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 --- lib/flex_proportions.c | 202 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 202 insertions(+) create mode 100644 lib/flex_proportions.c (limited to 'lib/flex_proportions.c') diff --git a/lib/flex_proportions.c b/lib/flex_proportions.c new file mode 100644 index 000000000..012d5614e --- /dev/null +++ b/lib/flex_proportions.c @@ -0,0 +1,202 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Floating proportions with flexible aging period + * + * Copyright (C) 2011, SUSE, Jan Kara + * + * The goal of this code is: Given different types of event, measure proportion + * of each type of event over time. The proportions are measured with + * exponentially decaying history to give smooth transitions. A formula + * expressing proportion of event of type 'j' is: + * + * p_{j} = (\Sum_{i>=0} x_{i,j}/2^{i+1})/(\Sum_{i>=0} x_i/2^{i+1}) + * + * Where x_{i,j} is j's number of events in i-th last time period and x_i is + * total number of events in i-th last time period. + * + * Note that p_{j}'s are normalised, i.e. + * + * \Sum_{j} p_{j} = 1, + * + * This formula can be straightforwardly computed by maintaining denominator + * (let's call it 'd') and for each event type its numerator (let's call it + * 'n_j'). When an event of type 'j' happens, we simply need to do: + * n_j++; d++; + * + * When a new period is declared, we could do: + * d /= 2 + * for each j + * n_j /= 2 + * + * To avoid iteration over all event types, we instead shift numerator of event + * j lazily when someone asks for a proportion of event j or when event j + * occurs. This can bit trivially implemented by remembering last period in + * which something happened with proportion of type j. + */ +#include + +int fprop_global_init(struct fprop_global *p, gfp_t gfp) +{ + int err; + + p->period = 0; + /* Use 1 to avoid dealing with periods with 0 events... */ + err = percpu_counter_init(&p->events, 1, gfp); + if (err) + return err; + seqcount_init(&p->sequence); + return 0; +} + +void fprop_global_destroy(struct fprop_global *p) +{ + percpu_counter_destroy(&p->events); +} + +/* + * Declare @periods new periods. It is upto the caller to make sure period + * transitions cannot happen in parallel. + * + * The function returns true if the proportions are still defined and false + * if aging zeroed out all events. This can be used to detect whether declaring + * further periods has any effect. + */ +bool fprop_new_period(struct fprop_global *p, int periods) +{ + s64 events = percpu_counter_sum(&p->events); + unsigned long flags; + + /* + * Don't do anything if there are no events. + */ + if (events <= 1) + return false; + local_irq_save(flags); + write_seqcount_begin(&p->sequence); + if (periods < 64) + events -= events >> periods; + /* Use addition to avoid losing events happening between sum and set */ + percpu_counter_add(&p->events, -events); + p->period += periods; + write_seqcount_end(&p->sequence); + local_irq_restore(flags); + + return true; +} + +/* + * ---- PERCPU ---- + */ +#define PROP_BATCH (8*(1+ilog2(nr_cpu_ids))) + +int fprop_local_init_percpu(struct fprop_local_percpu *pl, gfp_t gfp) +{ + int err; + + err = percpu_counter_init(&pl->events, 0, gfp); + if (err) + return err; + pl->period = 0; + raw_spin_lock_init(&pl->lock); + return 0; +} + +void fprop_local_destroy_percpu(struct fprop_local_percpu *pl) +{ + percpu_counter_destroy(&pl->events); +} + +static void fprop_reflect_period_percpu(struct fprop_global *p, + struct fprop_local_percpu *pl) +{ + unsigned int period = p->period; + unsigned long flags; + + /* Fast path - period didn't change */ + if (pl->period == period) + return; + raw_spin_lock_irqsave(&pl->lock, flags); + /* Someone updated pl->period while we were spinning? */ + if (pl->period >= period) { + raw_spin_unlock_irqrestore(&pl->lock, flags); + return; + } + /* Aging zeroed our fraction? */ + if (period - pl->period < BITS_PER_LONG) { + s64 val = percpu_counter_read(&pl->events); + + if (val < (nr_cpu_ids * PROP_BATCH)) + val = percpu_counter_sum(&pl->events); + + percpu_counter_add_batch(&pl->events, + -val + (val >> (period-pl->period)), PROP_BATCH); + } else + percpu_counter_set(&pl->events, 0); + pl->period = period; + raw_spin_unlock_irqrestore(&pl->lock, flags); +} + +/* Event of type pl happened */ +void __fprop_add_percpu(struct fprop_global *p, struct fprop_local_percpu *pl, + long nr) +{ + fprop_reflect_period_percpu(p, pl); + percpu_counter_add_batch(&pl->events, nr, PROP_BATCH); + percpu_counter_add(&p->events, nr); +} + +void fprop_fraction_percpu(struct fprop_global *p, + struct fprop_local_percpu *pl, + unsigned long *numerator, unsigned long *denominator) +{ + unsigned int seq; + s64 num, den; + + do { + seq = read_seqcount_begin(&p->sequence); + fprop_reflect_period_percpu(p, pl); + num = percpu_counter_read_positive(&pl->events); + den = percpu_counter_read_positive(&p->events); + } while (read_seqcount_retry(&p->sequence, seq)); + + /* + * Make fraction <= 1 and denominator > 0 even in presence of percpu + * counter errors + */ + if (den <= num) { + if (num) + den = num; + else + den = 1; + } + *denominator = den; + *numerator = num; +} + +/* + * Like __fprop_add_percpu() except that event is counted only if the given + * type has fraction smaller than @max_frac/FPROP_FRAC_BASE + */ +void __fprop_add_percpu_max(struct fprop_global *p, + struct fprop_local_percpu *pl, int max_frac, long nr) +{ + if (unlikely(max_frac < FPROP_FRAC_BASE)) { + unsigned long numerator, denominator; + s64 tmp; + + fprop_fraction_percpu(p, pl, &numerator, &denominator); + /* Adding 'nr' to fraction exceeds max_frac/FPROP_FRAC_BASE? */ + tmp = (u64)denominator * max_frac - + ((u64)numerator << FPROP_FRAC_SHIFT); + if (tmp < 0) { + /* Maximum fraction already exceeded? */ + return; + } else if (tmp < nr * (FPROP_FRAC_BASE - max_frac)) { + /* Add just enough for the fraction to saturate */ + nr = div_u64(tmp + FPROP_FRAC_BASE - max_frac - 1, + FPROP_FRAC_BASE - max_frac); + } + } + + __fprop_add_percpu(p, pl, nr); +} -- cgit v1.3.1