diff options
| author | Linus Torvalds | 2018-04-07 21:08:19 +0200 |
|---|---|---|
| committer | Linus Torvalds | 2018-04-07 21:08:19 +0200 |
| commit | 49a695ba723224875df50e327bd7b0b65dd9a56b (patch) | |
| tree | 02372931e3e751106ca16bae14567d990bf22ad8 /arch/powerpc/kernel | |
| parent | Merge tag 'leaks-4.17-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/t... (diff) | |
| parent | powerpc/64s/idle: Fix restore of AMOR on POWER9 after deep sleep (diff) | |
| download | kernel-qcow2-linux-49a695ba723224875df50e327bd7b0b65dd9a56b.tar.gz kernel-qcow2-linux-49a695ba723224875df50e327bd7b0b65dd9a56b.tar.xz kernel-qcow2-linux-49a695ba723224875df50e327bd7b0b65dd9a56b.zip | |
Merge tag 'powerpc-4.17-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux
Pull powerpc updates from Michael Ellerman:
"Notable changes:
- Support for 4PB user address space on 64-bit, opt-in via mmap().
- Removal of POWER4 support, which was accidentally broken in 2016
and no one noticed, and blocked use of some modern instructions.
- Workarounds so that the hypervisor can enable Transactional Memory
on Power9.
- A series to disable the DAWR (Data Address Watchpoint Register) on
Power9.
- More information displayed in the meltdown/spectre_v1/v2 sysfs
files.
- A vpermxor (Power8 Altivec) implementation for the raid6 Q
Syndrome.
- A big series to make the allocation of our pacas (per cpu area),
kernel page tables, and per-cpu stacks NUMA aware when using the
Radix MMU on Power9.
And as usual many fixes, reworks and cleanups.
Thanks to: Aaro Koskinen, Alexandre Belloni, Alexey Kardashevskiy,
Alistair Popple, Andy Shevchenko, Aneesh Kumar K.V, Anshuman Khandual,
Balbir Singh, Benjamin Herrenschmidt, Christophe Leroy, Christophe
Lombard, Cyril Bur, Daniel Axtens, Dave Young, Finn Thain, Frederic
Barrat, Gustavo Romero, Horia Geantă, Jonathan Neuschäfer, Kees Cook,
Larry Finger, Laurent Dufour, Laurent Vivier, Logan Gunthorpe,
Madhavan Srinivasan, Mark Greer, Mark Hairgrove, Markus Elfring,
Mathieu Malaterre, Matt Brown, Matt Evans, Mauricio Faria de Oliveira,
Michael Neuling, Naveen N. Rao, Nicholas Piggin, Paul Mackerras,
Philippe Bergheaud, Ram Pai, Rob Herring, Sam Bobroff, Segher
Boessenkool, Simon Guo, Simon Horman, Stewart Smith, Sukadev
Bhattiprolu, Suraj Jitindar Singh, Thiago Jung Bauermann, Vaibhav
Jain, Vaidyanathan Srinivasan, Vasant Hegde, Wei Yongjun"
* tag 'powerpc-4.17-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (207 commits)
powerpc/64s/idle: Fix restore of AMOR on POWER9 after deep sleep
powerpc/64s: Fix POWER9 DD2.2 and above in cputable features
powerpc/64s: Fix pkey support in dt_cpu_ftrs, add CPU_FTR_PKEY bit
powerpc/64s: Fix dt_cpu_ftrs to have restore_cpu clear unwanted LPCR bits
Revert "powerpc/64s/idle: POWER9 ESL=0 stop avoid save/restore overhead"
powerpc: iomap.c: introduce io{read|write}64_{lo_hi|hi_lo}
powerpc: io.h: move iomap.h include so that it can use readq/writeq defs
cxl: Fix possible deadlock when processing page faults from cxllib
powerpc/hw_breakpoint: Only disable hw breakpoint if cpu supports it
powerpc/mm/radix: Update command line parsing for disable_radix
powerpc/mm/radix: Parse disable_radix commandline correctly.
powerpc/mm/hugetlb: initialize the pagetable cache correctly for hugetlb
powerpc/mm/radix: Update pte fragment count from 16 to 256 on radix
powerpc/mm/keys: Update documentation and remove unnecessary check
powerpc/64s/idle: POWER9 ESL=0 stop avoid save/restore overhead
powerpc/64s/idle: Consolidate power9_offline_stop()/power9_idle_stop()
powerpc/powernv: Always stop secondaries before reboot/shutdown
powerpc: hard disable irqs in smp_send_stop loop
powerpc: use NMI IPI for smp_send_stop
powerpc/powernv: Fix SMT4 forcing idle code
...
Diffstat (limited to 'arch/powerpc/kernel')
40 files changed, 828 insertions, 521 deletions
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 2358f97d62ec..2b4c40b255e4 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -42,7 +42,7 @@ obj-$(CONFIG_VDSO32) += vdso32/ obj-$(CONFIG_PPC_WATCHDOG) += watchdog.o obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_ppc970.o cpu_setup_pa6t.o -obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o +obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o security.o obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_book3e.o obj-$(CONFIG_PPC64) += vdso64/ diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index ea5eb91b836e..6bee65f3cfd3 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -221,12 +221,17 @@ int main(void) OFFSET(PACA_EXMC, paca_struct, exmc); OFFSET(PACA_EXSLB, paca_struct, exslb); OFFSET(PACA_EXNMI, paca_struct, exnmi); +#ifdef CONFIG_PPC_PSERIES OFFSET(PACALPPACAPTR, paca_struct, lppaca_ptr); +#endif OFFSET(PACA_SLBSHADOWPTR, paca_struct, slb_shadow_ptr); OFFSET(SLBSHADOW_STACKVSID, slb_shadow, save_area[SLB_NUM_BOLTED - 1].vsid); OFFSET(SLBSHADOW_STACKESID, slb_shadow, save_area[SLB_NUM_BOLTED - 1].esid); OFFSET(SLBSHADOW_SAVEAREA, slb_shadow, save_area); OFFSET(LPPACA_PMCINUSE, lppaca, pmcregs_in_use); +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + OFFSET(PACA_PMCINUSE, paca_struct, pmcregs_in_use); +#endif OFFSET(LPPACA_DTLIDX, lppaca, dtl_idx); OFFSET(LPPACA_YIELDCOUNT, lppaca, yield_count); OFFSET(PACA_DTL_RIDX, paca_struct, dtl_ridx); @@ -568,6 +573,7 @@ int main(void) OFFSET(VCPU_TFHAR, kvm_vcpu, arch.tfhar); OFFSET(VCPU_TFIAR, kvm_vcpu, arch.tfiar); OFFSET(VCPU_TEXASR, kvm_vcpu, arch.texasr); + OFFSET(VCPU_ORIG_TEXASR, kvm_vcpu, arch.orig_texasr); OFFSET(VCPU_GPR_TM, kvm_vcpu, arch.gpr_tm); OFFSET(VCPU_FPRS_TM, kvm_vcpu, arch.fp_tm.fpr); OFFSET(VCPU_VRS_TM, kvm_vcpu, arch.vr_tm.vr); @@ -650,6 +656,7 @@ int main(void) HSTATE_FIELD(HSTATE_HOST_IPI, host_ipi); HSTATE_FIELD(HSTATE_PTID, ptid); HSTATE_FIELD(HSTATE_TID, tid); + HSTATE_FIELD(HSTATE_FAKE_SUSPEND, fake_suspend); HSTATE_FIELD(HSTATE_MMCR0, host_mmcr[0]); HSTATE_FIELD(HSTATE_MMCR1, host_mmcr[1]); HSTATE_FIELD(HSTATE_MMCRA, host_mmcr[2]); @@ -759,6 +766,7 @@ int main(void) OFFSET(PACA_SUBCORE_SIBLING_MASK, paca_struct, subcore_sibling_mask); OFFSET(PACA_SIBLING_PACA_PTRS, paca_struct, thread_sibling_pacas); OFFSET(PACA_REQ_PSSCR, paca_struct, requested_psscr); + OFFSET(PACA_DONT_STOP, paca_struct, dont_stop); #define STOP_SPR(x, f) OFFSET(x, paca_struct, stop_sprs.f) STOP_SPR(STOP_PID, pid); STOP_SPR(STOP_LDBAR, ldbar); diff --git a/arch/powerpc/kernel/cpu_setup_6xx.S b/arch/powerpc/kernel/cpu_setup_6xx.S index c5e5a94d9892..a9f3970693e1 100644 --- a/arch/powerpc/kernel/cpu_setup_6xx.S +++ b/arch/powerpc/kernel/cpu_setup_6xx.S @@ -226,7 +226,7 @@ BEGIN_FTR_SECTION beq 1f END_FTR_SECTION_IFSET(CPU_FTR_L3CR) lwz r6,CPU_SPEC_FEATURES(r4) - andi. r0,r6,CPU_FTR_L3_DISABLE_NAP + andis. r0,r6,CPU_FTR_L3_DISABLE_NAP@h beq 1f li r7,CPU_FTR_CAN_NAP andc r6,r6,r7 diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S index 462aed9bcf51..8d142e5d84cd 100644 --- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S +++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S @@ -162,7 +162,7 @@ _GLOBAL(__setup_cpu_e5500) * the feature on the primary core, avoid doing it on the * secondary core. */ - andis. r6, r3, CPU_FTR_EMB_HV@h + andi. r6, r3, CPU_FTR_EMB_HV beq 2f rlwinm r3, r3, 0, ~CPU_FTR_EMB_HV stw r3, CPU_SPEC_FEATURES(r4) diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index c40a9fc1e5d1..c8fc9691f8c7 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -133,36 +133,6 @@ extern void __restore_cpu_e6500(void); static struct cpu_spec __initdata cpu_specs[] = { #ifdef CONFIG_PPC_BOOK3S_64 - { /* Power4 */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00350000, - .cpu_name = "POWER4 (gp)", - .cpu_features = CPU_FTRS_POWER4, - .cpu_user_features = COMMON_USER_POWER4, - .mmu_features = MMU_FTRS_POWER4 | MMU_FTR_TLBIE_CROP_VA, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 8, - .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power4", - .oprofile_type = PPC_OPROFILE_POWER4, - .platform = "power4", - }, - { /* Power4+ */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00380000, - .cpu_name = "POWER4+ (gq)", - .cpu_features = CPU_FTRS_POWER4, - .cpu_user_features = COMMON_USER_POWER4, - .mmu_features = MMU_FTRS_POWER4 | MMU_FTR_TLBIE_CROP_VA, - .icache_bsize = 128, - .dcache_bsize = 128, - .num_pmcs = 8, - .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power4", - .oprofile_type = PPC_OPROFILE_POWER4, - .platform = "power4", - }, { /* PPC970 */ .pvr_mask = 0xffff0000, .pvr_value = 0x00390000, @@ -553,11 +523,30 @@ static struct cpu_spec __initdata cpu_specs[] = { .machine_check_early = __machine_check_early_realmode_p9, .platform = "power9", }, - { /* Power9 DD 2.1 or later (see DD2.0 above) */ + { /* Power9 DD 2.1 */ + .pvr_mask = 0xffffefff, + .pvr_value = 0x004e0201, + .cpu_name = "POWER9 (raw)", + .cpu_features = CPU_FTRS_POWER9_DD2_1, + .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, + .machine_check_early = __machine_check_early_realmode_p9, + .platform = "power9", + }, + { /* Power9 DD2.2 or later */ .pvr_mask = 0xffff0000, .pvr_value = 0x004e0000, .cpu_name = "POWER9 (raw)", - .cpu_features = CPU_FTRS_POWER9_DD2_1, + .cpu_features = CPU_FTRS_POWER9_DD2_2, .cpu_user_features = COMMON_USER_POWER9, .cpu_user_features2 = COMMON_USER2_POWER9, .mmu_features = MMU_FTRS_POWER9, @@ -609,15 +598,15 @@ static struct cpu_spec __initdata cpu_specs[] = { { /* default match */ .pvr_mask = 0x00000000, .pvr_value = 0x00000000, - .cpu_name = "POWER4 (compatible)", + .cpu_name = "POWER5 (compatible)", .cpu_features = CPU_FTRS_COMPATIBLE, .cpu_user_features = COMMON_USER_PPC64, - .mmu_features = MMU_FTRS_DEFAULT_HPTE_ARCH_V2, + .mmu_features = MMU_FTRS_POWER, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, .pmc_type = PPC_PMC_IBM, - .platform = "power4", + .platform = "power5", } #endif /* CONFIG_PPC_BOOK3S_64 */ diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c index 00b215125d3e..17c8b99680f2 100644 --- a/arch/powerpc/kernel/crash.c +++ b/arch/powerpc/kernel/crash.c @@ -238,7 +238,7 @@ static void __maybe_unused crash_kexec_wait_realmode(int cpu) if (i == cpu) continue; - while (paca[i].kexec_state < KEXEC_STATE_REAL_MODE) { + while (paca_ptrs[i]->kexec_state < KEXEC_STATE_REAL_MODE) { barrier(); if (!cpu_possible(i) || !cpu_online(i) || (msecs <= 0)) break; diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 8ca5d5b74618..e88fbb1fdb8f 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -54,8 +54,7 @@ struct dt_cpu_feature { }; #define CPU_FTRS_BASE \ - (CPU_FTR_USE_TB | \ - CPU_FTR_LWSYNC | \ + (CPU_FTR_LWSYNC | \ CPU_FTR_FPU_UNAVAILABLE |\ CPU_FTR_NODSISRALIGN |\ CPU_FTR_NOEXECUTE |\ @@ -84,6 +83,7 @@ static int hv_mode; static struct { u64 lpcr; + u64 lpcr_clear; u64 hfscr; u64 fscr; } system_registers; @@ -92,6 +92,8 @@ static void (*init_pmu_registers)(void); static void __restore_cpu_cpufeatures(void) { + u64 lpcr; + /* * LPCR is restored by the power on engine already. It can be changed * after early init e.g., by radix enable, and we have no unified API @@ -104,8 +106,10 @@ static void __restore_cpu_cpufeatures(void) * The best we can do to accommodate secondary boot and idle restore * for now is "or" LPCR with existing. */ - - mtspr(SPRN_LPCR, system_registers.lpcr | mfspr(SPRN_LPCR)); + lpcr = mfspr(SPRN_LPCR); + lpcr |= system_registers.lpcr; + lpcr &= ~system_registers.lpcr_clear; + mtspr(SPRN_LPCR, lpcr); if (hv_mode) { mtspr(SPRN_LPID, 0); mtspr(SPRN_HFSCR, system_registers.hfscr); @@ -325,8 +329,9 @@ static int __init feat_enable_mmu_hash_v3(struct dt_cpu_feature *f) { u64 lpcr; + system_registers.lpcr_clear |= (LPCR_ISL | LPCR_UPRT | LPCR_HR); lpcr = mfspr(SPRN_LPCR); - lpcr &= ~LPCR_ISL; + lpcr &= ~(LPCR_ISL | LPCR_UPRT | LPCR_HR); mtspr(SPRN_LPCR, lpcr); cur_cpu_spec->mmu_features |= MMU_FTRS_HASH_BASE; @@ -590,6 +595,8 @@ static struct dt_cpu_feature_match __initdata {"virtual-page-class-key-protection", feat_enable, 0}, {"transactional-memory", feat_enable_tm, CPU_FTR_TM}, {"transactional-memory-v3", feat_enable_tm, 0}, + {"tm-suspend-hypervisor-assist", feat_enable, CPU_FTR_P9_TM_HV_ASSIST}, + {"tm-suspend-xer-so-bug", feat_enable, CPU_FTR_P9_TM_XER_SO_BUG}, {"idle-nap", feat_enable_idle_nap, 0}, {"alignment-interrupt-dsisr", feat_enable_align_dsisr, 0}, {"idle-stop", feat_enable_idle_stop, 0}, @@ -707,11 +714,28 @@ static __init void cpufeatures_cpu_quirks(void) */ if ((version & 0xffffff00) == 0x004e0100) cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD1; + else if ((version & 0xffffefff) == 0x004e0200) + ; /* DD2.0 has no feature flag */ else if ((version & 0xffffefff) == 0x004e0201) cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1; + else if ((version & 0xffffefff) == 0x004e0202) { + cur_cpu_spec->cpu_features |= CPU_FTR_P9_TM_HV_ASSIST; + cur_cpu_spec->cpu_features |= CPU_FTR_P9_TM_XER_SO_BUG; + cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1; + } else /* DD2.1 and up have DD2_1 */ + cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1; - if ((version & 0xffff0000) == 0x004e0000) + if ((version & 0xffff0000) == 0x004e0000) { + cur_cpu_spec->cpu_features &= ~(CPU_FTR_DAWR); cur_cpu_spec->cpu_features |= CPU_FTR_P9_TLBIE_BUG; + } + + /* + * PKEY was not in the initial base or feature node + * specification, but it should become optional in the next + * cpu feature version sequence. + */ + cur_cpu_spec->cpu_features |= CPU_FTR_PKEY; } static void __init cpufeatures_setup_finished(void) diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 2b9df0040d6b..bc640e4c5ca5 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -394,9 +394,7 @@ static int eeh_phb_check_failure(struct eeh_pe *pe) /* Check PHB state */ ret = eeh_ops->get_state(phb_pe, NULL); if ((ret < 0) || - (ret == EEH_STATE_NOT_SUPPORT) || - (ret & (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) == - (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) { + (ret == EEH_STATE_NOT_SUPPORT) || eeh_state_active(ret)) { ret = 0; goto out; } @@ -433,7 +431,6 @@ out: int eeh_dev_check_failure(struct eeh_dev *edev) { int ret; - int active_flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE); unsigned long flags; struct device_node *dn; struct pci_dev *dev; @@ -525,8 +522,7 @@ int eeh_dev_check_failure(struct eeh_dev *edev) * state, PE is in good state. */ if ((ret < 0) || - (ret == EEH_STATE_NOT_SUPPORT) || - ((ret & active_flags) == active_flags)) { + (ret == EEH_STATE_NOT_SUPPORT) || eeh_state_active(ret)) { eeh_stats.false_positives++; pe->false_positives++; rc = 0; @@ -546,8 +542,7 @@ int eeh_dev_check_failure(struct eeh_dev *edev) /* Frozen parent PE ? */ ret = eeh_ops->get_state(parent_pe, NULL); - if (ret > 0 && - (ret & active_flags) != active_flags) + if (ret > 0 && !eeh_state_active(ret)) pe = parent_pe; /* Next parent level */ @@ -888,7 +883,6 @@ static void *eeh_set_dev_freset(void *data, void *flag) */ int eeh_pe_reset_full(struct eeh_pe *pe) { - int active_flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE); int reset_state = (EEH_PE_RESET | EEH_PE_CFG_BLOCKED); int type = EEH_RESET_HOT; unsigned int freset = 0; @@ -919,7 +913,7 @@ int eeh_pe_reset_full(struct eeh_pe *pe) /* Wait until the PE is in a functioning state */ state = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC); - if ((state & active_flags) == active_flags) + if (eeh_state_active(state)) break; if (state < 0) { @@ -1352,16 +1346,15 @@ static int eeh_pe_change_owner(struct eeh_pe *pe) struct eeh_dev *edev, *tmp; struct pci_dev *pdev; struct pci_device_id *id; - int flags, ret; + int ret; /* Check PE state */ - flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE); ret = eeh_ops->get_state(pe, NULL); if (ret < 0 || ret == EEH_STATE_NOT_SUPPORT) return 0; /* Unfrozen PE, nothing to do */ - if ((ret & flags) == flags) + if (eeh_state_active(ret)) return 0; /* Frozen PE, check if it needs PE level reset */ diff --git a/arch/powerpc/kernel/eeh_cache.c b/arch/powerpc/kernel/eeh_cache.c index d4cc26618809..201943d54a6e 100644 --- a/arch/powerpc/kernel/eeh_cache.c +++ b/arch/powerpc/kernel/eeh_cache.c @@ -84,8 +84,7 @@ static inline struct eeh_dev *__eeh_addr_cache_get_device(unsigned long addr) * @addr: mmio (PIO) phys address or i/o port number * * Given an mmio phys address, or a port number, find a pci device - * that implements this address. Be sure to pci_dev_put the device - * when finished. I/O port numbers are assumed to be offset + * that implements this address. I/O port numbers are assumed to be offset * from zero (that is, they do *not* have pci_io_addr added in). * It is safe to call this function within an interrupt. */ diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 0c0b66fc5bfb..b8a329f04814 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -207,18 +207,18 @@ static void *eeh_report_error(void *data, void *userdata) if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe)) return NULL; + + device_lock(&dev->dev); dev->error_state = pci_channel_io_frozen; driver = eeh_pcid_get(dev); - if (!driver) return NULL; + if (!driver) goto out_no_dev; eeh_disable_irq(dev); if (!driver->err_handler || - !driver->err_handler->error_detected) { - eeh_pcid_put(dev); - return NULL; - } + !driver->err_handler->error_detected) + goto out; rc = driver->err_handler->error_detected(dev, pci_channel_io_frozen); @@ -227,8 +227,12 @@ static void *eeh_report_error(void *data, void *userdata) if (*res == PCI_ERS_RESULT_NONE) *res = rc; edev->in_error = true; - eeh_pcid_put(dev); pci_uevent_ers(dev, PCI_ERS_RESULT_NONE); + +out: + eeh_pcid_put(dev); +out_no_dev: + device_unlock(&dev->dev); return NULL; } @@ -251,15 +255,14 @@ static void *eeh_report_mmio_enabled(void *data, void *userdata) if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe)) return NULL; + device_lock(&dev->dev); driver = eeh_pcid_get(dev); - if (!driver) return NULL; + if (!driver) goto out_no_dev; if (!driver->err_handler || !driver->err_handler->mmio_enabled || - (edev->mode & EEH_DEV_NO_HANDLER)) { - eeh_pcid_put(dev); - return NULL; - } + (edev->mode & EEH_DEV_NO_HANDLER)) + goto out; rc = driver->err_handler->mmio_enabled(dev); @@ -267,7 +270,10 @@ static void *eeh_report_mmio_enabled(void *data, void *userdata) if (rc == PCI_ERS_RESULT_NEED_RESET) *res = rc; if (*res == PCI_ERS_RESULT_NONE) *res = rc; +out: eeh_pcid_put(dev); +out_no_dev: + device_unlock(&dev->dev); return NULL; } @@ -290,20 +296,20 @@ static void *eeh_report_reset(void *data, void *userdata) if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe)) return NULL; + + device_lock(&dev->dev); dev->error_state = pci_channel_io_normal; driver = eeh_pcid_get(dev); - if (!driver) return NULL; + if (!driver) goto out_no_dev; eeh_enable_irq(dev); if (!driver->err_handler || !driver->err_handler->slot_reset || (edev->mode & EEH_DEV_NO_HANDLER) || - (!edev->in_error)) { - eeh_pcid_put(dev); - return NULL; - } + (!edev->in_error)) + goto out; rc = driver->err_handler->slot_reset(dev); if ((*res == PCI_ERS_RESULT_NONE) || @@ -311,7 +317,10 @@ static void *eeh_report_reset(void *data, void *userdata) if (*res == PCI_ERS_RESULT_DISCONNECT && rc == PCI_ERS_RESULT_NEED_RESET) *res = rc; +out: eeh_pcid_put(dev); +out_no_dev: + device_unlock(&dev->dev); return NULL; } @@ -362,10 +371,12 @@ static void *eeh_report_resume(void *data, void *userdata) if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe)) return NULL; + + device_lock(&dev->dev); dev->error_state = pci_channel_io_normal; driver = eeh_pcid_get(dev); - if (!driver) return NULL; + if (!driver) goto out_no_dev; was_in_error = edev->in_error; edev->in_error = false; @@ -375,18 +386,20 @@ static void *eeh_report_resume(void *data, void *userdata) !driver->err_handler->resume || (edev->mode & EEH_DEV_NO_HANDLER) || !was_in_error) { edev->mode &= ~EEH_DEV_NO_HANDLER; - eeh_pcid_put(dev); - return NULL; + goto out; } driver->err_handler->resume(dev); - eeh_pcid_put(dev); pci_uevent_ers(dev, PCI_ERS_RESULT_RECOVERED); +out: + eeh_pcid_put(dev); #ifdef CONFIG_PCI_IOV if (eeh_ops->notify_resume && eeh_dev_to_pdn(edev)) eeh_ops->notify_resume(eeh_dev_to_pdn(edev)); #endif +out_no_dev: + device_unlock(&dev->dev); return NULL; } @@ -406,23 +419,26 @@ static void *eeh_report_failure(void *data, void *userdata) if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe)) return NULL; + + device_lock(&dev->dev); dev->error_state = pci_channel_io_perm_failure; driver = eeh_pcid_get(dev); - if (!driver) return NULL; + if (!driver) goto out_no_dev; eeh_disable_irq(dev); if (!driver->err_handler || - !driver->err_handler->error_detected) { - eeh_pcid_put(dev); - return NULL; - } + !driver->err_handler->error_detected) + goto out; driver->err_handler->error_detected(dev, pci_channel_io_perm_failure); - eeh_pcid_put(dev); pci_uevent_ers(dev, PCI_ERS_RESULT_DISCONNECT); +out: + eeh_pcid_put(dev); +out_no_dev: + device_unlock(&dev->dev); return NULL; } @@ -619,17 +635,19 @@ int eeh_pe_reset_and_recover(struct eeh_pe *pe) /** * eeh_reset_device - Perform actual reset of a pci slot + * @driver_eeh_aware: Does the device's driver provide EEH support? * @pe: EEH PE * @bus: PCI bus corresponding to the isolcated slot + * @rmv_data: Optional, list to record removed devices * * This routine must be called to do reset on the indicated PE. * During the reset, udev might be invoked because those affected * PCI devices will be removed and then added. */ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, - struct eeh_rmv_data *rmv_data) + struct eeh_rmv_data *rmv_data, + bool driver_eeh_aware) { - struct pci_bus *frozen_bus = eeh_pe_bus_get(pe); time64_t tstamp; int cnt, rc; struct eeh_dev *edev; @@ -645,16 +663,12 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, * into pci_hp_add_devices(). */ eeh_pe_state_mark(pe, EEH_PE_KEEP); - if (bus) { - if (pe->type & EEH_PE_VF) { - eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL); - } else { - pci_lock_rescan_remove(); - pci_hp_remove_devices(bus); - pci_unlock_rescan_remove(); - } - } else if (frozen_bus) { + if (driver_eeh_aware || (pe->type & EEH_PE_VF)) { eeh_pe_dev_traverse(pe, eeh_rmv_device, rmv_data); + } else { + pci_lock_rescan_remove(); + pci_hp_remove_devices(bus); + pci_unlock_rescan_remove(); } /* @@ -689,8 +703,9 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, * the device up before the scripts have taken it down, * potentially weird things happen. */ - if (bus) { - pr_info("EEH: Sleep 5s ahead of complete hotplug\n"); + if (!driver_eeh_aware || rmv_data->removed) { + pr_info("EEH: Sleep 5s ahead of %s hotplug\n", + (driver_eeh_aware ? "partial" : "complete")); ssleep(5); /* @@ -703,19 +718,10 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, if (pe->type & EEH_PE_VF) { eeh_add_virt_device(edev, NULL); } else { - eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); + if (!driver_eeh_aware) + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); pci_hp_add_devices(bus); } - } else if (frozen_bus && rmv_data->removed) { - pr_info("EEH: Sleep 5s ahead of partial hotplug\n"); - ssleep(5); - - edev = list_first_entry(&pe->edevs, struct eeh_dev, list); - eeh_pe_traverse(pe, eeh_pe_detach_dev, NULL); - if (pe->type & EEH_PE_VF) - eeh_add_virt_device(edev, NULL); - else - pci_hp_add_devices(frozen_bus); } eeh_pe_state_clear(pe, EEH_PE_KEEP); @@ -733,28 +739,42 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, /** * eeh_handle_normal_event - Handle EEH events on a specific PE - * @pe: EEH PE + * @pe: EEH PE - which should not be used after we return, as it may + * have been invalidated. * * Attempts to recover the given PE. If recovery fails or the PE has failed * too many times, remove the PE. * - * Returns true if @pe should no longer be used, else false. + * While PHB detects address or data parity errors on particular PCI + * slot, the associated PE will be frozen. Besides, DMA's occurring + * to wild addresses (which usually happen due to bugs in device + * drivers or in PCI adapter firmware) can cause EEH error. #SERR, + * #PERR or other misc PCI-related errors also can trigger EEH errors. + * + * Recovery process consists of unplugging the device driver (which + * generated hotplug events to userspace), then issuing a PCI #RST to + * the device, then reconfiguring the PCI config space for all bridges + * & devices under this slot, and then finally restarting the device + * drivers (which cause a second set of hotplug events to go out to + * userspace). */ -static bool eeh_handle_normal_event(struct eeh_pe *pe) +void eeh_handle_normal_event(struct eeh_pe *pe) { - struct pci_bus *frozen_bus; + struct pci_bus *bus; struct eeh_dev *edev, *tmp; int rc = 0; enum pci_ers_result result = PCI_ERS_RESULT_NONE; struct eeh_rmv_data rmv_data = {LIST_HEAD_INIT(rmv_data.edev_list), 0}; - frozen_bus = eeh_pe_bus_get(pe); - if (!frozen_bus) { + bus = eeh_pe_bus_get(pe); + if (!bus) { pr_err("%s: Cannot find PCI bus for PHB#%x-PE#%x\n", __func__, pe->phb->global_number, pe->addr); - return false; + return; } + eeh_pe_state_mark(pe, EEH_PE_RECOVERING); + eeh_pe_update_time_stamp(pe); pe->freeze_count++; if (pe->freeze_count > eeh_max_freezes) { @@ -806,7 +826,7 @@ static bool eeh_handle_normal_event(struct eeh_pe *pe) */ if (result == PCI_ERS_RESULT_NONE) { pr_info("EEH: Reset with hotplug activity\n"); - rc = eeh_reset_device(pe, frozen_bus, NULL); + rc = eeh_reset_device(pe, bus, NULL, false); if (rc) { pr_warn("%s: Unable to reset, err=%d\n", __func__, rc); @@ -858,7 +878,7 @@ static bool eeh_handle_normal_event(struct eeh_pe *pe) /* If any device called out for a reset, then reset the slot */ if (result == PCI_ERS_RESULT_NEED_RESET) { pr_info("EEH: Reset without hotplug activity\n"); - rc = eeh_reset_device(pe, NULL, &rmv_data); + rc = eeh_reset_device(pe, bus, &rmv_data, true); if (rc) { pr_warn("%s: Cannot reset, err=%d\n", __func__, rc); @@ -891,7 +911,7 @@ static bool eeh_handle_normal_event(struct eeh_pe *pe) pr_info("EEH: Notify device driver to resume\n"); eeh_pe_dev_traverse(pe, eeh_report_resume, NULL); - return false; + goto final; hard_fail: /* @@ -916,23 +936,21 @@ hard_fail: * all removed devices correctly to avoid access * the their PCI config any more. */ - if (frozen_bus) { - if (pe->type & EEH_PE_VF) { - eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL); - eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); - } else { - eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); - eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); - - pci_lock_rescan_remove(); - pci_hp_remove_devices(frozen_bus); - pci_unlock_rescan_remove(); + if (pe->type & EEH_PE_VF) { + eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL); + eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); + } else { + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); + eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); - /* The passed PE should no longer be used */ - return true; - } + pci_lock_rescan_remove(); + pci_hp_remove_devices(bus); + pci_unlock_rescan_remove(); + /* The passed PE should no longer be used */ + return; } - return false; +final: + eeh_pe_state_clear(pe, EEH_PE_RECOVERING); } /** @@ -942,7 +960,7 @@ hard_fail: * specific PE. Iterates through possible failures and handles them as * necessary. */ -static void eeh_handle_special_event(void) +void eeh_handle_special_event(void) { struct eeh_pe *pe, *phb_pe; struct pci_bus *bus; @@ -1005,15 +1023,7 @@ static void eeh_handle_special_event(void) */ if (rc == EEH_NEXT_ERR_FROZEN_PE || rc == EEH_NEXT_ERR_FENCED_PHB) { - /* - * eeh_handle_normal_event() can make the PE stale if it - * determines that the PE cannot possibly be recovered. - * Don't modify the PE state if that's the case. - */ - if (eeh_handle_normal_event(pe)) - continue; - - eeh_pe_state_clear(pe, EEH_PE_RECOVERING); + eeh_handle_normal_event(pe); } else { pci_lock_rescan_remove(); list_for_each_entry(hose, &hose_list, list_node) { @@ -1049,28 +1059,3 @@ static void eeh_handle_special_event(void) break; } while (rc != EEH_NEXT_ERR_NONE); } - -/** - * eeh_handle_event - Reset a PCI device after hard lockup. - * @pe: EEH PE - * - * While PHB detects address or data parity errors on particular PCI - * slot, the associated PE will be frozen. Besides, DMA's occurring - * to wild addresses (which usually happen due to bugs in device - * drivers or in PCI adapter firmware) can cause EEH error. #SERR, - * #PERR or other misc PCI-related errors also can trigger EEH errors. - * - * Recovery process consists of unplugging the device driver (which - * generated hotplug events to userspace), then issuing a PCI #RST to - * the device, then reconfiguring the PCI config space for all bridges - * & devices under this slot, and then finally restarting the device - * drivers (which cause a second set of hotplug events to go out to - * userspace). - */ -void eeh_handle_event(struct eeh_pe *pe) -{ - if (pe) - eeh_handle_normal_event(pe); - else - eeh_handle_special_event(); -} diff --git a/arch/powerpc/kernel/eeh_event.c b/arch/powerpc/kernel/eeh_event.c index accbf8b5fd46..61c9356bf9c9 100644 --- a/arch/powerpc/kernel/eeh_event.c +++ b/arch/powerpc/kernel/eeh_event.c @@ -73,7 +73,6 @@ static int eeh_event_handler(void * dummy) /* We might have event without binding PE */ pe = event->pe; if (pe) { - eeh_pe_state_mark(pe, EEH_PE_RECOVERING); if (pe->type & EEH_PE_PHB) pr_info("EEH: Detected error on PHB#%x\n", pe->phb->global_number); @@ -81,10 +80,9 @@ static int eeh_event_handler(void * dummy) pr_info("EEH: Detected PCI bus error on " "PHB#%x-PE#%x\n", pe->phb->global_number, pe->addr); - eeh_handle_event(pe); - eeh_pe_state_clear(pe, EEH_PE_RECOVERING); + eeh_handle_normal_event(pe); } else { - eeh_handle_event(NULL); + eeh_handle_special_event(); } kfree(event); diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 2cb5109a7ea3..51695608c68b 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -545,7 +545,7 @@ _GLOBAL(_switch) /* Cancel all explict user streams as they will have no use after context * switch and will stop the HW from creating streams itself */ - DCBT_STOP_ALL_STREAM_IDS(r6) + DCBT_BOOK3S_STOP_ALL_STREAM_IDS(r6) #endif addi r6,r4,-THREAD /* Convert THREAD to 'current' */ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 1ecfd8ffb098..ae6a849db60b 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -139,6 +139,21 @@ EXC_COMMON_BEGIN(system_reset_idle_common) b pnv_powersave_wakeup #endif +/* + * Set IRQS_ALL_DISABLED unconditionally so arch_irqs_disabled does + * the right thing. We do not want to reconcile because that goes + * through irq tracing which we don't want in NMI. + * + * Save PACAIRQHAPPENED because some code will do a hard disable + * (e.g., xmon). So we want to restore this back to where it was + * when we return. DAR is unused in the stack, so save it there. + */ +#define ADD_RECONCILE_NMI \ + li r10,IRQS_ALL_DISABLED; \ + stb r10,PACAIRQSOFTMASK(r13); \ + lbz r10,PACAIRQHAPPENED(r13); \ + std r10,_DAR(r1) + EXC_COMMON_BEGIN(system_reset_common) /* * Increment paca->in_nmi then enable MSR_RI. SLB or MCE will be able @@ -157,16 +172,56 @@ EXC_COMMON_BEGIN(system_reset_common) subi r1,r1,INT_FRAME_SIZE EXCEPTION_COMMON_NORET_STACK(PACA_EXNMI, 0x100, system_reset, system_reset_exception, - ADD_NVGPRS;ADD_RECONCILE) + ADD_NVGPRS;ADD_RECONCILE_NMI) + + /* This (and MCE) can be simplified with mtmsrd L=1 */ + /* Clear MSR_RI before setting SRR0 and SRR1. */ + li r0,MSR_RI + mfmsr r9 + andc r9,r9,r0 + mtmsrd r9,1 /* - * The stack is no longer in use, decrement in_nmi. + * MSR_RI is clear, now we can decrement paca->in_nmi. */ lhz r10,PACA_IN_NMI(r13) subi r10,r10,1 sth r10,PACA_IN_NMI(r13) - b ret_from_except + /* + * Restore soft mask settings. + */ + ld r10,_DAR(r1) + stb r10,PACAIRQHAPPENED(r13) + ld r10,SOFTE(r1) + stb r10,PACAIRQSOFTMASK(r13) + + /* + * Keep below code in synch with MACHINE_CHECK_HANDLER_WINDUP. + * Should share common bits... + */ + + /* Move original SRR0 and SRR1 into the respective regs */ + ld r9,_MSR(r1) + mtspr SPRN_SRR1,r9 + ld r3,_NIP(r1) + mtspr SPRN_SRR0,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) + RFI_TO_USER_OR_KERNEL #ifdef CONFIG_PPC_PSERIES /* @@ -621,7 +676,10 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX) lwz r9,PACA_EXSLB+EX_CCR(r13) /* get saved CR */ mtlr r10 - beq- 8f /* if bad address, make full stack frame */ + /* + * Large address, check whether we have to allocate new contexts. + */ + beq- 8f bne- cr5,2f /* if unrecoverable exception, oops */ @@ -629,14 +687,11 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX) bne cr4,1f /* returning to kernel */ -.machine push -.machine "power4" mtcrf 0x80,r9 mtcrf 0x08,r9 /* MSR[PR] indication is in cr4 */ mtcrf 0x04,r9 /* MSR[RI] indication is in cr5 */ mtcrf 0x02,r9 /* I/D indication is in cr6 */ mtcrf 0x01,r9 /* slb_allocate uses cr0 and cr7 */ -.machine pop RESTORE_CTR(r9, PACA_EXSLB) RESTORE_PPR_PACA(PACA_EXSLB, r9) @@ -649,14 +704,11 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX) RFI_TO_USER b . /* prevent speculative execution */ 1: -.machine push -.machine "power4" mtcrf 0x80,r9 mtcrf 0x08,r9 /* MSR[PR] indication is in cr4 */ mtcrf 0x04,r9 /* MSR[RI] indication is in cr5 */ mtcrf 0x02,r9 /* I/D indication is in cr6 */ mtcrf 0x01,r9 /* slb_allocate uses cr0 and cr7 */ -.machine pop RESTORE_CTR(r9, PACA_EXSLB) RESTORE_PPR_PACA(PACA_EXSLB, r9) @@ -685,7 +737,7 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX) mr r3,r12 mfspr r11,SPRN_SRR0 mfspr r12,SPRN_SRR1 - LOAD_HANDLER(r10,bad_addr_slb) + LOAD_HANDLER(r10, large_addr_slb) mtspr SPRN_SRR0,r10 ld r10,PACAKMSR(r13) mtspr SPRN_SRR1,r10 @@ -700,7 +752,7 @@ EXC_COMMON_BEGIN(unrecov_slb) bl unrecoverable_exception b 1b -EXC_COMMON_BEGIN(bad_addr_slb) +EXC_COMMON_BEGIN(large_addr_slb) EXCEPTION_PROLOG_COMMON(0x380, PACA_EXSLB) RECONCILE_IRQ_STATE(r10, r11) ld r3, PACA_EXSLB+EX_DAR(r13) @@ -710,7 +762,7 @@ EXC_COMMON_BEGIN(bad_addr_slb) std r10, _TRAP(r1) 2: bl save_nvgprs addi r3, r1, STACK_FRAME_OVERHEAD - bl slb_miss_bad_addr + bl slb_miss_large_addr b ret_from_except EXC_REAL_BEGIN(hardware_interrupt, 0x500, 0x100) @@ -1273,7 +1325,7 @@ EXC_REAL_BEGIN(denorm_exception_hv, 0x1500, 0x100) bne+ denorm_assist #endif - KVMTEST_PR(0x1500) + KVMTEST_HV(0x1500) EXCEPTION_PROLOG_PSERIES_1(denorm_common, EXC_HV) EXC_REAL_END(denorm_exception_hv, 0x1500, 0x100) @@ -1285,7 +1337,7 @@ EXC_VIRT_END(denorm_exception, 0x5500, 0x100) EXC_VIRT_NONE(0x5500, 0x100) #endif -TRAMP_KVM_SKIP(PACA_EXGEN, 0x1500) +TRAMP_KVM_HV(PACA_EXGEN, 0x1500) #ifdef CONFIG_PPC_DENORMALISATION TRAMP_REAL_BEGIN(denorm_assist) @@ -1466,7 +1518,7 @@ TRAMP_REAL_BEGIN(rfi_flush_fallback) ld r11,PACA_L1D_FLUSH_SIZE(r13) srdi r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */ mtctr r11 - DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */ + DCBT_BOOK3S_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */ /* order ld/st prior to dcbt stop all streams with flushing */ sync @@ -1506,7 +1558,7 @@ TRAMP_REAL_BEGIN(hrfi_flush_fallback) ld r11,PACA_L1D_FLUSH_SIZE(r13) srdi r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */ mtctr r11 - DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */ + DCBT_BOOK3S_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */ /* order ld/st prior to dcbt stop all streams with flushing */ sync diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index a61151a6ea5e..6eca15f25c73 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -392,19 +392,20 @@ generic_secondary_common_init: * physical cpu id in r24, we need to search the pacas to find * which logical id maps to our physical one. */ - LOAD_REG_ADDR(r13, paca) /* Load paca pointer */ - ld r13,0(r13) /* Get base vaddr of paca array */ #ifndef CONFIG_SMP - addi r13,r13,PACA_SIZE /* know r13 if used accidentally */ b kexec_wait /* wait for next kernel if !SMP */ #else + LOAD_REG_ADDR(r8, paca_ptrs) /* Load paca_ptrs pointe */ + ld r8,0(r8) /* Get base vaddr of array */ LOAD_REG_ADDR(r7, nr_cpu_ids) /* Load nr_cpu_ids address */ lwz r7,0(r7) /* also the max paca allocated */ li r5,0 /* logical cpu id */ -1: lhz r6,PACAHWCPUID(r13) /* Load HW procid from paca */ +1: + sldi r9,r5,3 /* get paca_ptrs[] index from cpu id */ + ldx r13,r9,r8 /* r13 = paca_ptrs[cpu id] */ + lhz r6,PACAHWCPUID(r13) /* Load HW procid from paca */ cmpw r6,r24 /* Compare to our id */ beq 2f - addi r13,r13,PACA_SIZE /* Loop to next PACA on miss */ addi r5,r5,1 cmpw r5,r7 /* Check if more pacas exist */ blt 1b @@ -756,10 +757,10 @@ _GLOBAL(pmac_secondary_start) mtmsrd r3 /* RI on */ /* Set up a paca value for this processor. */ - LOAD_REG_ADDR(r4,paca) /* Load paca pointer */ - ld r4,0(r4) /* Get base vaddr of paca array */ - mulli r13,r24,PACA_SIZE /* Calculate vaddr of right paca */ - add r13,r13,r4 /* for this processor. */ + LOAD_REG_ADDR(r4,paca_ptrs) /* Load paca pointer */ + ld r4,0(r4) /* Get base vaddr of paca_ptrs array */ + sldi r5,r24,3 /* get paca_ptrs[] index from cpu id */ + ldx r13,r5,r4 /* r13 = paca_ptrs[cpu id] */ SET_PACA(r13) /* Save vaddr of paca in an SPRG*/ /* Mark interrupts soft and hard disabled (they might be enabled diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index 53b9c1dfd7d9..4c1012b80d3b 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -33,6 +33,7 @@ #include <asm/hw_breakpoint.h> #include <asm/processor.h> #include <asm/sstep.h> +#include <asm/debug.h> #include <linux/uaccess.h> /* @@ -171,6 +172,8 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) * HW_BREAKPOINT_ALIGN by rounding off to the lower address, the * 'symbolsize' should satisfy the check below. */ + if (!ppc_breakpoint_available()) + return -ENODEV; length_max = 8; /* DABR */ if (cpu_has_feature(CPU_FTR_DAWR)) { length_max = 512 ; /* 64 doublewords */ diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S index 01e1c1997893..79d005445c6c 100644 --- a/arch/powerpc/kernel/idle_book3s.S +++ b/arch/powerpc/kernel/idle_book3s.S @@ -325,12 +325,6 @@ enter_winkle: * r3 - PSSCR value corresponding to the requested stop state. */ power_enter_stop: -#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE - /* Tell KVM we're entering idle */ - li r4,KVM_HWTHREAD_IN_IDLE - /* DO THIS IN REAL MODE! See comment above. */ - stb r4,HSTATE_HWTHREAD_STATE(r13) -#endif /* * Check if we are executing the lite variant with ESL=EC=0 */ @@ -339,6 +333,7 @@ power_enter_stop: bne .Lhandle_esl_ec_set PPC_STOP li r3,0 /* Since we didn't lose state, return 0 */ + std r3, PACA_REQ_PSSCR(r13) /* * pnv_wakeup_noloss() expects r12 to contain the SRR1 value so @@ -427,13 +422,49 @@ ALT_FTR_SECTION_END_NESTED_IFSET(CPU_FTR_ARCH_207S, 66); \ /* * Entered with MSR[EE]=0 and no soft-masked interrupts pending. * r3 contains desired PSSCR register value. + * + * Offline (CPU unplug) case also must notify KVM that the CPU is + * idle. */ +_GLOBAL(power9_offline_stop) +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + /* + * Tell KVM we're entering idle. + * This does not have to be done in real mode because the P9 MMU + * is independent per-thread. Some steppings share radix/hash mode + * between threads, but in that case KVM has a barrier sync in real + * mode before and after switching between radix and hash. + */ + li r4,KVM_HWTHREAD_IN_IDLE + stb r4,HSTATE_HWTHREAD_STATE(r13) +#endif + /* fall through */ + _GLOBAL(power9_idle_stop) std r3, PACA_REQ_PSSCR(r13) +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE +BEGIN_FTR_SECTION + sync + lwz r5, PACA_DONT_STOP(r13) + cmpwi r5, 0 + bne 1f +END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_XER_SO_BUG) +#endif mtspr SPRN_PSSCR,r3 LOAD_REG_ADDR(r4,power_enter_stop) b pnv_powersave_common /* No return */ +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE +1: + /* + * We get here when TM / thread reconfiguration bug workaround + * code wants to get the CPU into SMT4 mode, and therefore + * we are being asked not to stop. + */ + li r3, 0 + std r3, PACA_REQ_PSSCR(r13) + blr /* return 0 for wakeup cause / SRR1 value */ +#endif /* * On waking up from stop 0,1,2 with ESL=1 on POWER9 DD1, @@ -520,6 +551,9 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300) mr r3,r12 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + lbz r0,HSTATE_HWTHREAD_STATE(r13) + cmpwi r0,KVM_HWTHREAD_IN_KERNEL + beq 1f li r0,KVM_HWTHREAD_IN_KERNEL stb r0,HSTATE_HWTHREAD_STATE(r13) /* Order setting hwthread_state vs. testing hwthread_req */ @@ -584,6 +618,8 @@ FTR_SECTION_ELSE_NESTED(71) mfspr r5, SPRN_PSSCR rldicl r5,r5,4,60 ALT_FTR_SECTION_END_NESTED_IFSET(CPU_FTR_POWER9_DD1, 71) + li r0, 0 /* clear requested_psscr to say we're awake */ + std r0, PACA_REQ_PSSCR(r13) cmpd cr4,r5,r4 bge cr4,pnv_wakeup_tb_loss /* returns to caller */ @@ -834,6 +870,8 @@ BEGIN_FTR_SECTION mtspr SPRN_PTCR,r4 ld r4,_RPR(r1) mtspr SPRN_RPR,r4 + ld r4,_AMOR(r1) + mtspr SPRN_AMOR,r4 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) ld r4,_TSCR(r1) diff --git a/arch/powerpc/kernel/iomap.c b/arch/powerpc/kernel/iomap.c index aab456ed2a00..5ac84efc6ede 100644 --- a/arch/powerpc/kernel/iomap.c +++ b/arch/powerpc/kernel/iomap.c @@ -45,12 +45,32 @@ u64 ioread64(void __iomem *addr) { return readq(addr); } +u64 ioread64_lo_hi(void __iomem *addr) +{ + return readq(addr); +} +u64 ioread64_hi_lo(void __iomem *addr) +{ + return readq(addr); +} u64 ioread64be(void __iomem *addr) { return readq_be(addr); } +u64 ioread64be_lo_hi(void __iomem *addr) +{ + return readq_be(addr); +} +u64 ioread64be_hi_lo(void __iomem *addr) +{ + return readq_be(addr); +} EXPORT_SYMBOL(ioread64); +EXPORT_SYMBOL(ioread64_lo_hi); +EXPORT_SYMBOL(ioread64_hi_lo); EXPORT_SYMBOL(ioread64be); +EXPORT_SYMBOL(ioread64be_lo_hi); +EXPORT_SYMBOL(ioread64be_hi_lo); #endif /* __powerpc64__ */ void iowrite8(u8 val, void __iomem *addr) @@ -83,12 +103,32 @@ void iowrite64(u64 val, void __iomem *addr) { writeq(val, addr); } +void iowrite64_lo_hi(u64 val, void __iomem *addr) +{ + writeq(val, addr); +} +void iowrite64_hi_lo(u64 val, void __iomem *addr) +{ + writeq(val, addr); +} void iowrite64be(u64 val, void __iomem *addr) { writeq_be(val, addr); } +void iowrite64be_lo_hi(u64 val, void __iomem *addr) +{ + writeq_be(val, addr); +} +void iowrite64be_hi_lo(u64 val, void __iomem *addr) +{ + writeq_be(val, addr); +} EXPORT_SYMBOL(iowrite64); +EXPORT_SYMBOL(iowrite64_lo_hi); +EXPORT_SYMBOL(iowrite64_hi_lo); EXPORT_SYMBOL(iowrite64be); +EXPORT_SYMBOL(iowrite64be_lo_hi); +EXPORT_SYMBOL(iowrite64be_hi_lo); #endif /* __powerpc64__ */ /* diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index ca5d5a081e75..e4c5bf33970b 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -455,29 +455,33 @@ static int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) } kretprobe_assert(ri, orig_ret_address, trampoline_address); - regs->nip = orig_ret_address; + /* - * Make LR point to the orig_ret_address. - * When the 'nop' inside the kretprobe_trampoline - * is optimized, we can do a 'blr' after executing the - * detour buffer code. + * We get here through one of two paths: + * 1. by taking a trap -> kprobe_handler() -> here + * 2. by optprobe branch -> optimized_callback() -> opt_pre_handler() -> here + * + * When going back through (1), we need regs->nip to be setup properly + * as it is used to determine the return address from the trap. + * For (2), since nip is not honoured with optprobes, we instead setup + * the link register properly so that the subsequent 'blr' in + * kretprobe_trampoline jumps back to the right instruction. + * + * For nip, we should set the address to the previous instruction since + * we end up emulating it in kprobe_handler(), which increments the nip + * again. */ + regs->nip = orig_ret_address - 4; regs->link = orig_ret_address; - reset_current_kprobe(); kretprobe_hash_unlock(current, &flags); - preempt_enable_no_resched(); hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); kfree(ri); } - /* - * By returning a non-zero value, we are telling - * kprobe_handler() that we don't want the post_handler - * to run (and have re-enabled preemption) - */ - return 1; + + return 0; } NOKPROBE_SYMBOL(trampoline_probe_handler); diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c index 49d34d7271e7..1044bf15d5ed 100644 --- a/arch/powerpc/kernel/machine_kexec_64.c +++ b/arch/powerpc/kernel/machine_kexec_64.c @@ -168,24 +168,25 @@ static void kexec_prepare_cpus_wait(int wait_state) * are correctly onlined. If somehow we start a CPU on boot with RTAS * start-cpu, but somehow that CPU doesn't write callin_cpu_map[] in * time, the boot CPU will timeout. If it does eventually execute - * stuff, the secondary will start up (paca[].cpu_start was written) and - * get into a peculiar state. If the platform supports - * smp_ops->take_timebase(), the secondary CPU will probably be spinning - * in there. If not (i.e. pseries), the secondary will continue on and - * try to online itself/idle/etc. If it survives that, we need to find - * these possible-but-not-online-but-should-be CPUs and chaperone them - * into kexec_smp_wait(). + * stuff, the secondary will start up (paca_ptrs[]->cpu_start was + * written) and get into a peculiar state. + * If the platform supports smp_ops->take_timebase(), the secondary CPU + * will probably be spinning in there. If not (i.e. pseries), the + * secondary will continue on and try to online itself/idle/etc. If it + * survives that, we need to find these + * possible-but-not-online-but-should-be CPUs and chaperone them into + * kexec_smp_wait(). */ for_each_online_cpu(i) { if (i == my_cpu) continue; - while (paca[i].kexec_state < wait_state) { + while (paca_ptrs[i]->kexec_state < wait_state) { barrier(); if (i != notified) { printk(KERN_INFO "kexec: waiting for cpu %d " "(physical %d) to enter %i state\n", - i, paca[i].hw_cpu_id, wait_state); + i, paca_ptrs[i]->hw_cpu_id, wait_state); notified = i; } } @@ -322,18 +323,24 @@ void default_machine_kexec(struct kimage *image) kexec_stack.thread_info.cpu = current_thread_info()->cpu; /* We need a static PACA, too; copy this CPU's PACA over and switch to - * it. Also poison per_cpu_offset to catch anyone using non-static - * data. + * it. Also poison per_cpu_offset and NULL lppaca to catch anyone using + * non-static data. */ memcpy(&kexec_paca, get_paca(), sizeof(struct paca_struct)); kexec_paca.data_offset = 0xedeaddeadeeeeeeeUL; - paca = (struct paca_struct *)RELOC_HIDE(&kexec_paca, 0) - - kexec_paca.paca_index; +#ifdef CONFIG_PPC_PSERIES + kexec_paca.lppaca_ptr = NULL; +#endif + paca_ptrs[kexec_paca.paca_index] = &kexec_paca; + setup_paca(&kexec_paca); - /* XXX: If anyone does 'dynamic lppacas' this will also need to be - * switched to a static version! + /* + * The lppaca should be unregistered at this point so the HV won't + * touch it. In the case of a crash, none of the lppacas are + * unregistered so there is not much we can do about it here. */ + /* * 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 diff --git a/arch/powerpc/kernel/machine_kexec_file_64.c b/arch/powerpc/kernel/machine_kexec_file_64.c index e4395f937d63..45e0b7d5f200 100644 --- a/arch/powerpc/kernel/machine_kexec_file_64.c +++ b/arch/powerpc/kernel/machine_kexec_file_64.c @@ -43,7 +43,7 @@ int arch_kexec_kernel_image_probe(struct kimage *image, void *buf, /* We don't support crash kernels yet. */ if (image->type == KEXEC_TYPE_CRASH) - return -ENOTSUPP; + return -EOPNOTSUPP; for (i = 0; i < ARRAY_SIZE(kexec_file_loaders); i++) { fops = kexec_file_loaders[i]; diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index 3280953a82cf..fa267e94090a 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -144,44 +144,6 @@ _GLOBAL_TOC(flush_dcache_range) blr EXPORT_SYMBOL(flush_dcache_range) -/* - * Like above, but works on non-mapped physical addresses. - * Use only for non-LPAR setups ! It also assumes real mode - * is cacheable. Used for flushing out the DART before using - * it as uncacheable memory - * - * flush_dcache_phys_range(unsigned long start, unsigned long stop) - * - * flush all bytes from start to stop-1 inclusive - */ -_GLOBAL(flush_dcache_phys_range) - ld r10,PPC64_CACHES@toc(r2) - lwz r7,DCACHEL1BLOCKSIZE(r10) /* Get dcache block size */ - addi r5,r7,-1 - andc r6,r3,r5 /* round low to line bdy */ - subf r8,r6,r4 /* compute length */ - add r8,r8,r5 /* ensure we get enough */ - lwz r9,DCACHEL1LOGBLOCKSIZE(r10) /* Get log-2 of dcache block size */ - srw. r8,r8,r9 /* compute line count */ - beqlr /* nothing to do? */ - mfmsr r5 /* Disable MMU Data Relocation */ - ori r0,r5,MSR_DR - xori r0,r0,MSR_DR - sync - mtmsr r0 - sync - isync - mtctr r8 -0: dcbst 0,r6 - add r6,r6,r7 - bdnz 0b - sync - isync - mtmsr r5 /* Re-enable MMU Data Relocation */ - sync - isync - blr - _GLOBAL(flush_inval_dcache_range) ld r10,PPC64_CACHES@toc(r2) lwz r7,DCACHEL1BLOCKSIZE(r10) /* Get dcache block size */ diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index 496d6393bd41..ba681dac7b46 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -207,8 +207,7 @@ int nvram_write_os_partition(struct nvram_os_partition *part, tmp_index = part->index; - rc = ppc_md.nvram_write((char *)&info, sizeof(struct err_log_info), - &tmp_index); + rc = ppc_md.nvram_write((char *)&info, sizeof(info), &tmp_index); if (rc <= 0) { pr_err("%s: Failed nvram_write (%d)\n", __func__, rc); return rc; @@ -244,9 +243,7 @@ int nvram_read_partition(struct nvram_os_partition *part, char *buff, tmp_index = part->index; if (part->os_partition) { - rc = ppc_md.nvram_read((char *)&info, - sizeof(struct err_log_info), - &tmp_index); + rc = ppc_md.nvram_read((char *)&info, sizeof(info), &tmp_index); if (rc <= 0) { pr_err("%s: Failed nvram_read (%d)\n", __func__, rc); return rc; @@ -1173,7 +1170,7 @@ int __init nvram_scan_partitions(void) "detected: 0-length partition\n"); goto out; } - tmp_part = kmalloc(sizeof(struct nvram_partition), GFP_KERNEL); + tmp_part = kmalloc(sizeof(*tmp_part), GFP_KERNEL); err = -ENOMEM; if (!tmp_part) { printk(KERN_ERR "nvram_scan_partitions: kmalloc failed\n"); diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 95ffedf14885..0ee3e6d50f28 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -20,116 +20,105 @@ #include "setup.h" -#ifdef CONFIG_PPC_BOOK3S +#ifndef CONFIG_SMP +#define boot_cpuid 0 +#endif + +static void *__init alloc_paca_data(unsigned long size, unsigned long align, + unsigned long limit, int cpu) +{ + unsigned long pa; + int nid; + + /* + * boot_cpuid paca is allocated very early before cpu_to_node is up. + * Set bottom-up mode, because the boot CPU should be on node-0, + * which will put its paca in the right place. + */ + if (cpu == boot_cpuid) { + nid = -1; + memblock_set_bottom_up(true); + } else { + nid = early_cpu_to_node(cpu); + } + + pa = memblock_alloc_base_nid(size, align, limit, nid, MEMBLOCK_NONE); + if (!pa) { + pa = memblock_alloc_base(size, align, limit); + if (!pa) + panic("cannot allocate paca data"); + } + + if (cpu == boot_cpuid) + memblock_set_bottom_up(false); + + return __va(pa); +} + +#ifdef CONFIG_PPC_PSERIES /* - * The structure which the hypervisor knows about - this structure - * should not cross a page boundary. The vpa_init/register_vpa call - * is now known to fail if the lppaca structure crosses a page - * boundary. The lppaca is also used on POWER5 pSeries boxes. - * The lppaca is 640 bytes long, and cannot readily - * change since the hypervisor knows its layout, so a 1kB alignment - * will suffice to ensure that it doesn't cross a page boundary. + * See asm/lppaca.h for more detail. + * + * lppaca structures must must be 1kB in size, L1 cache line aligned, + * and not cross 4kB boundary. A 1kB size and 1kB alignment will satisfy + * these requirements. */ -struct lppaca lppaca[] = { - [0 ... (NR_LPPACAS-1)] = { +static inline void init_lppaca(struct lppaca *lppaca) +{ + BUILD_BUG_ON(sizeof(struct lppaca) != 640); + + *lppaca = (struct lppaca) { .desc = cpu_to_be32(0xd397d781), /* "LpPa" */ - .size = cpu_to_be16(sizeof(struct lppaca)), + .size = cpu_to_be16(0x400), .fpregs_in_use = 1, .slb_count = cpu_to_be16(64), .vmxregs_in_use = 0, - .page_ins = 0, - }, + .page_ins = 0, }; }; -static struct lppaca *extra_lppacas; -static long __initdata lppaca_size; - -static void __init allocate_lppacas(int nr_cpus, unsigned long limit) -{ - if (nr_cpus <= NR_LPPACAS) - return; - - lppaca_size = PAGE_ALIGN(sizeof(struct lppaca) * - (nr_cpus - NR_LPPACAS)); - extra_lppacas = __va(memblock_alloc_base(lppaca_size, - PAGE_SIZE, limit)); -} - -static struct lppaca * __init new_lppaca(int cpu) +static struct lppaca * __init new_lppaca(int cpu, unsigned long limit) { struct lppaca *lp; + size_t size = 0x400; - if (cpu < NR_LPPACAS) - return &lppaca[cpu]; + BUILD_BUG_ON(size < sizeof(struct lppaca)); + + if (early_cpu_has_feature(CPU_FTR_HVMODE)) + return NULL; - lp = extra_lppacas + (cpu - NR_LPPACAS); - *lp = lppaca[0]; + lp = alloc_paca_data(size, 0x400, limit, cpu); + init_lppaca(lp); return lp; } - -static void __init free_lppacas(void) -{ - long new_size = 0, nr; - - if (!lppaca_size) - return; - nr = num_possible_cpus() - NR_LPPACAS; - if (nr > 0) - new_size = PAGE_ALIGN(nr * sizeof(struct lppaca)); - if (new_size >= lppaca_size) - return; - - memblock_free(__pa(extra_lppacas) + new_size, lppaca_size - new_size); - lppaca_size = new_size; -} - -#else - -static inline void allocate_lppacas(int nr_cpus, unsigned long limit) { } -static inline void free_lppacas(void) { } - #endif /* CONFIG_PPC_BOOK3S */ #ifdef CONFIG_PPC_BOOK3S_64 /* - * 3 persistent SLBs are registered here. The buffer will be zero + * 3 persistent SLBs are allocated here. The buffer will be zero * initially, hence will all be invaild until we actually write them. * * If you make the number of persistent SLB entries dynamic, please also * update PR KVM to flush and restore them accordingly. */ -static struct slb_shadow * __initdata slb_shadow; - -static void __init allocate_slb_shadows(int nr_cpus, int limit) -{ - int size = PAGE_ALIGN(sizeof(struct slb_shadow) * nr_cpus); - - if (early_radix_enabled()) - return; - - slb_shadow = __va(memblock_alloc_base(size, PAGE_SIZE, limit)); - memset(slb_shadow, 0, size); -} - -static struct slb_shadow * __init init_slb_shadow(int cpu) +static struct slb_shadow * __init new_slb_shadow(int cpu, unsigned long limit) { struct slb_shadow *s; - if (early_radix_enabled()) - return NULL; - - s = &slb_shadow[cpu]; + if (cpu != boot_cpuid) { + /* + * Boot CPU comes here before early_radix_enabled + * is parsed (e.g., for disable_radix). So allocate + * always and this will be fixed up in free_unused_pacas. + */ + if (early_radix_enabled()) + return NULL; + } - /* - * When we come through here to initialise boot_paca, the slb_shadow - * buffers are not allocated yet. That's OK, we'll get one later in - * boot, but make sure we don't corrupt memory at 0. - */ - if (!slb_shadow) - return NULL; + s = alloc_paca_data(sizeof(*s), L1_CACHE_BYTES, limit, cpu); + memset(s, 0, sizeof(*s)); s->persistent = cpu_to_be32(SLB_NUM_BOLTED); s->buffer_length = cpu_to_be32(sizeof(*s)); @@ -137,10 +126,6 @@ static struct slb_shadow * __init init_slb_shadow(int cpu) return s; } -#else /* !CONFIG_PPC_BOOK3S_64 */ - -static void __init allocate_slb_shadows(int nr_cpus, int limit) { } - #endif /* CONFIG_PPC_BOOK3S_64 */ /* The Paca is an array with one entry per processor. Each contains an @@ -152,14 +137,15 @@ static void __init allocate_slb_shadows(int nr_cpus, int limit) { } * processors. The processor VPD array needs one entry per physical * processor (not thread). */ -struct paca_struct *paca; -EXPORT_SYMBOL(paca); +struct paca_struct **paca_ptrs __read_mostly; +EXPORT_SYMBOL(paca_ptrs); void __init initialise_paca(struct paca_struct *new_paca, int cpu) { -#ifdef CONFIG_PPC_BOOK3S - new_paca->lppaca_ptr = new_lppaca(cpu); -#else +#ifdef CONFIG_PPC_PSERIES + new_paca->lppaca_ptr = NULL; +#endif +#ifdef CONFIG_PPC_BOOK3E new_paca->kernel_pgd = swapper_pg_dir; #endif new_paca->lock_token = 0x8000; @@ -173,7 +159,7 @@ void __init initialise_paca(struct paca_struct *new_paca, int cpu) new_paca->__current = &init_task; new_paca->data_offset = 0xfeeeeeeeeeeeeeeeULL; #ifdef CONFIG_PPC_BOOK3S_64 - new_paca->slb_shadow_ptr = init_slb_shadow(cpu); + new_paca->slb_shadow_ptr = NULL; #endif #ifdef CONFIG_PPC_BOOK3E @@ -203,12 +189,25 @@ void setup_paca(struct paca_struct *new_paca) } -static int __initdata paca_size; +static int __initdata paca_nr_cpu_ids; +static int __initdata paca_ptrs_size; +static int __initdata paca_struct_size; + +void __init allocate_paca_ptrs(void) +{ + paca_nr_cpu_ids = nr_cpu_ids; + + paca_ptrs_size = sizeof(struct paca_struct *) * nr_cpu_ids; + paca_ptrs = __va(memblock_alloc(paca_ptrs_size, 0)); + memset(paca_ptrs, 0x88, paca_ptrs_size); +} -void __init allocate_pacas(void) +void __init allocate_paca(int cpu) { u64 limit; - int cpu; + struct paca_struct *paca; + + BUG_ON(cpu >= paca_nr_cpu_ids); #ifdef CONFIG_PPC_BOOK3S_64 /* @@ -220,40 +219,44 @@ void __init allocate_pacas(void) limit = ppc64_rma_size; #endif - paca_size = PAGE_ALIGN(sizeof(struct paca_struct) * nr_cpu_ids); - - paca = __va(memblock_alloc_base(paca_size, PAGE_SIZE, limit)); - memset(paca, 0, paca_size); - - printk(KERN_DEBUG "Allocated %u bytes for %u pacas at %p\n", - paca_size, nr_cpu_ids, paca); - - allocate_lppacas(nr_cpu_ids, limit); - - allocate_slb_shadows(nr_cpu_ids, limit); + paca = alloc_paca_data(sizeof(struct paca_struct), L1_CACHE_BYTES, + limit, cpu); + paca_ptrs[cpu] = paca; + memset(paca, 0, sizeof(struct paca_struct)); - /* Can't use for_each_*_cpu, as they aren't functional yet */ - for (cpu = 0; cpu < nr_cpu_ids; cpu++) - initialise_paca(&paca[cpu], cpu); + initialise_paca(paca, cpu); +#ifdef CONFIG_PPC_PSERIES + paca->lppaca_ptr = new_lppaca(cpu, limit); +#endif +#ifdef CONFIG_PPC_BOOK3S_64 + paca->slb_shadow_ptr = new_slb_shadow(cpu, limit); +#endif + paca_struct_size += sizeof(struct paca_struct); } void __init free_unused_pacas(void) { - int new_size; - - new_size = PAGE_ALIGN(sizeof(struct paca_struct) * nr_cpu_ids); + int new_ptrs_size; - if (new_size >= paca_size) - return; + new_ptrs_size = sizeof(struct paca_struct *) * nr_cpu_ids; + if (new_ptrs_size < paca_ptrs_size) + memblock_free(__pa(paca_ptrs) + new_ptrs_size, + paca_ptrs_size - new_ptrs_size); - memblock_free(__pa(paca) + new_size, paca_size - new_size); + paca_nr_cpu_ids = nr_cpu_ids; + paca_ptrs_size = new_ptrs_size; - printk(KERN_DEBUG "Freed %u bytes for unused pacas\n", - paca_size - new_size); - - paca_size = new_size; +#ifdef CONFIG_PPC_BOOK3S_64 + if (early_radix_enabled()) { + /* Ugly fixup, see new_slb_shadow() */ + memblock_free(__pa(paca_ptrs[boot_cpuid]->slb_shadow_ptr), + sizeof(struct slb_shadow)); + paca_ptrs[boot_cpuid]->slb_shadow_ptr = NULL; + } +#endif - free_lppacas(); + printk(KERN_DEBUG "Allocated %u bytes for %u pacas\n", + paca_ptrs_size + paca_struct_size, nr_cpu_ids); } void copy_mm_to_paca(struct mm_struct *mm) @@ -265,7 +268,8 @@ void copy_mm_to_paca(struct mm_struct *mm) #ifdef CONFIG_PPC_MM_SLICES VM_BUG_ON(!mm->context.slb_addr_limit); get_paca()->mm_ctx_slb_addr_limit = mm->context.slb_addr_limit; - get_paca()->mm_ctx_low_slices_psize = context->low_slices_psize; + memcpy(&get_paca()->mm_ctx_low_slices_psize, + &context->low_slices_psize, sizeof(context->low_slices_psize)); memcpy(&get_paca()->mm_ctx_high_slices_psize, &context->high_slices_psize, TASK_SLICE_ARRAY_SZ(mm)); #else /* CONFIG_PPC_MM_SLICES */ diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 1738c4127b32..1237f13fed51 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -173,7 +173,7 @@ void __msr_check_and_clear(unsigned long bits) EXPORT_SYMBOL(__msr_check_and_clear); #ifdef CONFIG_PPC_FPU -void __giveup_fpu(struct task_struct *tsk) +static void __giveup_fpu(struct task_struct *tsk) { unsigned long msr; @@ -556,7 +556,7 @@ void restore_math(struct pt_regs *regs) regs->msr = msr; } -void save_all(struct task_struct *tsk) +static void save_all(struct task_struct *tsk) { unsigned long usermsr; @@ -718,7 +718,8 @@ static void set_debug_reg_defaults(struct thread_struct *thread) { thread->hw_brk.address = 0; thread->hw_brk.type = 0; - set_breakpoint(&thread->hw_brk); + if (ppc_breakpoint_available()) + set_breakpoint(&thread->hw_brk); } #endif /* !CONFIG_HAVE_HW_BREAKPOINT */ #endif /* CONFIG_PPC_ADV_DEBUG_REGS */ @@ -815,9 +816,14 @@ void __set_breakpoint(struct arch_hw_breakpoint *brk) memcpy(this_cpu_ptr(¤t_brk), brk, sizeof(*brk)); if (cpu_has_feature(CPU_FTR_DAWR)) + // Power8 or later set_dawr(brk); - else + else if (!cpu_has_feature(CPU_FTR_ARCH_207S)) + // Power7 or earlier set_dabr(brk); + else + // Shouldn't happen due to higher level checks + WARN_ON_ONCE(1); } void set_breakpoint(struct arch_hw_breakpoint *brk) @@ -827,6 +833,18 @@ void set_breakpoint(struct arch_hw_breakpoint *brk) preempt_enable(); } +/* Check if we have DAWR or DABR hardware */ +bool ppc_breakpoint_available(void) +{ + if (cpu_has_feature(CPU_FTR_DAWR)) + return true; /* POWER8 DAWR */ + if (cpu_has_feature(CPU_FTR_ARCH_207S)) + return false; /* POWER9 with DAWR disabled */ + /* DABR: Everything but POWER8 and POWER9 */ + return true; +} +EXPORT_SYMBOL_GPL(ppc_breakpoint_available); + #ifdef CONFIG_PPC64 DEFINE_PER_CPU(struct cpu_usage, cpu_usage_array); #endif diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 4dffef947b8a..9dbed488aba1 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -291,11 +291,11 @@ static inline void identical_pvr_fixup(unsigned long node) static void __init check_cpu_feature_properties(unsigned long node) { - unsigned long i; + int i; struct feature_property *fp = feature_properties; const __be32 *prop; - for (i = 0; i < ARRAY_SIZE(feature_properties); ++i, ++fp) { + for (i = 0; i < (int)ARRAY_SIZE(feature_properties); ++i, ++fp) { prop = of_get_flat_dt_prop(node, fp->name, NULL); if (prop && be32_to_cpup(prop) >= fp->min_value) { cur_cpu_spec->cpu_features |= fp->cpu_feature; @@ -365,7 +365,6 @@ static int __init early_init_dt_scan_cpus(unsigned long node, DBG("boot cpu: logical %d physical %d\n", found, be32_to_cpu(intserv[found_thread])); boot_cpuid = found; - set_hard_smp_processor_id(found, be32_to_cpu(intserv[found_thread])); /* * PAPR defines "logical" PVR values for cpus that @@ -403,7 +402,9 @@ static int __init early_init_dt_scan_cpus(unsigned long node, cur_cpu_spec->cpu_features &= ~CPU_FTR_SMT; else if (!dt_cpu_ftrs_in_use()) cur_cpu_spec->cpu_features |= CPU_FTR_SMT; + allocate_paca(boot_cpuid); #endif + set_hard_smp_processor_id(found, be32_to_cpu(intserv[found_thread])); return 0; } @@ -744,7 +745,7 @@ void __init early_init_devtree(void *params) * FIXME .. and the initrd too? */ move_device_tree(); - allocate_pacas(); + allocate_paca_ptrs(); DBG("Scanning CPUs ...\n"); @@ -874,5 +875,15 @@ EXPORT_SYMBOL(cpu_to_chip_id); bool arch_match_cpu_phys_id(int cpu, u64 phys_id) { +#ifdef CONFIG_SMP + /* + * Early firmware scanning must use this rather than + * get_hard_smp_processor_id because we don't have pacas allocated + * until memory topology is discovered. + */ + if (cpu_to_phys_id != NULL) + return (int)phys_id == cpu_to_phys_id[cpu]; +#endif + return (int)phys_id == get_hard_smp_processor_id(cpu); } diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index acf4b2e0530c..f9d6befb55a6 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -171,7 +171,7 @@ static unsigned long __initdata prom_tce_alloc_start; static unsigned long __initdata prom_tce_alloc_end; #endif -static bool __initdata prom_radix_disable; +static bool prom_radix_disable __initdata = !IS_ENABLED(CONFIG_PPC_RADIX_MMU_DEFAULT); struct platform_support { bool hash_mmu; @@ -641,9 +641,19 @@ static void __init early_cmdline_parse(void) opt = strstr(prom_cmd_line, "disable_radix"); if (opt) { - prom_debug("Radix disabled from cmdline\n"); - prom_radix_disable = true; + opt += 13; + if (*opt && *opt == '=') { + bool val; + + if (kstrtobool(++opt, &val)) + prom_radix_disable = false; + else + prom_radix_disable = val; + } else + prom_radix_disable = true; } + if (prom_radix_disable) + prom_debug("Radix disabled from cmdline\n"); } #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) @@ -1110,7 +1120,8 @@ static void __init prom_check_platform_support(void) } } - if (supported.radix_mmu && supported.radix_gtse) { + if (supported.radix_mmu && supported.radix_gtse && + IS_ENABLED(CONFIG_PPC_RADIX_MMU)) { /* Radix preferred - but we require GTSE for now */ prom_debug("Asking for radix with GTSE\n"); ibm_architecture_vec.vec5.mmu = OV5_FEAT(OV5_MMU_RADIX); @@ -1809,16 +1820,8 @@ static void __init prom_initialize_tce_table(void) * size to 4 MB. This is enough to map 2GB of PCI DMA space. * By doing this, we avoid the pitfalls of trying to DMA to * MMIO space and the DMA alias hole. - * - * On POWER4, firmware sets the TCE region by assuming - * each TCE table is 8MB. Using this memory for anything - * else will impact performance, so we always allocate 8MB. - * Anton */ - if (pvr_version_is(PVR_POWER4) || pvr_version_is(PVR_POWER4p)) - minsize = 8UL << 20; - else - minsize = 4UL << 20; + minsize = 4UL << 20; /* Align to the greater of the align or size */ align = max(minalign, minsize); diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh index 12640f7e726b..acb6b9226352 100644 --- a/arch/powerpc/kernel/prom_init_check.sh +++ b/arch/powerpc/kernel/prom_init_check.sh @@ -19,7 +19,7 @@ WHITELIST="add_reloc_offset __bss_start __bss_stop copy_and_flush _end enter_prom memcpy memset reloc_offset __secondary_hold __secondary_hold_acknowledge __secondary_hold_spinloop __start -strcmp strcpy strlcpy strlen strncmp strstr logo_linux_clut224 +strcmp strcpy strlcpy strlen strncmp strstr kstrtobool logo_linux_clut224 reloc_got2 kernstart_addr memstart_addr linux_banner _stext __prom_init_toc_start __prom_init_toc_end btext_setup_display TOC." diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index ca72d7391d40..d23cf632edf0 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -41,6 +41,7 @@ #include <asm/switch_to.h> #include <asm/tm.h> #include <asm/asm-prototypes.h> +#include <asm/debug.h> #define CREATE_TRACE_POINTS #include <trace/events/syscalls.h> @@ -2378,6 +2379,7 @@ static int ptrace_set_debugreg(struct task_struct *task, unsigned long addr, struct perf_event_attr attr; #endif /* CONFIG_HAVE_HW_BREAKPOINT */ #ifndef CONFIG_PPC_ADV_DEBUG_REGS + bool set_bp = true; struct arch_hw_breakpoint hw_brk; #endif @@ -2411,9 +2413,10 @@ static int ptrace_set_debugreg(struct task_struct *task, unsigned long addr, hw_brk.address = data & (~HW_BRK_TYPE_DABR); hw_brk.type = (data & HW_BRK_TYPE_DABR) | HW_BRK_TYPE_PRIV_ALL; hw_brk.len = 8; + set_bp = (data) && (hw_brk.type & HW_BRK_TYPE_RDWR); #ifdef CONFIG_HAVE_HW_BREAKPOINT bp = thread->ptrace_bps[0]; - if ((!data) || !(hw_brk.type & HW_BRK_TYPE_RDWR)) { + if (!set_bp) { if (bp) { unregister_hw_breakpoint(bp); thread->ptrace_bps[0] = NULL; @@ -2450,6 +2453,9 @@ static int ptrace_set_debugreg(struct task_struct *task, unsigned long addr, return PTR_ERR(bp); } +#else /* !CONFIG_HAVE_HW_BREAKPOINT */ + if (set_bp && (!ppc_breakpoint_available())) + return -ENODEV; #endif /* CONFIG_HAVE_HW_BREAKPOINT */ task->thread.hw_brk = hw_brk; #else /* CONFIG_PPC_ADV_DEBUG_REGS */ @@ -2904,6 +2910,9 @@ static long ppc_set_hwdebug(struct task_struct *child, if (child->thread.hw_brk.address) return -ENOSPC; + if (!ppc_breakpoint_available()) + return -ENODEV; + child->thread.hw_brk = brk; return 1; @@ -3052,7 +3061,10 @@ long arch_ptrace(struct task_struct *child, long request, #endif #else /* !CONFIG_PPC_ADV_DEBUG_REGS */ dbginfo.num_instruction_bps = 0; - dbginfo.num_data_bps = 1; + if (ppc_breakpoint_available()) + dbginfo.num_data_bps = 1; + else + dbginfo.num_data_bps = 0; dbginfo.num_condition_regs = 0; #ifdef CONFIG_PPC64 dbginfo.data_bp_alignment = 8; diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c new file mode 100644 index 000000000000..bab5a27ea805 --- /dev/null +++ b/arch/powerpc/kernel/security.c @@ -0,0 +1,88 @@ +// SPDX-License-Identifier: GPL-2.0+ +// +// Security related flags and so on. +// +// Copyright 2018, Michael Ellerman, IBM Corporation. + +#include <linux/kernel.h> +#include <linux/device.h> +#include <linux/seq_buf.h> + +#include <asm/security_features.h> + + +unsigned long powerpc_security_features __read_mostly = SEC_FTR_DEFAULT; + +ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) +{ + bool thread_priv; + + thread_priv = security_ftr_enabled(SEC_FTR_L1D_THREAD_PRIV); + + if (rfi_flush || thread_priv) { + struct seq_buf s; + seq_buf_init(&s, buf, PAGE_SIZE - 1); + + seq_buf_printf(&s, "Mitigation: "); + + if (rfi_flush) + seq_buf_printf(&s, "RFI Flush"); + + if (rfi_flush && thread_priv) + seq_buf_printf(&s, ", "); + + if (thread_priv) + seq_buf_printf(&s, "L1D private per thread"); + + seq_buf_printf(&s, "\n"); + + return s.len; + } + + if (!security_ftr_enabled(SEC_FTR_L1D_FLUSH_HV) && + !security_ftr_enabled(SEC_FTR_L1D_FLUSH_PR)) + return sprintf(buf, "Not affected\n"); + + return sprintf(buf, "Vulnerable\n"); +} + +ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf) +{ + if (!security_ftr_enabled(SEC_FTR_BNDS_CHK_SPEC_BAR)) + return sprintf(buf, "Not affected\n"); + + return sprintf(buf, "Vulnerable\n"); +} + +ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf) +{ + bool bcs, ccd, ori; + struct seq_buf s; + + seq_buf_init(&s, buf, PAGE_SIZE - 1); + + bcs = security_ftr_enabled(SEC_FTR_BCCTRL_SERIALISED); + ccd = security_ftr_enabled(SEC_FTR_COUNT_CACHE_DISABLED); + ori = security_ftr_enabled(SEC_FTR_SPEC_BAR_ORI31); + + if (bcs || ccd) { + seq_buf_printf(&s, "Mitigation: "); + + if (bcs) + seq_buf_printf(&s, "Indirect branch serialisation (kernel only)"); + + if (bcs && ccd) + seq_buf_printf(&s, ", "); + + if (ccd) + seq_buf_printf(&s, "Indirect branch cache disabled"); + } else + seq_buf_printf(&s, "Vulnerable"); + + if (ori) + seq_buf_printf(&s, ", ori31 speculation barrier enabled"); + + seq_buf_printf(&s, "\n"); + + return s.len; +} diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index d73ec518ef80..0af5c11b9e78 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -437,6 +437,8 @@ static void __init cpu_init_thread_core_maps(int tpc) } +u32 *cpu_to_phys_id = NULL; + /** * setup_cpu_maps - initialize the following cpu maps: * cpu_possible_mask @@ -463,6 +465,10 @@ void __init smp_setup_cpu_maps(void) DBG("smp_setup_cpu_maps()\n"); + cpu_to_phys_id = __va(memblock_alloc(nr_cpu_ids * sizeof(u32), + __alignof__(u32))); + memset(cpu_to_phys_id, 0, nr_cpu_ids * sizeof(u32)); + for_each_node_by_type(dn, "cpu") { const __be32 *intserv; __be32 cpu_be; @@ -480,6 +486,7 @@ void __init smp_setup_cpu_maps(void) intserv = of_get_property(dn, "reg", &len); if (!intserv) { cpu_be = cpu_to_be32(cpu); + /* XXX: what is this? uninitialized?? */ intserv = &cpu_be; /* assume logical == phys */ len = 4; } @@ -499,8 +506,8 @@ void __init smp_setup_cpu_maps(void) "enable-method", "spin-table"); set_cpu_present(cpu, avail); - set_hard_smp_processor_id(cpu, be32_to_cpu(intserv[j])); set_cpu_possible(cpu, true); + cpu_to_phys_id[cpu] = be32_to_cpu(intserv[j]); cpu++; } @@ -835,6 +842,23 @@ static __init void print_system_info(void) pr_info("-----------------------------------------------------\n"); } +#ifdef CONFIG_SMP +static void smp_setup_pacas(void) +{ + int cpu; + + for_each_possible_cpu(cpu) { + if (cpu == smp_processor_id()) + continue; + allocate_paca(cpu); + set_hard_smp_processor_id(cpu, cpu_to_phys_id[cpu]); + } + + memblock_free(__pa(cpu_to_phys_id), nr_cpu_ids * sizeof(u32)); + cpu_to_phys_id = NULL; +} +#endif + /* * Called into from start_kernel this initializes memblock, which is used * to manage page allocation until mem_init is called. @@ -888,8 +912,8 @@ void __init setup_arch(char **cmdline_p) /* Check the SMT related command line arguments (ppc64). */ check_smt_enabled(); - /* On BookE, setup per-core TLB data structures. */ - setup_tlb_core_data(); + /* Parse memory topology */ + mem_topology_setup(); /* * Release secondary cpus out of their spinloops at 0x60 now that @@ -899,6 +923,11 @@ void __init setup_arch(char **cmdline_p) * so smp_release_cpus() does nothing for them. */ #ifdef CONFIG_SMP + smp_setup_pacas(); + + /* On BookE, setup per-core TLB data structures. */ + setup_tlb_core_data(); + smp_release_cpus(); #endif @@ -919,6 +948,8 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_PPC64 if (!radix_enabled()) init_mm.context.slb_addr_limit = DEFAULT_MAP_WINDOW_USER64; +#elif defined(CONFIG_PPC_8xx) + init_mm.context.slb_addr_limit = DEFAULT_MAP_WINDOW; #else #error "context.addr_limit not initialized." #endif diff --git a/arch/powerpc/kernel/setup.h b/arch/powerpc/kernel/setup.h index 3fc11e30308f..d144df54ad40 100644 --- a/arch/powerpc/kernel/setup.h +++ b/arch/powerpc/kernel/setup.h @@ -46,13 +46,10 @@ static inline void emergency_stack_init(void) { }; #endif #ifdef CONFIG_PPC64 -void record_spr_defaults(void); -#else -static inline void record_spr_defaults(void) { }; -#endif - -#ifdef CONFIG_PPC64 u64 ppc64_bolted_size(void); + +/* Default SPR values from firmware/kexec */ +extern unsigned long spr_default_dscr; #endif /* diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 51ebc01fff52..74457485574b 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -39,6 +39,7 @@ #include <asm/udbg.h> #include <asm/code-patching.h> #include <asm/cpu_has_feature.h> +#include <asm/asm-prototypes.h> #define DBG(fmt...) @@ -121,7 +122,7 @@ notrace void __init machine_init(u64 dt_ptr) } /* Checks "l2cr=xxxx" command-line option */ -int __init ppc_setup_l2cr(char *str) +static int __init ppc_setup_l2cr(char *str) { if (cpu_has_feature(CPU_FTR_L2CR)) { unsigned long val = simple_strtoul(str, NULL, 0); @@ -134,7 +135,7 @@ int __init ppc_setup_l2cr(char *str) __setup("l2cr=", ppc_setup_l2cr); /* Checks "l3cr=xxxx" command-line option */ -int __init ppc_setup_l3cr(char *str) +static int __init ppc_setup_l3cr(char *str) { if (cpu_has_feature(CPU_FTR_L3CR)) { unsigned long val = simple_strtoul(str, NULL, 0); @@ -180,7 +181,7 @@ EXPORT_SYMBOL(nvram_sync); #endif /* CONFIG_NVRAM */ -int __init ppc_init(void) +static int __init ppc_init(void) { /* clear the progress line */ if (ppc_md.progress) @@ -192,7 +193,6 @@ int __init ppc_init(void) } return 0; } - arch_initcall(ppc_init); void __init irqstack_early_init(void) diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index c388cc3357fa..66f2b6299c40 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -110,7 +110,7 @@ void __init setup_tlb_core_data(void) if (cpu_first_thread_sibling(boot_cpuid) == first) first = boot_cpuid; - paca[cpu].tcd_ptr = &paca[first].tcd; + paca_ptrs[cpu]->tcd_ptr = &paca_ptrs[first]->tcd; /* * If we have threads, we need either tlbsrx. @@ -254,6 +254,14 @@ static void cpu_ready_for_interrupts(void) get_paca()->kernel_msr = MSR_KERNEL; } +unsigned long spr_default_dscr = 0; + +void __init record_spr_defaults(void) +{ + if (early_cpu_has_feature(CPU_FTR_DSCR)) + spr_default_dscr = mfspr(SPRN_DSCR); +} + /* * Early initialization entry point. This is called by head.S * with MMU translation disabled. We rely on the "feature" of @@ -304,7 +312,11 @@ void __init early_setup(unsigned long dt_ptr) early_init_devtree(__va(dt_ptr)); /* Now we know the logical id of our boot cpu, setup the paca. */ - setup_paca(&paca[boot_cpuid]); + if (boot_cpuid != 0) { + /* Poison paca_ptrs[0] again if it's not the boot cpu */ + memset(&paca_ptrs[0], 0x88, sizeof(paca_ptrs[0])); + } + setup_paca(paca_ptrs[boot_cpuid]); fixup_boot_paca(); /* @@ -599,6 +611,21 @@ __init u64 ppc64_bolted_size(void) #endif } +static void *__init alloc_stack(unsigned long limit, int cpu) +{ + unsigned long pa; + + pa = memblock_alloc_base_nid(THREAD_SIZE, THREAD_SIZE, limit, + early_cpu_to_node(cpu), MEMBLOCK_NONE); + if (!pa) { + pa = memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit); + if (!pa) + panic("cannot allocate stacks"); + } + + return __va(pa); +} + void __init irqstack_early_init(void) { u64 limit = ppc64_bolted_size(); @@ -610,12 +637,8 @@ void __init irqstack_early_init(void) * accessed in realmode. */ for_each_possible_cpu(i) { - softirq_ctx[i] = (struct thread_info *) - __va(memblock_alloc_base(THREAD_SIZE, - THREAD_SIZE, limit)); - hardirq_ctx[i] = (struct thread_info *) - __va(memblock_alloc_base(THREAD_SIZE, - THREAD_SIZE, limit)); + softirq_ctx[i] = alloc_stack(limit, i); + hardirq_ctx[i] = alloc_stack(limit, i); } } @@ -623,20 +646,21 @@ void __init irqstack_early_init(void) void __init exc_lvl_early_init(void) { unsigned int i; - unsigned long sp; for_each_possible_cpu(i) { - sp = memblock_alloc(THREAD_SIZE, THREAD_SIZE); - critirq_ctx[i] = (struct thread_info *)__va(sp); - paca[i].crit_kstack = __va(sp + THREAD_SIZE); + void *sp; + + sp = alloc_stack(ULONG_MAX, i); + critirq_ctx[i] = sp; + paca_ptrs[i]->crit_kstack = sp + THREAD_SIZE; - sp = memblock_alloc(THREAD_SIZE, THREAD_SIZE); - dbgirq_ctx[i] = (struct thread_info *)__va(sp); - paca[i].dbg_kstack = __va(sp + THREAD_SIZE); + sp = alloc_stack(ULONG_MAX, i); + dbgirq_ctx[i] = sp; + paca_ptrs[i]->dbg_kstack = sp + THREAD_SIZE; - sp = memblock_alloc(THREAD_SIZE, THREAD_SIZE); - mcheckirq_ctx[i] = (struct thread_info *)__va(sp); - paca[i].mc_kstack = __va(sp + THREAD_SIZE); + sp = alloc_stack(ULONG_MAX, i); + mcheckirq_ctx[i] = sp; + paca_ptrs[i]->mc_kstack = sp + THREAD_SIZE; } if (cpu_has_feature(CPU_FTR_DEBUG_LVL_EXC)) @@ -690,23 +714,24 @@ void __init emergency_stack_init(void) for_each_possible_cpu(i) { struct thread_info *ti; - ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit)); + + ti = alloc_stack(limit, i); memset(ti, 0, THREAD_SIZE); emerg_stack_init_thread_info(ti, i); - paca[i].emergency_sp = (void *)ti + THREAD_SIZE; + paca_ptrs[i]->emergency_sp = (void *)ti + THREAD_SIZE; #ifdef CONFIG_PPC_BOOK3S_64 /* emergency stack for NMI exception handling. */ - ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit)); + ti = alloc_stack(limit, i); memset(ti, 0, THREAD_SIZE); emerg_stack_init_thread_info(ti, i); - paca[i].nmi_emergency_sp = (void *)ti + THREAD_SIZE; + paca_ptrs[i]->nmi_emergency_sp = (void *)ti + THREAD_SIZE; /* emergency stack for machine check exception handling. */ - ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit)); + ti = alloc_stack(limit, i); memset(ti, 0, THREAD_SIZE); emerg_stack_init_thread_info(ti, i); - paca[i].mc_emergency_sp = (void *)ti + THREAD_SIZE; + paca_ptrs[i]->mc_emergency_sp = (void *)ti + THREAD_SIZE; #endif } } @@ -762,7 +787,7 @@ void __init setup_per_cpu_areas(void) delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start; for_each_possible_cpu(cpu) { __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu]; - paca[cpu].data_offset = __per_cpu_offset[cpu]; + paca_ptrs[cpu]->data_offset = __per_cpu_offset[cpu]; } } #endif @@ -846,9 +871,6 @@ static void do_nothing(void *unused) void rfi_flush_enable(bool enable) { - if (rfi_flush == enable) - return; - if (enable) { do_rfi_flush_fixups(enabled_flush_types); on_each_cpu(do_nothing, NULL, 1); @@ -863,6 +885,10 @@ static void init_fallback_flush(void) u64 l1d_size, limit; int cpu; + /* Only allocate the fallback flush area once (at boot time). */ + if (l1d_flush_fallback_area) + return; + l1d_size = ppc64_caches.l1d.size; limit = min(ppc64_bolted_size(), ppc64_rma_size); @@ -875,23 +901,24 @@ static void init_fallback_flush(void) memset(l1d_flush_fallback_area, 0, l1d_size * 2); for_each_possible_cpu(cpu) { - paca[cpu].rfi_flush_fallback_area = l1d_flush_fallback_area; - paca[cpu].l1d_flush_size = l1d_size; + struct paca_struct *paca = paca_ptrs[cpu]; + paca->rfi_flush_fallback_area = l1d_flush_fallback_area; + paca->l1d_flush_size = l1d_size; } } -void __init setup_rfi_flush(enum l1d_flush_type types, bool enable) +void setup_rfi_flush(enum l1d_flush_type types, bool enable) { if (types & L1D_FLUSH_FALLBACK) { - pr_info("rfi-flush: Using fallback displacement flush\n"); + pr_info("rfi-flush: fallback displacement flush available\n"); init_fallback_flush(); } if (types & L1D_FLUSH_ORI) - pr_info("rfi-flush: Using ori type flush\n"); + pr_info("rfi-flush: ori type flush available\n"); if (types & L1D_FLUSH_MTTRIG) - pr_info("rfi-flush: Using mttrig type flush\n"); + pr_info("rfi-flush: mttrig type flush available\n"); enabled_flush_types = types; @@ -902,13 +929,19 @@ void __init setup_rfi_flush(enum l1d_flush_type types, bool enable) #ifdef CONFIG_DEBUG_FS static int rfi_flush_set(void *data, u64 val) { + bool enable; + if (val == 1) - rfi_flush_enable(true); + enable = true; else if (val == 0) - rfi_flush_enable(false); + enable = false; else return -EINVAL; + /* Only do anything if we're changing state */ + if (enable != rfi_flush) + rfi_flush_enable(enable); + return 0; } @@ -927,12 +960,4 @@ static __init int rfi_flush_debugfs_init(void) } device_initcall(rfi_flush_debugfs_init); #endif - -ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) -{ - if (rfi_flush) - return sprintf(buf, "Mitigation: RFI Flush\n"); - - return sprintf(buf, "Vulnerable\n"); -} #endif /* CONFIG_PPC_BOOK3S_64 */ diff --git a/arch/powerpc/kernel/signal.h b/arch/powerpc/kernel/signal.h index 7c59d88b9d86..a6467f843acf 100644 --- a/arch/powerpc/kernel/signal.h +++ b/arch/powerpc/kernel/signal.h @@ -49,6 +49,11 @@ extern int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, #else /* CONFIG_PPC64 */ +extern long sys_rt_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, + struct pt_regs *regs); +extern long sys_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, + struct pt_regs *regs); + static inline int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, struct task_struct *tsk) { diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index a46de0035214..492f03451877 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -1045,7 +1045,7 @@ long sys_swapcontext(struct ucontext __user *old_ctx, struct ucontext __user *new_ctx, int ctx_size, int r6, int r7, int r8, struct pt_regs *regs) { - unsigned char tmp; + unsigned char tmp __maybe_unused; int ctx_has_vsx_region = 0; #ifdef CONFIG_PPC64 @@ -1231,7 +1231,7 @@ int sys_debug_setcontext(struct ucontext __user *ctx, { struct sig_dbg_op op; int i; - unsigned char tmp; + unsigned char tmp __maybe_unused; unsigned long new_msr = regs->msr; #ifdef CONFIG_PPC_ADV_DEBUG_REGS unsigned long new_dbcr0 = current->thread.debug.dbcr0; diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index bbe7634b3a43..e16ec7b3b427 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -123,8 +123,8 @@ int smp_generic_kick_cpu(int nr) * cpu_start field to become non-zero After we set cpu_start, * the processor will continue on to secondary_start */ - if (!paca[nr].cpu_start) { - paca[nr].cpu_start = 1; + if (!paca_ptrs[nr]->cpu_start) { + paca_ptrs[nr]->cpu_start = 1; smp_mb(); return 0; } @@ -565,19 +565,28 @@ void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *)) } #endif +#ifdef CONFIG_NMI_IPI +static void stop_this_cpu(struct pt_regs *regs) +#else static void stop_this_cpu(void *dummy) +#endif { /* Remove this CPU */ set_cpu_online(smp_processor_id(), false); - local_irq_disable(); + hard_irq_disable(); + spin_begin(); while (1) - ; + spin_cpu_relax(); } void smp_send_stop(void) { +#ifdef CONFIG_NMI_IPI + smp_send_nmi_ipi(NMI_IPI_ALL_OTHERS, stop_this_cpu, 1000000); +#else smp_call_function(stop_this_cpu, NULL, 0); +#endif } struct thread_info *current_set[NR_CPUS]; @@ -657,7 +666,7 @@ void smp_prepare_boot_cpu(void) { BUG_ON(smp_processor_id() != boot_cpuid); #ifdef CONFIG_PPC64 - paca[boot_cpuid].__current = current; + paca_ptrs[boot_cpuid]->__current = current; #endif set_numa_node(numa_cpu_lookup_table[boot_cpuid]); current_set[boot_cpuid] = task_thread_info(current); @@ -748,8 +757,8 @@ static void cpu_idle_thread_init(unsigned int cpu, struct task_struct *idle) struct thread_info *ti = task_thread_info(idle); #ifdef CONFIG_PPC64 - paca[cpu].__current = idle; - paca[cpu].kstack = (unsigned long)ti + THREAD_SIZE - STACK_FRAME_OVERHEAD; + paca_ptrs[cpu]->__current = idle; + paca_ptrs[cpu]->kstack = (unsigned long)ti + THREAD_SIZE - STACK_FRAME_OVERHEAD; #endif ti->cpu = cpu; secondary_ti = current_set[cpu] = ti; diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 04d0bbd7a1dd..755dc98a57ae 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -20,6 +20,7 @@ #include <asm/firmware.h> #include "cacheinfo.h" +#include "setup.h" #ifdef CONFIG_PPC64 #include <asm/paca.h> @@ -588,21 +589,18 @@ static DEVICE_ATTR(dscr_default, 0600, static void sysfs_create_dscr_default(void) { - int err = 0; - if (cpu_has_feature(CPU_FTR_DSCR)) - err = device_create_file(cpu_subsys.dev_root, &dev_attr_dscr_default); -} + if (cpu_has_feature(CPU_FTR_DSCR)) { + int err = 0; + int cpu; -void __init record_spr_defaults(void) -{ - int cpu; + dscr_default = spr_default_dscr; + for_each_possible_cpu(cpu) + paca_ptrs[cpu]->dscr_default = dscr_default; - if (cpu_has_feature(CPU_FTR_DSCR)) { - dscr_default = mfspr(SPRN_DSCR); - for (cpu = 0; cpu < nr_cpu_ids; cpu++) - paca[cpu].dscr_default = dscr_default; + err = device_create_file(cpu_subsys.dev_root, &dev_attr_dscr_default); } } + #endif /* CONFIG_PPC64 */ #ifdef HAS_PPC_PMC_PA6T diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index a32823dcd9a4..360e71d455cc 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -266,6 +266,9 @@ void accumulate_stolen_time(void) static inline u64 calculate_stolen_time(u64 stop_tb) { + if (!firmware_has_feature(FW_FEATURE_SPLPAR)) + return 0; + if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx)) return scan_dispatch_log(stop_tb); @@ -1234,7 +1237,7 @@ void calibrate_delay(void) static int rtc_generic_get_time(struct device *dev, struct rtc_time *tm) { ppc_md.get_rtc_time(tm); - return rtc_valid_tm(tm); + return 0; } static int rtc_generic_set_time(struct device *dev, struct rtc_time *tm) diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 1e48d157196a..a2ef0c0e6c31 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -208,6 +208,12 @@ static void oops_end(unsigned long flags, struct pt_regs *regs, } raw_local_irq_restore(flags); + /* + * system_reset_excption handles debugger, crash dump, panic, for 0x100 + */ + if (TRAP(regs) == 0x100) + return; + crash_fadump(regs, "die oops"); if (kexec_should_crash(current)) @@ -272,8 +278,13 @@ void die(const char *str, struct pt_regs *regs, long err) { unsigned long flags; - if (debugger(regs)) - return; + /* + * system_reset_excption handles debugger, crash dump, panic, for 0x100 + */ + if (TRAP(regs) != 0x100) { + if (debugger(regs)) + return; + } flags = oops_begin(regs); if (__die(str, regs, err)) @@ -460,7 +471,7 @@ static inline int check_io_access(struct pt_regs *regs) /* single-step stuff */ #define single_stepping(regs) (current->thread.debug.dbcr0 & DBCR0_IC) #define clear_single_step(regs) (current->thread.debug.dbcr0 &= ~DBCR0_IC) - +#define clear_br_trace(regs) do {} while(0) #else /* On non-4xx, the reason for the machine check or program exception is in the MSR. */ @@ -473,6 +484,7 @@ static inline int check_io_access(struct pt_regs *regs) #define single_stepping(regs) ((regs)->msr & MSR_SE) #define clear_single_step(regs) ((regs)->msr &= ~MSR_SE) +#define clear_br_trace(regs) ((regs)->msr &= ~MSR_BE) #endif #if defined(CONFIG_E500) @@ -988,6 +1000,7 @@ void single_step_exception(struct pt_regs *regs) enum ctx_state prev_state = exception_enter(); clear_single_step(regs); + clear_br_trace(regs); if (kprobe_post_handler(regs)) return; @@ -1495,18 +1508,6 @@ 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", diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index 22b01a3962f0..b44ec104a5a1 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -99,26 +99,28 @@ static struct vdso_patch_def vdso_patches[] = { CPU_FTR_COHERENT_ICACHE, CPU_FTR_COHERENT_ICACHE, "__kernel_sync_dicache", "__kernel_sync_dicache_p5" }, +#ifdef CONFIG_PPC32 { - CPU_FTR_USE_TB, 0, + CPU_FTR_USE_RTC, CPU_FTR_USE_RTC, "__kernel_gettimeofday", NULL }, { - CPU_FTR_USE_TB, 0, + CPU_FTR_USE_RTC, CPU_FTR_USE_RTC, "__kernel_clock_gettime", NULL }, { - CPU_FTR_USE_TB, 0, + CPU_FTR_USE_RTC, CPU_FTR_USE_RTC, "__kernel_clock_getres", NULL }, { - CPU_FTR_USE_TB, 0, + CPU_FTR_USE_RTC, CPU_FTR_USE_RTC, "__kernel_get_tbfreq", NULL }, { - CPU_FTR_USE_TB, 0, + CPU_FTR_USE_RTC, CPU_FTR_USE_RTC, "__kernel_time", NULL }, +#endif }; /* |