From 93a7f3b72f9acae1c369a6f1b9ab73e07368b62f Mon Sep 17 00:00:00 2001 From: eabdullin Date: Tue, 16 Sep 2025 08:42:31 +0000 Subject: [PATCH] Import of kernel-6.12.0-55.31.1.el10_0 --- ...5.30.1.el10 => COPYING-6.12.0-55.31.1.el10 | 0 Makefile.rhelver | 2 +- drivers/cxl/acpi.c | 43 ++--- drivers/dma-buf/udmabuf.c | 2 +- drivers/gpu/drm/drm_framebuffer.c | 31 +++- drivers/gpu/drm/drm_gem.c | 64 +++++++- drivers/gpu/drm/drm_internal.h | 2 + drivers/gpu/drm/vkms/vkms_drv.c | 15 +- drivers/nvme/host/ioctl.c | 13 +- include/drm/drm_framebuffer.h | 7 + kernel/sched/fair.c | 155 +++--------------- net/sched/sch_api.c | 19 +-- net/sched/sch_codel.c | 5 +- net/sched/sch_drr.c | 7 +- net/sched/sch_ets.c | 11 +- net/sched/sch_fq_codel.c | 6 +- net/sched/sch_htb.c | 13 +- net/sched/sch_qfq.c | 7 +- 18 files changed, 184 insertions(+), 218 deletions(-) rename COPYING-6.12.0-55.30.1.el10 => COPYING-6.12.0-55.31.1.el10 (100%) diff --git a/COPYING-6.12.0-55.30.1.el10 b/COPYING-6.12.0-55.31.1.el10 similarity index 100% rename from COPYING-6.12.0-55.30.1.el10 rename to COPYING-6.12.0-55.31.1.el10 diff --git a/Makefile.rhelver b/Makefile.rhelver index 776a64b1f1..9e79724b3a 100644 --- a/Makefile.rhelver +++ b/Makefile.rhelver @@ -12,7 +12,7 @@ RHEL_MINOR = 0 # # Use this spot to avoid future merge conflicts. # Do not trim this comment. -RHEL_RELEASE = 55.30.1 +RHEL_RELEASE = 55.31.1 # # RHEL_REBASE_NUM diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c index 432b7cfd12..483482e4fc 100644 --- a/drivers/cxl/acpi.c +++ b/drivers/cxl/acpi.c @@ -340,20 +340,24 @@ static int add_or_reset_cxl_resource(struct resource *parent, struct resource *r DEFINE_FREE(put_cxlrd, struct cxl_root_decoder *, if (!IS_ERR_OR_NULL(_T)) put_device(&_T->cxlsd.cxld.dev)) DEFINE_FREE(del_cxl_resource, struct resource *, if (_T) del_cxl_resource(_T)) -static int __cxl_parse_cfmws(struct acpi_cedt_cfmws *cfmws, - struct cxl_cfmws_context *ctx) +static int cxl_parse_cfmws(union acpi_subtable_headers *header, void *arg, + const unsigned long end) { int target_map[CXL_DECODER_MAX_INTERLEAVE]; + struct cxl_cfmws_context *ctx = arg; struct cxl_port *root_port = ctx->root_port; struct cxl_cxims_context cxims_ctx; struct device *dev = ctx->dev; + struct acpi_cedt_cfmws *cfmws; struct cxl_decoder *cxld; unsigned int ways, i, ig; int rc; + cfmws = (struct acpi_cedt_cfmws *) header; + rc = cxl_acpi_cfmws_verify(dev, cfmws); if (rc) - return rc; + return 0; rc = eiw_to_ways(cfmws->interleave_ways, &ways); if (rc) @@ -378,7 +382,7 @@ static int __cxl_parse_cfmws(struct acpi_cedt_cfmws *cfmws, cxl_root_decoder_alloc(root_port, ways); if (IS_ERR(cxlrd)) - return PTR_ERR(cxlrd); + return 0; cxld = &cxlrd->cxlsd.cxld; cxld->flags = cfmws_to_decoder_flags(cfmws->restrictions); @@ -421,29 +425,16 @@ static int __cxl_parse_cfmws(struct acpi_cedt_cfmws *cfmws, rc = cxl_decoder_add(cxld, target_map); if (rc) return rc; - return cxl_root_decoder_autoremove(dev, no_free_ptr(cxlrd)); -} + rc = cxl_root_decoder_autoremove(dev, no_free_ptr(cxlrd)); + if (rc) { + dev_err(dev, "Failed to add decode range: %pr", res); + return rc; + } + dev_dbg(dev, "add: %s node: %d range [%#llx - %#llx]\n", + dev_name(&cxld->dev), + phys_to_target_node(cxld->hpa_range.start), + cxld->hpa_range.start, cxld->hpa_range.end); -static int cxl_parse_cfmws(union acpi_subtable_headers *header, void *arg, - const unsigned long end) -{ - struct acpi_cedt_cfmws *cfmws = (struct acpi_cedt_cfmws *)header; - struct cxl_cfmws_context *ctx = arg; - struct device *dev = ctx->dev; - int rc; - - rc = __cxl_parse_cfmws(cfmws, ctx); - if (rc) - dev_err(dev, - "Failed to add decode range: [%#llx - %#llx] (%d)\n", - cfmws->base_hpa, - cfmws->base_hpa + cfmws->window_size - 1, rc); - else - dev_dbg(dev, "decode range: node: %d range [%#llx - %#llx]\n", - phys_to_target_node(cfmws->base_hpa), cfmws->base_hpa, - cfmws->base_hpa + cfmws->window_size - 1); - - /* never fail cxl_acpi load for a single window failure */ return 0; } diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c index 5e836e4e5b..a7d4b35b41 100644 --- a/drivers/dma-buf/udmabuf.c +++ b/drivers/dma-buf/udmabuf.c @@ -359,7 +359,7 @@ static long udmabuf_create(struct miscdevice *device, return -ENOMEM; INIT_LIST_HEAD(&ubuf->unpin_list); - pglimit = (size_limit_mb * 1024 * 1024) >> PAGE_SHIFT; + pglimit = ((u64)size_limit_mb * 1024 * 1024) >> PAGE_SHIFT; for (i = 0; i < head->count; i++) { if (!PAGE_ALIGNED(list[i].offset)) goto err; diff --git a/drivers/gpu/drm/drm_framebuffer.c b/drivers/gpu/drm/drm_framebuffer.c index 888aadb6a4..d6550b54fa 100644 --- a/drivers/gpu/drm/drm_framebuffer.c +++ b/drivers/gpu/drm/drm_framebuffer.c @@ -860,11 +860,23 @@ void drm_framebuffer_free(struct kref *kref) int drm_framebuffer_init(struct drm_device *dev, struct drm_framebuffer *fb, const struct drm_framebuffer_funcs *funcs) { + unsigned int i; int ret; + bool exists; if (WARN_ON_ONCE(fb->dev != dev || !fb->format)) return -EINVAL; + for (i = 0; i < fb->format->num_planes; i++) { + if (drm_WARN_ON_ONCE(dev, fb->internal_flags & DRM_FRAMEBUFFER_HAS_HANDLE_REF(i))) + fb->internal_flags &= ~DRM_FRAMEBUFFER_HAS_HANDLE_REF(i); + if (fb->obj[i]) { + exists = drm_gem_object_handle_get_if_exists_unlocked(fb->obj[i]); + if (exists) + fb->internal_flags |= DRM_FRAMEBUFFER_HAS_HANDLE_REF(i); + } + } + INIT_LIST_HEAD(&fb->filp_head); fb->funcs = funcs; @@ -873,7 +885,7 @@ int drm_framebuffer_init(struct drm_device *dev, struct drm_framebuffer *fb, ret = __drm_mode_object_add(dev, &fb->base, DRM_MODE_OBJECT_FB, false, drm_framebuffer_free); if (ret) - goto out; + goto err; mutex_lock(&dev->mode_config.fb_lock); dev->mode_config.num_fb++; @@ -881,7 +893,16 @@ int drm_framebuffer_init(struct drm_device *dev, struct drm_framebuffer *fb, mutex_unlock(&dev->mode_config.fb_lock); drm_mode_object_register(dev, &fb->base); -out: + + return 0; + +err: + for (i = 0; i < fb->format->num_planes; i++) { + if (fb->internal_flags & DRM_FRAMEBUFFER_HAS_HANDLE_REF(i)) { + drm_gem_object_handle_put_unlocked(fb->obj[i]); + fb->internal_flags &= ~DRM_FRAMEBUFFER_HAS_HANDLE_REF(i); + } + } return ret; } EXPORT_SYMBOL(drm_framebuffer_init); @@ -958,6 +979,12 @@ EXPORT_SYMBOL(drm_framebuffer_unregister_private); void drm_framebuffer_cleanup(struct drm_framebuffer *fb) { struct drm_device *dev = fb->dev; + unsigned int i; + + for (i = 0; i < fb->format->num_planes; i++) { + if (fb->internal_flags & DRM_FRAMEBUFFER_HAS_HANDLE_REF(i)) + drm_gem_object_handle_put_unlocked(fb->obj[i]); + } mutex_lock(&dev->mode_config.fb_lock); list_del(&fb->head); diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 149b8e25da..ae9e671bfc 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -186,6 +186,46 @@ void drm_gem_private_object_fini(struct drm_gem_object *obj) } EXPORT_SYMBOL(drm_gem_private_object_fini); +static void drm_gem_object_handle_get(struct drm_gem_object *obj) +{ + struct drm_device *dev = obj->dev; + + drm_WARN_ON(dev, !mutex_is_locked(&dev->object_name_lock)); + + if (obj->handle_count++ == 0) + drm_gem_object_get(obj); +} + +/** + * drm_gem_object_handle_get_if_exists_unlocked - acquire reference on user-space handle, if any + * @obj: GEM object + * + * Acquires a reference on the GEM buffer object's handle. Required to keep + * the GEM object alive. Call drm_gem_object_handle_put_if_exists_unlocked() + * to release the reference. Does nothing if the buffer object has no handle. + * + * Returns: + * True if a handle exists, or false otherwise + */ +bool drm_gem_object_handle_get_if_exists_unlocked(struct drm_gem_object *obj) +{ + struct drm_device *dev = obj->dev; + + guard(mutex)(&dev->object_name_lock); + + /* + * First ref taken during GEM object creation, if any. Some + * drivers set up internal framebuffers with GEM objects that + * do not have a GEM handle. Hence, this counter can be zero. + */ + if (!obj->handle_count) + return false; + + drm_gem_object_handle_get(obj); + + return true; +} + /** * drm_gem_object_handle_free - release resources bound to userspace handles * @obj: GEM object to clean up. @@ -216,20 +256,26 @@ static void drm_gem_object_exported_dma_buf_free(struct drm_gem_object *obj) } } -static void -drm_gem_object_handle_put_unlocked(struct drm_gem_object *obj) +/** + * drm_gem_object_handle_put_unlocked - releases reference on user-space handle + * @obj: GEM object + * + * Releases a reference on the GEM buffer object's handle. Possibly releases + * the GEM buffer object and associated dma-buf objects. + */ +void drm_gem_object_handle_put_unlocked(struct drm_gem_object *obj) { struct drm_device *dev = obj->dev; bool final = false; - if (WARN_ON(READ_ONCE(obj->handle_count) == 0)) + if (drm_WARN_ON(dev, READ_ONCE(obj->handle_count) == 0)) return; /* - * Must bump handle count first as this may be the last - * ref, in which case the object would disappear before we - * checked for a name - */ + * Must bump handle count first as this may be the last + * ref, in which case the object would disappear before + * we checked for a name. + */ mutex_lock(&dev->object_name_lock); if (--obj->handle_count == 0) { @@ -363,8 +409,8 @@ drm_gem_handle_create_tail(struct drm_file *file_priv, int ret; WARN_ON(!mutex_is_locked(&dev->object_name_lock)); - if (obj->handle_count++ == 0) - drm_gem_object_get(obj); + + drm_gem_object_handle_get(obj); /* * Get the user-visible handle using idr. Preload and perform diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h index 1705bfc90b..98b73c581c 100644 --- a/drivers/gpu/drm/drm_internal.h +++ b/drivers/gpu/drm/drm_internal.h @@ -153,6 +153,8 @@ void drm_sysfs_lease_event(struct drm_device *dev); /* drm_gem.c */ int drm_gem_init(struct drm_device *dev); +bool drm_gem_object_handle_get_if_exists_unlocked(struct drm_gem_object *obj); +void drm_gem_object_handle_put_unlocked(struct drm_gem_object *obj); int drm_gem_handle_create_tail(struct drm_file *file_priv, struct drm_gem_object *obj, u32 *handlep); diff --git a/drivers/gpu/drm/vkms/vkms_drv.c b/drivers/gpu/drm/vkms/vkms_drv.c index 0c1a713b7b..be642ee739 100644 --- a/drivers/gpu/drm/vkms/vkms_drv.c +++ b/drivers/gpu/drm/vkms/vkms_drv.c @@ -245,17 +245,19 @@ static int __init vkms_init(void) if (!config) return -ENOMEM; - default_config = config; - config->cursor = enable_cursor; config->writeback = enable_writeback; config->overlay = enable_overlay; ret = vkms_create(config); - if (ret) + if (ret) { kfree(config); + return ret; + } - return ret; + default_config = config; + + return 0; } static void vkms_destroy(struct vkms_config *config) @@ -279,9 +281,10 @@ static void vkms_destroy(struct vkms_config *config) static void __exit vkms_exit(void) { - if (default_config->dev) - vkms_destroy(default_config); + if (!default_config) + return; + vkms_destroy(default_config); kfree(default_config); } diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index a96976b22f..e4a347a19a 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -124,15 +124,18 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer, struct bio *bio = NULL; int ret; - if (has_metadata && !supports_metadata) - return -EINVAL; - + if (has_metadata && !supports_metadata) { + ret = -EINVAL; + goto out; + } if (ioucmd && (ioucmd->flags & IORING_URING_CMD_FIXED)) { struct iov_iter iter; /* fixedbufs is only for non-vectored io */ - if (WARN_ON_ONCE(flags & NVME_IOCTL_VEC)) - return -EINVAL; + if (flags & NVME_IOCTL_VEC) { + ret = -EINVAL; + goto out; + } ret = io_uring_cmd_import_fixed(ubuffer, bufflen, rq_data_dir(req), &iter, ioucmd); if (ret < 0) diff --git a/include/drm/drm_framebuffer.h b/include/drm/drm_framebuffer.h index 668077009f..38b24fc897 100644 --- a/include/drm/drm_framebuffer.h +++ b/include/drm/drm_framebuffer.h @@ -23,6 +23,7 @@ #ifndef __DRM_FRAMEBUFFER_H__ #define __DRM_FRAMEBUFFER_H__ +#include #include #include #include @@ -100,6 +101,8 @@ struct drm_framebuffer_funcs { unsigned num_clips); }; +#define DRM_FRAMEBUFFER_HAS_HANDLE_REF(_i) BIT(0u + (_i)) + /** * struct drm_framebuffer - frame buffer object * @@ -188,6 +191,10 @@ struct drm_framebuffer { * DRM_MODE_FB_MODIFIERS. */ int flags; + /** + * @internal_flags: Framebuffer flags like DRM_FRAMEBUFFER_HAS_HANDLE_REF. + */ + unsigned int internal_flags; /** * @filp_head: Placed on &drm_file.fbs, protected by &drm_file.fbs_lock. */ diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index fadf6ab964..2d2bfd3963 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -689,21 +689,16 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq) * * XXX could add max_slice to the augmented data to track this. */ -static s64 entity_lag(u64 avruntime, struct sched_entity *se) +static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se) { s64 vlag, limit; - vlag = avruntime - se->vruntime; - limit = calc_delta_fair(max_t(u64, 2*se->slice, TICK_NSEC), se); - - return clamp(vlag, -limit, limit); -} - -static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ SCHED_WARN_ON(!se->on_rq); - se->vlag = entity_lag(avg_vruntime(cfs_rq), se); + vlag = avg_vruntime(cfs_rq) - se->vruntime; + limit = calc_delta_fair(max_t(u64, 2*se->slice, TICK_NSEC), se); + + se->vlag = clamp(vlag, -limit, limit); } /* @@ -3774,137 +3769,33 @@ static inline void dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { } #endif -static void reweight_eevdf(struct sched_entity *se, u64 avruntime, - unsigned long weight) -{ - unsigned long old_weight = se->load.weight; - s64 vlag, vslice; - - /* - * VRUNTIME - * -------- - * - * COROLLARY #1: The virtual runtime of the entity needs to be - * adjusted if re-weight at !0-lag point. - * - * Proof: For contradiction assume this is not true, so we can - * re-weight without changing vruntime at !0-lag point. - * - * Weight VRuntime Avg-VRuntime - * before w v V - * after w' v' V' - * - * Since lag needs to be preserved through re-weight: - * - * lag = (V - v)*w = (V'- v')*w', where v = v' - * ==> V' = (V - v)*w/w' + v (1) - * - * Let W be the total weight of the entities before reweight, - * since V' is the new weighted average of entities: - * - * V' = (WV + w'v - wv) / (W + w' - w) (2) - * - * by using (1) & (2) we obtain: - * - * (WV + w'v - wv) / (W + w' - w) = (V - v)*w/w' + v - * ==> (WV-Wv+Wv+w'v-wv)/(W+w'-w) = (V - v)*w/w' + v - * ==> (WV - Wv)/(W + w' - w) + v = (V - v)*w/w' + v - * ==> (V - v)*W/(W + w' - w) = (V - v)*w/w' (3) - * - * Since we are doing at !0-lag point which means V != v, we - * can simplify (3): - * - * ==> W / (W + w' - w) = w / w' - * ==> Ww' = Ww + ww' - ww - * ==> W * (w' - w) = w * (w' - w) - * ==> W = w (re-weight indicates w' != w) - * - * So the cfs_rq contains only one entity, hence vruntime of - * the entity @v should always equal to the cfs_rq's weighted - * average vruntime @V, which means we will always re-weight - * at 0-lag point, thus breach assumption. Proof completed. - * - * - * COROLLARY #2: Re-weight does NOT affect weighted average - * vruntime of all the entities. - * - * Proof: According to corollary #1, Eq. (1) should be: - * - * (V - v)*w = (V' - v')*w' - * ==> v' = V' - (V - v)*w/w' (4) - * - * According to the weighted average formula, we have: - * - * V' = (WV - wv + w'v') / (W - w + w') - * = (WV - wv + w'(V' - (V - v)w/w')) / (W - w + w') - * = (WV - wv + w'V' - Vw + wv) / (W - w + w') - * = (WV + w'V' - Vw) / (W - w + w') - * - * ==> V'*(W - w + w') = WV + w'V' - Vw - * ==> V' * (W - w) = (W - w) * V (5) - * - * If the entity is the only one in the cfs_rq, then reweight - * always occurs at 0-lag point, so V won't change. Or else - * there are other entities, hence W != w, then Eq. (5) turns - * into V' = V. So V won't change in either case, proof done. - * - * - * So according to corollary #1 & #2, the effect of re-weight - * on vruntime should be: - * - * v' = V' - (V - v) * w / w' (4) - * = V - (V - v) * w / w' - * = V - vl * w / w' - * = V - vl' - */ - if (avruntime != se->vruntime) { - vlag = entity_lag(avruntime, se); - vlag = div_s64(vlag * old_weight, weight); - se->vruntime = avruntime - vlag; - } - - /* - * DEADLINE - * -------- - * - * When the weight changes, the virtual time slope changes and - * we should adjust the relative virtual deadline accordingly. - * - * d' = v' + (d - v)*w/w' - * = V' - (V - v)*w/w' + (d - v)*w/w' - * = V - (V - v)*w/w' + (d - v)*w/w' - * = V + (d - V)*w/w' - */ - vslice = (s64)(se->deadline - avruntime); - vslice = div_s64(vslice * old_weight, weight); - se->deadline = avruntime + vslice; -} +static void place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags); static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, unsigned long weight) { bool curr = cfs_rq->curr == se; - u64 avruntime; if (se->on_rq) { /* commit outstanding execution time */ update_curr(cfs_rq); - avruntime = avg_vruntime(cfs_rq); + update_entity_lag(cfs_rq, se); + se->deadline -= se->vruntime; + se->rel_deadline = 1; + cfs_rq->nr_running--; if (!curr) __dequeue_entity(cfs_rq, se); update_load_sub(&cfs_rq->load, se->load.weight); } dequeue_load_avg(cfs_rq, se); - if (se->on_rq) { - reweight_eevdf(se, avruntime, weight); - } else { - /* - * Because we keep se->vlag = V - v_i, while: lag_i = w_i*(V - v_i), - * we need to scale se->vlag when w_i changes. - */ - se->vlag = div_s64(se->vlag * se->load.weight, weight); - } + /* + * Because we keep se->vlag = V - v_i, while: lag_i = w_i*(V - v_i), + * we need to scale se->vlag when w_i changes. + */ + se->vlag = div_s64(se->vlag * se->load.weight, weight); + if (se->rel_deadline) + se->deadline = div_s64(se->deadline * se->load.weight, weight); update_load_set(&se->load, weight); @@ -3918,9 +3809,11 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, enqueue_load_avg(cfs_rq, se); if (se->on_rq) { + place_entity(cfs_rq, se, 0); update_load_add(&cfs_rq->load, se->load.weight); if (!curr) __enqueue_entity(cfs_rq, se); + cfs_rq->nr_running++; /* * The entity's vruntime has been adjusted, so let's check @@ -4065,7 +3958,11 @@ static void update_cfs_group(struct sched_entity *se) struct cfs_rq *gcfs_rq = group_cfs_rq(se); long shares; - if (!gcfs_rq) + /* + * When a group becomes empty, preserve its weight. This matters for + * DELAY_DEQUEUE. + */ + if (!gcfs_rq || !gcfs_rq->load.weight) return; if (throttled_hierarchy(gcfs_rq)) @@ -5291,7 +5188,7 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) * * EEVDF: placement strategy #1 / #2 */ - if (sched_feat(PLACE_LAG) && cfs_rq->nr_running) { + if (sched_feat(PLACE_LAG) && cfs_rq->nr_running && se->vlag) { struct sched_entity *curr = cfs_rq->curr; unsigned long load; @@ -5361,7 +5258,7 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) se->vruntime = vruntime - lag; - if (sched_feat(PLACE_REL_DEADLINE) && se->rel_deadline) { + if (se->rel_deadline) { se->deadline += se->vruntime; se->rel_deadline = 0; return; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index fe77c3b0ad..a3b1c212ac 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -784,15 +784,12 @@ static u32 qdisc_alloc_handle(struct net_device *dev) void qdisc_tree_reduce_backlog(struct Qdisc *sch, int n, int len) { - bool qdisc_is_offloaded = sch->flags & TCQ_F_OFFLOADED; const struct Qdisc_class_ops *cops; unsigned long cl; u32 parentid; bool notify; int drops; - if (n == 0 && len == 0) - return; drops = max_t(int, n, 0); rcu_read_lock(); while ((parentid = sch->parent)) { @@ -801,17 +798,8 @@ void qdisc_tree_reduce_backlog(struct Qdisc *sch, int n, int len) if (sch->flags & TCQ_F_NOPARENT) break; - /* Notify parent qdisc only if child qdisc becomes empty. - * - * If child was empty even before update then backlog - * counter is screwed and we skip notification because - * parent class is already passive. - * - * If the original child was offloaded then it is allowed - * to be seem as empty, so the parent is notified anyway. - */ - notify = !sch->q.qlen && !WARN_ON_ONCE(!n && - !qdisc_is_offloaded); + /* Notify parent qdisc only if child qdisc becomes empty. */ + notify = !sch->q.qlen; /* TODO: perform the search on a per txq basis */ sch = qdisc_lookup_rcu(qdisc_dev(sch), TC_H_MAJ(parentid)); if (sch == NULL) { @@ -820,6 +808,9 @@ void qdisc_tree_reduce_backlog(struct Qdisc *sch, int n, int len) } cops = sch->ops->cl_ops; if (notify && cops->qlen_notify) { + /* Note that qlen_notify must be idempotent as it may get called + * multiple times. + */ cl = cops->find(sch, parentid); cops->qlen_notify(sch, cl); } diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c index 3e8d4fe4d9..e1f6e7618d 100644 --- a/net/sched/sch_codel.c +++ b/net/sched/sch_codel.c @@ -65,10 +65,7 @@ static struct sk_buff *codel_qdisc_dequeue(struct Qdisc *sch) &q->stats, qdisc_pkt_len, codel_get_enqueue_time, drop_func, dequeue_func); - /* We cant call qdisc_tree_reduce_backlog() if our qlen is 0, - * or HTB crashes. Defer it for next round. - */ - if (q->stats.drop_count && sch->q.qlen) { + if (q->stats.drop_count) { qdisc_tree_reduce_backlog(sch, q->stats.drop_count, q->stats.drop_len); q->stats.drop_count = 0; q->stats.drop_len = 0; diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index c69b999fae..e0a81d313a 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -105,6 +105,7 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, return -ENOBUFS; gnet_stats_basic_sync_init(&cl->bstats); + INIT_LIST_HEAD(&cl->alist); cl->common.classid = classid; cl->quantum = quantum; cl->qdisc = qdisc_create_dflt(sch->dev_queue, @@ -229,7 +230,7 @@ static void drr_qlen_notify(struct Qdisc *csh, unsigned long arg) { struct drr_class *cl = (struct drr_class *)arg; - list_del(&cl->alist); + list_del_init(&cl->alist); } static int drr_dump_class(struct Qdisc *sch, unsigned long arg, @@ -390,7 +391,7 @@ static struct sk_buff *drr_dequeue(struct Qdisc *sch) if (unlikely(skb == NULL)) goto out; if (cl->qdisc->q.qlen == 0) - list_del(&cl->alist); + list_del_init(&cl->alist); bstats_update(&cl->bstats, skb); qdisc_bstats_update(sch, skb); @@ -431,7 +432,7 @@ static void drr_reset_qdisc(struct Qdisc *sch) for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) { if (cl->qdisc->q.qlen) - list_del(&cl->alist); + list_del_init(&cl->alist); qdisc_reset(cl->qdisc); } } diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index cc9baa719c..1ca098bf64 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -649,6 +649,12 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, sch_tree_lock(sch); + for (i = nbands; i < oldbands; i++) { + if (i >= q->nstrict && q->classes[i].qdisc->q.qlen) + list_del_init(&q->classes[i].alist); + qdisc_purge_queue(q->classes[i].qdisc); + } + WRITE_ONCE(q->nbands, nbands); for (i = nstrict; i < q->nstrict; i++) { if (q->classes[i].qdisc->q.qlen) { @@ -656,11 +662,6 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, q->classes[i].deficit = quanta[i]; } } - for (i = q->nbands; i < oldbands; i++) { - if (i >= q->nstrict && q->classes[i].qdisc->q.qlen) - list_del_init(&q->classes[i].alist); - qdisc_tree_flush_backlog(q->classes[i].qdisc); - } WRITE_ONCE(q->nstrict, nstrict); memcpy(q->prio2band, priomap, sizeof(priomap)); diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 4f908c11ba..778f6e5966 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -314,10 +314,8 @@ begin: } qdisc_bstats_update(sch, skb); flow->deficit -= qdisc_pkt_len(skb); - /* We cant call qdisc_tree_reduce_backlog() if our qlen is 0, - * or HTB crashes. Defer it for next round. - */ - if (q->cstats.drop_count && sch->q.qlen) { + + if (q->cstats.drop_count) { qdisc_tree_reduce_backlog(sch, q->cstats.drop_count, q->cstats.drop_len); q->cstats.drop_count = 0; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index ff3de37874..b2494d24a5 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -348,7 +348,8 @@ static void htb_add_to_wait_tree(struct htb_sched *q, */ static inline void htb_next_rb_node(struct rb_node **n) { - *n = rb_next(*n); + if (*n) + *n = rb_next(*n); } /** @@ -609,8 +610,8 @@ static inline void htb_activate(struct htb_sched *q, struct htb_class *cl) */ static inline void htb_deactivate(struct htb_sched *q, struct htb_class *cl) { - WARN_ON(!cl->prio_activity); - + if (!cl->prio_activity) + return; htb_deactivate_prios(q, cl); cl->prio_activity = 0; } @@ -1738,8 +1739,7 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg, if (cl->parent) cl->parent->children--; - if (cl->prio_activity) - htb_deactivate(q, cl); + htb_deactivate(q, cl); if (cl->cmode != HTB_CAN_SEND) htb_safe_rb_erase(&cl->pq_node, @@ -1947,8 +1947,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, /* turn parent into inner node */ qdisc_purge_queue(parent->leaf.q); parent_qdisc = parent->leaf.q; - if (parent->prio_activity) - htb_deactivate(q, parent); + htb_deactivate(q, parent); /* remove from evt list because of level change */ if (parent->cmode != HTB_CAN_SEND) { diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index d584c0c258..d1e6f9fcc0 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -347,7 +347,7 @@ static void qfq_deactivate_class(struct qfq_sched *q, struct qfq_class *cl) struct qfq_aggregate *agg = cl->agg; - list_del(&cl->alist); /* remove from RR queue of the aggregate */ + list_del_init(&cl->alist); /* remove from RR queue of the aggregate */ if (list_empty(&agg->active)) /* agg is now inactive */ qfq_deactivate_agg(q, agg); } @@ -477,6 +477,7 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, gnet_stats_basic_sync_init(&cl->bstats); cl->common.classid = classid; cl->deficit = lmax; + INIT_LIST_HEAD(&cl->alist); cl->qdisc = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid, NULL); @@ -985,7 +986,7 @@ static struct sk_buff *agg_dequeue(struct qfq_aggregate *agg, cl->deficit -= (int) len; if (cl->qdisc->q.qlen == 0) /* no more packets, remove from list */ - list_del(&cl->alist); + list_del_init(&cl->alist); else if (cl->deficit < qdisc_pkt_len(cl->qdisc->ops->peek(cl->qdisc))) { cl->deficit += agg->lmax; list_move_tail(&cl->alist, &agg->active); @@ -1418,6 +1419,8 @@ static void qfq_qlen_notify(struct Qdisc *sch, unsigned long arg) struct qfq_sched *q = qdisc_priv(sch); struct qfq_class *cl = (struct qfq_class *)arg; + if (list_empty(&cl->alist)) + return; qfq_deactivate_class(q, cl); }