- Linux-stable-mirror - lists.linaro.org

[tip: sched/core] sched/eevdf: Fix min_vruntime vs avg_vruntime

by tip-bot2 for Peter Zijlstra

The following commit has been merged into the sched/core branch of tip: Commit-ID: 79f3f9bedd149ea438aaeb0fb6a083637affe205 Gitweb: https://git.kernel.org/tip/79f3f9bedd149ea438aaeb0fb6a083637affe205 Author: Peter Zijlstra <peterz(a)infradead.org> AuthorDate: Wed, 02 Apr 2025 20:07:34 +02:00 Committer: Peter Zijlstra <peterz(a)infradead.org> CommitterDate: Tue, 11 Nov 2025 12:33:38 +01:00 sched/eevdf: Fix min_vruntime vs avg_vruntime Basically, from the constraint that the sum of lag is zero, you can infer that the 0-lag point is the weighted average of the individual vruntime, which is what we're trying to compute: \Sum w_i * v_i avg = -------------- \Sum w_i Now, since vruntime takes the whole u64 (worse, it wraps), this multiplication term in the numerator is not something we can compute; instead we do the min_vruntime (v0 henceforth) thing like: v_i = (v_i - v0) + v0 This does two things: - it keeps the key: (v_i - v0) 'small'; - it creates a relative 0-point in the modular space. If you do that subtitution and work it all out, you end up with: \Sum w_i * (v_i - v0) avg = --------------------- + v0 \Sum w_i Since you cannot very well track a ratio like that (and not suffer terrible numerical problems) we simpy track the numerator and denominator individually and only perform the division when strictly needed. Notably, the numerator lives in cfs_rq->avg_vruntime and the denominator lives in cfs_rq->avg_load. The one extra 'funny' is that these numbers track the entities in the tree, and current is typically outside of the tree, so avg_vruntime() adds current when needed before doing the division. (vruntime_eligible() elides the division by cross-wise multiplication) Anyway, as mentioned above, we currently use the CFS era min_vruntime for this purpose. However, this thing can only move forward, while the above avg can in fact move backward (when a non-eligible task leaves, the average becomes smaller), this can cause trouble when through happenstance (or construction) these values drift far enough apart to wreck the game. Replace cfs_rq::min_vruntime with cfs_rq::zero_vruntime which is kept near/at avg_vruntime, following its motion. The down-side is that this requires computing the avg more often. Fixes: 147f3efaa241 ("sched/fair: Implement an EEVDF-like scheduling policy") Reported-by: Zicheng Qu <quzicheng(a)huawei.com> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Link: https://patch.msgid.link/20251106111741.GC4068168@noisy.programming.kicks-a… Cc: stable(a)vger.kernel.org --- kernel/sched/debug.c | 8 +-- kernel/sched/fair.c | 114 +++++++++--------------------------------- kernel/sched/sched.h | 4 +- 3 files changed, 31 insertions(+), 95 deletions(-) diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 02e16b7..41caa22 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -796,7 +796,7 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu) void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) { - s64 left_vruntime = -1, min_vruntime, right_vruntime = -1, left_deadline = -1, spread; + s64 left_vruntime = -1, zero_vruntime, right_vruntime = -1, left_deadline = -1, spread; struct sched_entity *last, *first, *root; struct rq *rq = cpu_rq(cpu); unsigned long flags; @@ -819,15 +819,15 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) last = __pick_last_entity(cfs_rq); if (last) right_vruntime = last->vruntime; - min_vruntime = cfs_rq->min_vruntime; + zero_vruntime = cfs_rq->zero_vruntime; raw_spin_rq_unlock_irqrestore(rq, flags); SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "left_deadline", SPLIT_NS(left_deadline)); SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "left_vruntime", SPLIT_NS(left_vruntime)); - SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "min_vruntime", - SPLIT_NS(min_vruntime)); + SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "zero_vruntime", + SPLIT_NS(zero_vruntime)); SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "avg_vruntime", SPLIT_NS(avg_vruntime(cfs_rq))); SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "right_vruntime", diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 4a11a83..8d971d4 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -554,7 +554,7 @@ static inline bool entity_before(const struct sched_entity *a, static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se) { - return (s64)(se->vruntime - cfs_rq->min_vruntime); + return (s64)(se->vruntime - cfs_rq->zero_vruntime); } #define __node_2_se(node) \ @@ -606,13 +606,13 @@ static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se) * * Which we track using: * - * v0 := cfs_rq->min_vruntime + * v0 := cfs_rq->zero_vruntime * \Sum (v_i - v0) * w_i := cfs_rq->avg_vruntime * \Sum w_i := cfs_rq->avg_load * - * Since min_vruntime is a monotonic increasing variable that closely tracks - * the per-task service, these deltas: (v_i - v), will be in the order of the - * maximal (virtual) lag induced in the system due to quantisation. + * Since zero_vruntime closely tracks the per-task service, these + * deltas: (v_i - v), will be in the order of the maximal (virtual) lag + * induced in the system due to quantisation. * * Also, we use scale_load_down() to reduce the size. * @@ -671,7 +671,7 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq) avg = div_s64(avg, load); } - return cfs_rq->min_vruntime + avg; + return cfs_rq->zero_vruntime + avg; } /* @@ -732,7 +732,7 @@ static int vruntime_eligible(struct cfs_rq *cfs_rq, u64 vruntime) load += weight; } - return avg >= (s64)(vruntime - cfs_rq->min_vruntime) * load; + return avg >= (s64)(vruntime - cfs_rq->zero_vruntime) * load; } int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se) @@ -740,42 +740,14 @@ int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se) return vruntime_eligible(cfs_rq, se->vruntime); } -static u64 __update_min_vruntime(struct cfs_rq *cfs_rq, u64 vruntime) +static void update_zero_vruntime(struct cfs_rq *cfs_rq) { - u64 min_vruntime = cfs_rq->min_vruntime; - /* - * open coded max_vruntime() to allow updating avg_vruntime - */ - s64 delta = (s64)(vruntime - min_vruntime); - if (delta > 0) { - avg_vruntime_update(cfs_rq, delta); - min_vruntime = vruntime; - } - return min_vruntime; -} + u64 vruntime = avg_vruntime(cfs_rq); + s64 delta = (s64)(vruntime - cfs_rq->zero_vruntime); -static void update_min_vruntime(struct cfs_rq *cfs_rq) -{ - struct sched_entity *se = __pick_root_entity(cfs_rq); - struct sched_entity *curr = cfs_rq->curr; - u64 vruntime = cfs_rq->min_vruntime; - - if (curr) { - if (curr->on_rq) - vruntime = curr->vruntime; - else - curr = NULL; - } + avg_vruntime_update(cfs_rq, delta); - if (se) { - if (!curr) - vruntime = se->min_vruntime; - else - vruntime = min_vruntime(vruntime, se->min_vruntime); - } - - /* ensure we never gain time by being placed backwards. */ - cfs_rq->min_vruntime = __update_min_vruntime(cfs_rq, vruntime); + cfs_rq->zero_vruntime = vruntime; } static inline u64 cfs_rq_min_slice(struct cfs_rq *cfs_rq) @@ -848,6 +820,7 @@ RB_DECLARE_CALLBACKS(static, min_vruntime_cb, struct sched_entity, static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) { avg_vruntime_add(cfs_rq, se); + update_zero_vruntime(cfs_rq); se->min_vruntime = se->vruntime; se->min_slice = se->slice; rb_add_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline, @@ -859,6 +832,7 @@ static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) rb_erase_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline, &min_vruntime_cb); avg_vruntime_sub(cfs_rq, se); + update_zero_vruntime(cfs_rq); } struct sched_entity *__pick_root_entity(struct cfs_rq *cfs_rq) @@ -1226,7 +1200,6 @@ static void update_curr(struct cfs_rq *cfs_rq) curr->vruntime += calc_delta_fair(delta_exec, curr); resched = update_deadline(cfs_rq, curr); - update_min_vruntime(cfs_rq); if (entity_is_task(curr)) { /* @@ -3808,15 +3781,6 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, if (!curr) __enqueue_entity(cfs_rq, se); cfs_rq->nr_queued++; - - /* - * The entity's vruntime has been adjusted, so let's check - * whether the rq-wide min_vruntime needs updated too. Since - * the calculations above require stable min_vruntime rather - * than up-to-date one, we do the update at the end of the - * reweight process. - */ - update_min_vruntime(cfs_rq); } } @@ -5429,15 +5393,6 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) update_cfs_group(se); - /* - * Now advance min_vruntime if @se was the entity holding it back, - * except when: DEQUEUE_SAVE && !DEQUEUE_MOVE, in this case we'll be - * put back on, and if we advance min_vruntime, we'll be placed back - * further than we started -- i.e. we'll be penalized. - */ - if ((flags & (DEQUEUE_SAVE | DEQUEUE_MOVE)) != DEQUEUE_SAVE) - update_min_vruntime(cfs_rq); - if (flags & DEQUEUE_DELAYED) finish_delayed_dequeue_entity(se); @@ -9015,7 +8970,6 @@ static void yield_task_fair(struct rq *rq) if (entity_eligible(cfs_rq, se)) { se->vruntime = se->deadline; se->deadline += calc_delta_fair(se->slice, se); - update_min_vruntime(cfs_rq); } } @@ -13078,23 +13032,6 @@ static inline void task_tick_core(struct rq *rq, struct task_struct *curr) * Which shows that S and s_i transform alike (which makes perfect sense * given that S is basically the (weighted) average of s_i). * - * Then: - * - * x -> s_min := min{s_i} (8) - * - * to obtain: - * - * \Sum_i w_i (s_i - s_min) - * S = s_min + ------------------------ (9) - * \Sum_i w_i - * - * Which already looks familiar, and is the basis for our current - * approximation: - * - * S ~= s_min (10) - * - * Now, obviously, (10) is absolute crap :-), but it sorta works. - * * So the thing to remember is that the above is strictly UP. It is * possible to generalize to multiple runqueues -- however it gets really * yuck when you have to add affinity support, as illustrated by our very @@ -13116,23 +13053,23 @@ static inline void task_tick_core(struct rq *rq, struct task_struct *curr) * Let, for our runqueue 'k': * * T_k = \Sum_i w_i s_i - * W_k = \Sum_i w_i ; for all i of k (11) + * W_k = \Sum_i w_i ; for all i of k (8) * * Then we can write (6) like: * * T_k - * S_k = --- (12) + * S_k = --- (9) * W_k * * From which immediately follows that: * * T_k + T_l - * S_k+l = --------- (13) + * S_k+l = --------- (10) * W_k + W_l * * On which we can define a combined lag: * - * lag_k+l(i) := S_k+l - s_i (14) + * lag_k+l(i) := S_k+l - s_i (11) * * And that gives us the tools to compare tasks across a combined runqueue. * @@ -13143,7 +13080,7 @@ static inline void task_tick_core(struct rq *rq, struct task_struct *curr) * using (7); this only requires storing single 'time'-stamps. * * b) when comparing tasks between 2 runqueues of which one is forced-idle, - * compare the combined lag, per (14). + * compare the combined lag, per (11). * * Now, of course cgroups (I so hate them) make this more interesting in * that a) seems to suggest we need to iterate all cgroup on a CPU at such @@ -13191,12 +13128,11 @@ static inline void task_tick_core(struct rq *rq, struct task_struct *curr) * every tick. This limits the observed divergence due to the work * conservancy. * - * On top of that, we can improve upon things by moving away from our - * horrible (10) hack and moving to (9) and employing (13) here. + * On top of that, we can improve upon things by employing (10) here. */ /* - * se_fi_update - Update the cfs_rq->min_vruntime_fi in a CFS hierarchy if needed. + * se_fi_update - Update the cfs_rq->zero_vruntime_fi in a CFS hierarchy if needed. */ static void se_fi_update(const struct sched_entity *se, unsigned int fi_seq, bool forceidle) @@ -13210,7 +13146,7 @@ static void se_fi_update(const struct sched_entity *se, unsigned int fi_seq, cfs_rq->forceidle_seq = fi_seq; } - cfs_rq->min_vruntime_fi = cfs_rq->min_vruntime; + cfs_rq->zero_vruntime_fi = cfs_rq->zero_vruntime; } } @@ -13263,11 +13199,11 @@ bool cfs_prio_less(const struct task_struct *a, const struct task_struct *b, /* * Find delta after normalizing se's vruntime with its cfs_rq's - * min_vruntime_fi, which would have been updated in prior calls + * zero_vruntime_fi, which would have been updated in prior calls * to se_fi_update(). */ delta = (s64)(sea->vruntime - seb->vruntime) + - (s64)(cfs_rqb->min_vruntime_fi - cfs_rqa->min_vruntime_fi); + (s64)(cfs_rqb->zero_vruntime_fi - cfs_rqa->zero_vruntime_fi); return delta > 0; } @@ -13513,7 +13449,7 @@ static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first) void init_cfs_rq(struct cfs_rq *cfs_rq) { cfs_rq->tasks_timeline = RB_ROOT_CACHED; - cfs_rq->min_vruntime = (u64)(-(1LL << 20)); + cfs_rq->zero_vruntime = (u64)(-(1LL << 20)); raw_spin_lock_init(&cfs_rq->removed.lock); } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 82e74e8..5a3cf81 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -681,10 +681,10 @@ struct cfs_rq { s64 avg_vruntime; u64 avg_load; - u64 min_vruntime; + u64 zero_vruntime; #ifdef CONFIG_SCHED_CORE unsigned int forceidle_seq; - u64 min_vruntime_fi; + u64 zero_vruntime_fi; #endif struct rb_root_cached tasks_timeline;

1 day, 6 hours

1
0
0 0

[PATCH 6/6] Revert "PCI: dwc: Don't wait for link up if driver can detect Link Up event"

by Niklas Cassel

This reverts commit 8d3bf19f1b585a3cc0027f508b64c33484db8d0d. While this fake hotplugging was a nice idea, it has shown that this feature does not handle PCIe switches correctly: pci_bus 0004:43: busn_res: can not insert [bus 43-41] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci_bus 0004:43: busn_res: [bus 43-41] end is updated to 43 pci_bus 0004:43: busn_res: can not insert [bus 43] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci 0004:42:00.0: devices behind bridge are unusable because [bus 43] cannot be assigned for them pci_bus 0004:44: busn_res: can not insert [bus 44-41] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci_bus 0004:44: busn_res: [bus 44-41] end is updated to 44 pci_bus 0004:44: busn_res: can not insert [bus 44] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci 0004:42:02.0: devices behind bridge are unusable because [bus 44] cannot be assigned for them pci_bus 0004:45: busn_res: can not insert [bus 45-41] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci_bus 0004:45: busn_res: [bus 45-41] end is updated to 45 pci_bus 0004:45: busn_res: can not insert [bus 45] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci 0004:42:06.0: devices behind bridge are unusable because [bus 45] cannot be assigned for them pci_bus 0004:46: busn_res: can not insert [bus 46-41] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci_bus 0004:46: busn_res: [bus 46-41] end is updated to 46 pci_bus 0004:46: busn_res: can not insert [bus 46] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci 0004:42:0e.0: devices behind bridge are unusable because [bus 46] cannot be assigned for them pci_bus 0004:42: busn_res: [bus 42-41] end is updated to 46 pci_bus 0004:42: busn_res: can not insert [bus 42-46] under [bus 41] (conflicts with (null) [bus 41]) pci 0004:41:00.0: devices behind bridge are unusable because [bus 42-46] cannot be assigned for them pcieport 0004:40:00.0: bridge has subordinate 41 but max busn 46 During the initial scan, PCI core doesn't see the switch and since the Root Port is not hot plug capable, the secondary bus number gets assigned as the subordinate bus number. This means, the PCI core assumes that only one bus will appear behind the Root Port since the Root Port is not hot plug capable. This works perfectly fine for PCIe endpoints connected to the Root Port, since they don't extend the bus. However, if a PCIe switch is connected, then there is a problem when the downstream busses starts showing up and the PCI core doesn't extend the subordinate bus number after initial scan during boot. The long term plan is to migrate this driver to the pwrctrl framework, once it adds proper support for powering up and enumerating PCIe switches. Cc: stable(a)vger.kernel.org Suggested-by: Manivannan Sadhasivam <mani(a)kernel.org> Signed-off-by: Niklas Cassel <cassel(a)kernel.org> --- drivers/pci/controller/dwc/pcie-designware-host.c | 10 ++-------- drivers/pci/controller/dwc/pcie-designware.h | 1 - 2 files changed, 2 insertions(+), 9 deletions(-) diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c index e92513c5bda5..f7e13dc16653 100644 --- a/drivers/pci/controller/dwc/pcie-designware-host.c +++ b/drivers/pci/controller/dwc/pcie-designware-host.c @@ -664,14 +664,8 @@ int dw_pcie_host_init(struct dw_pcie_rp *pp) goto err_remove_edma; } - /* - * Note: Skip the link up delay only when a Link Up IRQ is present. - * If there is no Link Up IRQ, we should not bypass the delay - * because that would require users to manually rescan for devices. - */ - if (!pp->use_linkup_irq) - /* Ignore errors, the link may come up later */ - dw_pcie_wait_for_link(pci); + /* Ignore errors, the link may come up later */ + dw_pcie_wait_for_link(pci); ret = pci_host_probe(bridge); if (ret) diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h index e995f692a1ec..640827e9d093 100644 --- a/drivers/pci/controller/dwc/pcie-designware.h +++ b/drivers/pci/controller/dwc/pcie-designware.h @@ -426,7 +426,6 @@ struct dw_pcie_rp { bool use_atu_msg; int msg_atu_index; struct resource *msg_res; - bool use_linkup_irq; struct pci_eq_presets presets; struct pci_config_window *cfg; bool ecam_enabled; -- 2.51.1

1 day, 6 hours

1
0
0 0

[PATCH 5/6] Revert "PCI: qcom: Enumerate endpoints based on Link up event in 'global_irq' interrupt"

by Niklas Cassel

This reverts commit 4581403f67929d02c197cb187c4e1e811c9e762a. While this fake hotplugging was a nice idea, it has shown that this feature does not handle PCIe switches correctly: pci_bus 0004:43: busn_res: can not insert [bus 43-41] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci_bus 0004:43: busn_res: [bus 43-41] end is updated to 43 pci_bus 0004:43: busn_res: can not insert [bus 43] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci 0004:42:00.0: devices behind bridge are unusable because [bus 43] cannot be assigned for them pci_bus 0004:44: busn_res: can not insert [bus 44-41] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci_bus 0004:44: busn_res: [bus 44-41] end is updated to 44 pci_bus 0004:44: busn_res: can not insert [bus 44] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci 0004:42:02.0: devices behind bridge are unusable because [bus 44] cannot be assigned for them pci_bus 0004:45: busn_res: can not insert [bus 45-41] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci_bus 0004:45: busn_res: [bus 45-41] end is updated to 45 pci_bus 0004:45: busn_res: can not insert [bus 45] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci 0004:42:06.0: devices behind bridge are unusable because [bus 45] cannot be assigned for them pci_bus 0004:46: busn_res: can not insert [bus 46-41] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci_bus 0004:46: busn_res: [bus 46-41] end is updated to 46 pci_bus 0004:46: busn_res: can not insert [bus 46] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci 0004:42:0e.0: devices behind bridge are unusable because [bus 46] cannot be assigned for them pci_bus 0004:42: busn_res: [bus 42-41] end is updated to 46 pci_bus 0004:42: busn_res: can not insert [bus 42-46] under [bus 41] (conflicts with (null) [bus 41]) pci 0004:41:00.0: devices behind bridge are unusable because [bus 42-46] cannot be assigned for them pcieport 0004:40:00.0: bridge has subordinate 41 but max busn 46 During the initial scan, PCI core doesn't see the switch and since the Root Port is not hot plug capable, the secondary bus number gets assigned as the subordinate bus number. This means, the PCI core assumes that only one bus will appear behind the Root Port since the Root Port is not hot plug capable. This works perfectly fine for PCIe endpoints connected to the Root Port, since they don't extend the bus. However, if a PCIe switch is connected, then there is a problem when the downstream busses starts showing up and the PCI core doesn't extend the subordinate bus number after initial scan during boot. The long term plan is to migrate this driver to the pwrctrl framework, once it adds proper support for powering up and enumerating PCIe switches. Cc: stable(a)vger.kernel.org Suggested-by: Manivannan Sadhasivam <mani(a)kernel.org> Signed-off-by: Niklas Cassel <cassel(a)kernel.org> --- drivers/pci/controller/dwc/pcie-qcom.c | 58 +------------------------- 1 file changed, 1 insertion(+), 57 deletions(-) diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c index 28f5f7acb92a..b10e8adc79bb 100644 --- a/drivers/pci/controller/dwc/pcie-qcom.c +++ b/drivers/pci/controller/dwc/pcie-qcom.c @@ -55,9 +55,6 @@ #define PARF_AXI_MSTR_WR_ADDR_HALT_V2 0x1a8 #define PARF_Q2A_FLUSH 0x1ac #define PARF_LTSSM 0x1b0 -#define PARF_INT_ALL_STATUS 0x224 -#define PARF_INT_ALL_CLEAR 0x228 -#define PARF_INT_ALL_MASK 0x22c #define PARF_SID_OFFSET 0x234 #define PARF_BDF_TRANSLATE_CFG 0x24c #define PARF_DBI_BASE_ADDR_V2 0x350 @@ -134,9 +131,6 @@ /* PARF_LTSSM register fields */ #define LTSSM_EN BIT(8) -/* PARF_INT_ALL_{STATUS/CLEAR/MASK} register fields */ -#define PARF_INT_ALL_LINK_UP BIT(13) - /* PARF_NO_SNOOP_OVERRIDE register fields */ #define WR_NO_SNOOP_OVERRIDE_EN BIT(1) #define RD_NO_SNOOP_OVERRIDE_EN BIT(3) @@ -1604,32 +1598,6 @@ static void qcom_pcie_init_debugfs(struct qcom_pcie *pcie) qcom_pcie_link_transition_count); } -static irqreturn_t qcom_pcie_global_irq_thread(int irq, void *data) -{ - struct qcom_pcie *pcie = data; - struct dw_pcie_rp *pp = &pcie->pci->pp; - struct device *dev = pcie->pci->dev; - u32 status = readl_relaxed(pcie->parf + PARF_INT_ALL_STATUS); - - writel_relaxed(status, pcie->parf + PARF_INT_ALL_CLEAR); - - if (FIELD_GET(PARF_INT_ALL_LINK_UP, status)) { - msleep(PCIE_RESET_CONFIG_WAIT_MS); - dev_dbg(dev, "Received Link up event. Starting enumeration!\n"); - /* Rescan the bus to enumerate endpoint devices */ - pci_lock_rescan_remove(); - pci_rescan_bus(pp->bridge->bus); - pci_unlock_rescan_remove(); - - qcom_pcie_icc_opp_update(pcie); - } else { - dev_WARN_ONCE(dev, 1, "Received unknown event. INT_STATUS: 0x%08x\n", - status); - } - - return IRQ_HANDLED; -} - static void qcom_pci_free_msi(void *ptr) { struct dw_pcie_rp *pp = (struct dw_pcie_rp *)ptr; @@ -1774,8 +1742,7 @@ static int qcom_pcie_probe(struct platform_device *pdev) struct dw_pcie_rp *pp; struct resource *res; struct dw_pcie *pci; - int ret, irq; - char *name; + int ret; pcie_cfg = of_device_get_match_data(dev); if (!pcie_cfg) { @@ -1932,27 +1899,6 @@ static int qcom_pcie_probe(struct platform_device *pdev) goto err_phy_exit; } - name = devm_kasprintf(dev, GFP_KERNEL, "qcom_pcie_global_irq%d", - pci_domain_nr(pp->bridge->bus)); - if (!name) { - ret = -ENOMEM; - goto err_host_deinit; - } - - irq = platform_get_irq_byname_optional(pdev, "global"); - if (irq > 0) { - ret = devm_request_threaded_irq(&pdev->dev, irq, NULL, - qcom_pcie_global_irq_thread, - IRQF_ONESHOT, name, pcie); - if (ret) { - dev_err_probe(&pdev->dev, ret, - "Failed to request Global IRQ\n"); - goto err_host_deinit; - } - - writel_relaxed(PARF_INT_ALL_LINK_UP, pcie->parf + PARF_INT_ALL_MASK); - } - qcom_pcie_icc_opp_update(pcie); if (pcie->mhi) @@ -1960,8 +1906,6 @@ static int qcom_pcie_probe(struct platform_device *pdev) return 0; -err_host_deinit: - dw_pcie_host_deinit(pp); err_phy_exit: list_for_each_entry_safe(port, tmp, &pcie->ports, list) { phy_exit(port->phy); -- 2.51.1

1 day, 6 hours

1
0
0 0

[PATCH 4/6] Revert "PCI: qcom: Enable MSI interrupts together with Link up if 'Global IRQ' is supported"

by Niklas Cassel

This reverts commit ba4a2e2317b9faeca9193ed6d3193ddc3cf2aba3. While this fake hotplugging was a nice idea, it has shown that this feature does not handle PCIe switches correctly: pci_bus 0004:43: busn_res: can not insert [bus 43-41] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci_bus 0004:43: busn_res: [bus 43-41] end is updated to 43 pci_bus 0004:43: busn_res: can not insert [bus 43] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci 0004:42:00.0: devices behind bridge are unusable because [bus 43] cannot be assigned for them pci_bus 0004:44: busn_res: can not insert [bus 44-41] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci_bus 0004:44: busn_res: [bus 44-41] end is updated to 44 pci_bus 0004:44: busn_res: can not insert [bus 44] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci 0004:42:02.0: devices behind bridge are unusable because [bus 44] cannot be assigned for them pci_bus 0004:45: busn_res: can not insert [bus 45-41] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci_bus 0004:45: busn_res: [bus 45-41] end is updated to 45 pci_bus 0004:45: busn_res: can not insert [bus 45] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci 0004:42:06.0: devices behind bridge are unusable because [bus 45] cannot be assigned for them pci_bus 0004:46: busn_res: can not insert [bus 46-41] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci_bus 0004:46: busn_res: [bus 46-41] end is updated to 46 pci_bus 0004:46: busn_res: can not insert [bus 46] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci 0004:42:0e.0: devices behind bridge are unusable because [bus 46] cannot be assigned for them pci_bus 0004:42: busn_res: [bus 42-41] end is updated to 46 pci_bus 0004:42: busn_res: can not insert [bus 42-46] under [bus 41] (conflicts with (null) [bus 41]) pci 0004:41:00.0: devices behind bridge are unusable because [bus 42-46] cannot be assigned for them pcieport 0004:40:00.0: bridge has subordinate 41 but max busn 46 During the initial scan, PCI core doesn't see the switch and since the Root Port is not hot plug capable, the secondary bus number gets assigned as the subordinate bus number. This means, the PCI core assumes that only one bus will appear behind the Root Port since the Root Port is not hot plug capable. This works perfectly fine for PCIe endpoints connected to the Root Port, since they don't extend the bus. However, if a PCIe switch is connected, then there is a problem when the downstream busses starts showing up and the PCI core doesn't extend the subordinate bus number after initial scan during boot. The long term plan is to migrate this driver to the pwrctrl framework, once it adds proper support for powering up and enumerating PCIe switches. Cc: stable(a)vger.kernel.org Suggested-by: Manivannan Sadhasivam <mani(a)kernel.org> Signed-off-by: Niklas Cassel <cassel(a)kernel.org> --- drivers/pci/controller/dwc/pcie-qcom.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c index 70c0ae8b7523..28f5f7acb92a 100644 --- a/drivers/pci/controller/dwc/pcie-qcom.c +++ b/drivers/pci/controller/dwc/pcie-qcom.c @@ -136,7 +136,6 @@ /* PARF_INT_ALL_{STATUS/CLEAR/MASK} register fields */ #define PARF_INT_ALL_LINK_UP BIT(13) -#define PARF_INT_MSI_DEV_0_7 GENMASK(30, 23) /* PARF_NO_SNOOP_OVERRIDE register fields */ #define WR_NO_SNOOP_OVERRIDE_EN BIT(1) @@ -1951,8 +1950,7 @@ static int qcom_pcie_probe(struct platform_device *pdev) goto err_host_deinit; } - writel_relaxed(PARF_INT_ALL_LINK_UP | PARF_INT_MSI_DEV_0_7, - pcie->parf + PARF_INT_ALL_MASK); + writel_relaxed(PARF_INT_ALL_LINK_UP, pcie->parf + PARF_INT_ALL_MASK); } qcom_pcie_icc_opp_update(pcie); -- 2.51.1

1 day, 6 hours

1
0
0 0

[PATCH 3/6] Revert "PCI: qcom: Don't wait for link if we can detect Link Up"

by Niklas Cassel

This reverts commit 36971d6c5a9a134c15760ae9fd13c6d5f9a36abb. While this fake hotplugging was a nice idea, it has shown that this feature does not handle PCIe switches correctly: pci_bus 0004:43: busn_res: can not insert [bus 43-41] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci_bus 0004:43: busn_res: [bus 43-41] end is updated to 43 pci_bus 0004:43: busn_res: can not insert [bus 43] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci 0004:42:00.0: devices behind bridge are unusable because [bus 43] cannot be assigned for them pci_bus 0004:44: busn_res: can not insert [bus 44-41] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci_bus 0004:44: busn_res: [bus 44-41] end is updated to 44 pci_bus 0004:44: busn_res: can not insert [bus 44] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci 0004:42:02.0: devices behind bridge are unusable because [bus 44] cannot be assigned for them pci_bus 0004:45: busn_res: can not insert [bus 45-41] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci_bus 0004:45: busn_res: [bus 45-41] end is updated to 45 pci_bus 0004:45: busn_res: can not insert [bus 45] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci 0004:42:06.0: devices behind bridge are unusable because [bus 45] cannot be assigned for them pci_bus 0004:46: busn_res: can not insert [bus 46-41] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci_bus 0004:46: busn_res: [bus 46-41] end is updated to 46 pci_bus 0004:46: busn_res: can not insert [bus 46] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci 0004:42:0e.0: devices behind bridge are unusable because [bus 46] cannot be assigned for them pci_bus 0004:42: busn_res: [bus 42-41] end is updated to 46 pci_bus 0004:42: busn_res: can not insert [bus 42-46] under [bus 41] (conflicts with (null) [bus 41]) pci 0004:41:00.0: devices behind bridge are unusable because [bus 42-46] cannot be assigned for them pcieport 0004:40:00.0: bridge has subordinate 41 but max busn 46 During the initial scan, PCI core doesn't see the switch and since the Root Port is not hot plug capable, the secondary bus number gets assigned as the subordinate bus number. This means, the PCI core assumes that only one bus will appear behind the Root Port since the Root Port is not hot plug capable. This works perfectly fine for PCIe endpoints connected to the Root Port, since they don't extend the bus. However, if a PCIe switch is connected, then there is a problem when the downstream busses starts showing up and the PCI core doesn't extend the subordinate bus number after initial scan during boot. The long term plan is to migrate this driver to the pwrctrl framework, once it adds proper support for powering up and enumerating PCIe switches. Cc: stable(a)vger.kernel.org Suggested-by: Manivannan Sadhasivam <mani(a)kernel.org> Signed-off-by: Niklas Cassel <cassel(a)kernel.org> --- drivers/pci/controller/dwc/pcie-qcom.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c index c48a20602d7f..70c0ae8b7523 100644 --- a/drivers/pci/controller/dwc/pcie-qcom.c +++ b/drivers/pci/controller/dwc/pcie-qcom.c @@ -1927,10 +1927,6 @@ static int qcom_pcie_probe(struct platform_device *pdev) platform_set_drvdata(pdev, pcie); - irq = platform_get_irq_byname_optional(pdev, "global"); - if (irq > 0) - pp->use_linkup_irq = true; - ret = dw_pcie_host_init(pp); if (ret) { dev_err(dev, "cannot initialize host\n"); @@ -1944,6 +1940,7 @@ static int qcom_pcie_probe(struct platform_device *pdev) goto err_host_deinit; } + irq = platform_get_irq_byname_optional(pdev, "global"); if (irq > 0) { ret = devm_request_threaded_irq(&pdev->dev, irq, NULL, qcom_pcie_global_irq_thread, -- 2.51.1

1 day, 6 hours

1
0
0 0

[PATCH 2/6] Revert "PCI: dw-rockchip: Enumerate endpoints based on dll_link_up IRQ"

by Niklas Cassel

This reverts commit 0e0b45ab5d770a748487ba0ae8f77d1fb0f0de3e. While this fake hotplugging was a nice idea, it has shown that this feature does not handle PCIe switches correctly: pci_bus 0004:43: busn_res: can not insert [bus 43-41] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci_bus 0004:43: busn_res: [bus 43-41] end is updated to 43 pci_bus 0004:43: busn_res: can not insert [bus 43] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci 0004:42:00.0: devices behind bridge are unusable because [bus 43] cannot be assigned for them pci_bus 0004:44: busn_res: can not insert [bus 44-41] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci_bus 0004:44: busn_res: [bus 44-41] end is updated to 44 pci_bus 0004:44: busn_res: can not insert [bus 44] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci 0004:42:02.0: devices behind bridge are unusable because [bus 44] cannot be assigned for them pci_bus 0004:45: busn_res: can not insert [bus 45-41] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci_bus 0004:45: busn_res: [bus 45-41] end is updated to 45 pci_bus 0004:45: busn_res: can not insert [bus 45] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci 0004:42:06.0: devices behind bridge are unusable because [bus 45] cannot be assigned for them pci_bus 0004:46: busn_res: can not insert [bus 46-41] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci_bus 0004:46: busn_res: [bus 46-41] end is updated to 46 pci_bus 0004:46: busn_res: can not insert [bus 46] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci 0004:42:0e.0: devices behind bridge are unusable because [bus 46] cannot be assigned for them pci_bus 0004:42: busn_res: [bus 42-41] end is updated to 46 pci_bus 0004:42: busn_res: can not insert [bus 42-46] under [bus 41] (conflicts with (null) [bus 41]) pci 0004:41:00.0: devices behind bridge are unusable because [bus 42-46] cannot be assigned for them pcieport 0004:40:00.0: bridge has subordinate 41 but max busn 46 During the initial scan, PCI core doesn't see the switch and since the Root Port is not hot plug capable, the secondary bus number gets assigned as the subordinate bus number. This means, the PCI core assumes that only one bus will appear behind the Root Port since the Root Port is not hot plug capable. This works perfectly fine for PCIe endpoints connected to the Root Port, since they don't extend the bus. However, if a PCIe switch is connected, then there is a problem when the downstream busses starts showing up and the PCI core doesn't extend the subordinate bus number after initial scan during boot. The long term plan is to migrate this driver to the pwrctrl framework, once it adds proper support for powering up and enumerating PCIe switches. Cc: stable(a)vger.kernel.org Suggested-by: Manivannan Sadhasivam <mani(a)kernel.org> Signed-off-by: Niklas Cassel <cassel(a)kernel.org> --- drivers/pci/controller/dwc/pcie-dw-rockchip.c | 59 +------------------ 1 file changed, 3 insertions(+), 56 deletions(-) diff --git a/drivers/pci/controller/dwc/pcie-dw-rockchip.c b/drivers/pci/controller/dwc/pcie-dw-rockchip.c index 07378ececd88..7eceec8c9c83 100644 --- a/drivers/pci/controller/dwc/pcie-dw-rockchip.c +++ b/drivers/pci/controller/dwc/pcie-dw-rockchip.c @@ -448,34 +448,6 @@ static const struct dw_pcie_ops dw_pcie_ops = { .stop_link = rockchip_pcie_stop_link, }; -static irqreturn_t rockchip_pcie_rc_sys_irq_thread(int irq, void *arg) -{ - struct rockchip_pcie *rockchip = arg; - struct dw_pcie *pci = &rockchip->pci; - struct dw_pcie_rp *pp = &pci->pp; - struct device *dev = pci->dev; - u32 reg; - - reg = rockchip_pcie_readl_apb(rockchip, PCIE_CLIENT_INTR_STATUS_MISC); - rockchip_pcie_writel_apb(rockchip, reg, PCIE_CLIENT_INTR_STATUS_MISC); - - dev_dbg(dev, "PCIE_CLIENT_INTR_STATUS_MISC: %#x\n", reg); - dev_dbg(dev, "LTSSM_STATUS: %#x\n", rockchip_pcie_get_ltssm(rockchip)); - - if (reg & PCIE_RDLH_LINK_UP_CHGED) { - if (rockchip_pcie_link_up(pci)) { - msleep(PCIE_RESET_CONFIG_WAIT_MS); - dev_dbg(dev, "Received Link up event. Starting enumeration!\n"); - /* Rescan the bus to enumerate endpoint devices */ - pci_lock_rescan_remove(); - pci_rescan_bus(pp->bridge->bus); - pci_unlock_rescan_remove(); - } - } - - return IRQ_HANDLED; -} - static irqreturn_t rockchip_pcie_ep_sys_irq_thread(int irq, void *arg) { struct rockchip_pcie *rockchip = arg; @@ -508,29 +480,14 @@ static irqreturn_t rockchip_pcie_ep_sys_irq_thread(int irq, void *arg) return IRQ_HANDLED; } -static int rockchip_pcie_configure_rc(struct platform_device *pdev, - struct rockchip_pcie *rockchip) +static int rockchip_pcie_configure_rc(struct rockchip_pcie *rockchip) { - struct device *dev = &pdev->dev; struct dw_pcie_rp *pp; - int irq, ret; u32 val; if (!IS_ENABLED(CONFIG_PCIE_ROCKCHIP_DW_HOST)) return -ENODEV; - irq = platform_get_irq_byname(pdev, "sys"); - if (irq < 0) - return irq; - - ret = devm_request_threaded_irq(dev, irq, NULL, - rockchip_pcie_rc_sys_irq_thread, - IRQF_ONESHOT, "pcie-sys-rc", rockchip); - if (ret) { - dev_err(dev, "failed to request PCIe sys IRQ\n"); - return ret; - } - /* LTSSM enable control mode */ val = FIELD_PREP_WM16(PCIE_LTSSM_ENABLE_ENHANCE, 1); rockchip_pcie_writel_apb(rockchip, val, PCIE_CLIENT_HOT_RESET_CTRL); @@ -542,17 +499,7 @@ static int rockchip_pcie_configure_rc(struct platform_device *pdev, pp = &rockchip->pci.pp; pp->ops = &rockchip_pcie_host_ops; - ret = dw_pcie_host_init(pp); - if (ret) { - dev_err(dev, "failed to initialize host\n"); - return ret; - } - - /* unmask DLL up/down indicator */ - val = FIELD_PREP_WM16(PCIE_RDLH_LINK_UP_CHGED, 0); - rockchip_pcie_writel_apb(rockchip, val, PCIE_CLIENT_INTR_MASK_MISC); - - return ret; + return dw_pcie_host_init(pp); } static int rockchip_pcie_configure_ep(struct platform_device *pdev, @@ -678,7 +625,7 @@ static int rockchip_pcie_probe(struct platform_device *pdev) switch (data->mode) { case DW_PCIE_RC_TYPE: - ret = rockchip_pcie_configure_rc(pdev, rockchip); + ret = rockchip_pcie_configure_rc(rockchip); if (ret) goto deinit_clk; break; -- 2.51.1

1 day, 6 hours

1
0
0 0

[PATCH 1/6] Revert "PCI: dw-rockchip: Don't wait for link since we can detect Link Up"

by Niklas Cassel

This reverts commit ec9fd499b9c60a187ac8d6414c3c343c77d32e42. While this fake hotplugging was a nice idea, it has shown that this feature does not handle PCIe switches correctly: pci_bus 0004:43: busn_res: can not insert [bus 43-41] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci_bus 0004:43: busn_res: [bus 43-41] end is updated to 43 pci_bus 0004:43: busn_res: can not insert [bus 43] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci 0004:42:00.0: devices behind bridge are unusable because [bus 43] cannot be assigned for them pci_bus 0004:44: busn_res: can not insert [bus 44-41] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci_bus 0004:44: busn_res: [bus 44-41] end is updated to 44 pci_bus 0004:44: busn_res: can not insert [bus 44] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci 0004:42:02.0: devices behind bridge are unusable because [bus 44] cannot be assigned for them pci_bus 0004:45: busn_res: can not insert [bus 45-41] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci_bus 0004:45: busn_res: [bus 45-41] end is updated to 45 pci_bus 0004:45: busn_res: can not insert [bus 45] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci 0004:42:06.0: devices behind bridge are unusable because [bus 45] cannot be assigned for them pci_bus 0004:46: busn_res: can not insert [bus 46-41] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci_bus 0004:46: busn_res: [bus 46-41] end is updated to 46 pci_bus 0004:46: busn_res: can not insert [bus 46] under [bus 42-41] (conflicts with (null) [bus 42-41]) pci 0004:42:0e.0: devices behind bridge are unusable because [bus 46] cannot be assigned for them pci_bus 0004:42: busn_res: [bus 42-41] end is updated to 46 pci_bus 0004:42: busn_res: can not insert [bus 42-46] under [bus 41] (conflicts with (null) [bus 41]) pci 0004:41:00.0: devices behind bridge are unusable because [bus 42-46] cannot be assigned for them pcieport 0004:40:00.0: bridge has subordinate 41 but max busn 46 During the initial scan, PCI core doesn't see the switch and since the Root Port is not hot plug capable, the secondary bus number gets assigned as the subordinate bus number. This means, the PCI core assumes that only one bus will appear behind the Root Port since the Root Port is not hot plug capable. This works perfectly fine for PCIe endpoints connected to the Root Port, since they don't extend the bus. However, if a PCIe switch is connected, then there is a problem when the downstream busses starts showing up and the PCI core doesn't extend the subordinate bus number after initial scan during boot. The long term plan is to migrate this driver to the pwrctrl framework, once it adds proper support for powering up and enumerating PCIe switches. Cc: stable(a)vger.kernel.org Suggested-by: Manivannan Sadhasivam <mani(a)kernel.org> Signed-off-by: Niklas Cassel <cassel(a)kernel.org> --- drivers/pci/controller/dwc/pcie-dw-rockchip.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/pci/controller/dwc/pcie-dw-rockchip.c b/drivers/pci/controller/dwc/pcie-dw-rockchip.c index 3e2752c7dd09..07378ececd88 100644 --- a/drivers/pci/controller/dwc/pcie-dw-rockchip.c +++ b/drivers/pci/controller/dwc/pcie-dw-rockchip.c @@ -541,7 +541,6 @@ static int rockchip_pcie_configure_rc(struct platform_device *pdev, pp = &rockchip->pci.pp; pp->ops = &rockchip_pcie_host_ops; - pp->use_linkup_irq = true; ret = dw_pcie_host_init(pp); if (ret) { -- 2.51.1

1 day, 6 hours

1
0
0 0

[PATCH net v5 2/3] net,mptcp: fix proto fallback detection with BPF

by Jiayuan Chen

The sockmap feature allows bpf syscall from userspace, or based on bpf sockops, replacing the sk_prot of sockets during protocol stack processing with sockmap's custom read/write interfaces. ''' tcp_rcv_state_process() syn_recv_sock()/subflow_syn_recv_sock() tcp_init_transfer(BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB) bpf_skops_established <== sockops bpf_sock_map_update(sk) <== call bpf helper tcp_bpf_update_proto() <== update sk_prot ''' When the server has MPTCP enabled but the client sends a TCP SYN without MPTCP, subflow_syn_recv_sock() performs a fallback on the subflow, replacing the subflow sk's sk_prot with the native sk_prot. ''' subflow_syn_recv_sock() subflow_ulp_fallback() subflow_drop_ctx() mptcp_subflow_ops_undo_override() ''' Then, this subflow can be normally used by sockmap, which replaces the native sk_prot with sockmap's custom sk_prot. The issue occurs when the user executes accept::mptcp_stream_accept::mptcp_fallback_tcp_ops(). Here, it uses sk->sk_prot to compare with the native sk_prot, but this is incorrect when sockmap is used, as we may incorrectly set sk->sk_socket->ops. This fix uses the more generic sk_family for the comparison instead. Additionally, this also prevents a WARNING from occurring: result from ./scripts/decode_stacktrace.sh: ------------[ cut here ]------------ WARNING: CPU: 0 PID: 337 at net/mptcp/protocol.c:68 mptcp_stream_accept \ (net/mptcp/protocol.c:4005) Modules linked in: ... PKRU: 55555554 Call Trace: <TASK> do_accept (net/socket.c:1989) __sys_accept4 (net/socket.c:2028 net/socket.c:2057) __x64_sys_accept (net/socket.c:2067) x64_sys_call (arch/x86/entry/syscall_64.c:41) do_syscall_64 (arch/x86/entry/syscall_64.c:63 arch/x86/entry/syscall_64.c:94) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) RIP: 0033:0x7f87ac92b83d ---[ end trace 0000000000000000 ]--- Fixes: cec37a6e41aa ("mptcp: Handle MP_CAPABLE options for outgoing connections") Cc: <stable(a)vger.kernel.org> Signed-off-by: Jiayuan Chen <jiayuan.chen(a)linux.dev> Reviewed-by: Jakub Sitnicki <jakub(a)cloudflare.com> Reviewed-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> --- net/mptcp/protocol.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 2d6b8de35c44..90b4aeca2596 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -61,11 +61,13 @@ static u64 mptcp_wnd_end(const struct mptcp_sock *msk) static const struct proto_ops *mptcp_fallback_tcp_ops(const struct sock *sk) { + unsigned short family = READ_ONCE(sk->sk_family); + #if IS_ENABLED(CONFIG_MPTCP_IPV6) - if (sk->sk_prot == &tcpv6_prot) + if (family == AF_INET6) return &inet6_stream_ops; #endif - WARN_ON_ONCE(sk->sk_prot != &tcp_prot); + WARN_ON_ONCE(family != AF_INET); return &inet_stream_ops; } -- 2.43.0

1 day, 7 hours

2
1
0 0

[PATCH] ARM: dts: nxp: imx6ul: correct SAI3 interrupt line

by Maarten Zanders

The i.MX6UL reference manual lists two possible interrupt lines for SAI3 (56 and 57, offset +32). The current device tree entry uses the first one (24), which prevents IRQs from being handled properly. Use the second interrupt line (25), which does allow interrupts to work as expected. Fixes: 36e2edf6ac07 ("ARM: dts: imx6ul: add sai support") Signed-off-by: Maarten Zanders <maarten(a)zanders.be> Cc: stable(a)vger.kernel.org --- arch/arm/boot/dts/nxp/imx/imx6ul.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/nxp/imx/imx6ul.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ul.dtsi index 6de224dd2bb9..6eb80f867f50 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6ul.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6ul.dtsi @@ -339,7 +339,7 @@ sai3: sai@2030000 { #sound-dai-cells = <0>; compatible = "fsl,imx6ul-sai", "fsl,imx6sx-sai"; reg = <0x02030000 0x4000>; - interrupts = <GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 25 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX6UL_CLK_SAI3_IPG>, <&clks IMX6UL_CLK_SAI3>, <&clks IMX6UL_CLK_DUMMY>, <&clks IMX6UL_CLK_DUMMY>; -- 2.51.0

1 day, 7 hours

2
1
0 0

[PATCH v3] w1: therm: Fix off-by-one buffer overflow in alarms_store

by Thorsten Blum

The sysfs buffer passed to alarms_store() is allocated with 'size + 1' bytes and a NUL terminator is appended. However, the 'size' argument does not account for this extra byte. The original code then allocated 'size' bytes and used strcpy() to copy 'buf', which always writes one byte past the allocated buffer since strcpy() copies until the NUL terminator at index 'size'. Fix this by parsing the 'buf' parameter directly using simple_strtol() without allocating any intermediate memory or string copying. This removes the overflow while simplifying the code. Cc: stable(a)vger.kernel.org Fixes: e2c94d6f5720 ("w1_therm: adding alarm sysfs entry") Signed-off-by: Thorsten Blum <thorsten.blum(a)linux.dev> --- Compile-tested only. Changes in v3: - Add integer range check for 'temp' to match kstrtoint() behavior - Explicitly cast 'temp' to int when calling int_to_short() - Link to v2: https://lore.kernel.org/lkml/20251029130045.70127-2-thorsten.blum@linux.dev/ Changes in v2: - Fix buffer overflow instead of truncating the copy using strscpy() - Parse buffer directly using simple_strtol() as suggested by David - Update patch subject and description - Link to v1: https://lore.kernel.org/lkml/20251017170047.114224-2-thorsten.blum@linux.de… --- drivers/w1/slaves/w1_therm.c | 102 ++++++++++++----------------------- 1 file changed, 35 insertions(+), 67 deletions(-) diff --git a/drivers/w1/slaves/w1_therm.c b/drivers/w1/slaves/w1_therm.c index 9ccedb3264fb..1dad9fa1ec4a 100644 --- a/drivers/w1/slaves/w1_therm.c +++ b/drivers/w1/slaves/w1_therm.c @@ -1836,59 +1836,32 @@ static ssize_t alarms_store(struct device *device, struct w1_slave *sl = dev_to_w1_slave(device); struct therm_info info; u8 new_config_register[3]; /* array of data to be written */ - int temp, ret; - char *token = NULL; + long temp; + int ret; s8 tl, th; /* 1 byte per value + temp ring order */ - char *p_args, *orig; + const char *p = buf; + char *endp; - p_args = orig = kmalloc(size, GFP_KERNEL); - /* Safe string copys as buf is const */ - if (!p_args) { - dev_warn(device, - "%s: error unable to allocate memory %d\n", - __func__, -ENOMEM); - return size; + temp = simple_strtol(p, &endp, 10); + if (temp < INT_MIN || temp > INT_MAX || p == endp || *endp != ' ') { + dev_info(device, "%s: error parsing args %d\n", + __func__, -EINVAL); + goto err; } - strcpy(p_args, buf); - - /* Split string using space char */ - token = strsep(&p_args, " "); + /* Cast to short to eliminate out of range values */ + tl = int_to_short((int)temp); - if (!token) { - dev_info(device, - "%s: error parsing args %d\n", __func__, -EINVAL); - goto free_m; - } - - /* Convert 1st entry to int */ - ret = kstrtoint (token, 10, &temp); - if (ret) { - dev_info(device, - "%s: error parsing args %d\n", __func__, ret); - goto free_m; - } - - tl = int_to_short(temp); - - /* Split string using space char */ - token = strsep(&p_args, " "); - if (!token) { - dev_info(device, - "%s: error parsing args %d\n", __func__, -EINVAL); - goto free_m; - } - /* Convert 2nd entry to int */ - ret = kstrtoint (token, 10, &temp); - if (ret) { - dev_info(device, - "%s: error parsing args %d\n", __func__, ret); - goto free_m; + p = endp + 1; + temp = simple_strtol(p, &endp, 10); + if (temp < INT_MIN || temp > INT_MAX || p == endp) { + dev_info(device, "%s: error parsing args %d\n", + __func__, -EINVAL); + goto err; } + /* Cast to short to eliminate out of range values */ + th = int_to_short((int)temp); - /* Prepare to cast to short by eliminating out of range values */ - th = int_to_short(temp); - - /* Reorder if required th and tl */ + /* Reorder if required */ if (tl > th) swap(tl, th); @@ -1897,35 +1870,30 @@ static ssize_t alarms_store(struct device *device, * (th : byte 2 - tl: byte 3) */ ret = read_scratchpad(sl, &info); - if (!ret) { - new_config_register[0] = th; /* Byte 2 */ - new_config_register[1] = tl; /* Byte 3 */ - new_config_register[2] = info.rom[4];/* Byte 4 */ - } else { - dev_info(device, - "%s: error reading from the slave device %d\n", - __func__, ret); - goto free_m; + if (ret) { + dev_info(device, "%s: error reading from the slave device %d\n", + __func__, ret); + goto err; } + new_config_register[0] = th; /* Byte 2 */ + new_config_register[1] = tl; /* Byte 3 */ + new_config_register[2] = info.rom[4]; /* Byte 4 */ /* Write data in the device RAM */ if (!SLAVE_SPECIFIC_FUNC(sl)) { - dev_info(device, - "%s: Device not supported by the driver %d\n", - __func__, -ENODEV); - goto free_m; + dev_info(device, "%s: Device not supported by the driver %d\n", + __func__, -ENODEV); + goto err; } ret = SLAVE_SPECIFIC_FUNC(sl)->write_data(sl, new_config_register); - if (ret) - dev_info(device, - "%s: error writing to the slave device %d\n", + if (ret) { + dev_info(device, "%s: error writing to the slave device %d\n", __func__, ret); + goto err; + } -free_m: - /* free allocated memory */ - kfree(orig); - +err: return size; } -- 2.51.0

1 day, 8 hours

3
4
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror