diff options
author | André Fabian Silva Delgado <emulatorman@parabola.nu> | 2016-09-11 04:34:46 -0300 |
---|---|---|
committer | André Fabian Silva Delgado <emulatorman@parabola.nu> | 2016-09-11 04:34:46 -0300 |
commit | 863981e96738983919de841ec669e157e6bdaeb0 (patch) | |
tree | d6d89a12e7eb8017837c057935a2271290907f76 /arch/powerpc/kernel | |
parent | 8dec7c70575785729a6a9e6719a955e9c545bcab (diff) |
Linux-libre 4.7.1-gnupck-4.7.1-gnu
Diffstat (limited to 'arch/powerpc/kernel')
35 files changed, 390 insertions, 271 deletions
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 0d0183d31..9ea09551a 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -86,6 +86,10 @@ int main(void) DEFINE(KSP_LIMIT, offsetof(struct thread_struct, ksp_limit)); #endif /* CONFIG_PPC64 */ +#ifdef CONFIG_LIVEPATCH + DEFINE(TI_livepatch_sp, offsetof(struct thread_info, livepatch_sp)); +#endif + DEFINE(KSP, offsetof(struct thread_struct, ksp)); DEFINE(PT_REGS, offsetof(struct thread_struct, regs)); #ifdef CONFIG_BOOKE @@ -434,7 +438,11 @@ int main(void) DEFINE(BUG_ENTRY_SIZE, sizeof(struct bug_entry)); #endif +#ifdef MAX_PGD_TABLE_SIZE + DEFINE(PGD_TABLE_SIZE, MAX_PGD_TABLE_SIZE); +#else DEFINE(PGD_TABLE_SIZE, PGD_TABLE_SIZE); +#endif DEFINE(PTE_SIZE, sizeof(pte_t)); #ifdef CONFIG_KVM diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c index 41c011cb6..8275858a4 100644 --- a/arch/powerpc/kernel/btext.c +++ b/arch/powerpc/kernel/btext.c @@ -162,7 +162,7 @@ void btext_map(void) offset = ((unsigned long) dispDeviceBase) - base; size = dispDeviceRowBytes * dispDeviceRect[3] + offset + dispDeviceRect[0]; - vbase = __ioremap(base, size, _PAGE_NO_CACHE); + vbase = __ioremap(base, size, pgprot_val(pgprot_noncached_wc(__pgprot(0)))); if (vbase == 0) return; logicalDisplayBase = vbase + offset; diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 6c662b8de..eeeacf623 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -63,7 +63,6 @@ extern void __setup_cpu_745x(unsigned long offset, struct cpu_spec* spec); extern void __setup_cpu_ppc970(unsigned long offset, struct cpu_spec* spec); extern void __setup_cpu_ppc970MP(unsigned long offset, struct cpu_spec* spec); extern void __setup_cpu_pa6t(unsigned long offset, struct cpu_spec* spec); -extern void __setup_cpu_a2(unsigned long offset, struct cpu_spec* spec); extern void __restore_cpu_pa6t(void); extern void __restore_cpu_ppc970(void); extern void __setup_cpu_power7(unsigned long offset, struct cpu_spec* spec); @@ -72,7 +71,6 @@ extern void __setup_cpu_power8(unsigned long offset, struct cpu_spec* spec); extern void __restore_cpu_power8(void); extern void __setup_cpu_power9(unsigned long offset, struct cpu_spec* spec); extern void __restore_cpu_power9(void); -extern void __restore_cpu_a2(void); extern void __flush_tlb_power7(unsigned int action); extern void __flush_tlb_power8(unsigned int action); extern void __flush_tlb_power9(unsigned int action); diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 675848479..c9bc78e9c 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -48,7 +48,7 @@ /** Overview: - * EEH, or "Extended Error Handling" is a PCI bridge technology for + * EEH, or "Enhanced Error Handling" is a PCI bridge technology for * dealing with PCI bus errors that can't be dealt with within the * usual PCI framework, except by check-stopping the CPU. Systems * that are designed for high-availability/reliability cannot afford @@ -1336,14 +1336,11 @@ static int eeh_pe_change_owner(struct eeh_pe *pe) id->subdevice != pdev->subsystem_device) continue; - goto reset; + return eeh_pe_reset_and_recover(pe); } } return eeh_unfreeze_pe(pe, true); - -reset: - return eeh_pe_reset_and_recover(pe); } /** diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 31e4c7e1a..d70101e1e 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -575,7 +575,7 @@ static int eeh_clear_pe_frozen_state(struct eeh_pe *pe, int eeh_pe_reset_and_recover(struct eeh_pe *pe) { - int result, ret; + int ret; /* Bail if the PE is being recovered */ if (pe->state & EEH_PE_RECOVERING) @@ -601,15 +601,9 @@ int eeh_pe_reset_and_recover(struct eeh_pe *pe) return ret; } - /* Notify completion of reset */ - eeh_pe_dev_traverse(pe, eeh_report_reset, &result); - /* Restore device state */ eeh_pe_dev_traverse(pe, eeh_dev_restore_state, NULL); - /* Resume */ - eeh_pe_dev_traverse(pe, eeh_report_resume, NULL); - /* Clear recovery mode */ eeh_pe_state_clear(pe, EEH_PE_RECOVERING); @@ -641,20 +635,19 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, * We don't remove the corresponding PE instances because * we need the information afterwords. The attached EEH * devices are expected to be attached soon when calling - * into pcibios_add_pci_devices(). + * into pci_hp_add_devices(). */ eeh_pe_state_mark(pe, EEH_PE_KEEP); if (bus) { if (pe->type & EEH_PE_VF) { eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL); } else { - eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); pci_lock_rescan_remove(); - pcibios_remove_pci_devices(bus); + pci_hp_remove_devices(bus); pci_unlock_rescan_remove(); } } else if (frozen_bus) { - eeh_pe_dev_traverse(pe, eeh_rmv_device, &rmv_data); + eeh_pe_dev_traverse(pe, eeh_rmv_device, rmv_data); } /* @@ -698,10 +691,12 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, */ edev = list_first_entry(&pe->edevs, struct eeh_dev, list); eeh_pe_traverse(pe, eeh_pe_detach_dev, NULL); - if (pe->type & EEH_PE_VF) + if (pe->type & EEH_PE_VF) { eeh_add_virt_device(edev, NULL); - else - pcibios_add_pci_devices(bus); + } else { + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); + pci_hp_add_devices(bus); + } } else if (frozen_bus && rmv_data->removed) { pr_info("EEH: Sleep 5s ahead of partial hotplug\n"); ssleep(5); @@ -711,7 +706,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, if (pe->type & EEH_PE_VF) eeh_add_virt_device(edev, NULL); else - pcibios_add_pci_devices(frozen_bus); + pci_hp_add_devices(frozen_bus); } eeh_pe_state_clear(pe, EEH_PE_KEEP); @@ -916,7 +911,7 @@ perm_error: eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); pci_lock_rescan_remove(); - pcibios_remove_pci_devices(frozen_bus); + pci_hp_remove_devices(frozen_bus); pci_unlock_rescan_remove(); } } @@ -1001,7 +996,7 @@ static void eeh_handle_special_event(void) bus = eeh_pe_bus_get(phb_pe); eeh_pe_dev_traverse(pe, eeh_report_failure, NULL); - pcibios_remove_pci_devices(bus); + pci_hp_remove_devices(bus); } pci_unlock_rescan_remove(); } diff --git a/arch/powerpc/kernel/eeh_event.c b/arch/powerpc/kernel/eeh_event.c index 4eefb6e34..82e7327e3 100644 --- a/arch/powerpc/kernel/eeh_event.c +++ b/arch/powerpc/kernel/eeh_event.c @@ -36,7 +36,7 @@ static DEFINE_SPINLOCK(eeh_eventlist_lock); static struct semaphore eeh_eventlist_sem; -LIST_HEAD(eeh_eventlist); +static LIST_HEAD(eeh_eventlist); /** * eeh_event_handler - Dispatch EEH events. diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index eea48d8ba..f0520da85 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -249,7 +249,7 @@ static void *__eeh_pe_get(void *data, void *flag) } else { if (edev->pe_config_addr && (edev->pe_config_addr == pe->addr)) - return pe; + return pe; } /* Try BDF address */ diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 9916d150b..73e461a3d 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -20,6 +20,7 @@ #include <linux/errno.h> #include <linux/err.h> +#include <linux/magic.h> #include <asm/unistd.h> #include <asm/processor.h> #include <asm/page.h> @@ -36,6 +37,7 @@ #include <asm/hw_irq.h> #include <asm/context_tracking.h> #include <asm/tm.h> +#include <asm/ppc-opcode.h> /* * System calls. @@ -508,6 +510,14 @@ BEGIN_FTR_SECTION ldarx r6,0,r1 END_FTR_SECTION_IFSET(CPU_FTR_STCX_CHECKS_ADDRESS) +BEGIN_FTR_SECTION +/* + * A cp_abort (copy paste abort) here ensures that when context switching, a + * copy from one process can't leak into the paste of another. + */ + PPC_CP_ABORT +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) + #ifdef CONFIG_PPC_BOOK3S /* Cancel all explict user streams as they will have no use after context * switch and will stop the HW from creating streams itself @@ -519,7 +529,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_STCX_CHECKS_ADDRESS) std r6,PACACURRENT(r13) /* Set new 'current' */ ld r8,KSP(r4) /* new stack pointer */ -#ifdef CONFIG_PPC_BOOK3S +#ifdef CONFIG_PPC_STD_MMU_64 +BEGIN_MMU_FTR_SECTION + b 2f +END_MMU_FTR_SECTION_IFSET(MMU_FTR_RADIX) BEGIN_FTR_SECTION clrrdi r6,r8,28 /* get its ESID */ clrrdi r9,r1,28 /* get current sp ESID */ @@ -565,7 +578,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) slbmte r7,r0 isync 2: -#endif /* !CONFIG_PPC_BOOK3S */ +#endif /* CONFIG_PPC_STD_MMU_64 */ CURRENT_THREAD_INFO(r7, r8) /* base of new stack */ /* Note: this uses SWITCH_FRAME_SIZE rather than INT_FRAME_SIZE @@ -1248,6 +1261,9 @@ _GLOBAL(ftrace_caller) addi r3,r3,function_trace_op@toc@l ld r5,0(r3) +#ifdef CONFIG_LIVEPATCH + mr r14,r7 /* remember old NIP */ +#endif /* Calculate ip from nip-4 into r3 for call below */ subi r3, r7, MCOUNT_INSN_SIZE @@ -1272,6 +1288,9 @@ ftrace_call: /* Load ctr with the possibly modified NIP */ ld r3, _NIP(r1) mtctr r3 +#ifdef CONFIG_LIVEPATCH + cmpd r14,r3 /* has NIP been altered? */ +#endif /* Restore gprs */ REST_8GPRS(0,r1) @@ -1289,6 +1308,11 @@ ftrace_call: ld r0, LRSAVE(r1) mtlr r0 +#ifdef CONFIG_LIVEPATCH + /* Based on the cmpd above, if the NIP was altered handle livepatch */ + bne- livepatch_handler +#endif + #ifdef CONFIG_FUNCTION_GRAPH_TRACER stdu r1, -112(r1) .globl ftrace_graph_call @@ -1305,6 +1329,91 @@ _GLOBAL(ftrace_graph_stub) _GLOBAL(ftrace_stub) blr + +#ifdef CONFIG_LIVEPATCH + /* + * This function runs in the mcount context, between two functions. As + * such it can only clobber registers which are volatile and used in + * function linkage. + * + * We get here when a function A, calls another function B, but B has + * been live patched with a new function C. + * + * On entry: + * - we have no stack frame and can not allocate one + * - LR points back to the original caller (in A) + * - CTR holds the new NIP in C + * - r0 & r12 are free + * + * r0 can't be used as the base register for a DS-form load or store, so + * we temporarily shuffle r1 (stack pointer) into r0 and then put it back. + */ +livepatch_handler: + CURRENT_THREAD_INFO(r12, r1) + + /* Save stack pointer into r0 */ + mr r0, r1 + + /* Allocate 3 x 8 bytes */ + ld r1, TI_livepatch_sp(r12) + addi r1, r1, 24 + std r1, TI_livepatch_sp(r12) + + /* Save toc & real LR on livepatch stack */ + std r2, -24(r1) + mflr r12 + std r12, -16(r1) + + /* Store stack end marker */ + lis r12, STACK_END_MAGIC@h + ori r12, r12, STACK_END_MAGIC@l + std r12, -8(r1) + + /* Restore real stack pointer */ + mr r1, r0 + + /* Put ctr in r12 for global entry and branch there */ + mfctr r12 + bctrl + + /* + * Now we are returning from the patched function to the original + * caller A. We are free to use r0 and r12, and we can use r2 until we + * restore it. + */ + + CURRENT_THREAD_INFO(r12, r1) + + /* Save stack pointer into r0 */ + mr r0, r1 + + ld r1, TI_livepatch_sp(r12) + + /* Check stack marker hasn't been trashed */ + lis r2, STACK_END_MAGIC@h + ori r2, r2, STACK_END_MAGIC@l + ld r12, -8(r1) +1: tdne r12, r2 + EMIT_BUG_ENTRY 1b, __FILE__, __LINE__ - 1, 0 + + /* Restore LR & toc from livepatch stack */ + ld r12, -16(r1) + mtlr r12 + ld r2, -24(r1) + + /* Pop livepatch stack frame */ + CURRENT_THREAD_INFO(r12, r0) + subi r1, r1, 24 + std r1, TI_livepatch_sp(r12) + + /* Restore real stack pointer */ + mr r1, r0 + + /* Return to original caller of live patched function */ + blr +#endif + + #else _GLOBAL_TOC(_mcount) /* Taken from output of objdump from lib64/glibc */ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 2b66f25d4..8bcc1b457 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -189,7 +189,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) #endif /* CONFIG_PPC_P7_NAP */ EXCEPTION_PROLOG_0(PACA_EXMC) BEGIN_FTR_SECTION - b machine_check_pSeries_early + b machine_check_powernv_early FTR_SECTION_ELSE b machine_check_pSeries_0 ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE) @@ -209,11 +209,6 @@ data_access_slb_pSeries: EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST, 0x380) std r3,PACA_EXSLB+EX_R3(r13) mfspr r3,SPRN_DAR -#ifdef __DISABLED__ - /* Keep that around for when we re-implement dynamic VSIDs */ - cmpdi r3,0 - bge slb_miss_user_pseries -#endif /* __DISABLED__ */ mfspr r12,SPRN_SRR1 #ifndef CONFIG_RELOCATABLE b slb_miss_realmode @@ -240,11 +235,6 @@ instruction_access_slb_pSeries: EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST, 0x480) std r3,PACA_EXSLB+EX_R3(r13) mfspr r3,SPRN_SRR0 /* SRR0 is faulting address */ -#ifdef __DISABLED__ - /* Keep that around for when we re-implement dynamic VSIDs */ - cmpdi r3,0 - bge slb_miss_user_pseries -#endif /* __DISABLED__ */ mfspr r12,SPRN_SRR1 #ifndef CONFIG_RELOCATABLE b slb_miss_realmode @@ -443,7 +433,7 @@ denorm_exception_hv: .align 7 /* moved from 0x200 */ -machine_check_pSeries_early: +machine_check_powernv_early: BEGIN_FTR_SECTION EXCEPTION_PROLOG_1(PACA_EXMC, NOTEST, 0x200) /* @@ -709,34 +699,6 @@ system_reset_fwnmi: #endif /* CONFIG_PPC_PSERIES */ -#ifdef __DISABLED__ -/* - * This is used for when the SLB miss handler has to go virtual, - * which doesn't happen for now anymore but will once we re-implement - * dynamic VSIDs for shared page tables - */ -slb_miss_user_pseries: - std r10,PACA_EXGEN+EX_R10(r13) - std r11,PACA_EXGEN+EX_R11(r13) - std r12,PACA_EXGEN+EX_R12(r13) - GET_SCRATCH0(r10) - ld r11,PACA_EXSLB+EX_R9(r13) - ld r12,PACA_EXSLB+EX_R3(r13) - std r10,PACA_EXGEN+EX_R13(r13) - std r11,PACA_EXGEN+EX_R9(r13) - std r12,PACA_EXGEN+EX_R3(r13) - clrrdi r12,r13,32 - mfmsr r10 - mfspr r11,SRR0 /* save SRR0 */ - ori r12,r12,slb_miss_user_common@l /* virt addr of handler */ - ori r10,r10,MSR_IR|MSR_DR|MSR_RI - mtspr SRR0,r12 - mfspr r12,SRR1 /* and SRR1 */ - mtspr SRR1,r10 - rfid - b . /* prevent spec. execution */ -#endif /* __DISABLED__ */ - #ifdef CONFIG_KVM_BOOK3S_64_HANDLER kvmppc_skip_interrupt: /* @@ -764,11 +726,10 @@ kvmppc_skip_Hinterrupt: #endif /* - * Code from here down to __end_handlers is invoked from the - * exception prologs above. Because the prologs assemble the - * addresses of these handlers using the LOAD_HANDLER macro, - * which uses an ori instruction, these handlers must be in - * the first 64k of the kernel image. + * Ensure that any handlers that get invoked from the exception prologs + * above are below the first 64KB (0x10000) of the kernel image because + * the prologs assemble the addresses of these handlers using the + * LOAD_HANDLER macro, which uses an ori instruction. */ /*** Common interrupt handlers ***/ @@ -978,7 +939,13 @@ data_access_common: ld r3,PACA_EXGEN+EX_DAR(r13) lwz r4,PACA_EXGEN+EX_DSISR(r13) li r5,0x300 + std r3,_DAR(r1) + std r4,_DSISR(r1) +BEGIN_MMU_FTR_SECTION b do_hash_page /* Try to handle as hpte fault */ +MMU_FTR_SECTION_ELSE + b handle_page_fault +ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_RADIX) .align 7 .globl h_data_storage_common @@ -1003,73 +970,15 @@ instruction_access_common: ld r3,_NIP(r1) andis. r4,r12,0x5820 li r5,0x400 + std r3,_DAR(r1) + std r4,_DSISR(r1) +BEGIN_MMU_FTR_SECTION b do_hash_page /* Try to handle as hpte fault */ - - STD_EXCEPTION_COMMON(0xe20, h_instr_storage, unknown_exception) - -/* - * Here is the common SLB miss user that is used when going to virtual - * mode for SLB misses, that is currently not used - */ -#ifdef __DISABLED__ - .align 7 - .globl slb_miss_user_common -slb_miss_user_common: - mflr r10 - std r3,PACA_EXGEN+EX_DAR(r13) - stw r9,PACA_EXGEN+EX_CCR(r13) - std r10,PACA_EXGEN+EX_LR(r13) - std r11,PACA_EXGEN+EX_SRR0(r13) - bl slb_allocate_user - - ld r10,PACA_EXGEN+EX_LR(r13) - ld r3,PACA_EXGEN+EX_R3(r13) - lwz r9,PACA_EXGEN+EX_CCR(r13) - ld r11,PACA_EXGEN+EX_SRR0(r13) - mtlr r10 - beq- slb_miss_fault - - andi. r10,r12,MSR_RI /* check for unrecoverable exception */ - beq- unrecov_user_slb - mfmsr r10 - -.machine push -.machine "power4" - mtcrf 0x80,r9 -.machine pop - - clrrdi r10,r10,2 /* clear RI before setting SRR0/1 */ - mtmsrd r10,1 - - mtspr SRR0,r11 - mtspr SRR1,r12 - - 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) - rfid - b . - -slb_miss_fault: - EXCEPTION_PROLOG_COMMON(0x380, PACA_EXGEN) - ld r4,PACA_EXGEN+EX_DAR(r13) - li r5,0 - std r4,_DAR(r1) - std r5,_DSISR(r1) +MMU_FTR_SECTION_ELSE b handle_page_fault +ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_RADIX) -unrecov_user_slb: - EXCEPTION_PROLOG_COMMON(0x4200, PACA_EXGEN) - RECONCILE_IRQ_STATE(r10, r11) - bl save_nvgprs -1: addi r3,r1,STACK_FRAME_OVERHEAD - bl unrecoverable_exception - b 1b - -#endif /* __DISABLED__ */ - + STD_EXCEPTION_COMMON(0xe20, h_instr_storage, unknown_exception) /* * Machine check is different because we use a different @@ -1225,10 +1134,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX) STD_EXCEPTION_COMMON(0xf60, facility_unavailable, facility_unavailable_exception) STD_EXCEPTION_COMMON(0xf80, hv_facility_unavailable, facility_unavailable_exception) - .align 7 - .globl __end_handlers -__end_handlers: - /* Equivalents to the above handlers for relocation-on interrupt vectors */ STD_RELON_EXCEPTION_HV_OOL(0xe40, emulation_assist) MASKABLE_RELON_EXCEPTION_HV_OOL(0xe80, h_doorbell) @@ -1482,8 +1387,11 @@ slb_miss_realmode: stw r9,PACA_EXSLB+EX_CCR(r13) /* save CR in exc. frame */ std r10,PACA_EXSLB+EX_LR(r13) /* save LR */ +#ifdef CONFIG_PPC_STD_MMU_64 +BEGIN_MMU_FTR_SECTION bl slb_allocate_realmode - +END_MMU_FTR_SECTION_IFCLR(MMU_FTR_RADIX) +#endif /* All done -- return from exception. */ ld r10,PACA_EXSLB+EX_LR(r13) @@ -1491,9 +1399,12 @@ slb_miss_realmode: lwz r9,PACA_EXSLB+EX_CCR(r13) /* get saved CR */ mtlr r10 - andi. r10,r12,MSR_RI /* check for unrecoverable exception */ +BEGIN_MMU_FTR_SECTION beq- 2f +FTR_SECTION_ELSE + b 2f +ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_RADIX) .machine push .machine "power4" @@ -1542,9 +1453,7 @@ power4_fixup_nap: */ .align 7 do_hash_page: - std r3,_DAR(r1) - std r4,_DSISR(r1) - +#ifdef CONFIG_PPC_STD_MMU_64 andis. r0,r4,0xa410 /* weird error? */ bne- handle_page_fault /* if not, try to insert a HPTE */ andis. r0,r4,DSISR_DABRMATCH@h @@ -1572,6 +1481,7 @@ do_hash_page: /* Error */ blt- 13f +#endif /* CONFIG_PPC_STD_MMU_64 */ /* Here we have a page fault that hash_page can't handle. */ handle_page_fault: @@ -1598,6 +1508,7 @@ handle_dabr_fault: 12: b ret_from_except_lite +#ifdef CONFIG_PPC_STD_MMU_64 /* We have a page fault that hash_page could handle but HV refused * the PTE insertion */ @@ -1607,6 +1518,7 @@ handle_dabr_fault: ld r4,_DAR(r1) bl low_hash_fault b ret_from_except +#endif /* * We come here as a result of a DSI at a point where we don't want diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index 9dac18dab..1123a4d8d 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -607,3 +607,13 @@ unsigned long __init arch_syscall_addr(int nr) return sys_call_table[nr*2]; } #endif /* CONFIG_FTRACE_SYSCALLS && CONFIG_PPC64 */ + +#if defined(CONFIG_PPC64) && (!defined(_CALL_ELF) || _CALL_ELF != 2) +char *arch_ftrace_match_adjust(char *str, const char *search) +{ + if (str[0] == '.' && search[0] != '.') + return str + 1; + else + return str; +} +#endif /* defined(CONFIG_PPC64) && (!defined(_CALL_ELF) || _CALL_ELF != 2) */ diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 4286775cb..2d14774af 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -973,13 +973,16 @@ start_here_common: * This stuff goes at the beginning of the bss, which is page-aligned. */ .section ".bss" +/* + * pgd dir should be aligned to PGD_TABLE_SIZE which is 64K. + * We will need to find a better way to fix this + */ + .align 16 - .align PAGE_SHIFT + .globl swapper_pg_dir +swapper_pg_dir: + .space PGD_TABLE_SIZE .globl empty_zero_page empty_zero_page: .space PAGE_SIZE - - .globl swapper_pg_dir -swapper_pg_dir: - .space PGD_TABLE_SIZE diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c index ac86c53e2..a89f4f7a6 100644 --- a/arch/powerpc/kernel/ibmebus.c +++ b/arch/powerpc/kernel/ibmebus.c @@ -408,7 +408,7 @@ static ssize_t modalias_show(struct device *dev, return len+1; } -struct device_attribute ibmebus_bus_device_attrs[] = { +static struct device_attribute ibmebus_bus_device_attrs[] = { __ATTR_RO(devspec), __ATTR_RO(name), __ATTR_RO(modalias), diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 290559df1..3cb46a3b1 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -66,6 +66,7 @@ #include <asm/udbg.h> #include <asm/smp.h> #include <asm/debug.h> +#include <asm/livepatch.h> #ifdef CONFIG_PPC64 #include <asm/paca.h> @@ -607,10 +608,12 @@ void irq_ctx_init(void) memset((void *)softirq_ctx[i], 0, THREAD_SIZE); tp = softirq_ctx[i]; tp->cpu = i; + klp_init_thread_info(tp); memset((void *)hardirq_ctx[i], 0, THREAD_SIZE); tp = hardirq_ctx[i]; tp->cpu = i; + klp_init_thread_info(tp); } } diff --git a/arch/powerpc/kernel/isa-bridge.c b/arch/powerpc/kernel/isa-bridge.c index 0f1997097..ae1316106 100644 --- a/arch/powerpc/kernel/isa-bridge.c +++ b/arch/powerpc/kernel/isa-bridge.c @@ -109,14 +109,14 @@ static void pci_process_ISA_OF_ranges(struct device_node *isa_node, size = 0x10000; __ioremap_at(phb_io_base_phys, (void *)ISA_IO_BASE, - size, _PAGE_NO_CACHE|_PAGE_GUARDED); + size, pgprot_val(pgprot_noncached(__pgprot(0)))); return; inval_range: printk(KERN_ERR "no ISA IO ranges or unexpected isa range, " "mapping 64k\n"); __ioremap_at(phb_io_base_phys, (void *)ISA_IO_BASE, - 0x10000, _PAGE_NO_CACHE|_PAGE_GUARDED); + 0x10000, pgprot_val(pgprot_noncached(__pgprot(0)))); } diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c index 015ae55c1..2694d0787 100644 --- a/arch/powerpc/kernel/machine_kexec.c +++ b/arch/powerpc/kernel/machine_kexec.c @@ -228,17 +228,12 @@ static struct property memory_limit_prop = { static void __init export_crashk_values(struct device_node *node) { - struct property *prop; - /* 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) - of_remove_property(node, prop); - - prop = of_find_property(node, "linux,crashkernel-size", NULL); - if (prop) - of_remove_property(node, prop); + of_remove_property(node, of_find_property(node, + "linux,crashkernel-base", NULL)); + of_remove_property(node, of_find_property(node, + "linux,crashkernel-size", NULL)); if (crashk_res.start != 0) { crashk_base = cpu_to_be_ulong(crashk_res.start), @@ -258,16 +253,13 @@ static void __init export_crashk_values(struct device_node *node) static int __init kexec_setup(void) { struct device_node *node; - struct property *prop; node = of_find_node_by_path("/chosen"); if (!node) return -ENOENT; /* remove any stale properties so ours can be found */ - prop = of_find_property(node, kernel_end_prop.name, NULL); - if (prop) - of_remove_property(node, prop); + of_remove_property(node, of_find_property(node, kernel_end_prop.name, NULL)); /* information needed by userspace when using default_machine_kexec */ kernel_end = cpu_to_be_ulong(__pa(_end)); diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c index 0fbd75d18..b8c202d63 100644 --- a/arch/powerpc/kernel/machine_kexec_64.c +++ b/arch/powerpc/kernel/machine_kexec_64.c @@ -76,6 +76,7 @@ int default_machine_kexec_prepare(struct kimage *image) * end of the blocked region (begin >= high). Use the * boolean identity !(a || b) === (!a && !b). */ +#ifdef CONFIG_PPC_STD_MMU_64 if (htab_address) { low = __pa(htab_address); high = low + htab_size_bytes; @@ -88,6 +89,7 @@ int default_machine_kexec_prepare(struct kimage *image) return -ETXTBSY; } } +#endif /* CONFIG_PPC_STD_MMU_64 */ /* We also should not overwrite the tce tables */ for_each_node_by_type(node, "pci") { @@ -381,7 +383,7 @@ void default_machine_kexec(struct kimage *image) /* NOTREACHED */ } -#ifndef CONFIG_PPC_BOOK3E +#ifdef CONFIG_PPC_STD_MMU_64 /* Values we need to export to the second kernel via the device tree. */ static unsigned long htab_base; static unsigned long htab_size; @@ -401,7 +403,6 @@ static struct property htab_size_prop = { static int __init export_htab_values(void) { struct device_node *node; - struct property *prop; /* On machines with no htab htab_address is NULL */ if (!htab_address) @@ -412,12 +413,8 @@ static int __init export_htab_values(void) return -ENODEV; /* remove any stale propertys so ours can be found */ - prop = of_find_property(node, htab_base_prop.name, NULL); - if (prop) - of_remove_property(node, prop); - prop = of_find_property(node, htab_size_prop.name, NULL); - if (prop) - of_remove_property(node, prop); + of_remove_property(node, of_find_property(node, htab_base_prop.name, NULL)); + of_remove_property(node, of_find_property(node, htab_size_prop.name, NULL)); htab_base = cpu_to_be64(__pa(htab_address)); of_add_property(node, &htab_base_prop); @@ -428,4 +425,4 @@ static int __init export_htab_values(void) return 0; } late_initcall(export_htab_values); -#endif /* !CONFIG_PPC_BOOK3E */ +#endif /* CONFIG_PPC_STD_MMU_64 */ diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c index b2eb4686b..ef267fd9d 100644 --- a/arch/powerpc/kernel/mce.c +++ b/arch/powerpc/kernel/mce.c @@ -37,7 +37,7 @@ static DEFINE_PER_CPU(int, mce_queue_count); static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT], mce_event_queue); static void machine_check_process_queued_event(struct irq_work *work); -struct irq_work mce_event_process_work = { +static struct irq_work mce_event_process_work = { .func = machine_check_process_queued_event, }; @@ -284,7 +284,7 @@ void machine_check_print_event_info(struct machine_check_event *evt) printk("%s Effective address: %016llx\n", level, evt->u.ue_error.effective_address); if (evt->u.ue_error.physical_address_provided) - printk("%s Physial address: %016llx\n", + printk("%s Physical address: %016llx\n", level, evt->u.ue_error.physical_address); break; case MCE_ERROR_TYPE_SLB: diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c index ee62b1975..7353991c4 100644 --- a/arch/powerpc/kernel/mce_power.c +++ b/arch/powerpc/kernel/mce_power.c @@ -72,11 +72,15 @@ void __flush_tlb_power8(unsigned int action) void __flush_tlb_power9(unsigned int action) { + if (radix_enabled()) + flush_tlb_206(POWER9_TLB_SETS_RADIX, action); + flush_tlb_206(POWER9_TLB_SETS_HASH, action); } /* flush SLBs and reload */ +#ifdef CONFIG_PPC_STD_MMU_64 static void flush_and_reload_slb(void) { struct slb_shadow *slb; @@ -110,6 +114,7 @@ static void flush_and_reload_slb(void) asm volatile("slbmte %0,%1" : : "r" (rs), "r" (rb)); } } +#endif static long mce_handle_derror(uint64_t dsisr, uint64_t slb_error_bits) { @@ -120,6 +125,7 @@ static long mce_handle_derror(uint64_t dsisr, uint64_t slb_error_bits) * reset the error bits whenever we handle them so that at the end * we can check whether we handled all of them or not. * */ +#ifdef CONFIG_PPC_STD_MMU_64 if (dsisr & slb_error_bits) { flush_and_reload_slb(); /* reset error bits */ @@ -131,6 +137,7 @@ static long mce_handle_derror(uint64_t dsisr, uint64_t slb_error_bits) /* reset error bits */ dsisr &= ~P7_DSISR_MC_TLB_MULTIHIT_MFTLB; } +#endif /* Any other errors we don't understand? */ if (dsisr & 0xffffffffUL) handled = 0; @@ -150,6 +157,7 @@ static long mce_handle_common_ierror(uint64_t srr1) switch (P7_SRR1_MC_IFETCH(srr1)) { case 0: break; +#ifdef CONFIG_PPC_STD_MMU_64 case P7_SRR1_MC_IFETCH_SLB_PARITY: case P7_SRR1_MC_IFETCH_SLB_MULTIHIT: /* flush and reload SLBs for SLB errors. */ @@ -162,6 +170,7 @@ static long mce_handle_common_ierror(uint64_t srr1) handled = 1; } break; +#endif default: break; } @@ -175,10 +184,12 @@ static long mce_handle_ierror_p7(uint64_t srr1) handled = mce_handle_common_ierror(srr1); +#ifdef CONFIG_PPC_STD_MMU_64 if (P7_SRR1_MC_IFETCH(srr1) == P7_SRR1_MC_IFETCH_SLB_BOTH) { flush_and_reload_slb(); handled = 1; } +#endif return handled; } @@ -321,10 +332,12 @@ static long mce_handle_ierror_p8(uint64_t srr1) handled = mce_handle_common_ierror(srr1); +#ifdef CONFIG_PPC_STD_MMU_64 if (P7_SRR1_MC_IFETCH(srr1) == P8_SRR1_MC_IFETCH_ERAT_MULTIHIT) { flush_and_reload_slb(); handled = 1; } +#endif return handled; } diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index bf5160fbf..285ca8c6c 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -599,12 +599,6 @@ _GLOBAL(__bswapdi2) mr r4,r10 blr -_GLOBAL(abs) - srawi r4,r3,31 - xor r3,r3,r4 - sub r3,r3,r4 - blr - #ifdef CONFIG_SMP _GLOBAL(start_secondary_resume) /* Reset stack */ diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index 0cab9e8c3..856f9a794 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -15,8 +15,6 @@ * parsing code. */ -#include <linux/module.h> - #include <linux/types.h> #include <linux/errno.h> #include <linux/fs.h> @@ -1231,12 +1229,4 @@ static int __init nvram_init(void) return rc; } - -static void __exit nvram_cleanup(void) -{ - misc_deregister( &nvram_dev ); -} - -module_init(nvram_init); -module_exit(nvram_cleanup); -MODULE_LICENSE("GPL"); +device_initcall(nvram_init); diff --git a/arch/powerpc/kernel/pci-hotplug.c b/arch/powerpc/kernel/pci-hotplug.c index 59c436189..2d71269e7 100644 --- a/arch/powerpc/kernel/pci-hotplug.c +++ b/arch/powerpc/kernel/pci-hotplug.c @@ -21,6 +21,35 @@ #include <asm/firmware.h> #include <asm/eeh.h> +static struct pci_bus *find_bus_among_children(struct pci_bus *bus, + struct device_node *dn) +{ + struct pci_bus *child = NULL; + struct pci_bus *tmp; + + if (pci_bus_to_OF_node(bus) == dn) + return bus; + + list_for_each_entry(tmp, &bus->children, node) { + child = find_bus_among_children(tmp, dn); + if (child) + break; + } + + return child; +} + +struct pci_bus *pci_find_bus_by_node(struct device_node *dn) +{ + struct pci_dn *pdn = PCI_DN(dn); + + if (!pdn || !pdn->phb || !pdn->phb->bus) + return NULL; + + return find_bus_among_children(pdn->phb->bus, dn); +} +EXPORT_SYMBOL_GPL(pci_find_bus_by_node); + /** * pcibios_release_device - release PCI device * @dev: PCI device @@ -38,20 +67,20 @@ void pcibios_release_device(struct pci_dev *dev) } /** - * pcibios_remove_pci_devices - remove all devices under this bus + * pci_hp_remove_devices - remove all devices under this bus * @bus: the indicated PCI bus * * Remove all of the PCI devices under this bus both from the * linux pci device tree, and from the powerpc EEH address cache. */ -void pcibios_remove_pci_devices(struct pci_bus *bus) +void pci_hp_remove_devices(struct pci_bus *bus) { struct pci_dev *dev, *tmp; struct pci_bus *child_bus; /* First go down child busses */ list_for_each_entry(child_bus, &bus->children, node) - pcibios_remove_pci_devices(child_bus); + pci_hp_remove_devices(child_bus); pr_debug("PCI: Removing devices on bus %04x:%02x\n", pci_domain_nr(bus), bus->number); @@ -60,11 +89,10 @@ void pcibios_remove_pci_devices(struct pci_bus *bus) pci_stop_and_remove_bus_device(dev); } } - -EXPORT_SYMBOL_GPL(pcibios_remove_pci_devices); +EXPORT_SYMBOL_GPL(pci_hp_remove_devices); /** - * pcibios_add_pci_devices - adds new pci devices to bus + * pci_hp_add_devices - adds new pci devices to bus * @bus: the indicated PCI bus * * This routine will find and fixup new pci devices under @@ -74,7 +102,7 @@ EXPORT_SYMBOL_GPL(pcibios_remove_pci_devices); * is how this routine differs from other, similar pcibios * routines.) */ -void pcibios_add_pci_devices(struct pci_bus * bus) +void pci_hp_add_devices(struct pci_bus *bus) { int slotno, mode, pass, max; struct pci_dev *dev; @@ -92,7 +120,8 @@ void pcibios_add_pci_devices(struct pci_bus * bus) if (mode == PCI_PROBE_DEVTREE) { /* use ofdt-based probe */ of_rescan_bus(dn, bus); - } else if (mode == PCI_PROBE_NORMAL) { + } else if (mode == PCI_PROBE_NORMAL && + dn->child && PCI_DN(dn->child)) { /* * Use legacy probe. In the partial hotplug case, we * probably have grandchildren devices unplugged. So @@ -114,4 +143,4 @@ void pcibios_add_pci_devices(struct pci_bus * bus) } pcibios_finish_adding_to_bus(bus); } -EXPORT_SYMBOL_GPL(pcibios_add_pci_devices); +EXPORT_SYMBOL_GPL(pci_hp_add_devices); diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index 60bb187cb..a5ae49a2d 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -38,7 +38,7 @@ * ISA drivers use hard coded offsets. If no ISA bus exists nothing * is mapped on the first 64K of IO space */ -unsigned long pci_io_base = ISA_IO_BASE; +unsigned long pci_io_base; EXPORT_SYMBOL(pci_io_base); static int __init pcibios_init(void) @@ -159,7 +159,7 @@ static int pcibios_map_phb_io_space(struct pci_controller *hose) /* Establish the mapping */ if (__ioremap_at(phys_page, area->addr, size_page, - _PAGE_NO_CACHE | _PAGE_GUARDED) == NULL) + pgprot_val(pgprot_noncached(__pgprot(0)))) == NULL) return -ENOMEM; /* Fixup hose IO resource */ diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c index 38102cb9b..ecdccce78 100644 --- a/arch/powerpc/kernel/pci_dn.c +++ b/arch/powerpc/kernel/pci_dn.c @@ -282,13 +282,9 @@ void remove_dev_pci_data(struct pci_dev *pdev) #endif /* CONFIG_PCI_IOV */ } -/* - * Traverse_func that inits the PCI fields of the device node. - * NOTE: this *must* be done before read/write config to the device. - */ -void *update_dn_pci_info(struct device_node *dn, void *data) +struct pci_dn *pci_add_device_node_info(struct pci_controller *hose, + struct device_node *dn) { - struct pci_controller *phb = data; const __be32 *type = of_get_property(dn, "ibm,pci-config-space-type", NULL); const __be32 *regs; struct device_node *parent; @@ -299,7 +295,7 @@ void *update_dn_pci_info(struct device_node *dn, void *data) return NULL; dn->data = pdn; pdn->node = dn; - pdn->phb = phb; + pdn->phb = hose; #ifdef CONFIG_PPC_POWERNV pdn->pe_number = IODA_INVALID_PE; #endif @@ -331,8 +327,32 @@ void *update_dn_pci_info(struct device_node *dn, void *data) if (pdn->parent) list_add_tail(&pdn->list, &pdn->parent->child_list); - return NULL; + return pdn; } +EXPORT_SYMBOL_GPL(pci_add_device_node_info); + +void pci_remove_device_node_info(struct device_node *dn) +{ + struct pci_dn *pdn = dn ? PCI_DN(dn) : NULL; +#ifdef CONFIG_EEH + struct eeh_dev *edev = pdn_to_eeh_dev(pdn); + + if (edev) + edev->pdn = NULL; +#endif + + if (!pdn) + return; + + WARN_ON(!list_empty(&pdn->child_list)); + list_del(&pdn->list); + if (pdn->parent) + of_node_put(pdn->parent->node); + + dn->data = NULL; + kfree(pdn); +} +EXPORT_SYMBOL_GPL(pci_remove_device_node_info); /* * Traverse a device tree stopping each PCI device in the tree. @@ -352,8 +372,9 @@ void *update_dn_pci_info(struct device_node *dn, void *data) * one of these nodes we also assume its siblings are non-pci for * performance. */ -void *traverse_pci_devices(struct device_node *start, traverse_func pre, - void *data) +void *pci_traverse_device_nodes(struct device_node *start, + void *(*fn)(struct device_node *, void *), + void *data) { struct device_node *dn, *nextdn; void *ret; @@ -368,8 +389,11 @@ void *traverse_pci_devices(struct device_node *start, traverse_func pre, if (classp) class = of_read_number(classp, 1); - if (pre && ((ret = pre(dn, data)) != NULL)) - return ret; + if (fn) { + ret = fn(dn, data); + if (ret) + return ret; + } /* If we are a PCI bridge, go down */ if (dn->child && ((class >> 8) == PCI_CLASS_BRIDGE_PCI || @@ -391,6 +415,7 @@ void *traverse_pci_devices(struct device_node *start, traverse_func pre, } return NULL; } +EXPORT_SYMBOL_GPL(pci_traverse_device_nodes); static struct pci_dn *pci_dn_next_one(struct pci_dn *root, struct pci_dn *pdn) @@ -432,6 +457,18 @@ void *traverse_pci_dn(struct pci_dn *root, return NULL; } +static void *add_pdn(struct device_node *dn, void *data) +{ + struct pci_controller *hose = data; + struct pci_dn *pdn; + + pdn = pci_add_device_node_info(hose, dn); + if (!pdn) + return ERR_PTR(-ENOMEM); + + return NULL; +} + /** * pci_devs_phb_init_dynamic - setup pci devices under this PHB * phb: pci-to-host bridge (top-level bridge connecting to cpu) @@ -446,8 +483,7 @@ void pci_devs_phb_init_dynamic(struct pci_controller *phb) struct pci_dn *pdn; /* PHB nodes themselves must not match */ - update_dn_pci_info(dn, phb); - pdn = dn->data; + pdn = pci_add_device_node_info(phb, dn); if (pdn) { pdn->devfn = pdn->busno = -1; pdn->vendor_id = pdn->device_id = pdn->class_code = 0; @@ -456,7 +492,7 @@ void pci_devs_phb_init_dynamic(struct pci_controller *phb) } /* Update dn->phb ptrs for new phb and children devices */ - traverse_pci_devices(dn, update_dn_pci_info, phb); + pci_traverse_device_nodes(dn, add_pdn, phb); } /** diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index bec85055f..0b9389342 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -38,6 +38,7 @@ #include <linux/random.h> #include <linux/hw_breakpoint.h> #include <linux/uaccess.h> +#include <linux/elf-randomize.h> #include <asm/pgtable.h> #include <asm/io.h> @@ -55,6 +56,9 @@ #include <asm/firmware.h> #endif #include <asm/code-patching.h> +#include <asm/exec.h> +#include <asm/livepatch.h> + #include <linux/kprobes.h> #include <linux/kdebug.h> @@ -1075,7 +1079,7 @@ struct task_struct *__switch_to(struct task_struct *prev, } #endif /* CONFIG_PPC64 */ -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_STD_MMU_64 batch = this_cpu_ptr(&ppc64_tlb_batch); if (batch->active) { current_thread_info()->local_flags |= _TLF_LAZY_MMU; @@ -1083,7 +1087,7 @@ struct task_struct *__switch_to(struct task_struct *prev, __flush_tlb_pending(batch); batch->active = 0; } -#endif /* CONFIG_PPC_BOOK3S_64 */ +#endif /* CONFIG_PPC_STD_MMU_64 */ #ifdef CONFIG_PPC_ADV_DEBUG_REGS switch_booke_debug_regs(&new->thread.debug); @@ -1129,7 +1133,7 @@ struct task_struct *__switch_to(struct task_struct *prev, last = _switch(old_thread, new_thread); -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_STD_MMU_64 if (current_thread_info()->local_flags & _TLF_LAZY_MMU) { current_thread_info()->local_flags &= ~_TLF_LAZY_MMU; batch = this_cpu_ptr(&ppc64_tlb_batch); @@ -1138,8 +1142,7 @@ struct task_struct *__switch_to(struct task_struct *prev, if (current_thread_info()->task->thread.regs) restore_math(current_thread_info()->task->thread.regs); - -#endif /* CONFIG_PPC_BOOK3S_64 */ +#endif /* CONFIG_PPC_STD_MMU_64 */ return last; } @@ -1326,10 +1329,6 @@ void show_regs(struct pt_regs * regs) show_instructions(regs); } -void exit_thread(void) -{ -} - void flush_thread(void) { #ifdef CONFIG_HAVE_HW_BREAKPOINT @@ -1374,6 +1373,9 @@ static void setup_ksp_vsid(struct task_struct *p, unsigned long sp) unsigned long sp_vsid; unsigned long llp = mmu_psize_defs[mmu_linear_psize].sllp; + if (radix_enabled()) + return; + if (mmu_has_feature(MMU_FTR_1T_SEGMENT)) sp_vsid = get_kernel_vsid(sp, MMU_SEGSIZE_1T) << SLB_VSID_SHIFT_1T; @@ -1400,13 +1402,15 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, extern void ret_from_kernel_thread(void); void (*f)(void); unsigned long sp = (unsigned long)task_stack_page(p) + THREAD_SIZE; + struct thread_info *ti = task_thread_info(p); + + klp_init_thread_info(ti); /* Copy registers */ sp -= sizeof(struct pt_regs); childregs = (struct pt_regs *) sp; if (unlikely(p->flags & PF_KTHREAD)) { /* kernel thread */ - struct thread_info *ti = (void *)task_stack_page(p); memset(childregs, 0, sizeof(struct pt_regs)); childregs->gpr[1] = sp + sizeof(struct pt_regs); /* function */ @@ -1930,7 +1934,8 @@ unsigned long arch_randomize_brk(struct mm_struct *mm) * the heap, we can put it above 1TB so it is backed by a 1TB * segment. Otherwise the heap will be in the bottom 1TB * which always uses 256MB segments and this may result in a - * performance penalty. + * performance penalty. We don't need to worry about radix. For + * radix, mmu_highuser_ssize remains unchanged from 256MB. */ if (!is_32bit_task() && (mmu_highuser_ssize == MMU_SEGSIZE_1T)) base = max_t(unsigned long, mm->brk, 1UL << SID_SHIFT_1T); diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index a15fe1d4e..946e34ffe 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -34,6 +34,7 @@ #include <linux/of.h> #include <linux/of_fdt.h> #include <linux/libfdt.h> +#include <linux/cpu.h> #include <asm/prom.h> #include <asm/rtas.h> @@ -167,6 +168,7 @@ static struct ibm_pa_feature { */ {CPU_FTR_TM_COMP, 0, 0, PPC_FEATURE2_HTM_COMP|PPC_FEATURE2_HTM_NOSC_COMP, 22, 0, 0}, + {0, MMU_FTR_RADIX, 0, 0, 40, 0, 0}, }; static void __init scan_features(unsigned long node, const unsigned char *ftrs, diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 30a03c03f..060b140f0 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -377,7 +377,7 @@ static int fpr_get(struct task_struct *target, const struct user_regset *regset, #else BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) != - offsetof(struct thread_fp_state, fpr[32][0])); + offsetof(struct thread_fp_state, fpr[32])); return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &target->thread.fp_state, 0, -1); @@ -405,7 +405,7 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset, return 0; #else BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) != - offsetof(struct thread_fp_state, fpr[32][0])); + offsetof(struct thread_fp_state, fpr[32])); return user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.fp_state, 0, -1); diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c index aa610ce87..c638e2487 100644 --- a/arch/powerpc/kernel/rtasd.c +++ b/arch/powerpc/kernel/rtasd.c @@ -442,7 +442,7 @@ static void do_event_scan(void) } static void rtas_event_scan(struct work_struct *w); -DECLARE_DELAYED_WORK(event_scan_work, rtas_event_scan); +static DECLARE_DELAYED_WORK(event_scan_work, rtas_event_scan); /* * Delay should be at least one second since some machines have problems if diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 44c8d0355..8ca79b750 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -128,9 +128,7 @@ void machine_restart(char *cmd) machine_shutdown(); if (ppc_md.restart) ppc_md.restart(cmd); -#ifdef CONFIG_SMP smp_send_stop(); -#endif printk(KERN_EMERG "System Halted, OK to turn off power\n"); local_irq_disable(); while (1) ; @@ -141,9 +139,7 @@ void machine_power_off(void) machine_shutdown(); if (pm_power_off) pm_power_off(); -#ifdef CONFIG_SMP smp_send_stop(); -#endif printk(KERN_EMERG "System Halted, OK to turn off power\n"); local_irq_disable(); while (1) ; @@ -159,9 +155,7 @@ void machine_halt(void) machine_shutdown(); if (ppc_md.halt) ppc_md.halt(); -#ifdef CONFIG_SMP smp_send_stop(); -#endif printk(KERN_EMERG "System Halted, OK to turn off power\n"); local_irq_disable(); while (1) ; diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index f98be8383..96d4a2b23 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -69,6 +69,7 @@ #include <asm/kvm_ppc.h> #include <asm/hugetlb.h> #include <asm/epapr_hcalls.h> +#include <asm/livepatch.h> #ifdef DEBUG #define DBG(fmt...) udbg_printf(fmt) @@ -667,16 +668,16 @@ static void __init emergency_stack_init(void) limit = min(safe_stack_limit(), ppc64_rma_size); for_each_possible_cpu(i) { - unsigned long sp; - sp = memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit); - sp += THREAD_SIZE; - paca[i].emergency_sp = __va(sp); + struct thread_info *ti; + ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit)); + klp_init_thread_info(ti); + paca[i].emergency_sp = (void *)ti + THREAD_SIZE; #ifdef CONFIG_PPC_BOOK3S_64 /* emergency stack for machine check exception handling. */ - sp = memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit); - sp += THREAD_SIZE; - paca[i].mc_emergency_sp = __va(sp); + ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit)); + klp_init_thread_info(ti); + paca[i].mc_emergency_sp = (void *)ti + THREAD_SIZE; #endif } } @@ -700,6 +701,8 @@ void __init setup_arch(char **cmdline_p) if (ppc_md.panic) setup_panic(); + klp_init_thread_info(&init_thread_info); + init_mm.start_code = (unsigned long)_stext; init_mm.end_code = (unsigned long) _etext; init_mm.end_data = (unsigned long) _edata; diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 8cac1eb41..55c924b65 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -565,7 +565,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle) smp_ops->give_timebase(); /* Wait until cpu puts itself in the online & active maps */ - while (!cpu_online(cpu) || !cpu_active(cpu)) + while (!cpu_online(cpu)) cpu_relax(); return 0; diff --git a/arch/powerpc/kernel/swsusp.c b/arch/powerpc/kernel/swsusp.c index 6669b1752..6ae9bd508 100644 --- a/arch/powerpc/kernel/swsusp.c +++ b/arch/powerpc/kernel/swsusp.c @@ -31,6 +31,6 @@ void save_processor_state(void) void restore_processor_state(void) { #ifdef CONFIG_PPC32 - switch_mmu_context(current->active_mm, current->active_mm); + switch_mmu_context(current->active_mm, current->active_mm, NULL); #endif } diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 81b0900a3..3ed9a5a21 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -55,6 +55,7 @@ #include <linux/delay.h> #include <linux/irq_work.h> #include <linux/clk-provider.h> +#include <linux/suspend.h> #include <asm/trace.h> #include <asm/io.h> diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index bf8f34a58..b7019b559 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -110,17 +110,11 @@ _GLOBAL(tm_reclaim) std r3, STK_PARAM(R3)(r1) SAVE_NVGPRS(r1) - /* We need to setup MSR for VSX register save instructions. Here we - * also clear the MSR RI since when we do the treclaim, we won't have a - * valid kernel pointer for a while. We clear RI here as it avoids - * adding another mtmsr closer to the treclaim. This makes the region - * maked as non-recoverable wider than it needs to be but it saves on - * inserting another mtmsrd later. - */ + /* We need to setup MSR for VSX register save instructions. */ mfmsr r14 mr r15, r14 ori r15, r15, MSR_FP - li r16, MSR_RI + li r16, 0 ori r16, r16, MSR_EE /* IRQs hard off */ andc r15, r15, r16 oris r15, r15, MSR_VEC@h @@ -176,7 +170,17 @@ dont_backup_fp: 1: tdeqi r6, 0 EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0 - /* The moment we treclaim, ALL of our GPRs will switch + /* Clear MSR RI since we are about to change r1, EE is already off. */ + li r4, 0 + mtmsrd r4, 1 + + /* + * BE CAREFUL HERE: + * At this point we can't take an SLB miss since we have MSR_RI + * off. Load only to/from the stack/paca which are in SLB bolted regions + * until we turn MSR RI back on. + * + * The moment we treclaim, ALL of our GPRs will switch * to user register state. (FPRs, CCR etc. also!) * Use an sprg and a tm_scratch in the PACA to shuffle. */ @@ -197,6 +201,11 @@ dont_backup_fp: /* Store the PPR in r11 and reset to decent value */ std r11, GPR11(r1) /* Temporary stash */ + + /* Reset MSR RI so we can take SLB faults again */ + li r11, MSR_RI + mtmsrd r11, 1 + mfspr r11, SPRN_PPR HMT_MEDIUM @@ -397,11 +406,6 @@ restore_gprs: ld r5, THREAD_TM_DSCR(r3) ld r6, THREAD_TM_PPR(r3) - /* Clear the MSR RI since we are about to change R1. EE is already off - */ - li r4, 0 - mtmsrd r4, 1 - REST_GPR(0, r7) /* GPR0 */ REST_2GPRS(2, r7) /* GPR2-3 */ REST_GPR(4, r7) /* GPR4 */ @@ -439,10 +443,33 @@ restore_gprs: ld r6, _CCR(r7) mtcr r6 - REST_GPR(1, r7) /* GPR1 */ - REST_GPR(5, r7) /* GPR5-7 */ REST_GPR(6, r7) - ld r7, GPR7(r7) + + /* + * Store r1 and r5 on the stack so that we can access them + * after we clear MSR RI. + */ + + REST_GPR(5, r7) + std r5, -8(r1) + ld r5, GPR1(r7) + std r5, -16(r1) + + REST_GPR(7, r7) + + /* Clear MSR RI since we are about to change r1. EE is already off */ + li r5, 0 + mtmsrd r5, 1 + + /* + * BE CAREFUL HERE: + * At this point we can't take an SLB miss since we have MSR_RI + * off. Load only to/from the stack/paca which are in SLB bolted regions + * until we turn MSR RI back on. + */ + + ld r5, -8(r1) + ld r1, -16(r1) /* Commit register state as checkpointed state: */ TRECHKPT diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index def1b8b5e..6767605ea 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -195,7 +195,8 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) * and end up putting it elsewhere. * Add enough to the size so that the result can be aligned. */ - down_write(&mm->mmap_sem); + if (down_write_killable(&mm->mmap_sem)) + return -EINTR; vdso_base = get_unmapped_area(NULL, vdso_base, (vdso_pages << PAGE_SHIFT) + ((VDSO_ALIGNMENT - 1) & PAGE_MASK), diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index 5f8dcdaa2..8d7358f3a 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -87,7 +87,7 @@ struct vio_cmo_dev_entry { * @curr: bytes currently allocated * @high: high water mark for IO data usage */ -struct vio_cmo { +static struct vio_cmo { spinlock_t lock; struct delayed_work balance_q; struct list_head device_list; @@ -615,7 +615,7 @@ static u64 vio_dma_get_required_mask(struct device *dev) return dma_iommu_ops.get_required_mask(dev); } -struct dma_map_ops vio_dma_mapping_ops = { +static struct dma_map_ops vio_dma_mapping_ops = { .alloc = vio_dma_iommu_alloc_coherent, .free = vio_dma_iommu_free_coherent, .mmap = dma_direct_mmap_coherent, |