https://github.com/torvalds/linux
Revision 928501344fc645f80390afc12708c81b3595745d authored by Andrey Konovalov on 26 February 2021, 01:19:55 UTC, committed by Linus Torvalds on 26 February 2021, 17:41:02 UTC
Patch series "kasan: optimizations and fixes for HW_TAGS", v4.

This patchset makes the HW_TAGS mode more efficient, mostly by reworking
poisoning approaches and simplifying/inlining some internal helpers.

With this change, the overhead of HW_TAGS annotations excluding setting
and checking memory tags is ~3%.  The performance impact caused by tags
will be unknown until we have hardware that supports MTE.

As a side-effect, this patchset speeds up generic KASAN by ~15%.

This patch (of 13):

Currently KASAN saves allocation stacks in both kasan_slab_alloc() and
kasan_kmalloc() annotations.  This patch changes KASAN to save allocation
stacks for slab objects from kmalloc caches in kasan_kmalloc() only, and
stacks for other slab objects in kasan_slab_alloc() only.

This change requires ____kasan_kmalloc() knowing whether the object
belongs to a kmalloc cache.  This is implemented by adding a flag field to
the kasan_info structure.  That flag is only set for kmalloc caches via a
new kasan_cache_create_kmalloc() annotation.

Link: https://lkml.kernel.org/r/cover.1612546384.git.andreyknvl@google.com
Link: https://lkml.kernel.org/r/7c673ebca8d00f40a7ad6f04ab9a2bddeeae2097.1612546384.git.andreyknvl@google.com
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Reviewed-by: Marco Elver <elver@google.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Peter Collingbourne <pcc@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Branislav Rankov <Branislav.Rankov@arm.com>
Cc: Kevin Brodsky <kevin.brodsky@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent d3a61f7
Raw File
Tip revision: 928501344fc645f80390afc12708c81b3595745d authored by Andrey Konovalov on 26 February 2021, 01:19:55 UTC
kasan, mm: don't save alloc stacks twice
Tip revision: 9285013
cppc_acpi.h
/* SPDX-License-Identifier: GPL-2.0-only */
/*
 * CPPC (Collaborative Processor Performance Control) methods used
 * by CPUfreq drivers.
 *
 * (C) Copyright 2014, 2015 Linaro Ltd.
 * Author: Ashwin Chaugule <ashwin.chaugule@linaro.org>
 */

#ifndef _CPPC_ACPI_H
#define _CPPC_ACPI_H

#include <linux/acpi.h>
#include <linux/types.h>

#include <acpi/pcc.h>
#include <acpi/processor.h>

/* Support CPPCv2 and CPPCv3  */
#define CPPC_V2_REV	2
#define CPPC_V3_REV	3
#define CPPC_V2_NUM_ENT	21
#define CPPC_V3_NUM_ENT	23

#define PCC_CMD_COMPLETE_MASK	(1 << 0)
#define PCC_ERROR_MASK		(1 << 2)

#define MAX_CPC_REG_ENT 21

/* CPPC specific PCC commands. */
#define	CMD_READ 0
#define	CMD_WRITE 1

/* Each register has the folowing format. */
struct cpc_reg {
	u8 descriptor;
	u16 length;
	u8 space_id;
	u8 bit_width;
	u8 bit_offset;
	u8 access_width;
	u64 address;
} __packed;

/*
 * Each entry in the CPC table is either
 * of type ACPI_TYPE_BUFFER or
 * ACPI_TYPE_INTEGER.
 */
struct cpc_register_resource {
	acpi_object_type type;
	u64 __iomem *sys_mem_vaddr;
	union {
		struct cpc_reg reg;
		u64 int_value;
	} cpc_entry;
};

/* Container to hold the CPC details for each CPU */
struct cpc_desc {
	int num_entries;
	int version;
	int cpu_id;
	int write_cmd_status;
	int write_cmd_id;
	struct cpc_register_resource cpc_regs[MAX_CPC_REG_ENT];
	struct acpi_psd_package domain_info;
	struct kobject kobj;
};

/* These are indexes into the per-cpu cpc_regs[]. Order is important. */
enum cppc_regs {
	HIGHEST_PERF,
	NOMINAL_PERF,
	LOW_NON_LINEAR_PERF,
	LOWEST_PERF,
	GUARANTEED_PERF,
	DESIRED_PERF,
	MIN_PERF,
	MAX_PERF,
	PERF_REDUC_TOLERANCE,
	TIME_WINDOW,
	CTR_WRAP_TIME,
	REFERENCE_CTR,
	DELIVERED_CTR,
	PERF_LIMITED,
	ENABLE,
	AUTO_SEL_ENABLE,
	AUTO_ACT_WINDOW,
	ENERGY_PERF,
	REFERENCE_PERF,
	LOWEST_FREQ,
	NOMINAL_FREQ,
};

/*
 * Categorization of registers as described
 * in the ACPI v.5.1 spec.
 * XXX: Only filling up ones which are used by governors
 * today.
 */
struct cppc_perf_caps {
	u32 guaranteed_perf;
	u32 highest_perf;
	u32 nominal_perf;
	u32 lowest_perf;
	u32 lowest_nonlinear_perf;
	u32 lowest_freq;
	u32 nominal_freq;
};

struct cppc_perf_ctrls {
	u32 max_perf;
	u32 min_perf;
	u32 desired_perf;
};

struct cppc_perf_fb_ctrs {
	u64 reference;
	u64 delivered;
	u64 reference_perf;
	u64 wraparound_time;
};

/* Per CPU container for runtime CPPC management. */
struct cppc_cpudata {
	struct list_head node;
	struct cppc_perf_caps perf_caps;
	struct cppc_perf_ctrls perf_ctrls;
	struct cppc_perf_fb_ctrs perf_fb_ctrs;
	unsigned int shared_type;
	cpumask_var_t shared_cpu_map;
};

extern int cppc_get_desired_perf(int cpunum, u64 *desired_perf);
extern int cppc_get_perf_ctrs(int cpu, struct cppc_perf_fb_ctrs *perf_fb_ctrs);
extern int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls);
extern int cppc_get_perf_caps(int cpu, struct cppc_perf_caps *caps);
extern bool acpi_cpc_valid(void);
extern int acpi_get_psd_map(unsigned int cpu, struct cppc_cpudata *cpu_data);
extern unsigned int cppc_get_transition_latency(int cpu);
extern bool cpc_ffh_supported(void);
extern int cpc_read_ffh(int cpunum, struct cpc_reg *reg, u64 *val);
extern int cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val);

#endif /* _CPPC_ACPI_H*/
back to top