From db9d41cd7180f938ce3d3ab1b214d96fcf872f80 Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Sat, 15 Jul 2017 11:41:21 +1000 Subject: sparc64: NG4 memset 32 bits overflow Early in boot Linux patches memset and memcpy to branch to platform optimized versions of these routines. The NG4 (Niagra 4) versions are currently used on all platforms starting from T4. Recently, there were M7 optimized routines added into UEK4 but not into mainline yet. So, even with M7 optimized routines NG4 are still going to be used on T4, T5, M5, and M6 processors. While investigating how to improve initialization time of dentry_hashtable which is 8G long on M6 ldom with 7T of main memory, I noticed that memset() does not reset all the memory in this array, after studying the code, I realized that NG4memset() branches use %icc register instead of %xcc to check compare, so if value of length is over 32-bit long, which is true for 8G array, these routines fail to work properly. The fix is to replace all %icc with %xcc in these routines. (Alternative is to use %ncc, but this is misleading, as the code already has sparcv9 only instructions, and cannot be compiled on 32-bit). This is important to fix this bug, because even older T4-4 can have 2T of memory, and there are large memory proportional data structures in kernel which can be larger than 4G in size. The failing of memset() is silent and corruption is hard to detect. Link: http://lkml.kernel.org/r/1488432825-92126-2-git-send-email-pasha.tatashin@oracle.com Signed-off-by: Pavel Tatashin Reviewed-by: Babu Moger Cc: David Miller Cc: Al Viro Signed-off-by: Andrew Morton --- arch/sparc/lib/NG4memset.S | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) diff --git a/arch/sparc/lib/NG4memset.S b/arch/sparc/lib/NG4memset.S index 7c0c81f18837..c07834f3a6fc 100644 --- a/arch/sparc/lib/NG4memset.S +++ b/arch/sparc/lib/NG4memset.S @@ -13,14 +13,14 @@ .globl NG4memset NG4memset: andcc %o1, 0xff, %o4 - be,pt %icc, 1f + be,pt %xcc, 1f mov %o2, %o1 sllx %o4, 8, %g1 or %g1, %o4, %o2 sllx %o2, 16, %g1 or %g1, %o2, %o2 sllx %o2, 32, %g1 - ba,pt %icc, 1f + ba,pt %xcc, 1f or %g1, %o2, %o4 .size NG4memset,.-NG4memset @@ -29,7 +29,7 @@ NG4memset: NG4bzero: clr %o4 1: cmp %o1, 16 - ble %icc, .Ltiny + ble %xcc, .Ltiny mov %o0, %o3 sub %g0, %o0, %g1 and %g1, 0x7, %g1 @@ -37,7 +37,7 @@ NG4bzero: sub %o1, %g1, %o1 1: stb %o4, [%o0 + 0x00] subcc %g1, 1, %g1 - bne,pt %icc, 1b + bne,pt %xcc, 1b add %o0, 1, %o0 .Laligned8: cmp %o1, 64 + (64 - 8) @@ -48,7 +48,7 @@ NG4bzero: sub %o1, %g1, %o1 1: stx %o4, [%o0 + 0x00] subcc %g1, 8, %g1 - bne,pt %icc, 1b + bne,pt %xcc, 1b add %o0, 0x8, %o0 .Laligned64: andn %o1, 64 - 1, %g1 @@ -58,30 +58,30 @@ NG4bzero: 1: stxa %o4, [%o0 + %g0] ASI_BLK_INIT_QUAD_LDD_P subcc %g1, 0x40, %g1 stxa %o4, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P - bne,pt %icc, 1b + bne,pt %xcc, 1b add %o0, 0x40, %o0 .Lpostloop: cmp %o1, 8 - bl,pn %icc, .Ltiny + bl,pn %xcc, .Ltiny membar #StoreStore|#StoreLoad .Lmedium: andn %o1, 0x7, %g1 sub %o1, %g1, %o1 1: stx %o4, [%o0 + 0x00] subcc %g1, 0x8, %g1 - bne,pt %icc, 1b + bne,pt %xcc, 1b add %o0, 0x08, %o0 andcc %o1, 0x4, %g1 - be,pt %icc, .Ltiny + be,pt %xcc, .Ltiny sub %o1, %g1, %o1 stw %o4, [%o0 + 0x00] add %o0, 0x4, %o0 .Ltiny: cmp %o1, 0 - be,pn %icc, .Lexit + be,pn %xcc, .Lexit 1: subcc %o1, 1, %o1 stb %o4, [%o0 + 0x00] - bne,pt %icc, 1b + bne,pt %xcc, 1b add %o0, 1, %o0 .Lexit: retl @@ -99,8 +99,8 @@ NG4bzero: stxa %o4, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P stxa %o4, [%o0 + %g3] ASI_BLK_INIT_QUAD_LDD_P stxa %o4, [%o0 + %o5] ASI_BLK_INIT_QUAD_LDD_P - bne,pt %icc, 1b + bne,pt %xcc, 1b add %o0, 0x30, %o0 - ba,a,pt %icc, .Lpostloop + ba,a,pt %xcc, .Lpostloop nop .size NG4bzero,.-NG4bzero -- cgit v1.2.3 From 84940f8830a2b310484c69ab03b5513afa0e1c4d Mon Sep 17 00:00:00 2001 From: Andrey Vostrikov Date: Sat, 15 Jul 2017 11:41:21 +1000 Subject: lib/crc-ccitt: add CCITT-FALSE CRC16 variant In support of a soon to be published MFD driver using serdev to talk to a supervisory processor that uses the CCITT-FALSE CRC16 variant in it's protocol, this patch was tested successfully on an i.MX6 ARM platform. Link: http://lkml.kernel.org/r/20170413142932.27287-1-andrew.smirnov@gmail.com Signed-off-by: Andrey Vostrikov Signed-off-by: Andrey Smirnov Tested-by: Chris Healy Signed-off-by: Andrew Morton --- include/linux/crc-ccitt.h | 7 ++++++ lib/crc-ccitt.c | 58 ++++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 64 insertions(+), 1 deletion(-) diff --git a/include/linux/crc-ccitt.h b/include/linux/crc-ccitt.h index f52696a1ff0d..7cd45a4bc224 100644 --- a/include/linux/crc-ccitt.h +++ b/include/linux/crc-ccitt.h @@ -4,12 +4,19 @@ #include extern u16 const crc_ccitt_table[256]; +extern u16 const crc_ccitt_false_table[256]; extern u16 crc_ccitt(u16 crc, const u8 *buffer, size_t len); +extern u16 crc_ccitt_false(u16 crc, const u8 *buffer, size_t len); static inline u16 crc_ccitt_byte(u16 crc, const u8 c) { return (crc >> 8) ^ crc_ccitt_table[(crc ^ c) & 0xff]; } +static inline u16 crc_ccitt_false_byte(u16 crc, const u8 c) +{ + return (crc << 8) ^ crc_ccitt_false_table[(crc >> 8) ^ c]; +} + #endif /* _LINUX_CRC_CCITT_H */ diff --git a/lib/crc-ccitt.c b/lib/crc-ccitt.c index 7f6dd68d2d09..d873b34039ff 100644 --- a/lib/crc-ccitt.c +++ b/lib/crc-ccitt.c @@ -51,8 +51,49 @@ u16 const crc_ccitt_table[256] = { }; EXPORT_SYMBOL(crc_ccitt_table); +/* + * Similar table to calculate CRC16 variant known as CRC-CCITT-FALSE + * Reflected bits order, does not augment final value. + */ +u16 const crc_ccitt_false_table[256] = { + 0x0000, 0x1021, 0x2042, 0x3063, 0x4084, 0x50A5, 0x60C6, 0x70E7, + 0x8108, 0x9129, 0xA14A, 0xB16B, 0xC18C, 0xD1AD, 0xE1CE, 0xF1EF, + 0x1231, 0x0210, 0x3273, 0x2252, 0x52B5, 0x4294, 0x72F7, 0x62D6, + 0x9339, 0x8318, 0xB37B, 0xA35A, 0xD3BD, 0xC39C, 0xF3FF, 0xE3DE, + 0x2462, 0x3443, 0x0420, 0x1401, 0x64E6, 0x74C7, 0x44A4, 0x5485, + 0xA56A, 0xB54B, 0x8528, 0x9509, 0xE5EE, 0xF5CF, 0xC5AC, 0xD58D, + 0x3653, 0x2672, 0x1611, 0x0630, 0x76D7, 0x66F6, 0x5695, 0x46B4, + 0xB75B, 0xA77A, 0x9719, 0x8738, 0xF7DF, 0xE7FE, 0xD79D, 0xC7BC, + 0x48C4, 0x58E5, 0x6886, 0x78A7, 0x0840, 0x1861, 0x2802, 0x3823, + 0xC9CC, 0xD9ED, 0xE98E, 0xF9AF, 0x8948, 0x9969, 0xA90A, 0xB92B, + 0x5AF5, 0x4AD4, 0x7AB7, 0x6A96, 0x1A71, 0x0A50, 0x3A33, 0x2A12, + 0xDBFD, 0xCBDC, 0xFBBF, 0xEB9E, 0x9B79, 0x8B58, 0xBB3B, 0xAB1A, + 0x6CA6, 0x7C87, 0x4CE4, 0x5CC5, 0x2C22, 0x3C03, 0x0C60, 0x1C41, + 0xEDAE, 0xFD8F, 0xCDEC, 0xDDCD, 0xAD2A, 0xBD0B, 0x8D68, 0x9D49, + 0x7E97, 0x6EB6, 0x5ED5, 0x4EF4, 0x3E13, 0x2E32, 0x1E51, 0x0E70, + 0xFF9F, 0xEFBE, 0xDFDD, 0xCFFC, 0xBF1B, 0xAF3A, 0x9F59, 0x8F78, + 0x9188, 0x81A9, 0xB1CA, 0xA1EB, 0xD10C, 0xC12D, 0xF14E, 0xE16F, + 0x1080, 0x00A1, 0x30C2, 0x20E3, 0x5004, 0x4025, 0x7046, 0x6067, + 0x83B9, 0x9398, 0xA3FB, 0xB3DA, 0xC33D, 0xD31C, 0xE37F, 0xF35E, + 0x02B1, 0x1290, 0x22F3, 0x32D2, 0x4235, 0x5214, 0x6277, 0x7256, + 0xB5EA, 0xA5CB, 0x95A8, 0x8589, 0xF56E, 0xE54F, 0xD52C, 0xC50D, + 0x34E2, 0x24C3, 0x14A0, 0x0481, 0x7466, 0x6447, 0x5424, 0x4405, + 0xA7DB, 0xB7FA, 0x8799, 0x97B8, 0xE75F, 0xF77E, 0xC71D, 0xD73C, + 0x26D3, 0x36F2, 0x0691, 0x16B0, 0x6657, 0x7676, 0x4615, 0x5634, + 0xD94C, 0xC96D, 0xF90E, 0xE92F, 0x99C8, 0x89E9, 0xB98A, 0xA9AB, + 0x5844, 0x4865, 0x7806, 0x6827, 0x18C0, 0x08E1, 0x3882, 0x28A3, + 0xCB7D, 0xDB5C, 0xEB3F, 0xFB1E, 0x8BF9, 0x9BD8, 0xABBB, 0xBB9A, + 0x4A75, 0x5A54, 0x6A37, 0x7A16, 0x0AF1, 0x1AD0, 0x2AB3, 0x3A92, + 0xFD2E, 0xED0F, 0xDD6C, 0xCD4D, 0xBDAA, 0xAD8B, 0x9DE8, 0x8DC9, + 0x7C26, 0x6C07, 0x5C64, 0x4C45, 0x3CA2, 0x2C83, 0x1CE0, 0x0CC1, + 0xEF1F, 0xFF3E, 0xCF5D, 0xDF7C, 0xAF9B, 0xBFBA, 0x8FD9, 0x9FF8, + 0x6E17, 0x7E36, 0x4E55, 0x5E74, 0x2E93, 0x3EB2, 0x0ED1, 0x1EF0 +}; +EXPORT_SYMBOL(crc_ccitt_false_table); + /** - * crc_ccitt - recompute the CRC for the data buffer + * crc_ccitt - recompute the CRC (CRC-CCITT variant) for the data + * buffer * @crc: previous CRC value * @buffer: data pointer * @len: number of bytes in the buffer @@ -65,5 +106,20 @@ u16 crc_ccitt(u16 crc, u8 const *buffer, size_t len) } EXPORT_SYMBOL(crc_ccitt); +/** + * crc_ccitt_false - recompute the CRC (CRC-CCITT-FALSE variant) + * for the data buffer + * @crc: previous CRC value + * @buffer: data pointer + * @len: number of bytes in the buffer + */ +u16 crc_ccitt_false(u16 crc, u8 const *buffer, size_t len) +{ + while (len--) + crc = crc_ccitt_false_byte(crc, *buffer++); + return crc; +} +EXPORT_SYMBOL(crc_ccitt_false); + MODULE_DESCRIPTION("CRC-CCITT calculations"); MODULE_LICENSE("GPL"); -- cgit v1.2.3