From 22098763a10d9c1340827fcf6edab66f153b27f0 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 13 Sep 2026 12:27:00 -0700 Subject: Merge tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace Pull tracing fixes from Steven Rostedt: - Don't destroy user event fields when removal fails User event fields are destroyed before the event is removed from visibility. But that can fail leaving the still visible event with no fields. Move the destroying of the fields to after the event is successfully removed from visibility. - Initialize function graph state is fork before calling copy_exec_state() For non-CLONE_VM forks, copy_exec_state() allocates a new task_exec_state. If that allocation fails, ftrace_graph_exit_task() will free the tasks ret_stack pointer. Since that pointer is still using the parent's ret_stack, it mistakenly frees the parent's pointer too. Call ftrace_graph_init() on the task first which will NULL out the new tasks's ret_stack and if the copy fails, it will not free anything. - Remove FGRAPH_MAX_INDEX The macro FGRAPH_MAX_INDEX was added but never used. Remove it. - Save ent_size in function graph printing of nested functions The function graph tracer needs to look at the next event to see if the next event is the return of the current function entry. If it is, it prints a single line: ktime_get(); Otherwise it prints it like a nested function: tick_nohz_irq_exit() { ktime_get(); kcpustat_irq_exit(); } In order to look at the next event, it must save the current event so that it has the information to print from it. It saves the event in the iterator descriptor called "ent". What it doesn't save is the ent_size of the event which is now used to know if the function graph arguments are to be printed. The peek doesn't save the size so the size used happens to be that of the size of the last event that was seen. Save the entry event size in the iterator descriptor so that the correct size is used. - Fix several errors with freeing data in the histogram code The histogram code had a lot of leaked or or incorrect accounting when failures happen. Correct them. - Fix histogram regression of .percent and .graph modifiers Up until 6.3 histogram values could have "percent" or "graph" modifiers that changed how they were printed. But a change that added restricting histograms values from being strings, stack traces and other modifiers inadvertently prevented them from using the percent and graph modifiers, which were legal use cases for values. Put back the percent and graph modifiers. - Fix various typos in the comments - Set the trace_clock before initializing a histogram with clock argument The histogram API allows the user to specific which trace clock to use via a "clock=" string. The histogram is set up first before the clock is checked. If the passed in clock is not valid, it exits without fully fixing up the histogram leaving it on the list and a use-after-free can trigger. Update the clock argument first and if it fails then exit gracefully before the histogram trigger is placed on any lists. - Restore :mod: trailer after parsing in ftrace_set_clr_event The function ftrace_set_clr_event() modifies the parse string and needs to put it back to what was passed in. It searches for ":mod:" via a strsep() but fails to put back the first ':' in the string. Add back the ':' in the passed in string. - Take trace_array reference when opening a tracer options file The options files are dynamically created and some tracers add their own options. When a tracer adds their own list of options, the trace_array holding them has an array to hold the list of options for each tracer. This array increases in size via a krealloc(), and the new entry gets a newly allocated array to hold the options of the new tracer being added. The element in each entry of the tracer's option array holds a pointer back to the trace_array, a pointer to the tracer it is associated to, a pointer to the flags of the option. The issue is that these arrays are freed when the trace_array is freed when its instance it represents is removed from the instances directory. There's a race that an open of one of these options files can happen when the instance is being removed. Add a new helper function to be called by the open function of the options file to iterate all existing trace_arrays under a lock and find the one that has the given option element in one of it's tracer arrays. If found, then update the associated trace_array's reference counter to keep it from being freed. If not found, have the open call return -ENODEV. - Disable interrupts when acquiring the lock in rb_wake_up_waiters() The function rb_wake_up_waiters() assumes it will be called in interrupt context and does not disable irqs when taking cpu_buffer->reader_lock, which can be called in hard interrupt context. The issue is in PREEMPT_RT, this function is called in thread context leaving this lock open to a deadlock. Take the lock with interrupts disabled. - Use rcu_assign_pointer() for tmp_ops filter hash The tmp_ops used in update_ftrace_direct_mod() assigns its filter_hash field directly, but that field is annotated as __rcu and sparse complains. Assign it with rcu_assign_pointer() - Fix use-after-free in enable_trigger_private_data_free() The trace_event_call is accessed through the event_trigger_data's trace_event_file pointer to put the trace_event_call on freeing. The issue is that the trace_event_file data may have been freed already causing a use-after-free. Add a field to the event_trigger_data that points directly to the trace_event_call so that it can decrement its reference directly without needing to go through the trace_event_file. - Fix accounting of buffer data remote headers trace_buffer_desc_size() and trace_remote_alloc_buffer() undercount the number of pages is needed for the asked for size as it doesn't take into account the meta data on each page. Add a helper function to do the calculation properly and use that in these functions. - Catch nr_page_va overflow in ring_buffer_desc sizing The number of pages per remote ring buffer is capped by ring_buffer_desc::nr_page_va (32 bits). A buffer_size large enough to overflow that field would silently allocate a descriptor smaller than what was asked for. - Do not resize the subbuf order if any per_cpu buffer is disabled The mmapping of ring buffers disables resizing the subbuffers, but it is done per-cpu whereas the subbuf size change is done for all the per_cpu buffers under the buffer->mutex. It could change the size of some while the mapping is happening on others. Have the resize of the subbuf order check all the per_cpu buffers under the lock to see if any of them is disabled before starting and causing an inconsistency between buffers that are being mapped. * tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (25 commits) ring-buffer: Check resize_disabled before publishing the new subbuf order tracing/remotes: Catch nr_page_va overflow in ring_buffer_desc sizing tracing/remotes: Account for ring buffer page header in size calculation tracing: Don't dereference trace_event_file in deferred trigger free ftrace: Use rcu_assign_pointer() for tmp_ops filter hash ring-buffer: Acquire the lock with irqsave in rb_wake_up_waiters() tracing: Take trace_array reference when opening a tracer options file tracing: Fix ring_buffer_read_page_size() kernel-doc tracing: Restore :mod: trailer after parsing in ftrace_set_clr_event() tracing: Fix memory corruption from a "STACKTRACE" histogram key tracing: Fix memory corruption from the histogram stacktrace modifier tracing: Undo the registration when enabling the histogram trigger fails tracing: Take the reference before publishing the named histogram trigger tracing: Set the trace clock before registering the histogram trigger tracing: Fix typo "preceeded" in comment tracing: Fix typo "availabe" in comment tracing: Let histogram values keep the percent and graph modifiers tracing: Keep the entry count when the histogram stats allocation fails tracing: Free histogram the field rejected for a bad modifier tracing: Free histogram the var ref when its initialization fails ... --- include/net/codel.h | 167 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 167 insertions(+) create mode 100644 include/net/codel.h (limited to 'include/net/codel.h') diff --git a/include/net/codel.h b/include/net/codel.h new file mode 100644 index 000000000..aa80f7448 --- /dev/null +++ b/include/net/codel.h @@ -0,0 +1,167 @@ +#ifndef __NET_SCHED_CODEL_H +#define __NET_SCHED_CODEL_H + +/* + * Codel - The Controlled-Delay Active Queue Management algorithm + * + * Copyright (C) 2011-2012 Kathleen Nichols + * Copyright (C) 2011-2012 Van Jacobson + * Copyright (C) 2012 Michael D. Taht + * Copyright (C) 2012,2015 Eric Dumazet + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions, and the following disclaimer, + * without modification. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. The names of the authors may not be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * Alternatively, provided that this notice is retained in full, this + * software may be distributed under the terms of the GNU General + * Public License ("GPL") version 2, in which case the provisions of the + * GPL apply INSTEAD OF those given above. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH + * DAMAGE. + * + */ + +#include +#include +#include + +/* Controlling Queue Delay (CoDel) algorithm + * ========================================= + * Source : Kathleen Nichols and Van Jacobson + * http://queue.acm.org/detail.cfm?id=2209336 + * + * Implemented on linux by Dave Taht and Eric Dumazet + */ + + +/* CoDel uses a 1024 nsec clock, encoded in u32 + * This gives a range of 2199 seconds, because of signed compares + */ +typedef u32 codel_time_t; +typedef s32 codel_tdiff_t; +#define CODEL_SHIFT 10 +#define MS2TIME(a) ((a * NSEC_PER_MSEC) >> CODEL_SHIFT) + +static inline codel_time_t codel_get_time(void) +{ + u64 ns = ktime_get_ns(); + + return ns >> CODEL_SHIFT; +} + +/* Dealing with timer wrapping, according to RFC 1982, as desc in wikipedia: + * https://en.wikipedia.org/wiki/Serial_number_arithmetic#General_Solution + * codel_time_after(a,b) returns true if the time a is after time b. + */ +#define codel_time_after(a, b) \ + (typecheck(codel_time_t, a) && \ + typecheck(codel_time_t, b) && \ + ((s32)((a) - (b)) > 0)) +#define codel_time_before(a, b) codel_time_after(b, a) + +#define codel_time_after_eq(a, b) \ + (typecheck(codel_time_t, a) && \ + typecheck(codel_time_t, b) && \ + ((s32)((a) - (b)) >= 0)) +#define codel_time_before_eq(a, b) codel_time_after_eq(b, a) + +static inline u32 codel_time_to_us(codel_time_t val) +{ + u64 valns = ((u64)val << CODEL_SHIFT); + + do_div(valns, NSEC_PER_USEC); + return (u32)valns; +} + +/** + * struct codel_params - contains codel parameters + * @target: target queue size (in time units) + * @ce_threshold: threshold for marking packets with ECN CE + * @interval: width of moving time window + * @mtu: device mtu, or minimal queue backlog in bytes. + * @ecn: is Explicit Congestion Notification enabled + * @ce_threshold_selector: apply ce_threshold to packets matching this value + * in the diffserv/ECN byte of the IP header + * @ce_threshold_mask: mask to apply to ce_threshold_selector comparison + */ +struct codel_params { + codel_time_t target; + codel_time_t ce_threshold; + codel_time_t interval; + u32 mtu; + bool ecn; + u8 ce_threshold_selector; + u8 ce_threshold_mask; +}; + +/** + * struct codel_vars - contains codel variables + * @count: how many drops we've done since the last time we + * entered dropping state + * @lastcount: count at entry to dropping state + * @dropping: set to true if in dropping state + * @rec_inv_sqrt: reciprocal value of sqrt(count) >> 1 + * @first_above_time: when we went (or will go) continuously above target + * for interval + * @drop_next: time to drop next packet, or when we dropped last + * @ldelay: sojourn time of last dequeued packet + */ +struct codel_vars { + u32 count; + u32 lastcount; + bool dropping; + u16 rec_inv_sqrt; + codel_time_t first_above_time; + codel_time_t drop_next; + codel_time_t ldelay; +}; + +#define REC_INV_SQRT_BITS (8 * sizeof(u16)) /* or sizeof_in_bits(rec_inv_sqrt) */ +/* needed shift to get a Q0.32 number from rec_inv_sqrt */ +#define REC_INV_SQRT_SHIFT (32 - REC_INV_SQRT_BITS) + +/** + * struct codel_stats - contains codel shared variables and stats + * @maxpacket: largest packet we've seen so far + * @drop_count: temp count of dropped packets in dequeue() + * @drop_len: bytes of dropped packets in dequeue() + * @ecn_mark: number of packets we ECN marked instead of dropping + * @ce_mark: number of packets CE marked because sojourn time was above ce_threshold + */ +struct codel_stats { + u32 maxpacket; + u32 drop_count; + u32 drop_len; + u32 ecn_mark; + u32 ce_mark; +}; + +#define CODEL_DISABLED_THRESHOLD INT_MAX + +typedef u32 (*codel_skb_len_t)(const struct sk_buff *skb); +typedef codel_time_t (*codel_skb_time_t)(const struct sk_buff *skb); +typedef void (*codel_skb_drop_t)(struct sk_buff *skb, void *ctx); +typedef struct sk_buff * (*codel_skb_dequeue_t)(struct codel_vars *vars, + void *ctx); + +#endif -- cgit v1.3.1