From c2e406596571659451f4b95e37ddfd5a8ef1d0dc Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 2 Sep 2022 14:31:07 +0200 Subject: sched/debug: fix dentry leak in update_sched_domain_debugfs Kuyo reports that the pattern of using debugfs_remove(debugfs_lookup()) leaks a dentry and with a hotplug stress test, the machine eventually runs out of memory. Fix this up by using the newly created debugfs_lookup_and_remove() call instead which properly handles the dentry reference counting logic. Cc: Major Chen Cc: stable Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Juri Lelli Cc: Vincent Guittot Cc: Dietmar Eggemann Cc: Steven Rostedt Cc: Ben Segall Cc: Mel Gorman Cc: Daniel Bristot de Oliveira Cc: Valentin Schneider Cc: Matthias Brugger Reported-by: Kuyo Chang Tested-by: Kuyo Chang Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20220902123107.109274-2-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- kernel/sched/debug.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index bb3d63bdf4ae..667876da8382 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -416,7 +416,7 @@ void update_sched_domain_debugfs(void) char buf[32]; snprintf(buf, sizeof(buf), "cpu%d", cpu); - debugfs_remove(debugfs_lookup(buf, sd_dentry)); + debugfs_lookup_and_remove(buf, sd_dentry); d_cpu = debugfs_create_dir(buf, sd_dentry); i = 0; -- cgit From 85eaeb5058f0f04dffb124c97c86b4f18db0b833 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Wed, 24 Aug 2022 09:10:36 +0300 Subject: IB/core: Fix a nested dead lock as part of ODP flow Fix a nested dead lock as part of ODP flow by using mmput_async(). From the below call trace [1] can see that calling mmput() once we have the umem_odp->umem_mutex locked as required by ib_umem_odp_map_dma_and_lock() might trigger in the same task the exit_mmap()->__mmu_notifier_release()->mlx5_ib_invalidate_range() which may dead lock when trying to lock the same mutex. Moving to use mmput_async() will solve the problem as the above exit_mmap() flow will be called in other task and will be executed once the lock will be available. [1] [64843.077665] task:kworker/u133:2 state:D stack: 0 pid:80906 ppid: 2 flags:0x00004000 [64843.077672] Workqueue: mlx5_ib_page_fault mlx5_ib_eqe_pf_action [mlx5_ib] [64843.077719] Call Trace: [64843.077722] [64843.077724] __schedule+0x23d/0x590 [64843.077729] schedule+0x4e/0xb0 [64843.077735] schedule_preempt_disabled+0xe/0x10 [64843.077740] __mutex_lock.constprop.0+0x263/0x490 [64843.077747] __mutex_lock_slowpath+0x13/0x20 [64843.077752] mutex_lock+0x34/0x40 [64843.077758] mlx5_ib_invalidate_range+0x48/0x270 [mlx5_ib] [64843.077808] __mmu_notifier_release+0x1a4/0x200 [64843.077816] exit_mmap+0x1bc/0x200 [64843.077822] ? walk_page_range+0x9c/0x120 [64843.077828] ? __cond_resched+0x1a/0x50 [64843.077833] ? mutex_lock+0x13/0x40 [64843.077839] ? uprobe_clear_state+0xac/0x120 [64843.077860] mmput+0x5f/0x140 [64843.077867] ib_umem_odp_map_dma_and_lock+0x21b/0x580 [ib_core] [64843.077931] pagefault_real_mr+0x9a/0x140 [mlx5_ib] [64843.077962] pagefault_mr+0xb4/0x550 [mlx5_ib] [64843.077992] pagefault_single_data_segment.constprop.0+0x2ac/0x560 [mlx5_ib] [64843.078022] mlx5_ib_eqe_pf_action+0x528/0x780 [mlx5_ib] [64843.078051] process_one_work+0x22b/0x3d0 [64843.078059] worker_thread+0x53/0x410 [64843.078065] ? process_one_work+0x3d0/0x3d0 [64843.078073] kthread+0x12a/0x150 [64843.078079] ? set_kthread_struct+0x50/0x50 [64843.078085] ret_from_fork+0x22/0x30 [64843.078093] Fixes: 36f30e486dce ("IB/core: Improve ODP to use hmm_range_fault()") Reviewed-by: Maor Gottlieb Signed-off-by: Yishai Hadas Link: https://lore.kernel.org/r/74d93541ea533ef7daec6f126deb1072500aeb16.1661251841.git.leonro@nvidia.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/core/umem_odp.c | 2 +- kernel/fork.c | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c index 186ed8859920..d39e16c211e8 100644 --- a/drivers/infiniband/core/umem_odp.c +++ b/drivers/infiniband/core/umem_odp.c @@ -462,7 +462,7 @@ retry: mutex_unlock(&umem_odp->umem_mutex); out_put_mm: - mmput(owning_mm); + mmput_async(owning_mm); out_put_task: if (owning_process) put_task_struct(owning_process); diff --git a/kernel/fork.c b/kernel/fork.c index 90c85b17bf69..8a9e92068b15 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1225,6 +1225,7 @@ void mmput_async(struct mm_struct *mm) schedule_work(&mm->async_put_work); } } +EXPORT_SYMBOL_GPL(mmput_async); #endif /** -- cgit From baf2c002402702accc30dcc8f19199f303638306 Mon Sep 17 00:00:00 2001 From: Daniel Bristot de Oliveira Date: Tue, 23 Aug 2022 17:20:29 +0200 Subject: rv/monitors: Make monitor's automata definition static Monitor's automata definition is only used locally, so make them static for all existing monitors. Link: https://lore.kernel.org/all/202208210332.gtHXje45-lkp@intel.com Link: https://lore.kernel.org/all/202208210358.6HH3OrVs-lkp@intel.com Link: https://lkml.kernel.org/r/a50e27c3738d6ef809f4201857229fed64799234.1661266564.git.bristot@kernel.org Fixes: ccc319dcb450 ("rv/monitor: Add the wwnr monitor") Fixes: 8812d21219b9 ("rv/monitor: Add the wip monitor skeleton created by dot2k") Reported-by: kernel test robot Signed-off-by: Daniel Bristot de Oliveira Signed-off-by: Steven Rostedt (Google) --- kernel/trace/rv/monitors/wip/wip.h | 2 +- kernel/trace/rv/monitors/wwnr/wwnr.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/rv/monitors/wip/wip.h b/kernel/trace/rv/monitors/wip/wip.h index c1c47e2305ef..dacc37b62a2c 100644 --- a/kernel/trace/rv/monitors/wip/wip.h +++ b/kernel/trace/rv/monitors/wip/wip.h @@ -27,7 +27,7 @@ struct automaton_wip { bool final_states[state_max_wip]; }; -struct automaton_wip automaton_wip = { +static struct automaton_wip automaton_wip = { .state_names = { "preemptive", "non_preemptive" diff --git a/kernel/trace/rv/monitors/wwnr/wwnr.h b/kernel/trace/rv/monitors/wwnr/wwnr.h index d1afe55cdd4c..118e576b91b4 100644 --- a/kernel/trace/rv/monitors/wwnr/wwnr.h +++ b/kernel/trace/rv/monitors/wwnr/wwnr.h @@ -27,7 +27,7 @@ struct automaton_wwnr { bool final_states[state_max_wwnr]; }; -struct automaton_wwnr automaton_wwnr = { +static struct automaton_wwnr automaton_wwnr = { .state_names = { "not_running", "running" -- cgit From 54be5509422ebee333709c92441aa7185ca182fa Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Mon, 29 Aug 2022 10:10:48 -0700 Subject: tracepoint: Allow trace events in modules with TAINT_TEST Commit 2852ca7fba9f ("panic: Taint kernel if tests are run") introduced a new taint type, TAINT_TEST, to signal that an in-kernel test module has been loaded. TAINT_TEST taint type defaults into a 'bad_taint' list for kernel tracing and blocks the creation of trace events. This causes a problem for CXL testing where loading the cxl_test module makes all CXL modules out-of-tree, blocking any trace events. Trace events are in development for CXL at the moment and this issue was found in test with v6.0-rc1. Link: https://lkml.kernel.org/r/20220829171048.263065-1-alison.schofield@intel.com Fixes: 2852ca7fba9f7 ("panic: Taint kernel if tests are run") Reported-by: Ira Weiny Suggested-by: Dan Williams Tested-by: Ira Weiny Reviewed-by: David Gow Signed-off-by: Alison Schofield Signed-off-by: Steven Rostedt (Google) --- kernel/tracepoint.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index 64ea283f2f86..ef42c1a11920 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -571,7 +571,8 @@ static void for_each_tracepoint_range( bool trace_module_has_bad_taint(struct module *mod) { return mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP) | - (1 << TAINT_UNSIGNED_MODULE)); + (1 << TAINT_UNSIGNED_MODULE) | + (1 << TAINT_TEST)); } static BLOCKING_NOTIFIER_HEAD(tracepoint_notify_list); @@ -647,7 +648,7 @@ static int tracepoint_module_coming(struct module *mod) /* * We skip modules that taint the kernel, especially those with different * module headers (for forced load), to make sure we don't cause a crash. - * Staging, out-of-tree, and unsigned GPL modules are fine. + * Staging, out-of-tree, unsigned GPL, and test modules are fine. */ if (trace_module_has_bad_taint(mod)) return 0; -- cgit From 54c3931957f6a6194d5972eccc36d052964b2abe Mon Sep 17 00:00:00 2001 From: Yipeng Zou Date: Thu, 1 Sep 2022 18:45:14 +0800 Subject: tracing: hold caller_addr to hardirq_{enable,disable}_ip Currently, The arguments passing to lockdep_hardirqs_{on,off} was fixed in CALLER_ADDR0. The function trace_hardirqs_on_caller should have been intended to use caller_addr to represent the address that caller wants to be traced. For example, lockdep log in riscv showing the last {enabled,disabled} at __trace_hardirqs_{on,off} all the time(if called by): [ 57.853175] hardirqs last enabled at (2519): __trace_hardirqs_on+0xc/0x14 [ 57.853848] hardirqs last disabled at (2520): __trace_hardirqs_off+0xc/0x14 After use trace_hardirqs_xx_caller, we can get more effective information: [ 53.781428] hardirqs last enabled at (2595): restore_all+0xe/0x66 [ 53.782185] hardirqs last disabled at (2596): ret_from_exception+0xa/0x10 Link: https://lkml.kernel.org/r/20220901104515.135162-2-zouyipeng@huawei.com Cc: stable@vger.kernel.org Fixes: c3bc8fd637a96 ("tracing: Centralize preemptirq tracepoints and unify their usage") Signed-off-by: Yipeng Zou Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_preemptirq.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c index 95b58bd757ce..1e130da1b742 100644 --- a/kernel/trace/trace_preemptirq.c +++ b/kernel/trace/trace_preemptirq.c @@ -95,14 +95,14 @@ __visible void trace_hardirqs_on_caller(unsigned long caller_addr) } lockdep_hardirqs_on_prepare(); - lockdep_hardirqs_on(CALLER_ADDR0); + lockdep_hardirqs_on(caller_addr); } EXPORT_SYMBOL(trace_hardirqs_on_caller); NOKPROBE_SYMBOL(trace_hardirqs_on_caller); __visible void trace_hardirqs_off_caller(unsigned long caller_addr) { - lockdep_hardirqs_off(CALLER_ADDR0); + lockdep_hardirqs_off(caller_addr); if (!this_cpu_read(tracing_irq_cpu)) { this_cpu_write(tracing_irq_cpu, 1); -- cgit From cecf8e128ec69149fe53c9a7bafa505a4bee25d9 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Sun, 4 Sep 2022 13:12:29 +0900 Subject: tracing: Fix to check event_mutex is held while accessing trigger list Since the check_user_trigger() is called outside of RCU read lock, this list_for_each_entry_rcu() caused a suspicious RCU usage warning. # echo hist:keys=pid > events/sched/sched_stat_runtime/trigger # cat events/sched/sched_stat_runtime/trigger [ 43.167032] [ 43.167418] ============================= [ 43.167992] WARNING: suspicious RCU usage [ 43.168567] 5.19.0-rc5-00029-g19ebe4651abf #59 Not tainted [ 43.169283] ----------------------------- [ 43.169863] kernel/trace/trace_events_trigger.c:145 RCU-list traversed in non-reader section!! ... However, this file->triggers list is safe when it is accessed under event_mutex is held. To fix this warning, adds a lockdep_is_held check to the list_for_each_entry_rcu(). Link: https://lkml.kernel.org/r/166226474977.223837.1992182913048377113.stgit@devnote2 Cc: stable@vger.kernel.org Fixes: 7491e2c44278 ("tracing: Add a probe that attaches to trace events") Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_trigger.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index cb866c3141af..918730d74932 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -142,7 +142,8 @@ static bool check_user_trigger(struct trace_event_file *file) { struct event_trigger_data *data; - list_for_each_entry_rcu(data, &file->triggers, list) { + list_for_each_entry_rcu(data, &file->triggers, list, + lockdep_is_held(&event_mutex)) { if (data->flags & EVENT_TRIGGER_FL_PROBE) continue; return true; -- cgit From 93d71986a60c37395e0a1d2f7fe170ef1e0a8ba4 Mon Sep 17 00:00:00 2001 From: Xiu Jianfeng Date: Tue, 6 Sep 2022 22:12:10 +0800 Subject: rv/reactor: add __init/__exit annotations to module init/exit funcs Add missing __init/__exit annotations to module init/exit funcs. Link: https://lkml.kernel.org/r/20220906141210.132607-1-xiujianfeng@huawei.com Fixes: 135b881ea885 ("rv/reactor: Add the printk reactor") Fixes: e88043c0ac16 ("rv/reactor: Add the panic reactor") Signed-off-by: Xiu Jianfeng Acked-by: Daniel Bristot de Oliveira Signed-off-by: Steven Rostedt (Google) --- kernel/trace/rv/reactor_panic.c | 4 ++-- kernel/trace/rv/reactor_printk.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/rv/reactor_panic.c b/kernel/trace/rv/reactor_panic.c index b698d05dd069..d65f6c25a87c 100644 --- a/kernel/trace/rv/reactor_panic.c +++ b/kernel/trace/rv/reactor_panic.c @@ -24,13 +24,13 @@ static struct rv_reactor rv_panic = { .react = rv_panic_reaction }; -static int register_react_panic(void) +static int __init register_react_panic(void) { rv_register_reactor(&rv_panic); return 0; } -static void unregister_react_panic(void) +static void __exit unregister_react_panic(void) { rv_unregister_reactor(&rv_panic); } diff --git a/kernel/trace/rv/reactor_printk.c b/kernel/trace/rv/reactor_printk.c index 31899f953af4..4b6b7106a477 100644 --- a/kernel/trace/rv/reactor_printk.c +++ b/kernel/trace/rv/reactor_printk.c @@ -23,13 +23,13 @@ static struct rv_reactor rv_printk = { .react = rv_printk_reaction }; -static int register_react_printk(void) +static int __init register_react_printk(void) { rv_register_reactor(&rv_printk); return 0; } -static void unregister_react_printk(void) +static void __exit unregister_react_printk(void) { rv_unregister_reactor(&rv_printk); } -- cgit From 81c12e922b97b94f64e84aa9bfe5a9d1fca2dc25 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Wed, 31 Aug 2022 00:38:18 -0600 Subject: Revert "swiotlb: panic if nslabs is too small" This reverts commit 0bf28fc40d89b1a3e00d1b79473bad4e9ca20ad1. Reasons: 1. new panic()s shouldn't be added [1]. 2. It does no "cleanup" but breaks MIPS [2]. v2: properly solved the conflict [3] with commit 20347fca71a38 ("swiotlb: split up the global swiotlb lock") Reported-by: kernel test robot Reported-by: Dan Carpenter [1] https://lore.kernel.org/r/CAHk-=wit-DmhMfQErY29JSPjFgebx_Ld+pnerc4J2Ag990WwAA@mail.gmail.com/ [2] https://lore.kernel.org/r/20220820012031.1285979-1-yuzhao@google.com/ [3] https://lore.kernel.org/r/202208310701.LKr1WDCh-lkp@intel.com/ Fixes: 0bf28fc40d89b ("swiotlb: panic if nslabs is too small") Signed-off-by: Yu Zhao Signed-off-by: Christoph Hellwig --- kernel/dma/swiotlb.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index c5a9190b218f..dd8863987e0c 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -326,9 +326,6 @@ void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags, swiotlb_adjust_nareas(num_possible_cpus()); nslabs = default_nslabs; - if (nslabs < IO_TLB_MIN_SLABS) - panic("%s: nslabs = %lu too small\n", __func__, nslabs); - /* * By default allocate the bounce buffer memory from low memory, but * allow to pick a location everywhere for hypervisors with guest @@ -341,8 +338,7 @@ retry: else tlb = memblock_alloc_low(bytes, PAGE_SIZE); if (!tlb) { - pr_warn("%s: Failed to allocate %zu bytes tlb structure\n", - __func__, bytes); + pr_warn("%s: failed to allocate tlb structure\n", __func__); return; } -- cgit From 2995b8002cefc7b0b00b8f9a0ce36601a8c390c0 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 15 Aug 2022 20:28:40 +0100 Subject: dma-debug: improve search for partial syncs When bucket_find_contains() tries to find the original entry for a partial sync, it manages to constrain its search in a way that is both too restrictive and not restrictive enough. A driver which only uses single mappings rather than scatterlists might not set max_seg_size, but could still technically perform a partial sync at an offset of more than 64KB into a sufficiently large mapping, so we could stop searching too early before reaching a legitimate entry. Conversely, if no valid entry is present and max_range is large enough, we can pointlessly search buckets that we've already searched, or that represent an impossible wrapping around the bottom of the address space. At worst, the (legitimate) case of max_seg_size == UINT_MAX can make the loop infinite. Replace the fragile and frankly hard-to-follow "range" logic with a simple counted loop for the number of possible hash buckets below the given address. Reported-by: Yunfei Wang Signed-off-by: Robin Murphy Signed-off-by: Christoph Hellwig --- kernel/dma/debug.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index 2caafd13f8aa..18c93c2276ca 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -350,11 +350,10 @@ static struct dma_debug_entry *bucket_find_contain(struct hash_bucket **bucket, unsigned long *flags) { - unsigned int max_range = dma_get_max_seg_size(ref->dev); struct dma_debug_entry *entry, index = *ref; - unsigned int range = 0; + int limit = min(HASH_SIZE, (index.dev_addr >> HASH_FN_SHIFT) + 1); - while (range <= max_range) { + for (int i = 0; i < limit; i++) { entry = __hash_bucket_find(*bucket, ref, containing_match); if (entry) @@ -364,7 +363,6 @@ static struct dma_debug_entry *bucket_find_contain(struct hash_bucket **bucket, * Nothing found, go back a hash bucket */ put_hash_bucket(*bucket, *flags); - range += (1 << HASH_FN_SHIFT); index.dev_addr -= (1 << HASH_FN_SHIFT); *bucket = get_hash_bucket(&index, flags); } -- cgit From 3f0461613ebcdc8c4073e235053d06d5aa58750f Mon Sep 17 00:00:00 2001 From: Chao Gao Date: Fri, 19 Aug 2022 16:45:37 +0800 Subject: swiotlb: avoid potential left shift overflow The second operand passed to slot_addr() is declared as int or unsigned int in all call sites. The left-shift to get the offset of a slot can overflow if swiotlb size is larger than 4G. Convert the macro to an inline function and declare the second argument as phys_addr_t to avoid the potential overflow. Fixes: 26a7e094783d ("swiotlb: refactor swiotlb_tbl_map_single") Signed-off-by: Chao Gao Reviewed-by: Dongli Zhang Signed-off-by: Christoph Hellwig --- kernel/dma/swiotlb.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index dd8863987e0c..1ce8977d911c 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -575,7 +575,10 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size } } -#define slot_addr(start, idx) ((start) + ((idx) << IO_TLB_SHIFT)) +static inline phys_addr_t slot_addr(phys_addr_t start, phys_addr_t idx) +{ + return start + (idx << IO_TLB_SHIFT); +} /* * Carefully handle integer overflow which can occur when boundary_mask == ~0UL. -- cgit From 43b919017fe755ccd2b19afb2dc2d3da8f840038 Mon Sep 17 00:00:00 2001 From: Chao Gao Date: Fri, 26 Aug 2022 17:50:46 +0800 Subject: swiotlb: fix a typo "overwirte" isn't a word. It should be "overwrite". Signed-off-by: Chao Gao Signed-off-by: Christoph Hellwig --- kernel/dma/swiotlb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 1ce8977d911c..0ef6b12f961d 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -764,7 +764,7 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, /* * When dir == DMA_FROM_DEVICE we could omit the copy from the orig * to the tlb buffer, if we knew for sure the device will - * overwirte the entire current content. But we don't. Thus + * overwrite the entire current content. But we don't. Thus * unconditional bounce may prevent leaking swiotlb content (i.e. * kernel memory) to user-space. */ -- cgit From 9fc18f6d56d5b79d527c17a8100a0965d18345cf Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 21 Aug 2022 16:06:44 +0200 Subject: dma-mapping: mark dma_supported static Now that the remaining users in drivers are gone, this function can be marked static. Signed-off-by: Christoph Hellwig --- include/linux/dma-mapping.h | 5 ----- kernel/dma/mapping.c | 3 +-- 2 files changed, 1 insertion(+), 7 deletions(-) (limited to 'kernel') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 25a30906289d..0ee20b764000 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -139,7 +139,6 @@ int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs); bool dma_can_mmap(struct device *dev); -int dma_supported(struct device *dev, u64 mask); bool dma_pci_p2pdma_supported(struct device *dev); int dma_set_mask(struct device *dev, u64 mask); int dma_set_coherent_mask(struct device *dev, u64 mask); @@ -248,10 +247,6 @@ static inline bool dma_can_mmap(struct device *dev) { return false; } -static inline int dma_supported(struct device *dev, u64 mask) -{ - return 0; -} static inline bool dma_pci_p2pdma_supported(struct device *dev) { return false; diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 49cbf3e33de7..27f272381cf2 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -707,7 +707,7 @@ int dma_mmap_noncontiguous(struct device *dev, struct vm_area_struct *vma, } EXPORT_SYMBOL_GPL(dma_mmap_noncontiguous); -int dma_supported(struct device *dev, u64 mask) +static int dma_supported(struct device *dev, u64 mask) { const struct dma_map_ops *ops = get_dma_ops(dev); @@ -721,7 +721,6 @@ int dma_supported(struct device *dev, u64 mask) return 1; return ops->dma_supported(dev, mask); } -EXPORT_SYMBOL(dma_supported); bool dma_pci_p2pdma_supported(struct device *dev) { -- cgit From 1efda38d6f9ba26ac88b359c6277f1172db03f1e Mon Sep 17 00:00:00 2001 From: "Christian A. Ehrhardt" Date: Wed, 7 Sep 2022 22:09:17 +0200 Subject: kprobes: Prohibit probes in gate area The system call gate area counts as kernel text but trying to install a kprobe in this area fails with an Oops later on. To fix this explicitly disallow the gate area for kprobes. Found by syzkaller with the following reproducer: perf_event_open$cgroup(&(0x7f00000001c0)={0x6, 0x80, 0x0, 0x0, 0x0, 0x0, 0x80ffff, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, @perf_config_ext={0x0, 0xffffffffff600000}}, 0xffffffffffffffff, 0x0, 0xffffffffffffffff, 0x0) Sample report: BUG: unable to handle page fault for address: fffffbfff3ac6000 PGD 6dfcb067 P4D 6dfcb067 PUD 6df8f067 PMD 6de4d067 PTE 0 Oops: 0000 [#1] PREEMPT SMP KASAN NOPTI CPU: 0 PID: 21978 Comm: syz-executor.2 Not tainted 6.0.0-rc3-00363-g7726d4c3e60b-dirty #6 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 RIP: 0010:__insn_get_emulate_prefix arch/x86/lib/insn.c:91 [inline] RIP: 0010:insn_get_emulate_prefix arch/x86/lib/insn.c:106 [inline] RIP: 0010:insn_get_prefixes.part.0+0xa8/0x1110 arch/x86/lib/insn.c:134 Code: 49 be 00 00 00 00 00 fc ff df 48 8b 40 60 48 89 44 24 08 e9 81 00 00 00 e8 e5 4b 39 ff 4c 89 fa 4c 89 f9 48 c1 ea 03 83 e1 07 <42> 0f b6 14 32 38 ca 7f 08 84 d2 0f 85 06 10 00 00 48 89 d8 48 89 RSP: 0018:ffffc900088bf860 EFLAGS: 00010246 RAX: 0000000000040000 RBX: ffffffff9b9bebc0 RCX: 0000000000000000 RDX: 1ffffffff3ac6000 RSI: ffffc90002d82000 RDI: ffffc900088bf9e8 RBP: ffffffff9d630001 R08: 0000000000000000 R09: ffffc900088bf9e8 R10: 0000000000000000 R11: 0000000000000001 R12: 0000000000000001 R13: ffffffff9d630000 R14: dffffc0000000000 R15: ffffffff9d630000 FS: 00007f63eef63640(0000) GS:ffff88806d000000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: fffffbfff3ac6000 CR3: 0000000029d90005 CR4: 0000000000770ef0 PKRU: 55555554 Call Trace: insn_get_prefixes arch/x86/lib/insn.c:131 [inline] insn_get_opcode arch/x86/lib/insn.c:272 [inline] insn_get_modrm+0x64a/0x7b0 arch/x86/lib/insn.c:343 insn_get_sib+0x29a/0x330 arch/x86/lib/insn.c:421 insn_get_displacement+0x350/0x6b0 arch/x86/lib/insn.c:464 insn_get_immediate arch/x86/lib/insn.c:632 [inline] insn_get_length arch/x86/lib/insn.c:707 [inline] insn_decode+0x43a/0x490 arch/x86/lib/insn.c:747 can_probe+0xfc/0x1d0 arch/x86/kernel/kprobes/core.c:282 arch_prepare_kprobe+0x79/0x1c0 arch/x86/kernel/kprobes/core.c:739 prepare_kprobe kernel/kprobes.c:1160 [inline] register_kprobe kernel/kprobes.c:1641 [inline] register_kprobe+0xb6e/0x1690 kernel/kprobes.c:1603 __register_trace_kprobe kernel/trace/trace_kprobe.c:509 [inline] __register_trace_kprobe+0x26a/0x2d0 kernel/trace/trace_kprobe.c:477 create_local_trace_kprobe+0x1f7/0x350 kernel/trace/trace_kprobe.c:1833 perf_kprobe_init+0x18c/0x280 kernel/trace/trace_event_perf.c:271 perf_kprobe_event_init+0xf8/0x1c0 kernel/events/core.c:9888 perf_try_init_event+0x12d/0x570 kernel/events/core.c:11261 perf_init_event kernel/events/core.c:11325 [inline] perf_event_alloc.part.0+0xf7f/0x36a0 kernel/events/core.c:11619 perf_event_alloc kernel/events/core.c:12059 [inline] __do_sys_perf_event_open+0x4a8/0x2a00 kernel/events/core.c:12157 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x38/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f63ef7efaed Code: 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 f3 0f 1e fa 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 73 01 c3 48 c7 c1 b0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f63eef63028 EFLAGS: 00000246 ORIG_RAX: 000000000000012a RAX: ffffffffffffffda RBX: 00007f63ef90ff80 RCX: 00007f63ef7efaed RDX: 0000000000000000 RSI: ffffffffffffffff RDI: 00000000200001c0 RBP: 00007f63ef86019c R08: 0000000000000000 R09: 0000000000000000 R10: ffffffffffffffff R11: 0000000000000246 R12: 0000000000000000 R13: 0000000000000002 R14: 00007f63ef90ff80 R15: 00007f63eef43000 Modules linked in: CR2: fffffbfff3ac6000 ---[ end trace 0000000000000000 ]--- RIP: 0010:__insn_get_emulate_prefix arch/x86/lib/insn.c:91 [inline] RIP: 0010:insn_get_emulate_prefix arch/x86/lib/insn.c:106 [inline] RIP: 0010:insn_get_prefixes.part.0+0xa8/0x1110 arch/x86/lib/insn.c:134 Code: 49 be 00 00 00 00 00 fc ff df 48 8b 40 60 48 89 44 24 08 e9 81 00 00 00 e8 e5 4b 39 ff 4c 89 fa 4c 89 f9 48 c1 ea 03 83 e1 07 <42> 0f b6 14 32 38 ca 7f 08 84 d2 0f 85 06 10 00 00 48 89 d8 48 89 RSP: 0018:ffffc900088bf860 EFLAGS: 00010246 RAX: 0000000000040000 RBX: ffffffff9b9bebc0 RCX: 0000000000000000 RDX: 1ffffffff3ac6000 RSI: ffffc90002d82000 RDI: ffffc900088bf9e8 RBP: ffffffff9d630001 R08: 0000000000000000 R09: ffffc900088bf9e8 R10: 0000000000000000 R11: 0000000000000001 R12: 0000000000000001 R13: ffffffff9d630000 R14: dffffc0000000000 R15: ffffffff9d630000 FS: 00007f63eef63640(0000) GS:ffff88806d000000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: fffffbfff3ac6000 CR3: 0000000029d90005 CR4: 0000000000770ef0 PKRU: 55555554 ================================================================== Link: https://lkml.kernel.org/r/20220907200917.654103-1-lk@c--e.de cc: "Naveen N. Rao" cc: Anil S Keshavamurthy cc: "David S. Miller" Cc: stable@vger.kernel.org Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Acked-by: Masami Hiramatsu (Google) Signed-off-by: Christian A. Ehrhardt Signed-off-by: Steven Rostedt (Google) --- kernel/kprobes.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 08350e35aba2..ca9d834d0b84 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1562,6 +1562,7 @@ static int check_kprobe_address_safe(struct kprobe *p, /* Ensure it is not in reserved area nor out of text */ if (!(core_kernel_text((unsigned long) p->addr) || is_module_text_address((unsigned long) p->addr)) || + in_gate_area_no_mm((unsigned long) p->addr) || within_kprobe_blacklist((unsigned long) p->addr) || jump_label_text_reserved(p->addr, p->addr) || static_call_text_reserved(p->addr, p->addr) || -- cgit