diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2016-10-07 20:19:31 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-10-07 20:19:31 -0700 |
| commit | 07021b43597f506cc525d139ed1a94e79cf184f2 (patch) | |
| tree | 888ab33ec69b397ae6f8a2c82d14197047ee827e /arch/powerpc/kernel | |
| parent | d1f5323370fceaed43a7ee38f4c7bfc7e70f28d0 (diff) | |
| parent | b7b7013cac55d794940bd9cb7b7c55c9dececac4 (diff) | |
| download | linux-07021b43597f506cc525d139ed1a94e79cf184f2.tar.gz | |
Merge tag 'powerpc-4.9-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux
Pull powerpc updates from Michael Ellerman:
"Highlights:
- Major rework of Book3S 64-bit exception vectors (Nicholas Piggin)
- Use gas sections for arranging exception vectors et. al.
- Large set of TM cleanups and selftests (Cyril Bur)
- Enable transactional memory (TM) lazily for userspace (Cyril Bur)
- Support for XZ compression in the zImage wrapper (Oliver
O'Halloran)
- Add support for bpf constant blinding (Naveen N. Rao)
- Beginnings of upstream support for PA Semi Nemo motherboards
(Darren Stevens)
Fixes:
- Ensure .mem(init|exit).text are within _stext/_etext (Michael
Ellerman)
- xmon: Don't use ld on 32-bit (Michael Ellerman)
- vdso64: Use double word compare on pointers (Anton Blanchard)
- powerpc/nvram: Fix an incorrect partition merge (Pan Xinhui)
- powerpc: Fix usage of _PAGE_RO in hugepage (Christophe Leroy)
- powerpc/mm: Update FORCE_MAX_ZONEORDER range to allow hugetlb w/4K
(Aneesh Kumar K.V)
- Fix memory leak in queue_hotplug_event() error path (Andrew
Donnellan)
- Replay hypervisor maintenance interrupt first (Nicholas Piggin)
Various performance optimisations (Anton Blanchard):
- Align hot loops of memset() and backwards_memcpy()
- During context switch, check before setting mm_cpumask
- Remove static branch prediction in atomic{, 64}_add_unless
- Only disable HAVE_EFFICIENT_UNALIGNED_ACCESS on POWER7 little
endian
- Set default CPU type to POWER8 for little endian builds
Cleanups & features:
- Sparse fixes/cleanups (Daniel Axtens)
- Preserve CFAR value on SLB miss caused by access to bogus address
(Paul Mackerras)
- Radix MMU fixups for POWER9 (Aneesh Kumar K.V)
- Support for setting used_(vsr|vr|spe) in sigreturn path (for CRIU)
(Simon Guo)
- Optimise syscall entry for virtual, relocatable case (Nicholas
Piggin)
- Optimise MSR handling in exception handling (Nicholas Piggin)
- Support for kexec with Radix MMU (Benjamin Herrenschmidt)
- powernv EEH fixes (Russell Currey)
- Suprise PCI hotplug support for powernv (Gavin Shan)
- Endian/sparse fixes for powernv PCI (Gavin Shan)
- Defconfig updates (Anton Blanchard)
- KVM: PPC: Book3S HV: Migrate pinned pages out of CMA (Balbir Singh)
- cxl: Flush PSL cache before resetting the adapter (Frederic Barrat)
- cxl: replace loop with for_each_child_of_node(), remove unneeded
of_node_put() (Andrew Donnellan)
- Fix HV facility unavailable to use correct handler (Nicholas
Piggin)
- Remove unnecessary syscall trampoline (Nicholas Piggin)
- fadump: Fix build break when CONFIG_PROC_VMCORE=n (Michael
Ellerman)
- Quieten EEH message when no adapters are found (Anton Blanchard)
- powernv: Add PHB register dump debugfs handle (Russell Currey)
- Use kprobe blacklist for exception handlers & asm functions
(Nicholas Piggin)
- Document the syscall ABI (Nicholas Piggin)
- MAINTAINERS: Update cxl maintainers (Michael Neuling)
- powerpc: Remove all usages of NO_IRQ (Michael Ellerman)
Minor cleanups:
- Andrew Donnellan, Christophe Leroy, Colin Ian King, Cyril Bur,
Frederic Barrat, Pan Xinhui, PrasannaKumar Muralidharan, Rui Teng,
Simon Guo"
* tag 'powerpc-4.9-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (156 commits)
powerpc/bpf: Add support for bpf constant blinding
powerpc/bpf: Implement support for tail calls
powerpc/bpf: Introduce accessors for using the tmp local stack space
powerpc/fadump: Fix build break when CONFIG_PROC_VMCORE=n
powerpc: tm: Enable transactional memory (TM) lazily for userspace
powerpc/tm: Add TM Unavailable Exception
powerpc: Remove do_load_up_transact_{fpu,altivec}
powerpc: tm: Rename transct_(*) to ck(\1)_state
powerpc: tm: Always use fp_state and vr_state to store live registers
selftests/powerpc: Add checks for transactional VSXs in signal contexts
selftests/powerpc: Add checks for transactional VMXs in signal contexts
selftests/powerpc: Add checks for transactional FPUs in signal contexts
selftests/powerpc: Add checks for transactional GPRs in signal contexts
selftests/powerpc: Check that signals always get delivered
selftests/powerpc: Add TM tcheck helpers in C
selftests/powerpc: Allow tests to extend their kill timeout
selftests/powerpc: Introduce GPR asm helper header file
selftests/powerpc: Move VMX stack frame macros to header file
selftests/powerpc: Rework FPU stack placement macros and move to header file
selftests/powerpc: Check for VSX preservation across userspace preemption
...
Diffstat (limited to 'arch/powerpc/kernel')
41 files changed, 1842 insertions, 1799 deletions
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index fe4c075bcf50..aded29ad2e8f 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -31,8 +31,7 @@ obj-y := cputable.o ptrace.o syscalls.o \ process.o systbl.o idle.o \ signal.o sysfs.o cacheinfo.o time.o \ prom.o traps.o setup-common.o \ - udbg.o misc.o io.o dma.o \ - misc_$(CONFIG_WORD_SIZE).o \ + udbg.o misc.o io.o dma.o misc_$(BITS).o \ of_platform.o prom_parse.o obj-$(CONFIG_PPC64) += setup_64.o sys_ppc32.o \ signal_64.o ptrace32.o \ @@ -70,23 +69,23 @@ obj-$(CONFIG_HIBERNATION) += swsusp.o suspend.o ifeq ($(CONFIG_FSL_BOOKE),y) obj-$(CONFIG_HIBERNATION) += swsusp_booke.o else -obj-$(CONFIG_HIBERNATION) += swsusp_$(CONFIG_WORD_SIZE).o +obj-$(CONFIG_HIBERNATION) += swsusp_$(BITS).o endif obj64-$(CONFIG_HIBERNATION) += swsusp_asm64.o -obj-$(CONFIG_MODULES) += module.o module_$(CONFIG_WORD_SIZE).o +obj-$(CONFIG_MODULES) += module.o module_$(BITS).o obj-$(CONFIG_44x) += cpu_setup_44x.o obj-$(CONFIG_PPC_FSL_BOOK3E) += cpu_setup_fsl_booke.o obj-$(CONFIG_PPC_DOORBELL) += dbell.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o -extra-y := head_$(CONFIG_WORD_SIZE).o +extra-y := head_$(BITS).o extra-$(CONFIG_40x) := head_40x.o extra-$(CONFIG_44x) := head_44x.o extra-$(CONFIG_FSL_BOOKE) := head_fsl_booke.o extra-$(CONFIG_8xx) := head_8xx.o extra-y += vmlinux.lds -obj-$(CONFIG_RELOCATABLE) += reloc_$(CONFIG_WORD_SIZE).o +obj-$(CONFIG_RELOCATABLE) += reloc_$(BITS).o obj-$(CONFIG_PPC32) += entry_32.o setup_32.o obj-$(CONFIG_PPC64) += dma-iommu.o iommu.o @@ -104,11 +103,11 @@ obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-$(CONFIG_SWIOTLB) += dma-swiotlb.o pci64-$(CONFIG_PPC64) += pci_dn.o pci-hotplug.o isa-bridge.o -obj-$(CONFIG_PCI) += pci_$(CONFIG_WORD_SIZE).o $(pci64-y) \ +obj-$(CONFIG_PCI) += pci_$(BITS).o $(pci64-y) \ pci-common.o pci_of_scan.o obj-$(CONFIG_PCI_MSI) += msi.o obj-$(CONFIG_KEXEC) += machine_kexec.o crash.o \ - machine_kexec_$(CONFIG_WORD_SIZE).o + machine_kexec_$(BITS).o obj-$(CONFIG_AUDIT) += audit.o obj64-$(CONFIG_AUDIT) += compat_audit.o diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index a51ae9b165e0..caec7bf3b99a 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -142,12 +142,12 @@ int main(void) DEFINE(THREAD_TM_PPR, offsetof(struct thread_struct, tm_ppr)); DEFINE(THREAD_TM_DSCR, offsetof(struct thread_struct, tm_dscr)); DEFINE(PT_CKPT_REGS, offsetof(struct thread_struct, ckpt_regs)); - DEFINE(THREAD_TRANSACT_VRSTATE, offsetof(struct thread_struct, - transact_vr)); - DEFINE(THREAD_TRANSACT_VRSAVE, offsetof(struct thread_struct, - transact_vrsave)); - DEFINE(THREAD_TRANSACT_FPSTATE, offsetof(struct thread_struct, - transact_fp)); + DEFINE(THREAD_CKVRSTATE, offsetof(struct thread_struct, + ckvr_state)); + DEFINE(THREAD_CKVRSAVE, offsetof(struct thread_struct, + ckvrsave)); + DEFINE(THREAD_CKFPSTATE, offsetof(struct thread_struct, + ckfp_state)); /* Local pt_regs on stack for Transactional Memory funcs. */ DEFINE(TM_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs) + 16); diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 74248ab18e98..6c4646ac9234 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -506,6 +506,25 @@ static struct cpu_spec __initdata cpu_specs[] = { .machine_check_early = __machine_check_early_realmode_p8, .platform = "power8", }, + { /* Power9 DD1*/ + .pvr_mask = 0xffffff00, + .pvr_value = 0x004e0100, + .cpu_name = "POWER9 (raw)", + .cpu_features = CPU_FTRS_POWER9_DD1, + .cpu_user_features = COMMON_USER_POWER9, + .cpu_user_features2 = COMMON_USER2_POWER9, + .mmu_features = MMU_FTRS_POWER9, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .oprofile_cpu_type = "ppc64/power9", + .oprofile_type = PPC_OPROFILE_INVALID, + .cpu_setup = __setup_cpu_power9, + .cpu_restore = __restore_cpu_power9, + .flush_tlb = __flush_tlb_power9, + .platform = "power9", + }, { /* Power9 */ .pvr_mask = 0xffff0000, .pvr_value = 0x004e0000, diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 7429556eb8df..f25731627d7f 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -116,6 +116,7 @@ struct eeh_ops *eeh_ops = NULL; /* Lock to avoid races due to multiple reports of an error */ DEFINE_RAW_SPINLOCK(confirm_error_lock); +EXPORT_SYMBOL_GPL(confirm_error_lock); /* Lock to protect passed flags */ static DEFINE_MUTEX(eeh_dev_mutex); @@ -1044,7 +1045,7 @@ int eeh_init(void) if (eeh_enabled()) pr_info("EEH: PCI Enhanced I/O Error Handling Enabled\n"); else - pr_warn("EEH: No capable adapters found\n"); + pr_info("EEH: No capable adapters found\n"); return ret; } @@ -1502,6 +1503,7 @@ int eeh_pe_set_option(struct eeh_pe *pe, int option) break; case EEH_OPT_THAW_MMIO: case EEH_OPT_THAW_DMA: + case EEH_OPT_FREEZE_PE: if (!eeh_ops || !eeh_ops->set_option) { ret = -ENOENT; break; diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 5f36e8a70daa..a62be72da274 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -993,9 +993,17 @@ static void eeh_handle_special_event(void) /* Notify all devices to be down */ eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); - bus = eeh_pe_bus_get(phb_pe); eeh_pe_dev_traverse(pe, eeh_report_failure, NULL); + bus = eeh_pe_bus_get(phb_pe); + if (!bus) { + pr_err("%s: Cannot find PCI bus for " + "PHB#%d-PE#%x\n", + __func__, + pe->phb->global_number, + pe->addr); + break; + } pci_hp_remove_devices(bus); } pci_unlock_rescan_remove(); diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index f0520da85759..de7d091c4c31 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -581,6 +581,7 @@ void eeh_pe_state_mark(struct eeh_pe *pe, int state) { eeh_pe_traverse(pe, __eeh_pe_state_mark, &state); } +EXPORT_SYMBOL_GPL(eeh_pe_state_mark); static void *__eeh_pe_dev_mode_mark(void *data, void *flag) { diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 9899032230b4..83428a283fa0 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -654,7 +654,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_SPE) #endif /* CONFIG_SMP */ tophys(r0,r4) - CLR_TOP32(r0) mtspr SPRN_SPRG_THREAD,r0 /* Update current THREAD phys addr */ lwz r1,KSP(r4) /* Load new stack pointer */ diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 5afd03e5e8b8..51df82b61084 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -139,7 +139,7 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR) #ifdef CONFIG_PPC_BOOK3E wrteei 1 #else - ld r11,PACAKMSR(r13) + li r11,MSR_RI ori r11,r11,MSR_EE mtmsrd r11,1 #endif /* CONFIG_PPC_BOOK3E */ @@ -195,7 +195,6 @@ system_call: /* label this so stack traces look sane */ #ifdef CONFIG_PPC_BOOK3E wrteei 0 #else - ld r10,PACAKMSR(r13) /* * For performance reasons we clear RI the same time that we * clear EE. We only need to clear RI just before we restore r13 @@ -203,8 +202,7 @@ system_call: /* label this so stack traces look sane */ * We have to be careful to restore RI if we branch anywhere from * here (eg syscall_exit_work). */ - li r9,MSR_RI - andc r11,r10,r9 + li r11,0 mtmsrd r11,1 #endif /* CONFIG_PPC_BOOK3E */ @@ -221,13 +219,12 @@ system_call: /* label this so stack traces look sane */ #endif 2: addi r3,r1,STACK_FRAME_OVERHEAD #ifdef CONFIG_PPC_BOOK3S + li r10,MSR_RI mtmsrd r10,1 /* Restore RI */ #endif bl restore_math #ifdef CONFIG_PPC_BOOK3S - ld r10,PACAKMSR(r13) - li r9,MSR_RI - andc r11,r10,r9 /* Re-clear RI */ + li r11,0 mtmsrd r11,1 #endif ld r8,_MSR(r1) @@ -308,6 +305,7 @@ syscall_enosys: syscall_exit_work: #ifdef CONFIG_PPC_BOOK3S + li r10,MSR_RI mtmsrd r10,1 /* Restore RI */ #endif /* If TIF_RESTOREALL is set, don't scribble on either r3 or ccr. @@ -354,7 +352,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) #ifdef CONFIG_PPC_BOOK3E wrteei 1 #else - ld r10,PACAKMSR(r13) + li r10,MSR_RI ori r10,r10,MSR_EE mtmsrd r10,1 #endif /* CONFIG_PPC_BOOK3E */ @@ -619,7 +617,7 @@ _GLOBAL(ret_from_except_lite) #ifdef CONFIG_PPC_BOOK3E wrteei 0 #else - ld r10,PACAKMSR(r13) /* Get kernel MSR without EE */ + li r10,MSR_RI mtmsrd r10,1 /* Update machine state */ #endif /* CONFIG_PPC_BOOK3E */ @@ -751,7 +749,7 @@ resume_kernel: #ifdef CONFIG_PPC_BOOK3E wrteei 0 #else - ld r10,PACAKMSR(r13) /* Get kernel MSR without EE */ + li r10,MSR_RI mtmsrd r10,1 /* Update machine state */ #endif /* CONFIG_PPC_BOOK3E */ #endif /* CONFIG_PREEMPT */ @@ -841,8 +839,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) * userspace and we take an exception after restoring r13, * we end up corrupting the userspace r13 value. */ - ld r4,PACAKMSR(r13) /* Get kernel MSR without EE */ - andc r4,r4,r0 /* r0 contains MSR_RI here */ + li r4,0 mtmsrd r4,1 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index bffec73dbffc..08992f8f5036 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -16,72 +16,71 @@ #include <asm/exception-64s.h> #include <asm/ptrace.h> #include <asm/cpuidle.h> +#include <asm/head-64.h> /* + * There are a few constraints to be concerned with. + * - Real mode exceptions code/data must be located at their physical location. + * - Virtual mode exceptions must be mapped at their 0xc000... location. + * - Fixed location code must not call directly beyond the __end_interrupts + * area when built with CONFIG_RELOCATABLE. LOAD_HANDLER / bctr sequence + * must be used. + * - LOAD_HANDLER targets must be within first 64K of physical 0 / + * virtual 0xc00... + * - Conditional branch targets must be within +/-32K of caller. + * + * "Virtual exceptions" run with relocation on (MSR_IR=1, MSR_DR=1), and + * therefore don't have to run in physically located code or rfid to + * virtual mode kernel code. However on relocatable kernels they do have + * to branch to KERNELBASE offset because the rest of the kernel (outside + * the exception vectors) may be located elsewhere. + * + * Virtual exceptions correspond with physical, except their entry points + * are offset by 0xc000000000000000 and also tend to get an added 0x4000 + * offset applied. Virtual exceptions are enabled with the Alternate + * Interrupt Location (AIL) bit set in the LPCR. However this does not + * guarantee they will be delivered virtually. Some conditions (see the ISA) + * cause exceptions to be delivered in real mode. + * + * It's impossible to receive interrupts below 0x300 via AIL. + * + * KVM: None of the virtual exceptions are from the guest. Anything that + * escalated to HV=1 from HV=0 is delivered via real mode handlers. + * + * * We layout physical memory as follows: * 0x0000 - 0x00ff : Secondary processor spin code - * 0x0100 - 0x17ff : pSeries Interrupt prologs - * 0x1800 - 0x4000 : interrupt support common interrupt prologs - * 0x4000 - 0x5fff : pSeries interrupts with IR=1,DR=1 - * 0x6000 - 0x6fff : more interrupt support including for IR=1,DR=1 + * 0x0100 - 0x18ff : Real mode pSeries interrupt vectors + * 0x1900 - 0x3fff : Real mode trampolines + * 0x4000 - 0x58ff : Relon (IR=1,DR=1) mode pSeries interrupt vectors + * 0x5900 - 0x6fff : Relon mode trampolines * 0x7000 - 0x7fff : FWNMI data area - * 0x8000 - 0x8fff : Initial (CPU0) segment table - * 0x9000 - : Early init and support code + * 0x8000 - .... : Common interrupt handlers, remaining early + * setup code, rest of kernel. + * + * We could reclaim 0x4000-0x42ff for real mode trampolines if the space + * is necessary. Until then it's more consistent to explicitly put VIRT_NONE + * vectors there. */ - /* Syscall routine is used twice, in reloc-off and reloc-on paths */ -#define SYSCALL_PSERIES_1 \ -BEGIN_FTR_SECTION \ - cmpdi r0,0x1ebe ; \ - beq- 1f ; \ -END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) \ - mr r9,r13 ; \ - GET_PACA(r13) ; \ - mfspr r11,SPRN_SRR0 ; \ -0: - -#define SYSCALL_PSERIES_2_RFID \ - mfspr r12,SPRN_SRR1 ; \ - ld r10,PACAKBASE(r13) ; \ - LOAD_HANDLER(r10, system_call_entry) ; \ - mtspr SPRN_SRR0,r10 ; \ - ld r10,PACAKMSR(r13) ; \ - mtspr SPRN_SRR1,r10 ; \ - rfid ; \ - b . ; /* prevent speculative execution */ - -#define SYSCALL_PSERIES_3 \ - /* Fast LE/BE switch system call */ \ -1: mfspr r12,SPRN_SRR1 ; \ - xori r12,r12,MSR_LE ; \ - mtspr SPRN_SRR1,r12 ; \ - rfid ; /* return to userspace */ \ - b . ; /* prevent speculative execution */ - -#if defined(CONFIG_RELOCATABLE) - /* - * We can't branch directly so we do it via the CTR which - * is volatile across system calls. - */ -#define SYSCALL_PSERIES_2_DIRECT \ - mflr r10 ; \ - ld r12,PACAKBASE(r13) ; \ - LOAD_HANDLER(r12, system_call_entry) ; \ - mtctr r12 ; \ - mfspr r12,SPRN_SRR1 ; \ - /* Re-use of r13... No spare regs to do this */ \ - li r13,MSR_RI ; \ - mtmsrd r13,1 ; \ - GET_PACA(r13) ; /* get r13 back */ \ - bctr ; +OPEN_FIXED_SECTION(real_vectors, 0x0100, 0x1900) +OPEN_FIXED_SECTION(real_trampolines, 0x1900, 0x4000) +OPEN_FIXED_SECTION(virt_vectors, 0x4000, 0x5900) +OPEN_FIXED_SECTION(virt_trampolines, 0x5900, 0x7000) +#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) +/* + * Data area reserved for FWNMI option. + * This address (0x7000) is fixed by the RPA. + * pseries and powernv need to keep the whole page from + * 0x7000 to 0x8000 free for use by the firmware + */ +ZERO_FIXED_SECTION(fwnmi_page, 0x7000, 0x8000) +OPEN_TEXT_SECTION(0x8000) #else - /* We can branch directly */ -#define SYSCALL_PSERIES_2_DIRECT \ - mfspr r12,SPRN_SRR1 ; \ - li r10,MSR_RI ; \ - mtmsrd r10,1 ; /* Set RI (EE=0) */ \ - b system_call_common ; +OPEN_TEXT_SECTION(0x7000) #endif +USE_FIXED_SECTION(real_vectors) + /* * This is the start of the interrupt handlers for pSeries * This code runs with relocation off. @@ -90,12 +89,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) \ * Therefore any relative branches in this section must only * branch to labels in this section. */ - . = 0x100 .globl __start_interrupts __start_interrupts: - .globl system_reset_pSeries; -system_reset_pSeries: +/* No virt vectors corresponding with 0x0..0x100 */ +EXC_VIRT_NONE(0x4000, 0x4100) + +EXC_REAL_BEGIN(system_reset, 0x100, 0x200) SET_SCRATCH0(r13) #ifdef CONFIG_PPC_P7_NAP BEGIN_FTR_SECTION @@ -136,9 +136,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) #endif /* CONFIG_PPC_P7_NAP */ EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD, NOTEST, 0x100) +EXC_REAL_END(system_reset, 0x100, 0x200) +EXC_VIRT_NONE(0x4100, 0x4200) +EXC_COMMON(system_reset_common, 0x100, system_reset_exception) + +#ifdef CONFIG_PPC_PSERIES +/* + * Vectors for the FWNMI option. Share common code. + */ +TRAMP_REAL_BEGIN(system_reset_fwnmi) + SET_SCRATCH0(r13) /* save r13 */ + EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD, + NOTEST, 0x100) +#endif /* CONFIG_PPC_PSERIES */ + - . = 0x200 -machine_check_pSeries_1: +EXC_REAL_BEGIN(machine_check, 0x200, 0x300) /* This is moved out of line as it can be patched by FW, but * some code path might still want to branch into the original * vector @@ -158,253 +171,9 @@ BEGIN_FTR_SECTION FTR_SECTION_ELSE b machine_check_pSeries_0 ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE) - - . = 0x300 - .globl data_access_pSeries -data_access_pSeries: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common, EXC_STD, - KVMTEST, 0x300) - - . = 0x380 - .globl data_access_slb_pSeries -data_access_slb_pSeries: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXSLB) - EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST, 0x380) - std r3,PACA_EXSLB+EX_R3(r13) - mfspr r3,SPRN_DAR - mfspr r12,SPRN_SRR1 -#ifndef CONFIG_RELOCATABLE - b slb_miss_realmode -#else - /* - * We can't just use a direct branch to slb_miss_realmode - * because the distance from here to there depends on where - * the kernel ends up being put. - */ - mfctr r11 - ld r10,PACAKBASE(r13) - LOAD_HANDLER(r10, slb_miss_realmode) - mtctr r10 - bctr -#endif - - STD_EXCEPTION_PSERIES(0x400, instruction_access) - - . = 0x480 - .globl instruction_access_slb_pSeries -instruction_access_slb_pSeries: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXSLB) - EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST, 0x480) - std r3,PACA_EXSLB+EX_R3(r13) - mfspr r3,SPRN_SRR0 /* SRR0 is faulting address */ - mfspr r12,SPRN_SRR1 -#ifndef CONFIG_RELOCATABLE - b slb_miss_realmode -#else - mfctr r11 - ld r10,PACAKBASE(r13) - LOAD_HANDLER(r10, slb_miss_realmode) - mtctr r10 - bctr -#endif - - /* We open code these as we can't have a ". = x" (even with - * x = "." within a feature section - */ - . = 0x500; - .globl hardware_interrupt_pSeries; - .globl hardware_interrupt_hv; -hardware_interrupt_pSeries: -hardware_interrupt_hv: - BEGIN_FTR_SECTION - _MASKABLE_EXCEPTION_PSERIES(0x502, hardware_interrupt, - EXC_HV, SOFTEN_TEST_HV) - KVM_HANDLER(PACA_EXGEN, EXC_HV, 0x502) - FTR_SECTION_ELSE - _MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt, - EXC_STD, SOFTEN_TEST_PR) - KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x500) - ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) - - STD_EXCEPTION_PSERIES(0x600, alignment) - KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x600) - - STD_EXCEPTION_PSERIES(0x700, program_check) - KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x700) - - STD_EXCEPTION_PSERIES(0x800, fp_unavailable) - KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x800) - - . = 0x900 - .globl decrementer_pSeries -decrementer_pSeries: - _MASKABLE_EXCEPTION_PSERIES(0x900, decrementer, EXC_STD, SOFTEN_TEST_PR) - - STD_EXCEPTION_HV(0x980, 0x982, hdecrementer) - - MASKABLE_EXCEPTION_PSERIES(0xa00, 0xa00, doorbell_super) - KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xa00) - - STD_EXCEPTION_PSERIES(0xb00, trap_0b) - KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xb00) - - . = 0xc00 - .globl system_call_pSeries -system_call_pSeries: - /* - * If CONFIG_KVM_BOOK3S_64_HANDLER is set, save the PPR (on systems - * that support it) before changing to HMT_MEDIUM. That allows the KVM - * code to save that value into the guest state (it is the guest's PPR - * value). Otherwise just change to HMT_MEDIUM as userspace has - * already saved the PPR. - */ -#ifdef CONFIG_KVM_BOOK3S_64_HANDLER - SET_SCRATCH0(r13) - GET_PACA(r13) - std r9,PACA_EXGEN+EX_R9(r13) - OPT_GET_SPR(r9, SPRN_PPR, CPU_FTR_HAS_PPR); - HMT_MEDIUM; - std r10,PACA_EXGEN+EX_R10(r13) - OPT_SAVE_REG_TO_PACA(PACA_EXGEN+EX_PPR, r9, CPU_FTR_HAS_PPR); - mfcr r9 - KVMTEST(0xc00) - GET_SCRATCH0(r13) -#else - HMT_MEDIUM; -#endif - SYSCALL_PSERIES_1 - SYSCALL_PSERIES_2_RFID - SYSCALL_PSERIES_3 - KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xc00) - - STD_EXCEPTION_PSERIES(0xd00, single_step) - KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xd00) - - /* At 0xe??? we have a bunch of hypervisor exceptions, we branch - * out of line to handle them - */ - . = 0xe00 -hv_data_storage_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b h_data_storage_hv - - . = 0xe20 -hv_instr_storage_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b h_instr_storage_hv - - . = 0xe40 -emulation_assist_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b emulation_assist_hv - - . = 0xe60 -hv_exception_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b hmi_exception_early - - . = 0xe80 -hv_doorbell_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b h_doorbell_hv - - . = 0xea0 -hv_virt_irq_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b h_virt_irq_hv - - /* We need to deal with the Altivec unavailable exception - * here which is at 0xf20, thus in the middle of the - * prolog code of the PerformanceMonitor one. A little - * trickery is thus necessary - */ - . = 0xf00 -performance_monitor_pseries_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b performance_monitor_pSeries - - . = 0xf20 -altivec_unavailable_pseries_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b altivec_unavailable_pSeries - - . = 0xf40 -vsx_unavailable_pseries_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b vsx_unavailable_pSeries - - . = 0xf60 -facility_unavailable_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b facility_unavailable_pSeries - - . = 0xf80 -hv_facility_unavailable_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b facility_unavailable_hv - -#ifdef CONFIG_CBE_RAS - STD_EXCEPTION_HV(0x1200, 0x1202, cbe_system_error) - KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1202) -#endif /* CONFIG_CBE_RAS */ - - STD_EXCEPTION_PSERIES(0x1300, instruction_breakpoint) - KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x1300) - - . = 0x1500 - .global denorm_exception_hv -denorm_exception_hv: - mtspr SPRN_SPRG_HSCRATCH0,r13 - EXCEPTION_PROLOG_0(PACA_EXGEN) - EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, 0x1500) - -#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 - - KVMTEST(0x1500) - 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) -#endif /* CONFIG_CBE_RAS */ - - STD_EXCEPTION_PSERIES(0x1700, altivec_assist) - KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x1700) - -#ifdef CONFIG_CBE_RAS - STD_EXCEPTION_HV(0x1800, 0x1802, cbe_thermal) - KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1802) -#else - . = 0x1800 -#endif /* CONFIG_CBE_RAS */ - - -/*** Out of line interrupts support ***/ - - .align 7 - /* moved from 0x200 */ -machine_check_powernv_early: +EXC_REAL_END(machine_check, 0x200, 0x300) +EXC_VIRT_NONE(0x4200, 0x4300) +TRAMP_REAL_BEGIN(machine_check_powernv_early) BEGIN_FTR_SECTION EXCEPTION_PROLOG_1(PACA_EXMC, NOTEST, 0x200) /* @@ -457,7 +226,6 @@ BEGIN_FTR_SECTION mfmsr r11 /* get MSR value */ ori r11,r11,MSR_ME /* turn on ME bit */ ori r11,r11,MSR_RI /* turn on RI bit */ - ld r12,PACAKBASE(r13) /* get high part of &label */ LOAD_HANDLER(r12, machine_check_handle_early) 1: mtspr SPRN_SRR0,r12 mtspr SPRN_SRR1,r11 @@ -470,7 +238,6 @@ BEGIN_FTR_SECTION */ addi r1,r1,INT_FRAME_SIZE /* go back to previous stack frame */ ld r11,PACAKMSR(r13) - ld r12,PACAKBASE(r13) LOAD_HANDLER(r12, unrecover_mce) li r10,MSR_ME andc r11,r11,r10 /* Turn off MSR_ME */ @@ -478,20 +245,19 @@ BEGIN_FTR_SECTION b . /* prevent speculative execution */ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) -machine_check_pSeries: +TRAMP_REAL_BEGIN(machine_check_pSeries) .globl machine_check_fwnmi machine_check_fwnmi: SET_SCRATCH0(r13) /* save r13 */ EXCEPTION_PROLOG_0(PACA_EXMC) machine_check_pSeries_0: - EXCEPTION_PROLOG_1(PACA_EXMC, KVMTEST, 0x200) + EXCEPTION_PROLOG_1(PACA_EXMC, KVMTEST_PR, 0x200) /* * The following is essentially EXCEPTION_PROLOG_PSERIES_1 with the * difference that MSR_RI is not enabled, because PACA_EXMC is being * used, so nested machine check corrupts it. machine_check_common * enables MSR_RI. */ - ld r12,PACAKBASE(r13) ld r10,PACAKMSR(r13) xori r10,r10,MSR_RI mfspr r11,SPRN_SRR0 @@ -502,488 +268,13 @@ machine_check_pSeries_0: rfid b . /* prevent speculative execution */ - KVM_HANDLER_SKIP(PACA_EXMC, EXC_STD, 0x200) - KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x300) - KVM_HANDLER_SKIP(PACA_EXSLB, EXC_STD, 0x380) - KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x400) - KVM_HANDLER(PACA_EXSLB, EXC_STD, 0x480) - KVM_HANDLER(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 - -#define FMR2(n) fmr (n), (n) ; fmr n+1, n+1 -#define FMR4(n) FMR2(n) ; FMR2(n+2) -#define FMR8(n) FMR4(n) ; FMR4(n+4) -#define FMR16(n) FMR8(n) ; FMR8(n+8) -#define FMR32(n) FMR16(n) ; FMR16(n+16) - FMR32(0) - -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 - -#define XVCPSGNDP2(n) XVCPSGNDP(n,n,n) ; XVCPSGNDP(n+1,n+1,n+1) -#define XVCPSGNDP4(n) XVCPSGNDP2(n) ; XVCPSGNDP2(n+2) -#define XVCPSGNDP8(n) XVCPSGNDP4(n) ; XVCPSGNDP4(n+4) -#define XVCPSGNDP16(n) XVCPSGNDP8(n) ; XVCPSGNDP8(n+8) -#define XVCPSGNDP32(n) XVCPSGNDP16(n) ; XVCPSGNDP16(n+16) - XVCPSGNDP32(0) - -ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_206) - -BEGIN_FTR_SECTION - b denorm_done -END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) -/* - * To denormalise we need to move a copy of the register to itself. - * For POWER8 we need to do that for all 64 VSX registers - */ - XVCPSGNDP32(32) -denorm_done: - mtspr SPRN_HSRR0,r11 - mtcrf 0x80,r9 - ld r9,PACA_EXGEN+EX_R9(r13) - RESTORE_PPR_PACA(PACA_EXGEN, r10) -BEGIN_FTR_SECTION - ld r10,PACA_EXGEN+EX_CFAR(r13) - mtspr SPRN_CFAR,r10 -END_FTR_SECTION_IFSET(CPU_FTR_CFAR) - 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_OOL(0xe02, h_data_storage) - KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0xe02) - STD_EXCEPTION_HV_OOL(0xe22, h_instr_storage) - KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe22) - STD_EXCEPTION_HV_OOL(0xe42, emulation_assist) - KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe42) - MASKABLE_EXCEPTION_HV_OOL(0xe62, hmi_exception) - KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe62) - - MASKABLE_EXCEPTION_HV_OOL(0xe82, h_doorbell) - KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe82) - - MASKABLE_EXCEPTION_HV_OOL(0xea2, h_virt_irq) - KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xea2) - - /* moved from 0xf00 */ - STD_EXCEPTION_PSERIES_OOL(0xf00, performance_monitor) - KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf00) - STD_EXCEPTION_PSERIES_OOL(0xf20, altivec_unavailable) - KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf20) - STD_EXCEPTION_PSERIES_OOL(0xf40, vsx_unavailable) - KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf40) - STD_EXCEPTION_PSERIES_OOL(0xf60, facility_unavailable) - KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf60) - STD_EXCEPTION_HV_OOL(0xf82, facility_unavailable) - KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xf82) - -/* - * An interrupt came in while soft-disabled. We set paca->irq_happened, then: - * - If it was a decrementer interrupt, we bump the dec to max and and return. - * - If it was a doorbell we return immediately since doorbells are edge - * triggered and won't automatically refire. - * - If it was a HMI we return immediately since we handled it in realmode - * and it won't refire. - * - else we hard disable and return. - * This is called with r10 containing the value to OR to the paca field. - */ -#define MASKED_INTERRUPT(_H) \ -masked_##_H##interrupt: \ - std r11,PACA_EXGEN+EX_R11(r13); \ - lbz r11,PACAIRQHAPPENED(r13); \ - or r11,r11,r10; \ - stb r11,PACAIRQHAPPENED(r13); \ - cmpwi r10,PACA_IRQ_DEC; \ - bne 1f; \ - lis r10,0x7fff; \ - ori r10,r10,0xffff; \ - mtspr SPRN_DEC,r10; \ - b 2f; \ -1: cmpwi r10,PACA_IRQ_DBELL; \ - beq 2f; \ - cmpwi r10,PACA_IRQ_HMI; \ - beq 2f; \ - mfspr r10,SPRN_##_H##SRR1; \ - rldicl r10,r10,48,1; /* clear MSR_EE */ \ - rotldi r10,r10,16; \ - mtspr SPRN_##_H##SRR1,r10; \ -2: mtcrf 0x80,r9; \ - ld r9,PACA_EXGEN+EX_R9(r13); \ - ld r10,PACA_EXGEN+EX_R10(r13); \ - ld r11,PACA_EXGEN+EX_R11(r13); \ - GET_SCRATCH0(r13); \ - ##_H##rfid; \ - b . - - MASKED_INTERRUPT() - MASKED_INTERRUPT(H) - -/* - * Called from arch_local_irq_enable when an interrupt needs - * to be resent. r3 contains 0x500, 0x900, 0xa00 or 0xe80 to indicate - * which kind of interrupt. MSR:EE is already off. We generate a - * stackframe like if a real interrupt had happened. - * - * Note: While MSR:EE is off, we need to make sure that _MSR - * in the generated frame has EE set to 1 or the exception - * handler will not properly re-enable them. - */ -_GLOBAL(__replay_interrupt) - /* We are going to jump to the exception common code which - * will retrieve various register values from the PACA which - * we don't give a damn about, so we don't bother storing them. - */ - mfmsr r12 - mflr r11 - mfcr r9 - ori r12,r12,MSR_EE - cmpwi r3,0x900 - beq decrementer_common - cmpwi r3,0x500 - beq hardware_interrupt_common -BEGIN_FTR_SECTION - cmpwi r3,0xe80 - beq h_doorbell_common - cmpwi r3,0xea0 - beq h_virt_irq_common - cmpwi r3,0xe60 - beq hmi_exception_common -FTR_SECTION_ELSE - cmpwi r3,0xa00 - beq doorbell_super_common -ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE) - blr - -#ifdef CONFIG_PPC_PSERIES -/* - * Vectors for the FWNMI option. Share common code. - */ - .globl system_reset_fwnmi - .align 7 -system_reset_fwnmi: - SET_SCRATCH0(r13) /* save r13 */ - EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD, - NOTEST, 0x100) - -#endif /* CONFIG_PPC_PSERIES */ - -#ifdef CONFIG_KVM_BOOK3S_64_HANDLER -kvmppc_skip_interrupt: - /* - * Here all GPRs are unchanged from when the interrupt happened - * except for r13, which is saved in SPRG_SCRATCH0. - */ - mfspr r13, SPRN_SRR0 - addi r13, r13, 4 - mtspr SPRN_SRR0, r13 - GET_SCRATCH0(r13) - rfid - b . - -kvmppc_skip_Hinterrupt: - /* - * Here all GPRs are unchanged from when the interrupt happened - * except for r13, which is saved in SPRG_SCRATCH0. - */ - mfspr r13, SPRN_HSRR0 - addi r13, r13, 4 - mtspr SPRN_HSRR0, r13 - GET_SCRATCH0(r13) - hrfid - b . -#endif - -/* - * 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 ***/ - - STD_EXCEPTION_COMMON(0x100, system_reset, system_reset_exception) - - STD_EXCEPTION_COMMON_ASYNC(0x500, hardware_interrupt, do_IRQ) - STD_EXCEPTION_COMMON_ASYNC(0x900, decrementer, timer_interrupt) - STD_EXCEPTION_COMMON(0x980, hdecrementer, hdec_interrupt) -#ifdef CONFIG_PPC_DOORBELL - STD_EXCEPTION_COMMON_ASYNC(0xa00, doorbell_super, doorbell_exception) -#else - STD_EXCEPTION_COMMON_ASYNC(0xa00, doorbell_super, unknown_exception) -#endif - STD_EXCEPTION_COMMON(0xb00, trap_0b, unknown_exception) - STD_EXCEPTION_COMMON(0xd00, single_step, single_step_exception) - STD_EXCEPTION_COMMON(0xe00, trap_0e, unknown_exception) - STD_EXCEPTION_COMMON(0xe40, emulation_assist, emulation_assist_interrupt) - STD_EXCEPTION_COMMON_ASYNC(0xe60, hmi_exception, handle_hmi_exception) -#ifdef CONFIG_PPC_DOORBELL - STD_EXCEPTION_COMMON_ASYNC(0xe80, h_doorbell, doorbell_exception) -#else - STD_EXCEPTION_COMMON_ASYNC(0xe80, h_doorbell, unknown_exception) -#endif - STD_EXCEPTION_COMMON_ASYNC(0xea0, h_virt_irq, do_IRQ) - 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 - STD_EXCEPTION_COMMON(0x1700, altivec_assist, unknown_exception) -#endif - - /* - * Relocation-on interrupts: A subset of the interrupts can be delivered - * with IR=1/DR=1, if AIL==2 and MSR.HV won't be changed by delivering - * it. Addresses are the same as the original interrupt addresses, but - * offset by 0xc000000000004000. - * It's impossible to receive interrupts below 0x300 via this mechanism. - * KVM: None of these traps are from the guest ; anything that escalated - * to HV=1 from HV=0 is delivered via real mode handlers. - */ - - /* - * This uses the standard macro, since the original 0x300 vector - * only has extra guff for STAB-based processors -- which never - * come here. - */ - STD_RELON_EXCEPTION_PSERIES(0x4300, 0x300, data_access) - . = 0x4380 - .globl data_access_slb_relon_pSeries -data_access_slb_relon_pSeries: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXSLB) - EXCEPTION_PROLOG_1(PACA_EXSLB, NOTEST, 0x380) - std r3,PACA_EXSLB+EX_R3(r13) - mfspr r3,SPRN_DAR - mfspr r12,SPRN_SRR1 -#ifndef CONFIG_RELOCATABLE - b slb_miss_realmode -#else - /* - * We can't just use a direct branch to slb_miss_realmode - * because the distance from here to there depends on where - * the kernel ends up being put. - */ - mfctr r11 - ld r10,PACAKBASE(r13) - LOAD_HANDLER(r10, slb_miss_realmode) - mtctr r10 - bctr -#endif - - STD_RELON_EXCEPTION_PSERIES(0x4400, 0x400, instruction_access) - . = 0x4480 - .globl instruction_access_slb_relon_pSeries -instruction_access_slb_relon_pSeries: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXSLB) - EXCEPTION_PROLOG_1(PACA_EXSLB, NOTEST, 0x480) - std r3,PACA_EXSLB+EX_R3(r13) - mfspr r3,SPRN_SRR0 /* SRR0 is faulting address */ - mfspr r12,SPRN_SRR1 -#ifndef CONFIG_RELOCATABLE - b slb_miss_realmode -#else - mfctr r11 - ld r10,PACAKBASE(r13) - LOAD_HANDLER(r10, slb_miss_realmode) - mtctr r10 - bctr -#endif - - . = 0x4500 - .globl hardware_interrupt_relon_pSeries; - .globl hardware_interrupt_relon_hv; -hardware_interrupt_relon_pSeries: -hardware_interrupt_relon_hv: - BEGIN_FTR_SECTION - _MASKABLE_RELON_EXCEPTION_PSERIES(0x502, hardware_interrupt, EXC_HV, SOFTEN_TEST_HV) - FTR_SECTION_ELSE - _MASKABLE_RELON_EXCEPTION_PSERIES(0x500, hardware_interrupt, EXC_STD, SOFTEN_TEST_PR) - ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE) - STD_RELON_EXCEPTION_PSERIES(0x4600, 0x600, alignment) - STD_RELON_EXCEPTION_PSERIES(0x4700, 0x700, program_check) - STD_RELON_EXCEPTION_PSERIES(0x4800, 0x800, fp_unavailable) - MASKABLE_RELON_EXCEPTION_PSERIES(0x4900, 0x900, decrementer) - STD_RELON_EXCEPTION_HV(0x4980, 0x982, hdecrementer) - MASKABLE_RELON_EXCEPTION_PSERIES(0x4a00, 0xa00, doorbell_super) - STD_RELON_EXCEPTION_PSERIES(0x4b00, 0xb00, trap_0b) - - . = 0x4c00 - .globl system_call_relon_pSeries -system_call_relon_pSeries: - HMT_MEDIUM - SYSCALL_PSERIES_1 - SYSCALL_PSERIES_2_DIRECT - SYSCALL_PSERIES_3 - - STD_RELON_EXCEPTION_PSERIES(0x4d00, 0xd00, single_step) - - . = 0x4e00 - b . /* Can't happen, see v2.07 Book III-S section 6.5 */ - - . = 0x4e20 - b . /* Can't happen, see v2.07 Book III-S section 6.5 */ - - . = 0x4e40 -emulation_assist_relon_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b emulation_assist_relon_hv - - . = 0x4e60 - b . /* Can't happen, see v2.07 Book III-S section 6.5 */ - - . = 0x4e80 -h_doorbell_relon_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b h_doorbell_relon_hv - - . = 0x4ea0 -h_virt_irq_relon_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b h_virt_irq_relon_hv - - . = 0x4f00 -performance_monitor_relon_pseries_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b performance_monitor_relon_pSeries - - . = 0x4f20 -altivec_unavailable_relon_pseries_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b altivec_unavailable_relon_pSeries - - . = 0x4f40 -vsx_unavailable_relon_pseries_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b vsx_unavailable_relon_pSeries - - . = 0x4f60 -facility_unavailable_relon_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b facility_unavailable_relon_pSeries - - . = 0x4f80 -hv_facility_unavailable_relon_trampoline: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b hv_facility_unavailable_relon_hv - - STD_RELON_EXCEPTION_PSERIES(0x5300, 0x1300, instruction_breakpoint) -#ifdef CONFIG_PPC_DENORMALISATION - . = 0x5500 - b denorm_exception_hv -#endif - STD_RELON_EXCEPTION_PSERIES(0x5700, 0x1700, altivec_assist) - - .align 7 -system_call_entry: - b system_call_common - -ppc64_runlatch_on_trampoline: - b __ppc64_runlatch_on - -/* - * Here r13 points to the paca, r9 contains the saved CR, - * SRR0 and SRR1 are saved in r11 and r12, - * r9 - r13 are saved in paca->exgen. - */ - .align 7 - .globl data_access_common -data_access_common: - mfspr r10,SPRN_DAR - std r10,PACA_EXGEN+EX_DAR(r13) - mfspr r10,SPRN_DSISR - stw r10,PACA_EXGEN+EX_DSISR(r13) - EXCEPTION_PROLOG_COMMON(0x300, PACA_EXGEN) - RECONCILE_IRQ_STATE(r10, r11) - ld r12,_MSR(r1) - 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_TYPE_RADIX) - - .align 7 - .globl h_data_storage_common -h_data_storage_common: - mfspr r10,SPRN_HDAR - std r10,PACA_EXGEN+EX_DAR(r13) - mfspr r10,SPRN_HDSISR - stw r10,PACA_EXGEN+EX_DSISR(r13) - EXCEPTION_PROLOG_COMMON(0xe00, PACA_EXGEN) - bl save_nvgprs - RECONCILE_IRQ_STATE(r10, r11) - addi r3,r1,STACK_FRAME_OVERHEAD - bl unknown_exception - b ret_from_except - - .align 7 - .globl instruction_access_common -instruction_access_common: - EXCEPTION_PROLOG_COMMON(0x400, PACA_EXGEN) - RECONCILE_IRQ_STATE(r10, r11) - ld r12,_MSR(r1) - 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 */ -MMU_FTR_SECTION_ELSE - b handle_page_fault -ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) - - STD_EXCEPTION_COMMON(0xe20, h_instr_storage, unknown_exception) +TRAMP_KVM_SKIP(PACA_EXMC, 0x200) +EXC_COMMON_BEGIN(machine_check_common) /* * Machine check is different because we use a different * save area: PACA_EXMC instead of PACA_EXGEN. */ - .align 7 - .globl machine_check_common -machine_check_common: - mfspr r10,SPRN_DAR std r10,PACA_EXMC+EX_DAR(r13) mfspr r10,SPRN_DSISR @@ -1003,230 +294,6 @@ machine_check_common: bl machine_check_exception b ret_from_except - .align 7 - .globl alignment_common -alignment_common: - mfspr r10,SPRN_DAR - std r10,PACA_EXGEN+EX_DAR(r13) - mfspr r10,SPRN_DSISR - stw r10,PACA_EXGEN+EX_DSISR(r13) - EXCEPTION_PROLOG_COMMON(0x600, PACA_EXGEN) - ld r3,PACA_EXGEN+EX_DAR(r13) - lwz r4,PACA_EXGEN+EX_DSISR(r13) - std r3,_DAR(r1) - std r4,_DSISR(r1) - bl save_nvgprs - RECONCILE_IRQ_STATE(r10, r11) - addi r3,r1,STACK_FRAME_OVERHEAD - bl alignment_exception - b ret_from_except - - .align 7 - .globl program_check_common -program_check_common: - EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN) - bl save_nvgprs - RECONCILE_IRQ_STATE(r10, r11) - addi r3,r1,STACK_FRAME_OVERHEAD - bl program_check_exception - b ret_from_except - - .align 7 - .globl fp_unavailable_common -fp_unavailable_common: - EXCEPTION_PROLOG_COMMON(0x800, PACA_EXGEN) - bne 1f /* if from user, just load it up */ - bl save_nvgprs - RECONCILE_IRQ_STATE(r10, r11) - addi r3,r1,STACK_FRAME_OVERHEAD - bl kernel_fp_unavailable_exception - BUG_OPCODE -1: -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM -BEGIN_FTR_SECTION - /* Test if 2 TM state bits are zero. If non-zero (ie. userspace was in - * transaction), go do TM stuff - */ - rldicl. r0, r12, (64-MSR_TS_LG), (64-2) - bne- 2f -END_FTR_SECTION_IFSET(CPU_FTR_TM) -#endif - bl load_up_fpu - b fast_exception_return -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM -2: /* User process was in a transaction */ - bl save_nvgprs - RECONCILE_IRQ_STATE(r10, r11) - addi r3,r1,STACK_FRAME_OVERHEAD - bl fp_unavailable_tm - b ret_from_except -#endif - .align 7 - .globl altivec_unavailable_common -altivec_unavailable_common: - EXCEPTION_PROLOG_COMMON(0xf20, PACA_EXGEN) -#ifdef CONFIG_ALTIVEC -BEGIN_FTR_SECTION - beq 1f -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - BEGIN_FTR_SECTION_NESTED(69) - /* Test if 2 TM state bits are zero. If non-zero (ie. userspace was in - * transaction), go do TM stuff - */ - rldicl. r0, r12, (64-MSR_TS_LG), (64-2) - bne- 2f - END_FTR_SECTION_NESTED(CPU_FTR_TM, CPU_FTR_TM, 69) -#endif - bl load_up_altivec - b fast_exception_return -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM -2: /* User process was in a transaction */ - bl save_nvgprs - RECONCILE_IRQ_STATE(r10, r11) - addi r3,r1,STACK_FRAME_OVERHEAD - bl altivec_unavailable_tm - b ret_from_except -#endif -1: -END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) -#endif - bl save_nvgprs - RECONCILE_IRQ_STATE(r10, r11) - addi r3,r1,STACK_FRAME_OVERHEAD - bl altivec_unavailable_exception - b ret_from_except - - .align 7 - .globl vsx_unavailable_common -vsx_unavailable_common: - EXCEPTION_PROLOG_COMMON(0xf40, PACA_EXGEN) -#ifdef CONFIG_VSX -BEGIN_FTR_SECTION - beq 1f -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - BEGIN_FTR_SECTION_NESTED(69) - /* Test if 2 TM state bits are zero. If non-zero (ie. userspace was in - * transaction), go do TM stuff - */ - rldicl. r0, r12, (64-MSR_TS_LG), (64-2) - bne- 2f - END_FTR_SECTION_NESTED(CPU_FTR_TM, CPU_FTR_TM, 69) -#endif - b load_up_vsx -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM -2: /* User process was in a transaction */ - bl save_nvgprs - RECONCILE_IRQ_STATE(r10, r11) - addi r3,r1,STACK_FRAME_OVERHEAD - bl vsx_unavailable_tm - b ret_from_except -#endif -1: -END_FTR_SECTION_IFSET(CPU_FTR_VSX) -#endif - bl save_nvgprs - RECONCILE_IRQ_STATE(r10, r11) - addi r3,r1,STACK_FRAME_OVERHEAD - bl vsx_unavailable_exception - b ret_from_except - - /* 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) - MASKABLE_RELON_EXCEPTION_HV_OOL(0xea0, h_virt_irq) - - STD_RELON_EXCEPTION_PSERIES_OOL(0xf00, performance_monitor) - STD_RELON_EXCEPTION_PSERIES_OOL(0xf20, altivec_unavailable) - STD_RELON_EXCEPTION_PSERIES_OOL(0xf40, vsx_unavailable) - STD_RELON_EXCEPTION_PSERIES_OOL(0xf60, facility_unavailable) - STD_RELON_EXCEPTION_HV_OOL(0xf80, hv_facility_unavailable) - - /* - * The __end_interrupts marker must be past the out-of-line (OOL) - * handlers, so that they are copied to real address 0x100 when running - * a relocatable kernel. This ensures they can be reached from the short - * trampoline handlers (like 0x4f00, 0x4f20, etc.) which branch - * directly, without using LOAD_HANDLER(). - */ - .align 7 - .globl __end_interrupts -__end_interrupts: - -#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) -/* - * Data area reserved for FWNMI option. - * This address (0x7000) is fixed by the RPA. - */ - .= 0x7000 - .globl fwnmi_data_area -fwnmi_data_area: - - /* pseries and powernv need to keep the whole page from - * 0x7000 to 0x8000 free for use by the firmware - */ - . = 0x8000 -#endif /* defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) */ - - STD_EXCEPTION_COMMON(0xf60, facility_unavailable, facility_unavailable_exception) - STD_EXCEPTION_COMMON(0xf80, hv_facility_unavailable, facility_unavailable_exception) - -#ifdef CONFIG_CBE_RAS - STD_EXCEPTION_COMMON(0x1200, cbe_system_error, cbe_system_error_exception) - STD_EXCEPTION_COMMON(0x1600, cbe_maintenance, cbe_maintenance_exception) - STD_EXCEPTION_COMMON(0x1800, cbe_thermal, cbe_thermal_exception) -#endif /* CONFIG_CBE_RAS */ - - .globl hmi_exception_early -hmi_exception_early: - EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST, 0xe62) - mr r10,r1 /* Save r1 */ - ld r1,PACAEMERGSP(r13) /* Use emergency stack */ - subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */ - std r9,_CCR(r1) /* save CR in stackframe */ - mfspr r11,SPRN_HSRR0 /* Save HSRR0 */ - std r11,_NIP(r1) /* save HSRR0 in stackframe */ - mfspr r12,SPRN_HSRR1 /* Save SRR1 */ - std r12,_MSR(r1) /* save SRR1 in stackframe */ - std r10,0(r1) /* make stack chain pointer */ - std r0,GPR0(r1) /* save r0 in stackframe */ - std r10,GPR1(r1) /* save r1 in stackframe */ - EXCEPTION_PROLOG_COMMON_2(PACA_EXGEN) - EXCEPTION_PROLOG_COMMON_3(0xe60) - addi r3,r1,STACK_FRAME_OVERHEAD - bl hmi_exception_realmode - /* Windup the stack. */ - /* Move original HSRR0 and HSRR1 into the respective regs */ - ld r9,_MSR(r1) - mtspr SPRN_HSRR1,r9 - ld r3,_NIP(r1) - mtspr SPRN_HSRR0,r3 - ld r9,_CTR(r1) - mtctr r9 - ld r9,_XER(r1) - mtxer r9 - ld r9,_LINK(r1) - mtlr r9 - REST_GPR(0, r1) - REST_8GPRS(2, r1) - REST_GPR(10, r1) - ld r11,_CCR(r1) - mtcr r11 - REST_GPR(11, r1) - REST_2GPRS(12, r1) - /* restore original r1. */ - ld r1,GPR1(r1) - - /* - * Go to virtual mode and pull the HMI event information from - * firmware. - */ - .globl hmi_exception_after_realmode -hmi_exception_after_realmode: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b hmi_exception_hv - - #define MACHINE_CHECK_HANDLER_WINDUP \ /* Clear MSR_RI before setting SRR0 and SRR1. */\ li r0,MSR_RI; \ @@ -1262,9 +329,7 @@ hmi_exception_after_realmode: * Handle machine check early in real mode. We come here with * ME=1, MMU (IR=0 and DR=0) off and using MC emergency stack. */ - .align 7 - .globl machine_check_handle_early -machine_check_handle_early: +EXC_COMMON_BEGIN(machine_check_handle_early) std r0,GPR0(r1) /* Save r0 */ EXCEPTION_PROLOG_COMMON_3(0x200) bl save_nvgprs @@ -1353,7 +418,6 @@ machine_check_handle_early: andi. r11,r12,MSR_RI bne 2f 1: mfspr r11,SPRN_SRR0 - ld r10,PACAKBASE(r13) LOAD_HANDLER(r10,unrecover_mce) mtspr SPRN_SRR0,r10 ld r10,PACAKMSR(r13) @@ -1391,7 +455,7 @@ machine_check_handle_early: MACHINE_CHECK_HANDLER_WINDUP b machine_check_pSeries -unrecover_mce: +EXC_COMMON_BEGIN(unrecover_mce) /* Invoke machine_check_exception to print MCE event and panic. */ addi r3,r1,STACK_FRAME_OVERHEAD bl machine_check_exception @@ -1402,15 +466,155 @@ unrecover_mce: 1: addi r3,r1,STACK_FRAME_OVERHEAD bl unrecoverable_exception b 1b -/* - * r13 points to the PACA, r9 contains the saved CR, - * r12 contain the saved SRR1, SRR0 is still ready for return - * r3 has the faulting address - * r9 - r13 are saved in paca->exslb. - * r3 is saved in paca->slb_r3 - * We assume we aren't going to take any exceptions during this procedure. - */ -slb_miss_realmode: + + +EXC_REAL(data_access, 0x300, 0x380) +EXC_VIRT(data_access, 0x4300, 0x4380, 0x300) +TRAMP_KVM_SKIP(PACA_EXGEN, 0x300) + +EXC_COMMON_BEGIN(data_access_common) + /* + * Here r13 points to the paca, r9 contains the saved CR, + * SRR0 and SRR1 are saved in r11 and r12, + * r9 - r13 are saved in paca->exgen. + */ + mfspr r10,SPRN_DAR + std r10,PACA_EXGEN+EX_DAR(r13) + mfspr r10,SPRN_DSISR + stw r10,PACA_EXGEN+EX_DSISR(r13) + EXCEPTION_PROLOG_COMMON(0x300, PACA_EXGEN) + RECONCILE_IRQ_STATE(r10, r11) + ld r12,_MSR(r1) + 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_TYPE_RADIX) + + +EXC_REAL_BEGIN(data_access_slb, 0x380, 0x400) + SET_SCRATCH0(r13) + EXCEPTION_PROLOG_0(PACA_EXSLB) + EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x380) + std r3,PACA_EXSLB+EX_R3(r13) + mfspr r3,SPRN_DAR + mfspr r12,SPRN_SRR1 + crset 4*cr6+eq +#ifndef CONFIG_RELOCATABLE + b slb_miss_realmode +#else + /* + * We can't just use a direct branch to slb_miss_realmode + * because the distance from here to there depends on where + * the kernel ends up being put. + */ + mfctr r11 + LOAD_HANDLER(r10, slb_miss_realmode) + mtctr r10 + bctr +#endif +EXC_REAL_END(data_access_slb, 0x380, 0x400) + +EXC_VIRT_BEGIN(data_access_slb, 0x4380, 0x4400) + SET_SCRATCH0(r13) + EXCEPTION_PROLOG_0(PACA_EXSLB) + EXCEPTION_PROLOG_1(PACA_EXSLB, NOTEST, 0x380) + std r3,PACA_EXSLB+EX_R3(r13) + mfspr r3,SPRN_DAR + mfspr r12,SPRN_SRR1 + crset 4*cr6+eq +#ifndef CONFIG_RELOCATABLE + b slb_miss_realmode +#else + /* + * We can't just use a direct branch to slb_miss_realmode + * because the distance from here to there depends on where + * the kernel ends up being put. + */ + mfctr r11 + LOAD_HANDLER(r10, slb_miss_realmode) + mtctr r10 + bctr +#endif +EXC_VIRT_END(data_access_slb, 0x4380, 0x4400) +TRAMP_KVM_SKIP(PACA_EXSLB, 0x380) + + +EXC_REAL(instruction_access, 0x400, 0x480) +EXC_VIRT(instruction_access, 0x4400, 0x4480, 0x400) +TRAMP_KVM(PACA_EXGEN, 0x400) + +EXC_COMMON_BEGIN(instruction_access_common) + EXCEPTION_PROLOG_COMMON(0x400, PACA_EXGEN) + RECONCILE_IRQ_STATE(r10, r11) + ld r12,_MSR(r1) + 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 */ +MMU_FTR_SECTION_ELSE + b handle_page_fault +ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) + + +EXC_REAL_BEGIN(instruction_access_slb, 0x480, 0x500) + SET_SCRATCH0(r13) + EXCEPTION_PROLOG_0(PACA_EXSLB) + EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x480) + std r3,PACA_EXSLB+EX_R3(r13) + mfspr r3,SPRN_SRR0 /* SRR0 is faulting address */ + mfspr r12,SPRN_SRR1 + crclr 4*cr6+eq +#ifndef CONFIG_RELOCATABLE + b slb_miss_realmode +#else + mfctr r11 + LOAD_HANDLER(r10, slb_miss_realmode) + mtctr r10 + bctr +#endif +EXC_REAL_END(instruction_access_slb, 0x480, 0x500) + +EXC_VIRT_BEGIN(instruction_access_slb, 0x4480, 0x4500) + SET_SCRATCH0(r13) + EXCEPTION_PROLOG_0(PACA_EXSLB) + EXCEPTION_PROLOG_1(PACA_EXSLB, NOTEST, 0x480) + std r3,PACA_EXSLB+EX_R3(r13) + mfspr r3,SPRN_SRR0 /* SRR0 is faulting address */ + mfspr r12,SPRN_SRR1 + crclr 4*cr6+eq +#ifndef CONFIG_RELOCATABLE + b slb_miss_realmode +#else + mfctr r11 + LOAD_HANDLER(r10, slb_miss_realmode) + mtctr r10 + bctr +#endif +EXC_VIRT_END(instruction_access_slb, 0x4480, 0x4500) +TRAMP_KVM(PACA_EXSLB, 0x480) + + +/* This handler is used by both 0x380 and 0x480 slb miss interrupts */ +EXC_COMMON_BEGIN(slb_miss_realmode) + /* + * r13 points to the PACA, r9 contains the saved CR, + * r12 contain the saved SRR1, SRR0 is still ready for return + * r3 has the faulting address + * r9 - r13 are saved in paca->exslb. + * r3 is saved in paca->slb_r3 + * cr6.eq is set for a D-SLB miss, clear for a I-SLB miss + * We assume we aren't going to take any exceptions during this + * procedure. + */ mflr r10 #ifdef CONFIG_RELOCATABLE mtctr r11 @@ -1418,29 +622,31 @@ slb_miss_realmode: stw r9,PACA_EXSLB+EX_CCR(r13) /* save CR in exc. frame */ std r10,PACA_EXSLB+EX_LR(r13) /* save LR */ + std r3,PACA_EXSLB+EX_DAR(r13) + crset 4*cr0+eq #ifdef CONFIG_PPC_STD_MMU_64 BEGIN_MMU_FTR_SECTION bl slb_allocate_realmode END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX) #endif - /* All done -- return from exception. */ ld r10,PACA_EXSLB+EX_LR(r13) ld r3,PACA_EXSLB+EX_R3(r13) lwz r9,PACA_EXSLB+EX_CCR(r13) /* get saved CR */ - mtlr r10 + + beq 8f /* if bad address, make full stack frame */ + 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_TYPE_RADIX) + + /* All done -- return from exception. */ .machine push .machine "power4" mtcrf 0x80,r9 + mtcrf 0x02,r9 /* I/D indication is in cr6 */ mtcrf 0x01,r9 /* slb_allocate uses cr0 and cr7 */ .machine pop @@ -1454,7 +660,6 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) b . /* prevent speculative execution */ 2: mfspr r11,SPRN_SRR0 - ld r10,PACAKBASE(r13) LOAD_HANDLER(r10,unrecov_slb) mtspr SPRN_SRR0,r10 ld r10,PACAKMSR(r13) @@ -1462,7 +667,15 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) rfid b . -unrecov_slb: +8: mfspr r11,SPRN_SRR0 + LOAD_HANDLER(r10,bad_addr_slb) + mtspr SPRN_SRR0,r10 + ld r10,PACAKMSR(r13) + mtspr SPRN_SRR1,r10 + rfid + b . + +EXC_COMMON_BEGIN(unrecov_slb) EXCEPTION_PROLOG_COMMON(0x4100, PACA_EXSLB) RECONCILE_IRQ_STATE(r10, r11) bl save_nvgprs @@ -1470,9 +683,701 @@ unrecov_slb: bl unrecoverable_exception b 1b +EXC_COMMON_BEGIN(bad_addr_slb) + EXCEPTION_PROLOG_COMMON(0x380, PACA_EXSLB) + RECONCILE_IRQ_STATE(r10, r11) + ld r3, PACA_EXSLB+EX_DAR(r13) + std r3, _DAR(r1) + beq cr6, 2f + li r10, 0x480 /* fix trap number for I-SLB miss */ + std r10, _TRAP(r1) +2: bl save_nvgprs + addi r3, r1, STACK_FRAME_OVERHEAD + bl slb_miss_bad_addr + b ret_from_except + +EXC_REAL_BEGIN(hardware_interrupt, 0x500, 0x600) + .globl hardware_interrupt_hv; +hardware_interrupt_hv: + BEGIN_FTR_SECTION + _MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt_common, + EXC_HV, SOFTEN_TEST_HV) +do_kvm_H0x500: + KVM_HANDLER(PACA_EXGEN, EXC_HV, 0x502) + FTR_SECTION_ELSE + _MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt_common, + EXC_STD, SOFTEN_TEST_PR) +do_kvm_0x500: + KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x500) + ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) +EXC_REAL_END(hardware_interrupt, 0x500, 0x600) + +EXC_VIRT_BEGIN(hardware_interrupt, 0x4500, 0x4600) + .globl hardware_interrupt_relon_hv; +hardware_interrupt_relon_hv: + BEGIN_FTR_SECTION + _MASKABLE_RELON_EXCEPTION_PSERIES(0x500, hardware_interrupt_common, EXC_HV, SOFTEN_TEST_HV) + FTR_SECTION_ELSE + _MASKABLE_RELON_EXCEPTION_PSERIES(0x500, hardware_interrupt_common, EXC_STD, SOFTEN_TEST_PR) + ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE) +EXC_VIRT_END(hardware_interrupt, 0x4500, 0x4600) + +EXC_COMMON_ASYNC(hardware_interrupt_common, 0x500, do_IRQ) + + +EXC_REAL(alignment, 0x600, 0x700) +EXC_VIRT(alignment, 0x4600, 0x4700, 0x600) +TRAMP_KVM(PACA_EXGEN, 0x600) +EXC_COMMON_BEGIN(alignment_common) + mfspr r10,SPRN_DAR + std r10,PACA_EXGEN+EX_DAR(r13) + mfspr r10,SPRN_DSISR + stw r10,PACA_EXGEN+EX_DSISR(r13) + EXCEPTION_PROLOG_COMMON(0x600, PACA_EXGEN) + ld r3,PACA_EXGEN+EX_DAR(r13) + lwz r4,PACA_EXGEN+EX_DSISR(r13) + std r3,_DAR(r1) + std r4,_DSISR(r1) + bl save_nvgprs + RECONCILE_IRQ_STATE(r10, r11) + addi r3,r1,STACK_FRAME_OVERHEAD + bl alignment_exception + b ret_from_except + + +EXC_REAL(program_check, 0x700, 0x800) +EXC_VIRT(program_check, 0x4700, 0x4800, 0x700) +TRAMP_KVM(PACA_EXGEN, 0x700) +EXC_COMMON_BEGIN(program_check_common) + EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN) + bl save_nvgprs + RECONCILE_IRQ_STATE(r10, r11) + addi r3,r1,STACK_FRAME_OVERHEAD + bl program_check_exception + b ret_from_except + + +EXC_REAL(fp_unavailable, 0x800, 0x900) +EXC_VIRT(fp_unavailable, 0x4800, 0x4900, 0x800) +TRAMP_KVM(PACA_EXGEN, 0x800) +EXC_COMMON_BEGIN(fp_unavailable_common) + EXCEPTION_PROLOG_COMMON(0x800, PACA_EXGEN) + bne 1f /* if from user, just load it up */ + bl save_nvgprs + RECONCILE_IRQ_STATE(r10, r11) + addi r3,r1,STACK_FRAME_OVERHEAD + bl kernel_fp_unavailable_exception + BUG_OPCODE +1: +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +BEGIN_FTR_SECTION + /* Test if 2 TM state bits are zero. If non-zero (ie. userspace was in + * transaction), go do TM stuff + */ + rldicl. r0, r12, (64-MSR_TS_LG), (64-2) + bne- 2f +END_FTR_SECTION_IFSET(CPU_FTR_TM) +#endif + bl load_up_fpu + b fast_exception_return +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +2: /* User process was in a transaction */ + bl save_nvgprs + RECONCILE_IRQ_STATE(r10, r11) + addi r3,r1,STACK_FRAME_OVERHEAD + bl fp_unavailable_tm + b ret_from_except +#endif + + +EXC_REAL_MASKABLE(decrementer, 0x900, 0x980) +EXC_VIRT_MASKABLE(decrementer, 0x4900, 0x4980, 0x900) +TRAMP_KVM(PACA_EXGEN, 0x900) +EXC_COMMON_ASYNC(decrementer_common, 0x900, timer_interrupt) + + +EXC_REAL_HV(hdecrementer, 0x980, 0xa00) +EXC_VIRT_HV(hdecrementer, 0x4980, 0x4a00, 0x980) +TRAMP_KVM_HV(PACA_EXGEN, 0x980) +EXC_COMMON(hdecrementer_common, 0x980, hdec_interrupt) + + +EXC_REAL_MASKABLE(doorbell_super, 0xa00, 0xb00) +EXC_VIRT_MASKABLE(doorbell_super, 0x4a00, 0x4b00, 0xa00) +TRAMP_KVM(PACA_EXGEN, 0xa00) +#ifdef CONFIG_PPC_DOORBELL +EXC_COMMON_ASYNC(doorbell_super_common, 0xa00, doorbell_exception) +#else +EXC_COMMON_ASYNC(doorbell_super_common, 0xa00, unknown_exception) +#endif + + +EXC_REAL(trap_0b, 0xb00, 0xc00) +EXC_VIRT(trap_0b, 0x4b00, 0x4c00, 0xb00) +TRAMP_KVM(PACA_EXGEN, 0xb00) +EXC_COMMON(trap_0b_common, 0xb00, unknown_exception) + + +#define LOAD_SYSCALL_HANDLER(reg) \ + ld reg,PACAKBASE(r13); \ + ori reg,reg,(ABS_ADDR(system_call_common))@l; + +/* Syscall routine is used twice, in reloc-off and reloc-on paths */ +#define SYSCALL_PSERIES_1 \ +BEGIN_FTR_SECTION \ + cmpdi r0,0x1ebe ; \ + beq- 1f ; \ +END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) \ + mr r9,r13 ; \ + GET_PACA(r13) ; \ + mfspr r11,SPRN_SRR0 ; \ +0: + +#define SYSCALL_PSERIES_2_RFID \ + mfspr r12,SPRN_SRR1 ; \ + LOAD_SYSCALL_HANDLER(r10) ; \ + mtspr SPRN_SRR0,r10 ; \ + ld r10,PACAKMSR(r13) ; \ + mtspr SPRN_SRR1,r10 ; \ + rfid ; \ + b . ; /* prevent speculative execution */ + +#define SYSCALL_PSERIES_3 \ + /* Fast LE/BE switch system call */ \ +1: mfspr r12,SPRN_SRR1 ; \ + xori r12,r12,MSR_LE ; \ + mtspr SPRN_SRR1,r12 ; \ + rfid ; /* return to userspace */ \ + b . ; /* prevent speculative execution */ + +#if defined(CONFIG_RELOCATABLE) + /* + * We can't branch directly so we do it via the CTR which + * is volatile across system calls. + */ +#define SYSCALL_PSERIES_2_DIRECT \ + LOAD_SYSCALL_HANDLER(r12) ; \ + mtctr r12 ; \ + mfspr r12,SPRN_SRR1 ; \ + li r10,MSR_RI ; \ + mtmsrd r10,1 ; \ + bctr ; +#else + /* We can branch directly */ +#define SYSCALL_PSERIES_2_DIRECT \ + mfspr r12,SPRN_SRR1 ; \ + li r10,MSR_RI ; \ + mtmsrd r10,1 ; /* Set RI (EE=0) */ \ + b system_call_common ; +#endif + +EXC_REAL_BEGIN(system_call, 0xc00, 0xd00) + /* + * If CONFIG_KVM_BOOK3S_64_HANDLER is set, save the PPR (on systems + * that support it) before changing to HMT_MEDIUM. That allows the KVM + * code to save that value into the guest state (it is the guest's PPR + * value). Otherwise just change to HMT_MEDIUM as userspace has + * already saved the PPR. + */ +#ifdef CONFIG_KVM_BOOK3S_64_HANDLER + SET_SCRATCH0(r13) + GET_PACA(r13) + std r9,PACA_EXGEN+EX_R9(r13) + OPT_GET_SPR(r9, SPRN_PPR, CPU_FTR_HAS_PPR); + HMT_MEDIUM; + std r10,PACA_EXGEN+EX_R10(r13) + OPT_SAVE_REG_TO_PACA(PACA_EXGEN+EX_PPR, r9, CPU_FTR_HAS_PPR); + mfcr r9 + KVMTEST_PR(0xc00) + GET_SCRATCH0(r13) +#else + HMT_MEDIUM; +#endif + SYSCALL_PSERIES_1 + SYSCALL_PSERIES_2_RFID + SYSCALL_PSERIES_3 +EXC_REAL_END(system_call, 0xc00, 0xd00) + +EXC_VIRT_BEGIN(system_call, 0x4c00, 0x4d00) + HMT_MEDIUM + SYSCALL_PSERIES_1 + SYSCALL_PSERIES_2_DIRECT + SYSCALL_PSERIES_3 +EXC_VIRT_END(system_call, 0x4c00, 0x4d00) + +TRAMP_KVM(PACA_EXGEN, 0xc00) + + +EXC_REAL(single_step, 0xd00, 0xe00) +EXC_VIRT(single_step, 0x4d00, 0x4e00, 0xd00) +TRAMP_KVM(PACA_EXGEN, 0xd00) +EXC_COMMON(single_step_common, 0xd00, single_step_exception) + +EXC_REAL_OOL_HV(h_data_storage, 0xe00, 0xe20) +EXC_VIRT_NONE(0x4e00, 0x4e20) +TRAMP_KVM_HV_SKIP(PACA_EXGEN, 0xe00) +EXC_COMMON_BEGIN(h_data_storage_common) + mfspr r10,SPRN_HDAR + std r10,PACA_EXGEN+EX_DAR(r13) + mfspr r10,SPRN_HDSISR + stw r10,PACA_EXGEN+EX_DSISR(r13) + EXCEPTION_PROLOG_COMMON(0xe00, PACA_EXGEN) + bl save_nvgprs + RECONCILE_IRQ_STATE(r10, r11) + addi r3,r1,STACK_FRAME_OVERHEAD + bl unknown_exception + b ret_from_except + + +EXC_REAL_OOL_HV(h_instr_storage, 0xe20, 0xe40) +EXC_VIRT_NONE(0x4e20, 0x4e40) +TRAMP_KVM_HV(PACA_EXGEN, 0xe20) +EXC_COMMON(h_instr_storage_common, 0xe20, unknown_exception) + + +EXC_REAL_OOL_HV(emulation_assist, 0xe40, 0xe60) +EXC_VIRT_OOL_HV(emulation_assist, 0x4e40, 0x4e60, 0xe40) +TRAMP_KVM_HV(PACA_EXGEN, 0xe40) +EXC_COMMON(emulation_assist_common, 0xe40, emulation_assist_interrupt) + + +/* + * hmi_exception trampoline is a special case. It jumps to hmi_exception_early + * first, and then eventaully from there to the trampoline to get into virtual + * mode. + */ +__EXC_REAL_OOL_HV_DIRECT(hmi_exception, 0xe60, 0xe80, hmi_exception_early) +__TRAMP_REAL_REAL_OOL_MASKABLE_HV(hmi_exception, 0xe60) +EXC_VIRT_NONE(0x4e60, 0x4e80) +TRAMP_KVM_HV(PACA_EXGEN, 0xe60) +TRAMP_REAL_BEGIN(hmi_exception_early) + EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST_HV, 0xe60) + mr r10,r1 /* Save r1 */ + ld r1,PACAEMERGSP(r13) /* Use emergency stack */ + subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */ + std r9,_CCR(r1) /* save CR in stackframe */ + mfspr r11,SPRN_HSRR0 /* Save HSRR0 */ + std r11,_NIP(r1) /* save HSRR0 in stackframe */ + mfspr r12,SPRN_HSRR1 /* Save SRR1 */ + std r12,_MSR(r1) /* save SRR1 in stackframe */ + std r10,0(r1) /* make stack chain pointer */ + std r0,GPR0(r1) /* save r0 in stackframe */ + std r10,GPR1(r1) /* save r1 in stackframe */ + EXCEPTION_PROLOG_COMMON_2(PACA_EXGEN) + EXCEPTION_PROLOG_COMMON_3(0xe60) + addi r3,r1,STACK_FRAME_OVERHEAD + bl hmi_exception_realmode + /* Windup the stack. */ + /* Move original HSRR0 and HSRR1 into the respective regs */ + ld r9,_MSR(r1) + mtspr SPRN_HSRR1,r9 + ld r3,_NIP(r1) + mtspr SPRN_HSRR0,r3 + ld r9,_CTR(r1) + mtctr r9 + ld r9,_XER(r1) + mtxer r9 + ld r9,_LINK(r1) + mtlr r9 + REST_GPR(0, r1) + REST_8GPRS(2, r1) + REST_GPR(10, r1) + ld r11,_CCR(r1) + mtcr r11 + REST_GPR(11, r1) + REST_2GPRS(12, r1) + /* restore original r1. */ + ld r1,GPR1(r1) + + /* + * Go to virtual mode and pull the HMI event information from + * firmware. + */ + .globl hmi_exception_after_realmode +hmi_exception_after_realmode: + SET_SCRATCH0(r13) + EXCEPTION_PROLOG_0(PACA_EXGEN) + b tramp_real_hmi_exception + +EXC_COMMON_ASYNC(hmi_exception_common, 0xe60, handle_hmi_exception) + + +EXC_REAL_OOL_MASKABLE_HV(h_doorbell, 0xe80, 0xea0) +EXC_VIRT_OOL_MASKABLE_HV(h_doorbell, 0x4e80, 0x4ea0, 0xe80) +TRAMP_KVM_HV(PACA_EXGEN, 0xe80) +#ifdef CONFIG_PPC_DOORBELL +EXC_COMMON_ASYNC(h_doorbell_common, 0xe80, doorbell_exception) +#else +EXC_COMMON_ASYNC(h_doorbell_common, 0xe80, unknown_exception) +#endif + + +EXC_REAL_OOL_MASKABLE_HV(h_virt_irq, 0xea0, 0xec0) +EXC_VIRT_OOL_MASKABLE_HV(h_virt_irq, 0x4ea0, 0x4ec0, 0xea0) +TRAMP_KVM_HV(PACA_EXGEN, 0xea0) +EXC_COMMON_ASYNC(h_virt_irq_common, 0xea0, do_IRQ) + + +EXC_REAL_NONE(0xec0, 0xf00) +EXC_VIRT_NONE(0x4ec0, 0x4f00) + + +EXC_REAL_OOL(performance_monitor, 0xf00, 0xf20) +EXC_VIRT_OOL(performance_monitor, 0x4f00, 0x4f20, 0xf00) +TRAMP_KVM(PACA_EXGEN, 0xf00) +EXC_COMMON_ASYNC(performance_monitor_common, 0xf00, performance_monitor_exception) + + +EXC_REAL_OOL(altivec_unavailable, 0xf20, 0xf40) +EXC_VIRT_OOL(altivec_unavailable, 0x4f20, 0x4f40, 0xf20) +TRAMP_KVM(PACA_EXGEN, 0xf20) +EXC_COMMON_BEGIN(altivec_unavailable_common) + EXCEPTION_PROLOG_COMMON(0xf20, PACA_EXGEN) +#ifdef CONFIG_ALTIVEC +BEGIN_FTR_SECTION + beq 1f +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + BEGIN_FTR_SECTION_NESTED(69) + /* Test if 2 TM state bits are zero. If non-zero (ie. userspace was in + * transaction), go do TM stuff + */ + rldicl. r0, r12, (64-MSR_TS_LG), (64-2) + bne- 2f + END_FTR_SECTION_NESTED(CPU_FTR_TM, CPU_FTR_TM, 69) +#endif + bl load_up_altivec + b fast_exception_return +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +2: /* User process was in a transaction */ + bl save_nvgprs + RECONCILE_IRQ_STATE(r10, r11) + addi r3,r1,STACK_FRAME_OVERHEAD + bl altivec_unavailable_tm + b ret_from_except +#endif +1: +END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) +#endif + bl save_nvgprs + RECONCILE_IRQ_STATE(r10, r11) + addi r3,r1,STACK_FRAME_OVERHEAD + bl altivec_unavailable_exception + b ret_from_except + + +EXC_REAL_OOL(vsx_unavailable, 0xf40, 0xf60) +EXC_VIRT_OOL(vsx_unavailable, 0x4f40, 0x4f60, 0xf40) +TRAMP_KVM(PACA_EXGEN, 0xf40) +EXC_COMMON_BEGIN(vsx_unavailable_common) + EXCEPTION_PROLOG_COMMON(0xf40, PACA_EXGEN) +#ifdef CONFIG_VSX +BEGIN_FTR_SECTION + beq 1f +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + BEGIN_FTR_SECTION_NESTED(69) + /* Test if 2 TM state bits are zero. If non-zero (ie. userspace was in + * transaction), go do TM stuff + */ + rldicl. r0, r12, (64-MSR_TS_LG), (64-2) + bne- 2f + END_FTR_SECTION_NESTED(CPU_FTR_TM, CPU_FTR_TM, 69) +#endif + b load_up_vsx +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +2: /* User process was in a transaction */ + bl save_nvgprs + RECONCILE_IRQ_STATE(r10, r11) + addi r3,r1,STACK_FRAME_OVERHEAD + bl vsx_unavailable_tm + b ret_from_except +#endif +1: +END_FTR_SECTION_IFSET(CPU_FTR_VSX) +#endif + bl save_nvgprs + RECONCILE_IRQ_STATE(r10, r11) + addi r3,r1,STACK_FRAME_OVERHEAD + bl vsx_unavailable_exception + b ret_from_except + + +EXC_REAL_OOL(facility_unavailable, 0xf60, 0xf80) +EXC_VIRT_OOL(facility_unavailable, 0x4f60, 0x4f80, 0xf60) +TRAMP_KVM(PACA_EXGEN, 0xf60) +EXC_COMMON(facility_unavailable_common, 0xf60, facility_unavailable_exception) + + +EXC_REAL_OOL_HV(h_facility_unavailable, 0xf80, 0xfa0) +EXC_VIRT_OOL_HV(h_facility_unavailable, 0x4f80, 0x4fa0, 0xf80) +TRAMP_KVM_HV(PACA_EXGEN, 0xf80) +EXC_COMMON(h_facility_unavailable_common, 0xf80, facility_unavailable_exception) + + +EXC_REAL_NONE(0xfa0, 0x1200) +EXC_VIRT_NONE(0x4fa0, 0x5200) + +#ifdef CONFIG_CBE_RAS +EXC_REAL_HV(cbe_system_error, 0x1200, 0x1300) +EXC_VIRT_NONE(0x5200, 0x5300) +TRAMP_KVM_HV_SKIP(PACA_EXGEN, 0x1200) +EXC_COMMON(cbe_system_error_common, 0x1200, cbe_system_error_exception) +#else /* CONFIG_CBE_RAS */ +EXC_REAL_NONE(0x1200, 0x1300) +EXC_VIRT_NONE(0x5200, 0x5300) +#endif + + +EXC_REAL(instruction_breakpoint, 0x1300, 0x1400) +EXC_VIRT(instruction_breakpoint, 0x5300, 0x5400, 0x1300) +TRAMP_KVM_SKIP(PACA_EXGEN, 0x1300) +EXC_COMMON(instruction_breakpoint_common, 0x1300, instruction_breakpoint_exception) + +EXC_REAL_NONE(0x1400, 0x1500) +EXC_VIRT_NONE(0x5400, 0x5500) + +EXC_REAL_BEGIN(denorm_exception_hv, 0x1500, 0x1600) + mtspr SPRN_SPRG_HSCRATCH0,r13 + EXCEPTION_PROLOG_0(PACA_EXGEN) + EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, 0x1500) + +#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 + + KVMTEST_PR(0x1500) + EXCEPTION_PROLOG_PSERIES_1(denorm_common, EXC_HV) +EXC_REAL_END(denorm_exception_hv, 0x1500, 0x1600) + +#ifdef CONFIG_PPC_DENORMALISATION +EXC_VIRT_BEGIN(denorm_exception, 0x5500, 0x5600) + b exc_real_0x1500_denorm_exception_hv +EXC_VIRT_END(denorm_exception, 0x5500, 0x5600) +#else +EXC_VIRT_NONE(0x5500, 0x5600) +#endif + +TRAMP_KVM_SKIP(PACA_EXGEN, 0x1500) + +#ifdef CONFIG_PPC_DENORMALISATION +TRAMP_REAL_BEGIN(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 + +#define FMR2(n) fmr (n), (n) ; fmr n+1, n+1 +#define FMR4(n) FMR2(n) ; FMR2(n+2) +#define FMR8(n) FMR4(n) ; FMR4(n+4) +#define FMR16(n) FMR8(n) ; FMR8(n+8) +#define FMR32(n) FMR16(n) ; FMR16(n+16) + FMR32(0) + +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 + +#define XVCPSGNDP2(n) XVCPSGNDP(n,n,n) ; XVCPSGNDP(n+1,n+1,n+1) +#define XVCPSGNDP4(n) XVCPSGNDP2(n) ; XVCPSGNDP2(n+2) +#define XVCPSGNDP8(n) XVCPSGNDP4(n) ; XVCPSGNDP4(n+4) +#define XVCPSGNDP16(n) XVCPSGNDP8(n) ; XVCPSGNDP8(n+8) +#define XVCPSGNDP32(n) XVCPSGNDP16(n) ; XVCPSGNDP16(n+16) + XVCPSGNDP32(0) + +ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_206) + +BEGIN_FTR_SECTION + b denorm_done +END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) +/* + * To denormalise we need to move a copy of the register to itself. + * For POWER8 we need to do that for all 64 VSX registers + */ + XVCPSGNDP32(32) +denorm_done: + mtspr SPRN_HSRR0,r11 + mtcrf 0x80,r9 + ld r9,PACA_EXGEN+EX_R9(r13) + RESTORE_PPR_PACA(PACA_EXGEN, r10) +BEGIN_FTR_SECTION + ld r10,PACA_EXGEN+EX_CFAR(r13) + mtspr SPRN_CFAR,r10 +END_FTR_SECTION_IFSET(CPU_FTR_CFAR) + 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 + +EXC_COMMON_HV(denorm_common, 0x1500, unknown_exception) + + +#ifdef CONFIG_CBE_RAS +EXC_REAL_HV(cbe_maintenance, 0x1600, 0x1700) +EXC_VIRT_NONE(0x5600, 0x5700) +TRAMP_KVM_HV_SKIP(PACA_EXGEN, 0x1600) +EXC_COMMON(cbe_maintenance_common, 0x1600, cbe_maintenance_exception) +#else /* CONFIG_CBE_RAS */ +EXC_REAL_NONE(0x1600, 0x1700) +EXC_VIRT_NONE(0x5600, 0x5700) +#endif + + +EXC_REAL(altivec_assist, 0x1700, 0x1800) +EXC_VIRT(altivec_assist, 0x5700, 0x5800, 0x1700) +TRAMP_KVM(PACA_EXGEN, 0x1700) +#ifdef CONFIG_ALTIVEC +EXC_COMMON(altivec_assist_common, 0x1700, altivec_assist_exception) +#else +EXC_COMMON(altivec_assist_common, 0x1700, unknown_exception) +#endif + + +#ifdef CONFIG_CBE_RAS +EXC_REAL_HV(cbe_thermal, 0x1800, 0x1900) +EXC_VIRT_NONE(0x5800, 0x5900) +TRAMP_KVM_HV_SKIP(PACA_EXGEN, 0x1800) +EXC_COMMON(cbe_thermal_common, 0x1800, cbe_thermal_exception) +#else /* CONFIG_CBE_RAS */ +EXC_REAL_NONE(0x1800, 0x1900) +EXC_VIRT_NONE(0x5800, 0x5900) +#endif + + +/* + * An interrupt came in while soft-disabled. We set paca->irq_happened, then: + * - If it was a decrementer interrupt, we bump the dec to max and and return. + * - If it was a doorbell we return immediately since doorbells are edge + * triggered and won't automatically refire. + * - If it was a HMI we return immediately since we handled it in realmode + * and it won't refire. + * - else we hard disable and return. + * This is called with r10 containing the value to OR to the paca field. + */ +#define MASKED_INTERRUPT(_H) \ +masked_##_H##interrupt: \ + std r11,PACA_EXGEN+EX_R11(r13); \ + lbz r11,PACAIRQHAPPENED(r13); \ + or r11,r11,r10; \ + stb r11,PACAIRQHAPPENED(r13); \ + cmpwi r10,PACA_IRQ_DEC; \ + bne 1f; \ + lis r10,0x7fff; \ + ori r10,r10,0xffff; \ + mtspr SPRN_DEC,r10; \ + b 2f; \ +1: cmpwi r10,PACA_IRQ_DBELL; \ + beq 2f; \ + cmpwi r10,PACA_IRQ_HMI; \ + beq 2f; \ + mfspr r10,SPRN_##_H##SRR1; \ + rldicl r10,r10,48,1; /* clear MSR_EE */ \ + rotldi r10,r10,16; \ + mtspr SPRN_##_H##SRR1,r10; \ +2: mtcrf 0x80,r9; \ + ld r9,PACA_EXGEN+EX_R9(r13); \ + ld r10,PACA_EXGEN+EX_R10(r13); \ + ld r11,PACA_EXGEN+EX_R11(r13); \ + GET_SCRATCH0(r13); \ + ##_H##rfid; \ + b . + +/* + * Real mode exceptions actually use this too, but alternate + * instruction code patches (which end up in the common .text area) + * cannot reach these if they are put there. + */ +USE_FIXED_SECTION(virt_trampolines) + MASKED_INTERRUPT() + MASKED_INTERRUPT(H) + +#ifdef CONFIG_KVM_BOOK3S_64_HANDLER +TRAMP_REAL_BEGIN(kvmppc_skip_interrupt) + /* + * Here all GPRs are unchanged from when the interrupt happened + * except for r13, which is saved in SPRG_SCRATCH0. + */ + mfspr r13, SPRN_SRR0 + addi r13, r13, 4 + mtspr SPRN_SRR0, r13 + GET_SCRATCH0(r13) + rfid + b . + +TRAMP_REAL_BEGIN(kvmppc_skip_Hinterrupt) + /* + * Here all GPRs are unchanged from when the interrupt happened + * except for r13, which is saved in SPRG_SCRATCH0. + */ + mfspr r13, SPRN_HSRR0 + addi r13, r13, 4 + mtspr SPRN_HSRR0, r13 + GET_SCRATCH0(r13) + hrfid + b . +#endif + +/* + * 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 ***/ + + + /* + * Relocation-on interrupts: A subset of the interrupts can be delivered + * with IR=1/DR=1, if AIL==2 and MSR.HV won't be changed by delivering + * it. Addresses are the same as the original interrupt addresses, but + * offset by 0xc000000000004000. + * It's impossible to receive interrupts below 0x300 via this mechanism. + * KVM: None of these traps are from the guest ; anything that escalated + * to HV=1 from HV=0 is delivered via real mode handlers. + */ + + /* + * This uses the standard macro, since the original 0x300 vector + * only has extra guff for STAB-based processors -- which never + * come here. + */ + +EXC_COMMON_BEGIN(ppc64_runlatch_on_trampoline) + b __ppc64_runlatch_on + +USE_FIXED_SECTION(virt_trampolines) + /* + * The __end_interrupts marker must be past the out-of-line (OOL) + * handlers, so that they are copied to real address 0x100 when running + * a relocatable kernel. This ensures they can be reached from the short + * trampoline handlers (like 0x4f00, 0x4f20, etc.) which branch + * directly, without using LOAD_HANDLER(). + */ + .align 7 + .globl __end_interrupts +__end_interrupts: +DEFINE_FIXED_SYMBOL(__end_interrupts) #ifdef CONFIG_PPC_970_NAP -power4_fixup_nap: +TRAMP_REAL_BEGIN(power4_fixup_nap) andc r9,r9,r10 std r9,TI_LOCAL_FLAGS(r11) ld r10,_LINK(r1) /* make idle task do the */ @@ -1480,6 +1385,13 @@ power4_fixup_nap: blr #endif +CLOSE_FIXED_SECTION(real_vectors); +CLOSE_FIXED_SECTION(real_trampolines); +CLOSE_FIXED_SECTION(virt_vectors); +CLOSE_FIXED_SECTION(virt_trampolines); + +USE_TEXT_SECTION() + /* * Hash table stuff */ @@ -1625,3 +1537,39 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR) 1: addi r3,r1,STACK_FRAME_OVERHEAD bl kernel_bad_stack b 1b + +/* + * Called from arch_local_irq_enable when an interrupt needs + * to be resent. r3 contains 0x500, 0x900, 0xa00 or 0xe80 to indicate + * which kind of interrupt. MSR:EE is already off. We generate a + * stackframe like if a real interrupt had happened. + * + * Note: While MSR:EE is off, we need to make sure that _MSR + * in the generated frame has EE set to 1 or the exception + * handler will not properly re-enable them. + */ +_GLOBAL(__replay_interrupt) + /* We are going to jump to the exception common code which + * will retrieve various register values from the PACA which + * we don't give a damn about, so we don't bother storing them. + */ + mfmsr r12 + mflr r11 + mfcr r9 + ori r12,r12,MSR_EE + cmpwi r3,0x900 + beq decrementer_common + cmpwi r3,0x500 + beq hardware_interrupt_common +BEGIN_FTR_SECTION + cmpwi r3,0xe80 + beq h_doorbell_common + cmpwi r3,0xea0 + beq h_virt_irq_common + cmpwi r3,0xe60 + beq hmi_exception_common +FTR_SECTION_ELSE + cmpwi r3,0xa00 + beq doorbell_super_common +ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE) + blr diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index b3a663333d36..963918e0974a 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -778,7 +778,11 @@ static int fadump_init_elfcore_header(char *bufp) elf->e_entry = 0; elf->e_phoff = sizeof(struct elfhdr); elf->e_shoff = 0; - elf->e_flags = ELF_CORE_EFLAGS; +#if defined(_CALL_ELF) + elf->e_flags = _CALL_ELF; +#else + elf->e_flags = 0; +#endif elf->e_ehsize = sizeof(struct elfhdr); elf->e_phentsize = sizeof(struct elf_phdr); elf->e_phnum = 0; @@ -1104,7 +1108,9 @@ static ssize_t fadump_release_memory_store(struct kobject *kobj, * Take away the '/proc/vmcore'. We are releasing the dump * memory, hence it will not be valid anymore. */ +#ifdef CONFIG_PROC_VMCORE vmcore_cleanup(); +#endif fadump_invalidate_release_mem(); } else diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S index 15da2b5df85e..08d14b096eb9 100644 --- a/arch/powerpc/kernel/fpu.S +++ b/arch/powerpc/kernel/fpu.S @@ -50,32 +50,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX); \ #define REST_32FPVSRS(n,c,base) __REST_32FPVSRS(n,__REG_##c,__REG_##base) #define SAVE_32FPVSRS(n,c,base) __SAVE_32FPVSRS(n,__REG_##c,__REG_##base) -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM -/* void do_load_up_transact_fpu(struct thread_struct *thread) - * - * This is similar to load_up_fpu but for the transactional version of the FP - * register set. It doesn't mess with the task MSR or valid flags. - * Furthermore, we don't do lazy FP with TM currently. - */ -_GLOBAL(do_load_up_transact_fpu) - mfmsr r6 - ori r5,r6,MSR_FP -#ifdef CONFIG_VSX -BEGIN_FTR_SECTION - oris r5,r5,MSR_VSX@h -END_FTR_SECTION_IFSET(CPU_FTR_VSX) -#endif - SYNC - MTMSRD(r5) - - addi r7,r3,THREAD_TRANSACT_FPSTATE - lfd fr0,FPSTATE_FPSCR(r7) - MTFSF_L(fr0) - REST_32FPVSRS(0, R4, R7) - - blr -#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ - /* * Load state from memory into FP registers including FPSCR. * Assumes the caller has enabled FP in the MSR. diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index dc0488b6f6e1..a3f821eb7e9a 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -266,7 +266,6 @@ __secondary_hold_acknowledge: #define EXCEPTION_PROLOG_2 \ - CLR_TOP32(r11); \ stw r10,_CCR(r11); /* save registers */ \ stw r12,GPR12(r11); \ stw r9,GPR9(r11); \ @@ -862,7 +861,6 @@ __secondary_start: /* ptr to phys current thread */ tophys(r4,r2) addi r4,r4,THREAD /* phys address of our thread_struct */ - CLR_TOP32(r4) mtspr SPRN_SPRG_THREAD,r4 li r3,0 mtspr SPRN_SPRG_RTAS,r3 /* 0 => not in RTAS */ @@ -949,7 +947,6 @@ start_here: /* ptr to phys current thread */ tophys(r4,r2) addi r4,r4,THREAD /* init task's THREAD */ - CLR_TOP32(r4) mtspr SPRN_SPRG_THREAD,r4 li r3,0 mtspr SPRN_SPRG_RTAS,r3 /* 0 => not in RTAS */ diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index f765b0434731..79da0641bae2 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -28,6 +28,7 @@ #include <asm/page.h> #include <asm/mmu.h> #include <asm/ppc_asm.h> +#include <asm/head-64.h> #include <asm/asm-offsets.h> #include <asm/bug.h> #include <asm/cputable.h> @@ -65,9 +66,14 @@ * 2. The kernel is entered at __start */ - .text - .globl _stext -_stext: +OPEN_FIXED_SECTION(first_256B, 0x0, 0x100) +USE_FIXED_SECTION(first_256B) + /* + * Offsets are relative from the start of fixed section, and + * first_256B starts at 0. Offsets are a bit easier to use here + * than the fixed section entry macros. + */ + . = 0x0 _GLOBAL(__start) /* NOP this out unconditionally */ BEGIN_FTR_SECTION @@ -104,6 +110,7 @@ __secondary_hold_acknowledge: . = 0x5c .globl __run_at_load __run_at_load: +DEFINE_FIXED_SYMBOL(__run_at_load) .long 0x72756e30 /* "run0" -- relocate to 0 by default */ #endif @@ -133,7 +140,7 @@ __secondary_hold: /* Tell the master cpu we're here */ /* Relocation is off & we are located at an address less */ /* than 0x100, so only need to grab low order offset. */ - std r24,__secondary_hold_acknowledge-_stext(0) + std r24,(ABS_ADDR(__secondary_hold_acknowledge))(0) sync li r26,0 @@ -141,7 +148,7 @@ __secondary_hold: tovirt(r26,r26) #endif /* All secondary cpus wait here until told to start. */ -100: ld r12,__secondary_hold_spinloop-_stext(r26) +100: ld r12,(ABS_ADDR(__secondary_hold_spinloop))(r26) cmpdi 0,r12,0 beq 100b @@ -166,12 +173,13 @@ __secondary_hold: #else BUG_OPCODE #endif +CLOSE_FIXED_SECTION(first_256B) /* This value is used to mark exception frames on the stack. */ .section ".toc","aw" exception_marker: .tc ID_72656773_68657265[TC],0x7265677368657265 - .text + .previous /* * On server, we include the exception vectors code here as it @@ -180,8 +188,12 @@ exception_marker: */ #ifdef CONFIG_PPC_BOOK3S #include "exceptions-64s.S" +#else +OPEN_TEXT_SECTION(0x100) #endif +USE_TEXT_SECTION() + #ifdef CONFIG_PPC_BOOK3E /* * The booting_thread_hwid holds the thread id we want to boot in cpu @@ -558,7 +570,7 @@ __after_prom_start: #if defined(CONFIG_PPC_BOOK3E) tovirt(r26,r26) /* on booke, we already run at PAGE_OFFSET */ #endif - lwz r7,__run_at_load-_stext(r26) + lwz r7,(FIXED_SYMBOL_ABS_ADDR(__run_at_load))(r26) #if defined(CONFIG_PPC_BOOK3E) tophys(r26,r26) #endif @@ -601,7 +613,7 @@ __after_prom_start: #if defined(CONFIG_PPC_BOOK3E) tovirt(r26,r26) /* on booke, we already run at PAGE_OFFSET */ #endif - lwz r7,__run_at_load-_stext(r26) + lwz r7,(FIXED_SYMBOL_ABS_ADDR(__run_at_load))(r26) cmplwi cr0,r7,1 bne 3f @@ -611,28 +623,35 @@ __after_prom_start: sub r5,r5,r11 #else /* just copy interrupts */ - LOAD_REG_IMMEDIATE(r5, __end_interrupts - _stext) + LOAD_REG_IMMEDIATE(r5, FIXED_SYMBOL_ABS_ADDR(__end_interrupts)) #endif b 5f 3: #endif - lis r5,(copy_to_here - _stext)@ha - addi r5,r5,(copy_to_here - _stext)@l /* # bytes of memory to copy */ + /* # bytes of memory to copy */ + lis r5,(ABS_ADDR(copy_to_here))@ha + addi r5,r5,(ABS_ADDR(copy_to_here))@l bl copy_and_flush /* copy the first n bytes */ /* this includes the code being */ /* executed here. */ - addis r8,r3,(4f - _stext)@ha /* Jump to the copy of this code */ - addi r12,r8,(4f - _stext)@l /* that we just made */ + /* Jump to the copy of this code that we just made */ + addis r8,r3,(ABS_ADDR(4f))@ha + addi r12,r8,(ABS_ADDR(4f))@l mtctr r12 bctr .balign 8 -p_end: .llong _end - _stext +p_end: .llong _end - copy_to_here -4: /* Now copy the rest of the kernel up to _end */ - addis r5,r26,(p_end - _stext)@ha - ld r5,(p_end - _stext)@l(r5) /* get _end */ +4: + /* + * Now copy the rest of the kernel up to _end, add + * _end - copy_to_here to the copy limit and run again. + */ + addis r8,r26,(ABS_ADDR(p_end))@ha + ld r8,(ABS_ADDR(p_end))@l(r8) + add r5,r5,r8 5: bl copy_and_flush /* copy the rest */ 9: b start_here_multiplatform diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 43ddaae42baf..3a185c51ce8f 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -151,7 +151,6 @@ turn_on_mmu: #define EXCEPTION_PROLOG_2 \ - CLR_TOP32(r11); \ stw r10,_CCR(r11); /* save registers */ \ stw r12,GPR12(r11); \ stw r9,GPR9(r11); \ diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index aec9a1b1d25b..9781c69eae57 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -206,7 +206,7 @@ void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs) /* * Handle debug exception notifications. */ -int __kprobes hw_breakpoint_handler(struct die_args *args) +int hw_breakpoint_handler(struct die_args *args) { int rc = NOTIFY_STOP; struct perf_event *bp; @@ -290,11 +290,12 @@ out: rcu_read_unlock(); return rc; } +NOKPROBE_SYMBOL(hw_breakpoint_handler); /* * Handle single-step exceptions following a DABR hit. */ -static int __kprobes single_step_dabr_instruction(struct die_args *args) +static int single_step_dabr_instruction(struct die_args *args) { struct pt_regs *regs = args->regs; struct perf_event *bp = NULL; @@ -329,11 +330,12 @@ static int __kprobes single_step_dabr_instruction(struct die_args *args) return NOTIFY_STOP; } +NOKPROBE_SYMBOL(single_step_dabr_instruction); /* * Handle debug exception notifications. */ -int __kprobes hw_breakpoint_exceptions_notify( +int hw_breakpoint_exceptions_notify( struct notifier_block *unused, unsigned long val, void *data) { int ret = NOTIFY_DONE; @@ -349,6 +351,7 @@ int __kprobes hw_breakpoint_exceptions_notify( return ret; } +NOKPROBE_SYMBOL(hw_breakpoint_exceptions_notify); /* * Release the user breakpoints used by ptrace diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c index c1ca9282f4a0..6ca9a2ffaac7 100644 --- a/arch/powerpc/kernel/ibmebus.c +++ b/arch/powerpc/kernel/ibmebus.c @@ -227,7 +227,7 @@ int ibmebus_request_irq(u32 ist, irq_handler_t handler, { unsigned int irq = irq_create_mapping(NULL, ist); - if (irq == NO_IRQ) + if (!irq) return -EINVAL; return request_irq(irq, handler, irq_flags, devname, dev_id); diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 08887cf2b20e..3c05c311e35e 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -67,6 +67,7 @@ #include <asm/smp.h> #include <asm/debug.h> #include <asm/livepatch.h> +#include <asm/asm-prototypes.h> #ifdef CONFIG_PPC64 #include <asm/paca.h> @@ -156,6 +157,15 @@ notrace unsigned int __check_irq_replay(void) } /* + * Check if an hypervisor Maintenance interrupt happened. + * This is a higher priority interrupt than the others, so + * replay it first. + */ + local_paca->irq_happened &= ~PACA_IRQ_HMI; + if (happened & PACA_IRQ_HMI) + return 0xe60; + + /* * We may have missed a decrementer interrupt. We check the * decrementer itself rather than the paca irq_happened field * in case we also had a rollover while hard disabled @@ -190,11 +200,6 @@ notrace unsigned int __check_irq_replay(void) } #endif /* CONFIG_PPC_BOOK3E */ - /* Check if an hypervisor Maintenance interrupt happened */ - local_paca->irq_happened &= ~PACA_IRQ_HMI; - if (happened & PACA_IRQ_HMI) - return 0xe60; - /* There should be nothing left ! */ BUG_ON(local_paca->irq_happened != 0); @@ -514,7 +519,7 @@ void __do_irq(struct pt_regs *regs) may_hard_irq_enable(); /* And finally process it */ - if (unlikely(irq == NO_IRQ)) + if (unlikely(!irq)) __this_cpu_inc(irq_stat.spurious_irqs); else generic_handle_irq(irq); diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c index 7b750c4ed5c7..bc525ea0dc09 100644 --- a/arch/powerpc/kernel/legacy_serial.c +++ b/arch/powerpc/kernel/legacy_serial.c @@ -193,10 +193,10 @@ static int __init add_legacy_soc_port(struct device_node *np, */ if (tsi && !strcmp(tsi->type, "tsi-bridge")) return add_legacy_port(np, -1, UPIO_TSI, addr, addr, - NO_IRQ, legacy_port_flags, 0); + 0, legacy_port_flags, 0); else return add_legacy_port(np, -1, UPIO_MEM, addr, addr, - NO_IRQ, legacy_port_flags, 0); + 0, legacy_port_flags, 0); } static int __init add_legacy_isa_port(struct device_node *np, @@ -242,7 +242,7 @@ static int __init add_legacy_isa_port(struct device_node *np, /* Add port, irq will be dealt with later */ return add_legacy_port(np, index, UPIO_PORT, be32_to_cpu(reg[1]), - taddr, NO_IRQ, legacy_port_flags, 0); + taddr, 0, legacy_port_flags, 0); } @@ -314,7 +314,7 @@ static int __init add_legacy_pci_port(struct device_node *np, /* Add port, irq will be dealt with later. We passed a translated * IO port value. It will be fixed up later along with the irq */ - return add_legacy_port(np, index, iotype, base, addr, NO_IRQ, + return add_legacy_port(np, index, iotype, base, addr, 0, legacy_port_flags, np != pci_dev); } #endif @@ -462,14 +462,14 @@ static void __init fixup_port_irq(int index, DBG("fixup_port_irq(%d)\n", index); virq = irq_of_parse_and_map(np, 0); - if (virq == NO_IRQ && legacy_serial_infos[index].irq_check_parent) { + if (!virq && legacy_serial_infos[index].irq_check_parent) { np = of_get_parent(np); if (np == NULL) return; virq = irq_of_parse_and_map(np, 0); of_node_put(np); } - if (virq == NO_IRQ) + if (!virq) return; port->irq = virq; @@ -543,7 +543,7 @@ static int __init serial_dev_init(void) struct plat_serial8250_port *port = &legacy_serial_ports[i]; struct device_node *np = legacy_serial_infos[i].np; - if (port->irq == NO_IRQ) + if (!port->irq) fixup_port_irq(i, np, port); if (port->iotype == UPIO_PORT) fixup_port_pio(i, np, port); diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c index 4c780a342282..a205fa3d9bf3 100644 --- a/arch/powerpc/kernel/machine_kexec_64.c +++ b/arch/powerpc/kernel/machine_kexec_64.c @@ -23,6 +23,7 @@ #include <asm/current.h> #include <asm/machdep.h> #include <asm/cacheflush.h> +#include <asm/firmware.h> #include <asm/paca.h> #include <asm/mmu.h> #include <asm/sections.h> /* _end */ @@ -31,21 +32,6 @@ #include <asm/hw_breakpoint.h> #include <asm/asm-prototypes.h> -#ifdef CONFIG_PPC_BOOK3E -int default_machine_kexec_prepare(struct kimage *image) -{ - int i; - /* - * Since we use the kernel fault handlers and paging code to - * handle the virtual mode, we must make sure no destination - * overlaps kernel static data or bss. - */ - for (i = 0; i < image->nr_segments; i++) - if (image->segment[i].mem < __pa(_end)) - return -ETXTBSY; - return 0; -} -#else int default_machine_kexec_prepare(struct kimage *image) { int i; @@ -55,9 +41,6 @@ int default_machine_kexec_prepare(struct kimage *image) const unsigned long *basep; const unsigned int *sizep; - if (!mmu_hash_ops.hpte_clear_all) - return -ENOENT; - /* * Since we use the kernel fault handlers and paging code to * handle the virtual mode, we must make sure no destination @@ -67,31 +50,6 @@ int default_machine_kexec_prepare(struct kimage *image) if (image->segment[i].mem < __pa(_end)) return -ETXTBSY; - /* - * For non-LPAR, we absolutely can not overwrite the mmu hash - * table, since we are still using the bolted entries in it to - * do the copy. Check that here. - * - * It is safe if the end is below the start of the blocked - * region (end <= low), or if the beginning is after the - * 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; - - for (i = 0; i < image->nr_segments; i++) { - begin = image->segment[i].mem; - end = begin + image->segment[i].memsz; - - if ((begin < high) && (end > low)) - return -ETXTBSY; - } - } -#endif /* CONFIG_PPC_STD_MMU_64 */ - /* We also should not overwrite the tce tables */ for_each_node_by_type(node, "pci") { basep = of_get_property(node, "linux,tce-base", NULL); @@ -113,7 +71,6 @@ int default_machine_kexec_prepare(struct kimage *image) return 0; } -#endif /* !CONFIG_PPC_BOOK3E */ static void copy_segments(unsigned long ind) { @@ -332,11 +289,14 @@ struct paca_struct kexec_paca; /* Our assembly helper, in misc_64.S */ extern void kexec_sequence(void *newstack, unsigned long start, void *image, void *control, - void (*clear_all)(void)) __noreturn; + void (*clear_all)(void), + bool copy_with_mmu_off) __noreturn; /* too late to fail here */ void default_machine_kexec(struct kimage *image) { + bool copy_with_mmu_off; + /* prepare control code if any */ /* @@ -374,18 +334,29 @@ void default_machine_kexec(struct kimage *image) /* XXX: If anyone does 'dynamic lppacas' this will also need to be * switched to a static version! */ + /* + * On Book3S, the copy must happen with the MMU off if we are either + * using Radix page tables or we are not in an LPAR since we can + * overwrite the page tables while copying. + * + * In an LPAR, we keep the MMU on otherwise we can't access beyond + * the RMA. On BookE there is no real MMU off mode, so we have to + * keep it enabled as well (but then we have bolted TLB entries). + */ +#ifdef CONFIG_PPC_BOOK3E + copy_with_mmu_off = false; +#else + copy_with_mmu_off = radix_enabled() || + !(firmware_has_feature(FW_FEATURE_LPAR) || + firmware_has_feature(FW_FEATURE_PS3_LV1)); +#endif /* Some things are best done in assembly. Finding globals with * a toc is easier in C, so pass in what we can. */ kexec_sequence(&kexec_stack, image->start, image, - page_address(image->control_code_page), -#ifdef CONFIG_PPC_STD_MMU - mmu_hash_ops.hpte_clear_all -#else - NULL -#endif - ); + page_address(image->control_code_page), + mmu_cleanup_all, copy_with_mmu_off); /* NOTREACHED */ } diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index d9c912b6e632..03756ffdcd71 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -328,7 +328,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_UNIFIED_ID_CACHE) * * flush_icache_range(unsigned long start, unsigned long stop) */ -_KPROBE(flush_icache_range) +_GLOBAL(flush_icache_range) BEGIN_FTR_SECTION PURGE_PREFETCHED_INS blr /* for 601, do nothing */ @@ -358,6 +358,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) sync /* additional sync needed on g4 */ isync blr +_ASM_NOKPROBE_SYMBOL(flush_icache_range) + /* * Flush a particular page from the data cache to RAM. * Note: this is necessary because the instruction cache does *not* diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index cb195157b318..9f0bed214bcb 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -66,7 +66,7 @@ PPC64_CACHES: * flush all bytes from start through stop-1 inclusive */ -_KPROBE(flush_icache_range) +_GLOBAL(flush_icache_range) BEGIN_FTR_SECTION PURGE_PREFETCHED_INS blr @@ -109,7 +109,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) bdnz 2b isync blr - .previous .text +_ASM_NOKPROBE_SYMBOL(flush_icache_range) + /* * Like above, but only do the D-cache. * @@ -591,7 +592,8 @@ real_mode: /* assume normal blr return */ #endif /* - * kexec_sequence(newstack, start, image, control, clear_all()) + * kexec_sequence(newstack, start, image, control, clear_all(), + copy_with_mmu_off) * * does the grungy work with stack switching and real mode switches * also does simple calls to other code @@ -627,7 +629,7 @@ _GLOBAL(kexec_sequence) mr r29,r5 /* image (virt) */ mr r28,r6 /* control, unused */ mr r27,r7 /* clear_all() fn desc */ - mr r26,r8 /* spare */ + mr r26,r8 /* copy_with_mmu_off */ lhz r25,PACAHWCPUID(r13) /* get our phys cpu from paca */ /* disable interrupts, we are overwriting kernel data next */ @@ -639,15 +641,24 @@ _GLOBAL(kexec_sequence) mtmsrd r3,1 #endif + /* We need to turn the MMU off unless we are in hash mode + * under a hypervisor + */ + cmpdi r26,0 + beq 1f + bl real_mode +1: /* copy dest pages, flush whole dest image */ mr r3,r29 bl kexec_copy_flush /* (image) */ - /* turn off mmu */ + /* turn off mmu now if not done earlier */ + cmpdi r26,0 + bne 1f bl real_mode /* copy 0x100 bytes starting at start to 0 */ - li r3,0 +1: li r3,0 mr r4,r30 /* start, aka phys mem offset */ li r5,0x100 li r6,0 @@ -659,7 +670,9 @@ _GLOBAL(kexec_sequence) li r6,1 stw r6,kexec_flag-1b(5) -#ifndef CONFIG_PPC_BOOK3E + cmpdi r27,0 + beq 1f + /* clear out hardware hash page table and tlb */ #ifdef PPC64_ELF_ABI_v1 ld r12,0(r27) /* deref function descriptor */ @@ -668,7 +681,6 @@ _GLOBAL(kexec_sequence) #endif mtctr r12 bctrl /* mmu_hash_ops.hpte_clear_all(void); */ -#endif /* !CONFIG_PPC_BOOK3E */ /* * kexec image calling is: @@ -695,7 +707,7 @@ _GLOBAL(kexec_sequence) * are the boot cpu ????? * other device tree differences (prop sizes, va vs pa, etc)... */ - mr r3,r25 # my phys cpu +1: mr r3,r25 # my phys cpu mr r4,r30 # start, aka phys mem offset mtlr 4 li r5,0 diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c index d1f1b35bf0c7..30b89d5cbb03 100644 --- a/arch/powerpc/kernel/module.c +++ b/arch/powerpc/kernel/module.c @@ -27,7 +27,7 @@ #include <linux/sort.h> #include <asm/setup.h> -LIST_HEAD(module_bug_list); +static LIST_HEAD(module_bug_list); static const Elf_Shdr *find_section(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index 64174bf95611..34d2c595de23 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -542,9 +542,9 @@ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type, time->tv_nsec = 0; } *buf = kmemdup(buff + hdr_size, length, GFP_KERNEL); + kfree(buff); if (*buf == NULL) return -ENOMEM; - kfree(buff); *ecc_notice_size = 0; if (err_type == ERR_TYPE_KERNEL_PANIC_GZ) @@ -851,7 +851,7 @@ static long dev_nvram_ioctl(struct file *file, unsigned int cmd, } } -const struct file_operations nvram_fops = { +static const struct file_operations nvram_fops = { .owner = THIS_MODULE, .llseek = dev_nvram_llseek, .read = dev_nvram_read, @@ -956,7 +956,7 @@ int __init nvram_remove_partition(const char *name, int sig, /* Make partition a free partition */ part->header.signature = NVRAM_SIG_FREE; - strncpy(part->header.name, "wwwwwwwwwwww", 12); + memset(part->header.name, 'w', 12); part->header.checksum = nvram_checksum(&part->header); rc = nvram_write_header(part); if (rc <= 0) { @@ -974,8 +974,8 @@ int __init nvram_remove_partition(const char *name, int sig, } if (prev) { prev->header.length += part->header.length; - prev->header.checksum = nvram_checksum(&part->header); - rc = nvram_write_header(part); + prev->header.checksum = nvram_checksum(&prev->header); + rc = nvram_write_header(prev); if (rc <= 0) { printk(KERN_ERR "nvram_remove_partition: nvram_write failed (%d)\n", rc); return rc; diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index e58908066b0e..95d3769a2e26 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -360,7 +360,7 @@ static int pci_read_irq_line(struct pci_dev *pci_dev) line, pin); virq = irq_create_mapping(NULL, line); - if (virq != NO_IRQ) + if (virq) irq_set_irq_type(virq, IRQ_TYPE_LEVEL_LOW); } else { pr_debug(" Got one, spec %d cells (0x%08x 0x%08x...) on %s\n", @@ -369,7 +369,8 @@ static int pci_read_irq_line(struct pci_dev *pci_dev) virq = irq_create_of_mapping(&oirq); } - if(virq == NO_IRQ) { + + if (!virq) { pr_debug(" Failed to map !\n"); return -1; } diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c index 526ac6750e4d..ea3d98115b88 100644 --- a/arch/powerpc/kernel/pci_of_scan.c +++ b/arch/powerpc/kernel/pci_of_scan.c @@ -178,7 +178,7 @@ struct pci_dev *of_create_pci_dev(struct device_node *node, dev->hdr_type = PCI_HEADER_TYPE_NORMAL; dev->rom_base_reg = PCI_ROM_ADDRESS; /* Maybe do a default OF mapping here */ - dev->irq = NO_IRQ; + dev->irq = 0; } of_pci_parse_addrs(node, dev); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 9ee2623e0f67..9e7c10fe205f 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -59,6 +59,7 @@ #include <asm/exec.h> #include <asm/livepatch.h> #include <asm/cpu_has_feature.h> +#include <asm/asm-prototypes.h> #include <linux/kprobes.h> #include <linux/kdebug.h> @@ -88,7 +89,13 @@ static void check_if_tm_restore_required(struct task_struct *tsk) set_thread_flag(TIF_RESTORE_TM); } } + +static inline bool msr_tm_active(unsigned long msr) +{ + return MSR_TM_ACTIVE(msr); +} #else +static inline bool msr_tm_active(unsigned long msr) { return false; } static inline void check_if_tm_restore_required(struct task_struct *tsk) { } #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ @@ -104,7 +111,7 @@ static int __init enable_strict_msr_control(char *str) } early_param("ppc_strict_facility_enable", enable_strict_msr_control); -void msr_check_and_set(unsigned long bits) +unsigned long msr_check_and_set(unsigned long bits) { unsigned long oldmsr = mfmsr(); unsigned long newmsr; @@ -118,6 +125,8 @@ void msr_check_and_set(unsigned long bits) if (oldmsr != newmsr) mtmsr_isync(newmsr); + + return newmsr; } void __msr_check_and_clear(unsigned long bits) @@ -196,19 +205,30 @@ EXPORT_SYMBOL_GPL(flush_fp_to_thread); void enable_kernel_fp(void) { + unsigned long cpumsr; + WARN_ON(preemptible()); - msr_check_and_set(MSR_FP); + cpumsr = msr_check_and_set(MSR_FP); if (current->thread.regs && (current->thread.regs->msr & MSR_FP)) { check_if_tm_restore_required(current); + /* + * If a thread has already been reclaimed then the + * checkpointed registers are on the CPU but have definitely + * been saved by the reclaim code. Don't need to and *cannot* + * giveup as this would save to the 'live' structure not the + * checkpointed structure. + */ + if(!msr_tm_active(cpumsr) && msr_tm_active(current->thread.regs->msr)) + return; __giveup_fpu(current); } } EXPORT_SYMBOL(enable_kernel_fp); static int restore_fp(struct task_struct *tsk) { - if (tsk->thread.load_fp) { + if (tsk->thread.load_fp || msr_tm_active(tsk->thread.regs->msr)) { load_fp_state(¤t->thread.fp_state); current->thread.load_fp++; return 1; @@ -248,12 +268,23 @@ EXPORT_SYMBOL(giveup_altivec); void enable_kernel_altivec(void) { + unsigned long cpumsr; + WARN_ON(preemptible()); - msr_check_and_set(MSR_VEC); + cpumsr = msr_check_and_set(MSR_VEC); if (current->thread.regs && (current->thread.regs->msr & MSR_VEC)) { check_if_tm_restore_required(current); + /* + * If a thread has already been reclaimed then the + * checkpointed registers are on the CPU but have definitely + * been saved by the reclaim code. Don't need to and *cannot* + * giveup as this would save to the 'live' structure not the + * checkpointed structure. + */ + if(!msr_tm_active(cpumsr) && msr_tm_active(current->thread.regs->msr)) + return; __giveup_altivec(current); } } @@ -278,7 +309,8 @@ EXPORT_SYMBOL_GPL(flush_altivec_to_thread); static int restore_altivec(struct task_struct *tsk) { - if (cpu_has_feature(CPU_FTR_ALTIVEC) && tsk->thread.load_vec) { + if (cpu_has_feature(CPU_FTR_ALTIVEC) && + (tsk->thread.load_vec || msr_tm_active(tsk->thread.regs->msr))) { load_vr_state(&tsk->thread.vr_state); tsk->thread.used_vr = 1; tsk->thread.load_vec++; @@ -321,12 +353,23 @@ static void save_vsx(struct task_struct *tsk) void enable_kernel_vsx(void) { + unsigned long cpumsr; + WARN_ON(preemptible()); - msr_check_and_set(MSR_FP|MSR_VEC|MSR_VSX); + cpumsr = msr_check_and_set(MSR_FP|MSR_VEC|MSR_VSX); if (current->thread.regs && (current->thread.regs->msr & MSR_VSX)) { check_if_tm_restore_required(current); + /* + * If a thread has already been reclaimed then the + * checkpointed registers are on the CPU but have definitely + * been saved by the reclaim code. Don't need to and *cannot* + * giveup as this would save to the 'live' structure not the + * checkpointed structure. + */ + if(!msr_tm_active(cpumsr) && msr_tm_active(current->thread.regs->msr)) + return; if (current->thread.regs->msr & MSR_FP) __giveup_fpu(current); if (current->thread.regs->msr & MSR_VEC) @@ -438,6 +481,7 @@ void giveup_all(struct task_struct *tsk) return; msr_check_and_set(msr_all_available); + check_if_tm_restore_required(tsk); #ifdef CONFIG_PPC_FPU if (usermsr & MSR_FP) @@ -464,7 +508,8 @@ void restore_math(struct pt_regs *regs) { unsigned long msr; - if (!current->thread.load_fp && !loadvec(current->thread)) + if (!msr_tm_active(regs->msr) && + !current->thread.load_fp && !loadvec(current->thread)) return; msr = regs->msr; @@ -767,29 +812,15 @@ static inline bool hw_brk_match(struct arch_hw_breakpoint *a, } #ifdef CONFIG_PPC_TRANSACTIONAL_MEM + +static inline bool tm_enabled(struct task_struct *tsk) +{ + return tsk && tsk->thread.regs && (tsk->thread.regs->msr & MSR_TM); +} + static void tm_reclaim_thread(struct thread_struct *thr, struct thread_info *ti, uint8_t cause) { - unsigned long msr_diff = 0; - - /* - * If FP/VSX registers have been already saved to the - * thread_struct, move them to the transact_fp array. - * We clear the TIF_RESTORE_TM bit since after the reclaim - * the thread will no longer be transactional. - */ - if (test_ti_thread_flag(ti, TIF_RESTORE_TM)) { - msr_diff = thr->ckpt_regs.msr & ~thr->regs->msr; - if (msr_diff & MSR_FP) - memcpy(&thr->transact_fp, &thr->fp_state, - sizeof(struct thread_fp_state)); - if (msr_diff & MSR_VEC) - memcpy(&thr->transact_vr, &thr->vr_state, - sizeof(struct thread_vr_state)); - clear_ti_thread_flag(ti, TIF_RESTORE_TM); - msr_diff &= MSR_FP | MSR_VEC | MSR_VSX | MSR_FE0 | MSR_FE1; - } - /* * Use the current MSR TM suspended bit to track if we have * checkpointed state outstanding. @@ -808,15 +839,9 @@ static void tm_reclaim_thread(struct thread_struct *thr, if (!MSR_TM_SUSPENDED(mfmsr())) return; - tm_reclaim(thr, thr->regs->msr, cause); + giveup_all(container_of(thr, struct task_struct, thread)); - /* Having done the reclaim, we now have the checkpointed - * FP/VSX values in the registers. These might be valid - * even if we have previously called enable_kernel_fp() or - * flush_fp_to_thread(), so update thr->regs->msr to - * indicate their current validity. - */ - thr->regs->msr |= msr_diff; + tm_reclaim(thr, thr->ckpt_regs.msr, cause); } void tm_reclaim_current(uint8_t cause) @@ -832,8 +857,8 @@ static inline void tm_reclaim_task(struct task_struct *tsk) * * In switching we need to maintain a 2nd register state as * oldtask->thread.ckpt_regs. We tm_reclaim(oldproc); this saves the - * checkpointed (tbegin) state in ckpt_regs and saves the transactional - * (current) FPRs into oldtask->thread.transact_fpr[]. + * checkpointed (tbegin) state in ckpt_regs, ckfp_state and + * ckvr_state * * We also context switch (save) TFHAR/TEXASR/TFIAR in here. */ @@ -845,14 +870,6 @@ static inline void tm_reclaim_task(struct task_struct *tsk) if (!MSR_TM_ACTIVE(thr->regs->msr)) goto out_and_saveregs; - /* Stash the original thread MSR, as giveup_fpu et al will - * modify it. We hold onto it to see whether the task used - * FP & vector regs. If the TIF_RESTORE_TM flag is set, - * ckpt_regs.msr is already set. - */ - if (!test_ti_thread_flag(task_thread_info(tsk), TIF_RESTORE_TM)) - thr->ckpt_regs.msr = thr->regs->msr; - TM_DEBUG("--- tm_reclaim on pid %d (NIP=%lx, " "ccr=%lx, msr=%lx, trap=%lx)\n", tsk->pid, thr->regs->nip, @@ -881,6 +898,9 @@ void tm_recheckpoint(struct thread_struct *thread, { unsigned long flags; + if (!(thread->regs->msr & MSR_TM)) + return; + /* We really can't be interrupted here as the TEXASR registers can't * change and later in the trecheckpoint code, we have a userspace R1. * So let's hard disable over this region. @@ -910,10 +930,10 @@ static inline void tm_recheckpoint_new_task(struct task_struct *new) * If the task was using FP, we non-lazily reload both the original and * the speculative FP register states. This is because the kernel * doesn't see if/when a TM rollback occurs, so if we take an FP - * unavoidable later, we are unable to determine which set of FP regs + * unavailable later, we are unable to determine which set of FP regs * need to be restored. */ - if (!new->thread.regs) + if (!tm_enabled(new)) return; if (!MSR_TM_ACTIVE(new->thread.regs->msr)){ @@ -926,35 +946,35 @@ static inline void tm_recheckpoint_new_task(struct task_struct *new) "(new->msr 0x%lx, new->origmsr 0x%lx)\n", new->pid, new->thread.regs->msr, msr); - /* This loads the checkpointed FP/VEC state, if used */ tm_recheckpoint(&new->thread, msr); - /* This loads the speculative FP/VEC state, if used */ - if (msr & MSR_FP) { - do_load_up_transact_fpu(&new->thread); - new->thread.regs->msr |= - (MSR_FP | new->thread.fpexc_mode); - } -#ifdef CONFIG_ALTIVEC - if (msr & MSR_VEC) { - do_load_up_transact_altivec(&new->thread); - new->thread.regs->msr |= MSR_VEC; - } -#endif - /* We may as well turn on VSX too since all the state is restored now */ - if (msr & MSR_VSX) - new->thread.regs->msr |= MSR_VSX; + /* + * The checkpointed state has been restored but the live state has + * not, ensure all the math functionality is turned off to trigger + * restore_math() to reload. + */ + new->thread.regs->msr &= ~(MSR_FP | MSR_VEC | MSR_VSX); TM_DEBUG("*** tm_recheckpoint of pid %d complete " "(kernel msr 0x%lx)\n", new->pid, mfmsr()); } -static inline void __switch_to_tm(struct task_struct *prev) +static inline void __switch_to_tm(struct task_struct *prev, + struct task_struct *new) { if (cpu_has_feature(CPU_FTR_TM)) { - tm_enable(); - tm_reclaim_task(prev); + if (tm_enabled(prev) || tm_enabled(new)) + tm_enable(); + + if (tm_enabled(prev)) { + prev->thread.load_tm++; + tm_reclaim_task(prev); + if (!MSR_TM_ACTIVE(prev->thread.regs->msr) && prev->thread.load_tm == 0) + prev->thread.regs->msr &= ~MSR_TM; + } + + tm_recheckpoint_new_task(new); } } @@ -976,6 +996,12 @@ void restore_tm_state(struct pt_regs *regs) { unsigned long msr_diff; + /* + * This is the only moment we should clear TIF_RESTORE_TM as + * it is here that ckpt_regs.msr and pt_regs.msr become the same + * again, anything else could lead to an incorrect ckpt_msr being + * saved and therefore incorrect signal contexts. + */ clear_thread_flag(TIF_RESTORE_TM); if (!MSR_TM_ACTIVE(regs->msr)) return; @@ -983,6 +1009,13 @@ void restore_tm_state(struct pt_regs *regs) msr_diff = current->thread.ckpt_regs.msr & ~regs->msr; msr_diff &= MSR_FP | MSR_VEC | MSR_VSX; + /* Ensure that restore_math() will restore */ + if (msr_diff & MSR_FP) + current->thread.load_fp = 1; +#ifdef CONFIG_ALIVEC + if (cpu_has_feature(CPU_FTR_ALTIVEC) && msr_diff & MSR_VEC) + current->thread.load_vec = 1; +#endif restore_math(regs); regs->msr |= msr_diff; @@ -990,7 +1023,7 @@ void restore_tm_state(struct pt_regs *regs) #else #define tm_recheckpoint_new_task(new) -#define __switch_to_tm(prev) +#define __switch_to_tm(prev, new) #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ static inline void save_sprs(struct thread_struct *t) @@ -1131,11 +1164,11 @@ struct task_struct *__switch_to(struct task_struct *prev, */ save_sprs(&prev->thread); - __switch_to_tm(prev); - /* Save FPU, Altivec, VSX and SPE state */ giveup_all(prev); + __switch_to_tm(prev, new); + /* * 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 @@ -1143,8 +1176,6 @@ struct task_struct *__switch_to(struct task_struct *prev, */ hard_irq_disable(); - tm_recheckpoint_new_task(new); - /* * Call restore_sprs() before calling _switch(). If we move it after * _switch() then we miss out on calling it for new tasks. The reason @@ -1379,9 +1410,11 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) * transitions the CPU out of TM mode. Hence we need to call * tm_recheckpoint_new_task() (on the same task) to restore the * checkpointed state back and the TM mode. + * + * Can't pass dst because it isn't ready. Doesn't matter, passing + * dst is only important for __switch_to() */ - __switch_to_tm(src); - tm_recheckpoint_new_task(src); + __switch_to_tm(src, src); *dst = *src; @@ -1623,8 +1656,6 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) current->thread.used_spe = 0; #endif /* CONFIG_SPE */ #ifdef CONFIG_PPC_TRANSACTIONAL_MEM - if (cpu_has_feature(CPU_FTR_TM)) - regs->msr |= MSR_TM; current->thread.tm_tfhar = 0; current->thread.tm_texasr = 0; current->thread.tm_tfiar = 0; diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index d3eff99e938c..88ac964f4858 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -42,6 +42,7 @@ #include <asm/sections.h> #include <asm/machdep.h> #include <asm/opal.h> +#include <asm/asm-prototypes.h> #include <linux/linux_logo.h> @@ -2643,6 +2644,86 @@ static void __init fixup_device_tree_efika(void) #define fixup_device_tree_efika() #endif +#ifdef CONFIG_PPC_PASEMI_NEMO +/* + * CFE supplied on Nemo is broken in several ways, biggest + * problem is that it reassigns ISA interrupts to unused mpic ints. + * Add an interrupt-controller property for the io-bridge to use + * and correct the ints so we can attach them to an irq_domain + */ +static void __init fixup_device_tree_pasemi(void) +{ + u32 interrupts[2], parent, rval, val = 0; + char *name, *pci_name; + phandle iob, node; + + /* Find the root pci node */ + name = "/pxp@0,e0000000"; + iob = call_prom("finddevice", 1, 1, ADDR(name)); + if (!PHANDLE_VALID(iob)) + return; + + /* check if interrupt-controller node set yet */ + if (prom_getproplen(iob, "interrupt-controller") !=PROM_ERROR) + return; + + prom_printf("adding interrupt-controller property for SB600...\n"); + + prom_setprop(iob, name, "interrupt-controller", &val, 0); + + pci_name = "/pxp@0,e0000000/pci@11"; + node = call_prom("finddevice", 1, 1, ADDR(pci_name)); + parent = ADDR(iob); + + for( ; prom_next_node(&node); ) { + /* scan each node for one with an interrupt */ + if (!PHANDLE_VALID(node)) + continue; + + rval = prom_getproplen(node, "interrupts"); + if (rval == 0 || rval == PROM_ERROR) + continue; + + prom_getprop(node, "interrupts", &interrupts, sizeof(interrupts)); + if ((interrupts[0] < 212) || (interrupts[0] > 222)) + continue; + + /* found a node, update both interrupts and interrupt-parent */ + if ((interrupts[0] >= 212) && (interrupts[0] <= 215)) + interrupts[0] -= 203; + if ((interrupts[0] >= 216) && (interrupts[0] <= 220)) + interrupts[0] -= 213; + if (interrupts[0] == 221) + interrupts[0] = 14; + if (interrupts[0] == 222) + interrupts[0] = 8; + + prom_setprop(node, pci_name, "interrupts", interrupts, + sizeof(interrupts)); + prom_setprop(node, pci_name, "interrupt-parent", &parent, + sizeof(parent)); + } + + /* + * The io-bridge has device_type set to 'io-bridge' change it to 'isa' + * so that generic isa-bridge code can add the SB600 and its on-board + * peripherals. + */ + name = "/pxp@0,e0000000/io-bridge@0"; + iob = call_prom("finddevice", 1, 1, ADDR(name)); + if (!PHANDLE_VALID(iob)) + return; + + /* device_type is already set, just change it. */ + + prom_printf("Changing device_type of SB600 node...\n"); + + prom_setprop(iob, name, "device_type", "isa", sizeof("isa")); +} +#else /* !CONFIG_PPC_PASEMI_NEMO */ +static inline void fixup_device_tree_pasemi(void) { } +#endif + static void __init fixup_device_tree(void) { fixup_device_tree_maple(); @@ -2650,6 +2731,7 @@ static void __init fixup_device_tree(void) fixup_device_tree_chrp(); fixup_device_tree_pmac(); fixup_device_tree_efika(); + fixup_device_tree_pasemi(); } static void __init prom_find_boot_cpu(void) diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index bf91658a8a40..b1ec62f2cc31 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -39,6 +39,7 @@ #include <asm/pgtable.h> #include <asm/switch_to.h> #include <asm/tm.h> +#include <asm/asm-prototypes.h> #define CREATE_TRACE_POINTS #include <trace/events/syscalls.h> @@ -402,13 +403,9 @@ static int gpr_set(struct task_struct *target, const struct user_regset *regset, } /* - * When the transaction is active, 'transact_fp' holds the current running - * value of all FPR registers and 'fp_state' holds the last checkpointed - * value of all FPR registers for the current transaction. When transaction - * is not active 'fp_state' holds the current running state of all the FPR - * registers. So this function which returns the current running values of - * all the FPR registers, needs to know whether any transaction is active - * or not. + * Regardless of transactions, 'fp_state' holds the current running + * value of all FPR registers and 'ckfp_state' holds the last checkpointed + * value of all FPR registers for the current transaction. * * Userspace interface buffer layout: * @@ -416,13 +413,6 @@ static int gpr_set(struct task_struct *target, const struct user_regset *regset, * u64 fpr[32]; * u64 fpscr; * }; - * - * There are two config options CONFIG_VSX and CONFIG_PPC_TRANSACTIONAL_MEM - * which determines the final code in this function. All the combinations of - * these two config options are possible except the one below as transactional - * memory config pulls in CONFIG_VSX automatically. - * - * !defined(CONFIG_VSX) && defined(CONFIG_PPC_TRANSACTIONAL_MEM) */ static int fpr_get(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, @@ -431,50 +421,29 @@ static int fpr_get(struct task_struct *target, const struct user_regset *regset, #ifdef CONFIG_VSX u64 buf[33]; int i; -#endif - flush_fp_to_thread(target); -#if defined(CONFIG_VSX) && defined(CONFIG_PPC_TRANSACTIONAL_MEM) - /* copy to local buffer then write that out */ - if (MSR_TM_ACTIVE(target->thread.regs->msr)) { - flush_altivec_to_thread(target); - flush_tmregs_to_thread(target); - for (i = 0; i < 32 ; i++) - buf[i] = target->thread.TS_TRANS_FPR(i); - buf[32] = target->thread.transact_fp.fpscr; - } else { - for (i = 0; i < 32 ; i++) - buf[i] = target->thread.TS_FPR(i); - buf[32] = target->thread.fp_state.fpscr; - } - return user_regset_copyout(&pos, &count, &kbuf, &ubuf, buf, 0, -1); -#endif + flush_fp_to_thread(target); -#if defined(CONFIG_VSX) && !defined(CONFIG_PPC_TRANSACTIONAL_MEM) /* copy to local buffer then write that out */ for (i = 0; i < 32 ; i++) buf[i] = target->thread.TS_FPR(i); buf[32] = target->thread.fp_state.fpscr; return user_regset_copyout(&pos, &count, &kbuf, &ubuf, buf, 0, -1); -#endif - -#if !defined(CONFIG_VSX) && !defined(CONFIG_PPC_TRANSACTIONAL_MEM) +#else BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) != offsetof(struct thread_fp_state, fpr[32])); + flush_fp_to_thread(target); + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &target->thread.fp_state, 0, -1); #endif } /* - * When the transaction is active, 'transact_fp' holds the current running - * value of all FPR registers and 'fp_state' holds the last checkpointed - * value of all FPR registers for the current transaction. When transaction - * is not active 'fp_state' holds the current running state of all the FPR - * registers. So this function which setss the current running values of - * all the FPR registers, needs to know whether any transaction is active - * or not. + * Regardless of transactions, 'fp_state' holds the current running + * value of all FPR registers and 'ckfp_state' holds the last checkpointed + * value of all FPR registers for the current transaction. * * Userspace interface buffer layout: * @@ -483,12 +452,6 @@ static int fpr_get(struct task_struct *target, const struct user_regset *regset, * u64 fpscr; * }; * - * There are two config options CONFIG_VSX and CONFIG_PPC_TRANSACTIONAL_MEM - * which determines the final code in this function. All the combinations of - * these two config options are possible except the one below as transactional - * memory config pulls in CONFIG_VSX automatically. - * - * !defined(CONFIG_VSX) && defined(CONFIG_PPC_TRANSACTIONAL_MEM) */ static int fpr_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, @@ -497,44 +460,24 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset, #ifdef CONFIG_VSX u64 buf[33]; int i; -#endif + flush_fp_to_thread(target); -#if defined(CONFIG_VSX) && defined(CONFIG_PPC_TRANSACTIONAL_MEM) /* copy to local buffer then write that out */ i = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, -1); if (i) return i; - if (MSR_TM_ACTIVE(target->thread.regs->msr)) { - flush_altivec_to_thread(target); - flush_tmregs_to_thread(target); - for (i = 0; i < 32 ; i++) - target->thread.TS_TRANS_FPR(i) = buf[i]; - target->thread.transact_fp.fpscr = buf[32]; - } else { - for (i = 0; i < 32 ; i++) - target->thread.TS_FPR(i) = buf[i]; - target->thread.fp_state.fpscr = buf[32]; - } - return 0; -#endif - -#if defined(CONFIG_VSX) && !defined(CONFIG_PPC_TRANSACTIONAL_MEM) - /* copy to local buffer then write that out */ - i = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, -1); - if (i) - return i; for (i = 0; i < 32 ; i++) target->thread.TS_FPR(i) = buf[i]; target->thread.fp_state.fpscr = buf[32]; return 0; -#endif - -#if !defined(CONFIG_VSX) && !defined(CONFIG_PPC_TRANSACTIONAL_MEM) +#else BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) != offsetof(struct thread_fp_state, fpr[32])); + flush_fp_to_thread(target); + return user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.fp_state, 0, -1); #endif @@ -562,13 +505,10 @@ static int vr_active(struct task_struct *target, } /* - * When the transaction is active, 'transact_vr' holds the current running - * value of all the VMX registers and 'vr_state' holds the last checkpointed - * value of all the VMX registers for the current transaction to fall back - * on in case it aborts. When transaction is not active 'vr_state' holds - * the current running state of all the VMX registers. So this function which - * gets the current running values of all the VMX registers, needs to know - * whether any transaction is active or not. + * Regardless of transactions, 'vr_state' holds the current running + * value of all the VMX registers and 'ckvr_state' holds the last + * checkpointed value of all the VMX registers for the current + * transaction to fall back on in case it aborts. * * Userspace interface buffer layout: * @@ -582,7 +522,6 @@ static int vr_get(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) { - struct thread_vr_state *addr; int ret; flush_altivec_to_thread(target); @@ -590,19 +529,8 @@ static int vr_get(struct task_struct *target, const struct user_regset *regset, BUILD_BUG_ON(offsetof(struct thread_vr_state, vscr) != offsetof(struct thread_vr_state, vr[32])); -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - if (MSR_TM_ACTIVE(target->thread.regs->msr)) { - flush_fp_to_thread(target); - flush_tmregs_to_thread(target); - addr = &target->thread.transact_vr; - } else { - addr = &target->thread.vr_state; - } -#else - addr = &target->thread.vr_state; -#endif ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, - addr, 0, + &target->thread.vr_state, 0, 33 * sizeof(vector128)); if (!ret) { /* @@ -614,14 +542,7 @@ static int vr_get(struct task_struct *target, const struct user_regset *regset, } vrsave; memset(&vrsave, 0, sizeof(vrsave)); -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - if (MSR_TM_ACTIVE(target->thread.regs->msr)) - vrsave.word = target->thread.transact_vrsave; - else - vrsave.word = target->thread.vrsave; -#else vrsave.word = target->thread.vrsave; -#endif ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &vrsave, 33 * sizeof(vector128), -1); @@ -631,13 +552,10 @@ static int vr_get(struct task_struct *target, const struct user_regset *regset, } /* - * When the transaction is active, 'transact_vr' holds the current running - * value of all the VMX registers and 'vr_state' holds the last checkpointed - * value of all the VMX registers for the current transaction to fall back - * on in case it aborts. When transaction is not active 'vr_state' holds - * the current running state of all the VMX registers. So this function which - * sets the current running values of all the VMX registers, needs to know - * whether any transaction is active or not. + * Regardless of transactions, 'vr_state' holds the current running + * value of all the VMX registers and 'ckvr_state' holds the last + * checkpointed value of all the VMX registers for the current + * transaction to fall back on in case it aborts. * * Userspace interface buffer layout: * @@ -651,7 +569,6 @@ static int vr_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { - struct thread_vr_state *addr; int ret; flush_altivec_to_thread(target); @@ -659,19 +576,8 @@ static int vr_set(struct task_struct *target, const struct user_regset *regset, BUILD_BUG_ON(offsetof(struct thread_vr_state, vscr) != offsetof(struct thread_vr_state, vr[32])); -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - if (MSR_TM_ACTIVE(target->thread.regs->msr)) { - flush_fp_to_thread(target); - flush_tmregs_to_thread(target); - addr = &target->thread.transact_vr; - } else { - addr = &target->thread.vr_state; - } -#else - addr = &target->thread.vr_state; -#endif ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - addr, 0, + &target->thread.vr_state, 0, 33 * sizeof(vector128)); if (!ret && count > 0) { /* @@ -683,27 +589,12 @@ static int vr_set(struct task_struct *target, const struct user_regset *regset, } vrsave; memset(&vrsave, 0, sizeof(vrsave)); -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - if (MSR_TM_ACTIVE(target->thread.regs->msr)) - vrsave.word = target->thread.transact_vrsave; - else - vrsave.word = target->thread.vrsave; -#else vrsave.word = target->thread.vrsave; -#endif + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &vrsave, 33 * sizeof(vector128), -1); - if (!ret) { - -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - if (MSR_TM_ACTIVE(target->thread.regs->msr)) - target->thread.transact_vrsave = vrsave.word; - else - target->thread.vrsave = vrsave.word; -#else + if (!ret) target->thread.vrsave = vrsave.word; -#endif - } } return ret; @@ -725,13 +616,10 @@ static int vsr_active(struct task_struct *target, } /* - * When the transaction is active, 'transact_fp' holds the current running - * value of all FPR registers and 'fp_state' holds the last checkpointed - * value of all FPR registers for the current transaction. When transaction - * is not active 'fp_state' holds the current running state of all the FPR - * registers. So this function which returns the current running values of - * all the FPR registers, needs to know whether any transaction is active - * or not. + * Regardless of transactions, 'fp_state' holds the current running + * value of all FPR registers and 'ckfp_state' holds the last + * checkpointed value of all FPR registers for the current + * transaction. * * Userspace interface buffer layout: * @@ -746,27 +634,14 @@ static int vsr_get(struct task_struct *target, const struct user_regset *regset, u64 buf[32]; int ret, i; -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + flush_tmregs_to_thread(target); flush_fp_to_thread(target); flush_altivec_to_thread(target); - flush_tmregs_to_thread(target); -#endif flush_vsx_to_thread(target); -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - if (MSR_TM_ACTIVE(target->thread.regs->msr)) { - for (i = 0; i < 32 ; i++) - buf[i] = target->thread. - transact_fp.fpr[i][TS_VSRLOWOFFSET]; - } else { - for (i = 0; i < 32 ; i++) - buf[i] = target->thread. - fp_state.fpr[i][TS_VSRLOWOFFSET]; - } -#else for (i = 0; i < 32 ; i++) buf[i] = target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET]; -#endif + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, buf, 0, 32 * sizeof(double)); @@ -774,12 +649,10 @@ static int vsr_get(struct task_struct *target, const struct user_regset *regset, } /* - * When the transaction is active, 'transact_fp' holds the current running - * value of all FPR registers and 'fp_state' holds the last checkpointed - * value of all FPR registers for the current transaction. When transaction - * is not active 'fp_state' holds the current running state of all the FPR - * registers. So this function which sets the current running values of all - * the FPR registers, needs to know whether any transaction is active or not. + * Regardless of transactions, 'fp_state' holds the current running + * value of all FPR registers and 'ckfp_state' holds the last + * checkpointed value of all FPR registers for the current + * transaction. * * Userspace interface buffer layout: * @@ -794,31 +667,16 @@ static int vsr_set(struct task_struct *target, const struct user_regset *regset, u64 buf[32]; int ret,i; -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + flush_tmregs_to_thread(target); flush_fp_to_thread(target); flush_altivec_to_thread(target); - flush_tmregs_to_thread(target); -#endif flush_vsx_to_thread(target); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, 32 * sizeof(double)); - -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - if (MSR_TM_ACTIVE(target->thread.regs->msr)) { - for (i = 0; i < 32 ; i++) - target->thread.transact_fp. - fpr[i][TS_VSRLOWOFFSET] = buf[i]; - } else { + if (!ret) for (i = 0; i < 32 ; i++) - target->thread.fp_state. - fpr[i][TS_VSRLOWOFFSET] = buf[i]; - } -#else - for (i = 0; i < 32 ; i++) - target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i]; -#endif - + target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i]; return ret; } @@ -944,9 +802,9 @@ static int tm_cgpr_get(struct task_struct *target, if (!MSR_TM_ACTIVE(target->thread.regs->msr)) return -ENODATA; + flush_tmregs_to_thread(target); flush_fp_to_thread(target); flush_altivec_to_thread(target); - flush_tmregs_to_thread(target); ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &target->thread.ckpt_regs, @@ -1009,9 +867,9 @@ static int tm_cgpr_set(struct task_struct *target, if (!MSR_TM_ACTIVE(target->thread.regs->msr)) return -ENODATA; + flush_tmregs_to_thread(target); flush_fp_to_thread(target); flush_altivec_to_thread(target); - flush_tmregs_to_thread(target); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.ckpt_regs, @@ -1087,7 +945,7 @@ static int tm_cfpr_active(struct task_struct *target, * * This function gets in transaction checkpointed FPR registers. * - * When the transaction is active 'fp_state' holds the checkpointed + * When the transaction is active 'ckfp_state' holds the checkpointed * values for the current transaction to fall back on if it aborts * in between. This function gets those checkpointed FPR registers. * The userspace interface buffer layout is as follows. @@ -1111,14 +969,14 @@ static int tm_cfpr_get(struct task_struct *target, if (!MSR_TM_ACTIVE(target->thread.regs->msr)) return -ENODATA; + flush_tmregs_to_thread(target); flush_fp_to_thread(target); flush_altivec_to_thread(target); - flush_tmregs_to_thread(target); /* copy to local buffer then write that out */ for (i = 0; i < 32 ; i++) - buf[i] = target->thread.TS_FPR(i); - buf[32] = target->thread.fp_state.fpscr; + buf[i] = target->thread.TS_CKFPR(i); + buf[32] = target->thread.ckfp_state.fpscr; return user_regset_copyout(&pos, &count, &kbuf, &ubuf, buf, 0, -1); } @@ -1133,7 +991,7 @@ static int tm_cfpr_get(struct task_struct *target, * * This function sets in transaction checkpointed FPR registers. * - * When the transaction is active 'fp_state' holds the checkpointed + * When the transaction is active 'ckfp_state' holds the checkpointed * FPR register values for the current transaction to fall back on * if it aborts in between. This function sets these checkpointed * FPR registers. The userspace interface buffer layout is as follows. @@ -1157,17 +1015,17 @@ static int tm_cfpr_set(struct task_struct *target, if (!MSR_TM_ACTIVE(target->thread.regs->msr)) return -ENODATA; + flush_tmregs_to_thread(target); flush_fp_to_thread(target); flush_altivec_to_thread(target); - flush_tmregs_to_thread(target); /* copy to local buffer then write that out */ i = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, -1); if (i) return i; for (i = 0; i < 32 ; i++) - target->thread.TS_FPR(i) = buf[i]; - target->thread.fp_state.fpscr = buf[32]; + target->thread.TS_CKFPR(i) = buf[i]; + target->thread.ckfp_state.fpscr = buf[32]; return 0; } @@ -1202,7 +1060,7 @@ static int tm_cvmx_active(struct task_struct *target, * * This function gets in transaction checkpointed VMX registers. * - * When the transaction is active 'vr_state' and 'vr_save' hold + * When the transaction is active 'ckvr_state' and 'ckvrsave' hold * the checkpointed values for the current transaction to fall * back on if it aborts in between. The userspace interface buffer * layout is as follows. @@ -1229,12 +1087,12 @@ static int tm_cvmx_get(struct task_struct *target, return -ENODATA; /* Flush the state */ + flush_tmregs_to_thread(target); flush_fp_to_thread(target); flush_altivec_to_thread(target); - flush_tmregs_to_thread(target); ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, - &target->thread.vr_state, 0, + &target->thread.ckvr_state, 0, 33 * sizeof(vector128)); if (!ret) { /* @@ -1245,7 +1103,7 @@ static int tm_cvmx_get(struct task_struct *target, u32 word; } vrsave; memset(&vrsave, 0, sizeof(vrsave)); - vrsave.word = target->thread.vrsave; + vrsave.word = target->thread.ckvrsave; ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &vrsave, 33 * sizeof(vector128), -1); } @@ -1264,7 +1122,7 @@ static int tm_cvmx_get(struct task_struct *target, * * This function sets in transaction checkpointed VMX registers. * - * When the transaction is active 'vr_state' and 'vr_save' hold + * When the transaction is active 'ckvr_state' and 'ckvrsave' hold * the checkpointed values for the current transaction to fall * back on if it aborts in between. The userspace interface buffer * layout is as follows. @@ -1290,12 +1148,12 @@ static int tm_cvmx_set(struct task_struct *target, if (!MSR_TM_ACTIVE(target->thread.regs->msr)) return -ENODATA; + flush_tmregs_to_thread(target); flush_fp_to_thread(target); flush_altivec_to_thread(target); - flush_tmregs_to_thread(target); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &target->thread.vr_state, 0, + &target->thread.ckvr_state, 0, 33 * sizeof(vector128)); if (!ret && count > 0) { /* @@ -1306,11 +1164,11 @@ static int tm_cvmx_set(struct task_struct *target, u32 word; } vrsave; memset(&vrsave, 0, sizeof(vrsave)); - vrsave.word = target->thread.vrsave; + vrsave.word = target->thread.ckvrsave; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &vrsave, 33 * sizeof(vector128), -1); if (!ret) - target->thread.vrsave = vrsave.word; + target->thread.ckvrsave = vrsave.word; } return ret; @@ -1348,7 +1206,7 @@ static int tm_cvsx_active(struct task_struct *target, * * This function gets in transaction checkpointed VSX registers. * - * When the transaction is active 'fp_state' holds the checkpointed + * When the transaction is active 'ckfp_state' holds the checkpointed * values for the current transaction to fall back on if it aborts * in between. This function gets those checkpointed VSX registers. * The userspace interface buffer layout is as follows. @@ -1372,13 +1230,13 @@ static int tm_cvsx_get(struct task_struct *target, return -ENODATA; /* Flush the state */ + flush_tmregs_to_thread(target); flush_fp_to_thread(target); flush_altivec_to_thread(target); - flush_tmregs_to_thread(target); flush_vsx_to_thread(target); for (i = 0; i < 32 ; i++) - buf[i] = target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET]; + buf[i] = target->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET]; ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, buf, 0, 32 * sizeof(double)); @@ -1396,7 +1254,7 @@ static int tm_cvsx_get(struct task_struct *target, * * This function sets in transaction checkpointed VSX registers. * - * When the transaction is active 'fp_state' holds the checkpointed + * When the transaction is active 'ckfp_state' holds the checkpointed * VSX register values for the current transaction to fall back on * if it aborts in between. This function sets these checkpointed * FPR registers. The userspace interface buffer layout is as follows. @@ -1420,15 +1278,16 @@ static int tm_cvsx_set(struct task_struct *target, return -ENODATA; /* Flush the state */ + flush_tmregs_to_thread(target); flush_fp_to_thread(target); flush_altivec_to_thread(target); - flush_tmregs_to_thread(target); flush_vsx_to_thread(target); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, 32 * sizeof(double)); - for (i = 0; i < 32 ; i++) - target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i]; + if (!ret) + for (i = 0; i < 32 ; i++) + target->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i]; return ret; } @@ -1484,9 +1343,9 @@ static int tm_spr_get(struct task_struct *target, return -ENODEV; /* Flush the states */ + flush_tmregs_to_thread(target); flush_fp_to_thread(target); flush_altivec_to_thread(target); - flush_tmregs_to_thread(target); /* TFHAR register */ ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, @@ -1540,9 +1399,9 @@ static int tm_spr_set(struct task_struct *target, return -ENODEV; /* Flush the states */ + flush_tmregs_to_thread(target); flush_fp_to_thread(target); flush_altivec_to_thread(target); - flush_tmregs_to_thread(target); /* TFHAR register */ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, @@ -2065,33 +1924,12 @@ static const struct user_regset_view user_ppc_native_view = { static int gpr32_get_common(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf, bool tm_active) + void *kbuf, void __user *ubuf, + unsigned long *regs) { - const unsigned long *regs = &target->thread.regs->gpr[0]; - const unsigned long *ckpt_regs; compat_ulong_t *k = kbuf; compat_ulong_t __user *u = ubuf; compat_ulong_t reg; - int i; - -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - ckpt_regs = &target->thread.ckpt_regs.gpr[0]; -#endif - if (tm_active) { - regs = ckpt_regs; - } else { - if (target->thread.regs == NULL) - return -EIO; - - if (!FULL_REGS(target->thread.regs)) { - /* - * We have a partial register set. - * Fill 14-31 with bogus values. - */ - for (i = 14; i < 32; i++) - target->thread.regs->gpr[i] = NV_REG_POISON; - } - } pos /= sizeof(reg); count /= sizeof(reg); @@ -2133,29 +1971,13 @@ static int gpr32_get_common(struct task_struct *target, static int gpr32_set_common(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, - const void *kbuf, const void __user *ubuf, bool tm_active) + const void *kbuf, const void __user *ubuf, + unsigned long *regs) { - unsigned long *regs = &target->thread.regs->gpr[0]; - unsigned long *ckpt_regs; const compat_ulong_t *k = kbuf; const compat_ulong_t __user *u = ubuf; compat_ulong_t reg; -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - ckpt_regs = &target->thread.ckpt_regs.gpr[0]; -#endif - - if (tm_active) { - regs = ckpt_regs; - } else { - regs = &target->thread.regs->gpr[0]; - - if (target->thread.regs == NULL) - return -EIO; - - CHECK_FULL_REGS(target->thread.regs); - } - pos /= sizeof(reg); count /= sizeof(reg); @@ -2220,7 +2042,8 @@ static int tm_cgpr32_get(struct task_struct *target, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) { - return gpr32_get_common(target, regset, pos, count, kbuf, ubuf, 1); + return gpr32_get_common(target, regset, pos, count, kbuf, ubuf, + &target->thread.ckpt_regs.gpr[0]); } static int tm_cgpr32_set(struct task_struct *target, @@ -2228,7 +2051,8 @@ static int tm_cgpr32_set(struct task_struct *target, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { - return gpr32_set_common(target, regset, pos, count, kbuf, ubuf, 1); + return gpr32_set_common(target, regset, pos, count, kbuf, ubuf, + &target->thread.ckpt_regs.gpr[0]); } #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ @@ -2237,7 +2061,21 @@ static int gpr32_get(struct task_struct *target, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) { - return gpr32_get_common(target, regset, pos, count, kbuf, ubuf, 0); + int i; + + if (target->thread.regs == NULL) + return -EIO; + + if (!FULL_REGS(target->thread.regs)) { + /* + * We have a partial register set. + * Fill 14-31 with bogus values. + */ + for (i = 14; i < 32; i++) + target->thread.regs->gpr[i] = NV_REG_POISON; + } + return gpr32_get_common(target, regset, pos, count, kbuf, ubuf, + &target->thread.regs->gpr[0]); } static int gpr32_set(struct task_struct *target, @@ -2245,7 +2083,12 @@ static int gpr32_set(struct task_struct *target, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { - return gpr32_set_common(target, regset, pos, count, kbuf, ubuf, 0); + if (target->thread.regs == NULL) + return -EIO; + + CHECK_FULL_REGS(target->thread.regs); + return gpr32_set_common(target, regset, pos, count, kbuf, ubuf, + &target->thread.regs->gpr[0]); } /* diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index cb64d6feb45a..bbe77aed198d 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -99,22 +99,24 @@ static void check_syscall_restart(struct pt_regs *regs, struct k_sigaction *ka, } } -static void do_signal(struct pt_regs *regs) +static void do_signal(struct task_struct *tsk) { sigset_t *oldset = sigmask_to_save(); struct ksignal ksig; int ret; int is32 = is_32bit_task(); + BUG_ON(tsk != current); + get_signal(&ksig); /* Is there any syscall restart business here ? */ - check_syscall_restart(regs, &ksig.ka, ksig.sig > 0); + check_syscall_restart(tsk->thread.regs, &ksig.ka, ksig.sig > 0); if (ksig.sig <= 0) { /* No signal to deliver -- put the saved sigmask back */ restore_saved_sigmask(); - regs->trap = 0; + tsk->thread.regs->trap = 0; return; /* no signals delivered */ } @@ -124,23 +126,22 @@ static void do_signal(struct pt_regs *regs) * user space. The DABR will have been cleared if it * triggered inside the kernel. */ - if (current->thread.hw_brk.address && - current->thread.hw_brk.type) - __set_breakpoint(¤t->thread.hw_brk); + if (tsk->thread.hw_brk.address && tsk->thread.hw_brk.type) + __set_breakpoint(&tsk->thread.hw_brk); #endif /* Re-enable the breakpoints for the signal stack */ - thread_change_pc(current, regs); + thread_change_pc(tsk, tsk->thread.regs); if (is32) { if (ksig.ka.sa.sa_flags & SA_SIGINFO) - ret = handle_rt_signal32(&ksig, oldset, regs); + ret = handle_rt_signal32(&ksig, oldset, tsk); else - ret = handle_signal32(&ksig, oldset, regs); + ret = handle_signal32(&ksig, oldset, tsk); } else { - ret = handle_rt_signal64(&ksig, oldset, regs); + ret = handle_rt_signal64(&ksig, oldset, tsk); } - regs->trap = 0; + tsk->thread.regs->trap = 0; signal_setup_done(ret, &ksig, test_thread_flag(TIF_SINGLESTEP)); } @@ -151,8 +152,10 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags) if (thread_info_flags & _TIF_UPROBE) uprobe_notify_resume(regs); - if (thread_info_flags & _TIF_SIGPENDING) - do_signal(regs); + if (thread_info_flags & _TIF_SIGPENDING) { + BUG_ON(regs != current->thread.regs); + do_signal(current); + } if (thread_info_flags & _TIF_NOTIFY_RESUME) { clear_thread_flag(TIF_NOTIFY_RESUME); @@ -162,7 +165,7 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags) user_enter(); } -unsigned long get_tm_stackpointer(struct pt_regs *regs) +unsigned long get_tm_stackpointer(struct task_struct *tsk) { /* When in an active transaction that takes a signal, we need to be * careful with the stack. It's possible that the stack has moved back @@ -187,11 +190,13 @@ unsigned long get_tm_stackpointer(struct pt_regs *regs) */ #ifdef CONFIG_PPC_TRANSACTIONAL_MEM - if (MSR_TM_ACTIVE(regs->msr)) { + BUG_ON(tsk != current); + + if (MSR_TM_ACTIVE(tsk->thread.regs->msr)) { tm_reclaim_current(TM_CAUSE_SIGNAL); - if (MSR_TM_TRANSACTIONAL(regs->msr)) - return current->thread.ckpt_regs.gpr[1]; + if (MSR_TM_TRANSACTIONAL(tsk->thread.regs->msr)) + return tsk->thread.ckpt_regs.gpr[1]; } #endif - return regs->gpr[1]; + return tsk->thread.regs->gpr[1]; } diff --git a/arch/powerpc/kernel/signal.h b/arch/powerpc/kernel/signal.h index be305c858e51..7c59d88b9d86 100644 --- a/arch/powerpc/kernel/signal.h +++ b/arch/powerpc/kernel/signal.h @@ -16,39 +16,41 @@ extern void __user *get_sigframe(struct ksignal *ksig, unsigned long sp, size_t frame_size, int is_32); extern int handle_signal32(struct ksignal *ksig, sigset_t *oldset, - struct pt_regs *regs); + struct task_struct *tsk); extern int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset, - struct pt_regs *regs); + struct task_struct *tsk); extern unsigned long copy_fpr_to_user(void __user *to, struct task_struct *task); -extern unsigned long copy_transact_fpr_to_user(void __user *to, +extern unsigned long copy_ckfpr_to_user(void __user *to, struct task_struct *task); extern unsigned long copy_fpr_from_user(struct task_struct *task, void __user *from); -extern unsigned long copy_transact_fpr_from_user(struct task_struct *task, +extern unsigned long copy_ckfpr_from_user(struct task_struct *task, void __user *from); +extern unsigned long get_tm_stackpointer(struct task_struct *tsk); + #ifdef CONFIG_VSX extern unsigned long copy_vsx_to_user(void __user *to, struct task_struct *task); -extern unsigned long copy_transact_vsx_to_user(void __user *to, +extern unsigned long copy_ckvsx_to_user(void __user *to, struct task_struct *task); extern unsigned long copy_vsx_from_user(struct task_struct *task, void __user *from); -extern unsigned long copy_transact_vsx_from_user(struct task_struct *task, +extern unsigned long copy_ckvsx_from_user(struct task_struct *task, void __user *from); #endif #ifdef CONFIG_PPC64 extern int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, - struct pt_regs *regs); + struct task_struct *tsk); #else /* CONFIG_PPC64 */ static inline int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, - struct pt_regs *regs) + struct task_struct *tsk) { return -EFAULT; } diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index a7daf749b97f..27aa913ac91d 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -44,6 +44,7 @@ #include <asm/vdso.h> #include <asm/switch_to.h> #include <asm/tm.h> +#include <asm/asm-prototypes.h> #ifdef CONFIG_PPC64 #include "ppc32.h" #include <asm/unistd.h> @@ -315,7 +316,7 @@ unsigned long copy_vsx_from_user(struct task_struct *task, } #ifdef CONFIG_PPC_TRANSACTIONAL_MEM -unsigned long copy_transact_fpr_to_user(void __user *to, +unsigned long copy_ckfpr_to_user(void __user *to, struct task_struct *task) { u64 buf[ELF_NFPREG]; @@ -323,12 +324,12 @@ unsigned long copy_transact_fpr_to_user(void __user *to, /* save FPR copy to local buffer then write to the thread_struct */ for (i = 0; i < (ELF_NFPREG - 1) ; i++) - buf[i] = task->thread.TS_TRANS_FPR(i); - buf[i] = task->thread.transact_fp.fpscr; + buf[i] = task->thread.TS_CKFPR(i); + buf[i] = task->thread.ckfp_state.fpscr; return __copy_to_user(to, buf, ELF_NFPREG * sizeof(double)); } -unsigned long copy_transact_fpr_from_user(struct task_struct *task, +unsigned long copy_ckfpr_from_user(struct task_struct *task, void __user *from) { u64 buf[ELF_NFPREG]; @@ -337,13 +338,13 @@ unsigned long copy_transact_fpr_from_user(struct task_struct *task, if (__copy_from_user(buf, from, ELF_NFPREG * sizeof(double))) return 1; for (i = 0; i < (ELF_NFPREG - 1) ; i++) - task->thread.TS_TRANS_FPR(i) = buf[i]; - task->thread.transact_fp.fpscr = buf[i]; + task->thread.TS_CKFPR(i) = buf[i]; + task->thread.ckfp_state.fpscr = buf[i]; return 0; } -unsigned long copy_transact_vsx_to_user(void __user *to, +unsigned long copy_ckvsx_to_user(void __user *to, struct task_struct *task) { u64 buf[ELF_NVSRHALFREG]; @@ -351,11 +352,11 @@ unsigned long copy_transact_vsx_to_user(void __user *to, /* save FPR copy to local buffer then write to the thread_struct */ for (i = 0; i < ELF_NVSRHALFREG; i++) - buf[i] = task->thread.transact_fp.fpr[i][TS_VSRLOWOFFSET]; + buf[i] = task->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET]; return __copy_to_user(to, buf, ELF_NVSRHALFREG * sizeof(double)); } -unsigned long copy_transact_vsx_from_user(struct task_struct *task, +unsigned long copy_ckvsx_from_user(struct task_struct *task, void __user *from) { u64 buf[ELF_NVSRHALFREG]; @@ -364,7 +365,7 @@ unsigned long copy_transact_vsx_from_user(struct task_struct *task, if (__copy_from_user(buf, from, ELF_NVSRHALFREG * sizeof(double))) return 1; for (i = 0; i < ELF_NVSRHALFREG ; i++) - task->thread.transact_fp.fpr[i][TS_VSRLOWOFFSET] = buf[i]; + task->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i]; return 0; } #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ @@ -384,17 +385,17 @@ inline unsigned long copy_fpr_from_user(struct task_struct *task, } #ifdef CONFIG_PPC_TRANSACTIONAL_MEM -inline unsigned long copy_transact_fpr_to_user(void __user *to, +inline unsigned long copy_ckfpr_to_user(void __user *to, struct task_struct *task) { - return __copy_to_user(to, task->thread.transact_fp.fpr, + return __copy_to_user(to, task->thread.ckfp_state.fpr, ELF_NFPREG * sizeof(double)); } -inline unsigned long copy_transact_fpr_from_user(struct task_struct *task, +inline unsigned long copy_ckfpr_from_user(struct task_struct *task, void __user *from) { - return __copy_from_user(task->thread.transact_fp.fpr, from, + return __copy_from_user(task->thread.ckfp_state.fpr, from, ELF_NFPREG * sizeof(double)); } #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ @@ -525,9 +526,6 @@ static int save_tm_user_regs(struct pt_regs *regs, */ regs->msr &= ~MSR_TS_MASK; - /* Make sure floating point registers are stored in regs */ - flush_fp_to_thread(current); - /* Save both sets of general registers */ if (save_general_regs(¤t->thread.ckpt_regs, frame) || save_general_regs(regs, tm_frame)) @@ -545,18 +543,17 @@ static int save_tm_user_regs(struct pt_regs *regs, #ifdef CONFIG_ALTIVEC /* save altivec registers */ if (current->thread.used_vr) { - flush_altivec_to_thread(current); - if (__copy_to_user(&frame->mc_vregs, ¤t->thread.vr_state, + if (__copy_to_user(&frame->mc_vregs, ¤t->thread.ckvr_state, ELF_NVRREG * sizeof(vector128))) return 1; if (msr & MSR_VEC) { if (__copy_to_user(&tm_frame->mc_vregs, - ¤t->thread.transact_vr, + ¤t->thread.vr_state, ELF_NVRREG * sizeof(vector128))) return 1; } else { if (__copy_to_user(&tm_frame->mc_vregs, - ¤t->thread.vr_state, + ¤t->thread.ckvr_state, ELF_NVRREG * sizeof(vector128))) return 1; } @@ -573,28 +570,28 @@ static int save_tm_user_regs(struct pt_regs *regs, * most significant bits of that same vector. --BenH */ if (cpu_has_feature(CPU_FTR_ALTIVEC)) - current->thread.vrsave = mfspr(SPRN_VRSAVE); - if (__put_user(current->thread.vrsave, + current->thread.ckvrsave = mfspr(SPRN_VRSAVE); + if (__put_user(current->thread.ckvrsave, (u32 __user *)&frame->mc_vregs[32])) return 1; if (msr & MSR_VEC) { - if (__put_user(current->thread.transact_vrsave, + if (__put_user(current->thread.vrsave, (u32 __user *)&tm_frame->mc_vregs[32])) return 1; } else { - if (__put_user(current->thread.vrsave, + if (__put_user(current->thread.ckvrsave, (u32 __user *)&tm_frame->mc_vregs[32])) return 1; } #endif /* CONFIG_ALTIVEC */ - if (copy_fpr_to_user(&frame->mc_fregs, current)) + if (copy_ckfpr_to_user(&frame->mc_fregs, current)) return 1; if (msr & MSR_FP) { - if (copy_transact_fpr_to_user(&tm_frame->mc_fregs, current)) + if (copy_fpr_to_user(&tm_frame->mc_fregs, current)) return 1; } else { - if (copy_fpr_to_user(&tm_frame->mc_fregs, current)) + if (copy_ckfpr_to_user(&tm_frame->mc_fregs, current)) return 1; } @@ -606,15 +603,14 @@ static int save_tm_user_regs(struct pt_regs *regs, * contains valid data */ if (current->thread.used_vsr) { - flush_vsx_to_thread(current); - if (copy_vsx_to_user(&frame->mc_vsregs, current)) + if (copy_ckvsx_to_user(&frame->mc_vsregs, current)) return 1; if (msr & MSR_VSX) { - if (copy_transact_vsx_to_user(&tm_frame->mc_vsregs, + if (copy_vsx_to_user(&tm_frame->mc_vsregs, current)) return 1; } else { - if (copy_vsx_to_user(&tm_frame->mc_vsregs, current)) + if (copy_ckvsx_to_user(&tm_frame->mc_vsregs, current)) return 1; } @@ -698,6 +694,7 @@ static long restore_user_regs(struct pt_regs *regs, if (__copy_from_user(¤t->thread.vr_state, &sr->mc_vregs, sizeof(sr->mc_vregs))) return 1; + current->thread.used_vr = true; } else if (current->thread.used_vr) memset(¤t->thread.vr_state, 0, ELF_NVRREG * sizeof(vector128)); @@ -724,6 +721,7 @@ static long restore_user_regs(struct pt_regs *regs, */ if (copy_vsx_from_user(current, &sr->mc_vsregs)) return 1; + current->thread.used_vsr = true; } else if (current->thread.used_vsr) for (i = 0; i < 32 ; i++) current->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = 0; @@ -743,6 +741,7 @@ static long restore_user_regs(struct pt_regs *regs, if (__copy_from_user(current->thread.evr, &sr->mc_vregs, ELF_NEVRREG * sizeof(u32))) return 1; + current->thread.used_spe = true; } else if (current->thread.used_spe) memset(current->thread.evr, 0, ELF_NEVRREG * sizeof(u32)); @@ -793,33 +792,34 @@ static long restore_tm_user_regs(struct pt_regs *regs, regs->msr &= ~MSR_VEC; if (msr & MSR_VEC) { /* restore altivec registers from the stack */ - if (__copy_from_user(¤t->thread.vr_state, &sr->mc_vregs, + if (__copy_from_user(¤t->thread.ckvr_state, &sr->mc_vregs, sizeof(sr->mc_vregs)) || - __copy_from_user(¤t->thread.transact_vr, + __copy_from_user(¤t->thread.vr_state, &tm_sr->mc_vregs, sizeof(sr->mc_vregs))) return 1; + current->thread.used_vr = true; } else if (current->thread.used_vr) { memset(¤t->thread.vr_state, 0, ELF_NVRREG * sizeof(vector128)); - memset(¤t->thread.transact_vr, 0, + memset(¤t->thread.ckvr_state, 0, ELF_NVRREG * sizeof(vector128)); } /* Always get VRSAVE back */ - if (__get_user(current->thread.vrsave, + if (__get_user(current->thread.ckvrsave, (u32 __user *)&sr->mc_vregs[32]) || - __get_user(current->thread.transact_vrsave, + __get_user(current->thread.vrsave, (u32 __user *)&tm_sr->mc_vregs[32])) return 1; if (cpu_has_feature(CPU_FTR_ALTIVEC)) - mtspr(SPRN_VRSAVE, current->thread.vrsave); + mtspr(SPRN_VRSAVE, current->thread.ckvrsave); #endif /* CONFIG_ALTIVEC */ regs->msr &= ~(MSR_FP | MSR_FE0 | MSR_FE1); if (copy_fpr_from_user(current, &sr->mc_fregs) || - copy_transact_fpr_from_user(current, &tm_sr->mc_fregs)) + copy_ckfpr_from_user(current, &tm_sr->mc_fregs)) return 1; #ifdef CONFIG_VSX @@ -829,13 +829,14 @@ static long restore_tm_user_regs(struct pt_regs *regs, * Restore altivec registers from the stack to a local * buffer, then write this out to the thread_struct */ - if (copy_vsx_from_user(current, &sr->mc_vsregs) || - copy_transact_vsx_from_user(current, &tm_sr->mc_vsregs)) + if (copy_vsx_from_user(current, &tm_sr->mc_vsregs) || + copy_ckvsx_from_user(current, &sr->mc_vsregs)) return 1; + current->thread.used_vsr = true; } else if (current->thread.used_vsr) for (i = 0; i < 32 ; i++) { current->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = 0; - current->thread.transact_fp.fpr[i][TS_VSRLOWOFFSET] = 0; + current->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET] = 0; } #endif /* CONFIG_VSX */ @@ -848,6 +849,7 @@ static long restore_tm_user_regs(struct pt_regs *regs, if (__copy_from_user(current->thread.evr, &sr->mc_vregs, ELF_NEVRREG * sizeof(u32))) return 1; + current->thread.used_spe = true; } else if (current->thread.used_spe) memset(current->thread.evr, 0, ELF_NEVRREG * sizeof(u32)); @@ -877,13 +879,14 @@ static long restore_tm_user_regs(struct pt_regs *regs, tm_recheckpoint(¤t->thread, msr); /* This loads the speculative FP/VEC state, if used */ + msr_check_and_set(msr & (MSR_FP | MSR_VEC)); if (msr & MSR_FP) { - do_load_up_transact_fpu(¤t->thread); + load_fp_state(¤t->thread.fp_state); regs->msr |= (MSR_FP | current->thread.fpexc_mode); } #ifdef CONFIG_ALTIVEC if (msr & MSR_VEC) { - do_load_up_transact_altivec(¤t->thread); + load_vr_state(¤t->thread.vr_state); regs->msr |= MSR_VEC; } #endif @@ -971,7 +974,7 @@ int copy_siginfo_from_user32(siginfo_t *to, struct compat_siginfo __user *from) * (one which gets siginfo). */ int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset, - struct pt_regs *regs) + struct task_struct *tsk) { struct rt_sigframe __user *rt_sf; struct mcontext __user *frame; @@ -980,10 +983,13 @@ int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset, unsigned long newsp = 0; int sigret; unsigned long tramp; + struct pt_regs *regs = tsk->thread.regs; + + BUG_ON(tsk != current); /* Set up Signal Frame */ /* Put a Real Time Context onto stack */ - rt_sf = get_sigframe(ksig, get_tm_stackpointer(regs), sizeof(*rt_sf), 1); + rt_sf = get_sigframe(ksig, get_tm_stackpointer(tsk), sizeof(*rt_sf), 1); addr = rt_sf; if (unlikely(rt_sf == NULL)) goto badframe; @@ -1000,9 +1006,9 @@ int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset, /* Save user registers on the stack */ frame = &rt_sf->uc.uc_mcontext; addr = frame; - if (vdso32_rt_sigtramp && current->mm->context.vdso_base) { + if (vdso32_rt_sigtramp && tsk->mm->context.vdso_base) { sigret = 0; - tramp = current->mm->context.vdso_base + vdso32_rt_sigtramp; + tramp = tsk->mm->context.vdso_base + vdso32_rt_sigtramp; } else { sigret = __NR_rt_sigreturn; tramp = (unsigned long) frame->tramp; @@ -1029,7 +1035,7 @@ int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset, } regs->link = tramp; - current->thread.fp_state.fpscr = 0; /* turn off all fp exceptions */ + tsk->thread.fp_state.fpscr = 0; /* turn off all fp exceptions */ /* create a stack frame for the caller of the handler */ newsp = ((unsigned long)rt_sf) - (__SIGNAL_FRAMESIZE + 16); @@ -1054,7 +1060,7 @@ badframe: printk_ratelimited(KERN_INFO "%s[%d]: bad frame in handle_rt_signal32: " "%p nip %08lx lr %08lx\n", - current->comm, current->pid, + tsk->comm, tsk->pid, addr, regs->nip, regs->link); return 1; @@ -1410,7 +1416,8 @@ int sys_debug_setcontext(struct ucontext __user *ctx, /* * OK, we're invoking a handler */ -int handle_signal32(struct ksignal *ksig, sigset_t *oldset, struct pt_regs *regs) +int handle_signal32(struct ksignal *ksig, sigset_t *oldset, + struct task_struct *tsk) { struct sigcontext __user *sc; struct sigframe __user *frame; @@ -1418,9 +1425,12 @@ int handle_signal32(struct ksignal *ksig, sigset_t *oldset, struct pt_regs *regs unsigned long newsp = 0; int sigret; unsigned long tramp; + struct pt_regs *regs = tsk->thread.regs; + + BUG_ON(tsk != current); /* Set up Signal Frame */ - frame = get_sigframe(ksig, get_tm_stackpointer(regs), sizeof(*frame), 1); + frame = get_sigframe(ksig, get_tm_stackpointer(tsk), sizeof(*frame), 1); if (unlikely(frame == NULL)) goto badframe; sc = (struct sigcontext __user *) &frame->sctx; @@ -1439,9 +1449,9 @@ int handle_signal32(struct ksignal *ksig, sigset_t *oldset, struct pt_regs *regs || __put_user(ksig->sig, &sc->signal)) goto badframe; - if (vdso32_sigtramp && current->mm->context.vdso_base) { + if (vdso32_sigtramp && tsk->mm->context.vdso_base) { sigret = 0; - tramp = current->mm->context.vdso_base + vdso32_sigtramp; + tramp = tsk->mm->context.vdso_base + vdso32_sigtramp; } else { sigret = __NR_sigreturn; tramp = (unsigned long) frame->mctx.tramp; @@ -1463,7 +1473,7 @@ int handle_signal32(struct ksignal *ksig, sigset_t *oldset, struct pt_regs *regs regs->link = tramp; - current->thread.fp_state.fpscr = 0; /* turn off all fp exceptions */ + tsk->thread.fp_state.fpscr = 0; /* turn off all fp exceptions */ /* create a stack frame for the caller of the handler */ newsp = ((unsigned long)frame) - __SIGNAL_FRAMESIZE; @@ -1483,7 +1493,7 @@ badframe: printk_ratelimited(KERN_INFO "%s[%d]: bad frame in handle_signal32: " "%p nip %08lx lr %08lx\n", - current->comm, current->pid, + tsk->comm, tsk->pid, frame, regs->nip, regs->link); return 1; diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 70409bb90a95..96698fdf93b4 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -35,6 +35,7 @@ #include <asm/vdso.h> #include <asm/switch_to.h> #include <asm/tm.h> +#include <asm/asm-prototypes.h> #include "signal.h" @@ -90,9 +91,9 @@ static elf_vrreg_t __user *sigcontext_vmx_regs(struct sigcontext __user *sc) * Set up the sigcontext for the signal frame. */ -static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs, - int signr, sigset_t *set, unsigned long handler, - int ctx_has_vsx_region) +static long setup_sigcontext(struct sigcontext __user *sc, + struct task_struct *tsk, int signr, sigset_t *set, + unsigned long handler, int ctx_has_vsx_region) { /* When CONFIG_ALTIVEC is set, we _always_ setup v_regs even if the * process never used altivec yet (MSR_VEC is zero in pt_regs of @@ -106,17 +107,20 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs, elf_vrreg_t __user *v_regs = sigcontext_vmx_regs(sc); unsigned long vrsave; #endif + struct pt_regs *regs = tsk->thread.regs; unsigned long msr = regs->msr; long err = 0; + BUG_ON(tsk != current); + #ifdef CONFIG_ALTIVEC err |= __put_user(v_regs, &sc->v_regs); /* save altivec registers */ - if (current->thread.used_vr) { - flush_altivec_to_thread(current); + if (tsk->thread.used_vr) { + flush_altivec_to_thread(tsk); /* Copy 33 vec registers (vr0..31 and vscr) to the stack */ - err |= __copy_to_user(v_regs, ¤t->thread.vr_state, + err |= __copy_to_user(v_regs, &tsk->thread.vr_state, 33 * sizeof(vector128)); /* set MSR_VEC in the MSR value in the frame to indicate that sc->v_reg) * contains valid data. @@ -129,16 +133,16 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs, vrsave = 0; if (cpu_has_feature(CPU_FTR_ALTIVEC)) { vrsave = mfspr(SPRN_VRSAVE); - current->thread.vrsave = vrsave; + tsk->thread.vrsave = vrsave; } err |= __put_user(vrsave, (u32 __user *)&v_regs[33]); #else /* CONFIG_ALTIVEC */ err |= __put_user(0, &sc->v_regs); #endif /* CONFIG_ALTIVEC */ - flush_fp_to_thread(current); + flush_fp_to_thread(tsk); /* copy fpr regs and fpscr */ - err |= copy_fpr_to_user(&sc->fp_regs, current); + err |= copy_fpr_to_user(&sc->fp_regs, tsk); /* * Clear the MSR VSX bit to indicate there is no valid state attached @@ -151,10 +155,10 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs, * then out to userspace. Update v_regs to point after the * VMX data. */ - if (current->thread.used_vsr && ctx_has_vsx_region) { - flush_vsx_to_thread(current); + if (tsk->thread.used_vsr && ctx_has_vsx_region) { + flush_vsx_to_thread(tsk); v_regs += ELF_NVRREG; - err |= copy_vsx_to_user(v_regs, current); + err |= copy_vsx_to_user(v_regs, tsk); /* set MSR_VSX in the MSR value in the frame to * indicate that sc->vs_reg) contains valid data. */ @@ -187,7 +191,7 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs, */ static long setup_tm_sigcontexts(struct sigcontext __user *sc, struct sigcontext __user *tm_sc, - struct pt_regs *regs, + struct task_struct *tsk, int signr, sigset_t *set, unsigned long handler) { /* When CONFIG_ALTIVEC is set, we _always_ setup v_regs even if the @@ -202,9 +206,12 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc, elf_vrreg_t __user *v_regs = sigcontext_vmx_regs(sc); elf_vrreg_t __user *tm_v_regs = sigcontext_vmx_regs(tm_sc); #endif - unsigned long msr = regs->msr; + struct pt_regs *regs = tsk->thread.regs; + unsigned long msr = tsk->thread.ckpt_regs.msr; long err = 0; + BUG_ON(tsk != current); + BUG_ON(!MSR_TM_ACTIVE(regs->msr)); /* Remove TM bits from thread's MSR. The MSR in the sigcontext @@ -214,28 +221,25 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc, */ regs->msr &= ~MSR_TS_MASK; - flush_fp_to_thread(current); - #ifdef CONFIG_ALTIVEC err |= __put_user(v_regs, &sc->v_regs); err |= __put_user(tm_v_regs, &tm_sc->v_regs); /* save altivec registers */ - if (current->thread.used_vr) { - flush_altivec_to_thread(current); + if (tsk->thread.used_vr) { /* Copy 33 vec registers (vr0..31 and vscr) to the stack */ - err |= __copy_to_user(v_regs, ¤t->thread.vr_state, + err |= __copy_to_user(v_regs, &tsk->thread.ckvr_state, 33 * sizeof(vector128)); /* If VEC was enabled there are transactional VRs valid too, * else they're a copy of the checkpointed VRs. */ if (msr & MSR_VEC) err |= __copy_to_user(tm_v_regs, - ¤t->thread.transact_vr, + &tsk->thread.vr_state, 33 * sizeof(vector128)); else err |= __copy_to_user(tm_v_regs, - ¤t->thread.vr_state, + &tsk->thread.ckvr_state, 33 * sizeof(vector128)); /* set MSR_VEC in the MSR value in the frame to indicate @@ -247,13 +251,13 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc, * use altivec. */ if (cpu_has_feature(CPU_FTR_ALTIVEC)) - current->thread.vrsave = mfspr(SPRN_VRSAVE); - err |= __put_user(current->thread.vrsave, (u32 __user *)&v_regs[33]); + tsk->thread.ckvrsave = mfspr(SPRN_VRSAVE); + err |= __put_user(tsk->thread.ckvrsave, (u32 __user *)&v_regs[33]); if (msr & MSR_VEC) - err |= __put_user(current->thread.transact_vrsave, + err |= __put_user(tsk->thread.vrsave, (u32 __user *)&tm_v_regs[33]); else - err |= __put_user(current->thread.vrsave, + err |= __put_user(tsk->thread.ckvrsave, (u32 __user *)&tm_v_regs[33]); #else /* CONFIG_ALTIVEC */ @@ -262,11 +266,11 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc, #endif /* CONFIG_ALTIVEC */ /* copy fpr regs and fpscr */ - err |= copy_fpr_to_user(&sc->fp_regs, current); + err |= copy_ckfpr_to_user(&sc->fp_regs, tsk); if (msr & MSR_FP) - err |= copy_transact_fpr_to_user(&tm_sc->fp_regs, current); + err |= copy_fpr_to_user(&tm_sc->fp_regs, tsk); else - err |= copy_fpr_to_user(&tm_sc->fp_regs, current); + err |= copy_ckfpr_to_user(&tm_sc->fp_regs, tsk); #ifdef CONFIG_VSX /* @@ -274,17 +278,16 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc, * then out to userspace. Update v_regs to point after the * VMX data. */ - if (current->thread.used_vsr) { - flush_vsx_to_thread(current); + if (tsk->thread.used_vsr) { v_regs += ELF_NVRREG; tm_v_regs += ELF_NVRREG; - err |= copy_vsx_to_user(v_regs, current); + err |= copy_ckvsx_to_user(v_regs, tsk); if (msr & MSR_VSX) - err |= copy_transact_vsx_to_user(tm_v_regs, current); + err |= copy_vsx_to_user(tm_v_regs, tsk); else - err |= copy_vsx_to_user(tm_v_regs, current); + err |= copy_ckvsx_to_user(tm_v_regs, tsk); /* set MSR_VSX in the MSR value in the frame to * indicate that sc->vs_reg) contains valid data. @@ -298,7 +301,7 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc, WARN_ON(!FULL_REGS(regs)); err |= __copy_to_user(&tm_sc->gp_regs, regs, GP_REGS_SIZE); err |= __copy_to_user(&sc->gp_regs, - ¤t->thread.ckpt_regs, GP_REGS_SIZE); + &tsk->thread.ckpt_regs, GP_REGS_SIZE); err |= __put_user(msr, &tm_sc->gp_regs[PT_MSR]); err |= __put_user(msr, &sc->gp_regs[PT_MSR]); err |= __put_user(signr, &sc->signal); @@ -314,7 +317,7 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc, * Restore the sigcontext from the signal frame. */ -static long restore_sigcontext(struct pt_regs *regs, sigset_t *set, int sig, +static long restore_sigcontext(struct task_struct *tsk, sigset_t *set, int sig, struct sigcontext __user *sc) { #ifdef CONFIG_ALTIVEC @@ -323,10 +326,13 @@ static long restore_sigcontext(struct pt_regs *regs, sigset_t *set, int sig, unsigned long err = 0; unsigned long save_r13 = 0; unsigned long msr; + struct pt_regs *regs = tsk->thread.regs; #ifdef CONFIG_VSX int i; #endif + BUG_ON(tsk != current); + /* If this is not a signal return, we preserve the TLS in r13 */ if (!sig) save_r13 = regs->gpr[13]; @@ -356,7 +362,7 @@ static long restore_sigcontext(struct pt_regs *regs, sigset_t *set, int sig, /* * Force reload of FP/VEC. - * This has to be done before copying stuff into current->thread.fpr/vr + * This has to be done before copying stuff into tsk->thread.fpr/vr * for the reasons explained in the previous comment. */ regs->msr &= ~(MSR_FP | MSR_FE0 | MSR_FE1 | MSR_VEC | MSR_VSX); @@ -368,21 +374,23 @@ static long restore_sigcontext(struct pt_regs *regs, sigset_t *set, int sig, if (v_regs && !access_ok(VERIFY_READ, v_regs, 34 * sizeof(vector128))) return -EFAULT; /* Copy 33 vec registers (vr0..31 and vscr) from the stack */ - if (v_regs != NULL && (msr & MSR_VEC) != 0) - err |= __copy_from_user(¤t->thread.vr_state, v_regs, + if (v_regs != NULL && (msr & MSR_VEC) != 0) { + err |= __copy_from_user(&tsk->thread.vr_state, v_regs, 33 * sizeof(vector128)); - else if (current->thread.used_vr) - memset(¤t->thread.vr_state, 0, 33 * sizeof(vector128)); + tsk->thread.used_vr = true; + } else if (tsk->thread.used_vr) { + memset(&tsk->thread.vr_state, 0, 33 * sizeof(vector128)); + } /* Always get VRSAVE back */ if (v_regs != NULL) - err |= __get_user(current->thread.vrsave, (u32 __user *)&v_regs[33]); + err |= __get_user(tsk->thread.vrsave, (u32 __user *)&v_regs[33]); else - current->thread.vrsave = 0; + tsk->thread.vrsave = 0; if (cpu_has_feature(CPU_FTR_ALTIVEC)) - mtspr(SPRN_VRSAVE, current->thread.vrsave); + mtspr(SPRN_VRSAVE, tsk->thread.vrsave); #endif /* CONFIG_ALTIVEC */ /* restore floating point */ - err |= copy_fpr_from_user(current, &sc->fp_regs); + err |= copy_fpr_from_user(tsk, &sc->fp_regs); #ifdef CONFIG_VSX /* * Get additional VSX data. Update v_regs to point after the @@ -390,11 +398,13 @@ static long restore_sigcontext(struct pt_regs *regs, sigset_t *set, int sig, * buffer for formatting, then into the taskstruct. */ v_regs += ELF_NVRREG; - if ((msr & MSR_VSX) != 0) - err |= copy_vsx_from_user(current, v_regs); - else + if ((msr & MSR_VSX) != 0) { + err |= copy_vsx_from_user(tsk, v_regs); + tsk->thread.used_vsr = true; + } else { for (i = 0; i < 32 ; i++) - current->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = 0; + tsk->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = 0; + } #endif return err; } @@ -404,7 +414,7 @@ static long restore_sigcontext(struct pt_regs *regs, sigset_t *set, int sig, * Restore the two sigcontexts from the frame of a transactional processes. */ -static long restore_tm_sigcontexts(struct pt_regs *regs, +static long restore_tm_sigcontexts(struct task_struct *tsk, struct sigcontext __user *sc, struct sigcontext __user *tm_sc) { @@ -413,12 +423,16 @@ static long restore_tm_sigcontexts(struct pt_regs *regs, #endif unsigned long err = 0; unsigned long msr; + struct pt_regs *regs = tsk->thread.regs; #ifdef CONFIG_VSX int i; #endif + + BUG_ON(tsk != current); + /* copy the GPRs */ err |= __copy_from_user(regs->gpr, tm_sc->gp_regs, sizeof(regs->gpr)); - err |= __copy_from_user(¤t->thread.ckpt_regs, sc->gp_regs, + err |= __copy_from_user(&tsk->thread.ckpt_regs, sc->gp_regs, sizeof(regs->gpr)); /* @@ -430,7 +444,7 @@ static long restore_tm_sigcontexts(struct pt_regs *regs, * we don't need to re-copy them here. */ err |= __get_user(regs->nip, &tm_sc->gp_regs[PT_NIP]); - err |= __get_user(current->thread.tm_tfhar, &sc->gp_regs[PT_NIP]); + err |= __get_user(tsk->thread.tm_tfhar, &sc->gp_regs[PT_NIP]); /* get MSR separately, transfer the LE bit if doing signal return */ err |= __get_user(msr, &sc->gp_regs[PT_MSR]); @@ -449,13 +463,13 @@ static long restore_tm_sigcontexts(struct pt_regs *regs, err |= __get_user(regs->link, &tm_sc->gp_regs[PT_LNK]); err |= __get_user(regs->xer, &tm_sc->gp_regs[PT_XER]); err |= __get_user(regs->ccr, &tm_sc->gp_regs[PT_CCR]); - err |= __get_user(current->thread.ckpt_regs.ctr, + err |= __get_user(tsk->thread.ckpt_regs.ctr, &sc->gp_regs[PT_CTR]); - err |= __get_user(current->thread.ckpt_regs.link, + err |= __get_user(tsk->thread.ckpt_regs.link, &sc->gp_regs[PT_LNK]); - err |= __get_user(current->thread.ckpt_regs.xer, + err |= __get_user(tsk->thread.ckpt_regs.xer, &sc->gp_regs[PT_XER]); - err |= __get_user(current->thread.ckpt_regs.ccr, + err |= __get_user(tsk->thread.ckpt_regs.ccr, &sc->gp_regs[PT_CCR]); /* These regs are not checkpointed; they can go in 'regs'. */ @@ -466,7 +480,7 @@ static long restore_tm_sigcontexts(struct pt_regs *regs, /* * Force reload of FP/VEC. - * This has to be done before copying stuff into current->thread.fpr/vr + * This has to be done before copying stuff into tsk->thread.fpr/vr * for the reasons explained in the previous comment. */ regs->msr &= ~(MSR_FP | MSR_FE0 | MSR_FE1 | MSR_VEC | MSR_VSX); @@ -483,32 +497,33 @@ static long restore_tm_sigcontexts(struct pt_regs *regs, return -EFAULT; /* Copy 33 vec registers (vr0..31 and vscr) from the stack */ if (v_regs != NULL && tm_v_regs != NULL && (msr & MSR_VEC) != 0) { - err |= __copy_from_user(¤t->thread.vr_state, v_regs, + err |= __copy_from_user(&tsk->thread.ckvr_state, v_regs, 33 * sizeof(vector128)); - err |= __copy_from_user(¤t->thread.transact_vr, tm_v_regs, + err |= __copy_from_user(&tsk->thread.vr_state, tm_v_regs, 33 * sizeof(vector128)); + current->thread.used_vr = true; } - else if (current->thread.used_vr) { - memset(¤t->thread.vr_state, 0, 33 * sizeof(vector128)); - memset(¤t->thread.transact_vr, 0, 33 * sizeof(vector128)); + else if (tsk->thread.used_vr) { + memset(&tsk->thread.vr_state, 0, 33 * sizeof(vector128)); + memset(&tsk->thread.ckvr_state, 0, 33 * sizeof(vector128)); } /* Always get VRSAVE back */ if (v_regs != NULL && tm_v_regs != NULL) { - err |= __get_user(current->thread.vrsave, + err |= __get_user(tsk->thread.ckvrsave, (u32 __user *)&v_regs[33]); - err |= __get_user(current->thread.transact_vrsave, + err |= __get_user(tsk->thread.vrsave, (u32 __user *)&tm_v_regs[33]); } else { - current->thread.vrsave = 0; - current->thread.transact_vrsave = 0; + tsk->thread.vrsave = 0; + tsk->thread.ckvrsave = 0; } if (cpu_has_feature(CPU_FTR_ALTIVEC)) - mtspr(SPRN_VRSAVE, current->thread.vrsave); + mtspr(SPRN_VRSAVE, tsk->thread.vrsave); #endif /* CONFIG_ALTIVEC */ /* restore floating point */ - err |= copy_fpr_from_user(current, &sc->fp_regs); - err |= copy_transact_fpr_from_user(current, &tm_sc->fp_regs); + err |= copy_fpr_from_user(tsk, &tm_sc->fp_regs); + err |= copy_ckfpr_from_user(tsk, &sc->fp_regs); #ifdef CONFIG_VSX /* * Get additional VSX data. Update v_regs to point after the @@ -518,32 +533,31 @@ static long restore_tm_sigcontexts(struct pt_regs *regs, if (v_regs && ((msr & MSR_VSX) != 0)) { v_regs += ELF_NVRREG; tm_v_regs += ELF_NVRREG; - err |= copy_vsx_from_user(current, v_regs); - err |= copy_transact_vsx_from_user(current, tm_v_regs); + err |= copy_vsx_from_user(tsk, tm_v_regs); + err |= copy_ckvsx_from_user(tsk, v_regs); + tsk->thread.used_vsr = true; } else { for (i = 0; i < 32 ; i++) { - current->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = 0; - current->thread.transact_fp.fpr[i][TS_VSRLOWOFFSET] = 0; + tsk->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = 0; + tsk->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET] = 0; } } #endif tm_enable(); /* Make sure the transaction is marked as failed */ - current->thread.tm_texasr |= TEXASR_FS; + tsk->thread.tm_texasr |= TEXASR_FS; /* This loads the checkpointed FP/VEC state, if used */ - tm_recheckpoint(¤t->thread, msr); + tm_recheckpoint(&tsk->thread, msr); - /* This loads the speculative FP/VEC state, if used */ + msr_check_and_set(msr & (MSR_FP | MSR_VEC)); if (msr & MSR_FP) { - do_load_up_transact_fpu(¤t->thread); - regs->msr |= (MSR_FP | current->thread.fpexc_mode); + load_fp_state(&tsk->thread.fp_state); + regs->msr |= (MSR_FP | tsk->thread.fpexc_mode); } -#ifdef CONFIG_ALTIVEC if (msr & MSR_VEC) { - do_load_up_transact_altivec(¤t->thread); + load_vr_state(&tsk->thread.vr_state); regs->msr |= MSR_VEC; } -#endif return err; } @@ -594,6 +608,8 @@ int sys_swapcontext(struct ucontext __user *old_ctx, unsigned long new_msr = 0; int ctx_has_vsx_region = 0; + BUG_ON(regs != current->thread.regs); + if (new_ctx && get_user(new_msr, &new_ctx->uc_mcontext.gp_regs[PT_MSR])) return -EFAULT; @@ -616,7 +632,7 @@ int sys_swapcontext(struct ucontext __user *old_ctx, if (old_ctx != NULL) { if (!access_ok(VERIFY_WRITE, old_ctx, ctx_size) - || setup_sigcontext(&old_ctx->uc_mcontext, regs, 0, NULL, 0, + || setup_sigcontext(&old_ctx->uc_mcontext, current, 0, NULL, 0, ctx_has_vsx_region) || __copy_to_user(&old_ctx->uc_sigmask, ¤t->blocked, sizeof(sigset_t))) @@ -644,7 +660,7 @@ int sys_swapcontext(struct ucontext __user *old_ctx, if (__copy_from_user(&set, &new_ctx->uc_sigmask, sizeof(set))) do_exit(SIGSEGV); set_current_blocked(&set); - if (restore_sigcontext(regs, NULL, 0, &new_ctx->uc_mcontext)) + if (restore_sigcontext(current, NULL, 0, &new_ctx->uc_mcontext)) do_exit(SIGSEGV); /* This returns like rt_sigreturn */ @@ -667,6 +683,8 @@ int sys_rt_sigreturn(unsigned long r3, unsigned long r4, unsigned long r5, unsigned long msr; #endif + BUG_ON(current->thread.regs != regs); + /* Always make any pending restarted system calls return -EINTR */ current->restart_block.fn = do_no_restart_syscall; @@ -698,14 +716,14 @@ int sys_rt_sigreturn(unsigned long r3, unsigned long r4, unsigned long r5, struct ucontext __user *uc_transact; if (__get_user(uc_transact, &uc->uc_link)) goto badframe; - if (restore_tm_sigcontexts(regs, &uc->uc_mcontext, + if (restore_tm_sigcontexts(current, &uc->uc_mcontext, &uc_transact->uc_mcontext)) goto badframe; } else /* Fall through, for non-TM restore */ #endif - if (restore_sigcontext(regs, NULL, 1, &uc->uc_mcontext)) + if (restore_sigcontext(current, NULL, 1, &uc->uc_mcontext)) goto badframe; if (restore_altstack(&uc->uc_stack)) @@ -724,13 +742,17 @@ badframe: return 0; } -int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs) +int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, + struct task_struct *tsk) { struct rt_sigframe __user *frame; unsigned long newsp = 0; long err = 0; + struct pt_regs *regs = tsk->thread.regs; + + BUG_ON(tsk != current); - frame = get_sigframe(ksig, get_tm_stackpointer(regs), sizeof(*frame), 0); + frame = get_sigframe(ksig, get_tm_stackpointer(tsk), sizeof(*frame), 0); if (unlikely(frame == NULL)) goto badframe; @@ -751,14 +773,13 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs err |= __put_user(&frame->uc_transact, &frame->uc.uc_link); err |= setup_tm_sigcontexts(&frame->uc.uc_mcontext, &frame->uc_transact.uc_mcontext, - regs, ksig->sig, - NULL, + tsk, ksig->sig, NULL, (unsigned long)ksig->ka.sa.sa_handler); } else #endif { err |= __put_user(0, &frame->uc.uc_link); - err |= setup_sigcontext(&frame->uc.uc_mcontext, regs, ksig->sig, + err |= setup_sigcontext(&frame->uc.uc_mcontext, tsk, ksig->sig, NULL, (unsigned long)ksig->ka.sa.sa_handler, 1); } @@ -767,11 +788,11 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs goto badframe; /* Make sure signal handler doesn't get spurious FP exceptions */ - current->thread.fp_state.fpscr = 0; + tsk->thread.fp_state.fpscr = 0; /* Set up to return from userspace. */ - if (vdso64_rt_sigtramp && current->mm->context.vdso_base) { - regs->link = current->mm->context.vdso_base + vdso64_rt_sigtramp; + if (vdso64_rt_sigtramp && tsk->mm->context.vdso_base) { + regs->link = tsk->mm->context.vdso_base + vdso64_rt_sigtramp; } else { err |= setup_trampoline(__NR_rt_sigreturn, &frame->tramp[0]); if (err) @@ -821,7 +842,7 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs badframe: if (show_unhandled_signals) printk_ratelimited(regs->msr & MSR_64BIT ? fmt64 : fmt32, - current->comm, current->pid, "setup_rt_frame", + tsk->comm, tsk->pid, "setup_rt_frame", (long)frame, regs->nip, regs->link); return 1; diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c index 5fa92706444b..644cce3d8dce 100644 --- a/arch/powerpc/kernel/syscalls.c +++ b/arch/powerpc/kernel/syscalls.c @@ -40,6 +40,7 @@ #include <asm/syscalls.h> #include <asm/time.h> #include <asm/unistd.h> +#include <asm/asm-prototypes.h> static inline unsigned long do_mmap2(unsigned long addr, size_t len, unsigned long prot, unsigned long flags, diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 3efbedefba6a..67859b7d1c97 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -73,6 +73,7 @@ #include <asm/vdso_datapage.h> #include <asm/firmware.h> #include <asm/cputime.h> +#include <asm/asm-prototypes.h> /* powerpc clocksource/clockevent code */ diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index 298afcf3bf2a..3a2d04134da9 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -108,6 +108,7 @@ _GLOBAL(tm_reclaim) /* We've a struct pt_regs at [r1+STACK_FRAME_OVERHEAD]. */ std r3, STK_PARAM(R3)(r1) + std r4, STK_PARAM(R4)(r1) SAVE_NVGPRS(r1) /* We need to setup MSR for VSX register save instructions. */ @@ -126,43 +127,6 @@ _GLOBAL(tm_reclaim) mtmsrd r15 std r14, TM_FRAME_L0(r1) - /* Stash the stack pointer away for use after reclaim */ - std r1, PACAR1(r13) - - /* ******************** FPR/VR/VSRs ************ - * Before reclaiming, capture the current/transactional FPR/VR - * versions /if used/. - * - * (If VSX used, FP and VMX are implied. Or, we don't need to look - * at MSR.VSX as copying FP regs if .FP, vector regs if .VMX covers it.) - * - * We're passed the thread's MSR as parameter 2. - * - * We enabled VEC/FP/VSX in the msr above, so we can execute these - * instructions! - */ - andis. r0, r4, MSR_VEC@h - beq dont_backup_vec - - addi r7, r3, THREAD_TRANSACT_VRSTATE - SAVE_32VRS(0, r6, r7) /* r6 scratch, r7 transact vr state */ - mfvscr v0 - li r6, VRSTATE_VSCR - stvx v0, r7, r6 -dont_backup_vec: - mfspr r0, SPRN_VRSAVE - std r0, THREAD_TRANSACT_VRSAVE(r3) - - andi. r0, r4, MSR_FP - beq dont_backup_fp - - addi r7, r3, THREAD_TRANSACT_FPSTATE - SAVE_32FPRS_VSRS(0, R6, R7) /* r6 scratch, r7 transact fp state */ - - mffs fr0 - stfd fr0,FPSTATE_FPSCR(r7) - -dont_backup_fp: /* Do sanity check on MSR to make sure we are suspended */ li r7, (MSR_TS_S)@higher srdi r6, r14, 32 @@ -170,6 +134,9 @@ dont_backup_fp: 1: tdeqi r6, 0 EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0 + /* Stash the stack pointer away for use after reclaim */ + std r1, PACAR1(r13) + /* Clear MSR RI since we are about to change r1, EE is already off. */ li r4, 0 mtmsrd r4, 1 @@ -273,6 +240,43 @@ dont_backup_fp: * MSR. */ + + /* ******************** FPR/VR/VSRs ************ + * After reclaiming, capture the checkpointed FPRs/VRs /if used/. + * + * (If VSX used, FP and VMX are implied. Or, we don't need to look + * at MSR.VSX as copying FP regs if .FP, vector regs if .VMX covers it.) + * + * We're passed the thread's MSR as the second parameter + * + * We enabled VEC/FP/VSX in the msr above, so we can execute these + * instructions! + */ + ld r4, STK_PARAM(R4)(r1) /* Second parameter, MSR * */ + mr r3, r12 + andis. r0, r4, MSR_VEC@h + beq dont_backup_vec + + addi r7, r3, THREAD_CKVRSTATE + SAVE_32VRS(0, r6, r7) /* r6 scratch, r7 transact vr state */ + mfvscr v0 + li r6, VRSTATE_VSCR + stvx v0, r7, r6 +dont_backup_vec: + mfspr r0, SPRN_VRSAVE + std r0, THREAD_CKVRSAVE(r3) + + andi. r0, r4, MSR_FP + beq dont_backup_fp + + addi r7, r3, THREAD_CKFPSTATE + SAVE_32FPRS_VSRS(0, R6, R7) /* r6 scratch, r7 transact fp state */ + + mffs fr0 + stfd fr0,FPSTATE_FPSCR(r7) + +dont_backup_fp: + /* TM regs, incl TEXASR -- these live in thread_struct. Note they've * been updated by the treclaim, to explain to userland the failure * cause (aborted). @@ -288,6 +292,7 @@ dont_backup_fp: /* Restore original MSR/IRQ state & clear TM mode */ ld r14, TM_FRAME_L0(r1) /* Orig MSR */ + li r15, 0 rldimi r14, r15, MSR_TS_LG, (63-MSR_TS_LG)-1 mtmsrd r14 @@ -356,28 +361,29 @@ _GLOBAL(__tm_recheckpoint) mtmsr r5 #ifdef CONFIG_ALTIVEC - /* FP and VEC registers: These are recheckpointed from thread.fpr[] - * and thread.vr[] respectively. The thread.transact_fpr[] version - * is more modern, and will be loaded subsequently by any FPUnavailable - * trap. + /* + * FP and VEC registers: These are recheckpointed from + * thread.ckfp_state and thread.ckvr_state respectively. The + * thread.fp_state[] version holds the 'live' (transactional) + * and will be loaded subsequently by any FPUnavailable trap. */ andis. r0, r4, MSR_VEC@h beq dont_restore_vec - addi r8, r3, THREAD_VRSTATE + addi r8, r3, THREAD_CKVRSTATE li r5, VRSTATE_VSCR lvx v0, r8, r5 mtvscr v0 REST_32VRS(0, r5, r8) /* r5 scratch, r8 ptr */ dont_restore_vec: - ld r5, THREAD_VRSAVE(r3) + ld r5, THREAD_CKVRSAVE(r3) mtspr SPRN_VRSAVE, r5 #endif andi. r0, r4, MSR_FP beq dont_restore_fp - addi r8, r3, THREAD_FPSTATE + addi r8, r3, THREAD_CKFPSTATE lfd fr0, FPSTATE_FPSCR(r8) MTFSF_L(fr0) REST_32FPRS_VSRS(0, R4, R8) diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 62859ebe0062..a1f8f5641e9e 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -117,7 +117,7 @@ static int die_owner = -1; static unsigned int die_nest_count; static int die_counter; -static unsigned __kprobes long oops_begin(struct pt_regs *regs) +static unsigned long oops_begin(struct pt_regs *regs) { int cpu; unsigned long flags; @@ -144,8 +144,9 @@ static unsigned __kprobes long oops_begin(struct pt_regs *regs) pmac_backlight_unblank(); return flags; } +NOKPROBE_SYMBOL(oops_begin); -static void __kprobes oops_end(unsigned long flags, struct pt_regs *regs, +static void oops_end(unsigned long flags, struct pt_regs *regs, int signr) { bust_spinlocks(0); @@ -196,8 +197,9 @@ static void __kprobes oops_end(unsigned long flags, struct pt_regs *regs, panic("Fatal exception"); do_exit(signr); } +NOKPROBE_SYMBOL(oops_end); -static int __kprobes __die(const char *str, struct pt_regs *regs, long err) +static int __die(const char *str, struct pt_regs *regs, long err) { printk("Oops: %s, sig: %ld [#%d]\n", str, err, ++die_counter); #ifdef CONFIG_PREEMPT @@ -221,6 +223,7 @@ static int __kprobes __die(const char *str, struct pt_regs *regs, long err) return 0; } +NOKPROBE_SYMBOL(__die); void die(const char *str, struct pt_regs *regs, long err) { @@ -802,7 +805,7 @@ void RunModeException(struct pt_regs *regs) _exception(SIGTRAP, regs, 0, 0); } -void __kprobes single_step_exception(struct pt_regs *regs) +void single_step_exception(struct pt_regs *regs) { enum ctx_state prev_state = exception_enter(); @@ -819,6 +822,7 @@ void __kprobes single_step_exception(struct pt_regs *regs) bail: exception_exit(prev_state); } +NOKPROBE_SYMBOL(single_step_exception); /* * After we have successfully emulated an instruction, we have to @@ -1140,7 +1144,7 @@ static int emulate_math(struct pt_regs *regs) static inline int emulate_math(struct pt_regs *regs) { return -1; } #endif -void __kprobes program_check_exception(struct pt_regs *regs) +void program_check_exception(struct pt_regs *regs) { enum ctx_state prev_state = exception_enter(); unsigned int reason = get_reason(regs); @@ -1260,16 +1264,18 @@ sigill: bail: exception_exit(prev_state); } +NOKPROBE_SYMBOL(program_check_exception); /* * This occurs when running in hypervisor mode on POWER6 or later * and an illegal instruction is encountered. */ -void __kprobes emulation_assist_interrupt(struct pt_regs *regs) +void emulation_assist_interrupt(struct pt_regs *regs) { regs->msr |= REASON_ILLEGAL; program_check_exception(regs); } +NOKPROBE_SYMBOL(emulation_assist_interrupt); void alignment_exception(struct pt_regs *regs) { @@ -1310,6 +1316,18 @@ bail: exception_exit(prev_state); } +void slb_miss_bad_addr(struct pt_regs *regs) +{ + enum ctx_state prev_state = exception_enter(); + + if (user_mode(regs)) + _exception(SIGSEGV, regs, SEGV_BNDERR, regs->dar); + else + bad_page_fault(regs, regs->dar, SIGSEGV); + + exception_exit(prev_state); +} + void StackOverflow(struct pt_regs *regs) { printk(KERN_CRIT "Kernel stack overflow in process %p, r1=%lx\n", @@ -1372,6 +1390,22 @@ void vsx_unavailable_exception(struct pt_regs *regs) } #ifdef CONFIG_PPC64 +static void tm_unavailable(struct pt_regs *regs) +{ +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (user_mode(regs)) { + current->thread.load_tm++; + regs->msr |= MSR_TM; + tm_enable(); + tm_restore_sprs(¤t->thread); + return; + } +#endif + pr_emerg("Unrecoverable TM Unavailable Exception " + "%lx at %lx\n", regs->trap, regs->nip); + die("Unrecoverable TM Unavailable Exception", regs, SIGABRT); +} + void facility_unavailable_exception(struct pt_regs *regs) { static char *facility_strings[] = { @@ -1451,6 +1485,27 @@ void facility_unavailable_exception(struct pt_regs *regs) return; } + if (status == FSCR_TM_LG) { + /* + * If we're here then the hardware is TM aware because it + * generated an exception with FSRM_TM set. + * + * If cpu_has_feature(CPU_FTR_TM) is false, then either firmware + * told us not to do TM, or the kernel is not built with TM + * support. + * + * If both of those things are true, then userspace can spam the + * console by triggering the printk() below just by continually + * doing tbegin (or any TM instruction). So in that case just + * send the process a SIGILL immediately. + */ + if (!cpu_has_feature(CPU_FTR_TM)) + goto out; + + tm_unavailable(regs); + return; + } + if ((status < ARRAY_SIZE(facility_strings)) && facility_strings[status]) facility = facility_strings[status]; @@ -1463,6 +1518,7 @@ void facility_unavailable_exception(struct pt_regs *regs) "%sFacility '%s' unavailable, exception at 0x%lx, MSR=%lx\n", hv ? "Hypervisor " : "", facility, regs->nip, regs->msr); +out: if (user_mode(regs)) { _exception(SIGILL, regs, ILL_ILLOPC, regs->nip); return; @@ -1504,7 +1560,8 @@ void fp_unavailable_tm(struct pt_regs *regs) /* If VMX is in use, get the transactional values back */ if (regs->msr & MSR_VEC) { - do_load_up_transact_altivec(¤t->thread); + msr_check_and_set(MSR_VEC); + load_vr_state(¤t->thread.vr_state); /* At this point all the VSX state is loaded, so enable it */ regs->msr |= MSR_VSX; } @@ -1525,7 +1582,8 @@ void altivec_unavailable_tm(struct pt_regs *regs) current->thread.used_vr = 1; if (regs->msr & MSR_FP) { - do_load_up_transact_fpu(¤t->thread); + msr_check_and_set(MSR_FP); + load_fp_state(¤t->thread.fp_state); regs->msr |= MSR_VSX; } } @@ -1564,10 +1622,12 @@ void vsx_unavailable_tm(struct pt_regs *regs) */ tm_recheckpoint(¤t->thread, regs->msr & ~orig_msr); + msr_check_and_set(orig_msr & (MSR_FP | MSR_VEC)); + if (orig_msr & MSR_FP) - do_load_up_transact_fpu(¤t->thread); + load_fp_state(¤t->thread.fp_state); if (orig_msr & MSR_VEC) - do_load_up_transact_altivec(¤t->thread); + load_vr_state(¤t->thread.vr_state); } #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ @@ -1656,7 +1716,7 @@ static void handle_debug(struct pt_regs *regs, unsigned long debug_status) mtspr(SPRN_DBCR0, current->thread.debug.dbcr0); } -void __kprobes DebugException(struct pt_regs *regs, unsigned long debug_status) +void DebugException(struct pt_regs *regs, unsigned long debug_status) { current->thread.debug.dbsr = debug_status; @@ -1717,6 +1777,7 @@ void __kprobes DebugException(struct pt_regs *regs, unsigned long debug_status) } else handle_debug(regs, debug_status); } +NOKPROBE_SYMBOL(DebugException); #endif /* CONFIG_PPC_ADV_DEBUG_REGS */ #if !defined(CONFIG_TAU_INT) diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile index 366ae09b14c1..31107bf5a61f 100644 --- a/arch/powerpc/kernel/vdso64/Makefile +++ b/arch/powerpc/kernel/vdso64/Makefile @@ -31,15 +31,9 @@ $(obj)/%.so: OBJCOPYFLAGS := -S $(obj)/%.so: $(obj)/%.so.dbg FORCE $(call if_changed,objcopy) -# assembly rules for the .S files -$(obj-vdso64): %.o: %.S FORCE - $(call if_changed_dep,vdso64as) - # actual build commands quiet_cmd_vdso64ld = VDSO64L $@ cmd_vdso64ld = $(CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) -quiet_cmd_vdso64as = VDSO64A $@ - cmd_vdso64as = $(CC) $(a_flags) -c -o $@ $< # install commands for the unstripped file quiet_cmd_vdso_install = INSTALL $@ diff --git a/arch/powerpc/kernel/vdso64/datapage.S b/arch/powerpc/kernel/vdso64/datapage.S index 184a6ba7f283..abf17feffe40 100644 --- a/arch/powerpc/kernel/vdso64/datapage.S +++ b/arch/powerpc/kernel/vdso64/datapage.S @@ -59,7 +59,7 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map) bl V_LOCAL_FUNC(__get_datapage) mtlr r12 addi r3,r3,CFG_SYSCALL_MAP64 - cmpli cr0,r4,0 + cmpldi cr0,r4,0 crclr cr0*4+so beqlr li r0,NR_syscalls diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S index a76b4af37ef2..382021324883 100644 --- a/arch/powerpc/kernel/vdso64/gettimeofday.S +++ b/arch/powerpc/kernel/vdso64/gettimeofday.S @@ -145,7 +145,7 @@ V_FUNCTION_BEGIN(__kernel_clock_getres) bne cr0,99f li r3,0 - cmpli cr0,r4,0 + cmpldi cr0,r4,0 crclr cr0*4+so beqlr lis r5,CLOCK_REALTIME_RES@h diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S index 616a6d854638..bc85bdff4e01 100644 --- a/arch/powerpc/kernel/vector.S +++ b/arch/powerpc/kernel/vector.S @@ -7,31 +7,6 @@ #include <asm/page.h> #include <asm/ptrace.h> -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM -/* void do_load_up_transact_altivec(struct thread_struct *thread) - * - * This is similar to load_up_altivec but for the transactional version of the - * vector regs. It doesn't mess with the task MSR or valid flags. - * Furthermore, VEC laziness is not supported with TM currently. - */ -_GLOBAL(do_load_up_transact_altivec) - mfmsr r6 - oris r5,r6,MSR_VEC@h - MTMSRD(r5) - isync - - li r4,1 - stw r4,THREAD_USED_VR(r3) - - li r10,THREAD_TRANSACT_VRSTATE+VRSTATE_VSCR - lvx v0,r10,r3 - mtvscr v0 - addi r10,r3,THREAD_TRANSACT_VRSTATE - REST_32VRS(0,r4,r10) - - blr -#endif - /* * Load state from memory into VMX registers including VSCR. * Assumes the caller has enabled VMX in the MSR. diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index b5fba689fca6..2d1cfafd1404 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -44,11 +44,58 @@ SECTIONS * Text, read only data and other permanent read-only sections */ - /* Text and gots */ + _text = .; + _stext = .; + + /* + * Head text. + * This needs to be in its own output section to avoid ld placing + * branch trampoline stubs randomly throughout the fixed sections, + * which it will do (even if the branch comes from another section) + * in order to optimize stub generation. + */ + .head.text : AT(ADDR(.head.text) - LOAD_OFFSET) { +#ifdef CONFIG_PPC64 + KEEP(*(.head.text.first_256B)); +#ifdef CONFIG_PPC_BOOK3E +# define END_FIXED 0x100 +#else + KEEP(*(.head.text.real_vectors)); + *(.head.text.real_trampolines); + KEEP(*(.head.text.virt_vectors)); + *(.head.text.virt_trampolines); +# if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) + KEEP(*(.head.data.fwnmi_page)); +# define END_FIXED 0x8000 +# else +# define END_FIXED 0x7000 +# endif +#endif + ASSERT((. == END_FIXED), "vmlinux.lds.S: fixed section overflow error"); +#else /* !CONFIG_PPC64 */ + HEAD_TEXT +#endif + } :kernel + + /* + * If the build dies here, it's likely code in head_64.S is referencing + * labels it can't reach, and the linker inserting stubs without the + * assembler's knowledge. To debug, remove the above assert and + * rebuild. Look for branch stubs in the fixed section region. + * + * Linker stub generation could be allowed in "trampoline" + * sections if absolutely necessary, but this would require + * some rework of the fixed sections. Before resorting to this, + * consider references that have sufficient addressing range, + * (e.g., hand coded trampolines) so the linker does not have + * to add stubs. + * + * Linker stubs at the top of the main text section are currently not + * detected, and will result in a crash at boot due to offsets being + * wrong. + */ .text : AT(ADDR(.text) - LOAD_OFFSET) { ALIGN_FUNCTION(); - HEAD_TEXT - _text = .; /* careful! __ftr_alt_* sections need to be close to .text */ *(.text .fixup __ftr_alt_* .ref.text) SCHED_TEXT @@ -56,6 +103,8 @@ SECTIONS KPROBES_TEXT IRQENTRY_TEXT SOFTIRQENTRY_TEXT + MEM_KEEP(init.text) + MEM_KEEP(exit.text) #ifdef CONFIG_PPC32 *(.got1) |