From 912da2c384d510ce40c5af9c3adc316afa4ec547 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 8 Oct 2024 14:32:42 -0400 Subject: ring-buffer: Do not have boot mapped buffers hook to CPU hotplug The boot mapped ring buffer has its buffer mapped at a fixed location found at boot up. It is not dynamic. It cannot grow or be expanded when new CPUs come online. Do not hook fixed memory mapped ring buffers to the CPU hotplug callback, otherwise it can cause a crash when it tries to add the buffer to the memory that is already fully occupied. Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Link: https://lore.kernel.org/20241008143242.25e20801@gandalf.local.home Fixes: be68d63a139bd ("ring-buffer: Add ring_buffer_alloc_range()") Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ring_buffer.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'kernel/trace/ring_buffer.c') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 77dc0b25140e..fb04445f92c3 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2337,9 +2337,12 @@ static struct trace_buffer *alloc_buffer(unsigned long size, unsigned flags, if (!buffer->buffers[cpu]) goto fail_free_buffers; - ret = cpuhp_state_add_instance(CPUHP_TRACE_RB_PREPARE, &buffer->node); - if (ret < 0) - goto fail_free_buffers; + /* If already mapped, do not hook to CPU hotplug */ + if (!start) { + ret = cpuhp_state_add_instance(CPUHP_TRACE_RB_PREPARE, &buffer->node); + if (ret < 0) + goto fail_free_buffers; + } mutex_init(&buffer->mutex); -- cgit v1.2.3 From 09661f75e75cb6c1d2d8326a70c311d46729235f Mon Sep 17 00:00:00 2001 From: Petr Pavlu Date: Tue, 15 Oct 2024 13:24:29 +0200 Subject: ring-buffer: Fix reader locking when changing the sub buffer order The function ring_buffer_subbuf_order_set() updates each ring_buffer_per_cpu and installs new sub buffers that match the requested page order. This operation may be invoked concurrently with readers that rely on some of the modified data, such as the head bit (RB_PAGE_HEAD), or the ring_buffer_per_cpu.pages and reader_page pointers. However, no exclusive access is acquired by ring_buffer_subbuf_order_set(). Modifying the mentioned data while a reader also operates on them can then result in incorrect memory access and various crashes. Fix the problem by taking the reader_lock when updating a specific ring_buffer_per_cpu in ring_buffer_subbuf_order_set(). Link: https://lore.kernel.org/linux-trace-kernel/20240715145141.5528-1-petr.pavlu@suse.com/ Link: https://lore.kernel.org/linux-trace-kernel/20241010195849.2f77cc3f@gandalf.local.home/ Link: https://lore.kernel.org/linux-trace-kernel/20241011112850.17212b25@gandalf.local.home/ Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Link: https://lore.kernel.org/20241015112440.26987-1-petr.pavlu@suse.com Fixes: 8e7b58c27b3c ("ring-buffer: Just update the subbuffers when changing their allocation order") Signed-off-by: Petr Pavlu Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ring_buffer.c | 44 ++++++++++++++++++++++++++------------------ 1 file changed, 26 insertions(+), 18 deletions(-) (limited to 'kernel/trace/ring_buffer.c') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index fb04445f92c3..3ea4f7bb1837 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -6728,39 +6728,38 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order) } for_each_buffer_cpu(buffer, cpu) { + struct buffer_data_page *old_free_data_page; + struct list_head old_pages; + unsigned long flags; if (!cpumask_test_cpu(cpu, buffer->cpumask)) continue; cpu_buffer = buffer->buffers[cpu]; + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + /* Clear the head bit to make the link list normal to read */ rb_head_page_deactivate(cpu_buffer); - /* Now walk the list and free all the old sub buffers */ - list_for_each_entry_safe(bpage, tmp, cpu_buffer->pages, list) { - list_del_init(&bpage->list); - free_buffer_page(bpage); - } - /* The above loop stopped an the last page needing to be freed */ - bpage = list_entry(cpu_buffer->pages, struct buffer_page, list); - free_buffer_page(bpage); - - /* Free the current reader page */ - free_buffer_page(cpu_buffer->reader_page); + /* + * Collect buffers from the cpu_buffer pages list and the + * reader_page on old_pages, so they can be freed later when not + * under a spinlock. The pages list is a linked list with no + * head, adding old_pages turns it into a regular list with + * old_pages being the head. + */ + list_add(&old_pages, cpu_buffer->pages); + list_add(&cpu_buffer->reader_page->list, &old_pages); /* One page was allocated for the reader page */ cpu_buffer->reader_page = list_entry(cpu_buffer->new_pages.next, struct buffer_page, list); list_del_init(&cpu_buffer->reader_page->list); - /* The cpu_buffer pages are a link list with no head */ + /* Install the new pages, remove the head from the list */ cpu_buffer->pages = cpu_buffer->new_pages.next; - cpu_buffer->new_pages.next->prev = cpu_buffer->new_pages.prev; - cpu_buffer->new_pages.prev->next = cpu_buffer->new_pages.next; - - /* Clear the new_pages list */ - INIT_LIST_HEAD(&cpu_buffer->new_pages); + list_del_init(&cpu_buffer->new_pages); cpu_buffer->head_page = list_entry(cpu_buffer->pages, struct buffer_page, list); @@ -6769,11 +6768,20 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order) cpu_buffer->nr_pages = cpu_buffer->nr_pages_to_update; cpu_buffer->nr_pages_to_update = 0; - free_pages((unsigned long)cpu_buffer->free_page, old_order); + old_free_data_page = cpu_buffer->free_page; cpu_buffer->free_page = NULL; rb_head_page_activate(cpu_buffer); + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + + /* Free old sub buffers */ + list_for_each_entry_safe(bpage, tmp, &old_pages, list) { + list_del_init(&bpage->list); + free_buffer_page(bpage); + } + free_pages((unsigned long)old_free_data_page, old_order); + rb_check_pages(cpu_buffer); } -- cgit v1.2.3