From 034dd340b08be1f2f0477ad16131d609f9dbd53c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 30 Aug 2026 09:22:00 -0700 Subject: Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace Pull tracing fixes from Steven Rostedt: - Fix error output of boot instance creation failure Currently if a boot instance creation fails, instead of printing out the name of the instance that failed, it prints "(null)". That is because it prints "cur_str" that had already been processed by strsep(). Print the saved name instead. While at it, print the error code of the failure. - Fix use-after-free for same named historgrams Histograms can be named so that they can be used in multiple events. But if the named histogram has a variable attached, the second event that uses the named histogram which duplicates it and needs to free the original after duplication leaves the old variable in place and still visible. If another histogram uses than variable, it will use the stale one which will try to reference the freed duplicate histogram and crash the kernel. Free the duplicate variables along with the duplicated histogram data. - Check return value of kthread_run() in event self test The events self tests uses a kthread for testing but does not check if it succeeded in creating a kthread. If the kthread creation were to fail, the code will still try to call kthread_stop() on the error returned. - Fix race between reading trace_pipe and updating subbuffer size If a user is reading the trace_pipe file at the same time they update the ring buffer sub-buffer size, can cause the trace_pipe read to read stale data. Add trace_access_lock() around updating the ring buffer sub-buffer size. - Fix eventfs_inode on failure path in creation of the events directory In the creation of the "events" directory, if after allocating the eventfs_inode a failure is detected, it calls cleanup_ei() which calls free_ei(). The free_ei() will test if eventfs_inode being freed has no children. It is a bug if it does. But on the failure case of the creation of the "events" directory, the children lists have not yet been initialized and the free will trigger a warning because list_empty() on an uninitialized list returns false. Move the initialization into init_ei() where it makes more sense and makes sure that a created eventfs_inode has its lists initialized upon creation. - Check return value of kthread_run() in ftrace direct sample code The sample code that shows how to use the ftrace direct calls does not test the return of kthread_run() to see if it succeeds. Return a failure if the kthread_run() doesn't succeed. - Clear user events state on fork in case of alloc failure On fork, the child gets a pointer to the parent's user events state. It makes a copy of it then updates the child's pointer to it. But if the allocation fails, the duplication function leaves the child with a pointer to its parent's descriptor. When the child cleans up its data, it will free the parent's descriptor while the parent is still using it. In the duplication function, set the child's user_event_mm to NULL before testing if the allocation succeeded, and when it exits it will not free the parent's descriptor. - Fix retry exhaustion in simple ring buffer reader swap simple_ring_buffer_swap_reader_page() starts with retry set to 8 and post-decrements it only after a failed link replacement. On the final attempt, a successful replacement leaves retry at zero, while a failed replacement leaves it at -1. But the check for success expects the retry value to be non-zero and exits with an error on zero. This is the opposite result. Fix it. - Fail nicely when the remote swap_reader_page() returns an error Currently, if the swap_reader_page() of a remote buffer fails, it triggers a WARN_ON_ONCE() and continues normally. Instead, have it exit with an error and a pr_warn() print instead of a full WARNING. * tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: ring-buffer: Stop remote reader update when page swap fails tracing: Fix retry exhaustion in simple ring buffer reader swap tracing/user_events: Clear copied tracing state before fork duplication samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify eventfs: Initialize ei->children and ei->list in init_ei() tracing: Fix use-after-free in trace_pipe read on sub-buffer order change tracing: Fix crash passing ERR_PTR to kthread_stop() tracing: Fix use-after-free with same-name named triggers tracing: Fix logged instance name on creation failure --- 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