linux-brain/arch/arc/include/asm/cache.h

131 lines
3.6 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
*/
#ifndef __ARC_ASM_CACHE_H
#define __ARC_ASM_CACHE_H
/* In case $$ not config, setup a dummy number for rest of kernel */
#ifndef CONFIG_ARC_CACHE_LINE_SHIFT
#define L1_CACHE_SHIFT 6
#else
#define L1_CACHE_SHIFT CONFIG_ARC_CACHE_LINE_SHIFT
#endif
#define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT)
#define CACHE_LINE_MASK (~(L1_CACHE_BYTES - 1))
/*
* ARC700 doesn't cache any access in top 1G (0xc000_0000 to 0xFFFF_FFFF)
* Ideal for wiring memory mapped peripherals as we don't need to do
* explicit uncached accesses (LD.di/ST.di) hence more portable drivers
*/
#define ARC_UNCACHED_ADDR_SPACE 0xc0000000
#ifndef __ASSEMBLY__
/* Uncached access macros */
#define arc_read_uncached_32(ptr) \
({ \
unsigned int __ret; \
__asm__ __volatile__( \
" ld.di %0, [%1] \n" \
: "=r"(__ret) \
: "r"(ptr)); \
__ret; \
})
#define arc_write_uncached_32(ptr, data)\
({ \
__asm__ __volatile__( \
" st.di %0, [%1] \n" \
: \
: "r"(data), "r"(ptr)); \
})
/* Largest line length for either L1 or L2 is 128 bytes */
ARC: dma [non-IOC] setup SMP_CACHE_BYTES and cache_line_size As for today we don't setup SMP_CACHE_BYTES and cache_line_size for ARC, so they are set to L1_CACHE_BYTES by default. L1 line length (L1_CACHE_BYTES) might be easily smaller than L2 line (which is usually the case BTW). This breaks code. For example this breaks ethernet infrastructure on HSDK/AXS103 boards with IOC disabled, involving manual cache flushes Functions which alloc and manage sk_buff packet data area rely on SMP_CACHE_BYTES define. In the result we can share last L2 cache line in sk_buff linear packet data area between DMA buffer and some useful data in other structure. So we can lose this data when we invalidate DMA buffer. sk_buff linear packet data area | | | skb->end skb->tail V | | V V ----------------------------------------------. packet data | <tail padding> | <useful data in other struct> ----------------------------------------------. ---------------------.--------------------------------------------------. SLC line | SLC (L2 cache) line (128B) | ---------------------.--------------------------------------------------. ^ ^ | | These cache lines will be invalidated when we invalidate skb linear packet data area before DMA transaction starting. This leads to issues painful to debug as it reproduces only if (sk_buff->end - sk_buff->tail) < SLC_LINE_SIZE and if we have some useful data right after sk_buff->end. Fix that by hardcode SMP_CACHE_BYTES to max line length we may have. Signed-off-by: Eugeniy Paltsev <Eugeniy.Paltsev@synopsys.com> Signed-off-by: Vineet Gupta <vgupta@synopsys.com>
2018-07-26 22:15:43 +09:00
#define SMP_CACHE_BYTES 128
#define cache_line_size() SMP_CACHE_BYTES
#define ARCH_DMA_MINALIGN SMP_CACHE_BYTES
ARC: define ARCH_SLAB_MINALIGN = 8 The default value of ARCH_SLAB_MINALIGN in "include/linux/slab.h" is "__alignof__(unsigned long long)" which for ARC unexpectedly turns out to be 4. This is not a compiler bug, but as defined by ARC ABI [1] Thus slab allocator would allocate a struct which is 32-bit aligned, which is generally OK even if struct has long long members. There was however potetial problem when it had any atomic64_t which use LLOCKD/SCONDD instructions which are required by ISA to take 64-bit addresses. This is the problem we ran into [ 4.015732] EXT4-fs (mmcblk0p2): re-mounted. Opts: (null) [ 4.167881] Misaligned Access [ 4.172356] Path: /bin/busybox.nosuid [ 4.176004] CPU: 2 PID: 171 Comm: rm Not tainted 4.19.14-yocto-standard #1 [ 4.182851] [ 4.182851] [ECR ]: 0x000d0000 => Check Programmer's Manual [ 4.190061] [EFA ]: 0xbeaec3fc [ 4.190061] [BLINK ]: ext4_delete_entry+0x210/0x234 [ 4.190061] [ERET ]: ext4_delete_entry+0x13e/0x234 [ 4.202985] [STAT32]: 0x80080002 : IE K [ 4.207236] BTA: 0x9009329c SP: 0xbe5b1ec4 FP: 0x00000000 [ 4.212790] LPS: 0x9074b118 LPE: 0x9074b120 LPC: 0x00000000 [ 4.218348] r00: 0x00000040 r01: 0x00000021 r02: 0x00000001 ... ... [ 4.270510] Stack Trace: [ 4.274510] ext4_delete_entry+0x13e/0x234 [ 4.278695] ext4_rmdir+0xe0/0x238 [ 4.282187] vfs_rmdir+0x50/0xf0 [ 4.285492] do_rmdir+0x9e/0x154 [ 4.288802] EV_Trap+0x110/0x114 The fix is to make sure slab allocations are 64-bit aligned. Do note that atomic64_t is __attribute__((aligned(8)) which means gcc does generate 64-bit aligned references, relative to beginning of container struct. However the issue is if the container itself is not 64-bit aligned, atomic64_t ends up unaligned which is what this patch ensures. [1] https://github.com/foss-for-synopsys-dwc-arc-processors/toolchain/wiki/files/ARCv2_ABI.pdf Signed-off-by: Alexey Brodkin <abrodkin@synopsys.com> Cc: <stable@vger.kernel.org> # 4.8+ Signed-off-by: Vineet Gupta <vgupta@synopsys.com> [vgupta: reworked changelog, added dependency on LL64+LLSC]
2019-02-08 19:55:19 +09:00
/*
* Make sure slab-allocated buffers are 64-bit aligned when atomic64_t uses
* ARCv2 64-bit atomics (LLOCKD/SCONDD). This guarantess runtime 64-bit
* alignment for any atomic64_t embedded in buffer.
* Default ARCH_SLAB_MINALIGN is __alignof__(long long) which has a relaxed
* value of 4 (and not 8) in ARC ABI.
*/
#if defined(CONFIG_ARC_HAS_LL64) && defined(CONFIG_ARC_HAS_LLSC)
#define ARCH_SLAB_MINALIGN 8
#endif
extern void arc_cache_init(void);
extern char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len);
extern void read_decode_cache_bcr(void);
extern int ioc_enable;
extern unsigned long perip_base, perip_end;
#endif /* !__ASSEMBLY__ */
/* Instruction cache related Auxiliary registers */
#define ARC_REG_IC_BCR 0x77 /* Build Config reg */
#define ARC_REG_IC_IVIC 0x10
#define ARC_REG_IC_CTRL 0x11
#define ARC_REG_IC_IVIR 0x16
#define ARC_REG_IC_ENDR 0x17
#define ARC_REG_IC_IVIL 0x19
#define ARC_REG_IC_PTAG 0x1E
#define ARC_REG_IC_PTAG_HI 0x1F
/* Bit val in IC_CTRL */
#define IC_CTRL_DIS 0x1
/* Data cache related Auxiliary registers */
#define ARC_REG_DC_BCR 0x72 /* Build Config reg */
#define ARC_REG_DC_IVDC 0x47
#define ARC_REG_DC_CTRL 0x48
#define ARC_REG_DC_IVDL 0x4A
#define ARC_REG_DC_FLSH 0x4B
#define ARC_REG_DC_FLDL 0x4C
#define ARC_REG_DC_STARTR 0x4D
#define ARC_REG_DC_ENDR 0x4E
#define ARC_REG_DC_PTAG 0x5C
#define ARC_REG_DC_PTAG_HI 0x5F
/* Bit val in DC_CTRL */
#define DC_CTRL_DIS 0x001
#define DC_CTRL_INV_MODE_FLUSH 0x040
#define DC_CTRL_FLUSH_STATUS 0x100
#define DC_CTRL_RGN_OP_INV 0x200
2017-05-03 08:23:57 +09:00
#define DC_CTRL_RGN_OP_MSK 0x200
/*System-level cache (L2 cache) related Auxiliary registers */
#define ARC_REG_SLC_CFG 0x901
#define ARC_REG_SLC_CTRL 0x903
#define ARC_REG_SLC_FLUSH 0x904
#define ARC_REG_SLC_INVALIDATE 0x905
#define ARC_AUX_SLC_IVDL 0x910
#define ARC_AUX_SLC_FLDL 0x912
#define ARC_REG_SLC_RGN_START 0x914
#define ARC_REG_SLC_RGN_START1 0x915
#define ARC_REG_SLC_RGN_END 0x916
#define ARC_REG_SLC_RGN_END1 0x917
/* Bit val in SLC_CONTROL */
#define SLC_CTRL_DIS 0x001
#define SLC_CTRL_IM 0x040
#define SLC_CTRL_BUSY 0x100
#define SLC_CTRL_RGN_OP_INV 0x200
/* IO coherency related Auxiliary registers */
#define ARC_REG_IO_COH_ENABLE 0x500
#define ARC_IO_COH_ENABLE_BIT BIT(0)
#define ARC_REG_IO_COH_PARTIAL 0x501
#define ARC_IO_COH_PARTIAL_BIT BIT(0)
#define ARC_REG_IO_COH_AP0_BASE 0x508
#define ARC_REG_IO_COH_AP0_SIZE 0x509
#endif /* _ASM_CACHE_H */