Revision d0313e629f2690edfd269896b398048275227db0 authored by Ian Rogers on 12 August 2022, 23:09:49 UTC, committed by Arnaldo Carvalho de Melo on 13 August 2022, 18:03:09 UTC
If a shorter string ends a longer string then the shorter string may
reuse the longer string at an offset. For example, on x86 the event
arith.cycles_div_busy and cycles_div_busy can be folded, even though
they have difference names the strings are identical after 6
characters. cycles_div_busy can reuse the arith.cycles_div_busy string
at an offset of 6.

In pmu-events.c this looks like the following where the 'also:' lists
folded strings:

/* offset=177541 */ "arith.cycles_div_busy\000\000pipeline\000Cycles the divider is busy\000\000\000event=0x14,period=2000000,umask=0x1\000\000\000\000\000\000\000\000\000" /* also: cycles_div_busy\000\000pipeline\000Cycles the divider is busy\000\000\000event=0x14,period=2000000,umask=0x1\000\000\000\000\000\000\000\000\000 */

As jevents.py combines multiple strings for an event into a larger
string, the amount of folding is minimal as all parts of the event must
align. Other organizations can benefit more from folding, but lose space
by say recording more offsets.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.garry@huawei.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Will Deacon <will@kernel.org>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20220812230949.683239-15-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
1 parent 9118259
Raw File
scs.c
// SPDX-License-Identifier: GPL-2.0
/*
 * Shadow Call Stack support.
 *
 * Copyright (C) 2019 Google LLC
 */

#include <linux/cpuhotplug.h>
#include <linux/kasan.h>
#include <linux/mm.h>
#include <linux/scs.h>
#include <linux/vmalloc.h>
#include <linux/vmstat.h>

static void __scs_account(void *s, int account)
{
	struct page *scs_page = vmalloc_to_page(s);

	mod_node_page_state(page_pgdat(scs_page), NR_KERNEL_SCS_KB,
			    account * (SCS_SIZE / SZ_1K));
}

/* Matches NR_CACHED_STACKS for VMAP_STACK */
#define NR_CACHED_SCS 2
static DEFINE_PER_CPU(void *, scs_cache[NR_CACHED_SCS]);

static void *__scs_alloc(int node)
{
	int i;
	void *s;

	for (i = 0; i < NR_CACHED_SCS; i++) {
		s = this_cpu_xchg(scs_cache[i], NULL);
		if (s) {
			s = kasan_unpoison_vmalloc(s, SCS_SIZE,
						   KASAN_VMALLOC_PROT_NORMAL);
			memset(s, 0, SCS_SIZE);
			goto out;
		}
	}

	s = __vmalloc_node_range(SCS_SIZE, 1, VMALLOC_START, VMALLOC_END,
				    GFP_SCS, PAGE_KERNEL, 0, node,
				    __builtin_return_address(0));

out:
	return kasan_reset_tag(s);
}

void *scs_alloc(int node)
{
	void *s;

	s = __scs_alloc(node);
	if (!s)
		return NULL;

	*__scs_magic(s) = SCS_END_MAGIC;

	/*
	 * Poison the allocation to catch unintentional accesses to
	 * the shadow stack when KASAN is enabled.
	 */
	kasan_poison_vmalloc(s, SCS_SIZE);
	__scs_account(s, 1);
	return s;
}

void scs_free(void *s)
{
	int i;

	__scs_account(s, -1);

	/*
	 * We cannot sleep as this can be called in interrupt context,
	 * so use this_cpu_cmpxchg to update the cache, and vfree_atomic
	 * to free the stack.
	 */

	for (i = 0; i < NR_CACHED_SCS; i++)
		if (this_cpu_cmpxchg(scs_cache[i], 0, s) == NULL)
			return;

	kasan_unpoison_vmalloc(s, SCS_SIZE, KASAN_VMALLOC_PROT_NORMAL);
	vfree_atomic(s);
}

static int scs_cleanup(unsigned int cpu)
{
	int i;
	void **cache = per_cpu_ptr(scs_cache, cpu);

	for (i = 0; i < NR_CACHED_SCS; i++) {
		vfree(cache[i]);
		cache[i] = NULL;
	}

	return 0;
}

void __init scs_init(void)
{
	cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "scs:scs_cache", NULL,
			  scs_cleanup);
}

int scs_prepare(struct task_struct *tsk, int node)
{
	void *s = scs_alloc(node);

	if (!s)
		return -ENOMEM;

	task_scs(tsk) = task_scs_sp(tsk) = s;
	return 0;
}

static void scs_check_usage(struct task_struct *tsk)
{
	static unsigned long highest;

	unsigned long *p, prev, curr = highest, used = 0;

	if (!IS_ENABLED(CONFIG_DEBUG_STACK_USAGE))
		return;

	for (p = task_scs(tsk); p < __scs_magic(tsk); ++p) {
		if (!READ_ONCE_NOCHECK(*p))
			break;
		used += sizeof(*p);
	}

	while (used > curr) {
		prev = cmpxchg_relaxed(&highest, curr, used);

		if (prev == curr) {
			pr_info("%s (%d): highest shadow stack usage: %lu bytes\n",
				tsk->comm, task_pid_nr(tsk), used);
			break;
		}

		curr = prev;
	}
}

void scs_release(struct task_struct *tsk)
{
	void *s = task_scs(tsk);

	if (!s)
		return;

	WARN(task_scs_end_corrupted(tsk),
	     "corrupted shadow stack detected when freeing task\n");
	scs_check_usage(tsk);
	scs_free(s);
}
back to top