diff options
155 files changed, 1436 insertions, 463 deletions
@@ -1987,6 +1987,7 @@ D: netfilter: TCP window tracking code D: netfilter: raw table D: netfilter: iprange match D: netfilter: new logging interfaces +D: netfilter: ipset D: netfilter: various other hacks S: Tata S: Hungary diff --git a/Documentation/admin-guide/blockdev/zoned_loop.rst b/Documentation/admin-guide/blockdev/zoned_loop.rst index 806adde664db..6aa865424ac3 100644 --- a/Documentation/admin-guide/blockdev/zoned_loop.rst +++ b/Documentation/admin-guide/blockdev/zoned_loop.rst @@ -134,7 +134,7 @@ MB and a zone capacity of 63 MB:: $ modprobe zloop $ mkdir -p /var/local/zloop/0 - $ echo "add capacity_mb=2048,zone_size_mb=64,zone_capacity=63MB" > /dev/zloop-control + $ echo "add capacity_mb=2048,zone_size_mb=64,zone_capacity_mb=63" > /dev/zloop-control For the device created (/dev/zloop0), the zone backing files are all created under the default base directory (/var/local/zloop):: diff --git a/MAINTAINERS b/MAINTAINERS index 5b11839cba9d..dc731d37c8fe 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -18028,7 +18028,6 @@ F: drivers/net/ethernet/neterion/ NETFILTER M: Pablo Neira Ayuso <pablo@netfilter.org> -M: Jozsef Kadlecsik <kadlec@netfilter.org> M: Florian Westphal <fw@strlen.de> R: Phil Sutter <phil@nwl.cc> L: netfilter-devel@vger.kernel.org @@ -26464,6 +26463,7 @@ L: linux-trace-kernel@vger.kernel.org S: Maintained Q: https://patchwork.kernel.org/project/linux-trace-kernel/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace.git +F: Documentation/core-api/tracepoint.rst F: Documentation/trace/* F: fs/tracefs/ F: include/linux/trace*.h diff --git a/arch/arm64/include/asm/simd.h b/arch/arm64/include/asm/simd.h index 0941f6f58a14..69ecbd69ca8c 100644 --- a/arch/arm64/include/asm/simd.h +++ b/arch/arm64/include/asm/simd.h @@ -48,6 +48,13 @@ DEFINE_LOCK_GUARD_1(ksimd, kernel_neon_begin(_T->lock), kernel_neon_end(_T->lock)) -#define scoped_ksimd() scoped_guard(ksimd, &(struct user_fpsimd_state){}) +#define __scoped_ksimd(_label) \ + for (struct user_fpsimd_state __uninitialized __st; \ + true; ({ goto _label; })) \ + if (0) { \ +_label: break; \ + } else scoped_guard(ksimd, &__st) + +#define scoped_ksimd() __scoped_ksimd(__UNIQUE_ID(label)) #endif diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 4806cc28d7ca..b74ff8bc7f2a 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -108,7 +108,7 @@ static int xen_cpu_dead_pv(unsigned int cpu); * calls. */ DEFINE_PER_CPU(bool, xen_in_preemptible_hcall); -EXPORT_SYMBOL_GPL(xen_in_preemptible_hcall); +EXPORT_PER_CPU_SYMBOL_GPL(xen_in_preemptible_hcall); /* * In case of scheduling the flag must be cleared and restored after diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 4a8d3d96bfe4..6e54b1d3d8bc 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -7181,7 +7181,7 @@ static void bfq_exit_queue(struct elevator_queue *e) blk_stat_disable_accounting(bfqd->queue); blk_queue_flag_clear(QUEUE_FLAG_DISABLE_WBT_DEF, bfqd->queue); - set_bit(ELEVATOR_FLAG_ENABLE_WBT_ON_EXIT, &e->flags); + wbt_enable_default(bfqd->queue->disk); kfree(bfqd); } diff --git a/block/blk-settings.c b/block/blk-settings.c index 51401f08ce05..a9e65dc090da 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -161,10 +161,9 @@ static int blk_validate_integrity_limits(struct queue_limits *lim) return -EINVAL; } - if (bi->pi_tuple_size > bi->metadata_size) { - pr_warn("pi_tuple_size (%u) exceeds metadata_size (%u)\n", - bi->pi_tuple_size, - bi->metadata_size); + if (bi->pi_offset + bi->pi_tuple_size > bi->metadata_size) { + pr_warn("pi_offset (%u) + pi_tuple_size (%u) exceeds metadata_size (%u)\n", + bi->pi_offset, bi->pi_tuple_size, bi->metadata_size); return -EINVAL; } @@ -194,8 +193,13 @@ static int blk_validate_integrity_limits(struct queue_limits *lim) break; } - if (!bi->interval_exp) + if (!bi->interval_exp) { bi->interval_exp = ilog2(lim->logical_block_size); + } else if (bi->interval_exp < SECTOR_SHIFT || + bi->interval_exp > ilog2(lim->logical_block_size)) { + pr_warn("invalid interval_exp %u\n", bi->interval_exp); + return -EINVAL; + } /* * The PI generation / validation helpers do not expect intervals to diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 8684c57498cc..e0a70d26972b 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -932,7 +932,7 @@ int blk_register_queue(struct gendisk *disk) elevator_set_default(q); blk_queue_flag_set(QUEUE_FLAG_REGISTERED, q); - wbt_enable_default(disk); + wbt_init_enable_default(disk); /* Now everything is ready and send out KOBJ_ADD uevent */ kobject_uevent(&disk->queue_kobj, KOBJ_ADD); diff --git a/block/blk-wbt.c b/block/blk-wbt.c index eb8037bae0bd..0974875f77bd 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -699,7 +699,7 @@ static void wbt_requeue(struct rq_qos *rqos, struct request *rq) /* * Enable wbt if defaults are configured that way */ -void wbt_enable_default(struct gendisk *disk) +static bool __wbt_enable_default(struct gendisk *disk) { struct request_queue *q = disk->queue; struct rq_qos *rqos; @@ -716,19 +716,31 @@ void wbt_enable_default(struct gendisk *disk) if (enable && RQWB(rqos)->enable_state == WBT_STATE_OFF_DEFAULT) RQWB(rqos)->enable_state = WBT_STATE_ON_DEFAULT; mutex_unlock(&disk->rqos_state_mutex); - return; + return false; } mutex_unlock(&disk->rqos_state_mutex); /* Queue not registered? Maybe shutting down... */ if (!blk_queue_registered(q)) - return; + return false; if (queue_is_mq(q) && enable) - wbt_init(disk); + return true; + return false; +} + +void wbt_enable_default(struct gendisk *disk) +{ + __wbt_enable_default(disk); } EXPORT_SYMBOL_GPL(wbt_enable_default); +void wbt_init_enable_default(struct gendisk *disk) +{ + if (__wbt_enable_default(disk)) + WARN_ON_ONCE(wbt_init(disk)); +} + u64 wbt_default_latency_nsec(struct request_queue *q) { /* diff --git a/block/blk-wbt.h b/block/blk-wbt.h index e5fc653b9b76..925f22475738 100644 --- a/block/blk-wbt.h +++ b/block/blk-wbt.h @@ -5,6 +5,7 @@ #ifdef CONFIG_BLK_WBT int wbt_init(struct gendisk *disk); +void wbt_init_enable_default(struct gendisk *disk); void wbt_disable_default(struct gendisk *disk); void wbt_enable_default(struct gendisk *disk); @@ -16,6 +17,10 @@ u64 wbt_default_latency_nsec(struct request_queue *); #else +static inline void wbt_init_enable_default(struct gendisk *disk) +{ +} + static inline void wbt_disable_default(struct gendisk *disk) { } diff --git a/block/elevator.c b/block/elevator.c index 5b37ef44f52d..a2f8b2251dc6 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -633,14 +633,10 @@ static int elevator_change_done(struct request_queue *q, .et = ctx->old->et, .data = ctx->old->elevator_data }; - bool enable_wbt = test_bit(ELEVATOR_FLAG_ENABLE_WBT_ON_EXIT, - &ctx->old->flags); elv_unregister_queue(q, ctx->old); blk_mq_free_sched_res(&res, ctx->old->type, q->tag_set); kobject_put(&ctx->old->kobj); - if (enable_wbt) - wbt_enable_default(q->disk); } if (ctx->new) { ret = elv_register_queue(q, ctx->new, !ctx->no_uevent); diff --git a/block/elevator.h b/block/elevator.h index a9d092c5a9e8..3eb32516be0b 100644 --- a/block/elevator.h +++ b/block/elevator.h @@ -156,7 +156,6 @@ struct elevator_queue #define ELEVATOR_FLAG_REGISTERED 0 #define ELEVATOR_FLAG_DYING 1 -#define ELEVATOR_FLAG_ENABLE_WBT_ON_EXIT 2 /* * block elevator interface diff --git a/block/ioctl.c b/block/ioctl.c index 61feed686418..344478348a54 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -442,11 +442,12 @@ static int blkdev_pr_read_keys(struct block_device *bdev, blk_mode_t mode, if (copy_from_user(&read_keys, arg, sizeof(read_keys))) return -EFAULT; - keys_info_len = struct_size(keys_info, keys, read_keys.num_keys); - if (keys_info_len == SIZE_MAX) + if (read_keys.num_keys > PR_KEYS_MAX) return -EINVAL; - keys_info = kzalloc(keys_info_len, GFP_KERNEL); + keys_info_len = struct_size(keys_info, keys, read_keys.num_keys); + + keys_info = kvzalloc(keys_info_len, GFP_KERNEL); if (!keys_info) return -ENOMEM; @@ -473,7 +474,7 @@ static int blkdev_pr_read_keys(struct block_device *bdev, blk_mode_t mode, if (copy_to_user(arg, &read_keys, sizeof(read_keys))) ret = -EFAULT; out: - kfree(keys_info); + kvfree(keys_info); return ret; } diff --git a/drivers/acpi/acpi_pcc.c b/drivers/acpi/acpi_pcc.c index 97064e943768..e3f302b9dee5 100644 --- a/drivers/acpi/acpi_pcc.c +++ b/drivers/acpi/acpi_pcc.c @@ -52,7 +52,7 @@ acpi_pcc_address_space_setup(acpi_handle region_handle, u32 function, struct pcc_data *data; struct acpi_pcc_info *ctx = handler_context; struct pcc_mbox_chan *pcc_chan; - static acpi_status ret; + acpi_status ret; data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index 3bdeeee3414e..e66e20d1f31b 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -1366,7 +1366,8 @@ int cppc_get_perf_caps(int cpunum, struct cppc_perf_caps *perf_caps) /* Are any of the regs PCC ?*/ if (CPC_IN_PCC(highest_reg) || CPC_IN_PCC(lowest_reg) || CPC_IN_PCC(lowest_non_linear_reg) || CPC_IN_PCC(nominal_reg) || - CPC_IN_PCC(low_freq_reg) || CPC_IN_PCC(nom_freq_reg)) { + CPC_IN_PCC(low_freq_reg) || CPC_IN_PCC(nom_freq_reg) || + CPC_IN_PCC(guaranteed_reg)) { if (pcc_ss_id < 0) { pr_debug("Invalid pcc_ss_id\n"); return -ENODEV; diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 84676cc24221..0ee8ea971aa4 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -1868,16 +1868,18 @@ void pm_runtime_init(struct device *dev) */ void pm_runtime_reinit(struct device *dev) { - if (!pm_runtime_enabled(dev)) { - if (dev->power.runtime_status == RPM_ACTIVE) - pm_runtime_set_suspended(dev); - if (dev->power.irq_safe) { - spin_lock_irq(&dev->power.lock); - dev->power.irq_safe = 0; - spin_unlock_irq(&dev->power.lock); - if (dev->parent) - pm_runtime_put(dev->parent); - } + if (pm_runtime_enabled(dev)) + return; + + if (dev->power.runtime_status == RPM_ACTIVE) + pm_runtime_set_suspended(dev); + + if (dev->power.irq_safe) { + spin_lock_irq(&dev->power.lock); + dev->power.irq_safe = 0; + spin_unlock_irq(&dev->power.lock); + if (dev->parent) + pm_runtime_put(dev->parent); } /* * Clear power.needs_force_resume in case it has been set by diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 272bc608e528..32a3a5b13802 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1082,7 +1082,7 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode, /* Order wrt reading lo_state in loop_validate_file(). */ wmb(); - lo->lo_state = Lo_bound; + WRITE_ONCE(lo->lo_state, Lo_bound); if (part_shift) lo->lo_flags |= LO_FLAGS_PARTSCAN; partscan = lo->lo_flags & LO_FLAGS_PARTSCAN; @@ -1179,7 +1179,7 @@ static void __loop_clr_fd(struct loop_device *lo) if (!part_shift) set_bit(GD_SUPPRESS_PART_SCAN, &lo->lo_disk->state); mutex_lock(&lo->lo_mutex); - lo->lo_state = Lo_unbound; + WRITE_ONCE(lo->lo_state, Lo_unbound); mutex_unlock(&lo->lo_mutex); /* @@ -1218,7 +1218,7 @@ static int loop_clr_fd(struct loop_device *lo) lo->lo_flags |= LO_FLAGS_AUTOCLEAR; if (disk_openers(lo->lo_disk) == 1) - lo->lo_state = Lo_rundown; + WRITE_ONCE(lo->lo_state, Lo_rundown); loop_global_unlock(lo, true); return 0; @@ -1743,7 +1743,7 @@ static void lo_release(struct gendisk *disk) mutex_lock(&lo->lo_mutex); if (lo->lo_state == Lo_bound && (lo->lo_flags & LO_FLAGS_AUTOCLEAR)) - lo->lo_state = Lo_rundown; + WRITE_ONCE(lo->lo_state, Lo_rundown); need_clear = (lo->lo_state == Lo_rundown); mutex_unlock(&lo->lo_mutex); @@ -1858,7 +1858,7 @@ static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx, blk_mq_start_request(rq); - if (lo->lo_state != Lo_bound) + if (data_race(READ_ONCE(lo->lo_state)) != Lo_bound) return BLK_STS_IOERR; switch (req_op(rq)) { @@ -2016,7 +2016,7 @@ static int loop_add(int i) lo->worker_tree = RB_ROOT; INIT_LIST_HEAD(&lo->idle_worker_list); timer_setup(&lo->timer, loop_free_idle_workers_timer, TIMER_DEFERRABLE); - lo->lo_state = Lo_unbound; + WRITE_ONCE(lo->lo_state, Lo_unbound); err = mutex_lock_killable(&loop_ctl_mutex); if (err) @@ -2174,7 +2174,7 @@ static int loop_control_remove(int idx) goto mark_visible; } /* Mark this loop device as no more bound, but not quite unbound yet */ - lo->lo_state = Lo_deleting; + WRITE_ONCE(lo->lo_state, Lo_deleting); mutex_unlock(&lo->lo_mutex); loop_remove(lo); @@ -2197,8 +2197,12 @@ static int loop_control_get_free(int idx) if (ret) return ret; idr_for_each_entry(&loop_index_idr, lo, id) { - /* Hitting a race results in creating a new loop device which is harmless. */ - if (lo->idr_visible && data_race(lo->lo_state) == Lo_unbound) + /* + * Hitting a race results in creating a new loop device + * which is harmless. + */ + if (lo->idr_visible && + data_race(READ_ONCE(lo->lo_state)) == Lo_unbound) goto found; } mutex_unlock(&loop_ctl_mutex); diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c index f1409e54010a..d1c354636315 100644 --- a/drivers/block/rnbd/rnbd-clt.c +++ b/drivers/block/rnbd/rnbd-clt.c @@ -1423,9 +1423,11 @@ static struct rnbd_clt_dev *init_dev(struct rnbd_clt_session *sess, goto out_alloc; } - ret = ida_alloc_max(&index_ida, (1 << (MINORBITS - RNBD_PART_BITS)) - 1, - GFP_KERNEL); - if (ret < 0) { + dev->clt_device_id = ida_alloc_max(&index_ida, + (1 << (MINORBITS - RNBD_PART_BITS)) - 1, + GFP_KERNEL); + if (dev->clt_device_id < 0) { + ret = dev->clt_device_id; pr_err("Failed to initialize device '%s' from session %s, allocating idr failed, err: %d\n", pathname, sess->sessname, ret); goto out_queues; @@ -1434,10 +1436,9 @@ static struct rnbd_clt_dev *init_dev(struct rnbd_clt_session *sess, dev->pathname = kstrdup(pathname, GFP_KERNEL); if (!dev->pathname) { ret = -ENOMEM; - goto out_queues; + goto out_ida; } - dev->clt_device_id = ret; dev->sess = sess; dev->access_mode = access_mode; dev->nr_poll_queues = nr_poll_queues; @@ -1453,6 +1454,8 @@ static struct rnbd_clt_dev *init_dev(struct rnbd_clt_session *sess, return dev; +out_ida: + ida_free(&index_ida, dev->clt_device_id); out_queues: kfree(dev->hw_queues); out_alloc: diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index df9831783a13..cfd2132410dd 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -1080,12 +1080,20 @@ static inline struct ublk_uring_cmd_pdu *ublk_get_uring_cmd_pdu( return io_uring_cmd_to_pdu(ioucmd, struct ublk_uring_cmd_pdu); } +static void ublk_end_request(struct request *req, blk_status_t error) +{ + local_bh_disable(); + blk_mq_end_request(req, error); + local_bh_enable(); +} + /* todo: handle partial completion */ static inline void __ublk_complete_rq(struct request *req, struct ublk_io *io, bool need_map) { unsigned int unmapped_bytes; blk_status_t res = BLK_STS_OK; + bool requeue; /* failed read IO if nothing is read */ if (!io->res && req_op(req) == REQ_OP_READ) @@ -1117,14 +1125,30 @@ static inline void __ublk_complete_rq(struct request *req, struct ublk_io *io, if (unlikely(unmapped_bytes < io->res)) io->res = unmapped_bytes; - if (blk_update_request(req, BLK_STS_OK, io->res)) + /* + * Run bio->bi_end_io() with softirqs disabled. If the final fput + * happens off this path, then that will prevent ublk's blkdev_release() + * from being called on current's task work, see fput() implementation. + * + * Otherwise, ublk server may not provide forward progress in case of + * reading the partition table from bdev_open() with disk->open_mutex + * held, and causes dead lock as we could already be holding + * disk->open_mutex here. + * + * Preferably we would not be doing IO with a mutex held that is also + * used for release, but this work-around will suffice for now. + */ + local_bh_disable(); + requeue = blk_update_request(req, BLK_STS_OK, io->res); + local_bh_enable(); + if (requeue) blk_mq_requeue_request(req, true); else if (likely(!blk_should_fake_timeout(req->q))) __blk_mq_end_request(req, BLK_STS_OK); return; exit: - blk_mq_end_request(req, res); + ublk_end_request(req, res); } static struct io_uring_cmd *__ublk_prep_compl_io_cmd(struct ublk_io *io, @@ -1164,7 +1188,7 @@ static inline void __ublk_abort_rq(struct ublk_queue *ubq, if (ublk_nosrv_dev_should_queue_io(ubq->dev)) blk_mq_requeue_request(rq, false); else - blk_mq_end_request(rq, BLK_STS_IOERR); + ublk_end_request(rq, BLK_STS_IOERR); } static void @@ -1209,7 +1233,7 @@ __ublk_do_auto_buf_reg(const struct ublk_queue *ubq, struct request *req, ublk_auto_buf_reg_fallback(ubq, req->tag); return AUTO_BUF_REG_FALLBACK; } - blk_mq_end_request(req, BLK_STS_IOERR); + ublk_end_request(req, BLK_STS_IOERR); return AUTO_BUF_REG_FAIL; } diff --git a/drivers/block/zloop.c b/drivers/block/zloop.c index 77bd6081b244..8e334f5025fc 100644 --- a/drivers/block/zloop.c +++ b/drivers/block/zloop.c @@ -697,7 +697,7 @@ static blk_status_t zloop_queue_rq(struct blk_mq_hw_ctx *hctx, struct zloop_cmd *cmd = blk_mq_rq_to_pdu(rq); struct zloop_device *zlo = rq->q->queuedata; - if (zlo->state == Zlo_deleting) + if (data_race(READ_ONCE(zlo->state)) == Zlo_deleting) return BLK_STS_IOERR; /* @@ -1002,7 +1002,7 @@ static int zloop_ctl_add(struct zloop_options *opts) ret = -ENOMEM; goto out; } - zlo->state = Zlo_creating; + WRITE_ONCE(zlo->state, Zlo_creating); ret = mutex_lock_killable(&zloop_ctl_mutex); if (ret) @@ -1113,7 +1113,7 @@ static int zloop_ctl_add(struct zloop_options *opts) } mutex_lock(&zloop_ctl_mutex); - zlo->state = Zlo_live; + WRITE_ONCE(zlo->state, Zlo_live); mutex_unlock(&zloop_ctl_mutex); pr_info("zloop: device %d, %u zones of %llu MiB, %u B block size\n", @@ -1177,7 +1177,7 @@ static int zloop_ctl_remove(struct zloop_options *opts) ret = -EINVAL; } else { idr_remove(&zloop_index_idr, zlo->id); - zlo->state = Zlo_deleting; + WRITE_ONCE(zlo->state, Zlo_deleting); } mutex_unlock(&zloop_ctl_mutex); diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h index 25044d28f28a..b742ef1adb35 100644 --- a/drivers/iommu/amd/amd_iommu.h +++ b/drivers/iommu/amd/amd_iommu.h @@ -173,6 +173,11 @@ static inline struct protection_domain *to_pdomain(struct iommu_domain *dom) bool translation_pre_enabled(struct amd_iommu *iommu); int __init add_special_device(u8 type, u8 id, u32 *devid, bool cmd_line); +int amd_iommu_pdom_id_alloc(void); +int amd_iommu_pdom_id_reserve(u16 id, gfp_t gfp); +void amd_iommu_pdom_id_free(int id); +void amd_iommu_pdom_id_destroy(void); + #ifdef CONFIG_DMI void amd_iommu_apply_ivrs_quirks(void); #else diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 4b2953418977..384c90b4f90a 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -1136,8 +1136,11 @@ static void set_dte_bit(struct dev_table_entry *dte, u8 bit) static bool __reuse_device_table(struct amd_iommu *iommu) { struct amd_iommu_pci_seg *pci_seg = iommu->pci_seg; - u32 lo, hi, old_devtb_size; + struct dev_table_entry *old_dev_tbl_entry; + u32 lo, hi, old_devtb_size, devid; phys_addr_t old_devtb_phys; + u16 dom_id; + bool dte_v; u64 entry; /* Each IOMMU use separate device table with the same size */ @@ -1173,6 +1176,22 @@ static bool __reuse_device_table(struct amd_iommu *iommu) return false; } + for (devid = 0; devid <= pci_seg->last_bdf; devid++) { + old_dev_tbl_entry = &pci_seg->old_dev_tbl_cpy[devid]; + dte_v = FIELD_GET(DTE_FLAG_V, old_dev_tbl_entry->data[0]); + dom_id = FIELD_GET(DEV_DOMID_MASK, old_dev_tbl_entry->data[1]); + + if (!dte_v || !dom_id) + continue; + /* + * ID reservation can fail with -ENOSPC when there + * are multiple devices present in the same domain, + * hence check only for -ENOMEM. + */ + if (amd_iommu_pdom_id_reserve(dom_id, GFP_KERNEL) == -ENOMEM) + return false; + } + return true; } @@ -3127,8 +3146,7 @@ static bool __init check_ioapic_information(void) static void __init free_dma_resources(void) { - ida_destroy(&pdom_ids); - + amd_iommu_pdom_id_destroy(); free_unity_maps(); } diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 9f1d56a5e145..5d45795c367a 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -1811,17 +1811,26 @@ int amd_iommu_complete_ppr(struct device *dev, u32 pasid, int status, int tag) * contain. * ****************************************************************************/ - -static int pdom_id_alloc(void) +int amd_iommu_pdom_id_alloc(void) { return ida_alloc_range(&pdom_ids, 1, MAX_DOMAIN_ID - 1, GFP_ATOMIC); } -static void pdom_id_free(int id) +int amd_iommu_pdom_id_reserve(u16 id, gfp_t gfp) +{ + return ida_alloc_range(&pdom_ids, id, id, gfp); +} + +void amd_iommu_pdom_id_free(int id) { ida_free(&pdom_ids, id); } +void amd_iommu_pdom_id_destroy(void) +{ + ida_destroy(&pdom_ids); +} + static void free_gcr3_tbl_level1(u64 *tbl) { u64 *ptr; @@ -1864,7 +1873,7 @@ static void free_gcr3_table(struct gcr3_tbl_info *gcr3_info) gcr3_info->glx = 0; /* Free per device domain ID */ - pdom_id_free(gcr3_info->domid); + amd_iommu_pdom_id_free(gcr3_info->domid); iommu_free_pages(gcr3_info->gcr3_tbl); gcr3_info->gcr3_tbl = NULL; @@ -1900,14 +1909,14 @@ static int setup_gcr3_table(struct gcr3_tbl_info *gcr3_info, return -EBUSY; /* Allocate per device domain ID */ - domid = pdom_id_alloc(); + domid = amd_iommu_pdom_id_alloc(); if (domid <= 0) return -ENOSPC; gcr3_info->domid = domid; gcr3_info->gcr3_tbl = iommu_alloc_pages_node_sz(nid, GFP_ATOMIC, SZ_4K); if (gcr3_info->gcr3_tbl == NULL) { - pdom_id_free(domid); + amd_iommu_pdom_id_free(domid); return -ENOMEM; } @@ -2503,7 +2512,7 @@ struct protection_domain *protection_domain_alloc(void) if (!domain) return NULL; - domid = pdom_id_alloc(); + domid = amd_iommu_pdom_id_alloc(); if (domid <= 0) { kfree(domain); return NULL; @@ -2802,7 +2811,7 @@ void amd_iommu_domain_free(struct iommu_domain *dom) WARN_ON(!list_empty(&domain->dev_list)); pt_iommu_deinit(&domain->iommu); - pdom_id_free(domain->id); + amd_iommu_pdom_id_free(domain->id); kfree(domain); } @@ -2853,7 +2862,7 @@ void amd_iommu_init_identity_domain(void) domain->ops = &identity_domain_ops; domain->owner = &amd_iommu_ops; - identity_domain.id = pdom_id_alloc(); + identity_domain.id = amd_iommu_pdom_id_alloc(); protection_domain_init(&identity_domain); } diff --git a/drivers/iommu/generic_pt/iommu_pt.h b/drivers/iommu/generic_pt/iommu_pt.h index 97aeda1ad01c..3327116a441c 100644 --- a/drivers/iommu/generic_pt/iommu_pt.h +++ b/drivers/iommu/generic_pt/iommu_pt.h @@ -372,6 +372,9 @@ static inline struct pt_table_p *_table_alloc(struct pt_common *common, table_mem = iommu_alloc_pages_node_sz(iommu_table->nid, gfp, log2_to_int(lg2sz)); + if (!table_mem) + return ERR_PTR(-ENOMEM); + if (pt_feature(common, PT_FEAT_DMA_INCOHERENT) && mode == ALLOC_NORMAL) { int ret = iommu_pages_start_incoherent( diff --git a/drivers/iommu/iommufd/io_pagetable.c b/drivers/iommu/iommufd/io_pagetable.c index 54cf4d856179..436992331111 100644 --- a/drivers/iommu/iommufd/io_pagetable.c +++ b/drivers/iommu/iommufd/io_pagetable.c @@ -495,7 +495,11 @@ int iopt_map_file_pages(struct iommufd_ctx *ictx, struct io_pagetable *iopt, return -EOVERFLOW; start_byte = start - ALIGN_DOWN(start, PAGE_SIZE); - dmabuf = dma_buf_get(fd); + if (IS_ENABLED(CONFIG_DMA_SHARED_BUFFER)) + dmabuf = dma_buf_get(fd); + else + dmabuf = ERR_PTR(-ENXIO); + if (!IS_ERR(dmabuf)) { pages = iopt_alloc_dmabuf_pages(ictx, dmabuf, start_byte, start, length, diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c index c4322fd26f93..550ff36dec3a 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -1184,14 +1184,20 @@ static int iommufd_test_add_reserved(struct iommufd_ucmd *ucmd, unsigned int mockpt_id, unsigned long start, size_t length) { + unsigned long last; struct iommufd_ioas *ioas; int rc; + if (!length) + return -EINVAL; + if (check_add_overflow(start, length - 1, &last)) + return -EOVERFLOW; + ioas = iommufd_get_ioas(ucmd->ictx, mockpt_id); if (IS_ERR(ioas)) return PTR_ERR(ioas); down_write(&ioas->iopt.iova_rwsem); - rc = iopt_reserve_iova(&ioas->iopt, start, start + length - 1, NULL); + rc = iopt_reserve_iova(&ioas->iopt, start, last, NULL); up_write(&ioas->iopt.iova_rwsem); iommufd_put_object(ucmd->ictx, &ioas->obj); return rc; @@ -1215,8 +1221,10 @@ static int iommufd_test_md_check_pa(struct iommufd_ucmd *ucmd, page_size = 1 << __ffs(mock->domain.pgsize_bitmap); if (iova % page_size || length % page_size || (uintptr_t)uptr % page_size || - check_add_overflow((uintptr_t)uptr, (uintptr_t)length, &end)) - return -EINVAL; + check_add_overflow((uintptr_t)uptr, (uintptr_t)length, &end)) { + rc = -EINVAL; + goto out_put; + } for (; length; length -= page_size) { struct page *pages[1]; diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig index e15e320db476..cfaea6178a71 100644 --- a/drivers/net/can/Kconfig +++ b/drivers/net/can/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only menuconfig CAN_DEV - tristate "CAN Device Drivers" + bool "CAN Device Drivers" default y depends on CAN help @@ -17,10 +17,7 @@ menuconfig CAN_DEV virtual ones. If you own such devices or plan to use the virtual CAN interfaces to develop applications, say Y here. - To compile as a module, choose M here: the module will be called - can-dev. - -if CAN_DEV +if CAN_DEV && CAN config CAN_VCAN tristate "Virtual Local CAN Interface (vcan)" diff --git a/drivers/net/can/Makefile b/drivers/net/can/Makefile index d7bc10a6b8ea..37e2f1a2faec 100644 --- a/drivers/net/can/Makefile +++ b/drivers/net/can/Makefile @@ -7,7 +7,7 @@ obj-$(CONFIG_CAN_VCAN) += vcan.o obj-$(CONFIG_CAN_VXCAN) += vxcan.o obj-$(CONFIG_CAN_SLCAN) += slcan/ -obj-y += dev/ +obj-$(CONFIG_CAN_DEV) += dev/ obj-y += esd/ obj-y += rcar/ obj-y += rockchip/ diff --git a/drivers/net/can/dev/Makefile b/drivers/net/can/dev/Makefile index 633687d6b6c0..64226acf0f3d 100644 --- a/drivers/net/can/dev/Makefile +++ b/drivers/net/can/dev/Makefile @@ -1,9 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_CAN_DEV) += can-dev.o - -can-dev-y += skb.o +obj-$(CONFIG_CAN) += can-dev.o +can-dev-$(CONFIG_CAN_DEV) += skb.o can-dev-$(CONFIG_CAN_CALC_BITTIMING) += calc_bittiming.o can-dev-$(CONFIG_CAN_NETLINK) += bittiming.o can-dev-$(CONFIG_CAN_NETLINK) += dev.o diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index e29e85b67fd4..a0233e550a5a 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -1074,7 +1074,7 @@ out_usb_free_urb: usb_free_urb(urb); out_usb_kill_anchored_urbs: if (!parent->active_channels) { - usb_kill_anchored_urbs(&dev->tx_submitted); + usb_kill_anchored_urbs(&parent->rx_submitted); if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP) gs_usb_timestamp_stop(parent); diff --git a/drivers/net/dsa/lantiq/lantiq_gswip.c b/drivers/net/dsa/lantiq/lantiq_gswip.c index 57dd063c0740..b094001a7c80 100644 --- a/drivers/net/dsa/lantiq/lantiq_gswip.c +++ b/drivers/net/dsa/lantiq/lantiq_gswip.c @@ -444,9 +444,6 @@ static void gswip_remove(struct platform_device *pdev) if (!priv) return; - /* disable the switch */ - gswip_disable_switch(priv); - dsa_unregister_switch(priv->ds); for (i = 0; i < priv->num_gphy_fw; i++) diff --git a/drivers/net/dsa/lantiq/lantiq_gswip.h b/drivers/net/dsa/lantiq/lantiq_gswip.h index 9c38e51a75e8..2e0f2afbadbb 100644 --- a/drivers/net/dsa/lantiq/lantiq_gswip.h +++ b/drivers/net/dsa/lantiq/lantiq_gswip.h @@ -294,8 +294,6 @@ struct gswip_priv { u16 version; }; -void gswip_disable_switch(struct gswip_priv *priv); - int gswip_probe_common(struct gswip_priv *priv, u32 version); #endif /* __LANTIQ_GSWIP_H */ diff --git a/drivers/net/dsa/lantiq/lantiq_gswip_common.c b/drivers/net/dsa/lantiq/lantiq_gswip_common.c index 9da39edf8f57..e790f2ef7588 100644 --- a/drivers/net/dsa/lantiq/lantiq_gswip_common.c +++ b/drivers/net/dsa/lantiq/lantiq_gswip_common.c @@ -752,6 +752,13 @@ static int gswip_setup(struct dsa_switch *ds) return 0; } +static void gswip_teardown(struct dsa_switch *ds) +{ + struct gswip_priv *priv = ds->priv; + + regmap_clear_bits(priv->mdio, GSWIP_MDIO_GLOB, GSWIP_MDIO_GLOB_ENABLE); +} + static enum dsa_tag_protocol gswip_get_tag_protocol(struct dsa_switch *ds, int port, enum dsa_tag_protocol mp) @@ -1629,6 +1636,7 @@ static const struct phylink_mac_ops gswip_phylink_mac_ops = { static const struct dsa_switch_ops gswip_switch_ops = { .get_tag_protocol = gswip_get_tag_protocol, .setup = gswip_setup, + .teardown = gswip_teardown, .port_setup = gswip_port_setup, .port_enable = gswip_port_enable, .port_disable = gswip_port_disable, @@ -1656,12 +1664,6 @@ static const struct dsa_switch_ops gswip_switch_ops = { .port_hsr_leave = dsa_port_simple_hsr_leave, }; -void gswip_disable_switch(struct gswip_priv *priv) -{ - regmap_clear_bits(priv->mdio, GSWIP_MDIO_GLOB, GSWIP_MDIO_GLOB_ENABLE); -} -EXPORT_SYMBOL_GPL(gswip_disable_switch); - static int gswip_validate_cpu_port(struct dsa_switch *ds) { struct gswip_priv *priv = ds->priv; @@ -1718,15 +1720,14 @@ int gswip_probe_common(struct gswip_priv *priv, u32 version) err = gswip_validate_cpu_port(priv->ds); if (err) - goto disable_switch; + goto unregister_switch; dev_info(priv->dev, "probed GSWIP version %lx mod %lx\n", GSWIP_VERSION_REV(version), GSWIP_VERSION_MOD(version)); return 0; -disable_switch: - gswip_disable_switch(priv); +unregister_switch: dsa_unregister_switch(priv->ds); return err; diff --git a/drivers/net/dsa/lantiq/mxl-gsw1xx.c b/drivers/net/dsa/lantiq/mxl-gsw1xx.c index 0816c61a47f1..f8ff8a604bf5 100644 --- a/drivers/net/dsa/lantiq/mxl-gsw1xx.c +++ b/drivers/net/dsa/lantiq/mxl-gsw1xx.c @@ -11,10 +11,12 @@ #include <linux/bits.h> #include <linux/delay.h> +#include <linux/jiffies.h> #include <linux/module.h> #include <linux/of_device.h> #include <linux/of_mdio.h> #include <linux/regmap.h> +#include <linux/workqueue.h> #include <net/dsa.h> #include "lantiq_gswip.h" @@ -29,6 +31,7 @@ struct gsw1xx_priv { struct regmap *clk; struct regmap *shell; struct phylink_pcs pcs; + struct delayed_work clear_raneg; phy_interface_t tbi_interface; struct gswip_priv gswip; }; @@ -145,7 +148,9 @@ static void gsw1xx_pcs_disable(struct phylink_pcs *pcs) { struct gsw1xx_priv *priv = pcs_to_gsw1xx(pcs); - /* Assert SGMII shell reset */ + cancel_delayed_work_sync(&priv->clear_raneg); + + /* Assert SGMII shell reset (will also clear RANEG bit) */ regmap_set_bits(priv->shell, GSW1XX_SHELL_RST_REQ, GSW1XX_RST_REQ_SGMII_SHELL); @@ -255,10 +260,16 @@ static int gsw1xx_pcs_reset(struct gsw1xx_priv *priv) FIELD_PREP(GSW1XX_SGMII_PHY_RX0_CFG2_FILT_CNT, GSW1XX_SGMII_PHY_RX0_CFG2_FILT_CNT_DEF); - /* TODO: Take care of inverted RX pair once generic property is + /* RX lane seems to be inverted internally, so bit + * GSW1XX_SGMII_PHY_RX0_CFG2_INVERT needs to be set for normal + * (ie. non-inverted) operation. + * + * TODO: Take care of inverted RX pair once generic property is * available */ + val |= GSW1XX_SGMII_PHY_RX0_CFG2_INVERT; + ret = regmap_write(priv->sgmii, GSW1XX_SGMII_PHY_RX0_CFG2, val); if (ret < 0) return ret; @@ -422,12 +433,29 @@ static int gsw1xx_pcs_config(struct phylink_pcs *pcs, unsigned int neg_mode, return 0; } +static void gsw1xx_pcs_clear_raneg(struct work_struct *work) +{ + struct gsw1xx_priv *priv = + container_of(work, struct gsw1xx_priv, clear_raneg.work); + + regmap_clear_bits(priv->sgmii, GSW1XX_SGMII_TBI_ANEGCTL, + GSW1XX_SGMII_TBI_ANEGCTL_RANEG); +} + static void gsw1xx_pcs_an_restart(struct phylink_pcs *pcs) { struct gsw1xx_priv *priv = pcs_to_gsw1xx(pcs); + cancel_delayed_work_sync(&priv->clear_raneg); + regmap_set_bits(priv->sgmii, GSW1XX_SGMII_TBI_ANEGCTL, GSW1XX_SGMII_TBI_ANEGCTL_RANEG); + + /* despite being documented as self-clearing, the RANEG bit + * sometimes remains set, preventing auto-negotiation from happening. + * MaxLinear advises to manually clear the bit after 10ms. + */ + schedule_delayed_work(&priv->clear_raneg, msecs_to_jiffies(10)); } static void gsw1xx_pcs_link_up(struct phylink_pcs *pcs, @@ -630,6 +658,8 @@ static int gsw1xx_probe(struct mdio_device *mdiodev) if (ret) return ret; + INIT_DELAYED_WORK(&priv->clear_raneg, gsw1xx_pcs_clear_raneg); + ret = gswip_probe_common(&priv->gswip, version); if (ret) return ret; @@ -642,25 +672,31 @@ static int gsw1xx_probe(struct mdio_device *mdiodev) static void gsw1xx_remove(struct mdio_device *mdiodev) { struct gswip_priv *priv = dev_get_drvdata(&mdiodev->dev); + struct gsw1xx_priv *gsw1xx_priv; if (!priv) return; - gswip_disable_switch(priv); - dsa_unregister_switch(priv->ds); + + gsw1xx_priv = container_of(priv, struct gsw1xx_priv, gswip); + cancel_delayed_work_sync(&gsw1xx_priv->clear_raneg); } static void gsw1xx_shutdown(struct mdio_device *mdiodev) { struct gswip_priv *priv = dev_get_drvdata(&mdiodev->dev); + struct gsw1xx_priv *gsw1xx_priv; if (!priv) return; + dsa_switch_shutdown(priv->ds); + dev_set_drvdata(&mdiodev->dev, NULL); - gswip_disable_switch(priv); + gsw1xx_priv = container_of(priv, struct gsw1xx_priv, gswip); + cancel_delayed_work_sync(&gsw1xx_priv->clear_raneg); } static const struct gswip_hw_info gsw12x_data = { diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c index 888f28f11406..90df02e0039c 100644 --- a/drivers/net/ethernet/broadcom/b44.c +++ b/drivers/net/ethernet/broadcom/b44.c @@ -1790,6 +1790,9 @@ static int b44_nway_reset(struct net_device *dev) u32 bmcr; int r; + if (bp->flags & B44_FLAG_EXTERNAL_PHY) + return phy_ethtool_nway_reset(dev); + spin_lock_irq(&bp->lock); b44_readphy(bp, MII_BMCR, &bmcr); b44_readphy(bp, MII_BMCR, &bmcr); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index 3e77a96e5a3e..c94a391b1ba5 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -268,13 +268,11 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, case XDP_TX: rx_buf = &rxr->rx_buf_ring[cons]; mapping = rx_buf->mapping - bp->rx_dma_offset; - *event &= BNXT_TX_CMP_EVENT; if (unlikely(xdp_buff_has_frags(xdp))) { struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); tx_needed += sinfo->nr_frags; - *event = BNXT_AGG_EVENT; } if (tx_avail < tx_needed) { @@ -287,6 +285,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, dma_sync_single_for_device(&pdev->dev, mapping + offset, *len, bp->rx_dir); + *event &= ~BNXT_RX_EVENT; *event |= BNXT_TX_EVENT; __bnxt_xmit_xdp(bp, txr, mapping + offset, *len, NEXT_RX(rxr->rx_prod), xdp); diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index d5e5800b84ef..53b26cece16a 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -1787,7 +1787,8 @@ int enetc_xdp_xmit(struct net_device *ndev, int num_frames, int xdp_tx_bd_cnt, i, k; int xdp_tx_frm_cnt = 0; - if (unlikely(test_bit(ENETC_TX_DOWN, &priv->flags))) + if (unlikely(test_bit(ENETC_TX_DOWN, &priv->flags) || + !netif_carrier_ok(ndev))) return -ENETDOWN; enetc_lock_mdio(); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index c685a5c0cc51..a753265961af 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3933,7 +3933,12 @@ static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep, txq->bd.cur = bdp; /* Trigger transmission start */ - writel(0, txq->bd.reg_desc_active); + if (!(fep->quirks & FEC_QUIRK_ERR007885) || + !readl(txq->bd.reg_desc_active) || + !readl(txq->bd.reg_desc_active) || + !readl(txq->bd.reg_desc_active) || + !readl(txq->bd.reg_desc_active)) + writel(0, txq->bd.reg_desc_active); return 0; } diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index a5a2b18d309b..a7a088a77f37 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -647,12 +647,9 @@ static int gve_setup_device_resources(struct gve_priv *priv) err = gve_alloc_counter_array(priv); if (err) goto abort_with_rss_config_cache; - err = gve_init_clock(priv); - if (err) - goto abort_with_counter; err = gve_alloc_notify_blocks(priv); if (err) - goto abort_with_clock; + goto abort_with_counter; err = gve_alloc_stats_report(priv); if (err) goto abort_with_ntfy_blocks; @@ -683,10 +680,16 @@ static int gve_setup_device_resources(struct gve_priv *priv) } } + err = gve_init_clock(priv); + if (err) { + dev_err(&priv->pdev->dev, "Failed to init clock"); + goto abort_with_ptype_lut; + } + err = gve_init_rss_config(priv, priv->rx_cfg.num_queues); if (err) { dev_err(&priv->pdev->dev, "Failed to init RSS config"); - goto abort_with_ptype_lut; + goto abort_with_clock; } err = gve_adminq_report_stats(priv, priv->stats_report_len, @@ -698,6 +701,8 @@ static int gve_setup_device_resources(struct gve_priv *priv) gve_set_device_resources_ok(priv); return 0; +abort_with_clock: + gve_teardown_clock(priv); abort_with_ptype_lut: kvfree(priv->ptype_lut_dqo); priv->ptype_lut_dqo = NULL; @@ -705,8 +710,6 @@ abort_with_stats_report: gve_free_stats_report(priv); abort_with_ntfy_blocks: gve_free_notify_blocks(priv); -abort_with_clock: - gve_teardown_clock(priv); abort_with_counter: gve_free_counter_array(priv); abort_with_rss_config_cache: diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index cf8abbe01840..c589baea7c77 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -10555,6 +10555,9 @@ int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto, bool writen_to_tbl = false; int ret = 0; + if (vlan_id >= VLAN_N_VID) + return -EINVAL; + /* When device is resetting or reset failed, firmware is unable to * handle mailbox. Just record the vlan id, and remove it after * reset finished. diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index c7ff12a6c076..b7d4e06a55d4 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -193,10 +193,10 @@ static int hclge_get_ring_chain_from_mbx( return -EINVAL; for (i = 0; i < ring_num; i++) { - if (req->msg.param[i].tqp_index >= vport->nic.kinfo.rss_size) { + if (req->msg.param[i].tqp_index >= vport->nic.kinfo.num_tqps) { dev_err(&hdev->pdev->dev, "tqp index(%u) is out of range(0-%u)\n", req->msg.param[i].tqp_index, - vport->nic.kinfo.rss_size - 1U); + vport->nic.kinfo.num_tqps - 1U); return -EINVAL; } } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 8fcf220a120d..70327a73dee3 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -368,12 +368,12 @@ static int hclgevf_knic_setup(struct hclgevf_dev *hdev) new_tqps = kinfo->rss_size * num_tc; kinfo->num_tqps = min(new_tqps, hdev->num_tqps); - kinfo->tqp = devm_kcalloc(&hdev->pdev->dev, kinfo->num_tqps, + kinfo->tqp = devm_kcalloc(&hdev->pdev->dev, hdev->num_tqps, sizeof(struct hnae3_queue *), GFP_KERNEL); if (!kinfo->tqp) return -ENOMEM; - for (i = 0; i < kinfo->num_tqps; i++) { + for (i = 0; i < hdev->num_tqps; i++) { hdev->htqp[i].q.handle = &hdev->nic; hdev->htqp[i].q.tqp_index = i; kinfo->tqp[i] = &hdev->htqp[i].q; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index 887adf4807d1..ea77fbd98396 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -197,6 +197,11 @@ static int mlx5_devlink_reload_down(struct devlink *devlink, bool netns_change, struct pci_dev *pdev = dev->pdev; int ret = 0; + if (mlx5_fw_reset_in_progress(dev)) { + NL_SET_ERR_MSG_MOD(extack, "Can't reload during firmware reset"); + return -EBUSY; + } + if (mlx5_dev_is_lightweight(dev)) { if (action != DEVLINK_RELOAD_ACTION_DRIVER_REINIT) return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index 7bcf822a89f9..6b4ec457ce22 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -33,6 +33,7 @@ #include "lib/eq.h" #include "fw_tracer.h" #include "fw_tracer_tracepoint.h" +#include <linux/ctype.h> static int mlx5_query_mtrc_caps(struct mlx5_fw_tracer *tracer) { @@ -358,6 +359,47 @@ static const char *VAL_PARM = "%llx"; static const char *REPLACE_64_VAL_PARM = "%x%x"; static const char *PARAM_CHAR = "%"; +static bool mlx5_is_valid_spec(const char *str) +{ + /* Parse format specifiers to find the actual type. + * Structure: %[flags][width][.precision][length]type + * Skip flags, width, precision & length. + */ + while (isdigit(*str) || *str == '#' || *str == '.' || *str == 'l') + str++; + + /* Check if it's a valid integer/hex specifier or %%: + * Valid formats: %x, %d, %i, %u, etc. + */ + if (*str != 'x' && *str != 'X' && *str != 'd' && *str != 'i' && + *str != 'u' && *str != 'c' && *str != '%') + return false; + + return true; +} + +static bool mlx5_tracer_validate_params(const char *str) +{ + const char *substr = str; + + if (!str) + return false; + + substr = strstr(substr, PARAM_CHAR); + while (substr) { + if (!mlx5_is_valid_spec(substr + 1)) + return false; + + if (*(substr + 1) == '%') + substr = strstr(substr + 2, PARAM_CHAR); + else + substr = strstr(substr + 1, PARAM_CHAR); + + } + + return true; +} + static int mlx5_tracer_message_hash(u32 message_id) { return jhash_1word(message_id, 0) & (MESSAGE_HASH_SIZE - 1); @@ -419,6 +461,10 @@ static int mlx5_tracer_get_num_of_params(char *str) char *substr, *pstr = str; int num_of_params = 0; + /* Validate that all parameters are valid before processing */ + if (!mlx5_tracer_validate_params(str)) + return -EINVAL; + /* replace %llx with %x%x */ substr = strstr(pstr, VAL_PARM); while (substr) { @@ -427,11 +473,15 @@ static int mlx5_tracer_get_num_of_params(char *str) substr = strstr(pstr, VAL_PARM); } - /* count all the % characters */ + /* count all the % characters, but skip %% (escaped percent) */ substr = strstr(str, PARAM_CHAR); while (substr) { - num_of_params += 1; - str = substr + 1; + if (*(substr + 1) != '%') { + num_of_params += 1; + str = substr + 1; + } else { + str = substr + 2; + } substr = strstr(str, PARAM_CHAR); } @@ -570,14 +620,17 @@ void mlx5_tracer_print_trace(struct tracer_string_format *str_frmt, { char tmp[512]; - snprintf(tmp, sizeof(tmp), str_frmt->string, - str_frmt->params[0], - str_frmt->params[1], - str_frmt->params[2], - str_frmt->params[3], - str_frmt->params[4], - str_frmt->params[5], - str_frmt->params[6]); + if (str_frmt->invalid_string) + snprintf(tmp, sizeof(tmp), "BAD_FORMAT: %s", str_frmt->string); + else + snprintf(tmp, sizeof(tmp), str_frmt->string, + str_frmt->params[0], + str_frmt->params[1], + str_frmt->params[2], + str_frmt->params[3], + str_frmt->params[4], + str_frmt->params[5], + str_frmt->params[6]); trace_mlx5_fw(dev->tracer, trace_timestamp, str_frmt->lost, str_frmt->event_id, tmp); @@ -609,6 +662,13 @@ static int mlx5_tracer_handle_raw_string(struct mlx5_fw_tracer *tracer, return 0; } +static void mlx5_tracer_handle_bad_format_string(struct mlx5_fw_tracer *tracer, + struct tracer_string_format *cur_string) +{ + cur_string->invalid_string = true; + list_add_tail(&cur_string->list, &tracer->ready_strings_list); +} + static int mlx5_tracer_handle_string_trace(struct mlx5_fw_tracer *tracer, struct tracer_event *tracer_event) { @@ -619,12 +679,18 @@ static int mlx5_tracer_handle_string_trace(struct mlx5_fw_tracer *tracer, if (!cur_string) return mlx5_tracer_handle_raw_string(tracer, tracer_event); - cur_string->num_of_params = mlx5_tracer_get_num_of_params(cur_string->string); - cur_string->last_param_num = 0; cur_string->event_id = tracer_event->event_id; cur_string->tmsn = tracer_event->string_event.tmsn; cur_string->timestamp = tracer_event->string_event.timestamp; cur_string->lost = tracer_event->lost_event; + cur_string->last_param_num = 0; + cur_string->num_of_params = mlx5_tracer_get_num_of_params(cur_string->string); + if (cur_string->num_of_params < 0) { + pr_debug("%s Invalid format string parameters\n", + __func__); + mlx5_tracer_handle_bad_format_string(tracer, cur_string); + return 0; + } if (cur_string->num_of_params == 0) /* trace with no params */ list_add_tail(&cur_string->list, &tracer->ready_strings_list); } else { @@ -634,6 +700,11 @@ static int mlx5_tracer_handle_string_trace(struct mlx5_fw_tracer *tracer, __func__, tracer_event->string_event.tmsn); return mlx5_tracer_handle_raw_string(tracer, tracer_event); } + if (cur_string->num_of_params < 0) { + pr_debug("%s string parameter of invalid string, dumping\n", + __func__); + return 0; + } cur_string->last_param_num += 1; if (cur_string->last_param_num > TRACER_MAX_PARAMS) { pr_debug("%s Number of params exceeds the max (%d)\n", diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h index 5c548bb74f07..30d0bcba8847 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h @@ -125,6 +125,7 @@ struct tracer_string_format { struct list_head list; u32 timestamp; bool lost; + bool invalid_string; }; enum mlx5_fw_tracer_ownership_state { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 811178d8976c..262dc032e276 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -69,7 +69,7 @@ struct page_pool; #define MLX5E_METADATA_ETHER_TYPE (0x8CE4) #define MLX5E_METADATA_ETHER_LEN 8 -#define MLX5E_ETH_HARD_MTU (ETH_HLEN + PSP_ENCAP_HLEN + PSP_TRL_SIZE + VLAN_HLEN + ETH_FCS_LEN) +#define MLX5E_ETH_HARD_MTU (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN) #define MLX5E_HW2SW_MTU(params, hwmtu) ((hwmtu) - ((params)->hard_mtu)) #define MLX5E_SW2HW_MTU(params, swmtu) ((swmtu) + ((params)->hard_mtu)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c index 35d9530037a6..a8fb4bec369c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c @@ -342,9 +342,8 @@ static void mlx5e_ipsec_init_macs(struct mlx5e_ipsec_sa_entry *sa_entry, rt_dst_entry = &rt->dst; break; case AF_INET6: - rt_dst_entry = ipv6_stub->ipv6_dst_lookup_flow( - dev_net(netdev), NULL, &fl6, NULL); - if (IS_ERR(rt_dst_entry)) + if (!IS_ENABLED(CONFIG_IPV6) || + ip6_dst_lookup(dev_net(netdev), NULL, &rt_dst_entry, &fl6)) goto neigh; break; default: @@ -359,6 +358,9 @@ static void mlx5e_ipsec_init_macs(struct mlx5e_ipsec_sa_entry *sa_entry, neigh_ha_snapshot(addr, n, netdev); ether_addr_copy(dst, addr); + if (attrs->dir == XFRM_DEV_OFFLOAD_OUT && + is_zero_ether_addr(addr)) + neigh_event_send(n, NULL); dst_release(rt_dst_entry); neigh_release(n); return; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 6168f0814414..07fc4d2c8fad 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -6825,7 +6825,6 @@ static void _mlx5e_remove(struct auxiliary_device *adev) * is already unregistered before changing to NIC profile. */ if (priv->netdev->reg_state == NETREG_REGISTERED) { - mlx5e_psp_unregister(priv); unregister_netdev(priv->netdev); _mlx5e_suspend(adev, false); } else { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 14884b9ea7f3..a01ee656a1e7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -939,7 +939,11 @@ void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq) sq->dma_fifo_cc = dma_fifo_cc; sq->cc = sqcc; - netdev_tx_completed_queue(sq->txq, npkts, nbytes); + /* Do not update BQL for TXQs that got replaced by new active ones, as + * netdev_tx_reset_queue() is called for them in mlx5e_activate_txqsq(). + */ + if (sq == sq->priv->txq2sq[sq->txq_ix]) + netdev_tx_completed_queue(sq->txq, npkts, nbytes); } #ifdef CONFIG_MLX5_CORE_IPOIB diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 8de6c7f6c294..ea94a727633f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -52,6 +52,7 @@ #include "devlink.h" #include "lag/lag.h" #include "en/tc/post_meter.h" +#include "fw_reset.h" /* There are two match-all miss flows, one for unicast dst mac and * one for multicast. @@ -3991,6 +3992,11 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, if (IS_ERR(esw)) return PTR_ERR(esw); + if (mlx5_fw_reset_in_progress(esw->dev)) { + NL_SET_ERR_MSG_MOD(extack, "Can't change eswitch mode during firmware reset"); + return -EBUSY; + } + if (esw_mode_from_devlink(mode, &mlx5_mode)) return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index 2bceb42c98cc..ae10665c53f3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -15,6 +15,7 @@ enum { MLX5_FW_RESET_FLAGS_DROP_NEW_REQUESTS, MLX5_FW_RESET_FLAGS_RELOAD_REQUIRED, MLX5_FW_RESET_FLAGS_UNLOAD_EVENT, + MLX5_FW_RESET_FLAGS_RESET_IN_PROGRESS, }; struct mlx5_fw_reset { @@ -128,6 +129,16 @@ int mlx5_fw_reset_query(struct mlx5_core_dev *dev, u8 *reset_level, u8 *reset_ty return mlx5_reg_mfrl_query(dev, reset_level, reset_type, NULL, NULL); } +bool mlx5_fw_reset_in_progress(struct mlx5_core_dev *dev) +{ + struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; + + if (!fw_reset) + return false; + + return test_bit(MLX5_FW_RESET_FLAGS_RESET_IN_PROGRESS, &fw_reset->reset_flags); +} + static int mlx5_fw_reset_get_reset_method(struct mlx5_core_dev *dev, u8 *reset_method) { @@ -243,6 +254,8 @@ static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev) BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE)); devl_unlock(devlink); } + + clear_bit(MLX5_FW_RESET_FLAGS_RESET_IN_PROGRESS, &fw_reset->reset_flags); } static void mlx5_stop_sync_reset_poll(struct mlx5_core_dev *dev) @@ -462,27 +475,48 @@ static void mlx5_sync_reset_request_event(struct work_struct *work) struct mlx5_fw_reset *fw_reset = container_of(work, struct mlx5_fw_reset, reset_request_work); struct mlx5_core_dev *dev = fw_reset->dev; + bool nack_request = false; + struct devlink *devlink; int err; err = mlx5_fw_reset_get_reset_method(dev, &fw_reset->reset_method); - if (err) + if (err) { + nack_request = true; mlx5_core_warn(dev, "Failed reading MFRL, err %d\n", err); + } else if (!mlx5_is_reset_now_capable(dev, fw_reset->reset_method) || + test_bit(MLX5_FW_RESET_FLAGS_NACK_RESET_REQUEST, + &fw_reset->reset_flags)) { + nack_request = true; + } - if (err || test_bit(MLX5_FW_RESET_FLAGS_NACK_RESET_REQUEST, &fw_reset->reset_flags) || - !mlx5_is_reset_now_capable(dev, fw_reset->reset_method)) { + devlink = priv_to_devlink(dev); + /* For external resets, try to acquire devl_lock. Skip if devlink reset is + * pending (lock already held) + */ + if (nack_request || + (!test_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, + &fw_reset->reset_flags) && + !devl_trylock(devlink))) { err = mlx5_fw_reset_set_reset_sync_nack(dev); mlx5_core_warn(dev, "PCI Sync FW Update Reset Nack %s", err ? "Failed" : "Sent"); return; } + if (mlx5_sync_reset_set_reset_requested(dev)) - return; + goto unlock; + + set_bit(MLX5_FW_RESET_FLAGS_RESET_IN_PROGRESS, &fw_reset->reset_flags); err = mlx5_fw_reset_set_reset_sync_ack(dev); if (err) mlx5_core_warn(dev, "PCI Sync FW Update Reset Ack Failed. Error code: %d\n", err); else mlx5_core_warn(dev, "PCI Sync FW Update Reset Ack. Device reset is expected.\n"); + +unlock: + if (!test_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags)) + devl_unlock(devlink); } static int mlx5_pci_link_toggle(struct mlx5_core_dev *dev, u16 dev_id) @@ -722,6 +756,8 @@ static void mlx5_sync_reset_abort_event(struct work_struct *work) if (mlx5_sync_reset_clear_reset_requested(dev, true)) return; + + clear_bit(MLX5_FW_RESET_FLAGS_RESET_IN_PROGRESS, &fw_reset->reset_flags); mlx5_core_warn(dev, "PCI Sync FW Update Reset Aborted.\n"); } @@ -758,6 +794,7 @@ static void mlx5_sync_reset_timeout_work(struct work_struct *work) if (mlx5_sync_reset_clear_reset_requested(dev, true)) return; + clear_bit(MLX5_FW_RESET_FLAGS_RESET_IN_PROGRESS, &fw_reset->reset_flags); mlx5_core_warn(dev, "PCI Sync FW Update Reset Timeout.\n"); } @@ -844,7 +881,8 @@ void mlx5_drain_fw_reset(struct mlx5_core_dev *dev) cancel_work_sync(&fw_reset->reset_reload_work); cancel_work_sync(&fw_reset->reset_now_work); cancel_work_sync(&fw_reset->reset_abort_work); - cancel_delayed_work(&fw_reset->reset_timeout_work); + if (test_bit(MLX5_FW_RESET_FLAGS_RESET_REQUESTED, &fw_reset->reset_flags)) + mlx5_sync_reset_clear_reset_requested(dev, true); } static const struct devlink_param mlx5_fw_reset_devlink_params[] = { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h index d5b28525c960..2d96b2adc1cd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h @@ -10,6 +10,7 @@ int mlx5_fw_reset_query(struct mlx5_core_dev *dev, u8 *reset_level, u8 *reset_ty int mlx5_fw_reset_set_reset_sync(struct mlx5_core_dev *dev, u8 reset_type_sel, struct netlink_ext_ack *extack); int mlx5_fw_reset_set_live_patch(struct mlx5_core_dev *dev); +bool mlx5_fw_reset_in_progress(struct mlx5_core_dev *dev); int mlx5_fw_reset_wait_reset_done(struct mlx5_core_dev *dev); void mlx5_sync_reset_unload_flow(struct mlx5_core_dev *dev, bool locked); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index 1ac933cd8f02..a459a30f36ca 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -1413,6 +1413,7 @@ static int __mlx5_lag_dev_add_mdev(struct mlx5_core_dev *dev) static void mlx5_lag_unregister_hca_devcom_comp(struct mlx5_core_dev *dev) { mlx5_devcom_unregister_component(dev->priv.hca_devcom_comp); + dev->priv.hca_devcom_comp = NULL; } static int mlx5_lag_register_hca_devcom_comp(struct mlx5_core_dev *dev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c index aad52d3a90e6..2d86af8f0d9b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c @@ -67,12 +67,19 @@ err_metadata: static int enable_mpesw(struct mlx5_lag *ldev) { - int idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1); struct mlx5_core_dev *dev0; int err; + int idx; int i; - if (idx < 0 || ldev->mode != MLX5_LAG_MODE_NONE) + if (ldev->mode == MLX5_LAG_MODE_MPESW) + return 0; + + if (ldev->mode != MLX5_LAG_MODE_NONE) + return -EINVAL; + + idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1); + if (idx < 0) return -EINVAL; dev0 = ldev->pf[idx].dev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 1ab569ce3fcf..4209da722f9a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -2231,6 +2231,7 @@ static void shutdown(struct pci_dev *pdev) mlx5_core_info(dev, "Shutdown was called\n"); set_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state); + mlx5_drain_fw_reset(dev); mlx5_drain_health_wq(dev); err = mlx5_try_fast_unload(dev); if (err) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c index 5afe6b155ef0..81935f87bfcd 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c @@ -440,7 +440,9 @@ int mlxsw_sp_mr_route_add(struct mlxsw_sp_mr_table *mr_table, rhashtable_remove_fast(&mr_table->route_ht, &mr_orig_route->ht_node, mlxsw_sp_mr_route_ht_params); + mutex_lock(&mr_table->route_list_lock); list_del(&mr_orig_route->node); + mutex_unlock(&mr_table->route_list_lock); mlxsw_sp_mr_route_destroy(mr_table, mr_orig_route); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index a2033837182e..2d0e89bd2fb9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -2265,6 +2265,7 @@ mlxsw_sp_neigh_entry_alloc(struct mlxsw_sp *mlxsw_sp, struct neighbour *n, if (!neigh_entry) return NULL; + neigh_hold(n); neigh_entry->key.n = n; neigh_entry->rif = rif; INIT_LIST_HEAD(&neigh_entry->nexthop_list); @@ -2274,6 +2275,7 @@ mlxsw_sp_neigh_entry_alloc(struct mlxsw_sp *mlxsw_sp, struct neighbour *n, static void mlxsw_sp_neigh_entry_free(struct mlxsw_sp_neigh_entry *neigh_entry) { + neigh_release(neigh_entry->key.n); kfree(neigh_entry); } @@ -2858,6 +2860,11 @@ static int mlxsw_sp_router_schedule_work(struct net *net, if (!net_work) return NOTIFY_BAD; + /* Take a reference to ensure the neighbour won't be destructed until + * we drop the reference in the work item. + */ + neigh_clone(n); + INIT_WORK(&net_work->work, cb); net_work->mlxsw_sp = router->mlxsw_sp; net_work->n = n; @@ -2881,11 +2888,6 @@ static int mlxsw_sp_router_schedule_neigh_work(struct mlxsw_sp_router *router, struct net *net; net = neigh_parms_net(n->parms); - - /* Take a reference to ensure the neighbour won't be destructed until we - * drop the reference in delayed work. - */ - neigh_clone(n); return mlxsw_sp_router_schedule_work(net, router, n, mlxsw_sp_router_neigh_event_work); } @@ -4320,6 +4322,8 @@ mlxsw_sp_nexthop_dead_neigh_replace(struct mlxsw_sp *mlxsw_sp, if (err) goto err_neigh_entry_insert; + neigh_release(old_n); + read_lock_bh(&n->lock); nud_state = n->nud_state; dead = n->dead; @@ -4328,14 +4332,10 @@ mlxsw_sp_nexthop_dead_neigh_replace(struct mlxsw_sp *mlxsw_sp, list_for_each_entry(nh, &neigh_entry->nexthop_list, neigh_list_node) { - neigh_release(old_n); - neigh_clone(n); __mlxsw_sp_nexthop_neigh_update(nh, !entry_connected); mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nhgi->nh_grp); } - neigh_release(n); - return 0; err_neigh_entry_insert: @@ -4428,6 +4428,11 @@ static int mlxsw_sp_nexthop_neigh_init(struct mlxsw_sp *mlxsw_sp, } } + /* Release the reference taken by neigh_lookup() / neigh_create() since + * neigh_entry already holds one. + */ + neigh_release(n); + /* If that is the first nexthop connected to that neigh, add to * nexthop_neighs_list */ @@ -4454,11 +4459,9 @@ static void mlxsw_sp_nexthop_neigh_fini(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop *nh) { struct mlxsw_sp_neigh_entry *neigh_entry = nh->neigh_entry; - struct neighbour *n; if (!neigh_entry) return; - n = neigh_entry->key.n; __mlxsw_sp_nexthop_neigh_update(nh, true); list_del(&nh->neigh_list_node); @@ -4472,8 +4475,6 @@ static void mlxsw_sp_nexthop_neigh_fini(struct mlxsw_sp *mlxsw_sp, if (!neigh_entry->connected && list_empty(&neigh_entry->nexthop_list)) mlxsw_sp_neigh_entry_destroy(mlxsw_sp, neigh_entry); - - neigh_release(n); } static bool mlxsw_sp_ipip_netdev_ul_up(struct net_device *ol_dev) diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 405e91eb3141..755083852eef 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -2655,9 +2655,6 @@ static void rtl_wol_enable_rx(struct rtl8169_private *tp) static void rtl_prepare_power_down(struct rtl8169_private *tp) { - if (tp->dash_enabled) - return; - if (tp->mac_version == RTL_GIGA_MAC_VER_32 || tp->mac_version == RTL_GIGA_MAC_VER_33) rtl_ephy_write(tp, 0x19, 0xff64); @@ -4812,7 +4809,7 @@ static void rtl8169_down(struct rtl8169_private *tp) rtl_disable_exit_l1(tp); rtl_prepare_power_down(tp); - if (tp->dash_type != RTL_DASH_NONE) + if (tp->dash_type != RTL_DASH_NONE && !tp->saved_wolopts) rtl8168_driver_stop(tp); } diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig index a54d71155263..fe5b2926d8ab 100644 --- a/drivers/net/ethernet/ti/Kconfig +++ b/drivers/net/ethernet/ti/Kconfig @@ -209,6 +209,7 @@ config TI_ICSSG_PRUETH_SR1 depends on PRU_REMOTEPROC depends on NET_SWITCHDEV depends on ARCH_K3 && OF && TI_K3_UDMA_GLUE_LAYER + depends on PTP_1588_CLOCK_OPTIONAL help Support dual Gigabit Ethernet ports over the ICSSG PRU Subsystem. This subsystem is available on the AM65 SR1.0 platform. @@ -234,7 +235,7 @@ config TI_PRUETH depends on PRU_REMOTEPROC depends on NET_SWITCHDEV select TI_ICSS_IEP - imply PTP_1588_CLOCK + depends on PTP_1588_CLOCK_OPTIONAL help Some TI SoCs has Programmable Realtime Unit (PRU) cores which can support Single or Dual Ethernet ports with the help of firmware code diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index dea411e132db..2efa3ba148aa 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -737,6 +737,9 @@ static rx_handler_result_t ipvlan_handle_mode_l2(struct sk_buff **pskb, struct ethhdr *eth = eth_hdr(skb); rx_handler_result_t ret = RX_HANDLER_PASS; + if (unlikely(skb->pkt_type == PACKET_LOOPBACK)) + return RX_HANDLER_PASS; + if (is_multicast_ether_addr(eth->h_dest)) { if (ipvlan_external_frame(skb, port)) { struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); diff --git a/drivers/net/phy/marvell-88q2xxx.c b/drivers/net/phy/marvell-88q2xxx.c index f3d83b04c953..201dee1a1698 100644 --- a/drivers/net/phy/marvell-88q2xxx.c +++ b/drivers/net/phy/marvell-88q2xxx.c @@ -698,7 +698,7 @@ static int mv88q2xxx_hwmon_write(struct device *dev, switch (attr) { case hwmon_temp_max: - clamp_val(val, -75000, 180000); + val = clamp(val, -75000, 180000); val = (val / 1000) + 75; val = FIELD_PREP(MDIO_MMD_PCS_MV_TEMP_SENSOR3_INT_THRESH_MASK, val); diff --git a/drivers/net/phy/realtek/realtek_main.c b/drivers/net/phy/realtek/realtek_main.c index 67ecf3d4af2b..6ff0385201a5 100644 --- a/drivers/net/phy/realtek/realtek_main.c +++ b/drivers/net/phy/realtek/realtek_main.c @@ -691,10 +691,6 @@ static int rtl8211f_config_aldps(struct phy_device *phydev) static int rtl8211f_config_phy_eee(struct phy_device *phydev) { - /* RTL8211FVD has no PHYCR2 register */ - if (phydev->drv->phy_id == RTL_8211FVD_PHYID) - return 0; - /* Disable PHY-mode EEE so LPI is passed to the MAC */ return phy_modify_paged(phydev, RTL8211F_PHYCR_PAGE, RTL8211F_PHYCR2, RTL8211F_PHYCR2_PHY_EEE_ENABLE, 0); diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index 0401fa6b24d2..6166e9196364 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -497,6 +497,8 @@ static const struct sfp_quirk sfp_quirks[] = { SFP_QUIRK("ALCATELLUCENT", "3FE46541AA", sfp_quirk_2500basex, sfp_fixup_nokia), + SFP_QUIRK_F("BIDB", "X-ONU-SFPP", sfp_fixup_potron), + // FLYPRO SFP-10GT-CS-30M uses Rollball protocol to talk to the PHY. SFP_QUIRK_F("FLYPRO", "SFP-10GT-CS-30M", sfp_fixup_rollball), diff --git a/drivers/nfc/pn533/usb.c b/drivers/nfc/pn533/usb.c index ffd7367ce119..018a80674f06 100644 --- a/drivers/nfc/pn533/usb.c +++ b/drivers/nfc/pn533/usb.c @@ -406,7 +406,7 @@ static int pn533_acr122_poweron_rdr(struct pn533_usb_phy *phy) if (rc || (transferred != sizeof(cmd))) { nfc_err(&phy->udev->dev, "Reader power on cmd error %d\n", rc); - return rc; + return rc ?: -EINVAL; } rc = usb_submit_urb(phy->in_urb, GFP_KERNEL); diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c index b9d87e56cbbc..3ff6da3bf4e6 100644 --- a/drivers/powercap/intel_rapl_common.c +++ b/drivers/powercap/intel_rapl_common.c @@ -2032,7 +2032,7 @@ end: return ret; } -int rapl_package_add_pmu(struct rapl_package *rp) +int rapl_package_add_pmu_locked(struct rapl_package *rp) { struct rapl_package_pmu_data *data = &rp->pmu_data; int idx; @@ -2040,8 +2040,6 @@ int rapl_package_add_pmu(struct rapl_package *rp) if (rp->has_pmu) return -EEXIST; - guard(cpus_read_lock)(); - for (idx = 0; idx < rp->nr_domains; idx++) { struct rapl_domain *rd = &rp->domains[idx]; int domain = rd->id; @@ -2091,17 +2089,23 @@ int rapl_package_add_pmu(struct rapl_package *rp) return rapl_pmu_update(rp); } +EXPORT_SYMBOL_GPL(rapl_package_add_pmu_locked); + +int rapl_package_add_pmu(struct rapl_package *rp) +{ + guard(cpus_read_lock)(); + + return rapl_package_add_pmu_locked(rp); +} EXPORT_SYMBOL_GPL(rapl_package_add_pmu); -void rapl_package_remove_pmu(struct rapl_package *rp) +void rapl_package_remove_pmu_locked(struct rapl_package *rp) { struct rapl_package *pos; if (!rp->has_pmu) return; - guard(cpus_read_lock)(); - list_for_each_entry(pos, &rapl_packages, plist) { /* PMU is still needed */ if (pos->has_pmu && pos != rp) @@ -2111,6 +2115,14 @@ void rapl_package_remove_pmu(struct rapl_package *rp) perf_pmu_unregister(&rapl_pmu.pmu); memset(&rapl_pmu, 0, sizeof(struct rapl_pmu)); } +EXPORT_SYMBOL_GPL(rapl_package_remove_pmu_locked); + +void rapl_package_remove_pmu(struct rapl_package *rp) +{ + guard(cpus_read_lock)(); + + rapl_package_remove_pmu_locked(rp); +} EXPORT_SYMBOL_GPL(rapl_package_remove_pmu); #endif diff --git a/drivers/powercap/intel_rapl_msr.c b/drivers/powercap/intel_rapl_msr.c index 0ce1096b6314..9a7e150b3536 100644 --- a/drivers/powercap/intel_rapl_msr.c +++ b/drivers/powercap/intel_rapl_msr.c @@ -82,7 +82,7 @@ static int rapl_cpu_online(unsigned int cpu) if (IS_ERR(rp)) return PTR_ERR(rp); if (rapl_msr_pmu) - rapl_package_add_pmu(rp); + rapl_package_add_pmu_locked(rp); } cpumask_set_cpu(cpu, &rp->cpumask); return 0; @@ -101,7 +101,7 @@ static int rapl_cpu_down_prep(unsigned int cpu) lead_cpu = cpumask_first(&rp->cpumask); if (lead_cpu >= nr_cpu_ids) { if (rapl_msr_pmu) - rapl_package_remove_pmu(rp); + rapl_package_remove_pmu_locked(rp); rapl_remove_package_cpuslocked(rp); } else if (rp->lead_cpu == cpu) { rp->lead_cpu = lead_cpu; diff --git a/drivers/powercap/powercap_sys.c b/drivers/powercap/powercap_sys.c index 4112a0097338..1ff369880beb 100644 --- a/drivers/powercap/powercap_sys.c +++ b/drivers/powercap/powercap_sys.c @@ -68,7 +68,7 @@ static ssize_t show_constraint_##_attr(struct device *dev, \ int id; \ struct powercap_zone_constraint *pconst;\ \ - if (!sscanf(dev_attr->attr.name, "constraint_%d_", &id)) \ + if (sscanf(dev_attr->attr.name, "constraint_%d_", &id) != 1) \ return -EINVAL; \ if (id >= power_zone->const_id_cnt) \ return -EINVAL; \ @@ -93,7 +93,7 @@ static ssize_t store_constraint_##_attr(struct device *dev,\ int id; \ struct powercap_zone_constraint *pconst;\ \ - if (!sscanf(dev_attr->attr.name, "constraint_%d_", &id)) \ + if (sscanf(dev_attr->attr.name, "constraint_%d_", &id) != 1) \ return -EINVAL; \ if (id >= power_zone->const_id_cnt) \ return -EINVAL; \ @@ -162,7 +162,7 @@ static ssize_t show_constraint_name(struct device *dev, ssize_t len = -ENODATA; struct powercap_zone_constraint *pconst; - if (!sscanf(dev_attr->attr.name, "constraint_%d_", &id)) + if (sscanf(dev_attr->attr.name, "constraint_%d_", &id) != 1) return -EINVAL; if (id >= power_zone->const_id_cnt) return -EINVAL; @@ -625,17 +625,23 @@ struct powercap_control_type *powercap_register_control_type( INIT_LIST_HEAD(&control_type->node); control_type->dev.class = &powercap_class; dev_set_name(&control_type->dev, "%s", name); - result = device_register(&control_type->dev); - if (result) { - put_device(&control_type->dev); - return ERR_PTR(result); - } idr_init(&control_type->idr); mutex_lock(&powercap_cntrl_list_lock); list_add_tail(&control_type->node, &powercap_cntrl_list); mutex_unlock(&powercap_cntrl_list_lock); + result = device_register(&control_type->dev); + if (result) { + mutex_lock(&powercap_cntrl_list_lock); + list_del(&control_type->node); + mutex_unlock(&powercap_cntrl_list_lock); + + idr_destroy(&control_type->idr); + put_device(&control_type->dev); + return ERR_PTR(result); + } + return control_type; } EXPORT_SYMBOL_GPL(powercap_register_control_type); diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c index 0d4dcc66e097..c693d934103a 100644 --- a/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c +++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c @@ -503,7 +503,8 @@ static const struct pci_device_id proc_thermal_pci_ids[] = { { PCI_DEVICE_DATA(INTEL, WCL_THERMAL, PROC_THERMAL_FEATURE_MSI_SUPPORT | PROC_THERMAL_FEATURE_RAPL | PROC_THERMAL_FEATURE_DLVR | PROC_THERMAL_FEATURE_DVFS | PROC_THERMAL_FEATURE_WT_HINT | - PROC_THERMAL_FEATURE_POWER_FLOOR | PROC_THERMAL_FEATURE_PTC) }, + PROC_THERMAL_FEATURE_POWER_FLOOR | PROC_THERMAL_FEATURE_PTC | + PROC_THERMAL_FEATURE_SOC_POWER_SLIDER) }, { PCI_DEVICE_DATA(INTEL, NVL_H_THERMAL, PROC_THERMAL_FEATURE_RAPL | PROC_THERMAL_FEATURE_DLVR | PROC_THERMAL_FEATURE_DVFS | PROC_THERMAL_FEATURE_MSI_SUPPORT | PROC_THERMAL_FEATURE_WT_HINT | diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 17ca5c082643..89758c9934ec 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -500,7 +500,7 @@ void thermal_zone_set_trip_hyst(struct thermal_zone_device *tz, WRITE_ONCE(trip->hysteresis, hyst); thermal_notify_tz_trip_change(tz, trip); /* - * If the zone temperature is above or at the trip tmperature, the trip + * If the zone temperature is above or at the trip temperature, the trip * is in the trips_reached list and its threshold is equal to its low * temperature. It needs to stay in that list, but its threshold needs * to be updated and the list ordering may need to be restored. @@ -1043,7 +1043,7 @@ static void thermal_cooling_device_init_complete(struct thermal_cooling_device * * @np: a pointer to a device tree node. * @type: the thermal cooling device type. * @devdata: device private data. - * @ops: standard thermal cooling devices callbacks. + * @ops: standard thermal cooling devices callbacks. * * This interface function adds a new thermal cooling device (fan/processor/...) * to /sys/class/thermal/ folder as cooling_device[0-*]. It tries to bind itself diff --git a/fs/file_attr.c b/fs/file_attr.c index 4c4916632f11..13cdb31a3e94 100644 --- a/fs/file_attr.c +++ b/fs/file_attr.c @@ -2,6 +2,7 @@ #include <linux/fs.h> #include <linux/security.h> #include <linux/fscrypt.h> +#include <linux/fsnotify.h> #include <linux/fileattr.h> #include <linux/export.h> #include <linux/syscalls.h> @@ -298,6 +299,7 @@ int vfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, err = inode->i_op->fileattr_set(idmap, dentry, fa); if (err) goto out; + fsnotify_xattr(dentry); } out: diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index d27ff5e5f165..71bd44e5ab6d 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -270,8 +270,15 @@ int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, /* * Include parent/name in notification either if some notification * groups require parent info or the parent is interested in this event. + * The parent interest in ACCESS/MODIFY events does not apply to special + * files, where read/write are not on the filesystem of the parent and + * events can provide an undesirable side-channel for information + * exfiltration. */ - parent_interested = mask & p_mask & ALL_FSNOTIFY_EVENTS; + parent_interested = mask & p_mask & ALL_FSNOTIFY_EVENTS && + !(data_type == FSNOTIFY_EVENT_PATH && + d_is_special(dentry) && + (mask & (FS_ACCESS | FS_MODIFY))); if (parent_needed || parent_interested) { /* When notifying parent, child should be passed as data */ WARN_ON_ONCE(inode != fsnotify_data_inode(data, data_type)); diff --git a/fs/smb/client/cifsfs.h b/fs/smb/client/cifsfs.h index e9534258d1ef..75d372ceb655 100644 --- a/fs/smb/client/cifsfs.h +++ b/fs/smb/client/cifsfs.h @@ -145,6 +145,6 @@ extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ /* when changing internal version - update following two lines at same time */ -#define SMB3_PRODUCT_BUILD 57 -#define CIFS_VERSION "2.57" +#define SMB3_PRODUCT_BUILD 58 +#define CIFS_VERSION "2.58" #endif /* _CIFSFS_H */ diff --git a/fs/smb/client/cifspdu.h b/fs/smb/client/cifspdu.h index eeb4011cb217..fdd84369e7b8 100644 --- a/fs/smb/client/cifspdu.h +++ b/fs/smb/client/cifspdu.h @@ -12,7 +12,7 @@ #include <net/sock.h> #include <linux/unaligned.h> #include "../common/smbfsctl.h" -#include "../common/smb2pdu.h" +#include "../common/smb1pdu.h" #define CIFS_PROT 0 #define POSIX_PROT (CIFS_PROT+1) diff --git a/fs/smb/common/smb1pdu.h b/fs/smb/common/smb1pdu.h new file mode 100644 index 000000000000..df6d4e11ae92 --- /dev/null +++ b/fs/smb/common/smb1pdu.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: LGPL-2.1 */ +/* + * + * Copyright (C) International Business Machines Corp., 2002,2009 + * 2018 Samsung Electronics Co., Ltd. + * Author(s): Steve French <sfrench@us.ibm.com> + * Namjae Jeon <linkinjeon@kernel.org> + * + */ + +#ifndef _COMMON_SMB1_PDU_H +#define _COMMON_SMB1_PDU_H + +#define SMB1_PROTO_NUMBER cpu_to_le32(0x424d53ff) + +/* + * See MS-CIFS 2.2.3.1 + * MS-SMB 2.2.3.1 + */ +struct smb_hdr { + __u8 Protocol[4]; + __u8 Command; + union { + struct { + __u8 ErrorClass; + __u8 Reserved; + __le16 Error; + } __packed DosError; + __le32 CifsError; + } __packed Status; + __u8 Flags; + __le16 Flags2; /* note: le */ + __le16 PidHigh; + union { + struct { + __le32 SequenceNumber; /* le */ + __u32 Reserved; /* zero */ + } __packed Sequence; + __u8 SecuritySignature[8]; /* le */ + } __packed Signature; + __u8 pad[2]; + __u16 Tid; + __le16 Pid; + __u16 Uid; + __le16 Mid; + __u8 WordCount; +} __packed; + +/* See MS-CIFS 2.2.4.52.1 */ +typedef struct smb_negotiate_req { + struct smb_hdr hdr; /* wct = 0 */ + __le16 ByteCount; + unsigned char DialectsArray[]; +} __packed SMB_NEGOTIATE_REQ; + +#endif /* _COMMON_SMB1_PDU_H */ diff --git a/fs/smb/common/smb2pdu.h b/fs/smb/common/smb2pdu.h index 3c8d8a4e7439..f5ebbe31384a 100644 --- a/fs/smb/common/smb2pdu.h +++ b/fs/smb/common/smb2pdu.h @@ -1293,6 +1293,7 @@ struct create_durable_handle_reconnect_v2 { struct create_context_hdr ccontext; __u8 Name[8]; struct durable_reconnect_context_v2 dcontext; + __u8 Pad[4]; } __packed; /* See MS-SMB2 2.2.14.2.12 */ @@ -1985,39 +1986,6 @@ struct smb2_lease_ack { __le64 LeaseDuration; } __packed; -/* - * See MS-CIFS 2.2.3.1 - * MS-SMB 2.2.3.1 - */ -struct smb_hdr { - __u8 Protocol[4]; - __u8 Command; - union { - struct { - __u8 ErrorClass; - __u8 Reserved; - __le16 Error; - } __packed DosError; - __le32 CifsError; - } __packed Status; - __u8 Flags; - __le16 Flags2; /* note: le */ - __le16 PidHigh; - union { - struct { - __le32 SequenceNumber; /* le */ - __u32 Reserved; /* zero */ - } __packed Sequence; - __u8 SecuritySignature[8]; /* le */ - } __packed Signature; - __u8 pad[2]; - __u16 Tid; - __le16 Pid; - __u16 Uid; - __le16 Mid; - __u8 WordCount; -} __packed; - #define OP_BREAK_STRUCT_SIZE_20 24 #define OP_BREAK_STRUCT_SIZE_21 36 @@ -2122,11 +2090,4 @@ struct smb_hdr { #define SET_MINIMUM_RIGHTS (FILE_READ_EA | FILE_READ_ATTRIBUTES \ | READ_CONTROL | SYNCHRONIZE) -/* See MS-CIFS 2.2.4.52.1 */ -typedef struct smb_negotiate_req { - struct smb_hdr hdr; /* wct = 0 */ - __le16 ByteCount; - unsigned char DialectsArray[]; -} __packed SMB_NEGOTIATE_REQ; - #endif /* _COMMON_SMB2PDU_H */ diff --git a/fs/smb/common/smbglob.h b/fs/smb/common/smbglob.h index 9562845a5617..4e33d91cdc9d 100644 --- a/fs/smb/common/smbglob.h +++ b/fs/smb/common/smbglob.h @@ -11,8 +11,6 @@ #ifndef _COMMON_SMB_GLOB_H #define _COMMON_SMB_GLOB_H -#define SMB1_PROTO_NUMBER cpu_to_le32(0x424d53ff) - struct smb_version_values { char *version_string; __u16 protocol_id; diff --git a/fs/smb/server/smb_common.h b/fs/smb/server/smb_common.h index 067b45048c73..95bf1465387b 100644 --- a/fs/smb/server/smb_common.h +++ b/fs/smb/server/smb_common.h @@ -10,6 +10,7 @@ #include "glob.h" #include "../common/smbglob.h" +#include "../common/smb1pdu.h" #include "../common/smb2pdu.h" #include "../common/fscc.h" #include "smb2pdu.h" diff --git a/include/linux/bio.h b/include/linux/bio.h index ad2d57908c1c..c75a9b3672aa 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -46,6 +46,21 @@ static inline unsigned int bio_max_segs(unsigned int nr_segs) #define bio_data_dir(bio) \ (op_is_write(bio_op(bio)) ? WRITE : READ) +static inline bool bio_flagged(const struct bio *bio, unsigned int bit) +{ + return bio->bi_flags & (1U << bit); +} + +static inline void bio_set_flag(struct bio *bio, unsigned int bit) +{ + bio->bi_flags |= (1U << bit); +} + +static inline void bio_clear_flag(struct bio *bio, unsigned int bit) +{ + bio->bi_flags &= ~(1U << bit); +} + /* * Check whether this bio carries any data or not. A NULL bio is allowed. */ @@ -225,21 +240,6 @@ static inline void bio_cnt_set(struct bio *bio, unsigned int count) atomic_set(&bio->__bi_cnt, count); } -static inline bool bio_flagged(struct bio *bio, unsigned int bit) -{ - return bio->bi_flags & (1U << bit); -} - -static inline void bio_set_flag(struct bio *bio, unsigned int bit) -{ - bio->bi_flags |= (1U << bit); -} - -static inline void bio_clear_flag(struct bio *bio, unsigned int bit) -{ - bio->bi_flags &= ~(1U << bit); -} - static inline struct bio_vec *bio_first_bvec_all(struct bio *bio) { WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)); diff --git a/include/linux/intel_rapl.h b/include/linux/intel_rapl.h index e9ade2ff4af6..f479ef5b3341 100644 --- a/include/linux/intel_rapl.h +++ b/include/linux/intel_rapl.h @@ -214,10 +214,14 @@ void rapl_remove_package(struct rapl_package *rp); #ifdef CONFIG_PERF_EVENTS int rapl_package_add_pmu(struct rapl_package *rp); +int rapl_package_add_pmu_locked(struct rapl_package *rp); void rapl_package_remove_pmu(struct rapl_package *rp); +void rapl_package_remove_pmu_locked(struct rapl_package *rp); #else static inline int rapl_package_add_pmu(struct rapl_package *rp) { return 0; } +static inline int rapl_package_add_pmu_locked(struct rapl_package *rp) { return 0; } static inline void rapl_package_remove_pmu(struct rapl_package *rp) { } +static inline void rapl_package_remove_pmu_locked(struct rapl_package *rp) { } #endif #endif /* __INTEL_RAPL_H__ */ diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 0eccd9c3a883..365925c9d262 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -123,27 +123,15 @@ void inet_frags_fini(struct inet_frags *); int fqdir_init(struct fqdir **fqdirp, struct inet_frags *f, struct net *net); -static inline void fqdir_pre_exit(struct fqdir *fqdir) -{ - /* Prevent creation of new frags. - * Pairs with READ_ONCE() in inet_frag_find(). - */ - WRITE_ONCE(fqdir->high_thresh, 0); - - /* Pairs with READ_ONCE() in inet_frag_kill(), ip_expire() - * and ip6frag_expire_frag_queue(). - */ - WRITE_ONCE(fqdir->dead, true); -} +void fqdir_pre_exit(struct fqdir *fqdir); void fqdir_exit(struct fqdir *fqdir); void inet_frag_kill(struct inet_frag_queue *q, int *refs); void inet_frag_destroy(struct inet_frag_queue *q); struct inet_frag_queue *inet_frag_find(struct fqdir *fqdir, void *key); -/* Free all skbs in the queue; return the sum of their truesizes. */ -unsigned int inet_frag_rbtree_purge(struct rb_root *root, - enum skb_drop_reason reason); +void inet_frag_queue_flush(struct inet_frag_queue *q, + enum skb_drop_reason reason); static inline void inet_frag_putn(struct inet_frag_queue *q, int refs) { diff --git a/include/net/ipv6_frag.h b/include/net/ipv6_frag.h index 38ef66826939..41d9fc6965f9 100644 --- a/include/net/ipv6_frag.h +++ b/include/net/ipv6_frag.h @@ -69,9 +69,6 @@ ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq) int refs = 1; rcu_read_lock(); - /* Paired with the WRITE_ONCE() in fqdir_pre_exit(). */ - if (READ_ONCE(fq->q.fqdir->dead)) - goto out_rcu_unlock; spin_lock(&fq->q.lock); if (fq->q.flags & INET_FRAG_COMPLETE) @@ -80,6 +77,12 @@ ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq) fq->q.flags |= INET_FRAG_DROP; inet_frag_kill(&fq->q, &refs); + /* Paired with the WRITE_ONCE() in fqdir_pre_exit(). */ + if (READ_ONCE(fq->q.fqdir->dead)) { + inet_frag_queue_flush(&fq->q, 0); + goto out; + } + dev = dev_get_by_index_rcu(net, fq->iif); if (!dev) goto out; diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index fab7dc73f738..0e266c2d0e7f 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1091,6 +1091,29 @@ struct nft_rule_blob { __attribute__((aligned(__alignof__(struct nft_rule_dp)))); }; +enum nft_chain_types { + NFT_CHAIN_T_DEFAULT = 0, + NFT_CHAIN_T_ROUTE, + NFT_CHAIN_T_NAT, + NFT_CHAIN_T_MAX +}; + +/** + * struct nft_chain_validate_state - validation state + * + * If a chain is encountered again during table validation it is + * possible to avoid revalidation provided the calling context is + * compatible. This structure stores relevant calling context of + * previous validations. + * + * @hook_mask: the hook numbers and locations the chain is linked to + * @depth: the deepest call chain level the chain is linked to + */ +struct nft_chain_validate_state { + u8 hook_mask[NFT_CHAIN_T_MAX]; + u8 depth; +}; + /** * struct nft_chain - nf_tables chain * @@ -1109,6 +1132,7 @@ struct nft_rule_blob { * @udlen: user data length * @udata: user data in the chain * @blob_next: rule blob pointer to the next in the chain + * @vstate: validation state */ struct nft_chain { struct nft_rule_blob __rcu *blob_gen_0; @@ -1128,9 +1152,10 @@ struct nft_chain { /* Only used during control plane commit phase: */ struct nft_rule_blob *blob_next; + struct nft_chain_validate_state vstate; }; -int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain); +int nft_chain_validate(const struct nft_ctx *ctx, struct nft_chain *chain); int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv); @@ -1138,13 +1163,6 @@ int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set); int nf_tables_bind_chain(const struct nft_ctx *ctx, struct nft_chain *chain); void nf_tables_unbind_chain(const struct nft_ctx *ctx, struct nft_chain *chain); -enum nft_chain_types { - NFT_CHAIN_T_DEFAULT = 0, - NFT_CHAIN_T_ROUTE, - NFT_CHAIN_T_NAT, - NFT_CHAIN_T_MAX -}; - /** * struct nft_chain_type - nf_tables chain type info * diff --git a/include/uapi/linux/energy_model.h b/include/uapi/linux/energy_model.h index 4ec4c0eabbbb..0bcad967854f 100644 --- a/include/uapi/linux/energy_model.h +++ b/include/uapi/linux/energy_model.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/em.yaml */ /* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _UAPI_LINUX_ENERGY_MODEL_H #define _UAPI_LINUX_ENERGY_MODEL_H diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 04eea6d1d0a9..72a5d030154e 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -40,6 +40,7 @@ #define MPTCP_PM_ADDR_FLAG_FULLMESH _BITUL(3) #define MPTCP_PM_ADDR_FLAG_IMPLICIT _BITUL(4) #define MPTCP_PM_ADDR_FLAG_LAMINAR _BITUL(5) +#define MPTCP_PM_ADDR_FLAGS_MASK GENMASK(5, 0) struct mptcp_info { __u8 mptcpi_subflows; diff --git a/include/uapi/linux/pr.h b/include/uapi/linux/pr.h index 847f3051057a..f0ecb1677317 100644 --- a/include/uapi/linux/pr.h +++ b/include/uapi/linux/pr.h @@ -79,4 +79,6 @@ struct pr_read_reservation { #define IOC_PR_READ_KEYS _IOWR('p', 206, struct pr_read_keys) #define IOC_PR_READ_RESERVATION _IOR('p', 207, struct pr_read_reservation) +#define PR_KEYS_MAX (1u << 16) + #endif /* _UAPI_PR_H */ diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index a63474b331bf..41c89f5c616d 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -1059,6 +1059,7 @@ static int io_import_kbuf(int ddir, struct iov_iter *iter, if (count < imu->len) { const struct bio_vec *bvec = iter->bvec; + len += iter->iov_offset; while (len > bvec->bv_len) { len -= bvec->bv_len; bvec++; diff --git a/kernel/power/em_netlink_autogen.c b/kernel/power/em_netlink_autogen.c index a7a09ab1d1c2..ceb3b2bb6ebe 100644 --- a/kernel/power/em_netlink_autogen.c +++ b/kernel/power/em_netlink_autogen.c @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/em.yaml */ /* YNL-GEN kernel source */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #include <net/netlink.h> #include <net/genetlink.h> diff --git a/kernel/power/em_netlink_autogen.h b/kernel/power/em_netlink_autogen.h index 78ce609641f1..140ab548103c 100644 --- a/kernel/power/em_netlink_autogen.h +++ b/kernel/power/em_netlink_autogen.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/em.yaml */ /* YNL-GEN kernel header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _LINUX_EM_GEN_H #define _LINUX_EM_GEN_H diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 3ec2033c0774..ef2d5dca6f70 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -4518,8 +4518,11 @@ static int t_show(struct seq_file *m, void *v) unsigned long direct; direct = ftrace_find_rec_direct(rec->ip); - if (direct) - seq_printf(m, "\n\tdirect-->%pS", (void *)direct); + if (direct) { + seq_printf(m, "\n\tdirect%s-->%pS", + ftrace_is_jmp(direct) ? "(jmp)" : "", + (void *)ftrace_jmp_get(direct)); + } } } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index e575956ef9b5..6f2148df14d9 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -10507,7 +10507,7 @@ static int __remove_instance(struct trace_array *tr) /* Disable all the flags that were enabled coming in */ for (i = 0; i < TRACE_FLAGS_MAX_SIZE; i++) { - if ((1 << i) & ZEROED_TRACE_FLAGS) + if ((1ULL << i) & ZEROED_TRACE_FLAGS) set_tracer_flag(tr, 1ULL << i, 0); } diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index b16a5a158040..76067529db61 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -700,6 +700,8 @@ int trace_event_reg(struct trace_event_call *call, #ifdef CONFIG_PERF_EVENTS case TRACE_REG_PERF_REGISTER: + if (!call->class->perf_probe) + return -ENODEV; return tracepoint_probe_register(call->tp, call->class->perf_probe, call); diff --git a/lib/crypto/riscv/.gitignore b/lib/crypto/riscv/.gitignore new file mode 100644 index 000000000000..0d47d4f21c6d --- /dev/null +++ b/lib/crypto/riscv/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +poly1305-core.S diff --git a/mm/slub.c b/mm/slub.c index f21b2f0c6f5a..861592ac5425 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -6539,6 +6539,8 @@ static void defer_free(struct kmem_cache *s, void *head) guard(preempt)(); + head = kasan_reset_tag(head); + df = this_cpu_ptr(&defer_free_objects); if (llist_add(head + s->offset, &df->objects)) irq_work_queue(&df->work); diff --git a/net/caif/cffrml.c b/net/caif/cffrml.c index 6651a8dc62e0..d4d63586053a 100644 --- a/net/caif/cffrml.c +++ b/net/caif/cffrml.c @@ -92,8 +92,15 @@ static int cffrml_receive(struct cflayer *layr, struct cfpkt *pkt) len = le16_to_cpu(tmp); /* Subtract for FCS on length if FCS is not used. */ - if (!this->dofcs) + if (!this->dofcs) { + if (len < 2) { + ++cffrml_rcv_error; + pr_err("Invalid frame length (%d)\n", len); + cfpkt_destroy(pkt); + return -EPROTO; + } len -= 2; + } if (cfpkt_setlen(pkt, len) < 0) { ++cffrml_rcv_error; diff --git a/net/can/Kconfig b/net/can/Kconfig index e4ccf731a24c..af64a6f76458 100644 --- a/net/can/Kconfig +++ b/net/can/Kconfig @@ -5,7 +5,6 @@ menuconfig CAN tristate "CAN bus subsystem support" - select CAN_DEV help Controller Area Network (CAN) is a slow (up to 1Mbit/s) serial communications protocol. Development of the CAN bus started in diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 6272326dd614..ff9c4fd7b433 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -482,6 +482,12 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr_unsized *uaddr, in goto out_release_sock; } + if (ndev->reg_state != NETREG_REGISTERED) { + dev_put(ndev); + ret = -ENODEV; + goto out_release_sock; + } + can_ml = can_get_ml_priv(ndev); if (!can_ml) { dev_put(ndev); diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index fbf5c8001c9d..613a911dda10 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -1567,6 +1567,8 @@ int j1939_session_activate(struct j1939_session *session) if (active) { j1939_session_put(active); ret = -EAGAIN; + } else if (priv->ndev->reg_state != NETREG_REGISTERED) { + ret = -ENODEV; } else { WARN_ON_ONCE(session->state != J1939_SESSION_NEW); list_add_tail(&session->active_session_list_entry, diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index fa83ddade4f8..9431e305b233 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -2383,7 +2383,10 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr) return -ENOMEM; WARN_ON_ONCE(!ret); - gstrings.len = ret; + if (gstrings.len && gstrings.len != ret) + gstrings.len = 0; + else + gstrings.len = ret; if (gstrings.len) { data = vzalloc(array_size(gstrings.len, ETH_GSTRING_LEN)); @@ -2509,10 +2512,13 @@ static int ethtool_get_stats(struct net_device *dev, void __user *useraddr) if (copy_from_user(&stats, useraddr, sizeof(stats))) return -EFAULT; - stats.n_stats = n_stats; + if (stats.n_stats && stats.n_stats != n_stats) + stats.n_stats = 0; + else + stats.n_stats = n_stats; - if (n_stats) { - data = vzalloc(array_size(n_stats, sizeof(u64))); + if (stats.n_stats) { + data = vzalloc(array_size(stats.n_stats, sizeof(u64))); if (!data) return -ENOMEM; ops->get_ethtool_stats(dev, &stats, data); @@ -2524,7 +2530,9 @@ static int ethtool_get_stats(struct net_device *dev, void __user *useraddr) if (copy_to_user(useraddr, &stats, sizeof(stats))) goto out; useraddr += sizeof(stats); - if (n_stats && copy_to_user(useraddr, data, array_size(n_stats, sizeof(u64)))) + if (stats.n_stats && + copy_to_user(useraddr, data, + array_size(stats.n_stats, sizeof(u64)))) goto out; ret = 0; @@ -2560,6 +2568,10 @@ static int ethtool_get_phy_stats_phydev(struct phy_device *phydev, return -EOPNOTSUPP; n_stats = phy_ops->get_sset_count(phydev); + if (stats->n_stats && stats->n_stats != n_stats) { + stats->n_stats = 0; + return 0; + } ret = ethtool_vzalloc_stats_array(n_stats, data); if (ret) @@ -2580,6 +2592,10 @@ static int ethtool_get_phy_stats_ethtool(struct net_device *dev, return -EOPNOTSUPP; n_stats = ops->get_sset_count(dev, ETH_SS_PHY_STATS); + if (stats->n_stats && stats->n_stats != n_stats) { + stats->n_stats = 0; + return 0; + } ret = ethtool_vzalloc_stats_array(n_stats, data); if (ret) @@ -2616,7 +2632,9 @@ static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr) } useraddr += sizeof(stats); - if (copy_to_user(useraddr, data, array_size(stats.n_stats, sizeof(u64)))) + if (stats.n_stats && + copy_to_user(useraddr, data, + array_size(stats.n_stats, sizeof(u64)))) ret = -EFAULT; out: diff --git a/net/handshake/request.c b/net/handshake/request.c index 274d2c89b6b2..6b7e3e0bf399 100644 --- a/net/handshake/request.c +++ b/net/handshake/request.c @@ -276,6 +276,8 @@ int handshake_req_submit(struct socket *sock, struct handshake_req *req, out_unlock: spin_unlock(&hn->hn_lock); out_err: + /* Restore original destructor so socket teardown still runs on failure */ + req->hr_sk->sk_destruct = req->hr_odestruct; trace_handshake_submit_err(net, req, req->hr_sk, ret); handshake_req_destroy(req); return ret; @@ -324,7 +326,11 @@ bool handshake_req_cancel(struct sock *sk) hn = handshake_pernet(net); if (hn && remove_pending(hn, req)) { - /* Request hadn't been accepted */ + /* Request hadn't been accepted - mark cancelled */ + if (test_and_set_bit(HANDSHAKE_F_REQ_COMPLETED, &req->hr_flags)) { + trace_handshake_cancel_busy(net, req, sk); + return false; + } goto out_true; } if (test_and_set_bit(HANDSHAKE_F_REQ_COMPLETED, &req->hr_flags)) { diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index 339f0d220212..aefc9b6936ba 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -205,6 +205,8 @@ struct sk_buff *prp_get_untagged_frame(struct hsr_frame_info *frame, __pskb_copy(frame->skb_prp, skb_headroom(frame->skb_prp), GFP_ATOMIC); + if (!frame->skb_std) + return NULL; } else { /* Unexpected */ WARN_ONCE(1, "%s:%d: Unexpected frame received (port_src %s)\n", diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 025895eb6ec5..001ee5c4d962 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -218,6 +218,41 @@ static int __init inet_frag_wq_init(void) pure_initcall(inet_frag_wq_init); +void fqdir_pre_exit(struct fqdir *fqdir) +{ + struct inet_frag_queue *fq; + struct rhashtable_iter hti; + + /* Prevent creation of new frags. + * Pairs with READ_ONCE() in inet_frag_find(). + */ + WRITE_ONCE(fqdir->high_thresh, 0); + + /* Pairs with READ_ONCE() in inet_frag_kill(), ip_expire() + * and ip6frag_expire_frag_queue(). + */ + WRITE_ONCE(fqdir->dead, true); + + rhashtable_walk_enter(&fqdir->rhashtable, &hti); + rhashtable_walk_start(&hti); + + while ((fq = rhashtable_walk_next(&hti))) { + if (IS_ERR(fq)) { + if (PTR_ERR(fq) != -EAGAIN) + break; + continue; + } + spin_lock_bh(&fq->lock); + if (!(fq->flags & INET_FRAG_COMPLETE)) + inet_frag_queue_flush(fq, 0); + spin_unlock_bh(&fq->lock); + } + + rhashtable_walk_stop(&hti); + rhashtable_walk_exit(&hti); +} +EXPORT_SYMBOL(fqdir_pre_exit); + void fqdir_exit(struct fqdir *fqdir) { INIT_WORK(&fqdir->destroy_work, fqdir_work_fn); @@ -263,8 +298,8 @@ static void inet_frag_destroy_rcu(struct rcu_head *head) kmem_cache_free(f->frags_cachep, q); } -unsigned int inet_frag_rbtree_purge(struct rb_root *root, - enum skb_drop_reason reason) +static unsigned int +inet_frag_rbtree_purge(struct rb_root *root, enum skb_drop_reason reason) { struct rb_node *p = rb_first(root); unsigned int sum = 0; @@ -284,7 +319,17 @@ unsigned int inet_frag_rbtree_purge(struct rb_root *root, } return sum; } -EXPORT_SYMBOL(inet_frag_rbtree_purge); + +void inet_frag_queue_flush(struct inet_frag_queue *q, + enum skb_drop_reason reason) +{ + unsigned int sum; + + reason = reason ?: SKB_DROP_REASON_FRAG_REASM_TIMEOUT; + sum = inet_frag_rbtree_purge(&q->rb_fragments, reason); + sub_frag_mem_limit(q->fqdir, sum); +} +EXPORT_SYMBOL(inet_frag_queue_flush); void inet_frag_destroy(struct inet_frag_queue *q) { @@ -327,7 +372,9 @@ static struct inet_frag_queue *inet_frag_alloc(struct fqdir *fqdir, timer_setup(&q->timer, f->frag_expire, 0); spin_lock_init(&q->lock); - /* One reference for the timer, one for the hash table. */ + /* One reference for the timer, one for the hash table. + * We never take any extra references, only decrement this field. + */ refcount_set(&q->refcnt, 2); return q; diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index f7012479713b..56b0f738d2f2 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -134,11 +134,6 @@ static void ip_expire(struct timer_list *t) net = qp->q.fqdir->net; rcu_read_lock(); - - /* Paired with WRITE_ONCE() in fqdir_pre_exit(). */ - if (READ_ONCE(qp->q.fqdir->dead)) - goto out_rcu_unlock; - spin_lock(&qp->q.lock); if (qp->q.flags & INET_FRAG_COMPLETE) @@ -146,6 +141,13 @@ static void ip_expire(struct timer_list *t) qp->q.flags |= INET_FRAG_DROP; inet_frag_kill(&qp->q, &refs); + + /* Paired with WRITE_ONCE() in fqdir_pre_exit(). */ + if (READ_ONCE(qp->q.fqdir->dead)) { + inet_frag_queue_flush(&qp->q, 0); + goto out; + } + __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); __IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT); @@ -240,16 +242,10 @@ static int ip_frag_too_far(struct ipq *qp) static int ip_frag_reinit(struct ipq *qp) { - unsigned int sum_truesize = 0; - - if (!mod_timer(&qp->q.timer, jiffies + qp->q.fqdir->timeout)) { - refcount_inc(&qp->q.refcnt); + if (!mod_timer_pending(&qp->q.timer, jiffies + qp->q.fqdir->timeout)) return -ETIMEDOUT; - } - sum_truesize = inet_frag_rbtree_purge(&qp->q.rb_fragments, - SKB_DROP_REASON_FRAG_TOO_FAR); - sub_frag_mem_limit(qp->q.fqdir, sum_truesize); + inet_frag_queue_flush(&qp->q, SKB_DROP_REASON_FRAG_TOO_FAR); qp->q.flags = 0; qp->q.len = 0; diff --git a/net/mptcp/Kconfig b/net/mptcp/Kconfig index 20328920f6ed..be71fc9b4638 100644 --- a/net/mptcp/Kconfig +++ b/net/mptcp/Kconfig @@ -4,7 +4,7 @@ config MPTCP depends on INET select SKB_EXTENSIONS select CRYPTO_LIB_SHA256 - select CRYPTO + select CRYPTO_LIB_UTILS help Multipath TCP (MPTCP) connections send and receive data over multiple subflows in order to utilize multiple network paths. Each subflow diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index d5b383870f79..7aa42de9c47b 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -119,7 +119,8 @@ int mptcp_pm_parse_entry(struct nlattr *attr, struct genl_info *info, } if (tb[MPTCP_PM_ADDR_ATTR_FLAGS]) - entry->flags = nla_get_u32(tb[MPTCP_PM_ADDR_ATTR_FLAGS]); + entry->flags = nla_get_u32(tb[MPTCP_PM_ADDR_ATTR_FLAGS]) & + MPTCP_PM_ADDR_FLAGS_MASK; if (tb[MPTCP_PM_ADDR_ATTR_PORT]) entry->addr.port = htons(nla_get_u16(tb[MPTCP_PM_ADDR_ATTR_PORT])); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index e212c1374bd0..9b1fafd87cb9 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1623,7 +1623,7 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags) struct mptcp_sendmsg_info info = { .flags = flags, }; - bool do_check_data_fin = false; + bool copied = false; int push_count = 1; while (mptcp_send_head(sk) && (push_count > 0)) { @@ -1665,7 +1665,7 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags) push_count--; continue; } - do_check_data_fin = true; + copied = true; } } } @@ -1674,11 +1674,14 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags) if (ssk) mptcp_push_release(ssk, &info); - /* ensure the rtx timer is running */ - if (!mptcp_rtx_timer_pending(sk)) - mptcp_reset_rtx_timer(sk); - if (do_check_data_fin) + /* Avoid scheduling the rtx timer if no data has been pushed; the timer + * will be updated on positive acks by __mptcp_cleanup_una(). + */ + if (copied) { + if (!mptcp_rtx_timer_pending(sk)) + mptcp_reset_rtx_timer(sk); mptcp_check_send_data_fin(sk); + } } static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool first) @@ -2766,10 +2769,13 @@ static void __mptcp_retrans(struct sock *sk) /* * make the whole retrans decision, xmit, disallow - * fallback atomic + * fallback atomic, note that we can't retrans even + * when an infinite fallback is in progress, i.e. new + * subflows are disallowed. */ spin_lock_bh(&msk->fallback_lock); - if (__mptcp_check_fallback(msk)) { + if (__mptcp_check_fallback(msk) || + !msk->allow_subflows) { spin_unlock_bh(&msk->fallback_lock); release_sock(ssk); goto clear_scheduled; diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 3162ce3c2640..64c697212578 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -408,6 +408,9 @@ err_put: return -1; err_unreach: + if (!skb->dev) + skb->dev = skb_dst(skb)->dev; + dst_link_failure(skb); return -1; } diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c index f1be4dd5cf85..3654f1e8976c 100644 --- a/net/netfilter/nf_conncount.c +++ b/net/netfilter/nf_conncount.c @@ -172,14 +172,14 @@ static int __nf_conncount_add(struct net *net, struct nf_conn *found_ct; unsigned int collect = 0; bool refcounted = false; + int err = 0; if (!get_ct_or_tuple_from_skb(net, skb, l3num, &ct, &tuple, &zone, &refcounted)) return -ENOENT; if (ct && nf_ct_is_confirmed(ct)) { - if (refcounted) - nf_ct_put(ct); - return -EEXIST; + err = -EEXIST; + goto out_put; } if ((u32)jiffies == list->last_gc) @@ -231,12 +231,16 @@ static int __nf_conncount_add(struct net *net, } add_new_node: - if (WARN_ON_ONCE(list->count > INT_MAX)) - return -EOVERFLOW; + if (WARN_ON_ONCE(list->count > INT_MAX)) { + err = -EOVERFLOW; + goto out_put; + } conn = kmem_cache_alloc(conncount_conn_cachep, GFP_ATOMIC); - if (conn == NULL) - return -ENOMEM; + if (conn == NULL) { + err = -ENOMEM; + goto out_put; + } conn->tuple = tuple; conn->zone = *zone; @@ -249,7 +253,7 @@ add_new_node: out_put: if (refcounted) nf_ct_put(ct); - return 0; + return err; } int nf_conncount_add_skb(struct net *net, @@ -456,11 +460,10 @@ restart: rb_link_node_rcu(&rbconn->node, parent, rbnode); rb_insert_color(&rbconn->node, root); - - if (refcounted) - nf_ct_put(ct); } out_unlock: + if (refcounted) + nf_ct_put(ct); spin_unlock_bh(&nf_conncount_locks[hash]); return count; } diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 0b95f226f211..d1f8eb725d42 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -2487,6 +2487,7 @@ void nf_conntrack_cleanup_net(struct net *net) void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list) { struct nf_ct_iter_data iter_data = {}; + unsigned long start = jiffies; struct net *net; int busy; @@ -2507,6 +2508,8 @@ i_see_dead_people: busy = 1; } if (busy) { + DEBUG_NET_WARN_ONCE(time_after(jiffies, start + 60 * HZ), + "conntrack cleanup blocked for 60s"); schedule(); goto i_see_dead_people; } diff --git a/net/netfilter/nf_flow_table_path.c b/net/netfilter/nf_flow_table_path.c index f0984cf69a09..eb24fe2715dc 100644 --- a/net/netfilter/nf_flow_table_path.c +++ b/net/netfilter/nf_flow_table_path.c @@ -250,6 +250,9 @@ static void nft_dev_forward_path(const struct nft_pktinfo *pkt, if (nft_dev_fill_forward_path(route, dst, ct, dir, ha, &stack) >= 0) nft_dev_path_info(&stack, &info, ha, &ft->data); + if (info.outdev) + route->tuple[dir].out.ifindex = info.outdev->ifindex; + if (!info.indev || !nft_flowtable_find_dev(info.indev, ft)) return; @@ -269,7 +272,6 @@ static void nft_dev_forward_path(const struct nft_pktinfo *pkt, route->tuple[!dir].in.num_encaps = info.num_encaps; route->tuple[!dir].in.ingress_vlans = info.ingress_vlans; - route->tuple[dir].out.ifindex = info.outdev->ifindex; if (info.xmit_type == FLOW_OFFLOAD_XMIT_DIRECT) { memcpy(route->tuple[dir].out.h_source, info.h_source, ETH_ALEN); diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 78a61dac4ade..e6b24586d2fe 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -294,25 +294,13 @@ nf_nat_used_tuple_new(const struct nf_conntrack_tuple *tuple, ct = nf_ct_tuplehash_to_ctrack(thash); - /* NB: IP_CT_DIR_ORIGINAL should be impossible because - * nf_nat_used_tuple() handles origin collisions. - * - * Handle remote chance other CPU confirmed its ct right after. - */ - if (thash->tuple.dst.dir != IP_CT_DIR_REPLY) - goto out; - /* clashing connection subject to NAT? Retry with new tuple. */ if (READ_ONCE(ct->status) & uses_nat) goto out; if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, - &ignored_ct->tuplehash[IP_CT_DIR_REPLY].tuple) && - nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple, - &ignored_ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple)) { + &ignored_ct->tuplehash[IP_CT_DIR_REPLY].tuple)) taken = false; - goto out; - } out: nf_ct_put(ct); return taken; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index f3de2f9bbebf..618af6e90773 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -123,6 +123,29 @@ static void nft_validate_state_update(struct nft_table *table, u8 new_validate_s table->validate_state = new_validate_state; } + +static bool nft_chain_vstate_valid(const struct nft_ctx *ctx, + const struct nft_chain *chain) +{ + const struct nft_base_chain *base_chain; + enum nft_chain_types type; + u8 hooknum; + + if (WARN_ON_ONCE(!nft_is_base_chain(ctx->chain))) + return false; + + base_chain = nft_base_chain(ctx->chain); + hooknum = base_chain->ops.hooknum; + type = base_chain->type->type; + + /* chain is already validated for this call depth */ + if (chain->vstate.depth >= ctx->level && + chain->vstate.hook_mask[type] & BIT(hooknum)) + return true; + + return false; +} + static void nf_tables_trans_destroy_work(struct work_struct *w); static void nft_trans_gc_work(struct work_struct *work); @@ -4079,6 +4102,29 @@ static void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *r nf_tables_rule_destroy(ctx, rule); } +static void nft_chain_vstate_update(const struct nft_ctx *ctx, struct nft_chain *chain) +{ + const struct nft_base_chain *base_chain; + enum nft_chain_types type; + u8 hooknum; + + /* ctx->chain must hold the calling base chain. */ + if (WARN_ON_ONCE(!nft_is_base_chain(ctx->chain))) { + memset(&chain->vstate, 0, sizeof(chain->vstate)); + return; + } + + base_chain = nft_base_chain(ctx->chain); + hooknum = base_chain->ops.hooknum; + type = base_chain->type->type; + + BUILD_BUG_ON(BIT(NF_INET_NUMHOOKS) > U8_MAX); + + chain->vstate.hook_mask[type] |= BIT(hooknum); + if (chain->vstate.depth < ctx->level) + chain->vstate.depth = ctx->level; +} + /** nft_chain_validate - loop detection and hook validation * * @ctx: context containing call depth and base chain @@ -4088,15 +4134,25 @@ static void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *r * and set lookups until either the jump limit is hit or all reachable * chains have been validated. */ -int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain) +int nft_chain_validate(const struct nft_ctx *ctx, struct nft_chain *chain) { struct nft_expr *expr, *last; struct nft_rule *rule; int err; + BUILD_BUG_ON(NFT_JUMP_STACK_SIZE > 255); if (ctx->level == NFT_JUMP_STACK_SIZE) return -EMLINK; + if (ctx->level > 0) { + /* jumps to base chains are not allowed. */ + if (nft_is_base_chain(chain)) + return -ELOOP; + + if (nft_chain_vstate_valid(ctx, chain)) + return 0; + } + list_for_each_entry(rule, &chain->rules, list) { if (fatal_signal_pending(current)) return -EINTR; @@ -4115,8 +4171,11 @@ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain) if (err < 0) return err; } + + cond_resched(); } + nft_chain_vstate_update(ctx, chain); return 0; } EXPORT_SYMBOL_GPL(nft_chain_validate); @@ -4128,7 +4187,7 @@ static int nft_table_validate(struct net *net, const struct nft_table *table) .net = net, .family = table->family, }; - int err; + int err = 0; list_for_each_entry(chain, &table->chains, list) { if (!nft_is_base_chain(chain)) @@ -4137,12 +4196,14 @@ static int nft_table_validate(struct net *net, const struct nft_table *table) ctx.chain = chain; err = nft_chain_validate(&ctx, chain); if (err < 0) - return err; - - cond_resched(); + goto err; } - return 0; +err: + list_for_each_entry(chain, &table->chains, list) + memset(&chain->vstate, 0, sizeof(chain->vstate)); + + return err; } int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set, @@ -11676,21 +11737,10 @@ static int nft_validate_register_store(const struct nft_ctx *ctx, enum nft_data_types type, unsigned int len) { - int err; - switch (reg) { case NFT_REG_VERDICT: if (type != NFT_DATA_VERDICT) return -EINVAL; - - if (data != NULL && - (data->verdict.code == NFT_GOTO || - data->verdict.code == NFT_JUMP)) { - err = nft_chain_validate(ctx, data->verdict.chain); - if (err < 0) - return err; - } - break; default: if (type != NFT_DATA_VALUE) diff --git a/net/netrom/nr_out.c b/net/netrom/nr_out.c index 5e531394a724..2b3cbceb0b52 100644 --- a/net/netrom/nr_out.c +++ b/net/netrom/nr_out.c @@ -43,8 +43,10 @@ void nr_output(struct sock *sk, struct sk_buff *skb) frontlen = skb_headroom(skb); while (skb->len > 0) { - if ((skbn = sock_alloc_send_skb(sk, frontlen + NR_MAX_PACKET_SIZE, 0, &err)) == NULL) + if ((skbn = sock_alloc_send_skb(sk, frontlen + NR_MAX_PACKET_SIZE, 0, &err)) == NULL) { + kfree_skb(skb); return; + } skb_reserve(skbn, frontlen); diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 1cb4f97335d8..2d536901309e 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2802,13 +2802,20 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, return err; } -static bool validate_push_nsh(const struct nlattr *attr, bool log) +static bool validate_push_nsh(const struct nlattr *a, bool log) { + struct nlattr *nsh_key = nla_data(a); struct sw_flow_match match; struct sw_flow_key key; + /* There must be one and only one NSH header. */ + if (!nla_ok(nsh_key, nla_len(a)) || + nla_total_size(nla_len(nsh_key)) != nla_len(a) || + nla_type(nsh_key) != OVS_KEY_ATTR_NSH) + return false; + ovs_match_init(&match, &key, true, NULL); - return !nsh_key_put_from_nlattr(attr, &match, false, true, log); + return !nsh_key_put_from_nlattr(nsh_key, &match, false, true, log); } /* Return false if there are any non-masked bits set. @@ -3389,7 +3396,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, return -EINVAL; } mac_proto = MAC_PROTO_NONE; - if (!validate_push_nsh(nla_data(a), log)) + if (!validate_push_nsh(a, log)) return -EINVAL; break; diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index f27b583def78..91c96cc625bd 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -281,6 +281,15 @@ static int tcf_mirred_to_dev(struct sk_buff *skb, struct tcf_mirred *m, want_ingress = tcf_mirred_act_wants_ingress(m_eaction); + if (dev == skb->dev && want_ingress == at_ingress) { + pr_notice_once("tc mirred: Loop (%s:%s --> %s:%s)\n", + netdev_name(skb->dev), + at_ingress ? "ingress" : "egress", + netdev_name(dev), + want_ingress ? "ingress" : "egress"); + goto err_cant_do; + } + /* All mirred/redirected skbs should clear previous ct info */ nf_reset_ct(skb_to_send); if (want_ingress && !at_ingress) /* drop dst for egress -> ingress */ diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index 82635dd2cfa5..306e046276d4 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -652,7 +652,7 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, sch_tree_lock(sch); for (i = nbands; i < oldbands; i++) { - if (i >= q->nstrict && q->classes[i].qdisc->q.qlen) + if (cl_is_active(&q->classes[i])) list_del_init(&q->classes[i].alist); qdisc_purge_queue(q->classes[i].qdisc); } @@ -664,6 +664,10 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, q->classes[i].deficit = quanta[i]; } } + for (i = q->nstrict; i < nstrict; i++) { + if (cl_is_active(&q->classes[i])) + list_del_init(&q->classes[i].alist); + } WRITE_ONCE(q->nstrict, nstrict); memcpy(q->prio2band, priomap, sizeof(priomap)); diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 069b7e45d8bd..531cb0690007 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -492,6 +492,8 @@ static void sctp_v6_copy_ip_options(struct sock *sk, struct sock *newsk) struct ipv6_pinfo *newnp, *np = inet6_sk(sk); struct ipv6_txoptions *opt; + inet_sk(newsk)->inet_opt = NULL; + newnp = inet6_sk(newsk); rcu_read_lock(); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index d808096f5ab1..2493a5b1fa3c 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4863,8 +4863,6 @@ static struct sock *sctp_clone_sock(struct sock *sk, newsp->pf->to_sk_daddr(&asoc->peer.primary_addr, newsk); newinet->inet_dport = htons(asoc->peer.port); - - newsp->pf->copy_ip_options(sk, newsk); atomic_set(&newinet->inet_id, get_random_u16()); inet_set_bit(MC_LOOP, newsk); @@ -4874,17 +4872,20 @@ static struct sock *sctp_clone_sock(struct sock *sk, #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6) { - struct ipv6_pinfo *newnp = inet6_sk(newsk); + struct ipv6_pinfo *newnp; newinet->pinet6 = &((struct sctp6_sock *)newsk)->inet6; newinet->ipv6_fl_list = NULL; + newnp = inet6_sk(newsk); memcpy(newnp, inet6_sk(sk), sizeof(struct ipv6_pinfo)); newnp->ipv6_mc_list = NULL; newnp->ipv6_ac_list = NULL; } #endif + newsp->pf->copy_ip_options(sk, newsk); + newsp->do_auto_asconf = 0; skb_queue_head_init(&newsp->pd_lobby); diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 78323d43e63e..25f65817faab 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -199,7 +199,7 @@ static void unix_free_vertices(struct scm_fp_list *fpl) } } -static DEFINE_SPINLOCK(unix_gc_lock); +static __cacheline_aligned_in_smp DEFINE_SPINLOCK(unix_gc_lock); void unix_add_edges(struct scm_fp_list *fpl, struct unix_sock *receiver) { diff --git a/tools/net/ynl/Makefile.deps b/tools/net/ynl/Makefile.deps index 865fd2e8519e..08205f9fc525 100644 --- a/tools/net/ynl/Makefile.deps +++ b/tools/net/ynl/Makefile.deps @@ -13,6 +13,7 @@ UAPI_PATH:=../../../../include/uapi/ # need the explicit -D matching what's in /usr, to avoid multiple definitions. get_hdr_inc=-D$(1) -include $(UAPI_PATH)/linux/$(2) +get_hdr_inc2=-D$(1) -D$(2) -include $(UAPI_PATH)/linux/$(3) CFLAGS_devlink:=$(call get_hdr_inc,_LINUX_DEVLINK_H_,devlink.h) CFLAGS_dpll:=$(call get_hdr_inc,_LINUX_DPLL_H,dpll.h) @@ -48,3 +49,4 @@ CFLAGS_tc:= $(call get_hdr_inc,__LINUX_RTNETLINK_H,rtnetlink.h) \ $(call get_hdr_inc,_TC_SKBEDIT_H,tc_act/tc_skbedit.h) \ $(call get_hdr_inc,_TC_TUNNEL_KEY_H,tc_act/tc_tunnel_key.h) CFLAGS_tcp_metrics:=$(call get_hdr_inc,_LINUX_TCP_METRICS_H,tcp_metrics.h) +CFLAGS_wireguard:=$(call get_hdr_inc2,_LINUX_WIREGUARD_H,_WG_UAPI_WIREGUARD_H,wireguard.h) diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c index 10e051b6f592..dadad277f4eb 100644 --- a/tools/testing/selftests/iommu/iommufd.c +++ b/tools/testing/selftests/iommu/iommufd.c @@ -755,9 +755,6 @@ TEST_F(iommufd_ioas, get_hw_info) struct iommu_test_hw_info info; uint64_t trailing_bytes; } buffer_larger; - struct iommu_test_hw_info_buffer_smaller { - __u32 flags; - } buffer_smaller; if (self->device_id) { uint8_t max_pasid = 0; @@ -789,8 +786,9 @@ TEST_F(iommufd_ioas, get_hw_info) * the fields within the size range still gets updated. */ test_cmd_get_hw_info(self->device_id, - IOMMU_HW_INFO_TYPE_DEFAULT, - &buffer_smaller, sizeof(buffer_smaller)); + IOMMU_HW_INFO_TYPE_DEFAULT, &buffer_exact, + offsetofend(struct iommu_test_hw_info, + flags)); test_cmd_get_hw_info_pasid(self->device_id, &max_pasid); ASSERT_EQ(0, max_pasid); if (variant->pasid_capable) { diff --git a/tools/testing/selftests/net/af_unix/Makefile b/tools/testing/selftests/net/af_unix/Makefile index 3cd677b72072..4c0375e28bbe 100644 --- a/tools/testing/selftests/net/af_unix/Makefile +++ b/tools/testing/selftests/net/af_unix/Makefile @@ -1,4 +1,9 @@ -CFLAGS += $(KHDR_INCLUDES) -Wall -Wflex-array-member-not-at-end +top_srcdir := ../../../../.. +include $(top_srcdir)/scripts/Makefile.compiler + +cc-option = $(call __cc-option, $(CC),,$(1),$(2)) + +CFLAGS += $(KHDR_INCLUDES) -Wall $(call cc-option,-Wflex-array-member-not-at-end) TEST_GEN_PROGS := \ diag_uid \ diff --git a/tools/testing/selftests/net/forwarding/config b/tools/testing/selftests/net/forwarding/config index ce64518aaa11..75a6c3d3c1da 100644 --- a/tools/testing/selftests/net/forwarding/config +++ b/tools/testing/selftests/net/forwarding/config @@ -29,6 +29,7 @@ CONFIG_NET_ACT_VLAN=m CONFIG_NET_CLS_BASIC=m CONFIG_NET_CLS_FLOWER=m CONFIG_NET_CLS_MATCHALL=m +CONFIG_NET_CLS_U32=m CONFIG_NET_EMATCH=y CONFIG_NET_EMATCH_META=m CONFIG_NETFILTER=y diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_mc_ul.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_mc_ul.sh index 6a570d256e07..2cf4c6d9245b 100755 --- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_mc_ul.sh +++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_mc_ul.sh @@ -138,13 +138,18 @@ install_capture() defer tc qdisc del dev "$dev" clsact tc filter add dev "$dev" ingress proto ip pref 104 \ - flower skip_hw ip_proto udp dst_port "$VXPORT" \ - action pass + u32 match ip protocol 0x11 0xff \ + match u16 "$VXPORT" 0xffff at 0x16 \ + match u16 0x0800 0xffff at 0x30 \ + action pass defer tc filter del dev "$dev" ingress proto ip pref 104 tc filter add dev "$dev" ingress proto ipv6 pref 106 \ - flower skip_hw ip_proto udp dst_port "$VXPORT" \ - action pass + u32 match ip6 protocol 0x11 0xff \ + match u16 "$VXPORT" 0xffff at 0x2a \ + match u16 0x86dd 0xffff at 0x44 \ + match u8 0x11 0xff at 0x4c \ + action pass defer tc filter del dev "$dev" ingress proto ipv6 pref 106 } @@ -248,13 +253,6 @@ vx_create() } export -f vx_create -vx_wait() -{ - # Wait for all the ARP, IGMP etc. noise to settle down so that the - # tunnel is clear for measurements. - sleep 10 -} - vx10_create() { vx_create vx10 10 id 1000 "$@" @@ -267,18 +265,6 @@ vx20_create() } export -f vx20_create -vx10_create_wait() -{ - vx10_create "$@" - vx_wait -} - -vx20_create_wait() -{ - vx20_create "$@" - vx_wait -} - ns_init_common() { local ns=$1; shift @@ -554,7 +540,7 @@ ipv4_nomcroute() # Install a misleading (S,G) rule to attempt to trick the system into # pushing the packets elsewhere. adf_install_broken_sg - vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$swp2" + vx10_create local 192.0.2.100 group "$GROUP4" dev "$swp2" do_test 4 10 0 "IPv4 nomcroute" } @@ -562,7 +548,7 @@ ipv6_nomcroute() { # Like for IPv4, install a misleading (S,G). adf_install_broken_sg - vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$swp2" + vx20_create local 2001:db8:4::1 group "$GROUP6" dev "$swp2" do_test 6 10 0 "IPv6 nomcroute" } @@ -581,35 +567,35 @@ ipv6_nomcroute_rx() ipv4_mcroute() { adf_install_sg - vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute + vx10_create local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute do_test 4 10 10 "IPv4 mcroute" } ipv6_mcroute() { adf_install_sg - vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute + vx20_create local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute do_test 6 10 10 "IPv6 mcroute" } ipv4_mcroute_rx() { adf_install_sg - vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute + vx10_create local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute ipv4_do_test_rx 0 "IPv4 mcroute ping" } ipv6_mcroute_rx() { adf_install_sg - vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute + vx20_create local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute ipv6_do_test_rx 0 "IPv6 mcroute ping" } ipv4_mcroute_changelink() { adf_install_sg - vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" + vx10_create local 192.0.2.100 group "$GROUP4" dev "$IPMR" ip link set dev vx10 type vxlan mcroute sleep 1 do_test 4 10 10 "IPv4 mcroute changelink" @@ -618,7 +604,7 @@ ipv4_mcroute_changelink() ipv6_mcroute_changelink() { adf_install_sg - vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute + vx20_create local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute ip link set dev vx20 type vxlan mcroute sleep 1 do_test 6 10 10 "IPv6 mcroute changelink" @@ -627,47 +613,47 @@ ipv6_mcroute_changelink() ipv4_mcroute_starg() { adf_install_starg - vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute + vx10_create local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute do_test 4 10 10 "IPv4 mcroute (*,G)" } ipv6_mcroute_starg() { adf_install_starg - vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute + vx20_create local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute do_test 6 10 10 "IPv6 mcroute (*,G)" } ipv4_mcroute_starg_rx() { adf_install_starg - vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute + vx10_create local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute ipv4_do_test_rx 0 "IPv4 mcroute (*,G) ping" } ipv6_mcroute_starg_rx() { adf_install_starg - vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute + vx20_create local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute ipv6_do_test_rx 0 "IPv6 mcroute (*,G) ping" } ipv4_mcroute_noroute() { - vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute + vx10_create local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute do_test 4 0 0 "IPv4 mcroute, no route" } ipv6_mcroute_noroute() { - vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute + vx20_create local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute do_test 6 0 0 "IPv6 mcroute, no route" } ipv4_mcroute_fdb() { adf_install_sg - vx10_create_wait local 192.0.2.100 dev "$IPMR" mcroute + vx10_create local 192.0.2.100 dev "$IPMR" mcroute bridge fdb add dev vx10 \ 00:00:00:00:00:00 self static dst "$GROUP4" via "$IPMR" do_test 4 10 10 "IPv4 mcroute FDB" @@ -676,7 +662,7 @@ ipv4_mcroute_fdb() ipv6_mcroute_fdb() { adf_install_sg - vx20_create_wait local 2001:db8:4::1 dev "$IPMR" mcroute + vx20_create local 2001:db8:4::1 dev "$IPMR" mcroute bridge -6 fdb add dev vx20 \ 00:00:00:00:00:00 self static dst "$GROUP6" via "$IPMR" do_test 6 10 10 "IPv6 mcroute FDB" @@ -686,7 +672,7 @@ ipv6_mcroute_fdb() ipv4_mcroute_fdb_oif0() { adf_install_sg - vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute + vx10_create local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute bridge fdb del dev vx10 00:00:00:00:00:00 bridge fdb add dev vx10 00:00:00:00:00:00 self static dst "$GROUP4" do_test 4 10 10 "IPv4 mcroute oif=0" @@ -703,7 +689,7 @@ ipv6_mcroute_fdb_oif0() defer ip -6 route del table local multicast "$GROUP6/128" dev "$IPMR" adf_install_sg - vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute + vx20_create local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute bridge -6 fdb del dev vx20 00:00:00:00:00:00 bridge -6 fdb add dev vx20 00:00:00:00:00:00 self static dst "$GROUP6" do_test 6 10 10 "IPv6 mcroute oif=0" @@ -716,7 +702,7 @@ ipv4_mcroute_fdb_oif0_sep() adf_install_sg_sep adf_ip_addr_add lo 192.0.2.120/28 - vx10_create_wait local 192.0.2.120 group "$GROUP4" dev "$IPMR" mcroute + vx10_create local 192.0.2.120 group "$GROUP4" dev "$IPMR" mcroute bridge fdb del dev vx10 00:00:00:00:00:00 bridge fdb add dev vx10 00:00:00:00:00:00 self static dst "$GROUP4" do_test 4 10 10 "IPv4 mcroute TX!=RX oif=0" @@ -727,7 +713,7 @@ ipv4_mcroute_fdb_oif0_sep_rx() adf_install_sg_sep_rx lo adf_ip_addr_add lo 192.0.2.120/28 - vx10_create_wait local 192.0.2.120 group "$GROUP4" dev "$IPMR" mcroute + vx10_create local 192.0.2.120 group "$GROUP4" dev "$IPMR" mcroute bridge fdb del dev vx10 00:00:00:00:00:00 bridge fdb add dev vx10 00:00:00:00:00:00 self static dst "$GROUP4" ipv4_do_test_rx 0 "IPv4 mcroute TX!=RX oif=0 ping" @@ -738,7 +724,7 @@ ipv4_mcroute_fdb_sep_rx() adf_install_sg_sep_rx lo adf_ip_addr_add lo 192.0.2.120/28 - vx10_create_wait local 192.0.2.120 group "$GROUP4" dev "$IPMR" mcroute + vx10_create local 192.0.2.120 group "$GROUP4" dev "$IPMR" mcroute bridge fdb del dev vx10 00:00:00:00:00:00 bridge fdb add \ dev vx10 00:00:00:00:00:00 self static dst "$GROUP4" via lo @@ -750,7 +736,7 @@ ipv6_mcroute_fdb_sep_rx() adf_install_sg_sep_rx "X$IPMR" adf_ip_addr_add "X$IPMR" 2001:db8:5::1/64 - vx20_create_wait local 2001:db8:5::1 group "$GROUP6" dev "$IPMR" mcroute + vx20_create local 2001:db8:5::1 group "$GROUP6" dev "$IPMR" mcroute bridge -6 fdb del dev vx20 00:00:00:00:00:00 bridge -6 fdb add dev vx20 00:00:00:00:00:00 \ self static dst "$GROUP6" via "X$IPMR" diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index f448bafb3f20..0ec131b339bc 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -280,7 +280,8 @@ tc_rule_stats_get() local selector=${1:-.packets}; shift tc -j -s filter show dev $dev $dir pref $pref \ - | jq ".[1].options.actions[].stats$selector" + | jq ".[] | select(.options.actions) | + .options.actions[].stats$selector" } tc_rule_handle_stats_get() diff --git a/tools/testing/selftests/net/lib/ksft.h b/tools/testing/selftests/net/lib/ksft.h index 17dc34a612c6..03912902a6d3 100644 --- a/tools/testing/selftests/net/lib/ksft.h +++ b/tools/testing/selftests/net/lib/ksft.h @@ -24,7 +24,8 @@ static inline void ksft_ready(void) fd = STDOUT_FILENO; } - write(fd, msg, sizeof(msg)); + if (write(fd, msg, sizeof(msg)) < 0) + perror("write()"); if (fd != STDOUT_FILENO) close(fd); } @@ -48,7 +49,8 @@ static inline void ksft_wait(void) fd = STDIN_FILENO; } - read(fd, &byte, sizeof(byte)); + if (read(fd, &byte, sizeof(byte)) < 0) + perror("read()"); if (fd != STDIN_FILENO) close(fd); } diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index ec6a87588191..123d9d7a0278 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -192,6 +192,10 @@ check "show_endpoints" \ flush_endpoint check "show_endpoints" "" "flush addrs" +add_endpoint 10.0.1.1 flags unknown +check "show_endpoints" "$(format_endpoints "1,10.0.1.1")" "ignore unknown flags" +flush_endpoint + set_limits 9 1 2>/dev/null check "get_limits" "${default_limits}" "rcv addrs above hard limit" diff --git a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c index 65b374232ff5..99eecccbf0c8 100644 --- a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c +++ b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c @@ -24,6 +24,8 @@ #define IPPROTO_MPTCP 262 #endif +#define MPTCP_PM_ADDR_FLAG_UNKNOWN _BITUL(7) + static void syntax(char *argv[]) { fprintf(stderr, "%s add|ann|rem|csf|dsf|get|set|del|flush|dump|events|listen|accept [<args>]\n", argv[0]); @@ -836,6 +838,8 @@ int add_addr(int fd, int pm_family, int argc, char *argv[]) flags |= MPTCP_PM_ADDR_FLAG_BACKUP; else if (!strcmp(tok, "fullmesh")) flags |= MPTCP_PM_ADDR_FLAG_FULLMESH; + else if (!strcmp(tok, "unknown")) + flags |= MPTCP_PM_ADDR_FLAG_UNKNOWN; else error(1, errno, "unknown flag %s", argv[arg]); @@ -1048,6 +1052,13 @@ static void print_addr(struct rtattr *attrs, int len) printf(","); } + if (flags & MPTCP_PM_ADDR_FLAG_UNKNOWN) { + printf("unknown"); + flags &= ~MPTCP_PM_ADDR_FLAG_UNKNOWN; + if (flags) + printf(","); + } + /* bump unknown flags, if any */ if (flags) printf("0x%x", flags); diff --git a/tools/testing/selftests/net/netfilter/conntrack_clash.sh b/tools/testing/selftests/net/netfilter/conntrack_clash.sh index 7fc6c5dbd551..84b8eb12143a 100755 --- a/tools/testing/selftests/net/netfilter/conntrack_clash.sh +++ b/tools/testing/selftests/net/netfilter/conntrack_clash.sh @@ -116,7 +116,7 @@ run_one_clash_test() # not a failure: clash resolution logic did not trigger. # With right timing, xmit completed sequentially and # no parallel insertion occurs. - return $ksft_skip + return $ksft_xfail } run_clash_test() @@ -133,12 +133,12 @@ run_clash_test() if [ $rv -eq 0 ];then echo "PASS: clash resolution test for $daddr:$dport on attempt $i" return 0 - elif [ $rv -eq $ksft_skip ]; then + elif [ $rv -eq $ksft_xfail ]; then softerr=1 fi done - [ $softerr -eq 1 ] && echo "SKIP: clash resolution for $daddr:$dport did not trigger" + [ $softerr -eq 1 ] && echo "XFAIL: clash resolution for $daddr:$dport did not trigger" } ip link add veth0 netns "$nsclient1" type veth peer name veth0 netns "$nsrouter" @@ -167,8 +167,7 @@ load_simple_ruleset "$nsclient2" run_clash_test "$nsclient2" "$nsclient2" 127.0.0.1 9001 if [ $clash_resolution_active -eq 0 ];then - [ "$ret" -eq 0 ] && ret=$ksft_skip - echo "SKIP: Clash resolution did not trigger" + [ "$ret" -eq 0 ] && ret=$ksft_xfail fi exit $ret diff --git a/tools/testing/selftests/net/netfilter/conntrack_reverse_clash.c b/tools/testing/selftests/net/netfilter/conntrack_reverse_clash.c index 507930cee8cb..462d628cc3bd 100644 --- a/tools/testing/selftests/net/netfilter/conntrack_reverse_clash.c +++ b/tools/testing/selftests/net/netfilter/conntrack_reverse_clash.c @@ -33,9 +33,14 @@ static void die(const char *e) exit(111); } -static void die_port(uint16_t got, uint16_t want) +static void die_port(const struct sockaddr_in *sin, uint16_t want) { - fprintf(stderr, "Port number changed, wanted %d got %d\n", want, ntohs(got)); + uint16_t got = ntohs(sin->sin_port); + char str[INET_ADDRSTRLEN]; + + inet_ntop(AF_INET, &sin->sin_addr, str, sizeof(str)); + + fprintf(stderr, "Port number changed, wanted %d got %d from %s\n", want, got, str); exit(1); } @@ -100,7 +105,7 @@ int main(int argc, char *argv[]) die("child recvfrom"); if (peer.sin_port != htons(PORT)) - die_port(peer.sin_port, PORT); + die_port(&peer, PORT); } else { if (sendto(s2, buf, LEN, 0, (struct sockaddr *)&sa1, sizeof(sa1)) != LEN) continue; @@ -109,7 +114,7 @@ int main(int argc, char *argv[]) die("parent recvfrom"); if (peer.sin_port != htons((PORT + 1))) - die_port(peer.sin_port, PORT + 1); + die_port(&peer, PORT + 1); } } diff --git a/tools/testing/selftests/net/netfilter/conntrack_reverse_clash.sh b/tools/testing/selftests/net/netfilter/conntrack_reverse_clash.sh index a24c896347a8..dc7e9d6da062 100755 --- a/tools/testing/selftests/net/netfilter/conntrack_reverse_clash.sh +++ b/tools/testing/selftests/net/netfilter/conntrack_reverse_clash.sh @@ -45,6 +45,8 @@ if ip netns exec "$ns0" ./conntrack_reverse_clash; then echo "PASS: No SNAT performed for null bindings" else echo "ERROR: SNAT performed without any matching snat rule" + ip netns exec "$ns0" conntrack -L + ip netns exec "$ns0" conntrack -S exit 1 fi diff --git a/tools/testing/selftests/net/netfilter/packetdrill/conntrack_syn_challenge_ack.pkt b/tools/testing/selftests/net/netfilter/packetdrill/conntrack_syn_challenge_ack.pkt index 3442cd29bc93..cdb3910af95b 100644 --- a/tools/testing/selftests/net/netfilter/packetdrill/conntrack_syn_challenge_ack.pkt +++ b/tools/testing/selftests/net/netfilter/packetdrill/conntrack_syn_challenge_ack.pkt @@ -26,7 +26,7 @@ +0.01 > R 643160523:643160523(0) win 0 -+0.01 `conntrack -f $NFCT_IP_VERSION -L -p tcp --dport 8080 2>/dev/null | grep UNREPLIED | grep -q SYN_SENT` ++0.1 `conntrack -f $NFCT_IP_VERSION -L -p tcp --dport 8080 2>/dev/null | grep UNREPLIED | grep -q SYN_SENT` // Must go through. +0.01 > S 0:0(0) win 65535 <mss 1460,sackOK,TS val 1 ecr 0,nop,wscale 8> diff --git a/tools/testing/selftests/net/tfo.c b/tools/testing/selftests/net/tfo.c index eb3cac5e583c..8d82140f0f76 100644 --- a/tools/testing/selftests/net/tfo.c +++ b/tools/testing/selftests/net/tfo.c @@ -81,7 +81,8 @@ static void run_server(void) if (getsockopt(connfd, SOL_SOCKET, SO_INCOMING_NAPI_ID, &opt, &len) < 0) error(1, errno, "getsockopt(SO_INCOMING_NAPI_ID)"); - read(connfd, buf, 64); + if (read(connfd, buf, 64) < 0) + perror("read()"); fprintf(outfile, "%d\n", opt); fclose(outfile); diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index a3ef4b57eb5f..a4d16a460fbe 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -2786,10 +2786,10 @@ TEST_F(tls_err, epoll_partial_rec) TEST_F(tls_err, poll_partial_rec_async) { struct pollfd pfd = { }; + char token = '\0'; ssize_t rec_len; char rec[256]; char buf[128]; - char token; int p[2]; int ret; diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json index b73bd255ea36..da156feabcbf 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json @@ -1052,5 +1052,51 @@ "$TC qdisc del dev $DEV1 ingress_block 21 clsact", "$TC actions flush action mirred" ] + }, + { + "id": "7eba", + "name": "Redirect multiport: dummy egress -> dummy egress (Loop)", + "category": [ + "filter", + "mirred" + ], + "plugins": { + "requires": [ + "nsPlugin" + ] + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.10.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY handle 1: root drr", + "$TC filter add dev $DUMMY parent 1: protocol ip prio 10 matchall action mirred egress redirect dev $DUMMY index 1" + ], + "cmdUnderTest": "ping -c1 -W0.01 -I $DUMMY 10.10.10.1", + "expExitCode": "1", + "verifyCmd": "$TC -j -s actions get action mirred index 1", + "matchJSON": [ + { + "total acts": 0 + }, + { + "actions": [ + { + "order": 1, + "kind": "mirred", + "mirred_action": "redirect", + "direction": "egress", + "index": 1, + "stats": { + "packets": 1, + "overlimits": 1 + }, + "not_in_hw": true + } + ] + } + ], + "teardown": [ + "$TC qdisc del dev $DUMMY root" + ] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json index 47de27fd4f90..6a39640aa2a8 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json +++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json @@ -1033,5 +1033,83 @@ "teardown": [ "$TC qdisc del dev $DUMMY handle 1: root" ] + }, + { + "id": "6e4f", + "name": "Try to delete ets drr class' qdisc while still keeping it in the active list", + "category": [ + "qdisc", + "ets", + "tbf" + ], + "plugins": { + "requires": [ + "nsPlugin", + "scapyPlugin" + ] + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.11.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: ets bands 2 strict 1", + "$TC qdisc add dev $DUMMY parent 1:2 handle 20: tbf rate 8bit burst 100b latency 1s", + "$TC filter add dev $DUMMY parent 1: basic classid 1:2", + "ping -c2 -W0.01 -s 56 -I $DUMMY 10.10.11.11 || true", + "$TC qdisc change dev $DUMMY root handle 1: ets bands 2 strict 2", + "$TC qdisc change dev $DUMMY root handle 1: ets bands 1 strict 1" + ], + "cmdUnderTest": "ping -c1 -W0.01 -s 56 -I $DUMMY 10.10.11.11", + "expExitCode": "1", + "verifyCmd": "$TC -s -j qdisc ls dev $DUMMY root", + "matchJSON": [ + { + "kind": "ets", + "handle": "1:", + "bytes": 196, + "packets": 2 + } + ], + "teardown": [ + "$TC qdisc del dev $DUMMY root handle 1:" + ] + }, + { + "id": "0b8f", + "name": "Try to add ets class to the active list twice", + "category": [ + "qdisc", + "ets", + "tbf" + ], + "plugins": { + "requires": [ + "nsPlugin", + "scapyPlugin" + ] + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.11.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: ets bands 2 strict 1", + "$TC qdisc add dev $DUMMY parent 1:2 handle 20: tbf rate 8bit burst 100b latency 1s", + "$TC filter add dev $DUMMY parent 1: basic classid 1:2", + "ping -c2 -W0.01 -s 56 -I $DUMMY 10.10.11.11 || true", + "$TC qdisc change dev $DUMMY root handle 1: ets bands 2 strict 2", + "$TC qdisc change dev $DUMMY root handle 1: ets bands 2 strict 1" + ], + "cmdUnderTest": "ping -c1 -W0.01 -s 56 -I $DUMMY 10.10.11.11", + "expExitCode": "1", + "verifyCmd": "$TC -s -j qdisc ls dev $DUMMY root", + "matchJSON": [ + { + "kind": "ets", + "handle": "1:", + "bytes": 98, + "packets": 1 + } + ], + "teardown": [ + "$TC qdisc del dev $DUMMY root handle 1:" + ] } ] diff --git a/tools/testing/selftests/ublk/Makefile b/tools/testing/selftests/ublk/Makefile index 770269efe42a..837977b62417 100644 --- a/tools/testing/selftests/ublk/Makefile +++ b/tools/testing/selftests/ublk/Makefile @@ -21,24 +21,32 @@ TEST_PROGS += test_generic_10.sh TEST_PROGS += test_generic_11.sh TEST_PROGS += test_generic_12.sh TEST_PROGS += test_generic_13.sh +TEST_PROGS += test_generic_14.sh TEST_PROGS += test_null_01.sh TEST_PROGS += test_null_02.sh +TEST_PROGS += test_null_03.sh TEST_PROGS += test_loop_01.sh TEST_PROGS += test_loop_02.sh TEST_PROGS += test_loop_03.sh TEST_PROGS += test_loop_04.sh TEST_PROGS += test_loop_05.sh +TEST_PROGS += test_loop_06.sh +TEST_PROGS += test_loop_07.sh TEST_PROGS += test_stripe_01.sh TEST_PROGS += test_stripe_02.sh TEST_PROGS += test_stripe_03.sh TEST_PROGS += test_stripe_04.sh +TEST_PROGS += test_stripe_05.sh +TEST_PROGS += test_stripe_06.sh TEST_PROGS += test_stress_01.sh TEST_PROGS += test_stress_02.sh TEST_PROGS += test_stress_03.sh TEST_PROGS += test_stress_04.sh TEST_PROGS += test_stress_05.sh +TEST_PROGS += test_stress_06.sh +TEST_PROGS += test_stress_07.sh TEST_GEN_PROGS_EXTENDED = kublk diff --git a/tools/testing/selftests/ublk/file_backed.c b/tools/testing/selftests/ublk/file_backed.c index cd9fe69ecce2..269d5f124e06 100644 --- a/tools/testing/selftests/ublk/file_backed.c +++ b/tools/testing/selftests/ublk/file_backed.c @@ -34,8 +34,9 @@ static int loop_queue_tgt_rw_io(struct ublk_thread *t, struct ublk_queue *q, unsigned zc = ublk_queue_use_zc(q); unsigned auto_zc = ublk_queue_use_auto_zc(q); enum io_uring_op op = ublk_to_uring_op(iod, zc | auto_zc); + struct ublk_io *io = ublk_get_io(q, tag); struct io_uring_sqe *sqe[3]; - void *addr = (zc | auto_zc) ? NULL : (void *)iod->addr; + void *addr = io->buf_addr; if (!zc || auto_zc) { ublk_io_alloc_sqes(t, sqe, 1); @@ -56,7 +57,7 @@ static int loop_queue_tgt_rw_io(struct ublk_thread *t, struct ublk_queue *q, ublk_io_alloc_sqes(t, sqe, 3); - io_uring_prep_buf_register(sqe[0], q, tag, q->q_id, ublk_get_io(q, tag)->buf_index); + io_uring_prep_buf_register(sqe[0], q, tag, q->q_id, io->buf_index); sqe[0]->flags |= IOSQE_CQE_SKIP_SUCCESS | IOSQE_IO_HARDLINK; sqe[0]->user_data = build_user_data(tag, ublk_cmd_op_nr(sqe[0]->cmd_op), 0, q->q_id, 1); @@ -68,7 +69,7 @@ static int loop_queue_tgt_rw_io(struct ublk_thread *t, struct ublk_queue *q, sqe[1]->flags |= IOSQE_FIXED_FILE | IOSQE_IO_HARDLINK; sqe[1]->user_data = build_user_data(tag, ublk_op, 0, q->q_id, 1); - io_uring_prep_buf_unregister(sqe[2], q, tag, q->q_id, ublk_get_io(q, tag)->buf_index); + io_uring_prep_buf_unregister(sqe[2], q, tag, q->q_id, io->buf_index); sqe[2]->user_data = build_user_data(tag, ublk_cmd_op_nr(sqe[2]->cmd_op), 0, q->q_id, 1); return 2; diff --git a/tools/testing/selftests/ublk/kublk.c b/tools/testing/selftests/ublk/kublk.c index f8fa102a627f..185ba553686a 100644 --- a/tools/testing/selftests/ublk/kublk.c +++ b/tools/testing/selftests/ublk/kublk.c @@ -596,6 +596,38 @@ static void ublk_set_auto_buf_reg(const struct ublk_queue *q, sqe->addr = ublk_auto_buf_reg_to_sqe_addr(&buf); } +/* Copy in pieces to test the buffer offset logic */ +#define UBLK_USER_COPY_LEN 2048 + +static void ublk_user_copy(const struct ublk_io *io, __u8 match_ublk_op) +{ + const struct ublk_queue *q = ublk_io_to_queue(io); + const struct ublksrv_io_desc *iod = ublk_get_iod(q, io->tag); + __u64 off = ublk_user_copy_offset(q->q_id, io->tag); + __u8 ublk_op = ublksrv_get_op(iod); + __u32 len = iod->nr_sectors << 9; + void *addr = io->buf_addr; + + if (ublk_op != match_ublk_op) + return; + + while (len) { + __u32 copy_len = min(len, UBLK_USER_COPY_LEN); + ssize_t copied; + + if (ublk_op == UBLK_IO_OP_WRITE) + copied = pread(q->ublk_fd, addr, copy_len, off); + else if (ublk_op == UBLK_IO_OP_READ) + copied = pwrite(q->ublk_fd, addr, copy_len, off); + else + assert(0); + assert(copied == (ssize_t)copy_len); + addr += copy_len; + off += copy_len; + len -= copy_len; + } +} + int ublk_queue_io_cmd(struct ublk_thread *t, struct ublk_io *io) { struct ublk_queue *q = ublk_io_to_queue(io); @@ -618,9 +650,12 @@ int ublk_queue_io_cmd(struct ublk_thread *t, struct ublk_io *io) if (io->flags & UBLKS_IO_NEED_GET_DATA) cmd_op = UBLK_U_IO_NEED_GET_DATA; - else if (io->flags & UBLKS_IO_NEED_COMMIT_RQ_COMP) + else if (io->flags & UBLKS_IO_NEED_COMMIT_RQ_COMP) { + if (ublk_queue_use_user_copy(q)) + ublk_user_copy(io, UBLK_IO_OP_READ); + cmd_op = UBLK_U_IO_COMMIT_AND_FETCH_REQ; - else if (io->flags & UBLKS_IO_NEED_FETCH_RQ) + } else if (io->flags & UBLKS_IO_NEED_FETCH_RQ) cmd_op = UBLK_U_IO_FETCH_REQ; if (io_uring_sq_space_left(&t->ring) < 1) @@ -649,7 +684,7 @@ int ublk_queue_io_cmd(struct ublk_thread *t, struct ublk_io *io) sqe[0]->rw_flags = 0; cmd->tag = io->tag; cmd->q_id = q->q_id; - if (!ublk_queue_no_buf(q)) + if (!ublk_queue_no_buf(q) && !ublk_queue_use_user_copy(q)) cmd->addr = (__u64) (uintptr_t) io->buf_addr; else cmd->addr = 0; @@ -751,6 +786,10 @@ static void ublk_handle_uring_cmd(struct ublk_thread *t, if (cqe->res == UBLK_IO_RES_OK) { assert(tag < q->q_depth); + + if (ublk_queue_use_user_copy(q)) + ublk_user_copy(io, UBLK_IO_OP_WRITE); + if (q->tgt_ops->queue_io) q->tgt_ops->queue_io(t, q, tag); } else if (cqe->res == UBLK_IO_RES_NEED_GET_DATA) { @@ -1507,7 +1546,7 @@ static void __cmd_create_help(char *exe, bool recovery) printf("%s %s -t [null|loop|stripe|fault_inject] [-q nr_queues] [-d depth] [-n dev_id]\n", exe, recovery ? "recover" : "add"); - printf("\t[--foreground] [--quiet] [-z] [--auto_zc] [--auto_zc_fallback] [--debug_mask mask] [-r 0|1 ] [-g]\n"); + printf("\t[--foreground] [--quiet] [-z] [--auto_zc] [--auto_zc_fallback] [--debug_mask mask] [-r 0|1] [-g] [-u]\n"); printf("\t[-e 0|1 ] [-i 0|1] [--no_ublk_fixed_fd]\n"); printf("\t[--nthreads threads] [--per_io_tasks]\n"); printf("\t[target options] [backfile1] [backfile2] ...\n"); @@ -1568,6 +1607,7 @@ int main(int argc, char *argv[]) { "get_data", 1, NULL, 'g'}, { "auto_zc", 0, NULL, 0 }, { "auto_zc_fallback", 0, NULL, 0 }, + { "user_copy", 0, NULL, 'u'}, { "size", 1, NULL, 's'}, { "nthreads", 1, NULL, 0 }, { "per_io_tasks", 0, NULL, 0 }, @@ -1593,7 +1633,7 @@ int main(int argc, char *argv[]) opterr = 0; optind = 2; - while ((opt = getopt_long(argc, argv, "t:n:d:q:r:e:i:s:gaz", + while ((opt = getopt_long(argc, argv, "t:n:d:q:r:e:i:s:gazu", longopts, &option_idx)) != -1) { switch (opt) { case 'a': @@ -1613,7 +1653,7 @@ int main(int argc, char *argv[]) ctx.queue_depth = strtol(optarg, NULL, 10); break; case 'z': - ctx.flags |= UBLK_F_SUPPORT_ZERO_COPY | UBLK_F_USER_COPY; + ctx.flags |= UBLK_F_SUPPORT_ZERO_COPY; break; case 'r': value = strtol(optarg, NULL, 10); @@ -1633,6 +1673,9 @@ int main(int argc, char *argv[]) case 'g': ctx.flags |= UBLK_F_NEED_GET_DATA; break; + case 'u': + ctx.flags |= UBLK_F_USER_COPY; + break; case 's': ctx.size = strtoull(optarg, NULL, 10); break; @@ -1686,6 +1729,15 @@ int main(int argc, char *argv[]) return -EINVAL; } + if (!!(ctx.flags & UBLK_F_NEED_GET_DATA) + + !!(ctx.flags & UBLK_F_USER_COPY) + + (ctx.flags & UBLK_F_SUPPORT_ZERO_COPY && !ctx.auto_zc_fallback) + + (ctx.flags & UBLK_F_AUTO_BUF_REG && !ctx.auto_zc_fallback) + + ctx.auto_zc_fallback > 1) { + fprintf(stderr, "too many data copy modes specified\n"); + return -EINVAL; + } + i = optind; while (i < argc && ctx.nr_files < MAX_BACK_FILES) { ctx.files[ctx.nr_files++] = argv[i++]; diff --git a/tools/testing/selftests/ublk/kublk.h b/tools/testing/selftests/ublk/kublk.h index fe42705c6d42..8a83b90ec603 100644 --- a/tools/testing/selftests/ublk/kublk.h +++ b/tools/testing/selftests/ublk/kublk.h @@ -208,6 +208,12 @@ static inline int ublk_io_auto_zc_fallback(const struct ublksrv_io_desc *iod) return !!(iod->op_flags & UBLK_IO_F_NEED_REG_BUF); } +static inline __u64 ublk_user_copy_offset(unsigned q_id, unsigned tag) +{ + return UBLKSRV_IO_BUF_OFFSET + + ((__u64)q_id << UBLK_QID_OFF | (__u64)tag << UBLK_TAG_OFF); +} + static inline int is_target_io(__u64 user_data) { return (user_data & (1ULL << 63)) != 0; @@ -390,19 +396,24 @@ static inline int ublk_completed_tgt_io(struct ublk_thread *t, return --io->tgt_ios == 0; } -static inline int ublk_queue_use_zc(const struct ublk_queue *q) +static inline bool ublk_queue_use_zc(const struct ublk_queue *q) +{ + return !!(q->flags & UBLK_F_SUPPORT_ZERO_COPY); +} + +static inline bool ublk_queue_use_auto_zc(const struct ublk_queue *q) { - return q->flags & UBLK_F_SUPPORT_ZERO_COPY; + return !!(q->flags & UBLK_F_AUTO_BUF_REG); } -static inline int ublk_queue_use_auto_zc(const struct ublk_queue *q) +static inline bool ublk_queue_auto_zc_fallback(const struct ublk_queue *q) { - return q->flags & UBLK_F_AUTO_BUF_REG; + return !!(q->flags & UBLKS_Q_AUTO_BUF_REG_FALLBACK); } -static inline int ublk_queue_auto_zc_fallback(const struct ublk_queue *q) +static inline bool ublk_queue_use_user_copy(const struct ublk_queue *q) { - return q->flags & UBLKS_Q_AUTO_BUF_REG_FALLBACK; + return !!(q->flags & UBLK_F_USER_COPY); } static inline int ublk_queue_no_buf(const struct ublk_queue *q) diff --git a/tools/testing/selftests/ublk/stripe.c b/tools/testing/selftests/ublk/stripe.c index 791fa8dc1651..fd412e1f01c0 100644 --- a/tools/testing/selftests/ublk/stripe.c +++ b/tools/testing/selftests/ublk/stripe.c @@ -134,7 +134,7 @@ static int stripe_queue_tgt_rw_io(struct ublk_thread *t, struct ublk_queue *q, struct stripe_array *s = alloc_stripe_array(conf, iod); struct ublk_io *io = ublk_get_io(q, tag); int i, extra = zc ? 2 : 0; - void *base = (zc | auto_zc) ? NULL : (void *)iod->addr; + void *base = io->buf_addr; io->private_data = s; calculate_stripe_array(conf, iod, s, base); diff --git a/tools/testing/selftests/ublk/test_common.sh b/tools/testing/selftests/ublk/test_common.sh index 8a4dbd09feb0..6f1c042de40e 100755 --- a/tools/testing/selftests/ublk/test_common.sh +++ b/tools/testing/selftests/ublk/test_common.sh @@ -333,11 +333,12 @@ run_io_and_kill_daemon() run_io_and_recover() { - local action=$1 + local size=$1 + local action=$2 local state local dev_id - shift 1 + shift 2 dev_id=$(_add_ublk_dev "$@") _check_add_dev "$TID" $? diff --git a/tools/testing/selftests/ublk/test_generic_04.sh b/tools/testing/selftests/ublk/test_generic_04.sh index 8b533217d4a1..baf5b156193d 100755 --- a/tools/testing/selftests/ublk/test_generic_04.sh +++ b/tools/testing/selftests/ublk/test_generic_04.sh @@ -8,7 +8,7 @@ ERR_CODE=0 ublk_run_recover_test() { - run_io_and_recover "kill_daemon" "$@" + run_io_and_recover 256M "kill_daemon" "$@" ERR_CODE=$? if [ ${ERR_CODE} -ne 0 ]; then echo "$TID failure: $*" diff --git a/tools/testing/selftests/ublk/test_generic_05.sh b/tools/testing/selftests/ublk/test_generic_05.sh index 398e9e2b58e1..7b5083afc02a 100755 --- a/tools/testing/selftests/ublk/test_generic_05.sh +++ b/tools/testing/selftests/ublk/test_generic_05.sh @@ -8,7 +8,7 @@ ERR_CODE=0 ublk_run_recover_test() { - run_io_and_recover "kill_daemon" "$@" + run_io_and_recover 256M "kill_daemon" "$@" ERR_CODE=$? if [ ${ERR_CODE} -ne 0 ]; then echo "$TID failure: $*" diff --git a/tools/testing/selftests/ublk/test_generic_11.sh b/tools/testing/selftests/ublk/test_generic_11.sh index a00357a5ec6b..d1f973c8c645 100755 --- a/tools/testing/selftests/ublk/test_generic_11.sh +++ b/tools/testing/selftests/ublk/test_generic_11.sh @@ -8,7 +8,7 @@ ERR_CODE=0 ublk_run_quiesce_recover() { - run_io_and_recover "quiesce_dev" "$@" + run_io_and_recover 256M "quiesce_dev" "$@" ERR_CODE=$? if [ ${ERR_CODE} -ne 0 ]; then echo "$TID failure: $*" diff --git a/tools/testing/selftests/ublk/test_generic_14.sh b/tools/testing/selftests/ublk/test_generic_14.sh new file mode 100755 index 000000000000..cd9b44b97c24 --- /dev/null +++ b/tools/testing/selftests/ublk/test_generic_14.sh @@ -0,0 +1,40 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh + +TID="generic_14" +ERR_CODE=0 + +ublk_run_recover_test() +{ + run_io_and_recover 256M "kill_daemon" "$@" + ERR_CODE=$? + if [ ${ERR_CODE} -ne 0 ]; then + echo "$TID failure: $*" + _show_result $TID $ERR_CODE + fi +} + +if ! _have_program fio; then + exit "$UBLK_SKIP_CODE" +fi + +_prep_test "recover" "basic recover function verification (user copy)" + +_create_backfile 0 256M +_create_backfile 1 128M +_create_backfile 2 128M + +ublk_run_recover_test -t null -q 2 -r 1 -u & +ublk_run_recover_test -t loop -q 2 -r 1 -u "${UBLK_BACKFILES[0]}" & +ublk_run_recover_test -t stripe -q 2 -r 1 -u "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & +wait + +ublk_run_recover_test -t null -q 2 -r 1 -u -i 1 & +ublk_run_recover_test -t loop -q 2 -r 1 -u -i 1 "${UBLK_BACKFILES[0]}" & +ublk_run_recover_test -t stripe -q 2 -r 1 -u -i 1 "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & +wait + +_cleanup_test "recover" +_show_result $TID $ERR_CODE diff --git a/tools/testing/selftests/ublk/test_loop_06.sh b/tools/testing/selftests/ublk/test_loop_06.sh new file mode 100755 index 000000000000..1d1a8a725502 --- /dev/null +++ b/tools/testing/selftests/ublk/test_loop_06.sh @@ -0,0 +1,25 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh + +TID="loop_06" +ERR_CODE=0 + +if ! _have_program fio; then + exit "$UBLK_SKIP_CODE" +fi + +_prep_test "loop" "write and verify over user copy" + +_create_backfile 0 256M +dev_id=$(_add_ublk_dev -t loop -u "${UBLK_BACKFILES[0]}") +_check_add_dev $TID $? + +# run fio over the ublk disk +_run_fio_verify_io --filename=/dev/ublkb"${dev_id}" --size=256M +ERR_CODE=$? + +_cleanup_test "loop" + +_show_result $TID $ERR_CODE diff --git a/tools/testing/selftests/ublk/test_loop_07.sh b/tools/testing/selftests/ublk/test_loop_07.sh new file mode 100755 index 000000000000..493f3fb611a5 --- /dev/null +++ b/tools/testing/selftests/ublk/test_loop_07.sh @@ -0,0 +1,21 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh + +TID="loop_07" +ERR_CODE=0 + +_prep_test "loop" "mkfs & mount & umount with user copy" + +_create_backfile 0 256M + +dev_id=$(_add_ublk_dev -t loop -u "${UBLK_BACKFILES[0]}") +_check_add_dev $TID $? + +_mkfs_mount_test /dev/ublkb"${dev_id}" +ERR_CODE=$? + +_cleanup_test "loop" + +_show_result $TID $ERR_CODE diff --git a/tools/testing/selftests/ublk/test_null_03.sh b/tools/testing/selftests/ublk/test_null_03.sh new file mode 100755 index 000000000000..0051067b4686 --- /dev/null +++ b/tools/testing/selftests/ublk/test_null_03.sh @@ -0,0 +1,24 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh + +TID="null_03" +ERR_CODE=0 + +if ! _have_program fio; then + exit "$UBLK_SKIP_CODE" +fi + +_prep_test "null" "basic IO test with user copy" + +dev_id=$(_add_ublk_dev -t null -u) +_check_add_dev $TID $? + +# run fio over the two disks +fio --name=job1 --filename=/dev/ublkb"${dev_id}" --ioengine=libaio --rw=readwrite --iodepth=32 --size=256M > /dev/null 2>&1 +ERR_CODE=$? + +_cleanup_test "null" + +_show_result $TID $ERR_CODE diff --git a/tools/testing/selftests/ublk/test_stress_04.sh b/tools/testing/selftests/ublk/test_stress_04.sh index 3f901db4d09d..efa8dc33234b 100755 --- a/tools/testing/selftests/ublk/test_stress_04.sh +++ b/tools/testing/selftests/ublk/test_stress_04.sh @@ -31,21 +31,23 @@ _create_backfile 2 128M ublk_io_and_kill_daemon 8G -t null -q 4 -z --no_ublk_fixed_fd & ublk_io_and_kill_daemon 256M -t loop -q 4 -z --no_ublk_fixed_fd "${UBLK_BACKFILES[0]}" & ublk_io_and_kill_daemon 256M -t stripe -q 4 -z "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & +wait if _have_feature "AUTO_BUF_REG"; then ublk_io_and_kill_daemon 8G -t null -q 4 --auto_zc & ublk_io_and_kill_daemon 256M -t loop -q 4 --auto_zc "${UBLK_BACKFILES[0]}" & ublk_io_and_kill_daemon 256M -t stripe -q 4 --auto_zc --no_ublk_fixed_fd "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & ublk_io_and_kill_daemon 8G -t null -q 4 -z --auto_zc --auto_zc_fallback & + wait fi if _have_feature "PER_IO_DAEMON"; then - ublk_io_and_kill_daemon 8G -t null -q 4 --nthreads 8 --per_io_tasks & - ublk_io_and_kill_daemon 256M -t loop -q 4 --nthreads 8 --per_io_tasks "${UBLK_BACKFILES[0]}" & - ublk_io_and_kill_daemon 256M -t stripe -q 4 --nthreads 8 --per_io_tasks "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & - ublk_io_and_kill_daemon 8G -t null -q 4 --nthreads 8 --per_io_tasks & + ublk_io_and_kill_daemon 8G -t null -q 4 --auto_zc --nthreads 8 --per_io_tasks & + ublk_io_and_kill_daemon 256M -t loop -q 4 --auto_zc --nthreads 8 --per_io_tasks "${UBLK_BACKFILES[0]}" & + ublk_io_and_kill_daemon 256M -t stripe -q 4 --auto_zc --nthreads 8 --per_io_tasks "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & + ublk_io_and_kill_daemon 8G -t null -q 4 -z --auto_zc --auto_zc_fallback --nthreads 8 --per_io_tasks & + wait fi -wait _cleanup_test "stress" _show_result $TID $ERR_CODE diff --git a/tools/testing/selftests/ublk/test_stress_05.sh b/tools/testing/selftests/ublk/test_stress_05.sh index 274295061042..68a194144302 100755 --- a/tools/testing/selftests/ublk/test_stress_05.sh +++ b/tools/testing/selftests/ublk/test_stress_05.sh @@ -58,17 +58,17 @@ done if _have_feature "ZERO_COPY"; then for reissue in $(seq 0 1); do - ublk_io_and_remove 8G -t null -q 4 -g -z -r 1 -i "$reissue" & - ublk_io_and_remove 256M -t loop -q 4 -g -z -r 1 -i "$reissue" "${UBLK_BACKFILES[1]}" & + ublk_io_and_remove 8G -t null -q 4 -z -r 1 -i "$reissue" & + ublk_io_and_remove 256M -t loop -q 4 -z -r 1 -i "$reissue" "${UBLK_BACKFILES[1]}" & wait done fi if _have_feature "AUTO_BUF_REG"; then for reissue in $(seq 0 1); do - ublk_io_and_remove 8G -t null -q 4 -g --auto_zc -r 1 -i "$reissue" & - ublk_io_and_remove 256M -t loop -q 4 -g --auto_zc -r 1 -i "$reissue" "${UBLK_BACKFILES[1]}" & - ublk_io_and_remove 8G -t null -q 4 -g -z --auto_zc --auto_zc_fallback -r 1 -i "$reissue" & + ublk_io_and_remove 8G -t null -q 4 --auto_zc -r 1 -i "$reissue" & + ublk_io_and_remove 256M -t loop -q 4 --auto_zc -r 1 -i "$reissue" "${UBLK_BACKFILES[1]}" & + ublk_io_and_remove 8G -t null -q 4 -z --auto_zc --auto_zc_fallback -r 1 -i "$reissue" & wait done fi diff --git a/tools/testing/selftests/ublk/test_stress_06.sh b/tools/testing/selftests/ublk/test_stress_06.sh new file mode 100755 index 000000000000..37188ec2e1f7 --- /dev/null +++ b/tools/testing/selftests/ublk/test_stress_06.sh @@ -0,0 +1,39 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh +TID="stress_06" +ERR_CODE=0 + +ublk_io_and_remove() +{ + run_io_and_remove "$@" + ERR_CODE=$? + if [ ${ERR_CODE} -ne 0 ]; then + echo "$TID failure: $*" + _show_result $TID $ERR_CODE + fi +} + +if ! _have_program fio; then + exit "$UBLK_SKIP_CODE" +fi + +_prep_test "stress" "run IO and remove device (user copy)" + +_create_backfile 0 256M +_create_backfile 1 128M +_create_backfile 2 128M + +ublk_io_and_remove 8G -t null -q 4 -u & +ublk_io_and_remove 256M -t loop -q 4 -u "${UBLK_BACKFILES[0]}" & +ublk_io_and_remove 256M -t stripe -q 4 -u "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & +wait + +ublk_io_and_remove 8G -t null -q 4 -u --nthreads 8 --per_io_tasks & +ublk_io_and_remove 256M -t loop -q 4 -u --nthreads 8 --per_io_tasks "${UBLK_BACKFILES[0]}" & +ublk_io_and_remove 256M -t stripe -q 4 -u --nthreads 8 --per_io_tasks "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & +wait + +_cleanup_test "stress" +_show_result $TID $ERR_CODE diff --git a/tools/testing/selftests/ublk/test_stress_07.sh b/tools/testing/selftests/ublk/test_stress_07.sh new file mode 100755 index 000000000000..fb061fc26d36 --- /dev/null +++ b/tools/testing/selftests/ublk/test_stress_07.sh @@ -0,0 +1,39 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh +TID="stress_07" +ERR_CODE=0 + +ublk_io_and_kill_daemon() +{ + run_io_and_kill_daemon "$@" + ERR_CODE=$? + if [ ${ERR_CODE} -ne 0 ]; then + echo "$TID failure: $*" + _show_result $TID $ERR_CODE + fi +} + +if ! _have_program fio; then + exit "$UBLK_SKIP_CODE" +fi + +_prep_test "stress" "run IO and kill ublk server (user copy)" + +_create_backfile 0 256M +_create_backfile 1 128M +_create_backfile 2 128M + +ublk_io_and_kill_daemon 8G -t null -q 4 -u --no_ublk_fixed_fd & +ublk_io_and_kill_daemon 256M -t loop -q 4 -u --no_ublk_fixed_fd "${UBLK_BACKFILES[0]}" & +ublk_io_and_kill_daemon 256M -t stripe -q 4 -u "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & +wait + +ublk_io_and_kill_daemon 8G -t null -q 4 -u --nthreads 8 --per_io_tasks & +ublk_io_and_kill_daemon 256M -t loop -q 4 -u --nthreads 8 --per_io_tasks "${UBLK_BACKFILES[0]}" & +ublk_io_and_kill_daemon 256M -t stripe -q 4 -u --nthreads 8 --per_io_tasks "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" & +wait + +_cleanup_test "stress" +_show_result $TID $ERR_CODE diff --git a/tools/testing/selftests/ublk/test_stripe_05.sh b/tools/testing/selftests/ublk/test_stripe_05.sh new file mode 100755 index 000000000000..05d71951d710 --- /dev/null +++ b/tools/testing/selftests/ublk/test_stripe_05.sh @@ -0,0 +1,26 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh + +TID="stripe_05" +ERR_CODE=0 + +if ! _have_program fio; then + exit "$UBLK_SKIP_CODE" +fi + +_prep_test "stripe" "write and verify test on user copy" + +_create_backfile 0 256M +_create_backfile 1 256M + +dev_id=$(_add_ublk_dev -t stripe -q 2 -u "${UBLK_BACKFILES[0]}" "${UBLK_BACKFILES[1]}") +_check_add_dev $TID $? + +# run fio over the ublk disk +_run_fio_verify_io --filename=/dev/ublkb"${dev_id}" --size=512M +ERR_CODE=$? + +_cleanup_test "stripe" +_show_result $TID $ERR_CODE diff --git a/tools/testing/selftests/ublk/test_stripe_06.sh b/tools/testing/selftests/ublk/test_stripe_06.sh new file mode 100755 index 000000000000..d06cac7626e2 --- /dev/null +++ b/tools/testing/selftests/ublk/test_stripe_06.sh @@ -0,0 +1,21 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh + +TID="stripe_06" +ERR_CODE=0 + +_prep_test "stripe" "mkfs & mount & umount on user copy" + +_create_backfile 0 256M +_create_backfile 1 256M + +dev_id=$(_add_ublk_dev -t stripe -u -q 2 "${UBLK_BACKFILES[0]}" "${UBLK_BACKFILES[1]}") +_check_add_dev $TID $? + +_mkfs_mount_test /dev/ublkb"${dev_id}" +ERR_CODE=$? + +_cleanup_test "stripe" +_show_result $TID $ERR_CODE diff --git a/tools/testing/selftests/ublk/trace/seq_io.bt b/tools/testing/selftests/ublk/trace/seq_io.bt index 272ac54c9d5f..b2f60a92b118 100644 --- a/tools/testing/selftests/ublk/trace/seq_io.bt +++ b/tools/testing/selftests/ublk/trace/seq_io.bt @@ -4,7 +4,7 @@ $3: strlen($2) */ BEGIN { - @last_rw[$1, str($2)] = 0; + @last_rw[$1, str($2)] = (uint64)0; } tracepoint:block:block_rq_complete { @@ -17,7 +17,6 @@ tracepoint:block:block_rq_complete } @last_rw[$dev, str($2)] = (args.sector + args.nr_sector); } - @ios = count(); } END { |