diff options
261 files changed, 2300 insertions, 1026 deletions
diff --git a/Documentation/ABI/testing/sysfs-class-net-queues b/Documentation/ABI/testing/sysfs-class-net-queues index 906ff3ca928a..5bff64d256c2 100644 --- a/Documentation/ABI/testing/sysfs-class-net-queues +++ b/Documentation/ABI/testing/sysfs-class-net-queues @@ -1,4 +1,4 @@ -What: /sys/class/<iface>/queues/rx-<queue>/rps_cpus +What: /sys/class/net/<iface>/queues/rx-<queue>/rps_cpus Date: March 2010 KernelVersion: 2.6.35 Contact: [email protected] @@ -8,7 +8,7 @@ Description: network device queue. Possible values depend on the number of available CPU(s) in the system. -What: /sys/class/<iface>/queues/rx-<queue>/rps_flow_cnt +What: /sys/class/net/<iface>/queues/rx-<queue>/rps_flow_cnt Date: April 2010 KernelVersion: 2.6.35 Contact: [email protected] @@ -16,7 +16,7 @@ Description: Number of Receive Packet Steering flows being currently processed by this particular network device receive queue. -What: /sys/class/<iface>/queues/tx-<queue>/tx_timeout +What: /sys/class/net/<iface>/queues/tx-<queue>/tx_timeout Date: November 2011 KernelVersion: 3.3 Contact: [email protected] @@ -24,7 +24,7 @@ Description: Indicates the number of transmit timeout events seen by this network interface transmit queue. -What: /sys/class/<iface>/queues/tx-<queue>/tx_maxrate +What: /sys/class/net/<iface>/queues/tx-<queue>/tx_maxrate Date: March 2015 KernelVersion: 4.1 Contact: [email protected] @@ -32,7 +32,7 @@ Description: A Mbps max-rate set for the queue, a value of zero means disabled, default is disabled. -What: /sys/class/<iface>/queues/tx-<queue>/xps_cpus +What: /sys/class/net/<iface>/queues/tx-<queue>/xps_cpus Date: November 2010 KernelVersion: 2.6.38 Contact: [email protected] @@ -42,7 +42,7 @@ Description: network device transmit queue. Possible values depend on the number of available CPU(s) in the system. -What: /sys/class/<iface>/queues/tx-<queue>/xps_rxqs +What: /sys/class/net/<iface>/queues/tx-<queue>/xps_rxqs Date: June 2018 KernelVersion: 4.18.0 Contact: [email protected] @@ -53,7 +53,7 @@ Description: number of available receive queue(s) in the network device. Default is disabled. -What: /sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/hold_time +What: /sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/hold_time Date: November 2011 KernelVersion: 3.3 Contact: [email protected] @@ -62,7 +62,7 @@ Description: of this particular network device transmit queue. Default value is 1000. -What: /sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/inflight +What: /sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/inflight Date: November 2011 KernelVersion: 3.3 Contact: [email protected] @@ -70,7 +70,7 @@ Description: Indicates the number of bytes (objects) in flight on this network device transmit queue. -What: /sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/limit +What: /sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/limit Date: November 2011 KernelVersion: 3.3 Contact: [email protected] @@ -79,7 +79,7 @@ Description: on this network device transmit queue. This value is clamped to be within the bounds defined by limit_max and limit_min. -What: /sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/limit_max +What: /sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/limit_max Date: November 2011 KernelVersion: 3.3 Contact: [email protected] @@ -88,7 +88,7 @@ Description: queued on this network device transmit queue. See include/linux/dynamic_queue_limits.h for the default value. -What: /sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/limit_min +What: /sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/limit_min Date: November 2011 KernelVersion: 3.3 Contact: [email protected] diff --git a/Documentation/filesystems/overlayfs.rst b/Documentation/filesystems/overlayfs.rst index 1c244866041a..165514401441 100644 --- a/Documentation/filesystems/overlayfs.rst +++ b/Documentation/filesystems/overlayfs.rst @@ -145,7 +145,9 @@ filesystem, an overlay filesystem needs to record in the upper filesystem that files have been removed. This is done using whiteouts and opaque directories (non-directories are always opaque). -A whiteout is created as a character device with 0/0 device number. +A whiteout is created as a character device with 0/0 device number or +as a zero-size regular file with the xattr "trusted.overlay.whiteout". + When a whiteout is found in the upper level of a merged directory, any matching name in the lower level is ignored, and the whiteout itself is also hidden. @@ -154,6 +156,13 @@ A directory is made opaque by setting the xattr "trusted.overlay.opaque" to "y". Where the upper filesystem contains an opaque directory, any directory in the lower filesystem with the same name is ignored. +An opaque directory should not conntain any whiteouts, because they do not +serve any purpose. A merge directory containing regular files with the xattr +"trusted.overlay.whiteout", should be additionally marked by setting the xattr +"trusted.overlay.opaque" to "x" on the merge directory itself. +This is needed to avoid the overhead of checking the "trusted.overlay.whiteout" +on all entries during readdir in the common case. + readdir ------- @@ -534,8 +543,9 @@ A lower dir with a regular whiteout will always be handled by the overlayfs mount, so to support storing an effective whiteout file in an overlayfs mount an alternative form of whiteout is supported. This form is a regular, zero-size file with the "overlay.whiteout" xattr set, inside a directory with the -"overlay.whiteouts" xattr set. Such whiteouts are never created by overlayfs, -but can be used by userspace tools (like containers) that generate lower layers. +"overlay.opaque" xattr set to "x" (see `whiteouts and opaque directories`_). +These alternative whiteouts are never created by overlayfs, but can be used by +userspace tools (like containers) that generate lower layers. These alternative whiteouts can be escaped using the standard xattr escape mechanism in order to properly nest to any depth. diff --git a/Documentation/netlink/specs/rt_link.yaml b/Documentation/netlink/specs/rt_link.yaml index 1ad01d52a863..8e4d19adee8c 100644 --- a/Documentation/netlink/specs/rt_link.yaml +++ b/Documentation/netlink/specs/rt_link.yaml @@ -942,6 +942,10 @@ attribute-sets: - name: gro-ipv4-max-size type: u32 + - + name: dpll-pin + type: nest + nested-attributes: link-dpll-pin-attrs - name: af-spec-attrs attributes: @@ -1627,6 +1631,12 @@ attribute-sets: - name: used type: u8 + - + name: link-dpll-pin-attrs + attributes: + - + name: id + type: u32 sub-messages: - diff --git a/MAINTAINERS b/MAINTAINERS index 8d1052fa6a69..6ae30c50e79f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4547,7 +4547,7 @@ F: drivers/net/ieee802154/ca8210.c CACHEFILES: FS-CACHE BACKEND FOR CACHING ON MOUNTED FILESYSTEMS M: David Howells <[email protected]> -L: [email protected] (moderated for non-subscribers) S: Supported F: Documentation/filesystems/caching/cachefiles.rst F: fs/cachefiles/ @@ -7955,12 +7955,13 @@ L: [email protected] S: Maintained F: rust/kernel/net/phy.rs -EXEC & BINFMT API +EXEC & BINFMT API, ELF R: Eric Biederman <[email protected]> R: Kees Cook <[email protected]> S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/execve +F: Documentation/userspace-api/ELF.rst F: fs/*binfmt_*.c F: fs/exec.c F: include/linux/binfmts.h @@ -8223,7 +8224,8 @@ F: include/linux/iomap.h FILESYSTEMS [NETFS LIBRARY] M: David Howells <[email protected]> -L: [email protected] (moderated for non-subscribers) +R: Jeff Layton <[email protected]> S: Supported F: Documentation/filesystems/caching/ @@ -15177,6 +15179,7 @@ F: Documentation/networking/net_cachelines/net_device.rst F: drivers/connector/ F: drivers/net/ F: include/dt-bindings/net/ +F: include/linux/cn_proc.h F: include/linux/etherdevice.h F: include/linux/fcdevice.h F: include/linux/fddidevice.h @@ -15184,6 +15187,7 @@ F: include/linux/hippidevice.h F: include/linux/if_* F: include/linux/inetdevice.h F: include/linux/netdevice.h +F: include/uapi/linux/cn_proc.h F: include/uapi/linux/if_* F: include/uapi/linux/netdevice.h X: drivers/net/wireless/ @@ -18081,7 +18085,6 @@ F: drivers/net/ethernet/qualcomm/emac/ QUALCOMM ETHQOS ETHERNET DRIVER M: Vinod Koul <[email protected]> -R: Bhupesh Sharma <[email protected]> S: Maintained @@ -986,6 +986,10 @@ NOSTDINC_FLAGS += -nostdinc # perform bounds checking. KBUILD_CFLAGS += $(call cc-option, -fstrict-flex-arrays=3) +#Currently, disable -Wstringop-overflow for GCC 11, globally. +KBUILD_CFLAGS-$(CONFIG_CC_NO_STRINGOP_OVERFLOW) += $(call cc-option, -Wno-stringop-overflow) +KBUILD_CFLAGS-$(CONFIG_CC_STRINGOP_OVERFLOW) += $(call cc-option, -Wstringop-overflow) + # disable invalid "can't wrap" optimizations for signed / pointers KBUILD_CFLAGS += -fno-strict-overflow diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index 58dc64dd94a8..719a97e7edb2 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -795,6 +795,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY]; struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT]; struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN]; + bool is_struct_ops = flags & BPF_TRAMP_F_INDIRECT; void *orig_call = func_addr; bool save_ret; u32 insn; @@ -878,7 +879,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, stack_size = round_up(stack_size, 16); - if (func_addr) { + if (!is_struct_ops) { /* For the trampoline called from function entry, * the frame of traced function and the frame of * trampoline need to be considered. @@ -998,7 +999,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, emit_ld(RV_REG_S1, -sreg_off, RV_REG_FP, ctx); - if (func_addr) { + if (!is_struct_ops) { /* trampoline called from function entry */ emit_ld(RV_REG_T0, stack_size - 8, RV_REG_SP, ctx); emit_ld(RV_REG_FP, stack_size - 16, RV_REG_SP, ctx); diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index a999b698b131..12b5d53ec856 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -3452,14 +3452,15 @@ static bool rbd_lock_add_request(struct rbd_img_request *img_req) static void rbd_lock_del_request(struct rbd_img_request *img_req) { struct rbd_device *rbd_dev = img_req->rbd_dev; - bool need_wakeup; + bool need_wakeup = false; lockdep_assert_held(&rbd_dev->lock_rwsem); spin_lock(&rbd_dev->lock_lists_lock); - rbd_assert(!list_empty(&img_req->lock_item)); - list_del_init(&img_req->lock_item); - need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_RELEASING && - list_empty(&rbd_dev->running_list)); + if (!list_empty(&img_req->lock_item)) { + list_del_init(&img_req->lock_item); + need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_RELEASING && + list_empty(&rbd_dev->running_list)); + } spin_unlock(&rbd_dev->lock_lists_lock); if (need_wakeup) complete(&rbd_dev->releasing_wait); @@ -3842,14 +3843,19 @@ static void wake_lock_waiters(struct rbd_device *rbd_dev, int result) return; } - list_for_each_entry(img_req, &rbd_dev->acquiring_list, lock_item) { + while (!list_empty(&rbd_dev->acquiring_list)) { + img_req = list_first_entry(&rbd_dev->acquiring_list, + struct rbd_img_request, lock_item); mutex_lock(&img_req->state_mutex); rbd_assert(img_req->state == RBD_IMG_EXCLUSIVE_LOCK); + if (!result) + list_move_tail(&img_req->lock_item, + &rbd_dev->running_list); + else + list_del_init(&img_req->lock_item); rbd_img_schedule(img_req, result); mutex_unlock(&img_req->state_mutex); } - - list_splice_tail_init(&rbd_dev->acquiring_list, &rbd_dev->running_list); } static bool locker_equal(const struct ceph_locker *lhs, @@ -5326,7 +5332,7 @@ static void rbd_dev_release(struct device *dev) if (need_put) { destroy_workqueue(rbd_dev->task_wq); - ida_simple_remove(&rbd_dev_id_ida, rbd_dev->dev_id); + ida_free(&rbd_dev_id_ida, rbd_dev->dev_id); } rbd_dev_free(rbd_dev); @@ -5402,9 +5408,9 @@ static struct rbd_device *rbd_dev_create(struct rbd_client *rbdc, return NULL; /* get an id and fill in device name */ - rbd_dev->dev_id = ida_simple_get(&rbd_dev_id_ida, 0, - minor_to_rbd_dev_id(1 << MINORBITS), - GFP_KERNEL); + rbd_dev->dev_id = ida_alloc_max(&rbd_dev_id_ida, + minor_to_rbd_dev_id(1 << MINORBITS) - 1, + GFP_KERNEL); if (rbd_dev->dev_id < 0) goto fail_rbd_dev; @@ -5425,7 +5431,7 @@ static struct rbd_device *rbd_dev_create(struct rbd_client *rbdc, return rbd_dev; fail_dev_id: - ida_simple_remove(&rbd_dev_id_ida, rbd_dev->dev_id); + ida_free(&rbd_dev_id_ida, rbd_dev->dev_id); fail_rbd_dev: rbd_dev_free(rbd_dev); return NULL; diff --git a/drivers/dpll/dpll_core.c b/drivers/dpll/dpll_core.c index 1eca8cc271f8..5152bd1b0daf 100644 --- a/drivers/dpll/dpll_core.c +++ b/drivers/dpll/dpll_core.c @@ -29,8 +29,6 @@ static u32 dpll_pin_xa_id; WARN_ON_ONCE(!xa_get_mark(&dpll_device_xa, (d)->id, DPLL_REGISTERED)) #define ASSERT_DPLL_NOT_REGISTERED(d) \ WARN_ON_ONCE(xa_get_mark(&dpll_device_xa, (d)->id, DPLL_REGISTERED)) -#define ASSERT_PIN_REGISTERED(p) \ - WARN_ON_ONCE(!xa_get_mark(&dpll_pin_xa, (p)->id, DPLL_REGISTERED)) struct dpll_device_registration { struct list_head list; @@ -425,6 +423,53 @@ void dpll_device_unregister(struct dpll_device *dpll, } EXPORT_SYMBOL_GPL(dpll_device_unregister); +static void dpll_pin_prop_free(struct dpll_pin_properties *prop) +{ + kfree(prop->package_label); + kfree(prop->panel_label); + kfree(prop->board_label); + kfree(prop->freq_supported); +} + +static int dpll_pin_prop_dup(const struct dpll_pin_properties *src, + struct dpll_pin_properties *dst) +{ + memcpy(dst, src, sizeof(*dst)); + if (src->freq_supported && src->freq_supported_num) { + size_t freq_size = src->freq_supported_num * + sizeof(*src->freq_supported); + dst->freq_supported = kmemdup(src->freq_supported, + freq_size, GFP_KERNEL); + if (!src->freq_supported) + return -ENOMEM; + } + if (src->board_label) { + dst->board_label = kstrdup(src->board_label, GFP_KERNEL); + if (!dst->board_label) + goto err_board_label; + } + if (src->panel_label) { + dst->panel_label = kstrdup(src->panel_label, GFP_KERNEL); + if (!dst->panel_label) + goto err_panel_label; + } + if (src->package_label) { + dst->package_label = kstrdup(src->package_label, GFP_KERNEL); + if (!dst->package_label) + goto err_package_label; + } + + return 0; + +err_package_label: + kfree(dst->panel_label); +err_panel_label: + kfree(dst->board_label); +err_board_label: + kfree(dst->freq_supported); + return -ENOMEM; +} + static struct dpll_pin * dpll_pin_alloc(u64 clock_id, u32 pin_idx, struct module *module, const struct dpll_pin_properties *prop) @@ -441,20 +486,24 @@ dpll_pin_alloc(u64 clock_id, u32 pin_idx, struct module *module, if (WARN_ON(prop->type < DPLL_PIN_TYPE_MUX || prop->type > DPLL_PIN_TYPE_MAX)) { ret = -EINVAL; - goto err; + goto err_pin_prop; } - pin->prop = prop; + ret = dpll_pin_prop_dup(prop, &pin->prop); + if (ret) + goto err_pin_prop; refcount_set(&pin->refcount, 1); xa_init_flags(&pin->dpll_refs, XA_FLAGS_ALLOC); xa_init_flags(&pin->parent_refs, XA_FLAGS_ALLOC); ret = xa_alloc_cyclic(&dpll_pin_xa, &pin->id, pin, xa_limit_32b, &dpll_pin_xa_id, GFP_KERNEL); if (ret) - goto err; + goto err_xa_alloc; return pin; -err: +err_xa_alloc: xa_destroy(&pin->dpll_refs); xa_destroy(&pin->parent_refs); + dpll_pin_prop_free(&pin->prop); +err_pin_prop: kfree(pin); return ERR_PTR(ret); } @@ -514,6 +563,7 @@ void dpll_pin_put(struct dpll_pin *pin) xa_destroy(&pin->dpll_refs); xa_destroy(&pin->parent_refs); xa_erase(&dpll_pin_xa, pin->id); + dpll_pin_prop_free(&pin->prop); kfree(pin); } mutex_unlock(&dpll_lock); @@ -564,8 +614,6 @@ dpll_pin_register(struct dpll_device *dpll, struct dpll_pin *pin, WARN_ON(!ops->state_on_dpll_get) || WARN_ON(!ops->direction_get)) return -EINVAL; - if (ASSERT_DPLL_REGISTERED(dpll)) - return -EINVAL; mutex_lock(&dpll_lock); if (WARN_ON(!(dpll->module == pin->module && @@ -636,15 +684,13 @@ int dpll_pin_on_pin_register(struct dpll_pin *parent, struct dpll_pin *pin, unsigned long i, stop; int ret; - if (WARN_ON(parent->prop->type != DPLL_PIN_TYPE_MUX)) + if (WARN_ON(parent->prop.type != DPLL_PIN_TYPE_MUX)) return -EINVAL; if (WARN_ON(!ops) || WARN_ON(!ops->state_on_pin_get) || WARN_ON(!ops->direction_get)) return -EINVAL; - if (ASSERT_PIN_REGISTERED(parent)) - return -EINVAL; mutex_lock(&dpll_lock); ret = dpll_xa_ref_pin_add(&pin->parent_refs, parent, ops, priv); diff --git a/drivers/dpll/dpll_core.h b/drivers/dpll/dpll_core.h index 5585873c5c1b..717f715015c7 100644 --- a/drivers/dpll/dpll_core.h +++ b/drivers/dpll/dpll_core.h @@ -44,7 +44,7 @@ struct dpll_device { * @module: module of creator * @dpll_refs: hold referencees to dplls pin was registered with * @parent_refs: hold references to parent pins pin was registered with - * @prop: pointer to pin properties given by registerer + * @prop: pin properties copied from the registerer * @rclk_dev_name: holds name of device when pin can recover clock from it * @refcount: refcount **/ @@ -55,7 +55,7 @@ struct dpll_pin { struct module *module; struct xarray dpll_refs; struct xarray parent_refs; - const struct dpll_pin_properties *prop; + struct dpll_pin_properties prop; refcount_t refcount; }; diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c index 3370dbddb86b..314bb3775465 100644 --- a/drivers/dpll/dpll_netlink.c +++ b/drivers/dpll/dpll_netlink.c @@ -303,17 +303,17 @@ dpll_msg_add_pin_freq(struct sk_buff *msg, struct dpll_pin *pin, if (nla_put_64bit(msg, DPLL_A_PIN_FREQUENCY, sizeof(freq), &freq, DPLL_A_PIN_PAD)) return -EMSGSIZE; - for (fs = 0; fs < pin->prop->freq_supported_num; fs++) { + for (fs = 0; fs < pin->prop.freq_supported_num; fs++) { nest = nla_nest_start(msg, DPLL_A_PIN_FREQUENCY_SUPPORTED); if (!nest) return -EMSGSIZE; - freq = pin->prop->freq_supported[fs].min; + freq = pin->prop.freq_supported[fs].min; if (nla_put_64bit(msg, DPLL_A_PIN_FREQUENCY_MIN, sizeof(freq), &freq, DPLL_A_PIN_PAD)) { nla_nest_cancel(msg, nest); return -EMSGSIZE; } - freq = pin->prop->freq_supported[fs].max; + freq = pin->prop.freq_supported[fs].max; if (nla_put_64bit(msg, DPLL_A_PIN_FREQUENCY_MAX, sizeof(freq), &freq, DPLL_A_PIN_PAD)) { nla_nest_cancel(msg, nest); @@ -329,9 +329,9 @@ static bool dpll_pin_is_freq_supported(struct dpll_pin *pin, u32 freq) { int fs; - for (fs = 0; fs < pin->prop->freq_supported_num; fs++) - if (freq >= pin->prop->freq_supported[fs].min && - freq <= pin->prop->freq_supported[fs].max) + for (fs = 0; fs < pin->prop.freq_supported_num; fs++) + if (freq >= pin->prop.freq_supported[fs].min && + freq <= pin->prop.freq_supported[fs].max) return true; return false; } @@ -421,7 +421,7 @@ static int dpll_cmd_pin_get_one(struct sk_buff *msg, struct dpll_pin *pin, struct netlink_ext_ack *extack) { - const struct dpll_pin_properties *prop = pin->prop; + const struct dpll_pin_properties *prop = &pin->prop; struct dpll_pin_ref *ref; int ret; @@ -553,6 +553,24 @@ __dpll_device_change_ntf(struct dpll_device *dpll) return dpll_device_event_send(DPLL_CMD_DEVICE_CHANGE_NTF, dpll); } +static bool dpll_pin_available(struct dpll_pin *pin) +{ + struct dpll_pin_ref *par_ref; + unsigned long i; + + if (!xa_get_mark(&dpll_pin_xa, pin->id, DPLL_REGISTERED)) + return false; + xa_for_each(&pin->parent_refs, i, par_ref) + if (xa_get_mark(&dpll_pin_xa, par_ref->pin->id, + DPLL_REGISTERED)) + return true; + xa_for_each(&pin->dpll_refs, i, par_ref) + if (xa_get_mark(&dpll_device_xa, par_ref->dpll->id, + DPLL_REGISTERED)) + return true; + return false; +} + /** * dpll_device_change_ntf - notify that the dpll device has been changed * @dpll: registered dpll pointer @@ -579,7 +597,7 @@ dpll_pin_event_send(enum dpll_cmd event, struct dpll_pin *pin) int ret = -ENOMEM; void *hdr; - if (WARN_ON(!xa_get_mark(&dpll_pin_xa, pin->id, DPLL_REGISTERED))) + if (!dpll_pin_available(pin)) return -ENODEV; msg = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); @@ -717,7 +735,7 @@ dpll_pin_on_pin_state_set(struct dpll_pin *pin, u32 parent_idx, int ret; if (!(DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE & - pin->prop->capabilities)) { + pin->prop.capabilities)) { NL_SET_ERR_MSG(extack, "state changing is not allowed"); return -EOPNOTSUPP; } @@ -753,7 +771,7 @@ dpll_pin_state_set(struct dpll_device *dpll, struct dpll_pin *pin, int ret; if (!(DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE & - pin->prop->capabilities)) { + pin->prop.capabilities)) { NL_SET_ERR_MSG(extack, "state changing is not allowed"); return -EOPNOTSUPP; } @@ -780,7 +798,7 @@ dpll_pin_prio_set(struct dpll_device *dpll, struct dpll_pin *pin, int ret; if (!(DPLL_PIN_CAPABILITIES_PRIORITY_CAN_CHANGE & - pin->prop->capabilities)) { + pin->prop.capabilities)) { NL_SET_ERR_MSG(extack, "prio changing is not allowed"); return -EOPNOTSUPP; } @@ -808,7 +826,7 @@ dpll_pin_direction_set(struct dpll_pin *pin, struct dpll_device *dpll, int ret; if (!(DPLL_PIN_CAPABILITIES_DIRECTION_CAN_CHANGE & - pin->prop->capabilities)) { + pin->prop.capabilities)) { NL_SET_ERR_MSG(extack, "direction changing is not allowed"); return -EOPNOTSUPP; } @@ -838,8 +856,8 @@ dpll_pin_phase_adj_set(struct dpll_pin *pin, struct nlattr *phase_adj_attr, int ret; phase_adj = nla_get_s32(phase_adj_attr); - if (phase_adj > pin->prop->phase_range.max || - phase_adj < pin->prop->phase_range.min) { + if (phase_adj > pin->prop.phase_range.max || + phase_adj < pin->prop.phase_range.min) { NL_SET_ERR_MSG_ATTR(extack, phase_adj_attr, "phase adjust value not supported"); return -EINVAL; @@ -1023,7 +1041,7 @@ dpll_pin_find(u64 clock_id, struct nlattr *mod_name_attr, unsigned long i; xa_for_each_marked(&dpll_pin_xa, i, pin, DPLL_REGISTERED) { - prop = pin->prop; + prop = &pin->prop; cid_match = clock_id ? pin->clock_id == clock_id : true; mod_match = mod_name_attr && module_name(pin->module) ? !nla_strcmp(mod_name_attr, @@ -1130,6 +1148,10 @@ int dpll_nl_pin_id_get_doit(struct sk_buff *skb, struct genl_info *info) } pin = dpll_pin_find_from_nlattr(info); if (!IS_ERR(pin)) { + if (!dpll_pin_available(pin)) { + nlmsg_free(msg); + return -ENODEV; + } ret = dpll_msg_add_pin_handle(msg, pin); if (ret) { nlmsg_free(msg); @@ -1179,6 +1201,8 @@ int dpll_nl_pin_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) xa_for_each_marked_start(&dpll_pin_xa, i, pin, DPLL_REGISTERED, ctx->idx) { + if (!dpll_pin_available(pin)) + continue; hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &dpll_nl_family, NLM_F_MULTI, @@ -1441,7 +1465,8 @@ int dpll_pin_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb, } info->user_ptr[0] = xa_load(&dpll_pin_xa, nla_get_u32(info->attrs[DPLL_A_PIN_ID])); - if (!info->user_ptr[0]) { + if (!info->user_ptr[0] || + !dpll_pin_available(info->user_ptr[0])) { NL_SET_ERR_MSG(info->extack, "pin not found"); ret = -ENODEV; goto unlock_dev; diff --git a/drivers/gpu/drm/ttm/ttm_device.c b/drivers/gpu/drm/ttm/ttm_device.c index f5187b384ae9..4130945052ed 100644 --- a/drivers/gpu/drm/ttm/ttm_device.c +++ b/drivers/gpu/drm/ttm/ttm_device.c @@ -195,7 +195,7 @@ int ttm_device_init(struct ttm_device *bdev, const struct ttm_device_funcs *func bool use_dma_alloc, bool use_dma32) { struct ttm_global *glob = &ttm_glob; - int ret; + int ret, nid; if (WARN_ON(vma_manager == NULL)) return -EINVAL; @@ -215,7 +215,12 @@ int ttm_device_init(struct ttm_device *bdev, const struct ttm_device_funcs *func ttm_sys_man_init(bdev); - ttm_pool_init(&bdev->pool, dev, dev_to_node(dev), use_dma_alloc, use_dma32); + if (dev) + nid = dev_to_node(dev); + else + nid = NUMA_NO_NODE; + + ttm_pool_init(&bdev->pool, dev, nid, use_dma_alloc, use_dma32); bdev->vma_manager = vma_manager; spin_lock_init(&bdev->lru_lock); diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 391c4dbdff42..3c1f657593a8 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -2838,8 +2838,7 @@ static void mt753x_phylink_mac_link_up(struct dsa_switch *ds, int port, /* MT753x MAC works in 1G full duplex mode for all up-clocked * variants. */ - if (interface == PHY_INTERFACE_MODE_INTERNAL || - interface == PHY_INTERFACE_MODE_TRGMII || + if (interface == PHY_INTERFACE_MODE_TRGMII || (phy_interface_mode_is_8023z(interface))) { speed = SPEED_1000; duplex = DUPLEX_FULL; diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 383b3c4d6f59..614cabb5c1b0 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3659,7 +3659,7 @@ static int mv88e6xxx_mdio_read_c45(struct mii_bus *bus, int phy, int devad, int err; if (!chip->info->ops->phy_read_c45) - return -EOPNOTSUPP; + return 0xffff; mv88e6xxx_reg_lock(chip); err = chip->info->ops->phy_read_c45(chip, bus, phy, devad, reg, &val); diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c index c51f40960961..7a864329cb72 100644 --- a/drivers/net/dsa/qca/qca8k-8xxx.c +++ b/drivers/net/dsa/qca/qca8k-8xxx.c @@ -2051,12 +2051,11 @@ qca8k_sw_probe(struct mdio_device *mdiodev) priv->info = of_device_get_match_data(priv->dev); priv->reset_gpio = devm_gpiod_get_optional(priv->dev, "reset", - GPIOD_ASIS); + GPIOD_OUT_HIGH); if (IS_ERR(priv->reset_gpio)) return PTR_ERR(priv->reset_gpio); if (priv->reset_gpio) { - gpiod_set_value_cansleep(priv->reset_gpio, 1); /* The active low duration must be greater than 10 ms * and checkpatch.pl wants 20 ms. */ diff --git a/drivers/net/ethernet/8390/8390.c b/drivers/net/ethernet/8390/8390.c index 0e0aa4016858..c5636245f1ca 100644 --- a/drivers/net/ethernet/8390/8390.c +++ b/drivers/net/ethernet/8390/8390.c @@ -100,4 +100,5 @@ static void __exit ns8390_module_exit(void) module_init(ns8390_module_init); module_exit(ns8390_module_exit); #endif /* MODULE */ +MODULE_DESCRIPTION("National Semiconductor 8390 core driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/8390/8390p.c b/drivers/net/ethernet/8390/8390p.c index 6834742057b3..6d429b11e9c6 100644 --- a/drivers/net/ethernet/8390/8390p.c +++ b/drivers/net/ethernet/8390/8390p.c @@ -102,4 +102,5 @@ static void __exit NS8390p_cleanup_module(void) module_init(NS8390p_init_module); module_exit(NS8390p_cleanup_module); +MODULE_DESCRIPTION("National Semiconductor 8390 core for ISA driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/8390/apne.c b/drivers/net/ethernet/8390/apne.c index a09f383dd249..828edca8d30c 100644 --- a/drivers/net/ethernet/8390/apne.c +++ b/drivers/net/ethernet/8390/apne.c @@ -610,4 +610,5 @@ static int init_pcmcia(void) return 1; } +MODULE_DESCRIPTION("National Semiconductor 8390 Amiga PCMCIA ethernet driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/8390/hydra.c b/drivers/net/ethernet/8390/hydra.c index 24f49a8ff903..fd9dcdc356e6 100644 --- a/drivers/net/ethernet/8390/hydra.c +++ b/drivers/net/ethernet/8390/hydra.c @@ -270,4 +270,5 @@ static void __exit hydra_cleanup_module(void) module_init(hydra_init_module); module_exit(hydra_cleanup_module); +MODULE_DESCRIPTION("Zorro-II Hydra 8390 ethernet driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/8390/stnic.c b/drivers/net/ethernet/8390/stnic.c index 265976e3b64a..6cc0e190aa79 100644 --- a/drivers/net/ethernet/8390/stnic.c +++ b/drivers/net/ethernet/8390/stnic.c @@ -296,4 +296,5 @@ static void __exit stnic_cleanup(void) module_init(stnic_probe); module_exit(stnic_cleanup); +MODULE_DESCRIPTION("National Semiconductor DP83902AV ethernet driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/8390/zorro8390.c b/drivers/net/ethernet/8390/zorro8390.c index d70390e9d03d..c24dd4fe7a10 100644 --- a/drivers/net/ethernet/8390/zorro8390.c +++ b/drivers/net/ethernet/8390/zorro8390.c @@ -443,4 +443,5 @@ static void __exit zorro8390_cleanup_module(void) module_init(zorro8390_init_module); module_exit(zorro8390_cleanup_module); +MODULE_DESCRIPTION("Zorro NS8390-based ethernet driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/amd/pds_core/adminq.c b/drivers/net/ethernet/amd/pds_core/adminq.c index 5beadabc2136..ea773cfa0af6 100644 --- a/drivers/net/ethernet/amd/pds_core/adminq.c +++ b/drivers/net/ethernet/amd/pds_core/adminq.c @@ -63,6 +63,15 @@ static int pdsc_process_notifyq(struct pdsc_qcq *qcq) return nq_work; } +static bool pdsc_adminq_inc_if_up(struct pdsc *pdsc) +{ + if (pdsc->state & BIT_ULL(PDSC_S_STOPPING_DRIVER) || + pdsc->state & BIT_ULL(PDSC_S_FW_DEAD)) + return false; + + return refcount_inc_not_zero(&pdsc->adminq_refcnt); +} + void pdsc_process_adminq(struct pdsc_qcq *qcq) { union pds_core_adminq_comp *comp; @@ -75,9 +84,9 @@ void pdsc_process_adminq(struct pdsc_qcq *qcq) int aq_work = 0; int credits; - /* Don't process AdminQ when shutting down */ - if (pdsc->state & BIT_ULL(PDSC_S_STOPPING_DRIVER)) { - dev_err(pdsc->dev, "%s: called while PDSC_S_STOPPING_DRIVER\n", + /* Don't process AdminQ when it's not up */ + if (!pdsc_adminq_inc_if_up(pdsc)) { + dev_err(pdsc->dev, "%s: called while adminq is unavailable\n", __func__); return; } @@ -124,6 +133,7 @@ credits: pds_core_intr_credits(&pdsc->intr_ctrl[qcq->intx], credits, PDS_CORE_INTR_CRED_REARM); + refcount_dec(&pdsc->adminq_refcnt); } void pdsc_work_thread(struct work_struct *work) @@ -135,18 +145,20 @@ void pdsc_work_thread(struct work_struct *work) irqreturn_t pdsc_adminq_isr(int irq, void *data) { - struct pdsc_qcq *qcq = data; - struct pdsc *pdsc = qcq->pdsc; + struct pdsc *pdsc = data; + struct pdsc_qcq *qcq; - /* Don't process AdminQ when shutting down */ - if (pdsc->state & BIT_ULL(PDSC_S_STOPPING_DRIVER)) { - dev_err(pdsc->dev, "%s: called while PDSC_S_STOPPING_DRIVER\n", + /* Don't process AdminQ when it's not up */ + if (!pdsc_adminq_inc_if_up(pdsc)) { + dev_err(pdsc->dev, "%s: called while adminq is unavailable\n", __func__); return IRQ_HANDLED; } + qcq = &pdsc->adminqcq; queue_work(pdsc->wq, &qcq->work); pds_core_intr_mask(&pdsc->intr_ctrl[qcq->intx], PDS_CORE_INTR_MASK_CLEAR); + refcount_dec(&pdsc->adminq_refcnt); return IRQ_HANDLED; } @@ -179,10 +191,16 @@ static int __pdsc_adminq_post(struct pdsc *pdsc, /* Check that the FW is running */ if (!pdsc_is_fw_running(pdsc)) { - u8 fw_status = ioread8(&pdsc->info_regs->fw_status); - - dev_info(pdsc->dev, "%s: post failed - fw not running %#02x:\n", - __func__, fw_status); + if (pdsc->info_regs) { + u8 fw_status = + ioread8(&pdsc->info_regs->fw_status); + + dev_info(pdsc->dev, "%s: post failed - fw not running %#02x:\n", + __func__, fw_status); + } else { + dev_info(pdsc->dev, "%s: post failed - BARs not setup\n", + __func__); + } ret = -ENXIO; goto err_out_unlock; @@ -230,6 +248,12 @@ int pdsc_adminq_post(struct pdsc *pdsc, int err = 0; int index; + if (!pdsc_adminq_inc_if_up(pdsc)) { + dev_dbg(pdsc->dev, "%s: preventing adminq cmd %u\n", + __func__, cmd->opcode); + return -ENXIO; + } + wc.qcq = &pdsc->adminqcq; index = __pdsc_adminq_post(pdsc, &pdsc->adminqcq, cmd, comp, &wc); if (index < 0) { @@ -248,10 +272,16 @@ int pdsc_adminq_post(struct pdsc *pdsc, break; if (!pdsc_is_fw_running(pdsc)) { - u8 fw_status = ioread8(&pdsc->info_regs->fw_status); - - dev_dbg(pdsc->dev, "%s: post wait failed - fw not running %#02x:\n", - __func__, fw_status); + if (pdsc->info_regs) { + u8 fw_status = + ioread8(&pdsc->info_regs->fw_status); + + dev_dbg(pdsc->dev, "%s: post wait failed - fw not running %#02x:\n", + __func__, fw_status); + } else { + dev_dbg(pdsc->dev, "%s: post wait failed - BARs not setup\n", + __func__); + } err = -ENXIO; break; } @@ -285,6 +315,8 @@ err_out: queue_work(pdsc->wq, &pdsc->health_work); } + refcount_dec(&pdsc->adminq_refcnt); + return err; } EXPORT_SYMBOL_GPL(pdsc_adminq_post); diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c index 0d2091e9eb28..7658a7286767 100644 --- a/drivers/net/ethernet/amd/pds_core/core.c +++ b/drivers/net/ethernet/amd/pds_core/core.c @@ -125,7 +125,7 @@ static int pdsc_qcq_intr_alloc(struct pdsc *pdsc, struct pdsc_qcq *qcq) snprintf(name, sizeof(name), "%s-%d-%s", PDS_CORE_DRV_NAME, pdsc->pdev->bus->number, qcq->q.name); - index = pdsc_intr_alloc(pdsc, name, pdsc_adminq_isr, qcq); + index = pdsc_intr_alloc(pdsc, name, pdsc_adminq_isr, pdsc); if (index < 0) return index; qcq->intx = index; @@ -404,10 +404,7 @@ int pdsc_setup(struct pdsc *pdsc, bool init) int numdescs; int err; - if (init) - err = pdsc_dev_init(pdsc); - else - err = pdsc_dev_reinit(pdsc); + err = pdsc_dev_init(pdsc); if (err) return err; @@ -450,6 +447,7 @@ int pdsc_setup(struct pdsc *pdsc, bool init) pdsc_debugfs_add_viftype(pdsc); } + refcount_set(&pdsc->adminq_refcnt, 1); clear_bit(PDSC_S_FW_DEAD, &pdsc->state); return 0; @@ -464,6 +462,8 @@ void pdsc_teardown(struct pdsc *pdsc, bool removing) if (!pdsc->pdev->is_virtfn) pdsc_devcmd_reset(pdsc); + if (pdsc->adminqcq.work.func) + cancel_work_sync(&pdsc->adminqcq.work); pdsc_qcq_free(pdsc, &pdsc->notifyqcq); pdsc_qcq_free(pdsc, &pdsc->adminqcq); @@ -476,10 +476,9 @@ void pdsc_teardown(struct pdsc *pdsc, bool removing) for (i = 0; i < pdsc->nintrs; i++) pdsc_intr_free(pdsc, i); - if (removing) { - kfree(pdsc->intr_info); - pdsc->intr_info = NULL; - } + kfree(pdsc->intr_info); + pdsc->intr_info = NULL; + pdsc->nintrs = 0; } if (pdsc->kern_dbpage) { @@ -487,6 +486,7 @@ void pdsc_teardown(struct pdsc *pdsc, bool removing) pdsc->kern_dbpage = NULL; } + pci_free_irq_vectors(pdsc->pdev); set_bit(PDSC_S_FW_DEAD, &pdsc->state); } @@ -512,6 +512,24 @@ void pdsc_stop(struct pdsc *pdsc) PDS_CORE_INTR_MASK_SET); } +static void pdsc_adminq_wait_and_dec_once_unused(struct pdsc *pdsc) +{ + /* The driver initializes the adminq_refcnt to 1 when the adminq is + * allocated and ready for use. Other users/requesters will increment + * the refcnt while in use. If the refcnt is down to 1 then the adminq + * is not in use and the refcnt can be cleared and adminq freed. Before + * calling this function the driver will set PDSC_S_FW_DEAD, which + * prevent subsequent attempts to use the adminq and increment the + * refcnt to fail. This guarantees that this function will eventually + * exit. + */ + while (!refcount_dec_if_one(&pdsc->adminq_refcnt)) { + dev_dbg_ratelimited(pdsc->dev, "%s: adminq in use\n", + __func__); + cpu_relax(); + } +} + void pdsc_fw_down(struct pdsc *pdsc) { union pds_core_notifyq_comp reset_event = { @@ -527,6 +545,8 @@ void pdsc_fw_down(struct pdsc *pdsc) if (pdsc->pdev->is_virtfn) return; + pdsc_adminq_wait_and_dec_once_unused(pdsc); + /* Notify clients of fw_down */ if (pdsc->fw_reporter) devlink_health_report(pdsc->fw_reporter, "FW down reported", pdsc); @@ -577,7 +597,13 @@ err_out: static void pdsc_check_pci_health(struct pdsc *pdsc) { - u8 fw_status = ioread8(&pdsc->info_regs->fw_status); + u8 fw_status; + + /* some sort of teardown already in progress */ + if (!pdsc->info_regs) + return; + + fw_status = ioread8(&pdsc->info_regs->fw_status); /* is PCI broken? */ if (fw_status != PDS_RC_BAD_PCI) diff --git a/drivers/net/ethernet/amd/pds_core/core.h b/drivers/net/ethernet/amd/pds_core/core.h index e35d3e7006bf..110c4b826b22 100644 --- a/drivers/net/ethernet/amd/pds_core/core.h +++ b/drivers/net/ethernet/amd/pds_core/core.h @@ -184,6 +184,7 @@ struct pdsc { struct mutex devcmd_lock; /* lock for dev_cmd operations */ struct mutex config_lock; /* lock for configuration operations */ spinlock_t adminq_lock; /* lock for adminq operations */ + refcount_t adminq_refcnt; struct pds_core_dev_info_regs __iomem *info_regs; struct pds_core_dev_cmd_regs __iomem *cmd_regs; struct pds_core_intr __iomem *intr_ctrl; @@ -280,7 +281,6 @@ int pdsc_devcmd_locked(struct pdsc *pdsc, union pds_core_dev_cmd *cmd, union pds_core_dev_comp *comp, int max_seconds); int pdsc_devcmd_init(struct pdsc *pdsc); int pdsc_devcmd_reset(struct pdsc *pdsc); -int pdsc_dev_reinit(struct pdsc *pdsc); int pdsc_dev_init(struct pdsc *pdsc); void pdsc_reset_prepare(struct pci_dev *pdev); diff --git a/drivers/net/ethernet/amd/pds_core/debugfs.c b/drivers/net/ethernet/amd/pds_core/debugfs.c index 8ec392299b7d..4e8579ca1c8c 100644 --- a/drivers/net/ethernet/amd/pds_core/debugfs.c +++ b/drivers/net/ethernet/amd/pds_core/debugfs.c @@ -64,6 +64,10 @@ DEFINE_SHOW_ATTRIBUTE(identity); void pdsc_debugfs_add_ident(struct pdsc *pdsc) { + /* This file will already exist in the reset flow */ + if (debugfs_lookup("identity", pdsc->dentry)) + return; + debugfs_create_file("identity", 0400, pdsc->dentry, pdsc, &identity_fops); } diff --git a/drivers/net/ethernet/amd/pds_core/dev.c b/drivers/net/ethernet/amd/pds_core/dev.c index 31940b857e0e..e65a1632df50 100644 --- a/drivers/net/ethernet/amd/pds_core/dev.c +++ b/drivers/net/ethernet/amd/pds_core/dev.c @@ -57,6 +57,9 @@ int pdsc_err_to_errno(enum pds_core_status_code code) bool pdsc_is_fw_running(struct pdsc *pdsc) { + if (!pdsc->info_regs) + return false; + pdsc->fw_status = ioread8(&pdsc->info_regs->fw_status); pdsc->last_fw_time = jiffies; pdsc->last_hb = ioread32(&pdsc->info_regs->fw_heartbeat); @@ -182,13 +185,17 @@ int pdsc_devcmd_locked(struct pdsc *pdsc, union pds_core_dev_cmd *cmd, { int err; + if (!pdsc->cmd_regs) + return -ENXIO; + memcpy_toio(&pdsc->cmd_regs->cmd, cmd, sizeof(*cmd)); pdsc_devcmd_dbell(pdsc); err = pdsc_devcmd_wait(pdsc, cmd->opcode, max_seconds); - memcpy_fromio(comp, &pdsc->cmd_regs->comp, sizeof(*comp)); if ((err == -ENXIO || err == -ETIMEDOUT) && pdsc->wq) queue_work(pdsc->wq, &pdsc->health_work); + else + memcpy_fromio(comp, &pdsc->cmd_regs->comp, sizeof(*comp)); return err; } @@ -309,13 +316,6 @@ static int pdsc_identify(struct pdsc *pdsc) return 0; } -int pdsc_dev_reinit(struct pdsc *pdsc) -{ - pdsc_init_devinfo(pdsc); - - return pdsc_identify(pdsc); -} - int pdsc_dev_init(struct pdsc *pdsc) { unsigned int nintrs; diff --git a/drivers/net/ethernet/amd/pds_core/devlink.c b/drivers/net/ethernet/amd/pds_core/devlink.c index e9948ea5bbcd..54864f27c87a 100644 --- a/drivers/net/ethernet/amd/pds_core/devlink.c +++ b/drivers/net/ethernet/amd/pds_core/devlink.c @@ -111,7 +111,8 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req, mutex_lock(&pdsc->devcmd_lock); err = pdsc_devcmd_locked(pdsc, &cmd, &comp, pdsc->devcmd_timeout * 2); - memcpy_fromio(&fw_list, pdsc->cmd_regs->data, sizeof(fw_list)); + if (!err) + memcpy_fromio(&fw_list, pdsc->cmd_regs->data, sizeof(fw_list)); mutex_unlock(&pdsc->devcmd_lock); if (err && err != -EIO) return err; diff --git a/drivers/net/ethernet/amd/pds_core/fw.c b/drivers/net/ethernet/amd/pds_core/fw.c index 90a811f3878a..fa626719e68d 100644 --- a/drivers/net/ethernet/amd/pds_core/fw.c +++ b/drivers/net/ethernet/amd/pds_core/fw.c @@ -107,6 +107,9 @@ int pdsc_firmware_update(struct pdsc *pdsc, const struct firmware *fw, dev_info(pdsc->dev, "Installing firmware\n"); + if (!pdsc->cmd_regs) + return -ENXIO; + dl = priv_to_devlink(pdsc); devlink_flash_update_status_notify(dl, "Preparing to flash", NULL, 0, 0); diff --git a/drivers/net/ethernet/amd/pds_core/main.c b/drivers/net/ethernet/amd/pds_core/main.c index 3080898d7b95..cdbf053b5376 100644 --- a/drivers/net/ethernet/amd/pds_core/main.c +++ b/drivers/net/ethernet/amd/pds_core/main.c @@ -37,6 +37,11 @@ static void pdsc_unmap_bars(struct pdsc *pdsc) struct pdsc_dev_bar *bars = pdsc->bars; unsigned int i; + pdsc->info_regs = NULL; + pdsc->cmd_regs = NULL; + pdsc->intr_status = NULL; + pdsc->intr_ctrl = NULL; + for (i = 0; i < PDS_CORE_BARS_MAX; i++) { if (bars[i].vaddr) pci_iounmap(pdsc->pdev, bars[i].vaddr); @@ -293,7 +298,7 @@ err_out_stop: err_out_teardown: pdsc_teardown(pdsc, PDSC_TEARDOWN_REMOVING); err_out_unmap_bars: - del_timer_sync(&pdsc->wdtimer); + timer_shutdown_sync(&pdsc->wdtimer); if (pdsc->wq) destroy_workqueue(pdsc->wq); mutex_destroy(&pdsc->config_lock); @@ -420,7 +425,7 @@ static void pdsc_remove(struct pci_dev *pdev) */ pdsc_sriov_configure(pdev, 0); - del_timer_sync(&pdsc->wdtimer); + timer_shutdown_sync(&pdsc->wdtimer); if (pdsc->wq) destroy_workqueue(pdsc->wq); @@ -433,7 +438,6 @@ static void pdsc_remove(struct pci_dev *pdev) mutex_destroy(&pdsc->config_lock); mutex_destroy(&pdsc->devcmd_lock); - pci_free_irq_vectors(pdev); pdsc_unmap_bars(pdsc); pci_release_regions(pdev); } @@ -445,13 +449,26 @@ static void pdsc_remove(struct pci_dev *pdev) devlink_free(dl); } +static void pdsc_stop_health_thread(struct pdsc *pdsc) +{ + timer_shutdown_sync(&pdsc->wdtimer); + if (pdsc->health_work.func) + cancel_work_sync(&pdsc->health_work); +} + +static void pdsc_restart_health_thread(struct pdsc *pdsc) +{ + timer_setup(&pdsc->wdtimer, pdsc_wdtimer_cb, 0); + mod_timer(&pdsc->wdtimer, jiffies + 1); +} + void pdsc_reset_prepare(struct pci_dev *pdev) { struct pdsc *pdsc = pci_get_drvdata(pdev); + pdsc_stop_health_thread(pdsc); pdsc_fw_down(pdsc); - pci_free_irq_vectors(pdev); pdsc_unmap_bars(pdsc); pci_release_regions(pdev); pci_disable_device(pdev); @@ -486,6 +503,7 @@ void pdsc_reset_done(struct pci_dev *pdev) } pdsc_fw_up(pdsc); + pdsc_restart_health_thread(pdsc); } static const struct pci_error_handlers pdsc_err_handler = { diff --git a/drivers/net/ethernet/broadcom/bcm4908_enet.c b/drivers/net/ethernet/broadcom/bcm4908_enet.c index 3e7c8671cd11..72df1bb10172 100644 --- a/drivers/net/ethernet/broadcom/bcm4908_enet.c +++ b/drivers/net/ethernet/broadcom/bcm4908_enet.c @@ -793,5 +793,6 @@ static struct platform_driver bcm4908_enet_driver = { }; module_platform_driver(bcm4908_enet_driver); +MODULE_DESCRIPTION("Broadcom BCM4908 Gigabit Ethernet driver"); MODULE_LICENSE("GPL v2"); MODULE_DEVICE_TABLE(of, bcm4908_enet_of_match); diff --git a/drivers/net/ethernet/broadcom/bgmac-bcma-mdio.c b/drivers/net/ethernet/broadcom/bgmac-bcma-mdio.c index 9b83d5361699..50b8e97a811d 100644 --- a/drivers/net/ethernet/broadcom/bgmac-bcma-mdio.c +++ b/drivers/net/ethernet/broadcom/bgmac-bcma-mdio.c @@ -260,4 +260,5 @@ void bcma_mdio_mii_unregister(struct mii_bus *mii_bus) EXPORT_SYMBOL_GPL(bcma_mdio_mii_unregister); MODULE_AUTHOR("Rafał Miłecki"); +MODULE_DESCRIPTION("Broadcom iProc GBit BCMA MDIO helpers"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/broadcom/bgmac-bcma.c b/drivers/net/ethernet/broadcom/bgmac-bcma.c index 6e4f36aaf5db..36f9bad28e6a 100644 --- a/drivers/net/ethernet/broadcom/bgmac-bcma.c +++ b/drivers/net/ethernet/broadcom/bgmac-bcma.c @@ -362,4 +362,5 @@ module_init(bgmac_init) module_exit(bgmac_exit) MODULE_AUTHOR("Rafał Miłecki"); +MODULE_DESCRIPTION("Broadcom iProc GBit BCMA interface driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c index 0b21fd5bd457..77425c7a32db 100644 --- a/drivers/net/ethernet/broadcom/bgmac-platform.c +++ b/drivers/net/ethernet/broadcom/bgmac-platform.c @@ -298,4 +298,5 @@ static struct platform_driver bgmac_enet_driver = { }; module_platform_driver(bgmac_enet_driver); +MODULE_DESCRIPTION("Broadcom iProc GBit platform interface driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index 448a1b90de5e..6ffdc4229407 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -1626,4 +1626,5 @@ int bgmac_enet_resume(struct bgmac *bgmac) EXPORT_SYMBOL_GPL(bgmac_enet_resume); MODULE_AUTHOR("Rafał Miłecki"); +MODULE_DESCRIPTION("Broadcom iProc GBit driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 0aacd3c6ed5c..39845d556baf 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -3817,7 +3817,7 @@ static int bnxt_alloc_cp_rings(struct bnxt *bp) { bool sh = !!(bp->flags & BNXT_FLAG_SHARED_RINGS); int i, j, rc, ulp_base_vec, ulp_msix; - int tcs = netdev_get_num_tc(bp->dev); + int tcs = bp->num_tc; if (!tcs) tcs = 1; @@ -5935,8 +5935,12 @@ static u16 bnxt_get_max_rss_ring(struct bnxt *bp) int bnxt_get_nr_rss_ctxs(struct bnxt *bp, int rx_rings) { - if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) - return DIV_ROUND_UP(rx_rings, BNXT_RSS_TABLE_ENTRIES_P5); + if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) { + if (!rx_rings) + return 0; + return bnxt_calc_nr_ring_pages(rx_rings - 1, + BNXT_RSS_TABLE_ENTRIES_P5); + } if (BNXT_CHIP_TYPE_NITRO_A0(bp)) return 2; return 1; @@ -6926,7 +6930,7 @@ static int bnxt_hwrm_get_rings(struct bnxt *bp) if (cp < (rx + tx)) { rc = __bnxt_trim_rings(bp, &rx, &tx, cp, false); if (rc) - return rc; + goto get_rings_exit; if (bp->flags & BNXT_FLAG_AGG_RINGS) rx <<= 1; hw_resc->resv_rx_rings = rx; @@ -6938,8 +6942,9 @@ static int bnxt_hwrm_get_rings(struct bnxt *bp) hw_resc->resv_cp_rings = cp; hw_resc->resv_stat_ctxs = stats; } +get_rings_exit: hwrm_req_drop(bp, req); - return 0; + return rc; } int __bnxt_hwrm_get_tx_rings(struct bnxt *bp, u16 fid, int *tx_rings) @@ -7000,10 +7005,11 @@ __bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings, req->num_rx_rings = cpu_to_le16(rx_rings); if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) { + u16 rss_ctx = bnxt_get_nr_rss_ctxs(bp, ring_grps); + req->num_cmpl_rings = cpu_to_le16(tx_rings + ring_grps); req->num_msix = cpu_to_le16(cp_rings); - req->num_rsscos_ctxs = - cpu_to_le16(DIV_ROUND_UP(ring_grps, 64)); + req->num_rsscos_ctxs = cpu_to_le16(rss_ctx); } else { req->num_cmpl_rings = cpu_to_le16(cp_rings); req->num_hw_ring_grps = cpu_to_le16(ring_grps); @@ -7050,8 +7056,10 @@ __bnxt_hwrm_reserve_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings, req->num_tx_rings = cpu_to_le16(tx_rings); req->num_rx_rings = cpu_to_le16(rx_rings); if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) { + u16 rss_ctx = bnxt_get_nr_rss_ctxs(bp, ring_grps); + req->num_cmpl_rings = cpu_to_le16(tx_rings + ring_grps); - req->num_rsscos_ctxs = cpu_to_le16(DIV_ROUND_UP(ring_grps, 64)); + req->num_rsscos_ctxs = cpu_to_le16(rss_ctx); } else { req->num_cmpl_rings = cpu_to_le16(cp_rings); req->num_hw_ring_grps = cpu_to_le16(ring_grps); @@ -9938,7 +9946,7 @@ static int __bnxt_num_tx_to_cp(struct bnxt *bp, int tx, int tx_sets, int tx_xdp) int bnxt_num_tx_to_cp(struct bnxt *bp, int tx) { - int tcs = netdev_get_num_tc(bp->dev); + int tcs = bp->num_tc; if (!tcs) tcs = 1; @@ -9947,7 +9955,7 @@ int bnxt_num_tx_to_cp(struct bnxt *bp, int tx) static int bnxt_num_cp_to_tx(struct bnxt *bp, int tx_cp) { - int tcs = netdev_get_num_tc(bp->dev); + int tcs = bp->num_tc; return (tx_cp - bp->tx_nr_rings_xdp) * tcs + bp->tx_nr_rings_xdp; @@ -9977,7 +9985,7 @@ static void bnxt_setup_msix(struct bnxt *bp) struct net_device *dev = bp->dev; int tcs, i; - tcs = netdev_get_num_tc(dev); + tcs = bp->num_tc; if (tcs) { int i, off, count; @@ -10009,8 +10017,10 @@ static void bnxt_setup_inta(struct bnxt *bp) { const int len = sizeof(bp->irq_tbl[0].name); - if (netdev_get_num_tc(bp->dev)) + if (bp->num_tc) { netdev_reset_tc(bp->dev); + bp->num_tc = 0; + } snprintf(bp->irq_tbl[0].name, len, "%s-%s-%d", bp->dev->name, "TxRx", 0); @@ -10236,8 +10246,8 @@ static void bnxt_clear_int_mode(struct bnxt *bp) int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init) { - int tcs = netdev_get_num_tc(bp->dev); bool irq_cleared = false; + int tcs = bp->num_tc; int rc; if (!bnxt_need_reserve_rings(bp)) @@ -10263,6 +10273,7 @@ int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init) bp->tx_nr_rings - bp->tx_nr_rings_xdp)) { netdev_err(bp->dev, "tx ring reservation failure\n"); netdev_reset_tc(bp->dev); + bp->num_tc = 0; if (bp->tx_nr_rings_xdp) bp->tx_nr_rings_per_tc = bp->tx_nr_rings_xdp; else @@ -11564,10 +11575,12 @@ int bnxt_half_open_nic(struct bnxt *bp) netdev_err(bp->dev, "bnxt_alloc_mem err: %x\n", rc); goto half_open_err; } + bnxt_init_napi(bp); set_bit(BNXT_STATE_HALF_OPEN, &bp->state); rc = bnxt_init_nic(bp, true); if (rc) { clear_bit(BNXT_STATE_HALF_OPEN, &bp->state); + bnxt_del_napi(bp); netdev_err(bp->dev, "bnxt_init_nic err: %x\n", rc); goto half_open_err; } @@ -11586,6 +11599,7 @@ half_open_err: void bnxt_half_close_nic(struct bnxt *bp) { bnxt_hwrm_resource_free(bp, false, true); + bnxt_del_napi(bp); bnxt_free_skbs(bp); bnxt_free_mem(bp, true); clear_bit(BNXT_STATE_HALF_OPEN, &bp->state); @@ -13232,6 +13246,11 @@ static int bnxt_fw_init_one_p1(struct bnxt *bp) bp->fw_cap = 0; rc = bnxt_hwrm_ver_get(bp); + /* FW may be unresponsive after FLR. FLR must complete within 100 msec + * so wait before continuing with recovery. + */ + if (rc) + msleep(100); bnxt_try_map_fw_health_reg(bp); if (rc) { rc = bnxt_try_recover_fw(bp); @@ -13784,7 +13803,7 @@ int bnxt_setup_mq_tc(struct net_device *dev, u8 tc) return -EINVAL; } - if (netdev_get_num_tc(dev) == tc) + if (bp->num_tc == tc) return 0; if (bp->flags & BNXT_FLAG_SHARED_RINGS) @@ -13802,9 +13821,11 @@ int bnxt_setup_mq_tc(struct net_device *dev, u8 tc) if (tc) { bp->tx_nr_rings = bp->tx_nr_rings_per_tc * tc; netdev_set_num_tc(dev, tc); + bp->num_tc = tc; } else { bp->tx_nr_rings = bp->tx_nr_rings_per_tc; netdev_reset_tc(dev); + bp->num_tc = 0; } bp->tx_nr_rings += bp->tx_nr_rings_xdp; tx_cp = bnxt_num_tx_to_cp(bp, bp->tx_nr_rings); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index b8ef1717cb65..47338b48ca20 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -2225,6 +2225,7 @@ struct bnxt { u8 tc_to_qidx[BNXT_MAX_QUEUE]; u8 q_ids[BNXT_MAX_QUEUE]; u8 max_q; + u8 num_tc; unsigned int current_interval; #define BNXT_TIMER_INTERVAL HZ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c index 63e067038385..0dbb880a7aa0 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c @@ -228,7 +228,7 @@ static int bnxt_queue_remap(struct bnxt *bp, unsigned int lltc_mask) } } if (bp->ieee_ets) { - int tc = netdev_get_num_tc(bp->dev); + int tc = bp->num_tc; if (!tc) tc = 1; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 27b983c0a8a9..dc4ca706b0e2 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -884,7 +884,7 @@ static void bnxt_get_channels(struct net_device *dev, if (max_tx_sch_inputs) max_tx_rings = min_t(int, max_tx_rings, max_tx_sch_inputs); - tcs = netdev_get_num_tc(dev); + tcs = bp->num_tc; tx_grps = max(tcs, 1); if (bp->tx_nr_rings_xdp) tx_grps++; @@ -944,7 +944,7 @@ static int bnxt_set_channels(struct net_device *dev, if (channel->combined_count) sh = true; - tcs = netdev_get_num_tc(dev); + tcs = bp->num_tc; req_tx_rings = sh ? channel->combined_count : channel->tx_count; req_rx_rings = sh ? channel->combined_count : channel->rx_count; @@ -1574,7 +1574,8 @@ u32 bnxt_get_rxfh_indir_size(struct net_device *dev) struct bnxt *bp = netdev_priv(dev); if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) - return ALIGN(bp->rx_nr_rings, BNXT_RSS_TABLE_ENTRIES_P5); + return bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings) * + BNXT_RSS_TABLE_ENTRIES_P5; return HW_HASH_INDEX_SIZE; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c index adad188e38b8..cc07660330f5 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c @@ -684,7 +684,7 @@ static void bnxt_stamp_tx_skb(struct bnxt *bp, struct sk_buff *skb) timestamp.hwtstamp = ns_to_ktime(ns); skb_tstamp_tx(ptp->tx_skb, ×tamp); } else { - netdev_WARN_ONCE(bp->dev, + netdev_warn_once(bp->dev, "TS query for TX timer failed rc = %x\n", rc); } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index c2b25fc623ec..4079538bc310 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -407,7 +407,7 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog) if (prog) tx_xdp = bp->rx_nr_rings; - tc = netdev_get_num_tc(dev); + tc = bp->num_tc; if (!tc) tc = 1; rc = bnxt_check_rings(bp, bp->tx_nr_rings_per_tc, bp->rx_nr_rings, diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c index 9cc6303c82ff..f38d31bfab1b 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_core.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c @@ -27,6 +27,7 @@ #include "octeon_network.h" MODULE_AUTHOR("Cavium Networks, <[email protected]>"); +MODULE_DESCRIPTION("Cavium LiquidIO Intelligent Server Adapter Core"); MODULE_LICENSE("GPL"); /* OOM task polling interval */ diff --git a/drivers/net/ethernet/cirrus/ep93xx_eth.c b/drivers/net/ethernet/cirrus/ep93xx_eth.c index 1c2a540db13d..1f495cfd7959 100644 --- a/drivers/net/ethernet/cirrus/ep93xx_eth.c +++ b/drivers/net/ethernet/cirrus/ep93xx_eth.c @@ -868,5 +868,6 @@ static struct platform_driver ep93xx_eth_driver = { module_platform_driver(ep93xx_eth_driver); +MODULE_DESCRIPTION("Cirrus EP93xx Ethernet driver"); MODULE_LICENSE("GPL"); MODULE_ALIAS("platform:ep93xx-eth"); diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c index df40c720e7b2..9aeff2b37a61 100644 --- a/drivers/net/ethernet/engleder/tsnep_main.c +++ b/drivers/net/ethernet/engleder/tsnep_main.c @@ -1485,7 +1485,7 @@ static int tsnep_rx_poll(struct tsnep_rx *rx, struct napi_struct *napi, xdp_prepare_buff(&xdp, page_address(entry->page), XDP_PACKET_HEADROOM + TSNEP_RX_INLINE_METADATA_SIZE, - length, false); + length - ETH_FCS_LEN, false); consume = tsnep_xdp_run_prog(rx, prog, &xdp, &xdp_status, tx_nq, tx); @@ -1568,7 +1568,7 @@ static int tsnep_rx_poll_zc(struct tsnep_rx *rx, struct napi_struct *napi, prefetch(entry->xdp->data); length = __le32_to_cpu(entry->desc_wb->properties) & TSNEP_DESC_LENGTH_MASK; - xsk_buff_set_size(entry->xdp, length); + xsk_buff_set_size(entry->xdp, length - ETH_FCS_LEN); xsk_buff_dma_sync_for_cpu(entry->xdp, rx->xsk_pool); /* RX metadata with timestamps is in front of actual data, @@ -1762,6 +1762,19 @@ static void tsnep_rx_reopen_xsk(struct tsnep_rx *rx) allocated--; } } + + /* set need wakeup flag immediately if ring is not filled completely, + * first polling would be too late as need wakeup signalisation would + * be delayed for an indefinite time + */ + if (xsk_uses_need_wakeup(rx->xsk_pool)) { + int desc_available = tsnep_rx_desc_available(rx); + + if (desc_available) + xsk_set_rx_need_wakeup(rx->xsk_pool); + else + xsk_clear_rx_need_wakeup(rx->xsk_pool); + } } static bool tsnep_pending(struct tsnep_queue *queue) diff --git a/drivers/net/ethernet/ezchip/nps_enet.c b/drivers/net/ethernet/ezchip/nps_enet.c index 07c2b701b5fa..9ebe751c1df0 100644 --- a/drivers/net/ethernet/ezchip/nps_enet.c +++ b/drivers/net/ethernet/ezchip/nps_enet.c @@ -661,4 +661,5 @@ static struct platform_driver nps_enet_driver = { module_platform_driver(nps_enet_driver); MODULE_AUTHOR("EZchip Semiconductor"); +MODULE_DESCRIPTION("EZchip NPS Ethernet driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index cffbf27c4656..bfdbdab443ae 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -3216,4 +3216,5 @@ void enetc_pci_remove(struct pci_dev *pdev) } EXPORT_SYMBOL_GPL(enetc_pci_remove); +MODULE_DESCRIPTION("NXP ENETC Ethernet driver"); MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index d42594f32275..432523b2c789 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -2036,6 +2036,7 @@ static void fec_enet_adjust_link(struct net_device *ndev) /* if any of the above changed restart the FEC */ if (status_change) { + netif_stop_queue(ndev); napi_disable(&fep->napi); netif_tx_lock_bh(ndev); fec_restart(ndev); @@ -2045,6 +2046,7 @@ static void fec_enet_adjust_link(struct net_device *ndev) } } else { if (fep->link) { + netif_stop_queue(ndev); napi_disable(&fep->napi); netif_tx_lock_bh(ndev); fec_stop(ndev); @@ -4769,4 +4771,5 @@ static struct platform_driver fec_driver = { module_platform_driver(fec_driver); +MODULE_DESCRIPTION("NXP Fast Ethernet Controller (FEC) driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/freescale/fsl_pq_mdio.c b/drivers/net/ethernet/freescale/fsl_pq_mdio.c index 70dd982a5edc..026f7270a54d 100644 --- a/drivers/net/ethernet/freescale/fsl_pq_mdio.c +++ b/drivers/net/ethernet/freescale/fsl_pq_mdio.c @@ -531,4 +531,5 @@ static struct platform_driver fsl_pq_mdio_driver = { module_platform_driver(fsl_pq_mdio_driver); +MODULE_DESCRIPTION("Freescale PQ MDIO helpers"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c index 7a8dc5386fff..76615d47e055 100644 --- a/drivers/net/ethernet/google/gve/gve_rx.c +++ b/drivers/net/ethernet/google/gve/gve_rx.c @@ -356,7 +356,7 @@ static enum pkt_hash_types gve_rss_type(__be16 pkt_flags) static struct sk_buff *gve_rx_add_frags(struct napi_struct *napi, struct gve_rx_slot_page_info *page_info, - u16 packet_buffer_size, u16 len, + unsigned int truesize, u16 len, struct gve_rx_ctx *ctx) { u32 offset = page_info->page_offset + page_info->pad; @@ -389,10 +389,10 @@ static struct sk_buff *gve_rx_add_frags(struct napi_struct *napi, if (skb != ctx->skb_head) { ctx->skb_head->len += len; ctx->skb_head->data_len += len; - ctx->skb_head->truesize += packet_buffer_size; + ctx->skb_head->truesize += truesize; } skb_add_rx_frag(skb, num_frags, page_info->page, - offset, len, packet_buffer_size); + offset, len, truesize); return ctx->skb_head; } @@ -486,7 +486,7 @@ static struct sk_buff *gve_rx_copy_to_pool(struct gve_rx_ring *rx, memcpy(alloc_page_info.page_address, src, page_info->pad + len); skb = gve_rx_add_frags(napi, &alloc_page_info, - rx->packet_buffer_size, + PAGE_SIZE, len, ctx); u64_stats_update_begin(&rx->statss); diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h index a187582d2299..ba9c19e6994c 100644 --- a/drivers/net/ethernet/intel/e1000e/e1000.h +++ b/drivers/net/ethernet/intel/e1000e/e1000.h @@ -360,23 +360,43 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca); * As a result, a shift of INCVALUE_SHIFT_n is used to fit a value of * INCVALUE_n into the TIMINCA register allowing 32+8+(24-INCVALUE_SHIFT_n) * bits to count nanoseconds leaving the rest for fractional nonseconds. + * + * Any given INCVALUE also has an associated maximum adjustment value. This + * maximum adjustment value is the largest increase (or decrease) which can be + * safely applied without overflowing the INCVALUE. Since INCVALUE has + * a maximum range of 24 bits, its largest value is 0xFFFFFF. + * + * To understand where the maximum value comes from, consider the following + * equation: + * + * new_incval = base_incval + (base_incval * adjustment) / 1billion + * + * To avoid overflow that means: + * max_incval = base_incval + (base_incval * max_adj) / billion + * + * Re-arranging: + * max_adj = floor(((max_incval - base_incval) * 1billion) / 1billion) */ #define INCVALUE_96MHZ 125 #define INCVALUE_SHIFT_96MHZ 17 #define INCPERIOD_SHIFT_96MHZ 2 #define INCPERIOD_96MHZ (12 >> INCPERIOD_SHIFT_96MHZ) +#define MAX_PPB_96MHZ 23999900 /* 23,999,900 ppb */ #define INCVALUE_25MHZ 40 #define INCVALUE_SHIFT_25MHZ 18 #define INCPERIOD_25MHZ 1 +#define MAX_PPB_25MHZ 599999900 /* 599,999,900 ppb */ #define INCVALUE_24MHZ 125 #define INCVALUE_SHIFT_24MHZ 14 #define INCPERIOD_24MHZ 3 +#define MAX_PPB_24MHZ 999999999 /* 999,999,999 ppb */ #define INCVALUE_38400KHZ 26 #define INCVALUE_SHIFT_38400KHZ 19 #define INCPERIOD_38400KHZ 1 +#define MAX_PPB_38400KHZ 230769100 /* 230,769,100 ppb */ /* Another drawback of scaling the incvalue by a large factor is the * 64-bit SYSTIM register overflows more quickly. This is dealt with diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c index 02d871bc112a..bbcfd529399b 100644 --- a/drivers/net/ethernet/intel/e1000e/ptp.c +++ b/drivers/net/ethernet/intel/e1000e/ptp.c @@ -280,8 +280,17 @@ void e1000e_ptp_init(struct e1000_adapter *adapter) switch (hw->mac.type) { case e1000_pch2lan: + adapter->ptp_clock_info.max_adj = MAX_PPB_96MHZ; + break; case e1000_pch_lpt: + if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) + adapter->ptp_clock_info.max_adj = MAX_PPB_96MHZ; + else + adapter->ptp_clock_info.max_adj = MAX_PPB_25MHZ; + break; case e1000_pch_spt: + adapter->ptp_clock_info.max_adj = MAX_PPB_24MHZ; + break; case e1000_pch_cnp: case e1000_pch_tgp: case e1000_pch_adp: @@ -289,15 +298,14 @@ void e1000e_ptp_init(struct e1000_adapter *adapter) case e1000_pch_lnp: case e1000_pch_ptp: case e1000_pch_nvp: - if ((hw->mac.type < e1000_pch_lpt) || - (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI)) { - adapter->ptp_clock_info.max_adj = 24000000 - 1; - break; - } - fallthrough; + if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) + adapter->ptp_clock_info.max_adj = MAX_PPB_24MHZ; + else + adapter->ptp_clock_info.max_adj = MAX_PPB_38400KHZ; + break; case e1000_82574: case e1000_82583: - adapter->ptp_clock_info.max_adj = 600000000 - 1; + adapter->ptp_clock_info.max_adj = MAX_PPB_25MHZ; break; default: break; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index ae8f9f135725..6e7fd473abfd 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -3588,40 +3588,55 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) struct i40e_hmc_obj_rxq rx_ctx; int err = 0; bool ok; - int ret; bitmap_zero(ring->state, __I40E_RING_STATE_NBITS); /* clear the context structure first */ memset(&rx_ctx, 0, sizeof(rx_ctx)); - if (ring->vsi->type == I40E_VSI_MAIN) - xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); + ring->rx_buf_len = vsi->rx_buf_len; + + /* XDP RX-queue info only needed for RX rings exposed to XDP */ + if (ring->vsi->type != I40E_VSI_MAIN) + goto skip; + + if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) { + err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, + ring->queue_index, + ring->q_vector->napi.napi_id, + ring->rx_buf_len); + if (err) + return err; + } ring->xsk_pool = i40e_xsk_pool(ring); if (ring->xsk_pool) { - ring->rx_buf_len = - xsk_pool_get_rx_frame_size(ring->xsk_pool); - ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, + xdp_rxq_info_unreg(&ring->xdp_rxq); + ring->rx_buf_len = xsk_pool_get_rx_frame_size(ring->xsk_pool); + err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, + ring->queue_index, + ring->q_vector->napi.napi_id, + ring->rx_buf_len); + if (err) + return err; + err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_XSK_BUFF_POOL, NULL); - if (ret) - return ret; + if (err) + return err; dev_info(&vsi->back->pdev->dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n", ring->queue_index); } else { - ring->rx_buf_len = vsi->rx_buf_len; - if (ring->vsi->type == I40E_VSI_MAIN) { - ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, - MEM_TYPE_PAGE_SHARED, - NULL); - if (ret) - return ret; - } + err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, + MEM_TYPE_PAGE_SHARED, + NULL); + if (err) + return err; } +skip: xdp_init_buff(&ring->xdp, i40e_rx_pg_size(ring) / 2, &ring->xdp_rxq); rx_ctx.dbuff = DIV_ROUND_UP(ring->rx_buf_len, diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 971ba3322038..0d7177083708 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -1548,7 +1548,6 @@ void i40e_free_rx_resources(struct i40e_ring *rx_ring) int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring) { struct device *dev = rx_ring->dev; - int err; u64_stats_init(&rx_ring->syncp); @@ -1569,14 +1568,6 @@ int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring) rx_ring->next_to_process = 0; rx_ring->next_to_use = 0; - /* XDP RX-queue info only needed for RX rings exposed to XDP */ - if (rx_ring->vsi->type == I40E_VSI_MAIN) { - err = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev, - rx_ring->queue_index, rx_ring->q_vector->napi.napi_id); - if (err < 0) - return err; - } - rx_ring->xdp_prog = rx_ring->vsi->xdp_prog; rx_ring->rx_bi = @@ -2087,7 +2078,8 @@ static void i40e_put_rx_buffer(struct i40e_ring *rx_ring, static void i40e_process_rx_buffs(struct i40e_ring *rx_ring, int xdp_res, struct xdp_buff *xdp) { - u32 next = rx_ring->next_to_clean; + u32 nr_frags = xdp_get_shared_info_from_buff(xdp)->nr_frags; + u32 next = rx_ring->next_to_clean, i = 0; struct i40e_rx_buffer *rx_buffer; xdp->flags = 0; @@ -2100,10 +2092,10 @@ static void i40e_process_rx_buffs(struct i40e_ring *rx_ring, int xdp_res, if (!rx_buffer->page) continue; - if (xdp_res == I40E_XDP_CONSUMED) - rx_buffer->pagecnt_bias++; - else + if (xdp_res != I40E_XDP_CONSUMED) i40e_rx_buffer_flip(rx_buffer, xdp->frame_sz); + else if (i++ <= nr_frags) + rx_buffer->pagecnt_bias++; /* EOP buffer will be put in i40e_clean_rx_irq() */ if (next == rx_ring->next_to_process) @@ -2117,20 +2109,20 @@ static void i40e_process_rx_buffs(struct i40e_ring *rx_ring, int xdp_res, * i40e_construct_skb - Allocate skb and populate it * @rx_ring: rx descriptor ring to transact packets on * @xdp: xdp_buff pointing to the data - * @nr_frags: number of buffers for the packet * * This function allocates an skb. It then populates it with the page * data from the current receive descriptor, taking care to set up the * skb correctly. */ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring, - struct xdp_buff *xdp, - u32 nr_frags) + struct xdp_buff *xdp) { unsigned int size = xdp->data_end - xdp->data; struct i40e_rx_buffer *rx_buffer; + struct skb_shared_info *sinfo; unsigned int headlen; struct sk_buff *skb; + u32 nr_frags = 0; /* prefetch first cache line of first page */ net_prefetch(xdp->data); @@ -2168,6 +2160,10 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring, memcpy(__skb_put(skb, headlen), xdp->data, ALIGN(headlen, sizeof(long))); + if (unlikely(xdp_buff_has_frags(xdp))) { + sinfo = xdp_get_shared_info_from_buff(xdp); + nr_frags = sinfo->nr_frags; + } rx_buffer = i40e_rx_bi(rx_ring, rx_ring->next_to_clean); /* update all of the pointers */ size -= headlen; @@ -2187,9 +2183,8 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring, } if (unlikely(xdp_buff_has_frags(xdp))) { - struct skb_shared_info *sinfo, *skinfo = skb_shinfo(skb); + struct skb_shared_info *skinfo = skb_shinfo(skb); - sinfo = xdp_get_shared_info_from_buff(xdp); memcpy(&skinfo->frags[skinfo->nr_frags], &sinfo->frags[0], sizeof(skb_frag_t) * nr_frags); @@ -2212,17 +2207,17 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring, * i40e_build_skb - Build skb around an existing buffer * @rx_ring: Rx descriptor ring to transact packets on * @xdp: xdp_buff pointing to the data - * @nr_frags: number of buffers for the packet * * This function builds an skb around an existing Rx buffer, taking care * to set up the skb correctly and avoid any memcpy overhead. */ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring, - struct xdp_buff *xdp, - u32 nr_frags) + struct xdp_buff *xdp) { unsigned int metasize = xdp->data - xdp->data_meta; + struct skb_shared_info *sinfo; struct sk_buff *skb; + u32 nr_frags; /* Prefetch first cache line of first page. If xdp->data_meta * is unused, this points exactly as xdp->data, otherwise we @@ -2231,6 +2226,11 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring, */ net_prefetch(xdp->data_meta); + if (unlikely(xdp_buff_has_frags(xdp))) { + sinfo = xdp_get_shared_info_from_buff(xdp); + nr_frags = sinfo->nr_frags; + } + /* build an skb around the page buffer */ skb = napi_build_skb(xdp->data_hard_start, xdp->frame_sz); if (unlikely(!skb)) @@ -2243,9 +2243,6 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring, skb_metadata_set(skb, metasize); if (unlikely(xdp_buff_has_frags(xdp))) { - struct skb_shared_info *sinfo; - - sinfo = xdp_get_shared_info_from_buff(xdp); xdp_update_skb_shared_info(skb, nr_frags, sinfo->xdp_frags_size, nr_frags * xdp->frame_sz, @@ -2589,9 +2586,9 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget, total_rx_bytes += size; } else { if (ring_uses_build_skb(rx_ring)) - skb = i40e_build_skb(rx_ring, xdp, nfrags); + skb = i40e_build_skb(rx_ring, xdp); else - skb = i40e_construct_skb(rx_ring, xdp, nfrags); + skb = i40e_construct_skb(rx_ring, xdp); /* drop if we failed to retrieve a buffer */ if (!skb) { diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index af7d5fa6cdc1..11500003af0d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -414,7 +414,8 @@ i40e_add_xsk_frag(struct i40e_ring *rx_ring, struct xdp_buff *first, } __skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, - virt_to_page(xdp->data_hard_start), 0, size); + virt_to_page(xdp->data_hard_start), + XDP_PACKET_HEADROOM, size); sinfo->xdp_frags_size += size; xsk_buff_add_frag(xdp); @@ -498,7 +499,6 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) xdp_res = i40e_run_xdp_zc(rx_ring, first, xdp_prog); i40e_handle_xdp_result_zc(rx_ring, first, rx_desc, &rx_packets, &rx_bytes, xdp_res, &failure); - first->flags = 0; next_to_clean = next_to_process; if (failure) break; diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 533b923cae2d..7ac847718882 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -547,19 +547,27 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) ring->rx_buf_len = ring->vsi->rx_buf_len; if (ring->vsi->type == ICE_VSI_PF) { - if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) - /* coverity[check_return] */ - __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, - ring->q_index, - ring->q_vector->napi.napi_id, - ring->vsi->rx_buf_len); + if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) { + err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, + ring->q_index, + ring->q_vector->napi.napi_id, + ring->rx_buf_len); + if (err) + return err; + } ring->xsk_pool = ice_xsk_pool(ring); if (ring->xsk_pool) { - xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); + xdp_rxq_info_unreg(&ring->xdp_rxq); ring->rx_buf_len = xsk_pool_get_rx_frame_size(ring->xsk_pool); + err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, + ring->q_index, + ring->q_vector->napi.napi_id, + ring->rx_buf_len); + if (err) + return err; err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_XSK_BUFF_POOL, NULL); @@ -571,13 +579,14 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) dev_info(dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n", ring->q_index); } else { - if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) - /* coverity[check_return] */ - __xdp_rxq_info_reg(&ring->xdp_rxq, - ring->netdev, - ring->q_index, - ring->q_vector->napi.napi_id, - ring->vsi->rx_buf_len); + if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) { + err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, + ring->q_index, + ring->q_vector->napi.napi_id, + ring->rx_buf_len); + if (err) + return err; + } err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_PAGE_SHARED, diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 74d13cc5a3a7..97d41d6ebf1f 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -513,11 +513,6 @@ int ice_setup_rx_ring(struct ice_rx_ring *rx_ring) if (ice_is_xdp_ena_vsi(rx_ring->vsi)) WRITE_ONCE(rx_ring->xdp_prog, rx_ring->vsi->xdp_prog); - if (rx_ring->vsi->type == ICE_VSI_PF && - !xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) - if (xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev, - rx_ring->q_index, rx_ring->q_vector->napi.napi_id)) - goto err; return 0; err: @@ -603,9 +598,7 @@ out_failure: ret = ICE_XDP_CONSUMED; } exit: - rx_buf->act = ret; - if (unlikely(xdp_buff_has_frags(xdp))) - ice_set_rx_bufs_act(xdp, rx_ring, ret); + ice_set_rx_bufs_act(xdp, rx_ring, ret); } /** @@ -893,14 +886,17 @@ ice_add_xdp_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, } if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) { - if (unlikely(xdp_buff_has_frags(xdp))) - ice_set_rx_bufs_act(xdp, rx_ring, ICE_XDP_CONSUMED); + ice_set_rx_bufs_act(xdp, rx_ring, ICE_XDP_CONSUMED); return -ENOMEM; } __skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, rx_buf->page, rx_buf->page_offset, size); sinfo->xdp_frags_size += size; + /* remember frag count before XDP prog execution; bpf_xdp_adjust_tail() + * can pop off frags but driver has to handle it on its own + */ + rx_ring->nr_frags = sinfo->nr_frags; if (page_is_pfmemalloc(rx_buf->page)) xdp_buff_set_frag_pfmemalloc(xdp); @@ -1251,6 +1247,7 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) xdp->data = NULL; rx_ring->first_desc = ntc; + rx_ring->nr_frags = 0; continue; construct_skb: if (likely(ice_ring_uses_build_skb(rx_ring))) @@ -1266,10 +1263,12 @@ construct_skb: ICE_XDP_CONSUMED); xdp->data = NULL; rx_ring->first_desc = ntc; + rx_ring->nr_frags = 0; break; } xdp->data = NULL; rx_ring->first_desc = ntc; + rx_ring->nr_frags = 0; stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_RXE_S); if (unlikely(ice_test_staterr(rx_desc->wb.status_error0, diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index b3379ff73674..af955b0e5dc5 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -358,6 +358,7 @@ struct ice_rx_ring { struct ice_tx_ring *xdp_ring; struct ice_rx_ring *next; /* pointer to next ring in q_vector */ struct xsk_buff_pool *xsk_pool; + u32 nr_frags; dma_addr_t dma; /* physical address of ring */ u16 rx_buf_len; u8 dcb_tc; /* Traffic class of ring */ diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h index 762047508619..afcead4baef4 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h @@ -12,26 +12,39 @@ * act: action to store onto Rx buffers related to XDP buffer parts * * Set action that should be taken before putting Rx buffer from first frag - * to one before last. Last one is handled by caller of this function as it - * is the EOP frag that is currently being processed. This function is - * supposed to be called only when XDP buffer contains frags. + * to the last. */ static inline void ice_set_rx_bufs_act(struct xdp_buff *xdp, const struct ice_rx_ring *rx_ring, const unsigned int act) { - const struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); - u32 first = rx_ring->first_desc; - u32 nr_frags = sinfo->nr_frags; + u32 sinfo_frags = xdp_get_shared_info_from_buff(xdp)->nr_frags; + u32 nr_frags = rx_ring->nr_frags + 1; + u32 idx = rx_ring->first_desc; u32 cnt = rx_ring->count; struct ice_rx_buf *buf; for (int i = 0; i < nr_frags; i++) { - buf = &rx_ring->rx_buf[first]; + buf = &rx_ring->rx_buf[idx]; buf->act = act; - if (++first == cnt) - first = 0; + if (++idx == cnt) + idx = 0; + } + + /* adjust pagecnt_bias on frags freed by XDP prog */ + if (sinfo_frags < rx_ring->nr_frags && act == ICE_XDP_CONSUMED) { + u32 delta = rx_ring->nr_frags - sinfo_frags; + + while (delta) { + if (idx == 0) + idx = cnt - 1; + else + idx--; + buf = &rx_ring->rx_buf[idx]; + buf->pagecnt_bias--; + delta--; + } } } diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 5d1ae8e4058a..8b81a1677045 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -825,7 +825,8 @@ ice_add_xsk_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *first, } __skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, - virt_to_page(xdp->data_hard_start), 0, size); + virt_to_page(xdp->data_hard_start), + XDP_PACKET_HEADROOM, size); sinfo->xdp_frags_size += size; xsk_buff_add_frag(xdp); @@ -895,7 +896,6 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) if (!first) { first = xdp; - xdp_buff_clear_frags_flag(first); } else if (ice_add_xsk_frag(rx_ring, first, xdp, size)) { break; } diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c index 5fea2fd957eb..58179bd733ff 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_lib.c +++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c @@ -783,6 +783,8 @@ static int idpf_cfg_netdev(struct idpf_vport *vport) /* setup watchdog timeout value to be 5 second */ netdev->watchdog_timeo = 5 * HZ; + netdev->dev_port = idx; + /* configure default MTU size */ netdev->min_mtu = ETH_MIN_MTU; netdev->max_mtu = vport->max_mtu; diff --git a/drivers/net/ethernet/intel/idpf/virtchnl2.h b/drivers/net/ethernet/intel/idpf/virtchnl2.h index 8dc837889723..4a3c4454d25a 100644 --- a/drivers/net/ethernet/intel/idpf/virtchnl2.h +++ b/drivers/net/ethernet/intel/idpf/virtchnl2.h @@ -978,7 +978,7 @@ struct virtchnl2_ptype { u8 proto_id_count; __le16 pad; __le16 proto_id[]; -}; +} __packed __aligned(2); VIRTCHNL2_CHECK_STRUCT_LEN(6, virtchnl2_ptype); /** diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c index 6208923e29a2..c1adc94a5a65 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -716,7 +716,8 @@ static s32 ixgbe_read_iosf_sb_reg_x550(struct ixgbe_hw *hw, u32 reg_addr, if ((command & IXGBE_SB_IOSF_CTRL_RESP_STAT_MASK) != 0) { error = FIELD_GET(IXGBE_SB_IOSF_CTRL_CMPL_ERR_MASK, command); hw_dbg(hw, "Failed to read, error %x\n", error); - return -EIO; + ret = -EIO; + goto out; } if (!ret) diff --git a/drivers/net/ethernet/litex/litex_liteeth.c b/drivers/net/ethernet/litex/litex_liteeth.c index 5182fe737c37..ff54fbe41bcc 100644 --- a/drivers/net/ethernet/litex/litex_liteeth.c +++ b/drivers/net/ethernet/litex/litex_liteeth.c @@ -318,4 +318,5 @@ static struct platform_driver liteeth_driver = { module_platform_driver(liteeth_driver); MODULE_AUTHOR("Joel Stanley <[email protected]>"); +MODULE_DESCRIPTION("LiteX Liteeth Ethernet driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 820b1fabe297..23adf53c2aa1 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -614,12 +614,38 @@ static void mvpp23_bm_set_8pool_mode(struct mvpp2 *priv) mvpp2_write(priv, MVPP22_BM_POOL_BASE_ADDR_HIGH_REG, val); } +/* Cleanup pool before actual initialization in the OS */ +static void mvpp2_bm_pool_cleanup(struct mvpp2 *priv, int pool_id) +{ + unsigned int thread = mvpp2_cpu_to_thread(priv, get_cpu()); + u32 val; + int i; + + /* Drain the BM from all possible residues left by firmware */ + for (i = 0; i < MVPP2_BM_POOL_SIZE_MAX; i++) + mvpp2_thread_read(priv, thread, MVPP2_BM_PHY_ALLOC_REG(pool_id)); + + put_cpu(); + + /* Stop the BM pool */ + val = mvpp2_read(priv, MVPP2_BM_POOL_CTRL_REG(pool_id)); + val |= MVPP2_BM_STOP_MASK; + mvpp2_write(priv, MVPP2_BM_POOL_CTRL_REG(pool_id), val); +} + static int mvpp2_bm_init(struct device *dev, struct mvpp2 *priv) { enum dma_data_direction dma_dir = DMA_FROM_DEVICE; int i, err, poolnum = MVPP2_BM_POOLS_NUM; struct mvpp2_port *port; + if (priv->percpu_pools) + poolnum = mvpp2_get_nrxqs(priv) * 2; + + /* Clean up the pool state in case it contains stale state */ + for (i = 0; i < poolnum; i++) + mvpp2_bm_pool_cleanup(priv, i); + if (priv->percpu_pools) { for (i = 0; i < priv->port_count; i++) { port = priv->port_list[i]; @@ -629,7 +655,6 @@ static int mvpp2_bm_init(struct device *dev, struct mvpp2 *priv) } } - poolnum = mvpp2_get_nrxqs(priv) * 2; for (i = 0; i < poolnum; i++) { /* the pool in use */ int pn = i / (poolnum / 2); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c index 9690ac01f02c..b92264d0a77e 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c @@ -413,4 +413,5 @@ const char *otx2_mbox_id2name(u16 id) EXPORT_SYMBOL(otx2_mbox_id2name); MODULE_AUTHOR("Marvell."); +MODULE_DESCRIPTION("Marvell RVU NIC Mbox helpers"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c index 2928898c7f8d..7f786de61014 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c @@ -314,7 +314,6 @@ static int otx2_set_channels(struct net_device *dev, pfvf->hw.tx_queues = channel->tx_count; if (pfvf->xdp_prog) pfvf->hw.xdp_queues = channel->rx_count; - pfvf->hw.non_qos_queues = pfvf->hw.tx_queues + pfvf->hw.xdp_queues; if (if_up) err = dev->netdev_ops->ndo_open(dev); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index a57455aebff6..e5fe67e73865 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1744,6 +1744,7 @@ int otx2_open(struct net_device *netdev) /* RQ and SQs are mapped to different CQs, * so find out max CQ IRQs (i.e CINTs) needed. */ + pf->hw.non_qos_queues = pf->hw.tx_queues + pf->hw.xdp_queues; pf->hw.cint_cnt = max3(pf->hw.rx_queues, pf->hw.tx_queues, pf->hw.tc_tx_queues); @@ -2643,8 +2644,6 @@ static int otx2_xdp_setup(struct otx2_nic *pf, struct bpf_prog *prog) xdp_features_clear_redirect_target(dev); } - pf->hw.non_qos_queues += pf->hw.xdp_queues; - if (if_up) otx2_open(pf->netdev); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c index 4d519ea833b2..f828d32737af 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c @@ -1403,7 +1403,7 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf, struct otx2_cq_queue *cq, bool *need_xdp_flush) { - unsigned char *hard_start, *data; + unsigned char *hard_start; int qidx = cq->cq_idx; struct xdp_buff xdp; struct page *page; @@ -1417,9 +1417,8 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf, xdp_init_buff(&xdp, pfvf->rbsize, &cq->xdp_rxq); - data = (unsigned char *)phys_to_virt(pa); - hard_start = page_address(page); - xdp_prepare_buff(&xdp, hard_start, data - hard_start, + hard_start = (unsigned char *)phys_to_virt(pa); + xdp_prepare_buff(&xdp, hard_start, OTX2_HEAD_ROOM, cqe->sg.seg_size, false); act = bpf_prog_run_xdp(prog, &xdp); diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index a6e91573f8da..de123350bd46 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -4761,7 +4761,10 @@ static int mtk_probe(struct platform_device *pdev) } if (MTK_HAS_CAPS(eth->soc->caps, MTK_36BIT_DMA)) { - err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(36)); + err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(36)); + if (!err) + err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)); + if (err) { dev_err(&pdev->dev, "Wrong DMA config\n"); return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index a7b1f9686c09..4957412ff1f6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -1923,6 +1923,7 @@ static void cmd_status_log(struct mlx5_core_dev *dev, u16 opcode, u8 status, { const char *namep = mlx5_command_str(opcode); struct mlx5_cmd_stats *stats; + unsigned long flags; if (!err || !(strcmp(namep, "unknown command opcode"))) return; @@ -1930,7 +1931,7 @@ static void cmd_status_log(struct mlx5_core_dev *dev, u16 opcode, u8 status, stats = xa_load(&dev->cmd.stats, opcode); if (!stats) return; - spin_lock_irq(&stats->lock); + spin_lock_irqsave(&stats->lock, flags); stats->failed++; if (err < 0) stats->last_failed_errno = -err; @@ -1939,7 +1940,7 @@ static void cmd_status_log(struct mlx5_core_dev *dev, u16 opcode, u8 status, stats->last_failed_mbox_status = status; stats->last_failed_syndrome = syndrome; } - spin_unlock_irq(&stats->lock); + spin_unlock_irqrestore(&stats->lock, flags); } /* preserve -EREMOTEIO for outbox.status != OK, otherwise return err as is */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 0bfe1ca8a364..55c6ace0acd5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -1124,7 +1124,7 @@ static inline bool mlx5_tx_swp_supported(struct mlx5_core_dev *mdev) extern const struct ethtool_ops mlx5e_ethtool_ops; int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, u32 *mkey); -int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev); +int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev, bool create_tises); void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev); int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb, bool enable_mc_lb); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c b/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c index e1283531e0b8..671adbad0a40 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c @@ -436,6 +436,7 @@ static int fs_any_create_groups(struct mlx5e_flow_table *ft) in = kvzalloc(inlen, GFP_KERNEL); if (!in || !ft->g) { kfree(ft->g); + ft->g = NULL; kvfree(in); return -ENOMEM; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index 284253b79266..5d213a9886f1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -1064,8 +1064,8 @@ void mlx5e_build_sq_param(struct mlx5_core_dev *mdev, void *wq = MLX5_ADDR_OF(sqc, sqc, wq); bool allow_swp; - allow_swp = - mlx5_geneve_tx_allowed(mdev) || !!mlx5_ipsec_device_caps(mdev); + allow_swp = mlx5_geneve_tx_allowed(mdev) || + (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_CRYPTO); mlx5e_build_sq_param_common(mdev, param); MLX5_SET(wq, wq, log_wq_sz, params->log_sq_size); MLX5_SET(sqc, sqc, allow_swp, allow_swp); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index c206cc0a8483..078f56a3cbb2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -213,7 +213,7 @@ static void mlx5e_ptp_handle_ts_cqe(struct mlx5e_ptpsq *ptpsq, mlx5e_ptpsq_mark_ts_cqes_undelivered(ptpsq, hwtstamp); out: napi_consume_skb(skb, budget); - md_buff[*md_buff_sz++] = metadata_id; + md_buff[(*md_buff_sz)++] = metadata_id; if (unlikely(mlx5e_ptp_metadata_map_unhealthy(&ptpsq->metadata_map)) && !test_and_set_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) queue_work(ptpsq->txqsq.priv->wq, &ptpsq->report_unhealthy_work); 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 161c5190c236..05612d9c6080 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c @@ -336,12 +336,17 @@ void mlx5e_ipsec_build_accel_xfrm_attrs(struct mlx5e_ipsec_sa_entry *sa_entry, /* iv len */ aes_gcm->icv_len = x->aead->alg_icv_len; + attrs->dir = x->xso.dir; + /* esn */ if (x->props.flags & XFRM_STATE_ESN) { attrs->replay_esn.trigger = true; attrs->replay_esn.esn = sa_entry->esn_state.esn; attrs->replay_esn.esn_msb = sa_entry->esn_state.esn_msb; attrs->replay_esn.overlap = sa_entry->esn_state.overlap; + if (attrs->dir == XFRM_DEV_OFFLOAD_OUT) + goto skip_replay_window; + switch (x->replay_esn->replay_window) { case 32: attrs->replay_esn.replay_window = @@ -365,7 +370,7 @@ void mlx5e_ipsec_build_accel_xfrm_attrs(struct mlx5e_ipsec_sa_entry *sa_entry, } } - attrs->dir = x->xso.dir; +skip_replay_window: /* spi */ attrs->spi = be32_to_cpu(x->id.spi); @@ -501,7 +506,8 @@ static int mlx5e_xfrm_validate_state(struct mlx5_core_dev *mdev, return -EINVAL; } - if (x->replay_esn && x->replay_esn->replay_window != 32 && + if (x->replay_esn && x->xso.dir == XFRM_DEV_OFFLOAD_IN && + x->replay_esn->replay_window != 32 && x->replay_esn->replay_window != 64 && x->replay_esn->replay_window != 128 && x->replay_esn->replay_window != 256) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c index bb7f86c993e5..e66f486faafe 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c @@ -254,11 +254,13 @@ static int arfs_create_groups(struct mlx5e_flow_table *ft, ft->g = kcalloc(MLX5E_ARFS_NUM_GROUPS, sizeof(*ft->g), GFP_KERNEL); - in = kvzalloc(inlen, GFP_KERNEL); - if (!in || !ft->g) { - kfree(ft->g); - kvfree(in); + if (!ft->g) return -ENOMEM; + + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) { + err = -ENOMEM; + goto err_free_g; } mc = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); @@ -278,7 +280,7 @@ static int arfs_create_groups(struct mlx5e_flow_table *ft, break; default: err = -EINVAL; - goto out; + goto err_free_in; } switch (type) { @@ -300,7 +302,7 @@ static int arfs_create_groups(struct mlx5e_flow_table *ft, break; default: err = -EINVAL; - goto out; + goto err_free_in; } MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS); @@ -309,7 +311,7 @@ static int arfs_create_groups(struct mlx5e_flow_table *ft, MLX5_SET_CFG(in, end_flow_index, ix - 1); ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in); if (IS_ERR(ft->g[ft->num_groups])) - goto err; + goto err_clean_group; ft->num_groups++; memset(in, 0, inlen); @@ -318,18 +320,20 @@ static int arfs_create_groups(struct mlx5e_flow_table *ft, MLX5_SET_CFG(in, end_flow_index, ix - 1); ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in); if (IS_ERR(ft->g[ft->num_groups])) - goto err; + goto err_clean_group; ft->num_groups++; kvfree(in); return 0; -err: +err_clean_group: err = PTR_ERR(ft->g[ft->num_groups]); ft->g[ft->num_groups] = NULL; -out: +err_free_in: kvfree(in); - +err_free_g: + kfree(ft->g); + ft->g = NULL; return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c index 67f546683e85..6ed3a32b7e22 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c @@ -95,7 +95,7 @@ static void mlx5e_destroy_tises(struct mlx5_core_dev *mdev, u32 tisn[MLX5_MAX_PO { int tc, i; - for (i = 0; i < MLX5_MAX_PORTS; i++) + for (i = 0; i < mlx5e_get_num_lag_ports(mdev); i++) for (tc = 0; tc < MLX5_MAX_NUM_TC; tc++) mlx5e_destroy_tis(mdev, tisn[i][tc]); } @@ -110,7 +110,7 @@ static int mlx5e_create_tises(struct mlx5_core_dev *mdev, u32 tisn[MLX5_MAX_PORT int tc, i; int err; - for (i = 0; i < MLX5_MAX_PORTS; i++) { + for (i = 0; i < mlx5e_get_num_lag_ports(mdev); i++) { for (tc = 0; tc < MLX5_MAX_NUM_TC; tc++) { u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {}; void *tisc; @@ -140,7 +140,7 @@ err_close_tises: return err; } -int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev) +int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev, bool create_tises) { struct mlx5e_hw_objs *res = &mdev->mlx5e_res.hw_objs; int err; @@ -169,11 +169,15 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev) goto err_destroy_mkey; } - err = mlx5e_create_tises(mdev, res->tisn); - if (err) { - mlx5_core_err(mdev, "alloc tises failed, %d\n", err); - goto err_destroy_bfreg; + if (create_tises) { + err = mlx5e_create_tises(mdev, res->tisn); + if (err) { + mlx5_core_err(mdev, "alloc tises failed, %d\n", err); + goto err_destroy_bfreg; + } + res->tisn_valid = true; } + INIT_LIST_HEAD(&res->td.tirs_list); mutex_init(&res->td.list_lock); @@ -203,7 +207,8 @@ void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev) mlx5_crypto_dek_cleanup(mdev->mlx5e_res.dek_priv); mdev->mlx5e_res.dek_priv = NULL; - mlx5e_destroy_tises(mdev, res->tisn); + if (res->tisn_valid) + mlx5e_destroy_tises(mdev, res->tisn); mlx5_free_bfreg(mdev, &res->bfreg); mlx5_core_destroy_mkey(mdev, res->mkey); mlx5_core_dealloc_transport_domain(mdev, res->td.tdn); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index b5f1c4ca38ba..c8e8f512803e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -5992,7 +5992,7 @@ static int mlx5e_resume(struct auxiliary_device *adev) if (netif_device_present(netdev)) return 0; - err = mlx5e_create_mdev_resources(mdev); + err = mlx5e_create_mdev_resources(mdev, true); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 30932c9c9a8f..9fb2c057bd78 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -761,7 +761,7 @@ static int mlx5e_hairpin_create_indirect_rqt(struct mlx5e_hairpin *hp) err = mlx5e_rss_params_indir_init(&indir, mdev, mlx5e_rqt_size(mdev, hp->num_channels), - mlx5e_rqt_size(mdev, priv->max_nch)); + mlx5e_rqt_size(mdev, hp->num_channels)); if (err) return err; @@ -2014,9 +2014,10 @@ static void mlx5e_tc_del_fdb_peer_flow(struct mlx5e_tc_flow *flow, list_for_each_entry_safe(peer_flow, tmp, &flow->peer_flows, peer_flows) { if (peer_index != mlx5_get_dev_index(peer_flow->priv->mdev)) continue; + + list_del(&peer_flow->peer_flows); if (refcount_dec_and_test(&peer_flow->refcnt)) { mlx5e_tc_del_fdb_flow(peer_flow->priv, peer_flow); - list_del(&peer_flow->peer_flows); kfree(peer_flow); } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_mcast.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_mcast.c index a7ed87e9d842..22dd30cf8033 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_mcast.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_mcast.c @@ -83,6 +83,7 @@ mlx5_esw_bridge_mdb_flow_create(u16 esw_owner_vhca_id, struct mlx5_esw_bridge_md i++; } + rule_spec->flow_context.flags |= FLOW_CONTEXT_UPLINK_HAIRPIN_EN; rule_spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; dmac_v = MLX5_ADDR_OF(fte_match_param, rule_spec->match_value, outer_headers.dmac_47_16); ether_addr_copy(dmac_v, entry->key.addr); @@ -587,6 +588,7 @@ mlx5_esw_bridge_mcast_vlan_flow_create(u16 vlan_proto, struct mlx5_esw_bridge_po if (!rule_spec) return ERR_PTR(-ENOMEM); + rule_spec->flow_context.flags |= FLOW_CONTEXT_UPLINK_HAIRPIN_EN; rule_spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; @@ -662,6 +664,7 @@ mlx5_esw_bridge_mcast_fwd_flow_create(struct mlx5_esw_bridge_port *port) dest.vport.flags = MLX5_FLOW_DEST_VPORT_VHCA_ID; dest.vport.vhca_id = port->esw_owner_vhca_id; } + rule_spec->flow_context.flags |= FLOW_CONTEXT_UPLINK_HAIRPIN_EN; handle = mlx5_add_flow_rules(port->mcast.ft, rule_spec, &flow_act, &dest, 1); kvfree(rule_spec); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 1616a6144f7b..9b8599c200e2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -566,6 +566,8 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, fte->flow_context.flow_tag); MLX5_SET(flow_context, in_flow_context, flow_source, fte->flow_context.flow_source); + MLX5_SET(flow_context, in_flow_context, uplink_hairpin_en, + !!(fte->flow_context.flags & FLOW_CONTEXT_UPLINK_HAIRPIN_EN)); MLX5_SET(flow_context, in_flow_context, extended_destination, extended_dest); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 58845121954c..d77be1b4dd9c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -783,7 +783,7 @@ static int mlx5_rdma_setup_rn(struct ib_device *ibdev, u32 port_num, } /* This should only be called once per mdev */ - err = mlx5e_create_mdev_resources(mdev); + err = mlx5e_create_mdev_resources(mdev, false); if (err) goto destroy_ht; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c index 40c7be124041..58bd749b5e4d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c @@ -98,7 +98,7 @@ static int create_aso_cq(struct mlx5_aso_cq *cq, void *cqc_data) mlx5_fill_page_frag_array(&cq->wq_ctrl.buf, (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas)); - MLX5_SET(cqc, cqc, cq_period_mode, DIM_CQ_PERIOD_MODE_START_FROM_EQE); + MLX5_SET(cqc, cqc, cq_period_mode, MLX5_CQ_PERIOD_MODE_START_FROM_EQE); MLX5_SET(cqc, cqc, c_eqn_or_apu_element, eqn); MLX5_SET(cqc, cqc, uar_page, mdev->priv.uar->index); MLX5_SET(cqc, cqc, log_page_size, cq->wq_ctrl.buf.page_shift - diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c index 6f9790e97fed..2ebb61ef3ea9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c @@ -788,6 +788,7 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, switch (action_type) { case DR_ACTION_TYP_DROP: attr.final_icm_addr = nic_dmn->drop_icm_addr; + attr.hit_gvmi = nic_dmn->drop_icm_addr >> 48; break; case DR_ACTION_TYP_FT: dest_action = action; @@ -873,11 +874,17 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, action->sampler->tx_icm_addr; break; case DR_ACTION_TYP_VPORT: - attr.hit_gvmi = action->vport->caps->vhca_gvmi; - dest_action = action; - attr.final_icm_addr = rx_rule ? - action->vport->caps->icm_address_rx : - action->vport->caps->icm_address_tx; + if (unlikely(rx_rule && action->vport->caps->num == MLX5_VPORT_UPLINK)) { + /* can't go to uplink on RX rule - dropping instead */ + attr.final_icm_addr = nic_dmn->drop_icm_addr; + attr.hit_gvmi = nic_dmn->drop_icm_addr >> 48; + } else { + attr.hit_gvmi = action->vport->caps->vhca_gvmi; + dest_action = action; + attr.final_icm_addr = rx_rule ? + action->vport->caps->icm_address_rx : + action->vport->caps->icm_address_tx; + } break; case DR_ACTION_TYP_POP_VLAN: if (!rx_rule && !(dmn->ste_ctx->actions_caps & diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index 21753f327868..1005bb6935b6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -440,6 +440,27 @@ out: } EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_system_image_guid); +int mlx5_query_nic_vport_sd_group(struct mlx5_core_dev *mdev, u8 *sd_group) +{ + int outlen = MLX5_ST_SZ_BYTES(query_nic_vport_context_out); + u32 *out; + int err; + + out = kvzalloc(outlen, GFP_KERNEL); + if (!out) + return -ENOMEM; + + err = mlx5_query_nic_vport_context(mdev, 0, out); + if (err) + goto out; + + *sd_group = MLX5_GET(query_nic_vport_context_out, out, + nic_vport_context.sd_group); +out: + kvfree(out); + return err; +} + int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid) { u32 *out; diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_port.c b/drivers/net/ethernet/microchip/lan966x/lan966x_port.c index 92108d354051..2e83bbb9477e 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_port.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_port.c @@ -168,9 +168,10 @@ static void lan966x_port_link_up(struct lan966x_port *port) lan966x_taprio_speed_set(port, config->speed); /* Also the GIGA_MODE_ENA(1) needs to be set regardless of the - * port speed for QSGMII ports. + * port speed for QSGMII or SGMII ports. */ - if (phy_interface_num_ports(config->portmode) == 4) + if (phy_interface_num_ports(config->portmode) == 4 || + config->portmode == PHY_INTERFACE_MODE_SGMII) mode = DEV_MAC_MODE_CFG_GIGA_MODE_ENA_SET(1); lan_wr(config->duplex | mode, diff --git a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c index 2967bab72505..15180538b80a 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c +++ b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c @@ -1424,10 +1424,30 @@ static void nfp_nft_ct_translate_mangle_action(struct flow_action_entry *mangle_ mangle_action->mangle.mask = (__force u32)cpu_to_be32(mangle_action->mangle.mask); return; + /* Both struct tcphdr and struct udphdr start with + * __be16 source; + * __be16 dest; + * so we can use the same code for both. + */ case FLOW_ACT_MANGLE_HDR_TYPE_TCP: case FLOW_ACT_MANGLE_HDR_TYPE_UDP: - mangle_action->mangle.val = (__force u16)cpu_to_be16(mangle_action->mangle.val); - mangle_action->mangle.mask = (__force u16)cpu_to_be16(mangle_action->mangle.mask); + if (mangle_action->mangle.offset == offsetof(struct tcphdr, source)) { + mangle_action->mangle.val = + (__force u32)cpu_to_be32(mangle_action->mangle.val << 16); + /* The mask of mangle action is inverse mask, + * so clear the dest tp port with 0xFFFF to + * instead of rotate-left operation. + */ + mangle_action->mangle.mask = + (__force u32)cpu_to_be32(mangle_action->mangle.mask << 16 | 0xFFFF); + } + if (mangle_action->mangle.offset == offsetof(struct tcphdr, dest)) { + mangle_action->mangle.offset = 0; + mangle_action->mangle.val = + (__force u32)cpu_to_be32(mangle_action->mangle.val); + mangle_action->mangle.mask = + (__force u32)cpu_to_be32(mangle_action->mangle.mask); + } return; default: @@ -1864,10 +1884,30 @@ int nfp_fl_ct_handle_post_ct(struct nfp_flower_priv *priv, { struct flow_rule *rule = flow_cls_offload_flow_rule(flow); struct nfp_fl_ct_flow_entry *ct_entry; + struct flow_action_entry *ct_goto; struct nfp_fl_ct_zone_entry *zt; + struct flow_action_entry *act; bool wildcarded = false; struct flow_match_ct ct; - struct flow_action_entry *ct_goto; + int i; + + flow_action_for_each(i, act, &rule->action) { + switch (act->id) { + case FLOW_ACTION_REDIRECT: + case FLOW_ACTION_REDIRECT_INGRESS: + case FLOW_ACTION_MIRRED: + case FLOW_ACTION_MIRRED_INGRESS: + if (act->dev->rtnl_link_ops && + !strcmp(act->dev->rtnl_link_ops->kind, "openvswitch")) { + NL_SET_ERR_MSG_MOD(extack, + "unsupported offload: out port is openvswitch internal port"); + return -EOPNOTSUPP; + } + break; + default: + break; + } + } flow_rule_match_ct(rule, &ct); if (!ct.mask->ct_zone) { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c index 8f730ada71f9..6b65420e11b5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c @@ -353,6 +353,10 @@ static int imx_dwmac_probe(struct platform_device *pdev) if (data->flags & STMMAC_FLAG_HWTSTAMP_CORRECT_LATENCY) plat_dat->flags |= STMMAC_FLAG_HWTSTAMP_CORRECT_LATENCY; + /* Default TX Q0 to use TSO and rest TXQ for TBS */ + for (int i = 1; i < plat_dat->tx_queues_to_use; i++) + plat_dat->tx_queues_cfg[i].tbs_en = 1; + plat_dat->host_dma_width = dwmac->ops->addr_width; plat_dat->init = imx_dwmac_init; plat_dat->exit = imx_dwmac_exit; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index a0e46369ae15..25519952f754 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3932,6 +3932,9 @@ static int __stmmac_open(struct net_device *dev, priv->rx_copybreak = STMMAC_RX_COPYBREAK; buf_sz = dma_conf->dma_buf_sz; + for (int i = 0; i < MTL_MAX_TX_QUEUES; i++) + if (priv->dma_conf.tx_queue[i].tbs & STMMAC_TBS_EN) + dma_conf->tx_queue[i].tbs = priv->dma_conf.tx_queue[i].tbs; memcpy(&priv->dma_conf, dma_conf, sizeof(*dma_conf)); stmmac_reset_queues_param(priv); @@ -7542,6 +7545,9 @@ int stmmac_dvr_probe(struct device *device, dev_err(priv->device, "unable to bring out of ahb reset: %pe\n", ERR_PTR(ret)); + /* Wait a bit for the reset to take effect */ + udelay(10); + /* Init MAC and get the capabilities */ ret = stmmac_hw_init(priv); if (ret) diff --git a/drivers/net/fjes/fjes_hw.c b/drivers/net/fjes/fjes_hw.c index 704e949484d0..b9b5554ea862 100644 --- a/drivers/net/fjes/fjes_hw.c +++ b/drivers/net/fjes/fjes_hw.c @@ -221,21 +221,25 @@ static int fjes_hw_setup(struct fjes_hw *hw) mem_size = FJES_DEV_REQ_BUF_SIZE(hw->max_epid); hw->hw_info.req_buf = kzalloc(mem_size, GFP_KERNEL); - if (!(hw->hw_info.req_buf)) - return -ENOMEM; + if (!(hw->hw_info.req_buf)) { + result = -ENOMEM; + goto free_ep_info; + } hw->hw_info.req_buf_size = mem_size; mem_size = FJES_DEV_RES_BUF_SIZE(hw->max_epid); hw->hw_info.res_buf = kzalloc(mem_size, GFP_KERNEL); - if (!(hw->hw_info.res_buf)) - return -ENOMEM; + if (!(hw->hw_info.res_buf)) { + result = -ENOMEM; + goto free_req_buf; + } hw->hw_info.res_buf_size = mem_size; result = fjes_hw_alloc_shared_status_region(hw); if (result) - return result; + goto free_res_buf; hw->hw_info.buffer_share_bit = 0; hw->hw_info.buffer_unshare_reserve_bit = 0; @@ -246,11 +250,11 @@ static int fjes_hw_setup(struct fjes_hw *hw) result = fjes_hw_alloc_epbuf(&buf_pair->tx); if (result) - return result; + goto free_epbuf; result = fjes_hw_alloc_epbuf(&buf_pair->rx); if (result) - return result; + goto free_epbuf; spin_lock_irqsave(&hw->rx_status_lock, flags); fjes_hw_setup_epbuf(&buf_pair->tx, mac, @@ -273,6 +277,25 @@ static int fjes_hw_setup(struct fjes_hw *hw) fjes_hw_init_command_registers(hw, ¶m); return 0; + +free_epbuf: + for (epidx = 0; epidx < hw->max_epid ; epidx++) { + if (epidx == hw->my_epid) + continue; + fjes_hw_free_epbuf(&hw->ep_shm_info[epidx].tx); + fjes_hw_free_epbuf(&hw->ep_shm_info[epidx].rx); + } + fjes_hw_free_shared_status_region(hw); +free_res_buf: + kfree(hw->hw_info.res_buf); + hw->hw_info.res_buf = NULL; +free_req_buf: + kfree(hw->hw_info.req_buf); + hw->hw_info.req_buf = NULL; +free_ep_info: + kfree(hw->ep_shm_info); + hw->ep_shm_info = NULL; + return result; } static void fjes_hw_cleanup(struct fjes_hw *hw) diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 1dafa44155d0..a6fcbda64ecc 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -708,7 +708,10 @@ void netvsc_device_remove(struct hv_device *device) /* Disable NAPI and disassociate its context from the device. */ for (i = 0; i < net_device->num_chn; i++) { /* See also vmbus_reset_channel_cb(). */ - napi_disable(&net_device->chan_table[i].napi); + /* only disable enabled NAPI channel */ + if (i < ndev->real_num_rx_queues) + napi_disable(&net_device->chan_table[i].napi); + netif_napi_del(&net_device->chan_table[i].napi); } diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 4406427d4617..273bd8a20122 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -44,7 +44,7 @@ static unsigned int ring_size __ro_after_init = 128; module_param(ring_size, uint, 0444); -MODULE_PARM_DESC(ring_size, "Ring buffer size (# of pages)"); +MODULE_PARM_DESC(ring_size, "Ring buffer size (# of 4K pages)"); unsigned int netvsc_ring_bytes __ro_after_init; static const u32 default_msg = NETIF_MSG_DRV | NETIF_MSG_PROBE | @@ -2807,7 +2807,7 @@ static int __init netvsc_drv_init(void) pr_info("Increased ring_size to %u (min allowed)\n", ring_size); } - netvsc_ring_bytes = ring_size * PAGE_SIZE; + netvsc_ring_bytes = VMBUS_RING_SIZE(ring_size * 4096); register_netdevice_notifier(&netvsc_netdev_notifier); diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index e34816638569..7f5426285c61 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -607,11 +607,26 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb, return ERR_PTR(-EINVAL); } - ret = skb_ensure_writable_head_tail(skb, dev); - if (unlikely(ret < 0)) { - macsec_txsa_put(tx_sa); - kfree_skb(skb); - return ERR_PTR(ret); + if (unlikely(skb_headroom(skb) < MACSEC_NEEDED_HEADROOM || + skb_tailroom(skb) < MACSEC_NEEDED_TAILROOM)) { + struct sk_buff *nskb = skb_copy_expand(skb, + MACSEC_NEEDED_HEADROOM, + MACSEC_NEEDED_TAILROOM, + GFP_ATOMIC); + if (likely(nskb)) { + consume_skb(skb); + skb = nskb; + } else { + macsec_txsa_put(tx_sa); + kfree_skb(skb); + return ERR_PTR(-ENOMEM); + } + } else { + skb = skb_unshare(skb, GFP_ATOMIC); + if (!skb) { + macsec_txsa_put(tx_sa); + return ERR_PTR(-ENOMEM); + } } unprotected_len = skb->len; diff --git a/drivers/net/phy/mediatek-ge-soc.c b/drivers/net/phy/mediatek-ge-soc.c index 8a20d9889f10..0f3a1538a8b8 100644 --- a/drivers/net/phy/mediatek-ge-soc.c +++ b/drivers/net/phy/mediatek-ge-soc.c @@ -489,7 +489,7 @@ static int tx_r50_fill_result(struct phy_device *phydev, u16 tx_r50_cal_val, u16 reg, val; if (phydev->drv->phy_id == MTK_GPHY_ID_MT7988) - bias = -2; + bias = -1; val = clamp_val(bias + tx_r50_cal_val, 0, 63); @@ -705,6 +705,11 @@ restore: static void mt798x_phy_common_finetune(struct phy_device *phydev) { phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5); + /* SlvDSPreadyTime = 24, MasDSPreadyTime = 24 */ + __phy_write(phydev, 0x11, 0xc71); + __phy_write(phydev, 0x12, 0xc); + __phy_write(phydev, 0x10, 0x8fae); + /* EnabRandUpdTrig = 1 */ __phy_write(phydev, 0x11, 0x2f00); __phy_write(phydev, 0x12, 0xe); @@ -715,15 +720,56 @@ static void mt798x_phy_common_finetune(struct phy_device *phydev) __phy_write(phydev, 0x12, 0x0); __phy_write(phydev, 0x10, 0x83aa); - /* TrFreeze = 0 */ + /* FfeUpdGainForce = 1(Enable), FfeUpdGainForceVal = 4 */ + __phy_write(phydev, 0x11, 0x240); + __phy_write(phydev, 0x12, 0x0); + __phy_write(phydev, 0x10, 0x9680); + + /* TrFreeze = 0 (mt7988 default) */ __phy_write(phydev, 0x11, 0x0); __phy_write(phydev, 0x12, 0x0); __phy_write(phydev, 0x10, 0x9686); + /* SSTrKp100 = 5 */ + /* SSTrKf100 = 6 */ + /* SSTrKp1000Mas = 5 */ + /* SSTrKf1000Mas = 6 */ /* SSTrKp1000Slv = 5 */ + /* SSTrKf1000Slv = 6 */ __phy_write(phydev, 0x11, 0xbaef); __phy_write(phydev, 0x12, 0x2e); __phy_write(phydev, 0x10, 0x968c); + phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0); +} + +static void mt7981_phy_finetune(struct phy_device *phydev) +{ + u16 val[8] = { 0x01ce, 0x01c1, + 0x020f, 0x0202, + 0x03d0, 0x03c0, + 0x0013, 0x0005 }; + int i, k; + + /* 100M eye finetune: + * Keep middle level of TX MLT3 shapper as default. + * Only change TX MLT3 overshoot level here. + */ + for (k = 0, i = 1; i < 12; i++) { + if (i % 3 == 0) + continue; + phy_write_mmd(phydev, MDIO_MMD_VEND1, i, val[k++]); + } + + phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5); + /* ResetSyncOffset = 6 */ + __phy_write(phydev, 0x11, 0x600); + __phy_write(phydev, 0x12, 0x0); + __phy_write(phydev, 0x10, 0x8fc0); + + /* VgaDecRate = 1 */ + __phy_write(phydev, 0x11, 0x4c2a); + __phy_write(phydev, 0x12, 0x3e); + __phy_write(phydev, 0x10, 0x8fa4); /* MrvlTrFix100Kp = 3, MrvlTrFix100Kf = 2, * MrvlTrFix1000Kp = 3, MrvlTrFix1000Kf = 2 @@ -738,7 +784,7 @@ static void mt798x_phy_common_finetune(struct phy_device *phydev) __phy_write(phydev, 0x10, 0x8ec0); phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0); - /* TR_OPEN_LOOP_EN = 1, lpf_x_average = 9*/ + /* TR_OPEN_LOOP_EN = 1, lpf_x_average = 9 */ phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_DEV1E_REG234, MTK_PHY_TR_OPEN_LOOP_EN_MASK | MTK_PHY_LPF_X_AVERAGE_MASK, BIT(0) | FIELD_PREP(MTK_PHY_LPF_X_AVERAGE_MASK, 0x9)); @@ -771,48 +817,6 @@ static void mt798x_phy_common_finetune(struct phy_device *phydev) phy_write_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_LDO_OUTPUT_V, 0x2222); } -static void mt7981_phy_finetune(struct phy_device *phydev) -{ - u16 val[8] = { 0x01ce, 0x01c1, - 0x020f, 0x0202, - 0x03d0, 0x03c0, - 0x0013, 0x0005 }; - int i, k; - - /* 100M eye finetune: - * Keep middle level of TX MLT3 shapper as default. - * Only change TX MLT3 overshoot level here. - */ - for (k = 0, i = 1; i < 12; i++) { - if (i % 3 == 0) - continue; - phy_write_mmd(phydev, MDIO_MMD_VEND1, i, val[k++]); - } - - phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5); - /* SlvDSPreadyTime = 24, MasDSPreadyTime = 24 */ - __phy_write(phydev, 0x11, 0xc71); - __phy_write(phydev, 0x12, 0xc); - __phy_write(phydev, 0x10, 0x8fae); - - /* ResetSyncOffset = 6 */ - __phy_write(phydev, 0x11, 0x600); - __phy_write(phydev, 0x12, 0x0); - __phy_write(phydev, 0x10, 0x8fc0); - - /* VgaDecRate = 1 */ - __phy_write(phydev, 0x11, 0x4c2a); - __phy_write(phydev, 0x12, 0x3e); - __phy_write(phydev, 0x10, 0x8fa4); - - /* FfeUpdGainForce = 4 */ - __phy_write(phydev, 0x11, 0x240); - __phy_write(phydev, 0x12, 0x0); - __phy_write(phydev, 0x10, 0x9680); - - phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0); -} - static void mt7988_phy_finetune(struct phy_device *phydev) { u16 val[12] = { 0x0187, 0x01cd, 0x01c8, 0x0182, @@ -827,17 +831,7 @@ static void mt7988_phy_finetune(struct phy_device *phydev) /* TCT finetune */ phy_write_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_TX_FILTER, 0x5); - /* Disable TX power saving */ - phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RXADC_CTRL_RG7, - MTK_PHY_DA_AD_BUF_BIAS_LP_MASK, 0x3 << 8); - phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5); - - /* SlvDSPreadyTime = 24, MasDSPreadyTime = 12 */ - __phy_write(phydev, 0x11, 0x671); - __phy_write(phydev, 0x12, 0xc); - __phy_write(phydev, 0x10, 0x8fae); - /* ResetSyncOffset = 5 */ __phy_write(phydev, 0x11, 0x500); __phy_write(phydev, 0x12, 0x0); @@ -845,13 +839,27 @@ static void mt7988_phy_finetune(struct phy_device *phydev) /* VgaDecRate is 1 at default on mt7988 */ - phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0); + /* MrvlTrFix100Kp = 6, MrvlTrFix100Kf = 7, + * MrvlTrFix1000Kp = 6, MrvlTrFix1000Kf = 7 + */ + __phy_write(phydev, 0x11, 0xb90a); + __phy_write(phydev, 0x12, 0x6f); + __phy_write(phydev, 0x10, 0x8f82); + + /* RemAckCntLimitCtrl = 1 */ + __phy_write(phydev, 0x11, 0xfbba); + __phy_write(phydev, 0x12, 0xc3); + __phy_write(phydev, 0x10, 0x87f8); - phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_2A30); - /* TxClkOffset = 2 */ - __phy_modify(phydev, MTK_PHY_ANARG_RG, MTK_PHY_TCLKOFFSET_MASK, - FIELD_PREP(MTK_PHY_TCLKOFFSET_MASK, 0x2)); phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0); + + /* TR_OPEN_LOOP_EN = 1, lpf_x_average = 10 */ + phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_DEV1E_REG234, + MTK_PHY_TR_OPEN_LOOP_EN_MASK | MTK_PHY_LPF_X_AVERAGE_MASK, + BIT(0) | FIELD_PREP(MTK_PHY_LPF_X_AVERAGE_MASK, 0xa)); + + /* rg_tr_lpf_cnt_val = 1023 */ + phy_write_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_LPF_CNT_VAL, 0x3ff); } static void mt798x_phy_eee(struct phy_device *phydev) @@ -884,11 +892,11 @@ static void mt798x_phy_eee(struct phy_device *phydev) MTK_PHY_LPI_SLV_SEND_TX_EN, FIELD_PREP(MTK_PHY_LPI_SLV_SEND_TX_TIMER_MASK, 0x120)); - phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_DEV1E_REG239, - MTK_PHY_LPI_SEND_LOC_TIMER_MASK | - MTK_PHY_LPI_TXPCS_LOC_RCV, - FIELD_PREP(MTK_PHY_LPI_SEND_LOC_TIMER_MASK, 0x117)); + /* Keep MTK_PHY_LPI_SEND_LOC_TIMER as 375 */ + phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_DEV1E_REG239, + MTK_PHY_LPI_TXPCS_LOC_RCV); + /* This also fixes some IoT issues, such as CH340 */ phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_DEV1E_REG2C7, MTK_PHY_MAX_GAIN_MASK | MTK_PHY_MIN_GAIN_MASK, FIELD_PREP(MTK_PHY_MAX_GAIN_MASK, 0x8) | @@ -922,7 +930,7 @@ static void mt798x_phy_eee(struct phy_device *phydev) __phy_write(phydev, 0x12, 0x0); __phy_write(phydev, 0x10, 0x9690); - /* REG_EEE_st2TrKf1000 = 3 */ + /* REG_EEE_st2TrKf1000 = 2 */ __phy_write(phydev, 0x11, 0x114f); __phy_write(phydev, 0x12, 0x2); __phy_write(phydev, 0x10, 0x969a); @@ -947,7 +955,7 @@ static void mt798x_phy_eee(struct phy_device *phydev) __phy_write(phydev, 0x12, 0x0); __phy_write(phydev, 0x10, 0x96b8); - /* REGEEE_wake_slv_tr_wait_dfesigdet_en = 1 */ + /* REGEEE_wake_slv_tr_wait_dfesigdet_en = 0 */ __phy_write(phydev, 0x11, 0x1463); __phy_write(phydev, 0x12, 0x0); __phy_write(phydev, 0x10, 0x96ca); @@ -1459,6 +1467,13 @@ static int mt7988_phy_probe(struct phy_device *phydev) if (err) return err; + /* Disable TX power saving at probing to: + * 1. Meet common mode compliance test criteria + * 2. Make sure that TX-VCM calibration works fine + */ + phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RXADC_CTRL_RG7, + MTK_PHY_DA_AD_BUF_BIAS_LP_MASK, 0x3 << 8); + return mt798x_phy_calibration(phydev); } diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 81c20eb4b54b..dad720138baa 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -120,6 +120,11 @@ */ #define LAN8814_1PPM_FORMAT 17179 +#define PTP_RX_VERSION 0x0248 +#define PTP_TX_VERSION 0x0288 +#define PTP_MAX_VERSION(x) (((x) & GENMASK(7, 0)) << 8) +#define PTP_MIN_VERSION(x) ((x) & GENMASK(7, 0)) + #define PTP_RX_MOD 0x024F #define PTP_RX_MOD_BAD_UDPV4_CHKSUM_FORCE_FCS_DIS_ BIT(3) #define PTP_RX_TIMESTAMP_EN 0x024D @@ -3150,6 +3155,12 @@ static void lan8814_ptp_init(struct phy_device *phydev) lanphy_write_page_reg(phydev, 5, PTP_TX_PARSE_IP_ADDR_EN, 0); lanphy_write_page_reg(phydev, 5, PTP_RX_PARSE_IP_ADDR_EN, 0); + /* Disable checking for minorVersionPTP field */ + lanphy_write_page_reg(phydev, 5, PTP_RX_VERSION, + PTP_MAX_VERSION(0xff) | PTP_MIN_VERSION(0x0)); + lanphy_write_page_reg(phydev, 5, PTP_TX_VERSION, + PTP_MAX_VERSION(0xff) | PTP_MIN_VERSION(0x0)); + skb_queue_head_init(&ptp_priv->tx_queue); skb_queue_head_init(&ptp_priv->rx_queue); INIT_LIST_HEAD(&ptp_priv->rx_ts_list); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index afa5497f7c35..4a4f8c8e79fa 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1630,13 +1630,19 @@ static int tun_xdp_act(struct tun_struct *tun, struct bpf_prog *xdp_prog, switch (act) { case XDP_REDIRECT: err = xdp_do_redirect(tun->dev, xdp, xdp_prog); - if (err) + if (err) { + dev_core_stats_rx_dropped_inc(tun->dev); return err; + } + dev_sw_netstats_rx_add(tun->dev, xdp->data_end - xdp->data); break; case XDP_TX: err = tun_xdp_tx(tun->dev, xdp); - if (err < 0) + if (err < 0) { + dev_core_stats_rx_dropped_inc(tun->dev); return err; + } + dev_sw_netstats_rx_add(tun->dev, xdp->data_end - xdp->data); break; case XDP_PASS: break; diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h index 7e3b6779f4e9..02e160d831be 100644 --- a/drivers/net/wireless/ath/ath11k/core.h +++ b/drivers/net/wireless/ath/ath11k/core.h @@ -368,10 +368,6 @@ struct ath11k_vif { struct ieee80211_chanctx_conf chanctx; struct ath11k_arp_ns_offload arp_ns_offload; struct ath11k_rekey_data rekey_data; - -#ifdef CONFIG_ATH11K_DEBUGFS - struct dentry *debugfs_twt; -#endif /* CONFIG_ATH11K_DEBUGFS */ }; struct ath11k_vif_iter { diff --git a/drivers/net/wireless/ath/ath11k/debugfs.c b/drivers/net/wireless/ath/ath11k/debugfs.c index a847bc0d50c0..a48e737ef35d 100644 --- a/drivers/net/wireless/ath/ath11k/debugfs.c +++ b/drivers/net/wireless/ath/ath11k/debugfs.c @@ -1894,35 +1894,30 @@ static const struct file_operations ath11k_fops_twt_resume_dialog = { .open = simple_open }; -void ath11k_debugfs_add_interface(struct ath11k_vif *arvif) +void ath11k_debugfs_op_vif_add(struct ieee80211_hw *hw, + struct ieee80211_vif *vif) { + struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif); struct ath11k_base *ab = arvif->ar->ab; + struct dentry *debugfs_twt; if (arvif->vif->type != NL80211_IFTYPE_AP && !(arvif->vif->type == NL80211_IFTYPE_STATION && test_bit(WMI_TLV_SERVICE_STA_TWT, ab->wmi_ab.svc_map))) return; - arvif->debugfs_twt = debugfs_create_dir("twt", - arvif->vif->debugfs_dir); - debugfs_create_file("add_dialog", 0200, arvif->debugfs_twt, + debugfs_twt = debugfs_create_dir("twt", + arvif->vif->debugfs_dir); + debugfs_create_file("add_dialog", 0200, debugfs_twt, arvif, &ath11k_fops_twt_add_dialog); - debugfs_create_file("del_dialog", 0200, arvif->debugfs_twt, + debugfs_create_file("del_dialog", 0200, debugfs_twt, arvif, &ath11k_fops_twt_del_dialog); - debugfs_create_file("pause_dialog", 0200, arvif->debugfs_twt, + debugfs_create_file("pause_dialog", 0200, debugfs_twt, arvif, &ath11k_fops_twt_pause_dialog); - debugfs_create_file("resume_dialog", 0200, arvif->debugfs_twt, + debugfs_create_file("resume_dialog", 0200, debugfs_twt, arvif, &ath11k_fops_twt_resume_dialog); } -void ath11k_debugfs_remove_interface(struct ath11k_vif *arvif) -{ - if (!arvif->debugfs_twt) - return; - - debugfs_remove_recursive(arvif->debugfs_twt); - arvif->debugfs_twt = NULL; -} diff --git a/drivers/net/wireless/ath/ath11k/debugfs.h b/drivers/net/wireless/ath/ath11k/debugfs.h index 44d15845f39a..a39e458637b0 100644 --- a/drivers/net/wireless/ath/ath11k/debugfs.h +++ b/drivers/net/wireless/ath/ath11k/debugfs.h @@ -307,8 +307,8 @@ static inline int ath11k_debugfs_rx_filter(struct ath11k *ar) return ar->debug.rx_filter; } -void ath11k_debugfs_add_interface(struct ath11k_vif *arvif); -void ath11k_debugfs_remove_interface(struct ath11k_vif *arvif); +void ath11k_debugfs_op_vif_add(struct ieee80211_hw *hw, + struct ieee80211_vif *vif); void ath11k_debugfs_add_dbring_entry(struct ath11k *ar, enum wmi_direct_buffer_module id, enum ath11k_dbg_dbr_event event, @@ -387,14 +387,6 @@ static inline int ath11k_debugfs_get_fw_stats(struct ath11k *ar, return 0; } -static inline void ath11k_debugfs_add_interface(struct ath11k_vif *arvif) -{ -} - -static inline void ath11k_debugfs_remove_interface(struct ath11k_vif *arvif) -{ -} - static inline void ath11k_debugfs_add_dbring_entry(struct ath11k *ar, enum wmi_direct_buffer_module id, diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c index db241589424d..b13525bbbb80 100644 --- a/drivers/net/wireless/ath/ath11k/mac.c +++ b/drivers/net/wireless/ath/ath11k/mac.c @@ -6756,13 +6756,6 @@ static int ath11k_mac_op_add_interface(struct ieee80211_hw *hw, goto err; } - /* In the case of hardware recovery, debugfs files are - * not deleted since ieee80211_ops.remove_interface() is - * not invoked. In such cases, try to delete the files. - * These will be re-created later. - */ - ath11k_debugfs_remove_interface(arvif); - memset(arvif, 0, sizeof(*arvif)); arvif->ar = ar; @@ -6939,8 +6932,6 @@ static int ath11k_mac_op_add_interface(struct ieee80211_hw *hw, ath11k_dp_vdev_tx_attach(ar, arvif); - ath11k_debugfs_add_interface(arvif); - if (vif->type != NL80211_IFTYPE_MONITOR && test_bit(ATH11K_FLAG_MONITOR_CONF_ENABLED, &ar->monitor_flags)) { ret = ath11k_mac_monitor_vdev_create(ar); @@ -7056,8 +7047,6 @@ err_vdev_del: /* Recalc txpower for remaining vdev */ ath11k_mac_txpower_recalc(ar); - ath11k_debugfs_remove_interface(arvif); - /* TODO: recal traffic pause state based on the available vdevs */ mutex_unlock(&ar->conf_mutex); @@ -9153,6 +9142,7 @@ static const struct ieee80211_ops ath11k_ops = { #endif #ifdef CONFIG_ATH11K_DEBUGFS + .vif_add_debugfs = ath11k_debugfs_op_vif_add, .sta_add_debugfs = ath11k_debugfs_sta_op_add, #endif diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c index 3b14f6476743..72075720969c 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2018-2023 Intel Corporation + * Copyright (C) 2018-2024 Intel Corporation */ #include <linux/firmware.h> #include "iwl-drv.h" @@ -1096,7 +1096,7 @@ static int iwl_dbg_tlv_override_trig_node(struct iwl_fw_runtime *fwrt, node_trig = (void *)node_tlv->data; } - memcpy(node_trig->data + offset, trig->data, trig_data_len); + memcpy((u8 *)node_trig->data + offset, trig->data, trig_data_len); node_tlv->length = cpu_to_le32(size); if (policy & IWL_FW_INI_APPLY_POLICY_OVERRIDE_CFG) { diff --git a/drivers/net/wireless/intersil/p54/fwio.c b/drivers/net/wireless/intersil/p54/fwio.c index b52cce38115d..c4fe70e05b9b 100644 --- a/drivers/net/wireless/intersil/p54/fwio.c +++ b/drivers/net/wireless/intersil/p54/fwio.c @@ -125,7 +125,7 @@ int p54_parse_firmware(struct ieee80211_hw *dev, const struct firmware *fw) "FW rev %s - Softmac protocol %x.%x\n", fw_version, priv->fw_var >> 8, priv->fw_var & 0xff); snprintf(dev->wiphy->fw_version, sizeof(dev->wiphy->fw_version), - "%s - %x.%x", fw_version, + "%.19s - %x.%x", fw_version, priv->fw_var >> 8, priv->fw_var & 0xff); } diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 88f760a7cbc3..fab361a250d6 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -104,13 +104,12 @@ bool provides_xdp_headroom = true; module_param(provides_xdp_headroom, bool, 0644); static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx, - u8 status); + s8 status); static void make_tx_response(struct xenvif_queue *queue, - struct xen_netif_tx_request *txp, + const struct xen_netif_tx_request *txp, unsigned int extra_count, - s8 st); -static void push_tx_responses(struct xenvif_queue *queue); + s8 status); static void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx); @@ -208,13 +207,9 @@ static void xenvif_tx_err(struct xenvif_queue *queue, unsigned int extra_count, RING_IDX end) { RING_IDX cons = queue->tx.req_cons; - unsigned long flags; do { - spin_lock_irqsave(&queue->response_lock, flags); make_tx_response(queue, txp, extra_count, XEN_NETIF_RSP_ERROR); - push_tx_responses(queue); - spin_unlock_irqrestore(&queue->response_lock, flags); if (cons == end) break; RING_COPY_REQUEST(&queue->tx, cons++, txp); @@ -463,12 +458,20 @@ static void xenvif_get_requests(struct xenvif_queue *queue, } for (shinfo->nr_frags = 0; nr_slots > 0 && shinfo->nr_frags < MAX_SKB_FRAGS; - shinfo->nr_frags++, gop++, nr_slots--) { + nr_slots--) { + if (unlikely(!txp->size)) { + make_tx_response(queue, txp, 0, XEN_NETIF_RSP_OKAY); + ++txp; + continue; + } + index = pending_index(queue->pending_cons++); pending_idx = queue->pending_ring[index]; xenvif_tx_create_map_op(queue, pending_idx, txp, txp == first ? extra_count : 0, gop); frag_set_pending_idx(&frags[shinfo->nr_frags], pending_idx); + ++shinfo->nr_frags; + ++gop; if (txp == first) txp = txfrags; @@ -481,20 +484,33 @@ static void xenvif_get_requests(struct xenvif_queue *queue, shinfo = skb_shinfo(nskb); frags = shinfo->frags; - for (shinfo->nr_frags = 0; shinfo->nr_frags < nr_slots; - shinfo->nr_frags++, txp++, gop++) { + for (shinfo->nr_frags = 0; shinfo->nr_frags < nr_slots; ++txp) { + if (unlikely(!txp->size)) { + make_tx_response(queue, txp, 0, + XEN_NETIF_RSP_OKAY); + continue; + } + index = pending_index(queue->pending_cons++); pending_idx = queue->pending_ring[index]; xenvif_tx_create_map_op(queue, pending_idx, txp, 0, gop); frag_set_pending_idx(&frags[shinfo->nr_frags], pending_idx); + ++shinfo->nr_frags; + ++gop; + } + + if (shinfo->nr_frags) { + skb_shinfo(skb)->frag_list = nskb; + nskb = NULL; } + } - skb_shinfo(skb)->frag_list = nskb; - } else if (nskb) { + if (nskb) { /* A frag_list skb was allocated but it is no longer needed - * because enough slots were converted to copy ops above. + * because enough slots were converted to copy ops above or some + * were empty. */ kfree_skb(nskb); } @@ -963,7 +979,6 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, (ret == 0) ? XEN_NETIF_RSP_OKAY : XEN_NETIF_RSP_ERROR); - push_tx_responses(queue); continue; } @@ -975,7 +990,6 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, make_tx_response(queue, &txreq, extra_count, XEN_NETIF_RSP_OKAY); - push_tx_responses(queue); continue; } @@ -1401,8 +1415,35 @@ int xenvif_tx_action(struct xenvif_queue *queue, int budget) return work_done; } +static void _make_tx_response(struct xenvif_queue *queue, + const struct xen_netif_tx_request *txp, + unsigned int extra_count, + s8 status) +{ + RING_IDX i = queue->tx.rsp_prod_pvt; + struct xen_netif_tx_response *resp; + + resp = RING_GET_RESPONSE(&queue->tx, i); + resp->id = txp->id; + resp->status = status; + + while (extra_count-- != 0) + RING_GET_RESPONSE(&queue->tx, ++i)->status = XEN_NETIF_RSP_NULL; + + queue->tx.rsp_prod_pvt = ++i; +} + +static void push_tx_responses(struct xenvif_queue *queue) +{ + int notify; + + RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->tx, notify); + if (notify) + notify_remote_via_irq(queue->tx_irq); +} + static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx, - u8 status) + s8 status) { struct pending_tx_info *pending_tx_info; pending_ring_idx_t index; @@ -1412,8 +1453,8 @@ static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx, spin_lock_irqsave(&queue->response_lock, flags); - make_tx_response(queue, &pending_tx_info->req, - pending_tx_info->extra_count, status); + _make_tx_response(queue, &pending_tx_info->req, + pending_tx_info->extra_count, status); /* Release the pending index before pusing the Tx response so * its available before a new Tx request is pushed by the @@ -1427,32 +1468,19 @@ static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx, spin_unlock_irqrestore(&queue->response_lock, flags); } - static void make_tx_response(struct xenvif_queue *queue, - struct xen_netif_tx_request *txp, + const struct xen_netif_tx_request *txp, unsigned int extra_count, - s8 st) + s8 status) { - RING_IDX i = queue->tx.rsp_prod_pvt; - struct xen_netif_tx_response *resp; - - resp = RING_GET_RESPONSE(&queue->tx, i); - resp->id = txp->id; - resp->status = st; - - while (extra_count-- != 0) - RING_GET_RESPONSE(&queue->tx, ++i)->status = XEN_NETIF_RSP_NULL; + unsigned long flags; - queue->tx.rsp_prod_pvt = ++i; -} + spin_lock_irqsave(&queue->response_lock, flags); -static void push_tx_responses(struct xenvif_queue *queue) -{ - int notify; + _make_tx_response(queue, txp, extra_count, status); + push_tx_responses(queue); - RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->tx, notify); - if (notify) - notify_remote_via_irq(queue->tx_irq); + spin_unlock_irqrestore(&queue->response_lock, flags); } static void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx) diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 63af6ab034b5..1183e7a871f8 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -631,8 +631,7 @@ static void fbcon_prepare_logo(struct vc_data *vc, struct fb_info *info, if (logo_lines > vc->vc_bottom) { logo_shown = FBCON_LOGO_CANSHOW; - printk(KERN_INFO - "fbcon_init: disable boot-logo (boot-logo bigger than screen).\n"); + pr_info("fbcon: disable boot-logo (boot-logo bigger than screen).\n"); } else { logo_shown = FBCON_LOGO_DRAW; vc->vc_top = logo_lines; diff --git a/drivers/video/fbdev/savage/savagefb_driver.c b/drivers/video/fbdev/savage/savagefb_driver.c index dddd6afcb972..ebc9aeffdde7 100644 --- a/drivers/video/fbdev/savage/savagefb_driver.c +++ b/drivers/video/fbdev/savage/savagefb_driver.c @@ -869,6 +869,9 @@ static int savagefb_check_var(struct fb_var_screeninfo *var, DBG("savagefb_check_var"); + if (!var->pixclock) + return -EINVAL; + var->transp.offset = 0; var->transp.length = 0; switch (var->bits_per_pixel) { diff --git a/drivers/video/fbdev/sis/sis_main.c b/drivers/video/fbdev/sis/sis_main.c index 803ccb6aa479..009bf1d92644 100644 --- a/drivers/video/fbdev/sis/sis_main.c +++ b/drivers/video/fbdev/sis/sis_main.c @@ -1444,6 +1444,8 @@ sisfb_check_var(struct fb_var_screeninfo *var, struct fb_info *info) vtotal = var->upper_margin + var->lower_margin + var->vsync_len; + if (!var->pixclock) + return -EINVAL; pixclock = var->pixclock; if((var->vmode & FB_VMODE_MASK) == FB_VMODE_NONINTERLACED) { diff --git a/drivers/video/fbdev/stifb.c b/drivers/video/fbdev/stifb.c index 2de0e675fd15..8e5bac27542d 100644 --- a/drivers/video/fbdev/stifb.c +++ b/drivers/video/fbdev/stifb.c @@ -1158,7 +1158,7 @@ stifb_init_display(struct stifb_info *fb) } break; } - stifb_blank(0, (struct fb_info *)fb); /* 0=enable screen */ + stifb_blank(0, fb->info); /* 0=enable screen */ SETUP_FB(fb); } diff --git a/drivers/video/fbdev/vt8500lcdfb.c b/drivers/video/fbdev/vt8500lcdfb.c index 42c25dc85197..ac73937073a7 100644 --- a/drivers/video/fbdev/vt8500lcdfb.c +++ b/drivers/video/fbdev/vt8500lcdfb.c @@ -374,7 +374,6 @@ static int vt8500lcd_probe(struct platform_device *pdev) irq = platform_get_irq(pdev, 0); if (irq < 0) { - dev_err(&pdev->dev, "no IRQ defined\n"); ret = -ENODEV; goto failed_free_palette; } diff --git a/fs/afs/dir.c b/fs/afs/dir.c index c14533ef108f..b5b8de521f99 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -124,7 +124,7 @@ static void afs_dir_read_cleanup(struct afs_read *req) if (xas_retry(&xas, folio)) continue; BUG_ON(xa_is_value(folio)); - ASSERTCMP(folio_file_mapping(folio), ==, mapping); + ASSERTCMP(folio->mapping, ==, mapping); folio_put(folio); } @@ -202,12 +202,12 @@ static void afs_dir_dump(struct afs_vnode *dvnode, struct afs_read *req) if (xas_retry(&xas, folio)) continue; - BUG_ON(folio_file_mapping(folio) != mapping); + BUG_ON(folio->mapping != mapping); size = min_t(loff_t, folio_size(folio), req->actual_len - folio_pos(folio)); for (offset = 0; offset < size; offset += sizeof(*block)) { block = kmap_local_folio(folio, offset); - pr_warn("[%02lx] %32phN\n", folio_index(folio) + offset, block); + pr_warn("[%02lx] %32phN\n", folio->index + offset, block); kunmap_local(block); } } @@ -233,7 +233,7 @@ static int afs_dir_check(struct afs_vnode *dvnode, struct afs_read *req) if (xas_retry(&xas, folio)) continue; - BUG_ON(folio_file_mapping(folio) != mapping); + BUG_ON(folio->mapping != mapping); if (!afs_dir_check_folio(dvnode, folio, req->actual_len)) { afs_dir_dump(dvnode, req); @@ -474,6 +474,14 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode, continue; } + /* Don't expose silly rename entries to userspace. */ + if (nlen > 6 && + dire->u.name[0] == '.' && + ctx->actor != afs_lookup_filldir && + ctx->actor != afs_lookup_one_filldir && + memcmp(dire->u.name, ".__afs", 6) == 0) + continue; + /* found the next entry */ if (!dir_emit(ctx, dire->u.name, nlen, ntohl(dire->u.vnode), @@ -708,6 +716,8 @@ static void afs_do_lookup_success(struct afs_operation *op) break; } + if (vp->scb.status.abort_code) + trace_afs_bulkstat_error(op, &vp->fid, i, vp->scb.status.abort_code); if (!vp->scb.have_status && !vp->scb.have_error) continue; @@ -897,12 +907,16 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry, afs_begin_vnode_operation(op); afs_wait_for_operation(op); } - inode = ERR_PTR(afs_op_error(op)); out_op: if (!afs_op_error(op)) { - inode = &op->file[1].vnode->netfs.inode; - op->file[1].vnode = NULL; + if (op->file[1].scb.status.abort_code) { + afs_op_accumulate_error(op, -ECONNABORTED, + op->file[1].scb.status.abort_code); + } else { + inode = &op->file[1].vnode->netfs.inode; + op->file[1].vnode = NULL; + } } if (op->file[0].scb.have_status) @@ -2022,7 +2036,7 @@ static bool afs_dir_release_folio(struct folio *folio, gfp_t gfp_flags) { struct afs_vnode *dvnode = AFS_FS_I(folio_inode(folio)); - _enter("{{%llx:%llu}[%lu]}", dvnode->fid.vid, dvnode->fid.vnode, folio_index(folio)); + _enter("{{%llx:%llu}[%lu]}", dvnode->fid.vid, dvnode->fid.vnode, folio->index); folio_detach_private(folio); diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c index d3bc4a2d7085..c4d2711e20ad 100644 --- a/fs/afs/dynroot.c +++ b/fs/afs/dynroot.c @@ -258,16 +258,7 @@ const struct inode_operations afs_dynroot_inode_operations = { .lookup = afs_dynroot_lookup, }; -/* - * Dirs in the dynamic root don't need revalidation. - */ -static int afs_dynroot_d_revalidate(struct dentry *dentry, unsigned int flags) -{ - return 1; -} - const struct dentry_operations afs_dynroot_dentry_operations = { - .d_revalidate = afs_dynroot_d_revalidate, .d_delete = always_delete_dentry, .d_release = afs_d_release, .d_automount = afs_d_automount, diff --git a/fs/afs/proc.c b/fs/afs/proc.c index 3bd02571f30d..15eab053af6d 100644 --- a/fs/afs/proc.c +++ b/fs/afs/proc.c @@ -166,7 +166,7 @@ static int afs_proc_addr_prefs_show(struct seq_file *m, void *v) if (!preflist) { seq_puts(m, "NO PREFS\n"); - return 0; + goto out; } seq_printf(m, "PROT SUBNET PRIOR (v=%u n=%u/%u/%u)\n", @@ -191,7 +191,8 @@ static int afs_proc_addr_prefs_show(struct seq_file *m, void *v) } } - rcu_read_lock(); +out: + rcu_read_unlock(); return 0; } diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index 193168214eeb..68345f73d429 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -141,16 +141,16 @@ static int compression_decompress_bio(struct list_head *ws, } static int compression_decompress(int type, struct list_head *ws, - const u8 *data_in, struct page *dest_page, - unsigned long start_byte, size_t srclen, size_t destlen) + const u8 *data_in, struct page *dest_page, + unsigned long dest_pgoff, size_t srclen, size_t destlen) { switch (type) { case BTRFS_COMPRESS_ZLIB: return zlib_decompress(ws, data_in, dest_page, - start_byte, srclen, destlen); + dest_pgoff, srclen, destlen); case BTRFS_COMPRESS_LZO: return lzo_decompress(ws, data_in, dest_page, - start_byte, srclen, destlen); + dest_pgoff, srclen, destlen); case BTRFS_COMPRESS_ZSTD: return zstd_decompress(ws, data_in, dest_page, - start_byte, srclen, destlen); + dest_pgoff, srclen, destlen); case BTRFS_COMPRESS_NONE: default: /* @@ -1037,14 +1037,23 @@ static int btrfs_decompress_bio(struct compressed_bio *cb) * start_byte tells us the offset into the compressed data we're interested in */ int btrfs_decompress(int type, const u8 *data_in, struct page *dest_page, - unsigned long start_byte, size_t srclen, size_t destlen) + unsigned long dest_pgoff, size_t srclen, size_t destlen) { + struct btrfs_fs_info *fs_info = btrfs_sb(dest_page->mapping->host->i_sb); struct list_head *workspace; + const u32 sectorsize = fs_info->sectorsize; int ret; + /* + * The full destination page range should not exceed the page size. + * And the @destlen should not exceed sectorsize, as this is only called for + * inline file extents, which should not exceed sectorsize. + */ + ASSERT(dest_pgoff + destlen <= PAGE_SIZE && destlen <= sectorsize); + workspace = get_workspace(type, 0); ret = compression_decompress(type, workspace, data_in, dest_page, - start_byte, srclen, destlen); + dest_pgoff, srclen, destlen); put_workspace(type, workspace); return ret; diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h index 93cc92974dee..afd7e50d073d 100644 --- a/fs/btrfs/compression.h +++ b/fs/btrfs/compression.h @@ -148,7 +148,7 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping, unsigned long *total_in, unsigned long *total_out); int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb); int zlib_decompress(struct list_head *ws, const u8 *data_in, - struct page *dest_page, unsigned long start_byte, size_t srclen, + struct page *dest_page, unsigned long dest_pgoff, size_t srclen, size_t destlen); struct list_head *zlib_alloc_workspace(unsigned int level); void zlib_free_workspace(struct list_head *ws); @@ -159,7 +159,7 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping, unsigned long *total_in, unsigned long *total_out); int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb); int lzo_decompress(struct list_head *ws, const u8 *data_in, - struct page *dest_page, unsigned long start_byte, size_t srclen, + struct page *dest_page, unsigned long dest_pgoff, size_t srclen, size_t destlen); struct list_head *lzo_alloc_workspace(unsigned int level); void lzo_free_workspace(struct list_head *ws); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index f396aba92c57..8e8cc1111277 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1260,7 +1260,8 @@ static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len, u64 bytes_left, end; u64 aligned_start = ALIGN(start, 1 << SECTOR_SHIFT); - if (WARN_ON(start != aligned_start)) { + /* Adjust the range to be aligned to 512B sectors if necessary. */ + if (start != aligned_start) { len -= aligned_start - start; len = round_down(len, 1 << SECTOR_SHIFT); start = aligned_start; @@ -4298,6 +4299,42 @@ static int prepare_allocation_clustered(struct btrfs_fs_info *fs_info, return 0; } +static int prepare_allocation_zoned(struct btrfs_fs_info *fs_info, + struct find_free_extent_ctl *ffe_ctl) +{ + if (ffe_ctl->for_treelog) { + spin_lock(&fs_info->treelog_bg_lock); + if (fs_info->treelog_bg) + ffe_ctl->hint_byte = fs_info->treelog_bg; + spin_unlock(&fs_info->treelog_bg_lock); + } else if (ffe_ctl->for_data_reloc) { + spin_lock(&fs_info->relocation_bg_lock); + if (fs_info->data_reloc_bg) + ffe_ctl->hint_byte = fs_info->data_reloc_bg; + spin_unlock(&fs_info->relocation_bg_lock); + } else if (ffe_ctl->flags & BTRFS_BLOCK_GROUP_DATA) { + struct btrfs_block_group *block_group; + + spin_lock(&fs_info->zone_active_bgs_lock); + list_for_each_entry(block_group, &fs_info->zone_active_bgs, active_bg_list) { + /* + * No lock is OK here because avail is monotinically + * decreasing, and this is just a hint. + */ + u64 avail = block_group->zone_capacity - block_group->alloc_offset; + + if (block_group_bits(block_group, ffe_ctl->flags) && + avail >= ffe_ctl->num_bytes) { + ffe_ctl->hint_byte = block_group->start; + break; + } + } + spin_unlock(&fs_info->zone_active_bgs_lock); + } + + return 0; +} + static int prepare_allocation(struct btrfs_fs_info *fs_info, struct find_free_extent_ctl *ffe_ctl, struct btrfs_space_info *space_info, @@ -4308,19 +4345,7 @@ static int prepare_allocation(struct btrfs_fs_info *fs_info, return prepare_allocation_clustered(fs_info, ffe_ctl, space_info, ins); case BTRFS_EXTENT_ALLOC_ZONED: - if (ffe_ctl->for_treelog) { - spin_lock(&fs_info->treelog_bg_lock); - if (fs_info->treelog_bg) - ffe_ctl->hint_byte = fs_info->treelog_bg; - spin_unlock(&fs_info->treelog_bg_lock); - } - if (ffe_ctl->for_data_reloc) { - spin_lock(&fs_info->relocation_bg_lock); - if (fs_info->data_reloc_bg) - ffe_ctl->hint_byte = fs_info->data_reloc_bg; - spin_unlock(&fs_info->relocation_bg_lock); - } - return 0; + return prepare_allocation_zoned(fs_info, ffe_ctl); default: BUG(); } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 809b11472a80..1eb93d3962aa 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4458,6 +4458,8 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry) u64 root_flags; int ret; + down_write(&fs_info->subvol_sem); + /* * Don't allow to delete a subvolume with send in progress. This is * inside the inode lock so the error handling that has to drop the bit @@ -4469,25 +4471,25 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry) btrfs_warn(fs_info, "attempt to delete subvolume %llu during send", dest->root_key.objectid); - return -EPERM; + ret = -EPERM; + goto out_up_write; } if (atomic_read(&dest->nr_swapfiles)) { spin_unlock(&dest->root_item_lock); btrfs_warn(fs_info, "attempt to delete subvolume %llu with active swapfile", root->root_key.objectid); - return -EPERM; + ret = -EPERM; + goto out_up_write; } root_flags = btrfs_root_flags(&dest->root_item); btrfs_set_root_flags(&dest->root_item, root_flags | BTRFS_ROOT_SUBVOL_DEAD); spin_unlock(&dest->root_item_lock); - down_write(&fs_info->subvol_sem); - ret = may_destroy_subvol(dest); if (ret) - goto out_up_write; + goto out_undead; btrfs_init_block_rsv(&block_rsv, BTRFS_BLOCK_RSV_TEMP); /* @@ -4497,7 +4499,7 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry) */ ret = btrfs_subvolume_reserve_metadata(root, &block_rsv, 5, true); if (ret) - goto out_up_write; + goto out_undead; trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { @@ -4563,15 +4565,17 @@ out_end_trans: inode->i_flags |= S_DEAD; out_release: btrfs_subvolume_release_metadata(root, &block_rsv); -out_up_write: - up_write(&fs_info->subvol_sem); +out_undead: if (ret) { spin_lock(&dest->root_item_lock); root_flags = btrfs_root_flags(&dest->root_item); btrfs_set_root_flags(&dest->root_item, root_flags & ~BTRFS_ROOT_SUBVOL_DEAD); spin_unlock(&dest->root_item_lock); - } else { + } +out_up_write: + up_write(&fs_info->subvol_sem); + if (!ret) { d_invalidate(dentry); btrfs_prune_dentries(dest); ASSERT(dest->send_in_progress == 0); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 41b479861b3c..dfed9dd9c2d7 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -790,6 +790,9 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, return -EOPNOTSUPP; } + if (btrfs_root_refs(&root->root_item) == 0) + return -ENOENT; + if (!test_bit(BTRFS_ROOT_SHAREABLE, &root->state)) return -EINVAL; @@ -2608,6 +2611,10 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp) ret = -EFAULT; goto out; } + if (range.flags & ~BTRFS_DEFRAG_RANGE_FLAGS_SUPP) { + ret = -EOPNOTSUPP; + goto out; + } /* compression requires us to start the IO */ if ((range.flags & BTRFS_DEFRAG_RANGE_COMPRESS)) { range.flags |= BTRFS_DEFRAG_RANGE_START_IO; diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c index 1131d5a29d61..e43bc0fdc74e 100644 --- a/fs/btrfs/lzo.c +++ b/fs/btrfs/lzo.c @@ -425,16 +425,16 @@ int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb) } int lzo_decompress(struct list_head *ws, const u8 *data_in, - struct page *dest_page, unsigned long start_byte, size_t srclen, + struct page *dest_page, unsigned long dest_pgoff, size_t srclen, size_t destlen) { struct workspace *workspace = list_entry(ws, struct workspace, list); + struct btrfs_fs_info *fs_info = btrfs_sb(dest_page->mapping->host->i_sb); + const u32 sectorsize = fs_info->sectorsize; size_t in_len; size_t out_len; size_t max_segment_len = WORKSPACE_BUF_LENGTH; int ret = 0; - char *kaddr; - unsigned long bytes; if (srclen < LZO_LEN || srclen > max_segment_len + LZO_LEN * 2) return -EUCLEAN; @@ -451,7 +451,7 @@ int lzo_decompress(struct list_head *ws, const u8 *data_in, } data_in += LZO_LEN; - out_len = PAGE_SIZE; + out_len = sectorsize; ret = lzo1x_decompress_safe(data_in, in_len, workspace->buf, &out_len); if (ret != LZO_E_OK) { pr_warn("BTRFS: decompress failed!\n"); @@ -459,29 +459,13 @@ int lzo_decompress(struct list_head *ws, const u8 *data_in, goto out; } - if (out_len < start_byte) { + ASSERT(out_len <= sectorsize); + memcpy_to_page(dest_page, dest_pgoff, workspace->buf, out_len); + /* Early end, considered as an error. */ + if (unlikely(out_len < destlen)) { ret = -EIO; - goto out; + memzero_page(dest_page, dest_pgoff + out_len, destlen - out_len); } - - /* - * the caller is already checking against PAGE_SIZE, but lets - * move this check closer to the memcpy/memset - */ - destlen = min_t(unsigned long, destlen, PAGE_SIZE); - bytes = min_t(unsigned long, destlen, out_len - start_byte); - - kaddr = kmap_local_page(dest_page); - memcpy(kaddr, workspace->buf + start_byte, bytes); - - /* - * btrfs_getblock is doing a zero on the tail of the page too, - * but this will cover anything missing from the decompressed - * data. - */ - if (bytes < destlen) - memset(kaddr+bytes, 0, destlen-bytes); - kunmap_local(kaddr); out: return ret; } diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c index 6486f0d7e993..8c4fc98ca9ce 100644 --- a/fs/btrfs/ref-verify.c +++ b/fs/btrfs/ref-verify.c @@ -889,8 +889,10 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info, out_unlock: spin_unlock(&fs_info->ref_verify_lock); out: - if (ret) + if (ret) { + btrfs_free_ref_cache(fs_info); btrfs_clear_opt(fs_info->mount_opt, REF_VERIFY); + } return ret; } @@ -1021,8 +1023,8 @@ int btrfs_build_ref_tree(struct btrfs_fs_info *fs_info) } } if (ret) { - btrfs_clear_opt(fs_info->mount_opt, REF_VERIFY); btrfs_free_ref_cache(fs_info); + btrfs_clear_opt(fs_info->mount_opt, REF_VERIFY); } btrfs_free_path(path); return ret; diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index a01807cbd4d4..0123d2728923 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -1098,12 +1098,22 @@ out: static void scrub_read_endio(struct btrfs_bio *bbio) { struct scrub_stripe *stripe = bbio->private; + struct bio_vec *bvec; + int sector_nr = calc_sector_number(stripe, bio_first_bvec_all(&bbio->bio)); + int num_sectors; + u32 bio_size = 0; + int i; + + ASSERT(sector_nr < stripe->nr_sectors); + bio_for_each_bvec_all(bvec, &bbio->bio, i) + bio_size += bvec->bv_len; + num_sectors = bio_size >> stripe->bg->fs_info->sectorsize_bits; if (bbio->bio.bi_status) { - bitmap_set(&stripe->io_error_bitmap, 0, stripe->nr_sectors); - bitmap_set(&stripe->error_bitmap, 0, stripe->nr_sectors); + bitmap_set(&stripe->io_error_bitmap, sector_nr, num_sectors); + bitmap_set(&stripe->error_bitmap, sector_nr, num_sectors); } else { - bitmap_clear(&stripe->io_error_bitmap, 0, stripe->nr_sectors); + bitmap_clear(&stripe->io_error_bitmap, sector_nr, num_sectors); } bio_put(&bbio->bio); if (atomic_dec_and_test(&stripe->pending_io)) { @@ -1636,6 +1646,9 @@ static void scrub_submit_extent_sector_read(struct scrub_ctx *sctx, { struct btrfs_fs_info *fs_info = stripe->bg->fs_info; struct btrfs_bio *bbio = NULL; + unsigned int nr_sectors = min(BTRFS_STRIPE_LEN, stripe->bg->start + + stripe->bg->length - stripe->logical) >> + fs_info->sectorsize_bits; u64 stripe_len = BTRFS_STRIPE_LEN; int mirror = stripe->mirror_num; int i; @@ -1646,6 +1659,10 @@ static void scrub_submit_extent_sector_read(struct scrub_ctx *sctx, struct page *page = scrub_stripe_get_page(stripe, i); unsigned int pgoff = scrub_stripe_get_page_offset(stripe, i); + /* We're beyond the chunk boundary, no need to read anymore. */ + if (i >= nr_sectors) + break; + /* The current sector cannot be merged, submit the bio. */ if (bbio && ((i > 0 && @@ -1701,6 +1718,9 @@ static void scrub_submit_initial_read(struct scrub_ctx *sctx, { struct btrfs_fs_info *fs_info = sctx->fs_info; struct btrfs_bio *bbio; + unsigned int nr_sectors = min(BTRFS_STRIPE_LEN, stripe->bg->start + + stripe->bg->length - stripe->logical) >> + fs_info->sectorsize_bits; int mirror = stripe->mirror_num; ASSERT(stripe->bg); @@ -1715,14 +1735,16 @@ static void scrub_submit_initial_read(struct scrub_ctx *sctx, bbio = btrfs_bio_alloc(SCRUB_STRIPE_PAGES, REQ_OP_READ, fs_info, scrub_read_endio, stripe); - /* Read the whole stripe. */ bbio->bio.bi_iter.bi_sector = stripe->logical >> SECTOR_SHIFT; - for (int i = 0; i < BTRFS_STRIPE_LEN >> PAGE_SHIFT; i++) { + /* Read the whole range inside the chunk boundary. */ + for (unsigned int cur = 0; cur < nr_sectors; cur++) { + struct page *page = scrub_stripe_get_page(stripe, cur); + unsigned int pgoff = scrub_stripe_get_page_offset(stripe, cur); int ret; - ret = bio_add_page(&bbio->bio, stripe->pages[i], PAGE_SIZE, 0); + ret = bio_add_page(&bbio->bio, page, fs_info->sectorsize, pgoff); /* We should have allocated enough bio vectors. */ - ASSERT(ret == PAGE_SIZE); + ASSERT(ret == fs_info->sectorsize); } atomic_inc(&stripe->pending_io); diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 4e36550618e5..2d7519a6ce72 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -8205,8 +8205,8 @@ long btrfs_ioctl_send(struct inode *inode, struct btrfs_ioctl_send_args *arg) goto out; } - sctx->clone_roots = kvcalloc(sizeof(*sctx->clone_roots), - arg->clone_sources_count + 1, + sctx->clone_roots = kvcalloc(arg->clone_sources_count + 1, + sizeof(*sctx->clone_roots), GFP_KERNEL); if (!sctx->clone_roots) { ret = -ENOMEM; diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c index 93511d54abf8..0e49dab8dad2 100644 --- a/fs/btrfs/subpage.c +++ b/fs/btrfs/subpage.c @@ -475,7 +475,8 @@ void btrfs_subpage_set_writeback(const struct btrfs_fs_info *fs_info, spin_lock_irqsave(&subpage->lock, flags); bitmap_set(subpage->bitmaps, start_bit, len >> fs_info->sectorsize_bits); - folio_start_writeback(folio); + if (!folio_test_writeback(folio)) + folio_start_writeback(folio); spin_unlock_irqrestore(&subpage->lock, flags); } diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 896acfda1789..101f786963d4 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1457,6 +1457,14 @@ static int btrfs_reconfigure(struct fs_context *fc) btrfs_info_to_ctx(fs_info, &old_ctx); + /* + * This is our "bind mount" trick, we don't want to allow the user to do + * anything other than mount a different ro/rw and a different subvol, + * all of the mount options should be maintained. + */ + if (mount_reconfigure) + ctx->mount_opt = old_ctx.mount_opt; + sync_filesystem(sb); set_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state); diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 50fdc69fdddf..6eccf8496486 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1436,7 +1436,7 @@ static int check_extent_item(struct extent_buffer *leaf, if (unlikely(ptr + btrfs_extent_inline_ref_size(inline_type) > end)) { extent_err(leaf, slot, "inline ref item overflows extent item, ptr %lu iref size %u end %lu", - ptr, inline_type, end); + ptr, btrfs_extent_inline_ref_size(inline_type), end); return -EUCLEAN; } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 4c32497311d2..d67785be2c77 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -3087,7 +3087,6 @@ struct btrfs_chunk_map *btrfs_get_chunk_map(struct btrfs_fs_info *fs_info, map = btrfs_find_chunk_map(fs_info, logical, length); if (unlikely(!map)) { - read_unlock(&fs_info->mapping_tree_lock); btrfs_crit(fs_info, "unable to find chunk map for logical %llu length %llu", logical, length); @@ -3095,7 +3094,6 @@ struct btrfs_chunk_map *btrfs_get_chunk_map(struct btrfs_fs_info *fs_info, } if (unlikely(map->start > logical || map->start + map->chunk_len <= logical)) { - read_unlock(&fs_info->mapping_tree_lock); btrfs_crit(fs_info, "found a bad chunk map, wanted %llu-%llu, found %llu-%llu", logical, logical + length, map->start, diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c index 36cf1f0e338e..8da66ea699e8 100644 --- a/fs/btrfs/zlib.c +++ b/fs/btrfs/zlib.c @@ -354,18 +354,13 @@ done: } int zlib_decompress(struct list_head *ws, const u8 *data_in, - struct page *dest_page, unsigned long start_byte, size_t srclen, + struct page *dest_page, unsigned long dest_pgoff, size_t srclen, size_t destlen) { struct workspace *workspace = list_entry(ws, struct workspace, list); int ret = 0; int wbits = MAX_WBITS; - unsigned long bytes_left; - unsigned long total_out = 0; - unsigned long pg_offset = 0; - - destlen = min_t(unsigned long, destlen, PAGE_SIZE); - bytes_left = destlen; + unsigned long to_copy; workspace->strm.next_in = data_in; workspace->strm.avail_in = srclen; @@ -390,60 +385,30 @@ int zlib_decompress(struct list_head *ws, const u8 *data_in, return -EIO; } - while (bytes_left > 0) { - unsigned long buf_start; - unsigned long buf_offset; - unsigned long bytes; - - ret = zlib_inflate(&workspace->strm, Z_NO_FLUSH); - if (ret != Z_OK && ret != Z_STREAM_END) - break; - - buf_start = total_out; - total_out = workspace->strm.total_out; - - if (total_out == buf_start) { - ret = -EIO; - break; - } - - if (total_out <= start_byte) - goto next; - - if (total_out > start_byte && buf_start < start_byte) - buf_offset = start_byte - buf_start; - else - buf_offset = 0; - - bytes = min(PAGE_SIZE - pg_offset, - PAGE_SIZE - (buf_offset % PAGE_SIZE)); - bytes = min(bytes, bytes_left); + /* + * Everything (in/out buf) should be at most one sector, there should + * be no need to switch any input/output buffer. + */ + ret = zlib_inflate(&workspace->strm, Z_FINISH); + to_copy = min(workspace->strm.total_out, destlen); + if (ret != Z_STREAM_END) + goto out; - memcpy_to_page(dest_page, pg_offset, - workspace->buf + buf_offset, bytes); + memcpy_to_page(dest_page, dest_pgoff, workspace->buf, to_copy); - pg_offset += bytes; - bytes_left -= bytes; -next: - workspace->strm.next_out = workspace->buf; - workspace->strm.avail_out = workspace->buf_size; - } - - if (ret != Z_STREAM_END && bytes_left != 0) +out: + if (unlikely(to_copy != destlen)) { + pr_warn_ratelimited("BTRFS: infalte failed, decompressed=%lu expected=%zu\n", + to_copy, destlen); ret = -EIO; - else + } else { ret = 0; + } zlib_inflateEnd(&workspace->strm); - /* - * this should only happen if zlib returned fewer bytes than we - * expected. btrfs_get_block is responsible for zeroing from the - * end of the inline extent (destlen) to the end of the page - */ - if (pg_offset < destlen) { - memzero_page(dest_page, pg_offset, destlen - pg_offset); - } + if (unlikely(to_copy < destlen)) + memzero_page(dest_page, dest_pgoff + to_copy, destlen - to_copy); return ret; } diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 5bd76813b23f..168af9d000d1 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -2055,6 +2055,7 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group) map = block_group->physical_map; + spin_lock(&fs_info->zone_active_bgs_lock); spin_lock(&block_group->lock); if (test_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &block_group->runtime_flags)) { ret = true; @@ -2067,7 +2068,6 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group) goto out_unlock; } - spin_lock(&fs_info->zone_active_bgs_lock); for (i = 0; i < map->num_stripes; i++) { struct btrfs_zoned_device_info *zinfo; int reserved = 0; @@ -2087,20 +2087,17 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group) */ if (atomic_read(&zinfo->active_zones_left) <= reserved) { ret = false; - spin_unlock(&fs_info->zone_active_bgs_lock); goto out_unlock; } if (!btrfs_dev_set_active_zone(device, physical)) { /* Cannot activate the zone */ ret = false; - spin_unlock(&fs_info->zone_active_bgs_lock); goto out_unlock; } if (!is_data) zinfo->reserved_active_zones--; } - spin_unlock(&fs_info->zone_active_bgs_lock); /* Successfully activated all the zones */ set_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &block_group->runtime_flags); @@ -2108,8 +2105,6 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group) /* For the active block group list */ btrfs_get_block_group(block_group); - - spin_lock(&fs_info->zone_active_bgs_lock); list_add_tail(&block_group->active_bg_list, &fs_info->zone_active_bgs); spin_unlock(&fs_info->zone_active_bgs_lock); @@ -2117,6 +2112,7 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group) out_unlock: spin_unlock(&block_group->lock); + spin_unlock(&fs_info->zone_active_bgs_lock); return ret; } diff --git a/fs/cachefiles/ondemand.c b/fs/cachefiles/ondemand.c index 5fd74ec60bef..4ba42f1fa3b4 100644 --- a/fs/cachefiles/ondemand.c +++ b/fs/cachefiles/ondemand.c @@ -539,6 +539,9 @@ int cachefiles_ondemand_init_object(struct cachefiles_object *object) struct fscache_volume *volume = object->volume->vcookie; size_t volume_key_size, cookie_key_size, data_len; + if (!object->ondemand) + return 0; + /* * CacheFiles will firstly check the cache file under the root cache * directory. If the coherency check failed, it will fallback to diff --git a/fs/exec.c b/fs/exec.c index 8cdd5b2dd09c..af4fbb61cd53 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -128,7 +128,7 @@ SYSCALL_DEFINE1(uselib, const char __user *, library) struct filename *tmp = getname(library); int error = PTR_ERR(tmp); static const struct open_flags uselib_flags = { - .open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC, + .open_flag = O_LARGEFILE | O_RDONLY, .acc_mode = MAY_READ | MAY_EXEC, .intent = LOOKUP_OPEN, .lookup_flags = LOOKUP_FOLLOW, @@ -904,6 +904,10 @@ EXPORT_SYMBOL(transfer_args_to_stack); #endif /* CONFIG_MMU */ +/* + * On success, caller must call do_close_execat() on the returned + * struct file to close it. + */ static struct file *do_open_execat(int fd, struct filename *name, int flags) { struct file *file; @@ -948,6 +952,17 @@ exit: return ERR_PTR(err); } +/** + * open_exec - Open a path name for execution + * + * @name: path name to open with the intent of executing it. + * + * Returns ERR_PTR on failure or allocated struct file on success. + * + * As this is a wrapper for the internal do_open_execat(), callers + * must call allow_write_access() before fput() on release. Also see + * do_close_execat(). + */ struct file *open_exec(const char *name) { struct filename *filename = getname_kernel(name); @@ -1409,6 +1424,9 @@ int begin_new_exec(struct linux_binprm * bprm) out_unlock: up_write(&me->signal->exec_update_lock); + if (!bprm->cred) + mutex_unlock(&me->signal->cred_guard_mutex); + out: return retval; } @@ -1484,6 +1502,15 @@ static int prepare_bprm_creds(struct linux_binprm *bprm) return -ENOMEM; } +/* Matches do_open_execat() */ +static void do_close_execat(struct file *file) +{ + if (!file) + return; + allow_write_access(file); + fput(file); +} + static void free_bprm(struct linux_binprm *bprm) { if (bprm->mm) { @@ -1495,10 +1522,7 @@ static void free_bprm(struct linux_binprm *bprm) mutex_unlock(¤t->signal->cred_guard_mutex); abort_creds(bprm->cred); } - if (bprm->file) { - allow_write_access(bprm->file); - fput(bprm->file); - } + do_close_execat(bprm->file); if (bprm->executable) fput(bprm->executable); /* If a binfmt changed the interp, free it. */ @@ -1520,8 +1544,7 @@ static struct linux_binprm *alloc_bprm(int fd, struct filename *filename, int fl bprm = kzalloc(sizeof(*bprm), GFP_KERNEL); if (!bprm) { - allow_write_access(file); - fput(file); + do_close_execat(file); return ERR_PTR(-ENOMEM); } @@ -1610,6 +1633,7 @@ static void check_unsafe_exec(struct linux_binprm *bprm) } rcu_read_unlock(); + /* "users" and "in_exec" locked for copy_fs() */ if (p->fs->users > n_fs) bprm->unsafe |= LSM_UNSAFE_SHARE; else @@ -1826,9 +1850,6 @@ static int exec_binprm(struct linux_binprm *bprm) return 0; } -/* - * sys_execve() executes a new program. - */ static int bprm_execve(struct linux_binprm *bprm) { int retval; diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index a59e7b2edaac..3298c29b5548 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -101,7 +101,7 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) } if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) { - if (folio_index(folio) == rreq->no_unlock_folio && + if (folio->index == rreq->no_unlock_folio && test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags)) _debug("no unlock"); else @@ -246,13 +246,13 @@ EXPORT_SYMBOL(netfs_readahead); */ int netfs_read_folio(struct file *file, struct folio *folio) { - struct address_space *mapping = folio_file_mapping(folio); + struct address_space *mapping = folio->mapping; struct netfs_io_request *rreq; struct netfs_inode *ctx = netfs_inode(mapping->host); struct folio *sink = NULL; int ret; - _enter("%lx", folio_index(folio)); + _enter("%lx", folio->index); rreq = netfs_alloc_request(mapping, file, folio_file_pos(folio), folio_size(folio), @@ -460,7 +460,7 @@ retry: ret = PTR_ERR(rreq); goto error; } - rreq->no_unlock_folio = folio_index(folio); + rreq->no_unlock_folio = folio->index; __set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags); ret = netfs_begin_cache_read(rreq, ctx); @@ -518,7 +518,7 @@ int netfs_prefetch_for_write(struct file *file, struct folio *folio, size_t offset, size_t len) { struct netfs_io_request *rreq; - struct address_space *mapping = folio_file_mapping(folio); + struct address_space *mapping = folio->mapping; struct netfs_inode *ctx = netfs_inode(mapping->host); unsigned long long start = folio_pos(folio); size_t flen = folio_size(folio); @@ -535,7 +535,7 @@ int netfs_prefetch_for_write(struct file *file, struct folio *folio, goto error; } - rreq->no_unlock_folio = folio_index(folio); + rreq->no_unlock_folio = folio->index; __set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags); ret = netfs_begin_cache_read(rreq, ctx); if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c index 93dc76f34e39..a3059b3168fd 100644 --- a/fs/netfs/buffered_write.c +++ b/fs/netfs/buffered_write.c @@ -221,10 +221,11 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, if (unlikely(fault_in_iov_iter_readable(iter, part) == part)) break; - ret = -ENOMEM; folio = netfs_grab_folio_for_write(mapping, pos, part); - if (!folio) + if (IS_ERR(folio)) { + ret = PTR_ERR(folio); break; + } flen = folio_size(folio); offset = pos & (flen - 1); @@ -343,7 +344,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, break; default: WARN(true, "Unexpected modify type %u ix=%lx\n", - howto, folio_index(folio)); + howto, folio->index); ret = -EIO; goto error_folio_unlock; } @@ -648,7 +649,7 @@ static void netfs_pages_written_back(struct netfs_io_request *wreq) xas_for_each(&xas, folio, last) { WARN(!folio_test_writeback(folio), "bad %zx @%llx page %lx %lx\n", - wreq->len, wreq->start, folio_index(folio), last); + wreq->len, wreq->start, folio->index, last); if ((finfo = netfs_folio_info(folio))) { /* Streaming writes cannot be redirtied whilst under @@ -795,7 +796,7 @@ static void netfs_extend_writeback(struct address_space *mapping, continue; if (xa_is_value(folio)) break; - if (folio_index(folio) != index) { + if (folio->index != index) { xas_reset(xas); break; } @@ -901,7 +902,7 @@ static ssize_t netfs_write_back_from_locked_folio(struct address_space *mapping, long count = wbc->nr_to_write; int ret; - _enter(",%lx,%llx-%llx,%u", folio_index(folio), start, end, caching); + _enter(",%lx,%llx-%llx,%u", folio->index, start, end, caching); wreq = netfs_alloc_request(mapping, NULL, start, folio_size(folio), NETFS_WRITEBACK); @@ -1047,7 +1048,7 @@ search_again: start = folio_pos(folio); /* May regress with THPs */ - _debug("wback %lx", folio_index(folio)); + _debug("wback %lx", folio->index); /* At this point we hold neither the i_pages lock nor the page lock: * the page may be truncated or invalidated (changing page->mapping to diff --git a/fs/netfs/fscache_cache.c b/fs/netfs/fscache_cache.c index d645f8b302a2..9397ed39b0b4 100644 --- a/fs/netfs/fscache_cache.c +++ b/fs/netfs/fscache_cache.c @@ -179,13 +179,14 @@ EXPORT_SYMBOL(fscache_acquire_cache); void fscache_put_cache(struct fscache_cache *cache, enum fscache_cache_trace where) { - unsigned int debug_id = cache->debug_id; + unsigned int debug_id; bool zero; int ref; if (IS_ERR_OR_NULL(cache)) return; + debug_id = cache->debug_id; zero = __refcount_dec_and_test(&cache->ref, &ref); trace_fscache_cache(debug_id, ref - 1, where); diff --git a/fs/netfs/io.c b/fs/netfs/io.c index 4309edf33862..e8ff1e61ce79 100644 --- a/fs/netfs/io.c +++ b/fs/netfs/io.c @@ -124,7 +124,7 @@ static void netfs_rreq_unmark_after_write(struct netfs_io_request *rreq, /* We might have multiple writes from the same huge * folio, but we mustn't unlock a folio more than once. */ - if (have_unlocked && folio_index(folio) <= unlocked) + if (have_unlocked && folio->index <= unlocked) continue; unlocked = folio_next_index(folio) - 1; trace_netfs_folio(folio, netfs_folio_trace_end_copy); diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c index 0e3af37fc924..90051ced8e2a 100644 --- a/fs/netfs/misc.c +++ b/fs/netfs/misc.c @@ -180,7 +180,7 @@ void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length) struct netfs_folio *finfo = NULL; size_t flen = folio_size(folio); - _enter("{%lx},%zx,%zx", folio_index(folio), offset, length); + _enter("{%lx},%zx,%zx", folio->index, offset, length); folio_wait_fscache(folio); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 2fa54cfd4882..6dc6340e2852 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -7911,14 +7911,16 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) { struct file_lock *fl; int status = false; - struct nfsd_file *nf = find_any_file(fp); + struct nfsd_file *nf; struct inode *inode; struct file_lock_context *flctx; + spin_lock(&fp->fi_lock); + nf = find_any_file_locked(fp); if (!nf) { /* Any valid lock stateid should have some sort of access */ WARN_ON_ONCE(1); - return status; + goto out; } inode = file_inode(nf->nf_file); @@ -7934,7 +7936,8 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) } spin_unlock(&flctx->flc_lock); } - nfsd_file_put(nf); +out: + spin_unlock(&fp->fi_lock); return status; } @@ -7944,10 +7947,8 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) * @cstate: NFSv4 COMPOUND state * @u: RELEASE_LOCKOWNER arguments * - * The lockowner's so_count is bumped when a lock record is added - * or when copying a conflicting lock. The latter case is brief, - * but can lead to fleeting false positives when looking for - * locks-in-use. + * Check if theree are any locks still held and if not - free the lockowner + * and any lock state that is owned. * * Return values: * %nfs_ok: lockowner released or not found @@ -7983,10 +7984,13 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp, spin_unlock(&clp->cl_lock); return nfs_ok; } - if (atomic_read(&lo->lo_owner.so_count) != 2) { - spin_unlock(&clp->cl_lock); - nfs4_put_stateowner(&lo->lo_owner); - return nfserr_locks_held; + + list_for_each_entry(stp, &lo->lo_owner.so_stateids, st_perstateowner) { + if (check_for_locks(stp->st_stid.sc_file, lo)) { + spin_unlock(&clp->cl_lock); + nfs4_put_stateowner(&lo->lo_owner); + return nfserr_locks_held; + } } unhash_lockowner_locked(lo); while (!list_empty(&lo->lo_owner.so_stateids)) { diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index 984ffdaeed6c..5764f91d283e 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -18,10 +18,11 @@ struct ovl_lookup_data { struct super_block *sb; - struct vfsmount *mnt; + const struct ovl_layer *layer; struct qstr name; bool is_dir; bool opaque; + bool xwhiteouts; bool stop; bool last; char *redirect; @@ -201,17 +202,13 @@ struct dentry *ovl_decode_real_fh(struct ovl_fs *ofs, struct ovl_fh *fh, return real; } -static bool ovl_is_opaquedir(struct ovl_fs *ofs, const struct path *path) -{ - return ovl_path_check_dir_xattr(ofs, path, OVL_XATTR_OPAQUE); -} - static struct dentry *ovl_lookup_positive_unlocked(struct ovl_lookup_data *d, const char *name, struct dentry *base, int len, bool drop_negative) { - struct dentry *ret = lookup_one_unlocked(mnt_idmap(d->mnt), name, base, len); + struct dentry *ret = lookup_one_unlocked(mnt_idmap(d->layer->mnt), name, + base, len); if (!IS_ERR(ret) && d_flags_negative(smp_load_acquire(&ret->d_flags))) { if (drop_negative && ret->d_lockref.count == 1) { @@ -232,10 +229,13 @@ static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d, size_t prelen, const char *post, struct dentry **ret, bool drop_negative) { + struct ovl_fs *ofs = OVL_FS(d->sb); struct dentry *this; struct path path; int err; bool last_element = !post[0]; + bool is_upper = d->layer->idx == 0; + char val; this = ovl_lookup_positive_unlocked(d, name, base, namelen, drop_negative); if (IS_ERR(this)) { @@ -253,8 +253,8 @@ static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d, } path.dentry = this; - path.mnt = d->mnt; - if (ovl_path_is_whiteout(OVL_FS(d->sb), &path)) { + path.mnt = d->layer->mnt; + if (ovl_path_is_whiteout(ofs, &path)) { d->stop = d->opaque = true; goto put_and_out; } @@ -272,7 +272,7 @@ static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d, d->stop = true; goto put_and_out; } - err = ovl_check_metacopy_xattr(OVL_FS(d->sb), &path, NULL); + err = ovl_check_metacopy_xattr(ofs, &path, NULL); if (err < 0) goto out_err; @@ -292,7 +292,12 @@ static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d, if (d->last) goto out; - if (ovl_is_opaquedir(OVL_FS(d->sb), &path)) { + /* overlay.opaque=x means xwhiteouts directory */ + val = ovl_get_opaquedir_val(ofs, &path); + if (last_element && !is_upper && val == 'x') { + d->xwhiteouts = true; + ovl_layer_set_xwhiteouts(ofs, d->layer); + } else if (val == 'y') { d->stop = true; if (last_element) d->opaque = true; @@ -863,7 +868,8 @@ fail: * Returns next layer in stack starting from top. * Returns -1 if this is the last layer. */ -int ovl_path_next(int idx, struct dentry *dentry, struct path *path) +int ovl_path_next(int idx, struct dentry *dentry, struct path *path, + const struct ovl_layer **layer) { struct ovl_entry *oe = OVL_E(dentry); struct ovl_path *lowerstack = ovl_lowerstack(oe); @@ -871,13 +877,16 @@ int ovl_path_next(int idx, struct dentry *dentry, struct path *path) BUG_ON(idx < 0); if (idx == 0) { ovl_path_upper(dentry, path); - if (path->dentry) + if (path->dentry) { + *layer = &OVL_FS(dentry->d_sb)->layers[0]; return ovl_numlower(oe) ? 1 : -1; + } idx++; } BUG_ON(idx > ovl_numlower(oe)); path->dentry = lowerstack[idx - 1].dentry; - path->mnt = lowerstack[idx - 1].layer->mnt; + *layer = lowerstack[idx - 1].layer; + path->mnt = (*layer)->mnt; return (idx < ovl_numlower(oe)) ? idx + 1 : -1; } @@ -1055,7 +1064,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, old_cred = ovl_override_creds(dentry->d_sb); upperdir = ovl_dentry_upper(dentry->d_parent); if (upperdir) { - d.mnt = ovl_upper_mnt(ofs); + d.layer = &ofs->layers[0]; err = ovl_lookup_layer(upperdir, &d, &upperdentry, true); if (err) goto out; @@ -1111,7 +1120,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, else if (d.is_dir || !ofs->numdatalayer) d.last = lower.layer->idx == ovl_numlower(roe); - d.mnt = lower.layer->mnt; + d.layer = lower.layer; err = ovl_lookup_layer(lower.dentry, &d, &this, false); if (err) goto out_put; @@ -1278,6 +1287,8 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, if (upperopaque) ovl_dentry_set_opaque(dentry); + if (d.xwhiteouts) + ovl_dentry_set_xwhiteouts(dentry); if (upperdentry) ovl_dentry_set_upper_alias(dentry); diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 5ba11eb43767..ee949f3e7c77 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -50,7 +50,6 @@ enum ovl_xattr { OVL_XATTR_METACOPY, OVL_XATTR_PROTATTR, OVL_XATTR_XWHITEOUT, - OVL_XATTR_XWHITEOUTS, }; enum ovl_inode_flag { @@ -70,6 +69,8 @@ enum ovl_entry_flag { OVL_E_UPPER_ALIAS, OVL_E_OPAQUE, OVL_E_CONNECTED, + /* Lower stack may contain xwhiteout entries */ + OVL_E_XWHITEOUTS, }; enum { @@ -477,6 +478,10 @@ bool ovl_dentry_test_flag(unsigned long flag, struct dentry *dentry); bool ovl_dentry_is_opaque(struct dentry *dentry); bool ovl_dentry_is_whiteout(struct dentry *dentry); void ovl_dentry_set_opaque(struct dentry *dentry); +bool ovl_dentry_has_xwhiteouts(struct dentry *dentry); +void ovl_dentry_set_xwhiteouts(struct dentry *dentry); +void ovl_layer_set_xwhiteouts(struct ovl_fs *ofs, + const struct ovl_layer *layer); bool ovl_dentry_has_upper_alias(struct dentry *dentry); void ovl_dentry_set_upper_alias(struct dentry *dentry); bool ovl_dentry_needs_data_copy_up(struct dentry *dentry, int flags); @@ -494,11 +499,10 @@ struct file *ovl_path_open(const struct path *path, int flags); int ovl_copy_up_start(struct dentry *dentry, int flags); void ovl_copy_up_end(struct dentry *dentry); bool ovl_already_copied_up(struct dentry *dentry, int flags); -bool ovl_path_check_dir_xattr(struct ovl_fs *ofs, const struct path *path, - enum ovl_xattr ox); +char ovl_get_dir_xattr_val(struct ovl_fs *ofs, const struct path *path, + enum ovl_xattr ox); bool ovl_path_check_origin_xattr(struct ovl_fs *ofs, const struct path *path); bool ovl_path_check_xwhiteout_xattr(struct ovl_fs *ofs, const struct path *path); -bool ovl_path_check_xwhiteouts_xattr(struct ovl_fs *ofs, const struct path *path); bool ovl_init_uuid_xattr(struct super_block *sb, struct ovl_fs *ofs, const struct path *upperpath); @@ -573,7 +577,13 @@ static inline bool ovl_is_impuredir(struct super_block *sb, .mnt = ovl_upper_mnt(ofs), }; - return ovl_path_check_dir_xattr(ofs, &upperpath, OVL_XATTR_IMPURE); + return ovl_get_dir_xattr_val(ofs, &upperpath, OVL_XATTR_IMPURE) == 'y'; +} + +static inline char ovl_get_opaquedir_val(struct ovl_fs *ofs, + const struct path *path) +{ + return ovl_get_dir_xattr_val(ofs, path, OVL_XATTR_OPAQUE); } static inline bool ovl_redirect_follow(struct ovl_fs *ofs) @@ -680,7 +690,8 @@ int ovl_get_index_name(struct ovl_fs *ofs, struct dentry *origin, struct dentry *ovl_get_index_fh(struct ovl_fs *ofs, struct ovl_fh *fh); struct dentry *ovl_lookup_index(struct ovl_fs *ofs, struct dentry *upper, struct dentry *origin, bool verify); -int ovl_path_next(int idx, struct dentry *dentry, struct path *path); +int ovl_path_next(int idx, struct dentry *dentry, struct path *path, + const struct ovl_layer **layer); int ovl_verify_lowerdata(struct dentry *dentry); struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags); diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h index 5fa9c58af65f..cb449ab310a7 100644 --- a/fs/overlayfs/ovl_entry.h +++ b/fs/overlayfs/ovl_entry.h @@ -40,6 +40,8 @@ struct ovl_layer { int idx; /* One fsid per unique underlying sb (upper fsid == 0) */ int fsid; + /* xwhiteouts were found on this layer */ + bool has_xwhiteouts; }; struct ovl_path { @@ -59,7 +61,7 @@ struct ovl_fs { unsigned int numfs; /* Number of data-only lower layers */ unsigned int numdatalayer; - const struct ovl_layer *layers; + struct ovl_layer *layers; struct ovl_sb *fs; /* workbasedir is the path at workdir= mount option */ struct dentry *workbasedir; diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index e71156baa7bc..0ca8af060b0c 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -305,8 +305,6 @@ static inline int ovl_dir_read(const struct path *realpath, if (IS_ERR(realfile)) return PTR_ERR(realfile); - rdd->in_xwhiteouts_dir = rdd->dentry && - ovl_path_check_xwhiteouts_xattr(OVL_FS(rdd->dentry->d_sb), realpath); rdd->first_maybe_whiteout = NULL; rdd->ctx.pos = 0; do { @@ -359,10 +357,13 @@ static int ovl_dir_read_merged(struct dentry *dentry, struct list_head *list, .is_lowest = false, }; int idx, next; + const struct ovl_layer *layer; for (idx = 0; idx != -1; idx = next) { - next = ovl_path_next(idx, dentry, &realpath); + next = ovl_path_next(idx, dentry, &realpath, &layer); rdd.is_upper = ovl_dentry_upper(dentry) == realpath.dentry; + rdd.in_xwhiteouts_dir = layer->has_xwhiteouts && + ovl_dentry_has_xwhiteouts(dentry); if (next != -1) { err = ovl_dir_read(&realpath, &rdd); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 4ab66e3d4cff..2eef6c70b2ae 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -1249,6 +1249,7 @@ static struct dentry *ovl_get_root(struct super_block *sb, struct ovl_entry *oe) { struct dentry *root; + struct ovl_fs *ofs = OVL_FS(sb); struct ovl_path *lowerpath = ovl_lowerstack(oe); unsigned long ino = d_inode(lowerpath->dentry)->i_ino; int fsid = lowerpath->layer->fsid; @@ -1270,6 +1271,20 @@ static struct dentry *ovl_get_root(struct super_block *sb, ovl_set_flag(OVL_IMPURE, d_inode(root)); } + /* Look for xwhiteouts marker except in the lowermost layer */ + for (int i = 0; i < ovl_numlower(oe) - 1; i++, lowerpath++) { + struct path path = { + .mnt = lowerpath->layer->mnt, + .dentry = lowerpath->dentry, + }; + + /* overlay.opaque=x means xwhiteouts directory */ + if (ovl_get_opaquedir_val(ofs, &path) == 'x') { + ovl_layer_set_xwhiteouts(ofs, lowerpath->layer); + ovl_dentry_set_xwhiteouts(root); + } + } + /* Root is always merge -> can have whiteouts */ ovl_set_flag(OVL_WHITEOUTS, d_inode(root)); ovl_dentry_set_flag(OVL_E_CONNECTED, root); diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index 0217094c23ea..a8e17f14d7a2 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -461,6 +461,33 @@ void ovl_dentry_set_opaque(struct dentry *dentry) ovl_dentry_set_flag(OVL_E_OPAQUE, dentry); } +bool ovl_dentry_has_xwhiteouts(struct dentry *dentry) +{ + return ovl_dentry_test_flag(OVL_E_XWHITEOUTS, dentry); +} + +void ovl_dentry_set_xwhiteouts(struct dentry *dentry) +{ + ovl_dentry_set_flag(OVL_E_XWHITEOUTS, dentry); +} + +/* + * ovl_layer_set_xwhiteouts() is called before adding the overlay dir + * dentry to dcache, while readdir of that same directory happens after + * the overlay dir dentry is in dcache, so if some cpu observes that + * ovl_dentry_is_xwhiteouts(), it will also observe layer->has_xwhiteouts + * for the layers where xwhiteouts marker was found in that merge dir. + */ +void ovl_layer_set_xwhiteouts(struct ovl_fs *ofs, + const struct ovl_layer *layer) +{ + if (layer->has_xwhiteouts) + return; + + /* Write once to read-mostly layer properties */ + ofs->layers[layer->idx].has_xwhiteouts = true; +} + /* * For hard links and decoded file handles, it's possible for ovl_dentry_upper() * to return positive, while there's no actual upper alias for the inode. @@ -739,19 +766,6 @@ bool ovl_path_check_xwhiteout_xattr(struct ovl_fs *ofs, const struct path *path) return res >= 0; } -bool ovl_path_check_xwhiteouts_xattr(struct ovl_fs *ofs, const struct path *path) -{ - struct dentry *dentry = path->dentry; - int res; - - /* xattr.whiteouts must be a directory */ - if (!d_is_dir(dentry)) - return false; - - res = ovl_path_getxattr(ofs, path, OVL_XATTR_XWHITEOUTS, NULL, 0); - return res >= 0; -} - /* * Load persistent uuid from xattr into s_uuid if found, or store a new * random generated value in s_uuid and in xattr. @@ -811,20 +825,17 @@ fail: return false; } -bool ovl_path_check_dir_xattr(struct ovl_fs *ofs, const struct path *path, - enum ovl_xattr ox) +char ovl_get_dir_xattr_val(struct ovl_fs *ofs, const struct path *path, + enum ovl_xattr ox) { int res; char val; if (!d_is_dir(path->dentry)) - return false; + return 0; res = ovl_path_getxattr(ofs, path, ox, &val, 1); - if (res == 1 && val == 'y') - return true; - - return false; + return res == 1 ? val : 0; } #define OVL_XATTR_OPAQUE_POSTFIX "opaque" @@ -837,7 +848,6 @@ bool ovl_path_check_dir_xattr(struct ovl_fs *ofs, const struct path *path, #define OVL_XATTR_METACOPY_POSTFIX "metacopy" #define OVL_XATTR_PROTATTR_POSTFIX "protattr" #define OVL_XATTR_XWHITEOUT_POSTFIX "whiteout" -#define OVL_XATTR_XWHITEOUTS_POSTFIX "whiteouts" #define OVL_XATTR_TAB_ENTRY(x) \ [x] = { [false] = OVL_XATTR_TRUSTED_PREFIX x ## _POSTFIX, \ @@ -854,7 +864,6 @@ const char *const ovl_xattr_table[][2] = { OVL_XATTR_TAB_ENTRY(OVL_XATTR_METACOPY), OVL_XATTR_TAB_ENTRY(OVL_XATTR_PROTATTR), OVL_XATTR_TAB_ENTRY(OVL_XATTR_XWHITEOUT), - OVL_XATTR_TAB_ENTRY(OVL_XATTR_XWHITEOUTS), }; int ovl_check_setxattr(struct ovl_fs *ofs, struct dentry *upperdentry, diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 3a213432775b..90da81d0372a 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -87,7 +87,7 @@ void cifs_pages_written_back(struct inode *inode, loff_t start, unsigned int len continue; if (!folio_test_writeback(folio)) { WARN_ONCE(1, "bad %x @%llx page %lx %lx\n", - len, start, folio_index(folio), end); + len, start, folio->index, end); continue; } @@ -120,7 +120,7 @@ void cifs_pages_write_failed(struct inode *inode, loff_t start, unsigned int len continue; if (!folio_test_writeback(folio)) { WARN_ONCE(1, "bad %x @%llx page %lx %lx\n", - len, start, folio_index(folio), end); + len, start, folio->index, end); continue; } @@ -151,7 +151,7 @@ void cifs_pages_write_redirty(struct inode *inode, loff_t start, unsigned int le xas_for_each(&xas, folio, end) { if (!folio_test_writeback(folio)) { WARN_ONCE(1, "bad %x @%llx page %lx %lx\n", - len, start, folio_index(folio), end); + len, start, folio->index, end); continue; } @@ -2651,7 +2651,7 @@ static void cifs_extend_writeback(struct address_space *mapping, continue; if (xa_is_value(folio)) break; - if (folio_index(folio) != index) + if (folio->index != index) break; if (!folio_try_get_rcu(folio)) { xas_reset(&xas); @@ -2899,7 +2899,7 @@ redo_folio: goto skip_write; } - if (folio_mapping(folio) != mapping || + if (folio->mapping != mapping || !folio_test_dirty(folio)) { start += folio_size(folio); folio_unlock(folio); diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index 6795fda2af19..6b211522a13e 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -34,7 +34,15 @@ static DEFINE_MUTEX(eventfs_mutex); /* Choose something "unique" ;-) */ #define EVENTFS_FILE_INODE_INO 0x12c4e37 -#define EVENTFS_DIR_INODE_INO 0x134b2f5 + +/* Just try to make something consistent and unique */ +static int eventfs_dir_ino(struct eventfs_inode *ei) +{ + if (!ei->ino) + ei->ino = get_next_ino(); + + return ei->ino; +} /* * The eventfs_inode (ei) itself is protected by SRCU. It is released from @@ -396,7 +404,7 @@ static struct dentry *create_dir(struct eventfs_inode *ei, struct dentry *parent inode->i_fop = &eventfs_file_operations; /* All directories will have the same inode number */ - inode->i_ino = EVENTFS_DIR_INODE_INO; + inode->i_ino = eventfs_dir_ino(ei); ti = get_tracefs(inode); ti->flags |= TRACEFS_EVENT_INODE; @@ -802,7 +810,7 @@ static int eventfs_iterate(struct file *file, struct dir_context *ctx) name = ei_child->name; - ino = EVENTFS_DIR_INODE_INO; + ino = eventfs_dir_ino(ei_child); if (!dir_emit(ctx, name, strlen(name), ino, DT_DIR)) goto out_dec; diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h index 12b7d0150ae9..45397df9bb65 100644 --- a/fs/tracefs/internal.h +++ b/fs/tracefs/internal.h @@ -55,6 +55,10 @@ struct eventfs_inode { struct eventfs_attr *entry_attrs; struct eventfs_attr attr; void *data; + unsigned int is_freed:1; + unsigned int is_events:1; + unsigned int nr_entries:30; + unsigned int ino; /* * Union - used for deletion * @llist: for calling dput() if needed after RCU @@ -64,9 +68,6 @@ struct eventfs_inode { struct llist_node llist; struct rcu_head rcu; }; - unsigned int is_freed:1; - unsigned int is_events:1; - unsigned int nr_entries:30; }; static inline struct tracefs_inode *get_tracefs(const struct inode *inode) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 8c55ff351e5f..41f03b352401 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -681,6 +681,7 @@ struct mlx5e_resources { struct mlx5_sq_bfreg bfreg; #define MLX5_MAX_NUM_TC 8 u32 tisn[MLX5_MAX_PORTS][MLX5_MAX_NUM_TC]; + bool tisn_valid; } hw_objs; struct net_device *uplink_netdev; struct mutex uplink_netdev_lock; diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 6f7725238abc..3fb428ce7d1c 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -132,6 +132,7 @@ struct mlx5_flow_handle; enum { FLOW_CONTEXT_HAS_TAG = BIT(0), + FLOW_CONTEXT_UPLINK_HAIRPIN_EN = BIT(1), }; struct mlx5_flow_context { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index bf5320b28b8b..c726f90ab752 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -3576,7 +3576,7 @@ struct mlx5_ifc_flow_context_bits { u8 action[0x10]; u8 extended_destination[0x1]; - u8 reserved_at_81[0x1]; + u8 uplink_hairpin_en[0x1]; u8 flow_source[0x2]; u8 encrypt_decrypt_type[0x4]; u8 destination_list_size[0x18]; @@ -4036,8 +4036,13 @@ struct mlx5_ifc_nic_vport_context_bits { u8 affiliation_criteria[0x4]; u8 affiliated_vhca_id[0x10]; - u8 reserved_at_60[0xd0]; + u8 reserved_at_60[0xa0]; + + u8 reserved_at_100[0x1]; + u8 sd_group[0x3]; + u8 reserved_at_104[0x1c]; + u8 reserved_at_120[0x10]; u8 mtu[0x10]; u8 system_image_guid[0x40]; @@ -10122,8 +10127,7 @@ struct mlx5_ifc_mpir_reg_bits { u8 reserved_at_20[0x20]; u8 local_port[0x8]; - u8 reserved_at_28[0x15]; - u8 sd_group[0x3]; + u8 reserved_at_28[0x18]; u8 reserved_at_60[0x20]; }; diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index fbb9bf447889..c36cc6d82926 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -72,6 +72,7 @@ int mlx5_query_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 *mtu); int mlx5_modify_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 mtu); int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev, u64 *system_image_guid); +int mlx5_query_nic_vport_sd_group(struct mlx5_core_dev *mdev, u8 *sd_group); int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid); int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev, u16 vport, u64 node_guid); diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index e8c350a3ade1..e9f4f845d760 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -186,6 +186,8 @@ struct ip_set_type_variant { /* Return true if "b" set is the same as "a" * according to the create set parameters */ bool (*same_set)(const struct ip_set *a, const struct ip_set *b); + /* Cancel ongoing garbage collectors before destroying the set*/ + void (*cancel_gc)(struct ip_set *set); /* Region-locking is used */ bool region_lock; }; @@ -242,6 +244,8 @@ extern void ip_set_type_unregister(struct ip_set_type *set_type); /* A generic IP set */ struct ip_set { + /* For call_cru in destroy */ + struct rcu_head rcu; /* The name of the set */ char name[IPSET_MAXNAMELEN]; /* Lock protecting the set data */ diff --git a/include/linux/sched.h b/include/linux/sched.h index cdb8ea53c365..ffe8f618ab86 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -920,7 +920,7 @@ struct task_struct { unsigned sched_rt_mutex:1; #endif - /* Bit to tell LSMs we're in execve(): */ + /* Bit to tell TOMOYO we're in execve(): */ unsigned in_execve:1; unsigned in_iowait:1; #ifndef TIF_RESTORE_SIGMASK diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 888a4b217829..e65ec3fd2799 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -505,12 +505,6 @@ static inline bool sk_psock_strp_enabled(struct sk_psock *psock) return !!psock->saved_data_ready; } -static inline bool sk_is_udp(const struct sock *sk) -{ - return sk->sk_type == SOCK_DGRAM && - sk->sk_protocol == IPPROTO_UDP; -} - #if IS_ENABLED(CONFIG_NET_SOCK_MSG) #define BPF_F_STRPARSER (1UL << 1) diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 49c4640027d8..afd40dce40f3 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -46,12 +46,6 @@ struct scm_stat { #define UNIXCB(skb) (*(struct unix_skb_parms *)&((skb)->cb)) -#define unix_state_lock(s) spin_lock(&unix_sk(s)->lock) -#define unix_state_unlock(s) spin_unlock(&unix_sk(s)->lock) -#define unix_state_lock_nested(s) \ - spin_lock_nested(&unix_sk(s)->lock, \ - SINGLE_DEPTH_NESTING) - /* The AF_UNIX socket */ struct unix_sock { /* WARNING: sk has to be the first member */ @@ -77,6 +71,20 @@ struct unix_sock { #define unix_sk(ptr) container_of_const(ptr, struct unix_sock, sk) #define unix_peer(sk) (unix_sk(sk)->peer) +#define unix_state_lock(s) spin_lock(&unix_sk(s)->lock) +#define unix_state_unlock(s) spin_unlock(&unix_sk(s)->lock) +enum unix_socket_lock_class { + U_LOCK_NORMAL, + U_LOCK_SECOND, /* for double locking, see unix_state_double_lock(). */ + U_LOCK_DIAG, /* used while dumping icons, see sk_diag_dump_icons(). */ +}; + +static inline void unix_state_lock_nested(struct sock *sk, + enum unix_socket_lock_class subclass) +{ + spin_lock_nested(&unix_sk(sk)->lock, subclass); +} + #define peer_wait peer_wq.wait long unix_inq_len(struct sock *sk); diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index d0a2f827d5f2..9ab4bf704e86 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -357,4 +357,12 @@ static inline bool inet_csk_has_ulp(const struct sock *sk) return inet_test_bit(IS_ICSK, sk) && !!inet_csk(sk)->icsk_ulp_ops; } +static inline void inet_init_csk_locks(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + spin_lock_init(&icsk->icsk_accept_queue.rskq_lock); + spin_lock_init(&icsk->icsk_accept_queue.fastopenq.lock); +} + #endif /* _INET_CONNECTION_SOCK_H */ diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index aa86453f6b9b..d94c242eb3ed 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -307,11 +307,6 @@ static inline unsigned long inet_cmsg_flags(const struct inet_sock *inet) #define inet_assign_bit(nr, sk, val) \ assign_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags, val) -static inline bool sk_is_inet(struct sock *sk) -{ - return sk->sk_family == AF_INET || sk->sk_family == AF_INET6; -} - /** * sk_to_full_sk - Access to a full socket * @sk: pointer to a socket diff --git a/include/net/ip.h b/include/net/ip.h index de0c69c57e3c..25cb688bdc62 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -767,7 +767,7 @@ int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev); * Functions provided by ip_sockglue.c */ -void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb); +void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb, bool drop_dst); void ip_cmsg_recv_offset(struct msghdr *msg, struct sock *sk, struct sk_buff *skb, int tlen, int offset); int ip_cmsg_send(struct sock *sk, struct msghdr *msg, diff --git a/include/net/llc_pdu.h b/include/net/llc_pdu.h index 7e73f8e5e497..1d55ba7c45be 100644 --- a/include/net/llc_pdu.h +++ b/include/net/llc_pdu.h @@ -262,8 +262,7 @@ static inline void llc_pdu_header_init(struct sk_buff *skb, u8 type, */ static inline void llc_pdu_decode_sa(struct sk_buff *skb, u8 *sa) { - if (skb->protocol == htons(ETH_P_802_2)) - memcpy(sa, eth_hdr(skb)->h_source, ETH_ALEN); + memcpy(sa, eth_hdr(skb)->h_source, ETH_ALEN); } /** @@ -275,8 +274,7 @@ static inline void llc_pdu_decode_sa(struct sk_buff *skb, u8 *sa) */ static inline void llc_pdu_decode_da(struct sk_buff *skb, u8 *da) { - if (skb->protocol == htons(ETH_P_802_2)) - memcpy(da, eth_hdr(skb)->h_dest, ETH_ALEN); + memcpy(da, eth_hdr(skb)->h_dest, ETH_ALEN); } /** diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index b157c5cafd14..001226c34621 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -205,6 +205,7 @@ static inline void nft_data_copy(u32 *dst, const struct nft_data *src, * @nla: netlink attributes * @portid: netlink portID of the original message * @seq: netlink sequence number + * @flags: modifiers to new request * @family: protocol family * @level: depth of the chains * @report: notify via unicast netlink message @@ -282,6 +283,7 @@ struct nft_elem_priv { }; * * @key: element key * @key_end: closing element key + * @data: element data * @priv: element private data and extensions */ struct nft_set_elem { @@ -325,10 +327,10 @@ struct nft_set_iter { * @dtype: data type * @dlen: data length * @objtype: object type - * @flags: flags * @size: number of set elements * @policy: set policy * @gc_int: garbage collector interval + * @timeout: element timeout * @field_len: length of each field in concatenation, bytes * @field_count: number of concatenated fields in element * @expr: set must support for expressions @@ -351,9 +353,9 @@ struct nft_set_desc { /** * enum nft_set_class - performance class * - * @NFT_LOOKUP_O_1: constant, O(1) - * @NFT_LOOKUP_O_LOG_N: logarithmic, O(log N) - * @NFT_LOOKUP_O_N: linear, O(N) + * @NFT_SET_CLASS_O_1: constant, O(1) + * @NFT_SET_CLASS_O_LOG_N: logarithmic, O(log N) + * @NFT_SET_CLASS_O_N: linear, O(N) */ enum nft_set_class { NFT_SET_CLASS_O_1, @@ -422,9 +424,13 @@ struct nft_set_ext; * @remove: remove element from set * @walk: iterate over all set elements * @get: get set elements + * @commit: commit set elements + * @abort: abort set elements * @privsize: function to return size of set private data + * @estimate: estimate the required memory size and the lookup complexity class * @init: initialize private data of new set instance * @destroy: destroy private data of set instance + * @gc_init: initialize garbage collection * @elemsize: element private size * * Operations lookup, update and delete have simpler interfaces, are faster @@ -540,13 +546,16 @@ struct nft_set_elem_expr { * @policy: set parameterization (see enum nft_set_policies) * @udlen: user data length * @udata: user data - * @expr: stateful expression + * @pending_update: list of pending update set element * @ops: set ops * @flags: set flags * @dead: set will be freed, never cleared * @genmask: generation mask * @klen: key length * @dlen: data length + * @num_exprs: numbers of exprs + * @exprs: stateful expression + * @catchall_list: list of catch-all set element * @data: private set data */ struct nft_set { @@ -692,6 +701,7 @@ extern const struct nft_set_ext_type nft_set_ext_types[]; * * @len: length of extension area * @offset: offsets of individual extension types + * @ext_len: length of the expected extension(used to sanity check) */ struct nft_set_ext_tmpl { u16 len; @@ -840,6 +850,7 @@ struct nft_expr_ops; * @select_ops: function to select nft_expr_ops * @release_ops: release nft_expr_ops * @ops: default ops, used when no select_ops functions is present + * @inner_ops: inner ops, used for inner packet operation * @list: used internally * @name: Identifier * @owner: module reference @@ -881,14 +892,22 @@ struct nft_offload_ctx; * struct nft_expr_ops - nf_tables expression operations * * @eval: Expression evaluation function + * @clone: Expression clone function * @size: full expression size, including private data size * @init: initialization function * @activate: activate expression in the next generation * @deactivate: deactivate expression in next generation * @destroy: destruction function, called after synchronize_rcu + * @destroy_clone: destruction clone function * @dump: function to dump parameters - * @type: expression type * @validate: validate expression, called during loop detection + * @reduce: reduce expression + * @gc: garbage collection expression + * @offload: hardware offload expression + * @offload_action: function to report true/false to allocate one slot or not in the flow + * offload array + * @offload_stats: function to synchronize hardware stats via updating the counter expression + * @type: expression type * @data: extra data to attach to this expression operation */ struct nft_expr_ops { @@ -1041,14 +1060,21 @@ struct nft_rule_blob { /** * struct nft_chain - nf_tables chain * + * @blob_gen_0: rule blob pointer to the current generation + * @blob_gen_1: rule blob pointer to the future generation * @rules: list of rules in the chain * @list: used internally * @rhlhead: used internally * @table: table that this chain belongs to * @handle: chain handle * @use: number of jump references to this chain - * @flags: bitmask of enum nft_chain_flags + * @flags: bitmask of enum NFTA_CHAIN_FLAGS + * @bound: bind or not + * @genmask: generation mask * @name: name of the chain + * @udlen: user data length + * @udata: user data in the chain + * @blob_next: rule blob pointer to the next in the chain */ struct nft_chain { struct nft_rule_blob __rcu *blob_gen_0; @@ -1146,6 +1172,7 @@ struct nft_hook { * @hook_list: list of netfilter hooks (for NFPROTO_NETDEV family) * @type: chain type * @policy: default policy + * @flags: indicate the base chain disabled or not * @stats: per-cpu chain stats * @chain: the chain * @flow_block: flow block (for hardware offload) @@ -1274,11 +1301,13 @@ struct nft_object_hash_key { * struct nft_object - nf_tables stateful object * * @list: table stateful object list node - * @key: keys that identify this object * @rhlhead: nft_objname_ht node + * @key: keys that identify this object * @genmask: generation mask * @use: number of references to this stateful object * @handle: unique object handle + * @udlen: length of user data + * @udata: user data * @ops: object operations * @data: object data, layout depends on type */ @@ -1322,6 +1351,7 @@ void nft_obj_notify(struct net *net, const struct nft_table *table, * @type: stateful object numeric type * @owner: module owner * @maxattr: maximum netlink attribute + * @family: address family for AF-specific object types * @policy: netlink attribute policy */ struct nft_object_type { @@ -1331,6 +1361,7 @@ struct nft_object_type { struct list_head list; u32 type; unsigned int maxattr; + u8 family; struct module *owner; const struct nla_policy *policy; }; @@ -1344,6 +1375,7 @@ struct nft_object_type { * @destroy: release existing stateful object * @dump: netlink dump stateful object * @update: update stateful object + * @type: pointer to object type */ struct nft_object_ops { void (*eval)(struct nft_object *obj, @@ -1379,9 +1411,8 @@ void nft_unregister_obj(struct nft_object_type *obj_type); * @genmask: generation mask * @use: number of references to this flow table * @handle: unique object handle - * @dev_name: array of device names + * @hook_list: hook list for hooks per net_device in flowtables * @data: rhashtable and garbage collector - * @ops: array of hooks */ struct nft_flowtable { struct list_head list; diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index ba3e1b315de8..934fdb977551 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -375,6 +375,10 @@ struct tcf_proto_ops { struct nlattr **tca, struct netlink_ext_ack *extack); void (*tmplt_destroy)(void *tmplt_priv); + void (*tmplt_reoffload)(struct tcf_chain *chain, + bool add, + flow_setup_cb_t *cb, + void *cb_priv); struct tcf_exts * (*get_exts)(const struct tcf_proto *tp, u32 handle); diff --git a/include/net/sock.h b/include/net/sock.h index a7f815c7cfdf..54ca8dcbfb43 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2765,9 +2765,25 @@ static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags) &skb_shinfo(skb)->tskey); } +static inline bool sk_is_inet(const struct sock *sk) +{ + int family = READ_ONCE(sk->sk_family); + + return family == AF_INET || family == AF_INET6; +} + static inline bool sk_is_tcp(const struct sock *sk) { - return sk->sk_type == SOCK_STREAM && sk->sk_protocol == IPPROTO_TCP; + return sk_is_inet(sk) && + sk->sk_type == SOCK_STREAM && + sk->sk_protocol == IPPROTO_TCP; +} + +static inline bool sk_is_udp(const struct sock *sk) +{ + return sk_is_inet(sk) && + sk->sk_type == SOCK_DGRAM && + sk->sk_protocol == IPPROTO_UDP; } static inline bool sk_is_stream_unix(const struct sock *sk) diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index 526c1e7f505e..c9aec9ab6191 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -159,11 +159,29 @@ static inline struct xdp_buff *xsk_buff_get_frag(struct xdp_buff *first) return ret; } +static inline void xsk_buff_del_tail(struct xdp_buff *tail) +{ + struct xdp_buff_xsk *xskb = container_of(tail, struct xdp_buff_xsk, xdp); + + list_del(&xskb->xskb_list_node); +} + +static inline struct xdp_buff *xsk_buff_get_tail(struct xdp_buff *first) +{ + struct xdp_buff_xsk *xskb = container_of(first, struct xdp_buff_xsk, xdp); + struct xdp_buff_xsk *frag; + + frag = list_last_entry(&xskb->pool->xskb_list, struct xdp_buff_xsk, + xskb_list_node); + return &frag->xdp; +} + static inline void xsk_buff_set_size(struct xdp_buff *xdp, u32 size) { xdp->data = xdp->data_hard_start + XDP_PACKET_HEADROOM; xdp->data_meta = xdp->data; xdp->data_end = xdp->data + size; + xdp->flags = 0; } static inline dma_addr_t xsk_buff_raw_get_dma(struct xsk_buff_pool *pool, @@ -350,6 +368,15 @@ static inline struct xdp_buff *xsk_buff_get_frag(struct xdp_buff *first) return NULL; } +static inline void xsk_buff_del_tail(struct xdp_buff *tail) +{ +} + +static inline struct xdp_buff *xsk_buff_get_tail(struct xdp_buff *first) +{ + return NULL; +} + static inline void xsk_buff_set_size(struct xdp_buff *xdp, u32 size) { } diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h index 8d73171cb9f0..08f2c93d6b16 100644 --- a/include/trace/events/afs.h +++ b/include/trace/events/afs.h @@ -1071,6 +1071,31 @@ TRACE_EVENT(afs_file_error, __print_symbolic(__entry->where, afs_file_errors)) ); +TRACE_EVENT(afs_bulkstat_error, + TP_PROTO(struct afs_operation *op, struct afs_fid *fid, unsigned int index, s32 abort), + + TP_ARGS(op, fid, index, abort), + + TP_STRUCT__entry( + __field_struct(struct afs_fid, fid) + __field(unsigned int, op) + __field(unsigned int, index) + __field(s32, abort) + ), + + TP_fast_assign( + __entry->op = op->debug_id; + __entry->fid = *fid; + __entry->index = index; + __entry->abort = abort; + ), + + TP_printk("OP=%08x[%02x] %llx:%llx:%x a=%d", + __entry->op, __entry->index, + __entry->fid.vid, __entry->fid.vnode, __entry->fid.unique, + __entry->abort) + ); + TRACE_EVENT(afs_cm_no_server, TP_PROTO(struct afs_call *call, struct sockaddr_rxrpc *srx), diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index 7c29d82db9ee..f8bc34a6bcfa 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -614,6 +614,9 @@ struct btrfs_ioctl_clone_range_args { */ #define BTRFS_DEFRAG_RANGE_COMPRESS 1 #define BTRFS_DEFRAG_RANGE_START_IO 2 +#define BTRFS_DEFRAG_RANGE_FLAGS_SUPP (BTRFS_DEFRAG_RANGE_COMPRESS | \ + BTRFS_DEFRAG_RANGE_START_IO) + struct btrfs_ioctl_defrag_range_args { /* start of the defrag operation */ __u64 start; diff --git a/init/Kconfig b/init/Kconfig index 8df18f3a9748..8d4e836e1b6b 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -876,6 +876,18 @@ config CC_NO_ARRAY_BOUNDS bool default y if CC_IS_GCC && GCC_VERSION >= 110000 && GCC11_NO_ARRAY_BOUNDS +# Currently, disable -Wstringop-overflow for GCC 11, globally. +config GCC11_NO_STRINGOP_OVERFLOW + def_bool y + +config CC_NO_STRINGOP_OVERFLOW + bool + default y if CC_IS_GCC && GCC_VERSION >= 110000 && GCC_VERSION < 120000 && GCC11_NO_STRINGOP_OVERFLOW + +config CC_STRINGOP_OVERFLOW + bool + default y if CC_IS_GCC && !CC_NO_STRINGOP_OVERFLOW + # # For architectures that know their GCC __int128 support is sound # diff --git a/kernel/fork.c b/kernel/fork.c index 47ff3b35352e..0d944e92a43f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1748,6 +1748,7 @@ static int copy_fs(unsigned long clone_flags, struct task_struct *tsk) if (clone_flags & CLONE_FS) { /* tsk->fs is already what we want */ spin_lock(&fs->lock); + /* "users" and "in_exec" locked for check_unsafe_exec() */ if (fs->in_exec) { spin_unlock(&fs->lock); return -EAGAIN; diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 1ae851777806..b2bccfd37c38 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1013,6 +1013,38 @@ static bool rcu_future_gp_cleanup(struct rcu_node *rnp) return needmore; } +static void swake_up_one_online_ipi(void *arg) +{ + struct swait_queue_head *wqh = arg; + + swake_up_one(wqh); +} + +static void swake_up_one_online(struct swait_queue_head *wqh) +{ + int cpu = get_cpu(); + + /* + * If called from rcutree_report_cpu_starting(), wake up + * is dangerous that late in the CPU-down hotplug process. The + * scheduler might queue an ignored hrtimer. Defer the wake up + * to an online CPU instead. + */ + if (unlikely(cpu_is_offline(cpu))) { + int target; + + target = cpumask_any_and(housekeeping_cpumask(HK_TYPE_RCU), + cpu_online_mask); + + smp_call_function_single(target, swake_up_one_online_ipi, + wqh, 0); + put_cpu(); + } else { + put_cpu(); + swake_up_one(wqh); + } +} + /* * Awaken the grace-period kthread. Don't do a self-awaken (unless in an * interrupt or softirq handler, in which case we just might immediately @@ -1037,7 +1069,7 @@ static void rcu_gp_kthread_wake(void) return; WRITE_ONCE(rcu_state.gp_wake_time, jiffies); WRITE_ONCE(rcu_state.gp_wake_seq, READ_ONCE(rcu_state.gp_seq)); - swake_up_one(&rcu_state.gp_wq); + swake_up_one_online(&rcu_state.gp_wq); } /* diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index 6d7cea5d591f..2ac440bc7e10 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -173,7 +173,6 @@ static bool sync_rcu_exp_done_unlocked(struct rcu_node *rnp) return ret; } - /* * Report the exit from RCU read-side critical section for the last task * that queued itself during or before the current expedited preemptible-RCU @@ -201,7 +200,7 @@ static void __rcu_report_exp_rnp(struct rcu_node *rnp, raw_spin_unlock_irqrestore_rcu_node(rnp, flags); if (wake) { smp_mb(); /* EGP done before wake_up(). */ - swake_up_one(&rcu_state.expedited_wq); + swake_up_one_online(&rcu_state.expedited_wq); } break; } diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c index c774e560f2f9..a4dcf0f24352 100644 --- a/kernel/trace/tracing_map.c +++ b/kernel/trace/tracing_map.c @@ -574,7 +574,12 @@ __tracing_map_insert(struct tracing_map *map, void *key, bool lookup_only) } memcpy(elt->key, key, map->key_size); - entry->val = elt; + /* + * Ensure the initialization is visible and + * publish the elt. + */ + smp_wmb(); + WRITE_ONCE(entry->val, elt); atomic64_inc(&map->hits); return entry->val; diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index 214532173536..a3b68243fd4b 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -118,12 +118,16 @@ static int vlan_changelink(struct net_device *dev, struct nlattr *tb[], } if (data[IFLA_VLAN_INGRESS_QOS]) { nla_for_each_nested(attr, data[IFLA_VLAN_INGRESS_QOS], rem) { + if (nla_type(attr) != IFLA_VLAN_QOS_MAPPING) + continue; m = nla_data(attr); vlan_dev_set_ingress_priority(dev, m->to, m->from); } } if (data[IFLA_VLAN_EGRESS_QOS]) { nla_for_each_nested(attr, data[IFLA_VLAN_EGRESS_QOS], rem) { + if (nla_type(attr) != IFLA_VLAN_QOS_MAPPING) + continue; m = nla_data(attr); err = vlan_dev_set_egress_priority(dev, m->from, m->to); if (err) diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index d7d021af1029..2d7b73242958 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1762,6 +1762,10 @@ static void br_ip6_multicast_querier_expired(struct timer_list *t) } #endif +static void br_multicast_query_delay_expired(struct timer_list *t) +{ +} + static void br_multicast_select_own_querier(struct net_bridge_mcast *brmctx, struct br_ip *ip, struct sk_buff *skb) @@ -3198,7 +3202,7 @@ br_multicast_update_query_timer(struct net_bridge_mcast *brmctx, unsigned long max_delay) { if (!timer_pending(&query->timer)) - query->delay_time = jiffies + max_delay; + mod_timer(&query->delay_timer, jiffies + max_delay); mod_timer(&query->timer, jiffies + brmctx->multicast_querier_interval); } @@ -4041,13 +4045,11 @@ void br_multicast_ctx_init(struct net_bridge *br, brmctx->multicast_querier_interval = 255 * HZ; brmctx->multicast_membership_interval = 260 * HZ; - brmctx->ip4_other_query.delay_time = 0; brmctx->ip4_querier.port_ifidx = 0; seqcount_spinlock_init(&brmctx->ip4_querier.seq, &br->multicast_lock); brmctx->multicast_igmp_version = 2; #if IS_ENABLED(CONFIG_IPV6) brmctx->multicast_mld_version = 1; - brmctx->ip6_other_query.delay_time = 0; brmctx->ip6_querier.port_ifidx = 0; seqcount_spinlock_init(&brmctx->ip6_querier.seq, &br->multicast_lock); #endif @@ -4056,6 +4058,8 @@ void br_multicast_ctx_init(struct net_bridge *br, br_ip4_multicast_local_router_expired, 0); timer_setup(&brmctx->ip4_other_query.timer, br_ip4_multicast_querier_expired, 0); + timer_setup(&brmctx->ip4_other_query.delay_timer, + br_multicast_query_delay_expired, 0); timer_setup(&brmctx->ip4_own_query.timer, br_ip4_multicast_query_expired, 0); #if IS_ENABLED(CONFIG_IPV6) @@ -4063,6 +4067,8 @@ void br_multicast_ctx_init(struct net_bridge *br, br_ip6_multicast_local_router_expired, 0); timer_setup(&brmctx->ip6_other_query.timer, br_ip6_multicast_querier_expired, 0); + timer_setup(&brmctx->ip6_other_query.delay_timer, + br_multicast_query_delay_expired, 0); timer_setup(&brmctx->ip6_own_query.timer, br_ip6_multicast_query_expired, 0); #endif @@ -4197,10 +4203,12 @@ static void __br_multicast_stop(struct net_bridge_mcast *brmctx) { del_timer_sync(&brmctx->ip4_mc_router_timer); del_timer_sync(&brmctx->ip4_other_query.timer); + del_timer_sync(&brmctx->ip4_other_query.delay_timer); del_timer_sync(&brmctx->ip4_own_query.timer); #if IS_ENABLED(CONFIG_IPV6) del_timer_sync(&brmctx->ip6_mc_router_timer); del_timer_sync(&brmctx->ip6_other_query.timer); + del_timer_sync(&brmctx->ip6_other_query.delay_timer); del_timer_sync(&brmctx->ip6_own_query.timer); #endif } @@ -4643,13 +4651,15 @@ int br_multicast_set_querier(struct net_bridge_mcast *brmctx, unsigned long val) max_delay = brmctx->multicast_query_response_interval; if (!timer_pending(&brmctx->ip4_other_query.timer)) - brmctx->ip4_other_query.delay_time = jiffies + max_delay; + mod_timer(&brmctx->ip4_other_query.delay_timer, + jiffies + max_delay); br_multicast_start_querier(brmctx, &brmctx->ip4_own_query); #if IS_ENABLED(CONFIG_IPV6) if (!timer_pending(&brmctx->ip6_other_query.timer)) - brmctx->ip6_other_query.delay_time = jiffies + max_delay; + mod_timer(&brmctx->ip6_other_query.delay_timer, + jiffies + max_delay); br_multicast_start_querier(brmctx, &brmctx->ip6_own_query); #endif diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index b0a92c344722..86ea5e6689b5 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -78,7 +78,7 @@ struct bridge_mcast_own_query { /* other querier */ struct bridge_mcast_other_query { struct timer_list timer; - unsigned long delay_time; + struct timer_list delay_timer; }; /* selected querier */ @@ -1159,7 +1159,7 @@ __br_multicast_querier_exists(struct net_bridge_mcast *brmctx, own_querier_enabled = false; } - return time_is_before_jiffies(querier->delay_time) && + return !timer_pending(&querier->delay_timer) && (own_querier_enabled || timer_pending(&querier->timer)); } diff --git a/net/core/dev.c b/net/core/dev.c index f01a9b858347..cb2dab0feee0 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -11551,6 +11551,7 @@ static struct pernet_operations __net_initdata netdev_net_ops = { static void __net_exit default_device_exit_net(struct net *net) { + struct netdev_name_node *name_node, *tmp; struct net_device *dev, *aux; /* * Push all migratable network devices back to the @@ -11573,6 +11574,14 @@ static void __net_exit default_device_exit_net(struct net *net) snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex); if (netdev_name_in_use(&init_net, fb_name)) snprintf(fb_name, IFNAMSIZ, "dev%%d"); + + netdev_for_each_altname_safe(dev, name_node, tmp) + if (netdev_name_in_use(&init_net, name_node->name)) { + netdev_name_node_del(name_node); + synchronize_rcu(); + __netdev_name_node_alt_destroy(name_node); + } + err = dev_change_net_namespace(dev, &init_net, fb_name); if (err) { pr_emerg("%s: failed to move %s to init_net: %d\n", diff --git a/net/core/dev.h b/net/core/dev.h index cf93e188785b..7480b4c84298 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -63,6 +63,9 @@ int dev_change_name(struct net_device *dev, const char *newname); #define netdev_for_each_altname(dev, namenode) \ list_for_each_entry((namenode), &(dev)->name_node->list, list) +#define netdev_for_each_altname_safe(dev, namenode, next) \ + list_for_each_entry_safe((namenode), (next), &(dev)->name_node->list, \ + list) int netdev_name_node_alt_create(struct net_device *dev, const char *name); int netdev_name_node_alt_destroy(struct net_device *dev, const char *name); diff --git a/net/core/filter.c b/net/core/filter.c index 24061f29c9dd..ef3e78b6a39c 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -83,6 +83,7 @@ #include <net/netfilter/nf_conntrack_bpf.h> #include <net/netkit.h> #include <linux/un.h> +#include <net/xdp_sock_drv.h> #include "dev.h" @@ -4092,10 +4093,46 @@ static int bpf_xdp_frags_increase_tail(struct xdp_buff *xdp, int offset) memset(skb_frag_address(frag) + skb_frag_size(frag), 0, offset); skb_frag_size_add(frag, offset); sinfo->xdp_frags_size += offset; + if (rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL) + xsk_buff_get_tail(xdp)->data_end += offset; return 0; } +static void bpf_xdp_shrink_data_zc(struct xdp_buff *xdp, int shrink, + struct xdp_mem_info *mem_info, bool release) +{ + struct xdp_buff *zc_frag = xsk_buff_get_tail(xdp); + + if (release) { + xsk_buff_del_tail(zc_frag); + __xdp_return(NULL, mem_info, false, zc_frag); + } else { + zc_frag->data_end -= shrink; + } +} + +static bool bpf_xdp_shrink_data(struct xdp_buff *xdp, skb_frag_t *frag, + int shrink) +{ + struct xdp_mem_info *mem_info = &xdp->rxq->mem; + bool release = skb_frag_size(frag) == shrink; + + if (mem_info->type == MEM_TYPE_XSK_BUFF_POOL) { + bpf_xdp_shrink_data_zc(xdp, shrink, mem_info, release); + goto out; + } + + if (release) { + struct page *page = skb_frag_page(frag); + + __xdp_return(page_address(page), mem_info, false, NULL); + } + +out: + return release; +} + static int bpf_xdp_frags_shrink_tail(struct xdp_buff *xdp, int offset) { struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); @@ -4110,12 +4147,7 @@ static int bpf_xdp_frags_shrink_tail(struct xdp_buff *xdp, int offset) len_free += shrink; offset -= shrink; - - if (skb_frag_size(frag) == shrink) { - struct page *page = skb_frag_page(frag); - - __xdp_return(page_address(page), &xdp->rxq->mem, - false, NULL); + if (bpf_xdp_shrink_data(xdp, frag, shrink)) { n_frags_free++; } else { skb_frag_size_sub(frag, shrink); diff --git a/net/core/request_sock.c b/net/core/request_sock.c index f35c2e998406..63de5c635842 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -33,9 +33,6 @@ void reqsk_queue_alloc(struct request_sock_queue *queue) { - spin_lock_init(&queue->rskq_lock); - - spin_lock_init(&queue->fastopenq.lock); queue->fastopenq.rskq_rst_head = NULL; queue->fastopenq.rskq_rst_tail = NULL; queue->fastopenq.qlen = 0; diff --git a/net/core/sock.c b/net/core/sock.c index 158dbdebce6a..0a7f46c37f0c 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -107,6 +107,7 @@ #include <linux/interrupt.h> #include <linux/poll.h> #include <linux/tcp.h> +#include <linux/udp.h> #include <linux/init.h> #include <linux/highmem.h> #include <linux/user_namespace.h> @@ -4144,8 +4145,14 @@ bool sk_busy_loop_end(void *p, unsigned long start_time) { struct sock *sk = p; - return !skb_queue_empty_lockless(&sk->sk_receive_queue) || - sk_busy_loop_timeout(sk, start_time); + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) + return true; + + if (sk_is_udp(sk) && + !skb_queue_empty_lockless(&udp_sk(sk)->reader_queue)) + return true; + + return sk_busy_loop_timeout(sk, start_time); } EXPORT_SYMBOL(sk_busy_loop_end); #endif /* CONFIG_NET_RX_BUSY_POLL */ diff --git a/net/devlink/port.c b/net/devlink/port.c index 62e54e152ecf..78592912f657 100644 --- a/net/devlink/port.c +++ b/net/devlink/port.c @@ -674,7 +674,7 @@ static int devlink_port_function_validate(struct devlink_port *devlink_port, return -EOPNOTSUPP; } if (tb[DEVLINK_PORT_FN_ATTR_STATE] && !ops->port_fn_state_set) { - NL_SET_ERR_MSG_ATTR(extack, tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR], + NL_SET_ERR_MSG_ATTR(extack, tb[DEVLINK_PORT_FN_ATTR_STATE], "Function does not support state setting"); return -EOPNOTSUPP; } diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index 7ceb9ac6e730..9d71b66183da 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -308,7 +308,7 @@ static void send_hsr_supervision_frame(struct hsr_port *master, skb = hsr_init_skb(master); if (!skb) { - WARN_ONCE(1, "HSR: Could not send supervision frame\n"); + netdev_warn_once(master->dev, "HSR: Could not send supervision frame\n"); return; } @@ -355,7 +355,7 @@ static void send_prp_supervision_frame(struct hsr_port *master, skb = hsr_init_skb(master); if (!skb) { - WARN_ONCE(1, "PRP: Could not send supervision frame\n"); + netdev_warn_once(master->dev, "PRP: Could not send supervision frame\n"); return; } diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 835f4f9d98d2..4e635dd3d3c8 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -330,6 +330,9 @@ lookup_protocol: if (INET_PROTOSW_REUSE & answer_flags) sk->sk_reuse = SK_CAN_REUSE; + if (INET_PROTOSW_ICSK & answer_flags) + inet_init_csk_locks(sk); + inet = inet_sk(sk); inet_assign_bit(IS_ICSK, sk, INET_PROTOSW_ICSK & answer_flags); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 8e2eb1793685..459af1f89739 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -727,6 +727,10 @@ out: } if (req) reqsk_put(req); + + if (newsk) + inet_init_csk_locks(newsk); + return newsk; out_err: newsk = NULL; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index b06f678b03a1..41537d18eecf 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1287,6 +1287,12 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, if (unlikely(!rt)) return -EFAULT; + cork->fragsize = ip_sk_use_pmtu(sk) ? + dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu); + + if (!inetdev_valid_mtu(cork->fragsize)) + return -ENETUNREACH; + /* * setup for corking. */ @@ -1303,12 +1309,6 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, cork->addr = ipc->addr; } - cork->fragsize = ip_sk_use_pmtu(sk) ? - dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu); - - if (!inetdev_valid_mtu(cork->fragsize)) - return -ENETUNREACH; - cork->gso_size = ipc->gso_size; cork->dst = &rt->dst; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 7aa9dc0e6760..21d2ffa919e9 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -1363,12 +1363,13 @@ e_inval: * ipv4_pktinfo_prepare - transfer some info from rtable to skb * @sk: socket * @skb: buffer + * @drop_dst: if true, drops skb dst * * To support IP_CMSG_PKTINFO option, we store rt_iif and specific * destination in skb->cb[] before dst drop. * This way, receiver doesn't make cache line misses to read rtable. */ -void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb) +void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb, bool drop_dst) { struct in_pktinfo *pktinfo = PKTINFO_SKB_CB(skb); bool prepare = inet_test_bit(PKTINFO, sk) || @@ -1397,7 +1398,8 @@ void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb) pktinfo->ipi_ifindex = 0; pktinfo->ipi_spec_dst.s_addr = 0; } - skb_dst_drop(skb); + if (drop_dst) + skb_dst_drop(skb); } int ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 9d6f59531b3a..362229836510 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1073,7 +1073,7 @@ static int ipmr_cache_report(const struct mr_table *mrt, msg = (struct igmpmsg *)skb_network_header(skb); msg->im_vif = vifi; msg->im_vif_hi = vifi >> 8; - ipv4_pktinfo_prepare(mroute_sk, pkt); + ipv4_pktinfo_prepare(mroute_sk, pkt, false); memcpy(skb->cb, pkt->cb, sizeof(skb->cb)); /* Add our header */ igmp = skb_put(skb, sizeof(struct igmphdr)); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 27da9d7294c0..aea89326c697 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -292,7 +292,7 @@ static int raw_rcv_skb(struct sock *sk, struct sk_buff *skb) /* Charge it to the socket. */ - ipv4_pktinfo_prepare(sk, skb); + ipv4_pktinfo_prepare(sk, skb, true); if (sock_queue_rcv_skb_reason(sk, skb, &reason) < 0) { kfree_skb_reason(skb, reason); return NET_RX_DROP; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 1baa484d2190..7e2481b9eae1 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -722,6 +722,7 @@ void tcp_push(struct sock *sk, int flags, int mss_now, if (!test_bit(TSQ_THROTTLED, &sk->sk_tsq_flags)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAUTOCORKING); set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags); + smp_mb__after_atomic(); } /* It is possible TX completion already happened * before we set TSQ_THROTTLED. @@ -1785,7 +1786,17 @@ static skb_frag_t *skb_advance_to_frag(struct sk_buff *skb, u32 offset_skb, static bool can_map_frag(const skb_frag_t *frag) { - return skb_frag_size(frag) == PAGE_SIZE && !skb_frag_off(frag); + struct page *page; + + if (skb_frag_size(frag) != PAGE_SIZE || skb_frag_off(frag)) + return false; + + page = skb_frag_page(frag); + + if (PageCompound(page) || page->mapping) + return false; + + return true; } static int find_next_mappable_frag(const skb_frag_t *frag, diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 148ffb007969..f631b0a21af4 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2169,7 +2169,7 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) udp_csum_pull_header(skb); - ipv4_pktinfo_prepare(sk, skb); + ipv4_pktinfo_prepare(sk, skb, true); return __udp_queue_rcv_skb(sk, skb); csum_error: diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index 507a8353a6bd..c008d21925d7 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -220,19 +220,26 @@ const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) { EXPORT_SYMBOL_GPL(ipv6_stub); /* IPv6 Wildcard Address and Loopback Address defined by RFC2553 */ -const struct in6_addr in6addr_loopback = IN6ADDR_LOOPBACK_INIT; +const struct in6_addr in6addr_loopback __aligned(BITS_PER_LONG/8) + = IN6ADDR_LOOPBACK_INIT; EXPORT_SYMBOL(in6addr_loopback); -const struct in6_addr in6addr_any = IN6ADDR_ANY_INIT; +const struct in6_addr in6addr_any __aligned(BITS_PER_LONG/8) + = IN6ADDR_ANY_INIT; EXPORT_SYMBOL(in6addr_any); -const struct in6_addr in6addr_linklocal_allnodes = IN6ADDR_LINKLOCAL_ALLNODES_INIT; +const struct in6_addr in6addr_linklocal_allnodes __aligned(BITS_PER_LONG/8) + = IN6ADDR_LINKLOCAL_ALLNODES_INIT; EXPORT_SYMBOL(in6addr_linklocal_allnodes); -const struct in6_addr in6addr_linklocal_allrouters = IN6ADDR_LINKLOCAL_ALLROUTERS_INIT; +const struct in6_addr in6addr_linklocal_allrouters __aligned(BITS_PER_LONG/8) + = IN6ADDR_LINKLOCAL_ALLROUTERS_INIT; EXPORT_SYMBOL(in6addr_linklocal_allrouters); -const struct in6_addr in6addr_interfacelocal_allnodes = IN6ADDR_INTERFACELOCAL_ALLNODES_INIT; +const struct in6_addr in6addr_interfacelocal_allnodes __aligned(BITS_PER_LONG/8) + = IN6ADDR_INTERFACELOCAL_ALLNODES_INIT; EXPORT_SYMBOL(in6addr_interfacelocal_allnodes); -const struct in6_addr in6addr_interfacelocal_allrouters = IN6ADDR_INTERFACELOCAL_ALLROUTERS_INIT; +const struct in6_addr in6addr_interfacelocal_allrouters __aligned(BITS_PER_LONG/8) + = IN6ADDR_INTERFACELOCAL_ALLROUTERS_INIT; EXPORT_SYMBOL(in6addr_interfacelocal_allrouters); -const struct in6_addr in6addr_sitelocal_allrouters = IN6ADDR_SITELOCAL_ALLROUTERS_INIT; +const struct in6_addr in6addr_sitelocal_allrouters __aligned(BITS_PER_LONG/8) + = IN6ADDR_SITELOCAL_ALLROUTERS_INIT; EXPORT_SYMBOL(in6addr_sitelocal_allrouters); static void snmp6_free_dev(struct inet6_dev *idev) diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 13a1833a4df5..959bfd9f6344 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -199,6 +199,9 @@ lookup_protocol: if (INET_PROTOSW_REUSE & answer_flags) sk->sk_reuse = SK_CAN_REUSE; + if (INET_PROTOSW_ICSK & answer_flags) + inet_init_csk_locks(sk); + inet = inet_sk(sk); inet_assign_bit(IS_ICSK, sk, INET_PROTOSW_ICSK & answer_flags); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 46c19bd48990..9bbabf750a21 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -796,8 +796,8 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, struct sk_buff *skb), bool log_ecn_err) { - const struct ipv6hdr *ipv6h = ipv6_hdr(skb); - int err; + const struct ipv6hdr *ipv6h; + int nh, err; if ((!(tpi->flags & TUNNEL_CSUM) && (tunnel->parms.i_flags & TUNNEL_CSUM)) || @@ -829,7 +829,6 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, goto drop; } - ipv6h = ipv6_hdr(skb); skb->protocol = eth_type_trans(skb, tunnel->dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); } else { @@ -837,7 +836,23 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, skb_reset_mac_header(skb); } + /* Save offset of outer header relative to skb->head, + * because we are going to reset the network header to the inner header + * and might change skb->head. + */ + nh = skb_network_header(skb) - skb->head; + skb_reset_network_header(skb); + + if (!pskb_inet_may_pull(skb)) { + DEV_STATS_INC(tunnel->dev, rx_length_errors); + DEV_STATS_INC(tunnel->dev, rx_errors); + goto drop; + } + + /* Get the outer header. */ + ipv6h = (struct ipv6hdr *)(skb->head + nh); + memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); __skb_tunnel_rx(skb, tunnel->dev, tunnel->net); diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 9b06c380866b..fde1140d899e 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -226,6 +226,8 @@ static int llc_ui_release(struct socket *sock) } netdev_put(llc->dev, &llc->dev_tracker); sock_put(sk); + sock_orphan(sk); + sock->sk = NULL; llc_sk_free(sk); out: return 0; @@ -928,14 +930,15 @@ copy_uaddr: */ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { + DECLARE_SOCKADDR(struct sockaddr_llc *, addr, msg->msg_name); struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); - DECLARE_SOCKADDR(struct sockaddr_llc *, addr, msg->msg_name); int flags = msg->msg_flags; int noblock = flags & MSG_DONTWAIT; + int rc = -EINVAL, copied = 0, hdrlen, hh_len; struct sk_buff *skb = NULL; + struct net_device *dev; size_t size = 0; - int rc = -EINVAL, copied = 0, hdrlen; dprintk("%s: sending from %02X to %02X\n", __func__, llc->laddr.lsap, llc->daddr.lsap); @@ -955,22 +958,29 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (rc) goto out; } - hdrlen = llc->dev->hard_header_len + llc_ui_header_len(sk, addr); + dev = llc->dev; + hh_len = LL_RESERVED_SPACE(dev); + hdrlen = llc_ui_header_len(sk, addr); size = hdrlen + len; - if (size > llc->dev->mtu) - size = llc->dev->mtu; + size = min_t(size_t, size, READ_ONCE(dev->mtu)); copied = size - hdrlen; rc = -EINVAL; if (copied < 0) goto out; release_sock(sk); - skb = sock_alloc_send_skb(sk, size, noblock, &rc); + skb = sock_alloc_send_skb(sk, hh_len + size, noblock, &rc); lock_sock(sk); if (!skb) goto out; - skb->dev = llc->dev; + if (sock_flag(sk, SOCK_ZAPPED) || + llc->dev != dev || + hdrlen != llc_ui_header_len(sk, addr) || + hh_len != LL_RESERVED_SPACE(dev) || + size > READ_ONCE(dev->mtu)) + goto out; + skb->dev = dev; skb->protocol = llc_proto_type(addr->sllc_arphrd); - skb_reserve(skb, hdrlen); + skb_reserve(skb, hh_len + hdrlen); rc = memcpy_from_msg(skb_put(skb, copied), msg, copied); if (rc) goto out; diff --git a/net/llc/llc_core.c b/net/llc/llc_core.c index 6e387aadffce..4f16d9c88350 100644 --- a/net/llc/llc_core.c +++ b/net/llc/llc_core.c @@ -135,22 +135,15 @@ static struct packet_type llc_packet_type __read_mostly = { .func = llc_rcv, }; -static struct packet_type llc_tr_packet_type __read_mostly = { - .type = cpu_to_be16(ETH_P_TR_802_2), - .func = llc_rcv, -}; - static int __init llc_init(void) { dev_add_pack(&llc_packet_type); - dev_add_pack(&llc_tr_packet_type); return 0; } static void __exit llc_exit(void) { dev_remove_pack(&llc_packet_type); - dev_remove_pack(&llc_tr_packet_type); } module_init(llc_init); diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig index cb0291decf2e..13438cc0a6b1 100644 --- a/net/mac80211/Kconfig +++ b/net/mac80211/Kconfig @@ -62,7 +62,6 @@ config MAC80211_KUNIT_TEST depends on KUNIT depends on MAC80211 default KUNIT_ALL_TESTS - depends on !KERNEL_6_2 help Enable this option to test mac80211 internals with kunit. diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index bf1adcd96b41..4391d8dd634b 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -404,7 +404,10 @@ void sta_info_free(struct ieee80211_local *local, struct sta_info *sta) int i; for (i = 0; i < ARRAY_SIZE(sta->link); i++) { - if (!(sta->sta.valid_links & BIT(i))) + struct link_sta_info *link_sta; + + link_sta = rcu_access_pointer(sta->link[i]); + if (!link_sta) continue; sta_remove_link(sta, i, false); @@ -910,6 +913,8 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) if (ieee80211_vif_is_mesh(&sdata->vif)) mesh_accept_plinks_update(sdata); + ieee80211_check_fast_xmit(sta); + return 0; out_remove: if (sta->sta.valid_links) diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 314998fdb1a5..68a48abc7287 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -3048,7 +3048,7 @@ void ieee80211_check_fast_xmit(struct sta_info *sta) sdata->vif.type == NL80211_IFTYPE_STATION) goto out; - if (!test_sta_flag(sta, WLAN_STA_AUTHORIZED)) + if (!test_sta_flag(sta, WLAN_STA_AUTHORIZED) || !sta->uploaded) goto out; if (test_sta_flag(sta, WLAN_STA_PS_STA) || diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 3ed4709a7509..028e8b473626 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2314,9 +2314,6 @@ bool __mptcp_retransmit_pending_data(struct sock *sk) if (__mptcp_check_fallback(msk)) return false; - if (tcp_rtx_and_write_queues_empty(sk)) - return false; - /* the closing socket has some data untransmitted and/or unacked: * some data in the mptcp rtx queue has not really xmitted yet. * keep it simple and re-inject the whole mptcp level rtx queue diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h index 21f7860e8fa1..cb48a2b9cb9f 100644 --- a/net/netfilter/ipset/ip_set_bitmap_gen.h +++ b/net/netfilter/ipset/ip_set_bitmap_gen.h @@ -30,6 +30,7 @@ #define mtype_del IPSET_TOKEN(MTYPE, _del) #define mtype_list IPSET_TOKEN(MTYPE, _list) #define mtype_gc IPSET_TOKEN(MTYPE, _gc) +#define mtype_cancel_gc IPSET_TOKEN(MTYPE, _cancel_gc) #define mtype MTYPE #define get_ext(set, map, id) ((map)->extensions + ((set)->dsize * (id))) @@ -59,9 +60,6 @@ mtype_destroy(struct ip_set *set) { struct mtype *map = set->data; - if (SET_WITH_TIMEOUT(set)) - del_timer_sync(&map->gc); - if (set->dsize && set->extensions & IPSET_EXT_DESTROY) mtype_ext_cleanup(set); ip_set_free(map->members); @@ -290,6 +288,15 @@ mtype_gc(struct timer_list *t) add_timer(&map->gc); } +static void +mtype_cancel_gc(struct ip_set *set) +{ + struct mtype *map = set->data; + + if (SET_WITH_TIMEOUT(set)) + del_timer_sync(&map->gc); +} + static const struct ip_set_type_variant mtype = { .kadt = mtype_kadt, .uadt = mtype_uadt, @@ -303,6 +310,7 @@ static const struct ip_set_type_variant mtype = { .head = mtype_head, .list = mtype_list, .same_set = mtype_same_set, + .cancel_gc = mtype_cancel_gc, }; #endif /* __IP_SET_BITMAP_IP_GEN_H */ diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 4c133e06be1d..bcaad9c009fe 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1182,6 +1182,14 @@ ip_set_destroy_set(struct ip_set *set) kfree(set); } +static void +ip_set_destroy_set_rcu(struct rcu_head *head) +{ + struct ip_set *set = container_of(head, struct ip_set, rcu); + + ip_set_destroy_set(set); +} + static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const attr[]) { @@ -1193,8 +1201,6 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, if (unlikely(protocol_min_failed(attr))) return -IPSET_ERR_PROTOCOL; - /* Must wait for flush to be really finished in list:set */ - rcu_barrier(); /* Commands are serialized and references are * protected by the ip_set_ref_lock. @@ -1206,8 +1212,10 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, * counter, so if it's already zero, we can proceed * without holding the lock. */ - read_lock_bh(&ip_set_ref_lock); if (!attr[IPSET_ATTR_SETNAME]) { + /* Must wait for flush to be really finished in list:set */ + rcu_barrier(); + read_lock_bh(&ip_set_ref_lock); for (i = 0; i < inst->ip_set_max; i++) { s = ip_set(inst, i); if (s && (s->ref || s->ref_netlink)) { @@ -1221,6 +1229,8 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, s = ip_set(inst, i); if (s) { ip_set(inst, i) = NULL; + /* Must cancel garbage collectors */ + s->variant->cancel_gc(s); ip_set_destroy_set(s); } } @@ -1228,6 +1238,9 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, inst->is_destroyed = false; } else { u32 flags = flag_exist(info->nlh); + u16 features = 0; + + read_lock_bh(&ip_set_ref_lock); s = find_set_and_id(inst, nla_data(attr[IPSET_ATTR_SETNAME]), &i); if (!s) { @@ -1238,10 +1251,16 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, ret = -IPSET_ERR_BUSY; goto out; } + features = s->type->features; ip_set(inst, i) = NULL; read_unlock_bh(&ip_set_ref_lock); - - ip_set_destroy_set(s); + if (features & IPSET_TYPE_NAME) { + /* Must wait for flush to be really finished */ + rcu_barrier(); + } + /* Must cancel garbage collectors */ + s->variant->cancel_gc(s); + call_rcu(&s->rcu, ip_set_destroy_set_rcu); } return 0; out: @@ -1394,9 +1413,6 @@ static int ip_set_swap(struct sk_buff *skb, const struct nfnl_info *info, ip_set(inst, to_id) = from; write_unlock_bh(&ip_set_ref_lock); - /* Make sure all readers of the old set pointers are completed. */ - synchronize_rcu(); - return 0; } @@ -2409,8 +2425,11 @@ ip_set_fini(void) { nf_unregister_sockopt(&so_set); nfnetlink_subsys_unregister(&ip_set_netlink_subsys); - unregister_pernet_subsys(&ip_set_net_ops); + + /* Wait for call_rcu() in destroy */ + rcu_barrier(); + pr_debug("these are the famous last words\n"); } diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index cbf80da9a01c..1136510521a8 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -222,6 +222,7 @@ static const union nf_inet_addr zeromask = {}; #undef mtype_gc_do #undef mtype_gc #undef mtype_gc_init +#undef mtype_cancel_gc #undef mtype_variant #undef mtype_data_match @@ -266,6 +267,7 @@ static const union nf_inet_addr zeromask = {}; #define mtype_gc_do IPSET_TOKEN(MTYPE, _gc_do) #define mtype_gc IPSET_TOKEN(MTYPE, _gc) #define mtype_gc_init IPSET_TOKEN(MTYPE, _gc_init) +#define mtype_cancel_gc IPSET_TOKEN(MTYPE, _cancel_gc) #define mtype_variant IPSET_TOKEN(MTYPE, _variant) #define mtype_data_match IPSET_TOKEN(MTYPE, _data_match) @@ -450,9 +452,6 @@ mtype_destroy(struct ip_set *set) struct htype *h = set->data; struct list_head *l, *lt; - if (SET_WITH_TIMEOUT(set)) - cancel_delayed_work_sync(&h->gc.dwork); - mtype_ahash_destroy(set, ipset_dereference_nfnl(h->table), true); list_for_each_safe(l, lt, &h->ad) { list_del(l); @@ -599,6 +598,15 @@ mtype_gc_init(struct htable_gc *gc) queue_delayed_work(system_power_efficient_wq, &gc->dwork, HZ); } +static void +mtype_cancel_gc(struct ip_set *set) +{ + struct htype *h = set->data; + + if (SET_WITH_TIMEOUT(set)) + cancel_delayed_work_sync(&h->gc.dwork); +} + static int mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, struct ip_set_ext *mext, u32 flags); @@ -1441,6 +1449,7 @@ static const struct ip_set_type_variant mtype_variant = { .uref = mtype_uref, .resize = mtype_resize, .same_set = mtype_same_set, + .cancel_gc = mtype_cancel_gc, .region_lock = true, }; diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index e162636525cf..6c3f28bc59b3 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -426,9 +426,6 @@ list_set_destroy(struct ip_set *set) struct list_set *map = set->data; struct set_elem *e, *n; - if (SET_WITH_TIMEOUT(set)) - timer_shutdown_sync(&map->gc); - list_for_each_entry_safe(e, n, &map->members, list) { list_del(&e->list); ip_set_put_byindex(map->net, e->id); @@ -545,6 +542,15 @@ list_set_same_set(const struct ip_set *a, const struct ip_set *b) a->extensions == b->extensions; } +static void +list_set_cancel_gc(struct ip_set *set) +{ + struct list_set *map = set->data; + + if (SET_WITH_TIMEOUT(set)) + timer_shutdown_sync(&map->gc); +} + static const struct ip_set_type_variant set_variant = { .kadt = list_set_kadt, .uadt = list_set_uadt, @@ -558,6 +564,7 @@ static const struct ip_set_type_variant set_variant = { .head = list_set_head, .list = list_set_list, .same_set = list_set_same_set, + .cancel_gc = list_set_cancel_gc, }; static void diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index c6bd533983c1..4cc97f971264 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -283,7 +283,7 @@ sctp_new(struct nf_conn *ct, const struct sk_buff *skb, pr_debug("Setting vtag %x for secondary conntrack\n", sh->vtag); ct->proto.sctp.vtag[IP_CT_DIR_ORIGINAL] = sh->vtag; - } else { + } else if (sch->type == SCTP_CID_SHUTDOWN_ACK) { /* If it is a shutdown ack OOTB packet, we expect a return shutdown complete, otherwise an ABORT Sec 8.4 (5) and (8) */ pr_debug("Setting vtag %x for new conn OOTB\n", diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index e573be5afde7..ae493599a3ef 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -457,7 +457,8 @@ static void tcp_init_sender(struct ip_ct_tcp_state *sender, const struct sk_buff *skb, unsigned int dataoff, const struct tcphdr *tcph, - u32 end, u32 win) + u32 end, u32 win, + enum ip_conntrack_dir dir) { /* SYN-ACK in reply to a SYN * or SYN from reply direction in simultaneous open. @@ -471,7 +472,8 @@ static void tcp_init_sender(struct ip_ct_tcp_state *sender, * Both sides must send the Window Scale option * to enable window scaling in either direction. */ - if (!(sender->flags & IP_CT_TCP_FLAG_WINDOW_SCALE && + if (dir == IP_CT_DIR_REPLY && + !(sender->flags & IP_CT_TCP_FLAG_WINDOW_SCALE && receiver->flags & IP_CT_TCP_FLAG_WINDOW_SCALE)) { sender->td_scale = 0; receiver->td_scale = 0; @@ -542,7 +544,7 @@ tcp_in_window(struct nf_conn *ct, enum ip_conntrack_dir dir, if (tcph->syn) { tcp_init_sender(sender, receiver, skb, dataoff, tcph, - end, win); + end, win, dir); if (!tcph->ack) /* Simultaneous open */ return NFCT_TCP_ACCEPT; @@ -585,7 +587,7 @@ tcp_in_window(struct nf_conn *ct, enum ip_conntrack_dir dir, */ tcp_init_sender(sender, receiver, skb, dataoff, tcph, - end, win); + end, win, dir); if (dir == IP_CT_DIR_REPLY && !tcph->ack) return NFCT_TCP_ACCEPT; diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index 8cc52d2bd31b..e16f158388bb 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -193,11 +193,12 @@ void nf_logger_put(int pf, enum nf_log_type type) return; } - BUG_ON(loggers[pf][type] == NULL); - rcu_read_lock(); logger = rcu_dereference(loggers[pf][type]); - module_put(logger->me); + if (!logger) + WARN_ON_ONCE(1); + else + module_put(logger->me); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(nf_logger_put); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 4b55533ce5ca..fc016befb46f 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -24,6 +24,7 @@ #include <net/sock.h> #define NFT_MODULE_AUTOLOAD_LIMIT (MODULE_NAME_LEN - sizeof("nft-expr-255-")) +#define NFT_SET_MAX_ANONLEN 16 unsigned int nf_tables_net_id __read_mostly; @@ -4413,6 +4414,9 @@ static int nf_tables_set_alloc_name(struct nft_ctx *ctx, struct nft_set *set, if (p[1] != 'd' || strchr(p + 2, '%')) return -EINVAL; + if (strnlen(name, NFT_SET_MAX_ANONLEN) >= NFT_SET_MAX_ANONLEN) + return -EINVAL; + inuse = (unsigned long *)get_zeroed_page(GFP_KERNEL); if (inuse == NULL) return -ENOMEM; @@ -7547,11 +7551,15 @@ nla_put_failure: return -1; } -static const struct nft_object_type *__nft_obj_type_get(u32 objtype) +static const struct nft_object_type *__nft_obj_type_get(u32 objtype, u8 family) { const struct nft_object_type *type; list_for_each_entry(type, &nf_tables_objects, list) { + if (type->family != NFPROTO_UNSPEC && + type->family != family) + continue; + if (objtype == type->type) return type; } @@ -7559,11 +7567,11 @@ static const struct nft_object_type *__nft_obj_type_get(u32 objtype) } static const struct nft_object_type * -nft_obj_type_get(struct net *net, u32 objtype) +nft_obj_type_get(struct net *net, u32 objtype, u8 family) { const struct nft_object_type *type; - type = __nft_obj_type_get(objtype); + type = __nft_obj_type_get(objtype, family); if (type != NULL && try_module_get(type->owner)) return type; @@ -7656,7 +7664,7 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info, if (info->nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; - type = __nft_obj_type_get(objtype); + type = __nft_obj_type_get(objtype, family); if (WARN_ON_ONCE(!type)) return -ENOENT; @@ -7670,7 +7678,7 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info, if (!nft_use_inc(&table->use)) return -EMFILE; - type = nft_obj_type_get(net, objtype); + type = nft_obj_type_get(net, objtype, family); if (IS_ERR(type)) { err = PTR_ERR(type); goto err_type; @@ -10988,16 +10996,10 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, data->verdict.code = ntohl(nla_get_be32(tb[NFTA_VERDICT_CODE])); switch (data->verdict.code) { - default: - switch (data->verdict.code & NF_VERDICT_MASK) { - case NF_ACCEPT: - case NF_DROP: - case NF_QUEUE: - break; - default: - return -EINVAL; - } - fallthrough; + case NF_ACCEPT: + case NF_DROP: + case NF_QUEUE: + break; case NFT_CONTINUE: case NFT_BREAK: case NFT_RETURN: @@ -11032,6 +11034,8 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, data->verdict.chain = chain; break; + default: + return -EINVAL; } desc->len = sizeof(data->verdict); diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index 680fe557686e..274b6f7e6bb5 100644 --- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -357,9 +357,10 @@ static int nf_tables_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct nft_base_chain *basechain; struct nftables_pernet *nft_net; - struct nft_table *table; struct nft_chain *chain, *nr; + struct nft_table *table; struct nft_ctx ctx = { .net = dev_net(dev), }; @@ -371,7 +372,8 @@ static int nf_tables_netdev_event(struct notifier_block *this, nft_net = nft_pernet(ctx.net); mutex_lock(&nft_net->commit_mutex); list_for_each_entry(table, &nft_net->tables, list) { - if (table->family != NFPROTO_NETDEV) + if (table->family != NFPROTO_NETDEV && + table->family != NFPROTO_INET) continue; ctx.family = table->family; @@ -380,6 +382,11 @@ static int nf_tables_netdev_event(struct notifier_block *this, if (!nft_is_base_chain(chain)) continue; + basechain = nft_base_chain(chain); + if (table->family == NFPROTO_INET && + basechain->ops.hooknum != NF_INET_INGRESS) + continue; + ctx.chain = chain; nft_netdev_event(event, dev, &ctx); } diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 5284cd2ad532..f0eeda97bfcd 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -350,6 +350,12 @@ static int nft_target_validate(const struct nft_ctx *ctx, unsigned int hook_mask = 0; int ret; + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_BRIDGE && + ctx->family != NFPROTO_ARP) + return -EOPNOTSUPP; + if (nft_is_base_chain(ctx->chain)) { const struct nft_base_chain *basechain = nft_base_chain(ctx->chain); @@ -595,6 +601,12 @@ static int nft_match_validate(const struct nft_ctx *ctx, unsigned int hook_mask = 0; int ret; + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_BRIDGE && + ctx->family != NFPROTO_ARP) + return -EOPNOTSUPP; + if (nft_is_base_chain(ctx->chain)) { const struct nft_base_chain *basechain = nft_base_chain(ctx->chain); diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 86bb9d7797d9..aac98a3c966e 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -1250,7 +1250,31 @@ static int nft_ct_expect_obj_init(const struct nft_ctx *ctx, if (tb[NFTA_CT_EXPECT_L3PROTO]) priv->l3num = ntohs(nla_get_be16(tb[NFTA_CT_EXPECT_L3PROTO])); + switch (priv->l3num) { + case NFPROTO_IPV4: + case NFPROTO_IPV6: + if (priv->l3num != ctx->family) + return -EINVAL; + + fallthrough; + case NFPROTO_INET: + break; + default: + return -EOPNOTSUPP; + } + priv->l4proto = nla_get_u8(tb[NFTA_CT_EXPECT_L4PROTO]); + switch (priv->l4proto) { + case IPPROTO_TCP: + case IPPROTO_UDP: + case IPPROTO_UDPLITE: + case IPPROTO_DCCP: + case IPPROTO_SCTP: + break; + default: + return -EOPNOTSUPP; + } + priv->dport = nla_get_be16(tb[NFTA_CT_EXPECT_DPORT]); priv->timeout = nla_get_u32(tb[NFTA_CT_EXPECT_TIMEOUT]); priv->size = nla_get_u8(tb[NFTA_CT_EXPECT_SIZE]); diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index ab3362c483b4..397351fa4d5f 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -384,6 +384,11 @@ static int nft_flow_offload_validate(const struct nft_ctx *ctx, { unsigned int hook_mask = (1 << NF_INET_FORWARD); + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET) + return -EOPNOTSUPP; + return nft_chain_validate_hooks(ctx->chain, hook_mask); } diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c index 79039afde34e..cefa25e0dbb0 100644 --- a/net/netfilter/nft_limit.c +++ b/net/netfilter/nft_limit.c @@ -58,17 +58,19 @@ static inline bool nft_limit_eval(struct nft_limit_priv *priv, u64 cost) static int nft_limit_init(struct nft_limit_priv *priv, const struct nlattr * const tb[], bool pkts) { + u64 unit, tokens, rate_with_burst; bool invert = false; - u64 unit, tokens; if (tb[NFTA_LIMIT_RATE] == NULL || tb[NFTA_LIMIT_UNIT] == NULL) return -EINVAL; priv->rate = be64_to_cpu(nla_get_be64(tb[NFTA_LIMIT_RATE])); + if (priv->rate == 0) + return -EINVAL; + unit = be64_to_cpu(nla_get_be64(tb[NFTA_LIMIT_UNIT])); - priv->nsecs = unit * NSEC_PER_SEC; - if (priv->rate == 0 || priv->nsecs < unit) + if (check_mul_overflow(unit, NSEC_PER_SEC, &priv->nsecs)) return -EOVERFLOW; if (tb[NFTA_LIMIT_BURST]) @@ -77,18 +79,25 @@ static int nft_limit_init(struct nft_limit_priv *priv, if (pkts && priv->burst == 0) priv->burst = NFT_LIMIT_PKT_BURST_DEFAULT; - if (priv->rate + priv->burst < priv->rate) + if (check_add_overflow(priv->rate, priv->burst, &rate_with_burst)) return -EOVERFLOW; if (pkts) { - tokens = div64_u64(priv->nsecs, priv->rate) * priv->burst; + u64 tmp = div64_u64(priv->nsecs, priv->rate); + + if (check_mul_overflow(tmp, priv->burst, &tokens)) + return -EOVERFLOW; } else { + u64 tmp; + /* The token bucket size limits the number of tokens can be * accumulated. tokens_max specifies the bucket size. * tokens_max = unit * (rate + burst) / rate. */ - tokens = div64_u64(priv->nsecs * (priv->rate + priv->burst), - priv->rate); + if (check_mul_overflow(priv->nsecs, rate_with_burst, &tmp)) + return -EOVERFLOW; + + tokens = div64_u64(tmp, priv->rate); } if (tb[NFTA_LIMIT_FLAGS]) { diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index 583885ce7232..808f5802c270 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -143,6 +143,11 @@ static int nft_nat_validate(const struct nft_ctx *ctx, struct nft_nat *priv = nft_expr_priv(expr); int err; + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET) + return -EOPNOTSUPP; + err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT); if (err < 0) return err; diff --git a/net/netfilter/nft_rt.c b/net/netfilter/nft_rt.c index 35a2c28caa60..24d977138572 100644 --- a/net/netfilter/nft_rt.c +++ b/net/netfilter/nft_rt.c @@ -166,6 +166,11 @@ static int nft_rt_validate(const struct nft_ctx *ctx, const struct nft_expr *exp const struct nft_rt *priv = nft_expr_priv(expr); unsigned int hooks; + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET) + return -EOPNOTSUPP; + switch (priv->key) { case NFT_RT_NEXTHOP4: case NFT_RT_NEXTHOP6: diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c index 9ed85be79452..f30163e2ca62 100644 --- a/net/netfilter/nft_socket.c +++ b/net/netfilter/nft_socket.c @@ -242,6 +242,11 @@ static int nft_socket_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nft_data **data) { + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET) + return -EOPNOTSUPP; + return nft_chain_validate_hooks(ctx->chain, (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN) | diff --git a/net/netfilter/nft_synproxy.c b/net/netfilter/nft_synproxy.c index 13da882669a4..1d737f89dfc1 100644 --- a/net/netfilter/nft_synproxy.c +++ b/net/netfilter/nft_synproxy.c @@ -186,7 +186,6 @@ static int nft_synproxy_do_init(const struct nft_ctx *ctx, break; #endif case NFPROTO_INET: - case NFPROTO_BRIDGE: err = nf_synproxy_ipv4_init(snet, ctx->net); if (err) goto nf_ct_failure; @@ -219,7 +218,6 @@ static void nft_synproxy_do_destroy(const struct nft_ctx *ctx) break; #endif case NFPROTO_INET: - case NFPROTO_BRIDGE: nf_synproxy_ipv4_fini(snet, ctx->net); nf_synproxy_ipv6_fini(snet, ctx->net); break; @@ -253,6 +251,11 @@ static int nft_synproxy_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nft_data **data) { + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET) + return -EOPNOTSUPP; + return nft_chain_validate_hooks(ctx->chain, (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD)); } diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c index ae15cd693f0e..71412adb73d4 100644 --- a/net/netfilter/nft_tproxy.c +++ b/net/netfilter/nft_tproxy.c @@ -316,6 +316,11 @@ static int nft_tproxy_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nft_data **data) { + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET) + return -EOPNOTSUPP; + return nft_chain_validate_hooks(ctx->chain, 1 << NF_INET_PRE_ROUTING); } diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c index 9f21953c7433..f735d79d8be5 100644 --- a/net/netfilter/nft_tunnel.c +++ b/net/netfilter/nft_tunnel.c @@ -713,6 +713,7 @@ static const struct nft_object_ops nft_tunnel_obj_ops = { static struct nft_object_type nft_tunnel_obj_type __read_mostly = { .type = NFT_OBJECT_TUNNEL, + .family = NFPROTO_NETDEV, .ops = &nft_tunnel_obj_ops, .maxattr = NFTA_TUNNEL_KEY_MAX, .policy = nft_tunnel_key_policy, diff --git a/net/netfilter/nft_xfrm.c b/net/netfilter/nft_xfrm.c index 452f8587adda..1c866757db55 100644 --- a/net/netfilter/nft_xfrm.c +++ b/net/netfilter/nft_xfrm.c @@ -235,6 +235,11 @@ static int nft_xfrm_validate(const struct nft_ctx *ctx, const struct nft_expr *e const struct nft_xfrm *priv = nft_expr_priv(expr); unsigned int hooks; + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET) + return -EOPNOTSUPP; + switch (priv->dir) { case XFRM_POLICY_IN: hooks = (1 << NF_INET_FORWARD) | diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 4ed8ffd58ff3..9c962347cf85 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -374,7 +374,7 @@ static void netlink_skb_destructor(struct sk_buff *skb) if (is_vmalloc_addr(skb->head)) { if (!skb->cloned || !atomic_dec_return(&(skb_shinfo(skb)->dataref))) - vfree(skb->head); + vfree_atomic(skb->head); skb->head = NULL; } diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 97348cedb16b..cdad47b140fa 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -1208,6 +1208,10 @@ void nci_free_device(struct nci_dev *ndev) { nfc_free_device(ndev->nfc_dev); nci_hci_deallocate(ndev); + + /* drop partial rx data packet if present */ + if (ndev->rx_data_reassembly) + kfree_skb(ndev->rx_data_reassembly); kfree(ndev); } EXPORT_SYMBOL(nci_free_device); diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index 01c4cdfef45d..8435a20968ef 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -419,7 +419,7 @@ static int rds_recv_track_latency(struct rds_sock *rs, sockptr_t optval, rs->rs_rx_traces = trace.rx_traces; for (i = 0; i < rs->rs_rx_traces; i++) { - if (trace.rx_trace_pos[i] > RDS_MSG_RX_DGRAM_TRACE_MAX) { + if (trace.rx_trace_pos[i] >= RDS_MSG_RX_DGRAM_TRACE_MAX) { rs->rs_rx_traces = 0; return -EFAULT; } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 92a12e3d0fe6..ff3d396a65aa 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1560,6 +1560,9 @@ tcf_block_playback_offloads(struct tcf_block *block, flow_setup_cb_t *cb, chain_prev = chain, chain = __tcf_get_next_chain(block, chain), tcf_chain_put(chain_prev)) { + if (chain->tmplt_ops && add) + chain->tmplt_ops->tmplt_reoffload(chain, true, cb, + cb_priv); for (tp = __tcf_get_next_proto(chain, NULL); tp; tp_prev = tp, tp = __tcf_get_next_proto(chain, tp), @@ -1575,6 +1578,9 @@ tcf_block_playback_offloads(struct tcf_block *block, flow_setup_cb_t *cb, goto err_playback_remove; } } + if (chain->tmplt_ops && !add) + chain->tmplt_ops->tmplt_reoffload(chain, false, cb, + cb_priv); } return 0; @@ -3000,7 +3006,8 @@ static int tc_chain_tmplt_add(struct tcf_chain *chain, struct net *net, ops = tcf_proto_lookup_ops(name, true, extack); if (IS_ERR(ops)) return PTR_ERR(ops); - if (!ops->tmplt_create || !ops->tmplt_destroy || !ops->tmplt_dump) { + if (!ops->tmplt_create || !ops->tmplt_destroy || !ops->tmplt_dump || + !ops->tmplt_reoffload) { NL_SET_ERR_MSG(extack, "Chain templates are not supported with specified classifier"); module_put(ops->owner); return -EOPNOTSUPP; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index e5314a31f75a..efb9d2811b73 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -2721,6 +2721,28 @@ static void fl_tmplt_destroy(void *tmplt_priv) kfree(tmplt); } +static void fl_tmplt_reoffload(struct tcf_chain *chain, bool add, + flow_setup_cb_t *cb, void *cb_priv) +{ + struct fl_flow_tmplt *tmplt = chain->tmplt_priv; + struct flow_cls_offload cls_flower = {}; + + cls_flower.rule = flow_rule_alloc(0); + if (!cls_flower.rule) + return; + + cls_flower.common.chain_index = chain->index; + cls_flower.command = add ? FLOW_CLS_TMPLT_CREATE : + FLOW_CLS_TMPLT_DESTROY; + cls_flower.cookie = (unsigned long) tmplt; + cls_flower.rule->match.dissector = &tmplt->dissector; + cls_flower.rule->match.mask = &tmplt->mask; + cls_flower.rule->match.key = &tmplt->dummy_key; + + cb(TC_SETUP_CLSFLOWER, &cls_flower, cb_priv); + kfree(cls_flower.rule); +} + static int fl_dump_key_val(struct sk_buff *skb, void *val, int val_type, void *mask, int mask_type, int len) @@ -3628,6 +3650,7 @@ static struct tcf_proto_ops cls_fl_ops __read_mostly = { .bind_class = fl_bind_class, .tmplt_create = fl_tmplt_create, .tmplt_destroy = fl_tmplt_destroy, + .tmplt_reoffload = fl_tmplt_reoffload, .tmplt_dump = fl_tmplt_dump, .get_exts = fl_get_exts, .owner = THIS_MODULE, diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 95cc95458e2d..e4c858411207 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -1877,9 +1877,15 @@ static bool smcd_lgr_match(struct smc_link_group *lgr, struct smcd_dev *smcismdev, struct smcd_gid *peer_gid) { - return lgr->peer_gid.gid == peer_gid->gid && lgr->smcd == smcismdev && - smc_ism_is_virtual(smcismdev) ? - (lgr->peer_gid.gid_ext == peer_gid->gid_ext) : 1; + if (lgr->peer_gid.gid != peer_gid->gid || + lgr->smcd != smcismdev) + return false; + + if (smc_ism_is_virtual(smcismdev) && + lgr->peer_gid.gid_ext != peer_gid->gid_ext) + return false; + + return true; } /* create a new SMC connection (and a new link group if necessary) */ diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index 52f7c4f1e767..5a33908015f3 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -164,7 +164,7 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb, } if (smc_conn_lgr_valid(&smc->conn) && smc->conn.lgr->is_smcd && (req->diag_ext & (1 << (SMC_DIAG_DMBINFO - 1))) && - !list_empty(&smc->conn.lgr->list)) { + !list_empty(&smc->conn.lgr->list) && smc->conn.rmb_desc) { struct smc_connection *conn = &smc->conn; struct smcd_diag_dmbinfo dinfo; struct smcd_dev *smcd = conn->lgr->smcd; diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index bfb2f78523a8..545017a3daa4 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -717,12 +717,12 @@ static int svc_udp_sendto(struct svc_rqst *rqstp) ARRAY_SIZE(rqstp->rq_bvec), xdr); iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, rqstp->rq_bvec, - count, 0); + count, rqstp->rq_res.len); err = sock_sendmsg(svsk->sk_sock, &msg); if (err == -ECONNREFUSED) { /* ICMP error on earlier request. */ iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, rqstp->rq_bvec, - count, 0); + count, rqstp->rq_res.len); err = sock_sendmsg(svsk->sk_sock, &msg); } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index ac1f2bc18fc9..30b178ebba60 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1344,13 +1344,11 @@ static void unix_state_double_lock(struct sock *sk1, struct sock *sk2) unix_state_lock(sk1); return; } - if (sk1 < sk2) { - unix_state_lock(sk1); - unix_state_lock_nested(sk2); - } else { - unix_state_lock(sk2); - unix_state_lock_nested(sk1); - } + if (sk1 > sk2) + swap(sk1, sk2); + + unix_state_lock(sk1); + unix_state_lock_nested(sk2, U_LOCK_SECOND); } static void unix_state_double_unlock(struct sock *sk1, struct sock *sk2) @@ -1591,7 +1589,7 @@ restart: goto out_unlock; } - unix_state_lock_nested(sk); + unix_state_lock_nested(sk, U_LOCK_SECOND); if (sk->sk_state != st) { unix_state_unlock(sk); diff --git a/net/unix/diag.c b/net/unix/diag.c index bec09a3a1d44..be19827eca36 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -84,7 +84,7 @@ static int sk_diag_dump_icons(struct sock *sk, struct sk_buff *nlskb) * queue lock. With the other's queue locked it's * OK to lock the state. */ - unix_state_lock_nested(req); + unix_state_lock_nested(req, U_LOCK_DIAG); peer = unix_sk(req)->peer; buf[i++] = (peer ? sock_i_ino(peer) : 0); unix_state_unlock(req); diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig index a9ac85e09af3..10345388ad13 100644 --- a/net/wireless/Kconfig +++ b/net/wireless/Kconfig @@ -206,7 +206,6 @@ config CFG80211_KUNIT_TEST depends on KUNIT depends on CFG80211 default KUNIT_ALL_TESTS - depends on !KERNEL_6_2 help Enable this option to test cfg80211 functions with kunit. diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 60877b532993..b09700400d09 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -4020,6 +4020,7 @@ static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback * } wiphy_unlock(&rdev->wiphy); + if_start = 0; wp_idx++; } out: diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 9f13aa3353e3..1eadfac03cc4 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -167,8 +167,10 @@ static int xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) contd = XDP_PKT_CONTD; err = __xsk_rcv_zc(xs, xskb, len, contd); - if (err || likely(!frags)) - goto out; + if (err) + goto err; + if (likely(!frags)) + return 0; xskb_list = &xskb->pool->xskb_list; list_for_each_entry_safe(pos, tmp, xskb_list, xskb_list_node) { @@ -177,11 +179,13 @@ static int xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) len = pos->xdp.data_end - pos->xdp.data; err = __xsk_rcv_zc(xs, pos, len, contd); if (err) - return err; + goto err; list_del(&pos->xskb_list_node); } -out: + return 0; +err: + xsk_buff_free(xdp); return err; } diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index 28711cc44ced..ce60ecd48a4d 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -555,6 +555,7 @@ struct xdp_buff *xp_alloc(struct xsk_buff_pool *pool) xskb->xdp.data = xskb->xdp.data_hard_start + XDP_PACKET_HEADROOM; xskb->xdp.data_meta = xskb->xdp.data; + xskb->xdp.flags = 0; if (pool->dma_need_sync) { dma_sync_single_range_for_device(pool->dev, xskb->dma, 0, diff --git a/samples/cgroup/.gitignore b/samples/cgroup/.gitignore new file mode 100644 index 000000000000..3a0161194cce --- /dev/null +++ b/samples/cgroup/.gitignore @@ -0,0 +1,3 @@ +/cgroup_event_listener +/memcg_event_listener + diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn index 9b7a37ae28a8..a9e552a1e910 100644 --- a/scripts/Makefile.extrawarn +++ b/scripts/Makefile.extrawarn @@ -97,7 +97,6 @@ KBUILD_CFLAGS += $(call cc-option, -Wunused-const-variable) KBUILD_CFLAGS += $(call cc-option, -Wpacked-not-aligned) KBUILD_CFLAGS += $(call cc-option, -Wformat-overflow) KBUILD_CFLAGS += $(call cc-option, -Wformat-truncation) -KBUILD_CFLAGS += $(call cc-option, -Wstringop-overflow) KBUILD_CFLAGS += $(call cc-option, -Wstringop-truncation) KBUILD_CPPFLAGS += -Wundef @@ -113,7 +112,6 @@ KBUILD_CFLAGS += $(call cc-disable-warning, restrict) KBUILD_CFLAGS += $(call cc-disable-warning, packed-not-aligned) KBUILD_CFLAGS += $(call cc-disable-warning, format-overflow) KBUILD_CFLAGS += $(call cc-disable-warning, format-truncation) -KBUILD_CFLAGS += $(call cc-disable-warning, stringop-overflow) KBUILD_CFLAGS += $(call cc-disable-warning, stringop-truncation) ifdef CONFIG_CC_IS_CLANG diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index 7717354ce095..98e1150bee9d 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -469,8 +469,10 @@ static int apparmor_file_open(struct file *file) * Cache permissions granted by the previous exec check, with * implicit read and executable mmap which are required to * actually execute the image. + * + * Illogically, FMODE_EXEC is in f_flags, not f_mode. */ - if (current->in_execve) { + if (file->f_flags & __FMODE_EXEC) { fctx->allow = MAY_EXEC | MAY_READ | AA_EXEC_MMAP; return 0; } diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c index 76f55dd13cb8..8af2136069d2 100644 --- a/security/keys/encrypted-keys/encrypted.c +++ b/security/keys/encrypted-keys/encrypted.c @@ -237,10 +237,6 @@ static int datablob_parse(char *datablob, const char **format, break; } *decrypted_data = strsep(&datablob, " \t"); - if (!*decrypted_data) { - pr_info("encrypted_key: decrypted_data is missing\n"); - break; - } ret = 0; break; case Opt_load: diff --git a/security/tomoyo/tomoyo.c b/security/tomoyo/tomoyo.c index 3c3af149bf1c..04a92c3d65d4 100644 --- a/security/tomoyo/tomoyo.c +++ b/security/tomoyo/tomoyo.c @@ -328,7 +328,8 @@ static int tomoyo_file_fcntl(struct file *file, unsigned int cmd, static int tomoyo_file_open(struct file *f) { /* Don't check read permission here if called from execve(). */ - if (current->in_execve) + /* Illogically, FMODE_EXEC is in f_flags, not f_mode. */ + if (f->f_flags & __FMODE_EXEC) return 0; return tomoyo_check_open_permission(tomoyo_domain(), &f->f_path, f->f_flags); diff --git a/tools/testing/selftests/drivers/net/bonding/bond_options.sh b/tools/testing/selftests/drivers/net/bonding/bond_options.sh index c54d1697f439..d508486cc0bd 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond_options.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond_options.sh @@ -162,7 +162,7 @@ prio_arp() local mode=$1 for primary_reselect in 0 1 2; do - prio_test "mode active-backup arp_interval 100 arp_ip_target ${g_ip4} primary eth1 primary_reselect $primary_reselect" + prio_test "mode $mode arp_interval 100 arp_ip_target ${g_ip4} primary eth1 primary_reselect $primary_reselect" log_test "prio" "$mode arp_ip_target primary_reselect $primary_reselect" done } @@ -178,7 +178,7 @@ prio_ns() fi for primary_reselect in 0 1 2; do - prio_test "mode active-backup arp_interval 100 ns_ip6_target ${g_ip6} primary eth1 primary_reselect $primary_reselect" + prio_test "mode $mode arp_interval 100 ns_ip6_target ${g_ip6} primary eth1 primary_reselect $primary_reselect" log_test "prio" "$mode ns_ip6_target primary_reselect $primary_reselect" done } @@ -194,9 +194,9 @@ prio() for mode in $modes; do prio_miimon $mode - prio_arp $mode - prio_ns $mode done + prio_arp "active-backup" + prio_ns "active-backup" } arp_validate_test() diff --git a/tools/testing/selftests/drivers/net/bonding/lag_lib.sh b/tools/testing/selftests/drivers/net/bonding/lag_lib.sh index 2a268b17b61f..dbdd736a41d3 100644 --- a/tools/testing/selftests/drivers/net/bonding/lag_lib.sh +++ b/tools/testing/selftests/drivers/net/bonding/lag_lib.sh @@ -48,6 +48,17 @@ test_LAG_cleanup() ip link add mv0 link "$name" up address "$ucaddr" type macvlan # Used to test dev->mc handling ip address add "$addr6" dev "$name" + + # Check that addresses were added as expected + (grep_bridge_fdb "$ucaddr" bridge fdb show dev dummy1 || + grep_bridge_fdb "$ucaddr" bridge fdb show dev dummy2) >/dev/null + check_err $? "macvlan unicast address not found on a slave" + + # mcaddr is added asynchronously by addrconf_dad_work(), use busywait + (busywait 10000 grep_bridge_fdb "$mcaddr" bridge fdb show dev dummy1 || + grep_bridge_fdb "$mcaddr" bridge fdb show dev dummy2) >/dev/null + check_err $? "IPv6 solicited-node multicast mac address not found on a slave" + ip link set dev "$name" down ip link del "$name" diff --git a/tools/testing/selftests/drivers/net/bonding/settings b/tools/testing/selftests/drivers/net/bonding/settings index 6091b45d226b..79b65bdf05db 100644 --- a/tools/testing/selftests/drivers/net/bonding/settings +++ b/tools/testing/selftests/drivers/net/bonding/settings @@ -1 +1 @@ -timeout=120 +timeout=1200 diff --git a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh index 4855ef597a15..f98435c502f6 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh @@ -270,6 +270,7 @@ for port in 0 1; do echo 1 > $NSIM_DEV_SYS/new_port fi NSIM_NETDEV=`get_netdev_name old_netdevs` + ifconfig $NSIM_NETDEV up msg="new NIC device created" exp0=( 0 0 0 0 ) @@ -431,6 +432,7 @@ for port in 0 1; do fi echo $port > $NSIM_DEV_SYS/new_port + NSIM_NETDEV=`get_netdev_name old_netdevs` ifconfig $NSIM_NETDEV up overflow_table0 "overflow NIC table" @@ -488,6 +490,7 @@ for port in 0 1; do fi echo $port > $NSIM_DEV_SYS/new_port + NSIM_NETDEV=`get_netdev_name old_netdevs` ifconfig $NSIM_NETDEV up overflow_table0 "overflow NIC table" @@ -544,6 +547,7 @@ for port in 0 1; do fi echo $port > $NSIM_DEV_SYS/new_port + NSIM_NETDEV=`get_netdev_name old_netdevs` ifconfig $NSIM_NETDEV up overflow_table0 "destroy NIC" @@ -573,6 +577,7 @@ for port in 0 1; do fi echo $port > $NSIM_DEV_SYS/new_port + NSIM_NETDEV=`get_netdev_name old_netdevs` ifconfig $NSIM_NETDEV up msg="create VxLANs v6" @@ -633,6 +638,7 @@ for port in 0 1; do fi echo $port > $NSIM_DEV_SYS/new_port + NSIM_NETDEV=`get_netdev_name old_netdevs` ifconfig $NSIM_NETDEV up echo 110 > $NSIM_DEV_DFS/ports/$port/udp_ports_inject_error @@ -688,6 +694,7 @@ for port in 0 1; do fi echo $port > $NSIM_DEV_SYS/new_port + NSIM_NETDEV=`get_netdev_name old_netdevs` ifconfig $NSIM_NETDEV up msg="create VxLANs v6" @@ -747,6 +754,7 @@ for port in 0 1; do fi echo $port > $NSIM_DEV_SYS/new_port + NSIM_NETDEV=`get_netdev_name old_netdevs` ifconfig $NSIM_NETDEV up msg="create VxLANs v6" @@ -877,6 +885,7 @@ msg="re-add a port" echo 2 > $NSIM_DEV_SYS/del_port echo 2 > $NSIM_DEV_SYS/new_port +NSIM_NETDEV=`get_netdev_name old_netdevs` check_tables msg="replace VxLAN in overflow table" diff --git a/tools/testing/selftests/drivers/net/team/config b/tools/testing/selftests/drivers/net/team/config index 265b6882cc21..b5e3a3aad4bf 100644 --- a/tools/testing/selftests/drivers/net/team/config +++ b/tools/testing/selftests/drivers/net/team/config @@ -1,3 +1,5 @@ +CONFIG_DUMMY=y +CONFIG_IPV6=y +CONFIG_MACVLAN=y CONFIG_NET_TEAM=y CONFIG_NET_TEAM_MODE_LOADBALANCE=y -CONFIG_MACVLAN=y diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 50818075e566..211753756bde 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -53,8 +53,7 @@ TEST_PROGS += bind_bhash.sh TEST_PROGS += ip_local_port_range.sh TEST_PROGS += rps_default_mask.sh TEST_PROGS += big_tcp.sh -TEST_PROGS_EXTENDED := in_netns.sh setup_loopback.sh setup_veth.sh -TEST_PROGS_EXTENDED += toeplitz_client.sh toeplitz.sh lib.sh +TEST_PROGS_EXTENDED := toeplitz_client.sh toeplitz.sh TEST_GEN_FILES = socket nettest TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd txring_overwrite @@ -84,6 +83,7 @@ TEST_PROGS += sctp_vrf.sh TEST_GEN_FILES += sctp_hello TEST_GEN_FILES += csum TEST_GEN_FILES += nat6to4.o +TEST_GEN_FILES += xdp_dummy.o TEST_GEN_FILES += ip_local_port_range TEST_GEN_FILES += bind_wildcard TEST_PROGS += test_vxlan_mdb.sh @@ -95,6 +95,7 @@ TEST_PROGS += fq_band_pktlimit.sh TEST_PROGS += vlan_hw_filter.sh TEST_FILES := settings +TEST_FILES += in_netns.sh lib.sh net_helper.sh setup_loopback.sh setup_veth.sh include ../lib.mk @@ -104,7 +105,7 @@ $(OUTPUT)/tcp_inq: LDLIBS += -lpthread $(OUTPUT)/bind_bhash: LDLIBS += -lpthread $(OUTPUT)/io_uring_zerocopy_tx: CFLAGS += -I../../../include/ -# Rules to generate bpf obj nat6to4.o +# Rules to generate bpf objs CLANG ?= clang SCRATCH_DIR := $(OUTPUT)/tools BUILD_DIR := $(SCRATCH_DIR)/build @@ -139,7 +140,7 @@ endif CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH)) -$(OUTPUT)/nat6to4.o: nat6to4.c $(BPFOBJ) | $(MAKE_DIRS) +$(OUTPUT)/nat6to4.o $(OUTPUT)/xdp_dummy.o: $(OUTPUT)/%.o : %.c $(BPFOBJ) | $(MAKE_DIRS) $(CLANG) -O2 --target=bpf -c $< $(CCINCLUDE) $(CLANG_SYS_INCLUDES) -o $@ $(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \ diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index 8da562a9ae87..3b749addd364 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -1,5 +1,6 @@ CONFIG_USER_NS=y CONFIG_NET_NS=y +CONFIG_BONDING=m CONFIG_BPF_SYSCALL=y CONFIG_TEST_BPF=m CONFIG_NUMA=y @@ -14,9 +15,16 @@ CONFIG_VETH=y CONFIG_NET_IPVTI=y CONFIG_IPV6_VTI=y CONFIG_DUMMY=y +CONFIG_BRIDGE_VLAN_FILTERING=y CONFIG_BRIDGE=y +CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_VLAN_8021Q=y +CONFIG_GENEVE=m CONFIG_IFB=y +CONFIG_INET_DIAG=y +CONFIG_INET_ESP=y +CONFIG_INET_ESP_OFFLOAD=y +CONFIG_IP_GRE=m CONFIG_NETFILTER=y CONFIG_NETFILTER_ADVANCED=y CONFIG_NF_CONNTRACK=m @@ -24,16 +32,49 @@ CONFIG_NF_NAT=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP6_NF_NAT=m +CONFIG_IP6_NF_RAW=m CONFIG_IP_NF_NAT=m +CONFIG_IP_NF_RAW=m +CONFIG_IP_NF_TARGET_TTL=m +CONFIG_IPV6_GRE=m +CONFIG_IPV6_SEG6_LWTUNNEL=y +CONFIG_L2TP_ETH=m +CONFIG_L2TP_IP=m +CONFIG_L2TP=m +CONFIG_L2TP_V3=y +CONFIG_MACSEC=m +CONFIG_MACVLAN=y +CONFIG_MACVTAP=y +CONFIG_MPLS=y +CONFIG_MPTCP=y CONFIG_NF_TABLES=m CONFIG_NF_TABLES_IPV6=y CONFIG_NF_TABLES_IPV4=y CONFIG_NFT_NAT=m +CONFIG_NETFILTER_XT_MATCH_LENGTH=m +CONFIG_NET_ACT_CSUM=m +CONFIG_NET_ACT_CT=m +CONFIG_NET_ACT_GACT=m +CONFIG_NET_ACT_PEDIT=m +CONFIG_NET_CLS_BASIC=m +CONFIG_NET_CLS_BPF=m +CONFIG_NET_CLS_MATCHALL=m +CONFIG_NET_CLS_U32=m +CONFIG_NET_IPGRE_DEMUX=m +CONFIG_NET_IPGRE=m +CONFIG_NET_SCH_FQ_CODEL=m +CONFIG_NET_SCH_HTB=m CONFIG_NET_SCH_FQ=m CONFIG_NET_SCH_ETF=m CONFIG_NET_SCH_NETEM=y +CONFIG_NET_SCH_PRIO=m +CONFIG_NFT_COMPAT=m +CONFIG_NF_FLOW_TABLE=m +CONFIG_PSAMPLE=m +CONFIG_TCP_MD5SIG=y CONFIG_TEST_BLACKHOLE_DEV=m CONFIG_KALLSYMS=y +CONFIG_TLS=m CONFIG_TRACEPOINTS=y CONFIG_NET_DROP_MONITOR=m CONFIG_NETDEVSIM=m @@ -48,7 +89,10 @@ CONFIG_BAREUDP=m CONFIG_IPV6_IOAM6_LWTUNNEL=y CONFIG_CRYPTO_SM4_GENERIC=y CONFIG_AMT=m +CONFIG_TUN=y CONFIG_VXLAN=m CONFIG_IP_SCTP=m CONFIG_NETFILTER_XT_MATCH_POLICY=m CONFIG_CRYPTO_ARIA=y +CONFIG_XFRM_INTERFACE=m +CONFIG_XFRM_USER=m diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index 452693514be4..4de92632f483 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -112,7 +112,7 @@ TEST_PROGS = bridge_fdb_learning_limit.sh \ vxlan_symmetric_ipv6.sh \ vxlan_symmetric.sh -TEST_PROGS_EXTENDED := devlink_lib.sh \ +TEST_FILES := devlink_lib.sh \ ethtool_lib.sh \ fib_offload_lib.sh \ forwarding.config.sample \ diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index dca549443801..f9fe182dfbd4 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -4,6 +4,9 @@ ############################################################################## # Defines +WAIT_TIMEOUT=${WAIT_TIMEOUT:=20} +BUSYWAIT_TIMEOUT=$((WAIT_TIMEOUT * 1000)) # ms + # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 # namespace list created by setup_ns @@ -48,7 +51,7 @@ cleanup_ns() for ns in "$@"; do ip netns delete "${ns}" &> /dev/null - if ! busywait 2 ip netns list \| grep -vq "^$ns$" &> /dev/null; then + if ! busywait $BUSYWAIT_TIMEOUT ip netns list \| grep -vq "^$ns$" &> /dev/null; then echo "Warn: Failed to remove namespace $ns" ret=1 fi diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config index e317c2e44dae..4f80014cae49 100644 --- a/tools/testing/selftests/net/mptcp/config +++ b/tools/testing/selftests/net/mptcp/config @@ -22,8 +22,11 @@ CONFIG_NFT_TPROXY=m CONFIG_NFT_SOCKET=m CONFIG_IP_ADVANCED_ROUTER=y CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_IP_NF_FILTER=m +CONFIG_IP_NF_MANGLE=m CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IPV6_MULTIPLE_TABLES=y +CONFIG_IP6_NF_FILTER=m CONFIG_NET_ACT_CSUM=m CONFIG_NET_ACT_PEDIT=m CONFIG_NET_CLS_ACT=y diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 3a5b63026191..c07386e21e0a 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -643,13 +643,6 @@ kill_events_pids() mptcp_lib_kill_wait $evts_ns2_pid } -kill_tests_wait() -{ - #shellcheck disable=SC2046 - kill -SIGUSR1 $(ip netns pids $ns2) $(ip netns pids $ns1) - wait -} - pm_nl_set_limits() { local ns=$1 @@ -3453,7 +3446,7 @@ userspace_tests() chk_mptcp_info subflows 0 subflows 0 chk_subflows_total 1 1 kill_events_pids - wait $tests_pid + mptcp_lib_kill_wait $tests_pid fi # userspace pm create destroy subflow @@ -3475,7 +3468,7 @@ userspace_tests() chk_mptcp_info subflows 0 subflows 0 chk_subflows_total 1 1 kill_events_pids - wait $tests_pid + mptcp_lib_kill_wait $tests_pid fi # userspace pm create id 0 subflow @@ -3494,7 +3487,7 @@ userspace_tests() chk_mptcp_info subflows 1 subflows 1 chk_subflows_total 2 2 kill_events_pids - wait $tests_pid + mptcp_lib_kill_wait $tests_pid fi # userspace pm remove initial subflow @@ -3518,7 +3511,7 @@ userspace_tests() chk_mptcp_info subflows 1 subflows 1 chk_subflows_total 1 1 kill_events_pids - wait $tests_pid + mptcp_lib_kill_wait $tests_pid fi # userspace pm send RM_ADDR for ID 0 @@ -3544,7 +3537,7 @@ userspace_tests() chk_mptcp_info subflows 1 subflows 1 chk_subflows_total 1 1 kill_events_pids - wait $tests_pid + mptcp_lib_kill_wait $tests_pid fi } @@ -3558,7 +3551,8 @@ endpoint_tests() pm_nl_set_limits $ns2 2 2 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal speed=slow \ - run_tests $ns1 $ns2 10.0.1.1 2>/dev/null & + run_tests $ns1 $ns2 10.0.1.1 & + local tests_pid=$! wait_mpj $ns1 pm_nl_check_endpoint "creation" \ @@ -3573,7 +3567,7 @@ endpoint_tests() pm_nl_add_endpoint $ns2 10.0.2.2 flags signal pm_nl_check_endpoint "modif is allowed" \ $ns2 10.0.2.2 id 1 flags signal - kill_tests_wait + mptcp_lib_kill_wait $tests_pid fi if reset "delete and re-add" && @@ -3582,7 +3576,8 @@ endpoint_tests() pm_nl_set_limits $ns2 1 1 pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow test_linkfail=4 speed=20 \ - run_tests $ns1 $ns2 10.0.1.1 2>/dev/null & + run_tests $ns1 $ns2 10.0.1.1 & + local tests_pid=$! wait_mpj $ns2 chk_subflow_nr "before delete" 2 @@ -3597,7 +3592,7 @@ endpoint_tests() wait_mpj $ns2 chk_subflow_nr "after re-add" 2 chk_mptcp_info subflows 1 subflows 1 - kill_tests_wait + mptcp_lib_kill_wait $tests_pid fi } diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index 022262a2cfe0..3a2abae5993e 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -6,7 +6,7 @@ readonly KSFT_FAIL=1 readonly KSFT_SKIP=4 # shellcheck disable=SC2155 # declare and assign separately -readonly KSFT_TEST=$(basename "${0}" | sed 's/\.sh$//g') +readonly KSFT_TEST="${MPTCP_LIB_KSFT_TEST:-$(basename "${0}" .sh)}" MPTCP_LIB_SUBTESTS=() diff --git a/tools/testing/selftests/net/mptcp/settings b/tools/testing/selftests/net/mptcp/settings index 79b65bdf05db..abc5648b59ab 100644 --- a/tools/testing/selftests/net/mptcp/settings +++ b/tools/testing/selftests/net/mptcp/settings @@ -1 +1 @@ -timeout=1200 +timeout=1800 diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index ae8ad5d6fb9d..0cc964e6f2c1 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -284,12 +284,12 @@ done setup run_test 10 10 0 0 "balanced bwidth" -run_test 10 10 1 50 "balanced bwidth with unbalanced delay" +run_test 10 10 1 25 "balanced bwidth with unbalanced delay" # we still need some additional infrastructure to pass the following test-cases -run_test 30 10 0 0 "unbalanced bwidth" -run_test 30 10 1 50 "unbalanced bwidth with unbalanced delay" -run_test 30 10 50 1 "unbalanced bwidth with opposed, unbalanced delay" +run_test 10 3 0 0 "unbalanced bwidth" +run_test 10 3 1 25 "unbalanced bwidth with unbalanced delay" +run_test 10 3 25 1 "unbalanced bwidth with opposed, unbalanced delay" mptcp_lib_result_print_all_tap exit $ret diff --git a/tools/testing/selftests/net/net_helper.sh b/tools/testing/selftests/net/net_helper.sh index 4fe0befa13fb..4fe0befa13fb 100755..100644 --- a/tools/testing/selftests/net/net_helper.sh +++ b/tools/testing/selftests/net/net_helper.sh diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index f10879788f61..3f118e3f1c66 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -707,23 +707,23 @@ setup_xfrm6() { } setup_xfrm4udp() { - setup_xfrm 4 ${veth4_a_addr} ${veth4_b_addr} "encap espinudp 4500 4500 0.0.0.0" - setup_nettest_xfrm 4 4500 + setup_xfrm 4 ${veth4_a_addr} ${veth4_b_addr} "encap espinudp 4500 4500 0.0.0.0" && \ + setup_nettest_xfrm 4 4500 } setup_xfrm6udp() { - setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr} "encap espinudp 4500 4500 0.0.0.0" - setup_nettest_xfrm 6 4500 + setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr} "encap espinudp 4500 4500 0.0.0.0" && \ + setup_nettest_xfrm 6 4500 } setup_xfrm4udprouted() { - setup_xfrm 4 ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "encap espinudp 4500 4500 0.0.0.0" - setup_nettest_xfrm 4 4500 + setup_xfrm 4 ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "encap espinudp 4500 4500 0.0.0.0" && \ + setup_nettest_xfrm 4 4500 } setup_xfrm6udprouted() { - setup_xfrm 6 ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 "encap espinudp 4500 4500 0.0.0.0" - setup_nettest_xfrm 6 4500 + setup_xfrm 6 ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 "encap espinudp 4500 4500 0.0.0.0" && \ + setup_nettest_xfrm 6 4500 } setup_routing_old() { @@ -1339,7 +1339,7 @@ test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception() { sleep 1 - dd if=/dev/zero of=/dev/stdout status=none bs=1M count=1 | ${target} socat -T 3 -u STDIN $TCPDST,connect-timeout=3 + dd if=/dev/zero status=none bs=1M count=1 | ${target} socat -T 3 -u STDIN $TCPDST,connect-timeout=3 size=$(du -sb $tmpoutfile) size=${size%%/tmp/*} diff --git a/tools/testing/selftests/net/rps_default_mask.sh b/tools/testing/selftests/net/rps_default_mask.sh index a26c5624429f..4287a8529890 100755 --- a/tools/testing/selftests/net/rps_default_mask.sh +++ b/tools/testing/selftests/net/rps_default_mask.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 readonly ksft_skip=4 @@ -33,6 +33,10 @@ chk_rps() { rps_mask=$($cmd /sys/class/net/$dev_name/queues/rx-0/rps_cpus) printf "%-60s" "$msg" + + # In case there is more than 32 CPUs we need to remove commas from masks + rps_mask=${rps_mask//,} + expected_rps_mask=${expected_rps_mask//,} if [ $rps_mask -eq $expected_rps_mask ]; then echo "[ ok ]" else diff --git a/tools/testing/selftests/net/setup_loopback.sh b/tools/testing/selftests/net/setup_loopback.sh index 2070b57849de..2070b57849de 100755..100644 --- a/tools/testing/selftests/net/setup_loopback.sh +++ b/tools/testing/selftests/net/setup_loopback.sh diff --git a/tools/testing/selftests/net/setup_veth.sh b/tools/testing/selftests/net/setup_veth.sh index a9a1759e035c..1f78a87f6f37 100644 --- a/tools/testing/selftests/net/setup_veth.sh +++ b/tools/testing/selftests/net/setup_veth.sh @@ -11,7 +11,7 @@ setup_veth_ns() { local -r ns_mac="$4" [[ -e /var/run/netns/"${ns_name}" ]] || ip netns add "${ns_name}" - echo 100000 > "/sys/class/net/${ns_dev}/gro_flush_timeout" + echo 1000000 > "/sys/class/net/${ns_dev}/gro_flush_timeout" ip link set dev "${ns_dev}" netns "${ns_name}" mtu 65535 ip -netns "${ns_name}" link set dev "${ns_dev}" up diff --git a/tools/testing/selftests/net/so_incoming_cpu.c b/tools/testing/selftests/net/so_incoming_cpu.c index a14818164102..e9fa14e10732 100644 --- a/tools/testing/selftests/net/so_incoming_cpu.c +++ b/tools/testing/selftests/net/so_incoming_cpu.c @@ -3,19 +3,16 @@ #define _GNU_SOURCE #include <sched.h> +#include <fcntl.h> + #include <netinet/in.h> #include <sys/socket.h> #include <sys/sysinfo.h> #include "../kselftest_harness.h" -#define CLIENT_PER_SERVER 32 /* More sockets, more reliable */ -#define NR_SERVER self->nproc -#define NR_CLIENT (CLIENT_PER_SERVER * NR_SERVER) - FIXTURE(so_incoming_cpu) { - int nproc; int *servers; union { struct sockaddr addr; @@ -56,12 +53,47 @@ FIXTURE_VARIANT_ADD(so_incoming_cpu, after_all_listen) .when_to_set = AFTER_ALL_LISTEN, }; +static void write_sysctl(struct __test_metadata *_metadata, + char *filename, char *string) +{ + int fd, len, ret; + + fd = open(filename, O_WRONLY); + ASSERT_NE(fd, -1); + + len = strlen(string); + ret = write(fd, string, len); + ASSERT_EQ(ret, len); +} + +static void setup_netns(struct __test_metadata *_metadata) +{ + ASSERT_EQ(unshare(CLONE_NEWNET), 0); + ASSERT_EQ(system("ip link set lo up"), 0); + + write_sysctl(_metadata, "/proc/sys/net/ipv4/ip_local_port_range", "10000 60001"); + write_sysctl(_metadata, "/proc/sys/net/ipv4/tcp_tw_reuse", "0"); +} + +#define NR_PORT (60001 - 10000 - 1) +#define NR_CLIENT_PER_SERVER_DEFAULT 32 +static int nr_client_per_server, nr_server, nr_client; + FIXTURE_SETUP(so_incoming_cpu) { - self->nproc = get_nprocs(); - ASSERT_LE(2, self->nproc); + setup_netns(_metadata); + + nr_server = get_nprocs(); + ASSERT_LE(2, nr_server); + + if (NR_CLIENT_PER_SERVER_DEFAULT * nr_server < NR_PORT) + nr_client_per_server = NR_CLIENT_PER_SERVER_DEFAULT; + else + nr_client_per_server = NR_PORT / nr_server; + + nr_client = nr_client_per_server * nr_server; - self->servers = malloc(sizeof(int) * NR_SERVER); + self->servers = malloc(sizeof(int) * nr_server); ASSERT_NE(self->servers, NULL); self->in_addr.sin_family = AF_INET; @@ -74,7 +106,7 @@ FIXTURE_TEARDOWN(so_incoming_cpu) { int i; - for (i = 0; i < NR_SERVER; i++) + for (i = 0; i < nr_server; i++) close(self->servers[i]); free(self->servers); @@ -110,10 +142,10 @@ int create_server(struct __test_metadata *_metadata, if (variant->when_to_set == BEFORE_LISTEN) set_so_incoming_cpu(_metadata, fd, cpu); - /* We don't use CLIENT_PER_SERVER here not to block + /* We don't use nr_client_per_server here not to block * this test at connect() if SO_INCOMING_CPU is broken. */ - ret = listen(fd, NR_CLIENT); + ret = listen(fd, nr_client); ASSERT_EQ(ret, 0); if (variant->when_to_set == AFTER_LISTEN) @@ -128,7 +160,7 @@ void create_servers(struct __test_metadata *_metadata, { int i, ret; - for (i = 0; i < NR_SERVER; i++) { + for (i = 0; i < nr_server; i++) { self->servers[i] = create_server(_metadata, self, variant, i); if (i == 0) { @@ -138,7 +170,7 @@ void create_servers(struct __test_metadata *_metadata, } if (variant->when_to_set == AFTER_ALL_LISTEN) { - for (i = 0; i < NR_SERVER; i++) + for (i = 0; i < nr_server; i++) set_so_incoming_cpu(_metadata, self->servers[i], i); } } @@ -149,7 +181,7 @@ void create_clients(struct __test_metadata *_metadata, cpu_set_t cpu_set; int i, j, fd, ret; - for (i = 0; i < NR_SERVER; i++) { + for (i = 0; i < nr_server; i++) { CPU_ZERO(&cpu_set); CPU_SET(i, &cpu_set); @@ -162,7 +194,7 @@ void create_clients(struct __test_metadata *_metadata, ret = sched_setaffinity(0, sizeof(cpu_set), &cpu_set); ASSERT_EQ(ret, 0); - for (j = 0; j < CLIENT_PER_SERVER; j++) { + for (j = 0; j < nr_client_per_server; j++) { fd = socket(AF_INET, SOCK_STREAM, 0); ASSERT_NE(fd, -1); @@ -180,8 +212,8 @@ void verify_incoming_cpu(struct __test_metadata *_metadata, int i, j, fd, cpu, ret, total = 0; socklen_t len = sizeof(int); - for (i = 0; i < NR_SERVER; i++) { - for (j = 0; j < CLIENT_PER_SERVER; j++) { + for (i = 0; i < nr_server; i++) { + for (j = 0; j < nr_client_per_server; j++) { /* If we see -EAGAIN here, SO_INCOMING_CPU is broken */ fd = accept(self->servers[i], &self->addr, &self->addrlen); ASSERT_NE(fd, -1); @@ -195,7 +227,7 @@ void verify_incoming_cpu(struct __test_metadata *_metadata, } } - ASSERT_EQ(total, NR_CLIENT); + ASSERT_EQ(total, nr_client); TH_LOG("SO_INCOMING_CPU is very likely to be " "working correctly with %d sockets.", total); } diff --git a/tools/testing/selftests/net/tcp_ao/config b/tools/testing/selftests/net/tcp_ao/config new file mode 100644 index 000000000000..d3277a9de987 --- /dev/null +++ b/tools/testing/selftests/net/tcp_ao/config @@ -0,0 +1,10 @@ +CONFIG_CRYPTO_HMAC=y +CONFIG_CRYPTO_RMD160=y +CONFIG_CRYPTO_SHA1=y +CONFIG_IPV6_MULTIPLE_TABLES=y +CONFIG_IPV6=y +CONFIG_NET_L3_MASTER_DEV=y +CONFIG_NET_VRF=y +CONFIG_TCP_AO=y +CONFIG_TCP_MD5SIG=y +CONFIG_VETH=m diff --git a/tools/testing/selftests/net/tcp_ao/key-management.c b/tools/testing/selftests/net/tcp_ao/key-management.c index c48b4970ca17..24e62120b792 100644 --- a/tools/testing/selftests/net/tcp_ao/key-management.c +++ b/tools/testing/selftests/net/tcp_ao/key-management.c @@ -417,9 +417,9 @@ struct test_key { matches_vrf : 1, is_current : 1, is_rnext : 1, - used_on_handshake : 1, - used_after_accept : 1, - used_on_client : 1; + used_on_server_tx : 1, + used_on_client_tx : 1, + skip_counters_checks : 1; }; struct key_collection { @@ -609,16 +609,14 @@ static int key_collection_socket(bool server, unsigned int port) addr = &this_ip_dest; sndid = key->client_keyid; rcvid = key->server_keyid; - set_current = key->is_current; - set_rnext = key->is_rnext; + key->used_on_client_tx = set_current = key->is_current; + key->used_on_server_tx = set_rnext = key->is_rnext; } if (test_add_key_cr(sk, key->password, key->len, *addr, vrf, sndid, rcvid, key->maclen, key->alg, set_current, set_rnext)) test_key_error("setsockopt(TCP_AO_ADD_KEY)", key); - if (set_current || set_rnext) - key->used_on_handshake = 1; #ifdef DEBUG test_print("%s [%u/%u] key: { %s, %u:%u, %u, %u:%u:%u:%u (%u)}", server ? "server" : "client", i, collection.nr_keys, @@ -640,22 +638,22 @@ static void verify_counters(const char *tst_name, bool is_listen_sk, bool server for (i = 0; i < collection.nr_keys; i++) { struct test_key *key = &collection.keys[i]; uint8_t sndid, rcvid; - bool was_used; + bool rx_cnt_expected; + if (key->skip_counters_checks) + continue; if (server) { sndid = key->server_keyid; rcvid = key->client_keyid; - if (is_listen_sk) - was_used = key->used_on_handshake; - else - was_used = key->used_after_accept; + rx_cnt_expected = key->used_on_client_tx; } else { sndid = key->client_keyid; rcvid = key->server_keyid; - was_used = key->used_on_client; + rx_cnt_expected = key->used_on_server_tx; } - test_tcp_ao_key_counters_cmp(tst_name, a, b, was_used, + test_tcp_ao_key_counters_cmp(tst_name, a, b, + rx_cnt_expected ? TEST_CNT_KEY_GOOD : 0, sndid, rcvid); } test_tcp_ao_counters_free(a); @@ -843,7 +841,7 @@ static void end_server(const char *tst_name, int sk, synchronize_threads(); /* 4: verified => closed */ close(sk); - verify_counters(tst_name, true, false, begin, &end); + verify_counters(tst_name, false, true, begin, &end); synchronize_threads(); /* 5: counters */ } @@ -916,9 +914,8 @@ static int run_client(const char *tst_name, unsigned int port, current_index = nr_keys - 1; if (rnext_index < 0) rnext_index = nr_keys - 1; - collection.keys[current_index].used_on_handshake = 1; - collection.keys[rnext_index].used_after_accept = 1; - collection.keys[rnext_index].used_on_client = 1; + collection.keys[current_index].used_on_client_tx = 1; + collection.keys[rnext_index].used_on_server_tx = 1; synchronize_threads(); /* 3: accepted => send data */ if (test_client_verify(sk, msg_sz, msg_nr, TEST_TIMEOUT_SEC)) { @@ -1059,7 +1056,16 @@ static void check_current_back(const char *tst_name, unsigned int port, test_error("Can't change the current key"); if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC)) test_fail("verify failed"); - collection.keys[rotate_to_index].used_after_accept = 1; + /* There is a race here: between setting the current_key with + * setsockopt(TCP_AO_INFO) and starting to send some data - there + * might have been a segment received with the desired + * RNext_key set. In turn that would mean that the first outgoing + * segment will have the desired current_key (flipped back). + * Which is what the user/test wants. As it's racy, skip checking + * the counters, yet check what are the resulting current/rnext + * keys on both sides. + */ + collection.keys[rotate_to_index].skip_counters_checks = 1; end_client(tst_name, sk, nr_keys, current_index, rnext_index, &tmp); } @@ -1089,7 +1095,7 @@ static void roll_over_keys(const char *tst_name, unsigned int port, } verify_current_rnext(tst_name, sk, -1, collection.keys[i].server_keyid); - collection.keys[i].used_on_client = 1; + collection.keys[i].used_on_server_tx = 1; synchronize_threads(); /* verify current/rnext */ } end_client(tst_name, sk, nr_keys, current_index, rnext_index, &tmp); diff --git a/tools/testing/selftests/net/tcp_ao/lib/sock.c b/tools/testing/selftests/net/tcp_ao/lib/sock.c index c75d82885a2e..15aeb0963058 100644 --- a/tools/testing/selftests/net/tcp_ao/lib/sock.c +++ b/tools/testing/selftests/net/tcp_ao/lib/sock.c @@ -62,7 +62,9 @@ int test_wait_fd(int sk, time_t sec, bool write) return -ETIMEDOUT; } - if (getsockopt(sk, SOL_SOCKET, SO_ERROR, &ret, &slen) || ret) + if (getsockopt(sk, SOL_SOCKET, SO_ERROR, &ret, &slen)) + return -errno; + if (ret) return -ret; return 0; } @@ -584,9 +586,11 @@ int test_client_verify(int sk, const size_t msg_len, const size_t nr, { size_t buf_sz = msg_len * nr; char *buf = alloca(buf_sz); + ssize_t ret; randomize_buffer(buf, buf_sz); - if (test_client_loop(sk, buf, buf_sz, msg_len, timeout_sec) != buf_sz) - return -1; - return 0; + ret = test_client_loop(sk, buf, buf_sz, msg_len, timeout_sec); + if (ret < 0) + return (int)ret; + return ret != buf_sz ? -1 : 0; } diff --git a/tools/testing/selftests/net/tcp_ao/rst.c b/tools/testing/selftests/net/tcp_ao/rst.c index ac06009a7f5f..7df8b8700e39 100644 --- a/tools/testing/selftests/net/tcp_ao/rst.c +++ b/tools/testing/selftests/net/tcp_ao/rst.c @@ -1,10 +1,33 @@ // SPDX-License-Identifier: GPL-2.0 -/* Author: Dmitry Safonov <[email protected]> */ +/* + * The test checks that both active and passive reset have correct TCP-AO + * signature. An "active" reset (abort) here is procured from closing + * listen() socket with non-accepted connections in the queue: + * inet_csk_listen_stop() => inet_child_forget() => + * => tcp_disconnect() => tcp_send_active_reset() + * + * The passive reset is quite hard to get on established TCP connections. + * It could be procured from non-established states, but the synchronization + * part from userspace in order to reliably get RST seems uneasy. + * So, instead it's procured by corrupting SEQ number on TIMED-WAIT state. + * + * It's important to test both passive and active RST as they go through + * different code-paths: + * - tcp_send_active_reset() makes no-data skb, sends it with tcp_transmit_skb() + * - tcp_v*_send_reset() create their reply skbs and send them with + * ip_send_unicast_reply() + * + * In both cases TCP-AO signatures have to be correct, which is verified by + * (1) checking that the TCP-AO connection was reset and (2) TCP-AO counters. + * + * Author: Dmitry Safonov <[email protected]> + */ #include <inttypes.h> #include "../../../../include/linux/kernel.h" #include "aolib.h" const size_t quota = 1000; +const size_t packet_sz = 100; /* * Backlog == 0 means 1 connection in queue, see: * commit 64a146513f8f ("[NET]: Revert incorrect accept queue...") @@ -59,26 +82,6 @@ static void close_forced(int sk) close(sk); } -static int test_wait_for_exception(int sk, time_t sec) -{ - struct timeval tv = { .tv_sec = sec }; - struct timeval *ptv = NULL; - fd_set efds; - int ret; - - FD_ZERO(&efds); - FD_SET(sk, &efds); - - if (sec) - ptv = &tv; - - errno = 0; - ret = select(sk + 1, NULL, NULL, &efds, ptv); - if (ret < 0) - return -errno; - return ret ? sk : 0; -} - static void test_server_active_rst(unsigned int port) { struct tcp_ao_counters cnt1, cnt2; @@ -155,17 +158,16 @@ static void test_server_passive_rst(unsigned int port) test_fail("server returned %zd", bytes); } - synchronize_threads(); /* 3: chekpoint/restore the connection */ + synchronize_threads(); /* 3: checkpoint the client */ + synchronize_threads(); /* 4: close the server, creating twsk */ if (test_get_tcp_ao_counters(sk, &ao2)) test_error("test_get_tcp_ao_counters()"); - - synchronize_threads(); /* 4: terminate server + send more on client */ - bytes = test_server_run(sk, quota, TEST_RETRANSMIT_SEC); close(sk); + + synchronize_threads(); /* 5: restore the socket, send more data */ test_tcp_ao_counters_cmp("passive RST server", &ao1, &ao2, TEST_CNT_GOOD); - synchronize_threads(); /* 5: verified => closed */ - close(sk); + synchronize_threads(); /* 6: server exits */ } static void *server_fn(void *arg) @@ -284,7 +286,7 @@ static void test_client_active_rst(unsigned int port) test_error("test_wait_fds(): %d", err); synchronize_threads(); /* 3: close listen socket */ - if (test_client_verify(sk[0], 100, quota / 100, TEST_TIMEOUT_SEC)) + if (test_client_verify(sk[0], packet_sz, quota / packet_sz, TEST_TIMEOUT_SEC)) test_fail("Failed to send data on connected socket"); else test_ok("Verified established tcp connection"); @@ -323,7 +325,6 @@ static void test_client_passive_rst(unsigned int port) struct tcp_sock_state img; sockaddr_af saddr; int sk, err; - socklen_t slen = sizeof(err); sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP); if (sk < 0) @@ -337,18 +338,51 @@ static void test_client_passive_rst(unsigned int port) test_error("failed to connect()"); synchronize_threads(); /* 2: accepted => send data */ - if (test_client_verify(sk, 100, quota / 100, TEST_TIMEOUT_SEC)) + if (test_client_verify(sk, packet_sz, quota / packet_sz, TEST_TIMEOUT_SEC)) test_fail("Failed to send data on connected socket"); else test_ok("Verified established tcp connection"); - synchronize_threads(); /* 3: chekpoint/restore the connection */ + synchronize_threads(); /* 3: checkpoint the client */ test_enable_repair(sk); test_sock_checkpoint(sk, &img, &saddr); test_ao_checkpoint(sk, &ao_img); - test_kill_sk(sk); + test_disable_repair(sk); - img.out.seq += quota; + synchronize_threads(); /* 4: close the server, creating twsk */ + + /* + * The "corruption" in SEQ has to be small enough to fit into TCP + * window, see tcp_timewait_state_process() for out-of-window + * segments. + */ + img.out.seq += 5; /* 5 is more noticeable in tcpdump than 1 */ + + /* + * FIXME: This is kind-of ugly and dirty, but it works. + * + * At this moment, the server has close'ed(sk). + * The passive RST that is being targeted here is new data after + * half-duplex close, see tcp_timewait_state_process() => TCP_TW_RST + * + * What is needed here is: + * (1) wait for FIN from the server + * (2) make sure that the ACK from the client went out + * (3) make sure that the ACK was received and processed by the server + * + * Otherwise, the data that will be sent from "repaired" socket + * post SEQ corruption may get to the server before it's in + * TCP_FIN_WAIT2. + * + * (1) is easy with select()/poll() + * (2) is possible by polling tcpi_state from TCP_INFO + * (3) is quite complex: as server's socket was already closed, + * probably the way to do it would be tcp-diag. + */ + sleep(TEST_RETRANSMIT_SEC); + + synchronize_threads(); /* 5: restore the socket, send more data */ + test_kill_sk(sk); sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP); if (sk < 0) @@ -366,25 +400,33 @@ static void test_client_passive_rst(unsigned int port) test_disable_repair(sk); test_sock_state_free(&img); - synchronize_threads(); /* 4: terminate server + send more on client */ - if (test_client_verify(sk, 100, quota / 100, 2 * TEST_TIMEOUT_SEC)) - test_ok("client connection broken post-seq-adjust"); - else - test_fail("client connection still works post-seq-adjust"); - - test_wait_for_exception(sk, TEST_TIMEOUT_SEC); - - if (getsockopt(sk, SOL_SOCKET, SO_ERROR, &err, &slen)) - test_error("getsockopt()"); - if (err != ECONNRESET && err != EPIPE) - test_fail("client connection was not reset: %d", err); + /* + * This is how "passive reset" is acquired in this test from TCP_TW_RST: + * + * IP 10.0.254.1.7011 > 10.0.1.1.59772: Flags [P.], seq 901:1001, ack 1001, win 249, + * options [tcp-ao keyid 100 rnextkeyid 100 mac 0x10217d6c36a22379086ef3b1], length 100 + * IP 10.0.254.1.7011 > 10.0.1.1.59772: Flags [F.], seq 1001, ack 1001, win 249, + * options [tcp-ao keyid 100 rnextkeyid 100 mac 0x104ffc99b98c10a5298cc268], length 0 + * IP 10.0.1.1.59772 > 10.0.254.1.7011: Flags [.], ack 1002, win 251, + * options [tcp-ao keyid 100 rnextkeyid 100 mac 0xe496dd4f7f5a8a66873c6f93,nop,nop,sack 1 {1001:1002}], length 0 + * IP 10.0.1.1.59772 > 10.0.254.1.7011: Flags [P.], seq 1006:1106, ack 1001, win 251, + * options [tcp-ao keyid 100 rnextkeyid 100 mac 0x1b5f3330fb23fbcd0c77d0ca], length 100 + * IP 10.0.254.1.7011 > 10.0.1.1.59772: Flags [R], seq 3215596252, win 0, + * options [tcp-ao keyid 100 rnextkeyid 100 mac 0x0bcfbbf497bce844312304b2], length 0 + */ + err = test_client_verify(sk, packet_sz, quota / packet_sz, 2 * TEST_TIMEOUT_SEC); + /* Make sure that the connection was reset, not timeouted */ + if (err && err == -ECONNRESET) + test_ok("client sock was passively reset post-seq-adjust"); + else if (err) + test_fail("client sock was not reset post-seq-adjust: %d", err); else - test_ok("client connection was reset"); + test_fail("client sock is yet connected post-seq-adjust"); if (test_get_tcp_ao_counters(sk, &ao2)) test_error("test_get_tcp_ao_counters()"); - synchronize_threads(); /* 5: verified => closed */ + synchronize_threads(); /* 6: server exits */ close(sk); test_tcp_ao_counters_cmp("client passive RST", &ao1, &ao2, TEST_CNT_GOOD); } @@ -410,6 +452,6 @@ static void *client_fn(void *arg) int main(int argc, char *argv[]) { - test_init(15, server_fn, client_fn); + test_init(14, server_fn, client_fn); return 0; } diff --git a/tools/testing/selftests/net/tcp_ao/settings b/tools/testing/selftests/net/tcp_ao/settings new file mode 100644 index 000000000000..6091b45d226b --- /dev/null +++ b/tools/testing/selftests/net/tcp_ao/settings @@ -0,0 +1 @@ +timeout=120 diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh index af5dc57c8ce9..8802604148dd 100755 --- a/tools/testing/selftests/net/udpgro.sh +++ b/tools/testing/selftests/net/udpgro.sh @@ -7,7 +7,7 @@ source net_helper.sh readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)" -BPF_FILE="../bpf/xdp_dummy.bpf.o" +BPF_FILE="xdp_dummy.o" # set global exit status, but never reset nonzero one. check_err() @@ -197,7 +197,7 @@ run_all() { } if [ ! -f ${BPF_FILE} ]; then - echo "Missing ${BPF_FILE}. Build bpf selftest first" + echo "Missing ${BPF_FILE}. Run 'make' first" exit -1 fi diff --git a/tools/testing/selftests/net/udpgro_bench.sh b/tools/testing/selftests/net/udpgro_bench.sh index cb664679b434..7080eae5312b 100755 --- a/tools/testing/selftests/net/udpgro_bench.sh +++ b/tools/testing/selftests/net/udpgro_bench.sh @@ -7,7 +7,7 @@ source net_helper.sh readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)" -BPF_FILE="../bpf/xdp_dummy.bpf.o" +BPF_FILE="xdp_dummy.o" cleanup() { local -r jobs="$(jobs -p)" @@ -84,7 +84,7 @@ run_all() { } if [ ! -f ${BPF_FILE} ]; then - echo "Missing ${BPF_FILE}. Build bpf selftest first" + echo "Missing ${BPF_FILE}. Run 'make' first" exit -1 fi diff --git a/tools/testing/selftests/net/udpgro_frglist.sh b/tools/testing/selftests/net/udpgro_frglist.sh index dd47fa96f6b3..e1ff645bd3d1 100755 --- a/tools/testing/selftests/net/udpgro_frglist.sh +++ b/tools/testing/selftests/net/udpgro_frglist.sh @@ -7,7 +7,7 @@ source net_helper.sh readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)" -BPF_FILE="../bpf/xdp_dummy.bpf.o" +BPF_FILE="xdp_dummy.o" cleanup() { local -r jobs="$(jobs -p)" @@ -85,12 +85,12 @@ run_all() { } if [ ! -f ${BPF_FILE} ]; then - echo "Missing ${BPF_FILE}. Build bpf selftest first" + echo "Missing ${BPF_FILE}. Run 'make' first" exit -1 fi if [ ! -f nat6to4.o ]; then - echo "Missing nat6to4 helper. Build bpf nat6to4.o selftest first" + echo "Missing nat6to4 helper. Run 'make' first" exit -1 fi diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh index c079565add39..d6b9c759043c 100755 --- a/tools/testing/selftests/net/udpgro_fwd.sh +++ b/tools/testing/selftests/net/udpgro_fwd.sh @@ -1,7 +1,9 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -BPF_FILE="../bpf/xdp_dummy.bpf.o" +source net_helper.sh + +BPF_FILE="xdp_dummy.o" readonly BASE="ns-$(mktemp -u XXXXXX)" readonly SRC=2 readonly DST=1 @@ -119,7 +121,7 @@ run_test() { ip netns exec $NS_DST $ipt -A INPUT -p udp --dport 8000 ip netns exec $NS_DST ./udpgso_bench_rx -C 1000 -R 10 -n 10 -l 1300 $rx_args & local spid=$! - sleep 0.1 + wait_local_port_listen "$NS_DST" 8000 udp ip netns exec $NS_SRC ./udpgso_bench_tx $family -M 1 -s 13000 -S 1300 -D $dst local retc=$? wait $spid @@ -168,7 +170,7 @@ run_bench() { ip netns exec $NS_DST bash -c "echo 2 > /sys/class/net/veth$DST/queues/rx-0/rps_cpus" ip netns exec $NS_DST taskset 0x2 ./udpgso_bench_rx -C 1000 -R 10 & local spid=$! - sleep 0.1 + wait_local_port_listen "$NS_DST" 8000 udp ip netns exec $NS_SRC taskset 0x1 ./udpgso_bench_tx $family -l 3 -S 1300 -D $dst local retc=$? wait $spid diff --git a/tools/testing/selftests/net/veth.sh b/tools/testing/selftests/net/veth.sh index 2d073595c620..27574bbf2d63 100755 --- a/tools/testing/selftests/net/veth.sh +++ b/tools/testing/selftests/net/veth.sh @@ -1,7 +1,7 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 -BPF_FILE="../bpf/xdp_dummy.bpf.o" +BPF_FILE="xdp_dummy.o" readonly STATS="$(mktemp -p /tmp ns-XXXXXX)" readonly BASE=`basename $STATS` readonly SRC=2 @@ -218,7 +218,7 @@ while getopts "hs:" option; do done if [ ! -f ${BPF_FILE} ]; then - echo "Missing ${BPF_FILE}. Build bpf selftest first" + echo "Missing ${BPF_FILE}. Run 'make' first" exit 1 fi diff --git a/tools/testing/selftests/net/xdp_dummy.c b/tools/testing/selftests/net/xdp_dummy.c new file mode 100644 index 000000000000..d988b2e0cee8 --- /dev/null +++ b/tools/testing/selftests/net/xdp_dummy.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define KBUILD_MODNAME "xdp_dummy" +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +SEC("xdp") +int xdp_dummy_prog(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; |