static int ip_ttl_min = 1; static int ip_ttl_max = 255; static int tcp_syn_retries_min = 1; static int tcp_syn_retries_max = MAX_TCP_SYNCNT; -static int ip_ping_group_range_min[] = { 0, 0 }; -static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX }; +static unsigned long ip_ping_group_range_min[] = { 0, 0 }; +static unsigned long ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX }; static u32 u32_max_div_HZ = UINT_MAX / HZ; static int one_day_secs = 24 * 3600; static u32 fib_multipath_hash_fields_all_mask __maybe_unused = @@ -165,7 +165,7 @@ static int ipv4_ping_group_range(struct ctl_table *table, int write, { struct user_namespace *user_ns = current_user_ns(); int ret; - gid_t urange[2]; + unsigned long urange[2]; kgid_t low, high; struct ctl_table tmp = { .data = &urange, @@ -178,7 +178,7 @@ static int ipv4_ping_group_range(struct ctl_table *table, int write, inet_get_ping_group_range_table(table, &low, &high); urange[0] = from_kgid_munged(user_ns, low); urange[1] = from_kgid_munged(user_ns, high); - ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); + ret = proc_doulongvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && ret == 0) { low = make_kgid(user_ns, urange[0]); -- cgit v1.2.3 From b37a356df86b9e56d30cef4673cba2621c7b7a1e Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Mon, 22 May 2023 11:52:45 +0100 Subject: media: v4l2-subdev: Fix missing kerneldoc for client_caps Add missing kernel doc for the new 'client_caps' field in struct v4l2_subdev_fh. Signed-off-by: Tomi Valkeinen Reviewed-by: Laurent Pinchart Fixes: f57fa2959244 ("media: v4l2-subdev: Add new ioctl for client capabilities") Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-subdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index cfd19e72d0fc..b325df0d54d6 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -1119,6 +1119,7 @@ struct v4l2_subdev { * @vfh: pointer to &struct v4l2_fh * @state: pointer to &struct v4l2_subdev_state * @owner: module pointer to the owner of this file handle + * @client_caps: bitmask of ``V4L2_SUBDEV_CLIENT_CAP_*`` */ struct v4l2_subdev_fh { struct v4l2_fh vfh; -- cgit v1.2.3 From edf2e1d2019b2730d6076dbe4c040d37d7c10bbe Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 1 Jun 2023 16:04:44 +0000 Subject: net/ipv6: fix bool/int mismatch for skip_notify_on_dev_down skip_notify_on_dev_down ctl table expects this field to be an int (4 bytes), not a bool (1 byte). Because proc_dou8vec_minmax() was added in 5.13, this patch converts skip_notify_on_dev_down to an int. Following patch then converts the field to u8 and use proc_dou8vec_minmax(). Fixes: 7c6bb7d2faaf ("net/ipv6: Add knob to skip DELROUTE message on device down") Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Acked-by: Matthieu Baerts Signed-off-by: Jakub Kicinski --- include/net/netns/ipv6.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 3cceb3e9320b..d44b2ee49698 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -53,7 +53,7 @@ struct netns_sysctl_ipv6 { int seg6_flowlabel; u32 ioam6_id; u64 ioam6_id_wide; - bool skip_notify_on_dev_down; + int skip_notify_on_dev_down; u8 fib_notify_on_flag_change; u8 icmpv6_error_anycast_as_unicast; }; -- cgit v1.2.3 From ef62c0ae6db11c095880e473db9f846132d7eba8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 1 Jun 2023 16:04:45 +0000 Subject: net/ipv6: convert skip_notify_on_dev_down sysctl to u8 Save a bit a space, and could help future sysctls to use the same pattern. Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Acked-by: Matthieu Baerts Signed-off-by: Jakub Kicinski --- include/net/netns/ipv6.h | 2 +- net/ipv6/route.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index d44b2ee49698..5f2cfd84570a 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -53,7 +53,7 @@ struct netns_sysctl_ipv6 { int seg6_flowlabel; u32 ioam6_id; u64 ioam6_id_wide; - int skip_notify_on_dev_down; + u8 skip_notify_on_dev_down; u8 fib_notify_on_flag_change; u8 icmpv6_error_anycast_as_unicast; }; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index e3aec46bd466..392aaa373b66 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -6412,9 +6412,9 @@ static struct ctl_table ipv6_route_table_template[] = { { .procname = "skip_notify_on_dev_down", .data = &init_net.ipv6.sysctl.skip_notify_on_dev_down, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, -- cgit v1.2.3 From 132328e8e85174ea788faf8f627c33258c88fbad Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 5 Jun 2023 15:14:45 +0200 Subject: bpf: netfilter: Add BPF_NETFILTER bpf_attach_type Andrii Nakryiko writes: And we currently don't have an attach type for NETLINK BPF link. Thankfully it's not too late to add it. I see that link_create() in kernel/bpf/syscall.c just bypasses attach_type check. We shouldn't have done that. Instead we need to add BPF_NETLINK attach type to enum bpf_attach_type. And wire all that properly throughout the kernel and libbpf itself. This adds BPF_NETFILTER and uses it. This breaks uabi but this wasn't in any non-rc release yet, so it should be fine. v2: check link_attack prog type in link_create too Fixes: 84601d6ee68a ("bpf: add bpf_link support for BPF_NETFILTER programs") Suggested-by: Andrii Nakryiko Signed-off-by: Florian Westphal Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/CAEf4BzZ69YgrQW7DHCJUT_X+GqMq_ZQQPBwopaJJVGFD5=d5Vg@mail.gmail.com/ Link: https://lore.kernel.org/bpf/20230605131445.32016-1-fw@strlen.de --- include/uapi/linux/bpf.h | 1 + kernel/bpf/syscall.c | 9 +++++++++ tools/include/uapi/linux/bpf.h | 1 + tools/lib/bpf/libbpf.c | 3 ++- tools/lib/bpf/libbpf_probes.c | 2 ++ 5 files changed, 15 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 1bb11a6ee667..c994ff5b157c 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1035,6 +1035,7 @@ enum bpf_attach_type { BPF_TRACE_KPROBE_MULTI, BPF_LSM_CGROUP, BPF_STRUCT_OPS, + BPF_NETFILTER, __MAX_BPF_ATTACH_TYPE }; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 14f39c1e573e..0c21d0d8efe4 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2433,6 +2433,10 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, default: return -EINVAL; } + case BPF_PROG_TYPE_NETFILTER: + if (expected_attach_type == BPF_NETFILTER) + return 0; + return -EINVAL; case BPF_PROG_TYPE_SYSCALL: case BPF_PROG_TYPE_EXT: if (expected_attach_type) @@ -4590,7 +4594,12 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr) switch (prog->type) { case BPF_PROG_TYPE_EXT: + break; case BPF_PROG_TYPE_NETFILTER: + if (attr->link_create.attach_type != BPF_NETFILTER) { + ret = -EINVAL; + goto out; + } break; case BPF_PROG_TYPE_PERF_EVENT: case BPF_PROG_TYPE_TRACEPOINT: diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 1bb11a6ee667..c994ff5b157c 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1035,6 +1035,7 @@ enum bpf_attach_type { BPF_TRACE_KPROBE_MULTI, BPF_LSM_CGROUP, BPF_STRUCT_OPS, + BPF_NETFILTER, __MAX_BPF_ATTACH_TYPE }; diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index ad1ec893b41b..a27f6e9ccce7 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -117,6 +117,7 @@ static const char * const attach_type_name[] = { [BPF_PERF_EVENT] = "perf_event", [BPF_TRACE_KPROBE_MULTI] = "trace_kprobe_multi", [BPF_STRUCT_OPS] = "struct_ops", + [BPF_NETFILTER] = "netfilter", }; static const char * const link_type_name[] = { @@ -8712,7 +8713,7 @@ static const struct bpf_sec_def section_defs[] = { SEC_DEF("struct_ops+", STRUCT_OPS, 0, SEC_NONE), SEC_DEF("struct_ops.s+", STRUCT_OPS, 0, SEC_SLEEPABLE), SEC_DEF("sk_lookup", SK_LOOKUP, BPF_SK_LOOKUP, SEC_ATTACHABLE), - SEC_DEF("netfilter", NETFILTER, 0, SEC_NONE), + SEC_DEF("netfilter", NETFILTER, BPF_NETFILTER, SEC_NONE), }; static size_t custom_sec_def_cnt; diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index 6065f408a59c..b7d443129f1c 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -180,7 +180,9 @@ static int probe_prog_load(enum bpf_prog_type prog_type, case BPF_PROG_TYPE_SK_REUSEPORT: case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_CGROUP_SYSCTL: + break; case BPF_PROG_TYPE_NETFILTER: + opts.expected_attach_type = BPF_NETFILTER; break; default: return -EOPNOTSUPP; -- cgit v1.2.3 From 1857c19941c87eb36ad47f22a406be5dfe5eff9f Mon Sep 17 00:00:00 2001 From: Zhengping Jiang Date: Wed, 24 May 2023 17:11:58 -0700 Subject: Bluetooth: hci_sync: add lock to protect HCI_UNREGISTER When the HCI_UNREGISTER flag is set, no jobs should be scheduled. Fix potential race when HCI_UNREGISTER is set after the flag is tested in hci_cmd_sync_queue. Fixes: 0b94f2651f56 ("Bluetooth: hci_sync: Fix queuing commands when HCI_UNREGISTER is set") Signed-off-by: Zhengping Jiang Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_core.h | 1 + net/bluetooth/hci_core.c | 2 ++ net/bluetooth/hci_sync.c | 20 ++++++++++++++------ 3 files changed, 17 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 8baf34639939..fe3893855cd2 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -515,6 +515,7 @@ struct hci_dev { struct work_struct cmd_sync_work; struct list_head cmd_sync_work_list; struct mutex cmd_sync_work_lock; + struct mutex unregister_lock; struct work_struct cmd_sync_cancel_work; struct work_struct reenable_adv_work; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 0164b56de12d..48917c68358d 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2686,7 +2686,9 @@ void hci_unregister_dev(struct hci_dev *hdev) { BT_DBG("%p name %s bus %d", hdev, hdev->name, hdev->bus); + mutex_lock(&hdev->unregister_lock); hci_dev_set_flag(hdev, HCI_UNREGISTER); + mutex_unlock(&hdev->unregister_lock); write_lock(&hci_dev_list_lock); list_del(&hdev->list); diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 647a8ce54062..a59695f04c25 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -629,6 +629,7 @@ void hci_cmd_sync_init(struct hci_dev *hdev) INIT_WORK(&hdev->cmd_sync_work, hci_cmd_sync_work); INIT_LIST_HEAD(&hdev->cmd_sync_work_list); mutex_init(&hdev->cmd_sync_work_lock); + mutex_init(&hdev->unregister_lock); INIT_WORK(&hdev->cmd_sync_cancel_work, hci_cmd_sync_cancel_work); INIT_WORK(&hdev->reenable_adv_work, reenable_adv); @@ -692,14 +693,19 @@ int hci_cmd_sync_submit(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, void *data, hci_cmd_sync_work_destroy_t destroy) { struct hci_cmd_sync_work_entry *entry; + int err = 0; - if (hci_dev_test_flag(hdev, HCI_UNREGISTER)) - return -ENODEV; + mutex_lock(&hdev->unregister_lock); + if (hci_dev_test_flag(hdev, HCI_UNREGISTER)) { + err = -ENODEV; + goto unlock; + } entry = kmalloc(sizeof(*entry), GFP_KERNEL); - if (!entry) - return -ENOMEM; - + if (!entry) { + err = -ENOMEM; + goto unlock; + } entry->func = func; entry->data = data; entry->destroy = destroy; @@ -710,7 +716,9 @@ int hci_cmd_sync_submit(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, queue_work(hdev->req_workqueue, &hdev->cmd_sync_work); - return 0; +unlock: + mutex_unlock(&hdev->unregister_lock); + return err; } EXPORT_SYMBOL(hci_cmd_sync_submit); -- cgit v1.2.3 From fe2ccc6c29d53e14d3c8b3ddf8ad965a92e074ee Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 31 May 2023 10:57:58 +0200 Subject: Bluetooth: fix debugfs registration Since commit ec6cef9cd98d ("Bluetooth: Fix SMP channel registration for unconfigured controllers") the debugfs interface for unconfigured controllers will be created when the controller is configured. There is however currently nothing preventing a controller from being configured multiple time (e.g. setting the device address using btmgmt) which results in failed attempts to register the already registered debugfs entries: debugfs: File 'features' in directory 'hci0' already present! debugfs: File 'manufacturer' in directory 'hci0' already present! debugfs: File 'hci_version' in directory 'hci0' already present! ... debugfs: File 'quirk_simultaneous_discovery' in directory 'hci0' already present! Add a controller flag to avoid trying to register the debugfs interface more than once. Fixes: ec6cef9cd98d ("Bluetooth: Fix SMP channel registration for unconfigured controllers") Cc: stable@vger.kernel.org # 4.0 Signed-off-by: Johan Hovold Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci.h | 1 + net/bluetooth/hci_sync.c | 3 +++ 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 07df96c47ef4..872dcb91a540 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -350,6 +350,7 @@ enum { enum { HCI_SETUP, HCI_CONFIG, + HCI_DEBUGFS_CREATED, HCI_AUTO_OFF, HCI_RFKILLED, HCI_MGMT, diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index a59695f04c25..804cde43b4e0 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -4551,6 +4551,9 @@ static int hci_init_sync(struct hci_dev *hdev) !hci_dev_test_flag(hdev, HCI_CONFIG)) return 0; + if (hci_dev_test_and_set_flag(hdev, HCI_DEBUGFS_CREATED)) + return 0; + hci_debugfs_create_common(hdev); if (lmp_bredr_capable(hdev)) -- cgit v1.2.3 From 71e9588435c38112d6a8686d3d8e7cc1de8fe22c Mon Sep 17 00:00:00 2001 From: Pauli Virtanen Date: Thu, 1 Jun 2023 09:34:45 +0300 Subject: Bluetooth: ISO: use correct CIS order in Set CIG Parameters event The order of CIS handle array in Set CIG Parameters response shall match the order of the CIS_ID array in the command (Core v5.3 Vol 4 Part E Sec 7.8.97). We send CIS_IDs mainly in the order of increasing CIS_ID (but with "last" CIS first if it has fixed CIG_ID). In handling of the reply, we currently assume this is also the same as the order of hci_conn in hdev->conn_hash, but that is not true. Match the correct hci_conn to the correct handle by matching them based on the CIG+CIS combination. The CIG+CIS combination shall be unique for ISO_LINK hci_conn at state >= BT_BOUND, which we maintain in hci_le_set_cig_params. Fixes: 26afbd826ee3 ("Bluetooth: Add initial implementation of CIS connections") Signed-off-by: Pauli Virtanen Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_core.h | 3 ++- net/bluetooth/hci_event.c | 44 ++++++++++++++++++++++++---------------- 2 files changed, 28 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index fe3893855cd2..9654567cfae3 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1202,7 +1202,8 @@ static inline struct hci_conn *hci_conn_hash_lookup_cis(struct hci_dev *hdev, if (id != BT_ISO_QOS_CIS_UNSET && id != c->iso_qos.ucast.cis) continue; - if (ba_type == c->dst_type && !bacmp(&c->dst, ba)) { + /* Match destination address if set */ + if (!ba || (ba_type == c->dst_type && !bacmp(&c->dst, ba))) { rcu_read_unlock(); return c; } diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index d00ef6e3fc45..09ba6d8987ee 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -3804,48 +3804,56 @@ static u8 hci_cc_le_set_cig_params(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_le_set_cig_params *rp = data; + struct hci_cp_le_set_cig_params *cp; struct hci_conn *conn; - int i = 0; + u8 status = rp->status; + int i; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); + cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_CIG_PARAMS); + if (!cp || rp->num_handles != cp->num_cis || rp->cig_id != cp->cig_id) { + bt_dev_err(hdev, "unexpected Set CIG Parameters response data"); + status = HCI_ERROR_UNSPECIFIED; + } + hci_dev_lock(hdev); - if (rp->status) { + if (status) { while ((conn = hci_conn_hash_lookup_cig(hdev, rp->cig_id))) { conn->state = BT_CLOSED; - hci_connect_cfm(conn, rp->status); + hci_connect_cfm(conn, status); hci_conn_del(conn); } goto unlock; } - rcu_read_lock(); + /* BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E page 2553 + * + * If the Status return parameter is zero, then the Controller shall + * set the Connection_Handle arrayed return parameter to the connection + * handle(s) corresponding to the CIS configurations specified in + * the CIS_IDs command parameter, in the same order. + */ + for (i = 0; i < rp->num_handles; ++i) { + conn = hci_conn_hash_lookup_cis(hdev, NULL, 0, rp->cig_id, + cp->cis[i].cis_id); + if (!conn || !bacmp(&conn->dst, BDADDR_ANY)) + continue; - list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) { - if (conn->type != ISO_LINK || - conn->iso_qos.ucast.cig != rp->cig_id || - conn->state == BT_CONNECTED) + if (conn->state != BT_BOUND && conn->state != BT_CONNECT) continue; - conn->handle = __le16_to_cpu(rp->handle[i++]); + conn->handle = __le16_to_cpu(rp->handle[i]); bt_dev_dbg(hdev, "%p handle 0x%4.4x parent %p", conn, conn->handle, conn->parent); /* Create CIS if LE is already connected */ - if (conn->parent && conn->parent->state == BT_CONNECTED) { - rcu_read_unlock(); + if (conn->parent && conn->parent->state == BT_CONNECTED) hci_le_create_cis(conn); - rcu_read_lock(); - } - - if (i == rp->num_handles) - break; } - rcu_read_unlock(); - unlock: hci_dev_unlock(hdev); -- cgit v1.2.3 From a2f4c143d76b1a47c91ef9bc46907116b111da0b Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 5 Jun 2023 11:06:17 -0700 Subject: ipv6: rpl: Fix Route of Death. A remote DoS vulnerability of RPL Source Routing is assigned CVE-2023-2156. The Source Routing Header (SRH) has the following format: 0 1 2 3 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | Next Header | Hdr Ext Len | Routing Type | Segments Left | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | CmprI | CmprE | Pad | Reserved | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | | . . . Addresses[1..n] . . . | | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ The originator of an SRH places the first hop's IPv6 address in the IPv6 header's IPv6 Destination Address and the second hop's IPv6 address as the first address in Addresses[1..n]. The CmprI and CmprE fields indicate the number of prefix octets that are shared with the IPv6 Destination Address. When CmprI or CmprE is not 0, Addresses[1..n] are compressed as follows: 1..n-1 : (16 - CmprI) bytes n : (16 - CmprE) bytes Segments Left indicates the number of route segments remaining. When the value is not zero, the SRH is forwarded to the next hop. Its address is extracted from Addresses[n - Segment Left + 1] and swapped with IPv6 Destination Address. When Segment Left is greater than or equal to 2, the size of SRH is not changed because Addresses[1..n-1] are decompressed and recompressed with CmprI. OTOH, when Segment Left changes from 1 to 0, the new SRH could have a different size because Addresses[1..n-1] are decompressed with CmprI and recompressed with CmprE. Let's say CmprI is 15 and CmprE is 0. When we receive SRH with Segment Left >= 2, Addresses[1..n-1] have 1 byte for each, and Addresses[n] has 16 bytes. When Segment Left is 1, Addresses[1..n-1] is decompressed to 16 bytes and not recompressed. Finally, the new SRH will need more room in the header, and the size is (16 - 1) * (n - 1) bytes. Here the max value of n is 255 as Segment Left is u8, so in the worst case, we have to allocate 3825 bytes in the skb headroom. However, now we only allocate a small fixed buffer that is IPV6_RPL_SRH_WORST_SWAP_SIZE (16 + 7 bytes). If the decompressed size overflows the room, skb_push() hits BUG() below [0]. Instead of allocating the fixed buffer for every packet, let's allocate enough headroom only when we receive SRH with Segment Left 1. [0]: skbuff: skb_under_panic: text:ffffffff81c9f6e2 len:576 put:576 head:ffff8880070b5180 data:ffff8880070b4fb0 tail:0x70 end:0x140 dev:lo kernel BUG at net/core/skbuff.c:200! invalid opcode: 0000 [#1] PREEMPT SMP PTI CPU: 0 PID: 154 Comm: python3 Not tainted 6.4.0-rc4-00190-gc308e9ec0047 #7 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 RIP: 0010:skb_panic (net/core/skbuff.c:200) Code: 4f 70 50 8b 87 bc 00 00 00 50 8b 87 b8 00 00 00 50 ff b7 c8 00 00 00 4c 8b 8f c0 00 00 00 48 c7 c7 80 6e 77 82 e8 ad 8b 60 ff <0f> 0b 66 66 2e 0f 1f 84 00 00 00 00 00 90 90 90 90 90 90 90 90 90 RSP: 0018:ffffc90000003da0 EFLAGS: 00000246 RAX: 0000000000000085 RBX: ffff8880058a6600 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffff88807dc1c540 RDI: ffff88807dc1c540 RBP: ffffc90000003e48 R08: ffffffff82b392c8 R09: 00000000ffffdfff R10: ffffffff82a592e0 R11: ffffffff82b092e0 R12: ffff888005b1c800 R13: ffff8880070b51b8 R14: ffff888005b1ca18 R15: ffff8880070b5190 FS: 00007f4539f0b740(0000) GS:ffff88807dc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055670baf3000 CR3: 0000000005b0e000 CR4: 00000000007506f0 PKRU: 55555554 Call Trace: skb_push (net/core/skbuff.c:210) ipv6_rthdr_rcv (./include/linux/skbuff.h:2880 net/ipv6/exthdrs.c:634 net/ipv6/exthdrs.c:718) ip6_protocol_deliver_rcu (net/ipv6/ip6_input.c:437 (discriminator 5)) ip6_input_finish (./include/linux/rcupdate.h:805 net/ipv6/ip6_input.c:483) __netif_receive_skb_one_core (net/core/dev.c:5494) process_backlog (./include/linux/rcupdate.h:805 net/core/dev.c:5934) __napi_poll (net/core/dev.c:6496) net_rx_action (net/core/dev.c:6565 net/core/dev.c:6696) __do_softirq (./arch/x86/include/asm/jump_label.h:27 ./include/linux/jump_label.h:207 ./include/trace/events/irq.h:142 kernel/softirq.c:572) do_softirq (kernel/softirq.c:472 kernel/softirq.c:459) __local_bh_enable_ip (kernel/softirq.c:396) __dev_queue_xmit (net/core/dev.c:4272) ip6_finish_output2 (./include/net/neighbour.h:544 net/ipv6/ip6_output.c:134) rawv6_sendmsg (./include/net/dst.h:458 ./include/linux/netfilter.h:303 net/ipv6/raw.c:656 net/ipv6/raw.c:914) sock_sendmsg (net/socket.c:724 net/socket.c:747) __sys_sendto (net/socket.c:2144) __x64_sys_sendto (net/socket.c:2156 net/socket.c:2152 net/socket.c:2152) do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) RIP: 0033:0x7f453a138aea Code: d8 64 89 02 48 c7 c0 ff ff ff ff eb b8 0f 1f 00 f3 0f 1e fa 41 89 ca 64 8b 04 25 18 00 00 00 85 c0 75 15 b8 2c 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 7e c3 0f 1f 44 00 00 41 54 48 83 ec 30 44 89 RSP: 002b:00007ffcc212a1c8 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 00007ffcc212a288 RCX: 00007f453a138aea RDX: 0000000000000060 RSI: 00007f4539084c20 RDI: 0000000000000003 RBP: 00007f4538308e80 R08: 00007ffcc212a300 R09: 000000000000001c R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: ffffffffc4653600 R14: 0000000000000001 R15: 00007f4539712d1b Modules linked in: Fixes: 8610c7c6e3bd ("net: ipv6: add support for rpl sr exthdr") Reported-by: Max VA Closes: https://www.interruptlabs.co.uk/articles/linux-ipv6-route-of-death Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20230605180617.67284-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- include/net/rpl.h | 3 --- net/ipv6/exthdrs.c | 29 +++++++++++------------------ 2 files changed, 11 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/net/rpl.h b/include/net/rpl.h index 308ef0a05cae..30fe780d1e7c 100644 --- a/include/net/rpl.h +++ b/include/net/rpl.h @@ -23,9 +23,6 @@ static inline int rpl_init(void) static inline void rpl_exit(void) {} #endif -/* Worst decompression memory usage ipv6 address (16) + pad 7 */ -#define IPV6_RPL_SRH_WORST_SWAP_SIZE (sizeof(struct in6_addr) + 7) - size_t ipv6_rpl_srh_size(unsigned char n, unsigned char cmpri, unsigned char cmpre); diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index a8d961d3a477..5fa0e37305d9 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -569,24 +569,6 @@ looped_back: return -1; } - if (skb_cloned(skb)) { - if (pskb_expand_head(skb, IPV6_RPL_SRH_WORST_SWAP_SIZE, 0, - GFP_ATOMIC)) { - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_OUTDISCARDS); - kfree_skb(skb); - return -1; - } - } else { - err = skb_cow_head(skb, IPV6_RPL_SRH_WORST_SWAP_SIZE); - if (unlikely(err)) { - kfree_skb(skb); - return -1; - } - } - - hdr = (struct ipv6_rpl_sr_hdr *)skb_transport_header(skb); - if (!pskb_may_pull(skb, ipv6_rpl_srh_size(n, hdr->cmpri, hdr->cmpre))) { kfree_skb(skb); @@ -630,6 +612,17 @@ looped_back: skb_pull(skb, ((hdr->hdrlen + 1) << 3)); skb_postpull_rcsum(skb, oldhdr, sizeof(struct ipv6hdr) + ((hdr->hdrlen + 1) << 3)); + if (unlikely(!hdr->segments_left)) { + if (pskb_expand_head(skb, sizeof(struct ipv6hdr) + ((chdr->hdrlen + 1) << 3), 0, + GFP_ATOMIC)) { + __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTDISCARDS); + kfree_skb(skb); + kfree(buf); + return -1; + } + + oldhdr = ipv6_hdr(skb); + } skb_push(skb, ((chdr->hdrlen + 1) << 3) + sizeof(struct ipv6hdr)); skb_reset_network_header(skb); skb_mac_header_rebuild(skb); -- cgit v1.2.3 From 1e5c647c3f6d4f8497dedcd226204e1880e0ffb3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 6 Jun 2023 07:41:14 +0000 Subject: rfs: annotate lockless accesses to sk->sk_rxhash Add READ_ONCE()/WRITE_ONCE() on accesses to sk->sk_rxhash. This also prevents a (smart ?) compiler to remove the condition in: if (sk->sk_rxhash != newval) sk->sk_rxhash = newval; We need the condition to avoid dirtying a shared cache line. Fixes: fec5e652e58f ("rfs: Receive Flow Steering") Signed-off-by: Eric Dumazet Reviewed-by: Simon Horman Reviewed-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- include/net/sock.h | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index b418425d7230..6f428a7f3567 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1152,8 +1152,12 @@ static inline void sock_rps_record_flow(const struct sock *sk) * OR an additional socket flag * [1] : sk_state and sk_prot are in the same cache line. */ - if (sk->sk_state == TCP_ESTABLISHED) - sock_rps_record_flow_hash(sk->sk_rxhash); + if (sk->sk_state == TCP_ESTABLISHED) { + /* This READ_ONCE() is paired with the WRITE_ONCE() + * from sock_rps_save_rxhash() and sock_rps_reset_rxhash(). + */ + sock_rps_record_flow_hash(READ_ONCE(sk->sk_rxhash)); + } } #endif } @@ -1162,15 +1166,19 @@ static inline void sock_rps_save_rxhash(struct sock *sk, const struct sk_buff *skb) { #ifdef CONFIG_RPS - if (unlikely(sk->sk_rxhash != skb->hash)) - sk->sk_rxhash = skb->hash; + /* The following WRITE_ONCE() is paired with the READ_ONCE() + * here, and another one in sock_rps_record_flow(). + */ + if (unlikely(READ_ONCE(sk->sk_rxhash) != skb->hash)) + WRITE_ONCE(sk->sk_rxhash, skb->hash); #endif } static inline void sock_rps_reset_rxhash(struct sock *sk) { #ifdef CONFIG_RPS - sk->sk_rxhash = 0; + /* Paired with READ_ONCE() in sock_rps_record_flow() */ + WRITE_ONCE(sk->sk_rxhash, 0); #endif } -- cgit v1.2.3 From 5c3b74a92aa285a3df722bf6329ba7ccf70346d6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 6 Jun 2023 07:41:15 +0000 Subject: rfs: annotate lockless accesses to RFS sock flow table Add READ_ONCE()/WRITE_ONCE() on accesses to the sock flow table. This also prevents a (smart ?) compiler to remove the condition in: if (table->ents[index] != newval) table->ents[index] = newval; We need the condition to avoid dirtying a shared cache line. Fixes: fec5e652e58f ("rfs: Receive Flow Steering") Signed-off-by: Eric Dumazet Reviewed-by: Simon Horman Reviewed-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 +++++-- net/core/dev.c | 6 ++++-- 2 files changed, 9 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 08fbd4622ccf..e6f22b7403d0 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -768,8 +768,11 @@ static inline void rps_record_sock_flow(struct rps_sock_flow_table *table, /* We only give a hint, preemption can change CPU under us */ val |= raw_smp_processor_id(); - if (table->ents[index] != val) - table->ents[index] = val; + /* The following WRITE_ONCE() is paired with the READ_ONCE() + * here, and another one in get_rps_cpu(). + */ + if (READ_ONCE(table->ents[index]) != val) + WRITE_ONCE(table->ents[index], val); } } diff --git a/net/core/dev.c b/net/core/dev.c index b3c13e041935..1495f8aff288 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4471,8 +4471,10 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, u32 next_cpu; u32 ident; - /* First check into global flow table if there is a match */ - ident = sock_flow_table->ents[hash & sock_flow_table->mask]; + /* First check into global flow table if there is a match. + * This READ_ONCE() pairs with WRITE_ONCE() from rps_record_sock_flow(). + */ + ident = READ_ONCE(sock_flow_table->ents[hash & sock_flow_table->mask]); if ((ident ^ hash) & ~rps_cpu_mask) goto try_rps; -- cgit v1.2.3 From d636fc5dd692c8f4e00ae6e0359c0eceeb5d9bdb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 6 Jun 2023 11:19:29 +0000 Subject: net: sched: add rcu annotations around qdisc->qdisc_sleeping syzbot reported a race around qdisc->qdisc_sleeping [1] It is time we add proper annotations to reads and writes to/from qdisc->qdisc_sleeping. [1] BUG: KCSAN: data-race in dev_graft_qdisc / qdisc_lookup_rcu read to 0xffff8881286fc618 of 8 bytes by task 6928 on cpu 1: qdisc_lookup_rcu+0x192/0x2c0 net/sched/sch_api.c:331 __tcf_qdisc_find+0x74/0x3c0 net/sched/cls_api.c:1174 tc_get_tfilter+0x18f/0x990 net/sched/cls_api.c:2547 rtnetlink_rcv_msg+0x7af/0x8c0 net/core/rtnetlink.c:6386 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd write to 0xffff8881286fc618 of 8 bytes by task 6912 on cpu 0: dev_graft_qdisc+0x4f/0x80 net/sched/sch_generic.c:1115 qdisc_graft+0x7d0/0xb60 net/sched/sch_api.c:1103 tc_modify_qdisc+0x712/0xf10 net/sched/sch_api.c:1693 rtnetlink_rcv_msg+0x807/0x8c0 net/core/rtnetlink.c:6395 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 6912 Comm: syz-executor.5 Not tainted 6.4.0-rc3-syzkaller-00190-g0d85b27b0cc6 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/16/2023 Fixes: 3a7d0d07a386 ("net: sched: extend Qdisc with rcu") Reported-by: syzbot Signed-off-by: Eric Dumazet Cc: Vlad Buslov Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- include/net/sch_generic.h | 6 ++++-- net/core/dev.c | 2 +- net/sched/sch_api.c | 26 ++++++++++++++++---------- net/sched/sch_fq_pie.c | 2 ++ net/sched/sch_generic.c | 30 +++++++++++++++--------------- net/sched/sch_mq.c | 8 ++++---- net/sched/sch_mqprio.c | 8 ++++---- net/sched/sch_pie.c | 5 ++++- net/sched/sch_red.c | 5 ++++- net/sched/sch_sfq.c | 5 ++++- net/sched/sch_taprio.c | 6 +++--- net/sched/sch_teql.c | 2 +- 13 files changed, 63 insertions(+), 44 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e6f22b7403d0..c2f0c6002a84 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -620,7 +620,7 @@ struct netdev_queue { netdevice_tracker dev_tracker; struct Qdisc __rcu *qdisc; - struct Qdisc *qdisc_sleeping; + struct Qdisc __rcu *qdisc_sleeping; #ifdef CONFIG_SYSFS struct kobject kobj; #endif diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index fab5ba3e61b7..27271f2b37cb 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -545,7 +545,7 @@ static inline struct Qdisc *qdisc_root_bh(const struct Qdisc *qdisc) static inline struct Qdisc *qdisc_root_sleeping(const struct Qdisc *qdisc) { - return qdisc->dev_queue->qdisc_sleeping; + return rcu_dereference_rtnl(qdisc->dev_queue->qdisc_sleeping); } static inline spinlock_t *qdisc_root_sleeping_lock(const struct Qdisc *qdisc) @@ -754,7 +754,9 @@ static inline bool qdisc_tx_changing(const struct net_device *dev) for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); - if (rcu_access_pointer(txq->qdisc) != txq->qdisc_sleeping) + + if (rcu_access_pointer(txq->qdisc) != + rcu_access_pointer(txq->qdisc_sleeping)) return true; } return false; diff --git a/net/core/dev.c b/net/core/dev.c index 1495f8aff288..c29f3e1db3ca 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -10543,7 +10543,7 @@ struct netdev_queue *dev_ingress_queue_create(struct net_device *dev) return NULL; netdev_init_one_queue(dev, queue, NULL); RCU_INIT_POINTER(queue->qdisc, &noop_qdisc); - queue->qdisc_sleeping = &noop_qdisc; + RCU_INIT_POINTER(queue->qdisc_sleeping, &noop_qdisc); rcu_assign_pointer(dev->ingress_queue, queue); #endif return queue; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 9ea51812b9cf..e4b6452318c0 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -309,7 +309,7 @@ struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle) if (dev_ingress_queue(dev)) q = qdisc_match_from_root( - dev_ingress_queue(dev)->qdisc_sleeping, + rtnl_dereference(dev_ingress_queue(dev)->qdisc_sleeping), handle); out: return q; @@ -328,7 +328,8 @@ struct Qdisc *qdisc_lookup_rcu(struct net_device *dev, u32 handle) nq = dev_ingress_queue_rcu(dev); if (nq) - q = qdisc_match_from_root(nq->qdisc_sleeping, handle); + q = qdisc_match_from_root(rcu_dereference(nq->qdisc_sleeping), + handle); out: return q; } @@ -634,8 +635,13 @@ EXPORT_SYMBOL(qdisc_watchdog_init); void qdisc_watchdog_schedule_range_ns(struct qdisc_watchdog *wd, u64 expires, u64 delta_ns) { - if (test_bit(__QDISC_STATE_DEACTIVATED, - &qdisc_root_sleeping(wd->qdisc)->state)) + bool deactivated; + + rcu_read_lock(); + deactivated = test_bit(__QDISC_STATE_DEACTIVATED, + &qdisc_root_sleeping(wd->qdisc)->state); + rcu_read_unlock(); + if (deactivated) return; if (hrtimer_is_queued(&wd->timer)) { @@ -1478,7 +1484,7 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, } q = qdisc_leaf(p, clid); } else if (dev_ingress_queue(dev)) { - q = dev_ingress_queue(dev)->qdisc_sleeping; + q = rtnl_dereference(dev_ingress_queue(dev)->qdisc_sleeping); } } else { q = rtnl_dereference(dev->qdisc); @@ -1564,7 +1570,7 @@ replay: } q = qdisc_leaf(p, clid); } else if (dev_ingress_queue_create(dev)) { - q = dev_ingress_queue(dev)->qdisc_sleeping; + q = rtnl_dereference(dev_ingress_queue(dev)->qdisc_sleeping); } } else { q = rtnl_dereference(dev->qdisc); @@ -1805,8 +1811,8 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) dev_queue = dev_ingress_queue(dev); if (dev_queue && - tc_dump_qdisc_root(dev_queue->qdisc_sleeping, skb, cb, - &q_idx, s_q_idx, false, + tc_dump_qdisc_root(rtnl_dereference(dev_queue->qdisc_sleeping), + skb, cb, &q_idx, s_q_idx, false, tca[TCA_DUMP_INVISIBLE]) < 0) goto done; @@ -2249,8 +2255,8 @@ static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb) dev_queue = dev_ingress_queue(dev); if (dev_queue && - tc_dump_tclass_root(dev_queue->qdisc_sleeping, skb, tcm, cb, - &t, s_t, false) < 0) + tc_dump_tclass_root(rtnl_dereference(dev_queue->qdisc_sleeping), + skb, tcm, cb, &t, s_t, false) < 0) goto done; done: diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index c699e5095607..591d87d5e5c0 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -379,6 +379,7 @@ static void fq_pie_timer(struct timer_list *t) spinlock_t *root_lock; /* to lock qdisc for probability calculations */ u32 idx; + rcu_read_lock(); root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); @@ -391,6 +392,7 @@ static void fq_pie_timer(struct timer_list *t) mod_timer(&q->adapt_timer, jiffies + q->p_params.tupdate); spin_unlock(root_lock); + rcu_read_unlock(); } static int fq_pie_init(struct Qdisc *sch, struct nlattr *opt, diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 37e41f972f69..3248259eba32 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -648,7 +648,7 @@ struct Qdisc_ops noop_qdisc_ops __read_mostly = { static struct netdev_queue noop_netdev_queue = { RCU_POINTER_INITIALIZER(qdisc, &noop_qdisc), - .qdisc_sleeping = &noop_qdisc, + RCU_POINTER_INITIALIZER(qdisc_sleeping, &noop_qdisc), }; struct Qdisc noop_qdisc = { @@ -1103,7 +1103,7 @@ EXPORT_SYMBOL(qdisc_put_unlocked); struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, struct Qdisc *qdisc) { - struct Qdisc *oqdisc = dev_queue->qdisc_sleeping; + struct Qdisc *oqdisc = rtnl_dereference(dev_queue->qdisc_sleeping); spinlock_t *root_lock; root_lock = qdisc_lock(oqdisc); @@ -1112,7 +1112,7 @@ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, /* ... and graft new one */ if (qdisc == NULL) qdisc = &noop_qdisc; - dev_queue->qdisc_sleeping = qdisc; + rcu_assign_pointer(dev_queue->qdisc_sleeping, qdisc); rcu_assign_pointer(dev_queue->qdisc, &noop_qdisc); spin_unlock_bh(root_lock); @@ -1125,12 +1125,12 @@ static void shutdown_scheduler_queue(struct net_device *dev, struct netdev_queue *dev_queue, void *_qdisc_default) { - struct Qdisc *qdisc = dev_queue->qdisc_sleeping; + struct Qdisc *qdisc = rtnl_dereference(dev_queue->qdisc_sleeping); struct Qdisc *qdisc_default = _qdisc_default; if (qdisc) { rcu_assign_pointer(dev_queue->qdisc, qdisc_default); - dev_queue->qdisc_sleeping = qdisc_default; + rcu_assign_pointer(dev_queue->qdisc_sleeping, qdisc_default); qdisc_put(qdisc); } @@ -1154,7 +1154,7 @@ static void attach_one_default_qdisc(struct net_device *dev, if (!netif_is_multiqueue(dev)) qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; - dev_queue->qdisc_sleeping = qdisc; + rcu_assign_pointer(dev_queue->qdisc_sleeping, qdisc); } static void attach_default_qdiscs(struct net_device *dev) @@ -1167,7 +1167,7 @@ static void attach_default_qdiscs(struct net_device *dev) if (!netif_is_multiqueue(dev) || dev->priv_flags & IFF_NO_QUEUE) { netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL); - qdisc = txq->qdisc_sleeping; + qdisc = rtnl_dereference(txq->qdisc_sleeping); rcu_assign_pointer(dev->qdisc, qdisc); qdisc_refcount_inc(qdisc); } else { @@ -1186,7 +1186,7 @@ static void attach_default_qdiscs(struct net_device *dev) netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc); dev->priv_flags |= IFF_NO_QUEUE; netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL); - qdisc = txq->qdisc_sleeping; + qdisc = rtnl_dereference(txq->qdisc_sleeping); rcu_assign_pointer(dev->qdisc, qdisc); qdisc_refcount_inc(qdisc); dev->priv_flags ^= IFF_NO_QUEUE; @@ -1202,7 +1202,7 @@ static void transition_one_qdisc(struct net_device *dev, struct netdev_queue *dev_queue, void *_need_watchdog) { - struct Qdisc *new_qdisc = dev_queue->qdisc_sleeping; + struct Qdisc *new_qdisc = rtnl_dereference(dev_queue->qdisc_sleeping); int *need_watchdog_p = _need_watchdog; if (!(new_qdisc->flags & TCQ_F_BUILTIN)) @@ -1272,7 +1272,7 @@ static void dev_reset_queue(struct net_device *dev, struct Qdisc *qdisc; bool nolock; - qdisc = dev_queue->qdisc_sleeping; + qdisc = rtnl_dereference(dev_queue->qdisc_sleeping); if (!qdisc) return; @@ -1303,7 +1303,7 @@ static bool some_qdisc_is_busy(struct net_device *dev) int val; dev_queue = netdev_get_tx_queue(dev, i); - q = dev_queue->qdisc_sleeping; + q = rtnl_dereference(dev_queue->qdisc_sleeping); root_lock = qdisc_lock(q); spin_lock_bh(root_lock); @@ -1379,7 +1379,7 @@ EXPORT_SYMBOL(dev_deactivate); static int qdisc_change_tx_queue_len(struct net_device *dev, struct netdev_queue *dev_queue) { - struct Qdisc *qdisc = dev_queue->qdisc_sleeping; + struct Qdisc *qdisc = rtnl_dereference(dev_queue->qdisc_sleeping); const struct Qdisc_ops *ops = qdisc->ops; if (ops->change_tx_queue_len) @@ -1404,7 +1404,7 @@ void mq_change_real_num_tx(struct Qdisc *sch, unsigned int new_real_tx) unsigned int i; for (i = new_real_tx; i < dev->real_num_tx_queues; i++) { - qdisc = netdev_get_tx_queue(dev, i)->qdisc_sleeping; + qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc_sleeping); /* Only update the default qdiscs we created, * qdiscs with handles are always hashed. */ @@ -1412,7 +1412,7 @@ void mq_change_real_num_tx(struct Qdisc *sch, unsigned int new_real_tx) qdisc_hash_del(qdisc); } for (i = dev->real_num_tx_queues; i < new_real_tx; i++) { - qdisc = netdev_get_tx_queue(dev, i)->qdisc_sleeping; + qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc_sleeping); if (qdisc != &noop_qdisc && !qdisc->handle) qdisc_hash_add(qdisc, false); } @@ -1449,7 +1449,7 @@ static void dev_init_scheduler_queue(struct net_device *dev, struct Qdisc *qdisc = _qdisc; rcu_assign_pointer(dev_queue->qdisc, qdisc); - dev_queue->qdisc_sleeping = qdisc; + rcu_assign_pointer(dev_queue->qdisc_sleeping, qdisc); } void dev_init_scheduler(struct net_device *dev) diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index d0bc660d7401..c860119a8f09 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -141,7 +141,7 @@ static int mq_dump(struct Qdisc *sch, struct sk_buff *skb) * qdisc totals are added at end. */ for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { - qdisc = netdev_get_tx_queue(dev, ntx)->qdisc_sleeping; + qdisc = rtnl_dereference(netdev_get_tx_queue(dev, ntx)->qdisc_sleeping); spin_lock_bh(qdisc_lock(qdisc)); gnet_stats_add_basic(&sch->bstats, qdisc->cpu_bstats, @@ -202,7 +202,7 @@ static struct Qdisc *mq_leaf(struct Qdisc *sch, unsigned long cl) { struct netdev_queue *dev_queue = mq_queue_get(sch, cl); - return dev_queue->qdisc_sleeping; + return rtnl_dereference(dev_queue->qdisc_sleeping); } static unsigned long mq_find(struct Qdisc *sch, u32 classid) @@ -221,7 +221,7 @@ static int mq_dump_class(struct Qdisc *sch, unsigned long cl, tcm->tcm_parent = TC_H_ROOT; tcm->tcm_handle |= TC_H_MIN(cl); - tcm->tcm_info = dev_queue->qdisc_sleeping->handle; + tcm->tcm_info = rtnl_dereference(dev_queue->qdisc_sleeping)->handle; return 0; } @@ -230,7 +230,7 @@ static int mq_dump_class_stats(struct Qdisc *sch, unsigned long cl, { struct netdev_queue *dev_queue = mq_queue_get(sch, cl); - sch = dev_queue->qdisc_sleeping; + sch = rtnl_dereference(dev_queue->qdisc_sleeping); if (gnet_stats_copy_basic(d, sch->cpu_bstats, &sch->bstats, true) < 0 || qdisc_qstats_copy(d, sch) < 0) return -1; diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index dc5a0ff50b14..ab69ff7577fc 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -557,7 +557,7 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) * qdisc totals are added at end. */ for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { - qdisc = netdev_get_tx_queue(dev, ntx)->qdisc_sleeping; + qdisc = rtnl_dereference(netdev_get_tx_queue(dev, ntx)->qdisc_sleeping); spin_lock_bh(qdisc_lock(qdisc)); gnet_stats_add_basic(&sch->bstats, qdisc->cpu_bstats, @@ -604,7 +604,7 @@ static struct Qdisc *mqprio_leaf(struct Qdisc *sch, unsigned long cl) if (!dev_queue) return NULL; - return dev_queue->qdisc_sleeping; + return rtnl_dereference(dev_queue->qdisc_sleeping); } static unsigned long mqprio_find(struct Qdisc *sch, u32 classid) @@ -637,7 +637,7 @@ static int mqprio_dump_class(struct Qdisc *sch, unsigned long cl, tcm->tcm_parent = (tc < 0) ? 0 : TC_H_MAKE(TC_H_MAJ(sch->handle), TC_H_MIN(tc + TC_H_MIN_PRIORITY)); - tcm->tcm_info = dev_queue->qdisc_sleeping->handle; + tcm->tcm_info = rtnl_dereference(dev_queue->qdisc_sleeping)->handle; } else { tcm->tcm_parent = TC_H_ROOT; tcm->tcm_info = 0; @@ -693,7 +693,7 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, } else { struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl); - sch = dev_queue->qdisc_sleeping; + sch = rtnl_dereference(dev_queue->qdisc_sleeping); if (gnet_stats_copy_basic(d, sch->cpu_bstats, &sch->bstats, true) < 0 || qdisc_qstats_copy(d, sch) < 0) diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index 2152a56d73f8..2da6250ec346 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -421,8 +421,10 @@ static void pie_timer(struct timer_list *t) { struct pie_sched_data *q = from_timer(q, t, adapt_timer); struct Qdisc *sch = q->sch; - spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch)); + spinlock_t *root_lock; + rcu_read_lock(); + root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); pie_calculate_probability(&q->params, &q->vars, sch->qstats.backlog); @@ -430,6 +432,7 @@ static void pie_timer(struct timer_list *t) if (q->params.tupdate) mod_timer(&q->adapt_timer, jiffies + q->params.tupdate); spin_unlock(root_lock); + rcu_read_unlock(); } static int pie_init(struct Qdisc *sch, struct nlattr *opt, diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 98129324e157..16277b6a0238 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -321,12 +321,15 @@ static inline void red_adaptative_timer(struct timer_list *t) { struct red_sched_data *q = from_timer(q, t, adapt_timer); struct Qdisc *sch = q->sch; - spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch)); + spinlock_t *root_lock; + rcu_read_lock(); + root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); red_adaptative_algo(&q->parms, &q->vars); mod_timer(&q->adapt_timer, jiffies + HZ/2); spin_unlock(root_lock); + rcu_read_unlock(); } static int red_init(struct Qdisc *sch, struct nlattr *opt, diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index abd436307d6a..66dcb18638fe 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -606,10 +606,12 @@ static void sfq_perturbation(struct timer_list *t) { struct sfq_sched_data *q = from_timer(q, t, perturb_timer); struct Qdisc *sch = q->sch; - spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch)); + spinlock_t *root_lock; siphash_key_t nkey; get_random_bytes(&nkey, sizeof(nkey)); + rcu_read_lock(); + root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); q->perturbation = nkey; if (!q->filter_list && q->tail) @@ -618,6 +620,7 @@ static void sfq_perturbation(struct timer_list *t) if (q->perturb_period) mod_timer(&q->perturb_timer, jiffies + q->perturb_period); + rcu_read_unlock(); } static int sfq_change(struct Qdisc *sch, struct nlattr *opt) diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 76db9a10ef50..dd7dea2f6e83 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -2358,7 +2358,7 @@ static struct Qdisc *taprio_leaf(struct Qdisc *sch, unsigned long cl) if (!dev_queue) return NULL; - return dev_queue->qdisc_sleeping; + return rtnl_dereference(dev_queue->qdisc_sleeping); } static unsigned long taprio_find(struct Qdisc *sch, u32 classid) @@ -2377,7 +2377,7 @@ static int taprio_dump_class(struct Qdisc *sch, unsigned long cl, tcm->tcm_parent = TC_H_ROOT; tcm->tcm_handle |= TC_H_MIN(cl); - tcm->tcm_info = dev_queue->qdisc_sleeping->handle; + tcm->tcm_info = rtnl_dereference(dev_queue->qdisc_sleeping)->handle; return 0; } @@ -2389,7 +2389,7 @@ static int taprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, { struct netdev_queue *dev_queue = taprio_queue_get(sch, cl); - sch = dev_queue->qdisc_sleeping; + sch = rtnl_dereference(dev_queue->qdisc_sleeping); if (gnet_stats_copy_basic(d, NULL, &sch->bstats, true) < 0 || qdisc_qstats_copy(d, sch) < 0) return -1; diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 16f9238aa51d..7721239c185f 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -297,7 +297,7 @@ restart: struct net_device *slave = qdisc_dev(q); struct netdev_queue *slave_txq = netdev_get_tx_queue(slave, 0); - if (slave_txq->qdisc_sleeping != q) + if (rcu_access_pointer(slave_txq->qdisc_sleeping) != q) continue; if (netif_xmit_stopped(netdev_get_tx_queue(slave, subq)) || !netif_running(slave)) { -- cgit v1.2.3 From 886bc7d6ed3357975c5f1d3c784da96000d4bbb4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 6 Jun 2023 11:42:33 +0000 Subject: net: sched: move rtm_tca_policy declaration to include file rtm_tca_policy is used from net/sched/sch_api.c and net/sched/cls_api.c, thus should be declared in an include file. This fixes the following sparse warning: net/sched/sch_api.c:1434:25: warning: symbol 'rtm_tca_policy' was not declared. Should it be static? Fixes: e331473fee3d ("net/sched: cls_api: add missing validation of netlink attributes") Signed-off-by: Eric Dumazet Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/pkt_sched.h | 2 ++ net/sched/cls_api.c | 2 -- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index f436688b6efc..5722931d83d4 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -127,6 +127,8 @@ static inline void qdisc_run(struct Qdisc *q) } } +extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1]; + /* Calculate maximal size of packet seen by hard_start_xmit routine of this device. */ diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 2621550bfddc..b2432ee04f31 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -43,8 +43,6 @@ #include #include -extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1]; - /* The list of all installed classifier types */ static LIST_HEAD(tcf_proto_base); -- cgit v1.2.3