When lockdep is enabled on a 64-bit kernel the FPR offset into the thread structure exceeds the maximum range of the MSA ld.d/st.d instructions. For example THREAD_FPR31 = 4644 (instead of 2448), while the signed immediate field is only 10 bits with an implicit multiply by 8, giving a maximum offset of 511*8 = 4088. This isn't a problem when the toolchain doesn't support MSA as the ld_*/st_* macros perform the addition separately into $1 with [d]addui which has a 16bit signed immediate field. Fix the case where the toolchain does support MSA by doing a single addition of THREAD_FPR0 into $1 with [d]addui, and doing the ld_*/st_* relative to that. Signed-off-by: James Hogan <james.hogan@xxxxxxxxxx> Cc: Ralf Baechle <ralf@xxxxxxxxxxxxxx> Cc: Paul Burton <paul.burton@xxxxxxxxxx> Cc: linux-mips@xxxxxxxxxxxxxx --- arch/mips/include/asm/asmmacro.h | 147 ++++++++++++++++++++++----------------- 1 file changed, 82 insertions(+), 65 deletions(-) diff --git a/arch/mips/include/asm/asmmacro.h b/arch/mips/include/asm/asmmacro.h index e689b894353c..637fccab5604 100644 --- a/arch/mips/include/asm/asmmacro.h +++ b/arch/mips/include/asm/asmmacro.h @@ -496,41 +496,52 @@ .endm #endif +#ifdef TOOLCHAIN_SUPPORTS_MSA +#define FPR_BASE_OFFS THREAD_FPR0 +#define FPR_BASE $1 +#else +#define FPR_BASE_OFFS 0 +#define FPR_BASE \thread +#endif + .macro msa_save_all thread - st_d 0, THREAD_FPR0, \thread - st_d 1, THREAD_FPR1, \thread - st_d 2, THREAD_FPR2, \thread - st_d 3, THREAD_FPR3, \thread - st_d 4, THREAD_FPR4, \thread - st_d 5, THREAD_FPR5, \thread - st_d 6, THREAD_FPR6, \thread - st_d 7, THREAD_FPR7, \thread - st_d 8, THREAD_FPR8, \thread - st_d 9, THREAD_FPR9, \thread - st_d 10, THREAD_FPR10, \thread - st_d 11, THREAD_FPR11, \thread - st_d 12, THREAD_FPR12, \thread - st_d 13, THREAD_FPR13, \thread - st_d 14, THREAD_FPR14, \thread - st_d 15, THREAD_FPR15, \thread - st_d 16, THREAD_FPR16, \thread - st_d 17, THREAD_FPR17, \thread - st_d 18, THREAD_FPR18, \thread - st_d 19, THREAD_FPR19, \thread - st_d 20, THREAD_FPR20, \thread - st_d 21, THREAD_FPR21, \thread - st_d 22, THREAD_FPR22, \thread - st_d 23, THREAD_FPR23, \thread - st_d 24, THREAD_FPR24, \thread - st_d 25, THREAD_FPR25, \thread - st_d 26, THREAD_FPR26, \thread - st_d 27, THREAD_FPR27, \thread - st_d 28, THREAD_FPR28, \thread - st_d 29, THREAD_FPR29, \thread - st_d 30, THREAD_FPR30, \thread - st_d 31, THREAD_FPR31, \thread .set push .set noat +#ifdef TOOLCHAIN_SUPPORTS_MSA + PTR_ADDU FPR_BASE, \thread, FPR_BASE_OFFS +#endif + st_d 0, THREAD_FPR0 - FPR_BASE_OFFS, FPR_BASE + st_d 1, THREAD_FPR1 - FPR_BASE_OFFS, FPR_BASE + st_d 2, THREAD_FPR2 - FPR_BASE_OFFS, FPR_BASE + st_d 3, THREAD_FPR3 - FPR_BASE_OFFS, FPR_BASE + st_d 4, THREAD_FPR4 - FPR_BASE_OFFS, FPR_BASE + st_d 5, THREAD_FPR5 - FPR_BASE_OFFS, FPR_BASE + st_d 6, THREAD_FPR6 - FPR_BASE_OFFS, FPR_BASE + st_d 7, THREAD_FPR7 - FPR_BASE_OFFS, FPR_BASE + st_d 8, THREAD_FPR8 - FPR_BASE_OFFS, FPR_BASE + st_d 9, THREAD_FPR9 - FPR_BASE_OFFS, FPR_BASE + st_d 10, THREAD_FPR10 - FPR_BASE_OFFS, FPR_BASE + st_d 11, THREAD_FPR11 - FPR_BASE_OFFS, FPR_BASE + st_d 12, THREAD_FPR12 - FPR_BASE_OFFS, FPR_BASE + st_d 13, THREAD_FPR13 - FPR_BASE_OFFS, FPR_BASE + st_d 14, THREAD_FPR14 - FPR_BASE_OFFS, FPR_BASE + st_d 15, THREAD_FPR15 - FPR_BASE_OFFS, FPR_BASE + st_d 16, THREAD_FPR16 - FPR_BASE_OFFS, FPR_BASE + st_d 17, THREAD_FPR17 - FPR_BASE_OFFS, FPR_BASE + st_d 18, THREAD_FPR18 - FPR_BASE_OFFS, FPR_BASE + st_d 19, THREAD_FPR19 - FPR_BASE_OFFS, FPR_BASE + st_d 20, THREAD_FPR20 - FPR_BASE_OFFS, FPR_BASE + st_d 21, THREAD_FPR21 - FPR_BASE_OFFS, FPR_BASE + st_d 22, THREAD_FPR22 - FPR_BASE_OFFS, FPR_BASE + st_d 23, THREAD_FPR23 - FPR_BASE_OFFS, FPR_BASE + st_d 24, THREAD_FPR24 - FPR_BASE_OFFS, FPR_BASE + st_d 25, THREAD_FPR25 - FPR_BASE_OFFS, FPR_BASE + st_d 26, THREAD_FPR26 - FPR_BASE_OFFS, FPR_BASE + st_d 27, THREAD_FPR27 - FPR_BASE_OFFS, FPR_BASE + st_d 28, THREAD_FPR28 - FPR_BASE_OFFS, FPR_BASE + st_d 29, THREAD_FPR29 - FPR_BASE_OFFS, FPR_BASE + st_d 30, THREAD_FPR30 - FPR_BASE_OFFS, FPR_BASE + st_d 31, THREAD_FPR31 - FPR_BASE_OFFS, FPR_BASE SET_HARDFLOAT _cfcmsa $1, MSA_CSR sw $1, THREAD_MSA_CSR(\thread) @@ -543,41 +554,47 @@ SET_HARDFLOAT lw $1, THREAD_MSA_CSR(\thread) _ctcmsa MSA_CSR, $1 - .set pop - ld_d 0, THREAD_FPR0, \thread - ld_d 1, THREAD_FPR1, \thread - ld_d 2, THREAD_FPR2, \thread - ld_d 3, THREAD_FPR3, \thread - ld_d 4, THREAD_FPR4, \thread - ld_d 5, THREAD_FPR5, \thread - ld_d 6, THREAD_FPR6, \thread - ld_d 7, THREAD_FPR7, \thread - ld_d 8, THREAD_FPR8, \thread - ld_d 9, THREAD_FPR9, \thread - ld_d 10, THREAD_FPR10, \thread - ld_d 11, THREAD_FPR11, \thread - ld_d 12, THREAD_FPR12, \thread - ld_d 13, THREAD_FPR13, \thread - ld_d 14, THREAD_FPR14, \thread - ld_d 15, THREAD_FPR15, \thread - ld_d 16, THREAD_FPR16, \thread - ld_d 17, THREAD_FPR17, \thread - ld_d 18, THREAD_FPR18, \thread - ld_d 19, THREAD_FPR19, \thread - ld_d 20, THREAD_FPR20, \thread - ld_d 21, THREAD_FPR21, \thread - ld_d 22, THREAD_FPR22, \thread - ld_d 23, THREAD_FPR23, \thread - ld_d 24, THREAD_FPR24, \thread - ld_d 25, THREAD_FPR25, \thread - ld_d 26, THREAD_FPR26, \thread - ld_d 27, THREAD_FPR27, \thread - ld_d 28, THREAD_FPR28, \thread - ld_d 29, THREAD_FPR29, \thread - ld_d 30, THREAD_FPR30, \thread - ld_d 31, THREAD_FPR31, \thread +#ifdef TOOLCHAIN_SUPPORTS_MSA + PTR_ADDU FPR_BASE, \thread, FPR_BASE_OFFS +#endif + ld_d 0, THREAD_FPR0 - FPR_BASE_OFFS, FPR_BASE + ld_d 1, THREAD_FPR1 - FPR_BASE_OFFS, FPR_BASE + ld_d 2, THREAD_FPR2 - FPR_BASE_OFFS, FPR_BASE + ld_d 3, THREAD_FPR3 - FPR_BASE_OFFS, FPR_BASE + ld_d 4, THREAD_FPR4 - FPR_BASE_OFFS, FPR_BASE + ld_d 5, THREAD_FPR5 - FPR_BASE_OFFS, FPR_BASE + ld_d 6, THREAD_FPR6 - FPR_BASE_OFFS, FPR_BASE + ld_d 7, THREAD_FPR7 - FPR_BASE_OFFS, FPR_BASE + ld_d 8, THREAD_FPR8 - FPR_BASE_OFFS, FPR_BASE + ld_d 9, THREAD_FPR9 - FPR_BASE_OFFS, FPR_BASE + ld_d 10, THREAD_FPR10 - FPR_BASE_OFFS, FPR_BASE + ld_d 11, THREAD_FPR11 - FPR_BASE_OFFS, FPR_BASE + ld_d 12, THREAD_FPR12 - FPR_BASE_OFFS, FPR_BASE + ld_d 13, THREAD_FPR13 - FPR_BASE_OFFS, FPR_BASE + ld_d 14, THREAD_FPR14 - FPR_BASE_OFFS, FPR_BASE + ld_d 15, THREAD_FPR15 - FPR_BASE_OFFS, FPR_BASE + ld_d 16, THREAD_FPR16 - FPR_BASE_OFFS, FPR_BASE + ld_d 17, THREAD_FPR17 - FPR_BASE_OFFS, FPR_BASE + ld_d 18, THREAD_FPR18 - FPR_BASE_OFFS, FPR_BASE + ld_d 19, THREAD_FPR19 - FPR_BASE_OFFS, FPR_BASE + ld_d 20, THREAD_FPR20 - FPR_BASE_OFFS, FPR_BASE + ld_d 21, THREAD_FPR21 - FPR_BASE_OFFS, FPR_BASE + ld_d 22, THREAD_FPR22 - FPR_BASE_OFFS, FPR_BASE + ld_d 23, THREAD_FPR23 - FPR_BASE_OFFS, FPR_BASE + ld_d 24, THREAD_FPR24 - FPR_BASE_OFFS, FPR_BASE + ld_d 25, THREAD_FPR25 - FPR_BASE_OFFS, FPR_BASE + ld_d 26, THREAD_FPR26 - FPR_BASE_OFFS, FPR_BASE + ld_d 27, THREAD_FPR27 - FPR_BASE_OFFS, FPR_BASE + ld_d 28, THREAD_FPR28 - FPR_BASE_OFFS, FPR_BASE + ld_d 29, THREAD_FPR29 - FPR_BASE_OFFS, FPR_BASE + ld_d 30, THREAD_FPR30 - FPR_BASE_OFFS, FPR_BASE + ld_d 31, THREAD_FPR31 - FPR_BASE_OFFS, FPR_BASE + .set pop .endm +#undef FPR_BASE_OFFS +#undef FPR_BASE + .macro msa_init_upper wd #ifdef CONFIG_64BIT insert_d \wd, 1 -- 2.4.10
