From d560bb42814ca7ff6c9944310644d45eb53ca1ae Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 30 Jan 2020 20:24:03 +0100 Subject: [PATCH 001/256] ARC: Cleanup old Kconfig IO scheduler options CONFIG_IOSCHED_DEADLINE and CONFIG_IOSCHED_CFQ are gone since commit f382fb0bcef4 ("block: remove legacy IO schedulers"). The IOSCHED_DEADLINE was replaced by MQ_IOSCHED_DEADLINE and it will be now enabled by default (along with MQ_IOSCHED_KYBER). Signed-off-by: Krzysztof Kozlowski Signed-off-by: Vineet Gupta --- arch/arc/configs/nps_defconfig | 2 -- arch/arc/configs/nsimosci_defconfig | 2 -- arch/arc/configs/nsimosci_hs_defconfig | 2 -- arch/arc/configs/nsimosci_hs_smp_defconfig | 2 -- 4 files changed, 8 deletions(-) diff --git a/arch/arc/configs/nps_defconfig b/arch/arc/configs/nps_defconfig index 07f26ed39f02..f7a978dfdf1d 100644 --- a/arch/arc/configs/nps_defconfig +++ b/arch/arc/configs/nps_defconfig @@ -21,8 +21,6 @@ CONFIG_MODULES=y CONFIG_MODULE_FORCE_LOAD=y CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARC_PLAT_EZNPS=y CONFIG_SMP=y CONFIG_NR_CPUS=4096 diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig index 5dd470b6609e..bf39a0091679 100644 --- a/arch/arc/configs/nsimosci_defconfig +++ b/arch/arc/configs/nsimosci_defconfig @@ -20,8 +20,6 @@ CONFIG_ISA_ARCOMPACT=y CONFIG_KPROBES=y CONFIG_MODULES=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ARC_BUILTIN_DTB_NAME="nsimosci" # CONFIG_COMPACTION is not set CONFIG_NET=y diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig index 3532e86f7bff..7121bd71c543 100644 --- a/arch/arc/configs/nsimosci_hs_defconfig +++ b/arch/arc/configs/nsimosci_hs_defconfig @@ -19,8 +19,6 @@ CONFIG_PERF_EVENTS=y CONFIG_KPROBES=y CONFIG_MODULES=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ISA_ARCV2=y CONFIG_ARC_BUILTIN_DTB_NAME="nsimosci_hs" # CONFIG_COMPACTION is not set diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig index d90448bee064..f9863b294a70 100644 --- a/arch/arc/configs/nsimosci_hs_smp_defconfig +++ b/arch/arc/configs/nsimosci_hs_smp_defconfig @@ -14,8 +14,6 @@ CONFIG_PERF_EVENTS=y CONFIG_KPROBES=y CONFIG_MODULES=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set CONFIG_ISA_ARCV2=y CONFIG_SMP=y # CONFIG_ARC_TIMERS_64BIT is not set From a5760db25c6e68bf8cd34e1642196826c08715ed Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 31 Jan 2020 17:49:33 -0800 Subject: [PATCH 002/256] ARC: fix some Kconfig typos Fix language typos in arch/arc/Kconfig. Cc: linux-snps-arc@lists.infradead.org Signed-off-by: Randy Dunlap Signed-off-by: Vineet Gupta --- arch/arc/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index ff2a393b635c..7124ab82dfa3 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -154,7 +154,7 @@ config ARC_CPU_HS help Support for ARC HS38x Cores based on ARCv2 ISA The notable features are: - - SMP configurations of upto 4 core with coherency + - SMP configurations of up to 4 cores with coherency - Optional L2 Cache and IO-Coherency - Revised Interrupt Architecture (multiple priorites, reg banks, auto stack switch, auto regfile save/restore) @@ -192,7 +192,7 @@ config ARC_SMP_HALT_ON_RESET help In SMP configuration cores can be configured as Halt-on-reset or they could all start at same time. For Halt-on-reset, non - masters are parked until Master kicks them so they can start of + masters are parked until Master kicks them so they can start off at designated entry point. For other case, all jump to common entry point and spin wait for Master's signal. From 0acdf63d2296f9542437a4842ad94554d240eab6 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Fri, 7 Feb 2020 17:05:10 -0800 Subject: [PATCH 003/256] ARC: fpu: fix randconfig build error reported by 0-day test service Reported-by: kbuild test robot Link: http://lists.infradead.org/pipermail/linux-snps-arc/2020-February/006845.html Signed-off-by: Vineet Gupta --- arch/arc/include/asm/fpu.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arc/include/asm/fpu.h b/arch/arc/include/asm/fpu.h index 64347250fdf5..006bcf88a7a5 100644 --- a/arch/arc/include/asm/fpu.h +++ b/arch/arc/include/asm/fpu.h @@ -43,6 +43,8 @@ extern void fpu_init_task(struct pt_regs *regs); #endif /* !CONFIG_ISA_ARCOMPACT */ +struct task_struct; + extern void fpu_save_restore(struct task_struct *p, struct task_struct *n); #else /* !CONFIG_ARC_FPU_SAVE_RESTORE */ From 3b00b042eeaaea43b8702b2dd4b9cb0916a2e052 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 12 Feb 2020 11:00:47 +0100 Subject: [PATCH 004/256] ARC: Replace by The ARC platform code is not a clock provider, and just needs to call of_clk_init(). Hence it can include instead of . Signed-off-by: Geert Uytterhoeven Reviewed-by: Stephen Boyd Signed-off-by: Vineet Gupta --- arch/arc/kernel/setup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index e1c647490f00..aa41af6ef4ac 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -8,11 +8,11 @@ #include #include #include -#include #include #include #include #include +#include #include #include #include From 4a4472fdc098fb78f52a0848788faf46674a8423 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 12 Feb 2020 10:43:17 +0100 Subject: [PATCH 005/256] of: clk: Make of_clk_get_parent_{count,name}() parameter const of_clk_get_parent_count() and of_clk_get_parent_name() never modify the device nodes passed, so they can be const. Signed-off-by: Geert Uytterhoeven Link: https://lkml.kernel.org/r/20200212094317.1150-1-geert+renesas@glider.be Signed-off-by: Stephen Boyd --- drivers/clk/clk.c | 4 ++-- include/linux/of_clk.h | 8 ++++---- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index f0f2b599fd7e..95adf6c6db3d 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -4713,7 +4713,7 @@ EXPORT_SYMBOL(of_clk_get_by_name); * * Returns: The number of clocks that are possible parents of this node */ -unsigned int of_clk_get_parent_count(struct device_node *np) +unsigned int of_clk_get_parent_count(const struct device_node *np) { int count; @@ -4725,7 +4725,7 @@ unsigned int of_clk_get_parent_count(struct device_node *np) } EXPORT_SYMBOL_GPL(of_clk_get_parent_count); -const char *of_clk_get_parent_name(struct device_node *np, int index) +const char *of_clk_get_parent_name(const struct device_node *np, int index) { struct of_phandle_args clkspec; struct property *prop; diff --git a/include/linux/of_clk.h b/include/linux/of_clk.h index c86fcad23fc2..31b73a0da9db 100644 --- a/include/linux/of_clk.h +++ b/include/linux/of_clk.h @@ -11,17 +11,17 @@ struct of_device_id; #if defined(CONFIG_COMMON_CLK) && defined(CONFIG_OF) -unsigned int of_clk_get_parent_count(struct device_node *np); -const char *of_clk_get_parent_name(struct device_node *np, int index); +unsigned int of_clk_get_parent_count(const struct device_node *np); +const char *of_clk_get_parent_name(const struct device_node *np, int index); void of_clk_init(const struct of_device_id *matches); #else /* !CONFIG_COMMON_CLK || !CONFIG_OF */ -static inline unsigned int of_clk_get_parent_count(struct device_node *np) +static inline unsigned int of_clk_get_parent_count(const struct device_node *np) { return 0; } -static inline const char *of_clk_get_parent_name(struct device_node *np, +static inline const char *of_clk_get_parent_name(const struct device_node *np, int index) { return NULL; From dbb92f88648d6206bf22fcb764fb9fe2939d401a Mon Sep 17 00:00:00 2001 From: Andrea Parri Date: Wed, 22 Jan 2020 19:39:52 +0100 Subject: [PATCH 006/256] workqueue: Document (some) memory-ordering properties of {queue,schedule}_work() It's desirable to be able to rely on the following property: All stores preceding (in program order) a call to a successful queue_work() will be visible from the CPU which will execute the queued work by the time such work executes, e.g., { x is initially 0 } CPU0 CPU1 WRITE_ONCE(x, 1); [ "work" is being executed ] r0 = queue_work(wq, work); r1 = READ_ONCE(x); Forbids: r0 == true && r1 == 0 The current implementation of queue_work() provides such memory-ordering property: - In __queue_work(), the ->lock spinlock is acquired. - On the other side, in worker_thread(), this same ->lock is held when dequeueing work. So the locking ordering makes things work out. Add this property to the DocBook headers of {queue,schedule}_work(). Suggested-by: Paul E. McKenney Signed-off-by: Andrea Parri Acked-by: Paul E. McKenney Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 4261d1c6e87b..e48554e6526c 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -487,6 +487,19 @@ extern void wq_worker_comm(char *buf, size_t size, struct task_struct *task); * * We queue the work to the CPU on which it was submitted, but if the CPU dies * it can be processed by another CPU. + * + * Memory-ordering properties: If it returns %true, guarantees that all stores + * preceding the call to queue_work() in the program order will be visible from + * the CPU which will execute @work by the time such work executes, e.g., + * + * { x is initially 0 } + * + * CPU0 CPU1 + * + * WRITE_ONCE(x, 1); [ @work is being executed ] + * r0 = queue_work(wq, work); r1 = READ_ONCE(x); + * + * Forbids: r0 == true && r1 == 0 */ static inline bool queue_work(struct workqueue_struct *wq, struct work_struct *work) @@ -546,6 +559,9 @@ static inline bool schedule_work_on(int cpu, struct work_struct *work) * This puts a job in the kernel-global workqueue if it was not already * queued and leaves it in the same position on the kernel-global * workqueue otherwise. + * + * Shares the same memory-ordering properties of queue_work(), cf. the + * DocBook header of queue_work(). */ static inline bool schedule_work(struct work_struct *work) { From db8dd9697238be70a6b4f9d0284cd89f59c0e070 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Thu, 30 Jan 2020 13:34:49 +0300 Subject: [PATCH 007/256] cgroup-v1: cgroup_pidlist_next should update position index if seq_file .next fuction does not change position index, read after some lseek can generate unexpected output. # mount | grep cgroup # dd if=/mnt/cgroup.procs bs=1 # normal output ... 1294 1295 1296 1304 1382 584+0 records in 584+0 records out 584 bytes copied dd: /mnt/cgroup.procs: cannot skip to specified offset 83 <<< generates end of last line 1383 <<< ... and whole last line once again 0+1 records in 0+1 records out 8 bytes copied dd: /mnt/cgroup.procs: cannot skip to specified offset 1386 <<< generates last line anyway 0+1 records in 0+1 records out 5 bytes copied https://bugzilla.kernel.org/show_bug.cgi?id=206283 Signed-off-by: Vasily Averin Signed-off-by: Tejun Heo --- kernel/cgroup/cgroup-v1.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index be1a1c83cdd1..9a6f060cbf51 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -471,6 +471,7 @@ static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos) */ p++; if (p >= end) { + (*pos)++; return NULL; } else { *pos = *p; From 2d4ecb030dcc90fb725ecbfc82ce5d6c37906e0e Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Thu, 30 Jan 2020 13:34:59 +0300 Subject: [PATCH 008/256] cgroup: cgroup_procs_next should increase position index If seq_file .next fuction does not change position index, read after some lseek can generate unexpected output: 1) dd bs=1 skip output of each 2nd elements $ dd if=/sys/fs/cgroup/cgroup.procs bs=8 count=1 2 3 4 5 1+0 records in 1+0 records out 8 bytes copied, 0,000267297 s, 29,9 kB/s [test@localhost ~]$ dd if=/sys/fs/cgroup/cgroup.procs bs=1 count=8 2 4 <<< NB! 3 was skipped 6 <<< ... and 5 too 8 <<< ... and 7 8+0 records in 8+0 records out 8 bytes copied, 5,2123e-05 s, 153 kB/s This happen because __cgroup_procs_start() makes an extra extra cgroup_procs_next() call 2) read after lseek beyond end of file generates whole last line. 3) read after lseek into middle of last line generates expected rest of last line and unexpected whole line once again. Additionally patch removes an extra position index changes in __cgroup_procs_start() Cc: stable@vger.kernel.org https://bugzilla.kernel.org/show_bug.cgi?id=206283 Signed-off-by: Vasily Averin Signed-off-by: Tejun Heo --- kernel/cgroup/cgroup.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 75f687301bbf..927f7b82e5c1 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -4595,6 +4595,9 @@ static void *cgroup_procs_next(struct seq_file *s, void *v, loff_t *pos) struct kernfs_open_file *of = s->private; struct css_task_iter *it = of->priv; + if (pos) + (*pos)++; + return css_task_iter_next(it); } @@ -4610,7 +4613,7 @@ static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos, * from position 0, so we can simply keep iterating on !0 *pos. */ if (!it) { - if (WARN_ON_ONCE((*pos)++)) + if (WARN_ON_ONCE((*pos))) return ERR_PTR(-EINVAL); it = kzalloc(sizeof(*it), GFP_KERNEL); @@ -4618,10 +4621,11 @@ static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos, return ERR_PTR(-ENOMEM); of->priv = it; css_task_iter_start(&cgrp->self, iter_flags, it); - } else if (!(*pos)++) { + } else if (!(*pos)) { css_task_iter_end(it); css_task_iter_start(&cgrp->self, iter_flags, it); - } + } else + return it->cur_task; return cgroup_procs_next(s, NULL, NULL); } From 9c974c77246460fa6a92c18554c3311c8c83c160 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Michal=20Koutn=C3=BD?= Date: Fri, 24 Jan 2020 12:40:15 +0100 Subject: [PATCH 009/256] cgroup: Iterate tasks that did not finish do_exit() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit PF_EXITING is set earlier than actual removal from css_set when a task is exitting. This can confuse cgroup.procs readers who see no PF_EXITING tasks, however, rmdir is checking against css_set membership so it can transitionally fail with EBUSY. Fix this by listing tasks that weren't unlinked from css_set active lists. It may happen that other users of the task iterator (without CSS_TASK_ITER_PROCS) spot a PF_EXITING task before cgroup_exit(). This is equal to the state before commit c03cd7738a83 ("cgroup: Include dying leaders with live threads in PROCS iterations") but it may be reviewed later. Reported-by: Suren Baghdasaryan Fixes: c03cd7738a83 ("cgroup: Include dying leaders with live threads in PROCS iterations") Signed-off-by: Michal Koutný Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 1 + kernel/cgroup/cgroup.c | 23 ++++++++++++++++------- 2 files changed, 17 insertions(+), 7 deletions(-) diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index d7ddebd0cdec..e75d2191226b 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -62,6 +62,7 @@ struct css_task_iter { struct list_head *mg_tasks_head; struct list_head *dying_tasks_head; + struct list_head *cur_tasks_head; struct css_set *cur_cset; struct css_set *cur_dcset; struct task_struct *cur_task; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 927f7b82e5c1..c719a4154d6d 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -4400,12 +4400,16 @@ static void css_task_iter_advance_css_set(struct css_task_iter *it) } } while (!css_set_populated(cset) && list_empty(&cset->dying_tasks)); - if (!list_empty(&cset->tasks)) + if (!list_empty(&cset->tasks)) { it->task_pos = cset->tasks.next; - else if (!list_empty(&cset->mg_tasks)) + it->cur_tasks_head = &cset->tasks; + } else if (!list_empty(&cset->mg_tasks)) { it->task_pos = cset->mg_tasks.next; - else + it->cur_tasks_head = &cset->mg_tasks; + } else { it->task_pos = cset->dying_tasks.next; + it->cur_tasks_head = &cset->dying_tasks; + } it->tasks_head = &cset->tasks; it->mg_tasks_head = &cset->mg_tasks; @@ -4463,10 +4467,14 @@ repeat: else it->task_pos = it->task_pos->next; - if (it->task_pos == it->tasks_head) + if (it->task_pos == it->tasks_head) { it->task_pos = it->mg_tasks_head->next; - if (it->task_pos == it->mg_tasks_head) + it->cur_tasks_head = it->mg_tasks_head; + } + if (it->task_pos == it->mg_tasks_head) { it->task_pos = it->dying_tasks_head->next; + it->cur_tasks_head = it->dying_tasks_head; + } if (it->task_pos == it->dying_tasks_head) css_task_iter_advance_css_set(it); } else { @@ -4485,11 +4493,12 @@ repeat: goto repeat; /* and dying leaders w/o live member threads */ - if (!atomic_read(&task->signal->live)) + if (it->cur_tasks_head == it->dying_tasks_head && + !atomic_read(&task->signal->live)) goto repeat; } else { /* skip all dying ones */ - if (task->flags & PF_EXITING) + if (it->cur_tasks_head == it->dying_tasks_head) goto repeat; } } From 8de427d52da30d3bad06d416e486a6b1bd0f3850 Mon Sep 17 00:00:00 2001 From: Taniya Das Date: Tue, 11 Feb 2020 17:43:55 +0530 Subject: [PATCH 010/256] clk: qcom: videocc: Update the clock flag for video_cc_vcodec0_core_clk The clock disable signal for video_cc_vcodec0_core_clk is tied to vcodec0_gdsc which is supported in the HW control mode. Thus turning off the clock would be taken care automatically when the GDSC turns OFF by hardware and clock driver does not require to poll on the CLK_OFF bit. Signed-off-by: Taniya Das Link: https://lkml.kernel.org/r/1581423235-21341-1-git-send-email-tdas@codeaurora.org Fixes: 253dc75a0bb8 ("clk: qcom: Add video clock controller driver for SC7180") Signed-off-by: Stephen Boyd --- drivers/clk/qcom/videocc-sc7180.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/qcom/videocc-sc7180.c b/drivers/clk/qcom/videocc-sc7180.c index c363c3cc544e..276e5ecd4840 100644 --- a/drivers/clk/qcom/videocc-sc7180.c +++ b/drivers/clk/qcom/videocc-sc7180.c @@ -97,7 +97,7 @@ static struct clk_branch video_cc_vcodec0_axi_clk = { static struct clk_branch video_cc_vcodec0_core_clk = { .halt_reg = 0x890, - .halt_check = BRANCH_HALT, + .halt_check = BRANCH_HALT_VOTED, .clkr = { .enable_reg = 0x890, .enable_mask = BIT(0), From efbd9129dfe87fdeaa3c44e8246b019a775c484b Mon Sep 17 00:00:00 2001 From: Taniya Das Date: Tue, 11 Feb 2020 17:43:56 +0530 Subject: [PATCH 011/256] clk: qcom: dispcc: Remove support of disp_cc_mdss_rscc_ahb_clk The disp_cc_mdss_rscc_ahb_clk is default enabled from hardware and thus does not require to be marked CRITICAL. This which would allow the RCG to be turned OFF when the display turns OFF and not blocking XO. Signed-off-by: Taniya Das Link: https://lkml.kernel.org/r/1581423236-21341-2-git-send-email-tdas@codeaurora.org Fixes: dd3d06622138 ("clk: qcom: Add display clock controller driver for SC7180") Signed-off-by: Stephen Boyd --- drivers/clk/qcom/dispcc-sc7180.c | 19 ------------------- 1 file changed, 19 deletions(-) diff --git a/drivers/clk/qcom/dispcc-sc7180.c b/drivers/clk/qcom/dispcc-sc7180.c index dd7af41e47eb..0a5d395bce93 100644 --- a/drivers/clk/qcom/dispcc-sc7180.c +++ b/drivers/clk/qcom/dispcc-sc7180.c @@ -592,24 +592,6 @@ static struct clk_branch disp_cc_mdss_rot_clk = { }, }; -static struct clk_branch disp_cc_mdss_rscc_ahb_clk = { - .halt_reg = 0x400c, - .halt_check = BRANCH_HALT, - .clkr = { - .enable_reg = 0x400c, - .enable_mask = BIT(0), - .hw.init = &(struct clk_init_data){ - .name = "disp_cc_mdss_rscc_ahb_clk", - .parent_data = &(const struct clk_parent_data){ - .hw = &disp_cc_mdss_ahb_clk_src.clkr.hw, - }, - .num_parents = 1, - .flags = CLK_IS_CRITICAL | CLK_SET_RATE_PARENT, - .ops = &clk_branch2_ops, - }, - }, -}; - static struct clk_branch disp_cc_mdss_rscc_vsync_clk = { .halt_reg = 0x4008, .halt_check = BRANCH_HALT, @@ -687,7 +669,6 @@ static struct clk_regmap *disp_cc_sc7180_clocks[] = { [DISP_CC_MDSS_PCLK0_CLK_SRC] = &disp_cc_mdss_pclk0_clk_src.clkr, [DISP_CC_MDSS_ROT_CLK] = &disp_cc_mdss_rot_clk.clkr, [DISP_CC_MDSS_ROT_CLK_SRC] = &disp_cc_mdss_rot_clk_src.clkr, - [DISP_CC_MDSS_RSCC_AHB_CLK] = &disp_cc_mdss_rscc_ahb_clk.clkr, [DISP_CC_MDSS_RSCC_VSYNC_CLK] = &disp_cc_mdss_rscc_vsync_clk.clkr, [DISP_CC_MDSS_VSYNC_CLK] = &disp_cc_mdss_vsync_clk.clkr, [DISP_CC_MDSS_VSYNC_CLK_SRC] = &disp_cc_mdss_vsync_clk_src.clkr, From 3e8cb8b2eaeb22f540f1cbc00cbb594047b7ba89 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 13 Feb 2020 09:16:07 +0100 Subject: [PATCH 012/256] fuse: fix stack use after return Normal, synchronous requests will have their args allocated on the stack. After the FR_FINISHED bit is set by receiving the reply from the userspace fuse server, the originating task may return and reuse the stack frame, resulting in an Oops if the args structure is dereferenced. Fix by setting a flag in the request itself upon initializing, indicating whether it has an asynchronous ->end() callback. Reported-by: Kyle Sanderson Reported-by: Michael Stapelberg Fixes: 2b319d1f6f92 ("fuse: don't dereference req->args on finished request") Cc: # v5.4 Tested-by: Michael Stapelberg Signed-off-by: Miklos Szeredi --- fs/fuse/dev.c | 6 +++--- fs/fuse/fuse_i.h | 2 ++ 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 8e02d76fe104..97eec7522bf2 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -276,12 +276,10 @@ static void flush_bg_queue(struct fuse_conn *fc) void fuse_request_end(struct fuse_conn *fc, struct fuse_req *req) { struct fuse_iqueue *fiq = &fc->iq; - bool async; if (test_and_set_bit(FR_FINISHED, &req->flags)) goto put_request; - async = req->args->end; /* * test_and_set_bit() implies smp_mb() between bit * changing and below intr_entry check. Pairs with @@ -324,7 +322,7 @@ void fuse_request_end(struct fuse_conn *fc, struct fuse_req *req) wake_up(&req->waitq); } - if (async) + if (test_bit(FR_ASYNC, &req->flags)) req->args->end(fc, req->args, req->out.h.error); put_request: fuse_put_request(fc, req); @@ -471,6 +469,8 @@ static void fuse_args_to_req(struct fuse_req *req, struct fuse_args *args) req->in.h.opcode = args->opcode; req->in.h.nodeid = args->nodeid; req->args = args; + if (args->end) + __set_bit(FR_ASYNC, &req->flags); } ssize_t fuse_simple_request(struct fuse_conn *fc, struct fuse_args *args) diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index aa75e2305b75..ca344bf71404 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -301,6 +301,7 @@ struct fuse_io_priv { * FR_SENT: request is in userspace, waiting for an answer * FR_FINISHED: request is finished * FR_PRIVATE: request is on private list + * FR_ASYNC: request is asynchronous */ enum fuse_req_flag { FR_ISREPLY, @@ -314,6 +315,7 @@ enum fuse_req_flag { FR_SENT, FR_FINISHED, FR_PRIVATE, + FR_ASYNC, }; /** From a9149d243f259ad8f02b1e23dfe8ba06128f15e1 Mon Sep 17 00:00:00 2001 From: Dan Moulding Date: Tue, 28 Jan 2020 02:31:07 -0700 Subject: [PATCH 013/256] iwlwifi: mvm: Do not require PHY_SKU NVM section for 3168 devices The logic for checking required NVM sections was recently fixed in commit b3f20e098293 ("iwlwifi: mvm: fix NVM check for 3168 devices"). However, with that fixed the else is now taken for 3168 devices and within the else clause there is a mandatory check for the PHY_SKU section. This causes the parsing to fail for 3168 devices. The PHY_SKU section is really only mandatory for the IWL_NVM_EXT layout (the phy_sku parameter of iwl_parse_nvm_data is only used when the NVM type is IWL_NVM_EXT). So this changes the PHY_SKU section check so that it's only mandatory for IWL_NVM_EXT. Fixes: b3f20e098293 ("iwlwifi: mvm: fix NVM check for 3168 devices") Signed-off-by: Dan Moulding Signed-off-by: Kalle Valo --- drivers/net/wireless/intel/iwlwifi/mvm/nvm.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c index 70b29bf16bb9..60296a754af2 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c @@ -308,7 +308,8 @@ iwl_parse_nvm_sections(struct iwl_mvm *mvm) } /* PHY_SKU section is mandatory in B0 */ - if (!mvm->nvm_sections[NVM_SECTION_TYPE_PHY_SKU].data) { + if (mvm->trans->cfg->nvm_type == IWL_NVM_EXT && + !mvm->nvm_sections[NVM_SECTION_TYPE_PHY_SKU].data) { IWL_ERR(mvm, "Can't parse phy_sku in B0, empty sections\n"); return NULL; From 9051db381fabe75079ef38135ab73c5dd3a7c3e5 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Thu, 6 Feb 2020 08:21:24 -0800 Subject: [PATCH 014/256] mmc: sdhci-msm: Mark sdhci_msm_cqe_disable static This function is not exported and only used in this file. Mark it static. Cc: Ritesh Harjani Cc: Veerabhadrarao Badiganti Fixes: 87a8df0dce6a ("mmc: sdhci-msm: Add CQHCI support for sdhci-msm") Signed-off-by: Stephen Boyd Reviewed-by: Douglas Anderson Acked-by: Adrian Hunter Link: https://lore.kernel.org/r/20200206162124.201195-1-swboyd@chromium.org Signed-off-by: Ulf Hansson --- drivers/mmc/host/sdhci-msm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c index c3a160c18047..3955fa5db43c 100644 --- a/drivers/mmc/host/sdhci-msm.c +++ b/drivers/mmc/host/sdhci-msm.c @@ -1590,7 +1590,7 @@ static u32 sdhci_msm_cqe_irq(struct sdhci_host *host, u32 intmask) return 0; } -void sdhci_msm_cqe_disable(struct mmc_host *mmc, bool recovery) +static void sdhci_msm_cqe_disable(struct mmc_host *mmc, bool recovery) { struct sdhci_host *host = mmc_priv(mmc); unsigned long flags; From 5eb40257047fb11085d582b7b9ccd0bffe900726 Mon Sep 17 00:00:00 2001 From: Anson Huang Date: Mon, 17 Feb 2020 11:01:35 +0800 Subject: [PATCH 015/256] clk: imx8mn: Fix incorrect clock defines IMX8MN_CLK_I2C4 and IMX8MN_CLK_UART1's index definitions are incorrect, fix them. Fixes: 1e80936a42e1 ("dt-bindings: imx: Add clock binding doc for i.MX8MN") Signed-off-by: Anson Huang Signed-off-by: Shawn Guo --- include/dt-bindings/clock/imx8mn-clock.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/dt-bindings/clock/imx8mn-clock.h b/include/dt-bindings/clock/imx8mn-clock.h index 0f2b8423ce1d..65ac6eb6c733 100644 --- a/include/dt-bindings/clock/imx8mn-clock.h +++ b/include/dt-bindings/clock/imx8mn-clock.h @@ -122,8 +122,8 @@ #define IMX8MN_CLK_I2C1 105 #define IMX8MN_CLK_I2C2 106 #define IMX8MN_CLK_I2C3 107 -#define IMX8MN_CLK_I2C4 118 -#define IMX8MN_CLK_UART1 119 +#define IMX8MN_CLK_I2C4 108 +#define IMX8MN_CLK_UART1 109 #define IMX8MN_CLK_UART2 110 #define IMX8MN_CLK_UART3 111 #define IMX8MN_CLK_UART4 112 From 8e8ce08198de193e3d21d42e96945216e3d9ac7f Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Sun, 16 Feb 2020 13:02:06 +0100 Subject: [PATCH 016/256] batman-adv: Don't schedule OGM for disabled interface A transmission scheduling for an interface which is currently dropped by batadv_iv_ogm_iface_disable could still be in progress. The B.A.T.M.A.N. V is simply cancelling the workqueue item in an synchronous way but this is not possible with B.A.T.M.A.N. IV because the OGM submissions are intertwined. Instead it has to stop submitting the OGM when it detect that the buffer pointer is set to NULL. Reported-by: syzbot+a98f2016f40b9cd3818a@syzkaller.appspotmail.com Reported-by: syzbot+ac36b6a33c28a491e929@syzkaller.appspotmail.com Fixes: c6c8fea29769 ("net: Add batman-adv meshing protocol") Signed-off-by: Sven Eckelmann Cc: Hillf Danton Signed-off-by: Simon Wunderlich --- net/batman-adv/bat_iv_ogm.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index f0209505e41a..a7c8dd7ae513 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -789,6 +789,10 @@ static void batadv_iv_ogm_schedule_buff(struct batadv_hard_iface *hard_iface) lockdep_assert_held(&hard_iface->bat_iv.ogm_buff_mutex); + /* interface already disabled by batadv_iv_ogm_iface_disable */ + if (!*ogm_buff) + return; + /* the interface gets activated here to avoid race conditions between * the moment of activating the interface in * hardif_activate_interface() where the originator mac is set and From dc7a06b0dbbafac8623c2b7657e61362f2f479a7 Mon Sep 17 00:00:00 2001 From: Nicolas Belin Date: Thu, 20 Feb 2020 14:15:12 +0100 Subject: [PATCH 017/256] pinctrl: meson-gxl: fix GPIOX sdio pins In the gxl driver, the sdio cmd and clk pins are inverted. It has not caused any issue so far because devices using these pins always take both pins so the resulting configuration is OK. Fixes: 0f15f500ff2c ("pinctrl: meson: Add GXL pinctrl definitions") Reviewed-by: Jerome Brunet Signed-off-by: Nicolas Belin Link: https://lore.kernel.org/r/1582204512-7582-1-git-send-email-nbelin@baylibre.com Signed-off-by: Linus Walleij --- drivers/pinctrl/meson/pinctrl-meson-gxl.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/pinctrl/meson/pinctrl-meson-gxl.c b/drivers/pinctrl/meson/pinctrl-meson-gxl.c index 1b6e8646700f..2ac921c83da9 100644 --- a/drivers/pinctrl/meson/pinctrl-meson-gxl.c +++ b/drivers/pinctrl/meson/pinctrl-meson-gxl.c @@ -147,8 +147,8 @@ static const unsigned int sdio_d0_pins[] = { GPIOX_0 }; static const unsigned int sdio_d1_pins[] = { GPIOX_1 }; static const unsigned int sdio_d2_pins[] = { GPIOX_2 }; static const unsigned int sdio_d3_pins[] = { GPIOX_3 }; -static const unsigned int sdio_cmd_pins[] = { GPIOX_4 }; -static const unsigned int sdio_clk_pins[] = { GPIOX_5 }; +static const unsigned int sdio_clk_pins[] = { GPIOX_4 }; +static const unsigned int sdio_cmd_pins[] = { GPIOX_5 }; static const unsigned int sdio_irq_pins[] = { GPIOX_7 }; static const unsigned int nand_ce0_pins[] = { BOOT_8 }; From 4c48e549f39f8ed10cf8a0b6cb96f5eddf0391ce Mon Sep 17 00:00:00 2001 From: Leonard Crestez Date: Thu, 20 Feb 2020 18:29:37 +0200 Subject: [PATCH 018/256] pinctrl: imx: scu: Align imx sc msg structs to 4 The imx SC api strongly assumes that messages are composed out of 4-bytes words but some of our message structs have odd sizeofs. This produces many oopses with CONFIG_KASAN=y. Fix by marking with __aligned(4). Fixes: b96eea718bf6 ("pinctrl: fsl: add scu based pinctrl support") Signed-off-by: Leonard Crestez Link: https://lore.kernel.org/r/bd7ad5fd755739a6d8d5f4f65e03b3ca4f457bd2.1582216144.git.leonard.crestez@nxp.com Signed-off-by: Linus Walleij --- drivers/pinctrl/freescale/pinctrl-scu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/pinctrl/freescale/pinctrl-scu.c b/drivers/pinctrl/freescale/pinctrl-scu.c index 73bf1d9f9cc6..23cf04bdfc55 100644 --- a/drivers/pinctrl/freescale/pinctrl-scu.c +++ b/drivers/pinctrl/freescale/pinctrl-scu.c @@ -23,12 +23,12 @@ struct imx_sc_msg_req_pad_set { struct imx_sc_rpc_msg hdr; u32 val; u16 pad; -} __packed; +} __packed __aligned(4); struct imx_sc_msg_req_pad_get { struct imx_sc_rpc_msg hdr; u16 pad; -} __packed; +} __packed __aligned(4); struct imx_sc_msg_resp_pad_get { struct imx_sc_rpc_msg hdr; From 1cef21842ff3b6043c459b6462183e70295b5b19 Mon Sep 17 00:00:00 2001 From: Scott Mayhew Date: Fri, 21 Feb 2020 15:21:38 -0500 Subject: [PATCH 019/256] NFS: Ensure the fs_context has the correct fs_type before mounting This is necessary because unless userspace explicitly requests fstype "nfs4" (either via "mount -t nfs4" or by calling the "mount.nfs4" helper directly), the fstype will default to "nfs". This was fine on older kernels because the super_block->s_type was set via mount_info->nfs_mod->nfs_fs, which was set when parsing the mount options and subsequently passed in the "type" argument of sget(). After commit f2aedb713c28 ("NFS: Add fs_context support."), sget_fc(), which has no "type" argument, is called instead. In sget_fc(), the super_block->s_type is set via fs_context->fs_type, which was set when the filesystem context was initially created. Reported-by: Patrick Steinhardt Fixes: f2aedb713c28 ("NFS: Add fs_context support.") Signed-off-by: Scott Mayhew Signed-off-by: Anna Schumaker --- fs/nfs/fs_context.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c index e1b938457ab9..b616263b0eb6 100644 --- a/fs/nfs/fs_context.c +++ b/fs/nfs/fs_context.c @@ -1240,6 +1240,13 @@ static int nfs_fs_context_validate(struct fs_context *fc) } ctx->nfs_mod = nfs_mod; } + + /* Ensure the filesystem context has the correct fs_type */ + if (fc->fs_type != ctx->nfs_mod->nfs_fs) { + module_put(fc->fs_type->owner); + __module_get(ctx->nfs_mod->nfs_fs->owner); + fc->fs_type = ctx->nfs_mod->nfs_fs; + } return 0; out_no_device_name: From 1821b26a1fed8fca57a96ef87bac7a6a48e78815 Mon Sep 17 00:00:00 2001 From: Scott Mayhew Date: Thu, 20 Feb 2020 08:06:20 -0500 Subject: [PATCH 020/256] NFS: Don't hard-code the fs_type when submounting Hard-coding the fstype causes "nfs4" mounts to appear as "nfs", which breaks scripts that do "umount -at nfs4". Reported-by: Patrick Steinhardt Fixes: f2aedb713c28 ("NFS: Add fs_context support.") Signed-off-by: Scott Mayhew Signed-off-by: Anna Schumaker --- fs/nfs/namespace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index ad6077404947..f3ece8ed3203 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -153,7 +153,7 @@ struct vfsmount *nfs_d_automount(struct path *path) /* Open a new filesystem context, transferring parameters from the * parent superblock, including the network namespace. */ - fc = fs_context_for_submount(&nfs_fs_type, path->dentry); + fc = fs_context_for_submount(path->mnt->mnt_sb->s_type, path->dentry); if (IS_ERR(fc)) return ERR_CAST(fc); From 75a9b9176157f3095d3099adf512b5a233addbc7 Mon Sep 17 00:00:00 2001 From: Scott Mayhew Date: Tue, 25 Feb 2020 11:05:22 -0500 Subject: [PATCH 021/256] NFS: Fix leak of ctx->nfs_server.hostname If userspace passes an nfs_mount_data struct in the data argument of mount(2), then nfs23_parse_monolithic() or nfs4_parse_monolithic() will allocate memory for ctx->nfs_server.hostname. This needs to be freed in nfs_parse_source(), which also allocates memory for ctx->nfs_server.hostname, otherwise a leak will occur. Reported-by: syzbot+193c375dcddb4f345091@syzkaller.appspotmail.com Fixes: f2aedb713c28 ("NFS: Add fs_context support.") Signed-off-by: Scott Mayhew Signed-off-by: Anna Schumaker --- fs/nfs/fs_context.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c index b616263b0eb6..e113fcb4bb4c 100644 --- a/fs/nfs/fs_context.c +++ b/fs/nfs/fs_context.c @@ -832,6 +832,8 @@ static int nfs_parse_source(struct fs_context *fc, if (len > maxnamlen) goto out_hostname; + kfree(ctx->nfs_server.hostname); + /* N.B. caller will free nfs_server.hostname in all cases */ ctx->nfs_server.hostname = kmemdup_nul(dev_name, len, GFP_KERNEL); if (!ctx->nfs_server.hostname) From 55dee1bc0d72877b99805e42e0205087e98b9edd Mon Sep 17 00:00:00 2001 From: Scott Mayhew Date: Mon, 24 Feb 2020 16:29:32 -0500 Subject: [PATCH 022/256] nfs: add minor version to nfs_server_key for fscache An NFS client that mounts multiple exports from the same NFS server with higher NFSv4 versions disabled (i.e. 4.2) and without forcing a specific NFS version results in fscache index cookie collisions and the following messages: [ 570.004348] FS-Cache: Duplicate cookie detected Each nfs_client structure should have its own fscache index cookie, so add the minorversion to nfs_server_key. Link: https://bugzilla.kernel.org/show_bug.cgi?id=200145 Signed-off-by: Scott Mayhew Signed-off-by: Dave Wysochanski Signed-off-by: Anna Schumaker --- fs/nfs/client.c | 1 + fs/nfs/fscache.c | 2 ++ fs/nfs/nfs4client.c | 1 - 3 files changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 989c30c98511..f1ff3076e4a4 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -153,6 +153,7 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init) if ((clp = kzalloc(sizeof(*clp), GFP_KERNEL)) == NULL) goto error_0; + clp->cl_minorversion = cl_init->minorversion; clp->cl_nfs_mod = cl_init->nfs_mod; if (!try_module_get(clp->cl_nfs_mod->owner)) goto error_dealloc; diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index 52270bfac120..1abf126c2df4 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -31,6 +31,7 @@ static DEFINE_SPINLOCK(nfs_fscache_keys_lock); struct nfs_server_key { struct { uint16_t nfsversion; /* NFS protocol version */ + uint32_t minorversion; /* NFSv4 minor version */ uint16_t family; /* address family */ __be16 port; /* IP port */ } hdr; @@ -55,6 +56,7 @@ void nfs_fscache_get_client_cookie(struct nfs_client *clp) memset(&key, 0, sizeof(key)); key.hdr.nfsversion = clp->rpc_ops->version; + key.hdr.minorversion = clp->cl_minorversion; key.hdr.family = clp->cl_addr.ss_family; switch (clp->cl_addr.ss_family) { diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 0cd767e5c977..0bd77cc1f639 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -216,7 +216,6 @@ struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init) INIT_LIST_HEAD(&clp->cl_ds_clients); rpc_init_wait_queue(&clp->cl_rpcwaitq, "NFS client"); clp->cl_state = 1 << NFS4CLNT_LEASE_EXPIRED; - clp->cl_minorversion = cl_init->minorversion; clp->cl_mvops = nfs_v4_minor_ops[cl_init->minorversion]; clp->cl_mig_gen = 1; #if IS_ENABLED(CONFIG_NFS_V4_1) From d364847eed890211444ad74496bb549f838c6018 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 25 Feb 2020 14:55:15 +0100 Subject: [PATCH 023/256] x86/mce/therm_throt: Undo thermal polling properly on CPU offline Chris Wilson reported splats from running the thermal throttling workqueue callback on offlined CPUs. The problem is that that callback should not even run on offlined CPUs but it happens nevertheless because the offlining callback thermal_throttle_offline() does not symmetrically undo the setup work done in its onlining counterpart. IOW, 1. The thermal interrupt vector should be masked out before ... 2. ... cancelling any pending work synchronously so that no new work is enqueued anymore. Do those things and fix the issue properly. [ bp: Write commit message. ] Fixes: f6656208f04e ("x86/mce/therm_throt: Optimize notifications of thermal throttle") Reported-by: Chris Wilson Tested-by: Pandruvada, Srinivas Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/158120068234.18291.7938335950259651295@skylake-alporthouse-com --- arch/x86/kernel/cpu/mce/therm_throt.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/cpu/mce/therm_throt.c b/arch/x86/kernel/cpu/mce/therm_throt.c index 58b4ee3cda77..f36dc0742085 100644 --- a/arch/x86/kernel/cpu/mce/therm_throt.c +++ b/arch/x86/kernel/cpu/mce/therm_throt.c @@ -486,9 +486,14 @@ static int thermal_throttle_offline(unsigned int cpu) { struct thermal_state *state = &per_cpu(thermal_state, cpu); struct device *dev = get_cpu_device(cpu); + u32 l; - cancel_delayed_work(&state->package_throttle.therm_work); - cancel_delayed_work(&state->core_throttle.therm_work); + /* Mask the thermal vector before draining evtl. pending work */ + l = apic_read(APIC_LVTTHMR); + apic_write(APIC_LVTTHMR, l | APIC_LVT_MASKED); + + cancel_delayed_work_sync(&state->package_throttle.therm_work); + cancel_delayed_work_sync(&state->core_throttle.therm_work); state->package_throttle.rate_control_active = false; state->core_throttle.rate_control_active = false; From 8e029eb0bcd6a7fab6dc9191152c085784c31ee6 Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Tue, 25 Feb 2020 12:28:09 -0300 Subject: [PATCH 024/256] MIPS: Fix CONFIG_MIPS_CMDLINE_DTB_EXTEND handling The CONFIG_MIPS_CMDLINE_DTB_EXTEND option is used so that the kernel arguments provided in the 'bootargs' property in devicetree are extended with the kernel arguments provided by the bootloader. The code was broken, as it didn't actually take any of the kernel arguments provided in devicetree when that option was set. Fixes: 7784cac69735 ("MIPS: cmdline: Clean up boot_command_line initialization") Cc: stable@vger.kernel.org Signed-off-by: Paul Cercueil Signed-off-by: Thomas Bogendoerfer --- arch/mips/kernel/setup.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 1ac2752fb791..a7b469d89e2c 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -605,7 +605,8 @@ static void __init bootcmdline_init(char **cmdline_p) * If we're configured to take boot arguments from DT, look for those * now. */ - if (IS_ENABLED(CONFIG_MIPS_CMDLINE_FROM_DTB)) + if (IS_ENABLED(CONFIG_MIPS_CMDLINE_FROM_DTB) || + IS_ENABLED(CONFIG_MIPS_CMDLINE_DTB_EXTEND)) of_scan_flat_dt(bootcmdline_scan_chosen, &dt_bootargs); #endif From 59b5809655bdafb0767d3fd00a3e41711aab07e6 Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Tue, 25 Feb 2020 17:17:37 -0800 Subject: [PATCH 025/256] x86/mce: Fix logic and comments around MSR_PPIN_CTL There are two implemented bits in the PPIN_CTL MSR: Bit 0: LockOut (R/WO) Set 1 to prevent further writes to MSR_PPIN_CTL. Bit 1: Enable_PPIN (R/W) If 1, enables MSR_PPIN to be accessible using RDMSR. If 0, an attempt to read MSR_PPIN will cause #GP. So there are four defined values: 0: PPIN is disabled, PPIN_CTL may be updated 1: PPIN is disabled. PPIN_CTL is locked against updates 2: PPIN is enabled. PPIN_CTL may be updated 3: PPIN is enabled. PPIN_CTL is locked against updates Code would only enable the X86_FEATURE_INTEL_PPIN feature for case "2". When it should have done so for both case "2" and case "3". Fix the final test to just check for the enable bit. Also fix some of the other comments in this function. Fixes: 3f5a7896a509 ("x86/mce: Include the PPIN in MCE records when available") Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov Cc: Link: https://lkml.kernel.org/r/20200226011737.9958-1-tony.luck@intel.com --- arch/x86/kernel/cpu/mce/intel.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c index 5627b1091b85..f996ffb887bc 100644 --- a/arch/x86/kernel/cpu/mce/intel.c +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -493,17 +493,18 @@ static void intel_ppin_init(struct cpuinfo_x86 *c) return; if ((val & 3UL) == 1UL) { - /* PPIN available but disabled: */ + /* PPIN locked in disabled mode */ return; } - /* If PPIN is disabled, but not locked, try to enable: */ - if (!(val & 3UL)) { + /* If PPIN is disabled, try to enable */ + if (!(val & 2UL)) { wrmsrl_safe(MSR_PPIN_CTL, val | 2UL); rdmsrl_safe(MSR_PPIN_CTL, &val); } - if ((val & 3UL) == 2UL) + /* Is the enable bit set? */ + if (val & 2UL) set_cpu_cap(c, X86_FEATURE_INTEL_PPIN); } } From aafd56fc79041bf36f97712d4b35208cbe07db90 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Fri, 28 Feb 2020 15:41:42 +0000 Subject: [PATCH 026/256] pinctrl: core: Remove extra kref_get which blocks hogs being freed kref_init starts with the reference count at 1, which will be balanced by the pinctrl_put in pinctrl_unregister. The additional kref_get in pinctrl_claim_hogs will increase this count to 2 and cause the hogs to not get freed when pinctrl_unregister is called. Fixes: 6118714275f0 ("pinctrl: core: Fix pinctrl_register_and_init() with pinctrl_enable()") Signed-off-by: Charles Keepax Link: https://lore.kernel.org/r/20200228154142.13860-1-ckeepax@opensource.cirrus.com Signed-off-by: Linus Walleij --- drivers/pinctrl/core.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c index 446d84fe0e31..f23c55e22195 100644 --- a/drivers/pinctrl/core.c +++ b/drivers/pinctrl/core.c @@ -2021,7 +2021,6 @@ static int pinctrl_claim_hogs(struct pinctrl_dev *pctldev) return PTR_ERR(pctldev->p); } - kref_get(&pctldev->p->users); pctldev->hog_default = pinctrl_lookup_state(pctldev->p, PINCTRL_STATE_DEFAULT); if (IS_ERR(pctldev->hog_default)) { From 3567ee83c413a939d45fea2e2f2c4968a9f81460 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Fri, 28 Feb 2020 15:42:14 +0000 Subject: [PATCH 027/256] pinctrl: madera: Add missing call to pinctrl_unregister_mappings pinctrl_register_mappings is called in the pdata case, however a call to pinctrl_unregister_mappings is missing causing the mappings to be leaked on driver unbind. Add the missing call to correct this issue. Signed-off-by: Charles Keepax Link: https://lore.kernel.org/r/20200228154214.13916-1-ckeepax@opensource.cirrus.com Signed-off-by: Linus Walleij --- drivers/pinctrl/cirrus/pinctrl-madera-core.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/pinctrl/cirrus/pinctrl-madera-core.c b/drivers/pinctrl/cirrus/pinctrl-madera-core.c index 7b6409ef553c..dce2626384a9 100644 --- a/drivers/pinctrl/cirrus/pinctrl-madera-core.c +++ b/drivers/pinctrl/cirrus/pinctrl-madera-core.c @@ -1073,13 +1073,26 @@ static int madera_pin_probe(struct platform_device *pdev) return ret; } + platform_set_drvdata(pdev, priv); + dev_dbg(priv->dev, "pinctrl probed ok\n"); return 0; } +static int madera_pin_remove(struct platform_device *pdev) +{ + struct madera_pin_private *priv = platform_get_drvdata(pdev); + + if (priv->madera->pdata.gpio_configs) + pinctrl_unregister_mappings(priv->madera->pdata.gpio_configs); + + return 0; +} + static struct platform_driver madera_pin_driver = { .probe = madera_pin_probe, + .remove = madera_pin_remove, .driver = { .name = "madera-pinctrl", }, From d64c7a08034b32c285e576208ae44fc3ba3fa7df Mon Sep 17 00:00:00 2001 From: You-Sheng Yang Date: Wed, 26 Feb 2020 23:37:10 +0800 Subject: [PATCH 028/256] r8152: check disconnect status after long sleep Dell USB Type C docking WD19/WD19DC attaches additional peripherals as: /: Bus 02.Port 1: Dev 1, Class=root_hub, Driver=xhci_hcd/6p, 5000M |__ Port 1: Dev 11, If 0, Class=Hub, Driver=hub/4p, 5000M |__ Port 3: Dev 12, If 0, Class=Hub, Driver=hub/4p, 5000M |__ Port 4: Dev 13, If 0, Class=Vendor Specific Class, Driver=r8152, 5000M where usb 2-1-3 is a hub connecting all USB Type-A/C ports on the dock. When hotplugging such dock with additional usb devices already attached on it, the probing process may reset usb 2.1 port, therefore r8152 ethernet device is also reset. However, during r8152 device init there are several for-loops that, when it's unable to retrieve hardware registers due to being disconnected from USB, may take up to 14 seconds each in practice, and that has to be completed before USB may re-enumerate devices on the bus. As a result, devices attached to the dock will only be available after nearly 1 minute after the dock was plugged in: [ 216.388290] [250] r8152 2-1.4:1.0: usb_probe_interface [ 216.388292] [250] r8152 2-1.4:1.0: usb_probe_interface - got id [ 258.830410] r8152 2-1.4:1.0 (unnamed net_device) (uninitialized): PHY not ready [ 258.830460] r8152 2-1.4:1.0 (unnamed net_device) (uninitialized): Invalid header when reading pass-thru MAC addr [ 258.830464] r8152 2-1.4:1.0 (unnamed net_device) (uninitialized): Get ether addr fail This happens in, for example, r8153_init: static int generic_ocp_read(struct r8152 *tp, u16 index, u16 size, void *data, u16 type) { if (test_bit(RTL8152_UNPLUG, &tp->flags)) return -ENODEV; ... } static u16 ocp_read_word(struct r8152 *tp, u16 type, u16 index) { u32 data; ... generic_ocp_read(tp, index, sizeof(tmp), &tmp, type | byen); data = __le32_to_cpu(tmp); ... return (u16)data; } static void r8153_init(struct r8152 *tp) { ... if (test_bit(RTL8152_UNPLUG, &tp->flags)) return; for (i = 0; i < 500; i++) { if (ocp_read_word(tp, MCU_TYPE_PLA, PLA_BOOT_CTRL) & AUTOLOAD_DONE) break; msleep(20); } ... } Since ocp_read_word() doesn't check the return status of generic_ocp_read(), and the only exit condition for the loop is to have a match in the returned value, such loops will only ends after exceeding its maximum runs when the device has been marked as disconnected, which takes 500 * 20ms = 10 seconds in theory, 14 in practice. To solve this long latency another test to RTL8152_UNPLUG flag should be added after those 20ms sleep to skip unnecessary loops, so that the device probe can complete early and proceed to parent port reset/reprobe process. This can be reproduced on all kernel versions up to latest v5.6-rc2, but after v5.5-rc7 the reproduce rate is dramatically lowered to 1/30 or less while it was around 1/2. Signed-off-by: You-Sheng Yang Signed-off-by: David S. Miller --- drivers/net/usb/r8152.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 78ddbaf6401b..95b19ce96513 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -3221,6 +3221,8 @@ static u16 r8153_phy_status(struct r8152 *tp, u16 desired) } msleep(20); + if (test_bit(RTL8152_UNPLUG, &tp->flags)) + break; } return data; @@ -5402,7 +5404,10 @@ static void r8153_init(struct r8152 *tp) if (ocp_read_word(tp, MCU_TYPE_PLA, PLA_BOOT_CTRL) & AUTOLOAD_DONE) break; + msleep(20); + if (test_bit(RTL8152_UNPLUG, &tp->flags)) + break; } data = r8153_phy_status(tp, 0); @@ -5539,7 +5544,10 @@ static void r8153b_init(struct r8152 *tp) if (ocp_read_word(tp, MCU_TYPE_PLA, PLA_BOOT_CTRL) & AUTOLOAD_DONE) break; + msleep(20); + if (test_bit(RTL8152_UNPLUG, &tp->flags)) + break; } data = r8153_phy_status(tp, 0); From 84b3268027641401bb8ad4427a90a3cce2eb86f5 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 26 Feb 2020 19:47:34 +0100 Subject: [PATCH 029/256] netlink: Use netlink header as base to calculate bad attribute offset Userspace might send a batch that is composed of several netlink messages. The netlink_ack() function must use the pointer to the netlink header as base to calculate the bad attribute offset. Fixes: 2d4bc93368f5 ("netlink: extended ACK reporting") Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- net/netlink/af_netlink.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index edf3e285e242..5313f1cec170 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2434,7 +2434,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, in_skb->len)) WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_OFFS, (u8 *)extack->bad_attr - - in_skb->data)); + (u8 *)nlh)); } else { if (extack->cookie_len) WARN_ON(nla_put(skb, NLMSGERR_ATTR_COOKIE, From 8a171c5cc9de7fb0a485341b790aba736978ed73 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 27 Feb 2020 18:09:44 -0800 Subject: [PATCH 030/256] atm: nicstar: fix if-statement empty body warning MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When debugging via PRINTK() is not enabled, make the PRINTK() macro be an empty do-while block. Thix fixes a gcc warning when -Wextra is set: ../drivers/atm/nicstar.c:1819:23: warning: suggest braces around empty body in an ‘else’ statement [-Wempty-body] I have verified that there is no object code change (with gcc 7.5.0). Signed-off-by: Randy Dunlap Cc: Chas Williams <3chas3@gmail.com> Cc: linux-atm-general@lists.sourceforge.net Cc: netdev@vger.kernel.org Cc: David S. Miller Signed-off-by: David S. Miller --- drivers/atm/nicstar.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/atm/nicstar.c b/drivers/atm/nicstar.c index 8db8c0fb5e2d..7af74fb450a0 100644 --- a/drivers/atm/nicstar.c +++ b/drivers/atm/nicstar.c @@ -91,7 +91,7 @@ #ifdef GENERAL_DEBUG #define PRINTK(args...) printk(args) #else -#define PRINTK(args...) +#define PRINTK(args...) do {} while (0) #endif /* GENERAL_DEBUG */ #ifdef EXTRA_DEBUG From 0395823b8d9a4d87bd1bf74359123461c2ae801b Mon Sep 17 00:00:00 2001 From: Russell King Date: Fri, 28 Feb 2020 19:39:41 +0000 Subject: [PATCH 031/256] net: dsa: mv88e6xxx: fix lockup on warm boot If the switch is not hardware reset on a warm boot, interrupts can be left enabled, and possibly pending. This will cause us to enter an infinite loop trying to service an interrupt we are unable to handle, thereby preventing the kernel from booting. Ensure that the global 2 interrupt sources are disabled before we claim the parent interrupt. Observed on the ZII development revision B and C platforms with reworked serdes support, and using reboot -f to reboot the platform. Fixes: dc30c35be720 ("net: dsa: mv88e6xxx: Implement interrupt support.") Signed-off-by: Russell King Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/global2.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/net/dsa/mv88e6xxx/global2.c b/drivers/net/dsa/mv88e6xxx/global2.c index 01503014b1ee..8fd483020c5b 100644 --- a/drivers/net/dsa/mv88e6xxx/global2.c +++ b/drivers/net/dsa/mv88e6xxx/global2.c @@ -1099,6 +1099,13 @@ int mv88e6xxx_g2_irq_setup(struct mv88e6xxx_chip *chip) { int err, irq, virq; + chip->g2_irq.masked = ~0; + mv88e6xxx_reg_lock(chip); + err = mv88e6xxx_g2_int_mask(chip, ~chip->g2_irq.masked); + mv88e6xxx_reg_unlock(chip); + if (err) + return err; + chip->g2_irq.domain = irq_domain_add_simple( chip->dev->of_node, 16, 0, &mv88e6xxx_g2_irq_domain_ops, chip); if (!chip->g2_irq.domain) @@ -1108,7 +1115,6 @@ int mv88e6xxx_g2_irq_setup(struct mv88e6xxx_chip *chip) irq_create_mapping(chip->g2_irq.domain, irq); chip->g2_irq.chip = mv88e6xxx_g2_irq_chip; - chip->g2_irq.masked = ~0; chip->device_irq = irq_find_mapping(chip->g1_irq.domain, MV88E6XXX_G1_STS_IRQ_DEVICE); From 07758eb9ff52794fba15d03aa88d92dbd1b7d125 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Sat, 29 Feb 2020 17:27:13 +0800 Subject: [PATCH 032/256] net/ipv6: use configured metric when add peer route When we add peer address with metric configured, IPv4 could set the dest metric correctly, but IPv6 do not. e.g. ]# ip addr add 192.0.2.1 peer 192.0.2.2/32 dev eth1 metric 20 ]# ip route show dev eth1 192.0.2.2 proto kernel scope link src 192.0.2.1 metric 20 ]# ip addr add 2001:db8::1 peer 2001:db8::2/128 dev eth1 metric 20 ]# ip -6 route show dev eth1 2001:db8::1 proto kernel metric 20 pref medium 2001:db8::2 proto kernel metric 256 pref medium Fix this by using configured metric instead of default one. Reported-by: Jianlin Shi Fixes: 8308f3ff1753 ("net/ipv6: Add support for specifying metric of connected routes") Reviewed-by: David Ahern Signed-off-by: Hangbin Liu Signed-off-by: David S. Miller --- net/ipv6/addrconf.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index cb493e15959c..164c71c54b5c 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5983,9 +5983,9 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) if (ifp->idev->cnf.forwarding) addrconf_join_anycast(ifp); if (!ipv6_addr_any(&ifp->peer_addr)) - addrconf_prefix_route(&ifp->peer_addr, 128, 0, - ifp->idev->dev, 0, 0, - GFP_ATOMIC); + addrconf_prefix_route(&ifp->peer_addr, 128, + ifp->rt_priority, ifp->idev->dev, + 0, 0, GFP_ATOMIC); break; case RTM_DELADDR: if (ifp->idev->cnf.forwarding) From 52c0d4e306ca0261a896f5e2ad823112195b7f4b Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 29 Feb 2020 22:30:07 +0200 Subject: [PATCH 033/256] net: dsa: sja1105: Don't destroy not-yet-created xmit_worker Fixes the following NULL pointer dereference on PHY connect error path teardown: [ 2.291010] sja1105 spi0.1: Probed switch chip: SJA1105T [ 2.310044] sja1105 spi0.1: Enabled switch tagging [ 2.314970] fsl-gianfar soc:ethernet@2d90000 eth2: error -19 setting up slave phy [ 2.322463] 8<--- cut here --- [ 2.325497] Unable to handle kernel NULL pointer dereference at virtual address 00000018 [ 2.333555] pgd = (ptrval) [ 2.336241] [00000018] *pgd=00000000 [ 2.339797] Internal error: Oops: 5 [#1] SMP ARM [ 2.344384] Modules linked in: [ 2.347420] CPU: 1 PID: 64 Comm: kworker/1:1 Not tainted 5.5.0-rc5 #1 [ 2.353820] Hardware name: Freescale LS1021A [ 2.358070] Workqueue: events deferred_probe_work_func [ 2.363182] PC is at kthread_destroy_worker+0x4/0x74 [ 2.368117] LR is at sja1105_teardown+0x70/0xb4 [ 2.372617] pc : [] lr : [] psr: 60000013 [ 2.378845] sp : eeac3d30 ip : eeab1900 fp : eef45480 [ 2.384036] r10: eef4549c r9 : 00000001 r8 : 00000000 [ 2.389227] r7 : eef527c0 r6 : 00000034 r5 : ed8ddd0c r4 : ed8ddc40 [ 2.395714] r3 : 00000000 r2 : 00000000 r1 : eef4549c r0 : 00000000 [ 2.402204] Flags: nZCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment none [ 2.409297] Control: 10c5387d Table: 8020406a DAC: 00000051 [ 2.415008] Process kworker/1:1 (pid: 64, stack limit = 0x(ptrval)) [ 2.421237] Stack: (0xeeac3d30 to 0xeeac4000) [ 2.612635] [] (kthread_destroy_worker) from [] (sja1105_teardown+0x70/0xb4) [ 2.621379] [] (sja1105_teardown) from [] (dsa_switch_teardown.part.1+0x48/0x74) [ 2.630467] [] (dsa_switch_teardown.part.1) from [] (dsa_register_switch+0x8b0/0xbf4) [ 2.639984] [] (dsa_register_switch) from [] (sja1105_probe+0x2ac/0x464) [ 2.648378] [] (sja1105_probe) from [] (spi_drv_probe+0x7c/0xa0) [ 2.656081] [] (spi_drv_probe) from [] (really_probe+0x208/0x480) [ 2.663871] [] (really_probe) from [] (driver_probe_device+0x78/0x1c4) [ 2.672093] [] (driver_probe_device) from [] (bus_for_each_drv+0x80/0xc4) [ 2.680574] [] (bus_for_each_drv) from [] (__device_attach+0xd0/0x168) [ 2.688794] [] (__device_attach) from [] (bus_probe_device+0x84/0x8c) [ 2.696927] [] (bus_probe_device) from [] (deferred_probe_work_func+0x84/0xc4) [ 2.705842] [] (deferred_probe_work_func) from [] (process_one_work+0x22c/0x560) [ 2.714926] [] (process_one_work) from [] (worker_thread+0x2a8/0x5d4) [ 2.723059] [] (worker_thread) from [] (kthread+0x150/0x154) [ 2.730416] [] (kthread) from [] (ret_from_fork+0x14/0x2c) Checking for NULL pointer is correct because the per-port xmit kernel threads are created in sja1105_probe immediately after calling dsa_register_switch. Fixes: a68578c20a96 ("net: dsa: Make deferred_xmit private to sja1105") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 03ba6d25f7fe..7edea5741a5f 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -1741,7 +1741,8 @@ static void sja1105_teardown(struct dsa_switch *ds) if (!dsa_is_user_port(ds, port)) continue; - kthread_destroy_worker(sp->xmit_worker); + if (sp->xmit_worker) + kthread_destroy_worker(sp->xmit_worker); } sja1105_tas_teardown(ds); From 249bc9744e165abe74ae326f43e9d70bad54c3b7 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sun, 1 Mar 2020 21:36:09 +0100 Subject: [PATCH 034/256] net: phy: avoid clearing PHY interrupts twice in irq handler On all PHY drivers that implement did_interrupt() reading the interrupt status bits clears them. This means we may loose an interrupt that is triggered between calling did_interrupt() and phy_clear_interrupt(). As part of the fix make it a requirement that did_interrupt() clears the interrupt. The Fixes tag refers to the first commit where the patch applies cleanly. Fixes: 49644e68f472 ("net: phy: add callback for custom interrupt handler to struct phy_driver") Reported-by: Michael Walle Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- drivers/net/phy/phy.c | 3 ++- include/linux/phy.h | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index d76e038cf2cb..355bfdef48d2 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -727,7 +727,8 @@ static irqreturn_t phy_interrupt(int irq, void *phy_dat) phy_trigger_machine(phydev); } - if (phy_clear_interrupt(phydev)) + /* did_interrupt() may have cleared the interrupt already */ + if (!phydev->drv->did_interrupt && phy_clear_interrupt(phydev)) goto phy_err; return IRQ_HANDLED; diff --git a/include/linux/phy.h b/include/linux/phy.h index c570e162e05e..22f5e763e894 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -557,6 +557,7 @@ struct phy_driver { /* * Checks if the PHY generated an interrupt. * For multi-PHY devices with shared PHY interrupt pin + * Set interrupt bits have to be cleared. */ int (*did_interrupt)(struct phy_device *phydev); From a9b952d267e59a3b405e644930f46d252cea7122 Mon Sep 17 00:00:00 2001 From: Vasundhara Volam Date: Sun, 1 Mar 2020 22:07:17 -0500 Subject: [PATCH 035/256] bnxt_en: reinitialize IRQs when MTU is modified MTU changes may affect the number of IRQs so we must call bnxt_close_nic()/bnxt_open_nic() with the irq_re_init parameter set to true. The reason is that a larger MTU may require aggregation rings not needed with smaller MTU. We may not be able to allocate the required number of aggregation rings and so we reduce the number of channels which will change the number of IRQs. Without this patch, it may crash eventually in pci_disable_msix() when the IRQs are not properly unwound. Fixes: c0c050c58d84 ("bnxt_en: New Broadcom ethernet driver.") Signed-off-by: Vasundhara Volam Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index f9a8151f092c..c5c8effc0139 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -10982,13 +10982,13 @@ static int bnxt_change_mtu(struct net_device *dev, int new_mtu) struct bnxt *bp = netdev_priv(dev); if (netif_running(dev)) - bnxt_close_nic(bp, false, false); + bnxt_close_nic(bp, true, false); dev->mtu = new_mtu; bnxt_set_ring_params(bp); if (netif_running(dev)) - return bnxt_open_nic(bp, false, false); + return bnxt_open_nic(bp, true, false); return 0; } From 22630e28f9c2b55abd217869cc0696def89f2284 Mon Sep 17 00:00:00 2001 From: Edwin Peer Date: Sun, 1 Mar 2020 22:07:18 -0500 Subject: [PATCH 036/256] bnxt_en: fix error handling when flashing from file After bnxt_hwrm_do_send_message() was updated to return standard error codes in a recent commit, a regression in bnxt_flash_package_from_file() was introduced. The return value does not properly reflect all possible firmware errors when calling firmware to flash the package. Fix it by consolidating all errors in one local variable rc instead of having 2 variables for different errors. Fixes: d4f1420d3656 ("bnxt_en: Convert error code in firmware message response to standard code.") Signed-off-by: Edwin Peer Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- .../net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 24 +++++++++---------- 1 file changed, 11 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index e8fc1671c581..1f67e6729a2c 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -2007,8 +2007,8 @@ int bnxt_flash_package_from_file(struct net_device *dev, const char *filename, struct hwrm_nvm_install_update_output *resp = bp->hwrm_cmd_resp_addr; struct hwrm_nvm_install_update_input install = {0}; const struct firmware *fw; - int rc, hwrm_err = 0; u32 item_len; + int rc = 0; u16 index; bnxt_hwrm_fw_set_time(bp); @@ -2052,15 +2052,14 @@ int bnxt_flash_package_from_file(struct net_device *dev, const char *filename, memcpy(kmem, fw->data, fw->size); modify.host_src_addr = cpu_to_le64(dma_handle); - hwrm_err = hwrm_send_message(bp, &modify, - sizeof(modify), - FLASH_PACKAGE_TIMEOUT); + rc = hwrm_send_message(bp, &modify, sizeof(modify), + FLASH_PACKAGE_TIMEOUT); dma_free_coherent(&bp->pdev->dev, fw->size, kmem, dma_handle); } } release_firmware(fw); - if (rc || hwrm_err) + if (rc) goto err_exit; if ((install_type & 0xffff) == 0) @@ -2069,20 +2068,19 @@ int bnxt_flash_package_from_file(struct net_device *dev, const char *filename, install.install_type = cpu_to_le32(install_type); mutex_lock(&bp->hwrm_cmd_lock); - hwrm_err = _hwrm_send_message(bp, &install, sizeof(install), - INSTALL_PACKAGE_TIMEOUT); - if (hwrm_err) { + rc = _hwrm_send_message(bp, &install, sizeof(install), + INSTALL_PACKAGE_TIMEOUT); + if (rc) { u8 error_code = ((struct hwrm_err_output *)resp)->cmd_err; if (resp->error_code && error_code == NVM_INSTALL_UPDATE_CMD_ERR_CODE_FRAG_ERR) { install.flags |= cpu_to_le16( NVM_INSTALL_UPDATE_REQ_FLAGS_ALLOWED_TO_DEFRAG); - hwrm_err = _hwrm_send_message(bp, &install, - sizeof(install), - INSTALL_PACKAGE_TIMEOUT); + rc = _hwrm_send_message(bp, &install, sizeof(install), + INSTALL_PACKAGE_TIMEOUT); } - if (hwrm_err) + if (rc) goto flash_pkg_exit; } @@ -2094,7 +2092,7 @@ int bnxt_flash_package_from_file(struct net_device *dev, const char *filename, flash_pkg_exit: mutex_unlock(&bp->hwrm_cmd_lock); err_exit: - if (hwrm_err == -EACCES) + if (rc == -EACCES) bnxt_print_admin_err(bp); return rc; } From cff20b3151ccab690715cb6cf0f5da5cccb32adf Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 2 Mar 2020 11:13:19 -0300 Subject: [PATCH 037/256] perf tests bp_account: Make global variable static To fix the build with newer gccs, that without this patch exit with: LD /tmp/build/perf/tests/perf-in.o ld: /tmp/build/perf/tests/bp_account.o:/git/perf/tools/perf/tests/bp_account.c:22: multiple definition of `the_var'; /tmp/build/perf/tests/bp_signal.o:/git/perf/tools/perf/tests/bp_signal.c:38: first defined here make[4]: *** [/git/perf/tools/build/Makefile.build:145: /tmp/build/perf/tests/perf-in.o] Error 1 First noticed in fedora:rawhide/32 with: [perfbuilder@a5ff49d6e6e4 ~]$ gcc --version gcc (GCC) 10.0.1 20200216 (Red Hat 10.0.1-0.8) Reported-by: Jiri Olsa Cc: Adrian Hunter Cc: Namhyung Kim Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/bp_account.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/tests/bp_account.c b/tools/perf/tests/bp_account.c index d0b935356274..489b50604cf2 100644 --- a/tools/perf/tests/bp_account.c +++ b/tools/perf/tests/bp_account.c @@ -19,7 +19,7 @@ #include "../perf-sys.h" #include "cloexec.h" -volatile long the_var; +static volatile long the_var; static noinline int test_function(void) { From ebcb9464a2ae3a547e97de476575c82ece0e93e2 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 2 Mar 2020 11:23:03 -0300 Subject: [PATCH 038/256] perf env: Do not return pointers to local variables It is possible to return a pointer to a local variable when looking up the architecture name for the running system and no normalization is done on that value, i.e. we may end up returning the uts.machine local variable. While this doesn't happen on most arches, as normalization takes place, lets fix this by making that a static variable and optimize it a bit by not always running uname(), only the first time. Noticed in fedora rawhide running with: [perfbuilder@a5ff49d6e6e4 ~]$ gcc --version gcc (GCC) 10.0.1 20200216 (Red Hat 10.0.1-0.8) Reported-by: Jiri Olsa Cc: Adrian Hunter Cc: Namhyung Kim Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/env.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 6242a9215df7..4154f944f474 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -343,11 +343,11 @@ static const char *normalize_arch(char *arch) const char *perf_env__arch(struct perf_env *env) { - struct utsname uts; char *arch_name; if (!env || !env->arch) { /* Assume local operation */ - if (uname(&uts) < 0) + static struct utsname uts = { .machine[0] = '\0', }; + if (uts.machine[0] == '\0' && uname(&uts) < 0) return NULL; arch_name = uts.machine; } else From 7125f204501ed55493593209c6c71ac7c38f6b6c Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 2 Mar 2020 11:55:47 -0300 Subject: [PATCH 039/256] perf parse-events: Use asprintf() instead of strncpy() to read tracepoint files MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Make the code more compact by using asprintf() instead of malloc()+strncpy() which also uses less memory and avoids these warnings with gcc 10: CC /tmp/build/perf/util/cloexec.o In file included from /usr/include/string.h:495, from util/parse-events.h:12, from util/parse-events.c:18: In function ‘strncpy’, inlined from ‘tracepoint_id_to_path’ at util/parse-events.c:271:5: /usr/include/bits/string_fortified.h:106:10: error: ‘__builtin_strncpy’ offset [275, 511] from the object at ‘sys_dirent’ is out of the bounds of referenced subobject ‘d_name’ with type ‘char[256]’ at offset 19 [-Werror=array-bounds] 106 | return __builtin___strncpy_chk (__dest, __src, __len, __bos (__dest)); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ In file included from /usr/include/dirent.h:61, from util/parse-events.c:5: util/parse-events.c: In function ‘tracepoint_id_to_path’: /usr/include/bits/dirent.h:33:10: note: subobject ‘d_name’ declared here 33 | char d_name[256]; /* We must not include limits.h! */ | ^~~~~~ In file included from /usr/include/string.h:495, from util/parse-events.h:12, from util/parse-events.c:18: In function ‘strncpy’, inlined from ‘tracepoint_id_to_path’ at util/parse-events.c:273:5: /usr/include/bits/string_fortified.h:106:10: error: ‘__builtin_strncpy’ offset [275, 511] from the object at ‘evt_dirent’ is out of the bounds of referenced subobject ‘d_name’ with type ‘char[256]’ at offset 19 [-Werror=array-bounds] 106 | return __builtin___strncpy_chk (__dest, __src, __len, __bos (__dest)); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ In file included from /usr/include/dirent.h:61, from util/parse-events.c:5: util/parse-events.c: In function ‘tracepoint_id_to_path’: /usr/include/bits/dirent.h:33:10: note: subobject ‘d_name’ declared here 33 | char d_name[256]; /* We must not include limits.h! */ | ^~~~~~ CC /tmp/build/perf/util/call-path.o Cc: Adrian Hunter Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lore.kernel.org/lkml/20200302145535.GA28183@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-events.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index c01ba6f8fdad..a14995835d85 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -257,21 +257,15 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config) path = zalloc(sizeof(*path)); if (!path) return NULL; - path->system = malloc(MAX_EVENT_LENGTH); - if (!path->system) { + if (asprintf(&path->system, "%.*s", MAX_EVENT_LENGTH, sys_dirent->d_name) < 0) { free(path); return NULL; } - path->name = malloc(MAX_EVENT_LENGTH); - if (!path->name) { + if (asprintf(&path->name, "%.*s", MAX_EVENT_LENGTH, evt_dirent->d_name) < 0) { zfree(&path->system); free(path); return NULL; } - strncpy(path->system, sys_dirent->d_name, - MAX_EVENT_LENGTH); - strncpy(path->name, evt_dirent->d_name, - MAX_EVENT_LENGTH); return path; } } From 2de7fb60a4740135e03cf55c1982e393ccb87b6b Mon Sep 17 00:00:00 2001 From: Mike Gilbert Date: Wed, 26 Feb 2020 14:33:59 -0500 Subject: [PATCH 040/256] cpupower: avoid multiple definition with gcc -fno-common Building cpupower with -fno-common in CFLAGS results in errors due to multiple definitions of the 'cpu_count' and 'start_time' variables. ./utils/idle_monitor/snb_idle.o:./utils/idle_monitor/cpupower-monitor.h:28: multiple definition of `cpu_count'; ./utils/idle_monitor/nhm_idle.o:./utils/idle_monitor/cpupower-monitor.h:28: first defined here ... ./utils/idle_monitor/cpuidle_sysfs.o:./utils/idle_monitor/cpuidle_sysfs.c:22: multiple definition of `start_time'; ./utils/idle_monitor/amd_fam14h_idle.o:./utils/idle_monitor/amd_fam14h_idle.c:85: first defined here The -fno-common option will be enabled by default in GCC 10. Bug: https://bugs.gentoo.org/707462 Signed-off-by: Mike Gilbert Signed-off-by: Shuah Khan --- tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c | 2 +- tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c | 2 +- tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c | 2 ++ tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h | 2 +- 4 files changed, 5 insertions(+), 3 deletions(-) diff --git a/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c b/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c index 33dc34db4f3c..20f46348271b 100644 --- a/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c +++ b/tools/power/cpupower/utils/idle_monitor/amd_fam14h_idle.c @@ -82,7 +82,7 @@ static struct pci_access *pci_acc; static struct pci_dev *amd_fam14h_pci_dev; static int nbp1_entered; -struct timespec start_time; +static struct timespec start_time; static unsigned long long timediff; #ifdef DEBUG diff --git a/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c b/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c index 3c4cee160b0e..a65f7d011513 100644 --- a/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c +++ b/tools/power/cpupower/utils/idle_monitor/cpuidle_sysfs.c @@ -19,7 +19,7 @@ struct cpuidle_monitor cpuidle_sysfs_monitor; static unsigned long long **previous_count; static unsigned long long **current_count; -struct timespec start_time; +static struct timespec start_time; static unsigned long long timediff; static int cpuidle_get_count_percent(unsigned int id, double *percent, diff --git a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c index 6d44fec55ad5..7c77045fef52 100644 --- a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c +++ b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c @@ -27,6 +27,8 @@ struct cpuidle_monitor *all_monitors[] = { 0 }; +int cpu_count; + static struct cpuidle_monitor *monitors[MONITORS_MAX]; static unsigned int avail_monitors; diff --git a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h index 5b5eb1da0cce..c559d3115330 100644 --- a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h +++ b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.h @@ -25,7 +25,7 @@ #endif #define CSTATE_DESC_LEN 60 -int cpu_count; +extern int cpu_count; /* Hard to define the right names ...: */ enum power_range_e { From 02d715b4a8182f4887d82df82a7b83aced647760 Mon Sep 17 00:00:00 2001 From: Amol Grover Date: Sun, 23 Feb 2020 22:25:39 +0530 Subject: [PATCH 041/256] iommu/vt-d: Fix RCU list debugging warnings dmar_drhd_units is traversed using list_for_each_entry_rcu() outside of an RCU read side critical section but under the protection of dmar_global_lock. Hence add corresponding lockdep expression to silence the following false-positive warnings: [ 1.603975] ============================= [ 1.603976] WARNING: suspicious RCU usage [ 1.603977] 5.5.4-stable #17 Not tainted [ 1.603978] ----------------------------- [ 1.603980] drivers/iommu/intel-iommu.c:4769 RCU-list traversed in non-reader section!! [ 1.603869] ============================= [ 1.603870] WARNING: suspicious RCU usage [ 1.603872] 5.5.4-stable #17 Not tainted [ 1.603874] ----------------------------- [ 1.603875] drivers/iommu/dmar.c:293 RCU-list traversed in non-reader section!! Tested-by: Madhuparna Bhowmik Signed-off-by: Amol Grover Cc: stable@vger.kernel.org Acked-by: Lu Baolu Signed-off-by: Joerg Roedel --- include/linux/dmar.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/include/linux/dmar.h b/include/linux/dmar.h index f64ca27dc210..712be8bc6a7c 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -69,8 +69,9 @@ struct dmar_pci_notify_info { extern struct rw_semaphore dmar_global_lock; extern struct list_head dmar_drhd_units; -#define for_each_drhd_unit(drhd) \ - list_for_each_entry_rcu(drhd, &dmar_drhd_units, list) +#define for_each_drhd_unit(drhd) \ + list_for_each_entry_rcu(drhd, &dmar_drhd_units, list, \ + dmar_rcu_check()) #define for_each_active_drhd_unit(drhd) \ list_for_each_entry_rcu(drhd, &dmar_drhd_units, list) \ @@ -81,7 +82,8 @@ extern struct list_head dmar_drhd_units; if (i=drhd->iommu, drhd->ignored) {} else #define for_each_iommu(i, drhd) \ - list_for_each_entry_rcu(drhd, &dmar_drhd_units, list) \ + list_for_each_entry_rcu(drhd, &dmar_drhd_units, list, \ + dmar_rcu_check()) \ if (i=drhd->iommu, 0) {} else static inline bool dmar_rcu_check(void) From 9a11997e757bcf716c1b199ea7bd1abbadc4b357 Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Mon, 2 Mar 2020 15:15:36 +0800 Subject: [PATCH 042/256] KVM: X86: Fix dereference null cpufreq policy Naresh Kamboju reported: Linux version 5.6.0-rc4 (oe-user@oe-host) (gcc version (GCC)) #1 SMP Sun Mar 1 22:59:08 UTC 2020 kvm: no hardware support BUG: kernel NULL pointer dereference, address: 000000000000028c #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] SMP NOPTI CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.6.0-rc4 #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), 04/01/2014 RIP: 0010:kobject_put+0x12/0x1c0 Call Trace: cpufreq_cpu_put+0x15/0x20 kvm_arch_init+0x1f6/0x2b0 kvm_init+0x31/0x290 ? svm_check_processor_compat+0xd/0xd ? svm_check_processor_compat+0xd/0xd svm_init+0x21/0x23 do_one_initcall+0x61/0x2f0 ? rdinit_setup+0x30/0x30 ? rcu_read_lock_sched_held+0x4f/0x80 kernel_init_freeable+0x219/0x279 ? rest_init+0x250/0x250 kernel_init+0xe/0x110 ret_from_fork+0x27/0x50 Modules linked in: CR2: 000000000000028c ---[ end trace 239abf40c55c409b ]--- RIP: 0010:kobject_put+0x12/0x1c0 cpufreq policy which is get by cpufreq_cpu_get() can be NULL if it is failure, this patch takes care of it. Fixes: aaec7c03de (KVM: x86: avoid useless copy of cpufreq policy) Reported-by: Naresh Kamboju Cc: Naresh Kamboju Signed-off-by: Wanpeng Li Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 5de200663f51..3156e25b0774 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7195,10 +7195,12 @@ static void kvm_timer_init(void) cpu = get_cpu(); policy = cpufreq_cpu_get(cpu); - if (policy && policy->cpuinfo.max_freq) - max_tsc_khz = policy->cpuinfo.max_freq; + if (policy) { + if (policy->cpuinfo.max_freq) + max_tsc_khz = policy->cpuinfo.max_freq; + cpufreq_cpu_put(policy); + } put_cpu(); - cpufreq_cpu_put(policy); #endif cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block, CPUFREQ_TRANSITION_NOTIFIER); From aaca21007ba14005feca74a079888c49a9b6f6ac Mon Sep 17 00:00:00 2001 From: Haiwei Li Date: Mon, 2 Mar 2020 20:19:28 +0800 Subject: [PATCH 043/256] KVM: SVM: Fix the svm vmexit code for WRMSR In svm, exit_code for MSR writes is not EXIT_REASON_MSR_WRITE which belongs to vmx. According to amd manual, SVM_EXIT_MSR(7ch) is the exit_code of VMEXIT_MSR due to RDMSR or WRMSR access to protected MSR. Additionally, the processor indicates in the VMCB's EXITINFO1 whether a RDMSR(EXITINFO1=0) or WRMSR(EXITINFO1=1) was intercepted. Signed-off-by: Haiwei Li Fixes: 1e9e2622a149 ("KVM: VMX: FIXED+PHYSICAL mode single target IPI fastpath", 2019-11-21) Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 24c0b2ba8fb9..91000501756e 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -6312,7 +6312,8 @@ static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu, enum exit_fastpath_completion *exit_fastpath) { if (!is_guest_mode(vcpu) && - to_svm(vcpu)->vmcb->control.exit_code == EXIT_REASON_MSR_WRITE) + to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_MSR && + to_svm(vcpu)->vmcb->control.exit_info_1) *exit_fastpath = handle_fastpath_set_msr_irqoff(vcpu); } From 77a1bce84bba01f3f143d77127b72e872b573795 Mon Sep 17 00:00:00 2001 From: Yonghyun Hwang Date: Wed, 26 Feb 2020 12:30:06 -0800 Subject: [PATCH 044/256] iommu/vt-d: Fix a bug in intel_iommu_iova_to_phys() for huge page intel_iommu_iova_to_phys() has a bug when it translates an IOVA for a huge page onto its corresponding physical address. This commit fixes the bug by accomodating the level of page entry for the IOVA and adds IOVA's lower address to the physical address. Cc: Acked-by: Lu Baolu Reviewed-by: Moritz Fischer Signed-off-by: Yonghyun Hwang Fixes: 3871794642579 ("VT-d: Changes to support KVM") Signed-off-by: Joerg Roedel --- drivers/iommu/intel-iommu.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 6fa6de2b6ad5..33593fea0250 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -5700,8 +5700,10 @@ static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain, u64 phys = 0; pte = pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, &level); - if (pte) - phys = dma_pte_addr(pte); + if (pte && dma_pte_present(pte)) + phys = dma_pte_addr(pte) + + (iova & (BIT_MASK(level_to_offset_bits(level) + + VTD_PAGE_SHIFT) - 1)); return phys; } From 08090744f2dbba6b10d38fb17443c81f66798ca0 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Fri, 28 Feb 2020 14:18:55 +0000 Subject: [PATCH 045/256] iommu/io-pgtable-arm: Fix IOVA validation for 32-bit Since we ony support the TTB1 quirk for AArch64 contexts, and consequently only for 64-bit builds, the sign-extension aspect of the "are all bits above IAS consistent?" check should implicitly only apply to 64-bit IOVAs. Change the type of the cast to ensure that 32-bit longs don't inadvertently get sign-extended, and thus considered invalid, if they happen to be above 2GB in the TTB0 region. Reported-by: Stephan Gerhold Signed-off-by: Robin Murphy Acked-by: Acked-by: Will Deacon Fixes: db6903010aa5 ("iommu/io-pgtable-arm: Prepare for TTBR1 usage") Signed-off-by: Joerg Roedel --- drivers/iommu/io-pgtable-arm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index 983b08477e64..04fbd4bf0ff9 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -468,7 +468,7 @@ static int arm_lpae_map(struct io_pgtable_ops *ops, unsigned long iova, arm_lpae_iopte *ptep = data->pgd; int ret, lvl = data->start_level; arm_lpae_iopte prot; - long iaext = (long)iova >> cfg->ias; + long iaext = (s64)iova >> cfg->ias; /* If no access, then nothing to do */ if (!(iommu_prot & (IOMMU_READ | IOMMU_WRITE))) @@ -645,7 +645,7 @@ static size_t arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova, struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops); struct io_pgtable_cfg *cfg = &data->iop.cfg; arm_lpae_iopte *ptep = data->pgd; - long iaext = (long)iova >> cfg->ias; + long iaext = (s64)iova >> cfg->ias; if (WARN_ON(!size || (size & cfg->pgsize_bitmap) != size)) return 0; From 04d6067f1f19e70a418f92fa3170cf7fe53b7fdf Mon Sep 17 00:00:00 2001 From: Zhenyu Wang Date: Tue, 3 Mar 2020 13:54:12 +0800 Subject: [PATCH 046/256] drm/i915/gvt: Fix unnecessary schedule timer when no vGPU exits From commit f25a49ab8ab9 ("drm/i915/gvt: Use vgpu_lock to protect per vgpu access") the vgpu idr destroy is moved later than vgpu resource destroy, then it would fail to stop timer for schedule policy clean which to check vgpu idr for any left vGPU. So this trys to destroy vgpu idr earlier. Cc: Colin Xu Fixes: f25a49ab8ab9 ("drm/i915/gvt: Use vgpu_lock to protect per vgpu access") Acked-by: Colin Xu Signed-off-by: Zhenyu Wang Link: http://patchwork.freedesktop.org/patch/msgid/20200229055445.31481-1-zhenyuw@linux.intel.com --- drivers/gpu/drm/i915/gvt/vgpu.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index 487af6ea9972..345c2aa3b491 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -272,10 +272,17 @@ void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu) { struct intel_gvt *gvt = vgpu->gvt; - mutex_lock(&vgpu->vgpu_lock); - WARN(vgpu->active, "vGPU is still active!\n"); + /* + * remove idr first so later clean can judge if need to stop + * service if no active vgpu. + */ + mutex_lock(&gvt->lock); + idr_remove(&gvt->vgpu_idr, vgpu->id); + mutex_unlock(&gvt->lock); + + mutex_lock(&vgpu->vgpu_lock); intel_gvt_debugfs_remove_vgpu(vgpu); intel_vgpu_clean_sched_policy(vgpu); intel_vgpu_clean_submission(vgpu); @@ -290,7 +297,6 @@ void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu) mutex_unlock(&vgpu->vgpu_lock); mutex_lock(&gvt->lock); - idr_remove(&gvt->vgpu_idr, vgpu->id); if (idr_is_empty(&gvt->vgpu_idr)) intel_gvt_clean_irq(gvt); intel_gvt_update_vgpu_types(gvt); From b102f0c522cf668c8382c56a4f771b37d011cda2 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Thu, 20 Feb 2020 12:41:39 +0100 Subject: [PATCH 047/256] mt76: fix array overflow on receiving too many fragments for a packet If the hardware receives an oversized packet with too many rx fragments, skb_shinfo(skb)->frags can overflow and corrupt memory of adjacent pages. This becomes especially visible if it corrupts the freelist pointer of a slab page. Cc: stable@vger.kernel.org Signed-off-by: Felix Fietkau Signed-off-by: Kalle Valo --- drivers/net/wireless/mediatek/mt76/dma.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c index 6173c80189ba..1847f55e199b 100644 --- a/drivers/net/wireless/mediatek/mt76/dma.c +++ b/drivers/net/wireless/mediatek/mt76/dma.c @@ -447,10 +447,13 @@ mt76_add_fragment(struct mt76_dev *dev, struct mt76_queue *q, void *data, struct page *page = virt_to_head_page(data); int offset = data - page_address(page); struct sk_buff *skb = q->rx_head; + struct skb_shared_info *shinfo = skb_shinfo(skb); - offset += q->buf_offset; - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, offset, len, - q->buf_size); + if (shinfo->nr_frags < ARRAY_SIZE(shinfo->frags)) { + offset += q->buf_offset; + skb_add_rx_frag(skb, shinfo->nr_frags, page, offset, len, + q->buf_size); + } if (more) return; From 342993f96ab24d5864ab1216f46c0b199c2baf8e Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Tue, 3 Mar 2020 15:33:15 +0100 Subject: [PATCH 048/256] KVM: x86: clear stale x86_emulate_ctxt->intercept value After commit 07721feee46b ("KVM: nVMX: Don't emulate instructions in guest mode") Hyper-V guests on KVM stopped booting with: kvm_nested_vmexit: rip fffff802987d6169 reason EPT_VIOLATION info1 181 info2 0 int_info 0 int_info_err 0 kvm_page_fault: address febd0000 error_code 181 kvm_emulate_insn: 0:fffff802987d6169: f3 a5 kvm_emulate_insn: 0:fffff802987d6169: f3 a5 FAIL kvm_inj_exception: #UD (0x0) "f3 a5" is a "rep movsw" instruction, which should not be intercepted at all. Commit c44b4c6ab80e ("KVM: emulate: clean up initializations in init_decode_cache") reduced the number of fields cleared by init_decode_cache() claiming that they are being cleared elsewhere, 'intercept', however, is left uncleared if the instruction does not have any of the "slow path" flags (NotImpl, Stack, Op3264, Sse, Mmx, CheckPerm, NearBranch, No16 and of course Intercept itself). Fixes: c44b4c6ab80e ("KVM: emulate: clean up initializations in init_decode_cache") Fixes: 07721feee46b ("KVM: nVMX: Don't emulate instructions in guest mode") Cc: stable@vger.kernel.org Suggested-by: Paolo Bonzini Signed-off-by: Vitaly Kuznetsov Reviewed-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- arch/x86/kvm/emulate.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index dd19fb3539e0..bc00642e5d3b 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -5173,6 +5173,7 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) ctxt->fetch.ptr = ctxt->fetch.data; ctxt->fetch.end = ctxt->fetch.data + insn_len; ctxt->opcode_len = 1; + ctxt->intercept = x86_intercept_none; if (insn_len > 0) memcpy(ctxt->fetch.data, insn, insn_len); else { From d718fdc3e752ba51ddb2b5554d3db98a09355cc2 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Tue, 3 Mar 2020 15:33:16 +0100 Subject: [PATCH 049/256] KVM: x86: remove stale comment from struct x86_emulate_ctxt Commit c44b4c6ab80e ("KVM: emulate: clean up initializations in init_decode_cache") did some field shuffling and instead of [opcode_len, _regs) started clearing [has_seg_override, modrm). The comment about clearing fields altogether is not true anymore. Fixes: c44b4c6ab80e ("KVM: emulate: clean up initializations in init_decode_cache") Signed-off-by: Vitaly Kuznetsov Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_emulate.h | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 2a8f2bd2e5cf..c06e8353efd3 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -360,7 +360,6 @@ struct x86_emulate_ctxt { u64 d; unsigned long _eip; struct operand memop; - /* Fields above regs are cleared together. */ unsigned long _regs[NR_VCPU_REGS]; struct operand *memopp; struct fetch_cache fetch; From ecc421e05bab97cf3ff4fe456ade47ef84dba8c2 Mon Sep 17 00:00:00 2001 From: Cyril Hrubis Date: Tue, 3 Mar 2020 16:06:38 +0100 Subject: [PATCH 050/256] sys/sysinfo: Respect boottime inside time namespace The sysinfo() syscall includes uptime in seconds but has no correction for time namespaces which makes it inconsistent with the /proc/uptime inside of a time namespace. Add the missing time namespace adjustment call. Signed-off-by: Cyril Hrubis Signed-off-by: Thomas Gleixner Reviewed-by: Dmitry Safonov Link: https://lkml.kernel.org/r/20200303150638.7329-1-chrubis@suse.cz --- kernel/sys.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/sys.c b/kernel/sys.c index f9bc5c303e3f..d325f3ab624a 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -47,6 +47,7 @@ #include #include #include +#include #include #include @@ -2546,6 +2547,7 @@ static int do_sysinfo(struct sysinfo *info) memset(info, 0, sizeof(struct sysinfo)); ktime_get_boottime_ts64(&tp); + timens_add_boottime(&tp); info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0); get_avenrun(info->loads, 0, SI_LOAD_SHIFT - FSHIFT); From e4d9b04b973b2dbce7b42af95ea70d07da1c936d Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 2 Mar 2020 12:09:38 -0300 Subject: [PATCH 051/256] perf bench: Share some global variables to fix build with gcc 10 Noticed with gcc 10 (fedora rawhide) that those variables were not being declared as static, so end up with: ld: /tmp/build/perf/bench/epoll-wait.o:/git/perf/tools/perf/bench/epoll-wait.c:93: multiple definition of `end'; /tmp/build/perf/bench/futex-hash.o:/git/perf/tools/perf/bench/futex-hash.c:40: first defined here ld: /tmp/build/perf/bench/epoll-wait.o:/git/perf/tools/perf/bench/epoll-wait.c:93: multiple definition of `start'; /tmp/build/perf/bench/futex-hash.o:/git/perf/tools/perf/bench/futex-hash.c:40: first defined here ld: /tmp/build/perf/bench/epoll-wait.o:/git/perf/tools/perf/bench/epoll-wait.c:93: multiple definition of `runtime'; /tmp/build/perf/bench/futex-hash.o:/git/perf/tools/perf/bench/futex-hash.c:40: first defined here ld: /tmp/build/perf/bench/epoll-ctl.o:/git/perf/tools/perf/bench/epoll-ctl.c:38: multiple definition of `end'; /tmp/build/perf/bench/futex-hash.o:/git/perf/tools/perf/bench/futex-hash.c:40: first defined here ld: /tmp/build/perf/bench/epoll-ctl.o:/git/perf/tools/perf/bench/epoll-ctl.c:38: multiple definition of `start'; /tmp/build/perf/bench/futex-hash.o:/git/perf/tools/perf/bench/futex-hash.c:40: first defined here ld: /tmp/build/perf/bench/epoll-ctl.o:/git/perf/tools/perf/bench/epoll-ctl.c:38: multiple definition of `runtime'; /tmp/build/perf/bench/futex-hash.o:/git/perf/tools/perf/bench/futex-hash.c:40: first defined here make[4]: *** [/git/perf/tools/build/Makefile.build:145: /tmp/build/perf/bench/perf-in.o] Error 1 Prefix those with bench__ and add them to bench/bench.h, so that we can share those on the tools needing to access those variables from signal handlers. Acked-by: Thomas Gleixner Cc: Adrian Hunter Cc: Davidlohr Bueso Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lore.kernel.org/lkml/20200303155811.GD13702@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/bench/bench.h | 4 ++++ tools/perf/bench/epoll-ctl.c | 7 +++---- tools/perf/bench/epoll-wait.c | 11 +++++------ tools/perf/bench/futex-hash.c | 12 ++++++------ tools/perf/bench/futex-lock-pi.c | 11 +++++------ 5 files changed, 23 insertions(+), 22 deletions(-) diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h index fddb3ced9db6..4aa6de1aa67d 100644 --- a/tools/perf/bench/bench.h +++ b/tools/perf/bench/bench.h @@ -2,6 +2,10 @@ #ifndef BENCH_H #define BENCH_H +#include + +extern struct timeval bench__start, bench__end, bench__runtime; + /* * The madvise transparent hugepage constants were added in glibc * 2.13. For compatibility with older versions of glibc, define these diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c index bb617e568841..a7526c05df38 100644 --- a/tools/perf/bench/epoll-ctl.c +++ b/tools/perf/bench/epoll-ctl.c @@ -35,7 +35,6 @@ static unsigned int nthreads = 0; static unsigned int nsecs = 8; -struct timeval start, end, runtime; static bool done, __verbose, randomize; /* @@ -94,8 +93,8 @@ static void toggle_done(int sig __maybe_unused, { /* inform all threads that we're done for the day */ done = true; - gettimeofday(&end, NULL); - timersub(&end, &start, &runtime); + gettimeofday(&bench__end, NULL); + timersub(&bench__end, &bench__start, &bench__runtime); } static void nest_epollfd(void) @@ -361,7 +360,7 @@ int bench_epoll_ctl(int argc, const char **argv) threads_starting = nthreads; - gettimeofday(&start, NULL); + gettimeofday(&bench__start, NULL); do_threads(worker, cpu); diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c index 7af694437f4e..d1c5cb526b9f 100644 --- a/tools/perf/bench/epoll-wait.c +++ b/tools/perf/bench/epoll-wait.c @@ -90,7 +90,6 @@ static unsigned int nthreads = 0; static unsigned int nsecs = 8; -struct timeval start, end, runtime; static bool wdone, done, __verbose, randomize, nonblocking; /* @@ -276,8 +275,8 @@ static void toggle_done(int sig __maybe_unused, { /* inform all threads that we're done for the day */ done = true; - gettimeofday(&end, NULL); - timersub(&end, &start, &runtime); + gettimeofday(&bench__end, NULL); + timersub(&bench__end, &bench__start, &bench__runtime); } static void print_summary(void) @@ -287,7 +286,7 @@ static void print_summary(void) printf("\nAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n", avg, rel_stddev_stats(stddev, avg), - (int) runtime.tv_sec); + (int)bench__runtime.tv_sec); } static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) @@ -479,7 +478,7 @@ int bench_epoll_wait(int argc, const char **argv) threads_starting = nthreads; - gettimeofday(&start, NULL); + gettimeofday(&bench__start, NULL); do_threads(worker, cpu); @@ -519,7 +518,7 @@ int bench_epoll_wait(int argc, const char **argv) qsort(worker, nthreads, sizeof(struct worker), cmpworker); for (i = 0; i < nthreads; i++) { - unsigned long t = worker[i].ops/runtime.tv_sec; + unsigned long t = worker[i].ops / bench__runtime.tv_sec; update_stats(&throughput_stats, t); diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c index 8ba0c3330a9a..21776862e940 100644 --- a/tools/perf/bench/futex-hash.c +++ b/tools/perf/bench/futex-hash.c @@ -37,7 +37,7 @@ static unsigned int nfutexes = 1024; static bool fshared = false, done = false, silent = false; static int futex_flag = 0; -struct timeval start, end, runtime; +struct timeval bench__start, bench__end, bench__runtime; static pthread_mutex_t thread_lock; static unsigned int threads_starting; static struct stats throughput_stats; @@ -103,8 +103,8 @@ static void toggle_done(int sig __maybe_unused, { /* inform all threads that we're done for the day */ done = true; - gettimeofday(&end, NULL); - timersub(&end, &start, &runtime); + gettimeofday(&bench__end, NULL); + timersub(&bench__end, &bench__start, &bench__runtime); } static void print_summary(void) @@ -114,7 +114,7 @@ static void print_summary(void) printf("%sAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n", !silent ? "\n" : "", avg, rel_stddev_stats(stddev, avg), - (int) runtime.tv_sec); + (int)bench__runtime.tv_sec); } int bench_futex_hash(int argc, const char **argv) @@ -161,7 +161,7 @@ int bench_futex_hash(int argc, const char **argv) threads_starting = nthreads; pthread_attr_init(&thread_attr); - gettimeofday(&start, NULL); + gettimeofday(&bench__start, NULL); for (i = 0; i < nthreads; i++) { worker[i].tid = i; worker[i].futex = calloc(nfutexes, sizeof(*worker[i].futex)); @@ -204,7 +204,7 @@ int bench_futex_hash(int argc, const char **argv) pthread_mutex_destroy(&thread_lock); for (i = 0; i < nthreads; i++) { - unsigned long t = worker[i].ops/runtime.tv_sec; + unsigned long t = worker[i].ops / bench__runtime.tv_sec; update_stats(&throughput_stats, t); if (!silent) { if (nfutexes == 1) diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c index d0cae8125423..30d97121dc4f 100644 --- a/tools/perf/bench/futex-lock-pi.c +++ b/tools/perf/bench/futex-lock-pi.c @@ -37,7 +37,6 @@ static bool silent = false, multi = false; static bool done = false, fshared = false; static unsigned int nthreads = 0; static int futex_flag = 0; -struct timeval start, end, runtime; static pthread_mutex_t thread_lock; static unsigned int threads_starting; static struct stats throughput_stats; @@ -64,7 +63,7 @@ static void print_summary(void) printf("%sAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n", !silent ? "\n" : "", avg, rel_stddev_stats(stddev, avg), - (int) runtime.tv_sec); + (int)bench__runtime.tv_sec); } static void toggle_done(int sig __maybe_unused, @@ -73,8 +72,8 @@ static void toggle_done(int sig __maybe_unused, { /* inform all threads that we're done for the day */ done = true; - gettimeofday(&end, NULL); - timersub(&end, &start, &runtime); + gettimeofday(&bench__end, NULL); + timersub(&bench__end, &bench__start, &bench__runtime); } static void *workerfn(void *arg) @@ -185,7 +184,7 @@ int bench_futex_lock_pi(int argc, const char **argv) threads_starting = nthreads; pthread_attr_init(&thread_attr); - gettimeofday(&start, NULL); + gettimeofday(&bench__start, NULL); create_threads(worker, thread_attr, cpu); pthread_attr_destroy(&thread_attr); @@ -211,7 +210,7 @@ int bench_futex_lock_pi(int argc, const char **argv) pthread_mutex_destroy(&thread_lock); for (i = 0; i < nthreads; i++) { - unsigned long t = worker[i].ops/runtime.tv_sec; + unsigned long t = worker[i].ops / bench__runtime.tv_sec; update_stats(&throughput_stats, t); if (!silent) From b5c0951860ba98cfe1936b5c0739450875d51451 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 2 Mar 2020 16:03:34 -0300 Subject: [PATCH 052/256] perf symbols: Don't try to find a vmlinux file when looking for kernel modules The dso->kernel value is now set to everything that is in machine->kmaps, but that was being used to decide if vmlinux lookup is needed, which ended up making that lookup be made for kernel modules, that now have dso->kernel set, leading to these kinds of warnings when running on a machine with compressed kernel modules, like fedora:31: [root@five ~]# perf record -F 10000 -a sleep 2 [ perf record: Woken up 1 times to write data ] lzma: fopen failed on vmlinux: 'No such file or directory' lzma: fopen failed on /boot/vmlinux: 'No such file or directory' lzma: fopen failed on /boot/vmlinux-5.5.5-200.fc31.x86_64: 'No such file or directory' lzma: fopen failed on /usr/lib/debug/boot/vmlinux-5.5.5-200.fc31.x86_64: 'No such file or directory' lzma: fopen failed on /lib/modules/5.5.5-200.fc31.x86_64/build/vmlinux: 'No such file or directory' lzma: fopen failed on vmlinux: 'No such file or directory' lzma: fopen failed on /boot/vmlinux: 'No such file or directory' lzma: fopen failed on /boot/vmlinux-5.5.5-200.fc31.x86_64: 'No such file or directory' lzma: fopen failed on /usr/lib/debug/boot/vmlinux-5.5.5-200.fc31.x86_64: 'No such file or directory' lzma: fopen failed on /lib/modules/5.5.5-200.fc31.x86_64/build/vmlinux: 'No such file or directory' lzma: fopen failed on vmlinux: 'No such file or directory' lzma: fopen failed on /boot/vmlinux: 'No such file or directory' lzma: fopen failed on /boot/vmlinux-5.5.5-200.fc31.x86_64: 'No such file or directory' lzma: fopen failed on /usr/lib/debug/boot/vmlinux-5.5.5-200.fc31.x86_64: 'No such file or directory' lzma: fopen failed on /lib/modules/5.5.5-200.fc31.x86_64/build/vmlinux: 'No such file or directory' lzma: fopen failed on vmlinux: 'No such file or directory' lzma: fopen failed on /boot/vmlinux: 'No such file or directory' lzma: fopen failed on /boot/vmlinux-5.5.5-200.fc31.x86_64: 'No such file or directory' lzma: fopen failed on /usr/lib/debug/boot/vmlinux-5.5.5-200.fc31.x86_64: 'No such file or directory' lzma: fopen failed on /lib/modules/5.5.5-200.fc31.x86_64/build/vmlinux: 'No such file or directory' lzma: fopen failed on vmlinux: 'No such file or directory' lzma: fopen failed on /boot/vmlinux: 'No such file or directory' lzma: fopen failed on /boot/vmlinux-5.5.5-200.fc31.x86_64: 'No such file or directory' lzma: fopen failed on /usr/lib/debug/boot/vmlinux-5.5.5-200.fc31.x86_64: 'No such file or directory' lzma: fopen failed on /lib/modules/5.5.5-200.fc31.x86_64/build/vmlinux: 'No such file or directory' [ perf record: Captured and wrote 1.024 MB perf.data (1366 samples) ] [root@five ~]# This happens when collecting the buildid, when we find samples for kernel modules, fix it by checking if the looked up DSO is a kernel module by other means. Fixes: 02213cec64bb ("perf maps: Mark module DSOs with kernel type") Tested-by: Jiri Olsa Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Kim Phillips Cc: Michael Petlan Cc: Namhyung Kim Cc: Ravi Bangoria Link: http://lore.kernel.org/lkml/20200302191007.GD10335@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/symbol.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 1077013d8ce2..26bc6a0096ce 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -1622,7 +1622,12 @@ int dso__load(struct dso *dso, struct map *map) goto out; } - if (dso->kernel) { + kmod = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE || + dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP || + dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE || + dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP; + + if (dso->kernel && !kmod) { if (dso->kernel == DSO_TYPE_KERNEL) ret = dso__load_kernel_sym(dso, map); else if (dso->kernel == DSO_TYPE_GUEST_KERNEL) @@ -1650,12 +1655,6 @@ int dso__load(struct dso *dso, struct map *map) if (!name) goto out; - kmod = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE || - dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP || - dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE || - dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP; - - /* * Read the build id if possible. This is required for * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work From 8750939b6ad86abc3f53ec8a9683a1cded4a5654 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 2 Mar 2020 21:05:11 -0800 Subject: [PATCH 053/256] devlink: validate length of param values DEVLINK_ATTR_PARAM_VALUE_DATA may have different types so it's not checked by the normal netlink policy. Make sure the attribute length is what we expect. Fixes: e3b7ca18ad7b ("devlink: Add param set command") Signed-off-by: Jakub Kicinski Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- net/core/devlink.c | 31 +++++++++++++++++++------------ 1 file changed, 19 insertions(+), 12 deletions(-) diff --git a/net/core/devlink.c b/net/core/devlink.c index 5e220809844c..8e44dc5cde73 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -3352,34 +3352,41 @@ devlink_param_value_get_from_info(const struct devlink_param *param, struct genl_info *info, union devlink_param_value *value) { + struct nlattr *param_data; int len; - if (param->type != DEVLINK_PARAM_TYPE_BOOL && - !info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]) + param_data = info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]; + + if (param->type != DEVLINK_PARAM_TYPE_BOOL && !param_data) return -EINVAL; switch (param->type) { case DEVLINK_PARAM_TYPE_U8: - value->vu8 = nla_get_u8(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]); + if (nla_len(param_data) != sizeof(u8)) + return -EINVAL; + value->vu8 = nla_get_u8(param_data); break; case DEVLINK_PARAM_TYPE_U16: - value->vu16 = nla_get_u16(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]); + if (nla_len(param_data) != sizeof(u16)) + return -EINVAL; + value->vu16 = nla_get_u16(param_data); break; case DEVLINK_PARAM_TYPE_U32: - value->vu32 = nla_get_u32(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]); + if (nla_len(param_data) != sizeof(u32)) + return -EINVAL; + value->vu32 = nla_get_u32(param_data); break; case DEVLINK_PARAM_TYPE_STRING: - len = strnlen(nla_data(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]), - nla_len(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA])); - if (len == nla_len(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]) || + len = strnlen(nla_data(param_data), nla_len(param_data)); + if (len == nla_len(param_data) || len >= __DEVLINK_PARAM_MAX_STRING_VALUE) return -EINVAL; - strcpy(value->vstr, - nla_data(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA])); + strcpy(value->vstr, nla_data(param_data)); break; case DEVLINK_PARAM_TYPE_BOOL: - value->vbool = info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA] ? - true : false; + if (param_data && nla_len(param_data)) + return -EINVAL; + value->vbool = nla_get_flag(param_data); break; } return 0; From ff3b63b8c299b73ac599b120653b47e275407656 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 2 Mar 2020 21:05:12 -0800 Subject: [PATCH 054/256] devlink: validate length of region addr/len DEVLINK_ATTR_REGION_CHUNK_ADDR and DEVLINK_ATTR_REGION_CHUNK_LEN lack entries in the netlink policy. Corresponding nla_get_u64()s may read beyond the end of the message. Fixes: 4e54795a27f5 ("devlink: Add support for region snapshot read command") Signed-off-by: Jakub Kicinski Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- net/core/devlink.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/core/devlink.c b/net/core/devlink.c index 8e44dc5cde73..b831c5545d6a 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -5958,6 +5958,8 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_PARAM_VALUE_CMODE] = { .type = NLA_U8 }, [DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .type = NLA_U32 }, + [DEVLINK_ATTR_REGION_CHUNK_ADDR] = { .type = NLA_U64 }, + [DEVLINK_ATTR_REGION_CHUNK_LEN] = { .type = NLA_U64 }, [DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] = { .type = NLA_U64 }, [DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = { .type = NLA_U8 }, From 4c16d64ea04056f1b1b324ab6916019f6a064114 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 2 Mar 2020 21:05:13 -0800 Subject: [PATCH 055/256] fib: add missing attribute validation for tun_id Add missing netlink policy entry for FRA_TUN_ID. Fixes: e7030878fc84 ("fib: Add fib rule match on tunnel id") Signed-off-by: Jakub Kicinski Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/net/fib_rules.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index 54e227e6b06a..a259050f84af 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -108,6 +108,7 @@ struct fib_rule_notifier_info { [FRA_OIFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, \ [FRA_PRIORITY] = { .type = NLA_U32 }, \ [FRA_FWMARK] = { .type = NLA_U32 }, \ + [FRA_TUN_ID] = { .type = NLA_U64 }, \ [FRA_FWMASK] = { .type = NLA_U32 }, \ [FRA_TABLE] = { .type = NLA_U32 }, \ [FRA_SUPPRESS_PREFIXLEN] = { .type = NLA_U32 }, \ From 9322cd7c4af2ccc7fe7c5f01adb53f4f77949e92 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 2 Mar 2020 21:05:14 -0800 Subject: [PATCH 056/256] nl802154: add missing attribute validation Add missing attribute validation for several u8 types. Fixes: 2c21d11518b6 ("net: add NL802154 interface for configuration of 802.15.4 devices") Signed-off-by: Jakub Kicinski Acked-by: Stefan Schmidt Signed-off-by: David S. Miller --- net/ieee802154/nl_policy.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/ieee802154/nl_policy.c b/net/ieee802154/nl_policy.c index 2c7a38d76a3a..824e7e84014c 100644 --- a/net/ieee802154/nl_policy.c +++ b/net/ieee802154/nl_policy.c @@ -21,6 +21,11 @@ const struct nla_policy ieee802154_policy[IEEE802154_ATTR_MAX + 1] = { [IEEE802154_ATTR_HW_ADDR] = { .type = NLA_HW_ADDR, }, [IEEE802154_ATTR_PAN_ID] = { .type = NLA_U16, }, [IEEE802154_ATTR_CHANNEL] = { .type = NLA_U8, }, + [IEEE802154_ATTR_BCN_ORD] = { .type = NLA_U8, }, + [IEEE802154_ATTR_SF_ORD] = { .type = NLA_U8, }, + [IEEE802154_ATTR_PAN_COORD] = { .type = NLA_U8, }, + [IEEE802154_ATTR_BAT_EXT] = { .type = NLA_U8, }, + [IEEE802154_ATTR_COORD_REALIGN] = { .type = NLA_U8, }, [IEEE802154_ATTR_PAGE] = { .type = NLA_U8, }, [IEEE802154_ATTR_COORD_SHORT_ADDR] = { .type = NLA_U16, }, [IEEE802154_ATTR_COORD_HW_ADDR] = { .type = NLA_HW_ADDR, }, From b60673c4c418bef7550d02faf53c34fbfeb366bf Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 2 Mar 2020 21:05:15 -0800 Subject: [PATCH 057/256] nl802154: add missing attribute validation for dev_type Add missing attribute type validation for IEEE802154_ATTR_DEV_TYPE to the netlink policy. Fixes: 90c049b2c6ae ("ieee802154: interface type to be added") Signed-off-by: Jakub Kicinski Acked-by: Stefan Schmidt Signed-off-by: David S. Miller --- net/ieee802154/nl_policy.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/ieee802154/nl_policy.c b/net/ieee802154/nl_policy.c index 824e7e84014c..0672b2f01586 100644 --- a/net/ieee802154/nl_policy.c +++ b/net/ieee802154/nl_policy.c @@ -27,6 +27,7 @@ const struct nla_policy ieee802154_policy[IEEE802154_ATTR_MAX + 1] = { [IEEE802154_ATTR_BAT_EXT] = { .type = NLA_U8, }, [IEEE802154_ATTR_COORD_REALIGN] = { .type = NLA_U8, }, [IEEE802154_ATTR_PAGE] = { .type = NLA_U8, }, + [IEEE802154_ATTR_DEV_TYPE] = { .type = NLA_U8, }, [IEEE802154_ATTR_COORD_SHORT_ADDR] = { .type = NLA_U16, }, [IEEE802154_ATTR_COORD_HW_ADDR] = { .type = NLA_HW_ADDR, }, [IEEE802154_ATTR_COORD_PAN_ID] = { .type = NLA_U16, }, From ab02ad660586b94f5d08912a3952b939cf4c4430 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 2 Mar 2020 21:05:16 -0800 Subject: [PATCH 058/256] can: add missing attribute validation for termination Add missing attribute validation for IFLA_CAN_TERMINATION to the netlink policy. Fixes: 12a6075cabc0 ("can: dev: add CAN interface termination API") Signed-off-by: Jakub Kicinski Acked-by: Oliver Hartkopp Signed-off-by: David S. Miller --- drivers/net/can/dev.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index 6ee06a49fb4c..68834a2853c9 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -883,6 +883,7 @@ static const struct nla_policy can_policy[IFLA_CAN_MAX + 1] = { = { .len = sizeof(struct can_bittiming) }, [IFLA_CAN_DATA_BITTIMING_CONST] = { .len = sizeof(struct can_bittiming_const) }, + [IFLA_CAN_TERMINATION] = { .type = NLA_U16 }, }; static int can_validate(struct nlattr *tb[], struct nlattr *data[], From 31d9a1c524964bac77b7f9d0a1ac140dc6b57461 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 2 Mar 2020 21:05:17 -0800 Subject: [PATCH 059/256] macsec: add missing attribute validation for port Add missing attribute validation for IFLA_MACSEC_PORT to the netlink policy. Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver") Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/macsec.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 45bfd99f17fa..5af424eeea86 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -3342,6 +3342,7 @@ static const struct device_type macsec_type = { static const struct nla_policy macsec_rtnl_policy[IFLA_MACSEC_MAX + 1] = { [IFLA_MACSEC_SCI] = { .type = NLA_U64 }, + [IFLA_MACSEC_PORT] = { .type = NLA_U16 }, [IFLA_MACSEC_ICV_LEN] = { .type = NLA_U8 }, [IFLA_MACSEC_CIPHER_SUITE] = { .type = NLA_U64 }, [IFLA_MACSEC_WINDOW] = { .type = NLA_U32 }, From b5ab1f1be6180a2e975eede18731804b5164a05d Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 2 Mar 2020 21:05:18 -0800 Subject: [PATCH 060/256] openvswitch: add missing attribute validation for hash Add missing attribute validation for OVS_PACKET_ATTR_HASH to the netlink policy. Fixes: bd1903b7c459 ("net: openvswitch: add hash info to upcall") Signed-off-by: Jakub Kicinski Reviewed-by: Greg Rose Signed-off-by: David S. Miller --- net/openvswitch/datapath.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index c047afd12116..07a7dd185995 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -645,6 +645,7 @@ static const struct nla_policy packet_policy[OVS_PACKET_ATTR_MAX + 1] = { [OVS_PACKET_ATTR_ACTIONS] = { .type = NLA_NESTED }, [OVS_PACKET_ATTR_PROBE] = { .type = NLA_FLAG }, [OVS_PACKET_ATTR_MRU] = { .type = NLA_U16 }, + [OVS_PACKET_ATTR_HASH] = { .type = NLA_U64 }, }; static const struct genl_ops dp_packet_genl_ops[] = { From 7e6dc03eeb023e18427a373522f1d247b916a641 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 2 Mar 2020 21:05:19 -0800 Subject: [PATCH 061/256] net: fq: add missing attribute validation for orphan mask Add missing attribute validation for TCA_FQ_ORPHAN_MASK to the netlink policy. Fixes: 06eb395fa985 ("pkt_sched: fq: better control of DDOS traffic") Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- net/sched/sch_fq.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index a5a295477ecc..371ad84def3b 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -744,6 +744,7 @@ static const struct nla_policy fq_policy[TCA_FQ_MAX + 1] = { [TCA_FQ_FLOW_MAX_RATE] = { .type = NLA_U32 }, [TCA_FQ_BUCKETS_LOG] = { .type = NLA_U32 }, [TCA_FQ_FLOW_REFILL_DELAY] = { .type = NLA_U32 }, + [TCA_FQ_ORPHAN_MASK] = { .type = NLA_U32 }, [TCA_FQ_LOW_RATE_THRESHOLD] = { .type = NLA_U32 }, [TCA_FQ_CE_THRESHOLD] = { .type = NLA_U32 }, }; From e13aaa0643da10006ec35715954e7f92a62899a5 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 2 Mar 2020 21:05:20 -0800 Subject: [PATCH 062/256] net: taprio: add missing attribute validation for txtime delay Add missing attribute validation for TCA_TAPRIO_ATTR_TXTIME_DELAY to the netlink policy. Fixes: 4cfd5779bd6e ("taprio: Add support for txtime-assist mode") Signed-off-by: Jakub Kicinski Reviewed-by: Vinicius Costa Gomes Signed-off-by: David S. Miller --- net/sched/sch_taprio.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 660fc45ee40f..ee717e05372b 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -768,6 +768,7 @@ static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = { [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME] = { .type = NLA_S64 }, [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION] = { .type = NLA_S64 }, [TCA_TAPRIO_ATTR_FLAGS] = { .type = NLA_U32 }, + [TCA_TAPRIO_ATTR_TXTIME_DELAY] = { .type = NLA_U32 }, }; static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry, From dd25cb272ccce4db67dc8509278229099e4f5e99 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 2 Mar 2020 21:05:21 -0800 Subject: [PATCH 063/256] team: add missing attribute validation for port ifindex Add missing attribute validation for TEAM_ATTR_OPTION_PORT_IFINDEX to the netlink policy. Fixes: 80f7c6683fe0 ("team: add support for per-port options") Signed-off-by: Jakub Kicinski Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/team/team.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index ca70a1d840eb..44dd26a62a6d 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -2240,6 +2240,7 @@ team_nl_option_policy[TEAM_ATTR_OPTION_MAX + 1] = { [TEAM_ATTR_OPTION_CHANGED] = { .type = NLA_FLAG }, [TEAM_ATTR_OPTION_TYPE] = { .type = NLA_U8 }, [TEAM_ATTR_OPTION_DATA] = { .type = NLA_BINARY }, + [TEAM_ATTR_OPTION_PORT_IFINDEX] = { .type = NLA_U32 }, }; static int team_nl_cmd_noop(struct sk_buff *skb, struct genl_info *info) From 669fcd7795900cd1880237cbbb57a7db66cb9ac8 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 2 Mar 2020 21:05:22 -0800 Subject: [PATCH 064/256] team: add missing attribute validation for array index Add missing attribute validation for TEAM_ATTR_OPTION_ARRAY_INDEX to the netlink policy. Fixes: b13033262d24 ("team: introduce array options") Signed-off-by: Jakub Kicinski Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/team/team.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 44dd26a62a6d..4004f98e50d9 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -2241,6 +2241,7 @@ team_nl_option_policy[TEAM_ATTR_OPTION_MAX + 1] = { [TEAM_ATTR_OPTION_TYPE] = { .type = NLA_U8 }, [TEAM_ATTR_OPTION_DATA] = { .type = NLA_BINARY }, [TEAM_ATTR_OPTION_PORT_IFINDEX] = { .type = NLA_U32 }, + [TEAM_ATTR_OPTION_ARRAY_INDEX] = { .type = NLA_U32 }, }; static int team_nl_cmd_noop(struct sk_buff *skb, struct genl_info *info) From 213320a67962ff6e7b83b704d55cbebc341426db Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 2 Mar 2020 21:05:23 -0800 Subject: [PATCH 065/256] tipc: add missing attribute validation for MTU property Add missing attribute validation for TIPC_NLA_PROP_MTU to the netlink policy. Fixes: 901271e0403a ("tipc: implement configuration of UDP media MTU") Signed-off-by: Jakub Kicinski Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- net/tipc/netlink.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c index 7c35094c20b8..bb9862410e68 100644 --- a/net/tipc/netlink.c +++ b/net/tipc/netlink.c @@ -116,6 +116,7 @@ const struct nla_policy tipc_nl_prop_policy[TIPC_NLA_PROP_MAX + 1] = { [TIPC_NLA_PROP_PRIO] = { .type = NLA_U32 }, [TIPC_NLA_PROP_TOL] = { .type = NLA_U32 }, [TIPC_NLA_PROP_WIN] = { .type = NLA_U32 }, + [TIPC_NLA_PROP_MTU] = { .type = NLA_U32 }, [TIPC_NLA_PROP_BROADCAST] = { .type = NLA_U32 }, [TIPC_NLA_PROP_BROADCAST_RATIO] = { .type = NLA_U32 } }; From 361d23e41ca6e504033f7e66a03b95788377caae Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 2 Mar 2020 21:05:24 -0800 Subject: [PATCH 066/256] nfc: add missing attribute validation for SE API Add missing attribute validation for NFC_ATTR_SE_INDEX to the netlink policy. Fixes: 5ce3f32b5264 ("NFC: netlink: SE API implementation") Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- net/nfc/netlink.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index eee0dddb7749..842407a48f96 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -43,6 +43,7 @@ static const struct nla_policy nfc_genl_policy[NFC_ATTR_MAX + 1] = { [NFC_ATTR_LLC_SDP] = { .type = NLA_NESTED }, [NFC_ATTR_FIRMWARE_NAME] = { .type = NLA_STRING, .len = NFC_FIRMWARE_NAME_MAXSIZE }, + [NFC_ATTR_SE_INDEX] = { .type = NLA_U32 }, [NFC_ATTR_SE_APDU] = { .type = NLA_BINARY }, [NFC_ATTR_VENDOR_DATA] = { .type = NLA_BINARY }, From 88e706d5168b07df4792dbc3d1bc37b83e4bd74d Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 2 Mar 2020 21:05:25 -0800 Subject: [PATCH 067/256] nfc: add missing attribute validation for deactivate target Add missing attribute validation for NFC_ATTR_TARGET_INDEX to the netlink policy. Fixes: 4d63adfe12dd ("NFC: Add NFC_CMD_DEACTIVATE_TARGET support") Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- net/nfc/netlink.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index 842407a48f96..e988ca486d66 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -32,6 +32,7 @@ static const struct nla_policy nfc_genl_policy[NFC_ATTR_MAX + 1] = { [NFC_ATTR_DEVICE_NAME] = { .type = NLA_STRING, .len = NFC_DEVICE_NAME_MAXSIZE }, [NFC_ATTR_PROTOCOLS] = { .type = NLA_U32 }, + [NFC_ATTR_TARGET_INDEX] = { .type = NLA_U32 }, [NFC_ATTR_COMM_MODE] = { .type = NLA_U8 }, [NFC_ATTR_RF_MODE] = { .type = NLA_U8 }, [NFC_ATTR_DEVICE_POWERED] = { .type = NLA_U8 }, From 6ba3da446551f2150fadbf8c7788edcb977683d3 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 2 Mar 2020 21:05:26 -0800 Subject: [PATCH 068/256] nfc: add missing attribute validation for vendor subcommand Add missing attribute validation for vendor subcommand attributes to the netlink policy. Fixes: 9e58095f9660 ("NFC: netlink: Implement vendor command support") Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- net/nfc/netlink.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index e988ca486d66..e894254c17d4 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -46,6 +46,8 @@ static const struct nla_policy nfc_genl_policy[NFC_ATTR_MAX + 1] = { .len = NFC_FIRMWARE_NAME_MAXSIZE }, [NFC_ATTR_SE_INDEX] = { .type = NLA_U32 }, [NFC_ATTR_SE_APDU] = { .type = NLA_BINARY }, + [NFC_ATTR_VENDOR_ID] = { .type = NLA_U32 }, + [NFC_ATTR_VENDOR_SUBCMD] = { .type = NLA_U32 }, [NFC_ATTR_VENDOR_DATA] = { .type = NLA_BINARY }, }; From 617940123e0140521f3080d2befc2bf55bcda094 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Tue, 3 Mar 2020 14:37:34 +0800 Subject: [PATCH 069/256] net/ipv6: need update peer route when modify metric When we modify the route metric, the peer address's route need also be updated. Before the fix: + ip addr add dev dummy1 2001:db8::1 peer 2001:db8::2 metric 60 + ip -6 route show dev dummy1 2001:db8::1 proto kernel metric 60 pref medium 2001:db8::2 proto kernel metric 60 pref medium + ip addr change dev dummy1 2001:db8::1 peer 2001:db8::2 metric 61 + ip -6 route show dev dummy1 2001:db8::1 proto kernel metric 61 pref medium 2001:db8::2 proto kernel metric 60 pref medium After the fix: + ip addr change dev dummy1 2001:db8::1 peer 2001:db8::2 metric 61 + ip -6 route show dev dummy1 2001:db8::1 proto kernel metric 61 pref medium 2001:db8::2 proto kernel metric 61 pref medium Fixes: 8308f3ff1753 ("net/ipv6: Add support for specifying metric of connected routes") Signed-off-by: Hangbin Liu Reviewed-by: David Ahern Signed-off-by: David S. Miller --- net/ipv6/addrconf.c | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 164c71c54b5c..4fb72028ca45 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -4586,12 +4586,14 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, } static int modify_prefix_route(struct inet6_ifaddr *ifp, - unsigned long expires, u32 flags) + unsigned long expires, u32 flags, + bool modify_peer) { struct fib6_info *f6i; u32 prio; - f6i = addrconf_get_prefix_route(&ifp->addr, ifp->prefix_len, + f6i = addrconf_get_prefix_route(modify_peer ? &ifp->peer_addr : &ifp->addr, + ifp->prefix_len, ifp->idev->dev, 0, RTF_DEFAULT, true); if (!f6i) return -ENOENT; @@ -4602,7 +4604,8 @@ static int modify_prefix_route(struct inet6_ifaddr *ifp, ip6_del_rt(dev_net(ifp->idev->dev), f6i); /* add new one */ - addrconf_prefix_route(&ifp->addr, ifp->prefix_len, + addrconf_prefix_route(modify_peer ? &ifp->peer_addr : &ifp->addr, + ifp->prefix_len, ifp->rt_priority, ifp->idev->dev, expires, flags, GFP_KERNEL); } else { @@ -4678,7 +4681,7 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg) int rc = -ENOENT; if (had_prefixroute) - rc = modify_prefix_route(ifp, expires, flags); + rc = modify_prefix_route(ifp, expires, flags, false); /* prefix route could have been deleted; if so restore it */ if (rc == -ENOENT) { @@ -4686,6 +4689,15 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg) ifp->rt_priority, ifp->idev->dev, expires, flags, GFP_KERNEL); } + + if (had_prefixroute && !ipv6_addr_any(&ifp->peer_addr)) + rc = modify_prefix_route(ifp, expires, flags, true); + + if (rc == -ENOENT && !ipv6_addr_any(&ifp->peer_addr)) { + addrconf_prefix_route(&ifp->peer_addr, ifp->prefix_len, + ifp->rt_priority, ifp->idev->dev, + expires, flags, GFP_KERNEL); + } } else if (had_prefixroute) { enum cleanup_prefix_rt_t action; unsigned long rt_expires; From d0098e4c6b83e502cc1cd96d67ca86bc79a6c559 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Tue, 3 Mar 2020 14:37:35 +0800 Subject: [PATCH 070/256] net/ipv6: remove the old peer route if change it to a new one When we modify the peer route and changed it to a new one, we should remove the old route first. Before the fix: + ip addr add dev dummy1 2001:db8::1 peer 2001:db8::2 + ip -6 route show dev dummy1 2001:db8::1 proto kernel metric 256 pref medium 2001:db8::2 proto kernel metric 256 pref medium + ip addr change dev dummy1 2001:db8::1 peer 2001:db8::3 + ip -6 route show dev dummy1 2001:db8::1 proto kernel metric 256 pref medium 2001:db8::2 proto kernel metric 256 pref medium After the fix: + ip addr change dev dummy1 2001:db8::1 peer 2001:db8::3 + ip -6 route show dev dummy1 2001:db8::1 proto kernel metric 256 pref medium 2001:db8::3 proto kernel metric 256 pref medium This patch depend on the previous patch "net/ipv6: need update peer route when modify metric" to update new peer route after delete old one. Signed-off-by: Hangbin Liu Reviewed-by: David Ahern Signed-off-by: David S. Miller --- net/ipv6/addrconf.c | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 4fb72028ca45..e6e1290ea06f 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1226,11 +1226,13 @@ check_cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long *expires) } static void -cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires, bool del_rt) +cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires, + bool del_rt, bool del_peer) { struct fib6_info *f6i; - f6i = addrconf_get_prefix_route(&ifp->addr, ifp->prefix_len, + f6i = addrconf_get_prefix_route(del_peer ? &ifp->peer_addr : &ifp->addr, + ifp->prefix_len, ifp->idev->dev, 0, RTF_DEFAULT, true); if (f6i) { if (del_rt) @@ -1293,7 +1295,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) if (action != CLEANUP_PREFIX_RT_NOP) { cleanup_prefix_route(ifp, expires, - action == CLEANUP_PREFIX_RT_DEL); + action == CLEANUP_PREFIX_RT_DEL, false); } /* clean up prefsrc entries */ @@ -4627,6 +4629,7 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg) unsigned long timeout; bool was_managetempaddr; bool had_prefixroute; + bool new_peer = false; ASSERT_RTNL(); @@ -4658,6 +4661,13 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg) cfg->preferred_lft = timeout; } + if (cfg->peer_pfx && + memcmp(&ifp->peer_addr, cfg->peer_pfx, sizeof(struct in6_addr))) { + if (!ipv6_addr_any(&ifp->peer_addr)) + cleanup_prefix_route(ifp, expires, true, true); + new_peer = true; + } + spin_lock_bh(&ifp->lock); was_managetempaddr = ifp->flags & IFA_F_MANAGETEMPADDR; had_prefixroute = ifp->flags & IFA_F_PERMANENT && @@ -4673,6 +4683,9 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg) if (cfg->rt_priority && cfg->rt_priority != ifp->rt_priority) ifp->rt_priority = cfg->rt_priority; + if (new_peer) + ifp->peer_addr = *cfg->peer_pfx; + spin_unlock_bh(&ifp->lock); if (!(ifp->flags&IFA_F_TENTATIVE)) ipv6_ifa_notify(0, ifp); @@ -4708,7 +4721,7 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg) if (action != CLEANUP_PREFIX_RT_NOP) { cleanup_prefix_route(ifp, rt_expires, - action == CLEANUP_PREFIX_RT_DEL); + action == CLEANUP_PREFIX_RT_DEL, false); } } From 0d29169a708bf730ede287248e429d579f432d1d Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Tue, 3 Mar 2020 14:37:36 +0800 Subject: [PATCH 071/256] selftests/net/fib_tests: update addr_metric_test for peer route testing This patch update {ipv4, ipv6}_addr_metric_test with 1. Set metric of address with peer route and see if the route added correctly. 2. Modify metric and peer address for peer route and see if the route changed correctly. Signed-off-by: Hangbin Liu Reviewed-by: David Ahern Signed-off-by: David S. Miller --- tools/testing/selftests/net/fib_tests.sh | 34 +++++++++++++++++++++--- 1 file changed, 31 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 60273f1bc7d9..b7616704b55e 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -1041,6 +1041,27 @@ ipv6_addr_metric_test() fi log_test $rc 0 "Prefix route with metric on link up" + # verify peer metric added correctly + set -e + run_cmd "$IP -6 addr flush dev dummy2" + run_cmd "$IP -6 addr add dev dummy2 2001:db8:104::1 peer 2001:db8:104::2 metric 260" + set +e + + check_route6 "2001:db8:104::1 dev dummy2 proto kernel metric 260" + log_test $? 0 "Set metric with peer route on local side" + log_test $? 0 "User specified metric on local address" + check_route6 "2001:db8:104::2 dev dummy2 proto kernel metric 260" + log_test $? 0 "Set metric with peer route on peer side" + + set -e + run_cmd "$IP -6 addr change dev dummy2 2001:db8:104::1 peer 2001:db8:104::3 metric 261" + set +e + + check_route6 "2001:db8:104::1 dev dummy2 proto kernel metric 261" + log_test $? 0 "Modify metric and peer address on local side" + check_route6 "2001:db8:104::3 dev dummy2 proto kernel metric 261" + log_test $? 0 "Modify metric and peer address on peer side" + $IP li del dummy1 $IP li del dummy2 cleanup @@ -1457,13 +1478,20 @@ ipv4_addr_metric_test() run_cmd "$IP addr flush dev dummy2" run_cmd "$IP addr add dev dummy2 172.16.104.1/32 peer 172.16.104.2 metric 260" - run_cmd "$IP addr change dev dummy2 172.16.104.1/32 peer 172.16.104.2 metric 261" rc=$? if [ $rc -eq 0 ]; then - check_route "172.16.104.2 dev dummy2 proto kernel scope link src 172.16.104.1 metric 261" + check_route "172.16.104.2 dev dummy2 proto kernel scope link src 172.16.104.1 metric 260" rc=$? fi - log_test $rc 0 "Modify metric of address with peer route" + log_test $rc 0 "Set metric of address with peer route" + + run_cmd "$IP addr change dev dummy2 172.16.104.1/32 peer 172.16.104.3 metric 261" + rc=$? + if [ $rc -eq 0 ]; then + check_route "172.16.104.3 dev dummy2 proto kernel scope link src 172.16.104.1 metric 261" + rc=$? + fi + log_test $rc 0 "Modify metric and peer address for peer route" $IP li del dummy1 $IP li del dummy2 From 8640f8dc6d657ebfb4e67c202ad32c5457858a13 Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 3 Mar 2020 15:01:46 +0000 Subject: [PATCH 072/256] net: dsa: fix phylink_start()/phylink_stop() calls Place phylink_start()/phylink_stop() inside dsa_port_enable() and dsa_port_disable(), which ensures that we call phylink_stop() before tearing down phylink - which is a documented requirement. Failure to do so can cause use-after-free bugs. Fixes: 0e27921816ad ("net: dsa: Use PHYLINK for the CPU/DSA ports") Signed-off-by: Russell King Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- net/dsa/dsa_priv.h | 2 ++ net/dsa/port.c | 32 ++++++++++++++++++++++++++------ net/dsa/slave.c | 8 ++------ 3 files changed, 30 insertions(+), 12 deletions(-) diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index a7662e7a691d..760e6ea3178a 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -117,7 +117,9 @@ static inline struct net_device *dsa_master_find_slave(struct net_device *dev, /* port.c */ int dsa_port_set_state(struct dsa_port *dp, u8 state, struct switchdev_trans *trans); +int dsa_port_enable_rt(struct dsa_port *dp, struct phy_device *phy); int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy); +void dsa_port_disable_rt(struct dsa_port *dp); void dsa_port_disable(struct dsa_port *dp); int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br); void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br); diff --git a/net/dsa/port.c b/net/dsa/port.c index 774facb8d547..ed7dabb57985 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -63,7 +63,7 @@ static void dsa_port_set_state_now(struct dsa_port *dp, u8 state) pr_err("DSA: failed to set STP state %u (%d)\n", state, err); } -int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy) +int dsa_port_enable_rt(struct dsa_port *dp, struct phy_device *phy) { struct dsa_switch *ds = dp->ds; int port = dp->index; @@ -78,14 +78,31 @@ int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy) if (!dp->bridge_dev) dsa_port_set_state_now(dp, BR_STATE_FORWARDING); + if (dp->pl) + phylink_start(dp->pl); + return 0; } -void dsa_port_disable(struct dsa_port *dp) +int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy) +{ + int err; + + rtnl_lock(); + err = dsa_port_enable_rt(dp, phy); + rtnl_unlock(); + + return err; +} + +void dsa_port_disable_rt(struct dsa_port *dp) { struct dsa_switch *ds = dp->ds; int port = dp->index; + if (dp->pl) + phylink_stop(dp->pl); + if (!dp->bridge_dev) dsa_port_set_state_now(dp, BR_STATE_DISABLED); @@ -93,6 +110,13 @@ void dsa_port_disable(struct dsa_port *dp) ds->ops->port_disable(ds, port); } +void dsa_port_disable(struct dsa_port *dp) +{ + rtnl_lock(); + dsa_port_disable_rt(dp); + rtnl_unlock(); +} + int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br) { struct dsa_notifier_bridge_info info = { @@ -614,10 +638,6 @@ static int dsa_port_phylink_register(struct dsa_port *dp) goto err_phy_connect; } - rtnl_lock(); - phylink_start(dp->pl); - rtnl_unlock(); - return 0; err_phy_connect: diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 088c886e609e..ddc0f9236928 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -88,12 +88,10 @@ static int dsa_slave_open(struct net_device *dev) goto clear_allmulti; } - err = dsa_port_enable(dp, dev->phydev); + err = dsa_port_enable_rt(dp, dev->phydev); if (err) goto clear_promisc; - phylink_start(dp->pl); - return 0; clear_promisc: @@ -114,9 +112,7 @@ static int dsa_slave_close(struct net_device *dev) struct net_device *master = dsa_slave_to_master(dev); struct dsa_port *dp = dsa_slave_to_port(dev); - phylink_stop(dp->pl); - - dsa_port_disable(dp); + dsa_port_disable_rt(dp); dev_mc_unsync(master, dev); dev_uc_unsync(master, dev); From f8a0fea9518c5ff7c37679504bd9eeabeae8ee36 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jonathan=20Neusch=C3=A4fer?= Date: Tue, 3 Mar 2020 21:22:05 +0100 Subject: [PATCH 073/256] docs: networking: net_failover: Fix a few typos MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Jonathan Neuschäfer Signed-off-by: David S. Miller --- Documentation/networking/net_failover.rst | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/Documentation/networking/net_failover.rst b/Documentation/networking/net_failover.rst index 06c97dcb57ca..e143ab79a960 100644 --- a/Documentation/networking/net_failover.rst +++ b/Documentation/networking/net_failover.rst @@ -8,9 +8,9 @@ Overview ======== The net_failover driver provides an automated failover mechanism via APIs -to create and destroy a failover master netdev and mananges a primary and +to create and destroy a failover master netdev and manages a primary and standby slave netdevs that get registered via the generic failover -infrastructrure. +infrastructure. The failover netdev acts a master device and controls 2 slave devices. The original paravirtual interface is registered as 'standby' slave netdev and @@ -29,7 +29,7 @@ virtio-net accelerated datapath: STANDBY mode ============================================= net_failover enables hypervisor controlled accelerated datapath to virtio-net -enabled VMs in a transparent manner with no/minimal guest userspace chanages. +enabled VMs in a transparent manner with no/minimal guest userspace changes. To support this, the hypervisor needs to enable VIRTIO_NET_F_STANDBY feature on the virtio-net interface and assign the same MAC address to both From dc15af8e9dbd039ebb06336597d2c491ef46ab74 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Tue, 25 Feb 2020 10:05:47 +0300 Subject: [PATCH 074/256] netfilter: nf_conntrack: ct_cpu_seq_next should increase position index If .next function does not change position index, following .show function will repeat output related to current position index. Cc: stable@vger.kernel.org Fixes: 1f4aace60b0e ("fs/seq_file.c: simplify seq_file iteration code ...") Link: https://bugzilla.kernel.org/show_bug.cgi?id=206283 Signed-off-by: Vasily Averin Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_standalone.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 410809c669e1..4912069627b6 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -411,7 +411,7 @@ static void *ct_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos) *pos = cpu + 1; return per_cpu_ptr(net->ct.stat, cpu); } - + (*pos)++; return NULL; } From bb71f846a0002239f7058c84f1496648ff4a5c20 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Tue, 25 Feb 2020 10:05:59 +0300 Subject: [PATCH 075/256] netfilter: synproxy: synproxy_cpu_seq_next should increase position index If .next function does not change position index, following .show function will repeat output related to current position index. Cc: stable@vger.kernel.org Fixes: 1f4aace60b0e ("fs/seq_file.c: simplify seq_file iteration code ...") Link: https://bugzilla.kernel.org/show_bug.cgi?id=206283 Signed-off-by: Vasily Averin Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_synproxy_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index b0930d4aba22..b9cbe1e2453e 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -267,7 +267,7 @@ static void *synproxy_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos) *pos = cpu + 1; return per_cpu_ptr(snet->stats, cpu); } - + (*pos)++; return NULL; } From db25517a550926f609c63054b12ea9ad515e1a10 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Tue, 25 Feb 2020 10:06:29 +0300 Subject: [PATCH 076/256] netfilter: xt_recent: recent_seq_next should increase position index If .next function does not change position index, following .show function will repeat output related to current position index. Without the patch: # dd if=/proc/net/xt_recent/SSH # original file outpt src=127.0.0.4 ttl: 0 last_seen: 6275444819 oldest_pkt: 1 6275444819 src=127.0.0.2 ttl: 0 last_seen: 6275438906 oldest_pkt: 1 6275438906 src=127.0.0.3 ttl: 0 last_seen: 6275441953 oldest_pkt: 1 6275441953 0+1 records in 0+1 records out 204 bytes copied, 6.1332e-05 s, 3.3 MB/s Read after lseek into middle of last line (offset 140 in example below) generates expected end of last line and then unexpected whole last line once again # dd if=/proc/net/xt_recent/SSH bs=140 skip=1 dd: /proc/net/xt_recent/SSH: cannot skip to specified offset 127.0.0.3 ttl: 0 last_seen: 6275441953 oldest_pkt: 1 6275441953 src=127.0.0.3 ttl: 0 last_seen: 6275441953 oldest_pkt: 1 6275441953 0+1 records in 0+1 records out 132 bytes copied, 6.2487e-05 s, 2.1 MB/s Cc: stable@vger.kernel.org Fixes: 1f4aace60b0e ("fs/seq_file.c: simplify seq_file iteration code ...") Link: https://bugzilla.kernel.org/show_bug.cgi?id=206283 Signed-off-by: Vasily Averin Signed-off-by: Pablo Neira Ayuso --- net/netfilter/xt_recent.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index 0a9708004e20..225a7ab6d79a 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -492,12 +492,12 @@ static void *recent_seq_next(struct seq_file *seq, void *v, loff_t *pos) const struct recent_entry *e = v; const struct list_head *head = e->list.next; + (*pos)++; while (head == &t->iphash[st->bucket]) { if (++st->bucket >= ip_list_hash_size) return NULL; head = t->iphash[st->bucket].next; } - (*pos)++; return list_entry(head, struct recent_entry, list); } From ee84f19cbbe9cf7cba2958acb03163fed3ecbb0f Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Tue, 25 Feb 2020 10:07:12 +0300 Subject: [PATCH 077/256] netfilter: x_tables: xt_mttg_seq_next should increase position index If .next function does not change position index, following .show function will repeat output related to current position index. Without patch: # dd if=/proc/net/ip_tables_matches # original file output conntrack conntrack conntrack recent recent icmp udplite udp tcp 0+1 records in 0+1 records out 65 bytes copied, 5.4074e-05 s, 1.2 MB/s # dd if=/proc/net/ip_tables_matches bs=62 skip=1 dd: /proc/net/ip_tables_matches: cannot skip to specified offset cp <<< end of last line tcp <<< and then unexpected whole last line once again 0+1 records in 0+1 records out 7 bytes copied, 0.000102447 s, 68.3 kB/s Cc: stable@vger.kernel.org Fixes: 1f4aace60b0e ("fs/seq_file.c: simplify seq_file iteration code ...") Link: https://bugzilla.kernel.org/show_bug.cgi?id=206283 Signed-off-by: Vasily Averin Signed-off-by: Pablo Neira Ayuso --- net/netfilter/x_tables.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index e27c6c5ba9df..cd2b034eef59 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1551,6 +1551,9 @@ static void *xt_mttg_seq_next(struct seq_file *seq, void *v, loff_t *ppos, uint8_t nfproto = (unsigned long)PDE_DATA(file_inode(seq->file)); struct nf_mttg_trav *trav = seq->private; + if (ppos != NULL) + ++(*ppos); + switch (trav->class) { case MTTG_TRAV_INIT: trav->class = MTTG_TRAV_NFP_UNSPEC; @@ -1576,9 +1579,6 @@ static void *xt_mttg_seq_next(struct seq_file *seq, void *v, loff_t *ppos, default: return NULL; } - - if (ppos != NULL) - ++*ppos; return trav; } From 2d285f26ecd072800a29c5b71e63437f21ef830a Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 2 Mar 2020 21:58:50 +0100 Subject: [PATCH 078/256] netfilter: nf_tables: free flowtable hooks on hook register error If hook registration fails, the hooks allocated via nft_netdev_hook_alloc need to be freed. We can't change the goto label to 'goto 5' -- while it does fix the memleak it does cause a warning splat from the netfilter core (the hooks were not registered). Fixes: 3f0465a9ef02 ("netfilter: nf_tables: dynamically allocate hooks per net_device in flowtables") Reported-by: syzbot+a2ff6fa45162a5ed4dd3@syzkaller.appspotmail.com Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index d1318bdf49ca..bb064aa4154b 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -6300,8 +6300,13 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, goto err4; err = nft_register_flowtable_net_hooks(ctx.net, table, flowtable); - if (err < 0) + if (err < 0) { + list_for_each_entry_safe(hook, next, &flowtable->hook_list, list) { + list_del_rcu(&hook->list); + kfree_rcu(hook, rcu); + } goto err4; + } err = nft_trans_flowtable_add(&ctx, NFT_MSG_NEWFLOWTABLE, flowtable); if (err < 0) From c049b3450072b8e3998053490e025839fecfef31 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 2 Mar 2020 21:08:31 -0800 Subject: [PATCH 079/256] netfilter: cthelper: add missing attribute validation for cthelper Add missing attribute validation for cthelper to the netlink policy. Fixes: 12f7a505331e ("netfilter: add user-space connection tracking helper infrastructure") Signed-off-by: Jakub Kicinski Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nfnetlink_cthelper.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index de3a9596b7f1..a5f294aa8e4c 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -742,6 +742,8 @@ static const struct nla_policy nfnl_cthelper_policy[NFCTH_MAX+1] = { [NFCTH_NAME] = { .type = NLA_NUL_STRING, .len = NF_CT_HELPER_NAME_LEN-1 }, [NFCTH_QUEUE_NUM] = { .type = NLA_U32, }, + [NFCTH_PRIV_DATA_LEN] = { .type = NLA_U32, }, + [NFCTH_STATUS] = { .type = NLA_U32, }, }; static const struct nfnl_callback nfnl_cthelper_cb[NFNL_MSG_CTHELPER_MAX] = { From 9d6effb2f1523eb84516e44213c00f2fd9e6afff Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 2 Mar 2020 21:08:32 -0800 Subject: [PATCH 080/256] netfilter: nft_payload: add missing attribute validation for payload csum flags Add missing attribute validation for NFTA_PAYLOAD_CSUM_FLAGS to the netlink policy. Fixes: 1814096980bb ("netfilter: nft_payload: layer 4 checksum adjustment for pseudoheader fields") Signed-off-by: Jakub Kicinski Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_payload.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 1993af3a2979..a7de3a58f553 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -129,6 +129,7 @@ static const struct nla_policy nft_payload_policy[NFTA_PAYLOAD_MAX + 1] = { [NFTA_PAYLOAD_LEN] = { .type = NLA_U32 }, [NFTA_PAYLOAD_CSUM_TYPE] = { .type = NLA_U32 }, [NFTA_PAYLOAD_CSUM_OFFSET] = { .type = NLA_U32 }, + [NFTA_PAYLOAD_CSUM_FLAGS] = { .type = NLA_U32 }, }; static int nft_payload_init(const struct nft_ctx *ctx, From 88a637719a1570705c02cacb3297af164b1714e7 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 2 Mar 2020 21:08:33 -0800 Subject: [PATCH 081/256] netfilter: nft_tunnel: add missing attribute validation for tunnels Add missing attribute validation for tunnel source and destination ports to the netlink policy. Fixes: af308b94a2a4 ("netfilter: nf_tables: add tunnel support") Signed-off-by: Jakub Kicinski Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_tunnel.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c index 4c3f2e24c7cb..764e88682a81 100644 --- a/net/netfilter/nft_tunnel.c +++ b/net/netfilter/nft_tunnel.c @@ -339,6 +339,8 @@ static const struct nla_policy nft_tunnel_key_policy[NFTA_TUNNEL_KEY_MAX + 1] = [NFTA_TUNNEL_KEY_FLAGS] = { .type = NLA_U32, }, [NFTA_TUNNEL_KEY_TOS] = { .type = NLA_U8, }, [NFTA_TUNNEL_KEY_TTL] = { .type = NLA_U8, }, + [NFTA_TUNNEL_KEY_SPORT] = { .type = NLA_U16, }, + [NFTA_TUNNEL_KEY_DPORT] = { .type = NLA_U16, }, [NFTA_TUNNEL_KEY_OPTS] = { .type = NLA_NESTED, }, }; From 707518348ae7337db34bdeb544edf254f66e20f2 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 2 Mar 2020 14:21:19 -0800 Subject: [PATCH 082/256] devlink: remove trigger command from devlink-region.rst The devlink trigger command does not exist. While rewriting the documentation for devlink into the reStructuredText format, documentation for the trigger command was accidentally merged in. This occurred because the author was also working on a potential extension to devlink regions which included this trigger command, and accidentally squashed the documentation incorrectly. Further review eventually settled on using the previously unused "new" command instead of creating a new trigger command. Fix this by removing mention of the trigger command from the documentation. Fixes: 0b0f945f5458 ("devlink: add a file documenting devlink regions", 2020-01-10) Noticed-by: Jiri Pirko Signed-off-by: Jacob Keller Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- Documentation/networking/devlink/devlink-region.rst | 3 --- 1 file changed, 3 deletions(-) diff --git a/Documentation/networking/devlink/devlink-region.rst b/Documentation/networking/devlink/devlink-region.rst index 1a7683e7acb2..8b46e8591fe0 100644 --- a/Documentation/networking/devlink/devlink-region.rst +++ b/Documentation/networking/devlink/devlink-region.rst @@ -40,9 +40,6 @@ example usage # Delete a snapshot using: $ devlink region del pci/0000:00:05.0/cr-space snapshot 1 - # Trigger (request) a snapshot be taken: - $ devlink region trigger pci/0000:00:05.0/cr-space - # Dump a snapshot: $ devlink region dump pci/0000:00:05.0/fw-health snapshot 1 0000000000000000 0014 95dc 0014 9514 0035 1670 0034 db30 From 43de81b0601df7d7988d3f5617ee0987df65c883 Mon Sep 17 00:00:00 2001 From: Jonas Gorski Date: Mon, 2 Mar 2020 20:46:57 +0100 Subject: [PATCH 083/256] net: phy: bcm63xx: fix OOPS due to missing driver name 719655a14971 ("net: phy: Replace phy driver features u32 with link_mode bitmap") was a bit over-eager and also removed the second phy driver's name, resulting in a nasty OOPS on registration: [ 1.319854] CPU 0 Unable to handle kernel paging request at virtual address 00000000, epc == 804dd50c, ra == 804dd4f0 [ 1.330859] Oops[#1]: [ 1.333138] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.4.22 #0 [ 1.339217] $ 0 : 00000000 00000001 87ca7f00 805c1874 [ 1.344590] $ 4 : 00000000 00000047 00585000 8701f800 [ 1.349965] $ 8 : 8701f800 804f4a5c 00000003 64726976 [ 1.355341] $12 : 00000001 00000000 00000000 00000114 [ 1.360718] $16 : 87ca7f80 00000000 00000000 80639fe4 [ 1.366093] $20 : 00000002 00000000 806441d0 80b90000 [ 1.371470] $24 : 00000000 00000000 [ 1.376847] $28 : 87c1e000 87c1fda0 80b90000 804dd4f0 [ 1.382224] Hi : d1c8f8da [ 1.385180] Lo : 5518a480 [ 1.388182] epc : 804dd50c kset_find_obj+0x3c/0x114 [ 1.393345] ra : 804dd4f0 kset_find_obj+0x20/0x114 [ 1.398530] Status: 10008703 KERNEL EXL IE [ 1.402833] Cause : 00800008 (ExcCode 02) [ 1.406952] BadVA : 00000000 [ 1.409913] PrId : 0002a075 (Broadcom BMIPS4350) [ 1.414745] Modules linked in: [ 1.417895] Process swapper/0 (pid: 1, threadinfo=(ptrval), task=(ptrval), tls=00000000) [ 1.426214] Stack : 87cec000 80630000 80639370 80640658 80640000 80049af4 80639fe4 8063a0d8 [ 1.434816] 8063a0d8 802ef078 00000002 00000000 806441d0 80b90000 8063a0d8 802ef114 [ 1.443417] 87cea0de 87c1fde0 00000000 804de488 87cea000 8063a0d8 8063a0d8 80334e48 [ 1.452018] 80640000 8063984c 80639bf4 00000000 8065de48 00000001 8063a0d8 80334ed0 [ 1.460620] 806441d0 80b90000 80b90000 802ef164 8065dd70 80620000 80b90000 8065de58 [ 1.469222] ... [ 1.471734] Call Trace: [ 1.474255] [<804dd50c>] kset_find_obj+0x3c/0x114 [ 1.479141] [<802ef078>] driver_find+0x1c/0x44 [ 1.483665] [<802ef114>] driver_register+0x74/0x148 [ 1.488719] [<80334e48>] phy_driver_register+0x9c/0xd0 [ 1.493968] [<80334ed0>] phy_drivers_register+0x54/0xe8 [ 1.499345] [<8001061c>] do_one_initcall+0x7c/0x1f4 [ 1.504374] [<80644ed8>] kernel_init_freeable+0x1d4/0x2b4 [ 1.509940] [<804f4e24>] kernel_init+0x10/0xf8 [ 1.514502] [<80018e68>] ret_from_kernel_thread+0x14/0x1c [ 1.520040] Code: 1060000c 02202025 90650000 <90810000> 24630001 14250004 24840001 14a0fffb 90650000 [ 1.530061] [ 1.531698] ---[ end trace d52f1717cd29bdc8 ]--- Fix it by readding the name. Fixes: 719655a14971 ("net: phy: Replace phy driver features u32 with link_mode bitmap") Signed-off-by: Jonas Gorski Acked-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/phy/bcm63xx.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/phy/bcm63xx.c b/drivers/net/phy/bcm63xx.c index 23f1958ba6ad..459fb2069c7e 100644 --- a/drivers/net/phy/bcm63xx.c +++ b/drivers/net/phy/bcm63xx.c @@ -73,6 +73,7 @@ static struct phy_driver bcm63xx_driver[] = { /* same phy as above, with just a different OUI */ .phy_id = 0x002bdc00, .phy_id_mask = 0xfffffc00, + .name = "Broadcom BCM63XX (2)", /* PHY_BASIC_FEATURES */ .flags = PHY_IS_INTERNAL, .config_init = bcm63xx_config_init, From 20d8bb0d172d87dcc52727cb7174ae9994de8978 Mon Sep 17 00:00:00 2001 From: Hauke Mehrtens Date: Mon, 2 Mar 2020 00:55:02 +0100 Subject: [PATCH 084/256] phylink: Improve error message when validate failed This should improve the error message when the PHY validate in the MAC driver failed. I ran into this problem multiple times that I put wrong interface values into the device tree and was searching why it is failing with -22 (-EINVAL). This should make it easier to spot the problem. Signed-off-by: Hauke Mehrtens Acked-by: Russell King Signed-off-by: David S. Miller --- drivers/net/phy/phylink.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 70b9a143db84..6e66b8e77ec7 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -761,8 +761,14 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy, config.interface = interface; ret = phylink_validate(pl, supported, &config); - if (ret) + if (ret) { + phylink_warn(pl, "validation of %s with support %*pb and advertisement %*pb failed: %d\n", + phy_modes(config.interface), + __ETHTOOL_LINK_MODE_MASK_NBITS, phy->supported, + __ETHTOOL_LINK_MODE_MASK_NBITS, config.advertising, + ret); return ret; + } phy->phylink = pl; phy->phy_link_change = phylink_phy_change; From 116ca924aea664141afa86a1425edc3fcda0d06f Mon Sep 17 00:00:00 2001 From: Vishal Kulkarni Date: Mon, 2 Mar 2020 10:54:13 +0530 Subject: [PATCH 085/256] cxgb4: fix checks for max queues to allocate Hardware can support more than 8 queues currently limited by netif_get_num_default_rss_queues(). So, rework and fix checks for max number of queues to allocate. The checks should be based on how many are actually supported by hardware, OR the number of online cpus; whichever is lower. Fixes: 5952dde72307 ("cxgb4: set maximal number of default RSS queues") Signed-off-by: Vishal Kulkarni " Signed-off-by: David S. Miller --- .../net/ethernet/chelsio/cxgb4/cxgb4_main.c | 49 ++++++++++--------- 1 file changed, 27 insertions(+), 22 deletions(-) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 649842a8aa28..97f90edbc068 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -5381,12 +5381,11 @@ static inline bool is_x_10g_port(const struct link_config *lc) static int cfg_queues(struct adapter *adap) { u32 avail_qsets, avail_eth_qsets, avail_uld_qsets; + u32 i, n10g = 0, qidx = 0, n1g = 0; + u32 ncpus = num_online_cpus(); u32 niqflint, neq, num_ulds; struct sge *s = &adap->sge; - u32 i, n10g = 0, qidx = 0; -#ifndef CONFIG_CHELSIO_T4_DCB - int q10g = 0; -#endif + u32 q10g = 0, q1g; /* Reduce memory usage in kdump environment, disable all offload. */ if (is_kdump_kernel() || (is_uld(adap) && t4_uld_mem_alloc(adap))) { @@ -5424,44 +5423,50 @@ static int cfg_queues(struct adapter *adap) n10g += is_x_10g_port(&adap2pinfo(adap, i)->link_cfg); avail_eth_qsets = min_t(u32, avail_qsets, MAX_ETH_QSETS); + + /* We default to 1 queue per non-10G port and up to # of cores queues + * per 10G port. + */ + if (n10g) + q10g = (avail_eth_qsets - (adap->params.nports - n10g)) / n10g; + + n1g = adap->params.nports - n10g; #ifdef CONFIG_CHELSIO_T4_DCB /* For Data Center Bridging support we need to be able to support up * to 8 Traffic Priorities; each of which will be assigned to its * own TX Queue in order to prevent Head-Of-Line Blocking. */ + q1g = 8; if (adap->params.nports * 8 > avail_eth_qsets) { dev_err(adap->pdev_dev, "DCB avail_eth_qsets=%d < %d!\n", avail_eth_qsets, adap->params.nports * 8); return -ENOMEM; } - for_each_port(adap, i) { - struct port_info *pi = adap2pinfo(adap, i); + if (adap->params.nports * ncpus < avail_eth_qsets) + q10g = max(8U, ncpus); + else + q10g = max(8U, q10g); + + while ((q10g * n10g) > (avail_eth_qsets - n1g * q1g)) + q10g--; - pi->first_qset = qidx; - pi->nqsets = is_kdump_kernel() ? 1 : 8; - qidx += pi->nqsets; - } #else /* !CONFIG_CHELSIO_T4_DCB */ - /* We default to 1 queue per non-10G port and up to # of cores queues - * per 10G port. - */ - if (n10g) - q10g = (avail_eth_qsets - (adap->params.nports - n10g)) / n10g; - if (q10g > netif_get_num_default_rss_queues()) - q10g = netif_get_num_default_rss_queues(); - - if (is_kdump_kernel()) + q1g = 1; + q10g = min(q10g, ncpus); +#endif /* !CONFIG_CHELSIO_T4_DCB */ + if (is_kdump_kernel()) { q10g = 1; + q1g = 1; + } for_each_port(adap, i) { struct port_info *pi = adap2pinfo(adap, i); pi->first_qset = qidx; - pi->nqsets = is_x_10g_port(&pi->link_cfg) ? q10g : 1; + pi->nqsets = is_x_10g_port(&pi->link_cfg) ? q10g : q1g; qidx += pi->nqsets; } -#endif /* !CONFIG_CHELSIO_T4_DCB */ s->ethqsets = qidx; s->max_ethqsets = qidx; /* MSI-X may lower it later */ @@ -5473,7 +5478,7 @@ static int cfg_queues(struct adapter *adap) * capped by the number of available cores. */ num_ulds = adap->num_uld + adap->num_ofld_uld; - i = min_t(u32, MAX_OFLD_QSETS, num_online_cpus()); + i = min_t(u32, MAX_OFLD_QSETS, ncpus); avail_uld_qsets = roundup(i, adap->params.nports); if (avail_qsets < num_ulds * adap->params.nports) { adap->params.offload = 0; From 209c65b61d94344522c41a83cd6ce51aac5fd0a4 Mon Sep 17 00:00:00 2001 From: Dajun Jin Date: Mon, 2 Mar 2020 20:24:21 -0800 Subject: [PATCH 086/256] drivers/of/of_mdio.c:fix of_mdiobus_register() When registers a phy_device successful, should terminate the loop or the phy_device would be registered in other addr. If there are multiple PHYs without reg properties, it will go wrong. Signed-off-by: Dajun Jin Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/of/of_mdio.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index 8270bbf505fb..9f982c0627a0 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -306,6 +306,7 @@ int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np) rc = of_mdiobus_register_phy(mdio, child, addr); if (rc && rc != -ENODEV) goto unregister; + break; } } } From 31e43f31890ca6e909b27dcb539252b46aa465da Mon Sep 17 00:00:00 2001 From: Ben Chuang Date: Wed, 19 Feb 2020 17:29:00 +0800 Subject: [PATCH 087/256] mmc: sdhci-pci-gli: Enable MSI interrupt for GL975x Enable MSI interrupt for GL9750/GL9755. Some platforms do not support PCI INTx and devices can not work without interrupt. Like messages below: [ 4.487132] sdhci-pci 0000:01:00.0: SDHCI controller found [17a0:9755] (rev 0) [ 4.487198] ACPI BIOS Error (bug): Could not resolve symbol [\_SB.PCI0.PBR2._PRT.APS2], AE_NOT_FOUND (20190816/psargs-330) [ 4.487397] ACPI Error: Aborting method \_SB.PCI0.PBR2._PRT due to previous error (AE_NOT_FOUND) (20190816/psparse-529) [ 4.487707] pcieport 0000:00:01.3: can't derive routing for PCI INT A [ 4.487709] sdhci-pci 0000:01:00.0: PCI INT A: no GSI Signed-off-by: Ben Chuang Tested-by: Raul E Rangel Fixes: e51df6ce668a ("mmc: host: sdhci-pci: Add Genesys Logic GL975x support") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20200219092900.9151-1-benchuanggli@gmail.com Signed-off-by: Ulf Hansson --- drivers/mmc/host/sdhci-pci-gli.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/drivers/mmc/host/sdhci-pci-gli.c b/drivers/mmc/host/sdhci-pci-gli.c index 5eea8d70a85d..ce15a05f23d4 100644 --- a/drivers/mmc/host/sdhci-pci-gli.c +++ b/drivers/mmc/host/sdhci-pci-gli.c @@ -262,10 +262,26 @@ static int gl9750_execute_tuning(struct sdhci_host *host, u32 opcode) return 0; } +static void gli_pcie_enable_msi(struct sdhci_pci_slot *slot) +{ + int ret; + + ret = pci_alloc_irq_vectors(slot->chip->pdev, 1, 1, + PCI_IRQ_MSI | PCI_IRQ_MSIX); + if (ret < 0) { + pr_warn("%s: enable PCI MSI failed, error=%d\n", + mmc_hostname(slot->host->mmc), ret); + return; + } + + slot->host->irq = pci_irq_vector(slot->chip->pdev, 0); +} + static int gli_probe_slot_gl9750(struct sdhci_pci_slot *slot) { struct sdhci_host *host = slot->host; + gli_pcie_enable_msi(slot); slot->host->mmc->caps2 |= MMC_CAP2_NO_SDIO; sdhci_enable_v4_mode(host); @@ -276,6 +292,7 @@ static int gli_probe_slot_gl9755(struct sdhci_pci_slot *slot) { struct sdhci_host *host = slot->host; + gli_pcie_enable_msi(slot); slot->host->mmc->caps2 |= MMC_CAP2_NO_SDIO; sdhci_enable_v4_mode(host); From 65ac74f1de3334852fb7d9b1b430fa5a06524276 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 4 Mar 2020 11:11:17 +0000 Subject: [PATCH 088/256] iommu/dma: Fix MSI reservation allocation The way cookie_init_hw_msi_region() allocates the iommu_dma_msi_page structures doesn't match the way iommu_put_dma_cookie() frees them. The former performs a single allocation of all the required structures, while the latter tries to free them one at a time. It doesn't quite work for the main use case (the GICv3 ITS where the range is 64kB) when the base granule size is 4kB. This leads to a nice slab corruption on teardown, which is easily observable by simply creating a VF on a SRIOV-capable device, and tearing it down immediately (no need to even make use of it). Fortunately, this only affects systems where the ITS isn't translated by the SMMU, which are both rare and non-standard. Fix it by allocating iommu_dma_msi_page structures one at a time. Fixes: 7c1b058c8b5a3 ("iommu/dma: Handle IOMMU API reserved regions") Signed-off-by: Marc Zyngier Reviewed-by: Eric Auger Cc: Robin Murphy Cc: Joerg Roedel Cc: Will Deacon Cc: stable@vger.kernel.org Reviewed-by: Robin Murphy Signed-off-by: Joerg Roedel --- drivers/iommu/dma-iommu.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index a2e96a5fd9a7..ba128d1cdaee 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -177,15 +177,15 @@ static int cookie_init_hw_msi_region(struct iommu_dma_cookie *cookie, start -= iova_offset(iovad, start); num_pages = iova_align(iovad, end - start) >> iova_shift(iovad); - msi_page = kcalloc(num_pages, sizeof(*msi_page), GFP_KERNEL); - if (!msi_page) - return -ENOMEM; - for (i = 0; i < num_pages; i++) { - msi_page[i].phys = start; - msi_page[i].iova = start; - INIT_LIST_HEAD(&msi_page[i].list); - list_add(&msi_page[i].list, &cookie->msi_page_list); + msi_page = kmalloc(sizeof(*msi_page), GFP_KERNEL); + if (!msi_page) + return -ENOMEM; + + msi_page->phys = start; + msi_page->iova = start; + INIT_LIST_HEAD(&msi_page->list); + list_add(&msi_page->list, &cookie->msi_page_list); start += iovad->granule; } From 190ecb190a9cd8c0599d8499b901e3c32e87966a Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Sun, 23 Feb 2020 22:00:07 -0500 Subject: [PATCH 089/256] cgroup: fix psi_show() crash on 32bit ino archs Similar to the commit d7495343228f ("cgroup: fix incorrect WARN_ON_ONCE() in cgroup_setup_root()"), cgroup_id(root_cgrp) does not equal to 1 on 32bit ino archs which triggers all sorts of issues with psi_show() on s390x. For example, BUG: KASAN: slab-out-of-bounds in collect_percpu_times+0x2d0/ Read of size 4 at addr 000000001e0ce000 by task read_all/3667 collect_percpu_times+0x2d0/0x798 psi_show+0x7c/0x2a8 seq_read+0x2ac/0x830 vfs_read+0x92/0x150 ksys_read+0xe2/0x188 system_call+0xd8/0x2b4 Fix it by using cgroup_ino(). Fixes: 743210386c03 ("cgroup: use cgrp->kn->id as the cgroup ID") Signed-off-by: Qian Cai Acked-by: Johannes Weiner Signed-off-by: Tejun Heo Cc: stable@vger.kernel.org # v5.5 --- kernel/cgroup/cgroup.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index c719a4154d6d..7a39dc882095 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3542,21 +3542,21 @@ static int cpu_stat_show(struct seq_file *seq, void *v) static int cgroup_io_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; - struct psi_group *psi = cgroup_id(cgrp) == 1 ? &psi_system : &cgrp->psi; + struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : &cgrp->psi; return psi_show(seq, psi, PSI_IO); } static int cgroup_memory_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; - struct psi_group *psi = cgroup_id(cgrp) == 1 ? &psi_system : &cgrp->psi; + struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : &cgrp->psi; return psi_show(seq, psi, PSI_MEM); } static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; - struct psi_group *psi = cgroup_id(cgrp) == 1 ? &psi_system : &cgrp->psi; + struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : &cgrp->psi; return psi_show(seq, psi, PSI_CPU); } From 2e5383d7904e60529136727e49629a82058a5607 Mon Sep 17 00:00:00 2001 From: Tycho Andersen Date: Wed, 19 Feb 2020 12:01:29 -0700 Subject: [PATCH 090/256] cgroup1: don't call release_agent when it is "" Older (and maybe current) versions of systemd set release_agent to "" when shutting down, but do not set notify_on_release to 0. Since 64e90a8acb85 ("Introduce STATIC_USERMODEHELPER to mediate call_usermodehelper()"), we filter out such calls when the user mode helper path is "". However, when used in conjunction with an actual (i.e. non "") STATIC_USERMODEHELPER, the path is never "", so the real usermode helper will be called with argv[0] == "". Let's avoid this by not invoking the release_agent when it is "". Signed-off-by: Tycho Andersen Signed-off-by: Tejun Heo --- kernel/cgroup/cgroup-v1.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 9a6f060cbf51..f2d7cea86ffe 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -783,7 +783,7 @@ void cgroup1_release_agent(struct work_struct *work) pathbuf = kmalloc(PATH_MAX, GFP_KERNEL); agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL); - if (!pathbuf || !agentbuf) + if (!pathbuf || !agentbuf || !strlen(agentbuf)) goto out; spin_lock_irq(&css_set_lock); From 1579f1bc3b753d17a44de3457d5c6f4a5b14c752 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Sun, 1 Mar 2020 22:52:35 +0800 Subject: [PATCH 091/256] crypto: x86/curve25519 - support assemblers with no adx support Some older version of GAS do not support the ADX instructions, similarly to how they also don't support AVX and such. This commit adds the same build-time detection mechanisms we use for AVX and others for ADX, and then makes sure that the curve25519 library dispatcher calls the right functions. Reported-by: Willy Tarreau Signed-off-by: Jason A. Donenfeld Signed-off-by: Herbert Xu --- arch/x86/Makefile | 5 +++-- arch/x86/crypto/Makefile | 7 ++++++- include/crypto/curve25519.h | 6 ++++-- 3 files changed, 13 insertions(+), 5 deletions(-) diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 94df0868804b..513a55562d75 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -194,9 +194,10 @@ avx2_instr :=$(call as-instr,vpbroadcastb %xmm0$(comma)%ymm1,-DCONFIG_AS_AVX2=1) avx512_instr :=$(call as-instr,vpmovm2b %k1$(comma)%zmm5,-DCONFIG_AS_AVX512=1) sha1_ni_instr :=$(call as-instr,sha1msg1 %xmm0$(comma)%xmm1,-DCONFIG_AS_SHA1_NI=1) sha256_ni_instr :=$(call as-instr,sha256msg1 %xmm0$(comma)%xmm1,-DCONFIG_AS_SHA256_NI=1) +adx_instr := $(call as-instr,adox %r10$(comma)%r10,-DCONFIG_AS_ADX=1) -KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) $(avx512_instr) $(sha1_ni_instr) $(sha256_ni_instr) -KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) $(avx512_instr) $(sha1_ni_instr) $(sha256_ni_instr) +KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) $(avx512_instr) $(sha1_ni_instr) $(sha256_ni_instr) $(adx_instr) +KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) $(avx512_instr) $(sha1_ni_instr) $(sha256_ni_instr) $(adx_instr) KBUILD_LDFLAGS := -m elf_$(UTS_MACHINE) diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile index b69e00bf20b8..8c2e9eadee8a 100644 --- a/arch/x86/crypto/Makefile +++ b/arch/x86/crypto/Makefile @@ -11,6 +11,7 @@ avx2_supported := $(call as-instr,vpgatherdd %ymm0$(comma)(%eax$(comma)%ymm1\ avx512_supported :=$(call as-instr,vpmovm2b %k1$(comma)%zmm5,yes,no) sha1_ni_supported :=$(call as-instr,sha1msg1 %xmm0$(comma)%xmm1,yes,no) sha256_ni_supported :=$(call as-instr,sha256msg1 %xmm0$(comma)%xmm1,yes,no) +adx_supported := $(call as-instr,adox %r10$(comma)%r10,yes,no) obj-$(CONFIG_CRYPTO_GLUE_HELPER_X86) += glue_helper.o @@ -39,7 +40,11 @@ obj-$(CONFIG_CRYPTO_AEGIS128_AESNI_SSE2) += aegis128-aesni.o obj-$(CONFIG_CRYPTO_NHPOLY1305_SSE2) += nhpoly1305-sse2.o obj-$(CONFIG_CRYPTO_NHPOLY1305_AVX2) += nhpoly1305-avx2.o -obj-$(CONFIG_CRYPTO_CURVE25519_X86) += curve25519-x86_64.o + +# These modules require the assembler to support ADX. +ifeq ($(adx_supported),yes) + obj-$(CONFIG_CRYPTO_CURVE25519_X86) += curve25519-x86_64.o +endif # These modules require assembler to support AVX. ifeq ($(avx_supported),yes) diff --git a/include/crypto/curve25519.h b/include/crypto/curve25519.h index 4e6dc840b159..9ecb3c1f0f15 100644 --- a/include/crypto/curve25519.h +++ b/include/crypto/curve25519.h @@ -33,7 +33,8 @@ bool __must_check curve25519(u8 mypublic[CURVE25519_KEY_SIZE], const u8 secret[CURVE25519_KEY_SIZE], const u8 basepoint[CURVE25519_KEY_SIZE]) { - if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CURVE25519)) + if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CURVE25519) && + (!IS_ENABLED(CONFIG_CRYPTO_CURVE25519_X86) || IS_ENABLED(CONFIG_AS_ADX))) curve25519_arch(mypublic, secret, basepoint); else curve25519_generic(mypublic, secret, basepoint); @@ -49,7 +50,8 @@ __must_check curve25519_generate_public(u8 pub[CURVE25519_KEY_SIZE], CURVE25519_KEY_SIZE))) return false; - if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CURVE25519)) + if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CURVE25519) && + (!IS_ENABLED(CONFIG_CRYPTO_CURVE25519_X86) || IS_ENABLED(CONFIG_AS_ADX))) curve25519_base_arch(pub, secret); else curve25519_generic(pub, secret, curve25519_base_point); From d78008de6103c708171baff9650a7862645d23b0 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 3 Mar 2020 15:02:45 +0100 Subject: [PATCH 092/256] netfilter: nf_tables: dump NFTA_CHAIN_FLAGS attribute Missing NFTA_CHAIN_FLAGS netlink attribute when dumping basechain definitions. Fixes: c9626a2cbdb2 ("netfilter: nf_tables: add hardware offload support") Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index bb064aa4154b..f9e60981bd36 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1405,6 +1405,11 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net, lockdep_commit_lock_is_held(net)); if (nft_dump_stats(skb, stats)) goto nla_put_failure; + + if ((chain->flags & NFT_CHAIN_HW_OFFLOAD) && + nla_put_be32(skb, NFTA_CHAIN_FLAGS, + htonl(NFT_CHAIN_HW_OFFLOAD))) + goto nla_put_failure; } if (nla_put_be32(skb, NFTA_CHAIN_USE, htonl(chain->use))) From 1d305ba40eb8081ff21eeb8ca6ba5c70fd920934 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 5 Mar 2020 11:15:36 +0100 Subject: [PATCH 093/256] netfilter: nf_tables: fix infinite loop when expr is not available nft will loop forever if the kernel doesn't support an expression: 1. nft_expr_type_get() appends the family specific name to the module list. 2. -EAGAIN is returned to nfnetlink, nfnetlink calls abort path. 3. abort path sets ->done to true and calls request_module for the expression. 4. nfnetlink replays the batch, we end up in nft_expr_type_get() again. 5. nft_expr_type_get attempts to append family-specific name. This one already exists on the list, so we continue 6. nft_expr_type_get adds the generic expression name to the module list. -EAGAIN is returned, nfnetlink calls abort path. 7. abort path encounters the family-specific expression which has 'done' set, so it gets removed. 8. abort path requests the generic expression name, sets done to true. 9. batch is replayed. If the expression could not be loaded, then we will end up back at 1), because the family-specific name got removed and the cycle starts again. Note that userspace can SIGKILL the nft process to stop the cycle, but the desired behaviour is to return an error after the generic expr name fails to load the expression. Fixes: eb014de4fd418 ("netfilter: nf_tables: autoload modules from the abort path") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index f9e60981bd36..38c680f28f15 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -7388,13 +7388,8 @@ static void nf_tables_module_autoload(struct net *net) list_splice_init(&net->nft.module_list, &module_list); mutex_unlock(&net->nft.commit_mutex); list_for_each_entry_safe(req, next, &module_list, list) { - if (req->done) { - list_del(&req->list); - kfree(req); - } else { - request_module("%s", req->module); - req->done = true; - } + request_module("%s", req->module); + req->done = true; } mutex_lock(&net->nft.commit_mutex); list_splice(&module_list, &net->nft.module_list); @@ -8177,6 +8172,7 @@ static void __net_exit nf_tables_exit_net(struct net *net) __nft_release_tables(net); mutex_unlock(&net->nft.commit_mutex); WARN_ON_ONCE(!list_empty(&net->nft.tables)); + WARN_ON_ONCE(!list_empty(&net->nft.module_list)); } static struct pernet_operations nf_tables_net_ops = { From a754acc3e4bcf0b70f4356fc450fec72875762da Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 4 Mar 2020 18:42:21 +0800 Subject: [PATCH 094/256] KVM: fix Kconfig menu text for -Werror This was evidently copy and pasted from the i915 driver, but the text wasn't updated. Fixes: 4f337faf1c55 ("KVM: allow disabling -Werror") Signed-off-by: Jason A. Donenfeld Signed-off-by: Paolo Bonzini --- arch/x86/kvm/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 1bb4927030af..9fea0757db92 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -68,7 +68,7 @@ config KVM_WERROR depends on (X86_64 && !KASAN) || !COMPILE_TEST depends on EXPERT help - Add -Werror to the build flags for (and only for) i915.ko. + Add -Werror to the build flags for KVM. If in doubt, say "N". From 110a40dfb708fe940a3f3704d470e431c368d256 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 4 Mar 2020 15:51:43 -0800 Subject: [PATCH 095/256] slip: make slhc_compress() more robust against malicious packets Before accessing various fields in IPV4 network header and TCP header, make sure the packet : - Has IP version 4 (ip->version == 4) - Has not a silly network length (ip->ihl >= 5) - Is big enough to hold network and transport headers - Has not a silly TCP header size (th->doff >= sizeof(struct tcphdr) / 4) syzbot reported : BUG: KMSAN: uninit-value in slhc_compress+0x5b9/0x2e60 drivers/net/slip/slhc.c:270 CPU: 0 PID: 11728 Comm: syz-executor231 Not tainted 5.6.0-rc2-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x1c9/0x220 lib/dump_stack.c:118 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:118 __msan_warning+0x58/0xa0 mm/kmsan/kmsan_instr.c:215 slhc_compress+0x5b9/0x2e60 drivers/net/slip/slhc.c:270 ppp_send_frame drivers/net/ppp/ppp_generic.c:1637 [inline] __ppp_xmit_process+0x1902/0x2970 drivers/net/ppp/ppp_generic.c:1495 ppp_xmit_process+0x147/0x2f0 drivers/net/ppp/ppp_generic.c:1516 ppp_write+0x6bb/0x790 drivers/net/ppp/ppp_generic.c:512 do_loop_readv_writev fs/read_write.c:717 [inline] do_iter_write+0x812/0xdc0 fs/read_write.c:1000 compat_writev+0x2df/0x5a0 fs/read_write.c:1351 do_compat_pwritev64 fs/read_write.c:1400 [inline] __do_compat_sys_pwritev fs/read_write.c:1420 [inline] __se_compat_sys_pwritev fs/read_write.c:1414 [inline] __ia32_compat_sys_pwritev+0x349/0x3f0 fs/read_write.c:1414 do_syscall_32_irqs_on arch/x86/entry/common.c:339 [inline] do_fast_syscall_32+0x3c7/0x6e0 arch/x86/entry/common.c:410 entry_SYSENTER_compat+0x68/0x77 arch/x86/entry/entry_64_compat.S:139 RIP: 0023:0xf7f7cd99 Code: 90 e8 0b 00 00 00 f3 90 0f ae e8 eb f9 8d 74 26 00 89 3c 24 c3 90 90 90 90 90 90 90 90 90 90 90 90 51 52 55 89 e5 0f 34 cd 80 <5d> 5a 59 c3 90 90 90 90 eb 0d 90 90 90 90 90 90 90 90 90 90 90 90 RSP: 002b:00000000ffdb84ac EFLAGS: 00000217 ORIG_RAX: 000000000000014e RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00000000200001c0 RDX: 0000000000000001 RSI: 0000000000000000 RDI: 0000000000000003 RBP: 0000000040047459 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:144 [inline] kmsan_internal_poison_shadow+0x66/0xd0 mm/kmsan/kmsan.c:127 kmsan_slab_alloc+0x8a/0xe0 mm/kmsan/kmsan_hooks.c:82 slab_alloc_node mm/slub.c:2793 [inline] __kmalloc_node_track_caller+0xb40/0x1200 mm/slub.c:4401 __kmalloc_reserve net/core/skbuff.c:142 [inline] __alloc_skb+0x2fd/0xac0 net/core/skbuff.c:210 alloc_skb include/linux/skbuff.h:1051 [inline] ppp_write+0x115/0x790 drivers/net/ppp/ppp_generic.c:500 do_loop_readv_writev fs/read_write.c:717 [inline] do_iter_write+0x812/0xdc0 fs/read_write.c:1000 compat_writev+0x2df/0x5a0 fs/read_write.c:1351 do_compat_pwritev64 fs/read_write.c:1400 [inline] __do_compat_sys_pwritev fs/read_write.c:1420 [inline] __se_compat_sys_pwritev fs/read_write.c:1414 [inline] __ia32_compat_sys_pwritev+0x349/0x3f0 fs/read_write.c:1414 do_syscall_32_irqs_on arch/x86/entry/common.c:339 [inline] do_fast_syscall_32+0x3c7/0x6e0 arch/x86/entry/common.c:410 entry_SYSENTER_compat+0x68/0x77 arch/x86/entry/entry_64_compat.S:139 Fixes: b5451d783ade ("slip: Move the SLIP drivers") Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller --- drivers/net/slip/slhc.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/drivers/net/slip/slhc.c b/drivers/net/slip/slhc.c index 58a69f830d29..f78ceba42e57 100644 --- a/drivers/net/slip/slhc.c +++ b/drivers/net/slip/slhc.c @@ -232,7 +232,7 @@ slhc_compress(struct slcompress *comp, unsigned char *icp, int isize, struct cstate *cs = lcs->next; unsigned long deltaS, deltaA; short changes = 0; - int hlen; + int nlen, hlen; unsigned char new_seq[16]; unsigned char *cp = new_seq; struct iphdr *ip; @@ -248,6 +248,8 @@ slhc_compress(struct slcompress *comp, unsigned char *icp, int isize, return isize; ip = (struct iphdr *) icp; + if (ip->version != 4 || ip->ihl < 5) + return isize; /* Bail if this packet isn't TCP, or is an IP fragment */ if (ip->protocol != IPPROTO_TCP || (ntohs(ip->frag_off) & 0x3fff)) { @@ -258,10 +260,14 @@ slhc_compress(struct slcompress *comp, unsigned char *icp, int isize, comp->sls_o_tcp++; return isize; } - /* Extract TCP header */ + nlen = ip->ihl * 4; + if (isize < nlen + sizeof(*th)) + return isize; - th = (struct tcphdr *)(((unsigned char *)ip) + ip->ihl*4); - hlen = ip->ihl*4 + th->doff*4; + th = (struct tcphdr *)(icp + nlen); + if (th->doff < sizeof(struct tcphdr) / 4) + return isize; + hlen = nlen + th->doff * 4; /* Bail if the TCP packet isn't `compressible' (i.e., ACK isn't set or * some other control bit is set). Also uncompressible if From 68e1006f618e509fc7869259fe83ceec4a95dac3 Mon Sep 17 00:00:00 2001 From: Jian Shen Date: Thu, 5 Mar 2020 09:47:53 +0800 Subject: [PATCH 096/256] net: hns3: fix a not link up issue when fibre port supports autoneg When fibre port supports auto-negotiation, the IMP(Intelligent Management Process) processes the speed of auto-negotiation and the user's speed separately. For below case, the port will get a not link up problem. step 1: disables auto-negotiation and sets speed to A, then the driver's MAC speed will be updated to A. step 2: enables auto-negotiation and MAC gets negotiated speed B, then the driver's MAC speed will be updated to B through querying in periodical task. step 3: MAC gets new negotiated speed A. step 4: disables auto-negotiation and sets speed to B before periodical task query new MAC speed A, the driver will ignore the speed configuration. This patch fixes it by skipping speed and duplex checking when fibre port supports auto-negotiation. Fixes: 22f48e24a23d ("net: hns3: add autoneg and change speed support for fibre port") Signed-off-by: Jian Shen Signed-off-by: Huazhong Tan Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 492bc9446463..acf0c29fcbcd 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -2446,10 +2446,12 @@ static int hclge_cfg_mac_speed_dup_hw(struct hclge_dev *hdev, int speed, int hclge_cfg_mac_speed_dup(struct hclge_dev *hdev, int speed, u8 duplex) { + struct hclge_mac *mac = &hdev->hw.mac; int ret; duplex = hclge_check_speed_dup(duplex, speed); - if (hdev->hw.mac.speed == speed && hdev->hw.mac.duplex == duplex) + if (!mac->support_autoneg && mac->speed == speed && + mac->duplex == duplex) return 0; ret = hclge_cfg_mac_speed_dup_hw(hdev, speed, duplex); From 3b4f06c715d0d3ecd6497275e3c85fe91462d0ee Mon Sep 17 00:00:00 2001 From: Tom Zhao Date: Thu, 5 Mar 2020 11:38:45 +0000 Subject: [PATCH 097/256] sfc: complete the next packet when we receive a timestamp We now ignore the "completion" event when using tx queue timestamping, and only pay attention to the two (high and low) timestamp events. The NIC will send a pair of timestamp events for every packet transmitted. The current firmware may merge the completion events, and it is possible that future versions may reorder the completion and timestamp events. As such the completion event is not useful. Without this patch in place a merged completion event on a queue with timestamping will cause a "spurious TX completion" error. This affects SFN8000-series adapters. Signed-off-by: Tom Zhao Acked-by: Martin Habets Signed-off-by: David S. Miller --- drivers/net/ethernet/sfc/ef10.c | 32 +++++++++++----------- drivers/net/ethernet/sfc/efx.h | 1 + drivers/net/ethernet/sfc/net_driver.h | 3 --- drivers/net/ethernet/sfc/tx.c | 38 +++++++++++++++++++++++++++ drivers/net/ethernet/sfc/tx_common.c | 29 +++++++++++--------- drivers/net/ethernet/sfc/tx_common.h | 6 +++++ 6 files changed, 78 insertions(+), 31 deletions(-) diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 52113b7529d6..3f16bd807c6e 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -2853,11 +2853,24 @@ efx_ef10_handle_tx_event(struct efx_channel *channel, efx_qword_t *event) } /* Transmit timestamps are only available for 8XXX series. They result - * in three events per packet. These occur in order, and are: - * - the normal completion event + * in up to three events per packet. These occur in order, and are: + * - the normal completion event (may be omitted) * - the low part of the timestamp * - the high part of the timestamp * + * It's possible for multiple completion events to appear before the + * corresponding timestamps. So we can for example get: + * COMP N + * COMP N+1 + * TS_LO N + * TS_HI N + * TS_LO N+1 + * TS_HI N+1 + * + * In addition it's also possible for the adjacent completions to be + * merged, so we may not see COMP N above. As such, the completion + * events are not very useful here. + * * Each part of the timestamp is itself split across two 16 bit * fields in the event. */ @@ -2865,17 +2878,7 @@ efx_ef10_handle_tx_event(struct efx_channel *channel, efx_qword_t *event) switch (tx_ev_type) { case TX_TIMESTAMP_EVENT_TX_EV_COMPLETION: - /* In case of Queue flush or FLR, we might have received - * the previous TX completion event but not the Timestamp - * events. - */ - if (tx_queue->completed_desc_ptr != tx_queue->ptr_mask) - efx_xmit_done(tx_queue, tx_queue->completed_desc_ptr); - - tx_ev_desc_ptr = EFX_QWORD_FIELD(*event, - ESF_DZ_TX_DESCR_INDX); - tx_queue->completed_desc_ptr = - tx_ev_desc_ptr & tx_queue->ptr_mask; + /* Ignore this event - see above. */ break; case TX_TIMESTAMP_EVENT_TX_EV_TSTAMP_LO: @@ -2887,8 +2890,7 @@ efx_ef10_handle_tx_event(struct efx_channel *channel, efx_qword_t *event) ts_part = efx_ef10_extract_event_ts(event); tx_queue->completed_timestamp_major = ts_part; - efx_xmit_done(tx_queue, tx_queue->completed_desc_ptr); - tx_queue->completed_desc_ptr = tx_queue->ptr_mask; + efx_xmit_done_single(tx_queue); break; default: diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h index f1bdb04efbe4..95395d67ea2d 100644 --- a/drivers/net/ethernet/sfc/efx.h +++ b/drivers/net/ethernet/sfc/efx.h @@ -20,6 +20,7 @@ netdev_tx_t efx_hard_start_xmit(struct sk_buff *skb, struct net_device *net_dev); netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb); void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index); +void efx_xmit_done_single(struct efx_tx_queue *tx_queue); int efx_setup_tc(struct net_device *net_dev, enum tc_setup_type type, void *type_data); extern unsigned int efx_piobuf_size; diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index 9f9886f222c8..8164f0edcbf0 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -208,8 +208,6 @@ struct efx_tx_buffer { * avoid cache-line ping-pong between the xmit path and the * completion path. * @merge_events: Number of TX merged completion events - * @completed_desc_ptr: Most recent completed pointer - only used with - * timestamping. * @completed_timestamp_major: Top part of the most recent tx timestamp. * @completed_timestamp_minor: Low part of the most recent tx timestamp. * @insert_count: Current insert pointer @@ -269,7 +267,6 @@ struct efx_tx_queue { unsigned int merge_events; unsigned int bytes_compl; unsigned int pkts_compl; - unsigned int completed_desc_ptr; u32 completed_timestamp_major; u32 completed_timestamp_minor; diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index 04d7f41d7ed9..8aafc54a4684 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -535,6 +535,44 @@ netdev_tx_t efx_hard_start_xmit(struct sk_buff *skb, return efx_enqueue_skb(tx_queue, skb); } +void efx_xmit_done_single(struct efx_tx_queue *tx_queue) +{ + unsigned int pkts_compl = 0, bytes_compl = 0; + unsigned int read_ptr; + bool finished = false; + + read_ptr = tx_queue->read_count & tx_queue->ptr_mask; + + while (!finished) { + struct efx_tx_buffer *buffer = &tx_queue->buffer[read_ptr]; + + if (!efx_tx_buffer_in_use(buffer)) { + struct efx_nic *efx = tx_queue->efx; + + netif_err(efx, hw, efx->net_dev, + "TX queue %d spurious single TX completion\n", + tx_queue->queue); + efx_schedule_reset(efx, RESET_TYPE_TX_SKIP); + return; + } + + /* Need to check the flag before dequeueing. */ + if (buffer->flags & EFX_TX_BUF_SKB) + finished = true; + efx_dequeue_buffer(tx_queue, buffer, &pkts_compl, &bytes_compl); + + ++tx_queue->read_count; + read_ptr = tx_queue->read_count & tx_queue->ptr_mask; + } + + tx_queue->pkts_compl += pkts_compl; + tx_queue->bytes_compl += bytes_compl; + + EFX_WARN_ON_PARANOID(pkts_compl != 1); + + efx_xmit_done_check_empty(tx_queue); +} + void efx_init_tx_queue_core_txq(struct efx_tx_queue *tx_queue) { struct efx_nic *efx = tx_queue->efx; diff --git a/drivers/net/ethernet/sfc/tx_common.c b/drivers/net/ethernet/sfc/tx_common.c index b1571e9789d0..70876df1da69 100644 --- a/drivers/net/ethernet/sfc/tx_common.c +++ b/drivers/net/ethernet/sfc/tx_common.c @@ -80,7 +80,6 @@ void efx_init_tx_queue(struct efx_tx_queue *tx_queue) tx_queue->xmit_more_available = false; tx_queue->timestamping = (efx_ptp_use_mac_tx_timestamps(efx) && tx_queue->channel == efx_ptp_channel(efx)); - tx_queue->completed_desc_ptr = tx_queue->ptr_mask; tx_queue->completed_timestamp_major = 0; tx_queue->completed_timestamp_minor = 0; @@ -210,10 +209,9 @@ static void efx_dequeue_buffers(struct efx_tx_queue *tx_queue, while (read_ptr != stop_index) { struct efx_tx_buffer *buffer = &tx_queue->buffer[read_ptr]; - if (!(buffer->flags & EFX_TX_BUF_OPTION) && - unlikely(buffer->len == 0)) { + if (!efx_tx_buffer_in_use(buffer)) { netif_err(efx, tx_err, efx->net_dev, - "TX queue %d spurious TX completion id %x\n", + "TX queue %d spurious TX completion id %d\n", tx_queue->queue, read_ptr); efx_schedule_reset(efx, RESET_TYPE_TX_SKIP); return; @@ -226,6 +224,19 @@ static void efx_dequeue_buffers(struct efx_tx_queue *tx_queue, } } +void efx_xmit_done_check_empty(struct efx_tx_queue *tx_queue) +{ + if ((int)(tx_queue->read_count - tx_queue->old_write_count) >= 0) { + tx_queue->old_write_count = READ_ONCE(tx_queue->write_count); + if (tx_queue->read_count == tx_queue->old_write_count) { + /* Ensure that read_count is flushed. */ + smp_mb(); + tx_queue->empty_read_count = + tx_queue->read_count | EFX_EMPTY_COUNT_VALID; + } + } +} + void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index) { unsigned int fill_level, pkts_compl = 0, bytes_compl = 0; @@ -256,15 +267,7 @@ void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index) netif_tx_wake_queue(tx_queue->core_txq); } - /* Check whether the hardware queue is now empty */ - if ((int)(tx_queue->read_count - tx_queue->old_write_count) >= 0) { - tx_queue->old_write_count = READ_ONCE(tx_queue->write_count); - if (tx_queue->read_count == tx_queue->old_write_count) { - smp_mb(); - tx_queue->empty_read_count = - tx_queue->read_count | EFX_EMPTY_COUNT_VALID; - } - } + efx_xmit_done_check_empty(tx_queue); } /* Remove buffers put into a tx_queue for the current packet. diff --git a/drivers/net/ethernet/sfc/tx_common.h b/drivers/net/ethernet/sfc/tx_common.h index f92f1fe3a87f..99cf7ce2f36c 100644 --- a/drivers/net/ethernet/sfc/tx_common.h +++ b/drivers/net/ethernet/sfc/tx_common.h @@ -21,6 +21,12 @@ void efx_dequeue_buffer(struct efx_tx_queue *tx_queue, unsigned int *pkts_compl, unsigned int *bytes_compl); +static inline bool efx_tx_buffer_in_use(struct efx_tx_buffer *buffer) +{ + return buffer->len || (buffer->flags & EFX_TX_BUF_OPTION); +} + +void efx_xmit_done_check_empty(struct efx_tx_queue *tx_queue); void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index); void efx_enqueue_unwind(struct efx_tx_queue *tx_queue, From e25d5dbcffae62c9a7fa03517dfa4b8e67670e3d Mon Sep 17 00:00:00 2001 From: Jiang Lidong Date: Wed, 4 Mar 2020 09:49:29 +0800 Subject: [PATCH 098/256] veth: ignore peer tx_dropped when counting local rx_dropped When local NET_RX backlog is full due to traffic overrun, peer veth tx_dropped counter increases. At that time, list local veth stats, rx_dropped has double value of peer tx_dropped, even bigger than transmit packets by peer. In NET_RX softirq process, if any packet drop case happens, it increases dev's rx_dropped counter and returns NET_RX_DROP. At veth tx side, it records any error returned from peer netif_rx into local dev tx_dropped counter. In veth get stats process, it puts local dev rx_dropped and peer dev tx_dropped into together as local rx_drpped value. So that it shows double value of real dropped packets number in this case. This patch ignores peer tx_dropped when counting local rx_dropped, since peer tx_dropped is duplicated to local rx_dropped at most cases. Signed-off-by: Jiang Lidong Signed-off-by: David S. Miller --- drivers/net/veth.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 8cdc4415fa70..d4cbb9e8c63f 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -328,7 +328,7 @@ static void veth_get_stats64(struct net_device *dev, rcu_read_lock(); peer = rcu_dereference(priv->peer); if (peer) { - tot->rx_dropped += veth_stats_tx(peer, &packets, &bytes); + veth_stats_tx(peer, &packets, &bytes); tot->rx_bytes += bytes; tot->rx_packets += packets; From 2fa7e15c5f466fdd0c0b196b1dc4a65d191efd96 Mon Sep 17 00:00:00 2001 From: Tina Zhang Date: Thu, 5 Mar 2020 21:15:59 +0800 Subject: [PATCH 099/256] drm/i915/gvt: Fix emulated vbt size issue The emulated vbt doesn't tell its size correctly. According to the intel_vbt_defs.h, vbt_header.vbt_size should the size of VBT (VBT Header, BDB Header and data blocks), and bdb_header.bdb_size should be the size of BDB (BDB Header and data blocks). This patch fixes the issue and lets vbt provided by GVT-g pass the guest i915's sanity test. v2: refine the commit message. (Zhenyu) Signed-off-by: Tina Zhang Reviewed-by: Zhenyu Wang Signed-off-by: Zhenyu Wang Link: http://patchwork.freedesktop.org/patch/msgid/20200305131600.29640-1-tina.zhang@intel.com --- drivers/gpu/drm/i915/gvt/opregion.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/gvt/opregion.c b/drivers/gpu/drm/i915/gvt/opregion.c index 867e7629025b..33569b910ed5 100644 --- a/drivers/gpu/drm/i915/gvt/opregion.c +++ b/drivers/gpu/drm/i915/gvt/opregion.c @@ -147,15 +147,14 @@ static void virt_vbt_generation(struct vbt *v) /* there's features depending on version! */ v->header.version = 155; v->header.header_size = sizeof(v->header); - v->header.vbt_size = sizeof(struct vbt) - sizeof(v->header); + v->header.vbt_size = sizeof(struct vbt); v->header.bdb_offset = offsetof(struct vbt, bdb_header); strcpy(&v->bdb_header.signature[0], "BIOS_DATA_BLOCK"); v->bdb_header.version = 186; /* child_dev_size = 33 */ v->bdb_header.header_size = sizeof(v->bdb_header); - v->bdb_header.bdb_size = sizeof(struct vbt) - sizeof(struct vbt_header) - - sizeof(struct bdb_header); + v->bdb_header.bdb_size = sizeof(struct vbt) - sizeof(struct vbt_header); /* general features */ v->general_features_header.id = BDB_GENERAL_FEATURES; From a3aefbfe45751bf7b338c181b97608e276b5bb73 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 4 Mar 2020 17:24:31 +0300 Subject: [PATCH 100/256] net: nfc: fix bounds checking bugs on "pipe" This is similar to commit 674d9de02aa7 ("NFC: Fix possible memory corruption when handling SHDLC I-Frame commands") and commit d7ee81ad09f0 ("NFC: nci: Add some bounds checking in nci_hci_cmd_received()") which added range checks on "pipe". The "pipe" variable comes skb->data[0] in nfc_hci_msg_rx_work(). It's in the 0-255 range. We're using it as the array index into the hdev->pipes[] array which has NFC_HCI_MAX_PIPES (128) members. Fixes: 118278f20aa8 ("NFC: hci: Add pipes table to reference them with a tuple {gate, host}") Signed-off-by: Dan Carpenter Signed-off-by: David S. Miller --- net/nfc/hci/core.c | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c index 6f1b096e601c..43811b5219b5 100644 --- a/net/nfc/hci/core.c +++ b/net/nfc/hci/core.c @@ -181,13 +181,20 @@ exit: void nfc_hci_cmd_received(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd, struct sk_buff *skb) { - u8 gate = hdev->pipes[pipe].gate; u8 status = NFC_HCI_ANY_OK; struct hci_create_pipe_resp *create_info; struct hci_delete_pipe_noti *delete_info; struct hci_all_pipe_cleared_noti *cleared_info; + u8 gate; - pr_debug("from gate %x pipe %x cmd %x\n", gate, pipe, cmd); + pr_debug("from pipe %x cmd %x\n", pipe, cmd); + + if (pipe >= NFC_HCI_MAX_PIPES) { + status = NFC_HCI_ANY_E_NOK; + goto exit; + } + + gate = hdev->pipes[pipe].gate; switch (cmd) { case NFC_HCI_ADM_NOTIFY_PIPE_CREATED: @@ -375,8 +382,14 @@ void nfc_hci_event_received(struct nfc_hci_dev *hdev, u8 pipe, u8 event, struct sk_buff *skb) { int r = 0; - u8 gate = hdev->pipes[pipe].gate; + u8 gate; + if (pipe >= NFC_HCI_MAX_PIPES) { + pr_err("Discarded event %x to invalid pipe %x\n", event, pipe); + goto exit; + } + + gate = hdev->pipes[pipe].gate; if (gate == NFC_HCI_INVALID_GATE) { pr_err("Discarded event %x to unopened pipe %x\n", event, pipe); goto exit; From 2398e3991bda7caa6b112a6f650fbab92f732b91 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 4 Mar 2020 16:51:07 +0100 Subject: [PATCH 101/256] mptcp: always include dack if possible. Currently passive MPTCP socket can skip including the DACK option - if the peer sends data before accept() completes. The above happens because the msk 'can_ack' flag is set only after the accept() call. Such missing DACK option may cause - as per RFC spec - unwanted fallback to TCP. This change addresses the issue using the key material available in the current subflow, if any, to create a suitable dack option when msk ack seq is not yet available. v1 -> v2: - adavance the generated ack after the initial MPC packet Fixes: d22f4988ffec ("mptcp: process MP_CAPABLE data option") Signed-off-by: Paolo Abeni Reviewed-by: Mat Martineau Signed-off-by: David S. Miller --- net/mptcp/options.c | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 45acd877bef3..fd2c3150e591 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -334,6 +334,8 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, struct mptcp_sock *msk; unsigned int ack_size; bool ret = false; + bool can_ack; + u64 ack_seq; u8 tcp_fin; if (skb) { @@ -360,9 +362,22 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, ret = true; } + /* passive sockets msk will set the 'can_ack' after accept(), even + * if the first subflow may have the already the remote key handy + */ + can_ack = true; opts->ext_copy.use_ack = 0; msk = mptcp_sk(subflow->conn); - if (!msk || !READ_ONCE(msk->can_ack)) { + if (likely(msk && READ_ONCE(msk->can_ack))) { + ack_seq = msk->ack_seq; + } else if (subflow->can_ack) { + mptcp_crypto_key_sha(subflow->remote_key, NULL, &ack_seq); + ack_seq++; + } else { + can_ack = false; + } + + if (unlikely(!can_ack)) { *size = ALIGN(dss_size, 4); return ret; } @@ -375,7 +390,7 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, dss_size += ack_size; - opts->ext_copy.data_ack = msk->ack_seq; + opts->ext_copy.data_ack = ack_seq; opts->ext_copy.ack64 = 1; opts->ext_copy.use_ack = 1; From 8019ad13ef7f64be44d4f892af9c840179009254 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 4 Mar 2020 11:28:31 +0100 Subject: [PATCH 102/256] futex: Fix inode life-time issue As reported by Jann, ihold() does not in fact guarantee inode persistence. And instead of making it so, replace the usage of inode pointers with a per boot, machine wide, unique inode identifier. This sequence number is global, but shared (file backed) futexes are rare enough that this should not become a performance issue. Reported-by: Jann Horn Suggested-by: Linus Torvalds Signed-off-by: Peter Zijlstra (Intel) --- fs/inode.c | 1 + include/linux/fs.h | 1 + include/linux/futex.h | 17 +++++---- kernel/futex.c | 89 ++++++++++++++++++++++++++----------------- 4 files changed, 65 insertions(+), 43 deletions(-) diff --git a/fs/inode.c b/fs/inode.c index 7d57068b6b7a..93d9252a00ab 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -138,6 +138,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode) inode->i_sb = sb; inode->i_blkbits = sb->s_blocksize_bits; inode->i_flags = 0; + atomic64_set(&inode->i_sequence, 0); atomic_set(&inode->i_count, 1); inode->i_op = &empty_iops; inode->i_fop = &no_open_fops; diff --git a/include/linux/fs.h b/include/linux/fs.h index 3cd4fe6b845e..abedbffe2c9e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -698,6 +698,7 @@ struct inode { struct rcu_head i_rcu; }; atomic64_t i_version; + atomic64_t i_sequence; /* see futex */ atomic_t i_count; atomic_t i_dio_count; atomic_t i_writecount; diff --git a/include/linux/futex.h b/include/linux/futex.h index 5cc3fed27d4c..b70df27d7e85 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -31,23 +31,26 @@ struct task_struct; union futex_key { struct { + u64 i_seq; unsigned long pgoff; - struct inode *inode; - int offset; + unsigned int offset; } shared; struct { + union { + struct mm_struct *mm; + u64 __tmp; + }; unsigned long address; - struct mm_struct *mm; - int offset; + unsigned int offset; } private; struct { + u64 ptr; unsigned long word; - void *ptr; - int offset; + unsigned int offset; } both; }; -#define FUTEX_KEY_INIT (union futex_key) { .both = { .ptr = NULL } } +#define FUTEX_KEY_INIT (union futex_key) { .both = { .ptr = 0ULL } } #ifdef CONFIG_FUTEX enum { diff --git a/kernel/futex.c b/kernel/futex.c index 0cf84c8664f2..e14f7cd45dbd 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -429,7 +429,7 @@ static void get_futex_key_refs(union futex_key *key) switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) { case FUT_OFF_INODE: - ihold(key->shared.inode); /* implies smp_mb(); (B) */ + smp_mb(); /* explicit smp_mb(); (B) */ break; case FUT_OFF_MMSHARED: futex_get_mm(key); /* implies smp_mb(); (B) */ @@ -463,7 +463,6 @@ static void drop_futex_key_refs(union futex_key *key) switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) { case FUT_OFF_INODE: - iput(key->shared.inode); break; case FUT_OFF_MMSHARED: mmdrop(key->private.mm); @@ -505,6 +504,46 @@ futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout, return timeout; } +/* + * Generate a machine wide unique identifier for this inode. + * + * This relies on u64 not wrapping in the life-time of the machine; which with + * 1ns resolution means almost 585 years. + * + * This further relies on the fact that a well formed program will not unmap + * the file while it has a (shared) futex waiting on it. This mapping will have + * a file reference which pins the mount and inode. + * + * If for some reason an inode gets evicted and read back in again, it will get + * a new sequence number and will _NOT_ match, even though it is the exact same + * file. + * + * It is important that match_futex() will never have a false-positive, esp. + * for PI futexes that can mess up the state. The above argues that false-negatives + * are only possible for malformed programs. + */ +static u64 get_inode_sequence_number(struct inode *inode) +{ + static atomic64_t i_seq; + u64 old; + + /* Does the inode already have a sequence number? */ + old = atomic64_read(&inode->i_sequence); + if (likely(old)) + return old; + + for (;;) { + u64 new = atomic64_add_return(1, &i_seq); + if (WARN_ON_ONCE(!new)) + continue; + + old = atomic64_cmpxchg_relaxed(&inode->i_sequence, 0, new); + if (old) + return old; + return new; + } +} + /** * get_futex_key() - Get parameters which are the keys for a futex * @uaddr: virtual address of the futex @@ -517,9 +556,15 @@ futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout, * * The key words are stored in @key on success. * - * For shared mappings, it's (page->index, file_inode(vma->vm_file), - * offset_within_page). For private mappings, it's (uaddr, current->mm). - * We can usually work out the index without swapping in the page. + * For shared mappings (when @fshared), the key is: + * ( inode->i_sequence, page->index, offset_within_page ) + * [ also see get_inode_sequence_number() ] + * + * For private mappings (or when !@fshared), the key is: + * ( current->mm, address, 0 ) + * + * This allows (cross process, where applicable) identification of the futex + * without keeping the page pinned for the duration of the FUTEX_WAIT. * * lock_page() might sleep, the caller should not hold a spinlock. */ @@ -659,8 +704,6 @@ again: key->private.mm = mm; key->private.address = address; - get_futex_key_refs(key); /* implies smp_mb(); (B) */ - } else { struct inode *inode; @@ -692,40 +735,14 @@ again: goto again; } - /* - * Take a reference unless it is about to be freed. Previously - * this reference was taken by ihold under the page lock - * pinning the inode in place so i_lock was unnecessary. The - * only way for this check to fail is if the inode was - * truncated in parallel which is almost certainly an - * application bug. In such a case, just retry. - * - * We are not calling into get_futex_key_refs() in file-backed - * cases, therefore a successful atomic_inc return below will - * guarantee that get_futex_key() will still imply smp_mb(); (B). - */ - if (!atomic_inc_not_zero(&inode->i_count)) { - rcu_read_unlock(); - put_page(page); - - goto again; - } - - /* Should be impossible but lets be paranoid for now */ - if (WARN_ON_ONCE(inode->i_mapping != mapping)) { - err = -EFAULT; - rcu_read_unlock(); - iput(inode); - - goto out; - } - key->both.offset |= FUT_OFF_INODE; /* inode-based key */ - key->shared.inode = inode; + key->shared.i_seq = get_inode_sequence_number(inode); key->shared.pgoff = basepage_index(tail); rcu_read_unlock(); } + get_futex_key_refs(key); /* implies smp_mb(); (B) */ + out: put_page(page); return err; From cfd3bc752a3f5529506d279deb42e3bc8055695b Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Sun, 23 Feb 2020 11:34:49 -0800 Subject: [PATCH 103/256] perf diff: Fix undefined string comparision spotted by clang's -Wstring-compare clang warns: util/block-info.c:298:18: error: result of comparison against a string literal is unspecified (use an explicit string comparison function instead) [-Werror,-Wstring-compare] if ((start_line != SRCLINE_UNKNOWN) && (end_line != SRCLINE_UNKNOWN)) { ^ ~~~~~~~~~~~~~~~ util/block-info.c:298:51: error: result of comparison against a string literal is unspecified (use an explicit string comparison function instead) [-Werror,-Wstring-compare] if ((start_line != SRCLINE_UNKNOWN) && (end_line != SRCLINE_UNKNOWN)) { ^ ~~~~~~~~~~~~~~~ util/block-info.c:298:18: error: result of comparison against a string literal is unspecified (use an explicit string comparison function instead) [-Werror,-Wstring-compare] if ((start_line != SRCLINE_UNKNOWN) && (end_line != SRCLINE_UNKNOWN)) { ^ ~~~~~~~~~~~~~~~ util/block-info.c:298:51: error: result of comparison against a string literal is unspecified (use an explicit string comparison function instead) [-Werror,-Wstring-compare] if ((start_line != SRCLINE_UNKNOWN) && (end_line != SRCLINE_UNKNOWN)) { ^ ~~~~~~~~~~~~~~~ util/map.c:434:15: error: result of comparison against a string literal is unspecified (use an explicit string comparison function instead) [-Werror,-Wstring-compare] if (srcline != SRCLINE_UNKNOWN) ^ ~~~~~~~~~~~~~~~ Reviewer Notes: Looks good to me. Some more context: https://clang.llvm.org/docs/DiagnosticsReference.html#wstring-compare The spec says: J.1 Unspecified behavior The following are unspecified: .. Whether two string literals result in distinct arrays (6.4.5). Signed-off-by: Nick Desaulniers Reviewed-by: Ian Rogers Cc: Alexander Shishkin Cc: Changbin Du Cc: Jin Yao Cc: Jiri Olsa Cc: John Keeping Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Song Liu Cc: clang-built-linux@googlegroups.com Link: https://github.com/ClangBuiltLinux/linux/issues/900 Link: http://lore.kernel.org/lkml/20200223193456.25291-1-nick.desaulniers@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-diff.c | 3 ++- tools/perf/util/block-info.c | 3 ++- tools/perf/util/map.c | 2 +- 3 files changed, 5 insertions(+), 3 deletions(-) diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index f8b6ae557d8b..c03c36fde7e2 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -1312,7 +1312,8 @@ static int cycles_printf(struct hist_entry *he, struct hist_entry *pair, end_line = map__srcline(he->ms.map, bi->sym->start + bi->end, he->ms.sym); - if ((start_line != SRCLINE_UNKNOWN) && (end_line != SRCLINE_UNKNOWN)) { + if ((strncmp(start_line, SRCLINE_UNKNOWN, strlen(SRCLINE_UNKNOWN)) != 0) && + (strncmp(end_line, SRCLINE_UNKNOWN, strlen(SRCLINE_UNKNOWN)) != 0)) { scnprintf(buf, sizeof(buf), "[%s -> %s] %4ld", start_line, end_line, block_he->diff.cycles); } else { diff --git a/tools/perf/util/block-info.c b/tools/perf/util/block-info.c index c4b030bf6ec2..fbbb6d640dad 100644 --- a/tools/perf/util/block-info.c +++ b/tools/perf/util/block-info.c @@ -295,7 +295,8 @@ static int block_range_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, end_line = map__srcline(he->ms.map, bi->sym->start + bi->end, he->ms.sym); - if ((start_line != SRCLINE_UNKNOWN) && (end_line != SRCLINE_UNKNOWN)) { + if ((strncmp(start_line, SRCLINE_UNKNOWN, strlen(SRCLINE_UNKNOWN)) != 0) && + (strncmp(end_line, SRCLINE_UNKNOWN, strlen(SRCLINE_UNKNOWN)) != 0)) { scnprintf(buf, sizeof(buf), "[%s -> %s]", start_line, end_line); } else { diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index a08ca276098e..95428511300d 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -431,7 +431,7 @@ int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix, if (map && map->dso) { char *srcline = map__srcline(map, addr, NULL); - if (srcline != SRCLINE_UNKNOWN) + if (strncmp(srcline, SRCLINE_UNKNOWN, strlen(SRCLINE_UNKNOWN)) != 0) ret = fprintf(fp, "%s%s", prefix, srcline); free_srcline(srcline); } From 29b4f5f188571c112713c35cc87eefb46efee612 Mon Sep 17 00:00:00 2001 From: Tommi Rantala Date: Thu, 5 Mar 2020 10:37:12 +0200 Subject: [PATCH 104/256] perf top: Fix stdio interface input handling with glibc 2.28+ Since glibc 2.28 when running 'perf top --stdio', input handling no longer works, but hitting any key always just prints the "Mapped keys" help text. To fix it, call clearerr() in the display_thread() loop to clear any EOF sticky errors, as instructed in the glibc NEWS file (https://sourceware.org/git/?p=glibc.git;a=blob;f=NEWS): * All stdio functions now treat end-of-file as a sticky condition. If you read from a file until EOF, and then the file is enlarged by another process, you must call clearerr or another function with the same effect (e.g. fseek, rewind) before you can read the additional data. This corrects a longstanding C99 conformance bug. It is most likely to affect programs that use stdio to read interactive input from a terminal. (Bug #1190.) Signed-off-by: Tommi Rantala Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20200305083714.9381-2-tommi.t.rantala@nokia.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-top.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index f6dd1a63f159..d2539b793f9d 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -684,7 +684,9 @@ repeat: delay_msecs = top->delay_secs * MSEC_PER_SEC; set_term_quiet_input(&save); /* trash return*/ - getc(stdin); + clearerr(stdin); + if (poll(&stdin_poll, 1, 0) > 0) + getc(stdin); while (!done) { perf_top__print_sym_table(top); From f649bd9dd5d5004543bbc3c50b829577b49f5d75 Mon Sep 17 00:00:00 2001 From: Tommi Rantala Date: Thu, 5 Mar 2020 10:37:13 +0200 Subject: [PATCH 105/256] perf bench futex-wake: Restore thread count default to online CPU count Since commit 3b2323c2c1c4 ("perf bench futex: Use cpumaps") the default number of threads the benchmark uses got changed from number of online CPUs to zero: $ perf bench futex wake # Running 'futex/wake' benchmark: Run summary [PID 15930]: blocking on 0 threads (at [private] futex 0x558b8ee4bfac), waking up 1 at a time. [Run 1]: Wokeup 0 of 0 threads in 0.0000 ms [...] [Run 10]: Wokeup 0 of 0 threads in 0.0000 ms Wokeup 0 of 0 threads in 0.0004 ms (+-40.82%) Restore the old behavior by grabbing the number of online CPUs via cpu->nr: $ perf bench futex wake # Running 'futex/wake' benchmark: Run summary [PID 18356]: blocking on 8 threads (at [private] futex 0xb3e62c), waking up 1 at a time. [Run 1]: Wokeup 8 of 8 threads in 0.0260 ms [...] [Run 10]: Wokeup 8 of 8 threads in 0.0270 ms Wokeup 8 of 8 threads in 0.0419 ms (+-24.35%) Fixes: 3b2323c2c1c4 ("perf bench futex: Use cpumaps") Signed-off-by: Tommi Rantala Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Darren Hart Cc: Davidlohr Bueso Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lore.kernel.org/lkml/20200305083714.9381-3-tommi.t.rantala@nokia.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/bench/futex-wake.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c index df810096abfe..58906e9499bb 100644 --- a/tools/perf/bench/futex-wake.c +++ b/tools/perf/bench/futex-wake.c @@ -43,7 +43,7 @@ static bool done = false, silent = false, fshared = false; static pthread_mutex_t thread_lock; static pthread_cond_t thread_parent, thread_worker; static struct stats waketime_stats, wakeup_stats; -static unsigned int ncpus, threads_starting, nthreads = 0; +static unsigned int threads_starting, nthreads = 0; static int futex_flag = 0; static const struct option options[] = { @@ -141,7 +141,7 @@ int bench_futex_wake(int argc, const char **argv) sigaction(SIGINT, &act, NULL); if (!nthreads) - nthreads = ncpus; + nthreads = cpu->nr; worker = calloc(nthreads, sizeof(*worker)); if (!worker) From 7b919a53102d81cd2e310b4941ac51c465d249ca Mon Sep 17 00:00:00 2001 From: Tommi Rantala Date: Thu, 5 Mar 2020 10:37:14 +0200 Subject: [PATCH 106/256] perf bench: Clear struct sigaction before sigaction() syscall Avoid garbage in sigaction structs used in sigaction() syscalls. Valgrind is complaining about it. Signed-off-by: Tommi Rantala Cc: Alexander Shishkin Cc: Changbin Du Cc: Darren Hart Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lore.kernel.org/lkml/20200305083714.9381-4-tommi.t.rantala@nokia.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/bench/epoll-ctl.c | 1 + tools/perf/bench/epoll-wait.c | 1 + tools/perf/bench/futex-hash.c | 1 + tools/perf/bench/futex-lock-pi.c | 1 + tools/perf/bench/futex-requeue.c | 1 + tools/perf/bench/futex-wake-parallel.c | 1 + tools/perf/bench/futex-wake.c | 1 + 7 files changed, 7 insertions(+) diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c index a7526c05df38..cadc18d42aa4 100644 --- a/tools/perf/bench/epoll-ctl.c +++ b/tools/perf/bench/epoll-ctl.c @@ -312,6 +312,7 @@ int bench_epoll_ctl(int argc, const char **argv) exit(EXIT_FAILURE); } + memset(&act, 0, sizeof(act)); sigfillset(&act.sa_mask); act.sa_sigaction = toggle_done; sigaction(SIGINT, &act, NULL); diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c index d1c5cb526b9f..f938c585d512 100644 --- a/tools/perf/bench/epoll-wait.c +++ b/tools/perf/bench/epoll-wait.c @@ -426,6 +426,7 @@ int bench_epoll_wait(int argc, const char **argv) exit(EXIT_FAILURE); } + memset(&act, 0, sizeof(act)); sigfillset(&act.sa_mask); act.sa_sigaction = toggle_done; sigaction(SIGINT, &act, NULL); diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c index 21776862e940..65eebe06c04d 100644 --- a/tools/perf/bench/futex-hash.c +++ b/tools/perf/bench/futex-hash.c @@ -137,6 +137,7 @@ int bench_futex_hash(int argc, const char **argv) if (!cpu) goto errmem; + memset(&act, 0, sizeof(act)); sigfillset(&act.sa_mask); act.sa_sigaction = toggle_done; sigaction(SIGINT, &act, NULL); diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c index 30d97121dc4f..89fd8f325f38 100644 --- a/tools/perf/bench/futex-lock-pi.c +++ b/tools/perf/bench/futex-lock-pi.c @@ -160,6 +160,7 @@ int bench_futex_lock_pi(int argc, const char **argv) if (!cpu) err(EXIT_FAILURE, "calloc"); + memset(&act, 0, sizeof(act)); sigfillset(&act.sa_mask); act.sa_sigaction = toggle_done; sigaction(SIGINT, &act, NULL); diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c index a00a6891447a..7a15c2e61022 100644 --- a/tools/perf/bench/futex-requeue.c +++ b/tools/perf/bench/futex-requeue.c @@ -128,6 +128,7 @@ int bench_futex_requeue(int argc, const char **argv) if (!cpu) err(EXIT_FAILURE, "cpu_map__new"); + memset(&act, 0, sizeof(act)); sigfillset(&act.sa_mask); act.sa_sigaction = toggle_done; sigaction(SIGINT, &act, NULL); diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c index a053cf2b7039..cd2b81a845ac 100644 --- a/tools/perf/bench/futex-wake-parallel.c +++ b/tools/perf/bench/futex-wake-parallel.c @@ -234,6 +234,7 @@ int bench_futex_wake_parallel(int argc, const char **argv) exit(EXIT_FAILURE); } + memset(&act, 0, sizeof(act)); sigfillset(&act.sa_mask); act.sa_sigaction = toggle_done; sigaction(SIGINT, &act, NULL); diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c index 58906e9499bb..2dfcef3e371e 100644 --- a/tools/perf/bench/futex-wake.c +++ b/tools/perf/bench/futex-wake.c @@ -136,6 +136,7 @@ int bench_futex_wake(int argc, const char **argv) if (!cpu) err(EXIT_FAILURE, "calloc"); + memset(&act, 0, sizeof(act)); sigfillset(&act.sa_mask); act.sa_sigaction = toggle_done; sigaction(SIGINT, &act, NULL); From 3f5777fbaf04c58d940526a22a2e0c813c837936 Mon Sep 17 00:00:00 2001 From: John Garry Date: Thu, 5 Mar 2020 19:08:01 +0800 Subject: [PATCH 107/256] perf jevents: Fix leak of mapfile memory The memory for global pointer is never freed during normal program execution, so let's do that in the main function exit as a good programming practice. A stray blank line is also removed. Reported-by: Jiri Olsa Signed-off-by: John Garry Cc: Alexander Shishkin Cc: Andi Kleen Cc: James Clark Cc: Joakim Zhang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Will Deacon Cc: linuxarm@huawei.com Link: http://lore.kernel.org/lkml/1583406486-154841-2-git-send-email-john.garry@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/jevents.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index 079c77b6a2fd..27b4da80f751 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -1082,10 +1082,9 @@ static int process_one_file(const char *fpath, const struct stat *sb, */ int main(int argc, char *argv[]) { - int rc; + int rc, ret = 0; int maxfds; char ldirname[PATH_MAX]; - const char *arch; const char *output_file; const char *start_dirname; @@ -1156,7 +1155,8 @@ int main(int argc, char *argv[]) /* Make build fail */ fclose(eventsfp); free_arch_std_events(); - return 1; + ret = 1; + goto out_free_mapfile; } else if (rc) { goto empty_map; } @@ -1174,14 +1174,17 @@ int main(int argc, char *argv[]) /* Make build fail */ fclose(eventsfp); free_arch_std_events(); - return 1; + ret = 1; } - return 0; + + goto out_free_mapfile; empty_map: fclose(eventsfp); create_empty_mapping(output_file); free_arch_std_events(); - return 0; +out_free_mapfile: + free(mapfile); + return ret; } From 441b62acd9c809e87bab45ad1d82b1b3b77cb4f0 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 5 Mar 2020 23:11:08 -0800 Subject: [PATCH 108/256] tools: Fix off-by 1 relative directory includes This is currently working due to extra include paths in the build. Committer testing: $ cd tools/include/uapi/asm/ Before this patch: $ ls -la ../../arch/x86/include/uapi/asm/errno.h ls: cannot access '../../arch/x86/include/uapi/asm/errno.h': No such file or directory $ After this patch; $ ls -la ../../../arch/x86/include/uapi/asm/errno.h -rw-rw-r--. 1 acme acme 31 Feb 20 12:42 ../../../arch/x86/include/uapi/asm/errno.h $ Check that that is still under tools/, i.e. hasn't escaped into the main kernel sources: $ cd ../../../arch/x86/include/uapi/asm/ $ pwd /home/acme/git/perf/tools/arch/x86/include/uapi/asm $ Signed-off-by: Ian Rogers Tested-by: Arnaldo Carvalho de Melo Acked-by: Jiri Olsa Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexios Zavras Cc: Andi Kleen Cc: Greg Kroah-Hartman Cc: Igor Lubashev Cc: Kan Liang Cc: Mark Rutland Cc: Mathieu Poirier Cc: Namhyung Kim Cc: Nick Desaulniers Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Wei Li Link: http://lore.kernel.org/lkml/20200306071110.130202-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/asm/errno.h | 14 +++++------ tools/perf/arch/arm64/util/arm-spe.c | 20 ++++++++-------- tools/perf/arch/arm64/util/perf_regs.c | 2 +- tools/perf/arch/powerpc/util/perf_regs.c | 4 ++-- tools/perf/arch/x86/util/auxtrace.c | 14 +++++------ tools/perf/arch/x86/util/event.c | 12 +++++----- tools/perf/arch/x86/util/header.c | 4 ++-- tools/perf/arch/x86/util/intel-bts.c | 24 +++++++++---------- tools/perf/arch/x86/util/intel-pt.c | 30 ++++++++++++------------ tools/perf/arch/x86/util/machine.c | 6 ++--- tools/perf/arch/x86/util/perf_regs.c | 8 +++---- tools/perf/arch/x86/util/pmu.c | 6 ++--- 12 files changed, 72 insertions(+), 72 deletions(-) diff --git a/tools/include/uapi/asm/errno.h b/tools/include/uapi/asm/errno.h index ce3c5945a1c4..637189ec1ab9 100644 --- a/tools/include/uapi/asm/errno.h +++ b/tools/include/uapi/asm/errno.h @@ -1,18 +1,18 @@ /* SPDX-License-Identifier: GPL-2.0 */ #if defined(__i386__) || defined(__x86_64__) -#include "../../arch/x86/include/uapi/asm/errno.h" +#include "../../../arch/x86/include/uapi/asm/errno.h" #elif defined(__powerpc__) -#include "../../arch/powerpc/include/uapi/asm/errno.h" +#include "../../../arch/powerpc/include/uapi/asm/errno.h" #elif defined(__sparc__) -#include "../../arch/sparc/include/uapi/asm/errno.h" +#include "../../../arch/sparc/include/uapi/asm/errno.h" #elif defined(__alpha__) -#include "../../arch/alpha/include/uapi/asm/errno.h" +#include "../../../arch/alpha/include/uapi/asm/errno.h" #elif defined(__mips__) -#include "../../arch/mips/include/uapi/asm/errno.h" +#include "../../../arch/mips/include/uapi/asm/errno.h" #elif defined(__ia64__) -#include "../../arch/ia64/include/uapi/asm/errno.h" +#include "../../../arch/ia64/include/uapi/asm/errno.h" #elif defined(__xtensa__) -#include "../../arch/xtensa/include/uapi/asm/errno.h" +#include "../../../arch/xtensa/include/uapi/asm/errno.h" #else #include #endif diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c index 8d6821d9c3f6..27653be24447 100644 --- a/tools/perf/arch/arm64/util/arm-spe.c +++ b/tools/perf/arch/arm64/util/arm-spe.c @@ -11,17 +11,17 @@ #include #include -#include "../../util/cpumap.h" -#include "../../util/event.h" -#include "../../util/evsel.h" -#include "../../util/evlist.h" -#include "../../util/session.h" +#include "../../../util/cpumap.h" +#include "../../../util/event.h" +#include "../../../util/evsel.h" +#include "../../../util/evlist.h" +#include "../../../util/session.h" #include // page_size -#include "../../util/pmu.h" -#include "../../util/debug.h" -#include "../../util/auxtrace.h" -#include "../../util/record.h" -#include "../../util/arm-spe.h" +#include "../../../util/pmu.h" +#include "../../../util/debug.h" +#include "../../../util/auxtrace.h" +#include "../../../util/record.h" +#include "../../../util/arm-spe.h" #define KiB(x) ((x) * 1024) #define MiB(x) ((x) * 1024 * 1024) diff --git a/tools/perf/arch/arm64/util/perf_regs.c b/tools/perf/arch/arm64/util/perf_regs.c index 2864e2e3776d..2833e101a7c6 100644 --- a/tools/perf/arch/arm64/util/perf_regs.c +++ b/tools/perf/arch/arm64/util/perf_regs.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -#include "../../util/perf_regs.h" +#include "../../../util/perf_regs.h" const struct sample_reg sample_reg_masks[] = { SMPL_REG_END diff --git a/tools/perf/arch/powerpc/util/perf_regs.c b/tools/perf/arch/powerpc/util/perf_regs.c index e9c436eeffc9..0a5242900248 100644 --- a/tools/perf/arch/powerpc/util/perf_regs.c +++ b/tools/perf/arch/powerpc/util/perf_regs.c @@ -4,8 +4,8 @@ #include #include -#include "../../util/perf_regs.h" -#include "../../util/debug.h" +#include "../../../util/perf_regs.h" +#include "../../../util/debug.h" #include diff --git a/tools/perf/arch/x86/util/auxtrace.c b/tools/perf/arch/x86/util/auxtrace.c index 7abc9fd4cbec..3da506e13f49 100644 --- a/tools/perf/arch/x86/util/auxtrace.c +++ b/tools/perf/arch/x86/util/auxtrace.c @@ -7,13 +7,13 @@ #include #include -#include "../../util/header.h" -#include "../../util/debug.h" -#include "../../util/pmu.h" -#include "../../util/auxtrace.h" -#include "../../util/intel-pt.h" -#include "../../util/intel-bts.h" -#include "../../util/evlist.h" +#include "../../../util/header.h" +#include "../../../util/debug.h" +#include "../../../util/pmu.h" +#include "../../../util/auxtrace.h" +#include "../../../util/intel-pt.h" +#include "../../../util/intel-bts.h" +#include "../../../util/evlist.h" static struct auxtrace_record *auxtrace_record__init_intel(struct evlist *evlist, diff --git a/tools/perf/arch/x86/util/event.c b/tools/perf/arch/x86/util/event.c index ac45015cc6ba..047dc00eafa6 100644 --- a/tools/perf/arch/x86/util/event.c +++ b/tools/perf/arch/x86/util/event.c @@ -3,12 +3,12 @@ #include #include -#include "../../util/event.h" -#include "../../util/synthetic-events.h" -#include "../../util/machine.h" -#include "../../util/tool.h" -#include "../../util/map.h" -#include "../../util/debug.h" +#include "../../../util/event.h" +#include "../../../util/synthetic-events.h" +#include "../../../util/machine.h" +#include "../../../util/tool.h" +#include "../../../util/map.h" +#include "../../../util/debug.h" #if defined(__x86_64__) diff --git a/tools/perf/arch/x86/util/header.c b/tools/perf/arch/x86/util/header.c index aa6deb463bf3..578c8c568ffd 100644 --- a/tools/perf/arch/x86/util/header.c +++ b/tools/perf/arch/x86/util/header.c @@ -7,8 +7,8 @@ #include #include -#include "../../util/debug.h" -#include "../../util/header.h" +#include "../../../util/debug.h" +#include "../../../util/header.h" static inline void cpuid(unsigned int op, unsigned int *a, unsigned int *b, unsigned int *c, diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c index 26cee1052179..09f93800bffd 100644 --- a/tools/perf/arch/x86/util/intel-bts.c +++ b/tools/perf/arch/x86/util/intel-bts.c @@ -11,18 +11,18 @@ #include #include -#include "../../util/cpumap.h" -#include "../../util/event.h" -#include "../../util/evsel.h" -#include "../../util/evlist.h" -#include "../../util/mmap.h" -#include "../../util/session.h" -#include "../../util/pmu.h" -#include "../../util/debug.h" -#include "../../util/record.h" -#include "../../util/tsc.h" -#include "../../util/auxtrace.h" -#include "../../util/intel-bts.h" +#include "../../../util/cpumap.h" +#include "../../../util/event.h" +#include "../../../util/evsel.h" +#include "../../../util/evlist.h" +#include "../../../util/mmap.h" +#include "../../../util/session.h" +#include "../../../util/pmu.h" +#include "../../../util/debug.h" +#include "../../../util/record.h" +#include "../../../util/tsc.h" +#include "../../../util/auxtrace.h" +#include "../../../util/intel-bts.h" #include // page_size #define KiB(x) ((x) * 1024) diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index 7eea4fd7ce58..1643aed8c4c8 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -13,23 +13,23 @@ #include #include -#include "../../util/session.h" -#include "../../util/event.h" -#include "../../util/evlist.h" -#include "../../util/evsel.h" -#include "../../util/evsel_config.h" -#include "../../util/cpumap.h" -#include "../../util/mmap.h" +#include "../../../util/session.h" +#include "../../../util/event.h" +#include "../../../util/evlist.h" +#include "../../../util/evsel.h" +#include "../../../util/evsel_config.h" +#include "../../../util/cpumap.h" +#include "../../../util/mmap.h" #include -#include "../../util/parse-events.h" -#include "../../util/pmu.h" -#include "../../util/debug.h" -#include "../../util/auxtrace.h" -#include "../../util/record.h" -#include "../../util/target.h" -#include "../../util/tsc.h" +#include "../../../util/parse-events.h" +#include "../../../util/pmu.h" +#include "../../../util/debug.h" +#include "../../../util/auxtrace.h" +#include "../../../util/record.h" +#include "../../../util/target.h" +#include "../../../util/tsc.h" #include // page_size -#include "../../util/intel-pt.h" +#include "../../../util/intel-pt.h" #define KiB(x) ((x) * 1024) #define MiB(x) ((x) * 1024 * 1024) diff --git a/tools/perf/arch/x86/util/machine.c b/tools/perf/arch/x86/util/machine.c index e17e080e76f4..31679c35d493 100644 --- a/tools/perf/arch/x86/util/machine.c +++ b/tools/perf/arch/x86/util/machine.c @@ -5,9 +5,9 @@ #include #include // page_size -#include "../../util/machine.h" -#include "../../util/map.h" -#include "../../util/symbol.h" +#include "../../../util/machine.h" +#include "../../../util/map.h" +#include "../../../util/symbol.h" #include #include diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c index c218b83e063b..fca81b39b09f 100644 --- a/tools/perf/arch/x86/util/perf_regs.c +++ b/tools/perf/arch/x86/util/perf_regs.c @@ -5,10 +5,10 @@ #include #include -#include "../../perf-sys.h" -#include "../../util/perf_regs.h" -#include "../../util/debug.h" -#include "../../util/event.h" +#include "../../../perf-sys.h" +#include "../../../util/perf_regs.h" +#include "../../../util/debug.h" +#include "../../../util/event.h" const struct sample_reg sample_reg_masks[] = { SMPL_REG(AX, PERF_REG_X86_AX), diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c index e33ef5bc31c5..d48d608517fd 100644 --- a/tools/perf/arch/x86/util/pmu.c +++ b/tools/perf/arch/x86/util/pmu.c @@ -4,9 +4,9 @@ #include #include -#include "../../util/intel-pt.h" -#include "../../util/intel-bts.h" -#include "../../util/pmu.h" +#include "../../../util/intel-pt.h" +#include "../../../util/intel-bts.h" +#include "../../../util/pmu.h" struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused) { From 6a42cefb25d8bdc1b391f4a53c78c32164eea2dd Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 6 Mar 2020 17:37:28 +0100 Subject: [PATCH 109/256] netfilter: nft_chain_nat: inet family is missing module ownership Set owner to THIS_MODULE, otherwise the nft_chain_nat module might be removed while there are still inet/nat chains in place. [ 117.942096] BUG: unable to handle page fault for address: ffffffffa0d5e040 [ 117.942101] #PF: supervisor read access in kernel mode [ 117.942103] #PF: error_code(0x0000) - not-present page [ 117.942106] PGD 200c067 P4D 200c067 PUD 200d063 PMD 3dc909067 PTE 0 [ 117.942113] Oops: 0000 [#1] PREEMPT SMP PTI [ 117.942118] CPU: 3 PID: 27 Comm: kworker/3:0 Not tainted 5.6.0-rc3+ #348 [ 117.942133] Workqueue: events nf_tables_trans_destroy_work [nf_tables] [ 117.942145] RIP: 0010:nf_tables_chain_destroy.isra.0+0x94/0x15a [nf_tables] [ 117.942149] Code: f6 45 54 01 0f 84 d1 00 00 00 80 3b 05 74 44 48 8b 75 e8 48 c7 c7 72 be de a0 e8 56 e6 2d e0 48 8b 45 e8 48 c7 c7 7f be de a0 <48> 8b 30 e8 43 e6 2d e0 48 8b 45 e8 48 8b 40 10 48 85 c0 74 5b 8b [ 117.942152] RSP: 0018:ffffc9000015be10 EFLAGS: 00010292 [ 117.942155] RAX: ffffffffa0d5e040 RBX: ffff88840be87fc2 RCX: 0000000000000007 [ 117.942158] RDX: 0000000000000007 RSI: 0000000000000086 RDI: ffffffffa0debe7f [ 117.942160] RBP: ffff888403b54b50 R08: 0000000000001482 R09: 0000000000000004 [ 117.942162] R10: 0000000000000000 R11: 0000000000000001 R12: ffff8883eda7e540 [ 117.942164] R13: dead000000000122 R14: dead000000000100 R15: ffff888403b3db80 [ 117.942167] FS: 0000000000000000(0000) GS:ffff88840e4c0000(0000) knlGS:0000000000000000 [ 117.942169] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 117.942172] CR2: ffffffffa0d5e040 CR3: 00000003e4c52002 CR4: 00000000001606e0 [ 117.942174] Call Trace: [ 117.942188] nf_tables_trans_destroy_work.cold+0xd/0x12 [nf_tables] [ 117.942196] process_one_work+0x1d6/0x3b0 [ 117.942200] worker_thread+0x45/0x3c0 [ 117.942203] ? process_one_work+0x3b0/0x3b0 [ 117.942210] kthread+0x112/0x130 [ 117.942214] ? kthread_create_worker_on_cpu+0x40/0x40 [ 117.942221] ret_from_fork+0x35/0x40 nf_tables_chain_destroy() crashes on module_put() because the module is gone. Fixes: d164385ec572 ("netfilter: nat: add inet family nat support") Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_chain_nat.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/netfilter/nft_chain_nat.c b/net/netfilter/nft_chain_nat.c index ff9ac8ae0031..eac4a901233f 100644 --- a/net/netfilter/nft_chain_nat.c +++ b/net/netfilter/nft_chain_nat.c @@ -89,6 +89,7 @@ static const struct nft_chain_type nft_chain_nat_inet = { .name = "nat", .type = NFT_CHAIN_T_NAT, .family = NFPROTO_INET, + .owner = THIS_MODULE, .hook_mask = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_LOCAL_OUT) | From 11a4a8f73b3ce71b32f36e9f1655f6ddf8f1732b Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Fri, 6 Mar 2020 21:50:00 +0100 Subject: [PATCH 110/256] clang-format: Update with the latest for_each macro list Re-run the shell fragment that generated the original list. Signed-off-by: Miguel Ojeda --- .clang-format | 25 +++++++++++++++++++++---- 1 file changed, 21 insertions(+), 4 deletions(-) diff --git a/.clang-format b/.clang-format index 196ca317bd1f..6ec5558b516b 100644 --- a/.clang-format +++ b/.clang-format @@ -86,6 +86,8 @@ ForEachMacros: - 'bio_for_each_segment_all' - 'bio_list_for_each' - 'bip_for_each_vec' + - 'bitmap_for_each_clear_region' + - 'bitmap_for_each_set_region' - 'blkg_for_each_descendant_post' - 'blkg_for_each_descendant_pre' - 'blk_queue_for_each_rl' @@ -115,6 +117,7 @@ ForEachMacros: - 'drm_client_for_each_connector_iter' - 'drm_client_for_each_modeset' - 'drm_connector_for_each_possible_encoder' + - 'drm_for_each_bridge_in_chain' - 'drm_for_each_connector_iter' - 'drm_for_each_crtc' - 'drm_for_each_encoder' @@ -136,9 +139,10 @@ ForEachMacros: - 'for_each_bio' - 'for_each_board_func_rsrc' - 'for_each_bvec' + - 'for_each_card_auxs' + - 'for_each_card_auxs_safe' - 'for_each_card_components' - - 'for_each_card_links' - - 'for_each_card_links_safe' + - 'for_each_card_pre_auxs' - 'for_each_card_prelinks' - 'for_each_card_rtds' - 'for_each_card_rtds_safe' @@ -166,6 +170,7 @@ ForEachMacros: - 'for_each_dpcm_fe' - 'for_each_drhd_unit' - 'for_each_dss_dev' + - 'for_each_efi_handle' - 'for_each_efi_memory_desc' - 'for_each_efi_memory_desc_in_map' - 'for_each_element' @@ -190,6 +195,7 @@ ForEachMacros: - 'for_each_lru' - 'for_each_matching_node' - 'for_each_matching_node_and_match' + - 'for_each_member' - 'for_each_memblock' - 'for_each_memblock_type' - 'for_each_memcg_cache_index' @@ -200,9 +206,11 @@ ForEachMacros: - 'for_each_msi_entry' - 'for_each_msi_entry_safe' - 'for_each_net' + - 'for_each_net_continue_reverse' - 'for_each_netdev' - 'for_each_netdev_continue' - 'for_each_netdev_continue_rcu' + - 'for_each_netdev_continue_reverse' - 'for_each_netdev_feature' - 'for_each_netdev_in_bond_rcu' - 'for_each_netdev_rcu' @@ -254,10 +262,10 @@ ForEachMacros: - 'for_each_reserved_mem_region' - 'for_each_rtd_codec_dai' - 'for_each_rtd_codec_dai_rollback' - - 'for_each_rtdcom' - - 'for_each_rtdcom_safe' + - 'for_each_rtd_components' - 'for_each_set_bit' - 'for_each_set_bit_from' + - 'for_each_set_clump8' - 'for_each_sg' - 'for_each_sg_dma_page' - 'for_each_sg_page' @@ -267,6 +275,7 @@ ForEachMacros: - 'for_each_subelement_id' - '__for_each_thread' - 'for_each_thread' + - 'for_each_wakeup_source' - 'for_each_zone' - 'for_each_zone_zonelist' - 'for_each_zone_zonelist_nodemask' @@ -330,6 +339,7 @@ ForEachMacros: - 'list_for_each' - 'list_for_each_codec' - 'list_for_each_codec_safe' + - 'list_for_each_continue' - 'list_for_each_entry' - 'list_for_each_entry_continue' - 'list_for_each_entry_continue_rcu' @@ -351,6 +361,7 @@ ForEachMacros: - 'llist_for_each_entry' - 'llist_for_each_entry_safe' - 'llist_for_each_safe' + - 'mci_for_each_dimm' - 'media_device_for_each_entity' - 'media_device_for_each_intf' - 'media_device_for_each_link' @@ -444,10 +455,16 @@ ForEachMacros: - 'virtio_device_for_each_vq' - 'xa_for_each' - 'xa_for_each_marked' + - 'xa_for_each_range' - 'xa_for_each_start' - 'xas_for_each' - 'xas_for_each_conflict' - 'xas_for_each_marked' + - 'xbc_array_for_each_value' + - 'xbc_for_each_key_value' + - 'xbc_node_for_each_array_value' + - 'xbc_node_for_each_child' + - 'xbc_node_for_each_key_value' - 'zorro_for_each_dev' #IncludeBlocks: Preserve # Unknown to clang-format-5.0 From d568bbd2f872cdd1b605d8e6b9b9c719a0ebd306 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 21 Nov 2019 04:20:41 +0100 Subject: [PATCH 111/256] auxdisplay: Fix Kconfig indentation Adjust indentation from spaces to tab (+optional two spaces) as in coding style with command like: $ sed -e 's/^ /\t/' -i */Kconfig Signed-off-by: Krzysztof Kozlowski Signed-off-by: Miguel Ojeda --- drivers/auxdisplay/Kconfig | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/auxdisplay/Kconfig b/drivers/auxdisplay/Kconfig index b8313a04422d..48efa7a047f3 100644 --- a/drivers/auxdisplay/Kconfig +++ b/drivers/auxdisplay/Kconfig @@ -111,7 +111,7 @@ config CFAG12864B If unsure, say N. config CFAG12864B_RATE - int "Refresh rate (hertz)" + int "Refresh rate (hertz)" depends on CFAG12864B default "20" ---help--- @@ -329,7 +329,7 @@ config PANEL_LCD_PROTO config PANEL_LCD_PIN_E depends on PANEL_PROFILE="0" && PANEL_LCD="1" && PANEL_LCD_PROTO="0" - int "Parallel port pin number & polarity connected to the LCD E signal (-17...17) " + int "Parallel port pin number & polarity connected to the LCD E signal (-17...17) " range -17 17 default 14 ---help--- @@ -344,7 +344,7 @@ config PANEL_LCD_PIN_E config PANEL_LCD_PIN_RS depends on PANEL_PROFILE="0" && PANEL_LCD="1" && PANEL_LCD_PROTO="0" - int "Parallel port pin number & polarity connected to the LCD RS signal (-17...17) " + int "Parallel port pin number & polarity connected to the LCD RS signal (-17...17) " range -17 17 default 17 ---help--- @@ -359,7 +359,7 @@ config PANEL_LCD_PIN_RS config PANEL_LCD_PIN_RW depends on PANEL_PROFILE="0" && PANEL_LCD="1" && PANEL_LCD_PROTO="0" - int "Parallel port pin number & polarity connected to the LCD RW signal (-17...17) " + int "Parallel port pin number & polarity connected to the LCD RW signal (-17...17) " range -17 17 default 16 ---help--- @@ -374,7 +374,7 @@ config PANEL_LCD_PIN_RW config PANEL_LCD_PIN_SCL depends on PANEL_PROFILE="0" && PANEL_LCD="1" && PANEL_LCD_PROTO!="0" - int "Parallel port pin number & polarity connected to the LCD SCL signal (-17...17) " + int "Parallel port pin number & polarity connected to the LCD SCL signal (-17...17) " range -17 17 default 1 ---help--- @@ -389,7 +389,7 @@ config PANEL_LCD_PIN_SCL config PANEL_LCD_PIN_SDA depends on PANEL_PROFILE="0" && PANEL_LCD="1" && PANEL_LCD_PROTO!="0" - int "Parallel port pin number & polarity connected to the LCD SDA signal (-17...17) " + int "Parallel port pin number & polarity connected to the LCD SDA signal (-17...17) " range -17 17 default 2 ---help--- @@ -404,12 +404,12 @@ config PANEL_LCD_PIN_SDA config PANEL_LCD_PIN_BL depends on PANEL_PROFILE="0" && PANEL_LCD="1" - int "Parallel port pin number & polarity connected to the LCD backlight signal (-17...17) " + int "Parallel port pin number & polarity connected to the LCD backlight signal (-17...17) " range -17 17 default 0 ---help--- This describes the number of the parallel port pin to which the LCD 'BL' signal - has been connected. It can be : + has been connected. It can be : 0 : no connection (eg: connected to ground) 1..17 : directly connected to any of these pins on the DB25 plug From e8897e4fe8f27d407b1e00ee0410fd3ec396275c Mon Sep 17 00:00:00 2001 From: Yangtao Li Date: Sun, 29 Dec 2019 07:04:19 +0000 Subject: [PATCH 112/256] auxdisplay: img-ascii-lcd: convert to devm_platform_ioremap_resource Use devm_platform_ioremap_resource() to simplify code. Signed-off-by: Yangtao Li Signed-off-by: Miguel Ojeda --- drivers/auxdisplay/img-ascii-lcd.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/auxdisplay/img-ascii-lcd.c b/drivers/auxdisplay/img-ascii-lcd.c index efb928e25aef..1cce409ce5ca 100644 --- a/drivers/auxdisplay/img-ascii-lcd.c +++ b/drivers/auxdisplay/img-ascii-lcd.c @@ -356,7 +356,6 @@ static int img_ascii_lcd_probe(struct platform_device *pdev) const struct of_device_id *match; const struct img_ascii_lcd_config *cfg; struct img_ascii_lcd_ctx *ctx; - struct resource *res; int err; match = of_match_device(img_ascii_lcd_matches, &pdev->dev); @@ -378,8 +377,7 @@ static int img_ascii_lcd_probe(struct platform_device *pdev) &ctx->offset)) return -EINVAL; } else { - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - ctx->base = devm_ioremap_resource(&pdev->dev, res); + ctx->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(ctx->base)) return PTR_ERR(ctx->base); } From 2f920c0f0e29268827c2894c6e8f237a78159718 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Wed, 12 Feb 2020 13:52:31 -0600 Subject: [PATCH 113/256] auxdisplay: charlcd: replace zero-length array with flexible-array member The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Signed-off-by: Miguel Ojeda --- drivers/auxdisplay/charlcd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/auxdisplay/charlcd.c b/drivers/auxdisplay/charlcd.c index 874c259a8829..c0da3820454b 100644 --- a/drivers/auxdisplay/charlcd.c +++ b/drivers/auxdisplay/charlcd.c @@ -88,7 +88,7 @@ struct charlcd_priv { int len; } esc_seq; - unsigned long long drvdata[0]; + unsigned long long drvdata[]; }; #define charlcd_to_priv(p) container_of(p, struct charlcd_priv, lcd) From 26d5bb9e4c4b541c475751e015072eb2cbf70d15 Mon Sep 17 00:00:00 2001 From: Madalin Bucur Date: Wed, 4 Mar 2020 18:04:25 +0200 Subject: [PATCH 114/256] dt-bindings: net: FMan erratum A050385 FMAN DMA read or writes under heavy traffic load may cause FMAN internal resource leak; thus stopping further packet processing. The FMAN internal queue can overflow when FMAN splits single read or write transactions into multiple smaller transactions such that more than 17 AXI transactions are in flight from FMAN to interconnect. When the FMAN internal queue overflows, it can stall further packet processing. The issue can occur with any one of the following three conditions: 1. FMAN AXI transaction crosses 4K address boundary (Errata A010022) 2. FMAN DMA address for an AXI transaction is not 16 byte aligned, i.e. the last 4 bits of an address are non-zero 3. Scatter Gather (SG) frames have more than one SG buffer in the SG list and any one of the buffers, except the last buffer in the SG list has data size that is not a multiple of 16 bytes, i.e., other than 16, 32, 48, 64, etc. With any one of the above three conditions present, there is likelihood of stalled FMAN packet processing, especially under stress with multiple ports injecting line-rate traffic. To avoid situations that stall FMAN packet processing, all of the above three conditions must be avoided; therefore, configure the system with the following rules: 1. Frame buffers must not span a 4KB address boundary, unless the frame start address is 256 byte aligned 2. All FMAN DMA start addresses (for example, BMAN buffer address, FD[address] + FD[offset]) are 16B aligned 3. SG table and buffer addresses are 16B aligned and the size of SG buffers are multiple of 16 bytes, except for the last SG buffer that can be of any size. Additional workaround notes: - Address alignment of 64 bytes is recommended for maximally efficient system bus transactions (although 16 byte alignment is sufficient to avoid the stall condition) - To support frame sizes that are larger than 4K bytes, there are two options: 1. Large single buffer frames that span a 4KB page boundary can be converted into SG frames to avoid transaction splits at the 4KB boundary, 2. Align the large single buffer to 256B address boundaries, ensure that the frame address plus offset is 256B aligned. - If software generated SG frames have buffers that are unaligned and with random non-multiple of 16 byte lengths, before transmitting such frames via FMAN, frames will need to be copied into a new single buffer or multiple buffer SG frame that is compliant with the three rules listed above. Signed-off-by: Madalin Bucur Signed-off-by: David S. Miller --- Documentation/devicetree/bindings/net/fsl-fman.txt | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/Documentation/devicetree/bindings/net/fsl-fman.txt b/Documentation/devicetree/bindings/net/fsl-fman.txt index 250f8d8cdce4..c00fb0d22c7b 100644 --- a/Documentation/devicetree/bindings/net/fsl-fman.txt +++ b/Documentation/devicetree/bindings/net/fsl-fman.txt @@ -110,6 +110,13 @@ PROPERTIES Usage: required Definition: See soc/fsl/qman.txt and soc/fsl/bman.txt +- fsl,erratum-a050385 + Usage: optional + Value type: boolean + Definition: A boolean property. Indicates the presence of the + erratum A050385 which indicates that DMA transactions that are + split can result in a FMan lock. + ============================================================================= FMan MURAM Node From b54d3900862374e1bb2846e6b39d79c896c0b200 Mon Sep 17 00:00:00 2001 From: Madalin Bucur Date: Wed, 4 Mar 2020 18:04:26 +0200 Subject: [PATCH 115/256] arm64: dts: ls1043a: FMan erratum A050385 The LS1043A SoC is affected by the A050385 erratum stating that FMAN DMA read or writes under heavy traffic load may cause FMAN internal resource leak thus stopping further packet processing. Signed-off-by: Madalin Bucur Signed-off-by: David S. Miller --- arch/arm64/boot/dts/freescale/fsl-ls1043-post.dtsi | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043-post.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1043-post.dtsi index 6082ae022136..d237162a8744 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1043-post.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1043-post.dtsi @@ -20,6 +20,8 @@ }; &fman0 { + fsl,erratum-a050385; + /* these aliases provide the FMan ports mapping */ enet0: ethernet@e0000 { }; From b281f7b93b258ce1419043bbd898a29254d5c9c7 Mon Sep 17 00:00:00 2001 From: Madalin Bucur Date: Wed, 4 Mar 2020 18:04:27 +0200 Subject: [PATCH 116/256] fsl/fman: detect FMan erratum A050385 Detect the presence of the A050385 erratum. Signed-off-by: Madalin Bucur Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/fman/Kconfig | 28 +++++++++++++++++++++ drivers/net/ethernet/freescale/fman/fman.c | 18 +++++++++++++ drivers/net/ethernet/freescale/fman/fman.h | 5 ++++ 3 files changed, 51 insertions(+) diff --git a/drivers/net/ethernet/freescale/fman/Kconfig b/drivers/net/ethernet/freescale/fman/Kconfig index 0139cb9042ec..34150182cc35 100644 --- a/drivers/net/ethernet/freescale/fman/Kconfig +++ b/drivers/net/ethernet/freescale/fman/Kconfig @@ -8,3 +8,31 @@ config FSL_FMAN help Freescale Data-Path Acceleration Architecture Frame Manager (FMan) support + +config DPAA_ERRATUM_A050385 + bool + depends on ARM64 && FSL_DPAA + default y + help + DPAA FMan erratum A050385 software workaround implementation: + align buffers, data start, SG fragment length to avoid FMan DMA + splits. + FMAN DMA read or writes under heavy traffic load may cause FMAN + internal resource leak thus stopping further packet processing. + The FMAN internal queue can overflow when FMAN splits single + read or write transactions into multiple smaller transactions + such that more than 17 AXI transactions are in flight from FMAN + to interconnect. When the FMAN internal queue overflows, it can + stall further packet processing. The issue can occur with any + one of the following three conditions: + 1. FMAN AXI transaction crosses 4K address boundary (Errata + A010022) + 2. FMAN DMA address for an AXI transaction is not 16 byte + aligned, i.e. the last 4 bits of an address are non-zero + 3. Scatter Gather (SG) frames have more than one SG buffer in + the SG list and any one of the buffers, except the last + buffer in the SG list has data size that is not a multiple + of 16 bytes, i.e., other than 16, 32, 48, 64, etc. + With any one of the above three conditions present, there is + likelihood of stalled FMAN packet processing, especially under + stress with multiple ports injecting line-rate traffic. diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c index 934111def0be..f151d6e111dd 100644 --- a/drivers/net/ethernet/freescale/fman/fman.c +++ b/drivers/net/ethernet/freescale/fman/fman.c @@ -1,5 +1,6 @@ /* * Copyright 2008-2015 Freescale Semiconductor Inc. + * Copyright 2020 NXP * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -566,6 +567,10 @@ struct fman_cfg { u32 qmi_def_tnums_thresh; }; +#ifdef CONFIG_DPAA_ERRATUM_A050385 +static bool fman_has_err_a050385; +#endif + static irqreturn_t fman_exceptions(struct fman *fman, enum fman_exceptions exception) { @@ -2518,6 +2523,14 @@ struct fman *fman_bind(struct device *fm_dev) } EXPORT_SYMBOL(fman_bind); +#ifdef CONFIG_DPAA_ERRATUM_A050385 +bool fman_has_errata_a050385(void) +{ + return fman_has_err_a050385; +} +EXPORT_SYMBOL(fman_has_errata_a050385); +#endif + static irqreturn_t fman_err_irq(int irq, void *handle) { struct fman *fman = (struct fman *)handle; @@ -2845,6 +2858,11 @@ static struct fman *read_dts_node(struct platform_device *of_dev) goto fman_free; } +#ifdef CONFIG_DPAA_ERRATUM_A050385 + fman_has_err_a050385 = + of_property_read_bool(fm_node, "fsl,erratum-a050385"); +#endif + return fman; fman_node_put: diff --git a/drivers/net/ethernet/freescale/fman/fman.h b/drivers/net/ethernet/freescale/fman/fman.h index 935c317fa696..f2ede1360f03 100644 --- a/drivers/net/ethernet/freescale/fman/fman.h +++ b/drivers/net/ethernet/freescale/fman/fman.h @@ -1,5 +1,6 @@ /* * Copyright 2008-2015 Freescale Semiconductor Inc. + * Copyright 2020 NXP * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -398,6 +399,10 @@ u16 fman_get_max_frm(void); int fman_get_rx_extra_headroom(void); +#ifdef CONFIG_DPAA_ERRATUM_A050385 +bool fman_has_errata_a050385(void); +#endif + struct fman *fman_bind(struct device *dev); #endif /* __FM_H */ From 3c68b8fffb48c0018c24e73c48f2bac768c6203e Mon Sep 17 00:00:00 2001 From: Madalin Bucur Date: Wed, 4 Mar 2020 18:04:28 +0200 Subject: [PATCH 117/256] dpaa_eth: FMan erratum A050385 workaround Align buffers, data start, SG fragment length to avoid DMA splits. These changes prevent the A050385 erratum to manifest itself: FMAN DMA read or writes under heavy traffic load may cause FMAN internal resource leak; thus stopping further packet processing. The FMAN internal queue can overflow when FMAN splits single read or write transactions into multiple smaller transactions such that more than 17 AXI transactions are in flight from FMAN to interconnect. When the FMAN internal queue overflows, it can stall further packet processing. The issue can occur with any one of the following three conditions: 1. FMAN AXI transaction crosses 4K address boundary (Errata A010022) 2. FMAN DMA address for an AXI transaction is not 16 byte aligned, i.e. the last 4 bits of an address are non-zero 3. Scatter Gather (SG) frames have more than one SG buffer in the SG list and any one of the buffers, except the last buffer in the SG list has data size that is not a multiple of 16 bytes, i.e., other than 16, 32, 48, 64, etc. With any one of the above three conditions present, there is likelihood of stalled FMAN packet processing, especially under stress with multiple ports injecting line-rate traffic. To avoid situations that stall FMAN packet processing, all of the above three conditions must be avoided; therefore, configure the system with the following rules: 1. Frame buffers must not span a 4KB address boundary, unless the frame start address is 256 byte aligned 2. All FMAN DMA start addresses (for example, BMAN buffer address, FD[address] + FD[offset]) are 16B aligned 3. SG table and buffer addresses are 16B aligned and the size of SG buffers are multiple of 16 bytes, except for the last SG buffer that can be of any size. Additional workaround notes: - Address alignment of 64 bytes is recommended for maximally efficient system bus transactions (although 16 byte alignment is sufficient to avoid the stall condition) - To support frame sizes that are larger than 4K bytes, there are two options: 1. Large single buffer frames that span a 4KB page boundary can be converted into SG frames to avoid transaction splits at the 4KB boundary, 2. Align the large single buffer to 256B address boundaries, ensure that the frame address plus offset is 256B aligned. - If software generated SG frames have buffers that are unaligned and with random non-multiple of 16 byte lengths, before transmitting such frames via FMAN, frames will need to be copied into a new single buffer or multiple buffer SG frame that is compliant with the three rules listed above. Signed-off-by: Madalin Bucur Signed-off-by: David S. Miller --- .../net/ethernet/freescale/dpaa/dpaa_eth.c | 110 +++++++++++++++++- 1 file changed, 107 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index fd93d542f497..e3ac9ec54c7c 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -1,4 +1,5 @@ /* Copyright 2008 - 2016 Freescale Semiconductor Inc. + * Copyright 2020 NXP * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -123,7 +124,22 @@ MODULE_PARM_DESC(tx_timeout, "The Tx timeout in ms"); #define FSL_QMAN_MAX_OAL 127 /* Default alignment for start of data in an Rx FD */ +#ifdef CONFIG_DPAA_ERRATUM_A050385 +/* aligning data start to 64 avoids DMA transaction splits, unless the buffer + * is crossing a 4k page boundary + */ +#define DPAA_FD_DATA_ALIGNMENT (fman_has_errata_a050385() ? 64 : 16) +/* aligning to 256 avoids DMA transaction splits caused by 4k page boundary + * crossings; also, all SG fragments except the last must have a size multiple + * of 256 to avoid DMA transaction splits + */ +#define DPAA_A050385_ALIGN 256 +#define DPAA_FD_RX_DATA_ALIGNMENT (fman_has_errata_a050385() ? \ + DPAA_A050385_ALIGN : 16) +#else #define DPAA_FD_DATA_ALIGNMENT 16 +#define DPAA_FD_RX_DATA_ALIGNMENT DPAA_FD_DATA_ALIGNMENT +#endif /* The DPAA requires 256 bytes reserved and mapped for the SGT */ #define DPAA_SGT_SIZE 256 @@ -158,8 +174,13 @@ MODULE_PARM_DESC(tx_timeout, "The Tx timeout in ms"); #define DPAA_PARSE_RESULTS_SIZE sizeof(struct fman_prs_result) #define DPAA_TIME_STAMP_SIZE 8 #define DPAA_HASH_RESULTS_SIZE 8 +#ifdef CONFIG_DPAA_ERRATUM_A050385 +#define DPAA_RX_PRIV_DATA_SIZE (DPAA_A050385_ALIGN - (DPAA_PARSE_RESULTS_SIZE\ + + DPAA_TIME_STAMP_SIZE + DPAA_HASH_RESULTS_SIZE)) +#else #define DPAA_RX_PRIV_DATA_SIZE (u16)(DPAA_TX_PRIV_DATA_SIZE + \ dpaa_rx_extra_headroom) +#endif #define DPAA_ETH_PCD_RXQ_NUM 128 @@ -180,7 +201,12 @@ static struct dpaa_bp *dpaa_bp_array[BM_MAX_NUM_OF_POOLS]; #define DPAA_BP_RAW_SIZE 4096 +#ifdef CONFIG_DPAA_ERRATUM_A050385 +#define dpaa_bp_size(raw_size) (SKB_WITH_OVERHEAD(raw_size) & \ + ~(DPAA_A050385_ALIGN - 1)) +#else #define dpaa_bp_size(raw_size) SKB_WITH_OVERHEAD(raw_size) +#endif static int dpaa_max_frm; @@ -1192,7 +1218,7 @@ static int dpaa_eth_init_rx_port(struct fman_port *port, struct dpaa_bp *bp, buf_prefix_content.pass_prs_result = true; buf_prefix_content.pass_hash_result = true; buf_prefix_content.pass_time_stamp = true; - buf_prefix_content.data_align = DPAA_FD_DATA_ALIGNMENT; + buf_prefix_content.data_align = DPAA_FD_RX_DATA_ALIGNMENT; rx_p = ¶ms.specific_params.rx_params; rx_p->err_fqid = errq->fqid; @@ -1662,6 +1688,8 @@ static u8 rx_csum_offload(const struct dpaa_priv *priv, const struct qm_fd *fd) return CHECKSUM_NONE; } +#define PTR_IS_ALIGNED(x, a) (IS_ALIGNED((unsigned long)(x), (a))) + /* Build a linear skb around the received buffer. * We are guaranteed there is enough room at the end of the data buffer to * accommodate the shared info area of the skb. @@ -1733,8 +1761,7 @@ static struct sk_buff *sg_fd_to_skb(const struct dpaa_priv *priv, sg_addr = qm_sg_addr(&sgt[i]); sg_vaddr = phys_to_virt(sg_addr); - WARN_ON(!IS_ALIGNED((unsigned long)sg_vaddr, - SMP_CACHE_BYTES)); + WARN_ON(!PTR_IS_ALIGNED(sg_vaddr, SMP_CACHE_BYTES)); dma_unmap_page(priv->rx_dma_dev, sg_addr, DPAA_BP_RAW_SIZE, DMA_FROM_DEVICE); @@ -2022,6 +2049,75 @@ static inline int dpaa_xmit(struct dpaa_priv *priv, return 0; } +#ifdef CONFIG_DPAA_ERRATUM_A050385 +int dpaa_a050385_wa(struct net_device *net_dev, struct sk_buff **s) +{ + struct dpaa_priv *priv = netdev_priv(net_dev); + struct sk_buff *new_skb, *skb = *s; + unsigned char *start, i; + + /* check linear buffer alignment */ + if (!PTR_IS_ALIGNED(skb->data, DPAA_A050385_ALIGN)) + goto workaround; + + /* linear buffers just need to have an aligned start */ + if (!skb_is_nonlinear(skb)) + return 0; + + /* linear data size for nonlinear skbs needs to be aligned */ + if (!IS_ALIGNED(skb_headlen(skb), DPAA_A050385_ALIGN)) + goto workaround; + + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + + /* all fragments need to have aligned start addresses */ + if (!IS_ALIGNED(skb_frag_off(frag), DPAA_A050385_ALIGN)) + goto workaround; + + /* all but last fragment need to have aligned sizes */ + if (!IS_ALIGNED(skb_frag_size(frag), DPAA_A050385_ALIGN) && + (i < skb_shinfo(skb)->nr_frags - 1)) + goto workaround; + } + + return 0; + +workaround: + /* copy all the skb content into a new linear buffer */ + new_skb = netdev_alloc_skb(net_dev, skb->len + DPAA_A050385_ALIGN - 1 + + priv->tx_headroom); + if (!new_skb) + return -ENOMEM; + + /* NET_SKB_PAD bytes already reserved, adding up to tx_headroom */ + skb_reserve(new_skb, priv->tx_headroom - NET_SKB_PAD); + + /* Workaround for DPAA_A050385 requires data start to be aligned */ + start = PTR_ALIGN(new_skb->data, DPAA_A050385_ALIGN); + if (start - new_skb->data != 0) + skb_reserve(new_skb, start - new_skb->data); + + skb_put(new_skb, skb->len); + skb_copy_bits(skb, 0, new_skb->data, skb->len); + skb_copy_header(new_skb, skb); + new_skb->dev = skb->dev; + + /* We move the headroom when we align it so we have to reset the + * network and transport header offsets relative to the new data + * pointer. The checksum offload relies on these offsets. + */ + skb_set_network_header(new_skb, skb_network_offset(skb)); + skb_set_transport_header(new_skb, skb_transport_offset(skb)); + + /* TODO: does timestamping need the result in the old skb? */ + dev_kfree_skb(skb); + *s = new_skb; + + return 0; +} +#endif + static netdev_tx_t dpaa_start_xmit(struct sk_buff *skb, struct net_device *net_dev) { @@ -2068,6 +2164,14 @@ dpaa_start_xmit(struct sk_buff *skb, struct net_device *net_dev) nonlinear = skb_is_nonlinear(skb); } +#ifdef CONFIG_DPAA_ERRATUM_A050385 + if (unlikely(fman_has_errata_a050385())) { + if (dpaa_a050385_wa(net_dev, &skb)) + goto enomem; + nonlinear = skb_is_nonlinear(skb); + } +#endif + if (nonlinear) { /* Just create a S/G fd based on the skb */ err = skb_to_sg_fd(priv, skb, &fd); From b7469e83d2add567e4e0b063963db185f3167cea Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 4 Mar 2020 09:32:16 -0800 Subject: [PATCH 118/256] bonding/alb: make sure arp header is pulled before accessing it Similar to commit 38f88c454042 ("bonding/alb: properly access headers in bond_alb_xmit()"), we need to make sure arp header was pulled in skb->head before blindly accessing it in rlb_arp_xmit(). Remove arp_pkt() private helper, since it is more readable/obvious to have the following construct back to back : if (!pskb_network_may_pull(skb, sizeof(*arp))) return NULL; arp = (struct arp_pkt *)skb_network_header(skb); syzbot reported : BUG: KMSAN: uninit-value in bond_slave_has_mac_rx include/net/bonding.h:704 [inline] BUG: KMSAN: uninit-value in rlb_arp_xmit drivers/net/bonding/bond_alb.c:662 [inline] BUG: KMSAN: uninit-value in bond_alb_xmit+0x575/0x25e0 drivers/net/bonding/bond_alb.c:1477 CPU: 0 PID: 12743 Comm: syz-executor.4 Not tainted 5.6.0-rc2-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x1c9/0x220 lib/dump_stack.c:118 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:118 __msan_warning+0x58/0xa0 mm/kmsan/kmsan_instr.c:215 bond_slave_has_mac_rx include/net/bonding.h:704 [inline] rlb_arp_xmit drivers/net/bonding/bond_alb.c:662 [inline] bond_alb_xmit+0x575/0x25e0 drivers/net/bonding/bond_alb.c:1477 __bond_start_xmit drivers/net/bonding/bond_main.c:4257 [inline] bond_start_xmit+0x85d/0x2f70 drivers/net/bonding/bond_main.c:4282 __netdev_start_xmit include/linux/netdevice.h:4524 [inline] netdev_start_xmit include/linux/netdevice.h:4538 [inline] xmit_one net/core/dev.c:3470 [inline] dev_hard_start_xmit+0x531/0xab0 net/core/dev.c:3486 __dev_queue_xmit+0x37de/0x4220 net/core/dev.c:4063 dev_queue_xmit+0x4b/0x60 net/core/dev.c:4096 packet_snd net/packet/af_packet.c:2967 [inline] packet_sendmsg+0x8347/0x93b0 net/packet/af_packet.c:2992 sock_sendmsg_nosec net/socket.c:652 [inline] sock_sendmsg net/socket.c:672 [inline] __sys_sendto+0xc1b/0xc50 net/socket.c:1998 __do_sys_sendto net/socket.c:2010 [inline] __se_sys_sendto+0x107/0x130 net/socket.c:2006 __x64_sys_sendto+0x6e/0x90 net/socket.c:2006 do_syscall_64+0xb8/0x160 arch/x86/entry/common.c:296 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x45c479 Code: ad b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007fc77ffbbc78 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 00007fc77ffbc6d4 RCX: 000000000045c479 RDX: 000000000000000e RSI: 00000000200004c0 RDI: 0000000000000003 RBP: 000000000076bf20 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff R13: 0000000000000a04 R14: 00000000004cc7b0 R15: 000000000076bf2c Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:144 [inline] kmsan_internal_poison_shadow+0x66/0xd0 mm/kmsan/kmsan.c:127 kmsan_slab_alloc+0x8a/0xe0 mm/kmsan/kmsan_hooks.c:82 slab_alloc_node mm/slub.c:2793 [inline] __kmalloc_node_track_caller+0xb40/0x1200 mm/slub.c:4401 __kmalloc_reserve net/core/skbuff.c:142 [inline] __alloc_skb+0x2fd/0xac0 net/core/skbuff.c:210 alloc_skb include/linux/skbuff.h:1051 [inline] alloc_skb_with_frags+0x18c/0xa70 net/core/skbuff.c:5766 sock_alloc_send_pskb+0xada/0xc60 net/core/sock.c:2242 packet_alloc_skb net/packet/af_packet.c:2815 [inline] packet_snd net/packet/af_packet.c:2910 [inline] packet_sendmsg+0x66a0/0x93b0 net/packet/af_packet.c:2992 sock_sendmsg_nosec net/socket.c:652 [inline] sock_sendmsg net/socket.c:672 [inline] __sys_sendto+0xc1b/0xc50 net/socket.c:1998 __do_sys_sendto net/socket.c:2010 [inline] __se_sys_sendto+0x107/0x130 net/socket.c:2006 __x64_sys_sendto+0x6e/0x90 net/socket.c:2006 do_syscall_64+0xb8/0x160 arch/x86/entry/common.c:296 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Reported-by: syzbot Cc: Jay Vosburgh Cc: Veaceslav Falico Cc: Andy Gospodarek Signed-off-by: David S. Miller --- drivers/net/bonding/bond_alb.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 1cc2cd894f87..c81698550e5a 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -50,11 +50,6 @@ struct arp_pkt { }; #pragma pack() -static inline struct arp_pkt *arp_pkt(const struct sk_buff *skb) -{ - return (struct arp_pkt *)skb_network_header(skb); -} - /* Forward declaration */ static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[], bool strict_match); @@ -553,10 +548,11 @@ static void rlb_req_update_subnet_clients(struct bonding *bond, __be32 src_ip) spin_unlock(&bond->mode_lock); } -static struct slave *rlb_choose_channel(struct sk_buff *skb, struct bonding *bond) +static struct slave *rlb_choose_channel(struct sk_buff *skb, + struct bonding *bond, + const struct arp_pkt *arp) { struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); - struct arp_pkt *arp = arp_pkt(skb); struct slave *assigned_slave, *curr_active_slave; struct rlb_client_info *client_info; u32 hash_index = 0; @@ -653,8 +649,12 @@ static struct slave *rlb_choose_channel(struct sk_buff *skb, struct bonding *bon */ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond) { - struct arp_pkt *arp = arp_pkt(skb); struct slave *tx_slave = NULL; + struct arp_pkt *arp; + + if (!pskb_network_may_pull(skb, sizeof(*arp))) + return NULL; + arp = (struct arp_pkt *)skb_network_header(skb); /* Don't modify or load balance ARPs that do not originate locally * (e.g.,arrive via a bridge). @@ -664,7 +664,7 @@ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond) if (arp->op_code == htons(ARPOP_REPLY)) { /* the arp must be sent on the selected rx channel */ - tx_slave = rlb_choose_channel(skb, bond); + tx_slave = rlb_choose_channel(skb, bond, arp); if (tx_slave) bond_hw_addr_copy(arp->mac_src, tx_slave->dev->dev_addr, tx_slave->dev->addr_len); @@ -676,7 +676,7 @@ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond) * When the arp reply is received the entry will be updated * with the correct unicast address of the client. */ - tx_slave = rlb_choose_channel(skb, bond); + tx_slave = rlb_choose_channel(skb, bond, arp); /* The ARP reply packets must be delayed so that * they can cancel out the influence of the ARP request. From e396ce5f4229388db5143fec0ec36af504bff12e Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Wed, 4 Mar 2020 09:42:10 -0800 Subject: [PATCH 119/256] ionic: fix vf op lock usage These are a couple of read locks that should be write locks. Fixes: fbb39807e9ae ("ionic: support sr-iov operations") Signed-off-by: Shannon Nelson Reviewed-by: Parav Pandit Signed-off-by: David S. Miller --- drivers/net/ethernet/pensando/ionic/ionic_lif.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 191271f6260d..c2f5b691e0fa 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -1688,7 +1688,7 @@ static int ionic_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) if (!(is_zero_ether_addr(mac) || is_valid_ether_addr(mac))) return -EINVAL; - down_read(&ionic->vf_op_lock); + down_write(&ionic->vf_op_lock); if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) { ret = -EINVAL; @@ -1698,7 +1698,7 @@ static int ionic_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) ether_addr_copy(ionic->vfs[vf].macaddr, mac); } - up_read(&ionic->vf_op_lock); + up_write(&ionic->vf_op_lock); return ret; } @@ -1719,7 +1719,7 @@ static int ionic_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, if (proto != htons(ETH_P_8021Q)) return -EPROTONOSUPPORT; - down_read(&ionic->vf_op_lock); + down_write(&ionic->vf_op_lock); if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) { ret = -EINVAL; @@ -1730,7 +1730,7 @@ static int ionic_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, ionic->vfs[vf].vlanid = vlan; } - up_read(&ionic->vf_op_lock); + up_write(&ionic->vf_op_lock); return ret; } From 03138e2bf78b2e219b5f15b9bbd84e2d457e3b73 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 4 Mar 2020 10:17:53 -0800 Subject: [PATCH 120/256] MAINTAINERS: remove bouncing pkaustub@cisco.com from enic pkaustub@cisco.com is bouncing, remove it. Signed-off-by: Jakub Kicinski Acked-by: Christian Benvenuti Signed-off-by: David S. Miller --- MAINTAINERS | 1 - 1 file changed, 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 8f27f40d22bb..b1935c2ae118 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4073,7 +4073,6 @@ F: drivers/scsi/snic/ CISCO VIC ETHERNET NIC DRIVER M: Christian Benvenuti M: Govindarajulu Varadarajan <_govind@gmx.com> -M: Parvi Kaustubhi S: Supported F: drivers/net/ethernet/cisco/enic/ From aeaa925bff844d225f259215a250d2811e436499 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jonathan=20Neusch=C3=A4fer?= Date: Thu, 5 Mar 2020 17:05:16 +0100 Subject: [PATCH 121/256] rhashtable: Document the right function parameters MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit rhashtable_lookup_get_insert_key doesn't have a parameter `data`. It does have a parameter `key`, however. Signed-off-by: Jonathan Neuschäfer Acked-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index beb9a9da1699..70ebef866cc8 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -972,9 +972,9 @@ static inline int rhashtable_lookup_insert_key( /** * rhashtable_lookup_get_insert_key - lookup and insert object into hash table * @ht: hash table + * @key: key * @obj: pointer to hash head inside object * @params: hash table parameters - * @data: pointer to element data already in hashes * * Just like rhashtable_lookup_insert_key(), but this function returns the * object if it exists, NULL if it does not and the insertion was successful, From e8d87a0b822d4b3d9a94a5da915f93aa1b674c93 Mon Sep 17 00:00:00 2001 From: "H. Nikolaus Schaller" Date: Fri, 6 Mar 2020 18:27:58 +0100 Subject: [PATCH 122/256] MIPS: DTS: CI20: fix PMU definitions for ACT8600 There is a ACT8600 on the CI20 board and the bindings of the ACT8865 driver have changed without updating the CI20 device tree. Therefore the PMU can not be probed successfully and is running in power-on reset state. Fix DT to match the latest act8865-regulator bindings. Fixes: 73f2b940474d ("MIPS: CI20: DTS: Add I2C nodes") Cc: stable@vger.kernel.org Signed-off-by: H. Nikolaus Schaller Reviewed-by: Paul Cercueil Signed-off-by: Thomas Bogendoerfer --- arch/mips/boot/dts/ingenic/ci20.dts | 39 ++++++++++++++++++----------- 1 file changed, 24 insertions(+), 15 deletions(-) diff --git a/arch/mips/boot/dts/ingenic/ci20.dts b/arch/mips/boot/dts/ingenic/ci20.dts index 37b93166bf22..8b5fb635c66f 100644 --- a/arch/mips/boot/dts/ingenic/ci20.dts +++ b/arch/mips/boot/dts/ingenic/ci20.dts @@ -4,6 +4,7 @@ #include "jz4780.dtsi" #include #include +#include / { compatible = "img,ci20", "ingenic,jz4780"; @@ -163,63 +164,71 @@ regulators { vddcore: SUDCDC1 { - regulator-name = "VDDCORE"; + regulator-name = "DCDC_REG1"; regulator-min-microvolt = <1100000>; regulator-max-microvolt = <1100000>; regulator-always-on; }; vddmem: SUDCDC2 { - regulator-name = "VDDMEM"; + regulator-name = "DCDC_REG2"; regulator-min-microvolt = <1500000>; regulator-max-microvolt = <1500000>; regulator-always-on; }; vcc_33: SUDCDC3 { - regulator-name = "VCC33"; + regulator-name = "DCDC_REG3"; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; regulator-always-on; }; vcc_50: SUDCDC4 { - regulator-name = "VCC50"; + regulator-name = "SUDCDC_REG4"; regulator-min-microvolt = <5000000>; regulator-max-microvolt = <5000000>; regulator-always-on; }; vcc_25: LDO_REG5 { - regulator-name = "VCC25"; + regulator-name = "LDO_REG5"; regulator-min-microvolt = <2500000>; regulator-max-microvolt = <2500000>; regulator-always-on; }; wifi_io: LDO_REG6 { - regulator-name = "WIFIIO"; + regulator-name = "LDO_REG6"; regulator-min-microvolt = <2500000>; regulator-max-microvolt = <2500000>; regulator-always-on; }; vcc_28: LDO_REG7 { - regulator-name = "VCC28"; + regulator-name = "LDO_REG7"; regulator-min-microvolt = <2800000>; regulator-max-microvolt = <2800000>; regulator-always-on; }; vcc_15: LDO_REG8 { - regulator-name = "VCC15"; + regulator-name = "LDO_REG8"; regulator-min-microvolt = <1500000>; regulator-max-microvolt = <1500000>; regulator-always-on; }; - vcc_18: LDO_REG9 { - regulator-name = "VCC18"; - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <1800000>; + vrtc_18: LDO_REG9 { + regulator-name = "LDO_REG9"; + /* Despite the datasheet stating 3.3V + * for REG9 and the driver expecting that, + * REG9 outputs 1.8V. + * Likely the CI20 uses a proprietary + * factory programmed chip variant. + * Since this is a simple on/off LDO the + * exact values do not matter. + */ + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; regulator-always-on; }; vcc_11: LDO_REG10 { - regulator-name = "VCC11"; - regulator-min-microvolt = <1100000>; - regulator-max-microvolt = <1100000>; + regulator-name = "LDO_REG10"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; regulator-always-on; }; }; From 130ab8819d81bd96f1a71e8461a8f73edf1fbe82 Mon Sep 17 00:00:00 2001 From: "H. Nikolaus Schaller" Date: Fri, 6 Mar 2020 18:28:30 +0100 Subject: [PATCH 123/256] MIPS: DTS: CI20: fix interrupt for pcf8563 RTC Interrupts should not be specified by interrupt line but by gpio parent and reference. Fixes: 73f2b940474d ("MIPS: CI20: DTS: Add I2C nodes") Cc: stable@vger.kernel.org Signed-off-by: H. Nikolaus Schaller Reviewed-by: Paul Cercueil Signed-off-by: Thomas Bogendoerfer --- arch/mips/boot/dts/ingenic/ci20.dts | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/mips/boot/dts/ingenic/ci20.dts b/arch/mips/boot/dts/ingenic/ci20.dts index 8b5fb635c66f..c340f947baa0 100644 --- a/arch/mips/boot/dts/ingenic/ci20.dts +++ b/arch/mips/boot/dts/ingenic/ci20.dts @@ -4,6 +4,7 @@ #include "jz4780.dtsi" #include #include +#include #include / { @@ -270,7 +271,9 @@ rtc@51 { compatible = "nxp,pcf8563"; reg = <0x51>; - interrupts = <110>; + + interrupt-parent = <&gpf>; + interrupts = <30 IRQ_TYPE_LEVEL_LOW>; }; }; From 2b4eae95c7361e0a147b838715c8baa1380a428f Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Thu, 5 Mar 2020 00:41:38 -0800 Subject: [PATCH 124/256] fscrypt: don't evict dirty inodes after removing key After FS_IOC_REMOVE_ENCRYPTION_KEY removes a key, it syncs the filesystem and tries to get and put all inodes that were unlocked by the key so that unused inodes get evicted via fscrypt_drop_inode(). Normally, the inodes are all clean due to the sync. However, after the filesystem is sync'ed, userspace can modify and close one of the files. (Userspace is *supposed* to close the files before removing the key. But it doesn't always happen, and the kernel can't assume it.) This causes the inode to be dirtied and have i_count == 0. Then, fscrypt_drop_inode() failed to consider this case and indicated that the inode can be dropped, causing the write to be lost. On f2fs, other problems such as a filesystem freeze could occur due to the inode being freed while still on f2fs's dirty inode list. Fix this bug by making fscrypt_drop_inode() only drop clean inodes. I've written an xfstest which detects this bug on ext4, f2fs, and ubifs. Fixes: b1c0ec3599f4 ("fscrypt: add FS_IOC_REMOVE_ENCRYPTION_KEY ioctl") Cc: # v5.4+ Link: https://lore.kernel.org/r/20200305084138.653498-1-ebiggers@kernel.org Signed-off-by: Eric Biggers --- fs/crypto/keysetup.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c index 65cb09fa6ead..08c9f216a54d 100644 --- a/fs/crypto/keysetup.c +++ b/fs/crypto/keysetup.c @@ -538,6 +538,15 @@ int fscrypt_drop_inode(struct inode *inode) return 0; mk = ci->ci_master_key->payload.data[0]; + /* + * With proper, non-racy use of FS_IOC_REMOVE_ENCRYPTION_KEY, all inodes + * protected by the key were cleaned by sync_filesystem(). But if + * userspace is still using the files, inodes can be dirtied between + * then and now. We mustn't lose any writes, so skip dirty inodes here. + */ + if (inode->i_state & I_DIRTY_ALL) + return 0; + /* * Note: since we aren't holding ->mk_secret_sem, the result here can * immediately become outdated. But there's no correctness problem with From 286d3250c9d6437340203fb64938bea344729a0e Mon Sep 17 00:00:00 2001 From: Vladis Dronov Date: Sun, 8 Mar 2020 09:08:54 +0100 Subject: [PATCH 125/256] efi: Fix a race and a buffer overflow while reading efivars via sysfs There is a race and a buffer overflow corrupting a kernel memory while reading an EFI variable with a size more than 1024 bytes via the older sysfs method. This happens because accessing struct efi_variable in efivar_{attr,size,data}_read() and friends is not protected from a concurrent access leading to a kernel memory corruption and, at best, to a crash. The race scenario is the following: CPU0: CPU1: efivar_attr_read() var->DataSize = 1024; efivar_entry_get(... &var->DataSize) down_interruptible(&efivars_lock) efivar_attr_read() // same EFI var var->DataSize = 1024; efivar_entry_get(... &var->DataSize) down_interruptible(&efivars_lock) virt_efi_get_variable() // returns EFI_BUFFER_TOO_SMALL but // var->DataSize is set to a real // var size more than 1024 bytes up(&efivars_lock) virt_efi_get_variable() // called with var->DataSize set // to a real var size, returns // successfully and overwrites // a 1024-bytes kernel buffer up(&efivars_lock) This can be reproduced by concurrent reading of an EFI variable which size is more than 1024 bytes: ts# for cpu in $(seq 0 $(nproc --ignore=1)); do ( taskset -c $cpu \ cat /sys/firmware/efi/vars/KEKDefault*/size & ) ; done Fix this by using a local variable for a var's data buffer size so it does not get overwritten. Fixes: e14ab23dde12b80d ("efivars: efivar_entry API") Reported-by: Bob Sanders and the LTP testsuite Signed-off-by: Vladis Dronov Signed-off-by: Ard Biesheuvel Signed-off-by: Ingo Molnar Cc: Link: https://lore.kernel.org/r/20200305084041.24053-2-vdronov@redhat.com Link: https://lore.kernel.org/r/20200308080859.21568-24-ardb@kernel.org --- drivers/firmware/efi/efivars.c | 29 ++++++++++++++++++++--------- 1 file changed, 20 insertions(+), 9 deletions(-) diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c index 7576450c8254..69f13bc4b931 100644 --- a/drivers/firmware/efi/efivars.c +++ b/drivers/firmware/efi/efivars.c @@ -83,13 +83,16 @@ static ssize_t efivar_attr_read(struct efivar_entry *entry, char *buf) { struct efi_variable *var = &entry->var; + unsigned long size = sizeof(var->Data); char *str = buf; + int ret; if (!entry || !buf) return -EINVAL; - var->DataSize = 1024; - if (efivar_entry_get(entry, &var->Attributes, &var->DataSize, var->Data)) + ret = efivar_entry_get(entry, &var->Attributes, &size, var->Data); + var->DataSize = size; + if (ret) return -EIO; if (var->Attributes & EFI_VARIABLE_NON_VOLATILE) @@ -116,13 +119,16 @@ static ssize_t efivar_size_read(struct efivar_entry *entry, char *buf) { struct efi_variable *var = &entry->var; + unsigned long size = sizeof(var->Data); char *str = buf; + int ret; if (!entry || !buf) return -EINVAL; - var->DataSize = 1024; - if (efivar_entry_get(entry, &var->Attributes, &var->DataSize, var->Data)) + ret = efivar_entry_get(entry, &var->Attributes, &size, var->Data); + var->DataSize = size; + if (ret) return -EIO; str += sprintf(str, "0x%lx\n", var->DataSize); @@ -133,12 +139,15 @@ static ssize_t efivar_data_read(struct efivar_entry *entry, char *buf) { struct efi_variable *var = &entry->var; + unsigned long size = sizeof(var->Data); + int ret; if (!entry || !buf) return -EINVAL; - var->DataSize = 1024; - if (efivar_entry_get(entry, &var->Attributes, &var->DataSize, var->Data)) + ret = efivar_entry_get(entry, &var->Attributes, &size, var->Data); + var->DataSize = size; + if (ret) return -EIO; memcpy(buf, var->Data, var->DataSize); @@ -250,14 +259,16 @@ efivar_show_raw(struct efivar_entry *entry, char *buf) { struct efi_variable *var = &entry->var; struct compat_efi_variable *compat; + unsigned long datasize = sizeof(var->Data); size_t size; + int ret; if (!entry || !buf) return 0; - var->DataSize = 1024; - if (efivar_entry_get(entry, &entry->var.Attributes, - &entry->var.DataSize, entry->var.Data)) + ret = efivar_entry_get(entry, &var->Attributes, &datasize, var->Data); + var->DataSize = datasize; + if (ret) return -EIO; if (in_compat_syscall()) { From d6c066fda90d578aacdf19771a027ed484a79825 Mon Sep 17 00:00:00 2001 From: Vladis Dronov Date: Sun, 8 Mar 2020 09:08:55 +0100 Subject: [PATCH 126/256] efi: Add a sanity check to efivar_store_raw() Add a sanity check to efivar_store_raw() the same way efivar_{attr,size,data}_read() and efivar_show_raw() have it. Signed-off-by: Vladis Dronov Signed-off-by: Ard Biesheuvel Signed-off-by: Ingo Molnar Cc: Link: https://lore.kernel.org/r/20200305084041.24053-3-vdronov@redhat.com Link: https://lore.kernel.org/r/20200308080859.21568-25-ardb@kernel.org --- drivers/firmware/efi/efivars.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c index 69f13bc4b931..aff3dfb4d7ba 100644 --- a/drivers/firmware/efi/efivars.c +++ b/drivers/firmware/efi/efivars.c @@ -208,6 +208,9 @@ efivar_store_raw(struct efivar_entry *entry, const char *buf, size_t count) u8 *data; int err; + if (!entry || !buf) + return -EINVAL; + if (in_compat_syscall()) { struct compat_efi_variable *compat; From f13f09a12cbd0c7b776e083c5d008b6c6a9c4e0b Mon Sep 17 00:00:00 2001 From: Suman Anna Date: Mon, 24 Feb 2020 15:26:43 -0600 Subject: [PATCH 127/256] virtio_ring: Fix mem leak with vring_new_virtqueue() The functions vring_new_virtqueue() and __vring_new_virtqueue() are used with split rings, and any allocations within these functions are managed outside of the .we_own_ring flag. The commit cbeedb72b97a ("virtio_ring: allocate desc state for split ring separately") allocates the desc state within the __vring_new_virtqueue() but frees it only when the .we_own_ring flag is set. This leads to a memory leak when freeing such allocated virtqueues with the vring_del_virtqueue() function. Fix this by moving the desc_state free code outside the flag and only for split rings. Issue was discovered during testing with remoteproc and virtio_rpmsg. Fixes: cbeedb72b97a ("virtio_ring: allocate desc state for split ring separately") Signed-off-by: Suman Anna Link: https://lore.kernel.org/r/20200224212643.30672-1-s-anna@ti.com Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- drivers/virtio/virtio_ring.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 867c7ebd3f10..58b96baa8d48 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -2203,10 +2203,10 @@ void vring_del_virtqueue(struct virtqueue *_vq) vq->split.queue_size_in_bytes, vq->split.vring.desc, vq->split.queue_dma_addr); - - kfree(vq->split.desc_state); } } + if (!vq->packed_ring) + kfree(vq->split.desc_state); list_del(&_vq->list); kfree(vq); } From f5f6b95c72f7f8bb46eace8c5306c752d0133daa Mon Sep 17 00:00:00 2001 From: Halil Pasic Date: Thu, 13 Feb 2020 13:37:27 +0100 Subject: [PATCH 128/256] virtio-blk: fix hw_queue stopped on arbitrary error Since nobody else is going to restart our hw_queue for us, the blk_mq_start_stopped_hw_queues() is in virtblk_done() is not sufficient necessarily sufficient to ensure that the queue will get started again. In case of global resource outage (-ENOMEM because mapping failure, because of swiotlb full) our virtqueue may be empty and we can get stuck with a stopped hw_queue. Let us not stop the queue on arbitrary errors, but only on -EONSPC which indicates a full virtqueue, where the hw_queue is guaranteed to get started by virtblk_done() before when it makes sense to carry on submitting requests. Let us also remove a stale comment. Signed-off-by: Halil Pasic Cc: Jens Axboe Fixes: f7728002c1c7 ("virtio_ring: fix return code on DMA mapping fails") Link: https://lore.kernel.org/r/20200213123728.61216-2-pasic@linux.ibm.com Signed-off-by: Michael S. Tsirkin Reviewed-by: Stefan Hajnoczi --- drivers/block/virtio_blk.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 54158766334b..adfe43f5ffe4 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -245,10 +245,12 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx, err = virtblk_add_req(vblk->vqs[qid].vq, vbr, vbr->sg, num); if (err) { virtqueue_kick(vblk->vqs[qid].vq); - blk_mq_stop_hw_queue(hctx); + /* Don't stop the queue if -ENOMEM: we may have failed to + * bounce the buffer due to global resource outage. + */ + if (err == -ENOSPC) + blk_mq_stop_hw_queue(hctx); spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags); - /* Out of mem doesn't actually happen, since we fall back - * to direct descriptors */ if (err == -ENOMEM || err == -ENOSPC) return BLK_STS_DEV_RESOURCE; return BLK_STS_IOERR; From 3d973b2e9a625996ee997c7303cd793b9d197c65 Mon Sep 17 00:00:00 2001 From: Halil Pasic Date: Thu, 13 Feb 2020 13:37:28 +0100 Subject: [PATCH 129/256] virtio-blk: improve virtqueue error to BLK_STS Let's change the mapping between virtqueue_add errors to BLK_STS statuses, so that -ENOSPC, which indicates virtqueue full is still mapped to BLK_STS_DEV_RESOURCE, but -ENOMEM which indicates non-device specific resource outage is mapped to BLK_STS_RESOURCE. Signed-off-by: Halil Pasic Link: https://lore.kernel.org/r/20200213123728.61216-3-pasic@linux.ibm.com Signed-off-by: Michael S. Tsirkin Reviewed-by: Stefan Hajnoczi --- drivers/block/virtio_blk.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index adfe43f5ffe4..0736248999b0 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -251,9 +251,14 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx, if (err == -ENOSPC) blk_mq_stop_hw_queue(hctx); spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags); - if (err == -ENOMEM || err == -ENOSPC) + switch (err) { + case -ENOSPC: return BLK_STS_DEV_RESOURCE; - return BLK_STS_IOERR; + case -ENOMEM: + return BLK_STS_RESOURCE; + default: + return BLK_STS_IOERR; + } } if (bd->last && virtqueue_kick_prepare(vblk->vqs[qid].vq)) From 6ae4edab2fbf86ec92fbf0a8f0c60b857d90d50f Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Sat, 15 Feb 2020 17:40:39 -0700 Subject: [PATCH 130/256] virtio_balloon: Adjust label in virtballoon_probe Clang warns when CONFIG_BALLOON_COMPACTION is unset: ../drivers/virtio/virtio_balloon.c:963:1: warning: unused label 'out_del_vqs' [-Wunused-label] out_del_vqs: ^~~~~~~~~~~~ 1 warning generated. Move the label within the preprocessor block since it is only used when CONFIG_BALLOON_COMPACTION is set. Fixes: 1ad6f58ea936 ("virtio_balloon: Fix memory leaks on errors in virtballoon_probe()") Link: https://github.com/ClangBuiltLinux/linux/issues/886 Signed-off-by: Nathan Chancellor Link: https://lore.kernel.org/r/20200216004039.23464-1-natechancellor@gmail.com Signed-off-by: Michael S. Tsirkin Reviewed-by: David Hildenbrand --- drivers/virtio/virtio_balloon.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 7bfe365d9372..341458fd95ca 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -959,8 +959,8 @@ out_iput: iput(vb->vb_dev_info.inode); out_kern_unmount: kern_unmount(balloon_mnt); -#endif out_del_vqs: +#endif vdev->config->del_vqs(vdev); out_free_vb: kfree(vb); From b26ebfe12f34f372cf041c6f801fa49c3fb382c5 Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Fri, 6 Mar 2020 11:23:14 -0600 Subject: [PATCH 131/256] pid: Fix error return value in some cases Recent changes to alloc_pid() allow the pid number to be specified on the command line. If set_tid_size is set, then the code scanning the levels will hard-set retval to -EPERM, overriding it's previous -ENOMEM value. After the code scanning the levels, there are error returns that do not set retval, assuming it is still set to -ENOMEM. So set retval back to -ENOMEM after scanning the levels. Fixes: 49cb2fc42ce4 ("fork: extend clone3() to support setting a PID") Signed-off-by: Corey Minyard Acked-by: Christian Brauner Cc: Andrei Vagin Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Oleg Nesterov Cc: Adrian Reber Cc: # 5.5 Link: https://lore.kernel.org/r/20200306172314.12232-1-minyard@acm.org [christian.brauner@ubuntu.com: fixup commit message] Signed-off-by: Christian Brauner --- kernel/pid.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/pid.c b/kernel/pid.c index 0f4ecb57214c..19645b25b77c 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -247,6 +247,8 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid, tmp = tmp->parent; } + retval = -ENOMEM; + if (unlikely(is_child_reaper(pid))) { if (pid_ns_prepare_proc(ns)) goto out_free; From 805b13adde3964c78cba125a15527e88c19f87b3 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 8 Mar 2020 20:07:28 -0600 Subject: [PATCH 132/256] io_uring: ensure RCU callback ordering with rcu_barrier() After more careful studying, Paul informs me that we cannot rely on ordering of RCU callbacks in the way that the the tagged commit did. The current construct looks like this: void C(struct rcu_head *rhp) { do_something(rhp); call_rcu(&p->rh, B); } call_rcu(&p->rh, A); call_rcu(&p->rh, C); and we're relying on ordering between A and B, which isn't guaranteed. Make this explicit instead, and have a work item issue the rcu_barrier() to ensure that A has run before we manually execute B. While thorough testing never showed this issue, it's dependent on the per-cpu load in terms of RCU callbacks. The updated method simplifies the code as well, and eliminates the need to maintain an rcu_head in the fileset data. Fixes: c1e2148f8ecb ("io_uring: free fixed_file_data after RCU grace period") Reported-by: Paul E. McKenney Signed-off-by: Jens Axboe --- fs/io_uring.c | 31 ++++++++++++++----------------- 1 file changed, 14 insertions(+), 17 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index c06082bb039a..1b2517291b78 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -191,7 +191,6 @@ struct fixed_file_data { struct llist_head put_llist; struct work_struct ref_work; struct completion done; - struct rcu_head rcu; }; struct io_ring_ctx { @@ -5331,26 +5330,23 @@ static void io_file_ref_kill(struct percpu_ref *ref) complete(&data->done); } -static void __io_file_ref_exit_and_free(struct rcu_head *rcu) +static void io_file_ref_exit_and_free(struct work_struct *work) { - struct fixed_file_data *data = container_of(rcu, struct fixed_file_data, - rcu); + struct fixed_file_data *data; + + data = container_of(work, struct fixed_file_data, ref_work); + + /* + * Ensure any percpu-ref atomic switch callback has run, it could have + * been in progress when the files were being unregistered. Once + * that's done, we can safely exit and free the ref and containing + * data structure. + */ + rcu_barrier(); percpu_ref_exit(&data->refs); kfree(data); } -static void io_file_ref_exit_and_free(struct rcu_head *rcu) -{ - /* - * We need to order our exit+free call against the potentially - * existing call_rcu() for switching to atomic. One way to do that - * is to have this rcu callback queue the final put and free, as we - * could otherwise have a pre-existing atomic switch complete _after_ - * the free callback we queued. - */ - call_rcu(rcu, __io_file_ref_exit_and_free); -} - static int io_sqe_files_unregister(struct io_ring_ctx *ctx) { struct fixed_file_data *data = ctx->file_data; @@ -5369,7 +5365,8 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx) for (i = 0; i < nr_tables; i++) kfree(data->table[i].files); kfree(data->table); - call_rcu(&data->rcu, io_file_ref_exit_and_free); + INIT_WORK(&data->ref_work, io_file_ref_exit_and_free); + queue_work(system_wq, &data->ref_work); ctx->file_data = NULL; ctx->nr_user_files = 0; return 0; From 63aae7b17344d4b08a7d05cb07044de4c0f9dcc6 Mon Sep 17 00:00:00 2001 From: Jiri Wiesner Date: Sat, 7 Mar 2020 13:31:57 +0100 Subject: [PATCH 133/256] ipvlan: do not add hardware address of master to its unicast filter list There is a problem when ipvlan slaves are created on a master device that is a vmxnet3 device (ipvlan in VMware guests). The vmxnet3 driver does not support unicast address filtering. When an ipvlan device is brought up in ipvlan_open(), the ipvlan driver calls dev_uc_add() to add the hardware address of the vmxnet3 master device to the unicast address list of the master device, phy_dev->uc. This inevitably leads to the vmxnet3 master device being forced into promiscuous mode by __dev_set_rx_mode(). Promiscuous mode is switched on the master despite the fact that there is still only one hardware address that the master device should use for filtering in order for the ipvlan device to be able to receive packets. The comment above struct net_device describes the uc_promisc member as a "counter, that indicates, that promiscuous mode has been enabled due to the need to listen to additional unicast addresses in a device that does not implement ndo_set_rx_mode()". Moreover, the design of ipvlan guarantees that only the hardware address of a master device, phy_dev->dev_addr, will be used to transmit and receive all packets from its ipvlan slaves. Thus, the unicast address list of the master device should not be modified by ipvlan_open() and ipvlan_stop() in order to make ipvlan a workable option on masters that do not support unicast address filtering. Fixes: 2ad7bf3638411 ("ipvlan: Initial check-in of the IPVLAN driver") Reported-by: Per Sundstrom Signed-off-by: Jiri Wiesner Reviewed-by: Eric Dumazet Acked-by: Mahesh Bandewar Signed-off-by: David S. Miller --- drivers/net/ipvlan/ipvlan_main.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index a70662261a5a..f195f278a83a 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -164,7 +164,6 @@ static void ipvlan_uninit(struct net_device *dev) static int ipvlan_open(struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); - struct net_device *phy_dev = ipvlan->phy_dev; struct ipvl_addr *addr; if (ipvlan->port->mode == IPVLAN_MODE_L3 || @@ -178,7 +177,7 @@ static int ipvlan_open(struct net_device *dev) ipvlan_ht_addr_add(ipvlan, addr); rcu_read_unlock(); - return dev_uc_add(phy_dev, phy_dev->dev_addr); + return 0; } static int ipvlan_stop(struct net_device *dev) @@ -190,8 +189,6 @@ static int ipvlan_stop(struct net_device *dev) dev_uc_unsync(phy_dev, dev); dev_mc_unsync(phy_dev, dev); - dev_uc_del(phy_dev, phy_dev->dev_addr); - rcu_read_lock(); list_for_each_entry_rcu(addr, &ipvlan->addrs, anode) ipvlan_ht_addr_del(addr); From 17c25cafd4d3e74c83dce56b158843b19c40b414 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 7 Mar 2020 22:05:14 -0800 Subject: [PATCH 134/256] gre: fix uninit-value in __iptunnel_pull_header syzbot found an interesting case of the kernel reading an uninit-value [1] Problem is in the handling of ETH_P_WCCP in gre_parse_header() We look at the byte following GRE options to eventually decide if the options are four bytes longer. Use skb_header_pointer() to not pull bytes if we found that no more bytes were needed. All callers of gre_parse_header() are properly using pskb_may_pull() anyway before proceeding to next header. [1] BUG: KMSAN: uninit-value in pskb_may_pull include/linux/skbuff.h:2303 [inline] BUG: KMSAN: uninit-value in __iptunnel_pull_header+0x30c/0xbd0 net/ipv4/ip_tunnel_core.c:94 CPU: 1 PID: 11784 Comm: syz-executor940 Not tainted 5.6.0-rc2-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x1c9/0x220 lib/dump_stack.c:118 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:118 __msan_warning+0x58/0xa0 mm/kmsan/kmsan_instr.c:215 pskb_may_pull include/linux/skbuff.h:2303 [inline] __iptunnel_pull_header+0x30c/0xbd0 net/ipv4/ip_tunnel_core.c:94 iptunnel_pull_header include/net/ip_tunnels.h:411 [inline] gre_rcv+0x15e/0x19c0 net/ipv6/ip6_gre.c:606 ip6_protocol_deliver_rcu+0x181b/0x22c0 net/ipv6/ip6_input.c:432 ip6_input_finish net/ipv6/ip6_input.c:473 [inline] NF_HOOK include/linux/netfilter.h:307 [inline] ip6_input net/ipv6/ip6_input.c:482 [inline] ip6_mc_input+0xdf2/0x1460 net/ipv6/ip6_input.c:576 dst_input include/net/dst.h:442 [inline] ip6_rcv_finish net/ipv6/ip6_input.c:76 [inline] NF_HOOK include/linux/netfilter.h:307 [inline] ipv6_rcv+0x683/0x710 net/ipv6/ip6_input.c:306 __netif_receive_skb_one_core net/core/dev.c:5198 [inline] __netif_receive_skb net/core/dev.c:5312 [inline] netif_receive_skb_internal net/core/dev.c:5402 [inline] netif_receive_skb+0x66b/0xf20 net/core/dev.c:5461 tun_rx_batched include/linux/skbuff.h:4321 [inline] tun_get_user+0x6aef/0x6f60 drivers/net/tun.c:1997 tun_chr_write_iter+0x1f2/0x360 drivers/net/tun.c:2026 call_write_iter include/linux/fs.h:1901 [inline] new_sync_write fs/read_write.c:483 [inline] __vfs_write+0xa5a/0xca0 fs/read_write.c:496 vfs_write+0x44a/0x8f0 fs/read_write.c:558 ksys_write+0x267/0x450 fs/read_write.c:611 __do_sys_write fs/read_write.c:623 [inline] __se_sys_write fs/read_write.c:620 [inline] __ia32_sys_write+0xdb/0x120 fs/read_write.c:620 do_syscall_32_irqs_on arch/x86/entry/common.c:339 [inline] do_fast_syscall_32+0x3c7/0x6e0 arch/x86/entry/common.c:410 entry_SYSENTER_compat+0x68/0x77 arch/x86/entry/entry_64_compat.S:139 RIP: 0023:0xf7f62d99 Code: 90 e8 0b 00 00 00 f3 90 0f ae e8 eb f9 8d 74 26 00 89 3c 24 c3 90 90 90 90 90 90 90 90 90 90 90 90 51 52 55 89 e5 0f 34 cd 80 <5d> 5a 59 c3 90 90 90 90 eb 0d 90 90 90 90 90 90 90 90 90 90 90 90 RSP: 002b:00000000fffedb2c EFLAGS: 00000217 ORIG_RAX: 0000000000000004 RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000020002580 RDX: 0000000000000fca RSI: 0000000000000036 RDI: 0000000000000004 RBP: 0000000000008914 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:144 [inline] kmsan_internal_poison_shadow+0x66/0xd0 mm/kmsan/kmsan.c:127 kmsan_slab_alloc+0x8a/0xe0 mm/kmsan/kmsan_hooks.c:82 slab_alloc_node mm/slub.c:2793 [inline] __kmalloc_node_track_caller+0xb40/0x1200 mm/slub.c:4401 __kmalloc_reserve net/core/skbuff.c:142 [inline] __alloc_skb+0x2fd/0xac0 net/core/skbuff.c:210 alloc_skb include/linux/skbuff.h:1051 [inline] alloc_skb_with_frags+0x18c/0xa70 net/core/skbuff.c:5766 sock_alloc_send_pskb+0xada/0xc60 net/core/sock.c:2242 tun_alloc_skb drivers/net/tun.c:1529 [inline] tun_get_user+0x10ae/0x6f60 drivers/net/tun.c:1843 tun_chr_write_iter+0x1f2/0x360 drivers/net/tun.c:2026 call_write_iter include/linux/fs.h:1901 [inline] new_sync_write fs/read_write.c:483 [inline] __vfs_write+0xa5a/0xca0 fs/read_write.c:496 vfs_write+0x44a/0x8f0 fs/read_write.c:558 ksys_write+0x267/0x450 fs/read_write.c:611 __do_sys_write fs/read_write.c:623 [inline] __se_sys_write fs/read_write.c:620 [inline] __ia32_sys_write+0xdb/0x120 fs/read_write.c:620 do_syscall_32_irqs_on arch/x86/entry/common.c:339 [inline] do_fast_syscall_32+0x3c7/0x6e0 arch/x86/entry/common.c:410 entry_SYSENTER_compat+0x68/0x77 arch/x86/entry/entry_64_compat.S:139 Fixes: 95f5c64c3c13 ("gre: Move utility functions to common headers") Fixes: c54419321455 ("GRE: Refactor GRE tunneling code.") Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller --- net/ipv4/gre_demux.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c index 5fd6e8ed02b5..66fdbfe5447c 100644 --- a/net/ipv4/gre_demux.c +++ b/net/ipv4/gre_demux.c @@ -56,7 +56,9 @@ int gre_del_protocol(const struct gre_protocol *proto, u8 version) } EXPORT_SYMBOL_GPL(gre_del_protocol); -/* Fills in tpi and returns header length to be pulled. */ +/* Fills in tpi and returns header length to be pulled. + * Note that caller must use pskb_may_pull() before pulling GRE header. + */ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, bool *csum_err, __be16 proto, int nhs) { @@ -110,8 +112,14 @@ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header */ if (greh->flags == 0 && tpi->proto == htons(ETH_P_WCCP)) { + u8 _val, *val; + + val = skb_header_pointer(skb, nhs + hdr_len, + sizeof(_val), &_val); + if (!val) + return -EINVAL; tpi->proto = proto; - if ((*(u8 *)options & 0xF0) != 0x40) + if ((*val & 0xF0) != 0x40) hdr_len += 4; } tpi->hdr_len = hdr_len; From b723bd933980f4956dabc8a8d84b3e83be8d094c Mon Sep 17 00:00:00 2001 From: Remi Pommarel Date: Sun, 8 Mar 2020 10:25:56 +0100 Subject: [PATCH 135/256] net: stmmac: dwmac1000: Disable ACS if enhanced descs are not used ACS (auto PAD/FCS stripping) removes FCS off 802.3 packets (LLC) so that there is no need to manually strip it for such packets. The enhanced DMA descriptors allow to flag LLC packets so that the receiving callback can use that to strip FCS manually or not. On the other hand, normal descriptors do not support that. Thus in order to not truncate LLC packet ACS should be disabled when using normal DMA descriptors. Fixes: 47dd7a540b8a0 ("net: add support for STMicroelectronics Ethernet controllers.") Signed-off-by: Remi Pommarel Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c index d0356fbd1e43..542784300620 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c @@ -24,6 +24,7 @@ static void dwmac1000_core_init(struct mac_device_info *hw, struct net_device *dev) { + struct stmmac_priv *priv = netdev_priv(dev); void __iomem *ioaddr = hw->pcsr; u32 value = readl(ioaddr + GMAC_CONTROL); int mtu = dev->mtu; @@ -35,7 +36,7 @@ static void dwmac1000_core_init(struct mac_device_info *hw, * Broadcom tags can look like invalid LLC/SNAP packets and cause the * hardware to truncate packets on reception. */ - if (netdev_uses_dsa(dev)) + if (netdev_uses_dsa(dev) || !priv->plat->enh_desc) value &= ~GMAC_CONTROL_ACS; if (mtu > 1500) From 83f73c5bb7b9a9135173f0ba2b1aa00c06664ff9 Mon Sep 17 00:00:00 2001 From: Dmitry Yakunin Date: Thu, 5 Mar 2020 15:33:12 +0300 Subject: [PATCH 136/256] inet_diag: return classid for all socket types In commit 1ec17dbd90f8 ("inet_diag: fix reporting cgroup classid and fallback to priority") croup classid reporting was fixed. But this works only for TCP sockets because for other socket types icsk parameter can be NULL and classid code path is skipped. This change moves classid handling to inet_diag_msg_attrs_fill() function. Also inet_diag_msg_attrs_size() helper was added and addends in nlmsg_new() were reordered to save order from inet_sk_diag_fill(). Fixes: 1ec17dbd90f8 ("inet_diag: fix reporting cgroup classid and fallback to priority") Signed-off-by: Dmitry Yakunin Reviewed-by: Konstantin Khlebnikov Signed-off-by: David S. Miller --- include/linux/inet_diag.h | 18 ++++++++++------ net/ipv4/inet_diag.c | 44 ++++++++++++++++++--------------------- net/ipv4/raw_diag.c | 5 +++-- net/ipv4/udp_diag.c | 5 +++-- net/sctp/diag.c | 8 ++----- 5 files changed, 40 insertions(+), 40 deletions(-) diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h index 39faaaf843e1..c91cf2dee12a 100644 --- a/include/linux/inet_diag.h +++ b/include/linux/inet_diag.h @@ -2,15 +2,10 @@ #ifndef _INET_DIAG_H_ #define _INET_DIAG_H_ 1 +#include #include -struct net; -struct sock; struct inet_hashinfo; -struct nlattr; -struct nlmsghdr; -struct sk_buff; -struct netlink_callback; struct inet_diag_handler { void (*dump)(struct sk_buff *skb, @@ -62,6 +57,17 @@ int inet_diag_bc_sk(const struct nlattr *_bc, struct sock *sk); void inet_diag_msg_common_fill(struct inet_diag_msg *r, struct sock *sk); +static inline size_t inet_diag_msg_attrs_size(void) +{ + return nla_total_size(1) /* INET_DIAG_SHUTDOWN */ + + nla_total_size(1) /* INET_DIAG_TOS */ +#if IS_ENABLED(CONFIG_IPV6) + + nla_total_size(1) /* INET_DIAG_TCLASS */ + + nla_total_size(1) /* INET_DIAG_SKV6ONLY */ +#endif + + nla_total_size(4) /* INET_DIAG_MARK */ + + nla_total_size(4); /* INET_DIAG_CLASS_ID */ +} int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, struct inet_diag_msg *r, int ext, struct user_namespace *user_ns, bool net_admin); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index f11e997e517b..8c8377568a78 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -100,13 +100,9 @@ static size_t inet_sk_attr_size(struct sock *sk, aux = handler->idiag_get_aux_size(sk, net_admin); return nla_total_size(sizeof(struct tcp_info)) - + nla_total_size(1) /* INET_DIAG_SHUTDOWN */ - + nla_total_size(1) /* INET_DIAG_TOS */ - + nla_total_size(1) /* INET_DIAG_TCLASS */ - + nla_total_size(4) /* INET_DIAG_MARK */ - + nla_total_size(4) /* INET_DIAG_CLASS_ID */ - + nla_total_size(sizeof(struct inet_diag_meminfo)) + nla_total_size(sizeof(struct inet_diag_msg)) + + inet_diag_msg_attrs_size() + + nla_total_size(sizeof(struct inet_diag_meminfo)) + nla_total_size(SK_MEMINFO_VARS * sizeof(u32)) + nla_total_size(TCP_CA_NAME_MAX) + nla_total_size(sizeof(struct tcpvegas_info)) @@ -147,6 +143,24 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, sk->sk_mark)) goto errout; + if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) || + ext & (1 << (INET_DIAG_TCLASS - 1))) { + u32 classid = 0; + +#ifdef CONFIG_SOCK_CGROUP_DATA + classid = sock_cgroup_classid(&sk->sk_cgrp_data); +#endif + /* Fallback to socket priority if class id isn't set. + * Classful qdiscs use it as direct reference to class. + * For cgroup2 classid is always zero. + */ + if (!classid) + classid = sk->sk_priority; + + if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid)) + goto errout; + } + r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk)); r->idiag_inode = sock_i_ino(sk); @@ -284,24 +298,6 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, goto errout; } - if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) || - ext & (1 << (INET_DIAG_TCLASS - 1))) { - u32 classid = 0; - -#ifdef CONFIG_SOCK_CGROUP_DATA - classid = sock_cgroup_classid(&sk->sk_cgrp_data); -#endif - /* Fallback to socket priority if class id isn't set. - * Classful qdiscs use it as direct reference to class. - * For cgroup2 classid is always zero. - */ - if (!classid) - classid = sk->sk_priority; - - if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid)) - goto errout; - } - out: nlmsg_end(skb, nlh); return 0; diff --git a/net/ipv4/raw_diag.c b/net/ipv4/raw_diag.c index e35736b99300..a93e7d1e1251 100644 --- a/net/ipv4/raw_diag.c +++ b/net/ipv4/raw_diag.c @@ -100,8 +100,9 @@ static int raw_diag_dump_one(struct sk_buff *in_skb, if (IS_ERR(sk)) return PTR_ERR(sk); - rep = nlmsg_new(sizeof(struct inet_diag_msg) + - sizeof(struct inet_diag_meminfo) + 64, + rep = nlmsg_new(nla_total_size(sizeof(struct inet_diag_msg)) + + inet_diag_msg_attrs_size() + + nla_total_size(sizeof(struct inet_diag_meminfo)) + 64, GFP_KERNEL); if (!rep) { sock_put(sk); diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index 910555a4d9fe..dccd2286bc28 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -64,8 +64,9 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, goto out; err = -ENOMEM; - rep = nlmsg_new(sizeof(struct inet_diag_msg) + - sizeof(struct inet_diag_meminfo) + 64, + rep = nlmsg_new(nla_total_size(sizeof(struct inet_diag_msg)) + + inet_diag_msg_attrs_size() + + nla_total_size(sizeof(struct inet_diag_meminfo)) + 64, GFP_KERNEL); if (!rep) goto out; diff --git a/net/sctp/diag.c b/net/sctp/diag.c index 8a15146faaeb..1069d7af3672 100644 --- a/net/sctp/diag.c +++ b/net/sctp/diag.c @@ -237,15 +237,11 @@ static size_t inet_assoc_attr_size(struct sctp_association *asoc) addrcnt++; return nla_total_size(sizeof(struct sctp_info)) - + nla_total_size(1) /* INET_DIAG_SHUTDOWN */ - + nla_total_size(1) /* INET_DIAG_TOS */ - + nla_total_size(1) /* INET_DIAG_TCLASS */ - + nla_total_size(4) /* INET_DIAG_MARK */ - + nla_total_size(4) /* INET_DIAG_CLASS_ID */ + nla_total_size(addrlen * asoc->peer.transport_count) + nla_total_size(addrlen * addrcnt) - + nla_total_size(sizeof(struct inet_diag_meminfo)) + nla_total_size(sizeof(struct inet_diag_msg)) + + inet_diag_msg_attrs_size() + + nla_total_size(sizeof(struct inet_diag_meminfo)) + 64; } From f7d5f5655ef7e5d2a128f6696ac35256e83b119b Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Sat, 7 Mar 2020 10:00:22 +0100 Subject: [PATCH 137/256] MAINTAINERS: Correct MIPS patchwork URL MIPS patchwork lives on patchwork.kernel.org for quite some time. Signed-off-by: Thomas Bogendoerfer --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 2c546977fb88..6f01bc6fa409 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11118,7 +11118,7 @@ M: Thomas Bogendoerfer L: linux-mips@vger.kernel.org W: http://www.linux-mips.org/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/mips/linux.git -Q: http://patchwork.linux-mips.org/project/linux-mips/list/ +Q: https://patchwork.kernel.org/project/linux-mips/list/ S: Maintained F: Documentation/devicetree/bindings/mips/ F: Documentation/mips/ From f98371476f36359da2285d1807b43e5b17fd18de Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 6 Mar 2020 15:34:15 +0100 Subject: [PATCH 138/256] pinctrl: qcom: ssbi-gpio: Fix fwspec parsing bug We are parsing SSBI gpios as fourcell fwspecs but they are twocell. Probably a simple copy-and-paste bug. Tested on the APQ8060 DragonBoard and after this ethernet and MMC card detection works again. Cc: Bjorn Andersson Cc: stable@vger.kernel.org Reviewed-by: Brian Masney Fixes: ae436fe81053 ("pinctrl: ssbi-gpio: convert to hierarchical IRQ helpers in gpio core") Link: https://lore.kernel.org/r/20200306143416.1476250-1-linus.walleij@linaro.org Signed-off-by: Linus Walleij --- drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c b/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c index fba1d41d20ec..338a15d08629 100644 --- a/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c +++ b/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c @@ -794,7 +794,7 @@ static int pm8xxx_gpio_probe(struct platform_device *pdev) girq->fwnode = of_node_to_fwnode(pctrl->dev->of_node); girq->parent_domain = parent_domain; girq->child_to_parent_hwirq = pm8xxx_child_to_parent_hwirq; - girq->populate_parent_alloc_arg = gpiochip_populate_parent_fwspec_fourcell; + girq->populate_parent_alloc_arg = gpiochip_populate_parent_fwspec_twocell; girq->child_offset_to_irq = pm8xxx_child_offset_to_irq; girq->child_irq_domain_ops.translate = pm8xxx_domain_translate; From d62e7fbea4951c124a24176da0c7bf3003ec53d4 Mon Sep 17 00:00:00 2001 From: Mathias Kresin Date: Thu, 5 Mar 2020 19:22:45 +0100 Subject: [PATCH 139/256] pinctrl: falcon: fix syntax error Add the missing semicolon after of_node_put to get the file compiled. Fixes: f17d2f54d36d ("pinctrl: falcon: Add of_node_put() before return") Cc: stable@vger.kernel.org # v5.4+ Signed-off-by: Mathias Kresin Link: https://lore.kernel.org/r/20200305182245.9636-1-dev@kresin.me Acked-by: Thomas Langer Signed-off-by: Linus Walleij --- drivers/pinctrl/pinctrl-falcon.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pinctrl/pinctrl-falcon.c b/drivers/pinctrl/pinctrl-falcon.c index a454f57c264e..62c02b969327 100644 --- a/drivers/pinctrl/pinctrl-falcon.c +++ b/drivers/pinctrl/pinctrl-falcon.c @@ -451,7 +451,7 @@ static int pinctrl_falcon_probe(struct platform_device *pdev) falcon_info.clk[*bank] = clk_get(&ppdev->dev, NULL); if (IS_ERR(falcon_info.clk[*bank])) { dev_err(&ppdev->dev, "failed to get clock\n"); - of_node_put(np) + of_node_put(np); return PTR_ERR(falcon_info.clk[*bank]); } falcon_info.membase[*bank] = devm_ioremap_resource(&pdev->dev, From 1cada2f307665e208a486d7ac2294ed9a6f74a6f Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 9 Mar 2020 16:26:04 +0100 Subject: [PATCH 140/256] pinctrl: qcom: Assign irq_eoi conditionally The hierarchical parts of MSM pinctrl/GPIO is only used when the device tree has a "wakeup-parent" as a phandle, but the .irq_eoi is anyway assigned leading to semantic problems on elder Qualcomm chipsets. When the drivers/mfd/qcom-pm8xxx.c driver calls chained_irq_exit() that call will in turn call chip->irq_eoi() which is set to irq_chip_eoi_parent() by default on a hierachical IRQ chip, and the parent is pinctrl-msm.c so that will in turn unconditionally call irq_chip_eoi_parent() again, but its parent is invalid so we get the following crash: Unnable to handle kernel NULL pointer dereference at virtual address 00000010 pgd = (ptrval) [00000010] *pgd=00000000 Internal error: Oops: 5 [#1] PREEMPT SMP ARM (...) PC is at irq_chip_eoi_parent+0x4/0x10 LR is at pm8xxx_irq_handler+0x1b4/0x2d8 If we solve this crash by avoiding to call up to irq_chip_eoi_parent(), the machine will hang and get reset by the watchdog, because of semantic issues, probably inside irq_chip. As a solution, just assign the .irq_eoi conditionally if we are actually using a wakeup parent. Cc: David Heidelberg Cc: Bjorn Andersson Cc: Lina Iyer Cc: Stephen Boyd Cc: stable@vger.kernel.org Fixes: e35a6ae0eb3a ("pinctrl/msm: Setup GPIO chip in hierarchy") Link: https://lore.kernel.org/r/20200306121221.1231296-1-linus.walleij@linaro.org Link: https://lore.kernel.org/r/20200309125207.571840-1-linus.walleij@linaro.org Link: https://lore.kernel.org/r/20200309152604.585112-1-linus.walleij@linaro.org Tested-by: David Heidelberg Acked-by: Marc Zyngier Signed-off-by: Linus Walleij --- drivers/pinctrl/qcom/pinctrl-msm.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c index 9a8daa256a32..1a948c3f54b7 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.c +++ b/drivers/pinctrl/qcom/pinctrl-msm.c @@ -1104,7 +1104,6 @@ static int msm_gpio_init(struct msm_pinctrl *pctrl) pctrl->irq_chip.irq_mask = msm_gpio_irq_mask; pctrl->irq_chip.irq_unmask = msm_gpio_irq_unmask; pctrl->irq_chip.irq_ack = msm_gpio_irq_ack; - pctrl->irq_chip.irq_eoi = irq_chip_eoi_parent; pctrl->irq_chip.irq_set_type = msm_gpio_irq_set_type; pctrl->irq_chip.irq_set_wake = msm_gpio_irq_set_wake; pctrl->irq_chip.irq_request_resources = msm_gpio_irq_reqres; @@ -1118,7 +1117,7 @@ static int msm_gpio_init(struct msm_pinctrl *pctrl) if (!chip->irq.parent_domain) return -EPROBE_DEFER; chip->irq.child_to_parent_hwirq = msm_gpio_wakeirq; - + pctrl->irq_chip.irq_eoi = irq_chip_eoi_parent; /* * Let's skip handling the GPIOs, if the parent irqchip * is handling the direct connect IRQ of the GPIO. From 661388f9b0004421b2ecdeac17248bd92a3bb818 Mon Sep 17 00:00:00 2001 From: Masanari Iida Date: Mon, 9 Mar 2020 19:43:56 +0900 Subject: [PATCH 141/256] linux-next: DOC: RDS: Fix a typo in rds.txt This patch fix a spelling typo in rds.txt Signed-off-by: Masanari Iida Signed-off-by: David S. Miller --- Documentation/networking/rds.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/networking/rds.txt b/Documentation/networking/rds.txt index f2a0147c933d..eec61694e894 100644 --- a/Documentation/networking/rds.txt +++ b/Documentation/networking/rds.txt @@ -159,7 +159,7 @@ Socket Interface set SO_RDS_TRANSPORT on a socket for which the transport has been previously attached explicitly (by SO_RDS_TRANSPORT) or implicitly (via bind(2)) will return an error of EOPNOTSUPP. - An attempt to set SO_RDS_TRANSPPORT to RDS_TRANS_NONE will + An attempt to set SO_RDS_TRANSPORT to RDS_TRANS_NONE will always return EINVAL. RDMA for RDS From d5349775c1726ce997b8eb4982cd85a01f1c8b42 Mon Sep 17 00:00:00 2001 From: Martin Leung Date: Mon, 24 Feb 2020 14:07:23 -0500 Subject: [PATCH 142/256] drm/amd/display: update soc bb for nv14 [why] nv14 previously inherited soc bb from generic dcn 2, did not match watermark values according to memory team [how] add nv14 specific soc bb: copy nv2 generic that it was using from before, but changed num channels to 8 Signed-off-by: Martin Leung Reviewed-by: Jun Lei Acked-by: Rodrigo Siqueira Signed-off-by: Alex Deucher --- .../drm/amd/display/dc/dcn20/dcn20_resource.c | 114 ++++++++++++++++++ 1 file changed, 114 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index 85f90f3e24cb..e310d67c399a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -335,6 +335,117 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_0_soc = { .use_urgent_burst_bw = 0 }; +struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv14_soc = { + .clock_limits = { + { + .state = 0, + .dcfclk_mhz = 560.0, + .fabricclk_mhz = 560.0, + .dispclk_mhz = 513.0, + .dppclk_mhz = 513.0, + .phyclk_mhz = 540.0, + .socclk_mhz = 560.0, + .dscclk_mhz = 171.0, + .dram_speed_mts = 8960.0, + }, + { + .state = 1, + .dcfclk_mhz = 694.0, + .fabricclk_mhz = 694.0, + .dispclk_mhz = 642.0, + .dppclk_mhz = 642.0, + .phyclk_mhz = 600.0, + .socclk_mhz = 694.0, + .dscclk_mhz = 214.0, + .dram_speed_mts = 11104.0, + }, + { + .state = 2, + .dcfclk_mhz = 875.0, + .fabricclk_mhz = 875.0, + .dispclk_mhz = 734.0, + .dppclk_mhz = 734.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 875.0, + .dscclk_mhz = 245.0, + .dram_speed_mts = 14000.0, + }, + { + .state = 3, + .dcfclk_mhz = 1000.0, + .fabricclk_mhz = 1000.0, + .dispclk_mhz = 1100.0, + .dppclk_mhz = 1100.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 1000.0, + .dscclk_mhz = 367.0, + .dram_speed_mts = 16000.0, + }, + { + .state = 4, + .dcfclk_mhz = 1200.0, + .fabricclk_mhz = 1200.0, + .dispclk_mhz = 1284.0, + .dppclk_mhz = 1284.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 1200.0, + .dscclk_mhz = 428.0, + .dram_speed_mts = 16000.0, + }, + /*Extra state, no dispclk ramping*/ + { + .state = 5, + .dcfclk_mhz = 1200.0, + .fabricclk_mhz = 1200.0, + .dispclk_mhz = 1284.0, + .dppclk_mhz = 1284.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 1200.0, + .dscclk_mhz = 428.0, + .dram_speed_mts = 16000.0, + }, + }, + .num_states = 5, + .sr_exit_time_us = 8.6, + .sr_enter_plus_exit_time_us = 10.9, + .urgent_latency_us = 4.0, + .urgent_latency_pixel_data_only_us = 4.0, + .urgent_latency_pixel_mixed_with_vm_data_us = 4.0, + .urgent_latency_vm_data_only_us = 4.0, + .urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096, + .urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096, + .urgent_out_of_order_return_per_channel_vm_only_bytes = 4096, + .pct_ideal_dram_sdp_bw_after_urgent_pixel_only = 40.0, + .pct_ideal_dram_sdp_bw_after_urgent_pixel_and_vm = 40.0, + .pct_ideal_dram_sdp_bw_after_urgent_vm_only = 40.0, + .max_avg_sdp_bw_use_normal_percent = 40.0, + .max_avg_dram_bw_use_normal_percent = 40.0, + .writeback_latency_us = 12.0, + .ideal_dram_bw_after_urgent_percent = 40.0, + .max_request_size_bytes = 256, + .dram_channel_width_bytes = 2, + .fabric_datapath_to_dcn_data_return_bytes = 64, + .dcn_downspread_percent = 0.5, + .downspread_percent = 0.38, + .dram_page_open_time_ns = 50.0, + .dram_rw_turnaround_time_ns = 17.5, + .dram_return_buffer_per_channel_bytes = 8192, + .round_trip_ping_latency_dcfclk_cycles = 131, + .urgent_out_of_order_return_per_channel_bytes = 256, + .channel_interleave_bytes = 256, + .num_banks = 8, + .num_chans = 8, + .vmm_page_size_bytes = 4096, + .dram_clock_change_latency_us = 404.0, + .dummy_pstate_latency_us = 5.0, + .writeback_dram_clock_change_latency_us = 23.0, + .return_bus_width_bytes = 64, + .dispclk_dppclk_vco_speed_mhz = 3850, + .xfc_bus_transport_time_us = 20, + .xfc_xbuf_latency_tolerance_us = 4, + .use_urgent_burst_bw = 0 +}; + struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv12_soc = { 0 }; #ifndef mmDP0_DP_DPHY_INTERNAL_CTRL @@ -3291,6 +3402,9 @@ void dcn20_patch_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_st static struct _vcs_dpi_soc_bounding_box_st *get_asic_rev_soc_bb( uint32_t hw_internal_rev) { + if (ASICREV_IS_NAVI14_M(hw_internal_rev)) + return &dcn2_0_nv14_soc; + if (ASICREV_IS_NAVI12_P(hw_internal_rev)) return &dcn2_0_nv12_soc; From afbac6c500da7235e9767b99e3fe2369cf3618a4 Mon Sep 17 00:00:00 2001 From: Masanari Iida Date: Mon, 30 Sep 2019 21:49:25 +0900 Subject: [PATCH 143/256] ktest: Fix some typos in sample.conf This patch fixes some spelling typo in sample.conf Link: http://lkml.kernel.org/r/20190930124925.20250-1-standby24x7@gmail.com Acked-by: Randy Dunlap Signed-off-by: Masanari Iida Signed-off-by: Steven Rostedt (VMware) --- tools/testing/ktest/sample.conf | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/tools/testing/ktest/sample.conf b/tools/testing/ktest/sample.conf index c3bc933d437b..10af34819642 100644 --- a/tools/testing/ktest/sample.conf +++ b/tools/testing/ktest/sample.conf @@ -10,7 +10,7 @@ # # Options set in the beginning of the file are considered to be -# default options. These options can be overriden by test specific +# default options. These options can be overridden by test specific # options, with the following exceptions: # # LOG_FILE @@ -204,7 +204,7 @@ # # This config file can also contain "config variables". # These are assigned with ":=" instead of the ktest option -# assigment "=". +# assignment "=". # # The difference between ktest options and config variables # is that config variables can be used multiple times, @@ -263,7 +263,7 @@ #### Using options in other options #### # # Options that are defined in the config file may also be used -# by other options. All options are evaulated at time of +# by other options. All options are evaluated at time of # use (except that config variables are evaluated at config # processing time). # @@ -707,7 +707,7 @@ # Line to define a successful boot up in console output. # This is what the line contains, not the entire line. If you need -# the entire line to match, then use regural expression syntax like: +# the entire line to match, then use regular expression syntax like: # (do not add any quotes around it) # # SUCCESS_LINE = ^MyBox Login:$ @@ -839,7 +839,7 @@ # (ignored if POWEROFF_ON_SUCCESS is set) #REBOOT_ON_SUCCESS = 1 -# In case there are isses with rebooting, you can specify this +# In case there are issues with rebooting, you can specify this # to always powercycle after this amount of time after calling # reboot. # Note, POWERCYCLE_AFTER_REBOOT = 0 does NOT disable it. It just @@ -848,7 +848,7 @@ # (default undefined) #POWERCYCLE_AFTER_REBOOT = 5 -# In case there's isses with halting, you can specify this +# In case there's issues with halting, you can specify this # to always poweroff after this amount of time after calling # halt. # Note, POWEROFF_AFTER_HALT = 0 does NOT disable it. It just @@ -972,7 +972,7 @@ # # PATCHCHECK_START is required and is the first patch to # test (the SHA1 of the commit). You may also specify anything -# that git checkout allows (branch name, tage, HEAD~3). +# that git checkout allows (branch name, tag, HEAD~3). # # PATCHCHECK_END is the last patch to check (default HEAD) # @@ -994,7 +994,7 @@ # IGNORE_WARNINGS is set for the given commit's sha1 # # IGNORE_WARNINGS can be used to disable the failure of patchcheck -# on a particuler commit (SHA1). You can add more than one commit +# on a particular commit (SHA1). You can add more than one commit # by adding a list of SHA1s that are space delimited. # # If BUILD_NOCLEAN is set, then make mrproper will not be run on @@ -1093,7 +1093,7 @@ # whatever reason. (Can't reboot, want to inspect each iteration) # Doing a BISECT_MANUAL will have the test wait for you to # tell it if the test passed or failed after each iteration. -# This is basicall the same as running git bisect yourself +# This is basically the same as running git bisect yourself # but ktest will rebuild and install the kernel for you. # # BISECT_CHECK = 1 (optional, default 0) @@ -1239,7 +1239,7 @@ # # CONFIG_BISECT_EXEC (optional) # The config bisect is a separate program that comes with ktest.pl. -# By befault, it will look for: +# By default, it will look for: # `pwd`/config-bisect.pl # the location ktest.pl was executed from. # If it does not find it there, it will look for: # `dirname `/config-bisect.pl # The directory that holds ktest.pl From 791dc9d6b3ca4291be6cfce7b9be468d61d7ed95 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Wed, 13 Nov 2019 13:36:24 -0500 Subject: [PATCH 144/256] ktest: Make default build option oldconfig not randconfig For the last time, I screwed up my ktest config file, and the build went into the default "randconfig", blowing away the .config that I had set up. The reason for the default randconfig was because when this was first written, I wanted to do a bunch of randconfigs. But as time progressed, ktest isn't about randconfig anymore, and because randconfig destroys the config in the build directory, it's a dangerous default to have. Use oldconfig as the default. Signed-off-by: Steven Rostedt (VMware) --- tools/testing/ktest/ktest.pl | 2 +- tools/testing/ktest/sample.conf | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl index 220d04f958a6..6a605ba75dd6 100755 --- a/tools/testing/ktest/ktest.pl +++ b/tools/testing/ktest/ktest.pl @@ -30,7 +30,7 @@ my %default = ( "EMAIL_WHEN_STARTED" => 0, "NUM_TESTS" => 1, "TEST_TYPE" => "build", - "BUILD_TYPE" => "randconfig", + "BUILD_TYPE" => "oldconfig", "MAKE_CMD" => "make", "CLOSE_CONSOLE_SIGNAL" => "INT", "TIMEOUT" => 120, diff --git a/tools/testing/ktest/sample.conf b/tools/testing/ktest/sample.conf index 10af34819642..27666b8007ed 100644 --- a/tools/testing/ktest/sample.conf +++ b/tools/testing/ktest/sample.conf @@ -505,7 +505,7 @@ #TEST = ssh user@machine /root/run_test # The build type is any make config type or special command -# (default randconfig) +# (default oldconfig) # nobuild - skip the clean and build step # useconfig:/path/to/config - use the given config and run # oldconfig on it. From 4d00fc477a2ce8b6d2b09fb34ef9fe9918e7d434 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Mon, 9 Mar 2020 16:00:11 -0400 Subject: [PATCH 145/256] ktest: Add timeout for ssh sync testing Before rebooting the box, a "ssh sync" is called to the test machine to see if it is alive or not. But if the test machine is in a partial state, that ssh may never actually finish, and the ktest test hangs. Add a 10 second timeout to the sync test, which will fail after 10 seconds and then cause the test to reboot the test machine. Cc: stable@vger.kernel.org Fixes: 6474ace999edd ("ktest.pl: Powercycle the box on reboot if no connection can be made") Signed-off-by: Steven Rostedt (VMware) --- tools/testing/ktest/ktest.pl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl index 6a605ba75dd6..8bdd7253c110 100755 --- a/tools/testing/ktest/ktest.pl +++ b/tools/testing/ktest/ktest.pl @@ -1383,7 +1383,7 @@ sub reboot { } else { # Make sure everything has been written to disk - run_ssh("sync"); + run_ssh("sync", 10); if (defined($time)) { start_monitor; From 1091c8fce8aa9c5abe1a73acab4bcaf58a729005 Mon Sep 17 00:00:00 2001 From: Masanari Iida Date: Mon, 9 Mar 2020 20:54:30 +0900 Subject: [PATCH 146/256] ktest: Fix typos in ktest.pl This patch fixes multipe spelling typo found in ktest.pl. Link: http://lkml.kernel.org/r/20200309115430.57540-1-standby24x7@gmail.com Acked-by: Randy Dunlap Signed-off-by: Masanari Iida Signed-off-by: Steven Rostedt (VMware) --- tools/testing/ktest/ktest.pl | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl index 8bdd7253c110..7570e36d636d 100755 --- a/tools/testing/ktest/ktest.pl +++ b/tools/testing/ktest/ktest.pl @@ -1030,7 +1030,7 @@ sub __read_config { } if (!$skip && $rest !~ /^\s*$/) { - die "$name: $.: Gargbage found after $type\n$_"; + die "$name: $.: Garbage found after $type\n$_"; } if ($skip && $type eq "TEST_START") { @@ -1063,7 +1063,7 @@ sub __read_config { } if ($rest !~ /^\s*$/) { - die "$name: $.: Gargbage found after DEFAULTS\n$_"; + die "$name: $.: Garbage found after DEFAULTS\n$_"; } } elsif (/^\s*INCLUDE\s+(\S+)/) { @@ -1154,7 +1154,7 @@ sub __read_config { # on of these sections that have SKIP defined. # The save variable can be # defined multiple times and the new one simply overrides - # the prevous one. + # the previous one. set_variable($lvalue, $rvalue); } else { @@ -1234,7 +1234,7 @@ sub read_config { foreach my $option (keys %not_used) { print "$option\n"; } - print "Set IGRNORE_UNUSED = 1 to have ktest ignore unused variables\n"; + print "Set IGNORE_UNUSED = 1 to have ktest ignore unused variables\n"; if (!read_yn "Do you want to continue?") { exit -1; } @@ -1345,7 +1345,7 @@ sub eval_option { # Check for recursive evaluations. # 100 deep should be more than enough. if ($r++ > 100) { - die "Over 100 evaluations accurred with $option\n" . + die "Over 100 evaluations occurred with $option\n" . "Check for recursive variables\n"; } $prev = $option; @@ -1461,7 +1461,7 @@ sub get_test_name() { sub dodie { - # avoid recusion + # avoid recursion return if ($in_die); $in_die = 1; From f1c2cd3f8fb959123a9beba18c0e8112dcb2e137 Mon Sep 17 00:00:00 2001 From: Hawking Zhang Date: Wed, 4 Mar 2020 17:03:48 +0800 Subject: [PATCH 147/256] drm/amdgpu: correct ROM_INDEX/DATA offset for VEGA20 The ROMC_INDEX/DATA offset was changed to e4/e5 since from smuio_v11 (vega20/arcturus). Signed-off-by: Hawking Zhang Tested-by: Candice Li Reviewed-by: Candice Li Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/soc15.c | 25 +++++++++++++++++++++++-- 1 file changed, 23 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index 2b488dfb2f21..d8945c31b622 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -89,6 +89,13 @@ #define HDP_MEM_POWER_CTRL__RC_MEM_POWER_CTRL_EN_MASK 0x00010000L #define HDP_MEM_POWER_CTRL__RC_MEM_POWER_LS_EN_MASK 0x00020000L #define mmHDP_MEM_POWER_CTRL_BASE_IDX 0 + +/* for Vega20/arcturus regiter offset change */ +#define mmROM_INDEX_VG20 0x00e4 +#define mmROM_INDEX_VG20_BASE_IDX 0 +#define mmROM_DATA_VG20 0x00e5 +#define mmROM_DATA_VG20_BASE_IDX 0 + /* * Indirect registers accessor */ @@ -309,6 +316,8 @@ static bool soc15_read_bios_from_rom(struct amdgpu_device *adev, { u32 *dw_ptr; u32 i, length_dw; + uint32_t rom_index_offset; + uint32_t rom_data_offset; if (bios == NULL) return false; @@ -321,11 +330,23 @@ static bool soc15_read_bios_from_rom(struct amdgpu_device *adev, dw_ptr = (u32 *)bios; length_dw = ALIGN(length_bytes, 4) / 4; + switch (adev->asic_type) { + case CHIP_VEGA20: + case CHIP_ARCTURUS: + rom_index_offset = SOC15_REG_OFFSET(SMUIO, 0, mmROM_INDEX_VG20); + rom_data_offset = SOC15_REG_OFFSET(SMUIO, 0, mmROM_DATA_VG20); + break; + default: + rom_index_offset = SOC15_REG_OFFSET(SMUIO, 0, mmROM_INDEX); + rom_data_offset = SOC15_REG_OFFSET(SMUIO, 0, mmROM_DATA); + break; + } + /* set rom index to 0 */ - WREG32(SOC15_REG_OFFSET(SMUIO, 0, mmROM_INDEX), 0); + WREG32(rom_index_offset, 0); /* read out the rom data */ for (i = 0; i < length_dw; i++) - dw_ptr[i] = RREG32(SOC15_REG_OFFSET(SMUIO, 0, mmROM_DATA)); + dw_ptr[i] = RREG32(rom_data_offset); return true; } From 8d67743653dce5a0e7aa500fcccb237cde7ad88e Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 8 Mar 2020 19:07:17 +0100 Subject: [PATCH 148/256] futex: Unbreak futex hashing The recent futex inode life time fix changed the ordering of the futex key union struct members, but forgot to adjust the hash function accordingly, As a result the hashing omits the leading 64bit and even hashes beyond the futex key causing a bad hash distribution which led to a ~100% performance regression. Hand in the futex key pointer instead of a random struct member and make the size calculation based of the struct offset. Fixes: 8019ad13ef7f ("futex: Fix inode life-time issue") Reported-by: Rong Chen Decoded-by: Linus Torvalds Signed-off-by: Thomas Gleixner Tested-by: Rong Chen Link: https://lkml.kernel.org/r/87h7yy90ve.fsf@nanos.tec.linutronix.de --- kernel/futex.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/futex.c b/kernel/futex.c index e14f7cd45dbd..82dfacb3250e 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -385,9 +385,9 @@ static inline int hb_waiters_pending(struct futex_hash_bucket *hb) */ static struct futex_hash_bucket *hash_futex(union futex_key *key) { - u32 hash = jhash2((u32*)&key->both.word, - (sizeof(key->both.word)+sizeof(key->both.ptr))/4, + u32 hash = jhash2((u32 *)key, offsetof(typeof(*key), both.offset) / 4, key->both.offset); + return &futex_queues[hash & (futex_hashsize - 1)]; } From 10dab84caf400f2f5f8b010ebb0c7c4272ec5093 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Sun, 8 Mar 2020 14:29:17 +0100 Subject: [PATCH 149/256] pid: make ENOMEM return value more obvious The alloc_pid() codepath used to be simpler. With the introducation of the ability to choose specific pids in 49cb2fc42ce4 ("fork: extend clone3() to support setting a PID") it got more complex. It hasn't been super obvious that ENOMEM is returned when the pid namespace init process/child subreaper of the pid namespace has died. As can be seen from multiple attempts to improve this see e.g. [1] and most recently [2]. We regressed returning ENOMEM in [3] and [2] restored it. Let's add a comment on top explaining that this is historic and documented behavior and cannot easily be changed. [1]: 35f71bc0a09a ("fork: report pid reservation failure properly") [2]: b26ebfe12f34 ("pid: Fix error return value in some cases") [3]: 49cb2fc42ce4 ("fork: extend clone3() to support setting a PID") Signed-off-by: Christian Brauner --- kernel/pid.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/kernel/pid.c b/kernel/pid.c index 19645b25b77c..647b4bb457b5 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -247,6 +247,14 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid, tmp = tmp->parent; } + /* + * ENOMEM is not the most obvious choice especially for the case + * where the child subreaper has already exited and the pid + * namespace denies the creation of any new processes. But ENOMEM + * is what we have exposed to userspace for a long time and it is + * documented behavior for pid namespaces. So we can't easily + * change it even if there were an error code better suited. + */ retval = -ENOMEM; if (unlikely(is_child_reaper(pid))) { From 4b1bd9db078f7d5332c8601a2f5bd43cf0458fd4 Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Mon, 9 Mar 2020 18:16:24 +0000 Subject: [PATCH 150/256] sfc: detach from cb_page in efx_copy_channel() It's a resource, not a parameter, so we can't copy it into the new channel's TX queues, otherwise aliasing will lead to resource- management bugs if the channel is subsequently torn down without being initialised. Before the Fixes:-tagged commit there was a similar bug with tsoh_page, but I'm not sure it's worth doing another fix for such old kernels. Fixes: e9117e5099ea ("sfc: Firmware-Assisted TSO version 2") Suggested-by: Derek Shute Signed-off-by: Edward Cree Signed-off-by: David S. Miller --- drivers/net/ethernet/sfc/efx_channels.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/sfc/efx_channels.c b/drivers/net/ethernet/sfc/efx_channels.c index aeb5e8aa2f2a..73d4e39b5b16 100644 --- a/drivers/net/ethernet/sfc/efx_channels.c +++ b/drivers/net/ethernet/sfc/efx_channels.c @@ -583,6 +583,7 @@ struct efx_channel *efx_copy_channel(const struct efx_channel *old_channel) if (tx_queue->channel) tx_queue->channel = channel; tx_queue->buffer = NULL; + tx_queue->cb_page = NULL; memset(&tx_queue->txd, 0, sizeof(tx_queue->txd)); } From ad8192767c9f9cf97da57b9ffcea70fb100febef Mon Sep 17 00:00:00 2001 From: Mahesh Bandewar Date: Mon, 9 Mar 2020 15:56:56 -0700 Subject: [PATCH 151/256] ipvlan: don't deref eth hdr before checking it's set MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit IPvlan in L3 mode discards outbound multicast packets but performs the check before ensuring the ether-header is set or not. This is an error that Eric found through code browsing. Fixes: 2ad7bf363841 (“ipvlan: Initial check-in of the IPVLAN driver.”) Signed-off-by: Mahesh Bandewar Reported-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/net/ipvlan/ipvlan_core.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index 30cd0c4f0be0..53dac397db37 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -498,19 +498,21 @@ static int ipvlan_process_outbound(struct sk_buff *skb) struct ethhdr *ethh = eth_hdr(skb); int ret = NET_XMIT_DROP; - /* In this mode we dont care about multicast and broadcast traffic */ - if (is_multicast_ether_addr(ethh->h_dest)) { - pr_debug_ratelimited("Dropped {multi|broad}cast of type=[%x]\n", - ntohs(skb->protocol)); - kfree_skb(skb); - goto out; - } - /* The ipvlan is a pseudo-L2 device, so the packets that we receive * will have L2; which need to discarded and processed further * in the net-ns of the main-device. */ if (skb_mac_header_was_set(skb)) { + /* In this mode we dont care about + * multicast and broadcast traffic */ + if (is_multicast_ether_addr(ethh->h_dest)) { + pr_debug_ratelimited( + "Dropped {multi|broad}cast of type=[%x]\n", + ntohs(skb->protocol)); + kfree_skb(skb); + goto out; + } + skb_pull(skb, sizeof(*ethh)); skb->mac_header = (typeof(skb->mac_header))~0U; skb_reset_network_header(skb); From e18b353f102e371580f3f01dd47567a25acc3c1d Mon Sep 17 00:00:00 2001 From: Mahesh Bandewar Date: Mon, 9 Mar 2020 15:57:02 -0700 Subject: [PATCH 152/256] ipvlan: add cond_resched_rcu() while processing muticast backlog MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If there are substantial number of slaves created as simulated by Syzbot, the backlog processing could take much longer and result into the issue found in the Syzbot report. INFO: rcu_sched detected stalls on CPUs/tasks: (detected by 1, t=10502 jiffies, g=5049, c=5048, q=752) All QSes seen, last rcu_sched kthread activity 10502 (4294965563-4294955061), jiffies_till_next_fqs=1, root ->qsmask 0x0 syz-executor.1 R running task on cpu 1 10984 11210 3866 0x30020008 179034491270 Call Trace: [] _sched_show_task kernel/sched/core.c:8063 [inline] [] _sched_show_task.cold+0x2fd/0x392 kernel/sched/core.c:8030 [] sched_show_task+0xb/0x10 kernel/sched/core.c:8073 [] print_other_cpu_stall kernel/rcu/tree.c:1577 [inline] [] check_cpu_stall kernel/rcu/tree.c:1695 [inline] [] __rcu_pending kernel/rcu/tree.c:3478 [inline] [] rcu_pending kernel/rcu/tree.c:3540 [inline] [] rcu_check_callbacks.cold+0xbb4/0xc29 kernel/rcu/tree.c:2876 [] update_process_times+0x32/0x80 kernel/time/timer.c:1635 [] tick_sched_handle+0xa0/0x180 kernel/time/tick-sched.c:161 [] tick_sched_timer+0x44/0x130 kernel/time/tick-sched.c:1193 [] __run_hrtimer kernel/time/hrtimer.c:1393 [inline] [] __hrtimer_run_queues+0x307/0xd90 kernel/time/hrtimer.c:1455 [] hrtimer_interrupt+0x2ea/0x730 kernel/time/hrtimer.c:1513 [] local_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1031 [inline] [] smp_apic_timer_interrupt+0x144/0x5e0 arch/x86/kernel/apic/apic.c:1056 [] apic_timer_interrupt+0x8e/0xa0 arch/x86/entry/entry_64.S:778 RIP: 0010:do_raw_read_lock+0x22/0x80 kernel/locking/spinlock_debug.c:153 RSP: 0018:ffff8801dad07ab8 EFLAGS: 00000a02 ORIG_RAX: ffffffffffffff12 RAX: 0000000000000000 RBX: ffff8801c4135680 RCX: 0000000000000000 RDX: 1ffff10038826afe RSI: ffff88019d816bb8 RDI: ffff8801c41357f0 RBP: ffff8801dad07ac0 R08: 0000000000004b15 R09: 0000000000310273 R10: ffff88019d816bb8 R11: 0000000000000001 R12: ffff8801c41357e8 R13: 0000000000000000 R14: ffff8801cfb19850 R15: ffff8801cfb198b0 [] __raw_read_lock_bh include/linux/rwlock_api_smp.h:177 [inline] [] _raw_read_lock_bh+0x3e/0x50 kernel/locking/spinlock.c:240 [] ipv6_chk_mcast_addr+0x11a/0x6f0 net/ipv6/mcast.c:1006 [] ip6_mc_input+0x319/0x8e0 net/ipv6/ip6_input.c:482 [] dst_input include/net/dst.h:449 [inline] [] ip6_rcv_finish+0x408/0x610 net/ipv6/ip6_input.c:78 [] NF_HOOK include/linux/netfilter.h:292 [inline] [] NF_HOOK include/linux/netfilter.h:286 [inline] [] ipv6_rcv+0x10e/0x420 net/ipv6/ip6_input.c:278 [] __netif_receive_skb_one_core+0x12a/0x1f0 net/core/dev.c:5303 [] __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:5417 [] process_backlog+0x216/0x6c0 net/core/dev.c:6243 [] napi_poll net/core/dev.c:6680 [inline] [] net_rx_action+0x47b/0xfb0 net/core/dev.c:6748 [] __do_softirq+0x2c8/0x99a kernel/softirq.c:317 [] invoke_softirq kernel/softirq.c:399 [inline] [] irq_exit+0x16a/0x1a0 kernel/softirq.c:439 [] exiting_irq arch/x86/include/asm/apic.h:561 [inline] [] smp_apic_timer_interrupt+0x165/0x5e0 arch/x86/kernel/apic/apic.c:1058 [] apic_timer_interrupt+0x8e/0xa0 arch/x86/entry/entry_64.S:778 RIP: 0010:__sanitizer_cov_trace_pc+0x26/0x50 kernel/kcov.c:102 RSP: 0018:ffff880196033bd8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff12 RAX: ffff88019d8161c0 RBX: 00000000ffffffff RCX: ffffc90003501000 RDX: 0000000000000002 RSI: ffffffff816236d1 RDI: 0000000000000005 RBP: ffff880196033bd8 R08: ffff88019d8161c0 R09: 0000000000000000 R10: 1ffff10032c067f0 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000080 R14: 0000000000000000 R15: 0000000000000000 [] do_futex+0x151/0x1d50 kernel/futex.c:3548 [] C_SYSC_futex kernel/futex_compat.c:201 [inline] [] compat_SyS_futex+0x270/0x3b0 kernel/futex_compat.c:175 [] do_syscall_32_irqs_on arch/x86/entry/common.c:353 [inline] [] do_fast_syscall_32+0x357/0xe1c arch/x86/entry/common.c:415 [] entry_SYSENTER_compat+0x8b/0x9d arch/x86/entry/entry_64_compat.S:139 RIP: 0023:0xf7f23c69 RSP: 002b:00000000f5d1f12c EFLAGS: 00000282 ORIG_RAX: 00000000000000f0 RAX: ffffffffffffffda RBX: 000000000816af88 RCX: 0000000000000080 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 000000000816af8c RBP: 00000000f5d1f228 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 rcu_sched kthread starved for 10502 jiffies! g5049 c5048 f0x2 RCU_GP_WAIT_FQS(3) ->state=0x0 ->cpu=1 rcu_sched R running task on cpu 1 13048 8 2 0x90000000 179099587640 Call Trace: [] context_switch+0x60f/0xa60 kernel/sched/core.c:3209 [] __schedule+0x5aa/0x1da0 kernel/sched/core.c:3934 [] schedule+0x8f/0x1b0 kernel/sched/core.c:4011 [] schedule_timeout+0x50d/0xee0 kernel/time/timer.c:1803 [] rcu_gp_kthread+0xda1/0x3b50 kernel/rcu/tree.c:2327 [] kthread+0x348/0x420 kernel/kthread.c:246 [] ret_from_fork+0x56/0x70 arch/x86/entry/entry_64.S:393 Fixes: ba35f8588f47 (“ipvlan: Defer multicast / broadcast processing to a work-queue”) Signed-off-by: Mahesh Bandewar Reported-by: syzbot Signed-off-by: David S. Miller --- drivers/net/ipvlan/ipvlan_core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index 53dac397db37..5759e91dec71 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -277,6 +277,7 @@ void ipvlan_process_multicast(struct work_struct *work) } ipvlan_count_rx(ipvlan, len, ret == NET_RX_SUCCESS, true); local_bh_enable(); + cond_resched_rcu(); } rcu_read_unlock(); From ce9a4186f9ac475c415ffd20348176a4ea366670 Mon Sep 17 00:00:00 2001 From: Mahesh Bandewar Date: Mon, 9 Mar 2020 15:57:07 -0700 Subject: [PATCH 153/256] macvlan: add cond_resched() during multicast processing The Rx bound multicast packets are deferred to a workqueue and macvlan can also suffer from the same attack that was discovered by Syzbot for IPvlan. This solution is not as effective as in IPvlan. IPvlan defers all (Tx and Rx) multicast packet processing to a workqueue while macvlan does this way only for the Rx. This fix should address the Rx codition to certain extent. Tx is still suseptible. Tx multicast processing happens when .ndo_start_xmit is called, hence we cannot add cond_resched(). However, it's not that severe since the user which is generating / flooding will be affected the most. Fixes: 412ca1550cbe ("macvlan: Move broadcasts into a work queue") Signed-off-by: Mahesh Bandewar Signed-off-by: David S. Miller --- drivers/net/macvlan.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 81aa7adf4801..e7289d67268f 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -334,6 +334,8 @@ static void macvlan_process_broadcast(struct work_struct *w) if (src) dev_put(src->dev); consume_skb(skb); + + cond_resched(); } } From 018d26fcd12a75fb9b5fe233762aa3f2f0854b88 Mon Sep 17 00:00:00 2001 From: Dmitry Yakunin Date: Thu, 5 Mar 2020 17:45:57 +0300 Subject: [PATCH 154/256] cgroup, netclassid: periodically release file_lock on classid updating MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In our production environment we have faced with problem that updating classid in cgroup with heavy tasks cause long freeze of the file tables in this tasks. By heavy tasks we understand tasks with many threads and opened sockets (e.g. balancers). This freeze leads to an increase number of client timeouts. This patch implements following logic to fix this issue: аfter iterating 1000 file descriptors file table lock will be released thus providing a time gap for socket creation/deletion. Now update is non atomic and socket may be skipped using calls: dup2(oldfd, newfd); close(oldfd); But this case is not typical. Moreover before this patch skip is possible too by hiding socket fd in unix socket buffer. New sockets will be allocated with updated classid because cgroup state is updated before start of the file descriptors iteration. So in common cases this patch has no side effects. Signed-off-by: Dmitry Yakunin Reviewed-by: Konstantin Khlebnikov Signed-off-by: David S. Miller --- net/core/netclassid_cgroup.c | 47 ++++++++++++++++++++++++++++-------- 1 file changed, 37 insertions(+), 10 deletions(-) diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c index 0642f91c4038..b4c87fe31be2 100644 --- a/net/core/netclassid_cgroup.c +++ b/net/core/netclassid_cgroup.c @@ -53,30 +53,60 @@ static void cgrp_css_free(struct cgroup_subsys_state *css) kfree(css_cls_state(css)); } +/* + * To avoid freezing of sockets creation for tasks with big number of threads + * and opened sockets lets release file_lock every 1000 iterated descriptors. + * New sockets will already have been created with new classid. + */ + +struct update_classid_context { + u32 classid; + unsigned int batch; +}; + +#define UPDATE_CLASSID_BATCH 1000 + static int update_classid_sock(const void *v, struct file *file, unsigned n) { int err; + struct update_classid_context *ctx = (void *)v; struct socket *sock = sock_from_file(file, &err); if (sock) { spin_lock(&cgroup_sk_update_lock); - sock_cgroup_set_classid(&sock->sk->sk_cgrp_data, - (unsigned long)v); + sock_cgroup_set_classid(&sock->sk->sk_cgrp_data, ctx->classid); spin_unlock(&cgroup_sk_update_lock); } + if (--ctx->batch == 0) { + ctx->batch = UPDATE_CLASSID_BATCH; + return n + 1; + } return 0; } +static void update_classid_task(struct task_struct *p, u32 classid) +{ + struct update_classid_context ctx = { + .classid = classid, + .batch = UPDATE_CLASSID_BATCH + }; + unsigned int fd = 0; + + do { + task_lock(p); + fd = iterate_fd(p->files, fd, update_classid_sock, &ctx); + task_unlock(p); + cond_resched(); + } while (fd); +} + static void cgrp_attach(struct cgroup_taskset *tset) { struct cgroup_subsys_state *css; struct task_struct *p; cgroup_taskset_for_each(p, css, tset) { - task_lock(p); - iterate_fd(p->files, 0, update_classid_sock, - (void *)(unsigned long)css_cls_state(css)->classid); - task_unlock(p); + update_classid_task(p, css_cls_state(css)->classid); } } @@ -98,10 +128,7 @@ static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft, css_task_iter_start(css, 0, &it); while ((p = css_task_iter_next(&it))) { - task_lock(p); - iterate_fd(p->files, 0, update_classid_sock, - (void *)(unsigned long)cs->classid); - task_unlock(p); + update_classid_task(p, cs->classid); cond_resched(); } css_task_iter_end(&it); From afe207d80a61e4d6e7cfa0611a4af46d0ba95628 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 9 Mar 2020 18:22:58 -0700 Subject: [PATCH 155/256] ipvlan: do not use cond_resched_rcu() in ipvlan_process_multicast() Commit e18b353f102e ("ipvlan: add cond_resched_rcu() while processing muticast backlog") added a cond_resched_rcu() in a loop using rcu protection to iterate over slaves. This is breaking rcu rules, so lets instead use cond_resched() at a point we can reschedule Fixes: e18b353f102e ("ipvlan: add cond_resched_rcu() while processing muticast backlog") Signed-off-by: Eric Dumazet Cc: Mahesh Bandewar Signed-off-by: David S. Miller --- drivers/net/ipvlan/ipvlan_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index 5759e91dec71..8801d093135c 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -277,7 +277,6 @@ void ipvlan_process_multicast(struct work_struct *work) } ipvlan_count_rx(ipvlan, len, ret == NET_RX_SUCCESS, true); local_bh_enable(); - cond_resched_rcu(); } rcu_read_unlock(); @@ -294,6 +293,7 @@ void ipvlan_process_multicast(struct work_struct *work) } if (dev) dev_put(dev); + cond_resched(); } } From a8015ded89ad740d21355470d41879c5bd82aab7 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 10 Mar 2020 03:28:18 +0200 Subject: [PATCH 156/256] net: mscc: ocelot: properly account for VLAN header length when setting MRU What the driver writes into MAC_MAXLEN_CFG does not actually represent VLAN_ETH_FRAME_LEN but instead ETH_FRAME_LEN + ETH_FCS_LEN. Yes they are numerically equal, but the difference is important, as the switch treats VLAN-tagged traffic specially and knows to increase the maximum accepted frame size automatically. So it is always wrong to account for VLAN in the MAC_MAXLEN_CFG register. Unconditionally increase the maximum allowed frame size for double-tagged traffic. Accounting for the additional length does not mean that the other VLAN membership checks aren't performed, so there's no harm done. Also, stop abusing the MTU name for configuring the MRU. There is no support for configuring the MRU on an interface at the moment. Fixes: a556c76adc05 ("net: mscc: Add initial Ocelot switch support") Fixes: fa914e9c4d94 ("net: mscc: ocelot: create a helper for changing the port MTU") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/ethernet/mscc/ocelot.c | 28 +++++++++++++++++----------- include/soc/mscc/ocelot_dev.h | 2 +- 2 files changed, 18 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 86d543ab1ab9..d3b7373c5961 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -2176,24 +2176,29 @@ static int ocelot_init_timestamp(struct ocelot *ocelot) return 0; } -static void ocelot_port_set_mtu(struct ocelot *ocelot, int port, size_t mtu) +/* Configure the maximum SDU (L2 payload) on RX to the value specified in @sdu. + * The length of VLAN tags is accounted for automatically via DEV_MAC_TAGS_CFG. + */ +static void ocelot_port_set_maxlen(struct ocelot *ocelot, int port, size_t sdu) { struct ocelot_port *ocelot_port = ocelot->ports[port]; + int maxlen = sdu + ETH_HLEN + ETH_FCS_LEN; int atop_wm; - ocelot_port_writel(ocelot_port, mtu, DEV_MAC_MAXLEN_CFG); + ocelot_port_writel(ocelot_port, maxlen, DEV_MAC_MAXLEN_CFG); /* Set Pause WM hysteresis - * 152 = 6 * mtu / OCELOT_BUFFER_CELL_SZ - * 101 = 4 * mtu / OCELOT_BUFFER_CELL_SZ + * 152 = 6 * maxlen / OCELOT_BUFFER_CELL_SZ + * 101 = 4 * maxlen / OCELOT_BUFFER_CELL_SZ */ ocelot_write_rix(ocelot, SYS_PAUSE_CFG_PAUSE_ENA | SYS_PAUSE_CFG_PAUSE_STOP(101) | SYS_PAUSE_CFG_PAUSE_START(152), SYS_PAUSE_CFG, port); /* Tail dropping watermark */ - atop_wm = (ocelot->shared_queue_sz - 9 * mtu) / OCELOT_BUFFER_CELL_SZ; - ocelot_write_rix(ocelot, ocelot_wm_enc(9 * mtu), + atop_wm = (ocelot->shared_queue_sz - 9 * maxlen) / + OCELOT_BUFFER_CELL_SZ; + ocelot_write_rix(ocelot, ocelot_wm_enc(9 * maxlen), SYS_ATOP, port); ocelot_write(ocelot, ocelot_wm_enc(atop_wm), SYS_ATOP_TOT_CFG); } @@ -2222,9 +2227,10 @@ void ocelot_init_port(struct ocelot *ocelot, int port) DEV_MAC_HDX_CFG); /* Set Max Length and maximum tags allowed */ - ocelot_port_set_mtu(ocelot, port, VLAN_ETH_FRAME_LEN); + ocelot_port_set_maxlen(ocelot, port, ETH_DATA_LEN); ocelot_port_writel(ocelot_port, DEV_MAC_TAGS_CFG_TAG_ID(ETH_P_8021AD) | DEV_MAC_TAGS_CFG_VLAN_AWR_ENA | + DEV_MAC_TAGS_CFG_VLAN_DBL_AWR_ENA | DEV_MAC_TAGS_CFG_VLAN_LEN_AWR_ENA, DEV_MAC_TAGS_CFG); @@ -2310,18 +2316,18 @@ void ocelot_set_cpu_port(struct ocelot *ocelot, int cpu, * Only one port can be an NPI at the same time. */ if (cpu < ocelot->num_phys_ports) { - int mtu = VLAN_ETH_FRAME_LEN + OCELOT_TAG_LEN; + int sdu = ETH_DATA_LEN + OCELOT_TAG_LEN; ocelot_write(ocelot, QSYS_EXT_CPU_CFG_EXT_CPUQ_MSK_M | QSYS_EXT_CPU_CFG_EXT_CPU_PORT(cpu), QSYS_EXT_CPU_CFG); if (injection == OCELOT_TAG_PREFIX_SHORT) - mtu += OCELOT_SHORT_PREFIX_LEN; + sdu += OCELOT_SHORT_PREFIX_LEN; else if (injection == OCELOT_TAG_PREFIX_LONG) - mtu += OCELOT_LONG_PREFIX_LEN; + sdu += OCELOT_LONG_PREFIX_LEN; - ocelot_port_set_mtu(ocelot, cpu, mtu); + ocelot_port_set_maxlen(ocelot, cpu, sdu); } /* CPU port Injection/Extraction configuration */ diff --git a/include/soc/mscc/ocelot_dev.h b/include/soc/mscc/ocelot_dev.h index 0a50d53bbd3f..7c08437061fc 100644 --- a/include/soc/mscc/ocelot_dev.h +++ b/include/soc/mscc/ocelot_dev.h @@ -74,7 +74,7 @@ #define DEV_MAC_TAGS_CFG_TAG_ID_M GENMASK(31, 16) #define DEV_MAC_TAGS_CFG_TAG_ID_X(x) (((x) & GENMASK(31, 16)) >> 16) #define DEV_MAC_TAGS_CFG_VLAN_LEN_AWR_ENA BIT(2) -#define DEV_MAC_TAGS_CFG_PB_ENA BIT(1) +#define DEV_MAC_TAGS_CFG_VLAN_DBL_AWR_ENA BIT(1) #define DEV_MAC_TAGS_CFG_VLAN_AWR_ENA BIT(0) #define DEV_MAC_ADV_CHK_CFG 0x2c From 07dc3678bacc2a75b1900febea7d996a31f178a2 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Mon, 9 Mar 2020 12:02:14 +0100 Subject: [PATCH 157/256] drm/exynos: Fix cleanup of IOMMU related objects Store the IOMMU mapping created by the device core of each Exynos DRM sub-device and restore it when the Exynos DRM driver is unbound. This fixes IOMMU initialization failure for the second time when a deferred probe is triggered from the bind() callback of master's compound DRM driver. This also fixes the following issue found using kmemleak detector: unreferenced object 0xc2137640 (size 64): comm "swapper/0", pid 1, jiffies 4294937900 (age 3127.400s) hex dump (first 32 bytes): 50 a3 14 c2 80 a2 14 c2 01 00 00 00 20 00 00 00 P........... ... 00 10 00 00 00 80 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<3acd268d>] arch_setup_dma_ops+0x4c/0x104 [<9f7d2cce>] of_dma_configure+0x19c/0x3a4 [] really_probe+0xb0/0x47c [<4f510e4f>] driver_probe_device+0x78/0x1c4 [<7481a0cf>] device_driver_attach+0x58/0x60 [<0ff8f5c1>] __driver_attach+0xb8/0x158 [<86006144>] bus_for_each_dev+0x74/0xb4 [<10159dca>] bus_add_driver+0x1c0/0x200 [<8a265265>] driver_register+0x74/0x108 [] exynos_drm_init+0xb0/0x134 [] do_one_initcall+0x90/0x458 [<6da35917>] kernel_init_freeable+0x188/0x200 [] kernel_init+0x8/0x110 [<1f3cddf9>] ret_from_fork+0x14/0x20 [<8cd12507>] 0x0 unreferenced object 0xc214a280 (size 128): comm "swapper/0", pid 1, jiffies 4294937900 (age 3127.400s) hex dump (first 32 bytes): 00 a0 ec ed 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<3acd268d>] arch_setup_dma_ops+0x4c/0x104 [<9f7d2cce>] of_dma_configure+0x19c/0x3a4 [] really_probe+0xb0/0x47c [<4f510e4f>] driver_probe_device+0x78/0x1c4 [<7481a0cf>] device_driver_attach+0x58/0x60 [<0ff8f5c1>] __driver_attach+0xb8/0x158 [<86006144>] bus_for_each_dev+0x74/0xb4 [<10159dca>] bus_add_driver+0x1c0/0x200 [<8a265265>] driver_register+0x74/0x108 [] exynos_drm_init+0xb0/0x134 [] do_one_initcall+0x90/0x458 [<6da35917>] kernel_init_freeable+0x188/0x200 [] kernel_init+0x8/0x110 [<1f3cddf9>] ret_from_fork+0x14/0x20 [<8cd12507>] 0x0 unreferenced object 0xedeca000 (size 4096): comm "swapper/0", pid 1, jiffies 4294937900 (age 3127.400s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<3acd268d>] arch_setup_dma_ops+0x4c/0x104 [<9f7d2cce>] of_dma_configure+0x19c/0x3a4 [] really_probe+0xb0/0x47c [<4f510e4f>] driver_probe_device+0x78/0x1c4 [<7481a0cf>] device_driver_attach+0x58/0x60 [<0ff8f5c1>] __driver_attach+0xb8/0x158 [<86006144>] bus_for_each_dev+0x74/0xb4 [<10159dca>] bus_add_driver+0x1c0/0x200 [<8a265265>] driver_register+0x74/0x108 [] exynos_drm_init+0xb0/0x134 [] do_one_initcall+0x90/0x458 [<6da35917>] kernel_init_freeable+0x188/0x200 [] kernel_init+0x8/0x110 [<1f3cddf9>] ret_from_fork+0x14/0x20 [<8cd12507>] 0x0 unreferenced object 0xc214a300 (size 128): comm "swapper/0", pid 1, jiffies 4294937900 (age 3127.400s) hex dump (first 32 bytes): 00 a3 14 c2 00 a3 14 c2 00 40 18 c2 00 80 18 c2 .........@...... 02 00 02 00 ad 4e ad de ff ff ff ff ff ff ff ff .....N.......... backtrace: [<08cbd8bc>] iommu_domain_alloc+0x24/0x50 [] arm_iommu_create_mapping+0xe4/0x134 [<3acd268d>] arch_setup_dma_ops+0x4c/0x104 [<9f7d2cce>] of_dma_configure+0x19c/0x3a4 [] really_probe+0xb0/0x47c [<4f510e4f>] driver_probe_device+0x78/0x1c4 [<7481a0cf>] device_driver_attach+0x58/0x60 [<0ff8f5c1>] __driver_attach+0xb8/0x158 [<86006144>] bus_for_each_dev+0x74/0xb4 [<10159dca>] bus_add_driver+0x1c0/0x200 [<8a265265>] driver_register+0x74/0x108 [] exynos_drm_init+0xb0/0x134 [] do_one_initcall+0x90/0x458 [<6da35917>] kernel_init_freeable+0x188/0x200 [] kernel_init+0x8/0x110 [<1f3cddf9>] ret_from_fork+0x14/0x20 Signed-off-by: Marek Szyprowski Reviewed-by: Lukasz Luba Signed-off-by: Inki Dae --- drivers/gpu/drm/exynos/exynos5433_drm_decon.c | 5 ++-- drivers/gpu/drm/exynos/exynos7_drm_decon.c | 5 ++-- drivers/gpu/drm/exynos/exynos_drm_dma.c | 28 +++++++++++++------ drivers/gpu/drm/exynos/exynos_drm_drv.h | 6 ++-- drivers/gpu/drm/exynos/exynos_drm_fimc.c | 5 ++-- drivers/gpu/drm/exynos/exynos_drm_fimd.c | 5 ++-- drivers/gpu/drm/exynos/exynos_drm_g2d.c | 5 ++-- drivers/gpu/drm/exynos/exynos_drm_gsc.c | 5 ++-- drivers/gpu/drm/exynos/exynos_drm_rotator.c | 5 ++-- drivers/gpu/drm/exynos/exynos_drm_scaler.c | 6 ++-- drivers/gpu/drm/exynos/exynos_mixer.c | 7 +++-- 11 files changed, 53 insertions(+), 29 deletions(-) diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c index 8428ae12dfa5..1f79bc2a881e 100644 --- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c @@ -55,6 +55,7 @@ static const char * const decon_clks_name[] = { struct decon_context { struct device *dev; struct drm_device *drm_dev; + void *dma_priv; struct exynos_drm_crtc *crtc; struct exynos_drm_plane planes[WINDOWS_NR]; struct exynos_drm_plane_config configs[WINDOWS_NR]; @@ -644,7 +645,7 @@ static int decon_bind(struct device *dev, struct device *master, void *data) decon_clear_channels(ctx->crtc); - return exynos_drm_register_dma(drm_dev, dev); + return exynos_drm_register_dma(drm_dev, dev, &ctx->dma_priv); } static void decon_unbind(struct device *dev, struct device *master, void *data) @@ -654,7 +655,7 @@ static void decon_unbind(struct device *dev, struct device *master, void *data) decon_atomic_disable(ctx->crtc); /* detach this sub driver from iommu mapping if supported. */ - exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev); + exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev, &ctx->dma_priv); } static const struct component_ops decon_component_ops = { diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c index ff59c641fa80..1eed3327999f 100644 --- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c @@ -40,6 +40,7 @@ struct decon_context { struct device *dev; struct drm_device *drm_dev; + void *dma_priv; struct exynos_drm_crtc *crtc; struct exynos_drm_plane planes[WINDOWS_NR]; struct exynos_drm_plane_config configs[WINDOWS_NR]; @@ -127,13 +128,13 @@ static int decon_ctx_initialize(struct decon_context *ctx, decon_clear_channels(ctx->crtc); - return exynos_drm_register_dma(drm_dev, ctx->dev); + return exynos_drm_register_dma(drm_dev, ctx->dev, &ctx->dma_priv); } static void decon_ctx_remove(struct decon_context *ctx) { /* detach this sub driver from iommu mapping if supported. */ - exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev); + exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev, &ctx->dma_priv); } static u32 decon_calc_clkdiv(struct decon_context *ctx, diff --git a/drivers/gpu/drm/exynos/exynos_drm_dma.c b/drivers/gpu/drm/exynos/exynos_drm_dma.c index 9ebc02768847..619f81435c1b 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dma.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dma.c @@ -58,7 +58,7 @@ static inline void clear_dma_max_seg_size(struct device *dev) * mapping. */ static int drm_iommu_attach_device(struct drm_device *drm_dev, - struct device *subdrv_dev) + struct device *subdrv_dev, void **dma_priv) { struct exynos_drm_private *priv = drm_dev->dev_private; int ret; @@ -74,7 +74,14 @@ static int drm_iommu_attach_device(struct drm_device *drm_dev, return ret; if (IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU)) { - if (to_dma_iommu_mapping(subdrv_dev)) + /* + * Keep the original DMA mapping of the sub-device and + * restore it on Exynos DRM detach, otherwise the DMA + * framework considers it as IOMMU-less during the next + * probe (in case of deferred probe or modular build) + */ + *dma_priv = to_dma_iommu_mapping(subdrv_dev); + if (*dma_priv) arm_iommu_detach_device(subdrv_dev); ret = arm_iommu_attach_device(subdrv_dev, priv->mapping); @@ -98,19 +105,21 @@ static int drm_iommu_attach_device(struct drm_device *drm_dev, * mapping */ static void drm_iommu_detach_device(struct drm_device *drm_dev, - struct device *subdrv_dev) + struct device *subdrv_dev, void **dma_priv) { struct exynos_drm_private *priv = drm_dev->dev_private; - if (IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU)) + if (IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU)) { arm_iommu_detach_device(subdrv_dev); - else if (IS_ENABLED(CONFIG_IOMMU_DMA)) + arm_iommu_attach_device(subdrv_dev, *dma_priv); + } else if (IS_ENABLED(CONFIG_IOMMU_DMA)) iommu_detach_device(priv->mapping, subdrv_dev); clear_dma_max_seg_size(subdrv_dev); } -int exynos_drm_register_dma(struct drm_device *drm, struct device *dev) +int exynos_drm_register_dma(struct drm_device *drm, struct device *dev, + void **dma_priv) { struct exynos_drm_private *priv = drm->dev_private; @@ -137,13 +146,14 @@ int exynos_drm_register_dma(struct drm_device *drm, struct device *dev) priv->mapping = mapping; } - return drm_iommu_attach_device(drm, dev); + return drm_iommu_attach_device(drm, dev, dma_priv); } -void exynos_drm_unregister_dma(struct drm_device *drm, struct device *dev) +void exynos_drm_unregister_dma(struct drm_device *drm, struct device *dev, + void **dma_priv) { if (IS_ENABLED(CONFIG_EXYNOS_IOMMU)) - drm_iommu_detach_device(drm, dev); + drm_iommu_detach_device(drm, dev, dma_priv); } void exynos_drm_cleanup_dma(struct drm_device *drm) diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h index d4d21d8cfb90..6ae9056e7a18 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_drv.h +++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h @@ -223,8 +223,10 @@ static inline bool is_drm_iommu_supported(struct drm_device *drm_dev) return priv->mapping ? true : false; } -int exynos_drm_register_dma(struct drm_device *drm, struct device *dev); -void exynos_drm_unregister_dma(struct drm_device *drm, struct device *dev); +int exynos_drm_register_dma(struct drm_device *drm, struct device *dev, + void **dma_priv); +void exynos_drm_unregister_dma(struct drm_device *drm, struct device *dev, + void **dma_priv); void exynos_drm_cleanup_dma(struct drm_device *drm); #ifdef CONFIG_DRM_EXYNOS_DPI diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c index 8ea2e1d77802..29ab8be8604c 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c @@ -97,6 +97,7 @@ struct fimc_scaler { struct fimc_context { struct exynos_drm_ipp ipp; struct drm_device *drm_dev; + void *dma_priv; struct device *dev; struct exynos_drm_ipp_task *task; struct exynos_drm_ipp_formats *formats; @@ -1133,7 +1134,7 @@ static int fimc_bind(struct device *dev, struct device *master, void *data) ctx->drm_dev = drm_dev; ipp->drm_dev = drm_dev; - exynos_drm_register_dma(drm_dev, dev); + exynos_drm_register_dma(drm_dev, dev, &ctx->dma_priv); exynos_drm_ipp_register(dev, ipp, &ipp_funcs, DRM_EXYNOS_IPP_CAP_CROP | DRM_EXYNOS_IPP_CAP_ROTATE | @@ -1153,7 +1154,7 @@ static void fimc_unbind(struct device *dev, struct device *master, struct exynos_drm_ipp *ipp = &ctx->ipp; exynos_drm_ipp_unregister(dev, ipp); - exynos_drm_unregister_dma(drm_dev, dev); + exynos_drm_unregister_dma(drm_dev, dev, &ctx->dma_priv); } static const struct component_ops fimc_component_ops = { diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c index 21aec38702fc..bb67cad8371f 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c @@ -167,6 +167,7 @@ static struct fimd_driver_data exynos5420_fimd_driver_data = { struct fimd_context { struct device *dev; struct drm_device *drm_dev; + void *dma_priv; struct exynos_drm_crtc *crtc; struct exynos_drm_plane planes[WINDOWS_NR]; struct exynos_drm_plane_config configs[WINDOWS_NR]; @@ -1090,7 +1091,7 @@ static int fimd_bind(struct device *dev, struct device *master, void *data) if (is_drm_iommu_supported(drm_dev)) fimd_clear_channels(ctx->crtc); - return exynos_drm_register_dma(drm_dev, dev); + return exynos_drm_register_dma(drm_dev, dev, &ctx->dma_priv); } static void fimd_unbind(struct device *dev, struct device *master, @@ -1100,7 +1101,7 @@ static void fimd_unbind(struct device *dev, struct device *master, fimd_atomic_disable(ctx->crtc); - exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev); + exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev, &ctx->dma_priv); if (ctx->encoder) exynos_dpi_remove(ctx->encoder); diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c index 2a3382d43bc9..fcee33a43aca 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c +++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c @@ -232,6 +232,7 @@ struct g2d_runqueue_node { struct g2d_data { struct device *dev; + void *dma_priv; struct clk *gate_clk; void __iomem *regs; int irq; @@ -1409,7 +1410,7 @@ static int g2d_bind(struct device *dev, struct device *master, void *data) return ret; } - ret = exynos_drm_register_dma(drm_dev, dev); + ret = exynos_drm_register_dma(drm_dev, dev, &g2d->dma_priv); if (ret < 0) { dev_err(dev, "failed to enable iommu.\n"); g2d_fini_cmdlist(g2d); @@ -1434,7 +1435,7 @@ static void g2d_unbind(struct device *dev, struct device *master, void *data) priv->g2d_dev = NULL; cancel_work_sync(&g2d->runqueue_work); - exynos_drm_unregister_dma(g2d->drm_dev, dev); + exynos_drm_unregister_dma(g2d->drm_dev, dev, &g2d->dma_priv); } static const struct component_ops g2d_component_ops = { diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c index 88b6fcaa20be..45e9aee8366a 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c @@ -97,6 +97,7 @@ struct gsc_scaler { struct gsc_context { struct exynos_drm_ipp ipp; struct drm_device *drm_dev; + void *dma_priv; struct device *dev; struct exynos_drm_ipp_task *task; struct exynos_drm_ipp_formats *formats; @@ -1169,7 +1170,7 @@ static int gsc_bind(struct device *dev, struct device *master, void *data) ctx->drm_dev = drm_dev; ctx->drm_dev = drm_dev; - exynos_drm_register_dma(drm_dev, dev); + exynos_drm_register_dma(drm_dev, dev, &ctx->dma_priv); exynos_drm_ipp_register(dev, ipp, &ipp_funcs, DRM_EXYNOS_IPP_CAP_CROP | DRM_EXYNOS_IPP_CAP_ROTATE | @@ -1189,7 +1190,7 @@ static void gsc_unbind(struct device *dev, struct device *master, struct exynos_drm_ipp *ipp = &ctx->ipp; exynos_drm_ipp_unregister(dev, ipp); - exynos_drm_unregister_dma(drm_dev, dev); + exynos_drm_unregister_dma(drm_dev, dev, &ctx->dma_priv); } static const struct component_ops gsc_component_ops = { diff --git a/drivers/gpu/drm/exynos/exynos_drm_rotator.c b/drivers/gpu/drm/exynos/exynos_drm_rotator.c index b98482990d1a..dafa87b82052 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_rotator.c +++ b/drivers/gpu/drm/exynos/exynos_drm_rotator.c @@ -56,6 +56,7 @@ struct rot_variant { struct rot_context { struct exynos_drm_ipp ipp; struct drm_device *drm_dev; + void *dma_priv; struct device *dev; void __iomem *regs; struct clk *clock; @@ -243,7 +244,7 @@ static int rotator_bind(struct device *dev, struct device *master, void *data) rot->drm_dev = drm_dev; ipp->drm_dev = drm_dev; - exynos_drm_register_dma(drm_dev, dev); + exynos_drm_register_dma(drm_dev, dev, &rot->dma_priv); exynos_drm_ipp_register(dev, ipp, &ipp_funcs, DRM_EXYNOS_IPP_CAP_CROP | DRM_EXYNOS_IPP_CAP_ROTATE, @@ -261,7 +262,7 @@ static void rotator_unbind(struct device *dev, struct device *master, struct exynos_drm_ipp *ipp = &rot->ipp; exynos_drm_ipp_unregister(dev, ipp); - exynos_drm_unregister_dma(rot->drm_dev, rot->dev); + exynos_drm_unregister_dma(rot->drm_dev, rot->dev, &rot->dma_priv); } static const struct component_ops rotator_component_ops = { diff --git a/drivers/gpu/drm/exynos/exynos_drm_scaler.c b/drivers/gpu/drm/exynos/exynos_drm_scaler.c index 497973e9b2c5..93c43c8d914e 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_scaler.c +++ b/drivers/gpu/drm/exynos/exynos_drm_scaler.c @@ -39,6 +39,7 @@ struct scaler_data { struct scaler_context { struct exynos_drm_ipp ipp; struct drm_device *drm_dev; + void *dma_priv; struct device *dev; void __iomem *regs; struct clk *clock[SCALER_MAX_CLK]; @@ -450,7 +451,7 @@ static int scaler_bind(struct device *dev, struct device *master, void *data) scaler->drm_dev = drm_dev; ipp->drm_dev = drm_dev; - exynos_drm_register_dma(drm_dev, dev); + exynos_drm_register_dma(drm_dev, dev, &scaler->dma_priv); exynos_drm_ipp_register(dev, ipp, &ipp_funcs, DRM_EXYNOS_IPP_CAP_CROP | DRM_EXYNOS_IPP_CAP_ROTATE | @@ -470,7 +471,8 @@ static void scaler_unbind(struct device *dev, struct device *master, struct exynos_drm_ipp *ipp = &scaler->ipp; exynos_drm_ipp_unregister(dev, ipp); - exynos_drm_unregister_dma(scaler->drm_dev, scaler->dev); + exynos_drm_unregister_dma(scaler->drm_dev, scaler->dev, + &scaler->dma_priv); } static const struct component_ops scaler_component_ops = { diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c index 38ae9c32feef..21b726baedea 100644 --- a/drivers/gpu/drm/exynos/exynos_mixer.c +++ b/drivers/gpu/drm/exynos/exynos_mixer.c @@ -94,6 +94,7 @@ struct mixer_context { struct platform_device *pdev; struct device *dev; struct drm_device *drm_dev; + void *dma_priv; struct exynos_drm_crtc *crtc; struct exynos_drm_plane planes[MIXER_WIN_NR]; unsigned long flags; @@ -894,12 +895,14 @@ static int mixer_initialize(struct mixer_context *mixer_ctx, } } - return exynos_drm_register_dma(drm_dev, mixer_ctx->dev); + return exynos_drm_register_dma(drm_dev, mixer_ctx->dev, + &mixer_ctx->dma_priv); } static void mixer_ctx_remove(struct mixer_context *mixer_ctx) { - exynos_drm_unregister_dma(mixer_ctx->drm_dev, mixer_ctx->dev); + exynos_drm_unregister_dma(mixer_ctx->drm_dev, mixer_ctx->dev, + &mixer_ctx->dma_priv); } static int mixer_enable_vblank(struct exynos_drm_crtc *crtc) From 7ca6ee38909109751bfab79e9f6c570d2ed258c6 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Wed, 26 Feb 2020 16:21:20 +0300 Subject: [PATCH 158/256] watchdog: iTCO_wdt: Export vendorsupport In preparation for making ->smi_res optional the iTCO_wdt driver needs to know whether vendorsupport is being set to non-zero. For this reason export the variable. Signed-off-by: Mika Westerberg Reviewed-by: Guenter Roeck Signed-off-by: Wolfram Sang --- drivers/watchdog/iTCO_vendor.h | 2 ++ drivers/watchdog/iTCO_vendor_support.c | 16 +++++++++------- 2 files changed, 11 insertions(+), 7 deletions(-) diff --git a/drivers/watchdog/iTCO_vendor.h b/drivers/watchdog/iTCO_vendor.h index 0f7373ba10d5..69e92e692ae0 100644 --- a/drivers/watchdog/iTCO_vendor.h +++ b/drivers/watchdog/iTCO_vendor.h @@ -1,10 +1,12 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* iTCO Vendor Specific Support hooks */ #ifdef CONFIG_ITCO_VENDOR_SUPPORT +extern int iTCO_vendorsupport; extern void iTCO_vendor_pre_start(struct resource *, unsigned int); extern void iTCO_vendor_pre_stop(struct resource *); extern int iTCO_vendor_check_noreboot_on(void); #else +#define iTCO_vendorsupport 0 #define iTCO_vendor_pre_start(acpibase, heartbeat) {} #define iTCO_vendor_pre_stop(acpibase) {} #define iTCO_vendor_check_noreboot_on() 1 diff --git a/drivers/watchdog/iTCO_vendor_support.c b/drivers/watchdog/iTCO_vendor_support.c index 4f1b96f59349..cf0eaa04b064 100644 --- a/drivers/watchdog/iTCO_vendor_support.c +++ b/drivers/watchdog/iTCO_vendor_support.c @@ -39,8 +39,10 @@ /* Broken BIOS */ #define BROKEN_BIOS 911 -static int vendorsupport; -module_param(vendorsupport, int, 0); +int iTCO_vendorsupport; +EXPORT_SYMBOL(iTCO_vendorsupport); + +module_param_named(vendorsupport, iTCO_vendorsupport, int, 0); MODULE_PARM_DESC(vendorsupport, "iTCO vendor specific support mode, default=" "0 (none), 1=SuperMicro Pent3, 911=Broken SMI BIOS"); @@ -152,7 +154,7 @@ static void broken_bios_stop(struct resource *smires) void iTCO_vendor_pre_start(struct resource *smires, unsigned int heartbeat) { - switch (vendorsupport) { + switch (iTCO_vendorsupport) { case SUPERMICRO_OLD_BOARD: supermicro_old_pre_start(smires); break; @@ -165,7 +167,7 @@ EXPORT_SYMBOL(iTCO_vendor_pre_start); void iTCO_vendor_pre_stop(struct resource *smires) { - switch (vendorsupport) { + switch (iTCO_vendorsupport) { case SUPERMICRO_OLD_BOARD: supermicro_old_pre_stop(smires); break; @@ -178,7 +180,7 @@ EXPORT_SYMBOL(iTCO_vendor_pre_stop); int iTCO_vendor_check_noreboot_on(void) { - switch (vendorsupport) { + switch (iTCO_vendorsupport) { case SUPERMICRO_OLD_BOARD: return 0; default: @@ -189,13 +191,13 @@ EXPORT_SYMBOL(iTCO_vendor_check_noreboot_on); static int __init iTCO_vendor_init_module(void) { - if (vendorsupport == SUPERMICRO_NEW_BOARD) { + if (iTCO_vendorsupport == SUPERMICRO_NEW_BOARD) { pr_warn("Option vendorsupport=%d is no longer supported, " "please use the w83627hf_wdt driver instead\n", SUPERMICRO_NEW_BOARD); return -EINVAL; } - pr_info("vendor-support=%d\n", vendorsupport); + pr_info("vendor-support=%d\n", iTCO_vendorsupport); return 0; } From e42b0c24389d5a1602e77db4f6def0d5a19e3e43 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Wed, 26 Feb 2020 16:21:21 +0300 Subject: [PATCH 159/256] watchdog: iTCO_wdt: Make ICH_RES_IO_SMI optional The iTCO_wdt driver only needs ICH_RES_IO_SMI I/O resource when either turn_SMI_watchdog_clear_off module parameter is set to match ->iTCO_version (or higher), and when legacy iTCO_vendorsupport is set. Modify the driver so that ICH_RES_IO_SMI is optional if the two conditions are not met. Signed-off-by: Mika Westerberg Reviewed-by: Guenter Roeck Signed-off-by: Wolfram Sang --- drivers/watchdog/iTCO_wdt.c | 28 ++++++++++++++++------------ 1 file changed, 16 insertions(+), 12 deletions(-) diff --git a/drivers/watchdog/iTCO_wdt.c b/drivers/watchdog/iTCO_wdt.c index 156360e37714..e707c4797f76 100644 --- a/drivers/watchdog/iTCO_wdt.c +++ b/drivers/watchdog/iTCO_wdt.c @@ -459,13 +459,25 @@ static int iTCO_wdt_probe(struct platform_device *pdev) if (!p->tco_res) return -ENODEV; - p->smi_res = platform_get_resource(pdev, IORESOURCE_IO, ICH_RES_IO_SMI); - if (!p->smi_res) - return -ENODEV; - p->iTCO_version = pdata->version; p->pci_dev = to_pci_dev(dev->parent); + p->smi_res = platform_get_resource(pdev, IORESOURCE_IO, ICH_RES_IO_SMI); + if (p->smi_res) { + /* The TCO logic uses the TCO_EN bit in the SMI_EN register */ + if (!devm_request_region(dev, p->smi_res->start, + resource_size(p->smi_res), + pdev->name)) { + pr_err("I/O address 0x%04llx already in use, device disabled\n", + (u64)SMI_EN(p)); + return -EBUSY; + } + } else if (iTCO_vendorsupport || + turn_SMI_watchdog_clear_off >= p->iTCO_version) { + pr_err("SMI I/O resource is missing\n"); + return -ENODEV; + } + iTCO_wdt_no_reboot_bit_setup(p, pdata); /* @@ -492,14 +504,6 @@ static int iTCO_wdt_probe(struct platform_device *pdev) /* Set the NO_REBOOT bit to prevent later reboots, just for sure */ p->update_no_reboot_bit(p->no_reboot_priv, true); - /* The TCO logic uses the TCO_EN bit in the SMI_EN register */ - if (!devm_request_region(dev, p->smi_res->start, - resource_size(p->smi_res), - pdev->name)) { - pr_err("I/O address 0x%04llx already in use, device disabled\n", - (u64)SMI_EN(p)); - return -EBUSY; - } if (turn_SMI_watchdog_clear_off >= p->iTCO_version) { /* * Bit 13: TCO_EN -> 0 From 04bbb97d1b732b2d197f103c5818f5c214a4cf81 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Wed, 26 Feb 2020 16:21:22 +0300 Subject: [PATCH 160/256] i2c: i801: Do not add ICH_RES_IO_SMI for the iTCO_wdt device Martin noticed that nct6775 driver does not load properly on his system in v5.4+ kernels. The issue was bisected to commit b84398d6d7f9 ("i2c: i801: Use iTCO version 6 in Cannon Lake PCH and beyond") but it is likely not the culprit because the faulty code has been in the driver already since commit 9424693035a5 ("i2c: i801: Create iTCO device on newer Intel PCHs"). So more likely some commit that added PCI IDs of recent chipsets made the driver to create the iTCO_wdt device on Martins system. The issue was debugged to be PCI configuration access to the PMC device that is not present. This returns all 1's when read and this caused the iTCO_wdt driver to accidentally request resourses used by nct6775. It turns out that the SMI resource is only required for some ancient systems, not the ones supported by this driver. For this reason do not populate the SMI resource at all and drop all the related code. The driver now always populates the main I/O resource and only in case of SPT (Intel Sunrisepoint) compatible devices it adds another resource for the NO_REBOOT bit. These two resources are of different types so platform_get_resource() used by the iTCO_wdt driver continues to find the both resources at index 0. Link: https://lore.kernel.org/linux-hwmon/CAM1AHpQ4196tyD=HhBu-2donSsuogabkfP03v1YF26Q7_BgvgA@mail.gmail.com/ Fixes: 9424693035a5 ("i2c: i801: Create iTCO device on newer Intel PCHs") [wsa: complete fix needs all of http://patchwork.ozlabs.org/project/linux-i2c/list/?series=160959&state=*] Reported-by: Martin Volf Signed-off-by: Mika Westerberg Reviewed-by: Guenter Roeck Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-i801.c | 45 ++++++++++------------------------- 1 file changed, 12 insertions(+), 33 deletions(-) diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index ca4f096fef74..a9c03f5c3482 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -132,11 +132,6 @@ #define TCOBASE 0x050 #define TCOCTL 0x054 -#define ACPIBASE 0x040 -#define ACPIBASE_SMI_OFF 0x030 -#define ACPICTRL 0x044 -#define ACPICTRL_EN 0x080 - #define SBREG_BAR 0x10 #define SBREG_SMBCTRL 0xc6000c #define SBREG_SMBCTRL_DNV 0xcf000c @@ -1553,7 +1548,7 @@ i801_add_tco_spt(struct i801_priv *priv, struct pci_dev *pci_dev, pci_bus_write_config_byte(pci_dev->bus, devfn, 0xe1, hidden); spin_unlock(&p2sb_spinlock); - res = &tco_res[ICH_RES_MEM_OFF]; + res = &tco_res[1]; if (pci_dev->device == PCI_DEVICE_ID_INTEL_DNV_SMBUS) res->start = (resource_size_t)base64_addr + SBREG_SMBCTRL_DNV; else @@ -1563,7 +1558,7 @@ i801_add_tco_spt(struct i801_priv *priv, struct pci_dev *pci_dev, res->flags = IORESOURCE_MEM; return platform_device_register_resndata(&pci_dev->dev, "iTCO_wdt", -1, - tco_res, 3, &spt_tco_platform_data, + tco_res, 2, &spt_tco_platform_data, sizeof(spt_tco_platform_data)); } @@ -1576,17 +1571,16 @@ static struct platform_device * i801_add_tco_cnl(struct i801_priv *priv, struct pci_dev *pci_dev, struct resource *tco_res) { - return platform_device_register_resndata(&pci_dev->dev, "iTCO_wdt", -1, - tco_res, 2, &cnl_tco_platform_data, - sizeof(cnl_tco_platform_data)); + return platform_device_register_resndata(&pci_dev->dev, + "iTCO_wdt", -1, tco_res, 1, &cnl_tco_platform_data, + sizeof(cnl_tco_platform_data)); } static void i801_add_tco(struct i801_priv *priv) { - u32 base_addr, tco_base, tco_ctl, ctrl_val; struct pci_dev *pci_dev = priv->pci_dev; - struct resource tco_res[3], *res; - unsigned int devfn; + struct resource tco_res[2], *res; + u32 tco_base, tco_ctl; /* If we have ACPI based watchdog use that instead */ if (acpi_has_watchdog()) @@ -1601,30 +1595,15 @@ static void i801_add_tco(struct i801_priv *priv) return; memset(tco_res, 0, sizeof(tco_res)); - - res = &tco_res[ICH_RES_IO_TCO]; + /* + * Always populate the main iTCO IO resource here. The second entry + * for NO_REBOOT MMIO is filled by the SPT specific function. + */ + res = &tco_res[0]; res->start = tco_base & ~1; res->end = res->start + 32 - 1; res->flags = IORESOURCE_IO; - /* - * Power Management registers. - */ - devfn = PCI_DEVFN(PCI_SLOT(pci_dev->devfn), 2); - pci_bus_read_config_dword(pci_dev->bus, devfn, ACPIBASE, &base_addr); - - res = &tco_res[ICH_RES_IO_SMI]; - res->start = (base_addr & ~1) + ACPIBASE_SMI_OFF; - res->end = res->start + 3; - res->flags = IORESOURCE_IO; - - /* - * Enable the ACPI I/O space. - */ - pci_bus_read_config_dword(pci_dev->bus, devfn, ACPICTRL, &ctrl_val); - ctrl_val |= ACPICTRL_EN; - pci_bus_write_config_dword(pci_dev->bus, devfn, ACPICTRL, ctrl_val); - if (priv->features & FEATURE_TCO_CNL) priv->tco_pdev = i801_add_tco_cnl(priv, pci_dev, tco_res); else From 2d48ea0efb8887ebba3e3720bb5b738aced4e574 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Thu, 5 Mar 2020 15:00:46 -0500 Subject: [PATCH 161/256] iommu/vt-d: Fix RCU-list bugs in intel_iommu_init() There are several places traverse RCU-list without holding any lock in intel_iommu_init(). Fix them by acquiring dmar_global_lock. WARNING: suspicious RCU usage ----------------------------- drivers/iommu/intel-iommu.c:5216 RCU-list traversed in non-reader section!! other info that might help us debug this: rcu_scheduler_active = 2, debug_locks = 1 no locks held by swapper/0/1. Call Trace: dump_stack+0xa0/0xea lockdep_rcu_suspicious+0x102/0x10b intel_iommu_init+0x947/0xb13 pci_iommu_init+0x26/0x62 do_one_initcall+0xfe/0x500 kernel_init_freeable+0x45a/0x4f8 kernel_init+0x11/0x139 ret_from_fork+0x3a/0x50 DMAR: Intel(R) Virtualization Technology for Directed I/O Fixes: d8190dc63886 ("iommu/vt-d: Enable DMA remapping after rmrr mapped") Signed-off-by: Qian Cai Acked-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel-iommu.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 33593fea0250..693380355dea 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -5193,6 +5193,7 @@ int __init intel_iommu_init(void) init_iommu_pm_ops(); + down_read(&dmar_global_lock); for_each_active_iommu(iommu, drhd) { iommu_device_sysfs_add(&iommu->iommu, NULL, intel_iommu_groups, @@ -5200,6 +5201,7 @@ int __init intel_iommu_init(void) iommu_device_set_ops(&iommu->iommu, &intel_iommu_ops); iommu_device_register(&iommu->iommu); } + up_read(&dmar_global_lock); bus_set_iommu(&pci_bus_type, &intel_iommu_ops); if (si_domain && !hw_pass_through) @@ -5210,7 +5212,6 @@ int __init intel_iommu_init(void) down_read(&dmar_global_lock); if (probe_acpi_namespace_devices()) pr_warn("ACPI name space devices didn't probe correctly\n"); - up_read(&dmar_global_lock); /* Finally, we enable the DMA remapping hardware. */ for_each_iommu(iommu, drhd) { @@ -5219,6 +5220,8 @@ int __init intel_iommu_init(void) iommu_disable_protect_mem_regions(iommu); } + up_read(&dmar_global_lock); + pr_info("Intel(R) Virtualization Technology for Directed I/O\n"); intel_iommu_enabled = 1; From f5152416528c2295f35dd9c9bd4fb27c4032413d Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Thu, 5 Mar 2020 15:15:02 -0500 Subject: [PATCH 162/256] iommu/vt-d: Silence RCU-list debugging warnings Similar to the commit 02d715b4a818 ("iommu/vt-d: Fix RCU list debugging warnings"), there are several other places that call list_for_each_entry_rcu() outside of an RCU read side critical section but with dmar_global_lock held. Silence those false positives as well. drivers/iommu/intel-iommu.c:4288 RCU-list traversed in non-reader section!! 1 lock held by swapper/0/1: #0: ffffffff935892c8 (dmar_global_lock){+.+.}, at: intel_iommu_init+0x1ad/0xb97 drivers/iommu/dmar.c:366 RCU-list traversed in non-reader section!! 1 lock held by swapper/0/1: #0: ffffffff935892c8 (dmar_global_lock){+.+.}, at: intel_iommu_init+0x125/0xb97 drivers/iommu/intel-iommu.c:5057 RCU-list traversed in non-reader section!! 1 lock held by swapper/0/1: #0: ffffffffa71892c8 (dmar_global_lock){++++}, at: intel_iommu_init+0x61a/0xb13 Signed-off-by: Qian Cai Acked-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/dmar.c | 3 ++- include/linux/dmar.h | 6 ++++-- 2 files changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index 071bb42bbbc5..7b16c4db40b4 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -363,7 +363,8 @@ dmar_find_dmaru(struct acpi_dmar_hardware_unit *drhd) { struct dmar_drhd_unit *dmaru; - list_for_each_entry_rcu(dmaru, &dmar_drhd_units, list) + list_for_each_entry_rcu(dmaru, &dmar_drhd_units, list, + dmar_rcu_check()) if (dmaru->segment == drhd->segment && dmaru->reg_base_addr == drhd->address) return dmaru; diff --git a/include/linux/dmar.h b/include/linux/dmar.h index 712be8bc6a7c..d7bf029df737 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -74,11 +74,13 @@ extern struct list_head dmar_drhd_units; dmar_rcu_check()) #define for_each_active_drhd_unit(drhd) \ - list_for_each_entry_rcu(drhd, &dmar_drhd_units, list) \ + list_for_each_entry_rcu(drhd, &dmar_drhd_units, list, \ + dmar_rcu_check()) \ if (drhd->ignored) {} else #define for_each_active_iommu(i, drhd) \ - list_for_each_entry_rcu(drhd, &dmar_drhd_units, list) \ + list_for_each_entry_rcu(drhd, &dmar_drhd_units, list, \ + dmar_rcu_check()) \ if (i=drhd->iommu, drhd->ignored) {} else #define for_each_iommu(i, drhd) \ From 9be8bc4dd6177cf992b93b0bd014c4f611283896 Mon Sep 17 00:00:00 2001 From: Jarkko Nikula Date: Thu, 13 Feb 2020 17:15:03 +0200 Subject: [PATCH 163/256] i2c: designware-pci: Fix BUG_ON during device removal Function i2c_dw_pci_remove() -> pci_free_irq_vectors() -> pci_disable_msi() -> free_msi_irqs() will throw a BUG_ON() for MSI enabled device since the driver has not released the requested IRQ before calling the pci_free_irq_vectors(). Here driver requests an IRQ using devm_request_irq() but automatic release happens only after remove callback. Fix this by explicitly freeing the IRQ before calling pci_free_irq_vectors(). Fixes: 21aa3983d619 ("i2c: designware-pci: Switch over to MSI interrupts") Cc: stable@vger.kernel.org # v5.4+ Signed-off-by: Jarkko Nikula Reviewed-by: Andy Shevchenko Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-designware-pcidrv.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/i2c/busses/i2c-designware-pcidrv.c b/drivers/i2c/busses/i2c-designware-pcidrv.c index 050adda7c1bd..05b35ac33ce3 100644 --- a/drivers/i2c/busses/i2c-designware-pcidrv.c +++ b/drivers/i2c/busses/i2c-designware-pcidrv.c @@ -313,6 +313,7 @@ static void i2c_dw_pci_remove(struct pci_dev *pdev) pm_runtime_get_noresume(&pdev->dev); i2c_del_adapter(&dev->adapter); + devm_free_irq(&pdev->dev, dev->irq, dev); pci_free_irq_vectors(pdev); } From bcf3588d8ed3517e6ffaf083f034812aee9dc8e2 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Tue, 3 Mar 2020 13:50:46 +0100 Subject: [PATCH 164/256] macintosh: windfarm: fix MODINFO regression Commit af503716ac14 made sure OF devices get an OF style modalias with I2C events. It assumed all in-tree users were converted, yet it missed some Macintosh drivers. Add an OF module device table for all windfarm drivers to make them automatically load again. Fixes: af503716ac14 ("i2c: core: report OF style module alias for devices registered via OF") Link: https://bugzilla.kernel.org/show_bug.cgi?id=199471 Reported-by: Erhard Furtner Tested-by: Erhard Furtner Acked-by: Michael Ellerman (powerpc) Signed-off-by: Wolfram Sang Cc: stable@kernel.org # v4.17+ --- drivers/macintosh/windfarm_ad7417_sensor.c | 7 +++++++ drivers/macintosh/windfarm_fcu_controls.c | 7 +++++++ drivers/macintosh/windfarm_lm75_sensor.c | 16 +++++++++++++++- drivers/macintosh/windfarm_lm87_sensor.c | 7 +++++++ drivers/macintosh/windfarm_max6690_sensor.c | 7 +++++++ drivers/macintosh/windfarm_smu_sat.c | 7 +++++++ 6 files changed, 50 insertions(+), 1 deletion(-) diff --git a/drivers/macintosh/windfarm_ad7417_sensor.c b/drivers/macintosh/windfarm_ad7417_sensor.c index 125605987b44..e7dec328c7cf 100644 --- a/drivers/macintosh/windfarm_ad7417_sensor.c +++ b/drivers/macintosh/windfarm_ad7417_sensor.c @@ -312,9 +312,16 @@ static const struct i2c_device_id wf_ad7417_id[] = { }; MODULE_DEVICE_TABLE(i2c, wf_ad7417_id); +static const struct of_device_id wf_ad7417_of_id[] = { + { .compatible = "ad7417", }, + { } +}; +MODULE_DEVICE_TABLE(of, wf_ad7417_of_id); + static struct i2c_driver wf_ad7417_driver = { .driver = { .name = "wf_ad7417", + .of_match_table = wf_ad7417_of_id, }, .probe = wf_ad7417_probe, .remove = wf_ad7417_remove, diff --git a/drivers/macintosh/windfarm_fcu_controls.c b/drivers/macintosh/windfarm_fcu_controls.c index 67daeec94b44..2470e5a725c8 100644 --- a/drivers/macintosh/windfarm_fcu_controls.c +++ b/drivers/macintosh/windfarm_fcu_controls.c @@ -580,9 +580,16 @@ static const struct i2c_device_id wf_fcu_id[] = { }; MODULE_DEVICE_TABLE(i2c, wf_fcu_id); +static const struct of_device_id wf_fcu_of_id[] = { + { .compatible = "fcu", }, + { } +}; +MODULE_DEVICE_TABLE(of, wf_fcu_of_id); + static struct i2c_driver wf_fcu_driver = { .driver = { .name = "wf_fcu", + .of_match_table = wf_fcu_of_id, }, .probe = wf_fcu_probe, .remove = wf_fcu_remove, diff --git a/drivers/macintosh/windfarm_lm75_sensor.c b/drivers/macintosh/windfarm_lm75_sensor.c index 282c28a17ea1..1e5fa09845e7 100644 --- a/drivers/macintosh/windfarm_lm75_sensor.c +++ b/drivers/macintosh/windfarm_lm75_sensor.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -91,9 +92,14 @@ static int wf_lm75_probe(struct i2c_client *client, const struct i2c_device_id *id) { struct wf_lm75_sensor *lm; - int rc, ds1775 = id->driver_data; + int rc, ds1775; const char *name, *loc; + if (id) + ds1775 = id->driver_data; + else + ds1775 = !!of_device_get_match_data(&client->dev); + DBG("wf_lm75: creating %s device at address 0x%02x\n", ds1775 ? "ds1775" : "lm75", client->addr); @@ -164,9 +170,17 @@ static const struct i2c_device_id wf_lm75_id[] = { }; MODULE_DEVICE_TABLE(i2c, wf_lm75_id); +static const struct of_device_id wf_lm75_of_id[] = { + { .compatible = "lm75", .data = (void *)0}, + { .compatible = "ds1775", .data = (void *)1 }, + { } +}; +MODULE_DEVICE_TABLE(of, wf_lm75_of_id); + static struct i2c_driver wf_lm75_driver = { .driver = { .name = "wf_lm75", + .of_match_table = wf_lm75_of_id, }, .probe = wf_lm75_probe, .remove = wf_lm75_remove, diff --git a/drivers/macintosh/windfarm_lm87_sensor.c b/drivers/macintosh/windfarm_lm87_sensor.c index b03a33b803b7..d011899c0a8a 100644 --- a/drivers/macintosh/windfarm_lm87_sensor.c +++ b/drivers/macintosh/windfarm_lm87_sensor.c @@ -166,9 +166,16 @@ static const struct i2c_device_id wf_lm87_id[] = { }; MODULE_DEVICE_TABLE(i2c, wf_lm87_id); +static const struct of_device_id wf_lm87_of_id[] = { + { .compatible = "lm87cimt", }, + { } +}; +MODULE_DEVICE_TABLE(of, wf_lm87_of_id); + static struct i2c_driver wf_lm87_driver = { .driver = { .name = "wf_lm87", + .of_match_table = wf_lm87_of_id, }, .probe = wf_lm87_probe, .remove = wf_lm87_remove, diff --git a/drivers/macintosh/windfarm_max6690_sensor.c b/drivers/macintosh/windfarm_max6690_sensor.c index e666cc020683..1e7b03d44ad9 100644 --- a/drivers/macintosh/windfarm_max6690_sensor.c +++ b/drivers/macintosh/windfarm_max6690_sensor.c @@ -120,9 +120,16 @@ static const struct i2c_device_id wf_max6690_id[] = { }; MODULE_DEVICE_TABLE(i2c, wf_max6690_id); +static const struct of_device_id wf_max6690_of_id[] = { + { .compatible = "max6690", }, + { } +}; +MODULE_DEVICE_TABLE(of, wf_max6690_of_id); + static struct i2c_driver wf_max6690_driver = { .driver = { .name = "wf_max6690", + .of_match_table = wf_max6690_of_id, }, .probe = wf_max6690_probe, .remove = wf_max6690_remove, diff --git a/drivers/macintosh/windfarm_smu_sat.c b/drivers/macintosh/windfarm_smu_sat.c index c84ec49c3741..cb75dc035616 100644 --- a/drivers/macintosh/windfarm_smu_sat.c +++ b/drivers/macintosh/windfarm_smu_sat.c @@ -341,9 +341,16 @@ static const struct i2c_device_id wf_sat_id[] = { }; MODULE_DEVICE_TABLE(i2c, wf_sat_id); +static const struct of_device_id wf_sat_of_id[] = { + { .compatible = "smu-sat", }, + { } +}; +MODULE_DEVICE_TABLE(of, wf_sat_of_id); + static struct i2c_driver wf_sat_driver = { .driver = { .name = "wf_smu_sat", + .of_match_table = wf_sat_of_id, }, .probe = wf_sat_probe, .remove = wf_sat_remove, From 3747cd2efe7ecb9604972285ab3f60c96cb753a8 Mon Sep 17 00:00:00 2001 From: Hamish Martin Date: Tue, 10 Mar 2020 10:16:18 +1300 Subject: [PATCH 165/256] i2c: gpio: suppress error on probe defer If a GPIO we are trying to use is not available and we are deferring the probe, don't output an error message. This seems to have been the intent of commit 05c74778858d ("i2c: gpio: Add support for named gpios in DT") but the error was still output due to not checking the updated 'retdesc'. Fixes: 05c74778858d ("i2c: gpio: Add support for named gpios in DT") Signed-off-by: Hamish Martin Acked-by: Linus Walleij Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-gpio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/i2c/busses/i2c-gpio.c b/drivers/i2c/busses/i2c-gpio.c index 3a9e840a3546..a4a6825c8758 100644 --- a/drivers/i2c/busses/i2c-gpio.c +++ b/drivers/i2c/busses/i2c-gpio.c @@ -348,7 +348,7 @@ static struct gpio_desc *i2c_gpio_get_desc(struct device *dev, if (ret == -ENOENT) retdesc = ERR_PTR(-EPROBE_DEFER); - if (ret != -EPROBE_DEFER) + if (PTR_ERR(retdesc) != -EPROBE_DEFER) dev_err(dev, "error trying to get descriptor: %d\n", ret); return retdesc; From aa202f1f56960c60e7befaa0f49c72b8fa11b0a8 Mon Sep 17 00:00:00 2001 From: Hillf Danton Date: Fri, 24 Jan 2020 20:14:45 -0500 Subject: [PATCH 166/256] workqueue: don't use wq_select_unbound_cpu() for bound works wq_select_unbound_cpu() is designed for unbound workqueues only, but it's wrongly called when using a bound workqueue too. Fixing this ensures work queued to a bound workqueue with cpu=WORK_CPU_UNBOUND always runs on the local CPU. Before, that would happen only if wq_unbound_cpumask happened to include it (likely almost always the case), or was empty, or we got lucky with forced round-robin placement. So restricting /sys/devices/virtual/workqueue/cpumask to a small subset of a machine's CPUs would cause some bound work items to run unexpectedly there. Fixes: ef557180447f ("workqueue: schedule WORK_CPU_UNBOUND work on wq_unbound_cpumask CPUs") Cc: stable@vger.kernel.org # v4.5+ Signed-off-by: Hillf Danton [dj: massage changelog] Signed-off-by: Daniel Jordan Cc: Tejun Heo Cc: Lai Jiangshan Cc: linux-kernel@vger.kernel.org Signed-off-by: Tejun Heo --- kernel/workqueue.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 301db4406bc3..4e01c448b4b4 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1411,14 +1411,16 @@ static void __queue_work(int cpu, struct workqueue_struct *wq, return; rcu_read_lock(); retry: - if (req_cpu == WORK_CPU_UNBOUND) - cpu = wq_select_unbound_cpu(raw_smp_processor_id()); - /* pwq which will be used unless @work is executing elsewhere */ - if (!(wq->flags & WQ_UNBOUND)) - pwq = per_cpu_ptr(wq->cpu_pwqs, cpu); - else + if (wq->flags & WQ_UNBOUND) { + if (req_cpu == WORK_CPU_UNBOUND) + cpu = wq_select_unbound_cpu(raw_smp_processor_id()); pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu)); + } else { + if (req_cpu == WORK_CPU_UNBOUND) + cpu = raw_smp_processor_id(); + pwq = per_cpu_ptr(wq->cpu_pwqs, cpu); + } /* * If @work was previously on a different pool, it might still be From dcd6589b11d3b1e71f516a87a7b9646ed356b4c0 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 10 Mar 2020 13:07:46 -0400 Subject: [PATCH 167/256] blk-iocost: fix incorrect vtime comparison in iocg_is_idle() vtimes may wrap and time_before/after64() should be used to determine whether a given vtime is before or after another. iocg_is_idle() was incorrectly using plain "<" comparison do determine whether done_vtime is before vtime. Here, the only thing we're interested in is whether done_vtime matches vtime which indicates that there's nothing in flight. Let's test for inequality instead. Signed-off-by: Tejun Heo Fixes: 7caa47151ab2 ("blkcg: implement blk-iocost") Cc: stable@vger.kernel.org # v5.4+ Signed-off-by: Jens Axboe --- block/blk-iocost.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 27ca68621137..9a599cc28c29 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -1318,7 +1318,7 @@ static bool iocg_is_idle(struct ioc_gq *iocg) return false; /* is something in flight? */ - if (atomic64_read(&iocg->done_vtime) < atomic64_read(&iocg->vtime)) + if (atomic64_read(&iocg->done_vtime) != atomic64_read(&iocg->vtime)) return false; return true; From 1d2686d417c5998af3817f93be01745b3db57ecd Mon Sep 17 00:00:00 2001 From: Hersen Wu Date: Thu, 13 Feb 2020 10:42:25 -0500 Subject: [PATCH 168/256] drm/amdgpu/powerplay: nv1x, renior copy dcn clock settings of watermark to smu during boot up dc to pplib interface is changed for navi1x, renoir. display_config_changed is not called by dc anymore. smu_write_watermarks_table is not executed for navi1x, renoir during boot up. solution: call smu_write_watermarks_table just after dc pass watermark clock settings to pplib Signed-off-by: Hersen Wu Reviewed-by: Evan Quan Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/powerplay/amdgpu_smu.c | 7 +++++-- drivers/gpu/drm/amd/powerplay/navi10_ppt.c | 22 +++++++++++++--------- drivers/gpu/drm/amd/powerplay/renoir_ppt.c | 5 +++-- 3 files changed, 21 insertions(+), 13 deletions(-) diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c index ad8e9b5628e4..96e81c7bc266 100644 --- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c @@ -2006,8 +2006,11 @@ int smu_set_watermarks_for_clock_ranges(struct smu_context *smu, smu_feature_is_enabled(smu, SMU_FEATURE_DPM_DCEFCLK_BIT) && smu_feature_is_enabled(smu, SMU_FEATURE_DPM_SOCCLK_BIT)) { smu_set_watermarks_table(smu, table, clock_ranges); - smu->watermarks_bitmap |= WATERMARKS_EXIST; - smu->watermarks_bitmap &= ~WATERMARKS_LOADED; + + if (!(smu->watermarks_bitmap & WATERMARKS_EXIST)) { + smu->watermarks_bitmap |= WATERMARKS_EXIST; + smu->watermarks_bitmap &= ~WATERMARKS_LOADED; + } } mutex_unlock(&smu->mutex); diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c index 0d73a49166af..aed4d6e60907 100644 --- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c @@ -1062,15 +1062,6 @@ static int navi10_display_config_changed(struct smu_context *smu) { int ret = 0; - if ((smu->watermarks_bitmap & WATERMARKS_EXIST) && - !(smu->watermarks_bitmap & WATERMARKS_LOADED)) { - ret = smu_write_watermarks_table(smu); - if (ret) - return ret; - - smu->watermarks_bitmap |= WATERMARKS_LOADED; - } - if ((smu->watermarks_bitmap & WATERMARKS_EXIST) && smu_feature_is_supported(smu, SMU_FEATURE_DPM_DCEFCLK_BIT) && smu_feature_is_supported(smu, SMU_FEATURE_DPM_SOCCLK_BIT)) { @@ -1493,6 +1484,7 @@ static int navi10_set_watermarks_table(struct smu_context *smu, *clock_ranges) { int i; + int ret = 0; Watermarks_t *table = watermarks; if (!table || !clock_ranges) @@ -1544,6 +1536,18 @@ static int navi10_set_watermarks_table(struct smu_context *smu, clock_ranges->wm_mcif_clocks_ranges[i].wm_set_id; } + smu->watermarks_bitmap |= WATERMARKS_EXIST; + + /* pass data to smu controller */ + if (!(smu->watermarks_bitmap & WATERMARKS_LOADED)) { + ret = smu_write_watermarks_table(smu); + if (ret) { + pr_err("Failed to update WMTABLE!"); + return ret; + } + smu->watermarks_bitmap |= WATERMARKS_LOADED; + } + return 0; } diff --git a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c index 568c041c2206..3ad0f4aa3aa3 100644 --- a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c @@ -806,9 +806,10 @@ static int renoir_set_watermarks_table( clock_ranges->wm_mcif_clocks_ranges[i].wm_set_id; } + smu->watermarks_bitmap |= WATERMARKS_EXIST; + /* pass data to smu controller */ - if ((smu->watermarks_bitmap & WATERMARKS_EXIST) && - !(smu->watermarks_bitmap & WATERMARKS_LOADED)) { + if (!(smu->watermarks_bitmap & WATERMARKS_LOADED)) { ret = smu_write_watermarks_table(smu); if (ret) { pr_err("Failed to update WMTABLE!"); From 65dfcf08072b072b633ba9a693ed48a53919b45f Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 9 Mar 2020 20:11:42 -0700 Subject: [PATCH 169/256] MAINTAINERS: update cxgb4vf maintainer to Vishal Casey Leedomn is bouncing, Vishal indicated he's happy to take the role. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index b1935c2ae118..6693ce1b9e21 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4571,7 +4571,7 @@ F: drivers/infiniband/hw/cxgb4/ F: include/uapi/rdma/cxgb4-abi.h CXGB4VF ETHERNET DRIVER (CXGB4VF) -M: Casey Leedom +M: Vishal Kulkarni L: netdev@vger.kernel.org W: http://www.chelsio.com S: Supported From e876ecc67db80dfdb8e237f71e5b43bb88ae549c Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Mon, 9 Mar 2020 22:16:05 -0700 Subject: [PATCH 170/256] cgroup: memcg: net: do not associate sock with unrelated cgroup We are testing network memory accounting in our setup and noticed inconsistent network memory usage and often unrelated cgroups network usage correlates with testing workload. On further inspection, it seems like mem_cgroup_sk_alloc() and cgroup_sk_alloc() are broken in irq context specially for cgroup v1. mem_cgroup_sk_alloc() and cgroup_sk_alloc() can be called in irq context and kind of assumes that this can only happen from sk_clone_lock() and the source sock object has already associated cgroup. However in cgroup v1, where network memory accounting is opt-in, the source sock can be unassociated with any cgroup and the new cloned sock can get associated with unrelated interrupted cgroup. Cgroup v2 can also suffer if the source sock object was created by process in the root cgroup or if sk_alloc() is called in irq context. The fix is to just do nothing in interrupt. WARNING: Please note that about half of the TCP sockets are allocated from the IRQ context, so, memory used by such sockets will not be accouted by the memcg. The stack trace of mem_cgroup_sk_alloc() from IRQ-context: CPU: 70 PID: 12720 Comm: ssh Tainted: 5.6.0-smp-DEV #1 Hardware name: ... Call Trace: dump_stack+0x57/0x75 mem_cgroup_sk_alloc+0xe9/0xf0 sk_clone_lock+0x2a7/0x420 inet_csk_clone_lock+0x1b/0x110 tcp_create_openreq_child+0x23/0x3b0 tcp_v6_syn_recv_sock+0x88/0x730 tcp_check_req+0x429/0x560 tcp_v6_rcv+0x72d/0xa40 ip6_protocol_deliver_rcu+0xc9/0x400 ip6_input+0x44/0xd0 ? ip6_protocol_deliver_rcu+0x400/0x400 ip6_rcv_finish+0x71/0x80 ipv6_rcv+0x5b/0xe0 ? ip6_sublist_rcv+0x2e0/0x2e0 process_backlog+0x108/0x1e0 net_rx_action+0x26b/0x460 __do_softirq+0x104/0x2a6 do_softirq_own_stack+0x2a/0x40 do_softirq.part.19+0x40/0x50 __local_bh_enable_ip+0x51/0x60 ip6_finish_output2+0x23d/0x520 ? ip6table_mangle_hook+0x55/0x160 __ip6_finish_output+0xa1/0x100 ip6_finish_output+0x30/0xd0 ip6_output+0x73/0x120 ? __ip6_finish_output+0x100/0x100 ip6_xmit+0x2e3/0x600 ? ipv6_anycast_cleanup+0x50/0x50 ? inet6_csk_route_socket+0x136/0x1e0 ? skb_free_head+0x1e/0x30 inet6_csk_xmit+0x95/0xf0 __tcp_transmit_skb+0x5b4/0xb20 __tcp_send_ack.part.60+0xa3/0x110 tcp_send_ack+0x1d/0x20 tcp_rcv_state_process+0xe64/0xe80 ? tcp_v6_connect+0x5d1/0x5f0 tcp_v6_do_rcv+0x1b1/0x3f0 ? tcp_v6_do_rcv+0x1b1/0x3f0 __release_sock+0x7f/0xd0 release_sock+0x30/0xa0 __inet_stream_connect+0x1c3/0x3b0 ? prepare_to_wait+0xb0/0xb0 inet_stream_connect+0x3b/0x60 __sys_connect+0x101/0x120 ? __sys_getsockopt+0x11b/0x140 __x64_sys_connect+0x1a/0x20 do_syscall_64+0x51/0x200 entry_SYSCALL_64_after_hwframe+0x44/0xa9 The stack trace of mem_cgroup_sk_alloc() from IRQ-context: Fixes: 2d7580738345 ("mm: memcontrol: consolidate cgroup socket tracking") Fixes: d979a39d7242 ("cgroup: duplicate cgroup reference when cloning sockets") Signed-off-by: Shakeel Butt Reviewed-by: Roman Gushchin Signed-off-by: David S. Miller --- kernel/cgroup/cgroup.c | 4 ++++ mm/memcontrol.c | 4 ++++ 2 files changed, 8 insertions(+) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 75f687301bbf..6b2fc56b2201 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -6258,6 +6258,10 @@ void cgroup_sk_alloc(struct sock_cgroup_data *skcd) return; } + /* Don't associate the sock with unrelated interrupted task's cgroup. */ + if (in_interrupt()) + return; + rcu_read_lock(); while (true) { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index d09776cd6e10..1cf41ee22258 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -6696,6 +6696,10 @@ void mem_cgroup_sk_alloc(struct sock *sk) return; } + /* Do not associate the sock with unrelated interrupted task's memcg. */ + if (in_interrupt()) + return; + rcu_read_lock(); memcg = mem_cgroup_from_task(current); if (memcg == root_mem_cgroup) From d752a4986532cb6305dfd5290a614cde8072769d Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Mon, 9 Mar 2020 22:16:06 -0700 Subject: [PATCH 171/256] net: memcg: late association of sock to memcg If a TCP socket is allocated in IRQ context or cloned from unassociated (i.e. not associated to a memcg) in IRQ context then it will remain unassociated for its whole life. Almost half of the TCPs created on the system are created in IRQ context, so, memory used by such sockets will not be accounted by the memcg. This issue is more widespread in cgroup v1 where network memory accounting is opt-in but it can happen in cgroup v2 if the source socket for the cloning was created in root memcg. To fix the issue, just do the association of the sockets at the accept() time in the process context and then force charge the memory buffer already used and reserved by the socket. Signed-off-by: Shakeel Butt Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- mm/memcontrol.c | 14 -------------- net/core/sock.c | 5 ++++- net/ipv4/inet_connection_sock.c | 20 ++++++++++++++++++++ 3 files changed, 24 insertions(+), 15 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 1cf41ee22258..2058b8da18db 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -6682,20 +6682,6 @@ void mem_cgroup_sk_alloc(struct sock *sk) if (!mem_cgroup_sockets_enabled) return; - /* - * Socket cloning can throw us here with sk_memcg already - * filled. It won't however, necessarily happen from - * process context. So the test for root memcg given - * the current task's memcg won't help us in this case. - * - * Respecting the original socket's memcg is a better - * decision in this case. - */ - if (sk->sk_memcg) { - css_get(&sk->sk_memcg->css); - return; - } - /* Do not associate the sock with unrelated interrupted task's memcg. */ if (in_interrupt()) return; diff --git a/net/core/sock.c b/net/core/sock.c index a4c8fac781ff..8f71684305c3 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1830,7 +1830,10 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) atomic_set(&newsk->sk_zckey, 0); sock_reset_flag(newsk, SOCK_DONE); - mem_cgroup_sk_alloc(newsk); + + /* sk->sk_memcg will be populated at accept() time */ + newsk->sk_memcg = NULL; + cgroup_sk_alloc(&newsk->sk_cgrp_data); rcu_read_lock(); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index a4db79b1b643..65a3b2565102 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -482,6 +482,26 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern) } spin_unlock_bh(&queue->fastopenq.lock); } + + if (mem_cgroup_sockets_enabled) { + int amt; + + /* atomically get the memory usage, set and charge the + * sk->sk_memcg. + */ + lock_sock(newsk); + + /* The sk has not been accepted yet, no need to look at + * sk->sk_wmem_queued. + */ + amt = sk_mem_pages(newsk->sk_forward_alloc + + atomic_read(&sk->sk_rmem_alloc)); + mem_cgroup_sk_alloc(newsk); + if (newsk->sk_memcg && amt) + mem_cgroup_charge_skmem(newsk->sk_memcg, amt); + + release_sock(newsk); + } out: release_sock(sk); if (req) From 60380488e4e0b95e9e82aa68aa9705baa86de84c Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Tue, 10 Mar 2020 15:27:37 +0800 Subject: [PATCH 172/256] ipv6/addrconf: call ipv6_mc_up() for non-Ethernet interface MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Rafał found an issue that for non-Ethernet interface, if we down and up frequently, the memory will be consumed slowly. The reason is we add allnodes/allrouters addressed in multicast list in ipv6_add_dev(). When link down, we call ipv6_mc_down(), store all multicast addresses via mld_add_delrec(). But when link up, we don't call ipv6_mc_up() for non-Ethernet interface to remove the addresses. This makes idev->mc_tomb getting bigger and bigger. The call stack looks like: addrconf_notify(NETDEV_REGISTER) ipv6_add_dev ipv6_dev_mc_inc(ff01::1) ipv6_dev_mc_inc(ff02::1) ipv6_dev_mc_inc(ff02::2) addrconf_notify(NETDEV_UP) addrconf_dev_config /* Alas, we support only Ethernet autoconfiguration. */ return; addrconf_notify(NETDEV_DOWN) addrconf_ifdown ipv6_mc_down igmp6_group_dropped(ff02::2) mld_add_delrec(ff02::2) igmp6_group_dropped(ff02::1) igmp6_group_dropped(ff01::1) After investigating, I can't found a rule to disable multicast on non-Ethernet interface. In RFC2460, the link could be Ethernet, PPP, ATM, tunnels, etc. In IPv4, it doesn't check the dev type when calls ip_mc_up() in inetdev_event(). Even for IPv6, we don't check the dev type and call ipv6_add_dev(), ipv6_dev_mc_inc() after register device. So I think it's OK to fix this memory consumer by calling ipv6_mc_up() for non-Ethernet interface. v2: Also check IFF_MULTICAST flag to make sure the interface supports multicast Reported-by: Rafał Miłecki Tested-by: Rafał Miłecki Fixes: 74235a25c673 ("[IPV6] addrconf: Fix IPv6 on tuntap tunnels") Fixes: 1666d49e1d41 ("mld: do not remove mld souce list info when set link down") Signed-off-by: Hangbin Liu Signed-off-by: David S. Miller --- net/ipv6/addrconf.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index e6e1290ea06f..46d614b611db 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3347,6 +3347,10 @@ static void addrconf_dev_config(struct net_device *dev) (dev->type != ARPHRD_NONE) && (dev->type != ARPHRD_RAWIP)) { /* Alas, we support only Ethernet autoconfiguration. */ + idev = __in6_dev_get(dev); + if (!IS_ERR_OR_NULL(idev) && dev->flags & IFF_UP && + dev->flags & IFF_MULTICAST) + ipv6_mc_up(idev); return; } From ece0d7bd74615773268475b6b64d6f1ebbd4b4c6 Mon Sep 17 00:00:00 2001 From: Karsten Graul Date: Tue, 10 Mar 2020 09:33:30 +0100 Subject: [PATCH 173/256] net/smc: cancel event worker during device removal During IB device removal, cancel the event worker before the device structure is freed. Fixes: a4cf0443c414 ("smc: introduce SMC as an IB-client") Reported-by: syzbot+b297c6825752e7a07272@syzkaller.appspotmail.com Signed-off-by: Karsten Graul Reviewed-by: Ursula Braun Reviewed-by: Leon Romanovsky Signed-off-by: David S. Miller --- net/smc/smc_ib.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index d6ba186f67e2..05b825b3cfa4 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -582,6 +582,7 @@ static void smc_ib_remove_dev(struct ib_device *ibdev, void *client_data) smc_smcr_terminate_all(smcibdev); smc_ib_cleanup_per_ibdev(smcibdev); ib_unregister_event_handler(&smcibdev->event_handler); + cancel_work_sync(&smcibdev->port_event_work); kfree(smcibdev); } From 7d7195a026bac47ac9943f11f84b7546276209dd Mon Sep 17 00:00:00 2001 From: Juliet Kim Date: Tue, 10 Mar 2020 09:23:58 -0500 Subject: [PATCH 174/256] ibmvnic: Do not process device remove during device reset The ibmvnic driver does not check the device state when the device is removed. If the device is removed while a device reset is being processed, the remove may free structures needed by the reset, causing an oops. Fix this by checking the device state before processing device remove. Signed-off-by: Juliet Kim Signed-off-by: David S. Miller --- drivers/net/ethernet/ibm/ibmvnic.c | 24 ++++++++++++++++++++++-- drivers/net/ethernet/ibm/ibmvnic.h | 6 +++++- 2 files changed, 27 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index c75239d8820f..4bd33245bad6 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2142,6 +2142,8 @@ static void __ibmvnic_reset(struct work_struct *work) { struct ibmvnic_rwi *rwi; struct ibmvnic_adapter *adapter; + bool saved_state = false; + unsigned long flags; u32 reset_state; int rc = 0; @@ -2153,17 +2155,25 @@ static void __ibmvnic_reset(struct work_struct *work) return; } - reset_state = adapter->state; - rwi = get_next_rwi(adapter); while (rwi) { + spin_lock_irqsave(&adapter->state_lock, flags); + if (adapter->state == VNIC_REMOVING || adapter->state == VNIC_REMOVED) { + spin_unlock_irqrestore(&adapter->state_lock, flags); kfree(rwi); rc = EBUSY; break; } + if (!saved_state) { + reset_state = adapter->state; + adapter->state = VNIC_RESETTING; + saved_state = true; + } + spin_unlock_irqrestore(&adapter->state_lock, flags); + if (rwi->reset_reason == VNIC_RESET_CHANGE_PARAM) { /* CHANGE_PARAM requestor holds rtnl_lock */ rc = do_change_param_reset(adapter, rwi, reset_state); @@ -5091,6 +5101,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) __ibmvnic_delayed_reset); INIT_LIST_HEAD(&adapter->rwi_list); spin_lock_init(&adapter->rwi_lock); + spin_lock_init(&adapter->state_lock); mutex_init(&adapter->fw_lock); init_completion(&adapter->init_done); init_completion(&adapter->fw_done); @@ -5163,8 +5174,17 @@ static int ibmvnic_remove(struct vio_dev *dev) { struct net_device *netdev = dev_get_drvdata(&dev->dev); struct ibmvnic_adapter *adapter = netdev_priv(netdev); + unsigned long flags; + + spin_lock_irqsave(&adapter->state_lock, flags); + if (adapter->state == VNIC_RESETTING) { + spin_unlock_irqrestore(&adapter->state_lock, flags); + return -EBUSY; + } adapter->state = VNIC_REMOVING; + spin_unlock_irqrestore(&adapter->state_lock, flags); + rtnl_lock(); unregister_netdevice(netdev); diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index 60eccaf91b12..f8416e1d4cf0 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -941,7 +941,8 @@ enum vnic_state {VNIC_PROBING = 1, VNIC_CLOSING, VNIC_CLOSED, VNIC_REMOVING, - VNIC_REMOVED}; + VNIC_REMOVED, + VNIC_RESETTING}; enum ibmvnic_reset_reason {VNIC_RESET_FAILOVER = 1, VNIC_RESET_MOBILITY, @@ -1090,4 +1091,7 @@ struct ibmvnic_adapter { struct ibmvnic_tunables desired; struct ibmvnic_tunables fallback; + + /* Used for serializatin of state field */ + spinlock_t state_lock; }; From 6fc498bc82929ee23aa2f35a828c6178dfd3f823 Mon Sep 17 00:00:00 2001 From: Dmitry Bogdanov Date: Tue, 10 Mar 2020 18:22:24 +0300 Subject: [PATCH 175/256] net: macsec: update SCI upon MAC address change. SCI should be updated, because it contains MAC in its first 6 octets. Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver") Signed-off-by: Dmitry Bogdanov Signed-off-by: Mark Starovoytov Signed-off-by: Igor Russkikh Signed-off-by: David S. Miller --- drivers/net/macsec.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 5af424eeea86..66c6392251bc 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -424,6 +424,11 @@ static struct macsec_eth_header *macsec_ethhdr(struct sk_buff *skb) return (struct macsec_eth_header *)skb_mac_header(skb); } +static sci_t dev_to_sci(struct net_device *dev, __be16 port) +{ + return make_sci(dev->dev_addr, port); +} + static void __macsec_pn_wrapped(struct macsec_secy *secy, struct macsec_tx_sa *tx_sa) { @@ -3268,6 +3273,7 @@ static int macsec_set_mac_address(struct net_device *dev, void *p) out: ether_addr_copy(dev->dev_addr, addr->sa_data); + macsec->secy.sci = dev_to_sci(dev, MACSEC_PORT_ES); return 0; } @@ -3593,11 +3599,6 @@ static bool sci_exists(struct net_device *dev, sci_t sci) return false; } -static sci_t dev_to_sci(struct net_device *dev, __be16 port) -{ - return make_sci(dev->dev_addr, port); -} - static int macsec_add_dev(struct net_device *dev, sci_t sci, u8 icv_len) { struct macsec_dev *macsec = macsec_priv(dev); From 09f4136c5d6b4c5144a965bd086009863d58ff08 Mon Sep 17 00:00:00 2001 From: Dmitry Bogdanov Date: Tue, 10 Mar 2020 18:22:25 +0300 Subject: [PATCH 176/256] net: macsec: invoke mdo_upd_secy callback when mac address changed Notify the offload engine about MAC address change to reconfigure it accordingly. Fixes: 3cf3227a21d1 ("net: macsec: hardware offloading infrastructure") Signed-off-by: Dmitry Bogdanov Signed-off-by: Mark Starovoytov Signed-off-by: Igor Russkikh Signed-off-by: David S. Miller --- drivers/net/macsec.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 66c6392251bc..6ec6fc191a6e 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -3274,6 +3274,19 @@ static int macsec_set_mac_address(struct net_device *dev, void *p) out: ether_addr_copy(dev->dev_addr, addr->sa_data); macsec->secy.sci = dev_to_sci(dev, MACSEC_PORT_ES); + + /* If h/w offloading is available, propagate to the device */ + if (macsec_is_offloaded(macsec)) { + const struct macsec_ops *ops; + struct macsec_context ctx; + + ops = macsec_get_ops(macsec, &ctx); + if (ops) { + ctx.secy = &macsec->secy; + macsec_offload(ops->mdo_upd_secy, &ctx); + } + } + return 0; } From be7594a424b4de7473b3d726635c3bf6aa19a86e Mon Sep 17 00:00:00 2001 From: Can Guo Date: Thu, 5 Mar 2020 00:53:07 -0800 Subject: [PATCH 177/256] scsi: ufs: Fix possible unclocked access to auto hibern8 timer register Before access auto hibner8 timer register, make sure power and clock are properly configured to avoid unclocked register access. Link: https://lore.kernel.org/r/1583398391-14273-1-git-send-email-cang@codeaurora.org Fixes: ba7af5ec5126 ("scsi: ufs: export ufshcd_auto_hibern8_update for vendor usage") Reviewed-by: Stanley Chu Signed-off-by: Can Guo Signed-off-by: Martin K. Petersen --- drivers/scsi/ufs/ufshcd.c | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index abd0e6b05f79..2d705694636c 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -3884,18 +3884,25 @@ EXPORT_SYMBOL_GPL(ufshcd_uic_hibern8_exit); void ufshcd_auto_hibern8_update(struct ufs_hba *hba, u32 ahit) { unsigned long flags; + bool update = false; - if (!(hba->capabilities & MASK_AUTO_HIBERN8_SUPPORT)) + if (!ufshcd_is_auto_hibern8_supported(hba)) return; spin_lock_irqsave(hba->host->host_lock, flags); - if (hba->ahit == ahit) - goto out_unlock; - hba->ahit = ahit; - if (!pm_runtime_suspended(hba->dev)) - ufshcd_writel(hba, hba->ahit, REG_AUTO_HIBERNATE_IDLE_TIMER); -out_unlock: + if (hba->ahit != ahit) { + hba->ahit = ahit; + update = true; + } spin_unlock_irqrestore(hba->host->host_lock, flags); + + if (update && !pm_runtime_suspended(hba->dev)) { + pm_runtime_get_sync(hba->dev); + ufshcd_hold(hba, false); + ufshcd_auto_hibern8_enable(hba); + ufshcd_release(hba); + pm_runtime_put(hba->dev); + } } EXPORT_SYMBOL_GPL(ufshcd_auto_hibern8_update); From 240c1948491b81cfe40f84ea040a8f2a4966f101 Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Tue, 10 Mar 2020 18:38:01 +0100 Subject: [PATCH 178/256] s390/qeth: don't reset default_out_queue When an OSA device in prio-queue setup is reduced to 1 TX queue due to HW restrictions, we reset its the default_out_queue to 0. In the old code this was needed so that qeth_get_priority_queue() gets the queue selection right. But with proper multiqueue support we already reduced dev->real_num_tx_queues to 1, and so the stack puts all traffic on txq 0 without even calling .ndo_select_queue. Thus we can preserve the user's configuration, and apply it if the OSA device later re-gains support for multiple TX queues. Fixes: 73dc2daf110f ("s390/qeth: add TX multiqueue support for OSA devices") Signed-off-by: Julian Wiedmann Signed-off-by: David S. Miller --- drivers/s390/net/qeth_core_main.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 8ca85c8a01a1..2a05d13a0e79 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -1204,7 +1204,6 @@ static int qeth_osa_set_output_queues(struct qeth_card *card, bool single) if (count == 1) dev_info(&card->gdev->dev, "Priority Queueing not supported\n"); - card->qdio.default_out_queue = single ? 0 : QETH_DEFAULT_QUEUE; card->qdio.no_out_queues = count; return 0; } From 17413852804d7e86e6f0576cca32c1541817800e Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Tue, 10 Mar 2020 18:38:02 +0100 Subject: [PATCH 179/256] s390/qeth: handle error when backing RX buffer qeth_init_qdio_queues() fills the RX ring with an initial set of RX buffers. If qeth_init_input_buffer() fails to back one of the RX buffers with memory, we need to bail out and report the error. Fixes: 4a71df50047f ("qeth: new qeth device driver") Signed-off-by: Julian Wiedmann Signed-off-by: David S. Miller --- drivers/s390/net/qeth_core_main.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 2a05d13a0e79..d8f0c610396e 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -2624,12 +2624,12 @@ static int qeth_init_input_buffer(struct qeth_card *card, ETH_HLEN + sizeof(struct ipv6hdr)); if (!buf->rx_skb) - return 1; + return -ENOMEM; } pool_entry = qeth_find_free_buffer_pool_entry(card); if (!pool_entry) - return 1; + return -ENOBUFS; /* * since the buffer is accessed only from the input_tasklet @@ -2674,10 +2674,15 @@ static int qeth_init_qdio_queues(struct qeth_card *card) /* inbound queue */ qdio_reset_buffers(card->qdio.in_q->qdio_bufs, QDIO_MAX_BUFFERS_PER_Q); memset(&card->rx, 0, sizeof(struct qeth_rx)); + qeth_initialize_working_pool_list(card); /*give only as many buffers to hardware as we have buffer pool entries*/ - for (i = 0; i < card->qdio.in_buf_pool.buf_count - 1; ++i) - qeth_init_input_buffer(card, &card->qdio.in_q->bufs[i]); + for (i = 0; i < card->qdio.in_buf_pool.buf_count - 1; i++) { + rc = qeth_init_input_buffer(card, &card->qdio.in_q->bufs[i]); + if (rc) + return rc; + } + card->qdio.in_q->next_buf_to_init = card->qdio.in_buf_pool.buf_count - 1; rc = do_QDIO(CARD_DDEV(card), QDIO_FLAG_SYNC_INPUT, 0, 0, From 0e635c2a8713e3e013b4adcb7cb7e28a048b7c42 Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Tue, 10 Mar 2020 18:38:03 +0100 Subject: [PATCH 180/256] s390/qeth: cancel RX reclaim work earlier When qeth's napi poll code fails to refill an entirely empty RX ring, it kicks off buffer_reclaim_work to try again later. Make sure that this worker is cancelled when setting the qeth device offline. Otherwise a RX refill action can unexpectedly end up running concurrently to bigger re-configurations (eg. resizing the buffer pool), without any locking. Fixes: b333293058aa ("qeth: add support for af_iucv HiperSockets transport") Signed-off-by: Julian Wiedmann Signed-off-by: David S. Miller --- drivers/s390/net/qeth_core_main.c | 1 - drivers/s390/net/qeth_l2_main.c | 1 + drivers/s390/net/qeth_l3_main.c | 1 + 3 files changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index d8f0c610396e..a599801d7727 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -2392,7 +2392,6 @@ static void qeth_free_qdio_queues(struct qeth_card *card) return; qeth_free_cq(card); - cancel_delayed_work_sync(&card->buffer_reclaim_work); for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; ++j) { if (card->qdio.in_q->bufs[j].rx_skb) dev_kfree_skb_any(card->qdio.in_q->bufs[j].rx_skb); diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 9972d96820f3..8fb29371788b 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -284,6 +284,7 @@ static void qeth_l2_stop_card(struct qeth_card *card) if (card->state == CARD_STATE_SOFTSETUP) { qeth_clear_ipacmd_list(card); qeth_drain_output_queues(card); + cancel_delayed_work_sync(&card->buffer_reclaim_work); card->state = CARD_STATE_DOWN; } diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 317d56647a4a..82f800d1d7b3 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -1178,6 +1178,7 @@ static void qeth_l3_stop_card(struct qeth_card *card) qeth_l3_clear_ip_htable(card, 1); qeth_clear_ipacmd_list(card); qeth_drain_output_queues(card); + cancel_delayed_work_sync(&card->buffer_reclaim_work); card->state = CARD_STATE_DOWN; } From 394b61711f3ce33f75bf70a3e22938464a13b3ee Mon Sep 17 00:00:00 2001 From: Wen Xiong Date: Fri, 6 Mar 2020 09:57:28 -0600 Subject: [PATCH 181/256] scsi: ipr: Fix softlockup when rescanning devices in petitboot When trying to rescan disks in petitboot shell, we hit the following softlockup stacktrace: Kernel panic - not syncing: System is deadlocked on memory [ 241.223394] CPU: 32 PID: 693 Comm: sh Not tainted 5.4.16-openpower1 #1 [ 241.223406] Call Trace: [ 241.223415] [c0000003f07c3180] [c000000000493fc4] dump_stack+0xa4/0xd8 (unreliable) [ 241.223432] [c0000003f07c31c0] [c00000000007d4ac] panic+0x148/0x3cc [ 241.223446] [c0000003f07c3260] [c000000000114b10] out_of_memory+0x468/0x4c4 [ 241.223461] [c0000003f07c3300] [c0000000001472b0] __alloc_pages_slowpath+0x594/0x6d8 [ 241.223476] [c0000003f07c3420] [c00000000014757c] __alloc_pages_nodemask+0x188/0x1a4 [ 241.223492] [c0000003f07c34a0] [c000000000153e10] alloc_pages_current+0xcc/0xd8 [ 241.223508] [c0000003f07c34e0] [c0000000001577ac] alloc_slab_page+0x30/0x98 [ 241.223524] [c0000003f07c3520] [c0000000001597fc] new_slab+0x138/0x40c [ 241.223538] [c0000003f07c35f0] [c00000000015b204] ___slab_alloc+0x1e4/0x404 [ 241.223552] [c0000003f07c36c0] [c00000000015b450] __slab_alloc+0x2c/0x48 [ 241.223566] [c0000003f07c36f0] [c00000000015b754] kmem_cache_alloc_node+0x9c/0x1b4 [ 241.223582] [c0000003f07c3760] [c000000000218c48] blk_alloc_queue_node+0x34/0x270 [ 241.223599] [c0000003f07c37b0] [c000000000226574] blk_mq_init_queue+0x2c/0x78 [ 241.223615] [c0000003f07c37e0] [c0000000002ff710] scsi_mq_alloc_queue+0x28/0x70 [ 241.223631] [c0000003f07c3810] [c0000000003005b8] scsi_alloc_sdev+0x184/0x264 [ 241.223647] [c0000003f07c38a0] [c000000000300ba0] scsi_probe_and_add_lun+0x288/0xa3c [ 241.223663] [c0000003f07c3a00] [c000000000301768] __scsi_scan_target+0xcc/0x478 [ 241.223679] [c0000003f07c3b20] [c000000000301c64] scsi_scan_channel.part.9+0x74/0x7c [ 241.223696] [c0000003f07c3b70] [c000000000301df4] scsi_scan_host_selected+0xe0/0x158 [ 241.223712] [c0000003f07c3bd0] [c000000000303f04] store_scan+0x104/0x114 [ 241.223727] [c0000003f07c3cb0] [c0000000002d5ac4] dev_attr_store+0x30/0x4c [ 241.223741] [c0000003f07c3cd0] [c0000000001dbc34] sysfs_kf_write+0x64/0x78 [ 241.223756] [c0000003f07c3cf0] [c0000000001da858] kernfs_fop_write+0x170/0x1b8 [ 241.223773] [c0000003f07c3d40] [c0000000001621fc] __vfs_write+0x34/0x60 [ 241.223787] [c0000003f07c3d60] [c000000000163c2c] vfs_write+0xa8/0xcc [ 241.223802] [c0000003f07c3db0] [c000000000163df4] ksys_write+0x70/0xbc [ 241.223816] [c0000003f07c3e20] [c00000000000b40c] system_call+0x5c/0x68 As a part of the scan process Linux will allocate and configure a scsi_device for each target to be scanned. If the device is not present, then the scsi_device is torn down. As a part of scsi_device teardown a workqueue item will be scheduled and the lockups we see are because there are 250k workqueue items to be processed. Accoding to the specification of SIS-64 sas controller, max_channel should be decreased on SIS-64 adapters to 4. The patch fixes softlockup issue. Thanks for Oliver Halloran's help with debugging and explanation! Link: https://lore.kernel.org/r/1583510248-23672-1-git-send-email-wenxiong@linux.vnet.ibm.com Signed-off-by: Wen Xiong Signed-off-by: Martin K. Petersen --- drivers/scsi/ipr.c | 3 ++- drivers/scsi/ipr.h | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index ae45cbe98ae2..cd8db1349871 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -9950,6 +9950,7 @@ static void ipr_init_ioa_cfg(struct ipr_ioa_cfg *ioa_cfg, ioa_cfg->max_devs_supported = ipr_max_devs; if (ioa_cfg->sis64) { + host->max_channel = IPR_MAX_SIS64_BUSES; host->max_id = IPR_MAX_SIS64_TARGETS_PER_BUS; host->max_lun = IPR_MAX_SIS64_LUNS_PER_TARGET; if (ipr_max_devs > IPR_MAX_SIS64_DEVS) @@ -9958,6 +9959,7 @@ static void ipr_init_ioa_cfg(struct ipr_ioa_cfg *ioa_cfg, + ((sizeof(struct ipr_config_table_entry64) * ioa_cfg->max_devs_supported))); } else { + host->max_channel = IPR_VSET_BUS; host->max_id = IPR_MAX_NUM_TARGETS_PER_BUS; host->max_lun = IPR_MAX_NUM_LUNS_PER_TARGET; if (ipr_max_devs > IPR_MAX_PHYSICAL_DEVS) @@ -9967,7 +9969,6 @@ static void ipr_init_ioa_cfg(struct ipr_ioa_cfg *ioa_cfg, * ioa_cfg->max_devs_supported))); } - host->max_channel = IPR_VSET_BUS; host->unique_id = host->host_no; host->max_cmd_len = IPR_MAX_CDB_LEN; host->can_queue = ioa_cfg->max_cmds; diff --git a/drivers/scsi/ipr.h b/drivers/scsi/ipr.h index a67baeb36d1f..b97aa9ac2ffe 100644 --- a/drivers/scsi/ipr.h +++ b/drivers/scsi/ipr.h @@ -1300,6 +1300,7 @@ struct ipr_resource_entry { #define IPR_ARRAY_VIRTUAL_BUS 0x1 #define IPR_VSET_VIRTUAL_BUS 0x2 #define IPR_IOAFP_VIRTUAL_BUS 0x3 +#define IPR_MAX_SIS64_BUSES 0x4 #define IPR_GET_RES_PHYS_LOC(res) \ (((res)->bus << 24) | ((res)->target << 8) | (res)->lun) From e93fc7b4544a5475cfdbc22f87e89f9829bf801c Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Tue, 3 Mar 2020 03:10:57 -0500 Subject: [PATCH 182/256] KVM: s390: Also reset registers in sync regs for initial cpu reset When we do the initial CPU reset we must not only clear the registers in the internal data structures but also in kvm_run sync_regs. For modern userspace sync_regs is the only place that it looks at. Fixes: 7de3f1423ff9 ("KVM: s390: Add new reset vcpu API") Acked-by: David Hildenbrand Signed-off-by: Christian Borntraeger --- arch/s390/kvm/kvm-s390.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index d7ff30e45589..c2e6d4ba4e23 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -3268,7 +3268,10 @@ static void kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu) /* Initial reset is a superset of the normal reset */ kvm_arch_vcpu_ioctl_normal_reset(vcpu); - /* this equals initial cpu reset in pop, but we don't switch to ESA */ + /* + * This equals initial cpu reset in pop, but we don't switch to ESA. + * We do not only reset the internal data, but also ... + */ vcpu->arch.sie_block->gpsw.mask = 0; vcpu->arch.sie_block->gpsw.addr = 0; kvm_s390_set_prefix(vcpu, 0); @@ -3278,6 +3281,19 @@ static void kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu) memset(vcpu->arch.sie_block->gcr, 0, sizeof(vcpu->arch.sie_block->gcr)); vcpu->arch.sie_block->gcr[0] = CR0_INITIAL_MASK; vcpu->arch.sie_block->gcr[14] = CR14_INITIAL_MASK; + + /* ... the data in sync regs */ + memset(vcpu->run->s.regs.crs, 0, sizeof(vcpu->run->s.regs.crs)); + vcpu->run->s.regs.ckc = 0; + vcpu->run->s.regs.crs[0] = CR0_INITIAL_MASK; + vcpu->run->s.regs.crs[14] = CR14_INITIAL_MASK; + vcpu->run->psw_addr = 0; + vcpu->run->psw_mask = 0; + vcpu->run->s.regs.todpr = 0; + vcpu->run->s.regs.cputm = 0; + vcpu->run->s.regs.ckc = 0; + vcpu->run->s.regs.pp = 0; + vcpu->run->s.regs.gbea = 1; vcpu->run->s.regs.fpc = 0; vcpu->arch.sie_block->gbea = 1; vcpu->arch.sie_block->pp = 0; From 0e1a1d853ecedc99da9d27f9f5c376935547a0e2 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 2 Mar 2020 21:10:56 -0800 Subject: [PATCH 183/256] nl80211: add missing attribute validation for critical protocol indication Add missing attribute validation for critical protocol fields to the netlink policy. Fixes: 5de17984898c ("cfg80211: introduce critical protocol indication from user-space") Signed-off-by: Jakub Kicinski Link: https://lore.kernel.org/r/20200303051058.4089398-2-kuba@kernel.org Signed-off-by: Johannes Berg --- net/wireless/nl80211.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 5b19e9fac4aa..cd0e024d7cb6 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -531,6 +531,8 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_MDID] = { .type = NLA_U16 }, [NL80211_ATTR_IE_RIC] = { .type = NLA_BINARY, .len = IEEE80211_MAX_DATA_LEN }, + [NL80211_ATTR_CRIT_PROT_ID] = { .type = NLA_U16 }, + [NL80211_ATTR_MAX_CRIT_PROT_DURATION] = { .type = NLA_U16 }, [NL80211_ATTR_PEER_AID] = NLA_POLICY_RANGE(NLA_U16, 1, IEEE80211_MAX_AID), [NL80211_ATTR_CH_SWITCH_COUNT] = { .type = NLA_U32 }, From 056e9375e1f3c4bf2fd49b70258c7daf788ecd9d Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 2 Mar 2020 21:10:57 -0800 Subject: [PATCH 184/256] nl80211: add missing attribute validation for beacon report scanning Add missing attribute validation for beacon report scanning to the netlink policy. Fixes: 1d76250bd34a ("nl80211: support beacon report scanning") Signed-off-by: Jakub Kicinski Link: https://lore.kernel.org/r/20200303051058.4089398-3-kuba@kernel.org Signed-off-by: Johannes Berg --- net/wireless/nl80211.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index cd0e024d7cb6..48e6508aba52 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -470,6 +470,8 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_WOWLAN_TRIGGERS] = { .type = NLA_NESTED }, [NL80211_ATTR_STA_PLINK_STATE] = NLA_POLICY_MAX(NLA_U8, NUM_NL80211_PLINK_STATES - 1), + [NL80211_ATTR_MEASUREMENT_DURATION] = { .type = NLA_U16 }, + [NL80211_ATTR_MEASUREMENT_DURATION_MANDATORY] = { .type = NLA_FLAG }, [NL80211_ATTR_MESH_PEER_AID] = NLA_POLICY_RANGE(NLA_U16, 1, IEEE80211_MAX_AID), [NL80211_ATTR_SCHED_SCAN_INTERVAL] = { .type = NLA_U32 }, From 5cde05c61cbe13cbb3fa66d52b9ae84f7975e5e6 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 2 Mar 2020 21:10:58 -0800 Subject: [PATCH 185/256] nl80211: add missing attribute validation for channel switch Add missing attribute validation for NL80211_ATTR_OPER_CLASS to the netlink policy. Fixes: 1057d35ede5d ("cfg80211: introduce TDLS channel switch commands") Signed-off-by: Jakub Kicinski Link: https://lore.kernel.org/r/20200303051058.4089398-4-kuba@kernel.org Signed-off-by: Johannes Berg --- net/wireless/nl80211.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 48e6508aba52..ec5d67794aab 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -565,6 +565,7 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { NLA_POLICY_MAX(NLA_U8, IEEE80211_NUM_UPS - 1), [NL80211_ATTR_ADMITTED_TIME] = { .type = NLA_U16 }, [NL80211_ATTR_SMPS_MODE] = { .type = NLA_U8 }, + [NL80211_ATTR_OPER_CLASS] = { .type = NLA_U8 }, [NL80211_ATTR_MAC_MASK] = { .type = NLA_EXACT_LEN_WARN, .len = ETH_ALEN From ba32679cac50c38fdf488296f96b1f3175532b8e Mon Sep 17 00:00:00 2001 From: Nicolas Cavallari Date: Thu, 5 Mar 2020 15:04:09 +0100 Subject: [PATCH 186/256] mac80211: Do not send mesh HWMP PREQ if HWMP is disabled When trying to transmit to an unknown destination, the mesh code would unconditionally transmit a HWMP PREQ even if HWMP is not the current path selection algorithm. Signed-off-by: Nicolas Cavallari Link: https://lore.kernel.org/r/20200305140409.12204-1-cavallar@lri.fr Signed-off-by: Johannes Berg --- net/mac80211/mesh_hwmp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index d69983370381..38a0383dfbcf 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -1152,7 +1152,8 @@ int mesh_nexthop_resolve(struct ieee80211_sub_if_data *sdata, } } - if (!(mpath->flags & MESH_PATH_RESOLVING)) + if (!(mpath->flags & MESH_PATH_RESOLVING) && + mesh_path_sel_is_hwmp(sdata)) mesh_queue_preq(mpath, PREQ_Q_F_START); if (skb_queue_len(&mpath->frame_queue) >= MESH_FRAME_QUEUE_LEN) From d9815bff6b379ff46981bea9dfeb146081eab314 Mon Sep 17 00:00:00 2001 From: Artem Savkov Date: Fri, 6 Mar 2020 18:43:17 +0100 Subject: [PATCH 187/256] ftrace: Return the first found result in lookup_rec() It appears that ip ranges can overlap so. In that case lookup_rec() returns whatever results it got last even if it found nothing in last searched page. This breaks an obscure livepatch late module patching usecase: - load livepatch - load the patched module - unload livepatch - try to load livepatch again To fix this return from lookup_rec() as soon as it found the record containing searched-for ip. This used to be this way prior lookup_rec() introduction. Link: http://lkml.kernel.org/r/20200306174317.21699-1-asavkov@redhat.com Cc: stable@vger.kernel.org Fixes: 7e16f581a817 ("ftrace: Separate out functionality from ftrace_location_range()") Signed-off-by: Artem Savkov Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ftrace.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 3f7ee102868a..fd81c7de77a7 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1547,6 +1547,8 @@ static struct dyn_ftrace *lookup_rec(unsigned long start, unsigned long end) rec = bsearch(&key, pg->records, pg->index, sizeof(struct dyn_ftrace), ftrace_cmp_recs); + if (rec) + break; } return rec; } From 985e537a4082b4635754a57f4f95430790afee6a Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Tue, 10 Mar 2020 18:35:57 +0100 Subject: [PATCH 188/256] x86/ioremap: Map EFI runtime services data as encrypted for SEV The dmidecode program fails to properly decode the SMBIOS data supplied by OVMF/UEFI when running in an SEV guest. The SMBIOS area, under SEV, is encrypted and resides in reserved memory that is marked as EFI runtime services data. As a result, when memremap() is attempted for the SMBIOS data, it can't be mapped as regular RAM (through try_ram_remap()) and, since the address isn't part of the iomem resources list, it isn't mapped encrypted through the fallback ioremap(). Add a new __ioremap_check_other() to deal with memory types like EFI_RUNTIME_SERVICES_DATA which are not covered by the resource ranges. This allows any runtime services data which has been created encrypted, to be mapped encrypted too. [ bp: Move functionality to a separate function. ] Signed-off-by: Tom Lendacky Signed-off-by: Borislav Petkov Reviewed-by: Joerg Roedel Tested-by: Joerg Roedel Cc: # 5.3 Link: https://lkml.kernel.org/r/2d9e16eb5b53dc82665c95c6764b7407719df7a0.1582645327.git.thomas.lendacky@amd.com --- arch/x86/mm/ioremap.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 44e4beb4239f..935a91e1fd77 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -106,6 +106,19 @@ static unsigned int __ioremap_check_encrypted(struct resource *res) return 0; } +/* + * The EFI runtime services data area is not covered by walk_mem_res(), but must + * be mapped encrypted when SEV is active. + */ +static void __ioremap_check_other(resource_size_t addr, struct ioremap_desc *desc) +{ + if (!sev_active()) + return; + + if (efi_mem_type(addr) == EFI_RUNTIME_SERVICES_DATA) + desc->flags |= IORES_MAP_ENCRYPTED; +} + static int __ioremap_collect_map_flags(struct resource *res, void *arg) { struct ioremap_desc *desc = arg; @@ -124,6 +137,9 @@ static int __ioremap_collect_map_flags(struct resource *res, void *arg) * To avoid multiple resource walks, this function walks resources marked as * IORESOURCE_MEM and IORESOURCE_BUSY and looking for system RAM and/or a * resource described not as IORES_DESC_NONE (e.g. IORES_DESC_ACPI_TABLES). + * + * After that, deal with misc other ranges in __ioremap_check_other() which do + * not fall into the above category. */ static void __ioremap_check_mem(resource_size_t addr, unsigned long size, struct ioremap_desc *desc) @@ -135,6 +151,8 @@ static void __ioremap_check_mem(resource_size_t addr, unsigned long size, memset(desc, 0, sizeof(struct ioremap_desc)); walk_mem_res(start, end, desc, __ioremap_collect_map_flags); + + __ioremap_check_other(addr, desc); } /* From 1292e3efb149ee21d8d33d725eeed4e6b1ade963 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Tue, 10 Mar 2020 12:49:43 +0100 Subject: [PATCH 189/256] mmc: core: Allow host controllers to require R1B for CMD6 It has turned out that some host controllers can't use R1B for CMD6 and other commands that have R1B associated with them. Therefore invent a new host cap, MMC_CAP_NEED_RSP_BUSY to let them specify this. In __mmc_switch(), let's check the flag and use it to prevent R1B responses from being converted into R1. Note that, this also means that the host are on its own, when it comes to manage the busy timeout. Suggested-by: Sowjanya Komatineni Cc: Tested-by: Anders Roxell Tested-by: Sowjanya Komatineni Tested-by: Faiz Abbas Tested-By: Peter Geis Signed-off-by: Ulf Hansson --- drivers/mmc/core/mmc_ops.c | 6 ++++-- include/linux/mmc/host.h | 1 + 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c index da425ee2d9bf..e025604e17d4 100644 --- a/drivers/mmc/core/mmc_ops.c +++ b/drivers/mmc/core/mmc_ops.c @@ -542,9 +542,11 @@ int __mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value, * If the max_busy_timeout of the host is specified, make sure it's * enough to fit the used timeout_ms. In case it's not, let's instruct * the host to avoid HW busy detection, by converting to a R1 response - * instead of a R1B. + * instead of a R1B. Note, some hosts requires R1B, which also means + * they are on their own when it comes to deal with the busy timeout. */ - if (host->max_busy_timeout && (timeout_ms > host->max_busy_timeout)) + if (!(host->caps & MMC_CAP_NEED_RSP_BUSY) && host->max_busy_timeout && + (timeout_ms > host->max_busy_timeout)) use_r1b_resp = false; cmd.opcode = MMC_SWITCH; diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index ba703384bea0..4c5eb3aa8e72 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -333,6 +333,7 @@ struct mmc_host { MMC_CAP_UHS_SDR50 | MMC_CAP_UHS_SDR104 | \ MMC_CAP_UHS_DDR50) #define MMC_CAP_SYNC_RUNTIME_PM (1 << 21) /* Synced runtime PM suspends. */ +#define MMC_CAP_NEED_RSP_BUSY (1 << 22) /* Commands with R1B can't use R1. */ #define MMC_CAP_DRIVER_TYPE_A (1 << 23) /* Host supports Driver Type A */ #define MMC_CAP_DRIVER_TYPE_C (1 << 24) /* Host supports Driver Type C */ #define MMC_CAP_DRIVER_TYPE_D (1 << 25) /* Host supports Driver Type D */ From 43cc64e5221cc6741252b64bc4531dd1eefb733d Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Tue, 10 Mar 2020 14:43:00 +0100 Subject: [PATCH 190/256] mmc: core: Respect MMC_CAP_NEED_RSP_BUSY for erase/trim/discard The busy timeout that is computed for each erase/trim/discard operation, can become quite long and may thus exceed the host->max_busy_timeout. If that becomes the case, mmc_do_erase() converts from using an R1B response to an R1 response, as to prevent the host from doing HW busy detection. However, it has turned out that some hosts requires an R1B response no matter what, so let's respect that via checking MMC_CAP_NEED_RSP_BUSY. Note that, if the R1B gets enforced, the host becomes fully responsible of managing the needed busy timeout, in one way or the other. Suggested-by: Sowjanya Komatineni Cc: Tested-by: Anders Roxell Tested-by: Sowjanya Komatineni Tested-by: Faiz Abbas Tested-By: Peter Geis Signed-off-by: Ulf Hansson --- drivers/mmc/core/core.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index aa54d359dab7..a971c4bcc442 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -1732,8 +1732,11 @@ static int mmc_do_erase(struct mmc_card *card, unsigned int from, * the erase operation does not exceed the max_busy_timeout, we should * use R1B response. Or we need to prevent the host from doing hw busy * detection, which is done by converting to a R1 response instead. + * Note, some hosts requires R1B, which also means they are on their own + * when it comes to deal with the busy timeout. */ - if (card->host->max_busy_timeout && + if (!(card->host->caps & MMC_CAP_NEED_RSP_BUSY) && + card->host->max_busy_timeout && busy_timeout > card->host->max_busy_timeout) { cmd.flags = MMC_RSP_SPI_R1 | MMC_RSP_R1 | MMC_CMD_AC; } else { From 055e04830d4544c57f2a5192a26c9e25915c29c0 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Tue, 10 Mar 2020 15:05:02 +0100 Subject: [PATCH 191/256] mmc: sdhci-omap: Fix busy detection by enabling MMC_CAP_NEED_RSP_BUSY It has turned out that the sdhci-omap controller requires the R1B response, for commands that has this response associated with them. So, converting from an R1B to an R1 response for a CMD6 for example, leads to problems with the HW busy detection support. Fix this by informing the mmc core about the requirement, via setting the host cap, MMC_CAP_NEED_RSP_BUSY. Reported-by: Naresh Kamboju Reported-by: Anders Roxell Reported-by: Faiz Abbas Cc: Tested-by: Anders Roxell Tested-by: Faiz Abbas Signed-off-by: Ulf Hansson --- drivers/mmc/host/sdhci-omap.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/mmc/host/sdhci-omap.c b/drivers/mmc/host/sdhci-omap.c index 882053151a47..c4978177ef88 100644 --- a/drivers/mmc/host/sdhci-omap.c +++ b/drivers/mmc/host/sdhci-omap.c @@ -1192,6 +1192,9 @@ static int sdhci_omap_probe(struct platform_device *pdev) if (of_find_property(dev->of_node, "dmas", NULL)) sdhci_switch_external_dma(host, true); + /* R1B responses is required to properly manage HW busy detection. */ + mmc->caps |= MMC_CAP_NEED_RSP_BUSY; + ret = sdhci_setup_host(host); if (ret) goto err_put_sync; From d2f8bfa4bff5028bc40ed56b4497c32e05b0178f Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Tue, 10 Mar 2020 15:50:11 +0100 Subject: [PATCH 192/256] mmc: sdhci-tegra: Fix busy detection by enabling MMC_CAP_NEED_RSP_BUSY It has turned out that the sdhci-tegra controller requires the R1B response, for commands that has this response associated with them. So, converting from an R1B to an R1 response for a CMD6 for example, leads to problems with the HW busy detection support. Fix this by informing the mmc core about the requirement, via setting the host cap, MMC_CAP_NEED_RSP_BUSY. Reported-by: Bitan Biswas Reported-by: Peter Geis Suggested-by: Sowjanya Komatineni Cc: Tested-by: Sowjanya Komatineni Tested-By: Peter Geis Signed-off-by: Ulf Hansson --- drivers/mmc/host/sdhci-tegra.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/mmc/host/sdhci-tegra.c b/drivers/mmc/host/sdhci-tegra.c index 403ac44a7378..a25c3a4d3f6c 100644 --- a/drivers/mmc/host/sdhci-tegra.c +++ b/drivers/mmc/host/sdhci-tegra.c @@ -1552,6 +1552,9 @@ static int sdhci_tegra_probe(struct platform_device *pdev) if (tegra_host->soc_data->nvquirks & NVQUIRK_ENABLE_DDR50) host->mmc->caps |= MMC_CAP_1_8V_DDR; + /* R1B responses is required to properly manage HW busy detection. */ + host->mmc->caps |= MMC_CAP_NEED_RSP_BUSY; + tegra_sdhci_parse_dt(host); tegra_host->power_gpio = devm_gpiod_get_optional(&pdev->dev, "power", From e3a36eb6dfaeea8175c05d5915dcf0b939be6dab Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 11 Mar 2020 17:07:10 +0100 Subject: [PATCH 193/256] driver code: clarify and fix platform device DMA mask allocation This does three inter-related things to clarify the usage of the platform device dma_mask field. In the process, fix the bug introduced by cdfee5623290 ("driver core: initialize a default DMA mask for platform device") that caused Artem Tashkinov's laptop to not boot with newer Fedora kernels. This does: - First off, rename the field to "platform_dma_mask" to make it greppable. We have way too many different random fields called "dma_mask" in various data structures, where some of them are actual masks, and some of them are just pointers to the mask. And the structures all have pointers to each other, or embed each other inside themselves, and "pdev" sometimes means "platform device" and sometimes it means "PCI device". So to make it clear in the code when you actually use this new field, give it a unique name (it really should be something even more unique like "platform_device_dma_mask", since it's per platform device, not per platform, but that gets old really fast, and this is unique enough in context). To further clarify when the field gets used, initialize it when we actually start using it with the default value. - Then, use this field instead of the random one-off allocation in platform_device_register_full() that is now unnecessary since we now already have a perfectly fine allocation for it in the platform device structure. - The above then allows us to fix the actual bug, where the error path of platform_device_register_full() would unconditionally free the platform device DMA allocation with 'kfree()'. That kfree() was dont regardless of whether the allocation had been done earlier with the (now removed) kmalloc, or whether setup_pdev_dma_masks() had already been used and the dma_mask pointer pointed to the mask that was part of the platform device. It seems most people never triggered the error path, or only triggered it from a call chain that set an explicit pdevinfo->dma_mask value (and thus caused the unnecessary allocation that was "cleaned up" in the error path) before calling platform_device_register_full(). Robin Murphy points out that in Artem's case the wdat_wdt driver failed in platform_device_add(), and that was the one that had called platform_device_register_full() with pdevinfo.dma_mask = 0, and would have caused that kfree() of pdev.dma_mask corrupting the heap. A later unrelated kmalloc() then oopsed due to the heap corruption. Fixes: cdfee5623290 ("driver core: initialize a default DMA mask for platform device") Reported-bisected-and-tested-by: Artem S. Tashkinov Reviewed-by: Robin Murphy Cc: Greg Kroah-Hartman Signed-off-by: Christoph Hellwig Signed-off-by: Linus Torvalds --- drivers/base/platform.c | 25 ++++++------------------- include/linux/platform_device.h | 2 +- 2 files changed, 7 insertions(+), 20 deletions(-) diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 7fa654f1288b..b5ce7b085795 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -363,10 +363,10 @@ static void setup_pdev_dma_masks(struct platform_device *pdev) { if (!pdev->dev.coherent_dma_mask) pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); - if (!pdev->dma_mask) - pdev->dma_mask = DMA_BIT_MASK(32); - if (!pdev->dev.dma_mask) - pdev->dev.dma_mask = &pdev->dma_mask; + if (!pdev->dev.dma_mask) { + pdev->platform_dma_mask = DMA_BIT_MASK(32); + pdev->dev.dma_mask = &pdev->platform_dma_mask; + } }; /** @@ -662,20 +662,8 @@ struct platform_device *platform_device_register_full( pdev->dev.of_node_reused = pdevinfo->of_node_reused; if (pdevinfo->dma_mask) { - /* - * This memory isn't freed when the device is put, - * I don't have a nice idea for that though. Conceptually - * dma_mask in struct device should not be a pointer. - * See http://thread.gmane.org/gmane.linux.kernel.pci/9081 - */ - pdev->dev.dma_mask = - kmalloc(sizeof(*pdev->dev.dma_mask), GFP_KERNEL); - if (!pdev->dev.dma_mask) - goto err; - - kmemleak_ignore(pdev->dev.dma_mask); - - *pdev->dev.dma_mask = pdevinfo->dma_mask; + pdev->platform_dma_mask = pdevinfo->dma_mask; + pdev->dev.dma_mask = &pdev->platform_dma_mask; pdev->dev.coherent_dma_mask = pdevinfo->dma_mask; } @@ -700,7 +688,6 @@ struct platform_device *platform_device_register_full( if (ret) { err: ACPI_COMPANION_SET(&pdev->dev, NULL); - kfree(pdev->dev.dma_mask); platform_device_put(pdev); return ERR_PTR(ret); } diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 276a03c24691..041bfa412aa0 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -24,7 +24,7 @@ struct platform_device { int id; bool id_auto; struct device dev; - u64 dma_mask; + u64 platform_dma_mask; u32 num_resources; struct resource *resource; From 204c7eceb76f348b89ccbf20fa3ba9a703ffada5 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Tue, 3 Mar 2020 22:10:01 -0800 Subject: [PATCH 194/256] ARC: show_regs: reduce lines of output Before ------ | CPU: 1 PID: 29061 Comm: tst-dynarray-at Not tainted 5.6.0-rc1-00002-g941fcc018ca6-dirty #12 | | [ECR ]: 0x00090000 => | [EFA ]: 0x00000000 | [ERET ]: 0x2004aa6c | @off 0x2aa6c in [/lib/libc-2.31.9000.so] VMA: 0x20020000 to 0x20122000 | [STAT32]: 0x80080a82 [IE U ] | BTA: 0x2004aa18 SP: 0x5ffff8a8 FP: 0x5ffff8fc | LPS: 0x2008788e LPE: 0x20087896 LPC: 0x00000000 | r00: 0x00000000 r01: 0x5ffff8a8 r02: 0x00000000 | r03: 0x00000008 r04: 0xffffffff r05: 0x00000000 | r06: 0x00000000 r07: 0x00000000 r08: 0x00000087 | r09: 0x00000000 r10: 0x2010691c r11: 0x00000020 | r12: 0x2003b214 r13: 0x5ffff8a8 r14: 0x20126e68 | r15: 0x2001f26c r16: 0x2012a000 r17: 0x00000001 | r18: 0x5ffff8fc r19: 0x00000000 r20: 0x5ffff948 | r21: 0x00000001 r22: 0xffffffff r23: 0x5fffff8c | r24: 0x4008c2a8 r25: 0x2001f6e0 After ----- | CPU: 1 PID: 29061 Comm: tst-dynarray-at Not tainted 5.6.0-rc1-00002-g941fcc018ca6-dirty #12 | @off 0x2aa6c in [/lib/libc-2.31.9000.so] VMA: 0x20020000 to 0x20122000 | ECR: 0x00090000 EFA: 0x00000000 ERET: 0x2004aa6c | STAT32: 0x80080a82 [IE U ] BTA: 0x2004aa18 | BLK: 0x2003b214 SP: 0x5ffff8a8 FP: 0x5ffff8fc | LPS: 0x2008788e LPE: 0x20087896 LPC: 0x00000000 | r00: 0x00000000 r01: 0x5ffff8a8 r02: 0x00000000 | r03: 0x00000008 r04: 0xffffffff r05: 0x00000000 | r06: 0x00000000 r07: 0x00000000 r08: 0x00000087 | r09: 0x00000000 r10: 0x2010691c r11: 0x00000020 | r12: 0x2003b214 r13: 0x5ffff8a8 r14: 0x20126e68 | r15: 0x2001f26c r16: 0x2012a000 r17: 0x00000001 | r18: 0x5ffff8fc r19: 0x00000000 r20: 0x5ffff948 | r21: 0x00000001 r22: 0xffffffff r23: 0x5fffff8c | r24: 0x4008c2a8 r25: 0x2001f6e0 BTA: 0x2004aa18 Signed-off-by: Vineet Gupta --- arch/arc/kernel/troubleshoot.c | 27 ++++++++++++--------------- 1 file changed, 12 insertions(+), 15 deletions(-) diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c index b79886a6cec8..d2999503fb8a 100644 --- a/arch/arc/kernel/troubleshoot.c +++ b/arch/arc/kernel/troubleshoot.c @@ -104,8 +104,7 @@ static void show_faulting_vma(unsigned long address) if (IS_ERR(nm)) nm = "?"; } - pr_info(" @off 0x%lx in [%s]\n" - " VMA: 0x%08lx to 0x%08lx\n", + pr_info(" @off 0x%lx in [%s] VMA: 0x%08lx to 0x%08lx\n", vma->vm_start < TASK_UNMAPPED_BASE ? address : address - vma->vm_start, nm, vma->vm_start, vma->vm_end); @@ -120,8 +119,6 @@ static void show_ecr_verbose(struct pt_regs *regs) unsigned int vec, cause_code; unsigned long address; - pr_info("\n[ECR ]: 0x%08lx => ", regs->event); - /* For Data fault, this is data address not instruction addr */ address = current->thread.fault_address; @@ -130,10 +127,10 @@ static void show_ecr_verbose(struct pt_regs *regs) /* For DTLB Miss or ProtV, display the memory involved too */ if (vec == ECR_V_DTLB_MISS) { - pr_cont("Invalid %s @ 0x%08lx by insn @ 0x%08lx\n", + pr_cont("Invalid %s @ 0x%08lx by insn @ %pS\n", (cause_code == 0x01) ? "Read" : ((cause_code == 0x02) ? "Write" : "EX"), - address, regs->ret); + address, (void *)regs->ret); } else if (vec == ECR_V_ITLB_MISS) { pr_cont("Insn could not be fetched\n"); } else if (vec == ECR_V_MACH_CHK) { @@ -191,31 +188,31 @@ void show_regs(struct pt_regs *regs) show_ecr_verbose(regs); - pr_info("[EFA ]: 0x%08lx\n[BLINK ]: %pS\n[ERET ]: %pS\n", - current->thread.fault_address, - (void *)regs->blink, (void *)regs->ret); - if (user_mode(regs)) show_faulting_vma(regs->ret); /* faulting code, not data */ - pr_info("[STAT32]: 0x%08lx", regs->status32); + pr_info("ECR: 0x%08lx EFA: 0x%08lx ERET: 0x%08lx\n", + regs->event, current->thread.fault_address, regs->ret); + + pr_info("STAT32: 0x%08lx", regs->status32); #define STS_BIT(r, bit) r->status32 & STATUS_##bit##_MASK ? #bit" " : "" #ifdef CONFIG_ISA_ARCOMPACT - pr_cont(" : %2s%2s%2s%2s%2s%2s%2s\n", + pr_cont(" [%2s%2s%2s%2s%2s%2s%2s]", (regs->status32 & STATUS_U_MASK) ? "U " : "K ", STS_BIT(regs, DE), STS_BIT(regs, AE), STS_BIT(regs, A2), STS_BIT(regs, A1), STS_BIT(regs, E2), STS_BIT(regs, E1)); #else - pr_cont(" : %2s%2s%2s%2s\n", + pr_cont(" [%2s%2s%2s%2s]", STS_BIT(regs, IE), (regs->status32 & STATUS_U_MASK) ? "U " : "K ", STS_BIT(regs, DE), STS_BIT(regs, AE)); #endif - pr_info("BTA: 0x%08lx\t SP: 0x%08lx\t FP: 0x%08lx\n", - regs->bta, regs->sp, regs->fp); + pr_cont(" BTA: 0x%08lx\n", regs->bta); + pr_info("BLK: %pS\n SP: 0x%08lx FP: 0x%08lx\n", + (void *)regs->blink, regs->sp, regs->fp); pr_info("LPS: 0x%08lx\tLPE: 0x%08lx\tLPC: 0x%08lx\n", regs->lp_start, regs->lp_end, regs->lp_count); From 8d92e992a785f35d23f845206cf8c6cafbc264e0 Mon Sep 17 00:00:00 2001 From: Eugeniy Paltsev Date: Wed, 11 Mar 2020 19:26:43 +0300 Subject: [PATCH 195/256] ARC: define __ALIGN_STR and __ALIGN symbols for ARC The default defintions use fill pattern 0x90 for padding which for ARC generates unintended "ldh_s r12,[r0,0x20]" corresponding to opcode 0x9090 So use ".align 4" which insert a "nop_s" instruction instead. Cc: stable@vger.kernel.org Acked-by: Vineet Gupta Signed-off-by: Eugeniy Paltsev Signed-off-by: Vineet Gupta --- arch/arc/include/asm/linkage.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arc/include/asm/linkage.h b/arch/arc/include/asm/linkage.h index d9ee43c6b7db..fe19f1d412e7 100644 --- a/arch/arc/include/asm/linkage.h +++ b/arch/arc/include/asm/linkage.h @@ -29,6 +29,8 @@ .endm #define ASM_NL ` /* use '`' to mark new line in macro */ +#define __ALIGN .align 4 +#define __ALIGN_STR __stringify(__ALIGN) /* annotation for data we want in DCCM - if enabled in .config */ .macro ARCFP_DATA nm From 7395f62d95aafacdb9bd4996ec2f95b4a655d7e6 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Tue, 10 Mar 2020 15:06:54 -0700 Subject: [PATCH 196/256] dpaa_eth: Remove unnecessary boolean expression in dpaa_get_headroom Clang warns: drivers/net/ethernet/freescale/dpaa/dpaa_eth.c:2860:9: warning: converting the result of '?:' with integer constants to a boolean always evaluates to 'true' [-Wtautological-constant-compare] return DPAA_FD_DATA_ALIGNMENT ? ALIGN(headroom, ^ drivers/net/ethernet/freescale/dpaa/dpaa_eth.c:131:34: note: expanded from macro 'DPAA_FD_DATA_ALIGNMENT' \#define DPAA_FD_DATA_ALIGNMENT (fman_has_errata_a050385() ? 64 : 16) ^ 1 warning generated. This was exposed by commit 3c68b8fffb48 ("dpaa_eth: FMan erratum A050385 workaround") even though it appears to have been an issue since the introductory commit 9ad1a3749333 ("dpaa_eth: add support for DPAA Ethernet") since DPAA_FD_DATA_ALIGNMENT has never been able to be zero. Just replace the whole boolean expression with the true branch, as it is always been true. Link: https://github.com/ClangBuiltLinux/linux/issues/928 Signed-off-by: Nathan Chancellor Reviewed-by: Madalin Bucur Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index e3ac9ec54c7c..ca74a684a904 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -2845,9 +2845,7 @@ static inline u16 dpaa_get_headroom(struct dpaa_buffer_layout *bl) headroom = (u16)(bl->priv_data_size + DPAA_PARSE_RESULTS_SIZE + DPAA_TIME_STAMP_SIZE + DPAA_HASH_RESULTS_SIZE); - return DPAA_FD_DATA_ALIGNMENT ? ALIGN(headroom, - DPAA_FD_DATA_ALIGNMENT) : - headroom; + return ALIGN(headroom, DPAA_FD_DATA_ALIGNMENT); } static int dpaa_eth_probe(struct platform_device *pdev) From c67b35d970ed3391069c21f3071a26f687399ab2 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Thu, 5 Mar 2020 10:42:10 +0000 Subject: [PATCH 197/256] drm/i915: Actually emit the await_start Fix the inverted test to emit the wait on the end of the previous request if we /haven't/ already. Fixes: 6a79d848403d ("drm/i915: Lock signaler timeline while navigating") Signed-off-by: Chris Wilson Cc: Tvrtko Ursulin Cc: # v5.5+ Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20200305104210.2619967-1-chris@chris-wilson.co.uk (cherry picked from commit 07e9c59d63df6a1c44c1975c01827ba18b69270a) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/i915_request.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index dcaa85a91090..468ca1052bcb 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -821,7 +821,7 @@ i915_request_await_start(struct i915_request *rq, struct i915_request *signal) return 0; err = 0; - if (intel_timeline_sync_is_later(i915_request_timeline(rq), fence)) + if (!intel_timeline_sync_is_later(i915_request_timeline(rq), fence)) err = i915_sw_fence_await_dma_fence(&rq->submit, fence, 0, I915_FENCE_GFP); From c951b0af2dddbb1f34be103029eb9030392d5554 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Thu, 5 Mar 2020 13:48:22 +0000 Subject: [PATCH 198/256] drm/i915: Return early for await_start on same timeline Requests within a timeline are ordered by that timeline, so awaiting for the start of a request within the timeline is a no-op. This used to work by falling out of the mutex_trylock() as the signaler and waiter had the same timeline and not returning an error. Fixes: 6a79d848403d ("drm/i915: Lock signaler timeline while navigating") Signed-off-by: Chris Wilson Cc: Tvrtko Ursulin Cc: # v5.5+ Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20200305134822.2750496-1-chris@chris-wilson.co.uk (cherry picked from commit ab7a69020fb5d5c7ba19fba60f62fd6f9ca9f779) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/i915_request.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 468ca1052bcb..7cd60b4a329b 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -776,8 +776,8 @@ i915_request_await_start(struct i915_request *rq, struct i915_request *signal) struct dma_fence *fence; int err; - GEM_BUG_ON(i915_request_timeline(rq) == - rcu_access_pointer(signal->timeline)); + if (i915_request_timeline(rq) == rcu_access_pointer(signal->timeline)) + return 0; if (i915_request_started(signal)) return 0; From 259170cb4c84f4165a36c0b05811eb74c495412c Mon Sep 17 00:00:00 2001 From: Tina Zhang Date: Thu, 27 Feb 2020 09:00:41 +0800 Subject: [PATCH 199/256] drm/i915/gvt: Fix dma-buf display blur issue on CFL Commit c3b5a8430daad ("drm/i915/gvt: Enable gfx virtualiztion for CFL") added the support on CFL. The vgpu emulation hotplug support on CFL was supposed to be included in that patch. Without the vgpu emulation hotplug support, the dma-buf based display gives us a blur face. So fix this issue by adding the vgpu emulation hotplug support on CFL. Fixes: c3b5a8430daad ("drm/i915/gvt: Enable gfx virtualiztion for CFL") Signed-off-by: Tina Zhang Acked-by: Zhenyu Wang Signed-off-by: Zhenyu Wang Link: http://patchwork.freedesktop.org/patch/msgid/20200227010041.32248-1-tina.zhang@intel.com (cherry picked from commit 135dde8853c7e00f6002e710f7e4787ed8585c0e) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/gvt/display.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c index e1c313da6c00..a62bdf9be682 100644 --- a/drivers/gpu/drm/i915/gvt/display.c +++ b/drivers/gpu/drm/i915/gvt/display.c @@ -457,7 +457,8 @@ void intel_vgpu_emulate_hotplug(struct intel_vgpu *vgpu, bool connected) struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv; /* TODO: add more platforms support */ - if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) { + if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv) || + IS_COFFEELAKE(dev_priv)) { if (connected) { vgpu_vreg_t(vgpu, SFUSE_STRAP) |= SFUSE_STRAP_DDID_DETECTED; From 1d61c5d711a2dc0b978ae905535edee9601f9449 Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Thu, 5 Mar 2020 20:35:34 +0000 Subject: [PATCH 200/256] drm/i915: be more solid in checking the alignment The alignment is u64, and yet is_power_of_2() assumes unsigned long, which might give different results between 32b and 64b kernel. Signed-off-by: Matthew Auld Cc: Chris Wilson Reviewed-by: Chris Wilson Signed-off-by: Chris Wilson Link: https://patchwork.freedesktop.org/patch/msgid/20200305203534.210466-1-matthew.auld@intel.com Cc: stable@vger.kernel.org (cherry picked from commit 2920516b2f719546f55079bc39a7fe409d9e80ab) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 3 ++- drivers/gpu/drm/i915/i915_utils.h | 5 +++++ 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index 60c984e10c4a..7643a30ba4cd 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -423,7 +423,8 @@ eb_validate_vma(struct i915_execbuffer *eb, if (unlikely(entry->flags & eb->invalid_flags)) return -EINVAL; - if (unlikely(entry->alignment && !is_power_of_2(entry->alignment))) + if (unlikely(entry->alignment && + !is_power_of_2_u64(entry->alignment))) return -EINVAL; /* diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h index b0ade76bec90..d34141f7dcd8 100644 --- a/drivers/gpu/drm/i915/i915_utils.h +++ b/drivers/gpu/drm/i915/i915_utils.h @@ -234,6 +234,11 @@ static inline u64 ptr_to_u64(const void *ptr) __idx; \ }) +static inline bool is_power_of_2_u64(u64 n) +{ + return (n != 0 && ((n & (n - 1)) == 0)); +} + static inline void __list_del_many(struct list_head *head, struct list_head *first) { From eafc2aa20fba319b6e791a1b0c45a91511eccb6b Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Fri, 6 Mar 2020 11:30:10 +0000 Subject: [PATCH 201/256] drm/i915/execlists: Enable timeslice on partial virtual engine dequeue If we stop filling the ELSP due to an incompatible virtual engine request, check if we should enable the timeslice on behalf of the queue. This fixes the case where we are inspecting the last->next element when we know that the last element is the last request in the execution queue, and so decided we did not need to enable timeslicing despite the intent to do so! Fixes: 8ee36e048c98 ("drm/i915/execlists: Minimalistic timeslicing") Signed-off-by: Chris Wilson Cc: Mika Kuoppala Cc: Tvrtko Ursulin Cc: # v5.4+ Reviewed-by: Mika Kuoppala Link: https://patchwork.freedesktop.org/patch/msgid/20200306113012.3184606-1-chris@chris-wilson.co.uk (cherry picked from commit 3df2deed411e0f1b7312baf0139aab8bba4c0410) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/gt/intel_lrc.c | 29 ++++++++++++++++++----------- 1 file changed, 18 insertions(+), 11 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index fe8a59aaa629..940e7f7df69a 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -1679,11 +1679,9 @@ need_timeslice(struct intel_engine_cs *engine, const struct i915_request *rq) if (!intel_engine_has_timeslices(engine)) return false; - if (list_is_last(&rq->sched.link, &engine->active.requests)) - return false; - - hint = max(rq_prio(list_next_entry(rq, sched.link)), - engine->execlists.queue_priority_hint); + hint = engine->execlists.queue_priority_hint; + if (!list_is_last(&rq->sched.link, &engine->active.requests)) + hint = max(hint, rq_prio(list_next_entry(rq, sched.link))); return hint >= effective_prio(rq); } @@ -1725,6 +1723,18 @@ static void set_timeslice(struct intel_engine_cs *engine) set_timer_ms(&engine->execlists.timer, active_timeslice(engine)); } +static void start_timeslice(struct intel_engine_cs *engine) +{ + struct intel_engine_execlists *execlists = &engine->execlists; + + execlists->switch_priority_hint = execlists->queue_priority_hint; + + if (timer_pending(&execlists->timer)) + return; + + set_timer_ms(&execlists->timer, timeslice(engine)); +} + static void record_preemption(struct intel_engine_execlists *execlists) { (void)I915_SELFTEST_ONLY(execlists->preempt_hang.count++); @@ -1888,11 +1898,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine) * Even if ELSP[1] is occupied and not worthy * of timeslices, our queue might be. */ - if (!execlists->timer.expires && - need_timeslice(engine, last)) - set_timer_ms(&execlists->timer, - timeslice(engine)); - + start_timeslice(engine); return; } } @@ -1927,7 +1933,8 @@ static void execlists_dequeue(struct intel_engine_cs *engine) if (last && !can_merge_rq(last, rq)) { spin_unlock(&ve->base.active.lock); - return; /* leave this for another */ + start_timeslice(engine); + return; /* leave this for another sibling */ } ENGINE_TRACE(engine, From 8ea6bb8e4d47e07518e5dba4f5cb77e210f0df82 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Fri, 6 Mar 2020 15:46:47 +0000 Subject: [PATCH 202/256] drm/i915/gt: Close race between cacheline_retire and free If the cacheline may still be busy, atomically mark it for future release, and only if we can determine that it will never be used again, immediately free it. Closes: https://gitlab.freedesktop.org/drm/intel/issues/1392 Fixes: ebece7539242 ("drm/i915: Keep timeline HWSP allocated until idle across the system") Signed-off-by: Chris Wilson Cc: Tvrtko Ursulin Cc: Mika Kuoppala Cc: Matthew Auld Reviewed-by: Mika Kuoppala Cc: # v5.2+ Link: https://patchwork.freedesktop.org/patch/msgid/20200306154647.3528345-1-chris@chris-wilson.co.uk (cherry picked from commit 2d4bd971f5baa51418625f379a69f5d58b5a0450) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/gt/intel_timeline.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c index 87716529cd2f..d8d9f1179c2b 100644 --- a/drivers/gpu/drm/i915/gt/intel_timeline.c +++ b/drivers/gpu/drm/i915/gt/intel_timeline.c @@ -192,11 +192,15 @@ static void cacheline_release(struct intel_timeline_cacheline *cl) static void cacheline_free(struct intel_timeline_cacheline *cl) { + if (!i915_active_acquire_if_busy(&cl->active)) { + __idle_cacheline_free(cl); + return; + } + GEM_BUG_ON(ptr_test_bit(cl->vaddr, CACHELINE_FREE)); cl->vaddr = ptr_set_bit(cl->vaddr, CACHELINE_FREE); - if (i915_active_is_idle(&cl->active)) - __idle_cacheline_free(cl); + i915_active_release(&cl->active); } int intel_timeline_init(struct intel_timeline *timeline, From 14a0d527a479eb2cb6067f9e5e163e1bf35db2a9 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Tue, 10 Mar 2020 10:17:20 +0000 Subject: [PATCH 203/256] drm/i915: Defer semaphore priority bumping to a workqueue Since the semaphore fence may be signaled from inside an interrupt handler from inside a request holding its request->lock, we cannot then enter into the engine->active.lock for processing the semaphore priority bump as we may traverse our call tree and end up on another held request. CPU 0: [ 2243.218864] _raw_spin_lock_irqsave+0x9a/0xb0 [ 2243.218867] i915_schedule_bump_priority+0x49/0x80 [i915] [ 2243.218869] semaphore_notify+0x6d/0x98 [i915] [ 2243.218871] __i915_sw_fence_complete+0x61/0x420 [i915] [ 2243.218874] ? kmem_cache_free+0x211/0x290 [ 2243.218876] i915_sw_fence_complete+0x58/0x80 [i915] [ 2243.218879] dma_i915_sw_fence_wake+0x3e/0x80 [i915] [ 2243.218881] signal_irq_work+0x571/0x690 [i915] [ 2243.218883] irq_work_run_list+0xd7/0x120 [ 2243.218885] irq_work_run+0x1d/0x50 [ 2243.218887] smp_irq_work_interrupt+0x21/0x30 [ 2243.218889] irq_work_interrupt+0xf/0x20 CPU 1: [ 2242.173107] _raw_spin_lock+0x8f/0xa0 [ 2242.173110] __i915_request_submit+0x64/0x4a0 [i915] [ 2242.173112] __execlists_submission_tasklet+0x8ee/0x2120 [i915] [ 2242.173114] ? i915_sched_lookup_priolist+0x1e3/0x2b0 [i915] [ 2242.173117] execlists_submit_request+0x2e8/0x2f0 [i915] [ 2242.173119] submit_notify+0x8f/0xc0 [i915] [ 2242.173121] __i915_sw_fence_complete+0x61/0x420 [i915] [ 2242.173124] ? _raw_spin_unlock_irqrestore+0x39/0x40 [ 2242.173137] i915_sw_fence_complete+0x58/0x80 [i915] [ 2242.173140] i915_sw_fence_commit+0x16/0x20 [i915] Closes: https://gitlab.freedesktop.org/drm/intel/issues/1318 Fixes: b7404c7ecb38 ("drm/i915: Bump ready tasks ahead of busywaits") Signed-off-by: Chris Wilson Cc: Tvrtko Ursulin Cc: # v5.2+ Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20200310101720.9944-1-chris@chris-wilson.co.uk (cherry picked from commit 209df10bb4536c81c2540df96c02cd079435357f) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/i915_request.c | 22 +++++++++++++++++----- drivers/gpu/drm/i915/i915_request.h | 2 ++ 2 files changed, 19 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 7cd60b4a329b..a18b2a244706 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -527,19 +527,31 @@ submit_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state) return NOTIFY_DONE; } +static void irq_semaphore_cb(struct irq_work *wrk) +{ + struct i915_request *rq = + container_of(wrk, typeof(*rq), semaphore_work); + + i915_schedule_bump_priority(rq, I915_PRIORITY_NOSEMAPHORE); + i915_request_put(rq); +} + static int __i915_sw_fence_call semaphore_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state) { - struct i915_request *request = - container_of(fence, typeof(*request), semaphore); + struct i915_request *rq = container_of(fence, typeof(*rq), semaphore); switch (state) { case FENCE_COMPLETE: - i915_schedule_bump_priority(request, I915_PRIORITY_NOSEMAPHORE); + if (!(READ_ONCE(rq->sched.attr.priority) & I915_PRIORITY_NOSEMAPHORE)) { + i915_request_get(rq); + init_irq_work(&rq->semaphore_work, irq_semaphore_cb); + irq_work_queue(&rq->semaphore_work); + } break; case FENCE_FREE: - i915_request_put(request); + i915_request_put(rq); break; } @@ -1318,9 +1330,9 @@ void __i915_request_queue(struct i915_request *rq, * decide whether to preempt the entire chain so that it is ready to * run at the earliest possible convenience. */ - i915_sw_fence_commit(&rq->semaphore); if (attr && rq->engine->schedule) rq->engine->schedule(rq, attr); + i915_sw_fence_commit(&rq->semaphore); i915_sw_fence_commit(&rq->submit); } diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h index f57eadcf3583..fccc339949ec 100644 --- a/drivers/gpu/drm/i915/i915_request.h +++ b/drivers/gpu/drm/i915/i915_request.h @@ -26,6 +26,7 @@ #define I915_REQUEST_H #include +#include #include #include "gem/i915_gem_context_types.h" @@ -208,6 +209,7 @@ struct i915_request { }; struct list_head execute_cb; struct i915_sw_fence semaphore; + struct irq_work semaphore_work; /* * A list of everyone we wait upon, and everyone who waits upon us. From 443d372d6a96cd94ad119e5c14bb4d63a536a7f6 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 5 Feb 2020 10:31:46 +0100 Subject: [PATCH 204/256] ipmi_si: Avoid spurious errors for optional IRQs Although the IRQ assignment in ipmi_si driver is optional, platform_get_irq() spews error messages unnecessarily: ipmi_si dmi-ipmi-si.0: IRQ index 0 not found Fix this by switching to platform_get_irq_optional(). Cc: stable@vger.kernel.org # 5.4.x Cc: John Donnelly Fixes: 7723f4c5ecdb ("driver core: platform: Add an error message to platform_get_irq*()") Reported-and-tested-by: Patrick Vo Signed-off-by: Takashi Iwai Message-Id: <20200205093146.1352-1-tiwai@suse.de> Signed-off-by: Corey Minyard --- drivers/char/ipmi/ipmi_si_platform.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/char/ipmi/ipmi_si_platform.c b/drivers/char/ipmi/ipmi_si_platform.c index c78127ccbc0d..638c693e17ad 100644 --- a/drivers/char/ipmi/ipmi_si_platform.c +++ b/drivers/char/ipmi/ipmi_si_platform.c @@ -194,7 +194,7 @@ static int platform_ipmi_probe(struct platform_device *pdev) else io.slave_addr = slave_addr; - io.irq = platform_get_irq(pdev, 0); + io.irq = platform_get_irq_optional(pdev, 0); if (io.irq > 0) io.irq_setup = ipmi_std_irq_setup; else @@ -378,7 +378,7 @@ static int acpi_ipmi_probe(struct platform_device *pdev) io.irq = tmp; io.irq_setup = acpi_gpe_irq_setup; } else { - int irq = platform_get_irq(pdev, 0); + int irq = platform_get_irq_optional(pdev, 0); if (irq > 0) { io.irq = irq; From ab14961d10d02d20767612c78ce148f6eb85bd58 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 10 Mar 2020 20:36:16 -0700 Subject: [PATCH 205/256] net: fec: validate the new settings in fec_enet_set_coalesce() fec_enet_set_coalesce() validates the previously set params and if they are within range proceeds to apply the new ones. The new ones, however, are not validated. This seems backwards, probably a copy-paste error? Compile tested only. Fixes: d851b47b22fc ("net: fec: add interrupt coalescence feature support") Signed-off-by: Jakub Kicinski Acked-by: Fugang Duan Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/fec_main.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 4432a59904c7..23c5fef2f1ad 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -2529,15 +2529,15 @@ fec_enet_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *ec) return -EINVAL; } - cycle = fec_enet_us_to_itr_clock(ndev, fep->rx_time_itr); + cycle = fec_enet_us_to_itr_clock(ndev, ec->rx_coalesce_usecs); if (cycle > 0xFFFF) { dev_err(dev, "Rx coalesced usec exceed hardware limitation\n"); return -EINVAL; } - cycle = fec_enet_us_to_itr_clock(ndev, fep->tx_time_itr); + cycle = fec_enet_us_to_itr_clock(ndev, ec->tx_coalesce_usecs); if (cycle > 0xFFFF) { - dev_err(dev, "Rx coalesced usec exceed hardware limitation\n"); + dev_err(dev, "Tx coalesced usec exceed hardware limitation\n"); return -EINVAL; } From eecba79e694eda24ba698fe1bdf0466d2f797b42 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 11 Mar 2020 16:37:02 -0700 Subject: [PATCH 206/256] MAINTAINERS: remove Sathya Perla as Emulex NIC maintainer Remove Sathya Perla, sathya.perla@broadcom.com is bouncing. The driver has 3 more maintainers. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- MAINTAINERS | 1 - 1 file changed, 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 6693ce1b9e21..39937a4d608e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6197,7 +6197,6 @@ S: Supported F: drivers/scsi/be2iscsi/ Emulex 10Gbps NIC BE2, BE3-R, Lancer, Skyhawk-R DRIVER (be2net) -M: Sathya Perla M: Ajit Khaparde M: Sriharsha Basavapatna M: Somnath Kotur From f9fc28a8de2fb367f1ab76f0cf176ca545db3d6f Mon Sep 17 00:00:00 2001 From: Amol Grover Date: Thu, 12 Mar 2020 11:04:20 +0530 Subject: [PATCH 207/256] net: caif: Add lockdep expression to RCU traversal primitive caifdevs->list is traversed using list_for_each_entry_rcu() outside an RCU read-side critical section but under the protection of rtnl_mutex. Hence, add the corresponding lockdep expression to silence the following false-positive warning: [ 10.868467] ============================= [ 10.869082] WARNING: suspicious RCU usage [ 10.869817] 5.6.0-rc1-00177-g06ec0a154aae4 #1 Not tainted [ 10.870804] ----------------------------- [ 10.871557] net/caif/caif_dev.c:115 RCU-list traversed in non-reader section!! Reported-by: kernel test robot Signed-off-by: Amol Grover Signed-off-by: David S. Miller --- net/caif/caif_dev.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index 03c7cdd8e4cb..195d2d67be8a 100644 --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -112,7 +112,8 @@ static struct caif_device_entry *caif_get(struct net_device *dev) caif_device_list(dev_net(dev)); struct caif_device_entry *caifd; - list_for_each_entry_rcu(caifd, &caifdevs->list, list) { + list_for_each_entry_rcu(caifd, &caifdevs->list, list, + lockdep_rtnl_is_held()) { if (caifd->netdev == dev) return caifd; } From f3cc008bf6d59b8d93b4190e01d3e557b0040e15 Mon Sep 17 00:00:00 2001 From: Dominik Czarnota Date: Mon, 9 Mar 2020 16:22:50 +0100 Subject: [PATCH 208/256] sxgbe: Fix off by one in samsung driver strncpy size arg This patch fixes an off-by-one error in strncpy size argument in drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c. The issue is that in: strncmp(opt, "eee_timer:", 6) the passed string literal: "eee_timer:" has 10 bytes (without the NULL byte) and the passed size argument is 6. As a result, the logic will also accept other, malformed strings, e.g. "eee_tiXXX:". This bug doesn't seem to have any security impact since its present in module's cmdline parsing code. Signed-off-by: Dominik Czarnota Signed-off-by: David S. Miller --- drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c index c705743d69f7..2cc8184b7e6b 100644 --- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c +++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c @@ -2277,7 +2277,7 @@ static int __init sxgbe_cmdline_opt(char *str) if (!str || !*str) return -EINVAL; while ((opt = strsep(&str, ",")) != NULL) { - if (!strncmp(opt, "eee_timer:", 6)) { + if (!strncmp(opt, "eee_timer:", 10)) { if (kstrtoint(opt + 10, 0, &eee_timer)) goto err; } From 46e4c421a053c36bf7a33dda2272481bcaf3eed3 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Mon, 9 Mar 2020 11:34:35 -0400 Subject: [PATCH 209/256] net/packet: tpacket_rcv: do not increment ring index on drop In one error case, tpacket_rcv drops packets after incrementing the ring producer index. If this happens, it does not update tp_status to TP_STATUS_USER and thus the reader is stalled for an iteration of the ring, causing out of order arrival. The only such error path is when virtio_net_hdr_from_skb fails due to encountering an unknown GSO type. Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- net/packet/af_packet.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 30c6879d6774..e5b0986215d2 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2274,6 +2274,13 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, TP_STATUS_KERNEL, (macoff+snaplen)); if (!h.raw) goto drop_n_account; + + if (do_vnet && + virtio_net_hdr_from_skb(skb, h.raw + macoff - + sizeof(struct virtio_net_hdr), + vio_le(), true, 0)) + goto drop_n_account; + if (po->tp_version <= TPACKET_V2) { packet_increment_rx_head(po, &po->rx_ring); /* @@ -2286,12 +2293,6 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, status |= TP_STATUS_LOSING; } - if (do_vnet && - virtio_net_hdr_from_skb(skb, h.raw + macoff - - sizeof(struct virtio_net_hdr), - vio_le(), true, 0)) - goto drop_n_account; - po->stats.stats1.tp_packets++; if (copy_skb) { status |= TP_STATUS_COPY; From a20f997010c4ec76eaa55b8cc047d76dcac69f70 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 11 Mar 2020 16:24:24 +0100 Subject: [PATCH 210/256] net: dsa: Don't instantiate phylink for CPU/DSA ports unless needed By default, DSA drivers should configure CPU and DSA ports to their maximum speed. In many configurations this is sufficient to make the link work. In some cases it is necessary to configure the link to run slower, e.g. because of limitations of the SoC it is connected to. Or back to back PHYs are used and the PHY needs to be driven in order to establish link. In this case, phylink is used. Only instantiate phylink if it is required. If there is no PHY, or no fixed link properties, phylink can upset a link which works in the default configuration. Fixes: 0e27921816ad ("net: dsa: Use PHYLINK for the CPU/DSA ports") Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- net/dsa/port.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/net/dsa/port.c b/net/dsa/port.c index ed7dabb57985..ec13dc666788 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -648,9 +648,14 @@ err_phy_connect: int dsa_port_link_register_of(struct dsa_port *dp) { struct dsa_switch *ds = dp->ds; + struct device_node *phy_np; - if (!ds->ops->adjust_link) - return dsa_port_phylink_register(dp); + if (!ds->ops->adjust_link) { + phy_np = of_parse_phandle(dp->dn, "phy-handle", 0); + if (of_phy_is_fixed_link(dp->dn) || phy_np) + return dsa_port_phylink_register(dp); + return 0; + } dev_warn(ds->dev, "Using legacy PHYLIB callbacks. Please migrate to PHYLINK!\n"); @@ -665,11 +670,12 @@ void dsa_port_link_unregister_of(struct dsa_port *dp) { struct dsa_switch *ds = dp->ds; - if (!ds->ops->adjust_link) { + if (!ds->ops->adjust_link && dp->pl) { rtnl_lock(); phylink_disconnect_phy(dp->pl); rtnl_unlock(); phylink_destroy(dp->pl); + dp->pl = NULL; return; } From 2677625387056136e256c743e3285b4fe3da87bb Mon Sep 17 00:00:00 2001 From: Paolo Lungaroni Date: Wed, 11 Mar 2020 17:54:06 +0100 Subject: [PATCH 211/256] seg6: fix SRv6 L2 tunnels to use IANA-assigned protocol number The Internet Assigned Numbers Authority (IANA) has recently assigned a protocol number value of 143 for Ethernet [1]. Before this assignment, encapsulation mechanisms such as Segment Routing used the IPv6-NoNxt protocol number (59) to indicate that the encapsulated payload is an Ethernet frame. In this patch, we add the definition of the Ethernet protocol number to the kernel headers and update the SRv6 L2 tunnels to use it. [1] https://www.iana.org/assignments/protocol-numbers/protocol-numbers.xhtml Signed-off-by: Paolo Lungaroni Reviewed-by: Andrea Mayer Acked-by: Ahmed Abdelsalam Signed-off-by: David S. Miller --- include/uapi/linux/in.h | 2 ++ net/ipv6/seg6_iptunnel.c | 2 +- net/ipv6/seg6_local.c | 2 +- 3 files changed, 4 insertions(+), 2 deletions(-) diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index 1521073b6348..8533bf07450f 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -74,6 +74,8 @@ enum { #define IPPROTO_UDPLITE IPPROTO_UDPLITE IPPROTO_MPLS = 137, /* MPLS in IP (RFC 4023) */ #define IPPROTO_MPLS IPPROTO_MPLS + IPPROTO_ETHERNET = 143, /* Ethernet-within-IPv6 Encapsulation */ +#define IPPROTO_ETHERNET IPPROTO_ETHERNET IPPROTO_RAW = 255, /* Raw IP packets */ #define IPPROTO_RAW IPPROTO_RAW IPPROTO_MPTCP = 262, /* Multipath TCP connection */ diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index ab7f124ff5d7..8c52efe299cc 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -268,7 +268,7 @@ static int seg6_do_srh(struct sk_buff *skb) skb_mac_header_rebuild(skb); skb_push(skb, skb->mac_len); - err = seg6_do_srh_encap(skb, tinfo->srh, NEXTHDR_NONE); + err = seg6_do_srh_encap(skb, tinfo->srh, IPPROTO_ETHERNET); if (err) return err; diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index 7cbc19731997..8165802d8e05 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -282,7 +282,7 @@ static int input_action_end_dx2(struct sk_buff *skb, struct net_device *odev; struct ethhdr *eth; - if (!decap_and_validate(skb, NEXTHDR_NONE)) + if (!decap_and_validate(skb, IPPROTO_ETHERNET)) goto drop; if (!pskb_may_pull(skb, ETH_HLEN)) From f81649dfa5343eef7e579eb6f8dd8bd6d300ec31 Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Wed, 11 Mar 2020 18:07:09 +0100 Subject: [PATCH 212/256] s390/qeth: use page pointers to manage RX buffer pool The RX buffer elements are always backed with full pages, reflect this in the pointer type. Signed-off-by: Julian Wiedmann Signed-off-by: David S. Miller --- drivers/s390/net/qeth_core.h | 2 +- drivers/s390/net/qeth_core_main.c | 35 +++++++++++++++---------------- 2 files changed, 18 insertions(+), 19 deletions(-) diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index 9575a627a1e1..242b05f644eb 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -369,7 +369,7 @@ enum qeth_qdio_info_states { struct qeth_buffer_pool_entry { struct list_head list; struct list_head init_list; - void *elements[QDIO_MAX_ELEMENTS_PER_BUFFER]; + struct page *elements[QDIO_MAX_ELEMENTS_PER_BUFFER]; }; struct qeth_qdio_buffer_pool { diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index a599801d7727..8f682fc178a9 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -215,7 +215,6 @@ EXPORT_SYMBOL_GPL(qeth_clear_working_pool_list); static int qeth_alloc_buffer_pool(struct qeth_card *card) { struct qeth_buffer_pool_entry *pool_entry; - void *ptr; int i, j; QETH_CARD_TEXT(card, 5, "alocpool"); @@ -225,17 +224,18 @@ static int qeth_alloc_buffer_pool(struct qeth_card *card) qeth_free_buffer_pool(card); return -ENOMEM; } + for (j = 0; j < QETH_MAX_BUFFER_ELEMENTS(card); ++j) { - ptr = (void *) __get_free_page(GFP_KERNEL); - if (!ptr) { + struct page *page = alloc_page(GFP_KERNEL); + + if (!page) { while (j > 0) - free_page((unsigned long) - pool_entry->elements[--j]); + __free_page(pool_entry->elements[--j]); kfree(pool_entry); qeth_free_buffer_pool(card); return -ENOMEM; } - pool_entry->elements[j] = ptr; + pool_entry->elements[j] = page; } list_add(&pool_entry->init_list, &card->qdio.init_pool.entry_list); @@ -1177,7 +1177,7 @@ static void qeth_free_buffer_pool(struct qeth_card *card) list_for_each_entry_safe(pool_entry, tmp, &card->qdio.init_pool.entry_list, init_list){ for (i = 0; i < QETH_MAX_BUFFER_ELEMENTS(card); ++i) - free_page((unsigned long)pool_entry->elements[i]); + __free_page(pool_entry->elements[i]); list_del(&pool_entry->init_list); kfree(pool_entry); } @@ -2573,7 +2573,6 @@ static struct qeth_buffer_pool_entry *qeth_find_free_buffer_pool_entry( struct list_head *plh; struct qeth_buffer_pool_entry *entry; int i, free; - struct page *page; if (list_empty(&card->qdio.in_buf_pool.entry_list)) return NULL; @@ -2582,7 +2581,7 @@ static struct qeth_buffer_pool_entry *qeth_find_free_buffer_pool_entry( entry = list_entry(plh, struct qeth_buffer_pool_entry, list); free = 1; for (i = 0; i < QETH_MAX_BUFFER_ELEMENTS(card); ++i) { - if (page_count(virt_to_page(entry->elements[i])) > 1) { + if (page_count(entry->elements[i]) > 1) { free = 0; break; } @@ -2597,15 +2596,15 @@ static struct qeth_buffer_pool_entry *qeth_find_free_buffer_pool_entry( entry = list_entry(card->qdio.in_buf_pool.entry_list.next, struct qeth_buffer_pool_entry, list); for (i = 0; i < QETH_MAX_BUFFER_ELEMENTS(card); ++i) { - if (page_count(virt_to_page(entry->elements[i])) > 1) { - page = alloc_page(GFP_ATOMIC); - if (!page) { + if (page_count(entry->elements[i]) > 1) { + struct page *page = alloc_page(GFP_ATOMIC); + + if (!page) return NULL; - } else { - free_page((unsigned long)entry->elements[i]); - entry->elements[i] = page_address(page); - QETH_CARD_STAT_INC(card, rx_sg_alloc_page); - } + + __free_page(entry->elements[i]); + entry->elements[i] = page; + QETH_CARD_STAT_INC(card, rx_sg_alloc_page); } } list_del_init(&entry->list); @@ -2641,7 +2640,7 @@ static int qeth_init_input_buffer(struct qeth_card *card, for (i = 0; i < QETH_MAX_BUFFER_ELEMENTS(card); ++i) { buf->buffer->element[i].length = PAGE_SIZE; buf->buffer->element[i].addr = - virt_to_phys(pool_entry->elements[i]); + page_to_phys(pool_entry->elements[i]); if (i == QETH_MAX_BUFFER_ELEMENTS(card) - 1) buf->buffer->element[i].eflags = SBAL_EFLAGS_LAST_ENTRY; else From 0f75e149298bedc48db03259a38a303611d247b1 Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Wed, 11 Mar 2020 18:07:10 +0100 Subject: [PATCH 213/256] s390/qeth: refactor buffer pool code In preparation for a subsequent fix, split out helpers to allocate/free individual pool entries. Signed-off-by: Julian Wiedmann Signed-off-by: David S. Miller --- drivers/s390/net/qeth_core_main.c | 83 +++++++++++++++++++------------ 1 file changed, 51 insertions(+), 32 deletions(-) diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 8f682fc178a9..ceab3d0c4dfa 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -65,7 +65,6 @@ static struct lock_class_key qdio_out_skb_queue_key; static void qeth_issue_next_read_cb(struct qeth_card *card, struct qeth_cmd_buffer *iob, unsigned int data_length); -static void qeth_free_buffer_pool(struct qeth_card *); static int qeth_qdio_establish(struct qeth_card *); static void qeth_free_qdio_queues(struct qeth_card *card); static void qeth_notify_skbs(struct qeth_qdio_out_q *queue, @@ -212,33 +211,66 @@ void qeth_clear_working_pool_list(struct qeth_card *card) } EXPORT_SYMBOL_GPL(qeth_clear_working_pool_list); +static void qeth_free_pool_entry(struct qeth_buffer_pool_entry *entry) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(entry->elements); i++) { + if (entry->elements[i]) + __free_page(entry->elements[i]); + } + + kfree(entry); +} + +static void qeth_free_buffer_pool(struct qeth_card *card) +{ + struct qeth_buffer_pool_entry *entry, *tmp; + + list_for_each_entry_safe(entry, tmp, &card->qdio.init_pool.entry_list, + init_list) { + list_del(&entry->init_list); + qeth_free_pool_entry(entry); + } +} + +static struct qeth_buffer_pool_entry *qeth_alloc_pool_entry(unsigned int pages) +{ + struct qeth_buffer_pool_entry *entry; + unsigned int i; + + entry = kzalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) + return NULL; + + for (i = 0; i < pages; i++) { + entry->elements[i] = alloc_page(GFP_KERNEL); + + if (!entry->elements[i]) { + qeth_free_pool_entry(entry); + return NULL; + } + } + + return entry; +} + static int qeth_alloc_buffer_pool(struct qeth_card *card) { - struct qeth_buffer_pool_entry *pool_entry; - int i, j; + unsigned int buf_elements = QETH_MAX_BUFFER_ELEMENTS(card); + unsigned int i; QETH_CARD_TEXT(card, 5, "alocpool"); for (i = 0; i < card->qdio.init_pool.buf_count; ++i) { - pool_entry = kzalloc(sizeof(*pool_entry), GFP_KERNEL); - if (!pool_entry) { + struct qeth_buffer_pool_entry *entry; + + entry = qeth_alloc_pool_entry(buf_elements); + if (!entry) { qeth_free_buffer_pool(card); return -ENOMEM; } - for (j = 0; j < QETH_MAX_BUFFER_ELEMENTS(card); ++j) { - struct page *page = alloc_page(GFP_KERNEL); - - if (!page) { - while (j > 0) - __free_page(pool_entry->elements[--j]); - kfree(pool_entry); - qeth_free_buffer_pool(card); - return -ENOMEM; - } - pool_entry->elements[j] = page; - } - list_add(&pool_entry->init_list, - &card->qdio.init_pool.entry_list); + list_add(&entry->init_list, &card->qdio.init_pool.entry_list); } return 0; } @@ -1170,19 +1202,6 @@ void qeth_drain_output_queues(struct qeth_card *card) } EXPORT_SYMBOL_GPL(qeth_drain_output_queues); -static void qeth_free_buffer_pool(struct qeth_card *card) -{ - struct qeth_buffer_pool_entry *pool_entry, *tmp; - int i = 0; - list_for_each_entry_safe(pool_entry, tmp, - &card->qdio.init_pool.entry_list, init_list){ - for (i = 0; i < QETH_MAX_BUFFER_ELEMENTS(card); ++i) - __free_page(pool_entry->elements[i]); - list_del(&pool_entry->init_list); - kfree(pool_entry); - } -} - static int qeth_osa_set_output_queues(struct qeth_card *card, bool single) { unsigned int count = single ? 1 : card->dev->num_tx_queues; From 5d4f78564c9ca38146102c4f8998edcad5afbc22 Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Wed, 11 Mar 2020 18:07:11 +0100 Subject: [PATCH 214/256] s390/qeth: implement smarter resizing of the RX buffer pool The RX buffer pool is allocated in qeth_alloc_qdio_queues(). A subsequent pool resizing is then handled in a very simple way: first free the current pool, then allocate a new pool of the requested size. There's two ways where this can go wrong: 1. if the resize action happens _before_ the initial pool was allocated, then a subsequent initialization will call qeth_alloc_qdio_queues() and fill the pool with a second(!) set of pages. We consume twice the planned amount of memory. This is easy to fix - just skip the resizing if the queues haven't been allocated yet. 2. if the initial pool was created by qeth_alloc_qdio_queues() but a subsequent resizing fails, then the device has no(!) RX buffer pool. The next initialization will _not_ call qeth_alloc_qdio_queues(), and attempting to back the RX buffers with pages in qeth_init_qdio_queues() will fail. Not very difficult to fix either - instead of re-allocating the whole pool, just allocate/free as many entries to match the desired size. Fixes: 4a71df50047f ("qeth: new qeth device driver") Signed-off-by: Julian Wiedmann Signed-off-by: David S. Miller --- drivers/s390/net/qeth_core.h | 2 +- drivers/s390/net/qeth_core_main.c | 55 ++++++++++++++++++++++++++----- drivers/s390/net/qeth_core_sys.c | 9 +++-- drivers/s390/net/qeth_l3_sys.c | 9 +++-- 4 files changed, 56 insertions(+), 19 deletions(-) diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index 242b05f644eb..468cada49e72 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -983,7 +983,7 @@ extern const struct attribute_group qeth_device_blkt_group; extern const struct device_type qeth_generic_devtype; const char *qeth_get_cardname_short(struct qeth_card *); -int qeth_realloc_buffer_pool(struct qeth_card *, int); +int qeth_resize_buffer_pool(struct qeth_card *card, unsigned int count); int qeth_core_load_discipline(struct qeth_card *, enum qeth_discipline_id); void qeth_core_free_discipline(struct qeth_card *); diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index ceab3d0c4dfa..6d3f2f14b414 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -275,18 +275,57 @@ static int qeth_alloc_buffer_pool(struct qeth_card *card) return 0; } -int qeth_realloc_buffer_pool(struct qeth_card *card, int bufcnt) +int qeth_resize_buffer_pool(struct qeth_card *card, unsigned int count) { + unsigned int buf_elements = QETH_MAX_BUFFER_ELEMENTS(card); + struct qeth_qdio_buffer_pool *pool = &card->qdio.init_pool; + struct qeth_buffer_pool_entry *entry, *tmp; + int delta = count - pool->buf_count; + LIST_HEAD(entries); + QETH_CARD_TEXT(card, 2, "realcbp"); - /* TODO: steel/add buffers from/to a running card's buffer pool (?) */ - qeth_clear_working_pool_list(card); - qeth_free_buffer_pool(card); - card->qdio.in_buf_pool.buf_count = bufcnt; - card->qdio.init_pool.buf_count = bufcnt; - return qeth_alloc_buffer_pool(card); + /* Defer until queue is allocated: */ + if (!card->qdio.in_q) + goto out; + + /* Remove entries from the pool: */ + while (delta < 0) { + entry = list_first_entry(&pool->entry_list, + struct qeth_buffer_pool_entry, + init_list); + list_del(&entry->init_list); + qeth_free_pool_entry(entry); + + delta++; + } + + /* Allocate additional entries: */ + while (delta > 0) { + entry = qeth_alloc_pool_entry(buf_elements); + if (!entry) { + list_for_each_entry_safe(entry, tmp, &entries, + init_list) { + list_del(&entry->init_list); + qeth_free_pool_entry(entry); + } + + return -ENOMEM; + } + + list_add(&entry->init_list, &entries); + + delta--; + } + + list_splice(&entries, &pool->entry_list); + +out: + card->qdio.in_buf_pool.buf_count = count; + pool->buf_count = count; + return 0; } -EXPORT_SYMBOL_GPL(qeth_realloc_buffer_pool); +EXPORT_SYMBOL_GPL(qeth_resize_buffer_pool); static void qeth_free_qdio_queue(struct qeth_qdio_q *q) { diff --git a/drivers/s390/net/qeth_core_sys.c b/drivers/s390/net/qeth_core_sys.c index 2bd9993aa60b..78cae61bc924 100644 --- a/drivers/s390/net/qeth_core_sys.c +++ b/drivers/s390/net/qeth_core_sys.c @@ -247,8 +247,8 @@ static ssize_t qeth_dev_bufcnt_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct qeth_card *card = dev_get_drvdata(dev); + unsigned int cnt; char *tmp; - int cnt, old_cnt; int rc = 0; mutex_lock(&card->conf_mutex); @@ -257,13 +257,12 @@ static ssize_t qeth_dev_bufcnt_store(struct device *dev, goto out; } - old_cnt = card->qdio.in_buf_pool.buf_count; cnt = simple_strtoul(buf, &tmp, 10); cnt = (cnt < QETH_IN_BUF_COUNT_MIN) ? QETH_IN_BUF_COUNT_MIN : ((cnt > QETH_IN_BUF_COUNT_MAX) ? QETH_IN_BUF_COUNT_MAX : cnt); - if (old_cnt != cnt) { - rc = qeth_realloc_buffer_pool(card, cnt); - } + + rc = qeth_resize_buffer_pool(card, cnt); + out: mutex_unlock(&card->conf_mutex); return rc ? rc : count; diff --git a/drivers/s390/net/qeth_l3_sys.c b/drivers/s390/net/qeth_l3_sys.c index 29f2517d2a31..a3d1c3bdfadb 100644 --- a/drivers/s390/net/qeth_l3_sys.c +++ b/drivers/s390/net/qeth_l3_sys.c @@ -206,12 +206,11 @@ static ssize_t qeth_l3_dev_sniffer_store(struct device *dev, qdio_get_ssqd_desc(CARD_DDEV(card), &card->ssqd); if (card->ssqd.qdioac2 & CHSC_AC2_SNIFFER_AVAILABLE) { card->options.sniffer = i; - if (card->qdio.init_pool.buf_count != - QETH_IN_BUF_COUNT_MAX) - qeth_realloc_buffer_pool(card, - QETH_IN_BUF_COUNT_MAX); - } else + qeth_resize_buffer_pool(card, QETH_IN_BUF_COUNT_MAX); + } else { rc = -EPERM; + } + break; default: rc = -EINVAL; From 06669ea346e476a5339033d77ef175566a40efbb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 11 Mar 2020 11:44:26 -0700 Subject: [PATCH 215/256] net: memcg: fix lockdep splat in inet_csk_accept() Locking newsk while still holding the listener lock triggered a lockdep splat [1] We can simply move the memcg code after we release the listener lock, as this can also help if multiple threads are sharing a common listener. Also fix a typo while reading socket sk_rmem_alloc. [1] WARNING: possible recursive locking detected 5.6.0-rc3-syzkaller #0 Not tainted -------------------------------------------- syz-executor598/9524 is trying to acquire lock: ffff88808b5b8b90 (sk_lock-AF_INET6){+.+.}, at: lock_sock include/net/sock.h:1541 [inline] ffff88808b5b8b90 (sk_lock-AF_INET6){+.+.}, at: inet_csk_accept+0x69f/0xd30 net/ipv4/inet_connection_sock.c:492 but task is already holding lock: ffff88808b5b9590 (sk_lock-AF_INET6){+.+.}, at: lock_sock include/net/sock.h:1541 [inline] ffff88808b5b9590 (sk_lock-AF_INET6){+.+.}, at: inet_csk_accept+0x8d/0xd30 net/ipv4/inet_connection_sock.c:445 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(sk_lock-AF_INET6); lock(sk_lock-AF_INET6); *** DEADLOCK *** May be due to missing lock nesting notation 1 lock held by syz-executor598/9524: #0: ffff88808b5b9590 (sk_lock-AF_INET6){+.+.}, at: lock_sock include/net/sock.h:1541 [inline] #0: ffff88808b5b9590 (sk_lock-AF_INET6){+.+.}, at: inet_csk_accept+0x8d/0xd30 net/ipv4/inet_connection_sock.c:445 stack backtrace: CPU: 0 PID: 9524 Comm: syz-executor598 Not tainted 5.6.0-rc3-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x188/0x20d lib/dump_stack.c:118 print_deadlock_bug kernel/locking/lockdep.c:2370 [inline] check_deadlock kernel/locking/lockdep.c:2411 [inline] validate_chain kernel/locking/lockdep.c:2954 [inline] __lock_acquire.cold+0x114/0x288 kernel/locking/lockdep.c:3954 lock_acquire+0x197/0x420 kernel/locking/lockdep.c:4484 lock_sock_nested+0xc5/0x110 net/core/sock.c:2947 lock_sock include/net/sock.h:1541 [inline] inet_csk_accept+0x69f/0xd30 net/ipv4/inet_connection_sock.c:492 inet_accept+0xe9/0x7c0 net/ipv4/af_inet.c:734 __sys_accept4_file+0x3ac/0x5b0 net/socket.c:1758 __sys_accept4+0x53/0x90 net/socket.c:1809 __do_sys_accept4 net/socket.c:1821 [inline] __se_sys_accept4 net/socket.c:1818 [inline] __x64_sys_accept4+0x93/0xf0 net/socket.c:1818 do_syscall_64+0xf6/0x790 arch/x86/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x4445c9 Code: e8 0c 0d 03 00 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 eb 08 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007ffc35b37608 EFLAGS: 00000246 ORIG_RAX: 0000000000000120 RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00000000004445c9 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000003 RBP: 0000000000000000 R08: 0000000000306777 R09: 0000000000306777 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00000000004053d0 R14: 0000000000000000 R15: 0000000000000000 Fixes: d752a4986532 ("net: memcg: late association of sock to memcg") Signed-off-by: Eric Dumazet Cc: Shakeel Butt Reported-by: syzbot Signed-off-by: David S. Miller --- net/ipv4/inet_connection_sock.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 65a3b2565102..d545fb99a8a1 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -483,27 +483,27 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern) spin_unlock_bh(&queue->fastopenq.lock); } - if (mem_cgroup_sockets_enabled) { +out: + release_sock(sk); + if (newsk && mem_cgroup_sockets_enabled) { int amt; /* atomically get the memory usage, set and charge the - * sk->sk_memcg. + * newsk->sk_memcg. */ lock_sock(newsk); - /* The sk has not been accepted yet, no need to look at - * sk->sk_wmem_queued. + /* The socket has not been accepted yet, no need to look at + * newsk->sk_wmem_queued. */ amt = sk_mem_pages(newsk->sk_forward_alloc + - atomic_read(&sk->sk_rmem_alloc)); + atomic_read(&newsk->sk_rmem_alloc)); mem_cgroup_sk_alloc(newsk); if (newsk->sk_memcg && amt) mem_cgroup_charge_skmem(newsk->sk_memcg, amt); release_sock(newsk); } -out: - release_sock(sk); if (req) reqsk_put(req); return newsk; From 012fc74517b25177dfede2ed45cd108258564e4a Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 11 Mar 2020 21:02:31 +0100 Subject: [PATCH 216/256] net: dsa: mv88e6xxx: Add missing mask of ATU occupancy register Only the bottom 12 bits contain the ATU bin occupancy statistics. The upper bits need masking off. Fixes: e0c69ca7dfbb ("net: dsa: mv88e6xxx: Add ATU occupancy via devlink resources") Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 8c9289549688..2f993e673ec7 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -2769,6 +2769,8 @@ static u64 mv88e6xxx_devlink_atu_bin_get(struct mv88e6xxx_chip *chip, goto unlock; } + occupancy &= MV88E6XXX_G2_ATU_STATS_MASK; + unlock: mv88e6xxx_reg_unlock(chip); From e1f550dc44a4d535da4e25ada1b0eaf8f3417929 Mon Sep 17 00:00:00 2001 From: Chris Packham Date: Thu, 12 Mar 2020 09:05:46 +1300 Subject: [PATCH 217/256] net: mvmdio: avoid error message for optional IRQ Per the dt-binding the interrupt is optional so use platform_get_irq_optional() instead of platform_get_irq(). Since commit 7723f4c5ecdb ("driver core: platform: Add an error message to platform_get_irq*()") platform_get_irq() produces an error message orion-mdio f1072004.mdio: IRQ index 0 not found which is perfectly normal if one hasn't specified the optional property in the device tree. Signed-off-by: Chris Packham Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvmdio.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c index 0b9e851f3da4..d2e2dc538428 100644 --- a/drivers/net/ethernet/marvell/mvmdio.c +++ b/drivers/net/ethernet/marvell/mvmdio.c @@ -347,7 +347,7 @@ static int orion_mdio_probe(struct platform_device *pdev) } - dev->err_interrupt = platform_get_irq(pdev, 0); + dev->err_interrupt = platform_get_irq_optional(pdev, 0); if (dev->err_interrupt > 0 && resource_size(r) < MVMDIO_ERR_INT_MASK + 4) { dev_err(&pdev->dev, @@ -364,8 +364,8 @@ static int orion_mdio_probe(struct platform_device *pdev) writel(MVMDIO_ERR_INT_SMI_DONE, dev->regs + MVMDIO_ERR_INT_MASK); - } else if (dev->err_interrupt == -EPROBE_DEFER) { - ret = -EPROBE_DEFER; + } else if (dev->err_interrupt < 0) { + ret = dev->err_interrupt; goto out_mdio; } From 58d6fee50e67bb1c69977f1a534ccb17bf58b0f1 Mon Sep 17 00:00:00 2001 From: Michael Auchter Date: Tue, 10 Mar 2020 15:58:40 -0500 Subject: [PATCH 218/256] misc: eeprom: at24: fix regulator underflow The at24 driver attempts to read a byte from the device to validate that it's actually present, and if not, disables the vcc regulator and returns -ENODEV. However, between the read and the error handling path, pm_runtime_idle() is called and invokes the driver's suspend callback, which also disables the vcc regulator. This leads to an underflow of the regulator enable count if the EEPROM is not present. Move the pm_runtime_suspend() call to be after the error handling path to resolve this. Fixes: cd5676db0574 ("misc: eeprom: at24: support pm_runtime control") Signed-off-by: Michael Auchter Signed-off-by: Bartosz Golaszewski --- drivers/misc/eeprom/at24.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c index 031eb64549af..282c9ef68ed2 100644 --- a/drivers/misc/eeprom/at24.c +++ b/drivers/misc/eeprom/at24.c @@ -712,13 +712,14 @@ static int at24_probe(struct i2c_client *client) * chip is functional. */ err = at24_read(at24, 0, &test_byte, 1); - pm_runtime_idle(dev); if (err) { pm_runtime_disable(dev); regulator_disable(at24->vcc_reg); return -ENODEV; } + pm_runtime_idle(dev); + if (writable) dev_info(dev, "%u byte %s EEPROM, writable, %u bytes/write\n", byte_len, client->name, at24->write_max); From 18d200460cd73636d4f20674085c39e32b4e0097 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Wed, 11 Mar 2020 10:20:36 +0100 Subject: [PATCH 219/256] mmc: core: Respect MMC_CAP_NEED_RSP_BUSY for eMMC sleep command The busy timeout for the CMD5 to put the eMMC into sleep state, is specific to the card. Potentially the timeout may exceed the host->max_busy_timeout. If that becomes the case, mmc_sleep() converts from using an R1B response to an R1 response, as to prevent the host from doing HW busy detection. However, it has turned out that some hosts requires an R1B response no matter what, so let's respect that via checking MMC_CAP_NEED_RSP_BUSY. Note that, if the R1B gets enforced, the host becomes fully responsible of managing the needed busy timeout, in one way or the other. Suggested-by: Sowjanya Komatineni Cc: Link: https://lore.kernel.org/r/20200311092036.16084-1-ulf.hansson@linaro.org Signed-off-by: Ulf Hansson --- drivers/mmc/core/mmc.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index f6912ded652d..de14b5845f52 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -1910,9 +1910,12 @@ static int mmc_sleep(struct mmc_host *host) * If the max_busy_timeout of the host is specified, validate it against * the sleep cmd timeout. A failure means we need to prevent the host * from doing hw busy detection, which is done by converting to a R1 - * response instead of a R1B. + * response instead of a R1B. Note, some hosts requires R1B, which also + * means they are on their own when it comes to deal with the busy + * timeout. */ - if (host->max_busy_timeout && (timeout_ms > host->max_busy_timeout)) { + if (!(host->caps & MMC_CAP_NEED_RSP_BUSY) && host->max_busy_timeout && + (timeout_ms > host->max_busy_timeout)) { cmd.flags = MMC_RSP_R1 | MMC_CMD_AC; } else { cmd.flags = MMC_RSP_R1B | MMC_CMD_AC; From f967140dfb7442e2db0868b03b961f9c59418a1b Mon Sep 17 00:00:00 2001 From: Kim Phillips Date: Wed, 11 Mar 2020 14:13:21 -0500 Subject: [PATCH 220/256] perf/amd/uncore: Replace manual sampling check with CAP_NO_INTERRUPT flag Enable the sampling check in kernel/events/core.c::perf_event_open(), which returns the more appropriate -EOPNOTSUPP. BEFORE: $ sudo perf record -a -e instructions,l3_request_g1.caching_l3_cache_accesses true Error: The sys_perf_event_open() syscall returned with 22 (Invalid argument) for event (l3_request_g1.caching_l3_cache_accesses). /bin/dmesg | grep -i perf may provide additional information. With nothing relevant in dmesg. AFTER: $ sudo perf record -a -e instructions,l3_request_g1.caching_l3_cache_accesses true Error: l3_request_g1.caching_l3_cache_accesses: PMU Hardware doesn't support sampling/overflow-interrupts. Try 'perf stat' Fixes: c43ca5091a37 ("perf/x86/amd: Add support for AMD NB and L2I "uncore" counters") Signed-off-by: Kim Phillips Signed-off-by: Borislav Petkov Acked-by: Peter Zijlstra Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20200311191323.13124-1-kim.phillips@amd.com --- arch/x86/events/amd/uncore.c | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c index a6ea07f2aa84..4d867a752f0e 100644 --- a/arch/x86/events/amd/uncore.c +++ b/arch/x86/events/amd/uncore.c @@ -190,15 +190,12 @@ static int amd_uncore_event_init(struct perf_event *event) /* * NB and Last level cache counters (MSRs) are shared across all cores - * that share the same NB / Last level cache. Interrupts can be directed - * to a single target core, however, event counts generated by processes - * running on other cores cannot be masked out. So we do not support - * sampling and per-thread events. + * that share the same NB / Last level cache. On family 16h and below, + * Interrupts can be directed to a single target core, however, event + * counts generated by processes running on other cores cannot be masked + * out. So we do not support sampling and per-thread events via + * CAP_NO_INTERRUPT, and we do not enable counter overflow interrupts: */ - if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK) - return -EINVAL; - - /* and we do not enable counter overflow interrupts */ hwc->config = event->attr.config & AMD64_RAW_EVENT_MASK_NB; hwc->idx = -1; @@ -306,7 +303,7 @@ static struct pmu amd_nb_pmu = { .start = amd_uncore_start, .stop = amd_uncore_stop, .read = amd_uncore_read, - .capabilities = PERF_PMU_CAP_NO_EXCLUDE, + .capabilities = PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT, }; static struct pmu amd_llc_pmu = { @@ -317,7 +314,7 @@ static struct pmu amd_llc_pmu = { .start = amd_uncore_start, .stop = amd_uncore_stop, .read = amd_uncore_read, - .capabilities = PERF_PMU_CAP_NO_EXCLUDE, + .capabilities = PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT, }; static struct amd_uncore *amd_uncore_alloc(unsigned int cpu) From 5e6bdd37c5526ef01326df5dabb93011ee89237e Mon Sep 17 00:00:00 2001 From: Stefan Haberland Date: Thu, 12 Mar 2020 14:17:15 +0100 Subject: [PATCH 221/256] s390/dasd: fix data corruption for thin provisioned devices Devices are formatted in multiple of tracks. For an Extent Space Efficient (ESE) volume we get errors when accessing unformatted tracks. In this case the driver either formats the track on the flight for write requests or returns zero data for read requests. In case a request spans multiple tracks, the indication of an unformatted track presented for the first track is incorrectly applied to all tracks covered by the request. As a result, tracks containing data will be handled as empty, resulting in zero data being returned on read, or overwriting existing data with zero on write. Fix by determining the track that gets the NRF error. For write requests only format the track that is surely not formatted. For Read requests all tracks before have returned valid data and should not be touched. All tracks after the unformatted track might be formatted or not. Those are returned to the blocklayer to build a new request. When using alias devices there is a chance that multiple write requests trigger a format of the same track which might lead to data loss. Ensure that a track is formatted only once by maintaining a list of currently processed tracks. Fixes: 5e2b17e712cf ("s390/dasd: Add dynamic formatting support for ESE volumes") Cc: stable@vger.kernel.org # 5.3+ Signed-off-by: Stefan Haberland Reviewed-by: Jan Hoeppner Reviewed-by: Peter Oberparleiter Signed-off-by: Jens Axboe --- drivers/s390/block/dasd.c | 27 +++++- drivers/s390/block/dasd_eckd.c | 163 +++++++++++++++++++++++++++++++-- drivers/s390/block/dasd_int.h | 15 ++- 3 files changed, 193 insertions(+), 12 deletions(-) diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 6cca72782af6..cf87eb27879f 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -178,6 +178,8 @@ struct dasd_block *dasd_alloc_block(void) (unsigned long) block); INIT_LIST_HEAD(&block->ccw_queue); spin_lock_init(&block->queue_lock); + INIT_LIST_HEAD(&block->format_list); + spin_lock_init(&block->format_lock); timer_setup(&block->timer, dasd_block_timeout, 0); spin_lock_init(&block->profile.lock); @@ -1779,20 +1781,26 @@ void dasd_int_handler(struct ccw_device *cdev, unsigned long intparm, if (dasd_ese_needs_format(cqr->block, irb)) { if (rq_data_dir((struct request *)cqr->callback_data) == READ) { - device->discipline->ese_read(cqr); + device->discipline->ese_read(cqr, irb); cqr->status = DASD_CQR_SUCCESS; cqr->stopclk = now; dasd_device_clear_timer(device); dasd_schedule_device_bh(device); return; } - fcqr = device->discipline->ese_format(device, cqr); + fcqr = device->discipline->ese_format(device, cqr, irb); if (IS_ERR(fcqr)) { + if (PTR_ERR(fcqr) == -EINVAL) { + cqr->status = DASD_CQR_ERROR; + return; + } /* * If we can't format now, let the request go * one extra round. Maybe we can format later. */ cqr->status = DASD_CQR_QUEUED; + dasd_schedule_device_bh(device); + return; } else { fcqr->status = DASD_CQR_QUEUED; cqr->status = DASD_CQR_QUEUED; @@ -2748,11 +2756,13 @@ static void __dasd_cleanup_cqr(struct dasd_ccw_req *cqr) { struct request *req; blk_status_t error = BLK_STS_OK; + unsigned int proc_bytes; int status; req = (struct request *) cqr->callback_data; dasd_profile_end(cqr->block, cqr, req); + proc_bytes = cqr->proc_bytes; status = cqr->block->base->discipline->free_cp(cqr, req); if (status < 0) error = errno_to_blk_status(status); @@ -2783,7 +2793,18 @@ static void __dasd_cleanup_cqr(struct dasd_ccw_req *cqr) blk_mq_end_request(req, error); blk_mq_run_hw_queues(req->q, true); } else { - blk_mq_complete_request(req); + /* + * Partial completed requests can happen with ESE devices. + * During read we might have gotten a NRF error and have to + * complete a request partially. + */ + if (proc_bytes) { + blk_update_request(req, BLK_STS_OK, + blk_rq_bytes(req) - proc_bytes); + blk_mq_requeue_request(req, true); + } else { + blk_mq_complete_request(req); + } } } diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index a28b9ff82378..ad44d22e8859 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -207,6 +207,45 @@ static void set_ch_t(struct ch_t *geo, __u32 cyl, __u8 head) geo->head |= head; } +/* + * calculate failing track from sense data depending if + * it is an EAV device or not + */ +static int dasd_eckd_track_from_irb(struct irb *irb, struct dasd_device *device, + sector_t *track) +{ + struct dasd_eckd_private *private = device->private; + u8 *sense = NULL; + u32 cyl; + u8 head; + + sense = dasd_get_sense(irb); + if (!sense) { + DBF_DEV_EVENT(DBF_WARNING, device, "%s", + "ESE error no sense data\n"); + return -EINVAL; + } + if (!(sense[27] & DASD_SENSE_BIT_2)) { + DBF_DEV_EVENT(DBF_WARNING, device, "%s", + "ESE error no valid track data\n"); + return -EINVAL; + } + + if (sense[27] & DASD_SENSE_BIT_3) { + /* enhanced addressing */ + cyl = sense[30] << 20; + cyl |= (sense[31] & 0xF0) << 12; + cyl |= sense[28] << 8; + cyl |= sense[29]; + } else { + cyl = sense[29] << 8; + cyl |= sense[30]; + } + head = sense[31] & 0x0F; + *track = cyl * private->rdc_data.trk_per_cyl + head; + return 0; +} + static int set_timestamp(struct ccw1 *ccw, struct DE_eckd_data *data, struct dasd_device *device) { @@ -2986,6 +3025,37 @@ static int dasd_eckd_format_device(struct dasd_device *base, 0, NULL); } +static bool test_and_set_format_track(struct dasd_format_entry *to_format, + struct dasd_block *block) +{ + struct dasd_format_entry *format; + unsigned long flags; + bool rc = false; + + spin_lock_irqsave(&block->format_lock, flags); + list_for_each_entry(format, &block->format_list, list) { + if (format->track == to_format->track) { + rc = true; + goto out; + } + } + list_add_tail(&to_format->list, &block->format_list); + +out: + spin_unlock_irqrestore(&block->format_lock, flags); + return rc; +} + +static void clear_format_track(struct dasd_format_entry *format, + struct dasd_block *block) +{ + unsigned long flags; + + spin_lock_irqsave(&block->format_lock, flags); + list_del_init(&format->list); + spin_unlock_irqrestore(&block->format_lock, flags); +} + /* * Callback function to free ESE format requests. */ @@ -2993,15 +3063,19 @@ static void dasd_eckd_ese_format_cb(struct dasd_ccw_req *cqr, void *data) { struct dasd_device *device = cqr->startdev; struct dasd_eckd_private *private = device->private; + struct dasd_format_entry *format = data; + clear_format_track(format, cqr->basedev->block); private->count--; dasd_ffree_request(cqr, device); } static struct dasd_ccw_req * -dasd_eckd_ese_format(struct dasd_device *startdev, struct dasd_ccw_req *cqr) +dasd_eckd_ese_format(struct dasd_device *startdev, struct dasd_ccw_req *cqr, + struct irb *irb) { struct dasd_eckd_private *private; + struct dasd_format_entry *format; struct format_data_t fdata; unsigned int recs_per_trk; struct dasd_ccw_req *fcqr; @@ -3011,23 +3085,39 @@ dasd_eckd_ese_format(struct dasd_device *startdev, struct dasd_ccw_req *cqr) struct request *req; sector_t first_trk; sector_t last_trk; + sector_t curr_trk; int rc; req = cqr->callback_data; - base = cqr->block->base; + block = cqr->block; + base = block->base; private = base->private; - block = base->block; blksize = block->bp_block; recs_per_trk = recs_per_track(&private->rdc_data, 0, blksize); + format = &startdev->format_entry; first_trk = blk_rq_pos(req) >> block->s2b_shift; sector_div(first_trk, recs_per_trk); last_trk = (blk_rq_pos(req) + blk_rq_sectors(req) - 1) >> block->s2b_shift; sector_div(last_trk, recs_per_trk); + rc = dasd_eckd_track_from_irb(irb, base, &curr_trk); + if (rc) + return ERR_PTR(rc); - fdata.start_unit = first_trk; - fdata.stop_unit = last_trk; + if (curr_trk < first_trk || curr_trk > last_trk) { + DBF_DEV_EVENT(DBF_WARNING, startdev, + "ESE error track %llu not within range %llu - %llu\n", + curr_trk, first_trk, last_trk); + return ERR_PTR(-EINVAL); + } + format->track = curr_trk; + /* test if track is already in formatting by another thread */ + if (test_and_set_format_track(format, block)) + return ERR_PTR(-EEXIST); + + fdata.start_unit = curr_trk; + fdata.stop_unit = curr_trk; fdata.blksize = blksize; fdata.intensity = private->uses_cdl ? DASD_FMT_INT_COMPAT : 0; @@ -3044,6 +3134,7 @@ dasd_eckd_ese_format(struct dasd_device *startdev, struct dasd_ccw_req *cqr) return fcqr; fcqr->callback = dasd_eckd_ese_format_cb; + fcqr->callback_data = (void *) format; return fcqr; } @@ -3051,29 +3142,87 @@ dasd_eckd_ese_format(struct dasd_device *startdev, struct dasd_ccw_req *cqr) /* * When data is read from an unformatted area of an ESE volume, this function * returns zeroed data and thereby mimics a read of zero data. + * + * The first unformatted track is the one that got the NRF error, the address is + * encoded in the sense data. + * + * All tracks before have returned valid data and should not be touched. + * All tracks after the unformatted track might be formatted or not. This is + * currently not known, remember the processed data and return the remainder of + * the request to the blocklayer in __dasd_cleanup_cqr(). */ -static void dasd_eckd_ese_read(struct dasd_ccw_req *cqr) +static int dasd_eckd_ese_read(struct dasd_ccw_req *cqr, struct irb *irb) { + struct dasd_eckd_private *private; + sector_t first_trk, last_trk; + sector_t first_blk, last_blk; unsigned int blksize, off; + unsigned int recs_per_trk; struct dasd_device *base; struct req_iterator iter; + struct dasd_block *block; + unsigned int skip_block; + unsigned int blk_count; struct request *req; struct bio_vec bv; + sector_t curr_trk; + sector_t end_blk; char *dst; + int rc; req = (struct request *) cqr->callback_data; base = cqr->block->base; blksize = base->block->bp_block; + block = cqr->block; + private = base->private; + skip_block = 0; + blk_count = 0; + + recs_per_trk = recs_per_track(&private->rdc_data, 0, blksize); + first_trk = first_blk = blk_rq_pos(req) >> block->s2b_shift; + sector_div(first_trk, recs_per_trk); + last_trk = last_blk = + (blk_rq_pos(req) + blk_rq_sectors(req) - 1) >> block->s2b_shift; + sector_div(last_trk, recs_per_trk); + rc = dasd_eckd_track_from_irb(irb, base, &curr_trk); + if (rc) + return rc; + + /* sanity check if the current track from sense data is valid */ + if (curr_trk < first_trk || curr_trk > last_trk) { + DBF_DEV_EVENT(DBF_WARNING, base, + "ESE error track %llu not within range %llu - %llu\n", + curr_trk, first_trk, last_trk); + return -EINVAL; + } + + /* + * if not the first track got the NRF error we have to skip over valid + * blocks + */ + if (curr_trk != first_trk) + skip_block = curr_trk * recs_per_trk - first_blk; + + /* we have no information beyond the current track */ + end_blk = (curr_trk + 1) * recs_per_trk; rq_for_each_segment(bv, req, iter) { dst = page_address(bv.bv_page) + bv.bv_offset; for (off = 0; off < bv.bv_len; off += blksize) { - if (dst && rq_data_dir(req) == READ) { + if (first_blk + blk_count >= end_blk) { + cqr->proc_bytes = blk_count * blksize; + return 0; + } + if (dst && !skip_block) { dst += off; memset(dst, 0, blksize); + } else { + skip_block--; } + blk_count++; } } + return 0; } /* diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h index 91c9f9586e0f..fa552f9f1666 100644 --- a/drivers/s390/block/dasd_int.h +++ b/drivers/s390/block/dasd_int.h @@ -187,6 +187,7 @@ struct dasd_ccw_req { void (*callback)(struct dasd_ccw_req *, void *data); void *callback_data; + unsigned int proc_bytes; /* bytes for partial completion */ }; /* @@ -387,8 +388,9 @@ struct dasd_discipline { int (*ext_pool_warn_thrshld)(struct dasd_device *); int (*ext_pool_oos)(struct dasd_device *); int (*ext_pool_exhaust)(struct dasd_device *, struct dasd_ccw_req *); - struct dasd_ccw_req *(*ese_format)(struct dasd_device *, struct dasd_ccw_req *); - void (*ese_read)(struct dasd_ccw_req *); + struct dasd_ccw_req *(*ese_format)(struct dasd_device *, + struct dasd_ccw_req *, struct irb *); + int (*ese_read)(struct dasd_ccw_req *, struct irb *); }; extern struct dasd_discipline *dasd_diag_discipline_pointer; @@ -474,6 +476,11 @@ struct dasd_profile { spinlock_t lock; }; +struct dasd_format_entry { + struct list_head list; + sector_t track; +}; + struct dasd_device { /* Block device stuff. */ struct dasd_block *block; @@ -539,6 +546,7 @@ struct dasd_device { struct dentry *debugfs_dentry; struct dentry *hosts_dentry; struct dasd_profile profile; + struct dasd_format_entry format_entry; }; struct dasd_block { @@ -564,6 +572,9 @@ struct dasd_block { struct dentry *debugfs_dentry; struct dasd_profile profile; + + struct list_head format_list; + spinlock_t format_lock; }; struct dasd_attention_data { From cc3200eac4c5eb11c3f34848a014d1f286316310 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 12 Mar 2020 17:15:48 +0800 Subject: [PATCH 222/256] blk-mq: insert flush request to the front of dispatch queue commit 01e99aeca397 ("blk-mq: insert passthrough request into hctx->dispatch directly") may change to add flush request to the tail of dispatch by applying the 'add_head' parameter of blk_mq_sched_insert_request. Turns out this way causes performance regression on NCQ controller because flush is non-NCQ command, which can't be queued when there is any in-flight NCQ command. When adding flush rq to the front of hctx->dispatch, it is easier to introduce extra time to flush rq's latency compared with adding to the tail of dispatch queue because of S_SCHED_RESTART, then chance of flush merge is increased, and less flush requests may be issued to controller. So always insert flush request to the front of dispatch queue just like before applying commit 01e99aeca397 ("blk-mq: insert passthrough request into hctx->dispatch directly"). Cc: Damien Le Moal Cc: Shinichiro Kawasaki Reported-by: Shinichiro Kawasaki Fixes: 01e99aeca397 ("blk-mq: insert passthrough request into hctx->dispatch directly") Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- block/blk-mq-sched.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 856356b1619e..74cedea56034 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -398,6 +398,28 @@ void blk_mq_sched_insert_request(struct request *rq, bool at_head, WARN_ON(e && (rq->tag != -1)); if (blk_mq_sched_bypass_insert(hctx, !!e, rq)) { + /* + * Firstly normal IO request is inserted to scheduler queue or + * sw queue, meantime we add flush request to dispatch queue( + * hctx->dispatch) directly and there is at most one in-flight + * flush request for each hw queue, so it doesn't matter to add + * flush request to tail or front of the dispatch queue. + * + * Secondly in case of NCQ, flush request belongs to non-NCQ + * command, and queueing it will fail when there is any + * in-flight normal IO request(NCQ command). When adding flush + * rq to the front of hctx->dispatch, it is easier to introduce + * extra time to flush rq's latency because of S_SCHED_RESTART + * compared with adding to the tail of dispatch queue, then + * chance of flush merge is increased, and less flush requests + * will be issued to controller. It is observed that ~10% time + * is saved in blktests block/004 on disk attached to AHCI/NCQ + * drive when adding flush rq to the front of hctx->dispatch. + * + * Simply queue flush rq to the front of hctx->dispatch so that + * intensive flush workloads can benefit in case of NCQ HW. + */ + at_head = (rq->rq_flags & RQF_FLUSH_SEQ) ? true : at_head; blk_mq_request_bypass_insert(rq, at_head, false); goto run; } From b53df2e7442c73a932fb74228147fb946e531585 Mon Sep 17 00:00:00 2001 From: Shin'ichiro Kawasaki Date: Fri, 21 Feb 2020 10:37:08 +0900 Subject: [PATCH 223/256] block: Fix partition support for host aware zoned block devices Commit b72053072c0b ("block: allow partitions on host aware zone devices") introduced the helper function disk_has_partitions() to check if a given disk has valid partitions. However, since this function result directly depends on the disk partition table length rather than the actual existence of valid partitions in the table, it returns true even after all partitions are removed from the disk. For host aware zoned block devices, this results in zone management support to be kept disabled even after removing all partitions. Fix this by changing disk_has_partitions() to walk through the partition table entries and return true if and only if a valid non-zero size partition is found. Fixes: b72053072c0b ("block: allow partitions on host aware zone devices") Cc: stable@vger.kernel.org # 5.5 Reviewed-by: Damien Le Moal Reviewed-by: Johannes Thumshirn Reviewed-by: Christoph Hellwig Signed-off-by: Shin'ichiro Kawasaki Signed-off-by: Jens Axboe --- block/genhd.c | 36 ++++++++++++++++++++++++++++++++++++ include/linux/genhd.h | 13 +------------ 2 files changed, 37 insertions(+), 12 deletions(-) diff --git a/block/genhd.c b/block/genhd.c index ff6268970ddc..9c2e13ce0d19 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -301,6 +301,42 @@ struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector) } EXPORT_SYMBOL_GPL(disk_map_sector_rcu); +/** + * disk_has_partitions + * @disk: gendisk of interest + * + * Walk through the partition table and check if valid partition exists. + * + * CONTEXT: + * Don't care. + * + * RETURNS: + * True if the gendisk has at least one valid non-zero size partition. + * Otherwise false. + */ +bool disk_has_partitions(struct gendisk *disk) +{ + struct disk_part_tbl *ptbl; + int i; + bool ret = false; + + rcu_read_lock(); + ptbl = rcu_dereference(disk->part_tbl); + + /* Iterate partitions skipping the whole device at index 0 */ + for (i = 1; i < ptbl->len; i++) { + if (rcu_dereference(ptbl->part[i])) { + ret = true; + break; + } + } + + rcu_read_unlock(); + + return ret; +} +EXPORT_SYMBOL_GPL(disk_has_partitions); + /* * Can be deleted altogether. Later. * diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 6fbe58538ad6..07dc91835b98 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -245,18 +245,6 @@ static inline bool disk_part_scan_enabled(struct gendisk *disk) !(disk->flags & GENHD_FL_NO_PART_SCAN); } -static inline bool disk_has_partitions(struct gendisk *disk) -{ - bool ret = false; - - rcu_read_lock(); - if (rcu_dereference(disk->part_tbl)->len > 1) - ret = true; - rcu_read_unlock(); - - return ret; -} - static inline dev_t disk_devt(struct gendisk *disk) { return MKDEV(disk->major, disk->first_minor); @@ -298,6 +286,7 @@ extern void disk_part_iter_exit(struct disk_part_iter *piter); extern struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector); +bool disk_has_partitions(struct gendisk *disk); /* * Macros to operate on percpu disk statistics: From 531d3040bc5cf37dea01b118608347cca9325f9d Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 2 Mar 2020 15:03:35 +0200 Subject: [PATCH 224/256] ovl: fix lock in ovl_llseek() ovl_inode_lock() is interruptible. When inode_lock() in ovl_llseek() was replaced with ovl_inode_lock(), we did not add a check for error. Fix this by making ovl_inode_lock() uninterruptible and change the existing call sites to use an _interruptible variant. Reported-by: syzbot+66a9752fa927f745385e@syzkaller.appspotmail.com Fixes: b1f9d3858f72 ("ovl: use ovl_inode_lock in ovl_llseek()") Signed-off-by: Amir Goldstein Signed-off-by: Miklos Szeredi --- fs/overlayfs/overlayfs.h | 7 ++++++- fs/overlayfs/util.c | 4 ++-- 2 files changed, 8 insertions(+), 3 deletions(-) diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 3623d28aa4fa..3d3f2b8bdae5 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -318,7 +318,12 @@ static inline unsigned int ovl_xino_bits(struct super_block *sb) return ovl_same_dev(sb) ? OVL_FS(sb)->xino_mode : 0; } -static inline int ovl_inode_lock(struct inode *inode) +static inline void ovl_inode_lock(struct inode *inode) +{ + mutex_lock(&OVL_I(inode)->lock); +} + +static inline int ovl_inode_lock_interruptible(struct inode *inode) { return mutex_lock_interruptible(&OVL_I(inode)->lock); } diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index ea005085803f..042f7eb4f7f4 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -509,7 +509,7 @@ int ovl_copy_up_start(struct dentry *dentry, int flags) struct inode *inode = d_inode(dentry); int err; - err = ovl_inode_lock(inode); + err = ovl_inode_lock_interruptible(inode); if (!err && ovl_already_copied_up_locked(dentry, flags)) { err = 1; /* Already copied up */ ovl_inode_unlock(inode); @@ -764,7 +764,7 @@ int ovl_nlink_start(struct dentry *dentry) return err; } - err = ovl_inode_lock(inode); + err = ovl_inode_lock_interruptible(inode); if (err) return err; From b09fe70ef520e011ba4a64f4b93f948a8f14717b Mon Sep 17 00:00:00 2001 From: Vinicius Costa Gomes Date: Mon, 9 Mar 2020 10:39:53 -0700 Subject: [PATCH 225/256] taprio: Fix sending packets without dequeueing them There was a bug that was causing packets to be sent to the driver without first calling dequeue() on the "child" qdisc. And the KASAN report below shows that sending a packet without calling dequeue() leads to bad results. The problem is that when checking the last qdisc "child" we do not set the returned skb to NULL, which can cause it to be sent to the driver, and so after the skb is sent, it may be freed, and in some situations a reference to it may still be in the child qdisc, because it was never dequeued. The crash log looks like this: [ 19.937538] ================================================================== [ 19.938300] BUG: KASAN: use-after-free in taprio_dequeue_soft+0x620/0x780 [ 19.938968] Read of size 4 at addr ffff8881128628cc by task swapper/1/0 [ 19.939612] [ 19.939772] CPU: 1 PID: 0 Comm: swapper/1 Not tainted 5.6.0-rc3+ #97 [ 19.940397] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qe4 [ 19.941523] Call Trace: [ 19.941774] [ 19.941985] dump_stack+0x97/0xe0 [ 19.942323] print_address_description.constprop.0+0x3b/0x60 [ 19.942884] ? taprio_dequeue_soft+0x620/0x780 [ 19.943325] ? taprio_dequeue_soft+0x620/0x780 [ 19.943767] __kasan_report.cold+0x1a/0x32 [ 19.944173] ? taprio_dequeue_soft+0x620/0x780 [ 19.944612] kasan_report+0xe/0x20 [ 19.944954] taprio_dequeue_soft+0x620/0x780 [ 19.945380] __qdisc_run+0x164/0x18d0 [ 19.945749] net_tx_action+0x2c4/0x730 [ 19.946124] __do_softirq+0x268/0x7bc [ 19.946491] irq_exit+0x17d/0x1b0 [ 19.946824] smp_apic_timer_interrupt+0xeb/0x380 [ 19.947280] apic_timer_interrupt+0xf/0x20 [ 19.947687] [ 19.947912] RIP: 0010:default_idle+0x2d/0x2d0 [ 19.948345] Code: 00 00 41 56 41 55 65 44 8b 2d 3f 8d 7c 7c 41 54 55 53 0f 1f 44 00 00 e8 b1 b2 c5 fd e9 07 00 3 [ 19.950166] RSP: 0018:ffff88811a3efda0 EFLAGS: 00000282 ORIG_RAX: ffffffffffffff13 [ 19.950909] RAX: 0000000080000000 RBX: ffff88811a3a9600 RCX: ffffffff8385327e [ 19.951608] RDX: 1ffff110234752c0 RSI: 0000000000000000 RDI: ffffffff8385262f [ 19.952309] RBP: ffffed10234752c0 R08: 0000000000000001 R09: ffffed10234752c1 [ 19.953009] R10: ffffed10234752c0 R11: ffff88811a3a9607 R12: 0000000000000001 [ 19.953709] R13: 0000000000000001 R14: 0000000000000000 R15: 0000000000000000 [ 19.954408] ? default_idle_call+0x2e/0x70 [ 19.954816] ? default_idle+0x1f/0x2d0 [ 19.955192] default_idle_call+0x5e/0x70 [ 19.955584] do_idle+0x3d4/0x500 [ 19.955909] ? arch_cpu_idle_exit+0x40/0x40 [ 19.956325] ? _raw_spin_unlock_irqrestore+0x23/0x30 [ 19.956829] ? trace_hardirqs_on+0x30/0x160 [ 19.957242] cpu_startup_entry+0x19/0x20 [ 19.957633] start_secondary+0x2a6/0x380 [ 19.958026] ? set_cpu_sibling_map+0x18b0/0x18b0 [ 19.958486] secondary_startup_64+0xa4/0xb0 [ 19.958921] [ 19.959078] Allocated by task 33: [ 19.959412] save_stack+0x1b/0x80 [ 19.959747] __kasan_kmalloc.constprop.0+0xc2/0xd0 [ 19.960222] kmem_cache_alloc+0xe4/0x230 [ 19.960617] __alloc_skb+0x91/0x510 [ 19.960967] ndisc_alloc_skb+0x133/0x330 [ 19.961358] ndisc_send_ns+0x134/0x810 [ 19.961735] addrconf_dad_work+0xad5/0xf80 [ 19.962144] process_one_work+0x78e/0x13a0 [ 19.962551] worker_thread+0x8f/0xfa0 [ 19.962919] kthread+0x2ba/0x3b0 [ 19.963242] ret_from_fork+0x3a/0x50 [ 19.963596] [ 19.963753] Freed by task 33: [ 19.964055] save_stack+0x1b/0x80 [ 19.964386] __kasan_slab_free+0x12f/0x180 [ 19.964830] kmem_cache_free+0x80/0x290 [ 19.965231] ip6_mc_input+0x38a/0x4d0 [ 19.965617] ipv6_rcv+0x1a4/0x1d0 [ 19.965948] __netif_receive_skb_one_core+0xf2/0x180 [ 19.966437] netif_receive_skb+0x8c/0x3c0 [ 19.966846] br_handle_frame_finish+0x779/0x1310 [ 19.967302] br_handle_frame+0x42a/0x830 [ 19.967694] __netif_receive_skb_core+0xf0e/0x2a90 [ 19.968167] __netif_receive_skb_one_core+0x96/0x180 [ 19.968658] process_backlog+0x198/0x650 [ 19.969047] net_rx_action+0x2fa/0xaa0 [ 19.969420] __do_softirq+0x268/0x7bc [ 19.969785] [ 19.969940] The buggy address belongs to the object at ffff888112862840 [ 19.969940] which belongs to the cache skbuff_head_cache of size 224 [ 19.971202] The buggy address is located 140 bytes inside of [ 19.971202] 224-byte region [ffff888112862840, ffff888112862920) [ 19.972344] The buggy address belongs to the page: [ 19.972820] page:ffffea00044a1800 refcount:1 mapcount:0 mapping:ffff88811a2bd1c0 index:0xffff8881128625c0 compo0 [ 19.973930] flags: 0x8000000000010200(slab|head) [ 19.974388] raw: 8000000000010200 ffff88811a2ed650 ffff88811a2ed650 ffff88811a2bd1c0 [ 19.975151] raw: ffff8881128625c0 0000000000190013 00000001ffffffff 0000000000000000 [ 19.975915] page dumped because: kasan: bad access detected [ 19.976461] page_owner tracks the page as allocated [ 19.976946] page last allocated via order 2, migratetype Unmovable, gfp_mask 0xd20c0(__GFP_IO|__GFP_FS|__GFP_NO) [ 19.978332] prep_new_page+0x24b/0x330 [ 19.978707] get_page_from_freelist+0x2057/0x2c90 [ 19.979170] __alloc_pages_nodemask+0x218/0x590 [ 19.979619] new_slab+0x9d/0x300 [ 19.979948] ___slab_alloc.constprop.0+0x2f9/0x6f0 [ 19.980421] __slab_alloc.constprop.0+0x30/0x60 [ 19.980870] kmem_cache_alloc+0x201/0x230 [ 19.981269] __alloc_skb+0x91/0x510 [ 19.981620] alloc_skb_with_frags+0x78/0x4a0 [ 19.982043] sock_alloc_send_pskb+0x5eb/0x750 [ 19.982476] unix_stream_sendmsg+0x399/0x7f0 [ 19.982904] sock_sendmsg+0xe2/0x110 [ 19.983262] ____sys_sendmsg+0x4de/0x6d0 [ 19.983660] ___sys_sendmsg+0xe4/0x160 [ 19.984032] __sys_sendmsg+0xab/0x130 [ 19.984396] do_syscall_64+0xe7/0xae0 [ 19.984761] page last free stack trace: [ 19.985142] __free_pages_ok+0x432/0xbc0 [ 19.985533] qlist_free_all+0x56/0xc0 [ 19.985907] quarantine_reduce+0x149/0x170 [ 19.986315] __kasan_kmalloc.constprop.0+0x9e/0xd0 [ 19.986791] kmem_cache_alloc+0xe4/0x230 [ 19.987182] prepare_creds+0x24/0x440 [ 19.987548] do_faccessat+0x80/0x590 [ 19.987906] do_syscall_64+0xe7/0xae0 [ 19.988276] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 19.988775] [ 19.988930] Memory state around the buggy address: [ 19.989402] ffff888112862780: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 19.990111] ffff888112862800: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb [ 19.990822] >ffff888112862880: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 19.991529] ^ [ 19.992081] ffff888112862900: fb fb fb fb fc fc fc fc fc fc fc fc fc fc fc fc [ 19.992796] ffff888112862980: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc Fixes: 5a781ccbd19e ("tc: Add support for configuring the taprio scheduler") Reported-by: Michael Schmidt Signed-off-by: Vinicius Costa Gomes Acked-by: Andre Guedes Signed-off-by: David S. Miller --- net/sched/sch_taprio.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index ee717e05372b..b1eb12d33b9a 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -564,8 +564,10 @@ static struct sk_buff *taprio_dequeue_soft(struct Qdisc *sch) prio = skb->priority; tc = netdev_get_prio_tc_map(dev, prio); - if (!(gate_mask & BIT(tc))) + if (!(gate_mask & BIT(tc))) { + skb = NULL; continue; + } len = qdisc_pkt_len(skb); guard = ktime_add_ns(taprio_get_time(q), @@ -575,13 +577,17 @@ static struct sk_buff *taprio_dequeue_soft(struct Qdisc *sch) * guard band ... */ if (gate_mask != TAPRIO_ALL_GATES_OPEN && - ktime_after(guard, entry->close_time)) + ktime_after(guard, entry->close_time)) { + skb = NULL; continue; + } /* ... and no budget. */ if (gate_mask != TAPRIO_ALL_GATES_OPEN && - atomic_sub_return(len, &entry->budget) < 0) + atomic_sub_return(len, &entry->budget) < 0) { + skb = NULL; continue; + } skb = child->ops->dequeue(child); if (unlikely(!skb)) From 5eb01ddfcfb25e6ebc404a41deae946bde776731 Mon Sep 17 00:00:00 2001 From: Yonglong Liu Date: Thu, 12 Mar 2020 15:11:03 +0800 Subject: [PATCH 226/256] net: hns3: fix "tc qdisc del" failed issue The HNS3 driver supports to configure TC numbers and TC to priority map via "tc" tool. But when delete the rule, will fail, because the HNS3 driver needs at least one TC, but the "tc" tool sets TC number to zero when delete. This patch makes sure that the TC number is at least one. Fixes: 30d240dfa2e8 ("net: hns3: Add mqprio hardware offload support in hns3 driver") Signed-off-by: Yonglong Liu Signed-off-by: Huazhong Tan Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index acb796cc10d0..a7f40aa1a0ea 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -1711,7 +1711,7 @@ static int hns3_setup_tc(struct net_device *netdev, void *type_data) netif_dbg(h, drv, netdev, "setup tc: num_tc=%u\n", tc); return (kinfo->dcb_ops && kinfo->dcb_ops->setup_tc) ? - kinfo->dcb_ops->setup_tc(h, tc, prio_tc) : -EOPNOTSUPP; + kinfo->dcb_ops->setup_tc(h, tc ? tc : 1, prio_tc) : -EOPNOTSUPP; } static int hns3_nic_setup_tc(struct net_device *dev, enum tc_setup_type type, From 23b4201dead410c4a5108a8e723240419ab75257 Mon Sep 17 00:00:00 2001 From: Jian Shen Date: Thu, 12 Mar 2020 15:11:04 +0800 Subject: [PATCH 227/256] net: hns3: fix VF VLAN table entries inconsistent issue Currently, if VF is loaded on the host side, the host doesn't clear the VF's VLAN table entries when VF removing. In this case, when doing reset and disabling sriov at the same time the VLAN device over VF will be removed, but the VLAN table entries in hardware are remained. This patch fixes it by asking PF to clear the VLAN table entries for VF when VF is removing. It also clears the VLAN table full bit after VF VLAN table entries being cleared. Fixes: c6075b193462 ("net: hns3: Record VF vlan tables") Signed-off-by: Jian Shen Signed-off-by: Huazhong Tan Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h | 1 + drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 1 + drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c | 1 + drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 3 +++ 4 files changed, 6 insertions(+) diff --git a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h index 1b0313900f98..d87158acdf6f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h +++ b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h @@ -46,6 +46,7 @@ enum HCLGE_MBX_OPCODE { HCLGE_MBX_PUSH_VLAN_INFO, /* (PF -> VF) push port base vlan */ HCLGE_MBX_GET_MEDIA_TYPE, /* (VF -> PF) get media type */ HCLGE_MBX_PUSH_PROMISC_INFO, /* (PF -> VF) push vf promisc info */ + HCLGE_MBX_VF_UNINIT, /* (VF -> PF) vf is unintializing */ HCLGE_MBX_GET_VF_FLR_STATUS = 200, /* (M7 -> PF) get vf flr status */ HCLGE_MBX_PUSH_LINK_STATUS, /* (M7 -> PF) get port link status */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index acf0c29fcbcd..6deeb964ea6b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -8272,6 +8272,7 @@ void hclge_rm_vport_all_vlan_table(struct hclge_vport *vport, bool is_del_list) kfree(vlan); } } + clear_bit(vport->vport_id, hdev->vf_vlan_full); } void hclge_uninit_vport_vlan_table(struct hclge_dev *hdev) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index a3c0822191a9..3d850f6b1e37 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -799,6 +799,7 @@ void hclge_mbx_handler(struct hclge_dev *hdev) hclge_get_link_mode(vport, req); break; case HCLGE_MBX_GET_VF_FLR_STATUS: + case HCLGE_MBX_VF_UNINIT: hclge_rm_vport_all_mac_table(vport, true, HCLGE_MAC_ADDR_UC); hclge_rm_vport_all_mac_table(vport, true, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index d6597206e692..0510d85a7f6a 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -2803,6 +2803,9 @@ static void hclgevf_uninit_hdev(struct hclgevf_dev *hdev) { hclgevf_state_uninit(hdev); + hclgevf_send_mbx_msg(hdev, HCLGE_MBX_VF_UNINIT, 0, NULL, 0, + false, NULL, 0); + if (test_bit(HCLGEVF_STATE_IRQ_INITED, &hdev->state)) { hclgevf_misc_irq_uninit(hdev); hclgevf_uninit_msi(hdev); From 903b85d3adce99a5301d5959c4d3c9d14a7974d4 Mon Sep 17 00:00:00 2001 From: Jian Shen Date: Thu, 12 Mar 2020 15:11:05 +0800 Subject: [PATCH 228/256] net: hns3: fix RMW issue for VLAN filter switch According to the user manual, the ingress and egress VLAN filter are configured at the same time. Currently, hclge_init_vlan_config() and hclge_set_vlan_spoofchk() will both change the VLAN filter switch. So it's necessary to read the old configuration before modifying it. Fixes: 22044f95faa0 ("net: hns3: add support for spoof check setting") Signed-off-by: Jian Shen Signed-off-by: Huazhong Tan Signed-off-by: David S. Miller --- .../hisilicon/hns3/hns3pf/hclge_main.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 6deeb964ea6b..06d0ed0fe4c9 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -7745,16 +7745,27 @@ static int hclge_set_vlan_filter_ctrl(struct hclge_dev *hdev, u8 vlan_type, struct hclge_desc desc; int ret; - hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_VLAN_FILTER_CTRL, false); - + /* read current vlan filter parameter */ + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_VLAN_FILTER_CTRL, true); req = (struct hclge_vlan_filter_ctrl_cmd *)desc.data; req->vlan_type = vlan_type; - req->vlan_fe = filter_en ? fe_type : 0; req->vf_id = vf_id; + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to get vlan filter config, ret = %d.\n", ret); + return ret; + } + + /* modify and write new config parameter */ + hclge_cmd_reuse_desc(&desc, false); + req->vlan_fe = filter_en ? + (req->vlan_fe | fe_type) : (req->vlan_fe & ~fe_type); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); if (ret) - dev_err(&hdev->pdev->dev, "set vlan filter fail, ret =%d.\n", + dev_err(&hdev->pdev->dev, "failed to set vlan filter, ret = %d.\n", ret); return ret; From 59359fc8a2f7af062777692e6a7aae73483729ec Mon Sep 17 00:00:00 2001 From: Jian Shen Date: Thu, 12 Mar 2020 15:11:06 +0800 Subject: [PATCH 229/256] net: hns3: clear port base VLAN when unload PF Currently, PF missed to clear the port base VLAN for VF when unload. In this case, the VLAN id will remain in the VLAN table. This patch fixes it. Fixes: 92f11ea177cd ("net: hns3: fix set port based VLAN issue for VF") Signed-off-by: Jian Shen Signed-off-by: Huazhong Tan Signed-off-by: David S. Miller --- .../hisilicon/hns3/hns3pf/hclge_main.c | 23 +++++++++++++++++++ 1 file changed, 23 insertions(+) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 06d0ed0fe4c9..d3b0cd74ecd2 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -8500,6 +8500,28 @@ static int hclge_set_vf_vlan_filter(struct hnae3_handle *handle, int vfid, } } +static void hclge_clear_vf_vlan(struct hclge_dev *hdev) +{ + struct hclge_vlan_info *vlan_info; + struct hclge_vport *vport; + int ret; + int vf; + + /* clear port base vlan for all vf */ + for (vf = HCLGE_VF_VPORT_START_NUM; vf < hdev->num_alloc_vport; vf++) { + vport = &hdev->vport[vf]; + vlan_info = &vport->port_base_vlan_cfg.vlan_info; + + ret = hclge_set_vlan_filter_hw(hdev, htons(ETH_P_8021Q), + vport->vport_id, + vlan_info->vlan_tag, true); + if (ret) + dev_err(&hdev->pdev->dev, + "failed to clear vf vlan for vf%d, ret = %d\n", + vf - HCLGE_VF_VPORT_START_NUM, ret); + } +} + int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto, u16 vlan_id, bool is_kill) { @@ -9909,6 +9931,7 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev) struct hclge_mac *mac = &hdev->hw.mac; hclge_reset_vf_rate(hdev); + hclge_clear_vf_vlan(hdev); hclge_misc_affinity_teardown(hdev); hclge_state_uninit(hdev); From 21039132650281de06a169cbe8a0f7e5c578fd8b Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 10 Mar 2020 09:31:41 -0400 Subject: [PATCH 230/256] gfs2_atomic_open(): fix O_EXCL|O_CREAT handling on cold dcache with the way fs/namei.c:do_last() had been done, ->atomic_open() instances needed to recognize the case when existing file got found with O_EXCL|O_CREAT, either by falling back to finish_no_open() or failing themselves. gfs2 one didn't. Fixes: 6d4ade986f9c (GFS2: Add atomic_open support) Cc: stable@kernel.org # v3.11 Signed-off-by: Al Viro --- fs/gfs2/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 2716d56ed0a0..8294851a9dd9 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -1248,7 +1248,7 @@ static int gfs2_atomic_open(struct inode *dir, struct dentry *dentry, if (!(file->f_mode & FMODE_OPENED)) return finish_no_open(file, d); dput(d); - return 0; + return excl && (flags & O_CREAT) ? -EEXIST : 0; } BUG_ON(d != NULL); From d9a9f4849fe0c9d560851ab22a85a666cddfdd24 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 12 Mar 2020 18:25:20 -0400 Subject: [PATCH 231/256] cifs_atomic_open(): fix double-put on late allocation failure several iterations of ->atomic_open() calling conventions ago, we used to need fput() if ->atomic_open() failed at some point after successful finish_open(). Now (since 2016) it's not needed - struct file carries enough state to make fput() work regardless of the point in struct file lifecycle and discarding it on failure exits in open() got unified. Unfortunately, I'd missed the fact that we had an instance of ->atomic_open() (cifs one) that used to need that fput(), as well as the stale comment in finish_open() demanding such late failure handling. Trivially fixed... Fixes: fe9ec8291fca "do_last(): take fput() on error after opening to out:" Cc: stable@kernel.org # v4.7+ Signed-off-by: Al Viro --- Documentation/filesystems/porting.rst | 8 ++++++++ fs/cifs/dir.c | 1 - fs/open.c | 3 --- 3 files changed, 8 insertions(+), 4 deletions(-) diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst index f18506083ced..26c093969573 100644 --- a/Documentation/filesystems/porting.rst +++ b/Documentation/filesystems/porting.rst @@ -850,3 +850,11 @@ business doing so. d_alloc_pseudo() is internal-only; uses outside of alloc_file_pseudo() are very suspect (and won't work in modules). Such uses are very likely to be misspelled d_alloc_anon(). + +--- + +**mandatory** + +[should've been added in 2016] stale comment in finish_open() nonwithstanding, +failure exits in ->atomic_open() instances should *NOT* fput() the file, +no matter what. Everything is handled by the caller. diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 0ef099442f20..36e7b2fd2190 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -555,7 +555,6 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry, if (server->ops->close) server->ops->close(xid, tcon, &fid); cifs_del_pending_open(&open); - fput(file); rc = -ENOMEM; } diff --git a/fs/open.c b/fs/open.c index 0788b3715731..b69d6eed67e6 100644 --- a/fs/open.c +++ b/fs/open.c @@ -860,9 +860,6 @@ cleanup_file: * the return value of d_splice_alias(), then the caller needs to perform dput() * on it after finish_open(). * - * On successful return @file is a fully instantiated open file. After this, if - * an error occurs in ->atomic_open(), it needs to clean up with fput(). - * * Returns zero on success or -errno if the open failed. */ int finish_open(struct file *file, struct dentry *dentry, From 611d779af7cad2b87487ff58e4931a90c20b113c Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Thu, 12 Mar 2020 22:25:20 +0100 Subject: [PATCH 232/256] net: phy: fix MDIO bus PM PHY resuming So far we have the unfortunate situation that mdio_bus_phy_may_suspend() is called in suspend AND resume path, assuming that function result is the same. After the original change this is no longer the case, resulting in broken resume as reported by Geert. To fix this call mdio_bus_phy_may_suspend() in the suspend path only, and let the phy_device store the info whether it was suspended by MDIO bus PM. Fixes: 503ba7c69610 ("net: phy: Avoid multiple suspends") Reported-by: Geert Uytterhoeven Tested-by: Geert Uytterhoeven Signed-off-by: Heiner Kallweit Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/phy/phy_device.c | 6 +++++- include/linux/phy.h | 2 ++ 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index c8b0c34030d3..28e3c5c0e3c3 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -286,6 +286,8 @@ static int mdio_bus_phy_suspend(struct device *dev) if (!mdio_bus_phy_may_suspend(phydev)) return 0; + phydev->suspended_by_mdio_bus = 1; + return phy_suspend(phydev); } @@ -294,9 +296,11 @@ static int mdio_bus_phy_resume(struct device *dev) struct phy_device *phydev = to_phy_device(dev); int ret; - if (!mdio_bus_phy_may_suspend(phydev)) + if (!phydev->suspended_by_mdio_bus) goto no_resume; + phydev->suspended_by_mdio_bus = 0; + ret = phy_resume(phydev); if (ret < 0) return ret; diff --git a/include/linux/phy.h b/include/linux/phy.h index 22f5e763e894..452e8ba8665f 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -357,6 +357,7 @@ struct macsec_ops; * is_gigabit_capable: Set to true if PHY supports 1000Mbps * has_fixups: Set to true if this phy has fixups/quirks. * suspended: Set to true if this phy has been suspended successfully. + * suspended_by_mdio_bus: Set to true if this phy was suspended by MDIO bus. * sysfs_links: Internal boolean tracking sysfs symbolic links setup/removal. * loopback_enabled: Set true if this phy has been loopbacked successfully. * state: state of the PHY for management purposes @@ -396,6 +397,7 @@ struct phy_device { unsigned is_gigabit_capable:1; unsigned has_fixups:1; unsigned suspended:1; + unsigned suspended_by_mdio_bus:1; unsigned sysfs_links:1; unsigned loopback_enabled:1; From 9d0e0cd9a529ba68b2acda68b5075d4a5ea7118a Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Thu, 12 Mar 2020 17:51:45 +0100 Subject: [PATCH 233/256] tc-testing: add ETS scheduler to tdc build configuration add CONFIG_NET_SCH_ETS to 'config', otherwise test suites using this file to perform a full tdc run will encounter the following warning: ok 645 e90e - Add ETS qdisc using bands # skipped - "-----> teardown stage" did not complete successfully Fixes: 82c664b69c8b ("selftests: qdiscs: Add test coverage for ETS Qdisc") Reported-by: Jamal Hadi Salim Signed-off-by: Davide Caratti Signed-off-by: David S. Miller --- tools/testing/selftests/tc-testing/config | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config index 477bc61b374a..c03af4600281 100644 --- a/tools/testing/selftests/tc-testing/config +++ b/tools/testing/selftests/tc-testing/config @@ -57,3 +57,4 @@ CONFIG_NET_IFE_SKBMARK=m CONFIG_NET_IFE_SKBPRIO=m CONFIG_NET_IFE_SKBTCINDEX=m CONFIG_NET_SCH_FIFO=y +CONFIG_NET_SCH_ETS=m From c0368595c1639947839c0db8294ee96aca0b3b86 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 12 Mar 2020 15:04:30 +0000 Subject: [PATCH 234/256] net: systemport: fix index check to avoid an array out of bounds access Currently the bounds check on index is off by one and can lead to an out of bounds access on array priv->filters_loc when index is RXCHK_BRCM_TAG_MAX. Fixes: bb9051a2b230 ("net: systemport: Add support for WAKE_FILTER") Signed-off-by: Colin Ian King Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bcmsysport.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index e0611cba87f9..15b31cddc054 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -2135,7 +2135,7 @@ static int bcm_sysport_rule_set(struct bcm_sysport_priv *priv, return -ENOSPC; index = find_first_zero_bit(priv->filters, RXCHK_BRCM_TAG_MAX); - if (index > RXCHK_BRCM_TAG_MAX) + if (index >= RXCHK_BRCM_TAG_MAX) return -ENOSPC; /* Location is the classification ID, and index is the position From b2feb1d6d34844c5c56eb34008c3e516664c5410 Mon Sep 17 00:00:00 2001 From: Lyude Paul Date: Fri, 6 Mar 2020 18:46:19 -0500 Subject: [PATCH 235/256] drm/dp_mst: Rename drm_dp_mst_is_dp_mst_end_device() to be less redundant It's already prefixed by dp_mst, so we don't really need to repeat ourselves here. One of the changes I should have picked up originally when reviewing MST DSC support. There should be no functional changes here Cc: Mikita Lipski Cc: Sean Paul Cc: Hans de Goede Signed-off-by: Lyude Paul Reviewed-by: Alex Deucher Tested-by: Hans de Goede Link: https://patchwork.freedesktop.org/patch/msgid/20200306234623.547525-2-lyude@redhat.com --- drivers/gpu/drm/drm_dp_mst_topology.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index cce0b1bba591..9188c53f5c96 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -1935,7 +1935,7 @@ static u8 drm_dp_calculate_rad(struct drm_dp_mst_port *port, return parent_lct + 1; } -static bool drm_dp_mst_is_dp_mst_end_device(u8 pdt, bool mcs) +static bool drm_dp_mst_is_end_device(u8 pdt, bool mcs) { switch (pdt) { case DP_PEER_DEVICE_DP_LEGACY_CONV: @@ -1965,13 +1965,13 @@ drm_dp_port_set_pdt(struct drm_dp_mst_port *port, u8 new_pdt, /* Teardown the old pdt, if there is one */ if (port->pdt != DP_PEER_DEVICE_NONE) { - if (drm_dp_mst_is_dp_mst_end_device(port->pdt, port->mcs)) { + if (drm_dp_mst_is_end_device(port->pdt, port->mcs)) { /* * If the new PDT would also have an i2c bus, * don't bother with reregistering it */ if (new_pdt != DP_PEER_DEVICE_NONE && - drm_dp_mst_is_dp_mst_end_device(new_pdt, new_mcs)) { + drm_dp_mst_is_end_device(new_pdt, new_mcs)) { port->pdt = new_pdt; port->mcs = new_mcs; return 0; @@ -1991,7 +1991,7 @@ drm_dp_port_set_pdt(struct drm_dp_mst_port *port, u8 new_pdt, port->mcs = new_mcs; if (port->pdt != DP_PEER_DEVICE_NONE) { - if (drm_dp_mst_is_dp_mst_end_device(port->pdt, port->mcs)) { + if (drm_dp_mst_is_end_device(port->pdt, port->mcs)) { /* add i2c over sideband */ ret = drm_dp_mst_register_i2c_bus(&port->aux); } else { @@ -2172,7 +2172,7 @@ drm_dp_mst_port_add_connector(struct drm_dp_mst_branch *mstb, } if (port->pdt != DP_PEER_DEVICE_NONE && - drm_dp_mst_is_dp_mst_end_device(port->pdt, port->mcs)) { + drm_dp_mst_is_end_device(port->pdt, port->mcs)) { port->cached_edid = drm_get_edid(port->connector, &port->aux.ddc); drm_connector_set_tile_property(port->connector); From fcf4638075964268bf8a0e212407096c6aab6fd3 Mon Sep 17 00:00:00 2001 From: Lyude Paul Date: Fri, 6 Mar 2020 18:46:20 -0500 Subject: [PATCH 236/256] drm/dp_mst: Use full_pbn instead of available_pbn for bandwidth checks DisplayPort specifications are fun. For a while, it's been really unclear to us what available_pbn actually does. There's a somewhat vague explanation in the DisplayPort spec (starting from 1.2) that partially explains it: The minimum payload bandwidth number supported by the path. Each node updates this number with its available payload bandwidth number if its payload bandwidth number is less than that in the Message Transaction reply. So, it sounds like available_pbn represents the smallest link rate in use between the source and the branch device. Cool, so full_pbn is just the highest possible PBN that the branch device supports right? Well, we assumed that for quite a while until Sean Paul noticed that on some MST hubs, available_pbn will actually get set to 0 whenever there's any active payloads on the respective branch device. This caused quite a bit of confusion since clearing the payload ID table would end up fixing the available_pbn value. So, we just went with that until commit cd82d82cbc04 ("drm/dp_mst: Add branch bandwidth validation to MST atomic check") started breaking people's setups due to us getting erroneous available_pbn values. So, we did some more digging and got confused until we finally looked at the definition for full_pbn: The bandwidth of the link at the trained link rate and lane count between the DP Source device and the DP Sink device with no time slots allocated to VC Payloads, represented as a Payload Bandwidth Number. As with the Available_Payload_Bandwidth_Number, this number is determined by the link with the lowest lane count and link rate. That's what we get for not reading specs closely enough, hehe. So, since full_pbn is definitely what we want for doing bandwidth restriction checks - let's start using that instead and ignore available_pbn entirely. Signed-off-by: Lyude Paul Fixes: cd82d82cbc04 ("drm/dp_mst: Add branch bandwidth validation to MST atomic check") Cc: Mikita Lipski Cc: Hans de Goede Cc: Sean Paul Reviewed-by: Mikita Lipski Link: https://patchwork.freedesktop.org/patch/msgid/20200306234623.547525-3-lyude@redhat.com Reviewed-by: Alex Deucher Tested-by: Hans de Goede --- drivers/gpu/drm/drm_dp_mst_topology.c | 15 +++++++-------- include/drm/drm_dp_mst_helper.h | 4 ++-- 2 files changed, 9 insertions(+), 10 deletions(-) diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index 9188c53f5c96..7df7676b45c4 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -2309,7 +2309,7 @@ drm_dp_mst_handle_link_address_port(struct drm_dp_mst_branch *mstb, port); } } else { - port->available_pbn = 0; + port->full_pbn = 0; } } @@ -2404,7 +2404,7 @@ drm_dp_mst_handle_conn_stat(struct drm_dp_mst_branch *mstb, if (port->ddps) { dowork = true; } else { - port->available_pbn = 0; + port->full_pbn = 0; } } @@ -2556,7 +2556,7 @@ static int drm_dp_check_and_send_link_address(struct drm_dp_mst_topology_mgr *mg if (port->input || !port->ddps) continue; - if (!port->available_pbn) { + if (!port->full_pbn) { drm_modeset_lock(&mgr->base.lock, NULL); drm_dp_send_enum_path_resources(mgr, mstb, port); drm_modeset_unlock(&mgr->base.lock); @@ -3002,8 +3002,7 @@ drm_dp_send_enum_path_resources(struct drm_dp_mst_topology_mgr *mgr, path_res->port_number, path_res->full_payload_bw_number, path_res->avail_payload_bw_number); - port->available_pbn = - path_res->avail_payload_bw_number; + port->full_pbn = path_res->full_payload_bw_number; port->fec_capable = path_res->fec_capable; } } @@ -3598,7 +3597,7 @@ drm_dp_mst_topology_mgr_invalidate_mstb(struct drm_dp_mst_branch *mstb) list_for_each_entry(port, &mstb->ports, next) { /* The PBN for each port will also need to be re-probed */ - port->available_pbn = 0; + port->full_pbn = 0; if (port->mstb) drm_dp_mst_topology_mgr_invalidate_mstb(port->mstb); @@ -4842,8 +4841,8 @@ int drm_dp_mst_atomic_check_bw_limit(struct drm_dp_mst_branch *branch, if (drm_dp_mst_atomic_check_bw_limit(port->mstb, mst_state)) return -ENOSPC; - if (port->available_pbn > 0) - pbn_limit = port->available_pbn; + if (port->full_pbn > 0) + pbn_limit = port->full_pbn; } DRM_DEBUG_ATOMIC("[MST BRANCH:%p] branch has %d PBN available\n", branch, pbn_limit); diff --git a/include/drm/drm_dp_mst_helper.h b/include/drm/drm_dp_mst_helper.h index bcb39da9adb4..41725d88d27e 100644 --- a/include/drm/drm_dp_mst_helper.h +++ b/include/drm/drm_dp_mst_helper.h @@ -81,7 +81,7 @@ struct drm_dp_vcpi { * &drm_dp_mst_topology_mgr.base.lock. * @num_sdp_stream_sinks: Number of stream sinks. Protected by * &drm_dp_mst_topology_mgr.base.lock. - * @available_pbn: Available bandwidth for this port. Protected by + * @full_pbn: Max possible bandwidth for this port. Protected by * &drm_dp_mst_topology_mgr.base.lock. * @next: link to next port on this branch device * @aux: i2c aux transport to talk to device connected to this port, protected @@ -126,7 +126,7 @@ struct drm_dp_mst_port { u8 dpcd_rev; u8 num_sdp_streams; u8 num_sdp_stream_sinks; - uint16_t available_pbn; + uint16_t full_pbn; struct list_head next; /** * @mstb: the branch device connected to this port, if there is one. From 87212b51bff02a6722d5e84f7842a6b0717eb7d4 Mon Sep 17 00:00:00 2001 From: Lyude Paul Date: Fri, 6 Mar 2020 18:46:21 -0500 Subject: [PATCH 237/256] drm/dp_mst: Reprobe path resources in CSN handler We used to punt off reprobing path resources to the link address probe work, but now that we handle CSNs asynchronously from the driver's HPD handling we can do whatever the heck we want from the CSN! So, reprobe the path resources from drm_dp_mst_handle_conn_stat(). Also, get rid of the path resource reprobing code in drm_dp_check_and_send_link_address() since it's needlessly complicated when we already reprobe path resources from drm_dp_handle_link_address_port(). And finally, teach drm_dp_send_enum_path_resources() to return 1 on PBN changes so we know if we need to send another hotplug or not. This fixes issues where we've indicated to userspace that a port has just been connected, before we actually probed it's available PBN - something that results in unexpected atomic check failures. Signed-off-by: Lyude Paul Fixes: cd82d82cbc04 ("drm/dp_mst: Add branch bandwidth validation to MST atomic check") Cc: Mikita Lipski Cc: Hans de Goede Cc: Sean Paul Link: https://patchwork.freedesktop.org/patch/msgid/20200306234623.547525-4-lyude@redhat.com Reviewed-by: Alex Deucher Tested-by: Hans de Goede --- drivers/gpu/drm/drm_dp_mst_topology.c | 48 ++++++++++++++------------- 1 file changed, 25 insertions(+), 23 deletions(-) diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index 7df7676b45c4..112972031a84 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -2302,12 +2302,16 @@ drm_dp_mst_handle_link_address_port(struct drm_dp_mst_branch *mstb, mutex_unlock(&mgr->lock); } - if (old_ddps != port->ddps) { - if (port->ddps) { - if (!port->input) { - drm_dp_send_enum_path_resources(mgr, mstb, - port); - } + /* + * Reprobe PBN caps on both hotplug, and when re-probing the link + * for our parent mstb + */ + if (old_ddps != port->ddps || !created) { + if (port->ddps && !port->input) { + ret = drm_dp_send_enum_path_resources(mgr, mstb, + port); + if (ret == 1) + changed = true; } else { port->full_pbn = 0; } @@ -2401,11 +2405,10 @@ drm_dp_mst_handle_conn_stat(struct drm_dp_mst_branch *mstb, port->ddps = conn_stat->displayport_device_plug_status; if (old_ddps != port->ddps) { - if (port->ddps) { - dowork = true; - } else { + if (port->ddps && !port->input) + drm_dp_send_enum_path_resources(mgr, mstb, port); + else port->full_pbn = 0; - } } new_pdt = port->input ? DP_PEER_DEVICE_NONE : conn_stat->peer_device_type; @@ -2556,13 +2559,6 @@ static int drm_dp_check_and_send_link_address(struct drm_dp_mst_topology_mgr *mg if (port->input || !port->ddps) continue; - if (!port->full_pbn) { - drm_modeset_lock(&mgr->base.lock, NULL); - drm_dp_send_enum_path_resources(mgr, mstb, port); - drm_modeset_unlock(&mgr->base.lock); - changed = true; - } - if (port->mstb) mstb_child = drm_dp_mst_topology_get_mstb_validated( mgr, port->mstb); @@ -2990,6 +2986,7 @@ drm_dp_send_enum_path_resources(struct drm_dp_mst_topology_mgr *mgr, ret = drm_dp_mst_wait_tx_reply(mstb, txmsg); if (ret > 0) { + ret = 0; path_res = &txmsg->reply.u.path_resources; if (txmsg->reply.reply_type == DP_SIDEBAND_REPLY_NAK) { @@ -3002,13 +2999,22 @@ drm_dp_send_enum_path_resources(struct drm_dp_mst_topology_mgr *mgr, path_res->port_number, path_res->full_payload_bw_number, path_res->avail_payload_bw_number); + + /* + * If something changed, make sure we send a + * hotplug + */ + if (port->full_pbn != path_res->full_payload_bw_number || + port->fec_capable != path_res->fec_capable) + ret = 1; + port->full_pbn = path_res->full_payload_bw_number; port->fec_capable = path_res->fec_capable; } } kfree(txmsg); - return 0; + return ret; } static struct drm_dp_mst_port *drm_dp_get_last_connected_port_to_mstb(struct drm_dp_mst_branch *mstb) @@ -3595,13 +3601,9 @@ drm_dp_mst_topology_mgr_invalidate_mstb(struct drm_dp_mst_branch *mstb) /* The link address will need to be re-sent on resume */ mstb->link_address_sent = false; - list_for_each_entry(port, &mstb->ports, next) { - /* The PBN for each port will also need to be re-probed */ - port->full_pbn = 0; - + list_for_each_entry(port, &mstb->ports, next) if (port->mstb) drm_dp_mst_topology_mgr_invalidate_mstb(port->mstb); - } } /** From 047d4cd2067b028e7bca906c5ce20f4c89b65386 Mon Sep 17 00:00:00 2001 From: Lyude Paul Date: Mon, 9 Mar 2020 17:01:31 -0400 Subject: [PATCH 238/256] drm/dp_mst: Rewrite and fix bandwidth limit checks MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Sigh, this is mostly my fault for not giving commit cd82d82cbc04 ("drm/dp_mst: Add branch bandwidth validation to MST atomic check") enough scrutiny during review. The way we're checking bandwidth limitations here is mostly wrong: For starters, drm_dp_mst_atomic_check_bw_limit() determines the pbn_limit of a branch by simply scanning each port on the current branch device, then uses the last non-zero full_pbn value that it finds. It then counts the sum of the PBN used on each branch device for that level, and compares against the full_pbn value it found before. This is wrong because ports can and will have different PBN limitations on many hubs, especially since a number of DisplayPort hubs out there will be clever and only use the smallest link rate required for each downstream sink - potentially giving every port a different full_pbn value depending on what link rate it's trained at. This means with our current code, which max PBN value we end up with is not well defined. Additionally, we also need to remember when checking bandwidth limitations that the top-most device in any MST topology is a branch device, not a port. This means that the first level of a topology doesn't technically have a full_pbn value that needs to be checked. Instead, we should assume that so long as our VCPI allocations fit we're within the bandwidth limitations of the primary MSTB. We do however, want to check full_pbn on every port including those of the primary MSTB. However, it's important to keep in mind that this value represents the minimum link rate /between a port's sink or mstb, and the mstb itself/. A quick diagram to explain: MSTB #1 / \ / \ Port #1 Port #2 full_pbn for Port #1 → | | ← full_pbn for Port #2 Sink #1 MSTB #2 | etc... Note that in the above diagram, the combined PBN from all VCPI allocations on said hub should not exceed the full_pbn value of port #2, and the display configuration on sink #1 should not exceed the full_pbn value of port #1. However, port #1 and port #2 can otherwise consume as much bandwidth as they want so long as their VCPI allocations still fit. And finally - our current bandwidth checking code also makes the mistake of not checking whether something is an end device or not before trying to traverse down it. So, let's fix it by rewriting our bandwidth checking helpers. We split the function into one part for handling branches which simply adds up the total PBN on each branch and returns it, and one for checking each port to ensure we're not going over its PBN limit. Phew. This should fix regressions seen, where we erroneously reject display configurations due to thinking they're going over our bandwidth limits when they're not. Changes since v1: * Took an even closer look at how PBN limitations are supposed to be handled, and did some experimenting with Sean Paul. Ended up rewriting these helpers again, but this time they should actually be correct! Changes since v2: * Small indenting fix * Fix pbn_used check in drm_dp_mst_atomic_check_port_bw_limit() Signed-off-by: Lyude Paul Fixes: cd82d82cbc04 ("drm/dp_mst: Add branch bandwidth validation to MST atomic check") Cc: Sean Paul Acked-by: Alex Deucher Reviewed-by: Mikita Lipski Tested-by: Hans de Goede Link: https://patchwork.freedesktop.org/patch/msgid/20200309210131.1497545-1-lyude@redhat.com --- drivers/gpu/drm/drm_dp_mst_topology.c | 123 ++++++++++++++++++++------ 1 file changed, 95 insertions(+), 28 deletions(-) diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index 112972031a84..ed0fea2ac322 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -4830,41 +4830,102 @@ static bool drm_dp_mst_port_downstream_of_branch(struct drm_dp_mst_port *port, return false; } -static inline -int drm_dp_mst_atomic_check_bw_limit(struct drm_dp_mst_branch *branch, - struct drm_dp_mst_topology_state *mst_state) +static int +drm_dp_mst_atomic_check_port_bw_limit(struct drm_dp_mst_port *port, + struct drm_dp_mst_topology_state *state); + +static int +drm_dp_mst_atomic_check_mstb_bw_limit(struct drm_dp_mst_branch *mstb, + struct drm_dp_mst_topology_state *state) { - struct drm_dp_mst_port *port; struct drm_dp_vcpi_allocation *vcpi; - int pbn_limit = 0, pbn_used = 0; + struct drm_dp_mst_port *port; + int pbn_used = 0, ret; + bool found = false; - list_for_each_entry(port, &branch->ports, next) { - if (port->mstb) - if (drm_dp_mst_atomic_check_bw_limit(port->mstb, mst_state)) - return -ENOSPC; - - if (port->full_pbn > 0) - pbn_limit = port->full_pbn; - } - DRM_DEBUG_ATOMIC("[MST BRANCH:%p] branch has %d PBN available\n", - branch, pbn_limit); - - list_for_each_entry(vcpi, &mst_state->vcpis, next) { - if (!vcpi->pbn) + /* Check that we have at least one port in our state that's downstream + * of this branch, otherwise we can skip this branch + */ + list_for_each_entry(vcpi, &state->vcpis, next) { + if (!vcpi->pbn || + !drm_dp_mst_port_downstream_of_branch(vcpi->port, mstb)) continue; - if (drm_dp_mst_port_downstream_of_branch(vcpi->port, branch)) - pbn_used += vcpi->pbn; + found = true; + break; } - DRM_DEBUG_ATOMIC("[MST BRANCH:%p] branch used %d PBN\n", - branch, pbn_used); + if (!found) + return 0; - if (pbn_used > pbn_limit) { - DRM_DEBUG_ATOMIC("[MST BRANCH:%p] No available bandwidth\n", - branch); + if (mstb->port_parent) + DRM_DEBUG_ATOMIC("[MSTB:%p] [MST PORT:%p] Checking bandwidth limits on [MSTB:%p]\n", + mstb->port_parent->parent, mstb->port_parent, + mstb); + else + DRM_DEBUG_ATOMIC("[MSTB:%p] Checking bandwidth limits\n", + mstb); + + list_for_each_entry(port, &mstb->ports, next) { + ret = drm_dp_mst_atomic_check_port_bw_limit(port, state); + if (ret < 0) + return ret; + + pbn_used += ret; + } + + return pbn_used; +} + +static int +drm_dp_mst_atomic_check_port_bw_limit(struct drm_dp_mst_port *port, + struct drm_dp_mst_topology_state *state) +{ + struct drm_dp_vcpi_allocation *vcpi; + int pbn_used = 0; + + if (port->pdt == DP_PEER_DEVICE_NONE) + return 0; + + if (drm_dp_mst_is_end_device(port->pdt, port->mcs)) { + bool found = false; + + list_for_each_entry(vcpi, &state->vcpis, next) { + if (vcpi->port != port) + continue; + if (!vcpi->pbn) + return 0; + + found = true; + break; + } + if (!found) + return 0; + + /* This should never happen, as it means we tried to + * set a mode before querying the full_pbn + */ + if (WARN_ON(!port->full_pbn)) + return -EINVAL; + + pbn_used = vcpi->pbn; + } else { + pbn_used = drm_dp_mst_atomic_check_mstb_bw_limit(port->mstb, + state); + if (pbn_used <= 0) + return pbn_used; + } + + if (pbn_used > port->full_pbn) { + DRM_DEBUG_ATOMIC("[MSTB:%p] [MST PORT:%p] required PBN of %d exceeds port limit of %d\n", + port->parent, port, pbn_used, + port->full_pbn); return -ENOSPC; } - return 0; + + DRM_DEBUG_ATOMIC("[MSTB:%p] [MST PORT:%p] uses %d out of %d PBN\n", + port->parent, port, pbn_used, port->full_pbn); + + return pbn_used; } static inline int @@ -5062,9 +5123,15 @@ int drm_dp_mst_atomic_check(struct drm_atomic_state *state) ret = drm_dp_mst_atomic_check_vcpi_alloc_limit(mgr, mst_state); if (ret) break; - ret = drm_dp_mst_atomic_check_bw_limit(mgr->mst_primary, mst_state); - if (ret) + + mutex_lock(&mgr->lock); + ret = drm_dp_mst_atomic_check_mstb_bw_limit(mgr->mst_primary, + mst_state); + mutex_unlock(&mgr->lock); + if (ret < 0) break; + else + ret = 0; } return ret; From 59833696442c674acbbd297772ba89e7ad8c753d Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Mon, 9 Mar 2020 15:01:37 +0100 Subject: [PATCH 239/256] iommu/vt-d: dmar: replace WARN_TAINT with pr_warn + add_taint Quoting from the comment describing the WARN functions in include/asm-generic/bug.h: * WARN(), WARN_ON(), WARN_ON_ONCE, and so on can be used to report * significant kernel issues that need prompt attention if they should ever * appear at runtime. * * Do not use these macros when checking for invalid external inputs The (buggy) firmware tables which the dmar code was calling WARN_TAINT for really are invalid external inputs. They are not under the kernel's control and the issues in them cannot be fixed by a kernel update. So logging a backtrace, which invites bug reports to be filed about this, is not helpful. Some distros, e.g. Fedora, have tools watching for the kernel backtraces logged by the WARN macros and offer the user an option to file a bug for this when these are encountered. The WARN_TAINT in warn_invalid_dmar() + another iommu WARN_TAINT, addressed in another patch, have lead to over a 100 bugs being filed this way. This commit replaces the WARN_TAINT("...") calls, with pr_warn(FW_BUG "...") + add_taint(TAINT_FIRMWARE_WORKAROUND, ...) calls avoiding the backtrace and thus also avoiding bug-reports being filed about this against the kernel. Fixes: fd0c8894893c ("intel-iommu: Set a more specific taint flag for invalid BIOS DMAR tables") Fixes: e625b4a95d50 ("iommu/vt-d: Parse ANDD records") Signed-off-by: Hans de Goede Signed-off-by: Joerg Roedel Acked-by: Lu Baolu Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20200309140138.3753-2-hdegoede@redhat.com BugLink: https://bugzilla.redhat.com/show_bug.cgi?id=1564895 --- drivers/iommu/dmar.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index 7b16c4db40b4..c000ddff822e 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -441,12 +441,13 @@ static int __init dmar_parse_one_andd(struct acpi_dmar_header *header, /* Check for NUL termination within the designated length */ if (strnlen(andd->device_name, header->length - 8) == header->length - 8) { - WARN_TAINT(1, TAINT_FIRMWARE_WORKAROUND, + pr_warn(FW_BUG "Your BIOS is broken; ANDD object name is not NUL-terminated\n" "BIOS vendor: %s; Ver: %s; Product Version: %s\n", dmi_get_system_info(DMI_BIOS_VENDOR), dmi_get_system_info(DMI_BIOS_VERSION), dmi_get_system_info(DMI_PRODUCT_VERSION)); + add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); return -EINVAL; } pr_info("ANDD device: %x name: %s\n", andd->device_number, @@ -472,14 +473,14 @@ static int dmar_parse_one_rhsa(struct acpi_dmar_header *header, void *arg) return 0; } } - WARN_TAINT( - 1, TAINT_FIRMWARE_WORKAROUND, + pr_warn(FW_BUG "Your BIOS is broken; RHSA refers to non-existent DMAR unit at %llx\n" "BIOS vendor: %s; Ver: %s; Product Version: %s\n", drhd->reg_base_addr, dmi_get_system_info(DMI_BIOS_VENDOR), dmi_get_system_info(DMI_BIOS_VERSION), dmi_get_system_info(DMI_PRODUCT_VERSION)); + add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); return 0; } @@ -828,14 +829,14 @@ int __init dmar_table_init(void) static void warn_invalid_dmar(u64 addr, const char *message) { - WARN_TAINT_ONCE( - 1, TAINT_FIRMWARE_WORKAROUND, + pr_warn_once(FW_BUG "Your BIOS is broken; DMAR reported at address %llx%s!\n" "BIOS vendor: %s; Ver: %s; Product Version: %s\n", addr, message, dmi_get_system_info(DMI_BIOS_VENDOR), dmi_get_system_info(DMI_BIOS_VERSION), dmi_get_system_info(DMI_PRODUCT_VERSION)); + add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); } static int __ref From 96788c7a7f1e7206519d4d736f89a2072dcfe0fc Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Mon, 9 Mar 2020 15:01:38 +0100 Subject: [PATCH 240/256] iommu/vt-d: dmar_parse_one_rmrr: replace WARN_TAINT with pr_warn + add_taint Quoting from the comment describing the WARN functions in include/asm-generic/bug.h: * WARN(), WARN_ON(), WARN_ON_ONCE, and so on can be used to report * significant kernel issues that need prompt attention if they should ever * appear at runtime. * * Do not use these macros when checking for invalid external inputs The (buggy) firmware tables which the dmar code was calling WARN_TAINT for really are invalid external inputs. They are not under the kernel's control and the issues in them cannot be fixed by a kernel update. So logging a backtrace, which invites bug reports to be filed about this, is not helpful. Some distros, e.g. Fedora, have tools watching for the kernel backtraces logged by the WARN macros and offer the user an option to file a bug for this when these are encountered. The WARN_TAINT in dmar_parse_one_rmrr + another iommu WARN_TAINT, addressed in another patch, have lead to over a 100 bugs being filed this way. This commit replaces the WARN_TAINT("...") call, with a pr_warn(FW_BUG "...") + add_taint(TAINT_FIRMWARE_WORKAROUND, ...) call avoiding the backtrace and thus also avoiding bug-reports being filed about this against the kernel. Fixes: f5a68bb0752e ("iommu/vt-d: Mark firmware tainted if RMRR fails sanity check") Signed-off-by: Hans de Goede Signed-off-by: Joerg Roedel Acked-by: Lu Baolu Cc: stable@vger.kernel.org Cc: Barret Rhoden Link: https://lore.kernel.org/r/20200309140138.3753-3-hdegoede@redhat.com BugLink: https://bugzilla.redhat.com/show_bug.cgi?id=1808874 --- drivers/iommu/intel-iommu.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 693380355dea..bdcdfff6015b 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -4460,14 +4460,16 @@ int __init dmar_parse_one_rmrr(struct acpi_dmar_header *header, void *arg) struct dmar_rmrr_unit *rmrru; rmrr = (struct acpi_dmar_reserved_memory *)header; - if (rmrr_sanity_check(rmrr)) - WARN_TAINT(1, TAINT_FIRMWARE_WORKAROUND, + if (rmrr_sanity_check(rmrr)) { + pr_warn(FW_BUG "Your BIOS is broken; bad RMRR [%#018Lx-%#018Lx]\n" "BIOS vendor: %s; Ver: %s; Product Version: %s\n", rmrr->base_address, rmrr->end_address, dmi_get_system_info(DMI_BIOS_VENDOR), dmi_get_system_info(DMI_BIOS_VERSION), dmi_get_system_info(DMI_PRODUCT_VERSION)); + add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); + } rmrru = kzalloc(sizeof(*rmrru), GFP_KERNEL); if (!rmrru) From 81ee85d0462410de8eeeec1b9761941fd6ed8c7b Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Mon, 9 Mar 2020 19:25:10 +0100 Subject: [PATCH 241/256] iommu/vt-d: quirk_ioat_snb_local_iommu: replace WARN_TAINT with pr_warn + add_taint Quoting from the comment describing the WARN functions in include/asm-generic/bug.h: * WARN(), WARN_ON(), WARN_ON_ONCE, and so on can be used to report * significant kernel issues that need prompt attention if they should ever * appear at runtime. * * Do not use these macros when checking for invalid external inputs The (buggy) firmware tables which the dmar code was calling WARN_TAINT for really are invalid external inputs. They are not under the kernel's control and the issues in them cannot be fixed by a kernel update. So logging a backtrace, which invites bug reports to be filed about this, is not helpful. Fixes: 556ab45f9a77 ("ioat2: catch and recover from broken vtd configurations v6") Signed-off-by: Hans de Goede Acked-by: Lu Baolu Link: https://lore.kernel.org/r/20200309182510.373875-1-hdegoede@redhat.com BugLink: https://bugzilla.redhat.com/show_bug.cgi?id=701847 Signed-off-by: Joerg Roedel --- drivers/iommu/intel-iommu.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index bdcdfff6015b..2943d3600b7c 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -4261,10 +4261,11 @@ static void quirk_ioat_snb_local_iommu(struct pci_dev *pdev) /* we know that the this iommu should be at offset 0xa000 from vtbar */ drhd = dmar_find_matched_drhd_unit(pdev); - if (WARN_TAINT_ONCE(!drhd || drhd->reg_base_addr - vtbar != 0xa000, - TAINT_FIRMWARE_WORKAROUND, - "BIOS assigned incorrect VT-d unit for Intel(R) QuickData Technology device\n")) + if (!drhd || drhd->reg_base_addr - vtbar != 0xa000) { + pr_warn_once(FW_BUG "BIOS assigned incorrect VT-d unit for Intel(R) QuickData Technology device\n"); + add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); pdev->dev.archdata.iommu = DUMMY_DEVICE_DOMAIN_INFO; + } } DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB, quirk_ioat_snb_local_iommu); From ba3b01d7a6f4ab9f8a0557044c9a7678f64ae070 Mon Sep 17 00:00:00 2001 From: Megha Dey Date: Mon, 9 Mar 2020 13:09:46 -0700 Subject: [PATCH 242/256] iommu/vt-d: Fix debugfs register reads Commit 6825d3ea6cde ("iommu/vt-d: Add debugfs support to show register contents") dumps the register contents for all IOMMU devices. Currently, a 64 bit read(dmar_readq) is done for all the IOMMU registers, even though some of the registers are 32 bits, which is incorrect. Use the correct read function variant (dmar_readl/dmar_readq) while reading the contents of 32/64 bit registers respectively. Signed-off-by: Megha Dey Link: https://lore.kernel.org/r/1583784587-26126-2-git-send-email-megha.dey@linux.intel.com Acked-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel-iommu-debugfs.c | 46 ++++++++++++++++++----------- include/linux/intel-iommu.h | 2 ++ 2 files changed, 30 insertions(+), 18 deletions(-) diff --git a/drivers/iommu/intel-iommu-debugfs.c b/drivers/iommu/intel-iommu-debugfs.c index c1257bef553c..0a7791934a16 100644 --- a/drivers/iommu/intel-iommu-debugfs.c +++ b/drivers/iommu/intel-iommu-debugfs.c @@ -33,38 +33,42 @@ struct iommu_regset { #define IOMMU_REGSET_ENTRY(_reg_) \ { DMAR_##_reg_##_REG, __stringify(_reg_) } -static const struct iommu_regset iommu_regs[] = { + +static const struct iommu_regset iommu_regs_32[] = { IOMMU_REGSET_ENTRY(VER), - IOMMU_REGSET_ENTRY(CAP), - IOMMU_REGSET_ENTRY(ECAP), IOMMU_REGSET_ENTRY(GCMD), IOMMU_REGSET_ENTRY(GSTS), - IOMMU_REGSET_ENTRY(RTADDR), - IOMMU_REGSET_ENTRY(CCMD), IOMMU_REGSET_ENTRY(FSTS), IOMMU_REGSET_ENTRY(FECTL), IOMMU_REGSET_ENTRY(FEDATA), IOMMU_REGSET_ENTRY(FEADDR), IOMMU_REGSET_ENTRY(FEUADDR), - IOMMU_REGSET_ENTRY(AFLOG), IOMMU_REGSET_ENTRY(PMEN), IOMMU_REGSET_ENTRY(PLMBASE), IOMMU_REGSET_ENTRY(PLMLIMIT), - IOMMU_REGSET_ENTRY(PHMBASE), - IOMMU_REGSET_ENTRY(PHMLIMIT), - IOMMU_REGSET_ENTRY(IQH), - IOMMU_REGSET_ENTRY(IQT), - IOMMU_REGSET_ENTRY(IQA), IOMMU_REGSET_ENTRY(ICS), - IOMMU_REGSET_ENTRY(IRTA), - IOMMU_REGSET_ENTRY(PQH), - IOMMU_REGSET_ENTRY(PQT), - IOMMU_REGSET_ENTRY(PQA), IOMMU_REGSET_ENTRY(PRS), IOMMU_REGSET_ENTRY(PECTL), IOMMU_REGSET_ENTRY(PEDATA), IOMMU_REGSET_ENTRY(PEADDR), IOMMU_REGSET_ENTRY(PEUADDR), +}; + +static const struct iommu_regset iommu_regs_64[] = { + IOMMU_REGSET_ENTRY(CAP), + IOMMU_REGSET_ENTRY(ECAP), + IOMMU_REGSET_ENTRY(RTADDR), + IOMMU_REGSET_ENTRY(CCMD), + IOMMU_REGSET_ENTRY(AFLOG), + IOMMU_REGSET_ENTRY(PHMBASE), + IOMMU_REGSET_ENTRY(PHMLIMIT), + IOMMU_REGSET_ENTRY(IQH), + IOMMU_REGSET_ENTRY(IQT), + IOMMU_REGSET_ENTRY(IQA), + IOMMU_REGSET_ENTRY(IRTA), + IOMMU_REGSET_ENTRY(PQH), + IOMMU_REGSET_ENTRY(PQT), + IOMMU_REGSET_ENTRY(PQA), IOMMU_REGSET_ENTRY(MTRRCAP), IOMMU_REGSET_ENTRY(MTRRDEF), IOMMU_REGSET_ENTRY(MTRR_FIX64K_00000), @@ -127,10 +131,16 @@ static int iommu_regset_show(struct seq_file *m, void *unused) * by adding the offset to the pointer (virtual address). */ raw_spin_lock_irqsave(&iommu->register_lock, flag); - for (i = 0 ; i < ARRAY_SIZE(iommu_regs); i++) { - value = dmar_readq(iommu->reg + iommu_regs[i].offset); + for (i = 0 ; i < ARRAY_SIZE(iommu_regs_32); i++) { + value = dmar_readl(iommu->reg + iommu_regs_32[i].offset); seq_printf(m, "%-16s\t0x%02x\t\t0x%016llx\n", - iommu_regs[i].regs, iommu_regs[i].offset, + iommu_regs_32[i].regs, iommu_regs_32[i].offset, + value); + } + for (i = 0 ; i < ARRAY_SIZE(iommu_regs_64); i++) { + value = dmar_readq(iommu->reg + iommu_regs_64[i].offset); + seq_printf(m, "%-16s\t0x%02x\t\t0x%016llx\n", + iommu_regs_64[i].regs, iommu_regs_64[i].offset, value); } raw_spin_unlock_irqrestore(&iommu->register_lock, flag); diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 4a16b39ae353..980234ae0312 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -123,6 +123,8 @@ #define dmar_readq(a) readq(a) #define dmar_writeq(a,v) writeq(v,a) +#define dmar_readl(a) readl(a) +#define dmar_writel(a, v) writel(v, a) #define DMAR_VER_MAJOR(v) (((v) & 0xf0) >> 4) #define DMAR_VER_MINOR(v) ((v) & 0x0f) From 8daee952b4389729358665fb91949460641659d4 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Thu, 12 Mar 2020 14:32:44 +0100 Subject: [PATCH 243/256] i2c: acpi: put device when verifying client fails i2c_verify_client() can fail, so we need to put the device when that happens. Fixes: 525e6fabeae2 ("i2c / ACPI: add support for ACPI reconfigure notifications") Reported-by: Geert Uytterhoeven Signed-off-by: Wolfram Sang Reviewed-by: Geert Uytterhoeven Reviewed-by: Andy Shevchenko Acked-by: Mika Westerberg Signed-off-by: Wolfram Sang --- drivers/i2c/i2c-core-acpi.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/i2c/i2c-core-acpi.c b/drivers/i2c/i2c-core-acpi.c index 8f3dbc97a057..8b0ff780919b 100644 --- a/drivers/i2c/i2c-core-acpi.c +++ b/drivers/i2c/i2c-core-acpi.c @@ -394,9 +394,17 @@ EXPORT_SYMBOL_GPL(i2c_acpi_find_adapter_by_handle); static struct i2c_client *i2c_acpi_find_client_by_adev(struct acpi_device *adev) { struct device *dev; + struct i2c_client *client; dev = bus_find_device_by_acpi_dev(&i2c_bus_type, adev); - return dev ? i2c_verify_client(dev) : NULL; + if (!dev) + return NULL; + + client = i2c_verify_client(dev); + if (!client) + put_device(dev); + + return client; } static int i2c_acpi_notify(struct notifier_block *nb, unsigned long value, From 469ff207b4c4033540b50bc59587dc915faa1367 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 12 Mar 2020 16:58:30 -0400 Subject: [PATCH 244/256] x86/vector: Remove warning on managed interrupt migration The vector management code assumes that managed interrupts cannot be migrated away from an online CPU. free_moved_vector() has a WARN_ON_ONCE() which triggers when a managed interrupt vector association on a online CPU is cleared. The CPU offline code uses a different mechanism which cannot trigger this. This assumption is not longer correct because the new CPU isolation feature which affects the placement of managed interrupts must be able to move a managed interrupt away from an online CPU. There are two reasons why this can happen: 1) When the interrupt is activated the affinity mask which was established in irq_create_affinity_masks() is handed in to the vector allocation code. This mask contains all CPUs to which the interrupt can be made affine to, but this does not take the CPU isolation 'managed_irq' mask into account. When the interrupt is finally requested by the device driver then the affinity is checked again and the CPU isolation 'managed_irq' mask is taken into account, which moves the interrupt to a non-isolated CPU if possible. 2) The interrupt can be affine to an isolated CPU because the non-isolated CPUs in the calculated affinity mask are not online. Once a non-isolated CPU which is in the mask comes online the interrupt is migrated to this non-isolated CPU In both cases the regular online migration mechanism is used which triggers the WARN_ON_ONCE() in free_moved_vector(). Case #1 could have been addressed by taking the isolation mask into account, but that would require a massive code change in the activation logic and the eventual migration event was accepted as a reasonable tradeoff when the isolation feature was developed. But even if #1 would be addressed, #2 would still trigger it. Of course the warning in free_moved_vector() was overlooked at that time and the above two cases which have been discussed during patch review have obviously never been tested before the final submission. So keep it simple and remove the warning. [ tglx: Rewrote changelog and added a comment to free_moved_vector() ] Fixes: 11ea68f553e2 ("genirq, sched/isolation: Isolate from handling managed interrupts") Signed-off-by: Peter Xu Signed-off-by: Thomas Gleixner Reviewed-by: Ming Lei Link: https://lkml.kernel.org/r/20200312205830.81796-1-peterx@redhat.com --- arch/x86/kernel/apic/vector.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 2c5676b0a6e7..48293d15f1e1 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -838,13 +838,15 @@ static void free_moved_vector(struct apic_chip_data *apicd) bool managed = apicd->is_managed; /* - * This should never happen. Managed interrupts are not - * migrated except on CPU down, which does not involve the - * cleanup vector. But try to keep the accounting correct - * nevertheless. + * Managed interrupts are usually not migrated away + * from an online CPU, but CPU isolation 'managed_irq' + * can make that happen. + * 1) Activation does not take the isolation into account + * to keep the code simple + * 2) Migration away from an isolated CPU can happen when + * a non-isolated CPU which is in the calculated + * affinity mask comes online. */ - WARN_ON_ONCE(managed); - trace_vector_free_moved(apicd->irq, cpu, vector, managed); irq_matrix_free(vector_matrix, cpu, vector, managed); per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED; From 53afcd310e867d25e394718558783c476301205c Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Fri, 21 Feb 2020 16:34:42 +0200 Subject: [PATCH 245/256] ovl: fix some xino configurations Fix up two bugs in the coversion to xino_mode: 1. xino=off does not always end up in disabled mode 2. xino=auto on 32bit arch should end up in disabled mode Take a proactive approach to disabling xino on 32bit kernel: 1. Disable XINO_AUTO config during build time 2. Disable xino with a warning on mount time As a by product, xino=on on 32bit arch also ends up in disabled mode. We never intended to enable xino on 32bit arch and this will make the rest of the logic simpler. Fixes: 0f831ec85eda ("ovl: simplify ovl_same_sb() helper") Signed-off-by: Amir Goldstein Signed-off-by: Miklos Szeredi --- fs/overlayfs/Kconfig | 1 + fs/overlayfs/super.c | 9 ++++++++- 2 files changed, 9 insertions(+), 1 deletion(-) diff --git a/fs/overlayfs/Kconfig b/fs/overlayfs/Kconfig index 444e2da4f60e..714c14c47ca5 100644 --- a/fs/overlayfs/Kconfig +++ b/fs/overlayfs/Kconfig @@ -93,6 +93,7 @@ config OVERLAY_FS_XINO_AUTO bool "Overlayfs: auto enable inode number mapping" default n depends on OVERLAY_FS + depends on 64BIT help If this config option is enabled then overlay filesystems will use unused high bits in undelying filesystem inode numbers to map all diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 319fe0d355b0..ac967f1cb6e5 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -1411,6 +1411,8 @@ static int ovl_get_layers(struct super_block *sb, struct ovl_fs *ofs, if (ofs->config.xino == OVL_XINO_ON) pr_info("\"xino=on\" is useless with all layers on same fs, ignore.\n"); ofs->xino_mode = 0; + } else if (ofs->config.xino == OVL_XINO_OFF) { + ofs->xino_mode = -1; } else if (ofs->config.xino == OVL_XINO_ON && ofs->xino_mode < 0) { /* * This is a roundup of number of bits needed for encoding @@ -1623,8 +1625,13 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) sb->s_stack_depth = 0; sb->s_maxbytes = MAX_LFS_FILESIZE; /* Assume underlaying fs uses 32bit inodes unless proven otherwise */ - if (ofs->config.xino != OVL_XINO_OFF) + if (ofs->config.xino != OVL_XINO_OFF) { ofs->xino_mode = BITS_PER_LONG - 32; + if (!ofs->xino_mode) { + pr_warn("xino not supported on 32bit kernel, falling back to xino=off.\n"); + ofs->config.xino = OVL_XINO_OFF; + } + } /* alloc/destroy_inode needed for setting up traps in inode cache */ sb->s_op = &ovl_super_operations; From c853680453ac235e9010987a8bdaaba0e116d3c8 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 13 Mar 2020 15:42:20 +0100 Subject: [PATCH 246/256] ovl: fix lockdep warning for async write Lockdep reports "WARNING: lock held when returning to user space!" due to async write holding freeze lock over the write. Apparently aio.c already deals with this by lying to lockdep about the state of the lock. Do the same here. No need to check for S_IFREG() here since these file ops are regular-only. Reported-by: syzbot+9331a354f4f624a52a55@syzkaller.appspotmail.com Fixes: 2406a307ac7d ("ovl: implement async IO routines") Signed-off-by: Miklos Szeredi --- fs/overlayfs/file.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index a5317216de73..87c362f65448 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -244,6 +244,9 @@ static void ovl_aio_cleanup_handler(struct ovl_aio_req *aio_req) if (iocb->ki_flags & IOCB_WRITE) { struct inode *inode = file_inode(orig_iocb->ki_filp); + /* Actually acquired in ovl_write_iter() */ + __sb_writers_acquired(file_inode(iocb->ki_filp)->i_sb, + SB_FREEZE_WRITE); file_end_write(iocb->ki_filp); ovl_copyattr(ovl_inode_real(inode), inode); } @@ -346,6 +349,9 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter) goto out; file_start_write(real.file); + /* Pacify lockdep, same trick as done in aio_write() */ + __sb_writers_release(file_inode(real.file)->i_sb, + SB_FREEZE_WRITE); aio_req->fd = real; real.flags = 0; aio_req->orig_iocb = iocb; From ddd2b85ff73bb60061a9fb08ac1f5a03a2d4bce0 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Thu, 12 Mar 2020 21:36:53 +0000 Subject: [PATCH 247/256] afs: Use kfree_rcu() instead of casting kfree() to rcu_callback_t afs_put_addrlist() casts kfree() to rcu_callback_t. Apart from being wrong in theory, this might also blow up when people start enforcing function types via compiler instrumentation, and it means the rcu_head has to be first in struct afs_addr_list. Use kfree_rcu() instead, it's simpler and more correct. Signed-off-by: Jann Horn Signed-off-by: David Howells Signed-off-by: Linus Torvalds --- fs/afs/addr_list.c | 2 +- fs/afs/internal.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/afs/addr_list.c b/fs/afs/addr_list.c index df415c05939e..de1ae0bead3b 100644 --- a/fs/afs/addr_list.c +++ b/fs/afs/addr_list.c @@ -19,7 +19,7 @@ void afs_put_addrlist(struct afs_addr_list *alist) { if (alist && refcount_dec_and_test(&alist->usage)) - call_rcu(&alist->rcu, (rcu_callback_t)kfree); + kfree_rcu(alist, rcu); } /* diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 1d81fc4c3058..35f951ac296f 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -81,7 +81,7 @@ enum afs_call_state { * List of server addresses. */ struct afs_addr_list { - struct rcu_head rcu; /* Must be first */ + struct rcu_head rcu; refcount_t usage; u32 version; /* Version */ unsigned char max_addrs; From b0bb0c22c4db623f2e7b1a471596fbf1c22c6dc5 Mon Sep 17 00:00:00 2001 From: Zhenzhong Duan Date: Thu, 12 Mar 2020 14:09:54 +0800 Subject: [PATCH 248/256] iommu/vt-d: Fix the wrong printing in RHSA parsing When base address in RHSA structure doesn't match base address in each DRHD structure, the base address in last DRHD is printed out. This doesn't make sense when there are multiple DRHD units, fix it by printing the buggy RHSA's base address. Signed-off-by: Lu Baolu Signed-off-by: Zhenzhong Duan Fixes: fd0c8894893cb ("intel-iommu: Set a more specific taint flag for invalid BIOS DMAR tables") Signed-off-by: Joerg Roedel --- drivers/iommu/dmar.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index c000ddff822e..c7b1461e8d0a 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -476,7 +476,7 @@ static int dmar_parse_one_rhsa(struct acpi_dmar_header *header, void *arg) pr_warn(FW_BUG "Your BIOS is broken; RHSA refers to non-existent DMAR unit at %llx\n" "BIOS vendor: %s; Ver: %s; Product Version: %s\n", - drhd->reg_base_addr, + rhsa->base_address, dmi_get_system_info(DMI_BIOS_VENDOR), dmi_get_system_info(DMI_BIOS_VERSION), dmi_get_system_info(DMI_PRODUCT_VERSION)); From da72a379b2ec0bad3eb265787f7008bead0b040c Mon Sep 17 00:00:00 2001 From: Daniel Drake Date: Thu, 12 Mar 2020 14:09:55 +0800 Subject: [PATCH 249/256] iommu/vt-d: Ignore devices with out-of-spec domain number MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit VMD subdevices are created with a PCI domain ID of 0x10000 or higher. These subdevices are also handled like all other PCI devices by dmar_pci_bus_notifier(). However, when dmar_alloc_pci_notify_info() take records of such devices, it will truncate the domain ID to a u16 value (in info->seg). The device at (e.g.) 10000:00:02.0 is then treated by the DMAR code as if it is 0000:00:02.0. In the unlucky event that a real device also exists at 0000:00:02.0 and also has a device-specific entry in the DMAR table, dmar_insert_dev_scope() will crash on:   BUG_ON(i >= devices_cnt); That's basically a sanity check that only one PCI device matches a single DMAR entry; in this case we seem to have two matching devices. Fix this by ignoring devices that have a domain number higher than what can be looked up in the DMAR table. This problem was carefully diagnosed by Jian-Hong Pan. Signed-off-by: Lu Baolu Signed-off-by: Daniel Drake Fixes: 59ce0515cdaf3 ("iommu/vt-d: Update DRHD/RMRR/ATSR device scope caches when PCI hotplug happens") Signed-off-by: Joerg Roedel --- drivers/iommu/dmar.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index c7b1461e8d0a..f77dae7ba7d4 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include @@ -128,6 +129,13 @@ dmar_alloc_pci_notify_info(struct pci_dev *dev, unsigned long event) BUG_ON(dev->is_virtfn); + /* + * Ignore devices that have a domain number higher than what can + * be looked up in DMAR, e.g. VMD subdevices with domain 0x10000 + */ + if (pci_domain_nr(dev->bus) > U16_MAX) + return NULL; + /* Only generate path[] for device addition event */ if (event == BUS_NOTIFY_ADD_DEVICE) for (tmp = dev; tmp; tmp = tmp->bus->self) From 730ad0ede130015a773229573559e97ba0943065 Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Thu, 12 Mar 2020 05:18:39 -0500 Subject: [PATCH 250/256] iommu/amd: Fix IOMMU AVIC not properly update the is_run bit in IRTE Commit b9c6ff94e43a ("iommu/amd: Re-factor guest virtual APIC (de-)activation code") accidentally left out the ir_data pointer when calling modity_irte_ga(), which causes the function amd_iommu_update_ga() to return prematurely due to struct amd_ir_data.ref is NULL and the "is_run" bit of IRTE does not get updated properly. This results in bad I/O performance since IOMMU AVIC always generate GA Log entry and notify IOMMU driver and KVM when it receives interrupt from the PCI pass-through device instead of directly inject interrupt to the vCPU. Fixes by passing ir_data when calling modify_irte_ga() as done previously. Fixes: b9c6ff94e43a ("iommu/amd: Re-factor guest virtual APIC (de-)activation code") Signed-off-by: Suravee Suthikulpanit Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index aac132bd1ef0..20cce366e951 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -3826,7 +3826,7 @@ int amd_iommu_activate_guest_mode(void *data) entry->lo.fields_vapic.ga_tag = ir_data->ga_tag; return modify_irte_ga(ir_data->irq_2_irte.devid, - ir_data->irq_2_irte.index, entry, NULL); + ir_data->irq_2_irte.index, entry, ir_data); } EXPORT_SYMBOL(amd_iommu_activate_guest_mode); @@ -3852,7 +3852,7 @@ int amd_iommu_deactivate_guest_mode(void *data) APICID_TO_IRTE_DEST_HI(cfg->dest_apicid); return modify_irte_ga(ir_data->irq_2_irte.devid, - ir_data->irq_2_irte.index, entry, NULL); + ir_data->irq_2_irte.index, entry, ir_data); } EXPORT_SYMBOL(amd_iommu_deactivate_guest_mode); From 7a57c09bb1cb89239f38f690b87cdf2c7db76c34 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 12 Mar 2020 11:04:16 -0700 Subject: [PATCH 251/256] KVM: VMX: Condition ENCLS-exiting enabling on CPU support for SGX1 Enable ENCLS-exiting (and thus set vmcs.ENCLS_EXITING_BITMAP) only if the CPU supports SGX1. Per Intel's SDM, all ENCLS leafs #UD if SGX1 is not supported[*], i.e. intercepting ENCLS to inject a #UD is unnecessary. Avoiding ENCLS-exiting even when it is reported as supported by the CPU works around a reported issue where SGX is "hard" disabled after an S3 suspend/resume cycle, i.e. CPUID.0x7.SGX=0 and the VMCS field/control are enumerated as unsupported. While the root cause of the S3 issue is unknown, it's definitely _not_ a KVM (or kernel) bug, i.e. this is a workaround for what is most likely a hardware or firmware issue. As a bonus side effect, KVM saves a VMWRITE when first preparing vmcs01 and vmcs02. Note, SGX must be disabled in BIOS to take advantage of this workaround [*] The additional ENCLS CPUID check on SGX1 exists so that SGX can be globally "soft" disabled post-reset, e.g. if #MC bits in MCi_CTL are cleared. Soft disabled meaning disabling SGX without clearing the primary CPUID bit (in leaf 0x7) and without poking into non-SGX CPU paths, e.g. for the VMCS controls. Fixes: 0b665d304028 ("KVM: vmx: Inject #UD for SGX ENCLS instruction in guest") Reported-by: Toni Spets Signed-off-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/vmx.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 40b1e6138cd5..26f8f31563e9 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -2338,6 +2338,17 @@ static void hardware_disable(void) kvm_cpu_vmxoff(); } +/* + * There is no X86_FEATURE for SGX yet, but anyway we need to query CPUID + * directly instead of going through cpu_has(), to ensure KVM is trapping + * ENCLS whenever it's supported in hardware. It does not matter whether + * the host OS supports or has enabled SGX. + */ +static bool cpu_has_sgx(void) +{ + return cpuid_eax(0) >= 0x12 && (cpuid_eax(0x12) & BIT(0)); +} + static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt, u32 msr, u32 *result) { @@ -2418,8 +2429,9 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | SECONDARY_EXEC_PT_USE_GPA | SECONDARY_EXEC_PT_CONCEAL_VMX | - SECONDARY_EXEC_ENABLE_VMFUNC | - SECONDARY_EXEC_ENCLS_EXITING; + SECONDARY_EXEC_ENABLE_VMFUNC; + if (cpu_has_sgx()) + opt2 |= SECONDARY_EXEC_ENCLS_EXITING; if (adjust_vmx_controls(min2, opt2, MSR_IA32_VMX_PROCBASED_CTLS2, &_cpu_based_2nd_exec_control) < 0) From 0c22056f8c43265da21a3dfe7b7e1379e5ff7c72 Mon Sep 17 00:00:00 2001 From: Nitesh Narayan Lal Date: Fri, 13 Mar 2020 09:16:24 -0400 Subject: [PATCH 252/256] KVM: x86: Initializing all kvm_lapic_irq fields in ioapic_write_indirect Previously all fields of structure kvm_lapic_irq were not initialized before it was passed to kvm_bitmap_or_dest_vcpus(). Which will cause an issue when any of those fields are used for processing a request. For example not initializing the msi_redir_hint field before passing to the kvm_bitmap_or_dest_vcpus(), may lead to a misbehavior of kvm_apic_map_get_dest_lapic(). This will specifically happen when the kvm_lowest_prio_delivery() returns TRUE due to a non-zero garbage value of msi_redir_hint, which should not happen as the request belongs to APIC fixed delivery mode and we do not want to deliver the interrupt only to the lowest priority candidate. This patch initializes all the fields of kvm_lapic_irq based on the values of ioapic redirect_entry object before passing it on to kvm_bitmap_or_dest_vcpus(). Fixes: 7ee30bc132c6 ("KVM: x86: deliver KVM IOAPIC scan request to target vCPUs") Signed-off-by: Nitesh Narayan Lal Reviewed-by: Vitaly Kuznetsov [Set level to false since the value doesn't really matter. Suggested by Vitaly Kuznetsov. - Paolo] Signed-off-by: Paolo Bonzini --- arch/x86/kvm/ioapic.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 7668fed1ce65..750ff0b29404 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -378,12 +378,15 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) if (e->fields.delivery_mode == APIC_DM_FIXED) { struct kvm_lapic_irq irq; - irq.shorthand = APIC_DEST_NOSHORT; irq.vector = e->fields.vector; irq.delivery_mode = e->fields.delivery_mode << 8; - irq.dest_id = e->fields.dest_id; irq.dest_mode = kvm_lapic_irq_dest_mode(!!e->fields.dest_mode); + irq.level = false; + irq.trig_mode = e->fields.trig_mode; + irq.shorthand = APIC_DEST_NOSHORT; + irq.dest_id = e->fields.dest_id; + irq.msi_redir_hint = false; bitmap_zero(&vcpu_bitmap, 16); kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq, &vcpu_bitmap); From d01fd161e85904064290435f67f4ed59af5daf74 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 11 Mar 2020 11:56:49 +0000 Subject: [PATCH 253/256] irqchip/gic-v3: Workaround Cavium erratum 38539 when reading GICD_TYPER2 Despite the architecture spec requiring that reserved registers in the GIC distributor memory map are RES0 (and thus are not allowed to generate an exception), the Cavium ThunderX (aka TX1) SoC explodes as such: [ 0.000000] GICv3: GIC: Using split EOI/Deactivate mode [ 0.000000] GICv3: 128 SPIs implemented [ 0.000000] GICv3: 0 Extended SPIs implemented [ 0.000000] Internal error: synchronous external abort: 96000210 [#1] SMP [ 0.000000] Modules linked in: [ 0.000000] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.4.0-rc4-00035-g3cf6a3d5725f #7956 [ 0.000000] Hardware name: cavium,thunder-88xx (DT) [ 0.000000] pstate: 60000085 (nZCv daIf -PAN -UAO) [ 0.000000] pc : __raw_readl+0x0/0x8 [ 0.000000] lr : gic_init_bases+0x110/0x560 [ 0.000000] sp : ffff800011243d90 [ 0.000000] x29: ffff800011243d90 x28: 0000000000000000 [ 0.000000] x27: 0000000000000018 x26: 0000000000000002 [ 0.000000] x25: ffff8000116f0000 x24: ffff000fbe6a2c80 [ 0.000000] x23: 0000000000000000 x22: ffff010fdc322b68 [ 0.000000] x21: ffff800010a7a208 x20: 00000000009b0404 [ 0.000000] x19: ffff80001124dad0 x18: 0000000000000010 [ 0.000000] x17: 000000004d8d492b x16: 00000000f67eb9af [ 0.000000] x15: ffffffffffffffff x14: ffff800011249908 [ 0.000000] x13: ffff800091243ae7 x12: ffff800011243af4 [ 0.000000] x11: ffff80001126e000 x10: ffff800011243a70 [ 0.000000] x9 : 00000000ffffffd0 x8 : ffff80001069c828 [ 0.000000] x7 : 0000000000000059 x6 : ffff8000113fb4d1 [ 0.000000] x5 : 0000000000000001 x4 : 0000000000000000 [ 0.000000] x3 : 0000000000000000 x2 : 0000000000000000 [ 0.000000] x1 : 0000000000000000 x0 : ffff8000116f000c [ 0.000000] Call trace: [ 0.000000] __raw_readl+0x0/0x8 [ 0.000000] gic_of_init+0x188/0x224 [ 0.000000] of_irq_init+0x200/0x3cc [ 0.000000] irqchip_init+0x1c/0x40 [ 0.000000] init_IRQ+0x160/0x1d0 [ 0.000000] start_kernel+0x2ec/0x4b8 [ 0.000000] Code: a8c47bfd d65f03c0 d538d080 d65f03c0 (b9400000) when reading the GICv4.1 GICD_TYPER2 register, which is unexpected... Work around it by adding a new quirk for the following variants: ThunderX: CN88xx OCTEON TX: CN83xx, CN81xx OCTEON TX2: CN93xx, CN96xx, CN98xx, CNF95xx* and use this flag to avoid accessing GICD_TYPER2. Note that all reserved registers (including redistributors and ITS) are impacted by this erratum, but that only GICD_TYPER2 has to be worked around so far. Signed-off-by: Marc Zyngier Tested-by: Robert Richter Tested-by: Mark Salter Tested-by: Tim Harvey Acked-by: Catalin Marinas Acked-by: Robert Richter Link: https://lore.kernel.org/r/20191027144234.8395-11-maz@kernel.org Link: https://lore.kernel.org/r/20200311115649.26060-1-maz@kernel.org --- Documentation/arm64/silicon-errata.rst | 2 ++ drivers/irqchip/irq-gic-v3.c | 30 +++++++++++++++++++++++++- 2 files changed, 31 insertions(+), 1 deletion(-) diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index 99b2545455ff..a1563da07b2c 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -108,6 +108,8 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | Cavium | ThunderX GICv3 | #23154 | CAVIUM_ERRATUM_23154 | +----------------+-----------------+-----------------+-----------------------------+ +| Cavium | ThunderX GICv3 | #38539 | N/A | ++----------------+-----------------+-----------------+-----------------------------+ | Cavium | ThunderX Core | #27456 | CAVIUM_ERRATUM_27456 | +----------------+-----------------+-----------------+-----------------------------+ | Cavium | ThunderX Core | #30115 | CAVIUM_ERRATUM_30115 | diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index c1f7af9d9ae7..1eec9d4649d5 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -34,6 +34,7 @@ #define GICD_INT_NMI_PRI (GICD_INT_DEF_PRI & ~0x80) #define FLAGS_WORKAROUND_GICR_WAKER_MSM8996 (1ULL << 0) +#define FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539 (1ULL << 1) struct redist_region { void __iomem *redist_base; @@ -1464,6 +1465,15 @@ static bool gic_enable_quirk_msm8996(void *data) return true; } +static bool gic_enable_quirk_cavium_38539(void *data) +{ + struct gic_chip_data *d = data; + + d->flags |= FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539; + + return true; +} + static bool gic_enable_quirk_hip06_07(void *data) { struct gic_chip_data *d = data; @@ -1502,6 +1512,19 @@ static const struct gic_quirk gic_quirks[] = { .mask = 0xffffffff, .init = gic_enable_quirk_hip06_07, }, + { + /* + * Reserved register accesses generate a Synchronous + * External Abort. This erratum applies to: + * - ThunderX: CN88xx + * - OCTEON TX: CN83xx, CN81xx + * - OCTEON TX2: CN93xx, CN96xx, CN98xx, CNF95xx* + */ + .desc = "GICv3: Cavium erratum 38539", + .iidr = 0xa000034c, + .mask = 0xe8f00fff, + .init = gic_enable_quirk_cavium_38539, + }, { } }; @@ -1577,7 +1600,12 @@ static int __init gic_init_bases(void __iomem *dist_base, pr_info("%d SPIs implemented\n", GIC_LINE_NR - 32); pr_info("%d Extended SPIs implemented\n", GIC_ESPI_NR); - gic_data.rdists.gicd_typer2 = readl_relaxed(gic_data.dist_base + GICD_TYPER2); + /* + * ThunderX1 explodes on reading GICD_TYPER2, in violation of the + * architecture spec (which says that reserved registers are RES0). + */ + if (!(gic_data.flags & FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539)) + gic_data.rdists.gicd_typer2 = readl_relaxed(gic_data.dist_base + GICD_TYPER2); gic_data.domain = irq_domain_create_tree(handle, &gic_irq_domain_ops, &gic_data); From 95fa10103dabc38be5de8efdfced5e67576ed896 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Mon, 9 Mar 2020 16:52:11 +0100 Subject: [PATCH 254/256] KVM: nVMX: avoid NULL pointer dereference with incorrect EVMCS GPAs When an EVMCS enabled L1 guest on KVM will tries doing enlightened VMEnter with EVMCS GPA = 0 the host crashes because the evmcs_gpa != vmx->nested.hv_evmcs_vmptr condition in nested_vmx_handle_enlightened_vmptrld() will evaluate to false (as nested.hv_evmcs_vmptr is zeroed after init). The crash will happen on vmx->nested.hv_evmcs pointer dereference. Another problematic EVMCS ptr value is '-1' but it only causes host crash after nested_release_evmcs() invocation. The problem is exactly the same as with '0', we mistakenly think that the EVMCS pointer hasn't changed and thus nested.hv_evmcs_vmptr is valid. Resolve the issue by adding an additional !vmx->nested.hv_evmcs check to nested_vmx_handle_enlightened_vmptrld(), this way we will always be trying kvm_vcpu_map() when nested.hv_evmcs is NULL and this is supposed to catch all invalid EVMCS GPAs. Also, initialize hv_evmcs_vmptr to '0' in nested_release_evmcs() to be consistent with initialization where we don't currently set hv_evmcs_vmptr to '-1'. Cc: stable@vger.kernel.org Signed-off-by: Vitaly Kuznetsov Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/nested.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index e920d7834d73..9750e590c89d 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -224,7 +224,7 @@ static inline void nested_release_evmcs(struct kvm_vcpu *vcpu) return; kvm_vcpu_unmap(vcpu, &vmx->nested.hv_evmcs_map, true); - vmx->nested.hv_evmcs_vmptr = -1ull; + vmx->nested.hv_evmcs_vmptr = 0; vmx->nested.hv_evmcs = NULL; } @@ -1923,7 +1923,8 @@ static int nested_vmx_handle_enlightened_vmptrld(struct kvm_vcpu *vcpu, if (!nested_enlightened_vmentry(vcpu, &evmcs_gpa)) return 1; - if (unlikely(evmcs_gpa != vmx->nested.hv_evmcs_vmptr)) { + if (unlikely(!vmx->nested.hv_evmcs || + evmcs_gpa != vmx->nested.hv_evmcs_vmptr)) { if (!vmx->nested.hv_evmcs) vmx->nested.current_vmptr = -1ull; From 1da8347d8505c137fb07ff06bbcd3f2bf37409bc Mon Sep 17 00:00:00 2001 From: Megha Dey Date: Sat, 14 Mar 2020 11:39:59 +0800 Subject: [PATCH 255/256] iommu/vt-d: Populate debugfs if IOMMUs are detected Currently, the intel iommu debugfs directory(/sys/kernel/debug/iommu/intel) gets populated only when DMA remapping is enabled (dmar_disabled = 0) irrespective of whether interrupt remapping is enabled or not. Instead, populate the intel iommu debugfs directory if any IOMMUs are detected. Cc: Dan Carpenter Fixes: ee2636b8670b1 ("iommu/vt-d: Enable base Intel IOMMU debugfs support") Signed-off-by: Megha Dey Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel-iommu-debugfs.c | 11 ++++++++++- drivers/iommu/intel-iommu.c | 4 +++- 2 files changed, 13 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/intel-iommu-debugfs.c b/drivers/iommu/intel-iommu-debugfs.c index 0a7791934a16..3eb1fe240fb0 100644 --- a/drivers/iommu/intel-iommu-debugfs.c +++ b/drivers/iommu/intel-iommu-debugfs.c @@ -282,9 +282,16 @@ static int dmar_translation_struct_show(struct seq_file *m, void *unused) { struct dmar_drhd_unit *drhd; struct intel_iommu *iommu; + u32 sts; rcu_read_lock(); for_each_active_iommu(iommu, drhd) { + sts = dmar_readl(iommu->reg + DMAR_GSTS_REG); + if (!(sts & DMA_GSTS_TES)) { + seq_printf(m, "DMA Remapping is not enabled on %s\n", + iommu->name); + continue; + } root_tbl_walk(m, iommu); seq_putc(m, '\n'); } @@ -425,6 +432,7 @@ static int ir_translation_struct_show(struct seq_file *m, void *unused) struct dmar_drhd_unit *drhd; struct intel_iommu *iommu; u64 irta; + u32 sts; rcu_read_lock(); for_each_active_iommu(iommu, drhd) { @@ -434,7 +442,8 @@ static int ir_translation_struct_show(struct seq_file *m, void *unused) seq_printf(m, "Remapped Interrupt supported on IOMMU: %s\n", iommu->name); - if (iommu->ir_table) { + sts = dmar_readl(iommu->reg + DMAR_GSTS_REG); + if (iommu->ir_table && (sts & DMA_GSTS_IRES)) { irta = virt_to_phys(iommu->ir_table->base); seq_printf(m, " IR table address:%llx\n", irta); ir_tbl_remap_entry_show(m, iommu); diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 2943d3600b7c..4be549478691 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -5133,6 +5133,9 @@ int __init intel_iommu_init(void) down_write(&dmar_global_lock); + if (!no_iommu) + intel_iommu_debugfs_init(); + if (no_iommu || dmar_disabled) { /* * We exit the function here to ensure IOMMU's remapping and @@ -5228,7 +5231,6 @@ int __init intel_iommu_init(void) pr_info("Intel(R) Virtualization Technology for Directed I/O\n"); intel_iommu_enabled = 1; - intel_iommu_debugfs_init(); return 0; From fb33c6510d5595144d585aa194d377cf74d31911 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 15 Mar 2020 15:01:23 -0700 Subject: [PATCH 256/256] Linux 5.6-rc6 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index e25db579ce74..171f2b004c8a 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 6 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc6 NAME = Kleptomaniac Octopus # *DOCUMENTATION*