diff options
Diffstat (limited to 'arch/powerpc/kernel')
40 files changed, 921 insertions, 417 deletions
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index bb282dd81612..cde12f8a4ebc 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -96,6 +96,7 @@ obj-$(CONFIG_MODULES) += ppc_ksyms.o obj-$(CONFIG_BOOTX_TEXT) += btext.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_KPROBES) += kprobes.o +obj-$(CONFIG_UPROBES) += uprobes.o obj-$(CONFIG_PPC_UDBG_16550) += legacy_serial.o udbg_16550.o obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-$(CONFIG_SWIOTLB) += dma-swiotlb.o diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index e8995727b1c1..7523539cfe9f 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -206,6 +206,7 @@ int main(void) DEFINE(PACA_SYSTEM_TIME, offsetof(struct paca_struct, system_time)); DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save)); DEFINE(PACA_NAPSTATELOST, offsetof(struct paca_struct, nap_state_lost)); + DEFINE(PACA_SPRG3, offsetof(struct paca_struct, sprg3)); #endif /* CONFIG_PPC64 */ /* RTAS */ @@ -534,7 +535,6 @@ int main(void) HSTATE_FIELD(HSTATE_VMHANDLER, vmhandler); HSTATE_FIELD(HSTATE_SCRATCH0, scratch0); HSTATE_FIELD(HSTATE_SCRATCH1, scratch1); - HSTATE_FIELD(HSTATE_SPRG3, sprg3); HSTATE_FIELD(HSTATE_IN_GUEST, in_guest); HSTATE_FIELD(HSTATE_RESTORE_HID5, restore_hid5); HSTATE_FIELD(HSTATE_NAPPING, napping); diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S index 69fdd2322a66..dcd881937f7a 100644 --- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S +++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S @@ -16,6 +16,8 @@ #include <asm/processor.h> #include <asm/cputable.h> #include <asm/ppc_asm.h> +#include <asm/mmu-book3e.h> +#include <asm/asm-offsets.h> _GLOBAL(__e500_icache_setup) mfspr r0, SPRN_L1CSR1 @@ -73,27 +75,81 @@ _GLOBAL(__setup_cpu_e500v2) mtlr r4 blr _GLOBAL(__setup_cpu_e500mc) - mr r5, r4 - mflr r4 +_GLOBAL(__setup_cpu_e5500) + mflr r5 bl __e500_icache_setup bl __e500_dcache_setup bl __setup_e500mc_ivors - mtlr r4 + /* + * We only want to touch IVOR38-41 if we're running on hardware + * that supports category E.HV. The architectural way to determine + * this is MMUCFG[LPIDSIZE]. + */ + mfspr r3, SPRN_MMUCFG + rlwinm. r3, r3, 0, MMUCFG_LPIDSIZE + beq 1f + bl __setup_ehv_ivors + b 2f +1: + lwz r3, CPU_SPEC_FEATURES(r4) + /* We need this check as cpu_setup is also called for + * the secondary cores. So, if we have already cleared + * the feature on the primary core, avoid doing it on the + * secondary core. + */ + andis. r6, r3, CPU_FTR_EMB_HV@h + beq 2f + rlwinm r3, r3, 0, ~CPU_FTR_EMB_HV + stw r3, CPU_SPEC_FEATURES(r4) +2: + mtlr r5 blr #endif -/* Right now, restore and setup are the same thing */ + +#ifdef CONFIG_PPC_BOOK3E_64 _GLOBAL(__restore_cpu_e5500) -_GLOBAL(__setup_cpu_e5500) mflr r4 bl __e500_icache_setup bl __e500_dcache_setup -#ifdef CONFIG_PPC_BOOK3E_64 bl .__setup_base_ivors bl .setup_perfmon_ivor bl .setup_doorbell_ivors + /* + * We only want to touch IVOR38-41 if we're running on hardware + * that supports category E.HV. The architectural way to determine + * this is MMUCFG[LPIDSIZE]. + */ + mfspr r10,SPRN_MMUCFG + rlwinm. r10,r10,0,MMUCFG_LPIDSIZE + beq 1f bl .setup_ehv_ivors -#else - bl __setup_e500mc_ivors -#endif +1: mtlr r4 blr + +_GLOBAL(__setup_cpu_e5500) + mflr r5 + bl __e500_icache_setup + bl __e500_dcache_setup + bl .__setup_base_ivors + bl .setup_perfmon_ivor + bl .setup_doorbell_ivors + /* + * We only want to touch IVOR38-41 if we're running on hardware + * that supports category E.HV. The architectural way to determine + * this is MMUCFG[LPIDSIZE]. + */ + mfspr r10,SPRN_MMUCFG + rlwinm. r10,r10,0,MMUCFG_LPIDSIZE + beq 1f + bl .setup_ehv_ivors + b 2f +1: + ld r10,CPU_SPEC_FEATURES(r4) + LOAD_REG_IMMEDIATE(r9,CPU_FTR_EMB_HV) + andc r10,r10,r9 + std r10,CPU_SPEC_FEATURES(r4) +2: + mtlr r5 + blr +#endif diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 455faa389876..0514c21f138b 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -2016,7 +2016,9 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_cpu_type = "ppc/e500mc", .oprofile_type = PPC_OPROFILE_FSL_EMB, .cpu_setup = __setup_cpu_e5500, +#ifndef CONFIG_PPC32 .cpu_restore = __restore_cpu_e5500, +#endif .machine_check = machine_check_e500mc, .platform = "ppce5500", }, @@ -2034,7 +2036,9 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_cpu_type = "ppc/e6500", .oprofile_type = PPC_OPROFILE_FSL_EMB, .cpu_setup = __setup_cpu_e5500, +#ifndef CONFIG_PPC32 .cpu_restore = __restore_cpu_e5500, +#endif .machine_check = machine_check_e500mc, .platform = "ppce6500", }, diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c index 46943651da23..bd1a2aba599f 100644 --- a/arch/powerpc/kernel/dma-swiotlb.c +++ b/arch/powerpc/kernel/dma-swiotlb.c @@ -12,6 +12,7 @@ */ #include <linux/dma-mapping.h> +#include <linux/memblock.h> #include <linux/pfn.h> #include <linux/of_platform.h> #include <linux/platform_device.h> @@ -20,7 +21,6 @@ #include <asm/machdep.h> #include <asm/swiotlb.h> #include <asm/dma.h> -#include <asm/abs_addr.h> unsigned int ppc_swiotlb_enable; @@ -105,3 +105,23 @@ int __init swiotlb_setup_bus_notifier(void) &ppc_swiotlb_plat_bus_notifier); return 0; } + +void swiotlb_detect_4g(void) +{ + if ((memblock_end_of_DRAM() - 1) > 0xffffffff) + ppc_swiotlb_enable = 1; +} + +static int __init swiotlb_late_init(void) +{ + if (ppc_swiotlb_enable) { + swiotlb_print_info(); + set_pci_dma_ops(&swiotlb_dma_ops); + ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb; + } else { + swiotlb_free(); + } + + return 0; +} +subsys_initcall(swiotlb_late_init); diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c index 355b9d84b0f8..8032b97ccdcb 100644 --- a/arch/powerpc/kernel/dma.c +++ b/arch/powerpc/kernel/dma.c @@ -14,7 +14,6 @@ #include <linux/pci.h> #include <asm/vio.h> #include <asm/bug.h> -#include <asm/abs_addr.h> #include <asm/machdep.h> /* @@ -50,7 +49,7 @@ void *dma_direct_alloc_coherent(struct device *dev, size_t size, return NULL; ret = page_address(page); memset(ret, 0, size); - *dma_handle = virt_to_abs(ret) + get_dma_offset(dev); + *dma_handle = __pa(ret) + get_dma_offset(dev); return ret; #endif diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index ead5016b02d0..9499385676e7 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -435,6 +435,22 @@ ret_from_fork: li r3,0 b ret_from_syscall + .globl ret_from_kernel_thread +ret_from_kernel_thread: + REST_NVGPRS(r1) + bl schedule_tail + mtlr r14 + mr r3,r15 + PPC440EP_ERR42 + blrl + li r3,0 + b do_exit # no return + + .globl __ret_from_kernel_execve +__ret_from_kernel_execve: + addi r1,r3,-STACK_FRAME_OVERHEAD + b ret_from_syscall + /* Traced system call support */ syscall_dotrace: SAVE_NVGPRS(r1) @@ -831,19 +847,56 @@ restore_user: bnel- load_dbcr0 #endif -#ifdef CONFIG_PREEMPT b restore /* N.B. the only way to get here is from the beq following ret_from_except. */ resume_kernel: - /* check current_thread_info->preempt_count */ + /* check current_thread_info, _TIF_EMULATE_STACK_STORE */ CURRENT_THREAD_INFO(r9, r1) + lwz r8,TI_FLAGS(r9) + andis. r8,r8,_TIF_EMULATE_STACK_STORE@h + beq+ 1f + + addi r8,r1,INT_FRAME_SIZE /* Get the kprobed function entry */ + + lwz r3,GPR1(r1) + subi r3,r3,INT_FRAME_SIZE /* dst: Allocate a trampoline exception frame */ + mr r4,r1 /* src: current exception frame */ + mr r1,r3 /* Reroute the trampoline frame to r1 */ + + /* Copy from the original to the trampoline. */ + li r5,INT_FRAME_SIZE/4 /* size: INT_FRAME_SIZE */ + li r6,0 /* start offset: 0 */ + mtctr r5 +2: lwzx r0,r6,r4 + stwx r0,r6,r3 + addi r6,r6,4 + bdnz 2b + + /* Do real store operation to complete stwu */ + lwz r5,GPR1(r1) + stw r8,0(r5) + + /* Clear _TIF_EMULATE_STACK_STORE flag */ + lis r11,_TIF_EMULATE_STACK_STORE@h + addi r5,r9,TI_FLAGS +0: lwarx r8,0,r5 + andc r8,r8,r11 +#ifdef CONFIG_IBM405_ERR77 + dcbt 0,r5 +#endif + stwcx. r8,0,r5 + bne- 0b +1: + +#ifdef CONFIG_PREEMPT + /* check current_thread_info->preempt_count */ lwz r0,TI_PREEMPT(r9) cmpwi 0,r0,0 /* if non-zero, just restore regs and return */ bne restore - lwz r0,TI_FLAGS(r9) - andi. r0,r0,_TIF_NEED_RESCHED + andi. r8,r8,_TIF_NEED_RESCHED beq+ restore + lwz r3,_MSR(r1) andi. r0,r3,MSR_EE /* interrupts off? */ beq restore /* don't schedule if so */ #ifdef CONFIG_TRACE_IRQFLAGS @@ -864,8 +917,6 @@ resume_kernel: */ bl trace_hardirqs_on #endif -#else -resume_kernel: #endif /* CONFIG_PREEMPT */ /* interrupts are hard-disabled at this point */ diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index b40e0b4815b3..56e0ff0878b5 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -370,6 +370,22 @@ _GLOBAL(ret_from_fork) li r3,0 b syscall_exit +_GLOBAL(ret_from_kernel_thread) + bl .schedule_tail + REST_NVGPRS(r1) + REST_GPR(2,r1) + mtlr r14 + mr r3,r15 + blrl + li r3,0 + b .do_exit # no return + +_GLOBAL(__ret_from_kernel_execve) + addi r1,r3,-STACK_FRAME_OVERHEAD + li r10,1 + std r10,SOFTE(r1) + b syscall_exit + .section ".toc","aw" DSCR_DEFAULT: .tc dscr_default[TC],dscr_default @@ -593,6 +609,41 @@ _GLOBAL(ret_from_except_lite) b .ret_from_except resume_kernel: + /* check current_thread_info, _TIF_EMULATE_STACK_STORE */ + CURRENT_THREAD_INFO(r9, r1) + ld r8,TI_FLAGS(r9) + andis. r8,r8,_TIF_EMULATE_STACK_STORE@h + beq+ 1f + + addi r8,r1,INT_FRAME_SIZE /* Get the kprobed function entry */ + + lwz r3,GPR1(r1) + subi r3,r3,INT_FRAME_SIZE /* dst: Allocate a trampoline exception frame */ + mr r4,r1 /* src: current exception frame */ + mr r1,r3 /* Reroute the trampoline frame to r1 */ + + /* Copy from the original to the trampoline. */ + li r5,INT_FRAME_SIZE/8 /* size: INT_FRAME_SIZE */ + li r6,0 /* start offset: 0 */ + mtctr r5 +2: ldx r0,r6,r4 + stdx r0,r6,r3 + addi r6,r6,8 + bdnz 2b + + /* Do real store operation to complete stwu */ + lwz r5,GPR1(r1) + std r8,0(r5) + + /* Clear _TIF_EMULATE_STACK_STORE flag */ + lis r11,_TIF_EMULATE_STACK_STORE@h + addi r5,r9,TI_FLAGS + ldarx r4,0,r5 + andc r4,r4,r11 + stdcx. r4,0,r5 + bne- 0b +1: + #ifdef CONFIG_PREEMPT /* Check if we need to preempt */ andi. r0,r4,_TIF_NEED_RESCHED diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index 98be7f0cd227..4684e33a26c3 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -25,6 +25,8 @@ #include <asm/ppc-opcode.h> #include <asm/mmu.h> #include <asm/hw_irq.h> +#include <asm/kvm_asm.h> +#include <asm/kvm_booke_hv_asm.h> /* XXX This will ultimately add space for a special exception save * structure used to save things like SRR0/SRR1, SPRGs, MAS, etc... @@ -35,16 +37,18 @@ #define SPECIAL_EXC_FRAME_SIZE INT_FRAME_SIZE /* Exception prolog code for all exceptions */ -#define EXCEPTION_PROLOG(n, type, addition) \ +#define EXCEPTION_PROLOG(n, intnum, type, addition) \ mtspr SPRN_SPRG_##type##_SCRATCH,r13; /* get spare registers */ \ mfspr r13,SPRN_SPRG_PACA; /* get PACA */ \ std r10,PACA_EX##type+EX_R10(r13); \ std r11,PACA_EX##type+EX_R11(r13); \ + PROLOG_STORE_RESTORE_SCRATCH_##type; \ mfcr r10; /* save CR */ \ + mfspr r11,SPRN_##type##_SRR1;/* what are we coming from */ \ + DO_KVM intnum,SPRN_##type##_SRR1; /* KVM hook */ \ + stw r10,PACA_EX##type+EX_CR(r13); /* save old CR in the PACA */ \ addition; /* additional code for that exc. */ \ std r1,PACA_EX##type+EX_R1(r13); /* save old r1 in the PACA */ \ - stw r10,PACA_EX##type+EX_CR(r13); /* save old CR in the PACA */ \ - mfspr r11,SPRN_##type##_SRR1;/* what are we coming from */ \ type##_SET_KSTACK; /* get special stack if necessary */\ andi. r10,r11,MSR_PR; /* save stack pointer */ \ beq 1f; /* branch around if supervisor */ \ @@ -59,6 +63,10 @@ #define SPRN_GEN_SRR0 SPRN_SRR0 #define SPRN_GEN_SRR1 SPRN_SRR1 +#define GDBELL_SET_KSTACK GEN_SET_KSTACK +#define SPRN_GDBELL_SRR0 SPRN_GSRR0 +#define SPRN_GDBELL_SRR1 SPRN_GSRR1 + #define CRIT_SET_KSTACK \ ld r1,PACA_CRIT_STACK(r13); \ subi r1,r1,SPECIAL_EXC_FRAME_SIZE; @@ -77,29 +85,46 @@ #define SPRN_MC_SRR0 SPRN_MCSRR0 #define SPRN_MC_SRR1 SPRN_MCSRR1 -#define NORMAL_EXCEPTION_PROLOG(n, addition) \ - EXCEPTION_PROLOG(n, GEN, addition##_GEN(n)) +#define NORMAL_EXCEPTION_PROLOG(n, intnum, addition) \ + EXCEPTION_PROLOG(n, intnum, GEN, addition##_GEN(n)) + +#define CRIT_EXCEPTION_PROLOG(n, intnum, addition) \ + EXCEPTION_PROLOG(n, intnum, CRIT, addition##_CRIT(n)) -#define CRIT_EXCEPTION_PROLOG(n, addition) \ - EXCEPTION_PROLOG(n, CRIT, addition##_CRIT(n)) +#define DBG_EXCEPTION_PROLOG(n, intnum, addition) \ + EXCEPTION_PROLOG(n, intnum, DBG, addition##_DBG(n)) -#define DBG_EXCEPTION_PROLOG(n, addition) \ - EXCEPTION_PROLOG(n, DBG, addition##_DBG(n)) +#define MC_EXCEPTION_PROLOG(n, intnum, addition) \ + EXCEPTION_PROLOG(n, intnum, MC, addition##_MC(n)) -#define MC_EXCEPTION_PROLOG(n, addition) \ - EXCEPTION_PROLOG(n, MC, addition##_MC(n)) +#define GDBELL_EXCEPTION_PROLOG(n, intnum, addition) \ + EXCEPTION_PROLOG(n, intnum, GDBELL, addition##_GDBELL(n)) +/* + * Store user-visible scratch in PACA exception slots and restore proper value + */ +#define PROLOG_STORE_RESTORE_SCRATCH_GEN +#define PROLOG_STORE_RESTORE_SCRATCH_GDBELL +#define PROLOG_STORE_RESTORE_SCRATCH_DBG +#define PROLOG_STORE_RESTORE_SCRATCH_MC + +#define PROLOG_STORE_RESTORE_SCRATCH_CRIT \ + mfspr r10,SPRN_SPRG_CRIT_SCRATCH; /* get r13 */ \ + std r10,PACA_EXCRIT+EX_R13(r13); \ + ld r11,PACA_SPRG3(r13); \ + mtspr SPRN_SPRG_CRIT_SCRATCH,r11; /* Variants of the "addition" argument for the prolog */ #define PROLOG_ADDITION_NONE_GEN(n) +#define PROLOG_ADDITION_NONE_GDBELL(n) #define PROLOG_ADDITION_NONE_CRIT(n) #define PROLOG_ADDITION_NONE_DBG(n) #define PROLOG_ADDITION_NONE_MC(n) #define PROLOG_ADDITION_MASKABLE_GEN(n) \ - lbz r11,PACASOFTIRQEN(r13); /* are irqs soft-disabled ? */ \ - cmpwi cr0,r11,0; /* yes -> go out of line */ \ + lbz r10,PACASOFTIRQEN(r13); /* are irqs soft-disabled ? */ \ + cmpwi cr0,r10,0; /* yes -> go out of line */ \ beq masked_interrupt_book3e_##n #define PROLOG_ADDITION_2REGS_GEN(n) \ @@ -233,9 +258,9 @@ exc_##n##_bad_stack: \ 1: -#define MASKABLE_EXCEPTION(trapnum, label, hdlr, ack) \ +#define MASKABLE_EXCEPTION(trapnum, intnum, label, hdlr, ack) \ START_EXCEPTION(label); \ - NORMAL_EXCEPTION_PROLOG(trapnum, PROLOG_ADDITION_MASKABLE) \ + NORMAL_EXCEPTION_PROLOG(trapnum, intnum, PROLOG_ADDITION_MASKABLE)\ EXCEPTION_COMMON(trapnum, PACA_EXGEN, INTS_DISABLE) \ ack(r8); \ CHECK_NAPPING(); \ @@ -286,7 +311,8 @@ interrupt_end_book3e: /* Critical Input Interrupt */ START_EXCEPTION(critical_input); - CRIT_EXCEPTION_PROLOG(0x100, PROLOG_ADDITION_NONE) + CRIT_EXCEPTION_PROLOG(0x100, BOOKE_INTERRUPT_CRITICAL, + PROLOG_ADDITION_NONE) // EXCEPTION_COMMON(0x100, PACA_EXCRIT, INTS_DISABLE) // bl special_reg_save_crit // CHECK_NAPPING(); @@ -297,7 +323,8 @@ interrupt_end_book3e: /* Machine Check Interrupt */ START_EXCEPTION(machine_check); - CRIT_EXCEPTION_PROLOG(0x200, PROLOG_ADDITION_NONE) + MC_EXCEPTION_PROLOG(0x200, BOOKE_INTERRUPT_MACHINE_CHECK, + PROLOG_ADDITION_NONE) // EXCEPTION_COMMON(0x200, PACA_EXMC, INTS_DISABLE) // bl special_reg_save_mc // addi r3,r1,STACK_FRAME_OVERHEAD @@ -308,7 +335,8 @@ interrupt_end_book3e: /* Data Storage Interrupt */ START_EXCEPTION(data_storage) - NORMAL_EXCEPTION_PROLOG(0x300, PROLOG_ADDITION_2REGS) + NORMAL_EXCEPTION_PROLOG(0x300, BOOKE_INTERRUPT_DATA_STORAGE, + PROLOG_ADDITION_2REGS) mfspr r14,SPRN_DEAR mfspr r15,SPRN_ESR EXCEPTION_COMMON(0x300, PACA_EXGEN, INTS_DISABLE) @@ -316,18 +344,21 @@ interrupt_end_book3e: /* Instruction Storage Interrupt */ START_EXCEPTION(instruction_storage); - NORMAL_EXCEPTION_PROLOG(0x400, PROLOG_ADDITION_2REGS) + NORMAL_EXCEPTION_PROLOG(0x400, BOOKE_INTERRUPT_INST_STORAGE, + PROLOG_ADDITION_2REGS) li r15,0 mr r14,r10 EXCEPTION_COMMON(0x400, PACA_EXGEN, INTS_DISABLE) b storage_fault_common /* External Input Interrupt */ - MASKABLE_EXCEPTION(0x500, external_input, .do_IRQ, ACK_NONE) + MASKABLE_EXCEPTION(0x500, BOOKE_INTERRUPT_EXTERNAL, + external_input, .do_IRQ, ACK_NONE) /* Alignment */ START_EXCEPTION(alignment); - NORMAL_EXCEPTION_PROLOG(0x600, PROLOG_ADDITION_2REGS) + NORMAL_EXCEPTION_PROLOG(0x600, BOOKE_INTERRUPT_ALIGNMENT, + PROLOG_ADDITION_2REGS) mfspr r14,SPRN_DEAR mfspr r15,SPRN_ESR EXCEPTION_COMMON(0x600, PACA_EXGEN, INTS_KEEP) @@ -335,7 +366,8 @@ interrupt_end_book3e: /* Program Interrupt */ START_EXCEPTION(program); - NORMAL_EXCEPTION_PROLOG(0x700, PROLOG_ADDITION_1REG) + NORMAL_EXCEPTION_PROLOG(0x700, BOOKE_INTERRUPT_PROGRAM, + PROLOG_ADDITION_1REG) mfspr r14,SPRN_ESR EXCEPTION_COMMON(0x700, PACA_EXGEN, INTS_DISABLE) std r14,_DSISR(r1) @@ -347,7 +379,8 @@ interrupt_end_book3e: /* Floating Point Unavailable Interrupt */ START_EXCEPTION(fp_unavailable); - NORMAL_EXCEPTION_PROLOG(0x800, PROLOG_ADDITION_NONE) + NORMAL_EXCEPTION_PROLOG(0x800, BOOKE_INTERRUPT_FP_UNAVAIL, + PROLOG_ADDITION_NONE) /* we can probably do a shorter exception entry for that one... */ EXCEPTION_COMMON(0x800, PACA_EXGEN, INTS_KEEP) ld r12,_MSR(r1) @@ -362,14 +395,17 @@ interrupt_end_book3e: b .ret_from_except /* Decrementer Interrupt */ - MASKABLE_EXCEPTION(0x900, decrementer, .timer_interrupt, ACK_DEC) + MASKABLE_EXCEPTION(0x900, BOOKE_INTERRUPT_DECREMENTER, + decrementer, .timer_interrupt, ACK_DEC) /* Fixed Interval Timer Interrupt */ - MASKABLE_EXCEPTION(0x980, fixed_interval, .unknown_exception, ACK_FIT) + MASKABLE_EXCEPTION(0x980, BOOKE_INTERRUPT_FIT, + fixed_interval, .unknown_exception, ACK_FIT) /* Watchdog Timer Interrupt */ START_EXCEPTION(watchdog); - CRIT_EXCEPTION_PROLOG(0x9f0, PROLOG_ADDITION_NONE) + CRIT_EXCEPTION_PROLOG(0x9f0, BOOKE_INTERRUPT_WATCHDOG, + PROLOG_ADDITION_NONE) // EXCEPTION_COMMON(0x9f0, PACA_EXCRIT, INTS_DISABLE) // bl special_reg_save_crit // CHECK_NAPPING(); @@ -388,7 +424,8 @@ interrupt_end_book3e: /* Auxiliary Processor Unavailable Interrupt */ START_EXCEPTION(ap_unavailable); - NORMAL_EXCEPTION_PROLOG(0xf20, PROLOG_ADDITION_NONE) + NORMAL_EXCEPTION_PROLOG(0xf20, BOOKE_INTERRUPT_AP_UNAVAIL, + PROLOG_ADDITION_NONE) EXCEPTION_COMMON(0xf20, PACA_EXGEN, INTS_DISABLE) bl .save_nvgprs addi r3,r1,STACK_FRAME_OVERHEAD @@ -397,7 +434,8 @@ interrupt_end_book3e: /* Debug exception as a critical interrupt*/ START_EXCEPTION(debug_crit); - CRIT_EXCEPTION_PROLOG(0xd00, PROLOG_ADDITION_2REGS) + CRIT_EXCEPTION_PROLOG(0xd00, BOOKE_INTERRUPT_DEBUG, + PROLOG_ADDITION_2REGS) /* * If there is a single step or branch-taken exception in an @@ -431,7 +469,7 @@ interrupt_end_book3e: mtcr r10 ld r10,PACA_EXCRIT+EX_R10(r13) /* restore registers */ ld r11,PACA_EXCRIT+EX_R11(r13) - mfspr r13,SPRN_SPRG_CRIT_SCRATCH + ld r13,PACA_EXCRIT+EX_R13(r13) rfci /* Normal debug exception */ @@ -444,7 +482,7 @@ interrupt_end_book3e: /* Now we mash up things to make it look like we are coming on a * normal exception */ - mfspr r15,SPRN_SPRG_CRIT_SCRATCH + ld r15,PACA_EXCRIT+EX_R13(r13) mtspr SPRN_SPRG_GEN_SCRATCH,r15 mfspr r14,SPRN_DBSR EXCEPTION_COMMON(0xd00, PACA_EXCRIT, INTS_DISABLE) @@ -462,7 +500,8 @@ kernel_dbg_exc: /* Debug exception as a debug interrupt*/ START_EXCEPTION(debug_debug); - DBG_EXCEPTION_PROLOG(0xd08, PROLOG_ADDITION_2REGS) + DBG_EXCEPTION_PROLOG(0xd00, BOOKE_INTERRUPT_DEBUG, + PROLOG_ADDITION_2REGS) /* * If there is a single step or branch-taken exception in an @@ -523,18 +562,21 @@ kernel_dbg_exc: b .ret_from_except START_EXCEPTION(perfmon); - NORMAL_EXCEPTION_PROLOG(0x260, PROLOG_ADDITION_NONE) + NORMAL_EXCEPTION_PROLOG(0x260, BOOKE_INTERRUPT_PERFORMANCE_MONITOR, + PROLOG_ADDITION_NONE) EXCEPTION_COMMON(0x260, PACA_EXGEN, INTS_DISABLE) addi r3,r1,STACK_FRAME_OVERHEAD bl .performance_monitor_exception b .ret_from_except_lite /* Doorbell interrupt */ - MASKABLE_EXCEPTION(0x280, doorbell, .doorbell_exception, ACK_NONE) + MASKABLE_EXCEPTION(0x280, BOOKE_INTERRUPT_DOORBELL, + doorbell, .doorbell_exception, ACK_NONE) /* Doorbell critical Interrupt */ START_EXCEPTION(doorbell_crit); - CRIT_EXCEPTION_PROLOG(0x2a0, PROLOG_ADDITION_NONE) + CRIT_EXCEPTION_PROLOG(0x2a0, BOOKE_INTERRUPT_DOORBELL_CRITICAL, + PROLOG_ADDITION_NONE) // EXCEPTION_COMMON(0x2a0, PACA_EXCRIT, INTS_DISABLE) // bl special_reg_save_crit // CHECK_NAPPING(); @@ -543,12 +585,24 @@ kernel_dbg_exc: // b ret_from_crit_except b . -/* Guest Doorbell */ - MASKABLE_EXCEPTION(0x2c0, guest_doorbell, .unknown_exception, ACK_NONE) +/* + * Guest doorbell interrupt + * This general exception use GSRRx save/restore registers + */ + START_EXCEPTION(guest_doorbell); + GDBELL_EXCEPTION_PROLOG(0x2c0, BOOKE_INTERRUPT_GUEST_DBELL, + PROLOG_ADDITION_NONE) + EXCEPTION_COMMON(0x2c0, PACA_EXGEN, INTS_KEEP) + addi r3,r1,STACK_FRAME_OVERHEAD + bl .save_nvgprs + INTS_RESTORE_HARD + bl .unknown_exception + b .ret_from_except /* Guest Doorbell critical Interrupt */ START_EXCEPTION(guest_doorbell_crit); - CRIT_EXCEPTION_PROLOG(0x2e0, PROLOG_ADDITION_NONE) + CRIT_EXCEPTION_PROLOG(0x2e0, BOOKE_INTERRUPT_GUEST_DBELL_CRIT, + PROLOG_ADDITION_NONE) // EXCEPTION_COMMON(0x2e0, PACA_EXCRIT, INTS_DISABLE) // bl special_reg_save_crit // CHECK_NAPPING(); @@ -559,7 +613,8 @@ kernel_dbg_exc: /* Hypervisor call */ START_EXCEPTION(hypercall); - NORMAL_EXCEPTION_PROLOG(0x310, PROLOG_ADDITION_NONE) + NORMAL_EXCEPTION_PROLOG(0x310, BOOKE_INTERRUPT_HV_SYSCALL, + PROLOG_ADDITION_NONE) EXCEPTION_COMMON(0x310, PACA_EXGEN, INTS_KEEP) addi r3,r1,STACK_FRAME_OVERHEAD bl .save_nvgprs @@ -569,7 +624,8 @@ kernel_dbg_exc: /* Embedded Hypervisor priviledged */ START_EXCEPTION(ehpriv); - NORMAL_EXCEPTION_PROLOG(0x320, PROLOG_ADDITION_NONE) + NORMAL_EXCEPTION_PROLOG(0x320, BOOKE_INTERRUPT_HV_PRIV, + PROLOG_ADDITION_NONE) EXCEPTION_COMMON(0x320, PACA_EXGEN, INTS_KEEP) addi r3,r1,STACK_FRAME_OVERHEAD bl .save_nvgprs @@ -582,44 +638,42 @@ kernel_dbg_exc: * accordingly and if the interrupt is level sensitive, we hard disable */ +.macro masked_interrupt_book3e paca_irq full_mask + lbz r10,PACAIRQHAPPENED(r13) + ori r10,r10,\paca_irq + stb r10,PACAIRQHAPPENED(r13) + + .if \full_mask == 1 + rldicl r10,r11,48,1 /* clear MSR_EE */ + rotldi r11,r10,16 + mtspr SPRN_SRR1,r11 + .endif + + lwz r11,PACA_EXGEN+EX_CR(r13) + mtcr r11 + ld r10,PACA_EXGEN+EX_R10(r13) + ld r11,PACA_EXGEN+EX_R11(r13) + mfspr r13,SPRN_SPRG_GEN_SCRATCH + rfi + b . +.endm + masked_interrupt_book3e_0x500: - /* XXX When adding support for EPR, use PACA_IRQ_EE_EDGE */ - li r11,PACA_IRQ_EE - b masked_interrupt_book3e_full_mask + // XXX When adding support for EPR, use PACA_IRQ_EE_EDGE + masked_interrupt_book3e PACA_IRQ_EE 1 masked_interrupt_book3e_0x900: - ACK_DEC(r11); - li r11,PACA_IRQ_DEC - b masked_interrupt_book3e_no_mask + ACK_DEC(r10); + masked_interrupt_book3e PACA_IRQ_DEC 0 + masked_interrupt_book3e_0x980: - ACK_FIT(r11); - li r11,PACA_IRQ_DEC - b masked_interrupt_book3e_no_mask + ACK_FIT(r10); + masked_interrupt_book3e PACA_IRQ_DEC 0 + masked_interrupt_book3e_0x280: masked_interrupt_book3e_0x2c0: - li r11,PACA_IRQ_DBELL - b masked_interrupt_book3e_no_mask + masked_interrupt_book3e PACA_IRQ_DBELL 0 -masked_interrupt_book3e_no_mask: - mtcr r10 - lbz r10,PACAIRQHAPPENED(r13) - or r10,r10,r11 - stb r10,PACAIRQHAPPENED(r13) - b 1f -masked_interrupt_book3e_full_mask: - mtcr r10 - lbz r10,PACAIRQHAPPENED(r13) - or r10,r10,r11 - stb r10,PACAIRQHAPPENED(r13) - mfspr r10,SPRN_SRR1 - rldicl r11,r10,48,1 /* clear MSR_EE */ - rotldi r10,r11,16 - mtspr SPRN_SRR1,r10 -1: ld r10,PACA_EXGEN+EX_R10(r13); - ld r11,PACA_EXGEN+EX_R11(r13); - mfspr r13,SPRN_SPRG_GEN_SCRATCH; - rfi - b . /* * Called from arch_local_irq_enable when an interrupt needs * to be resent. r3 contains either 0x500,0x900,0x260 or 0x280 @@ -1302,25 +1356,11 @@ _GLOBAL(setup_perfmon_ivor) _GLOBAL(setup_doorbell_ivors) SET_IVOR(36, 0x280) /* Processor Doorbell */ SET_IVOR(37, 0x2a0) /* Processor Doorbell Crit */ - - /* Check MMUCFG[LPIDSIZE] to determine if we have category E.HV */ - mfspr r10,SPRN_MMUCFG - rlwinm. r10,r10,0,MMUCFG_LPIDSIZE - beqlr - - SET_IVOR(38, 0x2c0) /* Guest Processor Doorbell */ - SET_IVOR(39, 0x2e0) /* Guest Processor Doorbell Crit/MC */ blr _GLOBAL(setup_ehv_ivors) - /* - * We may be running as a guest and lack E.HV even on a chip - * that normally has it. - */ - mfspr r10,SPRN_MMUCFG - rlwinm. r10,r10,0,MMUCFG_LPIDSIZE - beqlr - SET_IVOR(40, 0x300) /* Embedded Hypervisor System Call */ SET_IVOR(41, 0x320) /* Embedded Hypervisor Privilege */ + SET_IVOR(38, 0x2c0) /* Guest Processor Doorbell */ + SET_IVOR(39, 0x2e0) /* Guest Processor Doorbell Crit/MC */ blr diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 39aa97d3ff88..10b658ad65e1 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -275,6 +275,31 @@ vsx_unavailable_pSeries_1: STD_EXCEPTION_PSERIES(0x1300, 0x1300, instruction_breakpoint) KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_STD, 0x1300) + . = 0x1500 + .global denorm_Hypervisor +denorm_exception_hv: + HMT_MEDIUM + mtspr SPRN_SPRG_HSCRATCH0,r13 + mfspr r13,SPRN_SPRG_HPACA + std r9,PACA_EXGEN+EX_R9(r13) + std r10,PACA_EXGEN+EX_R10(r13) + std r11,PACA_EXGEN+EX_R11(r13) + std r12,PACA_EXGEN+EX_R12(r13) + mfspr r9,SPRN_SPRG_HSCRATCH0 + std r9,PACA_EXGEN+EX_R13(r13) + mfcr r9 + +#ifdef CONFIG_PPC_DENORMALISATION + mfspr r10,SPRN_HSRR1 + mfspr r11,SPRN_HSRR0 /* save HSRR0 */ + andis. r10,r10,(HSRR1_DENORM)@h /* denorm? */ + addi r11,r11,-4 /* HSRR0 is next instruction */ + bne+ denorm_assist +#endif + + EXCEPTION_PROLOG_PSERIES_1(denorm_common, EXC_HV) + KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x1500) + #ifdef CONFIG_CBE_RAS STD_EXCEPTION_HV(0x1600, 0x1602, cbe_maintenance) KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1602) @@ -336,6 +361,103 @@ do_stab_bolted_pSeries: KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x900) KVM_HANDLER(PACA_EXGEN, EXC_HV, 0x982) +#ifdef CONFIG_PPC_DENORMALISATION +denorm_assist: +BEGIN_FTR_SECTION +/* + * To denormalise we need to move a copy of the register to itself. + * For POWER6 do that here for all FP regs. + */ + mfmsr r10 + ori r10,r10,(MSR_FP|MSR_FE0|MSR_FE1) + xori r10,r10,(MSR_FE0|MSR_FE1) + mtmsrd r10 + sync + fmr 0,0 + fmr 1,1 + fmr 2,2 + fmr 3,3 + fmr 4,4 + fmr 5,5 + fmr 6,6 + fmr 7,7 + fmr 8,8 + fmr 9,9 + fmr 10,10 + fmr 11,11 + fmr 12,12 + fmr 13,13 + fmr 14,14 + fmr 15,15 + fmr 16,16 + fmr 17,17 + fmr 18,18 + fmr 19,19 + fmr 20,20 + fmr 21,21 + fmr 22,22 + fmr 23,23 + fmr 24,24 + fmr 25,25 + fmr 26,26 + fmr 27,27 + fmr 28,28 + fmr 29,29 + fmr 30,30 + fmr 31,31 +FTR_SECTION_ELSE +/* + * To denormalise we need to move a copy of the register to itself. + * For POWER7 do that here for the first 32 VSX registers only. + */ + mfmsr r10 + oris r10,r10,MSR_VSX@h + mtmsrd r10 + sync + XVCPSGNDP(0,0,0) + XVCPSGNDP(1,1,1) + XVCPSGNDP(2,2,2) + XVCPSGNDP(3,3,3) + XVCPSGNDP(4,4,4) + XVCPSGNDP(5,5,5) + XVCPSGNDP(6,6,6) + XVCPSGNDP(7,7,7) + XVCPSGNDP(8,8,8) + XVCPSGNDP(9,9,9) + XVCPSGNDP(10,10,10) + XVCPSGNDP(11,11,11) + XVCPSGNDP(12,12,12) + XVCPSGNDP(13,13,13) + XVCPSGNDP(14,14,14) + XVCPSGNDP(15,15,15) + XVCPSGNDP(16,16,16) + XVCPSGNDP(17,17,17) + XVCPSGNDP(18,18,18) + XVCPSGNDP(19,19,19) + XVCPSGNDP(20,20,20) + XVCPSGNDP(21,21,21) + XVCPSGNDP(22,22,22) + XVCPSGNDP(23,23,23) + XVCPSGNDP(24,24,24) + XVCPSGNDP(25,25,25) + XVCPSGNDP(26,26,26) + XVCPSGNDP(27,27,27) + XVCPSGNDP(28,28,28) + XVCPSGNDP(29,29,29) + XVCPSGNDP(30,30,30) + XVCPSGNDP(31,31,31) +ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_206) + mtspr SPRN_HSRR0,r11 + mtcrf 0x80,r9 + ld r9,PACA_EXGEN+EX_R9(r13) + ld r10,PACA_EXGEN+EX_R10(r13) + ld r11,PACA_EXGEN+EX_R11(r13) + ld r12,PACA_EXGEN+EX_R12(r13) + ld r13,PACA_EXGEN+EX_R13(r13) + HRFID + b . +#endif + .align 7 /* moved from 0xe00 */ STD_EXCEPTION_HV(., 0xe02, h_data_storage) @@ -495,6 +617,7 @@ machine_check_common: STD_EXCEPTION_COMMON(0xe60, hmi_exception, .unknown_exception) STD_EXCEPTION_COMMON_ASYNC(0xf00, performance_monitor, .performance_monitor_exception) STD_EXCEPTION_COMMON(0x1300, instruction_breakpoint, .instruction_breakpoint_exception) + STD_EXCEPTION_COMMON(0x1502, denorm, .unknown_exception) #ifdef CONFIG_ALTIVEC STD_EXCEPTION_COMMON(0x1700, altivec_assist, .altivec_assist_exception) #else @@ -960,7 +1083,9 @@ _GLOBAL(do_stab_bolted) rldimi r10,r11,7,52 /* r10 = first ste of the group */ /* Calculate VSID */ - /* This is a kernel address, so protovsid = ESID */ + /* This is a kernel address, so protovsid = ESID | 1 << 37 */ + li r9,0x1 + rldimi r11,r9,(CONTEXT_BITS + USER_ESID_BITS),0 ASM_VSID_SCRAMBLE(r11, r9, 256M) rldic r9,r11,12,16 /* r9 = vsid << 12 */ diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index 18bdf74fa164..06c8202a69cf 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -289,8 +289,7 @@ int __init fadump_reserve_mem(void) else memory_limit = memblock_end_of_DRAM(); printk(KERN_INFO "Adjusted memory_limit for firmware-assisted" - " dump, now %#016llx\n", - (unsigned long long)memory_limit); + " dump, now %#016llx\n", memory_limit); } if (memory_limit) memory_boundary = memory_limit; diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S index 0f59863c3ade..6f62a737f607 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -895,15 +895,11 @@ _GLOBAL(__setup_e500mc_ivors) mtspr SPRN_IVOR36,r3 li r3,CriticalDoorbell@l mtspr SPRN_IVOR37,r3 + sync + blr - /* - * We only want to touch IVOR38-41 if we're running on hardware - * that supports category E.HV. The architectural way to determine - * this is MMUCFG[LPIDSIZE]. - */ - mfspr r3, SPRN_MMUCFG - andis. r3, r3, MMUCFG_LPIDSIZE@h - beq no_hv +/* setup ehv ivors for */ +_GLOBAL(__setup_ehv_ivors) li r3,GuestDoorbell@l mtspr SPRN_IVOR38,r3 li r3,CriticalGuestDoorbell@l @@ -912,14 +908,8 @@ _GLOBAL(__setup_e500mc_ivors) mtspr SPRN_IVOR40,r3 li r3,Ehvpriv@l mtspr SPRN_IVOR41,r3 -skip_hv_ivors: sync blr -no_hv: - lwz r3, CPU_SPEC_FEATURES(r5) - rlwinm r3, r3, 0, ~CPU_FTR_EMB_HV - stw r3, CPU_SPEC_FEATURES(r5) - b skip_hv_ivors #ifdef CONFIG_SPE /* @@ -1043,6 +1033,34 @@ _GLOBAL(flush_dcache_L1) blr +/* Flush L1 d-cache, invalidate and disable d-cache and i-cache */ +_GLOBAL(__flush_disable_L1) + mflr r10 + bl flush_dcache_L1 /* Flush L1 d-cache */ + mtlr r10 + + mfspr r4, SPRN_L1CSR0 /* Invalidate and disable d-cache */ + li r5, 2 + rlwimi r4, r5, 0, 3 + + msync + isync + mtspr SPRN_L1CSR0, r4 + isync + +1: mfspr r4, SPRN_L1CSR0 /* Wait for the invalidate to finish */ + andi. r4, r4, 2 + bne 1b + + mfspr r4, SPRN_L1CSR1 /* Invalidate and disable i-cache */ + li r5, 2 + rlwimi r4, r5, 0, 3 + + mtspr SPRN_L1CSR1, r4 + isync + + blr + #ifdef CONFIG_SMP /* When we get here, r24 needs to hold the CPU # */ .globl __secondary_start diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index 956a4c496de9..a89cae481b04 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -73,7 +73,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp) * If so, DABR will be populated in single_step_dabr_instruction(). */ if (current->thread.last_hit_ubp != bp) - set_dabr(info->address | info->type | DABR_TRANSLATION); + set_dabr(info->address | info->type | DABR_TRANSLATION, info->dabrx); return 0; } @@ -97,7 +97,7 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp) } *slot = NULL; - set_dabr(0); + set_dabr(0, 0); } /* @@ -170,6 +170,13 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) info->address = bp->attr.bp_addr; info->len = bp->attr.bp_len; + info->dabrx = DABRX_ALL; + if (bp->attr.exclude_user) + info->dabrx &= ~DABRX_USER; + if (bp->attr.exclude_kernel) + info->dabrx &= ~DABRX_KERNEL; + if (bp->attr.exclude_hv) + info->dabrx &= ~DABRX_HYP; /* * Since breakpoint length can be a maximum of HW_BREAKPOINT_LEN(8) @@ -197,7 +204,7 @@ void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs) info = counter_arch_bp(tsk->thread.last_hit_ubp); regs->msr &= ~MSR_SE; - set_dabr(info->address | info->type | DABR_TRANSLATION); + set_dabr(info->address | info->type | DABR_TRANSLATION, info->dabrx); tsk->thread.last_hit_ubp = NULL; } @@ -215,7 +222,7 @@ int __kprobes hw_breakpoint_handler(struct die_args *args) unsigned long dar = regs->dar; /* Disable breakpoints during exception handling */ - set_dabr(0); + set_dabr(0, 0); /* * The counter may be concurrently released but that can only @@ -281,7 +288,7 @@ int __kprobes hw_breakpoint_handler(struct die_args *args) if (!info->extraneous_interrupt) perf_bp_event(bp, regs); - set_dabr(info->address | info->type | DABR_TRANSLATION); + set_dabr(info->address | info->type | DABR_TRANSLATION, info->dabrx); out: rcu_read_unlock(); return rc; @@ -294,7 +301,7 @@ int __kprobes single_step_dabr_instruction(struct die_args *args) { struct pt_regs *regs = args->regs; struct perf_event *bp = NULL; - struct arch_hw_breakpoint *bp_info; + struct arch_hw_breakpoint *info; bp = current->thread.last_hit_ubp; /* @@ -304,16 +311,16 @@ int __kprobes single_step_dabr_instruction(struct die_args *args) if (!bp) return NOTIFY_DONE; - bp_info = counter_arch_bp(bp); + info = counter_arch_bp(bp); /* * We shall invoke the user-defined callback function in the single * stepping handler to confirm to 'trigger-after-execute' semantics */ - if (!bp_info->extraneous_interrupt) + if (!info->extraneous_interrupt) perf_bp_event(bp, regs); - set_dabr(bp_info->address | bp_info->type | DABR_TRANSLATION); + set_dabr(info->address | info->type | DABR_TRANSLATION, info->dabrx); current->thread.last_hit_ubp = NULL; /* diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c index b01d14eeca8d..8220baa46faf 100644 --- a/arch/powerpc/kernel/ibmebus.c +++ b/arch/powerpc/kernel/ibmebus.c @@ -47,7 +47,6 @@ #include <linux/stat.h> #include <linux/of_platform.h> #include <asm/ibmebus.h> -#include <asm/abs_addr.h> static struct device ibmebus_bus_device = { /* fake "parent" device */ .init_name = "ibmebus", diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index ff5a6ce027b8..8226c6cb348a 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -215,7 +215,8 @@ static unsigned long iommu_range_alloc(struct device *dev, spin_lock_irqsave(&(pool->lock), flags); again: - if ((pass == 0) && handle && *handle) + if ((pass == 0) && handle && *handle && + (*handle >= pool->start) && (*handle < pool->end)) start = *handle; else start = pool->hint; @@ -236,7 +237,9 @@ again: * but on second pass, start at 0 in pool 0. */ if ((start & mask) >= limit || pass > 0) { + spin_unlock(&(pool->lock)); pool = &(tbl->pools[0]); + spin_lock(&(pool->lock)); start = pool->start; } else { start &= mask; diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 1f017bb7a7ce..71413f41278f 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -489,10 +489,10 @@ void do_IRQ(struct pt_regs *regs) struct pt_regs *old_regs = set_irq_regs(regs); unsigned int irq; - trace_irq_entry(regs); - irq_enter(); + trace_irq_entry(regs); + check_stack_overflow(); /* @@ -511,10 +511,10 @@ void do_IRQ(struct pt_regs *regs) else __get_cpu_var(irq_stat).spurious_irqs++; + trace_irq_exit(regs); + irq_exit(); set_irq_regs(old_regs); - - trace_irq_exit(regs); } void __init init_IRQ(void) diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c index 5df777794403..fa9f6c72f557 100644 --- a/arch/powerpc/kernel/machine_kexec.c +++ b/arch/powerpc/kernel/machine_kexec.c @@ -165,7 +165,7 @@ void __init reserve_crashkernel(void) if (memory_limit && memory_limit <= crashk_res.end) { memory_limit = crashk_res.end + 1; printk("Adjusted memory limit for crashkernel, now 0x%llx\n", - (unsigned long long)memory_limit); + memory_limit); } printk(KERN_INFO "Reserving %ldMB of memory at %ldMB " @@ -204,6 +204,12 @@ static struct property crashk_size_prop = { .value = &crashk_size, }; +static struct property memory_limit_prop = { + .name = "linux,memory-limit", + .length = sizeof(unsigned long long), + .value = &memory_limit, +}; + static void __init export_crashk_values(struct device_node *node) { struct property *prop; @@ -223,6 +229,12 @@ static void __init export_crashk_values(struct device_node *node) crashk_size = resource_size(&crashk_res); prom_add_property(node, &crashk_size_prop); } + + /* + * memory_limit is required by the kexec-tools to limit the + * crash regions to the actual memory used. + */ + prom_update_property(node, &memory_limit_prop); } static int __init kexec_setup(void) diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S index ba16874fe294..7ce26d45777e 100644 --- a/arch/powerpc/kernel/misc.S +++ b/arch/powerpc/kernel/misc.S @@ -54,13 +54,6 @@ _GLOBAL(add_reloc_offset) .align 3 2: PPC_LONG 1b -_GLOBAL(kernel_execve) - li r0,__NR_execve - sc - bnslr - neg r3,r3 - blr - _GLOBAL(setjmp) mflr r0 PPC_STL r0,0(r3) diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 407e293aad2f..19e096bd0e73 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -663,39 +663,6 @@ _GLOBAL(abs) sub r3,r3,r4 blr -/* - * Create a kernel thread - * kernel_thread(fn, arg, flags) - */ -_GLOBAL(kernel_thread) - stwu r1,-16(r1) - stw r30,8(r1) - stw r31,12(r1) - mr r30,r3 /* function */ - mr r31,r4 /* argument */ - ori r3,r5,CLONE_VM /* flags */ - oris r3,r3,CLONE_UNTRACED>>16 - li r4,0 /* new sp (unused) */ - li r0,__NR_clone - sc - bns+ 1f /* did system call indicate error? */ - neg r3,r3 /* if so, make return code negative */ -1: cmpwi 0,r3,0 /* parent or child? */ - bne 2f /* return if parent */ - li r0,0 /* make top-level stack frame */ - stwu r0,-16(r1) - mtlr r30 /* fn addr in lr */ - mr r3,r31 /* load arg and call fn */ - PPC440EP_ERR42 - blrl - li r0,__NR_exit /* exit if function returns */ - li r3,0 - sc -2: lwz r30,8(r1) - lwz r31,12(r1) - addi r1,r1,16 - blr - #ifdef CONFIG_SMP _GLOBAL(start_secondary_resume) /* Reset stack */ diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index 565b78625a32..5cfa8008693b 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -407,40 +407,6 @@ _GLOBAL(scom970_write) /* - * Create a kernel thread - * kernel_thread(fn, arg, flags) - */ -_GLOBAL(kernel_thread) - std r29,-24(r1) - std r30,-16(r1) - stdu r1,-STACK_FRAME_OVERHEAD(r1) - mr r29,r3 - mr r30,r4 - ori r3,r5,CLONE_VM /* flags */ - oris r3,r3,(CLONE_UNTRACED>>16) - li r4,0 /* new sp (unused) */ - li r0,__NR_clone - sc - bns+ 1f /* did system call indicate error? */ - neg r3,r3 /* if so, make return code negative */ -1: cmpdi 0,r3,0 /* parent or child? */ - bne 2f /* return if parent */ - li r0,0 - stdu r0,-STACK_FRAME_OVERHEAD(r1) - ld r2,8(r29) - ld r29,0(r29) - mtlr r29 /* fn addr in lr */ - mr r3,r30 /* load arg and call fn */ - blrl - li r0,__NR_exit /* exit after child exits */ - li r3,0 - sc -2: addi r1,r1,STACK_FRAME_OVERHEAD - ld r29,-24(r1) - ld r30,-16(r1) - blr - -/* * disable_kernel_fp() * Disable the FPU. */ diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index fbe1a12dc7f1..cd6da855090c 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -142,6 +142,7 @@ void __init initialise_paca(struct paca_struct *new_paca, int cpu) new_paca->hw_cpu_id = 0xffff; new_paca->kexec_state = KEXEC_STATE_NONE; new_paca->__current = &init_task; + new_paca->data_offset = 0xfeeeeeeeeeeeeeeeULL; #ifdef CONFIG_PPC_STD_MMU_64 new_paca->slb_shadow_ptr = &slb_shadow[cpu]; #endif /* CONFIG_PPC_STD_MMU_64 */ diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 2aa04f29e1de..7f94f760dd0c 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -99,6 +99,26 @@ void pcibios_free_controller(struct pci_controller *phb) kfree(phb); } +/* + * The function is used to return the minimal alignment + * for memory or I/O windows of the associated P2P bridge. + * By default, 4KiB alignment for I/O windows and 1MiB for + * memory windows. + */ +resource_size_t pcibios_window_alignment(struct pci_bus *bus, + unsigned long type) +{ + if (ppc_md.pcibios_window_alignment) + return ppc_md.pcibios_window_alignment(bus, type); + + /* + * PCI core will figure out the default + * alignment: 4KiB for I/O and 1MiB for + * memory window. + */ + return 1; +} + static resource_size_t pcibios_io_size(const struct pci_controller *hose) { #ifdef CONFIG_PPC64 @@ -960,13 +980,14 @@ static void __devinit pcibios_fixup_bridge(struct pci_bus *bus) if (i >= 3 && bus->self->transparent) continue; - /* If we are going to re-assign everything, mark the resource - * as unset and move it down to 0 + /* If we're going to reassign everything, we can + * shrink the P2P resource to have size as being + * of 0 in order to save space. */ if (pci_has_flag(PCI_REASSIGN_ALL_RSRC)) { res->flags |= IORESOURCE_UNSET; - res->end -= res->start; res->start = 0; + res->end = -1; continue; } @@ -1228,7 +1249,14 @@ void pcibios_allocate_bus_resources(struct pci_bus *bus) pr_warning("PCI: Cannot allocate resource region " "%d of PCI bridge %d, will remap\n", i, bus->number); clear_resource: - res->start = res->end = 0; + /* The resource might be figured out when doing + * reassignment based on the resources required + * by the downstream PCI devices. Here we set + * the size of the resource to be 0 in order to + * save more space. + */ + res->start = 0; + res->end = -1; res->flags = 0; } diff --git a/arch/powerpc/kernel/ppc32.h b/arch/powerpc/kernel/ppc32.h index dc16aefe1dd0..02fb0ee26093 100644 --- a/arch/powerpc/kernel/ppc32.h +++ b/arch/powerpc/kernel/ppc32.h @@ -16,57 +16,6 @@ /* These are here to support 32-bit syscalls on a 64-bit kernel. */ -typedef struct compat_siginfo { - int si_signo; - int si_errno; - int si_code; - - union { - int _pad[SI_PAD_SIZE32]; - - /* kill() */ - struct { - compat_pid_t _pid; /* sender's pid */ - compat_uid_t _uid; /* sender's uid */ - } _kill; - - /* POSIX.1b timers */ - struct { - compat_timer_t _tid; /* timer id */ - int _overrun; /* overrun count */ - compat_sigval_t _sigval; /* same as below */ - int _sys_private; /* not to be passed to user */ - } _timer; - - /* POSIX.1b signals */ - struct { - compat_pid_t _pid; /* sender's pid */ - compat_uid_t _uid; /* sender's uid */ - compat_sigval_t _sigval; - } _rt; - - /* SIGCHLD */ - struct { - compat_pid_t _pid; /* which child */ - compat_uid_t _uid; /* sender's uid */ - int _status; /* exit code */ - compat_clock_t _utime; - compat_clock_t _stime; - } _sigchld; - - /* SIGILL, SIGFPE, SIGSEGV, SIGBUS, SIGEMT */ - struct { - unsigned int _addr; /* faulting insn/memory ref. */ - } _sigfault; - - /* SIGPOLL */ - struct { - int _band; /* POLL_IN, POLL_OUT, POLL_MSG */ - int _fd; - } _sigpoll; - } _sifields; -} compat_siginfo_t; - #define __old_sigaction32 old_sigaction32 struct __old_sigaction32 { diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index 3e4031581c65..19e4288d8486 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -94,7 +94,6 @@ EXPORT_SYMBOL(pci_dram_offset); #endif /* CONFIG_PCI */ EXPORT_SYMBOL(start_thread); -EXPORT_SYMBOL(kernel_thread); EXPORT_SYMBOL(giveup_fpu); #ifdef CONFIG_ALTIVEC diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 1a1f2ddfb581..ba48233500f6 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -258,6 +258,7 @@ void do_send_trap(struct pt_regs *regs, unsigned long address, { siginfo_t info; + current->thread.trap_nr = signal_code; if (notify_die(DIE_DABR_MATCH, "dabr_match", regs, error_code, 11, SIGSEGV) == NOTIFY_STOP) return; @@ -275,6 +276,7 @@ void do_dabr(struct pt_regs *regs, unsigned long address, { siginfo_t info; + current->thread.trap_nr = TRAP_HWBKPT; if (notify_die(DIE_DABR_MATCH, "dabr_match", regs, error_code, 11, SIGSEGV) == NOTIFY_STOP) return; @@ -283,7 +285,7 @@ void do_dabr(struct pt_regs *regs, unsigned long address, return; /* Clear the DABR */ - set_dabr(0); + set_dabr(0, 0); /* Deliver the signal to userspace */ info.si_signo = SIGTRAP; @@ -364,18 +366,19 @@ static void set_debug_reg_defaults(struct thread_struct *thread) { if (thread->dabr) { thread->dabr = 0; - set_dabr(0); + thread->dabrx = 0; + set_dabr(0, 0); } } #endif /* !CONFIG_HAVE_HW_BREAKPOINT */ #endif /* CONFIG_PPC_ADV_DEBUG_REGS */ -int set_dabr(unsigned long dabr) +int set_dabr(unsigned long dabr, unsigned long dabrx) { __get_cpu_var(current_dabr) = dabr; if (ppc_md.set_dabr) - return ppc_md.set_dabr(dabr); + return ppc_md.set_dabr(dabr, dabrx); /* XXX should we have a CPU_FTR_HAS_DABR ? */ #ifdef CONFIG_PPC_ADV_DEBUG_REGS @@ -385,9 +388,8 @@ int set_dabr(unsigned long dabr) #endif #elif defined(CONFIG_PPC_BOOK3S) mtspr(SPRN_DABR, dabr); + mtspr(SPRN_DABRX, dabrx); #endif - - return 0; } @@ -480,7 +482,7 @@ struct task_struct *__switch_to(struct task_struct *prev, */ #ifndef CONFIG_HAVE_HW_BREAKPOINT if (unlikely(__get_cpu_var(current_dabr) != new->thread.dabr)) - set_dabr(new->thread.dabr); + set_dabr(new->thread.dabr, new->thread.dabrx); #endif /* CONFIG_HAVE_HW_BREAKPOINT */ #endif @@ -514,9 +516,6 @@ struct task_struct *__switch_to(struct task_struct *prev, local_irq_save(flags); - account_system_vtime(current); - account_process_vtime(current); - /* * We can't take a PMU exception inside _switch() since there is a * window where the kernel stack SLB and the kernel stack are out @@ -734,30 +733,39 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) extern unsigned long dscr_default; /* defined in arch/powerpc/kernel/sysfs.c */ int copy_thread(unsigned long clone_flags, unsigned long usp, - unsigned long unused, struct task_struct *p, + unsigned long arg, struct task_struct *p, struct pt_regs *regs) { struct pt_regs *childregs, *kregs; extern void ret_from_fork(void); + extern void ret_from_kernel_thread(void); + void (*f)(void); unsigned long sp = (unsigned long)task_stack_page(p) + THREAD_SIZE; - CHECK_FULL_REGS(regs); /* Copy registers */ sp -= sizeof(struct pt_regs); childregs = (struct pt_regs *) sp; - *childregs = *regs; - if ((childregs->msr & MSR_PR) == 0) { + if (!regs) { /* for kernel thread, set `current' and stackptr in new task */ + memset(childregs, 0, sizeof(struct pt_regs)); childregs->gpr[1] = sp + sizeof(struct pt_regs); -#ifdef CONFIG_PPC32 - childregs->gpr[2] = (unsigned long) p; -#else +#ifdef CONFIG_PPC64 + childregs->gpr[14] = *(unsigned long *)usp; + childregs->gpr[2] = ((unsigned long *)usp)[1], clear_tsk_thread_flag(p, TIF_32BIT); +#else + childregs->gpr[14] = usp; /* function */ + childregs->gpr[2] = (unsigned long) p; #endif + childregs->gpr[15] = arg; p->thread.regs = NULL; /* no user register state */ + f = ret_from_kernel_thread; } else { + CHECK_FULL_REGS(regs); + *childregs = *regs; childregs->gpr[1] = usp; p->thread.regs = childregs; + childregs->gpr[3] = 0; /* Result from fork() */ if (clone_flags & CLONE_SETTLS) { #ifdef CONFIG_PPC64 if (!is_32bit_task()) @@ -766,8 +774,9 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, #endif childregs->gpr[2] = childregs->gpr[6]; } + + f = ret_from_fork; } - childregs->gpr[3] = 0; /* Result from fork() */ sp -= STACK_FRAME_OVERHEAD; /* @@ -806,19 +815,17 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, p->thread.dscr = current->thread.dscr; } #endif - /* * The PPC64 ABI makes use of a TOC to contain function * pointers. The function (ret_from_except) is actually a pointer * to the TOC entry. The first entry is a pointer to the actual * function. - */ + */ #ifdef CONFIG_PPC64 - kregs->nip = *((unsigned long *)ret_from_fork); + kregs->nip = *((unsigned long *)f); #else - kregs->nip = (unsigned long)ret_from_fork; + kregs->nip = (unsigned long)f; #endif - return 0; } @@ -1056,26 +1063,13 @@ int sys_vfork(unsigned long p1, unsigned long p2, unsigned long p3, regs, 0, NULL, NULL); } -int sys_execve(unsigned long a0, unsigned long a1, unsigned long a2, - unsigned long a3, unsigned long a4, unsigned long a5, - struct pt_regs *regs) +void __ret_from_kernel_execve(struct pt_regs *normal) +__noreturn; + +void ret_from_kernel_execve(struct pt_regs *normal) { - int error; - char *filename; - - filename = getname((const char __user *) a0); - error = PTR_ERR(filename); - if (IS_ERR(filename)) - goto out; - flush_fp_to_thread(current); - flush_altivec_to_thread(current); - flush_spe_to_thread(current); - error = do_execve(filename, - (const char __user *const __user *) a1, - (const char __user *const __user *) a2, regs); - putname(filename); -out: - return error; + set_thread_flag(TIF_RESTOREALL); + __ret_from_kernel_execve(normal); } static inline int valid_irq_stack(unsigned long sp, struct task_struct *p, diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index f191bf02943a..37725e86651e 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -78,7 +78,7 @@ static int __init early_parse_mem(char *p) return 1; memory_limit = PAGE_ALIGN(memparse(p, &p)); - DBG("memory limit = 0x%llx\n", (unsigned long long)memory_limit); + DBG("memory limit = 0x%llx\n", memory_limit); return 0; } @@ -661,7 +661,7 @@ void __init early_init_devtree(void *params) /* make sure we've parsed cmdline for mem= before this */ if (memory_limit) - first_memblock_size = min(first_memblock_size, memory_limit); + first_memblock_size = min_t(u64, first_memblock_size, memory_limit); setup_initial_memory_limit(memstart_addr, first_memblock_size); /* Reserve MEMBLOCK regions used by kernel, initrd, dt, etc... */ memblock_reserve(PHYSICAL_START, __pa(klimit) - PHYSICAL_START); diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 0794a3017b1b..cb6c123722a2 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -705,6 +705,7 @@ static void __init early_cmdline_parse(void) #endif #define OV5_TYPE1_AFFINITY 0x80 /* Type 1 NUMA affinity */ #define OV5_PFO_HW_RNG 0x80 /* PFO Random Number Generator */ +#define OV5_PFO_HW_842 0x40 /* PFO Compression Accelerator */ #define OV5_PFO_HW_ENCR 0x20 /* PFO Encryption Accelerator */ /* Option Vector 6: IBM PAPR hints */ @@ -774,8 +775,7 @@ static unsigned char ibm_architecture_vec[] = { 0, 0, 0, - OV5_PFO_HW_RNG | OV5_PFO_HW_ENCR, - + OV5_PFO_HW_RNG | OV5_PFO_HW_ENCR | OV5_PFO_HW_842, /* option vector 6: IBM PAPR hints */ 4 - 2, /* length */ 0, @@ -1624,6 +1624,63 @@ static void __init prom_instantiate_rtas(void) #ifdef CONFIG_PPC64 /* + * Allocate room for and instantiate Stored Measurement Log (SML) + */ +static void __init prom_instantiate_sml(void) +{ + phandle ibmvtpm_node; + ihandle ibmvtpm_inst; + u32 entry = 0, size = 0; + u64 base; + + prom_debug("prom_instantiate_sml: start...\n"); + + ibmvtpm_node = call_prom("finddevice", 1, 1, ADDR("/ibm,vtpm")); + prom_debug("ibmvtpm_node: %x\n", ibmvtpm_node); + if (!PHANDLE_VALID(ibmvtpm_node)) + return; + + ibmvtpm_inst = call_prom("open", 1, 1, ADDR("/ibm,vtpm")); + if (!IHANDLE_VALID(ibmvtpm_inst)) { + prom_printf("opening vtpm package failed (%x)\n", ibmvtpm_inst); + return; + } + + if (call_prom_ret("call-method", 2, 2, &size, + ADDR("sml-get-handover-size"), + ibmvtpm_inst) != 0 || size == 0) { + prom_printf("SML get handover size failed\n"); + return; + } + + base = alloc_down(size, PAGE_SIZE, 0); + if (base == 0) + prom_panic("Could not allocate memory for sml\n"); + + prom_printf("instantiating sml at 0x%x...", base); + + if (call_prom_ret("call-method", 4, 2, &entry, + ADDR("sml-handover"), + ibmvtpm_inst, size, base) != 0 || entry == 0) { + prom_printf("SML handover failed\n"); + return; + } + prom_printf(" done\n"); + + reserve_mem(base, size); + + prom_setprop(ibmvtpm_node, "/ibm,vtpm", "linux,sml-base", + &base, sizeof(base)); + prom_setprop(ibmvtpm_node, "/ibm,vtpm", "linux,sml-size", + &size, sizeof(size)); + + prom_debug("sml base = 0x%x\n", base); + prom_debug("sml size = 0x%x\n", (long)size); + + prom_debug("prom_instantiate_sml: end...\n"); +} + +/* * Allocate room for and initialize TCE tables */ static void __init prom_initialize_tce_table(void) @@ -1691,7 +1748,7 @@ static void __init prom_initialize_tce_table(void) * else will impact performance, so we always allocate 8MB. * Anton */ - if (__is_processor(PV_POWER4) || __is_processor(PV_POWER4p)) + if (pvr_version_is(PVR_POWER4) || pvr_version_is(PVR_POWER4p)) minsize = 8UL << 20; else minsize = 4UL << 20; @@ -2916,6 +2973,11 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, prom_instantiate_opal(); #endif +#ifdef CONFIG_PPC64 + /* instantiate sml */ + prom_instantiate_sml(); +#endif + /* * On non-powermacs, put all CPUs in spin-loops. * diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index c10fc28b9092..79d8e56470df 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -960,6 +960,7 @@ int ptrace_set_debugreg(struct task_struct *task, unsigned long addr, thread->ptrace_bps[0] = bp; ptrace_put_breakpoints(task); thread->dabr = data; + thread->dabrx = DABRX_ALL; return 0; } @@ -983,6 +984,7 @@ int ptrace_set_debugreg(struct task_struct *task, unsigned long addr, /* Move contents to the DABR register */ task->thread.dabr = data; + task->thread.dabrx = DABRX_ALL; #else /* CONFIG_PPC_ADV_DEBUG_REGS */ /* As described above, it was assumed 3 bits were passed with the data * address, but we will assume only the mode bits will be passed @@ -1397,6 +1399,7 @@ static long ppc_set_hwdebug(struct task_struct *child, dabr |= DABR_DATA_WRITE; child->thread.dabr = dabr; + child->thread.dabrx = DABRX_ALL; return 1; #endif /* !CONFIG_PPC_ADV_DEBUG_DVCS */ diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c index 2c0ee6405633..20b0120db0c3 100644 --- a/arch/powerpc/kernel/rtas_flash.c +++ b/arch/powerpc/kernel/rtas_flash.c @@ -21,7 +21,6 @@ #include <asm/delay.h> #include <asm/uaccess.h> #include <asm/rtas.h> -#include <asm/abs_addr.h> #define MODULE_VERS "1.0" #define MODULE_NAME "rtas_flash" @@ -582,7 +581,7 @@ static void rtas_flash_firmware(int reboot_type) flist = (struct flash_block_list *)&rtas_data_buf[0]; flist->num_blocks = 0; flist->next = rtas_firmware_flash_list; - rtas_block_list = virt_to_abs(flist); + rtas_block_list = __pa(flist); if (rtas_block_list >= 4UL*1024*1024*1024) { printk(KERN_ALERT "FLASH: kernel bug...flash list header addr above 4GB\n"); spin_unlock(&rtas_data_buf_lock); @@ -596,13 +595,13 @@ static void rtas_flash_firmware(int reboot_type) for (f = flist; f; f = next) { /* Translate data addrs to absolute */ for (i = 0; i < f->num_blocks; i++) { - f->blocks[i].data = (char *)virt_to_abs(f->blocks[i].data); + f->blocks[i].data = (char *)__pa(f->blocks[i].data); image_size += f->blocks[i].length; } next = f->next; /* Don't translate NULL pointer for last entry */ if (f->next) - f->next = (struct flash_block_list *)virt_to_abs(f->next); + f->next = (struct flash_block_list *)__pa(f->next); else f->next = NULL; /* make num_blocks into the version/length field */ diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c index 179af906dcda..6de63e3250bb 100644 --- a/arch/powerpc/kernel/rtas_pci.c +++ b/arch/powerpc/kernel/rtas_pci.c @@ -81,7 +81,7 @@ int rtas_read_config(struct pci_dn *pdn, int where, int size, u32 *val) return PCIBIOS_DEVICE_NOT_FOUND; if (returnval == EEH_IO_ERROR_VALUE(size) && - eeh_dn_check_failure (pdn->node, NULL)) + eeh_dev_check_failure(of_node_to_eeh_dev(pdn->node))) return PCIBIOS_DEVICE_NOT_FOUND; return PCIBIOS_SUCCESSFUL; @@ -275,9 +275,6 @@ void __init find_and_init_phbs(void) of_node_put(root); pci_devs_phb_init(); - /* Create EEH devices for all PHBs */ - eeh_dev_phb_init(); - /* * PCI_PROBE_ONLY and PCI_REASSIGN_ALL_BUS can be set via properties * in chosen. diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 389bd4f0cdb1..efb6a41b3131 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -208,6 +208,8 @@ void __init early_setup(unsigned long dt_ptr) /* Fix up paca fields required for the boot cpu */ get_paca()->cpu_start = 1; + /* Allow percpu accesses to "work" until we setup percpu data */ + get_paca()->data_offset = 0; /* Probe the machine type */ probe_machine(); diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index 5c023c9cf16e..a2dc75793bd5 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -11,6 +11,7 @@ #include <linux/tracehook.h> #include <linux/signal.h> +#include <linux/uprobes.h> #include <linux/key.h> #include <asm/hw_breakpoint.h> #include <asm/uaccess.h> @@ -130,7 +131,7 @@ static int do_signal(struct pt_regs *regs) * triggered inside the kernel. */ if (current->thread.dabr) - set_dabr(current->thread.dabr); + set_dabr(current->thread.dabr, current->thread.dabrx); #endif /* Re-enable the breakpoints for the signal stack */ thread_change_pc(current, regs); @@ -157,6 +158,11 @@ static int do_signal(struct pt_regs *regs) void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags) { + if (thread_info_flags & _TIF_UPROBE) { + clear_thread_flag(TIF_UPROBE); + uprobe_notify_resume(regs); + } + if (thread_info_flags & _TIF_SIGPENDING) do_signal(regs); diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 8b4c049aee20..804e323c139d 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -35,7 +35,6 @@ #include <linux/stddef.h> #include <linux/tty.h> #include <linux/binfmts.h> -#include <linux/freezer.h> #endif #include <asm/uaccess.h> diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 8d4214afc21d..2b952b5386fd 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -102,7 +102,7 @@ int __devinit smp_generic_kick_cpu(int nr) * Ok it's not there, so it might be soft-unplugged, let's * try to bring it back */ - per_cpu(cpu_state, nr) = CPU_UP_PREPARE; + generic_set_cpu_up(nr); smp_wmb(); smp_send_reschedule(nr); #endif /* CONFIG_HOTPLUG_CPU */ @@ -171,7 +171,7 @@ int smp_request_message_ipi(int virq, int msg) } #endif err = request_irq(virq, smp_ipi_action[msg], - IRQF_PERCPU | IRQF_NO_THREAD, + IRQF_PERCPU | IRQF_NO_THREAD | IRQF_NO_SUSPEND, smp_ipi_name[msg], 0); WARN(err < 0, "unable to request_irq %d for %s (rc %d)\n", virq, smp_ipi_name[msg], err); @@ -413,6 +413,16 @@ void generic_set_cpu_dead(unsigned int cpu) per_cpu(cpu_state, cpu) = CPU_DEAD; } +/* + * The cpu_state should be set to CPU_UP_PREPARE in kick_cpu(), otherwise + * the cpu_state is always CPU_DEAD after calling generic_set_cpu_dead(), + * which makes the delay in generic_cpu_die() not happen. + */ +void generic_set_cpu_up(unsigned int cpu) +{ + per_cpu(cpu_state, cpu) = CPU_UP_PREPARE; +} + int generic_check_cpu_restart(unsigned int cpu) { return per_cpu(cpu_state, cpu) == CPU_UP_PREPARE; diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index 81c570633ead..9c2ed90ece8f 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -143,70 +143,17 @@ long compat_sys_ipc(u32 call, u32 first, u32 second, u32 third, compat_uptr_t pt * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode) * and the register representation of a signed int (msr in 64-bit mode) is performed. */ -asmlinkage long compat_sys_sendfile(u32 out_fd, u32 in_fd, compat_off_t __user * offset, u32 count) +asmlinkage long compat_sys_sendfile_wrapper(u32 out_fd, u32 in_fd, + compat_off_t __user *offset, u32 count) { - mm_segment_t old_fs = get_fs(); - int ret; - off_t of; - off_t __user *up; - - if (offset && get_user(of, offset)) - return -EFAULT; - - /* The __user pointer cast is valid because of the set_fs() */ - set_fs(KERNEL_DS); - up = offset ? (off_t __user *) &of : NULL; - ret = sys_sendfile((int)out_fd, (int)in_fd, up, count); - set_fs(old_fs); - - if (offset && put_user(of, offset)) - return -EFAULT; - - return ret; -} - -asmlinkage int compat_sys_sendfile64(int out_fd, int in_fd, compat_loff_t __user *offset, s32 count) -{ - mm_segment_t old_fs = get_fs(); - int ret; - loff_t lof; - loff_t __user *up; - - if (offset && get_user(lof, offset)) - return -EFAULT; - - /* The __user pointer cast is valid because of the set_fs() */ - set_fs(KERNEL_DS); - up = offset ? (loff_t __user *) &lof : NULL; - ret = sys_sendfile64(out_fd, in_fd, up, count); - set_fs(old_fs); - - if (offset && put_user(lof, offset)) - return -EFAULT; - - return ret; + return compat_sys_sendfile((int)out_fd, (int)in_fd, offset, count); } -long compat_sys_execve(unsigned long a0, unsigned long a1, unsigned long a2, - unsigned long a3, unsigned long a4, unsigned long a5, - struct pt_regs *regs) +asmlinkage long compat_sys_sendfile64_wrapper(u32 out_fd, u32 in_fd, + compat_loff_t __user *offset, u32 count) { - int error; - char * filename; - - filename = getname((char __user *) a0); - error = PTR_ERR(filename); - if (IS_ERR(filename)) - goto out; - flush_fp_to_thread(current); - flush_altivec_to_thread(current); - - error = compat_do_execve(filename, compat_ptr(a1), compat_ptr(a2), regs); - - putname(filename); - -out: - return error; + return sys_sendfile((int)out_fd, (int)in_fd, + (off_t __user *)offset, count); } /* Note: it is necessary to treat option as an unsigned int, diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index e49e93191b69..ce4cb772dc78 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -73,7 +73,7 @@ /* powerpc clocksource/clockevent code */ #include <linux/clockchips.h> -#include <linux/clocksource.h> +#include <linux/timekeeper_internal.h> static cycle_t rtc_read(struct clocksource *); static struct clocksource clocksource_rtc = { @@ -291,13 +291,12 @@ static inline u64 calculate_stolen_time(u64 stop_tb) * Account time for a transition between system, hard irq * or soft irq state. */ -void account_system_vtime(struct task_struct *tsk) +static u64 vtime_delta(struct task_struct *tsk, + u64 *sys_scaled, u64 *stolen) { - u64 now, nowscaled, delta, deltascaled; - unsigned long flags; - u64 stolen, udelta, sys_scaled, user_scaled; + u64 now, nowscaled, deltascaled; + u64 udelta, delta, user_scaled; - local_irq_save(flags); now = mftb(); nowscaled = read_spurr(now); get_paca()->system_time += now - get_paca()->starttime; @@ -305,7 +304,7 @@ void account_system_vtime(struct task_struct *tsk) deltascaled = nowscaled - get_paca()->startspurr; get_paca()->startspurr = nowscaled; - stolen = calculate_stolen_time(now); + *stolen = calculate_stolen_time(now); delta = get_paca()->system_time; get_paca()->system_time = 0; @@ -322,35 +321,45 @@ void account_system_vtime(struct task_struct *tsk) * the user ticks get saved up in paca->user_time_scaled to be * used by account_process_tick. */ - sys_scaled = delta; + *sys_scaled = delta; user_scaled = udelta; if (deltascaled != delta + udelta) { if (udelta) { - sys_scaled = deltascaled * delta / (delta + udelta); - user_scaled = deltascaled - sys_scaled; + *sys_scaled = deltascaled * delta / (delta + udelta); + user_scaled = deltascaled - *sys_scaled; } else { - sys_scaled = deltascaled; + *sys_scaled = deltascaled; } } get_paca()->user_time_scaled += user_scaled; - if (in_interrupt() || idle_task(smp_processor_id()) != tsk) { - account_system_time(tsk, 0, delta, sys_scaled); - if (stolen) - account_steal_time(stolen); - } else { - account_idle_time(delta + stolen); - } - local_irq_restore(flags); + return delta; +} + +void vtime_account_system(struct task_struct *tsk) +{ + u64 delta, sys_scaled, stolen; + + delta = vtime_delta(tsk, &sys_scaled, &stolen); + account_system_time(tsk, 0, delta, sys_scaled); + if (stolen) + account_steal_time(stolen); +} + +void vtime_account_idle(struct task_struct *tsk) +{ + u64 delta, sys_scaled, stolen; + + delta = vtime_delta(tsk, &sys_scaled, &stolen); + account_idle_time(delta + stolen); } -EXPORT_SYMBOL_GPL(account_system_vtime); /* * Transfer the user and system times accumulated in the paca * by the exception entry and exit code to the generic process * user and system time records. * Must be called with interrupts disabled. - * Assumes that account_system_vtime() has been called recently + * Assumes that vtime_account() has been called recently * (i.e. since the last entry from usermode) so that * get_paca()->user_time_scaled is up to date. */ @@ -366,6 +375,12 @@ void account_process_tick(struct task_struct *tsk, int user_tick) account_user_time(tsk, utime, utimescaled); } +void vtime_task_switch(struct task_struct *prev) +{ + vtime_account(prev); + account_process_tick(prev, 0); +} + #else /* ! CONFIG_VIRT_CPU_ACCOUNTING */ #define calc_cputime_factors() #endif @@ -493,8 +508,6 @@ void timer_interrupt(struct pt_regs * regs) */ may_hard_irq_enable(); - trace_timer_interrupt_entry(regs); - __get_cpu_var(irq_stat).timer_irqs++; #if defined(CONFIG_PPC32) && defined(CONFIG_PMAC) @@ -505,6 +518,8 @@ void timer_interrupt(struct pt_regs * regs) old_regs = set_irq_regs(regs); irq_enter(); + trace_timer_interrupt_entry(regs); + if (test_irq_work_pending()) { clear_irq_work_pending(); irq_work_run(); @@ -529,10 +544,10 @@ void timer_interrupt(struct pt_regs * regs) } #endif + trace_timer_interrupt_exit(regs); + irq_exit(); set_irq_regs(old_regs); - - trace_timer_interrupt_exit(regs); } /* @@ -712,7 +727,7 @@ static cycle_t timebase_read(struct clocksource *cs) return (cycle_t)get_tb(); } -void update_vsyscall(struct timespec *wall_time, struct timespec *wtm, +void update_vsyscall_old(struct timespec *wall_time, struct timespec *wtm, struct clocksource *clock, u32 mult) { u64 new_tb_to_xs, new_stamp_xsec; diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index ae0843fa7a61..32518401af68 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -251,6 +251,7 @@ void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr) if (arch_irqs_disabled() && !arch_irq_disabled_regs(regs)) local_irq_enable(); + current->thread.trap_nr = code; memset(&info, 0, sizeof(info)); info.si_signo = signr; info.si_code = code; diff --git a/arch/powerpc/kernel/uprobes.c b/arch/powerpc/kernel/uprobes.c new file mode 100644 index 000000000000..d2d46d1014f8 --- /dev/null +++ b/arch/powerpc/kernel/uprobes.c @@ -0,0 +1,184 @@ +/* + * User-space Probes (UProbes) for powerpc + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright IBM Corporation, 2007-2012 + * + * Adapted from the x86 port by Ananth N Mavinakayanahalli <ananth@in.ibm.com> + */ +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/ptrace.h> +#include <linux/uprobes.h> +#include <linux/uaccess.h> +#include <linux/kdebug.h> + +#include <asm/sstep.h> + +#define UPROBE_TRAP_NR UINT_MAX + +/** + * arch_uprobe_analyze_insn + * @mm: the probed address space. + * @arch_uprobe: the probepoint information. + * @addr: vaddr to probe. + * Return 0 on success or a -ve number on error. + */ +int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, + struct mm_struct *mm, unsigned long addr) +{ + if (addr & 0x03) + return -EINVAL; + + /* + * We currently don't support a uprobe on an already + * existing breakpoint instruction underneath + */ + if (is_trap(auprobe->ainsn)) + return -ENOTSUPP; + return 0; +} + +/* + * arch_uprobe_pre_xol - prepare to execute out of line. + * @auprobe: the probepoint information. + * @regs: reflects the saved user state of current task. + */ +int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + struct arch_uprobe_task *autask = ¤t->utask->autask; + + autask->saved_trap_nr = current->thread.trap_nr; + current->thread.trap_nr = UPROBE_TRAP_NR; + regs->nip = current->utask->xol_vaddr; + return 0; +} + +/** + * uprobe_get_swbp_addr - compute address of swbp given post-swbp regs + * @regs: Reflects the saved state of the task after it has hit a breakpoint + * instruction. + * Return the address of the breakpoint instruction. + */ +unsigned long uprobe_get_swbp_addr(struct pt_regs *regs) +{ + return instruction_pointer(regs); +} + +/* + * If xol insn itself traps and generates a signal (SIGILL/SIGSEGV/etc), + * then detect the case where a singlestepped instruction jumps back to its + * own address. It is assumed that anything like do_page_fault/do_trap/etc + * sets thread.trap_nr != UINT_MAX. + * + * arch_uprobe_pre_xol/arch_uprobe_post_xol save/restore thread.trap_nr, + * arch_uprobe_xol_was_trapped() simply checks that ->trap_nr is not equal to + * UPROBE_TRAP_NR == UINT_MAX set by arch_uprobe_pre_xol(). + */ +bool arch_uprobe_xol_was_trapped(struct task_struct *t) +{ + if (t->thread.trap_nr != UPROBE_TRAP_NR) + return true; + + return false; +} + +/* + * Called after single-stepping. To avoid the SMP problems that can + * occur when we temporarily put back the original opcode to + * single-step, we single-stepped a copy of the instruction. + * + * This function prepares to resume execution after the single-step. + */ +int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + struct uprobe_task *utask = current->utask; + + WARN_ON_ONCE(current->thread.trap_nr != UPROBE_TRAP_NR); + + current->thread.trap_nr = utask->autask.saved_trap_nr; + + /* + * On powerpc, except for loads and stores, most instructions + * including ones that alter code flow (branches, calls, returns) + * are emulated in the kernel. We get here only if the emulation + * support doesn't exist and have to fix-up the next instruction + * to be executed. + */ + regs->nip = utask->vaddr + MAX_UINSN_BYTES; + return 0; +} + +/* callback routine for handling exceptions. */ +int arch_uprobe_exception_notify(struct notifier_block *self, + unsigned long val, void *data) +{ + struct die_args *args = data; + struct pt_regs *regs = args->regs; + + /* regs == NULL is a kernel bug */ + if (WARN_ON(!regs)) + return NOTIFY_DONE; + + /* We are only interested in userspace traps */ + if (!user_mode(regs)) + return NOTIFY_DONE; + + switch (val) { + case DIE_BPT: + if (uprobe_pre_sstep_notifier(regs)) + return NOTIFY_STOP; + break; + case DIE_SSTEP: + if (uprobe_post_sstep_notifier(regs)) + return NOTIFY_STOP; + default: + break; + } + return NOTIFY_DONE; +} + +/* + * This function gets called when XOL instruction either gets trapped or + * the thread has a fatal signal, so reset the instruction pointer to its + * probed address. + */ +void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + struct uprobe_task *utask = current->utask; + + current->thread.trap_nr = utask->autask.saved_trap_nr; + instruction_pointer_set(regs, utask->vaddr); +} + +/* + * See if the instruction can be emulated. + * Returns true if instruction was emulated, false otherwise. + */ +bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + int ret; + + /* + * emulate_step() returns 1 if the insn was successfully emulated. + * For all other cases, we need to single-step in hardware. + */ + ret = emulate_step(regs, auprobe->ainsn); + if (ret > 0) + return true; + + return false; +} diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index b67db22e102d..1b2076f049ce 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -723,9 +723,7 @@ int __cpuinit vdso_getcpu_init(void) val = (cpu & 0xfff) | ((node & 0xffff) << 16); mtspr(SPRN_SPRG3, val); -#ifdef CONFIG_KVM_BOOK3S_HANDLER - get_paca()->kvm_hstate.sprg3 = val; -#endif + get_paca()->sprg3 = val; put_cpu(); diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index 02b32216bbc3..201ba59738be 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -33,7 +33,6 @@ #include <asm/prom.h> #include <asm/firmware.h> #include <asm/tce.h> -#include <asm/abs_addr.h> #include <asm/page.h> #include <asm/hvcall.h> |