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 --- arch/x86/lib/delay.c | 229 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 229 insertions(+) create mode 100644 arch/x86/lib/delay.c (limited to 'arch/x86/lib/delay.c') diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c new file mode 100644 index 000000000..70ad000e9 --- /dev/null +++ b/arch/x86/lib/delay.c @@ -0,0 +1,229 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Precise Delay Loops for i386 + * + * Copyright (C) 1993 Linus Torvalds + * Copyright (C) 1997 Martin Mares + * Copyright (C) 2008 Jiri Hladky + * + * The __delay function must _NOT_ be inlined as its execution time + * depends wildly on alignment on many x86 processors. The additional + * jump magic is needed to get the timing stable on all the CPU's + * we have to worry about. + */ + +#include +#include +#include +#include + +#include +#include +#include + +#ifdef CONFIG_SMP +# include +#endif + +static void delay_loop(u64 __loops); + +/* + * Calibration and selection of the delay mechanism happens only once + * during boot. + */ +static void (*delay_fn)(u64) __ro_after_init = delay_loop; +static void (*delay_halt_fn)(u64 start, u64 cycles) __ro_after_init; + +/* simple loop based delay: */ +static void delay_loop(u64 __loops) +{ + unsigned long loops = (unsigned long)__loops; + + asm volatile( + " test %0,%0 \n" + " jz 3f \n" + " jmp 1f \n" + + ".align 16 \n" + "1: jmp 2f \n" + + ".align 16 \n" + "2: dec %0 \n" + " jnz 2b \n" + "3: dec %0 \n" + + : "+a" (loops) + : + ); +} + +/* TSC based delay: */ +static void delay_tsc(u64 cycles) +{ + u64 bclock, now; + int cpu; + + preempt_disable(); + cpu = smp_processor_id(); + bclock = rdtsc_ordered(); + for (;;) { + now = rdtsc_ordered(); + if ((now - bclock) >= cycles) + break; + + /* Allow RT tasks to run */ + preempt_enable(); + native_pause(); + preempt_disable(); + + /* + * It is possible that we moved to another CPU, and + * since TSC's are per-cpu we need to calculate + * that. The delay must guarantee that we wait "at + * least" the amount of time. Being moved to another + * CPU could make the wait longer but we just need to + * make sure we waited long enough. Rebalance the + * counter for this CPU. + */ + if (unlikely(cpu != smp_processor_id())) { + cycles -= (now - bclock); + cpu = smp_processor_id(); + bclock = rdtsc_ordered(); + } + } + preempt_enable(); +} + +/* + * On Intel the TPAUSE instruction waits until any of: + * 1) the TSC counter exceeds the value provided in EDX:EAX + * 2) global timeout in IA32_UMWAIT_CONTROL is exceeded + * 3) an external interrupt occurs + */ +static void delay_halt_tpause(u64 start, u64 cycles) +{ + u64 until = start + cycles; + u32 eax, edx; + + eax = lower_32_bits(until); + edx = upper_32_bits(until); + + /* + * Hard code the deeper (C0.2) sleep state because exit latency is + * small compared to the "microseconds" that usleep() will delay. + */ + __tpause(TPAUSE_C02_STATE, edx, eax); +} + +/* + * On some AMD platforms, MWAITX has a configurable 32-bit timer, that + * counts with TSC frequency. The input value is the number of TSC cycles + * to wait. MWAITX will also exit when the timer expires. + */ +static void delay_halt_mwaitx(u64 unused, u64 cycles) +{ + u64 delay; + + delay = min_t(u64, MWAITX_MAX_WAIT_CYCLES, cycles); + /* + * Use cpu_tss_rw as a cacheline-aligned, seldom accessed per-cpu + * variable as the monitor target. + */ + __monitorx(raw_cpu_ptr(&cpu_tss_rw), 0, 0); + + /* + * AMD, like Intel, supports the EAX hint and EAX=0xf means, do not + * enter any deep C-state and we use it here in delay() to minimize + * wakeup latency. + */ + __mwaitx(MWAITX_DISABLE_CSTATES, delay, MWAITX_ECX_TIMER_ENABLE); +} + +/* + * Call a vendor specific function to delay for a given amount of time. Because + * these functions may return earlier than requested, check for actual elapsed + * time and call again until done. + */ +static void delay_halt(u64 __cycles) +{ + u64 start, end, cycles = __cycles; + + /* + * Timer value of 0 causes MWAITX to wait indefinitely, unless there + * is a store on the memory monitored by MONITORX. + */ + if (!cycles) + return; + + start = rdtsc_ordered(); + + for (;;) { + delay_halt_fn(start, cycles); + end = rdtsc_ordered(); + + if (cycles <= end - start) + break; + + cycles -= end - start; + start = end; + } +} + +void __init use_tsc_delay(void) +{ + if (delay_fn == delay_loop) + delay_fn = delay_tsc; +} + +void __init use_tpause_delay(void) +{ + delay_halt_fn = delay_halt_tpause; + delay_fn = delay_halt; +} + +void use_mwaitx_delay(void) +{ + delay_halt_fn = delay_halt_mwaitx; + delay_fn = delay_halt; +} + +bool delay_read_timer(unsigned long *timer_val) +{ + if (delay_fn == delay_tsc) { + *timer_val = rdtsc(); + return true; + } + return false; +} + +void __delay(unsigned long loops) +{ + delay_fn(loops); +} +EXPORT_SYMBOL(__delay); + +noinline void __const_udelay(unsigned long xloops) +{ + unsigned long lpj = this_cpu_read(cpu_info.loops_per_jiffy) ? : loops_per_jiffy; + int d0; + + xloops *= 4; + asm("mull %%edx" + :"=d" (xloops), "=&a" (d0) + :"1" (xloops), "0" (lpj * (HZ / 4))); + + __delay(++xloops); +} +EXPORT_SYMBOL(__const_udelay); + +void __udelay(unsigned long usecs) +{ + __const_udelay(usecs * 0x000010c7); /* 2**32 / 1000000 (rounded up) */ +} +EXPORT_SYMBOL(__udelay); + +void __ndelay(unsigned long nsecs) +{ + __const_udelay(nsecs * 0x00005); /* 2**32 / 1000000000 (rounded up) */ +} +EXPORT_SYMBOL(__ndelay); -- cgit v1.3.1