
When CONFIG_KASAN_HW_TAGS is enabled we currently increase the minimum slab alignment to 16. This happens even if MTE is not supported in hardware or disabled via kasan=off, which creates an unnecessary memory overhead in those cases. Eliminate this overhead by making the minimum slab alignment a runtime property and only aligning to 16 if KASAN is enabled at runtime. On a DragonBoard 845c (non-MTE hardware) with a kernel built with CONFIG_KASAN_HW_TAGS, waiting for quiescence after a full Android boot I see the following Slab measurements in /proc/meminfo (median of 3 reboots): Before: 169020 kB After: 167304 kB [akpm@linux-foundation.org: make slab alignment type `unsigned int' to avoid casting] Link: https://linux-review.googlesource.com/id/I752e725179b43b144153f4b6f584ceb646473ead Link: https://lkml.kernel.org/r/20220427195820.1716975-2-pcc@google.com Signed-off-by: Peter Collingbourne <pcc@google.com> Reviewed-by: Andrey Konovalov <andreyknvl@gmail.com> Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Acked-by: David Rientjes <rientjes@google.com> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Pekka Enberg <penberg@kernel.org> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Herbert Xu <herbert@gondor.apana.org.au> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Alexander Potapenko <glider@google.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Kees Cook <keescook@chromium.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Bug: 265364138 (cherry picked from commit d949a8155d139aa890795b802004a196b7f00598) [Zhenhua: fold 587cfd8e66df3515 ("ANDROID: fix alignment of struct shash_desc member") into this change, to keep ABI compatibility] Change-Id: I3749f8de65ef3619724e68a9affb4eefd1ebe737 Signed-off-by: Jaewon Kim <jaewon31.kim@samsung.com> Signed-off-by: Zhenhua Huang <quic_zhenhuah@quicinc.com>
137 lines
3.4 KiB
C
137 lines
3.4 KiB
C
/* SPDX-License-Identifier: GPL-2.0-only */
|
|
/*
|
|
* Copyright (C) 2012 ARM Ltd.
|
|
*/
|
|
#ifndef __ASM_CACHE_H
|
|
#define __ASM_CACHE_H
|
|
|
|
#include <asm/cputype.h>
|
|
#include <asm/mte-def.h>
|
|
|
|
#define CTR_L1IP_SHIFT 14
|
|
#define CTR_L1IP_MASK 3
|
|
#define CTR_DMINLINE_SHIFT 16
|
|
#define CTR_IMINLINE_SHIFT 0
|
|
#define CTR_IMINLINE_MASK 0xf
|
|
#define CTR_ERG_SHIFT 20
|
|
#define CTR_CWG_SHIFT 24
|
|
#define CTR_CWG_MASK 15
|
|
#define CTR_IDC_SHIFT 28
|
|
#define CTR_DIC_SHIFT 29
|
|
|
|
#define CTR_CACHE_MINLINE_MASK \
|
|
(0xf << CTR_DMINLINE_SHIFT | CTR_IMINLINE_MASK << CTR_IMINLINE_SHIFT)
|
|
|
|
#define CTR_L1IP(ctr) (((ctr) >> CTR_L1IP_SHIFT) & CTR_L1IP_MASK)
|
|
|
|
#define ICACHE_POLICY_VPIPT 0
|
|
#define ICACHE_POLICY_RESERVED 1
|
|
#define ICACHE_POLICY_VIPT 2
|
|
#define ICACHE_POLICY_PIPT 3
|
|
|
|
#define L1_CACHE_SHIFT (6)
|
|
#define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT)
|
|
|
|
|
|
#define CLIDR_LOUU_SHIFT 27
|
|
#define CLIDR_LOC_SHIFT 24
|
|
#define CLIDR_LOUIS_SHIFT 21
|
|
|
|
#define CLIDR_LOUU(clidr) (((clidr) >> CLIDR_LOUU_SHIFT) & 0x7)
|
|
#define CLIDR_LOC(clidr) (((clidr) >> CLIDR_LOC_SHIFT) & 0x7)
|
|
#define CLIDR_LOUIS(clidr) (((clidr) >> CLIDR_LOUIS_SHIFT) & 0x7)
|
|
|
|
/*
|
|
* Memory returned by kmalloc() may be used for DMA, so we must make
|
|
* sure that all such allocations are cache aligned. Otherwise,
|
|
* unrelated code may cause parts of the buffer to be read into the
|
|
* cache before the transfer is done, causing old data to be seen by
|
|
* the CPU.
|
|
*/
|
|
#define ARCH_DMA_MINALIGN (128)
|
|
|
|
#ifndef __ASSEMBLY__
|
|
|
|
#include <linux/bitops.h>
|
|
#include <linux/kasan-enabled.h>
|
|
|
|
#ifdef CONFIG_KASAN_SW_TAGS
|
|
#define ARCH_SLAB_MINALIGN (1ULL << KASAN_SHADOW_SCALE_SHIFT)
|
|
#elif defined(CONFIG_KASAN_HW_TAGS)
|
|
static inline unsigned int arch_slab_minalign(void)
|
|
{
|
|
return kasan_hw_tags_enabled() ? MTE_GRANULE_SIZE :
|
|
__alignof__(unsigned long long);
|
|
}
|
|
#define arch_slab_minalign() arch_slab_minalign()
|
|
#endif
|
|
|
|
#define ICACHEF_ALIASING 0
|
|
#define ICACHEF_VPIPT 1
|
|
extern unsigned long __icache_flags;
|
|
|
|
/*
|
|
* Whilst the D-side always behaves as PIPT on AArch64, aliasing is
|
|
* permitted in the I-cache.
|
|
*/
|
|
static inline int icache_is_aliasing(void)
|
|
{
|
|
return test_bit(ICACHEF_ALIASING, &__icache_flags);
|
|
}
|
|
|
|
static __always_inline int icache_is_vpipt(void)
|
|
{
|
|
return test_bit(ICACHEF_VPIPT, &__icache_flags);
|
|
}
|
|
|
|
static inline u32 cache_type_cwg(void)
|
|
{
|
|
return (read_cpuid_cachetype() >> CTR_CWG_SHIFT) & CTR_CWG_MASK;
|
|
}
|
|
|
|
#define __read_mostly __section(".data..read_mostly")
|
|
|
|
static inline int cache_line_size_of_cpu(void)
|
|
{
|
|
u32 cwg = cache_type_cwg();
|
|
|
|
return cwg ? 4 << cwg : ARCH_DMA_MINALIGN;
|
|
}
|
|
|
|
int cache_line_size(void);
|
|
|
|
/*
|
|
* Read the effective value of CTR_EL0.
|
|
*
|
|
* According to ARM ARM for ARMv8-A (ARM DDI 0487C.a),
|
|
* section D10.2.33 "CTR_EL0, Cache Type Register" :
|
|
*
|
|
* CTR_EL0.IDC reports the data cache clean requirements for
|
|
* instruction to data coherence.
|
|
*
|
|
* 0 - dcache clean to PoU is required unless :
|
|
* (CLIDR_EL1.LoC == 0) || (CLIDR_EL1.LoUIS == 0 && CLIDR_EL1.LoUU == 0)
|
|
* 1 - dcache clean to PoU is not required for i-to-d coherence.
|
|
*
|
|
* This routine provides the CTR_EL0 with the IDC field updated to the
|
|
* effective state.
|
|
*/
|
|
static inline u32 __attribute_const__ read_cpuid_effective_cachetype(void)
|
|
{
|
|
u32 ctr = read_cpuid_cachetype();
|
|
|
|
if (!(ctr & BIT(CTR_IDC_SHIFT))) {
|
|
u64 clidr = read_sysreg(clidr_el1);
|
|
|
|
if (CLIDR_LOC(clidr) == 0 ||
|
|
(CLIDR_LOUIS(clidr) == 0 && CLIDR_LOUU(clidr) == 0))
|
|
ctr |= BIT(CTR_IDC_SHIFT);
|
|
}
|
|
|
|
return ctr;
|
|
}
|
|
|
|
#endif /* __ASSEMBLY__ */
|
|
|
|
#endif
|