From cb6aeeb69af06b09e687fbef4da36a81c36b4994 Mon Sep 17 00:00:00 2001 From: Saurabh Sengar Date: Mon, 24 Apr 2023 03:10:16 -0700 Subject: [PATCH 01/34] x86/hyperv/vtl: Add noop for realmode pointers Assign the realmode pointers to noop, instead of NULL to fix kernel panic. Signed-off-by: Saurabh Sengar Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/1682331016-22561-1-git-send-email-ssengar@linux.microsoft.com Signed-off-by: Wei Liu --- arch/x86/hyperv/hv_vtl.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c index 1ba5d3b99b16..85d38b9f3586 100644 --- a/arch/x86/hyperv/hv_vtl.c +++ b/arch/x86/hyperv/hv_vtl.c @@ -20,6 +20,8 @@ void __init hv_vtl_init_platform(void) { pr_info("Linux runs in Hyper-V Virtual Trust Level\n"); + x86_platform.realmode_reserve = x86_init_noop; + x86_platform.realmode_init = x86_init_noop; x86_init.irqs.pre_vector_init = x86_init_noop; x86_init.timers.timer_init = x86_init_noop; From ec97e112985c2581ee61854a4b74f080f6cdfc2c Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Thu, 4 May 2023 15:41:55 -0700 Subject: [PATCH 02/34] Drivers: hv: vmbus: Call hv_synic_free() if hv_synic_alloc() fails Commit 572086325ce9 ("Drivers: hv: vmbus: Cleanup synic memory free path") says "Any memory allocations that succeeded will be freed when the caller cleans up by calling hv_synic_free()", but if the get_zeroed_page() in hv_synic_alloc() fails, currently hv_synic_free() is not really called in vmbus_bus_init(), consequently there will be a memory leak, e.g. hv_context.hv_numa_map is not freed in the error path. Fix this by updating the goto labels. Cc: stable@kernel.org Signed-off-by: Dexuan Cui Fixes: 4df4cb9e99f8 ("x86/hyperv: Initialize clockevents earlier in CPU onlining") Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20230504224155.10484-1-decui@microsoft.com Signed-off-by: Wei Liu --- drivers/hv/vmbus_drv.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 1c65a6dfb9fa..67f95a29aeca 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -1372,7 +1372,7 @@ static int vmbus_bus_init(void) ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "hyperv/vmbus:online", hv_synic_init, hv_synic_cleanup); if (ret < 0) - goto err_cpuhp; + goto err_alloc; hyperv_cpuhp_online = ret; ret = vmbus_connect(); @@ -1392,9 +1392,8 @@ static int vmbus_bus_init(void) err_connect: cpuhp_remove_state(hyperv_cpuhp_online); -err_cpuhp: - hv_synic_free(); err_alloc: + hv_synic_free(); if (vmbus_irq == -1) { hv_remove_vmbus_handler(); } else { From 320805ab61e5f1e2a5729ae266e16bec2904050c Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Thu, 18 May 2023 08:13:52 -0700 Subject: [PATCH 03/34] Drivers: hv: vmbus: Fix vmbus_wait_for_unload() to scan present CPUs vmbus_wait_for_unload() may be called in the panic path after other CPUs are stopped. vmbus_wait_for_unload() currently loops through online CPUs looking for the UNLOAD response message. But the values of CONFIG_KEXEC_CORE and crash_kexec_post_notifiers affect the path used to stop the other CPUs, and in one of the paths the stopped CPUs are removed from cpu_online_mask. This removal happens in both x86/x64 and arm64 architectures. In such a case, vmbus_wait_for_unload() only checks the panic'ing CPU, and misses the UNLOAD response message except when the panic'ing CPU is CPU 0. vmbus_wait_for_unload() eventually times out, but only after waiting 100 seconds. Fix this by looping through *present* CPUs in vmbus_wait_for_unload(). The cpu_present_mask is not modified by stopping the other CPUs in the panic path, nor should it be. Also, in a CoCo VM the synic_message_page is not allocated in hv_synic_alloc(), but is set and cleared in hv_synic_enable_regs() and hv_synic_disable_regs() such that it is set only when the CPU is online. If not all present CPUs are online when vmbus_wait_for_unload() is called, the synic_message_page might be NULL. Add a check for this. Fixes: cd95aad55793 ("Drivers: hv: vmbus: handle various crash scenarios") Cc: stable@vger.kernel.org Reported-by: John Starks Signed-off-by: Michael Kelley Reviewed-by: Vitaly Kuznetsov Link: https://lore.kernel.org/r/1684422832-38476-1-git-send-email-mikelley@microsoft.com Signed-off-by: Wei Liu --- drivers/hv/channel_mgmt.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index 007f26d5f1a4..2f4d09ce027a 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -829,11 +829,22 @@ static void vmbus_wait_for_unload(void) if (completion_done(&vmbus_connection.unload_event)) goto completed; - for_each_online_cpu(cpu) { + for_each_present_cpu(cpu) { struct hv_per_cpu_context *hv_cpu = per_cpu_ptr(hv_context.cpu_context, cpu); + /* + * In a CoCo VM the synic_message_page is not allocated + * in hv_synic_alloc(). Instead it is set/cleared in + * hv_synic_enable_regs() and hv_synic_disable_regs() + * such that it is set only when the CPU is online. If + * not all present CPUs are online, the message page + * might be NULL, so skip such CPUs. + */ page_addr = hv_cpu->synic_message_page; + if (!page_addr) + continue; + msg = (struct hv_message *)page_addr + VMBUS_MESSAGE_SINT; @@ -867,11 +878,14 @@ completed: * maybe-pending messages on all CPUs to be able to receive new * messages after we reconnect. */ - for_each_online_cpu(cpu) { + for_each_present_cpu(cpu) { struct hv_per_cpu_context *hv_cpu = per_cpu_ptr(hv_context.cpu_context, cpu); page_addr = hv_cpu->synic_message_page; + if (!page_addr) + continue; + msg = (struct hv_message *)page_addr + VMBUS_MESSAGE_SINT; msg->header.message_type = HVMSG_NONE; } From aafbb1eeabdc4e9241b400146f77369f041ec11b Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Mon, 29 May 2023 04:40:02 -0400 Subject: [PATCH 04/34] tracing/rv/rtla: Update MAINTAINERS file to point to proper mailing list The mailing list that goes to linux-trace-devel is for the tracing libraries, and the patchwork associated to the tracing libraries keys off of that mailing list. For anything that lives in the Linux kernel proper (including the tools directory) must go through linux-trace-kernel, as the patchwork to that list keys off of the Linux kernel proper. Update the MAINTAINERS file to reflect the proper mailing lists. Link: https://lore.kernel.org/linux-trace-kernel/20230529044002.0481452b@rorschach.local.home Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Daniel Bristot de Oliveira Signed-off-by: Steven Rostedt (Google) Acked-by: Daniel Bristot de Oliveira --- MAINTAINERS | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 27ef11624748..725d35b5d328 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -17806,7 +17806,7 @@ F: tools/testing/selftests/rtc/ Real-time Linux Analysis (RTLA) tools M: Daniel Bristot de Oliveira M: Steven Rostedt -L: linux-trace-devel@vger.kernel.org +L: linux-trace-kernel@vger.kernel.org S: Maintained F: Documentation/tools/rtla/ F: tools/tracing/rtla/ @@ -18368,7 +18368,7 @@ F: drivers/infiniband/ulp/rtrs/ RUNTIME VERIFICATION (RV) M: Daniel Bristot de Oliveira M: Steven Rostedt -L: linux-trace-devel@vger.kernel.org +L: linux-trace-kernel@vger.kernel.org S: Maintained F: Documentation/trace/rv/ F: include/linux/rv.h From ba470eebc2f6c2f704872955a715b9555328e7d0 Mon Sep 17 00:00:00 2001 From: sunliming Date: Mon, 29 May 2023 11:21:00 +0800 Subject: [PATCH 05/34] tracing/user_events: Prevent same name but different args event User processes register name_args for events. If the same name but different args event are registered. The trace outputs of second event are printed as the first event. This is incorrect. Return EADDRINUSE back to the user process if the same name but different args event has being registered. Link: https://lore.kernel.org/linux-trace-kernel/20230529032100.286534-1-sunliming@kylinos.cn Signed-off-by: sunliming Reviewed-by: Masami Hiramatsu (Google) Acked-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_user.c | 36 +++++++++++++++---- .../selftests/user_events/ftrace_test.c | 6 ++++ 2 files changed, 36 insertions(+), 6 deletions(-) diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index dbb14705d0d3..37a38496a6be 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -1786,6 +1786,8 @@ static int user_event_parse(struct user_event_group *group, char *name, int ret; u32 key; struct user_event *user; + int argc = 0; + char **argv; /* Prevent dyn_event from racing */ mutex_lock(&event_mutex); @@ -1793,13 +1795,35 @@ static int user_event_parse(struct user_event_group *group, char *name, mutex_unlock(&event_mutex); if (user) { - *newuser = user; - /* - * Name is allocated by caller, free it since it already exists. - * Caller only worries about failure cases for freeing. - */ - kfree(name); + if (args) { + argv = argv_split(GFP_KERNEL, args, &argc); + if (!argv) { + ret = -ENOMEM; + goto error; + } + + ret = user_fields_match(user, argc, (const char **)argv); + argv_free(argv); + + } else + ret = list_empty(&user->fields); + + if (ret) { + *newuser = user; + /* + * Name is allocated by caller, free it since it already exists. + * Caller only worries about failure cases for freeing. + */ + kfree(name); + } else { + ret = -EADDRINUSE; + goto error; + } + return 0; +error: + refcount_dec(&user->refcnt); + return ret; } user = kzalloc(sizeof(*user), GFP_KERNEL_ACCOUNT); diff --git a/tools/testing/selftests/user_events/ftrace_test.c b/tools/testing/selftests/user_events/ftrace_test.c index 7c99cef94a65..6e8c4b47281c 100644 --- a/tools/testing/selftests/user_events/ftrace_test.c +++ b/tools/testing/selftests/user_events/ftrace_test.c @@ -228,6 +228,12 @@ TEST_F(user, register_events) { ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); ASSERT_EQ(0, reg.write_index); + /* Multiple registers to same name but different args should fail */ + reg.enable_bit = 29; + reg.name_args = (__u64)"__test_event u32 field1;"; + ASSERT_EQ(-1, ioctl(self->data_fd, DIAG_IOCSREG, ®)); + ASSERT_EQ(EADDRINUSE, errno); + /* Ensure disabled */ self->enable_fd = open(enable_file, O_RDWR); ASSERT_NE(-1, self->enable_fd); From cfac4ed7279d056df6167bd665e460787dc9e0c4 Mon Sep 17 00:00:00 2001 From: sunliming Date: Mon, 29 May 2023 14:51:10 +0800 Subject: [PATCH 06/34] tracing/user_events: Handle matching arguments that is null from dyn_events When A registering user event from dyn_events has no argments, it will pass the matching check, regardless of whether there is a user event with the same name and arguments. Add the matching check when the arguments of registering user event is null. Link: https://lore.kernel.org/linux-trace-kernel/20230529065110.303440-1-sunliming@kylinos.cn Signed-off-by: sunliming Acked-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_user.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index 37a38496a6be..afe61dc86543 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -1745,6 +1745,8 @@ static bool user_event_match(const char *system, const char *event, if (match && argc > 0) match = user_fields_match(user, argc, argv); + else if (match && argc == 0) + match = list_empty(&user->fields); return match; } From e70bb54d7a51299e7feca9169c07d79f9a3fc01d Mon Sep 17 00:00:00 2001 From: sunliming Date: Thu, 25 May 2023 16:52:32 +0800 Subject: [PATCH 07/34] tracing: Modify print_fields() for fields output order Now the print_fields() print trace event fields in reverse order. Modify it to the positive sequence. Example outputs for a user event: test0 u32 count1; u32 count2 Output before: example-2547 [000] ..... 325.666387: test0: count2=0x2 (2) count1=0x1 (1) Output after: example-2742 [002] ..... 429.769370: test0: count1=0x1 (1) count2=0x2 (2) Link: https://lore.kernel.org/linux-trace-kernel/20230525085232.5096-1-sunliming@kylinos.cn Fixes: 80a76994b2d88 ("tracing: Add "fields" option to show raw trace event fields") Signed-off-by: sunliming Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_output.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 15f05faaae44..1e33f367783e 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -847,7 +847,7 @@ static void print_fields(struct trace_iterator *iter, struct trace_event_call *c int ret; void *pos; - list_for_each_entry(field, head, link) { + list_for_each_entry_reverse(field, head, link) { trace_seq_printf(&iter->seq, " %s=", field->name); if (field->offset + field->size > iter->ent_size) { trace_seq_puts(&iter->seq, ""); From 6f05dcabe5c241d066ec472cf38ac8b84f8c9c6f Mon Sep 17 00:00:00 2001 From: sunliming Date: Tue, 6 Jun 2023 14:20:24 +0800 Subject: [PATCH 08/34] tracing/user_events: Fix the incorrect trace record for empty arguments events The user_events support events that has empty arguments. But the trace event is discarded and not really committed when the arguments is empty. Fix this by not attempting to copy in zero-length data. Link: https://lkml.kernel.org/r/20230606062027.1008398-2-sunliming@kylinos.cn Acked-by: Beau Belgrave Acked-by: Masami Hiramatsu (Google) Signed-off-by: sunliming Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_user.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index afe61dc86543..49914b6cb651 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -1432,7 +1432,7 @@ static void user_event_ftrace(struct user_event *user, struct iov_iter *i, if (unlikely(!entry)) return; - if (unlikely(!copy_nofault(entry + 1, i->count, i))) + if (unlikely(i->count != 0 && !copy_nofault(entry + 1, i->count, i))) goto discard; if (!list_empty(&user->validators) && @@ -1473,7 +1473,7 @@ static void user_event_perf(struct user_event *user, struct iov_iter *i, perf_fetch_caller_regs(regs); - if (unlikely(!copy_nofault(perf_entry + 1, i->count, i))) + if (unlikely(i->count != 0 && !copy_nofault(perf_entry + 1, i->count, i))) goto discard; if (!list_empty(&user->validators) && From 3e7269dd5fd5e77c215829e80fc1f29c989c9c42 Mon Sep 17 00:00:00 2001 From: sunliming Date: Tue, 6 Jun 2023 14:20:25 +0800 Subject: [PATCH 09/34] selftests/user_events: Add ftrace self-test for empty arguments events Tests to ensure events that has empty arguments can input trace record correctly when using ftrace. Link: https://lkml.kernel.org/r/20230606062027.1008398-3-sunliming@kylinos.cn Acked-by: Beau Belgrave Acked-by: Masami Hiramatsu (Google) Signed-off-by: sunliming Signed-off-by: Steven Rostedt (Google) --- .../selftests/user_events/ftrace_test.c | 33 +++++++++++++++++++ 1 file changed, 33 insertions(+) diff --git a/tools/testing/selftests/user_events/ftrace_test.c b/tools/testing/selftests/user_events/ftrace_test.c index 6e8c4b47281c..abfb49558a26 100644 --- a/tools/testing/selftests/user_events/ftrace_test.c +++ b/tools/testing/selftests/user_events/ftrace_test.c @@ -316,6 +316,39 @@ TEST_F(user, write_events) { ASSERT_EQ(EINVAL, errno); } +TEST_F(user, write_empty_events) { + struct user_reg reg = {0}; + struct iovec io[1]; + int before = 0, after = 0; + + reg.size = sizeof(reg); + reg.name_args = (__u64)"__test_event"; + reg.enable_bit = 31; + reg.enable_addr = (__u64)&self->check; + reg.enable_size = sizeof(self->check); + + io[0].iov_base = ®.write_index; + io[0].iov_len = sizeof(reg.write_index); + + /* Register should work */ + ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); + ASSERT_EQ(0, reg.write_index); + ASSERT_EQ(0, self->check); + + /* Enable event */ + self->enable_fd = open(enable_file, O_RDWR); + ASSERT_NE(-1, write(self->enable_fd, "1", sizeof("1"))) + + /* Event should now be enabled */ + ASSERT_EQ(1 << reg.enable_bit, self->check); + + /* Write should make it out to ftrace buffers */ + before = trace_bytes(); + ASSERT_NE(-1, writev(self->data_fd, (const struct iovec *)io, 1)); + after = trace_bytes(); + ASSERT_GT(after, before); +} + TEST_F(user, write_fault) { struct user_reg reg = {0}; struct iovec io[2]; From 4b56c21b11dcd2c6e4c6ee81bde77bea05e64db0 Mon Sep 17 00:00:00 2001 From: sunliming Date: Tue, 6 Jun 2023 14:20:26 +0800 Subject: [PATCH 10/34] selftests/user_events: Clear the events after perf self-test When the self test is completed, perf self-test left the user events not to be cleared. Clear the events by unregister and delete the event. Link: https://lkml.kernel.org/r/20230606062027.1008398-4-sunliming@kylinos.cn Acked-by: Beau Belgrave Acked-by: Masami Hiramatsu (Google) Signed-off-by: sunliming Signed-off-by: Steven Rostedt (Google) --- .../testing/selftests/user_events/perf_test.c | 29 +++++++++++++++++++ 1 file changed, 29 insertions(+) diff --git a/tools/testing/selftests/user_events/perf_test.c b/tools/testing/selftests/user_events/perf_test.c index a070258d4449..e97f24ab6e2f 100644 --- a/tools/testing/selftests/user_events/perf_test.c +++ b/tools/testing/selftests/user_events/perf_test.c @@ -81,6 +81,32 @@ static int get_offset(void) return offset; } +static int clear(int *check) +{ + struct user_unreg unreg = {0}; + + unreg.size = sizeof(unreg); + unreg.disable_bit = 31; + unreg.disable_addr = (__u64)check; + + int fd = open(data_file, O_RDWR); + + if (fd == -1) + return -1; + + if (ioctl(fd, DIAG_IOCSUNREG, &unreg) == -1) + if (errno != ENOENT) + return -1; + + if (ioctl(fd, DIAG_IOCSDEL, "__test_event") == -1) + if (errno != ENOENT) + return -1; + + close(fd); + + return 0; +} + FIXTURE(user) { int data_fd; int check; @@ -93,6 +119,9 @@ FIXTURE_SETUP(user) { FIXTURE_TEARDOWN(user) { close(self->data_fd); + + if (clear(&self->check) != 0) + printf("WARNING: Clear didn't work!\n"); } TEST_F(user, perf_write) { From 42187bdc3ca45435bec96c66a90276315b2db1cb Mon Sep 17 00:00:00 2001 From: sunliming Date: Tue, 6 Jun 2023 14:20:27 +0800 Subject: [PATCH 11/34] selftests/user_events: Add perf self-test for empty arguments events Tests to ensure events that has empty arguments can input trace record correctly when using perf. Link: https://lkml.kernel.org/r/20230606062027.1008398-5-sunliming@kylinos.cn Acked-by: Beau Belgrave Acked-by: Masami Hiramatsu (Google) Signed-off-by: sunliming Signed-off-by: Steven Rostedt (Google) --- .../testing/selftests/user_events/perf_test.c | 53 +++++++++++++++++++ 1 file changed, 53 insertions(+) diff --git a/tools/testing/selftests/user_events/perf_test.c b/tools/testing/selftests/user_events/perf_test.c index e97f24ab6e2f..8b09be566fa2 100644 --- a/tools/testing/selftests/user_events/perf_test.c +++ b/tools/testing/selftests/user_events/perf_test.c @@ -189,6 +189,59 @@ TEST_F(user, perf_write) { ASSERT_EQ(0, self->check); } +TEST_F(user, perf_empty_events) { + struct perf_event_attr pe = {0}; + struct user_reg reg = {0}; + struct perf_event_mmap_page *perf_page; + int page_size = sysconf(_SC_PAGESIZE); + int id, fd; + __u32 *val; + + reg.size = sizeof(reg); + reg.name_args = (__u64)"__test_event"; + reg.enable_bit = 31; + reg.enable_addr = (__u64)&self->check; + reg.enable_size = sizeof(self->check); + + /* Register should work */ + ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); + ASSERT_EQ(0, reg.write_index); + ASSERT_EQ(0, self->check); + + /* Id should be there */ + id = get_id(); + ASSERT_NE(-1, id); + + pe.type = PERF_TYPE_TRACEPOINT; + pe.size = sizeof(pe); + pe.config = id; + pe.sample_type = PERF_SAMPLE_RAW; + pe.sample_period = 1; + pe.wakeup_events = 1; + + /* Tracepoint attach should work */ + fd = perf_event_open(&pe, 0, -1, -1, 0); + ASSERT_NE(-1, fd); + + perf_page = mmap(NULL, page_size * 2, PROT_READ, MAP_SHARED, fd, 0); + ASSERT_NE(MAP_FAILED, perf_page); + + /* Status should be updated */ + ASSERT_EQ(1 << reg.enable_bit, self->check); + + /* Ensure write shows up at correct offset */ + ASSERT_NE(-1, write(self->data_fd, ®.write_index, + sizeof(reg.write_index))); + val = (void *)(((char *)perf_page) + perf_page->data_offset); + ASSERT_EQ(PERF_RECORD_SAMPLE, *val); + + munmap(perf_page, page_size * 2); + close(fd); + + /* Status should be updated */ + ASSERT_EQ(0, self->check); +} + int main(int argc, char **argv) { return test_harness_run(argc, argv); From ed0e0ae0c932188654422d01f4e0ea14ff97c063 Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Thu, 1 Jun 2023 15:49:28 -0700 Subject: [PATCH 12/34] tracing/user_events: Remove user_ns walk for groups During discussions it was suggested that user_ns is not a good place to try to attach a tracing namespace. The current code has stubs to enable that work that are very likely to change and incur a performance cost. Remove the user_ns walk when creating a group and determining the system name to use, since it's unlikely user_ns will be used in the future. Link: https://lore.kernel.org/all/20230601-urenkel-holzofen-cd9403b9cadd@brauner/ Link: https://lore.kernel.org/linux-trace-kernel/20230601224928.301-1-beaub@linux.microsoft.com Suggested-by: Christian Brauner Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_user.c | 42 ++++---------------------------- 1 file changed, 5 insertions(+), 37 deletions(-) diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index 49914b6cb651..cf6d4c02c363 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -182,21 +182,11 @@ static void user_event_group_destroy(struct user_event_group *group) kfree(group); } -static char *user_event_group_system_name(struct user_namespace *user_ns) +static char *user_event_group_system_name(void) { char *system_name; int len = sizeof(USER_EVENTS_SYSTEM) + 1; - if (user_ns != &init_user_ns) { - /* - * Unexpected at this point: - * We only currently support init_user_ns. - * When we enable more, this will trigger a failure so log. - */ - pr_warn("user_events: Namespace other than init_user_ns!\n"); - return NULL; - } - system_name = kmalloc(len, GFP_KERNEL); if (!system_name) @@ -207,34 +197,12 @@ static char *user_event_group_system_name(struct user_namespace *user_ns) return system_name; } -static inline struct user_event_group -*user_event_group_from_user_ns(struct user_namespace *user_ns) -{ - if (user_ns == &init_user_ns) - return init_group; - - return NULL; -} - static struct user_event_group *current_user_event_group(void) { - struct user_namespace *user_ns = current_user_ns(); - struct user_event_group *group = NULL; - - while (user_ns) { - group = user_event_group_from_user_ns(user_ns); - - if (group) - break; - - user_ns = user_ns->parent; - } - - return group; + return init_group; } -static struct user_event_group -*user_event_group_create(struct user_namespace *user_ns) +static struct user_event_group *user_event_group_create(void) { struct user_event_group *group; @@ -243,7 +211,7 @@ static struct user_event_group if (!group) return NULL; - group->system_name = user_event_group_system_name(user_ns); + group->system_name = user_event_group_system_name(); if (!group->system_name) goto error; @@ -2603,7 +2571,7 @@ static int __init trace_events_user_init(void) if (!fault_cache) return -ENOMEM; - init_group = user_event_group_create(&init_user_ns); + init_group = user_event_group_create(); if (!init_group) { kmem_cache_destroy(fault_cache); From b08d72580584ab89c41d6fc0f15cd1cf4ce2ed93 Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Wed, 14 Jun 2023 09:33:31 -0700 Subject: [PATCH 13/34] tracing/user_events: Store register flags on events Currently we don't have any available flags for user processes to use to indicate options for user_events. We will soon have a flag to indicate the event should or should not auto-delete once it's not being used by anyone. Add a reg_flags field to user_events and parameters to existing functions to allow for this in future patches. Link: https://lkml.kernel.org/r/20230614163336.5797-2-beaub@linux.microsoft.com Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_user.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index cf6d4c02c363..629823e21447 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -87,6 +87,7 @@ struct user_event { struct list_head validators; refcount_t refcnt; int min_size; + int reg_flags; char status; }; @@ -165,7 +166,7 @@ typedef void (*user_event_func_t) (struct user_event *user, struct iov_iter *i, static int user_event_parse(struct user_event_group *group, char *name, char *args, char *flags, - struct user_event **newuser); + struct user_event **newuser, int reg_flags); static struct user_event_mm *user_event_mm_get(struct user_event_mm *mm); static struct user_event_mm *user_event_mm_get_all(struct user_event *user); @@ -810,7 +811,8 @@ static struct list_head *user_event_get_fields(struct trace_event_call *call) * Upon success user_event has its ref count increased by 1. */ static int user_event_parse_cmd(struct user_event_group *group, - char *raw_command, struct user_event **newuser) + char *raw_command, struct user_event **newuser, + int reg_flags) { char *name = raw_command; char *args = strpbrk(name, " "); @@ -824,7 +826,7 @@ static int user_event_parse_cmd(struct user_event_group *group, if (flags) *flags++ = '\0'; - return user_event_parse(group, name, args, flags, newuser); + return user_event_parse(group, name, args, flags, newuser, reg_flags); } static int user_field_array_size(const char *type) @@ -1588,7 +1590,7 @@ static int user_event_create(const char *raw_command) mutex_lock(&group->reg_mutex); - ret = user_event_parse_cmd(group, name, &user); + ret = user_event_parse_cmd(group, name, &user, 0); if (!ret) refcount_dec(&user->refcnt); @@ -1751,7 +1753,7 @@ static int user_event_trace_register(struct user_event *user) */ static int user_event_parse(struct user_event_group *group, char *name, char *args, char *flags, - struct user_event **newuser) + struct user_event **newuser, int reg_flags) { int ret; u32 key; @@ -1846,6 +1848,8 @@ error: if (ret) goto put_user_lock; + user->reg_flags = reg_flags; + /* Ensure we track self ref and caller ref (2) */ refcount_set(&user->refcnt, 2); @@ -2144,7 +2148,7 @@ static long user_events_ioctl_reg(struct user_event_file_info *info, return ret; } - ret = user_event_parse_cmd(info->group, name, &user); + ret = user_event_parse_cmd(info->group, name, &user, reg.flags); if (ret) { kfree(name); From f0dbf6fd0bddb9290c89fdd7afc53dad5051030e Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Wed, 14 Jun 2023 09:33:32 -0700 Subject: [PATCH 14/34] tracing/user_events: Track refcount consistently via put/get Various parts of the code today track user_event's refcnt field directly via a refcount_add/dec. This makes it hard to modify the behavior of the last reference decrement in all code paths consistently. For example, in the future we will auto-delete events upon the last reference going away. This last reference could happen in many places, but we want it to be consistently handled. Add user_event_get() and user_event_put() for the add/dec. Update all places where direct refcounts are being used to utilize these new functions. In each location pass if event_mutex is locked or not. This allows us to drop events automatically in future patches clearly. Ensure when caller states the lock is held, it really is (or is not) held. Link: https://lkml.kernel.org/r/20230614163336.5797-3-beaub@linux.microsoft.com Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_user.c | 69 +++++++++++++++++++------------- 1 file changed, 41 insertions(+), 28 deletions(-) diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index 629823e21447..c064458eea5c 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -177,6 +177,28 @@ static u32 user_event_key(char *name) return jhash(name, strlen(name), 0); } +static struct user_event *user_event_get(struct user_event *user) +{ + refcount_inc(&user->refcnt); + + return user; +} + +static void user_event_put(struct user_event *user, bool locked) +{ +#ifdef CONFIG_LOCKDEP + if (locked) + lockdep_assert_held(&event_mutex); + else + lockdep_assert_not_held(&event_mutex); +#endif + + if (unlikely(!user)) + return; + + refcount_dec(&user->refcnt); +} + static void user_event_group_destroy(struct user_event_group *group) { kfree(group->system_name); @@ -228,12 +250,13 @@ error: return NULL; }; -static void user_event_enabler_destroy(struct user_event_enabler *enabler) +static void user_event_enabler_destroy(struct user_event_enabler *enabler, + bool locked) { list_del_rcu(&enabler->mm_enablers_link); /* No longer tracking the event via the enabler */ - refcount_dec(&enabler->event->refcnt); + user_event_put(enabler->event, locked); kfree(enabler); } @@ -295,7 +318,7 @@ static void user_event_enabler_fault_fixup(struct work_struct *work) /* User asked for enabler to be removed during fault */ if (test_bit(ENABLE_VAL_FREEING_BIT, ENABLE_BITOPS(enabler))) { - user_event_enabler_destroy(enabler); + user_event_enabler_destroy(enabler, true); goto out; } @@ -470,14 +493,12 @@ static bool user_event_enabler_dup(struct user_event_enabler *orig, if (!enabler) return false; - enabler->event = orig->event; + enabler->event = user_event_get(orig->event); enabler->addr = orig->addr; /* Only dup part of value (ignore future flags, etc) */ enabler->values = orig->values & ENABLE_VAL_DUP_MASK; - refcount_inc(&enabler->event->refcnt); - /* Enablers not exposed yet, RCU not required */ list_add(&enabler->mm_enablers_link, &mm->enablers); @@ -594,7 +615,7 @@ static void user_event_mm_destroy(struct user_event_mm *mm) struct user_event_enabler *enabler, *next; list_for_each_entry_safe(enabler, next, &mm->enablers, mm_enablers_link) - user_event_enabler_destroy(enabler); + user_event_enabler_destroy(enabler, false); mmdrop(mm->mm); kfree(mm); @@ -749,7 +770,7 @@ retry: * exit or run exec(), which includes forks and clones. */ if (!*write_result) { - refcount_inc(&enabler->event->refcnt); + user_event_get(user); list_add_rcu(&enabler->mm_enablers_link, &user_mm->enablers); } @@ -1337,10 +1358,8 @@ static struct user_event *find_user_event(struct user_event_group *group, *outkey = key; hash_for_each_possible(group->register_table, user, node, key) - if (!strcmp(EVENT_NAME(user), name)) { - refcount_inc(&user->refcnt); - return user; - } + if (!strcmp(EVENT_NAME(user), name)) + return user_event_get(user); return NULL; } @@ -1554,12 +1573,12 @@ static int user_event_reg(struct trace_event_call *call, return ret; inc: - refcount_inc(&user->refcnt); + user_event_get(user); update_enable_bit_for(user); return 0; dec: update_enable_bit_for(user); - refcount_dec(&user->refcnt); + user_event_put(user, true); return 0; } @@ -1593,7 +1612,7 @@ static int user_event_create(const char *raw_command) ret = user_event_parse_cmd(group, name, &user, 0); if (!ret) - refcount_dec(&user->refcnt); + user_event_put(user, false); mutex_unlock(&group->reg_mutex); @@ -1794,7 +1813,7 @@ static int user_event_parse(struct user_event_group *group, char *name, return 0; error: - refcount_dec(&user->refcnt); + user_event_put(user, false); return ret; } @@ -1883,7 +1902,7 @@ static int delete_user_event(struct user_event_group *group, char *name) if (!user) return -ENOENT; - refcount_dec(&user->refcnt); + user_event_put(user, true); if (!user_event_last_ref(user)) return -EBUSY; @@ -2042,9 +2061,7 @@ static int user_events_ref_add(struct user_event_file_info *info, for (i = 0; i < count; ++i) new_refs->events[i] = refs->events[i]; - new_refs->events[i] = user; - - refcount_inc(&user->refcnt); + new_refs->events[i] = user_event_get(user); rcu_assign_pointer(info->refs, new_refs); @@ -2158,7 +2175,7 @@ static long user_events_ioctl_reg(struct user_event_file_info *info, ret = user_events_ref_add(info, user); /* No longer need parse ref, ref_add either worked or not */ - refcount_dec(&user->refcnt); + user_event_put(user, false); /* Positive number is index and valid */ if (ret < 0) @@ -2307,7 +2324,7 @@ static long user_events_ioctl_unreg(unsigned long uarg) set_bit(ENABLE_VAL_FREEING_BIT, ENABLE_BITOPS(enabler)); if (!test_bit(ENABLE_VAL_FAULTING_BIT, ENABLE_BITOPS(enabler))) - user_event_enabler_destroy(enabler); + user_event_enabler_destroy(enabler, true); /* Removed at least one */ ret = 0; @@ -2365,7 +2382,6 @@ static int user_events_release(struct inode *node, struct file *file) struct user_event_file_info *info = file->private_data; struct user_event_group *group; struct user_event_refs *refs; - struct user_event *user; int i; if (!info) @@ -2389,12 +2405,9 @@ static int user_events_release(struct inode *node, struct file *file) * The underlying user_events are ref counted, and cannot be freed. * After this decrement, the user_events may be freed elsewhere. */ - for (i = 0; i < refs->count; ++i) { - user = refs->events[i]; + for (i = 0; i < refs->count; ++i) + user_event_put(refs->events[i], false); - if (user) - refcount_dec(&user->refcnt); - } out: file->private_data = NULL; From a65442edb47a6d9c974b50049296ac9ddb378fee Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Wed, 14 Jun 2023 09:33:33 -0700 Subject: [PATCH 15/34] tracing/user_events: Add auto cleanup and future persist flag Currently user events need to be manually deleted via the delete IOCTL call or via the dynamic_events file. Most operators and processes wish to have these events auto cleanup when they are no longer used by anything to prevent them piling without manual maintenance. However, some operators may not want this, such as pre-registering events via the dynamic_events tracefs file. Update user_event_put() to attempt an auto delete of the event if it's the last reference. The auto delete must run in a work queue to ensure proper behavior of class->reg() invocations that don't expect the call to go away from underneath them during the unregister. Add work_struct to user_event struct to ensure we can do this reliably. Add a persist flag, that is not yet exposed, to ensure we can toggle between auto-cleanup and leaving the events existing in the future. When a non-zero flag is seen during register, return -EINVAL to ensure ABI is clear for the user processes while we work out the best approach for persistent events. Link: https://lkml.kernel.org/r/20230614163336.5797-4-beaub@linux.microsoft.com Link: https://lore.kernel.org/linux-trace-kernel/20230518093600.3f119d68@rorschach.local.home/ Suggested-by: Steven Rostedt Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_user.c | 139 ++++++++++++++++++++++++++++--- 1 file changed, 126 insertions(+), 13 deletions(-) diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index c064458eea5c..8df0550415e7 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -49,6 +49,18 @@ #define EVENT_STATUS_PERF BIT(1) #define EVENT_STATUS_OTHER BIT(7) +/* + * User register flags are not allowed yet, keep them here until we are + * ready to expose them out to the user ABI. + */ +enum user_reg_flag { + /* Event will not delete upon last reference closing */ + USER_EVENT_REG_PERSIST = 1U << 0, + + /* This value or above is currently non-ABI */ + USER_EVENT_REG_MAX = 1U << 1, +}; + /* * Stores the system name, tables, and locks for a group of events. This * allows isolation for events by various means. @@ -85,6 +97,7 @@ struct user_event { struct hlist_node node; struct list_head fields; struct list_head validators; + struct work_struct put_work; refcount_t refcnt; int min_size; int reg_flags; @@ -171,6 +184,7 @@ static int user_event_parse(struct user_event_group *group, char *name, static struct user_event_mm *user_event_mm_get(struct user_event_mm *mm); static struct user_event_mm *user_event_mm_get_all(struct user_event *user); static void user_event_mm_put(struct user_event_mm *mm); +static int destroy_user_event(struct user_event *user); static u32 user_event_key(char *name) { @@ -184,19 +198,103 @@ static struct user_event *user_event_get(struct user_event *user) return user; } +static void delayed_destroy_user_event(struct work_struct *work) +{ + struct user_event *user = container_of( + work, struct user_event, put_work); + + mutex_lock(&event_mutex); + + if (!refcount_dec_and_test(&user->refcnt)) + goto out; + + if (destroy_user_event(user)) { + /* + * The only reason this would fail here is if we cannot + * update the visibility of the event. In this case the + * event stays in the hashtable, waiting for someone to + * attempt to delete it later. + */ + pr_warn("user_events: Unable to delete event\n"); + refcount_set(&user->refcnt, 1); + } +out: + mutex_unlock(&event_mutex); +} + static void user_event_put(struct user_event *user, bool locked) { -#ifdef CONFIG_LOCKDEP - if (locked) - lockdep_assert_held(&event_mutex); - else - lockdep_assert_not_held(&event_mutex); -#endif + bool delete; if (unlikely(!user)) return; - refcount_dec(&user->refcnt); + /* + * When the event is not enabled for auto-delete there will always + * be at least 1 reference to the event. During the event creation + * we initially set the refcnt to 2 to achieve this. In those cases + * the caller must acquire event_mutex and after decrement check if + * the refcnt is 1, meaning this is the last reference. When auto + * delete is enabled, there will only be 1 ref, IE: refcnt will be + * only set to 1 during creation to allow the below checks to go + * through upon the last put. The last put must always be done with + * the event mutex held. + */ + if (!locked) { + lockdep_assert_not_held(&event_mutex); + delete = refcount_dec_and_mutex_lock(&user->refcnt, &event_mutex); + } else { + lockdep_assert_held(&event_mutex); + delete = refcount_dec_and_test(&user->refcnt); + } + + if (!delete) + return; + + /* + * We now have the event_mutex in all cases, which ensures that + * no new references will be taken until event_mutex is released. + * New references come through find_user_event(), which requires + * the event_mutex to be held. + */ + + if (user->reg_flags & USER_EVENT_REG_PERSIST) { + /* We should not get here when persist flag is set */ + pr_alert("BUG: Auto-delete engaged on persistent event\n"); + goto out; + } + + /* + * Unfortunately we have to attempt the actual destroy in a work + * queue. This is because not all cases handle a trace_event_call + * being removed within the class->reg() operation for unregister. + */ + INIT_WORK(&user->put_work, delayed_destroy_user_event); + + /* + * Since the event is still in the hashtable, we have to re-inc + * the ref count to 1. This count will be decremented and checked + * in the work queue to ensure it's still the last ref. This is + * needed because a user-process could register the same event in + * between the time of event_mutex release and the work queue + * running the delayed destroy. If we removed the item now from + * the hashtable, this would result in a timing window where a + * user process would fail a register because the trace_event_call + * register would fail in the tracing layers. + */ + refcount_set(&user->refcnt, 1); + + if (WARN_ON_ONCE(!schedule_work(&user->put_work))) { + /* + * If we fail we must wait for an admin to attempt delete or + * another register/close of the event, whichever is first. + */ + pr_warn("user_events: Unable to queue delayed destroy\n"); + } +out: + /* Ensure if we didn't have event_mutex before we unlock it */ + if (!locked) + mutex_unlock(&event_mutex); } static void user_event_group_destroy(struct user_event_group *group) @@ -793,7 +891,12 @@ out: static __always_inline __must_check bool user_event_last_ref(struct user_event *user) { - return refcount_read(&user->refcnt) == 1; + int last = 0; + + if (user->reg_flags & USER_EVENT_REG_PERSIST) + last = 1; + + return refcount_read(&user->refcnt) == last; } static __always_inline __must_check @@ -1609,7 +1712,8 @@ static int user_event_create(const char *raw_command) mutex_lock(&group->reg_mutex); - ret = user_event_parse_cmd(group, name, &user, 0); + /* Dyn events persist, otherwise they would cleanup immediately */ + ret = user_event_parse_cmd(group, name, &user, USER_EVENT_REG_PERSIST); if (!ret) user_event_put(user, false); @@ -1780,6 +1884,10 @@ static int user_event_parse(struct user_event_group *group, char *name, int argc = 0; char **argv; + /* User register flags are not ready yet */ + if (reg_flags != 0 || flags != NULL) + return -EINVAL; + /* Prevent dyn_event from racing */ mutex_lock(&event_mutex); user = find_user_event(group, name, &key); @@ -1869,8 +1977,13 @@ error: user->reg_flags = reg_flags; - /* Ensure we track self ref and caller ref (2) */ - refcount_set(&user->refcnt, 2); + if (user->reg_flags & USER_EVENT_REG_PERSIST) { + /* Ensure we track self ref and caller ref (2) */ + refcount_set(&user->refcnt, 2); + } else { + /* Ensure we track only caller ref (1) */ + refcount_set(&user->refcnt, 1); + } dyn_event_init(&user->devent, &user_event_dops); dyn_event_add(&user->devent, &user->call); @@ -2092,8 +2205,8 @@ static long user_reg_get(struct user_reg __user *ureg, struct user_reg *kreg) if (ret) return ret; - /* Ensure no flags, since we don't support any yet */ - if (kreg->flags != 0) + /* Ensure only valid flags */ + if (kreg->flags & ~(USER_EVENT_REG_MAX-1)) return -EINVAL; /* Ensure supported size */ From 216a137e3eadac888cece141bd2c940785e235a2 Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Wed, 14 Jun 2023 09:33:34 -0700 Subject: [PATCH 16/34] selftests/user_events: Ensure auto cleanup works as expected User events now auto cleanup upon the last reference put. Update ftrace_test to ensure this works as expected. Ensure EBUSY delays while event is being deleted do not cause transient failures by waiting and re-attempting. Link: https://lkml.kernel.org/r/20230614163336.5797-5-beaub@linux.microsoft.com Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- .../selftests/user_events/ftrace_test.c | 47 +++++++++++++++---- 1 file changed, 37 insertions(+), 10 deletions(-) diff --git a/tools/testing/selftests/user_events/ftrace_test.c b/tools/testing/selftests/user_events/ftrace_test.c index abfb49558a26..eb6904d89f14 100644 --- a/tools/testing/selftests/user_events/ftrace_test.c +++ b/tools/testing/selftests/user_events/ftrace_test.c @@ -102,30 +102,56 @@ err: return -1; } +static bool wait_for_delete(void) +{ + int i; + + for (i = 0; i < 1000; ++i) { + int fd = open(enable_file, O_RDONLY); + + if (fd == -1) + return true; + + close(fd); + usleep(1000); + } + + return false; +} + static int clear(int *check) { struct user_unreg unreg = {0}; + int fd; unreg.size = sizeof(unreg); unreg.disable_bit = 31; unreg.disable_addr = (__u64)check; - int fd = open(data_file, O_RDWR); + fd = open(data_file, O_RDWR); if (fd == -1) return -1; if (ioctl(fd, DIAG_IOCSUNREG, &unreg) == -1) if (errno != ENOENT) - return -1; + goto fail; - if (ioctl(fd, DIAG_IOCSDEL, "__test_event") == -1) - if (errno != ENOENT) - return -1; + if (ioctl(fd, DIAG_IOCSDEL, "__test_event") == -1) { + if (errno == EBUSY) { + if (!wait_for_delete()) + goto fail; + } else if (errno != ENOENT) + goto fail; + } close(fd); return 0; +fail: + close(fd); + + return -1; } static int check_print_fmt(const char *event, const char *expected, int *check) @@ -155,9 +181,8 @@ static int check_print_fmt(const char *event, const char *expected, int *check) /* Register should work */ ret = ioctl(fd, DIAG_IOCSREG, ®); - close(fd); - if (ret != 0) { + close(fd); printf("Reg failed in fmt\n"); return ret; } @@ -165,6 +190,8 @@ static int check_print_fmt(const char *event, const char *expected, int *check) /* Ensure correct print_fmt */ ret = get_print_fmt(print_fmt, sizeof(print_fmt)); + close(fd); + if (ret != 0) return ret; @@ -256,10 +283,10 @@ TEST_F(user, register_events) { unreg.disable_bit = 30; ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSUNREG, &unreg)); - /* Delete should work only after close and unregister */ + /* Delete should have been auto-done after close and unregister */ close(self->data_fd); - self->data_fd = open(data_file, O_RDWR); - ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSDEL, "__test_event")); + + ASSERT_EQ(true, wait_for_delete()); } TEST_F(user, write_events) { From 61701242e86f0b509a0f5f9deb226bedfc8dfab7 Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Wed, 14 Jun 2023 09:33:35 -0700 Subject: [PATCH 17/34] selftests/user_events: Adapt dyn_test to non-persist events Now that user_events does not honor persist events the dynamic_events file cannot be easily used to test parsing and matching cases. Update dyn_test to use the direct ABI file instead of dynamic_events so that we still have testing coverage until persist events and dynamic_events file integration has been decided. Link: https://lkml.kernel.org/r/20230614163336.5797-6-beaub@linux.microsoft.com Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- .../testing/selftests/user_events/dyn_test.c | 177 ++++++++++++++---- 1 file changed, 136 insertions(+), 41 deletions(-) diff --git a/tools/testing/selftests/user_events/dyn_test.c b/tools/testing/selftests/user_events/dyn_test.c index 8879a7b04c6a..d6979a48478f 100644 --- a/tools/testing/selftests/user_events/dyn_test.c +++ b/tools/testing/selftests/user_events/dyn_test.c @@ -16,42 +16,140 @@ #include "../kselftest_harness.h" -const char *dyn_file = "/sys/kernel/tracing/dynamic_events"; -const char *clear = "!u:__test_event"; +const char *abi_file = "/sys/kernel/tracing/user_events_data"; +const char *enable_file = "/sys/kernel/tracing/events/user_events/__test_event/enable"; -static int Append(const char *value) +static bool wait_for_delete(void) { - int fd = open(dyn_file, O_RDWR | O_APPEND); - int ret = write(fd, value, strlen(value)); + int i; + + for (i = 0; i < 1000; ++i) { + int fd = open(enable_file, O_RDONLY); + + if (fd == -1) + return true; + + close(fd); + usleep(1000); + } + + return false; +} + +static int reg_event(int fd, int *check, int bit, const char *value) +{ + struct user_reg reg = {0}; + + reg.size = sizeof(reg); + reg.name_args = (__u64)value; + reg.enable_bit = bit; + reg.enable_addr = (__u64)check; + reg.enable_size = sizeof(*check); + + if (ioctl(fd, DIAG_IOCSREG, ®) == -1) + return -1; + + return 0; +} + +static int unreg_event(int fd, int *check, int bit) +{ + struct user_unreg unreg = {0}; + + unreg.size = sizeof(unreg); + unreg.disable_bit = bit; + unreg.disable_addr = (__u64)check; + + return ioctl(fd, DIAG_IOCSUNREG, &unreg); +} + +static int parse(int *check, const char *value) +{ + int fd = open(abi_file, O_RDWR); + int ret; + + if (fd == -1) + return -1; + + /* Until we have persist flags via dynamic events, use the base name */ + if (value[0] != 'u' || value[1] != ':') { + close(fd); + return -1; + } + + ret = reg_event(fd, check, 31, value + 2); + + if (ret != -1) { + if (unreg_event(fd, check, 31) == -1) + printf("WARN: Couldn't unreg event\n"); + } close(fd); + return ret; } -#define CLEAR() \ +static int check_match(int *check, const char *first, const char *second, bool *match) +{ + int fd = open(abi_file, O_RDWR); + int ret = -1; + + if (fd == -1) + return -1; + + if (reg_event(fd, check, 31, first) == -1) + goto cleanup; + + if (reg_event(fd, check, 30, second) == -1) { + if (errno == EADDRINUSE) { + /* Name is in use, with different fields */ + *match = false; + ret = 0; + } + + goto cleanup; + } + + *match = true; + ret = 0; +cleanup: + unreg_event(fd, check, 31); + unreg_event(fd, check, 30); + + close(fd); + + wait_for_delete(); + + return ret; +} + +#define TEST_MATCH(x, y) \ do { \ - int ret = Append(clear); \ - if (ret == -1) \ - ASSERT_EQ(ENOENT, errno); \ + bool match; \ + ASSERT_NE(-1, check_match(&self->check, x, y, &match)); \ + ASSERT_EQ(true, match); \ } while (0) -#define TEST_PARSE(x) \ +#define TEST_NMATCH(x, y) \ do { \ - ASSERT_NE(-1, Append(x)); \ - CLEAR(); \ + bool match; \ + ASSERT_NE(-1, check_match(&self->check, x, y, &match)); \ + ASSERT_EQ(false, match); \ } while (0) -#define TEST_NPARSE(x) ASSERT_EQ(-1, Append(x)) +#define TEST_PARSE(x) ASSERT_NE(-1, parse(&self->check, x)) + +#define TEST_NPARSE(x) ASSERT_EQ(-1, parse(&self->check, x)) FIXTURE(user) { + int check; }; FIXTURE_SETUP(user) { - CLEAR(); } FIXTURE_TEARDOWN(user) { - CLEAR(); + wait_for_delete(); } TEST_F(user, basic_types) { @@ -95,33 +193,30 @@ TEST_F(user, size_types) { TEST_NPARSE("u:__test_event char a 20"); } -TEST_F(user, flags) { - /* Should work */ - TEST_PARSE("u:__test_event:BPF_ITER u32 a"); - /* Forward compat */ - TEST_PARSE("u:__test_event:BPF_ITER,FLAG_FUTURE u32 a"); -} - TEST_F(user, matching) { - /* Register */ - ASSERT_NE(-1, Append("u:__test_event struct custom a 20")); - /* Should not match */ - TEST_NPARSE("!u:__test_event struct custom b"); - /* Should match */ - TEST_PARSE("!u:__test_event struct custom a"); - /* Multi field reg */ - ASSERT_NE(-1, Append("u:__test_event u32 a; u32 b")); - /* Non matching cases */ - TEST_NPARSE("!u:__test_event u32 a"); - TEST_NPARSE("!u:__test_event u32 b"); - TEST_NPARSE("!u:__test_event u32 a; u32 "); - TEST_NPARSE("!u:__test_event u32 a; u32 a"); - /* Matching case */ - TEST_PARSE("!u:__test_event u32 a; u32 b"); - /* Register */ - ASSERT_NE(-1, Append("u:__test_event u32 a; u32 b")); - /* Ensure trailing semi-colon case */ - TEST_PARSE("!u:__test_event u32 a; u32 b;"); + /* Single name matches */ + TEST_MATCH("__test_event u32 a", + "__test_event u32 a"); + + /* Multiple names match */ + TEST_MATCH("__test_event u32 a; u32 b", + "__test_event u32 a; u32 b"); + + /* Multiple names match with dangling ; */ + TEST_MATCH("__test_event u32 a; u32 b", + "__test_event u32 a; u32 b;"); + + /* Single name doesn't match */ + TEST_NMATCH("__test_event u32 a", + "__test_event u32 b"); + + /* Multiple names don't match */ + TEST_NMATCH("__test_event u32 a; u32 b", + "__test_event u32 b; u32 a"); + + /* Types don't match */ + TEST_NMATCH("__test_event u64 a; u64 b", + "__test_event u32 a; u32 b"); } int main(int argc, char **argv) From 0113d4615dbf053ae9a7a1e0acbc6652713af01f Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Wed, 14 Jun 2023 09:33:36 -0700 Subject: [PATCH 18/34] tracing/user_events: Document auto-cleanup and remove dyn_event refs Now user_events auto-cleanup upon the last reference by default. This makes it not possible to use the dynamics event file via tracefs. Document that auto-cleanup is enabled by default and remove the refernce to /sys/kernel/tracing/dynamic_events file to make this clear. Link: https://lkml.kernel.org/r/20230614163336.5797-7-beaub@linux.microsoft.com Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- Documentation/trace/user_events.rst | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/Documentation/trace/user_events.rst b/Documentation/trace/user_events.rst index f79987e16cf4..e7b07313550a 100644 --- a/Documentation/trace/user_events.rst +++ b/Documentation/trace/user_events.rst @@ -14,10 +14,6 @@ Programs can view status of the events via /sys/kernel/tracing/user_events_status and can both register and write data out via /sys/kernel/tracing/user_events_data. -Programs can also use /sys/kernel/tracing/dynamic_events to register and -delete user based events via the u: prefix. The format of the command to -dynamic_events is the same as the ioctl with the u: prefix applied. - Typically programs will register a set of events that they wish to expose to tools that can read trace_events (such as ftrace and perf). The registration process tells the kernel which address and bit to reflect if any tool has @@ -144,6 +140,9 @@ its name. Delete will only succeed if there are no references left to the event (in both user and kernel space). User programs should use a separate file to request deletes than the one used for registration due to this. +**NOTE:** By default events will auto-delete when there are no references left +to the event. Flags in the future may change this logic. + Unregistering ------------- If after registering an event it is no longer wanted to be updated then it can From 22db06337f590d01d79f60f181d8dfe5a9ef9085 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 14 Jun 2023 17:29:21 +0200 Subject: [PATCH 19/34] ACPI: sleep: Avoid breaking S3 wakeup due to might_sleep() The addition of might_sleep() to down_timeout() caused the latter to enable interrupts unconditionally in some cases, which in turn broke the ACPI S3 wakeup path in acpi_suspend_enter(), where down_timeout() is called by acpi_disable_all_gpes() via acpi_ut_acquire_mutex(). Namely, if CONFIG_DEBUG_ATOMIC_SLEEP is set, might_sleep() causes might_resched() to be used and if CONFIG_PREEMPT_VOLUNTARY is set, this triggers __cond_resched() which may call preempt_schedule_common(), so __schedule() gets invoked and it ends up with enabled interrupts (in the prev == next case). Now, enabling interrupts early in the S3 wakeup path causes the kernel to crash. Address this by modifying acpi_suspend_enter() to disable GPEs without attempting to acquire the sleeping lock which is not needed in that code path anyway. Fixes: 99409b935c9a ("locking/semaphore: Add might_sleep() to down_*() family") Reported-by: Srinivas Pandruvada Signed-off-by: Rafael J. Wysocki Acked-by: Peter Zijlstra (Intel) Cc: 5.15+ # 5.15+ --- drivers/acpi/acpica/achware.h | 2 -- drivers/acpi/sleep.c | 16 ++++++++++++---- include/acpi/acpixf.h | 1 + 3 files changed, 13 insertions(+), 6 deletions(-) diff --git a/drivers/acpi/acpica/achware.h b/drivers/acpi/acpica/achware.h index ebf8fd373cf7..79bbfe00d241 100644 --- a/drivers/acpi/acpica/achware.h +++ b/drivers/acpi/acpica/achware.h @@ -101,8 +101,6 @@ acpi_status acpi_hw_get_gpe_status(struct acpi_gpe_event_info *gpe_event_info, acpi_event_status *event_status); -acpi_status acpi_hw_disable_all_gpes(void); - acpi_status acpi_hw_enable_all_runtime_gpes(void); acpi_status acpi_hw_enable_all_wakeup_gpes(void); diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 72470b9f16c4..f32570f72b90 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -636,11 +636,19 @@ static int acpi_suspend_enter(suspend_state_t pm_state) } /* - * Disable and clear GPE status before interrupt is enabled. Some GPEs - * (like wakeup GPE) haven't handler, this can avoid such GPE misfire. - * acpi_leave_sleep_state will reenable specific GPEs later + * Disable all GPE and clear their status bits before interrupts are + * enabled. Some GPEs (like wakeup GPEs) have no handlers and this can + * prevent them from producing spurious interrups. + * + * acpi_leave_sleep_state() will reenable specific GPEs later. + * + * Because this code runs on one CPU with disabled interrupts (all of + * the other CPUs are offline at this time), it need not acquire any + * sleeping locks which may trigger an implicit preemption point even + * if there is no contention, so avoid doing that by using a low-level + * library routine here. */ - acpi_disable_all_gpes(); + acpi_hw_disable_all_gpes(); /* Allow EC transactions to happen. */ acpi_ec_unblock_transactions(); diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index e6098a08c914..9ffdc0425bc2 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -761,6 +761,7 @@ ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_event_status *event_status)) ACPI_HW_DEPENDENT_RETURN_UINT32(u32 acpi_dispatch_gpe(acpi_handle gpe_device, u32 gpe_number)) +ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_hw_disable_all_gpes(void)) ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_disable_all_gpes(void)) ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_enable_all_runtime_gpes(void)) ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_enable_all_wakeup_gpes(void)) From 0bb619f9227aa370330d2b309733d74750705053 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Wed, 14 Jun 2023 12:07:56 +0200 Subject: [PATCH 20/34] thermal/intel/intel_soc_dts_iosf: Fix reporting wrong temperatures Since commit 955fb8719efb ("thermal/intel/intel_soc_dts_iosf: Use Intel TCC library") intel_soc_dts_iosf is reporting the wrong temperature. The driver expects tj_max to be in milli-degrees-celcius but after the switch to the TCC library this is now in degrees celcius so instead of e.g. 90000 it is set to 90 causing a temperature 45 degrees below tj_max to be reported as -44910 milli-degrees instead of as 45000 milli-degrees. Fix this by adding back the lost factor of 1000. Fixes: 955fb8719efb ("thermal/intel/intel_soc_dts_iosf: Use Intel TCC library") Reported-by: Bernhard Krug Signed-off-by: Hans de Goede Acked-by: Zhang Rui Cc: 6.3+ # 6.3+ Signed-off-by: Rafael J. Wysocki --- drivers/thermal/intel/intel_soc_dts_iosf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/thermal/intel/intel_soc_dts_iosf.c b/drivers/thermal/intel/intel_soc_dts_iosf.c index f99dc7e4ae89..db97499f4f0a 100644 --- a/drivers/thermal/intel/intel_soc_dts_iosf.c +++ b/drivers/thermal/intel/intel_soc_dts_iosf.c @@ -398,7 +398,7 @@ struct intel_soc_dts_sensors *intel_soc_dts_iosf_init( spin_lock_init(&sensors->intr_notify_lock); mutex_init(&sensors->dts_update_lock); sensors->intr_type = intr_type; - sensors->tj_max = tj_max; + sensors->tj_max = tj_max * 1000; if (intr_type == INTEL_SOC_DTS_INTERRUPT_NONE) notification = false; else From 2b9b8f3b68edb3d67d79962f02e26dbb5ae3808d Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Mon, 5 Jun 2023 01:57:34 +0900 Subject: [PATCH 21/34] ksmbd: validate command payload size ->StructureSize2 indicates command payload size. ksmbd should validate this size with rfc1002 length before accessing it. This patch remove unneeded check and add the validation for this. [ 8.912583] BUG: KASAN: slab-out-of-bounds in ksmbd_smb2_check_message+0x12a/0xc50 [ 8.913051] Read of size 2 at addr ffff88800ac7d92c by task kworker/0:0/7 ... [ 8.914967] Call Trace: [ 8.915126] [ 8.915267] dump_stack_lvl+0x33/0x50 [ 8.915506] print_report+0xcc/0x620 [ 8.916558] kasan_report+0xae/0xe0 [ 8.917080] kasan_check_range+0x35/0x1b0 [ 8.917334] ksmbd_smb2_check_message+0x12a/0xc50 [ 8.917935] ksmbd_verify_smb_message+0xae/0xd0 [ 8.918223] handle_ksmbd_work+0x192/0x820 [ 8.918478] process_one_work+0x419/0x760 [ 8.918727] worker_thread+0x2a2/0x6f0 [ 8.919222] kthread+0x187/0x1d0 [ 8.919723] ret_from_fork+0x1f/0x30 [ 8.919954] Cc: stable@vger.kernel.org Reported-by: Chih-Yen Chang Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/smb2misc.c | 23 ++++++++++++----------- 1 file changed, 12 insertions(+), 11 deletions(-) diff --git a/fs/smb/server/smb2misc.c b/fs/smb/server/smb2misc.c index 0ffe663b7590..57749f41b991 100644 --- a/fs/smb/server/smb2misc.c +++ b/fs/smb/server/smb2misc.c @@ -351,6 +351,7 @@ int ksmbd_smb2_check_message(struct ksmbd_work *work) int command; __u32 clc_len; /* calculated length */ __u32 len = get_rfc1002_len(work->request_buf); + __u32 req_struct_size; if (le32_to_cpu(hdr->NextCommand) > 0) len = le32_to_cpu(hdr->NextCommand); @@ -373,17 +374,9 @@ int ksmbd_smb2_check_message(struct ksmbd_work *work) } if (smb2_req_struct_sizes[command] != pdu->StructureSize2) { - if (command != SMB2_OPLOCK_BREAK_HE && - (hdr->Status == 0 || pdu->StructureSize2 != SMB2_ERROR_STRUCTURE_SIZE2_LE)) { - /* error packets have 9 byte structure size */ - ksmbd_debug(SMB, - "Illegal request size %u for command %d\n", - le16_to_cpu(pdu->StructureSize2), command); - return 1; - } else if (command == SMB2_OPLOCK_BREAK_HE && - hdr->Status == 0 && - le16_to_cpu(pdu->StructureSize2) != OP_BREAK_STRUCT_SIZE_20 && - le16_to_cpu(pdu->StructureSize2) != OP_BREAK_STRUCT_SIZE_21) { + if (command == SMB2_OPLOCK_BREAK_HE && + le16_to_cpu(pdu->StructureSize2) != OP_BREAK_STRUCT_SIZE_20 && + le16_to_cpu(pdu->StructureSize2) != OP_BREAK_STRUCT_SIZE_21) { /* special case for SMB2.1 lease break message */ ksmbd_debug(SMB, "Illegal request size %d for oplock break\n", @@ -392,6 +385,14 @@ int ksmbd_smb2_check_message(struct ksmbd_work *work) } } + req_struct_size = le16_to_cpu(pdu->StructureSize2) + + __SMB2_HEADER_STRUCTURE_SIZE; + if (command == SMB2_LOCK_HE) + req_struct_size -= sizeof(struct smb2_lock_element); + + if (req_struct_size > len + 1) + return 1; + if (smb2_calc_size(hdr, &clc_len)) return 1; From 40b268d384a22276dca1450549f53eed60e21deb Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Thu, 15 Jun 2023 15:56:32 +0900 Subject: [PATCH 22/34] ksmbd: add mnt_want_write to ksmbd vfs functions ksmbd is doing write access using vfs helpers. There are the cases that mnt_want_write() is not called in vfs helper. This patch add missing mnt_want_write() to ksmbd vfs functions. Cc: stable@vger.kernel.org Cc: Amir Goldstein Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/smb2pdu.c | 26 ++++----- fs/smb/server/smbacl.c | 10 ++-- fs/smb/server/vfs.c | 117 ++++++++++++++++++++++++++++++-------- fs/smb/server/vfs.h | 17 +++--- fs/smb/server/vfs_cache.c | 2 +- 5 files changed, 117 insertions(+), 55 deletions(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 25c0ba04c59d..ccecdb71d2bc 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -2249,7 +2249,7 @@ static int smb2_set_ea(struct smb2_ea_info *eabuf, unsigned int buf_len, /* delete the EA only when it exits */ if (rc > 0) { rc = ksmbd_vfs_remove_xattr(idmap, - path->dentry, + path, attr_name); if (rc < 0) { @@ -2263,8 +2263,7 @@ static int smb2_set_ea(struct smb2_ea_info *eabuf, unsigned int buf_len, /* if the EA doesn't exist, just do nothing. */ rc = 0; } else { - rc = ksmbd_vfs_setxattr(idmap, - path->dentry, attr_name, value, + rc = ksmbd_vfs_setxattr(idmap, path, attr_name, value, le16_to_cpu(eabuf->EaValueLength), 0); if (rc < 0) { ksmbd_debug(SMB, @@ -2321,8 +2320,7 @@ static noinline int smb2_set_stream_name_xattr(const struct path *path, return -EBADF; } - rc = ksmbd_vfs_setxattr(idmap, path->dentry, - xattr_stream_name, NULL, 0, 0); + rc = ksmbd_vfs_setxattr(idmap, path, xattr_stream_name, NULL, 0, 0); if (rc < 0) pr_err("Failed to store XATTR stream name :%d\n", rc); return 0; @@ -2350,7 +2348,7 @@ static int smb2_remove_smb_xattrs(const struct path *path) if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) && !strncmp(&name[XATTR_USER_PREFIX_LEN], STREAM_PREFIX, STREAM_PREFIX_LEN)) { - err = ksmbd_vfs_remove_xattr(idmap, path->dentry, + err = ksmbd_vfs_remove_xattr(idmap, path, name); if (err) ksmbd_debug(SMB, "remove xattr failed : %s\n", @@ -2397,8 +2395,7 @@ static void smb2_new_xattrs(struct ksmbd_tree_connect *tcon, const struct path * da.flags = XATTR_DOSINFO_ATTRIB | XATTR_DOSINFO_CREATE_TIME | XATTR_DOSINFO_ITIME; - rc = ksmbd_vfs_set_dos_attrib_xattr(mnt_idmap(path->mnt), - path->dentry, &da); + rc = ksmbd_vfs_set_dos_attrib_xattr(mnt_idmap(path->mnt), path, &da); if (rc) ksmbd_debug(SMB, "failed to store file attribute into xattr\n"); } @@ -2972,7 +2969,7 @@ int smb2_open(struct ksmbd_work *work) struct inode *inode = d_inode(path.dentry); posix_acl_rc = ksmbd_vfs_inherit_posix_acl(idmap, - path.dentry, + &path, d_inode(path.dentry->d_parent)); if (posix_acl_rc) ksmbd_debug(SMB, "inherit posix acl failed : %d\n", posix_acl_rc); @@ -2988,7 +2985,7 @@ int smb2_open(struct ksmbd_work *work) if (rc) { if (posix_acl_rc) ksmbd_vfs_set_init_posix_acl(idmap, - path.dentry); + &path); if (test_share_config_flag(work->tcon->share_conf, KSMBD_SHARE_FLAG_ACL_XATTR)) { @@ -3028,7 +3025,7 @@ int smb2_open(struct ksmbd_work *work) rc = ksmbd_vfs_set_sd_xattr(conn, idmap, - path.dentry, + &path, pntsd, pntsd_size); kfree(pntsd); @@ -5464,7 +5461,7 @@ static int smb2_rename(struct ksmbd_work *work, goto out; rc = ksmbd_vfs_setxattr(file_mnt_idmap(fp->filp), - fp->filp->f_path.dentry, + &fp->filp->f_path, xattr_stream_name, NULL, 0, 0); if (rc < 0) { @@ -5629,8 +5626,7 @@ static int set_file_basic_info(struct ksmbd_file *fp, da.flags = XATTR_DOSINFO_ATTRIB | XATTR_DOSINFO_CREATE_TIME | XATTR_DOSINFO_ITIME; - rc = ksmbd_vfs_set_dos_attrib_xattr(idmap, - filp->f_path.dentry, &da); + rc = ksmbd_vfs_set_dos_attrib_xattr(idmap, &filp->f_path, &da); if (rc) ksmbd_debug(SMB, "failed to restore file attribute in EA\n"); @@ -7485,7 +7481,7 @@ static inline int fsctl_set_sparse(struct ksmbd_work *work, u64 id, da.attr = le32_to_cpu(fp->f_ci->m_fattr); ret = ksmbd_vfs_set_dos_attrib_xattr(idmap, - fp->filp->f_path.dentry, &da); + &fp->filp->f_path, &da); if (ret) fp->f_ci->m_fattr = old_fattr; } diff --git a/fs/smb/server/smbacl.c b/fs/smb/server/smbacl.c index 0a5862a61c77..ad919a4239d0 100644 --- a/fs/smb/server/smbacl.c +++ b/fs/smb/server/smbacl.c @@ -1162,8 +1162,7 @@ pass: pntsd_size += sizeof(struct smb_acl) + nt_size; } - ksmbd_vfs_set_sd_xattr(conn, idmap, - path->dentry, pntsd, pntsd_size); + ksmbd_vfs_set_sd_xattr(conn, idmap, path, pntsd, pntsd_size); kfree(pntsd); } @@ -1383,7 +1382,7 @@ int set_info_sec(struct ksmbd_conn *conn, struct ksmbd_tree_connect *tcon, newattrs.ia_valid |= ATTR_MODE; newattrs.ia_mode = (inode->i_mode & ~0777) | (fattr.cf_mode & 0777); - ksmbd_vfs_remove_acl_xattrs(idmap, path->dentry); + ksmbd_vfs_remove_acl_xattrs(idmap, path); /* Update posix acls */ if (IS_ENABLED(CONFIG_FS_POSIX_ACL) && fattr.cf_dacls) { rc = set_posix_acl(idmap, path->dentry, @@ -1414,9 +1413,8 @@ int set_info_sec(struct ksmbd_conn *conn, struct ksmbd_tree_connect *tcon, if (test_share_config_flag(tcon->share_conf, KSMBD_SHARE_FLAG_ACL_XATTR)) { /* Update WinACL in xattr */ - ksmbd_vfs_remove_sd_xattrs(idmap, path->dentry); - ksmbd_vfs_set_sd_xattr(conn, idmap, - path->dentry, pntsd, ntsd_len); + ksmbd_vfs_remove_sd_xattrs(idmap, path); + ksmbd_vfs_set_sd_xattr(conn, idmap, path, pntsd, ntsd_len); } out: diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c index f9fb778247e7..81489fdedd8e 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -170,6 +170,10 @@ int ksmbd_vfs_create(struct ksmbd_work *work, const char *name, umode_t mode) return err; } + err = mnt_want_write(path.mnt); + if (err) + goto out_err; + mode |= S_IFREG; err = vfs_create(mnt_idmap(path.mnt), d_inode(path.dentry), dentry, mode, true); @@ -179,6 +183,9 @@ int ksmbd_vfs_create(struct ksmbd_work *work, const char *name, umode_t mode) } else { pr_err("File(%s): creation failed (err:%d)\n", name, err); } + mnt_drop_write(path.mnt); + +out_err: done_path_create(&path, dentry); return err; } @@ -209,30 +216,35 @@ int ksmbd_vfs_mkdir(struct ksmbd_work *work, const char *name, umode_t mode) return err; } + err = mnt_want_write(path.mnt); + if (err) + goto out_err2; + idmap = mnt_idmap(path.mnt); mode |= S_IFDIR; err = vfs_mkdir(idmap, d_inode(path.dentry), dentry, mode); - if (err) { - goto out; - } else if (d_unhashed(dentry)) { + if (!err && d_unhashed(dentry)) { struct dentry *d; d = lookup_one(idmap, dentry->d_name.name, dentry->d_parent, dentry->d_name.len); if (IS_ERR(d)) { err = PTR_ERR(d); - goto out; + goto out_err1; } if (unlikely(d_is_negative(d))) { dput(d); err = -ENOENT; - goto out; + goto out_err1; } ksmbd_vfs_inherit_owner(work, d_inode(path.dentry), d_inode(d)); dput(d); } -out: + +out_err1: + mnt_drop_write(path.mnt); +out_err2: done_path_create(&path, dentry); if (err) pr_err("mkdir(%s): creation failed (err:%d)\n", name, err); @@ -443,7 +455,7 @@ static int ksmbd_vfs_stream_write(struct ksmbd_file *fp, char *buf, loff_t *pos, memcpy(&stream_buf[*pos], buf, count); err = ksmbd_vfs_setxattr(idmap, - fp->filp->f_path.dentry, + &fp->filp->f_path, fp->stream.name, (void *)stream_buf, size, @@ -589,6 +601,10 @@ int ksmbd_vfs_remove_file(struct ksmbd_work *work, const struct path *path) goto out_err; } + err = mnt_want_write(path->mnt); + if (err) + goto out_err; + idmap = mnt_idmap(path->mnt); if (S_ISDIR(d_inode(path->dentry)->i_mode)) { err = vfs_rmdir(idmap, d_inode(parent), path->dentry); @@ -599,6 +615,7 @@ int ksmbd_vfs_remove_file(struct ksmbd_work *work, const struct path *path) if (err) ksmbd_debug(VFS, "unlink failed, err %d\n", err); } + mnt_drop_write(path->mnt); out_err: ksmbd_revert_fsids(work); @@ -644,11 +661,16 @@ int ksmbd_vfs_link(struct ksmbd_work *work, const char *oldname, goto out3; } + err = mnt_want_write(newpath.mnt); + if (err) + goto out3; + err = vfs_link(oldpath.dentry, mnt_idmap(newpath.mnt), d_inode(newpath.dentry), dentry, NULL); if (err) ksmbd_debug(VFS, "vfs_link failed err %d\n", err); + mnt_drop_write(newpath.mnt); out3: done_path_create(&newpath, dentry); @@ -694,6 +716,10 @@ retry: goto out2; } + err = mnt_want_write(old_path->mnt); + if (err) + goto out2; + trap = lock_rename_child(old_child, new_path.dentry); old_parent = dget(old_child->d_parent); @@ -757,6 +783,7 @@ out4: out3: dput(old_parent); unlock_rename(old_parent, new_path.dentry); + mnt_drop_write(old_path->mnt); out2: path_put(&new_path); @@ -897,19 +924,24 @@ ssize_t ksmbd_vfs_getxattr(struct mnt_idmap *idmap, * Return: 0 on success, otherwise error */ int ksmbd_vfs_setxattr(struct mnt_idmap *idmap, - struct dentry *dentry, const char *attr_name, + const struct path *path, const char *attr_name, void *attr_value, size_t attr_size, int flags) { int err; + err = mnt_want_write(path->mnt); + if (err) + return err; + err = vfs_setxattr(idmap, - dentry, + path->dentry, attr_name, attr_value, attr_size, flags); if (err) ksmbd_debug(VFS, "setxattr failed, err %d\n", err); + mnt_drop_write(path->mnt); return err; } @@ -1013,9 +1045,18 @@ int ksmbd_vfs_fqar_lseek(struct ksmbd_file *fp, loff_t start, loff_t length, } int ksmbd_vfs_remove_xattr(struct mnt_idmap *idmap, - struct dentry *dentry, char *attr_name) + const struct path *path, char *attr_name) { - return vfs_removexattr(idmap, dentry, attr_name); + int err; + + err = mnt_want_write(path->mnt); + if (err) + return err; + + err = vfs_removexattr(idmap, path->dentry, attr_name); + mnt_drop_write(path->mnt); + + return err; } int ksmbd_vfs_unlink(struct file *filp) @@ -1024,6 +1065,10 @@ int ksmbd_vfs_unlink(struct file *filp) struct dentry *dir, *dentry = filp->f_path.dentry; struct mnt_idmap *idmap = file_mnt_idmap(filp); + err = mnt_want_write(filp->f_path.mnt); + if (err) + return err; + dir = dget_parent(dentry); err = ksmbd_vfs_lock_parent(dir, dentry); if (err) @@ -1041,6 +1086,7 @@ int ksmbd_vfs_unlink(struct file *filp) ksmbd_debug(VFS, "failed to delete, err %d\n", err); out: dput(dir); + mnt_drop_write(filp->f_path.mnt); return err; } @@ -1244,13 +1290,13 @@ struct dentry *ksmbd_vfs_kern_path_create(struct ksmbd_work *work, } int ksmbd_vfs_remove_acl_xattrs(struct mnt_idmap *idmap, - struct dentry *dentry) + const struct path *path) { char *name, *xattr_list = NULL; ssize_t xattr_list_len; int err = 0; - xattr_list_len = ksmbd_vfs_listxattr(dentry, &xattr_list); + xattr_list_len = ksmbd_vfs_listxattr(path->dentry, &xattr_list); if (xattr_list_len < 0) { goto out; } else if (!xattr_list_len) { @@ -1258,6 +1304,10 @@ int ksmbd_vfs_remove_acl_xattrs(struct mnt_idmap *idmap, goto out; } + err = mnt_want_write(path->mnt); + if (err) + goto out; + for (name = xattr_list; name - xattr_list < xattr_list_len; name += strlen(name) + 1) { ksmbd_debug(SMB, "%s, len %zd\n", name, strlen(name)); @@ -1266,25 +1316,26 @@ int ksmbd_vfs_remove_acl_xattrs(struct mnt_idmap *idmap, sizeof(XATTR_NAME_POSIX_ACL_ACCESS) - 1) || !strncmp(name, XATTR_NAME_POSIX_ACL_DEFAULT, sizeof(XATTR_NAME_POSIX_ACL_DEFAULT) - 1)) { - err = vfs_remove_acl(idmap, dentry, name); + err = vfs_remove_acl(idmap, path->dentry, name); if (err) ksmbd_debug(SMB, "remove acl xattr failed : %s\n", name); } } + mnt_drop_write(path->mnt); + out: kvfree(xattr_list); return err; } -int ksmbd_vfs_remove_sd_xattrs(struct mnt_idmap *idmap, - struct dentry *dentry) +int ksmbd_vfs_remove_sd_xattrs(struct mnt_idmap *idmap, const struct path *path) { char *name, *xattr_list = NULL; ssize_t xattr_list_len; int err = 0; - xattr_list_len = ksmbd_vfs_listxattr(dentry, &xattr_list); + xattr_list_len = ksmbd_vfs_listxattr(path->dentry, &xattr_list); if (xattr_list_len < 0) { goto out; } else if (!xattr_list_len) { @@ -1297,7 +1348,7 @@ int ksmbd_vfs_remove_sd_xattrs(struct mnt_idmap *idmap, ksmbd_debug(SMB, "%s, len %zd\n", name, strlen(name)); if (!strncmp(name, XATTR_NAME_SD, XATTR_NAME_SD_LEN)) { - err = ksmbd_vfs_remove_xattr(idmap, dentry, name); + err = ksmbd_vfs_remove_xattr(idmap, path, name); if (err) ksmbd_debug(SMB, "remove xattr failed : %s\n", name); } @@ -1374,13 +1425,14 @@ out: int ksmbd_vfs_set_sd_xattr(struct ksmbd_conn *conn, struct mnt_idmap *idmap, - struct dentry *dentry, + const struct path *path, struct smb_ntsd *pntsd, int len) { int rc; struct ndr sd_ndr = {0}, acl_ndr = {0}; struct xattr_ntacl acl = {0}; struct xattr_smb_acl *smb_acl, *def_smb_acl = NULL; + struct dentry *dentry = path->dentry; struct inode *inode = d_inode(dentry); acl.version = 4; @@ -1432,7 +1484,7 @@ int ksmbd_vfs_set_sd_xattr(struct ksmbd_conn *conn, goto out; } - rc = ksmbd_vfs_setxattr(idmap, dentry, + rc = ksmbd_vfs_setxattr(idmap, path, XATTR_NAME_SD, sd_ndr.data, sd_ndr.offset, 0); if (rc < 0) @@ -1522,7 +1574,7 @@ free_n_data: } int ksmbd_vfs_set_dos_attrib_xattr(struct mnt_idmap *idmap, - struct dentry *dentry, + const struct path *path, struct xattr_dos_attrib *da) { struct ndr n; @@ -1532,7 +1584,7 @@ int ksmbd_vfs_set_dos_attrib_xattr(struct mnt_idmap *idmap, if (err) return err; - err = ksmbd_vfs_setxattr(idmap, dentry, XATTR_NAME_DOS_ATTRIBUTE, + err = ksmbd_vfs_setxattr(idmap, path, XATTR_NAME_DOS_ATTRIBUTE, (void *)n.data, n.offset, 0); if (err) ksmbd_debug(SMB, "failed to store dos attribute in xattr\n"); @@ -1769,10 +1821,11 @@ void ksmbd_vfs_posix_lock_unblock(struct file_lock *flock) } int ksmbd_vfs_set_init_posix_acl(struct mnt_idmap *idmap, - struct dentry *dentry) + struct path *path) { struct posix_acl_state acl_state; struct posix_acl *acls; + struct dentry *dentry = path->dentry; struct inode *inode = d_inode(dentry); int rc; @@ -1802,6 +1855,11 @@ int ksmbd_vfs_set_init_posix_acl(struct mnt_idmap *idmap, return -ENOMEM; } posix_state_to_acl(&acl_state, acls->a_entries); + + rc = mnt_want_write(path->mnt); + if (rc) + goto out_err; + rc = set_posix_acl(idmap, dentry, ACL_TYPE_ACCESS, acls); if (rc < 0) ksmbd_debug(SMB, "Set posix acl(ACL_TYPE_ACCESS) failed, rc : %d\n", @@ -1813,16 +1871,20 @@ int ksmbd_vfs_set_init_posix_acl(struct mnt_idmap *idmap, ksmbd_debug(SMB, "Set posix acl(ACL_TYPE_DEFAULT) failed, rc : %d\n", rc); } + mnt_drop_write(path->mnt); + +out_err: free_acl_state(&acl_state); posix_acl_release(acls); return rc; } int ksmbd_vfs_inherit_posix_acl(struct mnt_idmap *idmap, - struct dentry *dentry, struct inode *parent_inode) + struct path *path, struct inode *parent_inode) { struct posix_acl *acls; struct posix_acl_entry *pace; + struct dentry *dentry = path->dentry; struct inode *inode = d_inode(dentry); int rc, i; @@ -1841,6 +1903,10 @@ int ksmbd_vfs_inherit_posix_acl(struct mnt_idmap *idmap, } } + rc = mnt_want_write(path->mnt); + if (rc) + goto out_err; + rc = set_posix_acl(idmap, dentry, ACL_TYPE_ACCESS, acls); if (rc < 0) ksmbd_debug(SMB, "Set posix acl(ACL_TYPE_ACCESS) failed, rc : %d\n", @@ -1852,6 +1918,9 @@ int ksmbd_vfs_inherit_posix_acl(struct mnt_idmap *idmap, ksmbd_debug(SMB, "Set posix acl(ACL_TYPE_DEFAULT) failed, rc : %d\n", rc); } + mnt_drop_write(path->mnt); + +out_err: posix_acl_release(acls); return rc; } diff --git a/fs/smb/server/vfs.h b/fs/smb/server/vfs.h index a4ae89f3230d..8c0931d4d531 100644 --- a/fs/smb/server/vfs.h +++ b/fs/smb/server/vfs.h @@ -108,12 +108,12 @@ ssize_t ksmbd_vfs_casexattr_len(struct mnt_idmap *idmap, struct dentry *dentry, char *attr_name, int attr_name_len); int ksmbd_vfs_setxattr(struct mnt_idmap *idmap, - struct dentry *dentry, const char *attr_name, + const struct path *path, const char *attr_name, void *attr_value, size_t attr_size, int flags); int ksmbd_vfs_xattr_stream_name(char *stream_name, char **xattr_stream_name, size_t *xattr_stream_name_size, int s_type); int ksmbd_vfs_remove_xattr(struct mnt_idmap *idmap, - struct dentry *dentry, char *attr_name); + const struct path *path, char *attr_name); int ksmbd_vfs_kern_path_locked(struct ksmbd_work *work, char *name, unsigned int flags, struct path *path, bool caseless); @@ -139,26 +139,25 @@ void ksmbd_vfs_posix_lock_wait(struct file_lock *flock); int ksmbd_vfs_posix_lock_wait_timeout(struct file_lock *flock, long timeout); void ksmbd_vfs_posix_lock_unblock(struct file_lock *flock); int ksmbd_vfs_remove_acl_xattrs(struct mnt_idmap *idmap, - struct dentry *dentry); -int ksmbd_vfs_remove_sd_xattrs(struct mnt_idmap *idmap, - struct dentry *dentry); + const struct path *path); +int ksmbd_vfs_remove_sd_xattrs(struct mnt_idmap *idmap, const struct path *path); int ksmbd_vfs_set_sd_xattr(struct ksmbd_conn *conn, struct mnt_idmap *idmap, - struct dentry *dentry, + const struct path *path, struct smb_ntsd *pntsd, int len); int ksmbd_vfs_get_sd_xattr(struct ksmbd_conn *conn, struct mnt_idmap *idmap, struct dentry *dentry, struct smb_ntsd **pntsd); int ksmbd_vfs_set_dos_attrib_xattr(struct mnt_idmap *idmap, - struct dentry *dentry, + const struct path *path, struct xattr_dos_attrib *da); int ksmbd_vfs_get_dos_attrib_xattr(struct mnt_idmap *idmap, struct dentry *dentry, struct xattr_dos_attrib *da); int ksmbd_vfs_set_init_posix_acl(struct mnt_idmap *idmap, - struct dentry *dentry); + struct path *path); int ksmbd_vfs_inherit_posix_acl(struct mnt_idmap *idmap, - struct dentry *dentry, + struct path *path, struct inode *parent_inode); #endif /* __KSMBD_VFS_H__ */ diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index 2d0138e72d78..f41f8d6108ce 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -252,7 +252,7 @@ static void __ksmbd_inode_close(struct ksmbd_file *fp) if (ksmbd_stream_fd(fp) && (ci->m_flags & S_DEL_ON_CLS_STREAM)) { ci->m_flags &= ~S_DEL_ON_CLS_STREAM; err = ksmbd_vfs_remove_xattr(file_mnt_idmap(filp), - filp->f_path.dentry, + &filp->f_path, fp->stream.name); if (err) pr_err("remove xattr failed : %s\n", From 5fe7f7b78290638806211046a99f031ff26164e1 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Thu, 15 Jun 2023 22:04:40 +0900 Subject: [PATCH 23/34] ksmbd: fix out-of-bound read in smb2_write ksmbd_smb2_check_message doesn't validate hdr->NextCommand. If ->NextCommand is bigger than Offset + Length of smb2 write, It will allow oversized smb2 write length. It will cause OOB read in smb2_write. Cc: stable@vger.kernel.org Reported-by: zdi-disclosures@trendmicro.com # ZDI-CAN-21164 Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/smb2misc.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/fs/smb/server/smb2misc.c b/fs/smb/server/smb2misc.c index 57749f41b991..33b7e6c4ceff 100644 --- a/fs/smb/server/smb2misc.c +++ b/fs/smb/server/smb2misc.c @@ -351,10 +351,16 @@ int ksmbd_smb2_check_message(struct ksmbd_work *work) int command; __u32 clc_len; /* calculated length */ __u32 len = get_rfc1002_len(work->request_buf); - __u32 req_struct_size; + __u32 req_struct_size, next_cmd = le32_to_cpu(hdr->NextCommand); - if (le32_to_cpu(hdr->NextCommand) > 0) - len = le32_to_cpu(hdr->NextCommand); + if ((u64)work->next_smb2_rcv_hdr_off + next_cmd > len) { + pr_err("next command(%u) offset exceeds smb msg size\n", + next_cmd); + return 1; + } + + if (next_cmd > 0) + len = next_cmd; else if (work->next_smb2_rcv_hdr_off) len -= work->next_smb2_rcv_hdr_off; From 5005bcb4219156f1bf7587b185080ec1da08518e Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Thu, 15 Jun 2023 22:05:29 +0900 Subject: [PATCH 24/34] ksmbd: validate session id and tree id in the compound request This patch validate session id and tree id in compound request. If first operation in the compound is SMB2 ECHO request, ksmbd bypass session and tree validation. So work->sess and work->tcon could be NULL. If secound request in the compound access work->sess or tcon, It cause NULL pointer dereferecing error. Cc: stable@vger.kernel.org Reported-by: zdi-disclosures@trendmicro.com # ZDI-CAN-21165 Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/server.c | 33 +++++++++++++++++++------------ fs/smb/server/smb2pdu.c | 44 ++++++++++++++++++++++++++++++++++++----- 2 files changed, 59 insertions(+), 18 deletions(-) diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c index f9b2e0f19b03..ced7a9e916f0 100644 --- a/fs/smb/server/server.c +++ b/fs/smb/server/server.c @@ -185,24 +185,31 @@ static void __handle_ksmbd_work(struct ksmbd_work *work, goto send; } - if (conn->ops->check_user_session) { - rc = conn->ops->check_user_session(work); - if (rc < 0) { - command = conn->ops->get_cmd_val(work); - conn->ops->set_rsp_status(work, - STATUS_USER_SESSION_DELETED); - goto send; - } else if (rc > 0) { - rc = conn->ops->get_ksmbd_tcon(work); + do { + if (conn->ops->check_user_session) { + rc = conn->ops->check_user_session(work); if (rc < 0) { - conn->ops->set_rsp_status(work, - STATUS_NETWORK_NAME_DELETED); + if (rc == -EINVAL) + conn->ops->set_rsp_status(work, + STATUS_INVALID_PARAMETER); + else + conn->ops->set_rsp_status(work, + STATUS_USER_SESSION_DELETED); goto send; + } else if (rc > 0) { + rc = conn->ops->get_ksmbd_tcon(work); + if (rc < 0) { + if (rc == -EINVAL) + conn->ops->set_rsp_status(work, + STATUS_INVALID_PARAMETER); + else + conn->ops->set_rsp_status(work, + STATUS_NETWORK_NAME_DELETED); + goto send; + } } } - } - do { rc = __process_request(work, conn, &command); if (rc == SERVER_HANDLER_ABORT) break; diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index ccecdb71d2bc..da1787c68ba0 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -91,7 +91,6 @@ int smb2_get_ksmbd_tcon(struct ksmbd_work *work) unsigned int cmd = le16_to_cpu(req_hdr->Command); int tree_id; - work->tcon = NULL; if (cmd == SMB2_TREE_CONNECT_HE || cmd == SMB2_CANCEL_HE || cmd == SMB2_LOGOFF_HE) { @@ -105,10 +104,28 @@ int smb2_get_ksmbd_tcon(struct ksmbd_work *work) } tree_id = le32_to_cpu(req_hdr->Id.SyncId.TreeId); + + /* + * If request is not the first in Compound request, + * Just validate tree id in header with work->tcon->id. + */ + if (work->next_smb2_rcv_hdr_off) { + if (!work->tcon) { + pr_err("The first operation in the compound does not have tcon\n"); + return -EINVAL; + } + if (work->tcon->id != tree_id) { + pr_err("tree id(%u) is different with id(%u) in first operation\n", + tree_id, work->tcon->id); + return -EINVAL; + } + return 1; + } + work->tcon = ksmbd_tree_conn_lookup(work->sess, tree_id); if (!work->tcon) { pr_err("Invalid tid %d\n", tree_id); - return -EINVAL; + return -ENOENT; } return 1; @@ -547,7 +564,6 @@ int smb2_check_user_session(struct ksmbd_work *work) unsigned int cmd = conn->ops->get_cmd_val(work); unsigned long long sess_id; - work->sess = NULL; /* * SMB2_ECHO, SMB2_NEGOTIATE, SMB2_SESSION_SETUP command do not * require a session id, so no need to validate user session's for @@ -558,15 +574,33 @@ int smb2_check_user_session(struct ksmbd_work *work) return 0; if (!ksmbd_conn_good(conn)) - return -EINVAL; + return -EIO; sess_id = le64_to_cpu(req_hdr->SessionId); + + /* + * If request is not the first in Compound request, + * Just validate session id in header with work->sess->id. + */ + if (work->next_smb2_rcv_hdr_off) { + if (!work->sess) { + pr_err("The first operation in the compound does not have sess\n"); + return -EINVAL; + } + if (work->sess->id != sess_id) { + pr_err("session id(%llu) is different with the first operation(%lld)\n", + sess_id, work->sess->id); + return -EINVAL; + } + return 1; + } + /* Check for validity of user session */ work->sess = ksmbd_session_lookup_all(conn, sess_id); if (work->sess) return 1; ksmbd_debug(SMB, "Invalid user session, Uid %llu\n", sess_id); - return -EINVAL; + return -ENOENT; } static void destroy_previous_session(struct ksmbd_conn *conn, From 9636be85cc5bdd8b7a7f6a53405cbcc52161c93c Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Tue, 23 May 2023 10:14:21 -0700 Subject: [PATCH 25/34] x86/hyperv: Fix hyperv_pcpu_input_arg handling when CPUs go online/offline These commits a494aef23dfc ("PCI: hv: Replace retarget_msi_interrupt_params with hyperv_pcpu_input_arg") 2c6ba4216844 ("PCI: hv: Enable PCI pass-thru devices in Confidential VMs") update the Hyper-V virtual PCI driver to use the hyperv_pcpu_input_arg because that memory will be correctly marked as decrypted or encrypted for all VM types (CoCo or normal). But problems ensue when CPUs in the VM go online or offline after virtual PCI devices have been configured. When a CPU is brought online, the hyperv_pcpu_input_arg for that CPU is initialized by hv_cpu_init() running under state CPUHP_AP_ONLINE_DYN. But this state occurs after state CPUHP_AP_IRQ_AFFINITY_ONLINE, which may call the virtual PCI driver and fault trying to use the as yet uninitialized hyperv_pcpu_input_arg. A similar problem occurs in a CoCo VM if the MMIO read and write hypercalls are used from state CPUHP_AP_IRQ_AFFINITY_ONLINE. When a CPU is taken offline, IRQs may be reassigned in state CPUHP_TEARDOWN_CPU. Again, the virtual PCI driver may fault trying to use the hyperv_pcpu_input_arg that has already been freed by a higher state. Fix the onlining problem by adding state CPUHP_AP_HYPERV_ONLINE immediately after CPUHP_AP_ONLINE_IDLE (similar to CPUHP_AP_KVM_ONLINE) and before CPUHP_AP_IRQ_AFFINITY_ONLINE. Use this new state for Hyper-V initialization so that hyperv_pcpu_input_arg is allocated early enough. Fix the offlining problem by not freeing hyperv_pcpu_input_arg when a CPU goes offline. Retain the allocated memory, and reuse it if the CPU comes back online later. Signed-off-by: Michael Kelley Reviewed-by: Vitaly Kuznetsov Acked-by: Borislav Petkov (AMD) Reviewed-by: Dexuan Cui Link: https://lore.kernel.org/r/1684862062-51576-1-git-send-email-mikelley@microsoft.com Signed-off-by: Wei Liu --- arch/x86/hyperv/hv_init.c | 2 +- drivers/hv/hv_common.c | 48 +++++++++++++++++++------------------- include/linux/cpuhotplug.h | 1 + 3 files changed, 26 insertions(+), 25 deletions(-) diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index a5f9474f08e1..6c04b52f139b 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -416,7 +416,7 @@ void __init hyperv_init(void) goto free_vp_assist_page; } - cpuhp = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/hyperv_init:online", + cpuhp = cpuhp_setup_state(CPUHP_AP_HYPERV_ONLINE, "x86/hyperv_init:online", hv_cpu_init, hv_cpu_die); if (cpuhp < 0) goto free_ghcb_page; diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c index 64f9ceca887b..542a1d53b303 100644 --- a/drivers/hv/hv_common.c +++ b/drivers/hv/hv_common.c @@ -364,13 +364,20 @@ int hv_common_cpu_init(unsigned int cpu) flags = irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL; inputarg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg); - *inputarg = kmalloc(pgcount * HV_HYP_PAGE_SIZE, flags); - if (!(*inputarg)) - return -ENOMEM; - if (hv_root_partition) { - outputarg = (void **)this_cpu_ptr(hyperv_pcpu_output_arg); - *outputarg = (char *)(*inputarg) + HV_HYP_PAGE_SIZE; + /* + * hyperv_pcpu_input_arg and hyperv_pcpu_output_arg memory is already + * allocated if this CPU was previously online and then taken offline + */ + if (!*inputarg) { + *inputarg = kmalloc(pgcount * HV_HYP_PAGE_SIZE, flags); + if (!(*inputarg)) + return -ENOMEM; + + if (hv_root_partition) { + outputarg = (void **)this_cpu_ptr(hyperv_pcpu_output_arg); + *outputarg = (char *)(*inputarg) + HV_HYP_PAGE_SIZE; + } } msr_vp_index = hv_get_register(HV_REGISTER_VP_INDEX); @@ -385,24 +392,17 @@ int hv_common_cpu_init(unsigned int cpu) int hv_common_cpu_die(unsigned int cpu) { - unsigned long flags; - void **inputarg, **outputarg; - void *mem; - - local_irq_save(flags); - - inputarg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg); - mem = *inputarg; - *inputarg = NULL; - - if (hv_root_partition) { - outputarg = (void **)this_cpu_ptr(hyperv_pcpu_output_arg); - *outputarg = NULL; - } - - local_irq_restore(flags); - - kfree(mem); + /* + * The hyperv_pcpu_input_arg and hyperv_pcpu_output_arg memory + * is not freed when the CPU goes offline as the hyperv_pcpu_input_arg + * may be used by the Hyper-V vPCI driver in reassigning interrupts + * as part of the offlining process. The interrupt reassignment + * happens *after* the CPUHP_AP_HYPERV_ONLINE state has run and + * called this function. + * + * If a previously offlined CPU is brought back online again, the + * originally allocated memory is reused in hv_common_cpu_init(). + */ return 0; } diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 0f1001dca0e0..3ceb9dfa0993 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -200,6 +200,7 @@ enum cpuhp_state { /* Online section invoked on the hotplugged CPU from the hotplug thread */ CPUHP_AP_ONLINE_IDLE, + CPUHP_AP_HYPERV_ONLINE, CPUHP_AP_KVM_ONLINE, CPUHP_AP_SCHED_WAIT_EMPTY, CPUHP_AP_SMPBOOT_THREADS, From 52ae076c3a9b366b6fa9f7c7e67aed8b28716ed9 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Tue, 23 May 2023 10:14:22 -0700 Subject: [PATCH 26/34] arm64/hyperv: Use CPUHP_AP_HYPERV_ONLINE state to fix CPU online sequencing State CPUHP_AP_HYPERV_ONLINE has been introduced to correctly sequence the initialization of hyperv_pcpu_input_arg. Use this new state for Hyper-V initialization so that hyperv_pcpu_input_arg is allocated early enough. Signed-off-by: Michael Kelley Reviewed-by: Dexuan Cui Link: https://lore.kernel.org/r/1684862062-51576-2-git-send-email-mikelley@microsoft.com Signed-off-by: Wei Liu --- arch/arm64/hyperv/mshyperv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/hyperv/mshyperv.c b/arch/arm64/hyperv/mshyperv.c index a406454578f0..f1b8a04ee9f2 100644 --- a/arch/arm64/hyperv/mshyperv.c +++ b/arch/arm64/hyperv/mshyperv.c @@ -67,7 +67,7 @@ static int __init hyperv_init(void) if (ret) return ret; - ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "arm64/hyperv_init:online", + ret = cpuhp_setup_state(CPUHP_AP_HYPERV_ONLINE, "arm64/hyperv_init:online", hv_common_cpu_init, hv_common_cpu_die); if (ret < 0) { hv_common_free(); From 440b5e3663271b0ffbd4908115044a6a51fb938b Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Wed, 14 Jun 2023 21:44:47 -0700 Subject: [PATCH 27/34] PCI: hv: Fix a race condition bug in hv_pci_query_relations() Since day 1 of the driver, there has been a race between hv_pci_query_relations() and survey_child_resources(): during fast device hotplug, hv_pci_query_relations() may error out due to device-remove and the stack variable 'comp' is no longer valid; however, pci_devices_present_work() -> survey_child_resources() -> complete() may be running on another CPU and accessing the no-longer-valid 'comp'. Fix the race by flushing the workqueue before we exit from hv_pci_query_relations(). Fixes: 4daace0d8ce8 ("PCI: hv: Add paravirtual PCI front-end for Microsoft Hyper-V VMs") Signed-off-by: Dexuan Cui Reviewed-by: Michael Kelley Acked-by: Lorenzo Pieralisi Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230615044451.5580-2-decui@microsoft.com Signed-off-by: Wei Liu --- drivers/pci/controller/pci-hyperv.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index bc32662c6bb7..ea8862e656b6 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -3401,6 +3401,24 @@ static int hv_pci_query_relations(struct hv_device *hdev) if (!ret) ret = wait_for_response(hdev, &comp); + /* + * In the case of fast device addition/removal, it's possible that + * vmbus_sendpacket() or wait_for_response() returns -ENODEV but we + * already got a PCI_BUS_RELATIONS* message from the host and the + * channel callback already scheduled a work to hbus->wq, which can be + * running pci_devices_present_work() -> survey_child_resources() -> + * complete(&hbus->survey_event), even after hv_pci_query_relations() + * exits and the stack variable 'comp' is no longer valid; as a result, + * a hang or a page fault may happen when the complete() calls + * raw_spin_lock_irqsave(). Flush hbus->wq before we exit from + * hv_pci_query_relations() to avoid the issues. Note: if 'ret' is + * -ENODEV, there can't be any more work item scheduled to hbus->wq + * after the flush_workqueue(): see vmbus_onoffer_rescind() -> + * vmbus_reset_channel_cb(), vmbus_rescind_cleanup() -> + * channel->rescind = true. + */ + flush_workqueue(hbus->wq); + return ret; } From 2738d5ab7929a845b654cd171a1e275c37eb428e Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Wed, 14 Jun 2023 21:44:48 -0700 Subject: [PATCH 28/34] PCI: hv: Fix a race condition in hv_irq_unmask() that can cause panic When the host tries to remove a PCI device, the host first sends a PCI_EJECT message to the guest, and the guest is supposed to gracefully remove the PCI device and send a PCI_EJECTION_COMPLETE message to the host; the host then sends a VMBus message CHANNELMSG_RESCIND_CHANNELOFFER to the guest (when the guest receives this message, the device is already unassigned from the guest) and the guest can do some final cleanup work; if the guest fails to respond to the PCI_EJECT message within one minute, the host sends the VMBus message CHANNELMSG_RESCIND_CHANNELOFFER and removes the PCI device forcibly. In the case of fast device addition/removal, it's possible that the PCI device driver is still configuring MSI-X interrupts when the guest receives the PCI_EJECT message; the channel callback calls hv_pci_eject_device(), which sets hpdev->state to hv_pcichild_ejecting, and schedules a work hv_eject_device_work(); if the PCI device driver is calling pci_alloc_irq_vectors() -> ... -> hv_compose_msi_msg(), we can break the while loop in hv_compose_msi_msg() due to the updated hpdev->state, and leave data->chip_data with its default value of NULL; later, when the PCI device driver calls request_irq() -> ... -> hv_irq_unmask(), the guest crashes in hv_arch_irq_unmask() due to data->chip_data being NULL. Fix the issue by not testing hpdev->state in the while loop: when the guest receives PCI_EJECT, the device is still assigned to the guest, and the guest has one minute to finish the device removal gracefully. We don't really need to (and we should not) test hpdev->state in the loop. Fixes: de0aa7b2f97d ("PCI: hv: Fix 2 hang issues in hv_compose_msi_msg()") Signed-off-by: Dexuan Cui Reviewed-by: Michael Kelley Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230615044451.5580-3-decui@microsoft.com Signed-off-by: Wei Liu --- drivers/pci/controller/pci-hyperv.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index ea8862e656b6..733637d96765 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -635,6 +635,11 @@ static void hv_arch_irq_unmask(struct irq_data *data) pbus = pdev->bus; hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata); int_desc = data->chip_data; + if (!int_desc) { + dev_warn(&hbus->hdev->device, "%s() can not unmask irq %u\n", + __func__, data->irq); + return; + } local_irq_save(flags); @@ -2004,12 +2009,6 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) hv_pci_onchannelcallback(hbus); spin_unlock_irqrestore(&channel->sched_lock, flags); - if (hpdev->state == hv_pcichild_ejecting) { - dev_err_once(&hbus->hdev->device, - "the device is being ejected\n"); - goto enable_tasklet; - } - udelay(100); } From add9195e69c94b32e96f78c2f9cea68f0e850b3f Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Wed, 14 Jun 2023 21:44:49 -0700 Subject: [PATCH 29/34] PCI: hv: Remove the useless hv_pcichild_state from struct hv_pci_dev The hpdev->state is never really useful. The only use in hv_pci_eject_device() and hv_eject_device_work() is not really necessary. Signed-off-by: Dexuan Cui Reviewed-by: Michael Kelley Acked-by: Lorenzo Pieralisi Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230615044451.5580-4-decui@microsoft.com Signed-off-by: Wei Liu --- drivers/pci/controller/pci-hyperv.c | 12 ------------ 1 file changed, 12 deletions(-) diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index 733637d96765..a826b41c949a 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -545,19 +545,10 @@ struct hv_dr_state { struct hv_pcidev_description func[]; }; -enum hv_pcichild_state { - hv_pcichild_init = 0, - hv_pcichild_requirements, - hv_pcichild_resourced, - hv_pcichild_ejecting, - hv_pcichild_maximum -}; - struct hv_pci_dev { /* List protected by pci_rescan_remove_lock */ struct list_head list_entry; refcount_t refs; - enum hv_pcichild_state state; struct pci_slot *pci_slot; struct hv_pcidev_description desc; bool reported_missing; @@ -2843,8 +2834,6 @@ static void hv_eject_device_work(struct work_struct *work) hpdev = container_of(work, struct hv_pci_dev, wrk); hbus = hpdev->hbus; - WARN_ON(hpdev->state != hv_pcichild_ejecting); - /* * Ejection can come before or after the PCI bus has been set up, so * attempt to find it and tear down the bus state, if it exists. This @@ -2901,7 +2890,6 @@ static void hv_pci_eject_device(struct hv_pci_dev *hpdev) return; } - hpdev->state = hv_pcichild_ejecting; get_pcichild(hpdev); INIT_WORK(&hpdev->wrk, hv_eject_device_work); queue_work(hbus->wq, &hpdev->wrk); From a847234e24d03d01a9566d1d9dcce018cc018d67 Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Wed, 14 Jun 2023 21:44:50 -0700 Subject: [PATCH 30/34] Revert "PCI: hv: Fix a timing issue which causes kdump to fail occasionally" This reverts commit d6af2ed29c7c1c311b96dac989dcb991e90ee195. The statement "the hv_pci_bus_exit() call releases structures of all its child devices" in commit d6af2ed29c7c is not true: in the path hv_pci_probe() -> hv_pci_enter_d0() -> hv_pci_bus_exit(hdev, true): the parameter "keep_devs" is true, so hv_pci_bus_exit() does *not* release the child "struct hv_pci_dev *hpdev" that is created earlier in pci_devices_present_work() -> new_pcichild_device(). The commit d6af2ed29c7c was originally made in July 2020 for RHEL 7.7, where the old version of hv_pci_bus_exit() was used; when the commit was rebased and merged into the upstream, people didn't notice that it's not really necessary. The commit itself doesn't cause any issue, but it makes hv_pci_probe() more complicated. Revert it to facilitate some upcoming changes to hv_pci_probe(). Signed-off-by: Dexuan Cui Reviewed-by: Michael Kelley Acked-by: Wei Hu Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230615044451.5580-5-decui@microsoft.com Signed-off-by: Wei Liu --- drivers/pci/controller/pci-hyperv.c | 71 ++++++++++++++--------------- 1 file changed, 34 insertions(+), 37 deletions(-) diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index a826b41c949a..1a5296fad1c4 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -3318,8 +3318,10 @@ static int hv_pci_enter_d0(struct hv_device *hdev) struct pci_bus_d0_entry *d0_entry; struct hv_pci_compl comp_pkt; struct pci_packet *pkt; + bool retry = true; int ret; +enter_d0_retry: /* * Tell the host that the bus is ready to use, and moved into the * powered-on state. This includes telling the host which region @@ -3346,6 +3348,38 @@ static int hv_pci_enter_d0(struct hv_device *hdev) if (ret) goto exit; + /* + * In certain case (Kdump) the pci device of interest was + * not cleanly shut down and resource is still held on host + * side, the host could return invalid device status. + * We need to explicitly request host to release the resource + * and try to enter D0 again. + */ + if (comp_pkt.completion_status < 0 && retry) { + retry = false; + + dev_err(&hdev->device, "Retrying D0 Entry\n"); + + /* + * Hv_pci_bus_exit() calls hv_send_resource_released() + * to free up resources of its child devices. + * In the kdump kernel we need to set the + * wslot_res_allocated to 255 so it scans all child + * devices to release resources allocated in the + * normal kernel before panic happened. + */ + hbus->wslot_res_allocated = 255; + + ret = hv_pci_bus_exit(hdev, true); + + if (ret == 0) { + kfree(pkt); + goto enter_d0_retry; + } + dev_err(&hdev->device, + "Retrying D0 failed with ret %d\n", ret); + } + if (comp_pkt.completion_status < 0) { dev_err(&hdev->device, "PCI Pass-through VSP failed D0 Entry with status %x\n", @@ -3591,7 +3625,6 @@ static int hv_pci_probe(struct hv_device *hdev, struct hv_pcibus_device *hbus; u16 dom_req, dom; char *name; - bool enter_d0_retry = true; int ret; bridge = devm_pci_alloc_host_bridge(&hdev->device, 0); @@ -3708,47 +3741,11 @@ static int hv_pci_probe(struct hv_device *hdev, if (ret) goto free_fwnode; -retry: ret = hv_pci_query_relations(hdev); if (ret) goto free_irq_domain; ret = hv_pci_enter_d0(hdev); - /* - * In certain case (Kdump) the pci device of interest was - * not cleanly shut down and resource is still held on host - * side, the host could return invalid device status. - * We need to explicitly request host to release the resource - * and try to enter D0 again. - * Since the hv_pci_bus_exit() call releases structures - * of all its child devices, we need to start the retry from - * hv_pci_query_relations() call, requesting host to send - * the synchronous child device relations message before this - * information is needed in hv_send_resources_allocated() - * call later. - */ - if (ret == -EPROTO && enter_d0_retry) { - enter_d0_retry = false; - - dev_err(&hdev->device, "Retrying D0 Entry\n"); - - /* - * Hv_pci_bus_exit() calls hv_send_resources_released() - * to free up resources of its child devices. - * In the kdump kernel we need to set the - * wslot_res_allocated to 255 so it scans all child - * devices to release resources allocated in the - * normal kernel before panic happened. - */ - hbus->wslot_res_allocated = 255; - ret = hv_pci_bus_exit(hdev, true); - - if (ret == 0) - goto retry; - - dev_err(&hdev->device, - "Retrying D0 failed with ret %d\n", ret); - } if (ret) goto free_irq_domain; From 067d6ec7ed5b49380688e06c1e5f883a71bef4fe Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Wed, 14 Jun 2023 21:44:51 -0700 Subject: [PATCH 31/34] PCI: hv: Add a per-bus mutex state_lock In the case of fast device addition/removal, it's possible that hv_eject_device_work() can start to run before create_root_hv_pci_bus() starts to run; as a result, the pci_get_domain_bus_and_slot() in hv_eject_device_work() can return a 'pdev' of NULL, and hv_eject_device_work() can remove the 'hpdev', and immediately send a message PCI_EJECTION_COMPLETE to the host, and the host immediately unassigns the PCI device from the guest; meanwhile, create_root_hv_pci_bus() and the PCI device driver can be probing the dead PCI device and reporting timeout errors. Fix the issue by adding a per-bus mutex 'state_lock' and grabbing the mutex before powering on the PCI bus in hv_pci_enter_d0(): when hv_eject_device_work() starts to run, it's able to find the 'pdev' and call pci_stop_and_remove_bus_device(pdev): if the PCI device driver has loaded, the PCI device driver's probe() function is already called in create_root_hv_pci_bus() -> pci_bus_add_devices(), and now hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to call the PCI device driver's remove() function and remove the device reliably; if the PCI device driver hasn't loaded yet, the function call hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to remove the PCI device reliably and the PCI device driver's probe() function won't be called; if the PCI device driver's probe() is already running (e.g., systemd-udev is loading the PCI device driver), it must be holding the per-device lock, and after the probe() finishes and releases the lock, hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to proceed to remove the device reliably. Fixes: 4daace0d8ce8 ("PCI: hv: Add paravirtual PCI front-end for Microsoft Hyper-V VMs") Signed-off-by: Dexuan Cui Reviewed-by: Michael Kelley Acked-by: Lorenzo Pieralisi Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230615044451.5580-6-decui@microsoft.com Signed-off-by: Wei Liu --- drivers/pci/controller/pci-hyperv.c | 29 ++++++++++++++++++++++++++--- 1 file changed, 26 insertions(+), 3 deletions(-) diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index 1a5296fad1c4..2d93d0c4f10d 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -489,7 +489,10 @@ struct hv_pcibus_device { struct fwnode_handle *fwnode; /* Protocol version negotiated with the host */ enum pci_protocol_version_t protocol_version; + + struct mutex state_lock; enum hv_pcibus_state state; + struct hv_device *hdev; resource_size_t low_mmio_space; resource_size_t high_mmio_space; @@ -2605,6 +2608,8 @@ static void pci_devices_present_work(struct work_struct *work) if (!dr) return; + mutex_lock(&hbus->state_lock); + /* First, mark all existing children as reported missing. */ spin_lock_irqsave(&hbus->device_list_lock, flags); list_for_each_entry(hpdev, &hbus->children, list_entry) { @@ -2686,6 +2691,8 @@ static void pci_devices_present_work(struct work_struct *work) break; } + mutex_unlock(&hbus->state_lock); + kfree(dr); } @@ -2834,6 +2841,8 @@ static void hv_eject_device_work(struct work_struct *work) hpdev = container_of(work, struct hv_pci_dev, wrk); hbus = hpdev->hbus; + mutex_lock(&hbus->state_lock); + /* * Ejection can come before or after the PCI bus has been set up, so * attempt to find it and tear down the bus state, if it exists. This @@ -2870,6 +2879,8 @@ static void hv_eject_device_work(struct work_struct *work) put_pcichild(hpdev); put_pcichild(hpdev); /* hpdev has been freed. Do not use it any more. */ + + mutex_unlock(&hbus->state_lock); } /** @@ -3636,6 +3647,7 @@ static int hv_pci_probe(struct hv_device *hdev, return -ENOMEM; hbus->bridge = bridge; + mutex_init(&hbus->state_lock); hbus->state = hv_pcibus_init; hbus->wslot_res_allocated = -1; @@ -3745,9 +3757,11 @@ static int hv_pci_probe(struct hv_device *hdev, if (ret) goto free_irq_domain; + mutex_lock(&hbus->state_lock); + ret = hv_pci_enter_d0(hdev); if (ret) - goto free_irq_domain; + goto release_state_lock; ret = hv_pci_allocate_bridge_windows(hbus); if (ret) @@ -3765,12 +3779,15 @@ static int hv_pci_probe(struct hv_device *hdev, if (ret) goto free_windows; + mutex_unlock(&hbus->state_lock); return 0; free_windows: hv_pci_free_bridge_windows(hbus); exit_d0: (void) hv_pci_bus_exit(hdev, true); +release_state_lock: + mutex_unlock(&hbus->state_lock); free_irq_domain: irq_domain_remove(hbus->irq_domain); free_fwnode: @@ -4020,20 +4037,26 @@ static int hv_pci_resume(struct hv_device *hdev) if (ret) goto out; + mutex_lock(&hbus->state_lock); + ret = hv_pci_enter_d0(hdev); if (ret) - goto out; + goto release_state_lock; ret = hv_send_resources_allocated(hdev); if (ret) - goto out; + goto release_state_lock; prepopulate_bars(hbus); hv_pci_restore_msi_state(hbus); hbus->state = hv_pcibus_installed; + mutex_unlock(&hbus->state_lock); return 0; + +release_state_lock: + mutex_unlock(&hbus->state_lock); out: vmbus_close(hdev->channel); return ret; From a2b6f2ab3e144f8e23666aafeba0e4d9ea4b7975 Mon Sep 17 00:00:00 2001 From: "Vishal Moola (Oracle)" Date: Wed, 7 Jun 2023 13:41:19 -0700 Subject: [PATCH 32/34] afs: Fix dangling folio ref counts in writeback Commit acc8d8588cb7 converted afs_writepages_region() to write back a folio batch. If writeback needs rescheduling, the function exits without dropping the references to the folios in fbatch. This patch fixes that. [DH: Moved the added line before the _leave()] Fixes: acc8d8588cb7 ("afs: convert afs_writepages_region() to use filemap_get_folios_tag()") Signed-off-by: Vishal Moola (Oracle) Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org Link: https://lore.kernel.org/r/20230607204120.89416-1-vishal.moola@gmail.com/ --- fs/afs/write.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/afs/write.c b/fs/afs/write.c index c822d6006033..fd433024070e 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -763,6 +763,7 @@ static int afs_writepages_region(struct address_space *mapping, if (wbc->sync_mode == WB_SYNC_NONE) { if (skips >= 5 || need_resched()) { *_next = start; + folio_batch_release(&fbatch); _leave(" = 0 [%llx]", *_next); return 0; } From 819da022dd007398d0c42ebcd8dbb1b681acea53 Mon Sep 17 00:00:00 2001 From: "Vishal Moola (Oracle)" Date: Wed, 7 Jun 2023 13:41:20 -0700 Subject: [PATCH 33/34] afs: Fix waiting for writeback then skipping folio Commit acc8d8588cb7 converted afs_writepages_region() to write back a folio batch. The function waits for writeback to a folio, but then proceeds to the rest of the batch without trying to write that folio again. This patch fixes has it attempt to write the folio again. [DH: Also remove an 'else' that adding a goto makes redundant] Fixes: acc8d8588cb7 ("afs: convert afs_writepages_region() to use filemap_get_folios_tag()") Signed-off-by: Vishal Moola (Oracle) Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org Link: https://lore.kernel.org/r/20230607204120.89416-2-vishal.moola@gmail.com/ --- fs/afs/write.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/afs/write.c b/fs/afs/write.c index fd433024070e..8750b99c3f56 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -731,6 +731,7 @@ static int afs_writepages_region(struct address_space *mapping, * (changing page->mapping to NULL), or even swizzled * back from swapper_space to tmpfs file mapping */ +try_again: if (wbc->sync_mode != WB_SYNC_NONE) { ret = folio_lock_killable(folio); if (ret < 0) { @@ -757,9 +758,10 @@ static int afs_writepages_region(struct address_space *mapping, #ifdef CONFIG_AFS_FSCACHE folio_wait_fscache(folio); #endif - } else { - start += folio_size(folio); + goto try_again; } + + start += folio_size(folio); if (wbc->sync_mode == WB_SYNC_NONE) { if (skips >= 5 || need_resched()) { *_next = start; From a7299a18a179a9713651fce9ad00972a633c14a9 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Tue, 20 Jun 2023 17:57:31 +0800 Subject: [PATCH 34/34] btrfs: fix u32 overflows when left shifting stripe_nr [BUG] David reported an ASSERT() get triggered during fio load on 8 devices with data/raid6 and metadata/raid1c3: fio --rw=randrw --randrepeat=1 --size=3000m \ --bsrange=512b-64k --bs_unaligned \ --ioengine=libaio --fsync=1024 \ --name=job0 --name=job1 \ The ASSERT() is from rbio_add_bio() of raid56.c: ASSERT(orig_logical >= full_stripe_start && orig_logical + orig_len <= full_stripe_start + rbio->nr_data * BTRFS_STRIPE_LEN); Which is checking if the target rbio is crossing the full stripe boundary. [100.789] assertion failed: orig_logical >= full_stripe_start && orig_logical + orig_len <= full_stripe_start + rbio->nr_data * BTRFS_STRIPE_LEN, in fs/btrfs/raid56.c:1622 [100.795] ------------[ cut here ]------------ [100.796] kernel BUG at fs/btrfs/raid56.c:1622! [100.797] invalid opcode: 0000 [#1] PREEMPT SMP KASAN [100.798] CPU: 1 PID: 100 Comm: kworker/u8:4 Not tainted 6.4.0-rc6-default+ #124 [100.799] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552-rebuilt.opensuse.org 04/01/2014 [100.802] Workqueue: writeback wb_workfn (flush-btrfs-1) [100.803] RIP: 0010:rbio_add_bio+0x204/0x210 [btrfs] [100.806] RSP: 0018:ffff888104a8f300 EFLAGS: 00010246 [100.808] RAX: 00000000000000a1 RBX: ffff8881075907e0 RCX: ffffed1020951e01 [100.809] RDX: 0000000000000000 RSI: 0000000000000008 RDI: 0000000000000001 [100.811] RBP: 0000000141d20000 R08: 0000000000000001 R09: ffff888104a8f04f [100.813] R10: ffffed1020951e09 R11: 0000000000000003 R12: ffff88810e87f400 [100.815] R13: 0000000041d20000 R14: 0000000144529000 R15: ffff888101524000 [100.817] FS: 0000000000000000(0000) GS:ffff88811ac00000(0000) knlGS:0000000000000000 [100.821] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [100.822] CR2: 000055d54e44c270 CR3: 000000010a9a1006 CR4: 00000000003706a0 [100.824] Call Trace: [100.825] [100.825] ? die+0x32/0x80 [100.826] ? do_trap+0x12d/0x160 [100.827] ? rbio_add_bio+0x204/0x210 [btrfs] [100.827] ? rbio_add_bio+0x204/0x210 [btrfs] [100.829] ? do_error_trap+0x90/0x130 [100.830] ? rbio_add_bio+0x204/0x210 [btrfs] [100.831] ? handle_invalid_op+0x2c/0x30 [100.833] ? rbio_add_bio+0x204/0x210 [btrfs] [100.835] ? exc_invalid_op+0x29/0x40 [100.836] ? asm_exc_invalid_op+0x16/0x20 [100.837] ? rbio_add_bio+0x204/0x210 [btrfs] [100.837] raid56_parity_write+0x64/0x270 [btrfs] [100.838] btrfs_submit_chunk+0x26e/0x800 [btrfs] [100.840] ? btrfs_bio_init+0x80/0x80 [btrfs] [100.841] ? release_pages+0x503/0x6d0 [100.842] ? folio_unlock+0x2f/0x60 [100.844] ? __folio_put+0x60/0x60 [100.845] ? btrfs_do_readpage+0xae0/0xae0 [btrfs] [100.847] btrfs_submit_bio+0x21/0x60 [btrfs] [100.847] submit_one_bio+0x6a/0xb0 [btrfs] [100.849] extent_write_cache_pages+0x395/0x680 [btrfs] [100.850] ? __extent_writepage+0x520/0x520 [btrfs] [100.851] ? mark_usage+0x190/0x190 [100.852] extent_writepages+0xdb/0x130 [btrfs] [100.853] ? extent_write_locked_range+0x480/0x480 [btrfs] [100.854] ? mark_usage+0x190/0x190 [100.854] ? attach_extent_buffer_page+0x220/0x220 [btrfs] [100.855] ? reacquire_held_locks+0x178/0x280 [100.856] ? writeback_sb_inodes+0x245/0x7f0 [100.857] do_writepages+0x102/0x2e0 [100.858] ? page_writeback_cpu_online+0x10/0x10 [100.859] ? __lock_release.isra.0+0x14a/0x4d0 [100.860] ? reacquire_held_locks+0x280/0x280 [100.861] ? __lock_acquired+0x1e9/0x3d0 [100.862] ? do_raw_spin_lock+0x1b0/0x1b0 [100.863] __writeback_single_inode+0x94/0x450 [100.864] writeback_sb_inodes+0x372/0x7f0 [100.864] ? lock_sync+0xd0/0xd0 [100.865] ? do_raw_spin_unlock+0x93/0xf0 [100.866] ? sync_inode_metadata+0xc0/0xc0 [100.867] ? rwsem_optimistic_spin+0x340/0x340 [100.868] __writeback_inodes_wb+0x70/0x130 [100.869] wb_writeback+0x2d1/0x530 [100.869] ? __writeback_inodes_wb+0x130/0x130 [100.870] ? lockdep_hardirqs_on_prepare.part.0+0xf1/0x1c0 [100.870] wb_do_writeback+0x3eb/0x480 [100.871] ? wb_writeback+0x530/0x530 [100.871] ? mark_lock_irq+0xcd0/0xcd0 [100.872] wb_workfn+0xe0/0x3f0< [CAUSE] Commit a97699d1d610 ("btrfs: replace map_lookup->stripe_len by BTRFS_STRIPE_LEN") changes how we calculate the map length, to reduce u64 division. Function btrfs_max_io_len() is to get the length to the stripe boundary. It calculates the full stripe start offset (inside the chunk) by the following code: *full_stripe_start = rounddown(*stripe_nr, nr_data_stripes(map)) << BTRFS_STRIPE_LEN_SHIFT; The calculation itself is fine, but the value returned by rounddown() is dependent on both @stripe_nr (which is u32) and nr_data_stripes() (which returned int). Thus the result is also u32, then we do the left shift, which can overflow u32. If such overflow happens, @full_stripe_start will be a value way smaller than @offset, causing later "full_stripe_len - (offset - *full_stripe_start)" to underflow, thus make later length calculation to have no stripe boundary limit, resulting a write bio to exceed stripe boundary. There are some other locations like this, with a u32 @stripe_nr got left shift, which can lead to a similar overflow. [FIX] Fix all @stripe_nr with left shift with a type cast to u64 before the left shift. Those involved @stripe_nr or similar variables are recording the stripe number inside the chunk, which is small enough to be contained by u32, but their offset inside the chunk can not fit into u32. Thus for those specific left shifts, a type cast to u64 is necessary so this patch does not touch them and the code will be cleaned up in the future to keep the fix minimal. Reported-by: David Sterba Fixes: a97699d1d610 ("btrfs: replace map_lookup->stripe_len by BTRFS_STRIPE_LEN") Tested-by: David Sterba Signed-off-by: Qu Wenruo Signed-off-by: David Sterba --- fs/btrfs/volumes.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 841e799dece5..e60beb14852a 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -5975,12 +5975,12 @@ struct btrfs_discard_stripe *btrfs_map_discard(struct btrfs_fs_info *fs_info, stripe_nr = offset >> BTRFS_STRIPE_LEN_SHIFT; /* stripe_offset is the offset of this block in its stripe */ - stripe_offset = offset - (stripe_nr << BTRFS_STRIPE_LEN_SHIFT); + stripe_offset = offset - ((u64)stripe_nr << BTRFS_STRIPE_LEN_SHIFT); stripe_nr_end = round_up(offset + length, BTRFS_STRIPE_LEN) >> BTRFS_STRIPE_LEN_SHIFT; stripe_cnt = stripe_nr_end - stripe_nr; - stripe_end_offset = (stripe_nr_end << BTRFS_STRIPE_LEN_SHIFT) - + stripe_end_offset = ((u64)stripe_nr_end << BTRFS_STRIPE_LEN_SHIFT) - (offset + length); /* * after this, stripe_nr is the number of stripes on this @@ -6023,7 +6023,7 @@ struct btrfs_discard_stripe *btrfs_map_discard(struct btrfs_fs_info *fs_info, for (i = 0; i < *num_stripes; i++) { stripes[i].physical = map->stripes[stripe_index].physical + - stripe_offset + (stripe_nr << BTRFS_STRIPE_LEN_SHIFT); + stripe_offset + ((u64)stripe_nr << BTRFS_STRIPE_LEN_SHIFT); stripes[i].dev = map->stripes[stripe_index].dev; if (map->type & (BTRFS_BLOCK_GROUP_RAID0 | @@ -6196,9 +6196,11 @@ static u64 btrfs_max_io_len(struct map_lookup *map, enum btrfs_map_op op, * not ensured to be power of 2. */ *full_stripe_start = - rounddown(*stripe_nr, nr_data_stripes(map)) << + (u64)rounddown(*stripe_nr, nr_data_stripes(map)) << BTRFS_STRIPE_LEN_SHIFT; + ASSERT(*full_stripe_start + full_stripe_len > offset); + ASSERT(*full_stripe_start <= offset); /* * For writes to RAID56, allow to write a full stripe set, but * no straddling of stripe sets. @@ -6221,7 +6223,7 @@ static void set_io_stripe(struct btrfs_io_stripe *dst, const struct map_lookup * { dst->dev = map->stripes[stripe_index].dev; dst->physical = map->stripes[stripe_index].physical + - stripe_offset + (stripe_nr << BTRFS_STRIPE_LEN_SHIFT); + stripe_offset + ((u64)stripe_nr << BTRFS_STRIPE_LEN_SHIFT); } int __btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,