From c4bfd39d7fa5203d4b387c283d360e9a108e85b3 Mon Sep 17 00:00:00 2001 From: Matthias Kaehlcke Date: Wed, 17 May 2017 17:14:15 -0700 Subject: ring-buffer: Remove unused function __rb_data_page_index() This fixes the following warning when building with clang: kernel/trace/ring_buffer.c:1842:1: error: unused function '__rb_data_page_index' [-Werror,-Wunused-function] Link: http://lkml.kernel.org/r/20170518001415.5223-1-mka@chromium.org Reviewed-by: Douglas Anderson Signed-off-by: Matthias Kaehlcke Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ring_buffer.c | 6 ------ 1 file changed, 6 deletions(-) (limited to 'kernel/trace/ring_buffer.c') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 91874a95060d..c87766c1c204 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1799,12 +1799,6 @@ void ring_buffer_change_overwrite(struct ring_buffer *buffer, int val) } EXPORT_SYMBOL_GPL(ring_buffer_change_overwrite); -static __always_inline void * -__rb_data_page_index(struct buffer_data_page *bpage, unsigned index) -{ - return bpage->data + index; -} - static __always_inline void *__rb_page_index(struct buffer_page *bpage, unsigned index) { return bpage->page->data + index; -- cgit v1.2.3 From 45d8b80c2ac5d21cd1e2954431fb676bc2b1e099 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Fri, 22 Dec 2017 20:32:35 -0500 Subject: ring-buffer: Mask out the info bits when returning buffer page length Two info bits were added to the "commit" part of the ring buffer data page when returned to be consumed. This was to inform the user space readers that events have been missed, and that the count may be stored at the end of the page. What wasn't handled, was the splice code that actually called a function to return the length of the data in order to zero out the rest of the page before sending it up to user space. These data bits were returned with the length making the value negative, and that negative value was not checked. It was compared to PAGE_SIZE, and only used if the size was less than PAGE_SIZE. Luckily PAGE_SIZE is unsigned long which made the compare an unsigned compare, meaning the negative size value did not end up causing a large portion of memory to be randomly zeroed out. Cc: stable@vger.kernel.org Fixes: 66a8cb95ed040 ("ring-buffer: Add place holder recording of dropped events") Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ring_buffer.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'kernel/trace/ring_buffer.c') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index c87766c1c204..e06cde093f76 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -280,6 +280,8 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_data); /* Missed count stored at end */ #define RB_MISSED_STORED (1 << 30) +#define RB_MISSED_FLAGS (RB_MISSED_EVENTS|RB_MISSED_STORED) + struct buffer_data_page { u64 time_stamp; /* page time stamp */ local_t commit; /* write committed index */ @@ -331,7 +333,9 @@ static void rb_init_page(struct buffer_data_page *bpage) */ size_t ring_buffer_page_len(void *page) { - return local_read(&((struct buffer_data_page *)page)->commit) + struct buffer_data_page *bpage = page; + + return (local_read(&bpage->commit) & ~RB_MISSED_FLAGS) + BUF_PAGE_HDR_SIZE; } -- cgit v1.2.3 From ae415fa4c5248a8cf4faabd5a3c20576cb1ad607 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Fri, 22 Dec 2017 21:19:29 -0500 Subject: ring-buffer: Do no reuse reader page if still in use To free the reader page that is allocated with ring_buffer_alloc_read_page(), ring_buffer_free_read_page() must be called. For faster performance, this page can be reused by the ring buffer to avoid having to free and allocate new pages. The issue arises when the page is used with a splice pipe into the networking code. The networking code may up the page counter for the page, and keep it active while sending it is queued to go to the network. The incrementing of the page ref does not prevent it from being reused in the ring buffer, and this can cause the page that is being sent out to the network to be modified before it is sent by reading new data. Add a check to the page ref counter, and only reuse the page if it is not being used anywhere else. Cc: stable@vger.kernel.org Fixes: 73a757e63114d ("ring-buffer: Return reader page back into existing ring buffer") Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ring_buffer.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'kernel/trace/ring_buffer.c') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index e06cde093f76..9ab18995ff1e 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -4404,8 +4404,13 @@ void ring_buffer_free_read_page(struct ring_buffer *buffer, int cpu, void *data) { struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; struct buffer_data_page *bpage = data; + struct page *page = virt_to_page(bpage); unsigned long flags; + /* If the page is still in use someplace else, we can't reuse it */ + if (page_ref_count(page) > 1) + goto out; + local_irq_save(flags); arch_spin_lock(&cpu_buffer->lock); @@ -4417,6 +4422,7 @@ void ring_buffer_free_read_page(struct ring_buffer *buffer, int cpu, void *data) arch_spin_unlock(&cpu_buffer->lock); local_irq_restore(flags); + out: free_page((unsigned long)bpage); } EXPORT_SYMBOL_GPL(ring_buffer_free_read_page); -- cgit v1.2.3 From a0e3a18f4baf8e3754ac1e56f0ade924d0c0c721 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Mon, 15 Jan 2018 10:47:09 -0500 Subject: ring-buffer: Bring back context level recursive checks Commit 1a149d7d3f45 ("ring-buffer: Rewrite trace_recursive_(un)lock() to be simpler") replaced the context level recursion checks with a simple counter. This would prevent the ring buffer code from recursively calling itself more than the max number of contexts that exist (Normal, softirq, irq, nmi). But this change caused a lockup in a specific case, which was during suspend and resume using a global clock. Adding a stack dump to see where this occurred, the issue was in the trace global clock itself: trace_buffer_lock_reserve+0x1c/0x50 __trace_graph_entry+0x2d/0x90 trace_graph_entry+0xe8/0x200 prepare_ftrace_return+0x69/0xc0 ftrace_graph_caller+0x78/0xa8 queued_spin_lock_slowpath+0x5/0x1d0 trace_clock_global+0xb0/0xc0 ring_buffer_lock_reserve+0xf9/0x390 The function graph tracer traced queued_spin_lock_slowpath that was called by trace_clock_global. This pointed out that the trace_clock_global() is not reentrant, as it takes a spin lock. It depended on the ring buffer recursive lock from letting that happen. By removing the context detection and adding just a max number of allowable recursions, it allowed the trace_clock_global() to be entered again and try to retake the spinlock it already held, causing a deadlock. Fixes: 1a149d7d3f45 ("ring-buffer: Rewrite trace_recursive_(un)lock() to be simpler") Reported-by: David Weinehall Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ring_buffer.c | 62 +++++++++++++++++++++++++++++++++------------- 1 file changed, 45 insertions(+), 17 deletions(-) (limited to 'kernel/trace/ring_buffer.c') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 9ab18995ff1e..0cddf60186da 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2534,29 +2534,59 @@ rb_wakeups(struct ring_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer) * The lock and unlock are done within a preempt disable section. * The current_context per_cpu variable can only be modified * by the current task between lock and unlock. But it can - * be modified more than once via an interrupt. There are four - * different contexts that we need to consider. + * be modified more than once via an interrupt. To pass this + * information from the lock to the unlock without having to + * access the 'in_interrupt()' functions again (which do show + * a bit of overhead in something as critical as function tracing, + * we use a bitmask trick. * - * Normal context. - * SoftIRQ context - * IRQ context - * NMI context + * bit 0 = NMI context + * bit 1 = IRQ context + * bit 2 = SoftIRQ context + * bit 3 = normal context. * - * If for some reason the ring buffer starts to recurse, we - * only allow that to happen at most 4 times (one for each - * context). If it happens 5 times, then we consider this a - * recusive loop and do not let it go further. + * This works because this is the order of contexts that can + * preempt other contexts. A SoftIRQ never preempts an IRQ + * context. + * + * When the context is determined, the corresponding bit is + * checked and set (if it was set, then a recursion of that context + * happened). + * + * On unlock, we need to clear this bit. To do so, just subtract + * 1 from the current_context and AND it to itself. + * + * (binary) + * 101 - 1 = 100 + * 101 & 100 = 100 (clearing bit zero) + * + * 1010 - 1 = 1001 + * 1010 & 1001 = 1000 (clearing bit 1) + * + * The least significant bit can be cleared this way, and it + * just so happens that it is the same bit corresponding to + * the current context. */ static __always_inline int trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer) { - if (cpu_buffer->current_context >= 4) + unsigned int val = cpu_buffer->current_context; + unsigned long pc = preempt_count(); + int bit; + + if (!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET))) + bit = RB_CTX_NORMAL; + else + bit = pc & NMI_MASK ? RB_CTX_NMI : + pc & HARDIRQ_MASK ? RB_CTX_IRQ : + pc & SOFTIRQ_OFFSET ? 2 : RB_CTX_SOFTIRQ; + + if (unlikely(val & (1 << bit))) return 1; - cpu_buffer->current_context++; - /* Interrupts must see this update */ - barrier(); + val |= (1 << bit); + cpu_buffer->current_context = val; return 0; } @@ -2564,9 +2594,7 @@ trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer) static __always_inline void trace_recursive_unlock(struct ring_buffer_per_cpu *cpu_buffer) { - /* Don't let the dec leak out */ - barrier(); - cpu_buffer->current_context--; + cpu_buffer->current_context &= cpu_buffer->current_context - 1; } /** -- cgit v1.2.3 From 0164e0d7e803af3ee1c63770978c728f8778ad01 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 18 Jan 2018 15:42:09 -0500 Subject: ring-buffer: Fix duplicate results in mapping context to bits in recursive lock In bringing back the context checks, the code checks first if its normal (non-interrupt) context, and then for NMI then IRQ then softirq. The final check is redundant. Since the if branch is only hit if the context is one of NMI, IRQ, or SOFTIRQ, if it's not NMI or IRQ there's no reason to check if it is SOFTIRQ. The current code returns the same result even if its not a SOFTIRQ. Which is confusing. pc & SOFTIRQ_OFFSET ? 2 : RB_CTX_SOFTIRQ Is redundant as RB_CTX_SOFTIRQ *is* 2! Fixes: a0e3a18f4baf ("ring-buffer: Bring back context level recursive checks") Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ring_buffer.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'kernel/trace/ring_buffer.c') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 0cddf60186da..5af2842dea96 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2579,8 +2579,7 @@ trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer) bit = RB_CTX_NORMAL; else bit = pc & NMI_MASK ? RB_CTX_NMI : - pc & HARDIRQ_MASK ? RB_CTX_IRQ : - pc & SOFTIRQ_OFFSET ? 2 : RB_CTX_SOFTIRQ; + pc & HARDIRQ_MASK ? RB_CTX_IRQ : RB_CTX_SOFTIRQ; if (unlikely(val & (1 << bit))) return 1; -- cgit v1.2.3