diff options
Diffstat (limited to 'arch/powerpc/kernel')
49 files changed, 1229 insertions, 970 deletions
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c index faaec9c6f78f..4734b5de599d 100644 --- a/arch/powerpc/kernel/align.c +++ b/arch/powerpc/kernel/align.c @@ -35,17 +35,19 @@ struct aligninfo { #define INVALID { 0, 0 } -#define LD 1 /* load */ -#define ST 2 /* store */ -#define SE 4 /* sign-extend value */ -#define F 8 /* to/from fp regs */ -#define U 0x10 /* update index register */ -#define M 0x20 /* multiple load/store */ -#define SW 0x40 /* byte swap int or ... */ -#define S 0x40 /* ... single-precision fp */ -#define SX 0x40 /* byte count in XER */ +/* Bits in the flags field */ +#define LD 0 /* load */ +#define ST 1 /* store */ +#define SE 2 /* sign-extend value */ +#define F 4 /* to/from fp regs */ +#define U 8 /* update index register */ +#define M 0x10 /* multiple load/store */ +#define SW 0x20 /* byte swap */ +#define S 0x40 /* single-precision fp or... */ +#define SX 0x40 /* ... byte count in XER */ #define HARD 0x80 /* string, stwcx. */ +/* DSISR bits reported for a DCBZ instruction: */ #define DCBZ 0x5f /* 8xx/82xx dcbz faults when cache not enabled */ #define SWAP(a, b) (t = (a), (a) = (b), (b) = t) @@ -256,12 +258,16 @@ static int emulate_dcbz(struct pt_regs *regs, unsigned char __user *addr) #define REG_BYTE(rp, i) *((u8 *)(rp) + (i)) #endif +#define SWIZ_PTR(p) ((unsigned char __user *)((p) ^ swiz)) + static int emulate_multiple(struct pt_regs *regs, unsigned char __user *addr, unsigned int reg, unsigned int nb, - unsigned int flags, unsigned int instr) + unsigned int flags, unsigned int instr, + unsigned long swiz) { unsigned long *rptr; - unsigned int nb0, i; + unsigned int nb0, i, bswiz; + unsigned long p; /* * We do not try to emulate 8 bytes multiple as they aren't really @@ -280,9 +286,12 @@ static int emulate_multiple(struct pt_regs *regs, unsigned char __user *addr, if (nb == 0) return 1; } else { - if (__get_user(instr, - (unsigned int __user *)regs->nip)) + unsigned long pc = regs->nip ^ (swiz & 4); + + if (__get_user(instr, (unsigned int __user *)pc)) return -EFAULT; + if (swiz == 0 && (flags & SW)) + instr = cpu_to_le32(instr); nb = (instr >> 11) & 0x1f; if (nb == 0) nb = 32; @@ -300,7 +309,10 @@ static int emulate_multiple(struct pt_regs *regs, unsigned char __user *addr, return -EFAULT; /* bad address */ rptr = ®s->gpr[reg]; - if (flags & LD) { + p = (unsigned long) addr; + bswiz = (flags & SW)? 3: 0; + + if (!(flags & ST)) { /* * This zeroes the top 4 bytes of the affected registers * in 64-bit mode, and also zeroes out any remaining @@ -311,26 +323,28 @@ static int emulate_multiple(struct pt_regs *regs, unsigned char __user *addr, memset(®s->gpr[0], 0, ((nb0 + 3) / 4) * sizeof(unsigned long)); - for (i = 0; i < nb; ++i) - if (__get_user(REG_BYTE(rptr, i), addr + i)) + for (i = 0; i < nb; ++i, ++p) + if (__get_user(REG_BYTE(rptr, i ^ bswiz), SWIZ_PTR(p))) return -EFAULT; if (nb0 > 0) { rptr = ®s->gpr[0]; addr += nb; - for (i = 0; i < nb0; ++i) - if (__get_user(REG_BYTE(rptr, i), addr + i)) + for (i = 0; i < nb0; ++i, ++p) + if (__get_user(REG_BYTE(rptr, i ^ bswiz), + SWIZ_PTR(p))) return -EFAULT; } } else { - for (i = 0; i < nb; ++i) - if (__put_user(REG_BYTE(rptr, i), addr + i)) + for (i = 0; i < nb; ++i, ++p) + if (__put_user(REG_BYTE(rptr, i ^ bswiz), SWIZ_PTR(p))) return -EFAULT; if (nb0 > 0) { rptr = ®s->gpr[0]; addr += nb; - for (i = 0; i < nb0; ++i) - if (__put_user(REG_BYTE(rptr, i), addr + i)) + for (i = 0; i < nb0; ++i, ++p) + if (__put_user(REG_BYTE(rptr, i ^ bswiz), + SWIZ_PTR(p))) return -EFAULT; } } @@ -352,7 +366,7 @@ int fix_alignment(struct pt_regs *regs) unsigned int reg, areg; unsigned int dsisr; unsigned char __user *addr; - unsigned char __user *p; + unsigned long p, swiz; int ret, t; union { u64 ll; @@ -380,11 +394,15 @@ int fix_alignment(struct pt_regs *regs) * let's make one up from the instruction */ if (cpu_has_feature(CPU_FTR_NODSISRALIGN)) { - unsigned int real_instr; - if (unlikely(__get_user(real_instr, - (unsigned int __user *)regs->nip))) + unsigned long pc = regs->nip; + + if (cpu_has_feature(CPU_FTR_PPC_LE) && (regs->msr & MSR_LE)) + pc ^= 4; + if (unlikely(__get_user(instr, (unsigned int __user *)pc))) return -EFAULT; - dsisr = make_dsisr(real_instr); + if (cpu_has_feature(CPU_FTR_REAL_LE) && (regs->msr & MSR_LE)) + instr = cpu_to_le32(instr); + dsisr = make_dsisr(instr); } /* extract the operation and registers from the dsisr */ @@ -397,6 +415,24 @@ int fix_alignment(struct pt_regs *regs) nb = aligninfo[instr].len; flags = aligninfo[instr].flags; + /* Byteswap little endian loads and stores */ + swiz = 0; + if (regs->msr & MSR_LE) { + flags ^= SW; + /* + * So-called "PowerPC little endian" mode works by + * swizzling addresses rather than by actually doing + * any byte-swapping. To emulate this, we XOR each + * byte address with 7. We also byte-swap, because + * the processor's address swizzling depends on the + * operand size (it xors the address with 7 for bytes, + * 6 for halfwords, 4 for words, 0 for doublewords) but + * we will xor with 7 and load/store each byte separately. + */ + if (cpu_has_feature(CPU_FTR_PPC_LE)) + swiz = 7; + } + /* DAR has the operand effective address */ addr = (unsigned char __user *)regs->dar; @@ -412,7 +448,8 @@ int fix_alignment(struct pt_regs *regs) * function */ if (flags & M) - return emulate_multiple(regs, addr, reg, nb, flags, instr); + return emulate_multiple(regs, addr, reg, nb, + flags, instr, swiz); /* Verify the address of the operand */ if (unlikely(user_mode(regs) && @@ -431,51 +468,71 @@ int fix_alignment(struct pt_regs *regs) /* If we are loading, get the data from user space, else * get it from register values */ - if (flags & LD) { + if (!(flags & ST)) { data.ll = 0; ret = 0; - p = addr; + p = (unsigned long) addr; switch (nb) { case 8: - ret |= __get_user(data.v[0], p++); - ret |= __get_user(data.v[1], p++); - ret |= __get_user(data.v[2], p++); - ret |= __get_user(data.v[3], p++); + ret |= __get_user(data.v[0], SWIZ_PTR(p++)); + ret |= __get_user(data.v[1], SWIZ_PTR(p++)); + ret |= __get_user(data.v[2], SWIZ_PTR(p++)); + ret |= __get_user(data.v[3], SWIZ_PTR(p++)); case 4: - ret |= __get_user(data.v[4], p++); - ret |= __get_user(data.v[5], p++); + ret |= __get_user(data.v[4], SWIZ_PTR(p++)); + ret |= __get_user(data.v[5], SWIZ_PTR(p++)); case 2: - ret |= __get_user(data.v[6], p++); - ret |= __get_user(data.v[7], p++); + ret |= __get_user(data.v[6], SWIZ_PTR(p++)); + ret |= __get_user(data.v[7], SWIZ_PTR(p++)); if (unlikely(ret)) return -EFAULT; } - } else if (flags & F) + } else if (flags & F) { data.dd = current->thread.fpr[reg]; - else + if (flags & S) { + /* Single-precision FP store requires conversion... */ +#ifdef CONFIG_PPC_FPU + preempt_disable(); + enable_kernel_fp(); + cvt_df(&data.dd, (float *)&data.v[4], ¤t->thread); + preempt_enable(); +#else + return 0; +#endif + } + } else data.ll = regs->gpr[reg]; - /* Perform other misc operations like sign extension, byteswap, + if (flags & SW) { + switch (nb) { + case 8: + SWAP(data.v[0], data.v[7]); + SWAP(data.v[1], data.v[6]); + SWAP(data.v[2], data.v[5]); + SWAP(data.v[3], data.v[4]); + break; + case 4: + SWAP(data.v[4], data.v[7]); + SWAP(data.v[5], data.v[6]); + break; + case 2: + SWAP(data.v[6], data.v[7]); + break; + } + } + + /* Perform other misc operations like sign extension * or floating point single precision conversion */ - switch (flags & ~U) { + switch (flags & ~(U|SW)) { case LD+SE: /* sign extend */ if ( nb == 2 ) data.ll = data.x16.low16; else /* nb must be 4 */ data.ll = data.x32.low32; break; - case LD+S: /* byte-swap */ - case ST+S: - if (nb == 2) { - SWAP(data.v[6], data.v[7]); - } else { - SWAP(data.v[4], data.v[7]); - SWAP(data.v[5], data.v[6]); - } - break; - /* Single-precision FP load and store require conversions... */ + /* Single-precision FP load requires conversion... */ case LD+F+S: #ifdef CONFIG_PPC_FPU preempt_disable(); @@ -486,34 +543,24 @@ int fix_alignment(struct pt_regs *regs) return 0; #endif break; - case ST+F+S: -#ifdef CONFIG_PPC_FPU - preempt_disable(); - enable_kernel_fp(); - cvt_df(&data.dd, (float *)&data.v[4], ¤t->thread); - preempt_enable(); -#else - return 0; -#endif - break; } /* Store result to memory or update registers */ if (flags & ST) { ret = 0; - p = addr; + p = (unsigned long) addr; switch (nb) { case 8: - ret |= __put_user(data.v[0], p++); - ret |= __put_user(data.v[1], p++); - ret |= __put_user(data.v[2], p++); - ret |= __put_user(data.v[3], p++); + ret |= __put_user(data.v[0], SWIZ_PTR(p++)); + ret |= __put_user(data.v[1], SWIZ_PTR(p++)); + ret |= __put_user(data.v[2], SWIZ_PTR(p++)); + ret |= __put_user(data.v[3], SWIZ_PTR(p++)); case 4: - ret |= __put_user(data.v[4], p++); - ret |= __put_user(data.v[5], p++); + ret |= __put_user(data.v[4], SWIZ_PTR(p++)); + ret |= __put_user(data.v[5], SWIZ_PTR(p++)); case 2: - ret |= __put_user(data.v[6], p++); - ret |= __put_user(data.v[7], p++); + ret |= __put_user(data.v[6], SWIZ_PTR(p++)); + ret |= __put_user(data.v[7], SWIZ_PTR(p++)); } if (unlikely(ret)) return -EFAULT; diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 8f85c5e8a55a..ff2940548929 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -122,9 +122,8 @@ int main(void) DEFINE(PACASLBCACHE, offsetof(struct paca_struct, slb_cache)); DEFINE(PACASLBCACHEPTR, offsetof(struct paca_struct, slb_cache_ptr)); DEFINE(PACACONTEXTID, offsetof(struct paca_struct, context.id)); -#ifdef CONFIG_PPC_64K_PAGES - DEFINE(PACAPGDIR, offsetof(struct paca_struct, pgdir)); -#endif + DEFINE(PACACONTEXTSLLP, offsetof(struct paca_struct, context.sllp)); + DEFINE(PACAVMALLOCSLLP, offsetof(struct paca_struct, vmalloc_sllp)); #ifdef CONFIG_HUGETLB_PAGE DEFINE(PACALOWHTLBAREAS, offsetof(struct paca_struct, context.low_htlb_areas)); DEFINE(PACAHIGHHTLBAREAS, offsetof(struct paca_struct, context.high_htlb_areas)); diff --git a/arch/powerpc/kernel/cpu_setup_6xx.S b/arch/powerpc/kernel/cpu_setup_6xx.S index 55ed7716636f..365381fcb27c 100644 --- a/arch/powerpc/kernel/cpu_setup_6xx.S +++ b/arch/powerpc/kernel/cpu_setup_6xx.S @@ -210,9 +210,11 @@ setup_745x_specifics: * the firmware. If any, we disable NAP capability as * it's known to be bogus on rev 2.1 and earlier */ +BEGIN_FTR_SECTION mfspr r11,SPRN_L3CR andis. r11,r11,L3CR_L3E@h beq 1f +END_FTR_SECTION_IFSET(CPU_FTR_L3CR) lwz r6,CPU_SPEC_FEATURES(r5) andi. r0,r6,CPU_FTR_L3_DISABLE_NAP beq 1f diff --git a/arch/powerpc/kernel/cpu_setup_power4.S b/arch/powerpc/kernel/cpu_setup_power4.S index b61d86e7ceb6..271418308d53 100644 --- a/arch/powerpc/kernel/cpu_setup_power4.S +++ b/arch/powerpc/kernel/cpu_setup_power4.S @@ -73,23 +73,6 @@ _GLOBAL(__970_cpu_preinit) isync blr -_GLOBAL(__setup_cpu_power4) - blr - -_GLOBAL(__setup_cpu_be) - /* Set large page sizes LP=0: 16MB, LP=1: 64KB */ - addi r3, 0, 0 - ori r3, r3, HID6_LB - sldi r3, r3, 32 - nor r3, r3, r3 - mfspr r4, SPRN_HID6 - and r4, r4, r3 - addi r3, 0, 0x02000 - sldi r3, r3, 32 - or r4, r4, r3 - mtspr SPRN_HID6, r4 - blr - _GLOBAL(__setup_cpu_ppc970) mfspr r0,SPRN_HID0 li r11,5 /* clear DOZE and SLEEP */ diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 3f7182db9ed5..1c114880dc05 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -30,11 +30,7 @@ EXPORT_SYMBOL(cur_cpu_spec); * part of the cputable though. That has to be fixed for both ppc32 * and ppc64 */ -#ifdef CONFIG_PPC64 -extern void __setup_cpu_power3(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_power4(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_be(unsigned long offset, struct cpu_spec* spec); -#else +#ifdef CONFIG_PPC32 extern void __setup_cpu_603(unsigned long offset, struct cpu_spec* spec); extern void __setup_cpu_604(unsigned long offset, struct cpu_spec* spec); extern void __setup_cpu_750(unsigned long offset, struct cpu_spec* spec); @@ -58,7 +54,8 @@ extern void __setup_cpu_ppc970(unsigned long offset, struct cpu_spec* spec); #define COMMON_USER_POWER5_PLUS (COMMON_USER_PPC64 | PPC_FEATURE_POWER5_PLUS|\ PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP) #define COMMON_USER_POWER6 (COMMON_USER_PPC64 | PPC_FEATURE_ARCH_2_05 |\ - PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP) + PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP | \ + PPC_FEATURE_TRUE_LE) #define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \ PPC_FEATURE_BOOKE) @@ -78,11 +75,10 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x00400000, .cpu_name = "POWER3 (630)", .cpu_features = CPU_FTRS_POWER3, - .cpu_user_features = COMMON_USER_PPC64, + .cpu_user_features = COMMON_USER_PPC64|PPC_FEATURE_PPC_LE, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, - .cpu_setup = __setup_cpu_power3, .oprofile_cpu_type = "ppc64/power3", .oprofile_type = PPC_OPROFILE_RS64, .platform = "power3", @@ -92,11 +88,10 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x00410000, .cpu_name = "POWER3 (630+)", .cpu_features = CPU_FTRS_POWER3, - .cpu_user_features = COMMON_USER_PPC64, + .cpu_user_features = COMMON_USER_PPC64|PPC_FEATURE_PPC_LE, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, - .cpu_setup = __setup_cpu_power3, .oprofile_cpu_type = "ppc64/power3", .oprofile_type = PPC_OPROFILE_RS64, .platform = "power3", @@ -110,7 +105,6 @@ struct cpu_spec cpu_specs[] = { .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, - .cpu_setup = __setup_cpu_power3, .oprofile_cpu_type = "ppc64/rs64", .oprofile_type = PPC_OPROFILE_RS64, .platform = "rs64", @@ -124,7 +118,6 @@ struct cpu_spec cpu_specs[] = { .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, - .cpu_setup = __setup_cpu_power3, .oprofile_cpu_type = "ppc64/rs64", .oprofile_type = PPC_OPROFILE_RS64, .platform = "rs64", @@ -138,7 +131,6 @@ struct cpu_spec cpu_specs[] = { .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, - .cpu_setup = __setup_cpu_power3, .oprofile_cpu_type = "ppc64/rs64", .oprofile_type = PPC_OPROFILE_RS64, .platform = "rs64", @@ -152,7 +144,6 @@ struct cpu_spec cpu_specs[] = { .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, - .cpu_setup = __setup_cpu_power3, .oprofile_cpu_type = "ppc64/rs64", .oprofile_type = PPC_OPROFILE_RS64, .platform = "rs64", @@ -166,7 +157,6 @@ struct cpu_spec cpu_specs[] = { .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, - .cpu_setup = __setup_cpu_power4, .oprofile_cpu_type = "ppc64/power4", .oprofile_type = PPC_OPROFILE_POWER4, .platform = "power4", @@ -180,7 +170,6 @@ struct cpu_spec cpu_specs[] = { .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, - .cpu_setup = __setup_cpu_power4, .oprofile_cpu_type = "ppc64/power4", .oprofile_type = PPC_OPROFILE_POWER4, .platform = "power4", @@ -200,17 +189,11 @@ struct cpu_spec cpu_specs[] = { .oprofile_type = PPC_OPROFILE_POWER4, .platform = "ppc970", }, -#endif /* CONFIG_PPC64 */ -#if defined(CONFIG_PPC64) || defined(CONFIG_POWER4) { /* PPC970FX */ .pvr_mask = 0xffff0000, .pvr_value = 0x003c0000, .cpu_name = "PPC970FX", -#ifdef CONFIG_PPC32 - .cpu_features = CPU_FTRS_970_32, -#else .cpu_features = CPU_FTRS_PPC970, -#endif .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP, .icache_bsize = 128, @@ -221,8 +204,6 @@ struct cpu_spec cpu_specs[] = { .oprofile_type = PPC_OPROFILE_POWER4, .platform = "ppc970", }, -#endif /* defined(CONFIG_PPC64) || defined(CONFIG_POWER4) */ -#ifdef CONFIG_PPC64 { /* PPC970MP */ .pvr_mask = 0xffff0000, .pvr_value = 0x00440000, @@ -232,6 +213,7 @@ struct cpu_spec cpu_specs[] = { PPC_FEATURE_HAS_ALTIVEC_COMP, .icache_bsize = 128, .dcache_bsize = 128, + .num_pmcs = 8, .cpu_setup = __setup_cpu_ppc970, .oprofile_cpu_type = "ppc64/970", .oprofile_type = PPC_OPROFILE_POWER4, @@ -246,9 +228,13 @@ struct cpu_spec cpu_specs[] = { .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, - .cpu_setup = __setup_cpu_power4, .oprofile_cpu_type = "ppc64/power5", .oprofile_type = PPC_OPROFILE_POWER4, + /* SIHV / SIPR bits are implemented on POWER4+ (GQ) + * and above but only works on POWER5 and above + */ + .oprofile_mmcra_sihv = MMCRA_SIHV, + .oprofile_mmcra_sipr = MMCRA_SIPR, .platform = "power5", }, { /* Power5 GS */ @@ -260,9 +246,10 @@ struct cpu_spec cpu_specs[] = { .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, - .cpu_setup = __setup_cpu_power4, .oprofile_cpu_type = "ppc64/power5+", .oprofile_type = PPC_OPROFILE_POWER4, + .oprofile_mmcra_sihv = MMCRA_SIHV, + .oprofile_mmcra_sipr = MMCRA_SIPR, .platform = "power5+", }, { /* Power6 */ @@ -273,10 +260,13 @@ struct cpu_spec cpu_specs[] = { .cpu_user_features = COMMON_USER_POWER6, .icache_bsize = 128, .dcache_bsize = 128, - .num_pmcs = 6, - .cpu_setup = __setup_cpu_power4, + .num_pmcs = 8, .oprofile_cpu_type = "ppc64/power6", .oprofile_type = PPC_OPROFILE_POWER4, + .oprofile_mmcra_sihv = POWER6_MMCRA_SIHV, + .oprofile_mmcra_sipr = POWER6_MMCRA_SIPR, + .oprofile_mmcra_clear = POWER6_MMCRA_THRM | + POWER6_MMCRA_OTHER, .platform = "power6", }, { /* Cell Broadband Engine */ @@ -289,7 +279,6 @@ struct cpu_spec cpu_specs[] = { PPC_FEATURE_SMT, .icache_bsize = 128, .dcache_bsize = 128, - .cpu_setup = __setup_cpu_be, .platform = "ppc-cell-be", }, { /* default match */ @@ -301,7 +290,6 @@ struct cpu_spec cpu_specs[] = { .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, - .cpu_setup = __setup_cpu_power4, .platform = "power4", } #endif /* CONFIG_PPC64 */ @@ -323,7 +311,7 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x00030000, .cpu_name = "603", .cpu_features = CPU_FTRS_603, - .cpu_user_features = COMMON_USER, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_603, @@ -334,7 +322,7 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x00060000, .cpu_name = "603e", .cpu_features = CPU_FTRS_603, - .cpu_user_features = COMMON_USER, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_603, @@ -345,7 +333,7 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x00070000, .cpu_name = "603ev", .cpu_features = CPU_FTRS_603, - .cpu_user_features = COMMON_USER, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_603, @@ -356,7 +344,7 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x00040000, .cpu_name = "604", .cpu_features = CPU_FTRS_604, - .cpu_user_features = COMMON_USER, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 2, @@ -368,7 +356,7 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x00090000, .cpu_name = "604e", .cpu_features = CPU_FTRS_604, - .cpu_user_features = COMMON_USER, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -380,7 +368,7 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x00090000, .cpu_name = "604r", .cpu_features = CPU_FTRS_604, - .cpu_user_features = COMMON_USER, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -392,7 +380,7 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x000a0000, .cpu_name = "604ev", .cpu_features = CPU_FTRS_604, - .cpu_user_features = COMMON_USER, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -404,7 +392,7 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x00084202, .cpu_name = "740/750", .cpu_features = CPU_FTRS_740_NOTAU, - .cpu_user_features = COMMON_USER, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -416,7 +404,7 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x00080100, .cpu_name = "750CX", .cpu_features = CPU_FTRS_750, - .cpu_user_features = COMMON_USER, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -428,7 +416,7 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x00082200, .cpu_name = "750CX", .cpu_features = CPU_FTRS_750, - .cpu_user_features = COMMON_USER, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -440,7 +428,7 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x00082210, .cpu_name = "750CXe", .cpu_features = CPU_FTRS_750, - .cpu_user_features = COMMON_USER, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -452,7 +440,7 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x00083214, .cpu_name = "750CXe", .cpu_features = CPU_FTRS_750, - .cpu_user_features = COMMON_USER, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -464,7 +452,7 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x00083000, .cpu_name = "745/755", .cpu_features = CPU_FTRS_750, - .cpu_user_features = COMMON_USER, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -476,7 +464,7 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x70000100, .cpu_name = "750FX", .cpu_features = CPU_FTRS_750FX1, - .cpu_user_features = COMMON_USER, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -488,7 +476,7 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x70000200, .cpu_name = "750FX", .cpu_features = CPU_FTRS_750FX2, - .cpu_user_features = COMMON_USER, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -500,7 +488,7 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x70000000, .cpu_name = "750FX", .cpu_features = CPU_FTRS_750FX, - .cpu_user_features = COMMON_USER, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -512,7 +500,7 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x70020000, .cpu_name = "750GX", .cpu_features = CPU_FTRS_750GX, - .cpu_user_features = COMMON_USER, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -524,7 +512,7 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x00080000, .cpu_name = "740/750", .cpu_features = CPU_FTRS_740, - .cpu_user_features = COMMON_USER, + .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -536,7 +524,8 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x000c1101, .cpu_name = "7400 (1.1)", .cpu_features = CPU_FTRS_7400_NOTAU, - .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP, + .cpu_user_features = COMMON_USER | + PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -548,7 +537,8 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x000c0000, .cpu_name = "7400", .cpu_features = CPU_FTRS_7400, - .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP, + .cpu_user_features = COMMON_USER | + PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -560,7 +550,8 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x800c0000, .cpu_name = "7410", .cpu_features = CPU_FTRS_7400, - .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP, + .cpu_user_features = COMMON_USER | + PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -572,7 +563,8 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x80000200, .cpu_name = "7450", .cpu_features = CPU_FTRS_7450_20, - .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP, + .cpu_user_features = COMMON_USER | + PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 6, @@ -586,7 +578,8 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x80000201, .cpu_name = "7450", .cpu_features = CPU_FTRS_7450_21, - .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP, + .cpu_user_features = COMMON_USER | + PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 6, @@ -600,7 +593,8 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x80000000, .cpu_name = "7450", .cpu_features = CPU_FTRS_7450_23, - .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP, + .cpu_user_features = COMMON_USER | + PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 6, @@ -614,7 +608,8 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x80010100, .cpu_name = "7455", .cpu_features = CPU_FTRS_7455_1, - .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP, + .cpu_user_features = COMMON_USER | + PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 6, @@ -628,7 +623,8 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x80010200, .cpu_name = "7455", .cpu_features = CPU_FTRS_7455_20, - .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP, + .cpu_user_features = COMMON_USER | + PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 6, @@ -642,7 +638,8 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x80010000, .cpu_name = "7455", .cpu_features = CPU_FTRS_7455, - .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP, + .cpu_user_features = COMMON_USER | + PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 6, @@ -656,7 +653,8 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x80020100, .cpu_name = "7447/7457", .cpu_features = CPU_FTRS_7447_10, - .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP, + .cpu_user_features = COMMON_USER | + PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 6, @@ -670,7 +668,8 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x80020101, .cpu_name = "7447/7457", .cpu_features = CPU_FTRS_7447_10, - .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP, + .cpu_user_features = COMMON_USER | + PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 6, @@ -684,7 +683,7 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x80020000, .cpu_name = "7447/7457", .cpu_features = CPU_FTRS_7447, - .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP, + .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 6, @@ -698,7 +697,8 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x80030000, .cpu_name = "7447A", .cpu_features = CPU_FTRS_7447A, - .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP, + .cpu_user_features = COMMON_USER | + PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 6, @@ -712,7 +712,8 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x80040000, .cpu_name = "7448", .cpu_features = CPU_FTRS_7447A, - .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP, + .cpu_user_features = COMMON_USER | + PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 6, @@ -721,6 +722,18 @@ struct cpu_spec cpu_specs[] = { .oprofile_type = PPC_OPROFILE_G4, .platform = "ppc7450", }, + { /* 8641 */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x80040010, + .cpu_name = "8641", + .cpu_features = CPU_FTRS_7447A, + .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP, + .icache_bsize = 32, + .dcache_bsize = 32, + .num_pmcs = 6, + .cpu_setup = __setup_cpu_745x + }, + { /* 82xx (8240, 8245, 8260 are all 603e cores) */ .pvr_mask = 0x7fff0000, .pvr_value = 0x00810000, diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c index 778f22fd85d2..dbcb85994f46 100644 --- a/arch/powerpc/kernel/crash.c +++ b/arch/powerpc/kernel/crash.c @@ -22,6 +22,7 @@ #include <linux/elf.h> #include <linux/elfcore.h> #include <linux/init.h> +#include <linux/irq.h> #include <linux/types.h> #include <asm/processor.h> @@ -174,6 +175,8 @@ static void crash_kexec_prepare_cpus(void) void default_machine_crash_shutdown(struct pt_regs *regs) { + unsigned int irq; + /* * This function is only called after the system * has paniced or is otherwise in a critical state. @@ -186,6 +189,16 @@ void default_machine_crash_shutdown(struct pt_regs *regs) */ local_irq_disable(); + for_each_irq(irq) { + struct irq_desc *desc = irq_descp(irq); + + if (desc->status & IRQ_INPROGRESS) + desc->handler->end(irq); + + if (!(desc->status & IRQ_DISABLED)) + desc->handler->disable(irq); + } + if (ppc_md.kexec_cpu_down) ppc_md.kexec_cpu_down(1, 0); diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c index 764d07329716..371973be8d71 100644 --- a/arch/powerpc/kernel/crash_dump.c +++ b/arch/powerpc/kernel/crash_dump.c @@ -25,6 +25,11 @@ #define DBG(fmt...) #endif +void reserve_kdump_trampoline(void) +{ + lmb_reserve(0, KDUMP_RESERVE_LIMIT); +} + static void __init create_trampoline(unsigned long addr) { /* The maximum range of a single instruction branch, is the current @@ -39,11 +44,11 @@ static void __init create_trampoline(unsigned long addr) create_branch(addr + 4, addr + PHYSICAL_START, 0); } -void __init kdump_setup(void) +void __init setup_kdump_trampoline(void) { unsigned long i; - DBG(" -> kdump_setup()\n"); + DBG(" -> setup_kdump_trampoline()\n"); for (i = KDUMP_TRAMPOLINE_START; i < KDUMP_TRAMPOLINE_END; i += 8) { create_trampoline(i); @@ -52,7 +57,7 @@ void __init kdump_setup(void) create_trampoline(__pa(system_reset_fwnmi) - PHYSICAL_START); create_trampoline(__pa(machine_check_fwnmi) - PHYSICAL_START); - DBG(" <- kdump_setup()\n"); + DBG(" <- setup_kdump_trampoline()\n"); } #ifdef CONFIG_PROC_VMCORE diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 19ad5c6b1818..221062c960c9 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -57,6 +57,7 @@ system_call_common: beq- 1f ld r1,PACAKSAVE(r13) 1: std r10,0(r1) + crclr so std r11,_NIP(r1) std r12,_MSR(r1) std r0,GPR0(r1) @@ -75,7 +76,6 @@ system_call_common: std r11,GPR11(r1) std r11,GPR12(r1) std r9,GPR13(r1) - crclr so mfcr r9 mflr r10 li r11,0xc01 diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S index 340730fb8c91..01f71200c603 100644 --- a/arch/powerpc/kernel/fpu.S +++ b/arch/powerpc/kernel/fpu.S @@ -72,7 +72,7 @@ _GLOBAL(load_up_fpu) std r12,_MSR(r1) #endif lfd fr0,THREAD_FPSCR(r5) - mtfsf 0xff,fr0 + MTFSF_L(fr0) REST_32FPRS(0, r5) #ifndef CONFIG_SMP subi r4,r5,THREAD @@ -127,7 +127,7 @@ _GLOBAL(giveup_fpu) _GLOBAL(cvt_fd) lfd 0,THREAD_FPSCR(r5) /* load up fpscr value */ - mtfsf 0xff,0 + MTFSF_L(0) lfs 0,0(r3) stfd 0,0(r4) mffs 0 @@ -136,7 +136,7 @@ _GLOBAL(cvt_fd) _GLOBAL(cvt_df) lfd 0,THREAD_FPSCR(r5) /* load up fpscr value */ - mtfsf 0xff,0 + MTFSF_L(0) lfd 0,0(r3) stfs 0,0(r4) mffs 0 diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index a0579e859b21..b25b25902d15 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -973,6 +973,13 @@ __secondary_start_gemini: b __secondary_start #endif /* CONFIG_GEMINI */ + .globl __secondary_start_mpc86xx +__secondary_start_mpc86xx: + mfspr r3, SPRN_PIR + stw r3, __secondary_hold_acknowledge@l(0) + mr r24, r3 /* cpu # */ + b __secondary_start + .globl __secondary_start_pmac_0 __secondary_start_pmac_0: /* NB the entries for cpus 0, 1, 2 must each occupy 8 bytes. */ @@ -1088,7 +1095,12 @@ load_up_mmu: LOAD_BAT(1,r3,r4,r5) LOAD_BAT(2,r3,r4,r5) LOAD_BAT(3,r3,r4,r5) - +BEGIN_FTR_SECTION + LOAD_BAT(4,r3,r4,r5) + LOAD_BAT(5,r3,r4,r5) + LOAD_BAT(6,r3,r4,r5) + LOAD_BAT(7,r3,r4,r5) +END_FTR_SECTION_IFSET(CPU_FTR_HAS_HIGH_BATS) blr /* diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index b7d140430a41..831acbdf2592 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -316,6 +316,21 @@ label##_pSeries: \ mtspr SPRN_SPRG1,r13; /* save r13 */ \ EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common) +#define HSTD_EXCEPTION_PSERIES(n, label) \ + . = n; \ + .globl label##_pSeries; \ +label##_pSeries: \ + HMT_MEDIUM; \ + mtspr SPRN_SPRG1,r20; /* save r20 */ \ + mfspr r20,SPRN_HSRR0; /* copy HSRR0 to SRR0 */ \ + mtspr SPRN_SRR0,r20; \ + mfspr r20,SPRN_HSRR1; /* copy HSRR0 to SRR0 */ \ + mtspr SPRN_SRR1,r20; \ + mfspr r20,SPRN_SPRG1; /* restore r20 */ \ + mtspr SPRN_SPRG1,r13; /* save r13 */ \ + EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common) + + #define STD_EXCEPTION_ISERIES(n, label, area) \ .globl label##_iSeries; \ label##_iSeries: \ @@ -544,8 +559,17 @@ system_call_pSeries: STD_EXCEPTION_PSERIES(0xf20, altivec_unavailable) +#ifdef CONFIG_CBE_RAS + HSTD_EXCEPTION_PSERIES(0x1200, cbe_system_error) +#endif /* CONFIG_CBE_RAS */ STD_EXCEPTION_PSERIES(0x1300, instruction_breakpoint) +#ifdef CONFIG_CBE_RAS + HSTD_EXCEPTION_PSERIES(0x1600, cbe_maintenance) +#endif /* CONFIG_CBE_RAS */ STD_EXCEPTION_PSERIES(0x1700, altivec_assist) +#ifdef CONFIG_CBE_RAS + HSTD_EXCEPTION_PSERIES(0x1800, cbe_thermal) +#endif /* CONFIG_CBE_RAS */ . = 0x3000 @@ -827,6 +851,11 @@ machine_check_common: #else STD_EXCEPTION_COMMON(0x1700, altivec_assist, .unknown_exception) #endif +#ifdef CONFIG_CBE_RAS + STD_EXCEPTION_COMMON(0x1200, cbe_system_error, .cbe_system_error_exception) + STD_EXCEPTION_COMMON(0x1600, cbe_maintenance, .cbe_maintenance_exception) + STD_EXCEPTION_COMMON(0x1800, cbe_thermal, .cbe_thermal_exception) +#endif /* CONFIG_CBE_RAS */ /* * Here we have detected that the kernel stack pointer is bad. diff --git a/arch/powerpc/kernel/iomap.c b/arch/powerpc/kernel/iomap.c index fd8214caedee..a13a93dfc655 100644 --- a/arch/powerpc/kernel/iomap.c +++ b/arch/powerpc/kernel/iomap.c @@ -106,8 +106,6 @@ EXPORT_SYMBOL(iowrite32_rep); void __iomem *ioport_map(unsigned long port, unsigned int len) { - if (!_IO_IS_VALID(port)) - return NULL; return (void __iomem *) (port+pci_io_base); } diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 4eba60a32890..7cb77c20fc5d 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -418,10 +418,11 @@ void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist, * Build a iommu_table structure. This contains a bit map which * is used to manage allocation of the tce space. */ -struct iommu_table *iommu_init_table(struct iommu_table *tbl) +struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid) { unsigned long sz; static int welcomed = 0; + struct page *page; /* Set aside 1/4 of the table for large allocations. */ tbl->it_halfpoint = tbl->it_size * 3 / 4; @@ -429,10 +430,10 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl) /* number of bytes needed for the bitmap */ sz = (tbl->it_size + 7) >> 3; - tbl->it_map = (unsigned long *)__get_free_pages(GFP_ATOMIC, get_order(sz)); - if (!tbl->it_map) + page = alloc_pages_node(nid, GFP_ATOMIC, get_order(sz)); + if (!page) panic("iommu_init_table: Can't allocate %ld bytes\n", sz); - + tbl->it_map = page_address(page); memset(tbl->it_map, 0, sz); tbl->it_hint = 0; @@ -536,11 +537,12 @@ void iommu_unmap_single(struct iommu_table *tbl, dma_addr_t dma_handle, * to the dma address (mapping) of the first page. */ void *iommu_alloc_coherent(struct iommu_table *tbl, size_t size, - dma_addr_t *dma_handle, unsigned long mask, gfp_t flag) + dma_addr_t *dma_handle, unsigned long mask, gfp_t flag, int node) { void *ret = NULL; dma_addr_t mapping; unsigned int npages, order; + struct page *page; size = PAGE_ALIGN(size); npages = size >> PAGE_SHIFT; @@ -560,9 +562,10 @@ void *iommu_alloc_coherent(struct iommu_table *tbl, size_t size, return NULL; /* Alloc enough pages (and possibly more) */ - ret = (void *)__get_free_pages(flag, order); - if (!ret) + page = alloc_pages_node(node, flag, order); + if (!page) return NULL; + ret = page_address(page); memset(ret, 0, size); /* Set up tces to cover the allocated range */ @@ -570,9 +573,9 @@ void *iommu_alloc_coherent(struct iommu_table *tbl, size_t size, mask >> PAGE_SHIFT, order); if (mapping == DMA_ERROR_CODE) { free_pages((unsigned long)ret, order); - ret = NULL; - } else - *dma_handle = mapping; + return NULL; + } + *dma_handle = mapping; return ret; } diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 57d560c68897..40d4c14fde8f 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -47,6 +47,7 @@ #include <linux/cpumask.h> #include <linux/profile.h> #include <linux/bitops.h> +#include <linux/pci.h> #include <asm/uaccess.h> #include <asm/system.h> @@ -379,8 +380,8 @@ unsigned int real_irq_to_virt_slowpath(unsigned int real_irq) #endif /* CONFIG_PPC64 */ #ifdef CONFIG_IRQSTACKS -struct thread_info *softirq_ctx[NR_CPUS]; -struct thread_info *hardirq_ctx[NR_CPUS]; +struct thread_info *softirq_ctx[NR_CPUS] __read_mostly; +struct thread_info *hardirq_ctx[NR_CPUS] __read_mostly; void irq_ctx_init(void) { @@ -436,6 +437,30 @@ void do_softirq(void) } EXPORT_SYMBOL(do_softirq); +#ifdef CONFIG_PCI_MSI +int pci_enable_msi(struct pci_dev * pdev) +{ + if (ppc_md.enable_msi) + return ppc_md.enable_msi(pdev); + else + return -1; +} + +void pci_disable_msi(struct pci_dev * pdev) +{ + if (ppc_md.disable_msi) + ppc_md.disable_msi(pdev); +} + +void pci_scan_msi_device(struct pci_dev *dev) {} +int pci_enable_msix(struct pci_dev* dev, struct msix_entry *entries, int nvec) {return -1;} +void pci_disable_msix(struct pci_dev *dev) {} +void msi_remove_pci_irq_vectors(struct pci_dev *dev) {} +void disable_msi_mode(struct pci_dev *dev, int pos, int type) {} +void pci_no_msi(void) {} + +#endif + #ifdef CONFIG_PPC64 static int __init setup_noirqdistrib(char *str) { diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c index 2cbde865d4f5..c02deaab26c7 100644 --- a/arch/powerpc/kernel/lparcfg.c +++ b/arch/powerpc/kernel/lparcfg.c @@ -521,10 +521,10 @@ static ssize_t lparcfg_write(struct file *file, const char __user * buf, current_weight = (resource >> 5 * 8) & 0xFF; - pr_debug("%s: current_entitled = %lu, current_weight = %lu\n", + pr_debug("%s: current_entitled = %lu, current_weight = %u\n", __FUNCTION__, current_entitled, current_weight); - pr_debug("%s: new_entitled = %lu, new_weight = %lu\n", + pr_debug("%s: new_entitled = %lu, new_weight = %u\n", __FUNCTION__, *new_entitled_ptr, *new_weight_ptr); retval = plpar_hcall_norets(H_SET_PPP, *new_entitled_ptr, diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c index ee166c586642..a8fa04ef27cd 100644 --- a/arch/powerpc/kernel/machine_kexec_64.c +++ b/arch/powerpc/kernel/machine_kexec_64.c @@ -21,6 +21,7 @@ #include <asm/machdep.h> #include <asm/cacheflush.h> #include <asm/paca.h> +#include <asm/lmb.h> #include <asm/mmu.h> #include <asm/sections.h> /* _end */ #include <asm/prom.h> @@ -335,7 +336,105 @@ static void __init export_htab_values(void) of_node_put(node); } +static struct property crashk_base_prop = { + .name = "linux,crashkernel-base", + .length = sizeof(unsigned long), + .value = (unsigned char *)&crashk_res.start, +}; + +static unsigned long crashk_size; + +static struct property crashk_size_prop = { + .name = "linux,crashkernel-size", + .length = sizeof(unsigned long), + .value = (unsigned char *)&crashk_size, +}; + +static void __init export_crashk_values(void) +{ + struct device_node *node; + struct property *prop; + + node = of_find_node_by_path("/chosen"); + if (!node) + return; + + /* There might be existing crash kernel properties, but we can't + * be sure what's in them, so remove them. */ + prop = of_find_property(node, "linux,crashkernel-base", NULL); + if (prop) + prom_remove_property(node, prop); + + prop = of_find_property(node, "linux,crashkernel-size", NULL); + if (prop) + prom_remove_property(node, prop); + + if (crashk_res.start != 0) { + prom_add_property(node, &crashk_base_prop); + crashk_size = crashk_res.end - crashk_res.start + 1; + prom_add_property(node, &crashk_size_prop); + } + + of_node_put(node); +} + void __init kexec_setup(void) { export_htab_values(); + export_crashk_values(); +} + +static int __init early_parse_crashk(char *p) +{ + unsigned long size; + + if (!p) + return 1; + + size = memparse(p, &p); + + if (*p == '@') + crashk_res.start = memparse(p + 1, &p); + else + crashk_res.start = KDUMP_KERNELBASE; + + crashk_res.end = crashk_res.start + size - 1; + + return 0; +} +early_param("crashkernel", early_parse_crashk); + +void __init reserve_crashkernel(void) +{ + unsigned long size; + + if (crashk_res.start == 0) + return; + + /* We might have got these values via the command line or the + * device tree, either way sanitise them now. */ + + size = crashk_res.end - crashk_res.start + 1; + + if (crashk_res.start != KDUMP_KERNELBASE) + printk("Crash kernel location must be 0x%x\n", + KDUMP_KERNELBASE); + + crashk_res.start = KDUMP_KERNELBASE; + size = PAGE_ALIGN(size); + crashk_res.end = crashk_res.start + size - 1; + + /* Crash kernel trumps memory limit */ + if (memory_limit && memory_limit <= crashk_res.end) { + memory_limit = crashk_res.end + 1; + printk("Adjusted memory limit for crashkernel, now 0x%lx\n", + memory_limit); + } + + lmb_reserve(crashk_res.start, size); +} + +int overlaps_crashkernel(unsigned long start, unsigned long size) +{ + return (start + size) > crashk_res.start && start <= crashk_res.end; } diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index be982023409e..01d3916c4cb1 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -216,7 +216,7 @@ _GLOBAL(call_setup_cpu) lwz r4,0(r4) add r4,r4,r3 lwz r5,CPU_SPEC_SETUP(r4) - cmpi 0,r5,0 + cmpwi 0,r5,0 add r5,r5,r3 beqlr mtctr r5 diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index 2778cce058e2..e8883d42c43c 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -482,7 +482,9 @@ _GLOBAL(identify_cpu) sub r0,r3,r5 std r0,0(r4) ld r4,CPU_SPEC_SETUP(r3) + cmpdi 0,r4,0 add r4,r4,r5 + beqlr ld r4,0(r4) add r4,r4,r5 mtctr r4 @@ -768,9 +770,6 @@ _GLOBAL(giveup_altivec) #endif /* CONFIG_ALTIVEC */ -_GLOBAL(__setup_cpu_power3) - blr - _GLOBAL(execve) li r0,__NR_execve sc diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index ada50aa5b600..6960f090991e 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -204,7 +204,7 @@ static void nvram_print_partitions(char * label) printk(KERN_WARNING "indx\t\tsig\tchks\tlen\tname\n"); list_for_each(p, &nvram_part->partition) { tmp_part = list_entry(p, struct nvram_partition, partition); - printk(KERN_WARNING "%d \t%02x\t%02x\t%d\t%s\n", + printk(KERN_WARNING "%4d \t%02x\t%02x\t%d\t%s\n", tmp_part->index, tmp_part->header.signature, tmp_part->header.checksum, tmp_part->header.length, tmp_part->header.name); diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index b129d2e4b759..b5431ccf1147 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -1113,9 +1113,10 @@ check_for_io_childs(struct pci_bus *bus, struct resource* res, int *found_vga) int i; int rc = 0; -#define push_end(res, size) do { unsigned long __sz = (size) ; \ - res->end = ((res->end + __sz) / (__sz + 1)) * (__sz + 1) + __sz; \ - } while (0) +#define push_end(res, mask) do { \ + BUG_ON((mask+1) & mask); \ + res->end = (res->end + mask) | mask; \ +} while (0) list_for_each_entry(dev, &bus->devices, bus_list) { u16 class = dev->class >> 8; @@ -1653,7 +1654,6 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, return -EINVAL; vma->vm_pgoff = offset >> PAGE_SHIFT; - vma->vm_flags |= VM_SHM | VM_LOCKED | VM_IO; vma->vm_page_prot = __pci_mmap_set_pgprot(dev, rp, vma->vm_page_prot, mmap_state, write_combine); diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index 4c4449be81ce..247937dd8b73 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -42,14 +42,6 @@ unsigned long pci_probe_only = 1; int pci_assign_all_buses = 0; -/* - * legal IO pages under MAX_ISA_PORT. This is to ensure we don't touch - * devices we don't have access to. - */ -unsigned long io_page_mask; - -EXPORT_SYMBOL(io_page_mask); - #ifdef CONFIG_PPC_MULTIPLATFORM static void fixup_resource(struct resource *res, struct pci_dev *dev); static void do_bus_setup(struct pci_bus *bus); @@ -235,8 +227,10 @@ struct pci_controller * pcibios_alloc_controller(struct device_node *dev) pci_setup_pci_controller(phb); phb->arch_data = dev; phb->is_dynamic = mem_init_done; - if (dev) + if (dev) { + PHB_SET_NODE(phb, of_node_to_nid(dev)); add_linux_pci_domain(dev, phb); + } return phb; } @@ -396,7 +390,7 @@ struct pci_dev *of_create_pci_dev(struct device_node *node, dev->current_state = 4; /* unknown power state */ - if (!strcmp(type, "pci")) { + if (!strcmp(type, "pci") || !strcmp(type, "pciex")) { /* a PCI-PCI bridge */ dev->hdr_type = PCI_HEADER_TYPE_BRIDGE; dev->rom_base_reg = PCI_ROM_ADDRESS1; @@ -605,7 +599,7 @@ static int __init pcibios_init(void) iSeries_pcibios_init(); #endif - printk("PCI: Probing PCI hardware\n"); + printk(KERN_DEBUG "PCI: Probing PCI hardware\n"); /* Scan all of the recorded PCI controllers. */ list_for_each_entry_safe(hose, tmp, &hose_list, list_node) { @@ -630,14 +624,14 @@ static int __init pcibios_init(void) /* Cache the location of the ISA bridge (if we have one) */ ppc64_isabridge_dev = pci_get_class(PCI_CLASS_BRIDGE_ISA << 8, NULL); if (ppc64_isabridge_dev != NULL) - printk("ISA bridge at %s\n", pci_name(ppc64_isabridge_dev)); + printk(KERN_DEBUG "ISA bridge at %s\n", pci_name(ppc64_isabridge_dev)); #ifdef CONFIG_PPC_MULTIPLATFORM /* map in PCI I/O space */ phbs_remap_io(); #endif - printk("PCI: Probing PCI hardware done\n"); + printk(KERN_DEBUG "PCI: Probing PCI hardware done\n"); return 0; } @@ -804,7 +798,7 @@ static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp, else prot |= _PAGE_GUARDED; - printk("PCI map for %s:%lx, prot: %lx\n", pci_name(dev), rp->start, + printk(KERN_DEBUG "PCI map for %s:%lx, prot: %lx\n", pci_name(dev), rp->start, prot); return __pgprot(prot); @@ -883,7 +877,6 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, return -EINVAL; vma->vm_pgoff = offset >> PAGE_SHIFT; - vma->vm_flags |= VM_SHM | VM_LOCKED | VM_IO; vma->vm_page_prot = __pci_mmap_set_pgprot(dev, rp, vma->vm_page_prot, mmap_state, write_combine); @@ -894,8 +887,8 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, return ret; } -#ifdef CONFIG_PPC_MULTIPLATFORM -static ssize_t pci_show_devspec(struct device *dev, struct device_attribute *attr, char *buf) +static ssize_t pci_show_devspec(struct device *dev, + struct device_attribute *attr, char *buf) { struct pci_dev *pdev; struct device_node *np; @@ -907,13 +900,10 @@ static ssize_t pci_show_devspec(struct device *dev, struct device_attribute *att return sprintf(buf, "%s", np->full_name); } static DEVICE_ATTR(devspec, S_IRUGO, pci_show_devspec, NULL); -#endif /* CONFIG_PPC_MULTIPLATFORM */ void pcibios_add_platform_entries(struct pci_dev *pdev) { -#ifdef CONFIG_PPC_MULTIPLATFORM device_create_file(&pdev->dev, &dev_attr_devspec); -#endif /* CONFIG_PPC_MULTIPLATFORM */ } #ifdef CONFIG_PPC_MULTIPLATFORM @@ -1104,8 +1094,6 @@ void __init pci_setup_phb_io(struct pci_controller *hose, int primary) pci_process_ISA_OF_ranges(isa_dn, hose->io_base_phys, hose->io_base_virt); of_node_put(isa_dn); - /* Allow all IO */ - io_page_mask = -1; } } @@ -1212,7 +1200,7 @@ int remap_bus_range(struct pci_bus *bus) return 1; if (start_phys == 0) return 1; - printk("mapping IO %lx -> %lx, size: %lx\n", start_phys, start_virt, size); + printk(KERN_DEBUG "mapping IO %lx -> %lx, size: %lx\n", start_phys, start_virt, size); if (__ioremap_explicit(start_phys, start_virt, size, _PAGE_NO_CACHE | _PAGE_GUARDED)) return 1; @@ -1232,27 +1220,13 @@ static void phbs_remap_io(void) static void __devinit fixup_resource(struct resource *res, struct pci_dev *dev) { struct pci_controller *hose = pci_bus_to_host(dev->bus); - unsigned long start, end, mask, offset; + unsigned long offset; if (res->flags & IORESOURCE_IO) { offset = (unsigned long)hose->io_base_virt - pci_io_base; - start = res->start += offset; - end = res->end += offset; - - /* Need to allow IO access to pages that are in the - ISA range */ - if (start < MAX_ISA_PORT) { - if (end > MAX_ISA_PORT) - end = MAX_ISA_PORT; - - start >>= PAGE_SHIFT; - end >>= PAGE_SHIFT; - - /* get the range of pages for the map */ - mask = ((1 << (end+1)) - 1) ^ ((1 << start) - 1); - io_page_mask |= mask; - } + res->start += offset; + res->end += offset; } else if (res->flags & IORESOURCE_MEM) { res->start += hose->pci_mem_offset; res->end += hose->pci_mem_offset; @@ -1442,3 +1416,12 @@ long sys_pciconfig_iobase(long which, unsigned long in_bus, return -EOPNOTSUPP; } + +#ifdef CONFIG_NUMA +int pcibus_to_node(struct pci_bus *bus) +{ + struct pci_controller *phb = pci_bus_to_host(bus); + return phb->node; +} +EXPORT_SYMBOL(pcibus_to_node); +#endif diff --git a/arch/powerpc/kernel/pci_direct_iommu.c b/arch/powerpc/kernel/pci_direct_iommu.c index e1a32f802c0b..72ce082ce738 100644 --- a/arch/powerpc/kernel/pci_direct_iommu.c +++ b/arch/powerpc/kernel/pci_direct_iommu.c @@ -82,13 +82,17 @@ static int pci_direct_dma_supported(struct device *dev, u64 mask) return mask < 0x100000000ull; } +static struct dma_mapping_ops pci_direct_ops = { + .alloc_coherent = pci_direct_alloc_coherent, + .free_coherent = pci_direct_free_coherent, + .map_single = pci_direct_map_single, + .unmap_single = pci_direct_unmap_single, + .map_sg = pci_direct_map_sg, + .unmap_sg = pci_direct_unmap_sg, + .dma_supported = pci_direct_dma_supported, +}; + void __init pci_direct_iommu_init(void) { - pci_dma_ops.alloc_coherent = pci_direct_alloc_coherent; - pci_dma_ops.free_coherent = pci_direct_free_coherent; - pci_dma_ops.map_single = pci_direct_map_single; - pci_dma_ops.unmap_single = pci_direct_unmap_single; - pci_dma_ops.map_sg = pci_direct_map_sg; - pci_dma_ops.unmap_sg = pci_direct_unmap_sg; - pci_dma_ops.dma_supported = pci_direct_dma_supported; + pci_dma_ops = pci_direct_ops; } diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c index 12c4c9e9bbc7..1c18953514c3 100644 --- a/arch/powerpc/kernel/pci_dn.c +++ b/arch/powerpc/kernel/pci_dn.c @@ -31,6 +31,7 @@ #include <asm/pci-bridge.h> #include <asm/pSeries_reconfig.h> #include <asm/ppc-pci.h> +#include <asm/firmware.h> /* * Traverse_func that inits the PCI fields of the device node. @@ -59,6 +60,11 @@ static void * __devinit update_dn_pci_info(struct device_node *dn, void *data) pdn->busno = (regs[0] >> 16) & 0xff; pdn->devfn = (regs[0] >> 8) & 0xff; } + if (firmware_has_feature(FW_FEATURE_ISERIES)) { + u32 *busp = (u32 *)get_property(dn, "linux,subbus", NULL); + if (busp) + pdn->bussubno = *busp; + } pdn->pci_ext_config_space = (type && *type == 1); return NULL; diff --git a/arch/powerpc/kernel/pci_iommu.c b/arch/powerpc/kernel/pci_iommu.c index c1d95e14bbed..0688b2534acb 100644 --- a/arch/powerpc/kernel/pci_iommu.c +++ b/arch/powerpc/kernel/pci_iommu.c @@ -44,16 +44,16 @@ */ #define PCI_GET_DN(dev) ((struct device_node *)((dev)->sysdata)) -static inline struct iommu_table *devnode_table(struct device *dev) +static inline struct iommu_table *device_to_table(struct device *hwdev) { struct pci_dev *pdev; - if (!dev) { + if (!hwdev) { pdev = ppc64_isabridge_dev; if (!pdev) return NULL; } else - pdev = to_pci_dev(dev); + pdev = to_pci_dev(hwdev); return PCI_DN(PCI_GET_DN(pdev))->iommu_table; } @@ -85,14 +85,15 @@ static inline unsigned long device_to_mask(struct device *hwdev) static void *pci_iommu_alloc_coherent(struct device *hwdev, size_t size, dma_addr_t *dma_handle, gfp_t flag) { - return iommu_alloc_coherent(devnode_table(hwdev), size, dma_handle, - device_to_mask(hwdev), flag); + return iommu_alloc_coherent(device_to_table(hwdev), size, dma_handle, + device_to_mask(hwdev), flag, + pcibus_to_node(to_pci_dev(hwdev)->bus)); } static void pci_iommu_free_coherent(struct device *hwdev, size_t size, void *vaddr, dma_addr_t dma_handle) { - iommu_free_coherent(devnode_table(hwdev), size, vaddr, dma_handle); + iommu_free_coherent(device_to_table(hwdev), size, vaddr, dma_handle); } /* Creates TCEs for a user provided buffer. The user buffer must be @@ -104,7 +105,7 @@ static void pci_iommu_free_coherent(struct device *hwdev, size_t size, static dma_addr_t pci_iommu_map_single(struct device *hwdev, void *vaddr, size_t size, enum dma_data_direction direction) { - return iommu_map_single(devnode_table(hwdev), vaddr, size, + return iommu_map_single(device_to_table(hwdev), vaddr, size, device_to_mask(hwdev), direction); } @@ -112,27 +113,27 @@ static dma_addr_t pci_iommu_map_single(struct device *hwdev, void *vaddr, static void pci_iommu_unmap_single(struct device *hwdev, dma_addr_t dma_handle, size_t size, enum dma_data_direction direction) { - iommu_unmap_single(devnode_table(hwdev), dma_handle, size, direction); + iommu_unmap_single(device_to_table(hwdev), dma_handle, size, direction); } static int pci_iommu_map_sg(struct device *pdev, struct scatterlist *sglist, int nelems, enum dma_data_direction direction) { - return iommu_map_sg(pdev, devnode_table(pdev), sglist, + return iommu_map_sg(pdev, device_to_table(pdev), sglist, nelems, device_to_mask(pdev), direction); } static void pci_iommu_unmap_sg(struct device *pdev, struct scatterlist *sglist, int nelems, enum dma_data_direction direction) { - iommu_unmap_sg(devnode_table(pdev), sglist, nelems, direction); + iommu_unmap_sg(device_to_table(pdev), sglist, nelems, direction); } /* We support DMA to/from any memory page via the iommu */ static int pci_iommu_dma_supported(struct device *dev, u64 mask) { - struct iommu_table *tbl = devnode_table(dev); + struct iommu_table *tbl = device_to_table(dev); if (!tbl || tbl->it_offset > mask) { printk(KERN_INFO "Warning: IOMMU table offset too big for device mask\n"); @@ -147,13 +148,17 @@ static int pci_iommu_dma_supported(struct device *dev, u64 mask) return 1; } +struct dma_mapping_ops pci_iommu_ops = { + .alloc_coherent = pci_iommu_alloc_coherent, + .free_coherent = pci_iommu_free_coherent, + .map_single = pci_iommu_map_single, + .unmap_single = pci_iommu_unmap_single, + .map_sg = pci_iommu_map_sg, + .unmap_sg = pci_iommu_unmap_sg, + .dma_supported = pci_iommu_dma_supported, +}; + void pci_iommu_init(void) { - pci_dma_ops.alloc_coherent = pci_iommu_alloc_coherent; - pci_dma_ops.free_coherent = pci_iommu_free_coherent; - pci_dma_ops.map_single = pci_iommu_map_single; - pci_dma_ops.unmap_single = pci_iommu_unmap_single; - pci_dma_ops.map_sg = pci_iommu_map_sg; - pci_dma_ops.unmap_sg = pci_iommu_unmap_sg; - pci_dma_ops.dma_supported = pci_iommu_dma_supported; + pci_dma_ops = pci_iommu_ops; } diff --git a/arch/powerpc/kernel/proc_ppc64.c b/arch/powerpc/kernel/proc_ppc64.c index 3c2cf661f6d9..2ab8f2be911e 100644 --- a/arch/powerpc/kernel/proc_ppc64.c +++ b/arch/powerpc/kernel/proc_ppc64.c @@ -52,7 +52,7 @@ static int __init proc_ppc64_create(void) if (!root) return 1; - if (!machine_is(pseries) && !machine_is(cell)) + if (!of_find_node_by_path("/rtas")) return 0; if (!proc_mkdir("rtas", root)) @@ -115,8 +115,6 @@ static int page_map_mmap( struct file *file, struct vm_area_struct *vma ) { struct proc_dir_entry *dp = PDE(file->f_dentry->d_inode); - vma->vm_flags |= VM_SHM | VM_LOCKED; - if ((vma->vm_end - vma->vm_start) > dp->size) return -EINVAL; diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 2dd47d2dd998..e4732459c485 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -708,6 +708,61 @@ int get_fpexc_mode(struct task_struct *tsk, unsigned long adr) return put_user(val, (unsigned int __user *) adr); } +int set_endian(struct task_struct *tsk, unsigned int val) +{ + struct pt_regs *regs = tsk->thread.regs; + + if ((val == PR_ENDIAN_LITTLE && !cpu_has_feature(CPU_FTR_REAL_LE)) || + (val == PR_ENDIAN_PPC_LITTLE && !cpu_has_feature(CPU_FTR_PPC_LE))) + return -EINVAL; + + if (regs == NULL) + return -EINVAL; + + if (val == PR_ENDIAN_BIG) + regs->msr &= ~MSR_LE; + else if (val == PR_ENDIAN_LITTLE || val == PR_ENDIAN_PPC_LITTLE) + regs->msr |= MSR_LE; + else + return -EINVAL; + + return 0; +} + +int get_endian(struct task_struct *tsk, unsigned long adr) +{ + struct pt_regs *regs = tsk->thread.regs; + unsigned int val; + + if (!cpu_has_feature(CPU_FTR_PPC_LE) && + !cpu_has_feature(CPU_FTR_REAL_LE)) + return -EINVAL; + + if (regs == NULL) + return -EINVAL; + + if (regs->msr & MSR_LE) { + if (cpu_has_feature(CPU_FTR_REAL_LE)) + val = PR_ENDIAN_LITTLE; + else + val = PR_ENDIAN_PPC_LITTLE; + } else + val = PR_ENDIAN_BIG; + + return put_user(val, (unsigned int __user *)adr); +} + +int set_unalign_ctl(struct task_struct *tsk, unsigned int val) +{ + tsk->thread.align_ctl = val; + return 0; +} + +int get_unalign_ctl(struct task_struct *tsk, unsigned long adr) +{ + return put_user(tsk->thread.align_ctl, (unsigned int __user *)adr); +} + #define TRUNC_PTR(x) ((typeof(x))(((unsigned long)(x)) & 0xffffffff)) int sys_clone(unsigned long clone_flags, unsigned long usp, diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 9a07f97f0712..483455c5bb02 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -50,6 +50,7 @@ #include <asm/machdep.h> #include <asm/pSeries_reconfig.h> #include <asm/pci-bridge.h> +#include <asm/kexec.h> #ifdef DEBUG #define DBG(fmt...) printk(KERN_ERR fmt) @@ -836,6 +837,42 @@ static unsigned long __init unflatten_dt_node(unsigned long mem, return mem; } +static int __init early_parse_mem(char *p) +{ + if (!p) + return 1; + + memory_limit = PAGE_ALIGN(memparse(p, &p)); + DBG("memory limit = 0x%lx\n", memory_limit); + + return 0; +} +early_param("mem", early_parse_mem); + +/* + * The device tree may be allocated below our memory limit, or inside the + * crash kernel region for kdump. If so, move it out now. + */ +static void move_device_tree(void) +{ + unsigned long start, size; + void *p; + + DBG("-> move_device_tree\n"); + + start = __pa(initial_boot_params); + size = initial_boot_params->totalsize; + + if ((memory_limit && (start + size) > memory_limit) || + overlaps_crashkernel(start, size)) { + p = __va(lmb_alloc_base(size, PAGE_SIZE, lmb.rmo_size)); + memcpy(p, initial_boot_params, size); + initial_boot_params = (struct boot_param_header *)p; + DBG("Moved device tree to 0x%p\n", p); + } + + DBG("<- move_device_tree\n"); +} /** * unflattens the device-tree passed by the firmware, creating the @@ -911,7 +948,10 @@ static struct ibm_pa_feature { {CPU_FTR_CTRL, 0, 0, 3, 0}, {CPU_FTR_NOEXECUTE, 0, 0, 6, 0}, {CPU_FTR_NODSISRALIGN, 0, 1, 1, 1}, +#if 0 + /* put this back once we know how to test if firmware does 64k IO */ {CPU_FTR_CI_LARGE_PAGE, 0, 1, 2, 0}, +#endif }; static void __init check_cpu_pa_features(unsigned long node) @@ -1070,6 +1110,7 @@ static int __init early_init_dt_scan_chosen(unsigned long node, iommu_force_on = 1; #endif + /* mem=x on the command line is the preferred mechanism */ lprop = of_get_flat_dt_prop(node, "linux,memory-limit", NULL); if (lprop) memory_limit = *lprop; @@ -1123,17 +1164,6 @@ static int __init early_init_dt_scan_chosen(unsigned long node, DBG("Command line is: %s\n", cmd_line); - if (strstr(cmd_line, "mem=")) { - char *p, *q; - - for (q = cmd_line; (p = strstr(q, "mem=")) != 0; ) { - q = p + 4; - if (p > cmd_line && p[-1] != ' ') - continue; - memory_limit = memparse(q, &q); - } - } - /* break now */ return 1; } @@ -1237,9 +1267,17 @@ static void __init early_reserve_mem(void) { u64 base, size; u64 *reserve_map; + unsigned long self_base; + unsigned long self_size; reserve_map = (u64 *)(((unsigned long)initial_boot_params) + initial_boot_params->off_mem_rsvmap); + + /* before we do anything, lets reserve the dt blob */ + self_base = __pa((unsigned long)initial_boot_params); + self_size = initial_boot_params->totalsize; + lmb_reserve(self_base, self_size); + #ifdef CONFIG_PPC32 /* * Handle the case where we might be booting from an old kexec @@ -1254,6 +1292,9 @@ static void __init early_reserve_mem(void) size_32 = *(reserve_map_32++); if (size_32 == 0) break; + /* skip if the reservation is for the blob */ + if (base_32 == self_base && size_32 == self_size) + continue; DBG("reserving: %x -> %x\n", base_32, size_32); lmb_reserve(base_32, size_32); } @@ -1265,6 +1306,9 @@ static void __init early_reserve_mem(void) size = *(reserve_map++); if (size == 0) break; + /* skip if the reservation is for the blob */ + if (base == self_base && size == self_size) + continue; DBG("reserving: %llx -> %llx\n", base, size); lmb_reserve(base, size); } @@ -1292,18 +1336,26 @@ void __init early_init_devtree(void *params) lmb_init(); of_scan_flat_dt(early_init_dt_scan_root, NULL); of_scan_flat_dt(early_init_dt_scan_memory, NULL); - lmb_enforce_memory_limit(memory_limit); - lmb_analyze(); - DBG("Phys. mem: %lx\n", lmb_phys_mem_size()); + /* Save command line for /proc/cmdline and then parse parameters */ + strlcpy(saved_command_line, cmd_line, COMMAND_LINE_SIZE); + parse_early_param(); /* Reserve LMB regions used by kernel, initrd, dt, etc... */ lmb_reserve(PHYSICAL_START, __pa(klimit) - PHYSICAL_START); -#ifdef CONFIG_CRASH_DUMP - lmb_reserve(0, KDUMP_RESERVE_LIMIT); -#endif + reserve_kdump_trampoline(); + reserve_crashkernel(); early_reserve_mem(); + lmb_enforce_memory_limit(memory_limit); + lmb_analyze(); + + DBG("Phys. mem: %lx\n", lmb_phys_mem_size()); + + /* We may need to relocate the flat tree, do it now. + * FIXME .. and the initrd too? */ + move_device_tree(); + DBG("Scanning CPUs ...\n"); /* Retreive CPU related informations from the flat tree @@ -2053,29 +2105,46 @@ int prom_update_property(struct device_node *np, return 0; } -#ifdef CONFIG_KEXEC -/* We may have allocated the flat device tree inside the crash kernel region - * in prom_init. If so we need to move it out into regular memory. */ -void kdump_move_device_tree(void) -{ - unsigned long start, end; - struct boot_param_header *new; - - start = __pa((unsigned long)initial_boot_params); - end = start + initial_boot_params->totalsize; - - if (end < crashk_res.start || start > crashk_res.end) - return; - new = (struct boot_param_header*) - __va(lmb_alloc(initial_boot_params->totalsize, PAGE_SIZE)); - - memcpy(new, initial_boot_params, initial_boot_params->totalsize); +/* Find the device node for a given logical cpu number, also returns the cpu + * local thread number (index in ibm,interrupt-server#s) if relevant and + * asked for (non NULL) + */ +struct device_node *of_get_cpu_node(int cpu, unsigned int *thread) +{ + int hardid; + struct device_node *np; - initial_boot_params = new; + hardid = get_hard_smp_processor_id(cpu); - DBG("Flat device tree blob moved to %p\n", initial_boot_params); + for_each_node_by_type(np, "cpu") { + u32 *intserv; + unsigned int plen, t; - /* XXX should we unreserve the old DT? */ + /* Check for ibm,ppc-interrupt-server#s. If it doesn't exist + * fallback to "reg" property and assume no threads + */ + intserv = (u32 *)get_property(np, "ibm,ppc-interrupt-server#s", + &plen); + if (intserv == NULL) { + u32 *reg = (u32 *)get_property(np, "reg", NULL); + if (reg == NULL) + continue; + if (*reg == hardid) { + if (thread) + *thread = 0; + return np; + } + } else { + plen /= sizeof(u32); + for (t = 0; t < plen; t++) { + if (hardid == intserv[t]) { + if (thread) + *thread = t; + return np; + } + } + } + } + return NULL; } -#endif /* CONFIG_KEXEC */ diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 41e9ab40cd54..8c28eb0cbdac 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -194,19 +194,12 @@ static int __initdata of_platform; static char __initdata prom_cmd_line[COMMAND_LINE_SIZE]; -static unsigned long __initdata prom_memory_limit; - static unsigned long __initdata alloc_top; static unsigned long __initdata alloc_top_high; static unsigned long __initdata alloc_bottom; static unsigned long __initdata rmo_top; static unsigned long __initdata ram_top; -#ifdef CONFIG_KEXEC -static unsigned long __initdata prom_crashk_base; -static unsigned long __initdata prom_crashk_size; -#endif - static struct mem_map_entry __initdata mem_reserve_map[MEM_RESERVE_MAP_SIZE]; static int __initdata mem_reserve_cnt; @@ -574,7 +567,7 @@ static void __init early_cmdline_parse(void) if ((long)_prom->chosen > 0) l = prom_getprop(_prom->chosen, "bootargs", p, COMMAND_LINE_SIZE-1); #ifdef CONFIG_CMDLINE - if (l == 0) /* dbl check */ + if (l <= 0 || p[0] == '\0') /* dbl check */ strlcpy(RELOC(prom_cmd_line), RELOC(CONFIG_CMDLINE), sizeof(prom_cmd_line)); #endif /* CONFIG_CMDLINE */ @@ -593,45 +586,6 @@ static void __init early_cmdline_parse(void) RELOC(iommu_force_on) = 1; } #endif - - opt = strstr(RELOC(prom_cmd_line), RELOC("mem=")); - if (opt) { - opt += 4; - RELOC(prom_memory_limit) = prom_memparse(opt, (const char **)&opt); -#ifdef CONFIG_PPC64 - /* Align to 16 MB == size of ppc64 large page */ - RELOC(prom_memory_limit) = ALIGN(RELOC(prom_memory_limit), 0x1000000); -#endif - } - -#ifdef CONFIG_KEXEC - /* - * crashkernel=size@addr specifies the location to reserve for - * crash kernel. - */ - opt = strstr(RELOC(prom_cmd_line), RELOC("crashkernel=")); - if (opt) { - opt += 12; - RELOC(prom_crashk_size) = - prom_memparse(opt, (const char **)&opt); - - if (ALIGN(RELOC(prom_crashk_size), 0x1000000) != - RELOC(prom_crashk_size)) { - prom_printf("Warning: crashkernel size is not " - "aligned to 16MB\n"); - } - - /* - * At present, the crash kernel always run at 32MB. - * Just ignore whatever user passed. - */ - RELOC(prom_crashk_base) = 0x2000000; - if (*opt == '@') { - prom_printf("Warning: PPC64 kdump kernel always runs " - "at 32 MB\n"); - } - } -#endif } #ifdef CONFIG_PPC_PSERIES @@ -822,6 +776,7 @@ static void __init prom_send_capabilities(void) /* try calling the ibm,client-architecture-support method */ if (call_prom_ret("call-method", 3, 2, &ret, ADDR("ibm,client-architecture-support"), + root, ADDR(ibm_architecture_vec)) == 0) { /* the call exists... */ if (ret) @@ -1115,29 +1070,6 @@ static void __init prom_init_mem(void) } /* - * If prom_memory_limit is set we reduce the upper limits *except* for - * alloc_top_high. This must be the real top of RAM so we can put - * TCE's up there. - */ - - RELOC(alloc_top_high) = RELOC(ram_top); - - if (RELOC(prom_memory_limit)) { - if (RELOC(prom_memory_limit) <= RELOC(alloc_bottom)) { - prom_printf("Ignoring mem=%x <= alloc_bottom.\n", - RELOC(prom_memory_limit)); - RELOC(prom_memory_limit) = 0; - } else if (RELOC(prom_memory_limit) >= RELOC(ram_top)) { - prom_printf("Ignoring mem=%x >= ram_top.\n", - RELOC(prom_memory_limit)); - RELOC(prom_memory_limit) = 0; - } else { - RELOC(ram_top) = RELOC(prom_memory_limit); - RELOC(rmo_top) = min(RELOC(rmo_top), RELOC(prom_memory_limit)); - } - } - - /* * Setup our top alloc point, that is top of RMO or top of * segment 0 when running non-LPAR. * Some RS64 machines have buggy firmware where claims up at @@ -1149,20 +1081,14 @@ static void __init prom_init_mem(void) RELOC(rmo_top) = RELOC(ram_top); RELOC(rmo_top) = min(0x30000000ul, RELOC(rmo_top)); RELOC(alloc_top) = RELOC(rmo_top); + RELOC(alloc_top_high) = RELOC(ram_top); prom_printf("memory layout at init:\n"); - prom_printf(" memory_limit : %x (16 MB aligned)\n", RELOC(prom_memory_limit)); prom_printf(" alloc_bottom : %x\n", RELOC(alloc_bottom)); prom_printf(" alloc_top : %x\n", RELOC(alloc_top)); prom_printf(" alloc_top_hi : %x\n", RELOC(alloc_top_high)); prom_printf(" rmo_top : %x\n", RELOC(rmo_top)); prom_printf(" ram_top : %x\n", RELOC(ram_top)); -#ifdef CONFIG_KEXEC - if (RELOC(prom_crashk_base)) { - prom_printf(" crashk_base : %x\n", RELOC(prom_crashk_base)); - prom_printf(" crashk_size : %x\n", RELOC(prom_crashk_size)); - } -#endif } @@ -1348,16 +1274,10 @@ static void __init prom_initialize_tce_table(void) reserve_mem(local_alloc_bottom, local_alloc_top - local_alloc_bottom); - if (RELOC(prom_memory_limit)) { - /* - * We align the start to a 16MB boundary so we can map - * the TCE area using large pages if possible. - * The end should be the top of RAM so no need to align it. - */ - RELOC(prom_tce_alloc_start) = _ALIGN_DOWN(local_alloc_bottom, - 0x1000000); - RELOC(prom_tce_alloc_end) = local_alloc_top; - } + /* These are only really needed if there is a memory limit in + * effect, but we don't know so export them always. */ + RELOC(prom_tce_alloc_start) = local_alloc_bottom; + RELOC(prom_tce_alloc_end) = local_alloc_top; /* Flag the first invalid entry */ prom_debug("ending prom_initialize_tce_table\n"); @@ -1622,6 +1542,15 @@ static int __init prom_find_machine_type(void) if (strstr(p, RELOC("Power Macintosh")) || strstr(p, RELOC("MacRISC"))) return PLATFORM_POWERMAC; +#ifdef CONFIG_PPC64 + /* We must make sure we don't detect the IBM Cell + * blades as pSeries due to some firmware issues, + * so we do it here. + */ + if (strstr(p, RELOC("IBM,CBEA")) || + strstr(p, RELOC("IBM,CPBW-1.0"))) + return PLATFORM_GENERIC; +#endif /* CONFIG_PPC64 */ i += sl + 1; } } @@ -2031,11 +1960,7 @@ static void __init flatten_device_tree(void) /* Version 16 is not backward compatible */ hdr->last_comp_version = 0x10; - /* Reserve the whole thing and copy the reserve map in, we - * also bump mem_reserve_cnt to cause further reservations to - * fail since it's too late. - */ - reserve_mem(RELOC(dt_header_start), hdr->totalsize); + /* Copy the reserve map in */ memcpy(rsvmap, RELOC(mem_reserve_map), sizeof(mem_reserve_map)); #ifdef DEBUG_PROM @@ -2048,6 +1973,9 @@ static void __init flatten_device_tree(void) RELOC(mem_reserve_map)[i].size); } #endif + /* Bump mem_reserve_cnt to cause further reservations to fail + * since it's too late. + */ RELOC(mem_reserve_cnt) = MEM_RESERVE_MAP_SIZE; prom_printf("Device tree strings 0x%x -> 0x%x\n", @@ -2270,10 +2198,6 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, */ prom_init_mem(); -#ifdef CONFIG_KEXEC - if (RELOC(prom_crashk_base)) - reserve_mem(RELOC(prom_crashk_base), RELOC(prom_crashk_size)); -#endif /* * Determine which cpu is actually running right _now_ */ @@ -2307,10 +2231,6 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, /* * Fill in some infos for use by the kernel later on */ - if (RELOC(prom_memory_limit)) - prom_setprop(_prom->chosen, "/chosen", "linux,memory-limit", - &RELOC(prom_memory_limit), - sizeof(prom_memory_limit)); #ifdef CONFIG_PPC64 if (RELOC(ppc64_iommu_off)) prom_setprop(_prom->chosen, "/chosen", "linux,iommu-off", @@ -2330,16 +2250,6 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, } #endif -#ifdef CONFIG_KEXEC - if (RELOC(prom_crashk_base)) { - prom_setprop(_prom->chosen, "/chosen", "linux,crashkernel-base", - PTRRELOC(&prom_crashk_base), - sizeof(RELOC(prom_crashk_base))); - prom_setprop(_prom->chosen, "/chosen", "linux,crashkernel-size", - PTRRELOC(&prom_crashk_size), - sizeof(RELOC(prom_crashk_size))); - } -#endif /* * Fixup any known bugs in the device-tree */ diff --git a/arch/powerpc/kernel/prom_parse.c b/arch/powerpc/kernel/prom_parse.c index 3934c227549b..45df420383cc 100644 --- a/arch/powerpc/kernel/prom_parse.c +++ b/arch/powerpc/kernel/prom_parse.c @@ -548,3 +548,28 @@ int of_pci_address_to_resource(struct device_node *dev, int bar, return __of_address_to_resource(dev, addrp, size, flags, r); } EXPORT_SYMBOL_GPL(of_pci_address_to_resource); + +void of_parse_dma_window(struct device_node *dn, unsigned char *dma_window_prop, + unsigned long *busno, unsigned long *phys, unsigned long *size) +{ + u32 *dma_window, cells; + unsigned char *prop; + + dma_window = (u32 *)dma_window_prop; + + /* busno is always one cell */ + *busno = *(dma_window++); + + prop = get_property(dn, "ibm,#dma-address-cells", NULL); + if (!prop) + prop = get_property(dn, "#address-cells", NULL); + + cells = prop ? *(u32 *)prop : prom_n_addr_cells(dn); + *phys = of_read_addr(dma_window, cells); + + dma_window += cells; + + prop = get_property(dn, "ibm,#dma-size-cells", NULL); + cells = prop ? *(u32 *)prop : prom_n_size_cells(dn); + *size = of_read_addr(dma_window, cells); +} diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 4a677d1bd4ef..5563e2e7d89c 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -404,7 +404,6 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) ret = ptrace_detach(child, data); break; -#ifdef CONFIG_PPC64 case PPC_PTRACE_GETREGS: { /* Get GPRs 0 - 31. */ int i; unsigned long *reg = &((unsigned long *)child->thread.regs)[0]; @@ -468,7 +467,6 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) } break; } -#endif /* CONFIG_PPC64 */ #ifdef CONFIG_ALTIVEC case PTRACE_GETVRREGS: diff --git a/arch/powerpc/kernel/rtas-rtc.c b/arch/powerpc/kernel/rtas-rtc.c index 34d073fb6091..77578c093dda 100644 --- a/arch/powerpc/kernel/rtas-rtc.c +++ b/arch/powerpc/kernel/rtas-rtc.c @@ -14,19 +14,20 @@ unsigned long __init rtas_get_boot_time(void) { int ret[8]; - int error, wait_time; + int error; + unsigned int wait_time; u64 max_wait_tb; max_wait_tb = get_tb() + tb_ticks_per_usec * 1000 * MAX_RTC_WAIT; do { error = rtas_call(rtas_token("get-time-of-day"), 0, 8, ret); - if (error == RTAS_CLOCK_BUSY || rtas_is_extended_busy(error)) { - wait_time = rtas_extended_busy_delay_time(error); + + wait_time = rtas_busy_delay_time(error); + if (wait_time) { /* This is boot time so we spin. */ udelay(wait_time*1000); - error = RTAS_CLOCK_BUSY; } - } while (error == RTAS_CLOCK_BUSY && (get_tb() < max_wait_tb)); + } while (wait_time && (get_tb() < max_wait_tb)); if (error != 0 && printk_ratelimit()) { printk(KERN_WARNING "error: reading the clock failed (%d)\n", @@ -44,24 +45,25 @@ unsigned long __init rtas_get_boot_time(void) void rtas_get_rtc_time(struct rtc_time *rtc_tm) { int ret[8]; - int error, wait_time; + int error; + unsigned int wait_time; u64 max_wait_tb; max_wait_tb = get_tb() + tb_ticks_per_usec * 1000 * MAX_RTC_WAIT; do { error = rtas_call(rtas_token("get-time-of-day"), 0, 8, ret); - if (error == RTAS_CLOCK_BUSY || rtas_is_extended_busy(error)) { + + wait_time = rtas_busy_delay_time(error); + if (wait_time) { if (in_interrupt() && printk_ratelimit()) { memset(rtc_tm, 0, sizeof(struct rtc_time)); printk(KERN_WARNING "error: reading clock" " would delay interrupt\n"); return; /* delay not allowed */ } - wait_time = rtas_extended_busy_delay_time(error); msleep(wait_time); - error = RTAS_CLOCK_BUSY; } - } while (error == RTAS_CLOCK_BUSY && (get_tb() < max_wait_tb)); + } while (wait_time && (get_tb() < max_wait_tb)); if (error != 0 && printk_ratelimit()) { printk(KERN_WARNING "error: reading the clock failed (%d)\n", @@ -88,14 +90,14 @@ int rtas_set_rtc_time(struct rtc_time *tm) tm->tm_year + 1900, tm->tm_mon + 1, tm->tm_mday, tm->tm_hour, tm->tm_min, tm->tm_sec, 0); - if (error == RTAS_CLOCK_BUSY || rtas_is_extended_busy(error)) { + + wait_time = rtas_busy_delay_time(error); + if (wait_time) { if (in_interrupt()) return 1; /* probably decrementer */ - wait_time = rtas_extended_busy_delay_time(error); msleep(wait_time); - error = RTAS_CLOCK_BUSY; } - } while (error == RTAS_CLOCK_BUSY && (get_tb() < max_wait_tb)); + } while (wait_time && (get_tb() < max_wait_tb)); if (error != 0 && printk_ratelimit()) printk(KERN_WARNING "error: setting the clock failed (%d)\n", diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 0112318213ab..17dc79198515 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -370,24 +370,36 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...) return ret; } -/* Given an RTAS status code of 990n compute the hinted delay of 10^n - * (last digit) milliseconds. For now we bound at n=5 (100 sec). +/* For RTAS_BUSY (-2), delay for 1 millisecond. For an extended busy status + * code of 990n, perform the hinted delay of 10^n (last digit) milliseconds. */ -unsigned int rtas_extended_busy_delay_time(int status) +unsigned int rtas_busy_delay_time(int status) { - int order = status - 9900; - unsigned long ms; + int order; + unsigned int ms = 0; + + if (status == RTAS_BUSY) { + ms = 1; + } else if (status >= 9900 && status <= 9905) { + order = status - 9900; + for (ms = 1; order > 0; order--) + ms *= 10; + } - if (order < 0) - order = 0; /* RTC depends on this for -2 clock busy */ - else if (order > 5) - order = 5; /* bound */ + return ms; +} - /* Use microseconds for reasonable accuracy */ - for (ms = 1; order > 0; order--) - ms *= 10; +/* For an RTAS busy status code, perform the hinted delay. */ +unsigned int rtas_busy_delay(int status) +{ + unsigned int ms; - return ms; + might_sleep(); + ms = rtas_busy_delay_time(status); + if (ms) + msleep(ms); + + return ms; } int rtas_error_rc(int rtas_rc) @@ -438,22 +450,14 @@ int rtas_get_power_level(int powerdomain, int *level) int rtas_set_power_level(int powerdomain, int level, int *setlevel) { int token = rtas_token("set-power-level"); - unsigned int wait_time; int rc; if (token == RTAS_UNKNOWN_SERVICE) return -ENOENT; - while (1) { + do { rc = rtas_call(token, 2, 2, setlevel, powerdomain, level); - if (rc == RTAS_BUSY) - udelay(1); - else if (rtas_is_extended_busy(rc)) { - wait_time = rtas_extended_busy_delay_time(rc); - udelay(wait_time * 1000); - } else - break; - } + } while (rtas_busy_delay(rc)); if (rc < 0) return rtas_error_rc(rc); @@ -463,22 +467,14 @@ int rtas_set_power_level(int powerdomain, int level, int *setlevel) int rtas_get_sensor(int sensor, int index, int *state) { int token = rtas_token("get-sensor-state"); - unsigned int wait_time; int rc; if (token == RTAS_UNKNOWN_SERVICE) return -ENOENT; - while (1) { + do { rc = rtas_call(token, 2, 2, state, sensor, index); - if (rc == RTAS_BUSY) - udelay(1); - else if (rtas_is_extended_busy(rc)) { - wait_time = rtas_extended_busy_delay_time(rc); - udelay(wait_time * 1000); - } else - break; - } + } while (rtas_busy_delay(rc)); if (rc < 0) return rtas_error_rc(rc); @@ -488,23 +484,14 @@ int rtas_get_sensor(int sensor, int index, int *state) int rtas_set_indicator(int indicator, int index, int new_value) { int token = rtas_token("set-indicator"); - unsigned int wait_time; int rc; if (token == RTAS_UNKNOWN_SERVICE) return -ENOENT; - while (1) { + do { rc = rtas_call(token, 3, 1, NULL, indicator, index, new_value); - if (rc == RTAS_BUSY) - udelay(1); - else if (rtas_is_extended_busy(rc)) { - wait_time = rtas_extended_busy_delay_time(rc); - udelay(wait_time * 1000); - } - else - break; - } + } while (rtas_busy_delay(rc)); if (rc < 0) return rtas_error_rc(rc); @@ -555,13 +542,11 @@ void rtas_os_term(char *str) do { status = rtas_call(rtas_token("ibm,os-term"), 1, 1, NULL, __pa(rtas_os_term_buf)); + } while (rtas_busy_delay(status)); - if (status == RTAS_BUSY) - udelay(1); - else if (status != 0) - printk(KERN_EMERG "ibm,os-term call failed %d\n", + if (status != 0) + printk(KERN_EMERG "ibm,os-term call failed %d\n", status); - } while (status == RTAS_BUSY); } static int ibm_suspend_me_token = RTAS_UNKNOWN_SERVICE; @@ -608,9 +593,31 @@ out: static int rtas_ibm_suspend_me(struct rtas_args *args) { int i; + long state; + long rc; + unsigned long dummy; struct rtas_suspend_me_data data; + /* Make sure the state is valid */ + rc = plpar_hcall(H_VASI_STATE, + ((u64)args->args[0] << 32) | args->args[1], + 0, 0, 0, + &state, &dummy, &dummy); + + if (rc) { + printk(KERN_ERR "rtas_ibm_suspend_me: vasi_state returned %ld\n",rc); + return rc; + } else if (state == H_VASI_ENABLED) { + args->args[args->nargs] = RTAS_NOT_SUSPENDABLE; + return 0; + } else if (state != H_VASI_SUSPENDING) { + printk(KERN_ERR "rtas_ibm_suspend_me: vasi_state returned state %ld\n", + state); + args->args[args->nargs] = -1; + return 0; + } + data.waiting = 1; data.args = args; @@ -789,7 +796,8 @@ EXPORT_SYMBOL(rtas_token); EXPORT_SYMBOL(rtas_call); EXPORT_SYMBOL(rtas_data_buf); EXPORT_SYMBOL(rtas_data_buf_lock); -EXPORT_SYMBOL(rtas_extended_busy_delay_time); +EXPORT_SYMBOL(rtas_busy_delay_time); +EXPORT_SYMBOL(rtas_busy_delay); EXPORT_SYMBOL(rtas_get_sensor); EXPORT_SYMBOL(rtas_get_power_level); EXPORT_SYMBOL(rtas_set_power_level); diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c index aaf384c3f04a..1442b63a75da 100644 --- a/arch/powerpc/kernel/rtas_flash.c +++ b/arch/powerpc/kernel/rtas_flash.c @@ -365,20 +365,12 @@ static int rtas_excl_release(struct inode *inode, struct file *file) static void manage_flash(struct rtas_manage_flash_t *args_buf) { - unsigned int wait_time; s32 rc; - while (1) { + do { rc = rtas_call(rtas_token("ibm,manage-flash-image"), 1, 1, NULL, args_buf->op); - if (rc == RTAS_RC_BUSY) - udelay(1); - else if (rtas_is_extended_busy(rc)) { - wait_time = rtas_extended_busy_delay_time(rc); - udelay(wait_time * 1000); - } else - break; - } + } while (rtas_busy_delay(rc)); args_buf->status = rc; } @@ -451,27 +443,18 @@ static ssize_t manage_flash_write(struct file *file, const char __user *buf, static void validate_flash(struct rtas_validate_flash_t *args_buf) { int token = rtas_token("ibm,validate-flash-image"); - unsigned int wait_time; int update_results; s32 rc; rc = 0; - while(1) { + do { spin_lock(&rtas_data_buf_lock); memcpy(rtas_data_buf, args_buf->buf, VALIDATE_BUF_SIZE); rc = rtas_call(token, 2, 2, &update_results, (u32) __pa(rtas_data_buf), args_buf->buf_size); memcpy(args_buf->buf, rtas_data_buf, VALIDATE_BUF_SIZE); spin_unlock(&rtas_data_buf_lock); - - if (rc == RTAS_RC_BUSY) - udelay(1); - else if (rtas_is_extended_busy(rc)) { - wait_time = rtas_extended_busy_delay_time(rc); - udelay(wait_time * 1000); - } else - break; - } + } while (rtas_busy_delay(rc)); args_buf->status = rc; args_buf->update_results = update_results; diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c index 57b539a03fa9..6eb7e49b394a 100644 --- a/arch/powerpc/kernel/rtas_pci.c +++ b/arch/powerpc/kernel/rtas_pci.c @@ -313,7 +313,9 @@ unsigned long __init find_and_init_phbs(void) for (node = of_get_next_child(root, NULL); node != NULL; node = of_get_next_child(root, node)) { - if (node->type == NULL || strcmp(node->type, "pci") != 0) + + if (node->type == NULL || (strcmp(node->type, "pci") != 0 && + strcmp(node->type, "pciex") != 0)) continue; phb = pcibios_alloc_controller(node); diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 684ab1d49c65..bd328123af75 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -443,6 +443,7 @@ void __init smp_setup_cpu_maps(void) } #endif /* CONFIG_SMP */ +int __initdata do_early_xmon; #ifdef CONFIG_XMON static int __init early_xmon(char *p) { @@ -456,7 +457,7 @@ static int __init early_xmon(char *p) return 0; } xmon_init(1); - debugger(NULL); + do_early_xmon = 1; return 0; } @@ -524,3 +525,20 @@ int check_legacy_ioport(unsigned long base_port) return ppc_md.check_legacy_ioport(base_port); } EXPORT_SYMBOL(check_legacy_ioport); + +static int ppc_panic_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + ppc_md.panic(ptr); /* May not return */ + return NOTIFY_DONE; +} + +static struct notifier_block ppc_panic_block = { + .notifier_call = ppc_panic_event, + .priority = INT_MIN /* may not return; must be done last */ +}; + +void __init setup_panic(void) +{ + atomic_notifier_chain_register(&panic_notifier_list, &ppc_panic_block); +} diff --git a/arch/powerpc/kernel/setup.h b/arch/powerpc/kernel/setup.h index 2ebba755272e..4c67ad7fae08 100644 --- a/arch/powerpc/kernel/setup.h +++ b/arch/powerpc/kernel/setup.h @@ -2,5 +2,8 @@ #define _POWERPC_KERNEL_SETUP_H void check_for_initrd(void); +void do_init_bootmem(void); +void setup_panic(void); +extern int do_early_xmon; #endif /* _POWERPC_KERNEL_SETUP_H */ diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 69ac25701344..e5a44812441a 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -131,12 +131,6 @@ void __init machine_init(unsigned long dt_ptr, unsigned long phys) /* Do some early initialization based on the flat device tree */ early_init_devtree(__va(dt_ptr)); - /* Check default command line */ -#ifdef CONFIG_CMDLINE - if (cmd_line[0] == 0) - strlcpy(cmd_line, CONFIG_CMDLINE, sizeof(cmd_line)); -#endif /* CONFIG_CMDLINE */ - probe_machine(); #ifdef CONFIG_6xx @@ -235,7 +229,7 @@ arch_initcall(ppc_init); /* Warning, IO base is not yet inited */ void __init setup_arch(char **cmdline_p) { - extern void do_init_bootmem(void); + *cmdline_p = cmd_line; /* so udelay does something sensible, assume <= 1000 bogomips */ loops_per_jiffy = 500000000 / HZ; @@ -285,16 +279,16 @@ void __init setup_arch(char **cmdline_p) /* reboot on panic */ panic_timeout = 180; + if (ppc_md.panic) + setup_panic(); + init_mm.start_code = PAGE_OFFSET; init_mm.end_code = (unsigned long) _etext; init_mm.end_data = (unsigned long) _edata; init_mm.brk = klimit; - /* Save unparsed command line copy for /proc/cmdline */ - strlcpy(saved_command_line, cmd_line, COMMAND_LINE_SIZE); - *cmdline_p = cmd_line; - - parse_early_param(); + if (do_early_xmon) + debugger(NULL); /* set up the bootmem stuff with available memory */ do_init_bootmem(); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 4467c49903b6..78f3a5fd43f6 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -100,12 +100,6 @@ unsigned long SYSRQ_KEY; #endif /* CONFIG_MAGIC_SYSRQ */ -static int ppc64_panic_event(struct notifier_block *, unsigned long, void *); -static struct notifier_block ppc64_panic_block = { - .notifier_call = ppc64_panic_event, - .priority = INT_MIN /* may not return; must be done last */ -}; - #ifdef CONFIG_SMP static int smt_enabled_cmdline; @@ -199,9 +193,7 @@ void __init early_setup(unsigned long dt_ptr) /* Probe the machine type */ probe_machine(); -#ifdef CONFIG_CRASH_DUMP - kdump_setup(); -#endif + setup_kdump_trampoline(); DBG("Found, Initializing memory management...\n"); @@ -353,9 +345,6 @@ void __init setup_system(void) { DBG(" -> setup_system()\n"); -#ifdef CONFIG_KEXEC - kdump_move_device_tree(); -#endif /* * Unflatten the device-tree passed by prom_init or kexec */ @@ -420,10 +409,8 @@ void __init setup_system(void) */ register_early_udbg_console(); - /* Save unparsed command line copy for /proc/cmdline */ - strlcpy(saved_command_line, cmd_line, COMMAND_LINE_SIZE); - - parse_early_param(); + if (do_early_xmon) + debugger(NULL); check_smt_enabled(); smp_setup_cpu_maps(); @@ -456,13 +443,6 @@ void __init setup_system(void) DBG(" <- setup_system()\n"); } -static int ppc64_panic_event(struct notifier_block *this, - unsigned long event, void *ptr) -{ - ppc_md.panic((char *)ptr); /* May not return */ - return NOTIFY_DONE; -} - #ifdef CONFIG_IRQSTACKS static void __init irqstack_early_init(void) { @@ -517,8 +497,6 @@ static void __init emergency_stack_init(void) */ void __init setup_arch(char **cmdline_p) { - extern void do_init_bootmem(void); - ppc64_boot_msg(0x12, "Setup Arch"); *cmdline_p = cmd_line; @@ -535,8 +513,7 @@ void __init setup_arch(char **cmdline_p) panic_timeout = 180; if (ppc_md.panic) - atomic_notifier_chain_register(&panic_notifier_list, - &ppc64_panic_block); + setup_panic(); init_mm.start_code = PAGE_OFFSET; init_mm.end_code = (unsigned long) _etext; diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 01e3c08cb550..d73b25e22fca 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -419,9 +419,7 @@ static long restore_user_regs(struct pt_regs *regs, { long err; unsigned int save_r2 = 0; -#if defined(CONFIG_ALTIVEC) || defined(CONFIG_SPE) unsigned long msr; -#endif /* * restore general registers but not including MSR or SOFTE. Also @@ -430,11 +428,16 @@ static long restore_user_regs(struct pt_regs *regs, if (!sig) save_r2 = (unsigned int)regs->gpr[2]; err = restore_general_regs(regs, sr); + err |= __get_user(msr, &sr->mc_gregs[PT_MSR]); if (!sig) regs->gpr[2] = (unsigned long) save_r2; if (err) return 1; + /* if doing signal return, restore the previous little-endian mode */ + if (sig) + regs->msr = (regs->msr & ~MSR_LE) | (msr & MSR_LE); + /* * Do this before updating the thread state in * current->thread.fpr/vr/evr. That way, if we get preempted @@ -455,7 +458,7 @@ static long restore_user_regs(struct pt_regs *regs, /* force the process to reload the altivec registers from current->thread when it next does altivec instructions */ regs->msr &= ~MSR_VEC; - if (!__get_user(msr, &sr->mc_gregs[PT_MSR]) && (msr & MSR_VEC) != 0) { + if (msr & MSR_VEC) { /* restore altivec registers from the stack */ if (__copy_from_user(current->thread.vr, &sr->mc_vregs, sizeof(sr->mc_vregs))) @@ -472,7 +475,7 @@ static long restore_user_regs(struct pt_regs *regs, /* force the process to reload the spe registers from current->thread when it next does spe instructions */ regs->msr &= ~MSR_SPE; - if (!__get_user(msr, &sr->mc_gregs[PT_MSR]) && (msr & MSR_SPE) != 0) { + if (msr & MSR_SPE) { /* restore spe registers from the stack */ if (__copy_from_user(current->thread.evr, &sr->mc_vregs, ELF_NEVRREG * sizeof(u32))) @@ -757,10 +760,10 @@ static int handle_rt_signal(unsigned long sig, struct k_sigaction *ka, /* Save user registers on the stack */ frame = &rt_sf->uc.uc_mcontext; - if (vdso32_rt_sigtramp && current->thread.vdso_base) { + if (vdso32_rt_sigtramp && current->mm->context.vdso_base) { if (save_user_regs(regs, frame, 0)) goto badframe; - regs->link = current->thread.vdso_base + vdso32_rt_sigtramp; + regs->link = current->mm->context.vdso_base + vdso32_rt_sigtramp; } else { if (save_user_regs(regs, frame, __NR_rt_sigreturn)) goto badframe; @@ -777,6 +780,8 @@ static int handle_rt_signal(unsigned long sig, struct k_sigaction *ka, regs->gpr[5] = (unsigned long) &rt_sf->uc; regs->gpr[6] = (unsigned long) rt_sf; regs->nip = (unsigned long) ka->sa.sa_handler; + /* enter the signal handler in big-endian mode */ + regs->msr &= ~MSR_LE; regs->trap = 0; return 1; @@ -803,10 +808,13 @@ static int do_setcontext(struct ucontext __user *ucp, struct pt_regs *regs, int if (__get_user(cmcp, &ucp->uc_regs)) return -EFAULT; mcp = (struct mcontext __user *)(u64)cmcp; + /* no need to check access_ok(mcp), since mcp < 4GB */ } #else if (__get_user(mcp, &ucp->uc_regs)) return -EFAULT; + if (!access_ok(VERIFY_READ, mcp, sizeof(*mcp))) + return -EFAULT; #endif restore_sigmask(&set); if (restore_user_regs(regs, mcp, sig)) @@ -908,13 +916,14 @@ int sys_debug_setcontext(struct ucontext __user *ctx, { struct sig_dbg_op op; int i; + unsigned char tmp; unsigned long new_msr = regs->msr; #if defined(CONFIG_4xx) || defined(CONFIG_BOOKE) unsigned long new_dbcr0 = current->thread.dbcr0; #endif for (i=0; i<ndbg; i++) { - if (__copy_from_user(&op, dbg, sizeof(op))) + if (copy_from_user(&op, dbg + i, sizeof(op))) return -EFAULT; switch (op.dbg_type) { case SIG_DBG_SINGLE_STEPPING: @@ -959,6 +968,11 @@ int sys_debug_setcontext(struct ucontext __user *ctx, current->thread.dbcr0 = new_dbcr0; #endif + if (!access_ok(VERIFY_READ, ctx, sizeof(*ctx)) + || __get_user(tmp, (u8 __user *) ctx) + || __get_user(tmp, (u8 __user *) (ctx + 1) - 1)) + return -EFAULT; + /* * If we get a fault copying the context into the kernel's * image of the user's registers, we can't just return -EFAULT @@ -1029,10 +1043,10 @@ static int handle_signal(unsigned long sig, struct k_sigaction *ka, || __put_user(sig, &sc->signal)) goto badframe; - if (vdso32_sigtramp && current->thread.vdso_base) { + if (vdso32_sigtramp && current->mm->context.vdso_base) { if (save_user_regs(regs, &frame->mctx, 0)) goto badframe; - regs->link = current->thread.vdso_base + vdso32_sigtramp; + regs->link = current->mm->context.vdso_base + vdso32_sigtramp; } else { if (save_user_regs(regs, &frame->mctx, __NR_sigreturn)) goto badframe; @@ -1047,6 +1061,8 @@ static int handle_signal(unsigned long sig, struct k_sigaction *ka, regs->gpr[3] = sig; regs->gpr[4] = (unsigned long) sc; regs->nip = (unsigned long) ka->sa.sa_handler; + /* enter the signal handler in big-endian mode */ + regs->msr &= ~MSR_LE; regs->trap = 0; return 1; diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 27f65b95184d..6e75d7ab6d4d 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -141,9 +141,7 @@ static long restore_sigcontext(struct pt_regs *regs, sigset_t *set, int sig, unsigned long err = 0; unsigned long save_r13 = 0; elf_greg_t *gregs = (elf_greg_t *)regs; -#ifdef CONFIG_ALTIVEC unsigned long msr; -#endif int i; /* If this is not a signal return, we preserve the TLS in r13 */ @@ -154,7 +152,12 @@ static long restore_sigcontext(struct pt_regs *regs, sigset_t *set, int sig, err |= __copy_from_user(regs, &sc->gp_regs, PT_MSR*sizeof(unsigned long)); - /* skip MSR and SOFTE */ + /* get MSR separately, transfer the LE bit if doing signal return */ + err |= __get_user(msr, &sc->gp_regs[PT_MSR]); + if (sig) + regs->msr = (regs->msr & ~MSR_LE) | (msr & MSR_LE); + + /* skip SOFTE */ for (i = PT_MSR+1; i <= PT_RESULT; i++) { if (i == PT_SOFTE) continue; @@ -179,9 +182,10 @@ static long restore_sigcontext(struct pt_regs *regs, sigset_t *set, int sig, #ifdef CONFIG_ALTIVEC err |= __get_user(v_regs, &sc->v_regs); - err |= __get_user(msr, &sc->gp_regs[PT_MSR]); if (err) return err; + if (v_regs && !access_ok(VERIFY_READ, v_regs, 34 * sizeof(vector128))) + return -EFAULT; /* Copy 33 vec registers (vr0..31 and vscr) from the stack */ if (v_regs != 0 && (msr & MSR_VEC) != 0) err |= __copy_from_user(current->thread.vr, v_regs, @@ -394,8 +398,8 @@ static int setup_rt_frame(int signr, struct k_sigaction *ka, siginfo_t *info, current->thread.fpscr.val = 0; /* Set up to return from userspace. */ - if (vdso64_rt_sigtramp && current->thread.vdso_base) { - regs->link = current->thread.vdso_base + vdso64_rt_sigtramp; + if (vdso64_rt_sigtramp && current->mm->context.vdso_base) { + regs->link = current->mm->context.vdso_base + vdso64_rt_sigtramp; } else { err |= setup_trampoline(__NR_rt_sigreturn, &frame->tramp[0]); if (err) @@ -410,6 +414,8 @@ static int setup_rt_frame(int signr, struct k_sigaction *ka, siginfo_t *info, /* Set up "regs" so we "return" to the signal handler. */ err |= get_user(regs->nip, &funct_desc_ptr->entry); + /* enter the signal handler in big-endian mode */ + regs->msr &= ~MSR_LE; regs->gpr[1] = newsp; err |= get_user(regs->gpr[2], &funct_desc_ptr->toc); regs->gpr[3] = signr; diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 530f7dba0bd2..c5d179d4f818 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -492,7 +492,7 @@ int __devinit __cpu_up(unsigned int cpu) * -- Cort */ if (system_state < SYSTEM_RUNNING) - for (c = 5000; c && !cpu_callin_map[cpu]; c--) + for (c = 50000; c && !cpu_callin_map[cpu]; c--) udelay(100); #ifdef CONFIG_HOTPLUG_CPU else diff --git a/arch/powerpc/kernel/systbl.S b/arch/powerpc/kernel/systbl.S index 26ed1f5ef16e..ee75ccf1a802 100644 --- a/arch/powerpc/kernel/systbl.S +++ b/arch/powerpc/kernel/systbl.S @@ -32,6 +32,10 @@ #define SYS32ONLY(func) .long sys_##func #define SYSX(f, f3264, f32) .long f32 #endif +#define SYSCALL_SPU(func) SYSCALL(func) +#define COMPAT_SYS_SPU(func) COMPAT_SYS(func) +#define PPC_SYS_SPU(func) PPC_SYS(func) +#define SYSX_SPU(f, f3264, f32) SYSX(f, f3264, f32) #ifdef CONFIG_PPC64 #define sys_sigpending sys_ni_syscall @@ -39,309 +43,4 @@ #endif _GLOBAL(sys_call_table) -SYSCALL(restart_syscall) -SYSCALL(exit) -PPC_SYS(fork) -SYSCALL(read) -SYSCALL(write) -COMPAT_SYS(open) -SYSCALL(close) -COMPAT_SYS(waitpid) -COMPAT_SYS(creat) -SYSCALL(link) -SYSCALL(unlink) -COMPAT_SYS(execve) -SYSCALL(chdir) -COMPAT_SYS(time) -SYSCALL(mknod) -SYSCALL(chmod) -SYSCALL(lchown) -SYSCALL(ni_syscall) -OLDSYS(stat) -SYSX(sys_lseek,ppc32_lseek,sys_lseek) -SYSCALL(getpid) -COMPAT_SYS(mount) -SYSX(sys_ni_syscall,sys_oldumount,sys_oldumount) -SYSCALL(setuid) -SYSCALL(getuid) -COMPAT_SYS(stime) -COMPAT_SYS(ptrace) -SYSCALL(alarm) -OLDSYS(fstat) -COMPAT_SYS(pause) -COMPAT_SYS(utime) -SYSCALL(ni_syscall) -SYSCALL(ni_syscall) -COMPAT_SYS(access) -COMPAT_SYS(nice) -SYSCALL(ni_syscall) -SYSCALL(sync) -COMPAT_SYS(kill) -SYSCALL(rename) -COMPAT_SYS(mkdir) -SYSCALL(rmdir) -SYSCALL(dup) -SYSCALL(pipe) -COMPAT_SYS(times) -SYSCALL(ni_syscall) -SYSCALL(brk) -SYSCALL(setgid) -SYSCALL(getgid) -SYSCALL(signal) -SYSCALL(geteuid) -SYSCALL(getegid) -SYSCALL(acct) -SYSCALL(umount) -SYSCALL(ni_syscall) -COMPAT_SYS(ioctl) -COMPAT_SYS(fcntl) -SYSCALL(ni_syscall) -COMPAT_SYS(setpgid) -SYSCALL(ni_syscall) -SYSX(sys_ni_syscall,sys_olduname, sys_olduname) -COMPAT_SYS(umask) -SYSCALL(chroot) -SYSCALL(ustat) -SYSCALL(dup2) -SYSCALL(getppid) -SYSCALL(getpgrp) -SYSCALL(setsid) -SYS32ONLY(sigaction) -SYSCALL(sgetmask) -COMPAT_SYS(ssetmask) -SYSCALL(setreuid) -SYSCALL(setregid) -SYS32ONLY(sigsuspend) -COMPAT_SYS(sigpending) -COMPAT_SYS(sethostname) -COMPAT_SYS(setrlimit) -COMPAT_SYS(old_getrlimit) -COMPAT_SYS(getrusage) -COMPAT_SYS(gettimeofday) -COMPAT_SYS(settimeofday) -COMPAT_SYS(getgroups) -COMPAT_SYS(setgroups) -SYSX(sys_ni_syscall,sys_ni_syscall,ppc_select) -SYSCALL(symlink) -OLDSYS(lstat) -COMPAT_SYS(readlink) -SYSCALL(uselib) -SYSCALL(swapon) -SYSCALL(reboot) -SYSX(sys_ni_syscall,old32_readdir,old_readdir) -SYSCALL(mmap) -SYSCALL(munmap) -SYSCALL(truncate) -SYSCALL(ftruncate) -SYSCALL(fchmod) -SYSCALL(fchown) -COMPAT_SYS(getpriority) -COMPAT_SYS(setpriority) -SYSCALL(ni_syscall) -COMPAT_SYS(statfs) -COMPAT_SYS(fstatfs) -SYSCALL(ni_syscall) -COMPAT_SYS(socketcall) -COMPAT_SYS(syslog) -COMPAT_SYS(setitimer) -COMPAT_SYS(getitimer) -COMPAT_SYS(newstat) -COMPAT_SYS(newlstat) -COMPAT_SYS(newfstat) -SYSX(sys_ni_syscall,sys_uname,sys_uname) -SYSCALL(ni_syscall) -SYSCALL(vhangup) -SYSCALL(ni_syscall) -SYSCALL(ni_syscall) -COMPAT_SYS(wait4) -SYSCALL(swapoff) -COMPAT_SYS(sysinfo) -COMPAT_SYS(ipc) -SYSCALL(fsync) -SYS32ONLY(sigreturn) -PPC_SYS(clone) -COMPAT_SYS(setdomainname) -PPC_SYS(newuname) -SYSCALL(ni_syscall) -COMPAT_SYS(adjtimex) -SYSCALL(mprotect) -SYSX(sys_ni_syscall,compat_sys_sigprocmask,sys_sigprocmask) -SYSCALL(ni_syscall) -SYSCALL(init_module) -SYSCALL(delete_module) -SYSCALL(ni_syscall) -SYSCALL(quotactl) -COMPAT_SYS(getpgid) -SYSCALL(fchdir) -SYSCALL(bdflush) -COMPAT_SYS(sysfs) -SYSX(ppc64_personality,ppc64_personality,sys_personality) -SYSCALL(ni_syscall) -SYSCALL(setfsuid) -SYSCALL(setfsgid) -SYSCALL(llseek) -COMPAT_SYS(getdents) -SYSX(sys_select,ppc32_select,ppc_select) -SYSCALL(flock) -SYSCALL(msync) -COMPAT_SYS(readv) -COMPAT_SYS(writev) -COMPAT_SYS(getsid) -SYSCALL(fdatasync) -COMPAT_SYS(sysctl) -SYSCALL(mlock) -SYSCALL(munlock) -SYSCALL(mlockall) -SYSCALL(munlockall) -COMPAT_SYS(sched_setparam) -COMPAT_SYS(sched_getparam) -COMPAT_SYS(sched_setscheduler) -COMPAT_SYS(sched_getscheduler) -SYSCALL(sched_yield) -COMPAT_SYS(sched_get_priority_max) -COMPAT_SYS(sched_get_priority_min) -COMPAT_SYS(sched_rr_get_interval) -COMPAT_SYS(nanosleep) -SYSCALL(mremap) -SYSCALL(setresuid) -SYSCALL(getresuid) -SYSCALL(ni_syscall) -SYSCALL(poll) -COMPAT_SYS(nfsservctl) -SYSCALL(setresgid) -SYSCALL(getresgid) -COMPAT_SYS(prctl) -COMPAT_SYS(rt_sigreturn) -COMPAT_SYS(rt_sigaction) -COMPAT_SYS(rt_sigprocmask) -COMPAT_SYS(rt_sigpending) -COMPAT_SYS(rt_sigtimedwait) -COMPAT_SYS(rt_sigqueueinfo) -COMPAT_SYS(rt_sigsuspend) -COMPAT_SYS(pread64) -COMPAT_SYS(pwrite64) -SYSCALL(chown) -SYSCALL(getcwd) -SYSCALL(capget) -SYSCALL(capset) -COMPAT_SYS(sigaltstack) -SYSX(sys_sendfile64,compat_sys_sendfile,sys_sendfile) -SYSCALL(ni_syscall) -SYSCALL(ni_syscall) -PPC_SYS(vfork) -COMPAT_SYS(getrlimit) -COMPAT_SYS(readahead) -SYS32ONLY(mmap2) -SYS32ONLY(truncate64) -SYS32ONLY(ftruncate64) -SYSX(sys_ni_syscall,sys_stat64,sys_stat64) -SYSX(sys_ni_syscall,sys_lstat64,sys_lstat64) -SYSX(sys_ni_syscall,sys_fstat64,sys_fstat64) -SYSCALL(pciconfig_read) -SYSCALL(pciconfig_write) -SYSCALL(pciconfig_iobase) -SYSCALL(ni_syscall) -SYSCALL(getdents64) -SYSCALL(pivot_root) -SYSX(sys_ni_syscall,compat_sys_fcntl64,sys_fcntl64) -SYSCALL(madvise) -SYSCALL(mincore) -SYSCALL(gettid) -SYSCALL(tkill) -SYSCALL(setxattr) -SYSCALL(lsetxattr) -SYSCALL(fsetxattr) -SYSCALL(getxattr) -SYSCALL(lgetxattr) -SYSCALL(fgetxattr) -SYSCALL(listxattr) -SYSCALL(llistxattr) -SYSCALL(flistxattr) -SYSCALL(removexattr) -SYSCALL(lremovexattr) -SYSCALL(fremovexattr) -COMPAT_SYS(futex) -COMPAT_SYS(sched_setaffinity) -COMPAT_SYS(sched_getaffinity) -SYSCALL(ni_syscall) -SYSCALL(ni_syscall) -SYS32ONLY(sendfile64) -COMPAT_SYS(io_setup) -SYSCALL(io_destroy) -COMPAT_SYS(io_getevents) -COMPAT_SYS(io_submit) -SYSCALL(io_cancel) -SYSCALL(set_tid_address) -SYSX(sys_fadvise64,ppc32_fadvise64,sys_fadvise64) -SYSCALL(exit_group) -SYSX(sys_lookup_dcookie,ppc32_lookup_dcookie,sys_lookup_dcookie) -SYSCALL(epoll_create) -SYSCALL(epoll_ctl) -SYSCALL(epoll_wait) -SYSCALL(remap_file_pages) -SYSX(sys_timer_create,compat_sys_timer_create,sys_timer_create) -COMPAT_SYS(timer_settime) -COMPAT_SYS(timer_gettime) -SYSCALL(timer_getoverrun) -SYSCALL(timer_delete) -COMPAT_SYS(clock_settime) -COMPAT_SYS(clock_gettime) -COMPAT_SYS(clock_getres) -COMPAT_SYS(clock_nanosleep) -SYSX(ppc64_swapcontext,ppc32_swapcontext,ppc_swapcontext) -COMPAT_SYS(tgkill) -COMPAT_SYS(utimes) -COMPAT_SYS(statfs64) -COMPAT_SYS(fstatfs64) -SYSX(sys_ni_syscall, ppc_fadvise64_64, ppc_fadvise64_64) -PPC_SYS(rtas) -OLDSYS(debug_setcontext) -SYSCALL(ni_syscall) -SYSCALL(ni_syscall) -COMPAT_SYS(mbind) -COMPAT_SYS(get_mempolicy) -COMPAT_SYS(set_mempolicy) -COMPAT_SYS(mq_open) -SYSCALL(mq_unlink) -COMPAT_SYS(mq_timedsend) -COMPAT_SYS(mq_timedreceive) -COMPAT_SYS(mq_notify) -COMPAT_SYS(mq_getsetattr) -COMPAT_SYS(kexec_load) -COMPAT_SYS(add_key) -COMPAT_SYS(request_key) -COMPAT_SYS(keyctl) -COMPAT_SYS(waitid) -COMPAT_SYS(ioprio_set) -COMPAT_SYS(ioprio_get) -SYSCALL(inotify_init) -SYSCALL(inotify_add_watch) -SYSCALL(inotify_rm_watch) -SYSCALL(spu_run) -SYSCALL(spu_create) -COMPAT_SYS(pselect6) -COMPAT_SYS(ppoll) -SYSCALL(unshare) -SYSCALL(splice) -SYSCALL(tee) -SYSCALL(vmsplice) -COMPAT_SYS(openat) -SYSCALL(mkdirat) -SYSCALL(mknodat) -SYSCALL(fchownat) -COMPAT_SYS(futimesat) -SYSX(sys_newfstatat, sys_fstatat64, sys_fstatat64) -SYSCALL(unlinkat) -SYSCALL(renameat) -SYSCALL(linkat) -SYSCALL(symlinkat) -SYSCALL(readlinkat) -SYSCALL(fchmodat) -SYSCALL(faccessat) -COMPAT_SYS(get_robust_list) -COMPAT_SYS(set_robust_list) - -/* - * please add new calls to arch/powerpc/platforms/cell/spu_callbacks.c - * as well when appropriate. - */ +#include <asm/systbl.h> diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 24e3ad756de0..d20907561f46 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -76,7 +76,6 @@ /* keep track of when we need to update the rtc */ time_t last_rtc_update; -extern int piranha_simulator; #ifdef CONFIG_PPC_ISERIES unsigned long iSeries_recal_titan = 0; unsigned long iSeries_recal_tb = 0; @@ -858,42 +857,50 @@ int do_settimeofday(struct timespec *tv) EXPORT_SYMBOL(do_settimeofday); -void __init generic_calibrate_decr(void) +static int __init get_freq(char *name, int cells, unsigned long *val) { struct device_node *cpu; unsigned int *fp; - int node_found; + int found = 0; - /* - * The cpu node should have a timebase-frequency property - * to tell us the rate at which the decrementer counts. - */ + /* The cpu node should have timebase and clock frequency properties */ cpu = of_find_node_by_type(NULL, "cpu"); - ppc_tb_freq = DEFAULT_TB_FREQ; /* hardcoded default */ - node_found = 0; if (cpu) { - fp = (unsigned int *)get_property(cpu, "timebase-frequency", - NULL); + fp = (unsigned int *)get_property(cpu, name, NULL); if (fp) { - node_found = 1; - ppc_tb_freq = *fp; + found = 1; + *val = 0; + while (cells--) + *val = (*val << 32) | *fp++; } + + of_node_put(cpu); } - if (!node_found) + + return found; +} + +void __init generic_calibrate_decr(void) +{ + ppc_tb_freq = DEFAULT_TB_FREQ; /* hardcoded default */ + + if (!get_freq("ibm,extended-timebase-frequency", 2, &ppc_tb_freq) && + !get_freq("timebase-frequency", 1, &ppc_tb_freq)) { + printk(KERN_ERR "WARNING: Estimating decrementer frequency " "(not found)\n"); + } - ppc_proc_freq = DEFAULT_PROC_FREQ; - node_found = 0; - if (cpu) { - fp = (unsigned int *)get_property(cpu, "clock-frequency", - NULL); - if (fp) { - node_found = 1; - ppc_proc_freq = *fp; - } + ppc_proc_freq = DEFAULT_PROC_FREQ; /* hardcoded default */ + + if (!get_freq("ibm,extended-clock-frequency", 2, &ppc_proc_freq) && + !get_freq("clock-frequency", 1, &ppc_proc_freq)) { + + printk(KERN_ERR "WARNING: Estimating processor frequency " + "(not found)\n"); } + #ifdef CONFIG_BOOKE /* Set the time base to zero */ mtspr(SPRN_TBWL, 0); @@ -905,11 +912,6 @@ void __init generic_calibrate_decr(void) /* Enable decrementer interrupt */ mtspr(SPRN_TCR, TCR_DIE); #endif - if (!node_found) - printk(KERN_ERR "WARNING: Estimating processor frequency " - "(not found)\n"); - - of_node_put(cpu); } unsigned long get_boot_time(void) @@ -945,9 +947,9 @@ void __init time_init(void) } else { /* Normal PowerPC with timebase register */ ppc_md.calibrate_decr(); - printk(KERN_INFO "time_init: decrementer frequency = %lu.%.6lu MHz\n", + printk(KERN_DEBUG "time_init: decrementer frequency = %lu.%.6lu MHz\n", ppc_tb_freq / 1000000, ppc_tb_freq % 1000000); - printk(KERN_INFO "time_init: processor frequency = %lu.%.6lu MHz\n", + printk(KERN_DEBUG "time_init: processor frequency = %lu.%.6lu MHz\n", ppc_proc_freq / 1000000, ppc_proc_freq % 1000000); tb_last_stamp = tb_last_jiffy = get_tb(); } @@ -1010,10 +1012,7 @@ void __init time_init(void) tb_to_ns_scale = scale; tb_to_ns_shift = shift; -#ifdef CONFIG_PPC_ISERIES - if (!piranha_simulator) -#endif - tm = get_boot_time(); + tm = get_boot_time(); write_seqlock_irqsave(&xtime_lock, flags); diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 064a52564692..52f5659534f4 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -32,6 +32,7 @@ #include <linux/delay.h> #include <linux/kprobes.h> #include <linux/kexec.h> +#include <linux/backlight.h> #include <asm/kdebug.h> #include <asm/pgtable.h> @@ -105,10 +106,18 @@ int die(const char *str, struct pt_regs *regs, long err) spin_lock_irq(&die_lock); bust_spinlocks(1); #ifdef CONFIG_PMAC_BACKLIGHT - if (machine_is(powermac)) { - set_backlight_enable(1); - set_backlight_level(BACKLIGHT_MAX); + mutex_lock(&pmac_backlight_mutex); + if (machine_is(powermac) && pmac_backlight) { + struct backlight_properties *props; + + down(&pmac_backlight->sem); + props = pmac_backlight->props; + props->brightness = props->max_brightness; + props->power = FB_BLANK_UNBLANK; + props->update_status(pmac_backlight); + up(&pmac_backlight->sem); } + mutex_unlock(&pmac_backlight_mutex); #endif printk("Oops: %s, sig: %ld [#%d]\n", str, err, ++die_counter); #ifdef CONFIG_PREEMPT @@ -658,7 +667,7 @@ static int emulate_instruction(struct pt_regs *regs) u32 instword; u32 rd; - if (!user_mode(regs)) + if (!user_mode(regs) || (regs->msr & MSR_LE)) return -EINVAL; CHECK_FULL_REGS(regs); @@ -805,9 +814,11 @@ void __kprobes program_check_exception(struct pt_regs *regs) void alignment_exception(struct pt_regs *regs) { - int fixed; + int fixed = 0; - fixed = fix_alignment(regs); + /* we don't implement logging of alignment exceptions */ + if (!(current->thread.align_ctl & PR_UNALIGN_SIGBUS)) + fixed = fix_alignment(regs); if (fixed == 1) { regs->nip += 4; /* skip over emulated instruction */ diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c index 3774e80094f5..67d9fd9ae2b5 100644 --- a/arch/powerpc/kernel/udbg.c +++ b/arch/powerpc/kernel/udbg.c @@ -14,6 +14,7 @@ #include <linux/types.h> #include <linux/sched.h> #include <linux/console.h> +#include <linux/init.h> #include <asm/processor.h> #include <asm/udbg.h> @@ -141,12 +142,14 @@ static int early_console_initialized; void __init disable_early_printk(void) { -#if 1 if (!early_console_initialized) return; + if (strstr(saved_command_line, "udbg-immortal")) { + printk(KERN_INFO "early console immortal !\n"); + return; + } unregister_console(&udbg_console); early_console_initialized = 0; -#endif } /* called by setup_system */ diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index 573afb68d69e..bc3e15be3087 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -223,6 +223,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, struct vm_area_struct *vma; unsigned long vdso_pages; unsigned long vdso_base; + int rc; #ifdef CONFIG_PPC64 if (test_thread_flag(TIF_32BIT)) { @@ -237,20 +238,13 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, vdso_base = VDSO32_MBASE; #endif - current->thread.vdso_base = 0; + current->mm->context.vdso_base = 0; /* vDSO has a problem and was disabled, just don't "enable" it for the * process */ if (vdso_pages == 0) return 0; - - vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL); - if (vma == NULL) - return -ENOMEM; - - memset(vma, 0, sizeof(*vma)); - /* Add a page to the vdso size for the data page */ vdso_pages ++; @@ -259,17 +253,23 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, * at vdso_base which is the "natural" base for it, but we might fail * and end up putting it elsewhere. */ + down_write(&mm->mmap_sem); vdso_base = get_unmapped_area(NULL, vdso_base, vdso_pages << PAGE_SHIFT, 0, 0); - if (vdso_base & ~PAGE_MASK) { - kmem_cache_free(vm_area_cachep, vma); - return (int)vdso_base; + if (IS_ERR_VALUE(vdso_base)) { + rc = vdso_base; + goto fail_mmapsem; } - current->thread.vdso_base = vdso_base; + /* Allocate a VMA structure and fill it up */ + vma = kmem_cache_zalloc(vm_area_cachep, SLAB_KERNEL); + if (vma == NULL) { + rc = -ENOMEM; + goto fail_mmapsem; + } vma->vm_mm = mm; - vma->vm_start = current->thread.vdso_base; + vma->vm_start = vdso_base; vma->vm_end = vma->vm_start + (vdso_pages << PAGE_SHIFT); /* @@ -282,23 +282,38 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, * It's fine to use that for setting breakpoints in the vDSO code * pages though */ - vma->vm_flags = VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC; + vma->vm_flags = VM_READ|VM_EXEC|VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC; vma->vm_flags |= mm->def_flags; vma->vm_page_prot = protection_map[vma->vm_flags & 0x7]; vma->vm_ops = &vdso_vmops; - down_write(&mm->mmap_sem); - if (insert_vm_struct(mm, vma)) { - up_write(&mm->mmap_sem); - kmem_cache_free(vm_area_cachep, vma); - return -ENOMEM; - } + /* Insert new VMA */ + rc = insert_vm_struct(mm, vma); + if (rc) + goto fail_vma; + + /* Put vDSO base into mm struct and account for memory usage */ + current->mm->context.vdso_base = vdso_base; mm->total_vm += (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; up_write(&mm->mmap_sem); - return 0; + + fail_vma: + kmem_cache_free(vm_area_cachep, vma); + fail_mmapsem: + up_write(&mm->mmap_sem); + return rc; +} + +const char *arch_vma_name(struct vm_area_struct *vma) +{ + if (vma->vm_mm && vma->vm_start == vma->vm_mm->context.vdso_base) + return "[vdso]"; + return NULL; } + + static void * __init find_section32(Elf32_Ehdr *ehdr, const char *secname, unsigned long *size) { diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S index 66b3d03c5fa5..9416b4ab92ec 100644 --- a/arch/powerpc/kernel/vector.S +++ b/arch/powerpc/kernel/vector.S @@ -53,12 +53,12 @@ fpenable: stfd fr31,8(r1) LDCONST(fr1, fpzero) mffs fr31 - mtfsf 0xff,fr1 + MTFSF_L(fr1) blr fpdisable: mtlr r12 - mtfsf 0xff,fr31 + MTFSF_L(fr31) lfd fr31,8(r1) lfd fr1,16(r1) lfd fr0,24(r1) diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index 971020cf3f7d..cdf5867838a6 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -13,27 +13,116 @@ * 2 of the License, or (at your option) any later version. */ +#include <linux/types.h> +#include <linux/device.h> #include <linux/init.h> #include <linux/console.h> #include <linux/module.h> #include <linux/mm.h> #include <linux/dma-mapping.h> +#include <linux/kobject.h> + #include <asm/iommu.h> #include <asm/dma.h> #include <asm/vio.h> #include <asm/prom.h> - -static const struct vio_device_id *vio_match_device( - const struct vio_device_id *, const struct vio_dev *); - -struct vio_dev vio_bus_device = { /* fake "parent" device */ +#include <asm/firmware.h> +#include <asm/tce.h> +#include <asm/abs_addr.h> +#include <asm/page.h> +#include <asm/hvcall.h> +#include <asm/iseries/vio.h> +#include <asm/iseries/hv_types.h> +#include <asm/iseries/hv_lp_config.h> +#include <asm/iseries/hv_call_xm.h> +#include <asm/iseries/iommu.h> + +extern struct subsystem devices_subsys; /* needed for vio_find_name() */ + +static struct vio_dev vio_bus_device = { /* fake "parent" device */ .name = vio_bus_device.dev.bus_id, .type = "", .dev.bus_id = "vio", .dev.bus = &vio_bus_type, }; -static struct vio_bus_ops vio_bus_ops; +#ifdef CONFIG_PPC_ISERIES +struct device *iSeries_vio_dev = &vio_bus_device.dev; +EXPORT_SYMBOL(iSeries_vio_dev); + +static struct iommu_table veth_iommu_table; +static struct iommu_table vio_iommu_table; + +static void __init iommu_vio_init(void) +{ + iommu_table_getparms_iSeries(255, 0, 0xff, &veth_iommu_table); + veth_iommu_table.it_size /= 2; + vio_iommu_table = veth_iommu_table; + vio_iommu_table.it_offset += veth_iommu_table.it_size; + + if (!iommu_init_table(&veth_iommu_table, -1)) + printk("Virtual Bus VETH TCE table failed.\n"); + if (!iommu_init_table(&vio_iommu_table, -1)) + printk("Virtual Bus VIO TCE table failed.\n"); +} +#endif + +static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev) +{ +#ifdef CONFIG_PPC_ISERIES + if (firmware_has_feature(FW_FEATURE_ISERIES)) { + if (strcmp(dev->type, "network") == 0) + return &veth_iommu_table; + return &vio_iommu_table; + } else +#endif + { + unsigned char *dma_window; + struct iommu_table *tbl; + unsigned long offset, size; + + dma_window = get_property(dev->dev.platform_data, + "ibm,my-dma-window", NULL); + if (!dma_window) + return NULL; + + tbl = kmalloc(sizeof(*tbl), GFP_KERNEL); + + of_parse_dma_window(dev->dev.platform_data, dma_window, + &tbl->it_index, &offset, &size); + + /* TCE table size - measured in tce entries */ + tbl->it_size = size >> PAGE_SHIFT; + /* offset for VIO should always be 0 */ + tbl->it_offset = offset >> PAGE_SHIFT; + tbl->it_busno = 0; + tbl->it_type = TCE_VB; + + return iommu_init_table(tbl, -1); + } +} + +/** + * vio_match_device: - Tell if a VIO device has a matching + * VIO device id structure. + * @ids: array of VIO device id structures to search in + * @dev: the VIO device structure to match against + * + * Used by a driver to check whether a VIO device present in the + * system is in its list of supported devices. Returns the matching + * vio_device_id structure or NULL if there is no match. + */ +static const struct vio_device_id *vio_match_device( + const struct vio_device_id *ids, const struct vio_dev *dev) +{ + while (ids->type[0] != '\0') { + if ((strncmp(dev->type, ids->type, strlen(ids->type)) == 0) && + device_is_compatible(dev->dev.platform_data, ids->compat)) + return ids; + ids++; + } + return NULL; +} /* * Convert from struct device to struct vio_dev and pass to driver. @@ -106,35 +195,110 @@ void vio_unregister_driver(struct vio_driver *viodrv) } EXPORT_SYMBOL(vio_unregister_driver); +/* vio_dev refcount hit 0 */ +static void __devinit vio_dev_release(struct device *dev) +{ + if (dev->platform_data) { + /* XXX free TCE table */ + of_node_put(dev->platform_data); + } + kfree(to_vio_dev(dev)); +} + /** - * vio_match_device: - Tell if a VIO device has a matching - * VIO device id structure. - * @ids: array of VIO device id structures to search in - * @dev: the VIO device structure to match against + * vio_register_device_node: - Register a new vio device. + * @of_node: The OF node for this device. * - * Used by a driver to check whether a VIO device present in the - * system is in its list of supported devices. Returns the matching - * vio_device_id structure or NULL if there is no match. + * Creates and initializes a vio_dev structure from the data in + * of_node (dev.platform_data) and adds it to the list of virtual devices. + * Returns a pointer to the created vio_dev or NULL if node has + * NULL device_type or compatible fields. */ -static const struct vio_device_id *vio_match_device( - const struct vio_device_id *ids, const struct vio_dev *dev) +struct vio_dev * __devinit vio_register_device_node(struct device_node *of_node) { - while (ids->type[0] != '\0') { - if (vio_bus_ops.match(ids, dev)) - return ids; - ids++; + struct vio_dev *viodev; + unsigned int *unit_address; + unsigned int *irq_p; + + /* we need the 'device_type' property, in order to match with drivers */ + if (of_node->type == NULL) { + printk(KERN_WARNING "%s: node %s missing 'device_type'\n", + __FUNCTION__, + of_node->name ? of_node->name : "<unknown>"); + return NULL; } - return NULL; + + unit_address = (unsigned int *)get_property(of_node, "reg", NULL); + if (unit_address == NULL) { + printk(KERN_WARNING "%s: node %s missing 'reg'\n", + __FUNCTION__, + of_node->name ? of_node->name : "<unknown>"); + return NULL; + } + + /* allocate a vio_dev for this node */ + viodev = kzalloc(sizeof(struct vio_dev), GFP_KERNEL); + if (viodev == NULL) + return NULL; + + viodev->dev.platform_data = of_node_get(of_node); + + viodev->irq = NO_IRQ; + irq_p = (unsigned int *)get_property(of_node, "interrupts", NULL); + if (irq_p) { + int virq = virt_irq_create_mapping(*irq_p); + if (virq == NO_IRQ) { + printk(KERN_ERR "Unable to allocate interrupt " + "number for %s\n", of_node->full_name); + } else + viodev->irq = irq_offset_up(virq); + } + + snprintf(viodev->dev.bus_id, BUS_ID_SIZE, "%x", *unit_address); + viodev->name = of_node->name; + viodev->type = of_node->type; + viodev->unit_address = *unit_address; + if (firmware_has_feature(FW_FEATURE_ISERIES)) { + unit_address = (unsigned int *)get_property(of_node, + "linux,unit_address", NULL); + if (unit_address != NULL) + viodev->unit_address = *unit_address; + } + viodev->iommu_table = vio_build_iommu_table(viodev); + + /* init generic 'struct device' fields: */ + viodev->dev.parent = &vio_bus_device.dev; + viodev->dev.bus = &vio_bus_type; + viodev->dev.release = vio_dev_release; + + /* register with generic device framework */ + if (device_register(&viodev->dev)) { + printk(KERN_ERR "%s: failed to register device %s\n", + __FUNCTION__, viodev->dev.bus_id); + /* XXX free TCE table */ + kfree(viodev); + return NULL; + } + + return viodev; } +EXPORT_SYMBOL(vio_register_device_node); /** * vio_bus_init: - Initialize the virtual IO bus */ -int __init vio_bus_init(struct vio_bus_ops *ops) +static int __init vio_bus_init(void) { int err; + struct device_node *node_vroot; - vio_bus_ops = *ops; +#ifdef CONFIG_PPC_ISERIES + if (firmware_has_feature(FW_FEATURE_ISERIES)) { + iommu_vio_init(); + vio_bus_device.iommu_table = &vio_iommu_table; + iSeries_vio_dev = &vio_bus_device.dev; + } +#endif err = bus_register(&vio_bus_type); if (err) { @@ -153,47 +317,48 @@ int __init vio_bus_init(struct vio_bus_ops *ops) return err; } - return 0; -} + node_vroot = find_devices("vdevice"); + if (node_vroot) { + struct device_node *of_node; + + /* + * Create struct vio_devices for each virtual device in + * the device tree. Drivers will associate with them later. + */ + for (of_node = node_vroot->child; of_node != NULL; + of_node = of_node->sibling) { + printk(KERN_DEBUG "%s: processing %p\n", + __FUNCTION__, of_node); + vio_register_device_node(of_node); + } + } -/* vio_dev refcount hit 0 */ -static void __devinit vio_dev_release(struct device *dev) -{ - if (vio_bus_ops.release_device) - vio_bus_ops.release_device(dev); - kfree(to_vio_dev(dev)); + return 0; } +__initcall(vio_bus_init); -static ssize_t viodev_show_name(struct device *dev, +static ssize_t name_show(struct device *dev, struct device_attribute *attr, char *buf) { return sprintf(buf, "%s\n", to_vio_dev(dev)->name); } -DEVICE_ATTR(name, S_IRUSR | S_IRGRP | S_IROTH, viodev_show_name, NULL); -struct vio_dev * __devinit vio_register_device(struct vio_dev *viodev) +static ssize_t devspec_show(struct device *dev, + struct device_attribute *attr, char *buf) { - /* init generic 'struct device' fields: */ - viodev->dev.parent = &vio_bus_device.dev; - viodev->dev.bus = &vio_bus_type; - viodev->dev.release = vio_dev_release; - - /* register with generic device framework */ - if (device_register(&viodev->dev)) { - printk(KERN_ERR "%s: failed to register device %s\n", - __FUNCTION__, viodev->dev.bus_id); - return NULL; - } - device_create_file(&viodev->dev, &dev_attr_name); + struct device_node *of_node = dev->platform_data; - return viodev; + return sprintf(buf, "%s\n", of_node ? of_node->full_name : "none"); } +static struct device_attribute vio_dev_attrs[] = { + __ATTR_RO(name), + __ATTR_RO(devspec), + __ATTR_NULL +}; + void __devinit vio_unregister_device(struct vio_dev *viodev) { - if (vio_bus_ops.unregister_device) - vio_bus_ops.unregister_device(viodev); - device_remove_file(&viodev->dev, &dev_attr_name); device_unregister(&viodev->dev); } EXPORT_SYMBOL(vio_unregister_device); @@ -229,7 +394,7 @@ static void *vio_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag) { return iommu_alloc_coherent(to_vio_dev(dev)->iommu_table, size, - dma_handle, ~0ul, flag); + dma_handle, ~0ul, flag, -1); } static void vio_free_coherent(struct device *dev, size_t size, @@ -267,22 +432,23 @@ static int vio_hotplug(struct device *dev, char **envp, int num_envp, char *buffer, int buffer_size) { const struct vio_dev *vio_dev = to_vio_dev(dev); + struct device_node *dn = dev->platform_data; char *cp; int length; if (!num_envp) return -ENOMEM; - if (!vio_dev->dev.platform_data) + if (!dn) return -ENODEV; - cp = (char *)get_property(vio_dev->dev.platform_data, "compatible", &length); + cp = (char *)get_property(dn, "compatible", &length); if (!cp) return -ENODEV; envp[0] = buffer; length = scnprintf(buffer, buffer_size, "MODALIAS=vio:T%sS%s", vio_dev->type, cp); - if (buffer_size - length <= 0) + if ((buffer_size - length) <= 0) return -ENOMEM; envp[1] = NULL; return 0; @@ -290,9 +456,81 @@ static int vio_hotplug(struct device *dev, char **envp, int num_envp, struct bus_type vio_bus_type = { .name = "vio", + .dev_attrs = vio_dev_attrs, .uevent = vio_hotplug, .match = vio_bus_match, .probe = vio_bus_probe, .remove = vio_bus_remove, .shutdown = vio_bus_shutdown, }; + +/** + * vio_get_attribute: - get attribute for virtual device + * @vdev: The vio device to get property. + * @which: The property/attribute to be extracted. + * @length: Pointer to length of returned data size (unused if NULL). + * + * Calls prom.c's get_property() to return the value of the + * attribute specified by @which +*/ +const void *vio_get_attribute(struct vio_dev *vdev, char *which, int *length) +{ + return get_property(vdev->dev.platform_data, which, length); +} +EXPORT_SYMBOL(vio_get_attribute); + +#ifdef CONFIG_PPC_PSERIES +/* vio_find_name() - internal because only vio.c knows how we formatted the + * kobject name + * XXX once vio_bus_type.devices is actually used as a kset in + * drivers/base/bus.c, this function should be removed in favor of + * "device_find(kobj_name, &vio_bus_type)" + */ +static struct vio_dev *vio_find_name(const char *kobj_name) +{ + struct kobject *found; + + found = kset_find_obj(&devices_subsys.kset, kobj_name); + if (!found) + return NULL; + + return to_vio_dev(container_of(found, struct device, kobj)); +} + +/** + * vio_find_node - find an already-registered vio_dev + * @vnode: device_node of the virtual device we're looking for + */ +struct vio_dev *vio_find_node(struct device_node *vnode) +{ + uint32_t *unit_address; + char kobj_name[BUS_ID_SIZE]; + + /* construct the kobject name from the device node */ + unit_address = (uint32_t *)get_property(vnode, "reg", NULL); + if (!unit_address) + return NULL; + snprintf(kobj_name, BUS_ID_SIZE, "%x", *unit_address); + + return vio_find_name(kobj_name); +} +EXPORT_SYMBOL(vio_find_node); + +int vio_enable_interrupts(struct vio_dev *dev) +{ + int rc = h_vio_signal(dev->unit_address, VIO_IRQ_ENABLE); + if (rc != H_SUCCESS) + printk(KERN_ERR "vio: Error 0x%x enabling interrupts\n", rc); + return rc; +} +EXPORT_SYMBOL(vio_enable_interrupts); + +int vio_disable_interrupts(struct vio_dev *dev) +{ + int rc = h_vio_signal(dev->unit_address, VIO_IRQ_DISABLE); + if (rc != H_SUCCESS) + printk(KERN_ERR "vio: Error 0x%x disabling interrupts\n", rc); + return rc; +} +EXPORT_SYMBOL(vio_disable_interrupts); +#endif /* CONFIG_PPC_PSERIES */ diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index fe79c2584cb0..8b25953dc4f0 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -93,6 +93,11 @@ SECTIONS __ptov_table_begin = .; *(.ptov_fixup); __ptov_table_end = .; +#ifdef CONFIG_PPC_ISERIES + __dt_strings_start = .; + *(.dt_strings); + __dt_strings_end = .; +#endif } . = ALIGN(16); |