diff options
Diffstat (limited to 'arch/powerpc/kernel')
31 files changed, 832 insertions, 760 deletions
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index c8cf924bf9c0..06d2d1f78f71 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -54,6 +54,13 @@ CFLAGS_cputable.o += -DDISABLE_BRANCH_PROFILING CFLAGS_btext.o += -DDISABLE_BRANCH_PROFILING endif +#ifdef CONFIG_RANDOMIZE_KSTACK_OFFSET +# Remove stack protector to avoid triggering unneeded stack canary +# checks due to randomize_kstack_offset. +CFLAGS_REMOVE_syscall.o = -fstack-protector -fstack-protector-strong +CFLAGS_syscall.o += -fno-stack-protector +#endif + obj-y := cputable.o syscalls.o \ irq.o align.o signal_$(BITS).o pmc.o vdso.o \ process.o systbl.o idle.o \ @@ -62,9 +69,9 @@ obj-y := cputable.o syscalls.o \ udbg.o misc.o io.o misc_$(BITS).o \ of_platform.o prom_parse.o firmware.o \ hw_breakpoint_constraints.o interrupt.o \ - kdebugfs.o stacktrace.o + kdebugfs.o stacktrace.o syscall.o obj-y += ptrace/ -obj-$(CONFIG_PPC64) += setup_64.o \ +obj-$(CONFIG_PPC64) += setup_64.o irq_64.o\ paca.o nvram_64.o note.o obj-$(CONFIG_COMPAT) += sys_ppc32.o signal_32.o obj-$(CONFIG_VDSO32) += vdso32_wrapper.o diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index eec536aef83a..8c10f536e478 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -379,7 +379,7 @@ int main(void) OFFSET(VCPU_SPRG2, kvm_vcpu, arch.shregs.sprg2); OFFSET(VCPU_SPRG3, kvm_vcpu, arch.shregs.sprg3); #endif -#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING +#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING OFFSET(VCPU_TB_RMENTRY, kvm_vcpu, arch.rm_entry); OFFSET(VCPU_TB_RMINTR, kvm_vcpu, arch.rm_intr); OFFSET(VCPU_TB_RMEXIT, kvm_vcpu, arch.rm_exit); diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c index 8f69bb07e500..2769889219bf 100644 --- a/arch/powerpc/kernel/btext.c +++ b/arch/powerpc/kernel/btext.c @@ -73,7 +73,7 @@ static inline void rmci_maybe_off(void) * the display during identify_machine() and MMU_Init() * * The display is mapped to virtual address 0xD0000000, rather - * than 1:1, because some some CHRP machines put the frame buffer + * than 1:1, because some CHRP machines put the frame buffer * in the region starting at 0xC0000000 (PAGE_OFFSET). * This mapping is temporary and will disappear as soon as the * setup done by MMU_Init() is applied. diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index a5dbfccd2047..d8e42ef750f1 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -149,7 +149,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .pmc_type = PPC_PMC_IBM, .cpu_setup = __setup_cpu_ppc970, .cpu_restore = __restore_cpu_ppc970, - .oprofile_cpu_type = "ppc64/970", .platform = "ppc970", }, { /* PPC970FX */ @@ -166,7 +165,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .pmc_type = PPC_PMC_IBM, .cpu_setup = __setup_cpu_ppc970, .cpu_restore = __restore_cpu_ppc970, - .oprofile_cpu_type = "ppc64/970", .platform = "ppc970", }, { /* PPC970MP DD1.0 - no DEEPNAP, use regular 970 init */ @@ -183,7 +181,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .pmc_type = PPC_PMC_IBM, .cpu_setup = __setup_cpu_ppc970, .cpu_restore = __restore_cpu_ppc970, - .oprofile_cpu_type = "ppc64/970MP", .platform = "ppc970", }, { /* PPC970MP */ @@ -200,7 +197,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .pmc_type = PPC_PMC_IBM, .cpu_setup = __setup_cpu_ppc970MP, .cpu_restore = __restore_cpu_ppc970, - .oprofile_cpu_type = "ppc64/970MP", .platform = "ppc970", }, { /* PPC970GX */ @@ -216,7 +212,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .num_pmcs = 8, .pmc_type = PPC_PMC_IBM, .cpu_setup = __setup_cpu_ppc970, - .oprofile_cpu_type = "ppc64/970", .platform = "ppc970", }, { /* Power5 GR */ @@ -230,7 +225,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .dcache_bsize = 128, .num_pmcs = 6, .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power5", .platform = "power5", }, { /* Power5++ */ @@ -243,7 +237,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, - .oprofile_cpu_type = "ppc64/power5++", .platform = "power5+", }, { /* Power5 GS */ @@ -257,7 +250,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .dcache_bsize = 128, .num_pmcs = 6, .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power5+", .platform = "power5+", }, { /* POWER6 in P5+ mode; 2.04-compliant processor */ @@ -269,7 +261,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .mmu_features = MMU_FTRS_POWER5, .icache_bsize = 128, .dcache_bsize = 128, - .oprofile_cpu_type = "ppc64/ibm-compat-v1", .platform = "power5+", }, { /* Power6 */ @@ -284,7 +275,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .dcache_bsize = 128, .num_pmcs = 6, .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power6", .platform = "power6x", }, { /* 2.05-compliant processor, i.e. Power6 "architected" mode */ @@ -296,7 +286,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .mmu_features = MMU_FTRS_POWER6, .icache_bsize = 128, .dcache_bsize = 128, - .oprofile_cpu_type = "ppc64/ibm-compat-v1", .platform = "power6", }, { /* 2.06-compliant processor, i.e. Power7 "architected" mode */ @@ -309,7 +298,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .mmu_features = MMU_FTRS_POWER7, .icache_bsize = 128, .dcache_bsize = 128, - .oprofile_cpu_type = "ppc64/ibm-compat-v1", .cpu_setup = __setup_cpu_power7, .cpu_restore = __restore_cpu_power7, .machine_check_early = __machine_check_early_realmode_p7, @@ -325,7 +313,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .mmu_features = MMU_FTRS_POWER8, .icache_bsize = 128, .dcache_bsize = 128, - .oprofile_cpu_type = "ppc64/ibm-compat-v1", .cpu_setup = __setup_cpu_power8, .cpu_restore = __restore_cpu_power8, .machine_check_early = __machine_check_early_realmode_p8, @@ -341,7 +328,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .mmu_features = MMU_FTRS_POWER9, .icache_bsize = 128, .dcache_bsize = 128, - .oprofile_cpu_type = "ppc64/ibm-compat-v1", .cpu_setup = __setup_cpu_power9, .cpu_restore = __restore_cpu_power9, .platform = "power9", @@ -356,7 +342,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .mmu_features = MMU_FTRS_POWER10, .icache_bsize = 128, .dcache_bsize = 128, - .oprofile_cpu_type = "ppc64/ibm-compat-v1", .cpu_setup = __setup_cpu_power10, .cpu_restore = __restore_cpu_power10, .platform = "power10", @@ -373,7 +358,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .dcache_bsize = 128, .num_pmcs = 6, .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power7", .cpu_setup = __setup_cpu_power7, .cpu_restore = __restore_cpu_power7, .machine_check_early = __machine_check_early_realmode_p7, @@ -391,7 +375,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .dcache_bsize = 128, .num_pmcs = 6, .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power7", .cpu_setup = __setup_cpu_power7, .cpu_restore = __restore_cpu_power7, .machine_check_early = __machine_check_early_realmode_p7, @@ -409,7 +392,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .dcache_bsize = 128, .num_pmcs = 6, .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power8", .cpu_setup = __setup_cpu_power8, .cpu_restore = __restore_cpu_power8, .machine_check_early = __machine_check_early_realmode_p8, @@ -427,7 +409,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .dcache_bsize = 128, .num_pmcs = 6, .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power8", .cpu_setup = __setup_cpu_power8, .cpu_restore = __restore_cpu_power8, .machine_check_early = __machine_check_early_realmode_p8, @@ -445,7 +426,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .dcache_bsize = 128, .num_pmcs = 6, .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power8", .cpu_setup = __setup_cpu_power8, .cpu_restore = __restore_cpu_power8, .machine_check_early = __machine_check_early_realmode_p8, @@ -463,7 +443,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .dcache_bsize = 128, .num_pmcs = 6, .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power9", .cpu_setup = __setup_cpu_power9, .cpu_restore = __restore_cpu_power9, .machine_check_early = __machine_check_early_realmode_p9, @@ -481,7 +460,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .dcache_bsize = 128, .num_pmcs = 6, .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power9", .cpu_setup = __setup_cpu_power9, .cpu_restore = __restore_cpu_power9, .machine_check_early = __machine_check_early_realmode_p9, @@ -499,7 +477,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .dcache_bsize = 128, .num_pmcs = 6, .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power9", .cpu_setup = __setup_cpu_power9, .cpu_restore = __restore_cpu_power9, .machine_check_early = __machine_check_early_realmode_p9, @@ -517,7 +494,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .dcache_bsize = 128, .num_pmcs = 6, .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power9", .cpu_setup = __setup_cpu_power9, .cpu_restore = __restore_cpu_power9, .machine_check_early = __machine_check_early_realmode_p9, @@ -535,7 +511,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .dcache_bsize = 128, .num_pmcs = 6, .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/power10", .cpu_setup = __setup_cpu_power10, .cpu_restore = __restore_cpu_power10, .machine_check_early = __machine_check_early_realmode_p10, @@ -554,7 +529,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .dcache_bsize = 128, .num_pmcs = 4, .pmc_type = PPC_PMC_IBM, - .oprofile_cpu_type = "ppc64/cell-be", .platform = "ppc-cell-be", }, { /* PA Semi PA6T */ @@ -570,7 +544,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .pmc_type = PPC_PMC_PA6T, .cpu_setup = __setup_cpu_pa6t, .cpu_restore = __restore_cpu_pa6t, - .oprofile_cpu_type = "ppc64/pa6t", .platform = "pa6t", }, { /* default match */ @@ -734,7 +707,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_setup = __setup_cpu_750, .machine_check = machine_check_generic, .platform = "ppc750", - .oprofile_cpu_type = "ppc/750", }, { /* 745/755 */ .pvr_mask = 0xfffff000, @@ -765,7 +737,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_setup = __setup_cpu_750, .machine_check = machine_check_generic, .platform = "ppc750", - .oprofile_cpu_type = "ppc/750", }, { /* 750FX rev 2.0 must disable HID0[DPM] */ .pvr_mask = 0xffffffff, @@ -781,7 +752,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_setup = __setup_cpu_750, .machine_check = machine_check_generic, .platform = "ppc750", - .oprofile_cpu_type = "ppc/750", }, { /* 750FX (All revs except 2.0) */ .pvr_mask = 0xffff0000, @@ -797,7 +767,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_setup = __setup_cpu_750fx, .machine_check = machine_check_generic, .platform = "ppc750", - .oprofile_cpu_type = "ppc/750", }, { /* 750GX */ .pvr_mask = 0xffff0000, @@ -813,7 +782,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_setup = __setup_cpu_750fx, .machine_check = machine_check_generic, .platform = "ppc750", - .oprofile_cpu_type = "ppc/750", }, { /* 740/750 (L2CR bit need fixup for 740) */ .pvr_mask = 0xffff0000, @@ -891,7 +859,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .num_pmcs = 6, .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_745x, - .oprofile_cpu_type = "ppc/7450", .machine_check = machine_check_generic, .platform = "ppc7450", }, @@ -908,7 +875,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .num_pmcs = 6, .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_745x, - .oprofile_cpu_type = "ppc/7450", .machine_check = machine_check_generic, .platform = "ppc7450", }, @@ -925,7 +891,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .num_pmcs = 6, .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_745x, - .oprofile_cpu_type = "ppc/7450", .machine_check = machine_check_generic, .platform = "ppc7450", }, @@ -942,7 +907,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .num_pmcs = 6, .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_745x, - .oprofile_cpu_type = "ppc/7450", .machine_check = machine_check_generic, .platform = "ppc7450", }, @@ -959,7 +923,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .num_pmcs = 6, .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_745x, - .oprofile_cpu_type = "ppc/7450", .machine_check = machine_check_generic, .platform = "ppc7450", }, @@ -976,7 +939,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .num_pmcs = 6, .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_745x, - .oprofile_cpu_type = "ppc/7450", .machine_check = machine_check_generic, .platform = "ppc7450", }, @@ -993,7 +955,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .num_pmcs = 6, .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_745x, - .oprofile_cpu_type = "ppc/7450", .machine_check = machine_check_generic, .platform = "ppc7450", }, @@ -1010,7 +971,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .num_pmcs = 6, .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_745x, - .oprofile_cpu_type = "ppc/7450", .machine_check = machine_check_generic, .platform = "ppc7450", }, @@ -1026,7 +986,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .num_pmcs = 6, .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_745x, - .oprofile_cpu_type = "ppc/7450", .machine_check = machine_check_generic, .platform = "ppc7450", }, @@ -1043,7 +1002,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .num_pmcs = 6, .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_745x, - .oprofile_cpu_type = "ppc/7450", .machine_check = machine_check_generic, .platform = "ppc7450", }, @@ -1060,7 +1018,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .num_pmcs = 6, .pmc_type = PPC_PMC_G4, .cpu_setup = __setup_cpu_745x, - .oprofile_cpu_type = "ppc/7450", .machine_check = machine_check_generic, .platform = "ppc7450", }, @@ -1172,7 +1129,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_setup = __setup_cpu_603, .machine_check = machine_check_83xx, .num_pmcs = 4, - .oprofile_cpu_type = "ppc/e300", .platform = "ppc603", }, { /* e300c4 (e300c1, plus one IU) */ @@ -1188,7 +1144,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_setup = __setup_cpu_603, .machine_check = machine_check_83xx, .num_pmcs = 4, - .oprofile_cpu_type = "ppc/e300", .platform = "ppc603", }, #endif @@ -1884,7 +1839,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, - .oprofile_cpu_type = "ppc/e500", .cpu_setup = __setup_cpu_e500v1, .machine_check = machine_check_e500, .platform = "ppc8540", @@ -1903,7 +1857,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, - .oprofile_cpu_type = "ppc/e500", .cpu_setup = __setup_cpu_e500v2, .machine_check = machine_check_e500, .platform = "ppc8548", @@ -1922,7 +1875,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .icache_bsize = 64, .dcache_bsize = 64, .num_pmcs = 4, - .oprofile_cpu_type = "ppc/e500mc", .cpu_setup = __setup_cpu_e500mc, .machine_check = machine_check_e500mc, .platform = "ppce500mc", @@ -1943,7 +1895,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .icache_bsize = 64, .dcache_bsize = 64, .num_pmcs = 4, - .oprofile_cpu_type = "ppc/e500mc", .cpu_setup = __setup_cpu_e5500, #ifndef CONFIG_PPC32 .cpu_restore = __restore_cpu_e5500, @@ -1965,7 +1916,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .icache_bsize = 64, .dcache_bsize = 64, .num_pmcs = 6, - .oprofile_cpu_type = "ppc/e6500", .cpu_setup = __setup_cpu_e6500, #ifndef CONFIG_PPC32 .cpu_restore = __restore_cpu_e6500, @@ -2033,23 +1983,10 @@ static struct cpu_spec * __init setup_cpu_spec(unsigned long offset, t->pmc_type = old.pmc_type; /* - * If we have passed through this logic once before and - * have pulled the default case because the real PVR was - * not found inside cpu_specs[], then we are possibly - * running in compatibility mode. In that case, let the - * oprofiler know which set of compatibility counters to - * pull from by making sure the oprofile_cpu_type string - * is set to that of compatibility mode. If the - * oprofile_cpu_type already has a value, then we are - * possibly overriding a real PVR with a logical one, - * and, in that case, keep the current value for - * oprofile_cpu_type. Furthermore, let's ensure that the + * Let's ensure that the * fix for the PMAO bug is enabled on compatibility mode. */ - if (old.oprofile_cpu_type != NULL) { - t->oprofile_cpu_type = old.oprofile_cpu_type; - t->cpu_features |= old.cpu_features & CPU_FTR_PMAO_BUG; - } + t->cpu_features |= old.cpu_features & CPU_FTR_PMAO_BUG; } *PTRRELOC(&cur_cpu_spec) = &the_cpu_spec; diff --git a/arch/powerpc/kernel/dawr.c b/arch/powerpc/kernel/dawr.c index 30d4eca88d17..909a05cd2809 100644 --- a/arch/powerpc/kernel/dawr.c +++ b/arch/powerpc/kernel/dawr.c @@ -11,6 +11,7 @@ #include <linux/debugfs.h> #include <asm/machdep.h> #include <asm/hvcall.h> +#include <asm/firmware.h> bool dawr_force_enable; EXPORT_SYMBOL_GPL(dawr_force_enable); diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 2ad365c21afa..fc800a9fb2c4 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -102,7 +102,6 @@ static struct cpu_spec __initdata base_cpu_spec = { .dcache_bsize = 32, /* cache info init. */ .num_pmcs = 0, .pmc_type = PPC_PMC_DEFAULT, - .oprofile_cpu_type = NULL, .cpu_setup = NULL, .cpu_restore = __restore_cpu_cpufeatures, .machine_check_early = NULL, @@ -387,7 +386,6 @@ static int __init feat_enable_pmu_power8(struct dt_cpu_feature *f) cur_cpu_spec->num_pmcs = 6; cur_cpu_spec->pmc_type = PPC_PMC_IBM; - cur_cpu_spec->oprofile_cpu_type = "ppc64/power8"; return 1; } @@ -423,7 +421,6 @@ static int __init feat_enable_pmu_power9(struct dt_cpu_feature *f) cur_cpu_spec->num_pmcs = 6; cur_cpu_spec->pmc_type = PPC_PMC_IBM; - cur_cpu_spec->oprofile_cpu_type = "ppc64/power9"; return 1; } @@ -449,7 +446,6 @@ static int __init feat_enable_pmu_power10(struct dt_cpu_feature *f) cur_cpu_spec->num_pmcs = 6; cur_cpu_spec->pmc_type = PPC_PMC_IBM; - cur_cpu_spec->oprofile_cpu_type = "ppc64/power10"; return 1; } diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 260273e56431..f279295179bd 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -750,7 +750,7 @@ static void eeh_pe_cleanup(struct eeh_pe *pe) * @pdev: pci_dev to check * * This function may return a false positive if we can't determine the slot's - * presence state. This might happen for for PCIe slots if the PE containing + * presence state. This might happen for PCIe slots if the PE containing * the upstream bridge is also frozen, or the bridge is part of the same PE * as the device. * diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index b66dd6f775a4..3d0dc133a9ae 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -2779,7 +2779,7 @@ EXC_COMMON_BEGIN(soft_nmi_common) /* * 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 decrementer interrupt, we bump the dec to max 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 diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index d3eea633d11a..cf2c08902c05 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -965,6 +965,9 @@ start_here_multiplatform: * and SLB setup before we turn on relocation. */ +#ifdef CONFIG_KASAN + bl kasan_early_init +#endif /* Restore parameters passed from prom_init/kexec */ mr r3,r31 LOAD_REG_ADDR(r12, DOTSYM(early_setup)) diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S index 6c739beb938c..519b60695167 100644 --- a/arch/powerpc/kernel/head_book3s_32.S +++ b/arch/powerpc/kernel/head_book3s_32.S @@ -418,14 +418,14 @@ InstructionTLBMiss: */ /* Get PTE (linux-style) and check access */ mfspr r3,SPRN_IMISS -#if defined(CONFIG_MODULES) || defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE) +#ifdef CONFIG_MODULES lis r1, TASK_SIZE@h /* check if kernel address */ cmplw 0,r1,r3 #endif mfspr r2, SPRN_SDR1 li r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC | _PAGE_USER rlwinm r2, r2, 28, 0xfffff000 -#if defined(CONFIG_MODULES) || defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE) +#ifdef CONFIG_MODULES bgt- 112f lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */ li r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c index 784ea3289c84..0e75cb03244a 100644 --- a/arch/powerpc/kernel/interrupt.c +++ b/arch/powerpc/kernel/interrupt.c @@ -24,8 +24,6 @@ unsigned long global_dbcr0[NR_CPUS]; #endif -typedef long (*syscall_fn)(long, long, long, long, long, long); - #ifdef CONFIG_PPC_BOOK3S_64 DEFINE_STATIC_KEY_FALSE(interrupt_exit_not_reentrant); static inline bool exit_must_hard_disable(void) @@ -73,165 +71,6 @@ static notrace __always_inline bool prep_irq_for_enabled_exit(bool restartable) return true; } -/* Has to run notrace because it is entered not completely "reconciled" */ -notrace long system_call_exception(long r3, long r4, long r5, - long r6, long r7, long r8, - unsigned long r0, struct pt_regs *regs) -{ - syscall_fn f; - - kuap_lock(); - - regs->orig_gpr3 = r3; - - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) - BUG_ON(irq_soft_mask_return() != IRQS_ALL_DISABLED); - - trace_hardirqs_off(); /* finish reconciling */ - - CT_WARN_ON(ct_state() == CONTEXT_KERNEL); - user_exit_irqoff(); - - BUG_ON(regs_is_unrecoverable(regs)); - BUG_ON(!(regs->msr & MSR_PR)); - BUG_ON(arch_irq_disabled_regs(regs)); - -#ifdef CONFIG_PPC_PKEY - if (mmu_has_feature(MMU_FTR_PKEY)) { - unsigned long amr, iamr; - bool flush_needed = false; - /* - * When entering from userspace we mostly have the AMR/IAMR - * different from kernel default values. Hence don't compare. - */ - amr = mfspr(SPRN_AMR); - iamr = mfspr(SPRN_IAMR); - regs->amr = amr; - regs->iamr = iamr; - if (mmu_has_feature(MMU_FTR_BOOK3S_KUAP)) { - mtspr(SPRN_AMR, AMR_KUAP_BLOCKED); - flush_needed = true; - } - if (mmu_has_feature(MMU_FTR_BOOK3S_KUEP)) { - mtspr(SPRN_IAMR, AMR_KUEP_BLOCKED); - flush_needed = true; - } - if (flush_needed) - isync(); - } else -#endif - kuap_assert_locked(); - - booke_restore_dbcr0(); - - account_cpu_user_entry(); - - account_stolen_time(); - - /* - * This is not required for the syscall exit path, but makes the - * stack frame look nicer. If this was initialised in the first stack - * frame, or if the unwinder was taught the first stack frame always - * returns to user with IRQS_ENABLED, this store could be avoided! - */ - irq_soft_mask_regs_set_state(regs, IRQS_ENABLED); - - /* - * If system call is called with TM active, set _TIF_RESTOREALL to - * prevent RFSCV being used to return to userspace, because POWER9 - * TM implementation has problems with this instruction returning to - * transactional state. Final register values are not relevant because - * the transaction will be aborted upon return anyway. Or in the case - * of unsupported_scv SIGILL fault, the return state does not much - * matter because it's an edge case. - */ - if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) && - unlikely(MSR_TM_TRANSACTIONAL(regs->msr))) - set_bits(_TIF_RESTOREALL, ¤t_thread_info()->flags); - - /* - * If the system call was made with a transaction active, doom it and - * return without performing the system call. Unless it was an - * unsupported scv vector, in which case it's treated like an illegal - * instruction. - */ -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - if (unlikely(MSR_TM_TRANSACTIONAL(regs->msr)) && - !trap_is_unsupported_scv(regs)) { - /* Enable TM in the kernel, and disable EE (for scv) */ - hard_irq_disable(); - mtmsr(mfmsr() | MSR_TM); - - /* tabort, this dooms the transaction, nothing else */ - asm volatile(".long 0x7c00071d | ((%0) << 16)" - :: "r"(TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT)); - - /* - * Userspace will never see the return value. Execution will - * resume after the tbegin. of the aborted transaction with the - * checkpointed register state. A context switch could occur - * or signal delivered to the process before resuming the - * doomed transaction context, but that should all be handled - * as expected. - */ - return -ENOSYS; - } -#endif // CONFIG_PPC_TRANSACTIONAL_MEM - - local_irq_enable(); - - if (unlikely(read_thread_flags() & _TIF_SYSCALL_DOTRACE)) { - if (unlikely(trap_is_unsupported_scv(regs))) { - /* Unsupported scv vector */ - _exception(SIGILL, regs, ILL_ILLOPC, regs->nip); - return regs->gpr[3]; - } - /* - * We use the return value of do_syscall_trace_enter() as the - * syscall number. If the syscall was rejected for any reason - * do_syscall_trace_enter() returns an invalid syscall number - * and the test against NR_syscalls will fail and the return - * value to be used is in regs->gpr[3]. - */ - r0 = do_syscall_trace_enter(regs); - if (unlikely(r0 >= NR_syscalls)) - return regs->gpr[3]; - r3 = regs->gpr[3]; - r4 = regs->gpr[4]; - r5 = regs->gpr[5]; - r6 = regs->gpr[6]; - r7 = regs->gpr[7]; - r8 = regs->gpr[8]; - - } else if (unlikely(r0 >= NR_syscalls)) { - if (unlikely(trap_is_unsupported_scv(regs))) { - /* Unsupported scv vector */ - _exception(SIGILL, regs, ILL_ILLOPC, regs->nip); - return regs->gpr[3]; - } - return -ENOSYS; - } - - /* May be faster to do array_index_nospec? */ - barrier_nospec(); - - if (unlikely(is_compat_task())) { - f = (void *)compat_sys_call_table[r0]; - - r3 &= 0x00000000ffffffffULL; - r4 &= 0x00000000ffffffffULL; - r5 &= 0x00000000ffffffffULL; - r6 &= 0x00000000ffffffffULL; - r7 &= 0x00000000ffffffffULL; - r8 &= 0x00000000ffffffffULL; - - } else { - f = (void *)sys_call_table[r0]; - } - - return f(r3, r4, r5, r6, r7, r8); -} - static notrace void booke_load_dbcr0(void) { #ifdef CONFIG_PPC_ADV_DEBUG_REGS diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 7e56ddb3e0b9..caebe1431596 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -775,6 +775,11 @@ bool iommu_table_in_use(struct iommu_table *tbl) /* ignore reserved bit0 */ if (tbl->it_offset == 0) start = 1; + + /* Simple case with no reserved MMIO32 region */ + if (!tbl->it_reserved_start && !tbl->it_reserved_end) + return find_next_bit(tbl->it_map, tbl->it_size, start) != tbl->it_size; + end = tbl->it_reserved_start - tbl->it_offset; if (find_next_bit(tbl->it_map, end, start) != end) return true; diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 0822a274a549..0f17268c1f0b 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -65,13 +65,8 @@ #include <asm/smp.h> #include <asm/hw_irq.h> #include <asm/softirq_stack.h> +#include <asm/ppc_asm.h> -#ifdef CONFIG_PPC64 -#include <asm/paca.h> -#include <asm/firmware.h> -#include <asm/lv1call.h> -#include <asm/dbell.h> -#endif #define CREATE_TRACE_POINTS #include <asm/trace.h> #include <asm/cpu_has_feature.h> @@ -88,411 +83,6 @@ u32 tau_interrupts(unsigned long cpu); #endif #endif /* CONFIG_PPC32 */ -#ifdef CONFIG_PPC64 - -int distribute_irqs = 1; - -static inline notrace unsigned long get_irq_happened(void) -{ - unsigned long happened; - - __asm__ __volatile__("lbz %0,%1(13)" - : "=r" (happened) : "i" (offsetof(struct paca_struct, irq_happened))); - - return happened; -} - -void replay_soft_interrupts(void) -{ - struct pt_regs regs; - - /* - * Be careful here, calling these interrupt handlers can cause - * softirqs to be raised, which they may run when calling irq_exit, - * which will cause local_irq_enable() to be run, which can then - * recurse into this function. Don't keep any state across - * interrupt handler calls which may change underneath us. - * - * We use local_paca rather than get_paca() to avoid all the - * debug_smp_processor_id() business in this low level function. - */ - - ppc_save_regs(®s); - regs.softe = IRQS_ENABLED; - regs.msr |= MSR_EE; - -again: - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) - WARN_ON_ONCE(mfmsr() & MSR_EE); - - /* - * Force the delivery of pending soft-disabled interrupts on PS3. - * Any HV call will have this side effect. - */ - if (firmware_has_feature(FW_FEATURE_PS3_LV1)) { - u64 tmp, tmp2; - lv1_get_version_info(&tmp, &tmp2); - } - - /* - * Check if an hypervisor Maintenance interrupt happened. - * This is a higher priority interrupt than the others, so - * replay it first. - */ - if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (local_paca->irq_happened & PACA_IRQ_HMI)) { - local_paca->irq_happened &= ~PACA_IRQ_HMI; - regs.trap = INTERRUPT_HMI; - handle_hmi_exception(®s); - if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) - hard_irq_disable(); - } - - if (local_paca->irq_happened & PACA_IRQ_DEC) { - local_paca->irq_happened &= ~PACA_IRQ_DEC; - regs.trap = INTERRUPT_DECREMENTER; - timer_interrupt(®s); - if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) - hard_irq_disable(); - } - - if (local_paca->irq_happened & PACA_IRQ_EE) { - local_paca->irq_happened &= ~PACA_IRQ_EE; - regs.trap = INTERRUPT_EXTERNAL; - do_IRQ(®s); - if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) - hard_irq_disable(); - } - - if (IS_ENABLED(CONFIG_PPC_DOORBELL) && (local_paca->irq_happened & PACA_IRQ_DBELL)) { - local_paca->irq_happened &= ~PACA_IRQ_DBELL; - regs.trap = INTERRUPT_DOORBELL; - doorbell_exception(®s); - if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) - hard_irq_disable(); - } - - /* Book3E does not support soft-masking PMI interrupts */ - if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (local_paca->irq_happened & PACA_IRQ_PMI)) { - local_paca->irq_happened &= ~PACA_IRQ_PMI; - regs.trap = INTERRUPT_PERFMON; - performance_monitor_exception(®s); - if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) - hard_irq_disable(); - } - - if (local_paca->irq_happened & ~PACA_IRQ_HARD_DIS) { - /* - * We are responding to the next interrupt, so interrupt-off - * latencies should be reset here. - */ - trace_hardirqs_on(); - trace_hardirqs_off(); - goto again; - } -} - -#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_KUAP) -static inline void replay_soft_interrupts_irqrestore(void) -{ - unsigned long kuap_state = get_kuap(); - - /* - * Check if anything calls local_irq_enable/restore() when KUAP is - * disabled (user access enabled). We handle that case here by saving - * and re-locking AMR but we shouldn't get here in the first place, - * hence the warning. - */ - kuap_assert_locked(); - - if (kuap_state != AMR_KUAP_BLOCKED) - set_kuap(AMR_KUAP_BLOCKED); - - replay_soft_interrupts(); - - if (kuap_state != AMR_KUAP_BLOCKED) - set_kuap(kuap_state); -} -#else -#define replay_soft_interrupts_irqrestore() replay_soft_interrupts() -#endif - -notrace void arch_local_irq_restore(unsigned long mask) -{ - unsigned char irq_happened; - - /* Write the new soft-enabled value if it is a disable */ - if (mask) { - irq_soft_mask_set(mask); - return; - } - - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) - WARN_ON_ONCE(in_nmi() || in_hardirq()); - - /* - * After the stb, interrupts are unmasked and there are no interrupts - * pending replay. The restart sequence makes this atomic with - * respect to soft-masked interrupts. If this was just a simple code - * sequence, a soft-masked interrupt could become pending right after - * the comparison and before the stb. - * - * This allows interrupts to be unmasked without hard disabling, and - * also without new hard interrupts coming in ahead of pending ones. - */ - asm_volatile_goto( -"1: \n" -" lbz 9,%0(13) \n" -" cmpwi 9,0 \n" -" bne %l[happened] \n" -" stb 9,%1(13) \n" -"2: \n" - RESTART_TABLE(1b, 2b, 1b) - : : "i" (offsetof(struct paca_struct, irq_happened)), - "i" (offsetof(struct paca_struct, irq_soft_mask)) - : "cr0", "r9" - : happened); - - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) - WARN_ON_ONCE(!(mfmsr() & MSR_EE)); - - return; - -happened: - irq_happened = get_irq_happened(); - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) - WARN_ON_ONCE(!irq_happened); - - if (irq_happened == PACA_IRQ_HARD_DIS) { - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) - WARN_ON_ONCE(mfmsr() & MSR_EE); - irq_soft_mask_set(IRQS_ENABLED); - local_paca->irq_happened = 0; - __hard_irq_enable(); - return; - } - - /* Have interrupts to replay, need to hard disable first */ - if (!(irq_happened & PACA_IRQ_HARD_DIS)) { - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) { - if (!(mfmsr() & MSR_EE)) { - /* - * An interrupt could have come in and cleared - * MSR[EE] and set IRQ_HARD_DIS, so check - * IRQ_HARD_DIS again and warn if it is still - * clear. - */ - irq_happened = get_irq_happened(); - WARN_ON_ONCE(!(irq_happened & PACA_IRQ_HARD_DIS)); - } - } - __hard_irq_disable(); - local_paca->irq_happened |= PACA_IRQ_HARD_DIS; - } else { - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) { - if (WARN_ON_ONCE(mfmsr() & MSR_EE)) - __hard_irq_disable(); - } - } - - /* - * Disable preempt here, so that the below preempt_enable will - * perform resched if required (a replayed interrupt may set - * need_resched). - */ - preempt_disable(); - irq_soft_mask_set(IRQS_ALL_DISABLED); - trace_hardirqs_off(); - - replay_soft_interrupts_irqrestore(); - local_paca->irq_happened = 0; - - trace_hardirqs_on(); - irq_soft_mask_set(IRQS_ENABLED); - __hard_irq_enable(); - preempt_enable(); -} -EXPORT_SYMBOL(arch_local_irq_restore); - -/* - * This is a helper to use when about to go into idle low-power - * when the latter has the side effect of re-enabling interrupts - * (such as calling H_CEDE under pHyp). - * - * You call this function with interrupts soft-disabled (this is - * already the case when ppc_md.power_save is called). The function - * will return whether to enter power save or just return. - * - * In the former case, it will have notified lockdep of interrupts - * being re-enabled and generally sanitized the lazy irq state, - * and in the latter case it will leave with interrupts hard - * disabled and marked as such, so the local_irq_enable() call - * in arch_cpu_idle() will properly re-enable everything. - */ -bool prep_irq_for_idle(void) -{ - /* - * First we need to hard disable to ensure no interrupt - * occurs before we effectively enter the low power state - */ - __hard_irq_disable(); - local_paca->irq_happened |= PACA_IRQ_HARD_DIS; - - /* - * If anything happened while we were soft-disabled, - * we return now and do not enter the low power state. - */ - if (lazy_irq_pending()) - return false; - - /* Tell lockdep we are about to re-enable */ - trace_hardirqs_on(); - - /* - * Mark interrupts as soft-enabled and clear the - * PACA_IRQ_HARD_DIS from the pending mask since we - * are about to hard enable as well as a side effect - * of entering the low power state. - */ - local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS; - irq_soft_mask_set(IRQS_ENABLED); - - /* Tell the caller to enter the low power state */ - return true; -} - -#ifdef CONFIG_PPC_BOOK3S -/* - * This is for idle sequences that return with IRQs off, but the - * idle state itself wakes on interrupt. Tell the irq tracer that - * IRQs are enabled for the duration of idle so it does not get long - * off times. Must be paired with fini_irq_for_idle_irqsoff. - */ -bool prep_irq_for_idle_irqsoff(void) -{ - WARN_ON(!irqs_disabled()); - - /* - * First we need to hard disable to ensure no interrupt - * occurs before we effectively enter the low power state - */ - __hard_irq_disable(); - local_paca->irq_happened |= PACA_IRQ_HARD_DIS; - - /* - * If anything happened while we were soft-disabled, - * we return now and do not enter the low power state. - */ - if (lazy_irq_pending()) - return false; - - /* Tell lockdep we are about to re-enable */ - trace_hardirqs_on(); - - return true; -} - -/* - * Take the SRR1 wakeup reason, index into this table to find the - * appropriate irq_happened bit. - * - * Sytem reset exceptions taken in idle state also come through here, - * but they are NMI interrupts so do not need to wait for IRQs to be - * restored, and should be taken as early as practical. These are marked - * with 0xff in the table. The Power ISA specifies 0100b as the system - * reset interrupt reason. - */ -#define IRQ_SYSTEM_RESET 0xff - -static const u8 srr1_to_lazyirq[0x10] = { - 0, 0, 0, - PACA_IRQ_DBELL, - IRQ_SYSTEM_RESET, - PACA_IRQ_DBELL, - PACA_IRQ_DEC, - 0, - PACA_IRQ_EE, - PACA_IRQ_EE, - PACA_IRQ_HMI, - 0, 0, 0, 0, 0 }; - -void replay_system_reset(void) -{ - struct pt_regs regs; - - ppc_save_regs(®s); - regs.trap = 0x100; - get_paca()->in_nmi = 1; - system_reset_exception(®s); - get_paca()->in_nmi = 0; -} -EXPORT_SYMBOL_GPL(replay_system_reset); - -void irq_set_pending_from_srr1(unsigned long srr1) -{ - unsigned int idx = (srr1 & SRR1_WAKEMASK_P8) >> 18; - u8 reason = srr1_to_lazyirq[idx]; - - /* - * Take the system reset now, which is immediately after registers - * are restored from idle. It's an NMI, so interrupts need not be - * re-enabled before it is taken. - */ - if (unlikely(reason == IRQ_SYSTEM_RESET)) { - replay_system_reset(); - return; - } - - if (reason == PACA_IRQ_DBELL) { - /* - * When doorbell triggers a system reset wakeup, the message - * is not cleared, so if the doorbell interrupt is replayed - * and the IPI handled, the doorbell interrupt would still - * fire when EE is enabled. - * - * To avoid taking the superfluous doorbell interrupt, - * execute a msgclr here before the interrupt is replayed. - */ - ppc_msgclr(PPC_DBELL_MSGTYPE); - } - - /* - * The 0 index (SRR1[42:45]=b0000) must always evaluate to 0, - * so this can be called unconditionally with the SRR1 wake - * reason as returned by the idle code, which uses 0 to mean no - * interrupt. - * - * If a future CPU was to designate this as an interrupt reason, - * then a new index for no interrupt must be assigned. - */ - local_paca->irq_happened |= reason; -} -#endif /* CONFIG_PPC_BOOK3S */ - -/* - * Force a replay of the external interrupt handler on this CPU. - */ -void force_external_irq_replay(void) -{ - /* - * This must only be called with interrupts soft-disabled, - * the replay will happen when re-enabling. - */ - WARN_ON(!arch_irqs_disabled()); - - /* - * Interrupts must always be hard disabled before irq_happened is - * modified (to prevent lost update in case of interrupt between - * load and store). - */ - __hard_irq_disable(); - local_paca->irq_happened |= PACA_IRQ_HARD_DIS; - - /* Indicate in the PACA that we have an interrupt to replay */ - local_paca->irq_happened |= PACA_IRQ_EE; -} - -#endif /* CONFIG_PPC64 */ - int arch_show_interrupts(struct seq_file *p, int prec) { int j; @@ -595,17 +185,15 @@ u64 arch_irq_stat_cpu(unsigned int cpu) return sum; } -static inline void check_stack_overflow(void) +static inline void check_stack_overflow(unsigned long sp) { - long sp; - if (!IS_ENABLED(CONFIG_DEBUG_STACKOVERFLOW)) return; - sp = current_stack_pointer & (THREAD_SIZE - 1); + sp &= THREAD_SIZE - 1; - /* check for stack overflow: is there less than 2KB free? */ - if (unlikely(sp < 2048)) { + /* check for stack overflow: is there less than 1/4th free? */ + if (unlikely(sp < THREAD_SIZE / 4)) { pr_err("do_IRQ: stack overflow: %ld\n", sp); dump_stack(); } @@ -632,36 +220,16 @@ static __always_inline void call_do_softirq(const void *sp) } #endif -static __always_inline void call_do_irq(struct pt_regs *regs, void *sp) -{ - register unsigned long r3 asm("r3") = (unsigned long)regs; - - /* Temporarily switch r1 to sp, call __do_irq() then restore r1. */ - asm volatile ( - PPC_STLU " %%r1, %[offset](%[sp]) ;" - "mr %%r1, %[sp] ;" - "bl %[callee] ;" - PPC_LL " %%r1, 0(%%r1) ;" - : // Outputs - "+r" (r3) - : // Inputs - [sp] "b" (sp), [offset] "i" (THREAD_SIZE - STACK_FRAME_OVERHEAD), - [callee] "i" (__do_irq) - : // Clobbers - "lr", "xer", "ctr", "memory", "cr0", "cr1", "cr5", "cr6", - "cr7", "r0", "r4", "r5", "r6", "r7", "r8", "r9", "r10", - "r11", "r12" - ); -} - DEFINE_STATIC_CALL_RET0(ppc_get_irq, *ppc_md.get_irq); -void __do_irq(struct pt_regs *regs) +static void __do_irq(struct pt_regs *regs, unsigned long oldsp) { unsigned int irq; trace_irq_entry(regs); + check_stack_overflow(oldsp); + /* * Query the platform PIC for the interrupt & ack it. * @@ -682,6 +250,29 @@ void __do_irq(struct pt_regs *regs) trace_irq_exit(regs); } +static __always_inline void call_do_irq(struct pt_regs *regs, void *sp) +{ + register unsigned long r3 asm("r3") = (unsigned long)regs; + + /* Temporarily switch r1 to sp, call __do_irq() then restore r1. */ + asm volatile ( + PPC_STLU " %%r1, %[offset](%[sp]) ;" + "mr %%r4, %%r1 ;" + "mr %%r1, %[sp] ;" + "bl %[callee] ;" + PPC_LL " %%r1, 0(%%r1) ;" + : // Outputs + "+r" (r3) + : // Inputs + [sp] "b" (sp), [offset] "i" (THREAD_SIZE - STACK_FRAME_OVERHEAD), + [callee] "i" (__do_irq) + : // Clobbers + "lr", "xer", "ctr", "memory", "cr0", "cr1", "cr5", "cr6", + "cr7", "r0", "r4", "r5", "r6", "r7", "r8", "r9", "r10", + "r11", "r12" + ); +} + void __do_IRQ(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); @@ -692,16 +283,11 @@ void __do_IRQ(struct pt_regs *regs) irqsp = hardirq_ctx[raw_smp_processor_id()]; sirqsp = softirq_ctx[raw_smp_processor_id()]; - check_stack_overflow(); - - /* Already there ? */ - if (unlikely(cursp == irqsp || cursp == sirqsp)) { - __do_irq(regs); - set_irq_regs(old_regs); - return; - } - /* Switch stack and call */ - call_do_irq(regs, irqsp); + /* Already there ? If not switch stack and call */ + if (unlikely(cursp == irqsp || cursp == sirqsp)) + __do_irq(regs, current_stack_pointer); + else + call_do_irq(regs, irqsp); set_irq_regs(old_regs); } @@ -798,13 +384,3 @@ int irq_choose_cpu(const struct cpumask *mask) return hard_smp_processor_id(); } #endif - -#ifdef CONFIG_PPC64 -static int __init setup_noirqdistrib(char *str) -{ - distribute_irqs = 0; - return 1; -} - -__setup("noirqdistrib", setup_noirqdistrib); -#endif /* CONFIG_PPC64 */ diff --git a/arch/powerpc/kernel/irq_64.c b/arch/powerpc/kernel/irq_64.c new file mode 100644 index 000000000000..01645e03e9f0 --- /dev/null +++ b/arch/powerpc/kernel/irq_64.c @@ -0,0 +1,466 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Derived from arch/i386/kernel/irq.c + * Copyright (C) 1992 Linus Torvalds + * Adapted from arch/i386 by Gary Thomas + * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) + * Updated and modified by Cort Dougan <cort@fsmlabs.com> + * Copyright (C) 1996-2001 Cort Dougan + * Adapted for Power Macintosh by Paul Mackerras + * Copyright (C) 1996 Paul Mackerras (paulus@cs.anu.edu.au) + * + * This file contains the code used by various IRQ handling routines: + * asking for different IRQ's should be done through these routines + * instead of just grabbing them. Thus setups with different IRQ numbers + * shouldn't result in any weird surprises, and installing new handlers + * should be easier. + */ + +#undef DEBUG + +#include <linux/export.h> +#include <linux/threads.h> +#include <linux/kernel_stat.h> +#include <linux/signal.h> +#include <linux/sched.h> +#include <linux/ptrace.h> +#include <linux/ioport.h> +#include <linux/interrupt.h> +#include <linux/timex.h> +#include <linux/init.h> +#include <linux/slab.h> +#include <linux/delay.h> +#include <linux/irq.h> +#include <linux/seq_file.h> +#include <linux/cpumask.h> +#include <linux/profile.h> +#include <linux/bitops.h> +#include <linux/list.h> +#include <linux/radix-tree.h> +#include <linux/mutex.h> +#include <linux/pci.h> +#include <linux/debugfs.h> +#include <linux/of.h> +#include <linux/of_irq.h> +#include <linux/vmalloc.h> +#include <linux/pgtable.h> +#include <linux/static_call.h> + +#include <linux/uaccess.h> +#include <asm/interrupt.h> +#include <asm/io.h> +#include <asm/irq.h> +#include <asm/cache.h> +#include <asm/ptrace.h> +#include <asm/machdep.h> +#include <asm/udbg.h> +#include <asm/smp.h> +#include <asm/hw_irq.h> +#include <asm/softirq_stack.h> +#include <asm/ppc_asm.h> + +#include <asm/paca.h> +#include <asm/firmware.h> +#include <asm/lv1call.h> +#include <asm/dbell.h> +#include <asm/trace.h> +#include <asm/cpu_has_feature.h> + +int distribute_irqs = 1; + +void replay_soft_interrupts(void) +{ + struct pt_regs regs; + + /* + * Be careful here, calling these interrupt handlers can cause + * softirqs to be raised, which they may run when calling irq_exit, + * which will cause local_irq_enable() to be run, which can then + * recurse into this function. Don't keep any state across + * interrupt handler calls which may change underneath us. + * + * We use local_paca rather than get_paca() to avoid all the + * debug_smp_processor_id() business in this low level function. + */ + + ppc_save_regs(®s); + regs.softe = IRQS_ENABLED; + regs.msr |= MSR_EE; + +again: + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) + WARN_ON_ONCE(mfmsr() & MSR_EE); + + /* + * Force the delivery of pending soft-disabled interrupts on PS3. + * Any HV call will have this side effect. + */ + if (firmware_has_feature(FW_FEATURE_PS3_LV1)) { + u64 tmp, tmp2; + lv1_get_version_info(&tmp, &tmp2); + } + + /* + * Check if an hypervisor Maintenance interrupt happened. + * This is a higher priority interrupt than the others, so + * replay it first. + */ + if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (local_paca->irq_happened & PACA_IRQ_HMI)) { + local_paca->irq_happened &= ~PACA_IRQ_HMI; + regs.trap = INTERRUPT_HMI; + handle_hmi_exception(®s); + if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) + hard_irq_disable(); + } + + if (local_paca->irq_happened & PACA_IRQ_DEC) { + local_paca->irq_happened &= ~PACA_IRQ_DEC; + regs.trap = INTERRUPT_DECREMENTER; + timer_interrupt(®s); + if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) + hard_irq_disable(); + } + + if (local_paca->irq_happened & PACA_IRQ_EE) { + local_paca->irq_happened &= ~PACA_IRQ_EE; + regs.trap = INTERRUPT_EXTERNAL; + do_IRQ(®s); + if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) + hard_irq_disable(); + } + + if (IS_ENABLED(CONFIG_PPC_DOORBELL) && (local_paca->irq_happened & PACA_IRQ_DBELL)) { + local_paca->irq_happened &= ~PACA_IRQ_DBELL; + regs.trap = INTERRUPT_DOORBELL; + doorbell_exception(®s); + if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) + hard_irq_disable(); + } + + /* Book3E does not support soft-masking PMI interrupts */ + if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (local_paca->irq_happened & PACA_IRQ_PMI)) { + local_paca->irq_happened &= ~PACA_IRQ_PMI; + regs.trap = INTERRUPT_PERFMON; + performance_monitor_exception(®s); + if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) + hard_irq_disable(); + } + + if (local_paca->irq_happened & ~PACA_IRQ_HARD_DIS) { + /* + * We are responding to the next interrupt, so interrupt-off + * latencies should be reset here. + */ + trace_hardirqs_on(); + trace_hardirqs_off(); + goto again; + } +} + +#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_KUAP) +static inline void replay_soft_interrupts_irqrestore(void) +{ + unsigned long kuap_state = get_kuap(); + + /* + * Check if anything calls local_irq_enable/restore() when KUAP is + * disabled (user access enabled). We handle that case here by saving + * and re-locking AMR but we shouldn't get here in the first place, + * hence the warning. + */ + kuap_assert_locked(); + + if (kuap_state != AMR_KUAP_BLOCKED) + set_kuap(AMR_KUAP_BLOCKED); + + replay_soft_interrupts(); + + if (kuap_state != AMR_KUAP_BLOCKED) + set_kuap(kuap_state); +} +#else +#define replay_soft_interrupts_irqrestore() replay_soft_interrupts() +#endif + +notrace void arch_local_irq_restore(unsigned long mask) +{ + unsigned char irq_happened; + + /* Write the new soft-enabled value if it is a disable */ + if (mask) { + irq_soft_mask_set(mask); + return; + } + + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) + WARN_ON_ONCE(in_nmi() || in_hardirq()); + + /* + * After the stb, interrupts are unmasked and there are no interrupts + * pending replay. The restart sequence makes this atomic with + * respect to soft-masked interrupts. If this was just a simple code + * sequence, a soft-masked interrupt could become pending right after + * the comparison and before the stb. + * + * This allows interrupts to be unmasked without hard disabling, and + * also without new hard interrupts coming in ahead of pending ones. + */ + asm_volatile_goto( +"1: \n" +" lbz 9,%0(13) \n" +" cmpwi 9,0 \n" +" bne %l[happened] \n" +" stb 9,%1(13) \n" +"2: \n" + RESTART_TABLE(1b, 2b, 1b) + : : "i" (offsetof(struct paca_struct, irq_happened)), + "i" (offsetof(struct paca_struct, irq_soft_mask)) + : "cr0", "r9" + : happened); + + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) + WARN_ON_ONCE(!(mfmsr() & MSR_EE)); + + return; + +happened: + irq_happened = READ_ONCE(local_paca->irq_happened); + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) + WARN_ON_ONCE(!irq_happened); + + if (irq_happened == PACA_IRQ_HARD_DIS) { + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) + WARN_ON_ONCE(mfmsr() & MSR_EE); + irq_soft_mask_set(IRQS_ENABLED); + local_paca->irq_happened = 0; + __hard_irq_enable(); + return; + } + + /* Have interrupts to replay, need to hard disable first */ + if (!(irq_happened & PACA_IRQ_HARD_DIS)) { + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) { + if (!(mfmsr() & MSR_EE)) { + /* + * An interrupt could have come in and cleared + * MSR[EE] and set IRQ_HARD_DIS, so check + * IRQ_HARD_DIS again and warn if it is still + * clear. + */ + irq_happened = READ_ONCE(local_paca->irq_happened); + WARN_ON_ONCE(!(irq_happened & PACA_IRQ_HARD_DIS)); + } + } + __hard_irq_disable(); + local_paca->irq_happened |= PACA_IRQ_HARD_DIS; + } else { + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) { + if (WARN_ON_ONCE(mfmsr() & MSR_EE)) + __hard_irq_disable(); + } + } + + /* + * Disable preempt here, so that the below preempt_enable will + * perform resched if required (a replayed interrupt may set + * need_resched). + */ + preempt_disable(); + irq_soft_mask_set(IRQS_ALL_DISABLED); + trace_hardirqs_off(); + + replay_soft_interrupts_irqrestore(); + local_paca->irq_happened = 0; + + trace_hardirqs_on(); + irq_soft_mask_set(IRQS_ENABLED); + __hard_irq_enable(); + preempt_enable(); +} +EXPORT_SYMBOL(arch_local_irq_restore); + +/* + * This is a helper to use when about to go into idle low-power + * when the latter has the side effect of re-enabling interrupts + * (such as calling H_CEDE under pHyp). + * + * You call this function with interrupts soft-disabled (this is + * already the case when ppc_md.power_save is called). The function + * will return whether to enter power save or just return. + * + * In the former case, it will have notified lockdep of interrupts + * being re-enabled and generally sanitized the lazy irq state, + * and in the latter case it will leave with interrupts hard + * disabled and marked as such, so the local_irq_enable() call + * in arch_cpu_idle() will properly re-enable everything. + */ +bool prep_irq_for_idle(void) +{ + /* + * First we need to hard disable to ensure no interrupt + * occurs before we effectively enter the low power state + */ + __hard_irq_disable(); + local_paca->irq_happened |= PACA_IRQ_HARD_DIS; + + /* + * If anything happened while we were soft-disabled, + * we return now and do not enter the low power state. + */ + if (lazy_irq_pending()) + return false; + + /* Tell lockdep we are about to re-enable */ + trace_hardirqs_on(); + + /* + * Mark interrupts as soft-enabled and clear the + * PACA_IRQ_HARD_DIS from the pending mask since we + * are about to hard enable as well as a side effect + * of entering the low power state. + */ + local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS; + irq_soft_mask_set(IRQS_ENABLED); + + /* Tell the caller to enter the low power state */ + return true; +} + +#ifdef CONFIG_PPC_BOOK3S +/* + * This is for idle sequences that return with IRQs off, but the + * idle state itself wakes on interrupt. Tell the irq tracer that + * IRQs are enabled for the duration of idle so it does not get long + * off times. Must be paired with fini_irq_for_idle_irqsoff. + */ +bool prep_irq_for_idle_irqsoff(void) +{ + WARN_ON(!irqs_disabled()); + + /* + * First we need to hard disable to ensure no interrupt + * occurs before we effectively enter the low power state + */ + __hard_irq_disable(); + local_paca->irq_happened |= PACA_IRQ_HARD_DIS; + + /* + * If anything happened while we were soft-disabled, + * we return now and do not enter the low power state. + */ + if (lazy_irq_pending()) + return false; + + /* Tell lockdep we are about to re-enable */ + trace_hardirqs_on(); + + return true; +} + +/* + * Take the SRR1 wakeup reason, index into this table to find the + * appropriate irq_happened bit. + * + * Sytem reset exceptions taken in idle state also come through here, + * but they are NMI interrupts so do not need to wait for IRQs to be + * restored, and should be taken as early as practical. These are marked + * with 0xff in the table. The Power ISA specifies 0100b as the system + * reset interrupt reason. + */ +#define IRQ_SYSTEM_RESET 0xff + +static const u8 srr1_to_lazyirq[0x10] = { + 0, 0, 0, + PACA_IRQ_DBELL, + IRQ_SYSTEM_RESET, + PACA_IRQ_DBELL, + PACA_IRQ_DEC, + 0, + PACA_IRQ_EE, + PACA_IRQ_EE, + PACA_IRQ_HMI, + 0, 0, 0, 0, 0 }; + +void replay_system_reset(void) +{ + struct pt_regs regs; + + ppc_save_regs(®s); + regs.trap = 0x100; + get_paca()->in_nmi = 1; + system_reset_exception(®s); + get_paca()->in_nmi = 0; +} +EXPORT_SYMBOL_GPL(replay_system_reset); + +void irq_set_pending_from_srr1(unsigned long srr1) +{ + unsigned int idx = (srr1 & SRR1_WAKEMASK_P8) >> 18; + u8 reason = srr1_to_lazyirq[idx]; + + /* + * Take the system reset now, which is immediately after registers + * are restored from idle. It's an NMI, so interrupts need not be + * re-enabled before it is taken. + */ + if (unlikely(reason == IRQ_SYSTEM_RESET)) { + replay_system_reset(); + return; + } + + if (reason == PACA_IRQ_DBELL) { + /* + * When doorbell triggers a system reset wakeup, the message + * is not cleared, so if the doorbell interrupt is replayed + * and the IPI handled, the doorbell interrupt would still + * fire when EE is enabled. + * + * To avoid taking the superfluous doorbell interrupt, + * execute a msgclr here before the interrupt is replayed. + */ + ppc_msgclr(PPC_DBELL_MSGTYPE); + } + + /* + * The 0 index (SRR1[42:45]=b0000) must always evaluate to 0, + * so this can be called unconditionally with the SRR1 wake + * reason as returned by the idle code, which uses 0 to mean no + * interrupt. + * + * If a future CPU was to designate this as an interrupt reason, + * then a new index for no interrupt must be assigned. + */ + local_paca->irq_happened |= reason; +} +#endif /* CONFIG_PPC_BOOK3S */ + +/* + * Force a replay of the external interrupt handler on this CPU. + */ +void force_external_irq_replay(void) +{ + /* + * This must only be called with interrupts soft-disabled, + * the replay will happen when re-enabling. + */ + WARN_ON(!arch_irqs_disabled()); + + /* + * Interrupts must always be hard disabled before irq_happened is + * modified (to prevent lost update in case of interrupt between + * load and store). + */ + __hard_irq_disable(); + local_paca->irq_happened |= PACA_IRQ_HARD_DIS; + + /* Indicate in the PACA that we have an interrupt to replay */ + local_paca->irq_happened |= PACA_IRQ_EE; +} + +static int __init setup_noirqdistrib(char *str) +{ + distribute_irqs = 0; + return 1; +} + +__setup("noirqdistrib", setup_noirqdistrib); diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index 1c97c0f177ae..912d4f8a13be 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -269,7 +269,7 @@ static int try_to_emulate(struct kprobe *p, struct pt_regs *regs) * So, we should never get here... but, its still * good to catch them, just in case... */ - printk("Can't step on instruction %s\n", ppc_inst_as_str(insn)); + printk("Can't step on instruction %08lx\n", ppc_inst_as_ulong(insn)); BUG(); } else { /* diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c index 18173199b79d..6c5d30fba766 100644 --- a/arch/powerpc/kernel/mce.c +++ b/arch/powerpc/kernel/mce.c @@ -756,7 +756,7 @@ void __init mce_init(void) mce_info = memblock_alloc_try_nid(sizeof(*mce_info), __alignof__(*mce_info), MEMBLOCK_LOW_LIMIT, - limit, cpu_to_node(i)); + limit, early_cpu_to_node(i)); if (!mce_info) goto err; paca_ptrs[i]->mce_info = mce_info; diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 068410cd54a3..bdd3332200c5 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -39,6 +39,7 @@ #include <asm/machdep.h> #include <asm/ppc-pci.h> #include <asm/eeh.h> +#include <asm/setup.h> #include "../../../drivers/pci/pci.h" @@ -74,16 +75,32 @@ void __init set_pci_dma_ops(const struct dma_map_ops *dma_ops) static int get_phb_number(struct device_node *dn) { int ret, phb_id = -1; - u32 prop_32; u64 prop; /* * Try fixed PHB numbering first, by checking archs and reading - * the respective device-tree properties. Firstly, try powernv by - * reading "ibm,opal-phbid", only present in OPAL environment. + * the respective device-tree properties. Firstly, try reading + * standard "linux,pci-domain", then try reading "ibm,opal-phbid" + * (only present in powernv OPAL environment), then try device-tree + * alias and as the last try to use lower bits of "reg" property. */ - ret = of_property_read_u64(dn, "ibm,opal-phbid", &prop); + ret = of_get_pci_domain_nr(dn); + if (ret >= 0) { + prop = ret; + ret = 0; + } + if (ret) + ret = of_property_read_u64(dn, "ibm,opal-phbid", &prop); + if (ret) { + ret = of_alias_get_id(dn, "pci"); + if (ret >= 0) { + prop = ret; + ret = 0; + } + } + if (ret) { + u32 prop_32; ret = of_property_read_u32_index(dn, "reg", 1, &prop_32); prop = prop_32; } @@ -95,10 +112,7 @@ static int get_phb_number(struct device_node *dn) if ((phb_id >= 0) && !test_and_set_bit(phb_id, phb_bitmap)) return phb_id; - /* - * If not pseries nor powernv, or if fixed PHB numbering tried to add - * the same PHB number twice, then fallback to dynamic PHB numbering. - */ + /* If everything fails then fallback to dynamic PHB numbering. */ phb_id = find_first_zero_bit(phb_bitmap, MAX_PHBS); BUG_ON(phb_id >= MAX_PHBS); set_bit(phb_id, phb_bitmap); @@ -1087,7 +1101,7 @@ void pcibios_fixup_bus(struct pci_bus *bus) */ pci_read_bridge_bases(bus); - /* Now fixup the bus bus */ + /* Now fixup the bus */ pcibios_setup_bus_self(bus); } EXPORT_SYMBOL(pcibios_fixup_bus); diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index 5a174936c9a0..433965bf37b4 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -36,18 +36,13 @@ int pcibios_assign_bus_offset = 1; EXPORT_SYMBOL(isa_io_base); EXPORT_SYMBOL(pci_dram_offset); -void __init pcibios_make_OF_bus_map(void); - static void fixup_cpc710_pci64(struct pci_dev* dev); -static u8* pci_to_OF_bus_map; /* By default, we don't re-assign bus numbers. We do this only on * some pmacs */ static int pci_assign_all_buses; -static int pci_bus_count; - /* This will remain NULL for now, until isa-bridge.c is made common * to both 32-bit and 64-bit. */ @@ -67,6 +62,11 @@ fixup_cpc710_pci64(struct pci_dev* dev) } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_CPC710_PCI64, fixup_cpc710_pci64); +#if defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_CHRP) + +static u8* pci_to_OF_bus_map; +static int pci_bus_count; + /* * Functions below are used on OpenFirmware machines. */ @@ -108,7 +108,7 @@ make_one_node_map(struct device_node* node, u8 pci_bus) } } -void __init +static void __init pcibios_make_OF_bus_map(void) { int i; @@ -154,6 +154,7 @@ pcibios_make_OF_bus_map(void) } +#ifdef CONFIG_PPC_PMAC /* * Returns the PCI device matching a given OF node */ @@ -193,7 +194,9 @@ int pci_device_from_OF_node(struct device_node *node, u8 *bus, u8 *devfn) return -ENODEV; } EXPORT_SYMBOL(pci_device_from_OF_node); +#endif +#ifdef CONFIG_PPC_CHRP /* We create the "pci-OF-bus-map" property now so it appears in the * /proc device tree */ @@ -218,6 +221,9 @@ pci_create_OF_bus_map(void) of_node_put(dn); } } +#endif + +#endif /* defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_CHRP) */ void pcibios_setup_phb_io_space(struct pci_controller *hose) { @@ -233,7 +239,9 @@ void pcibios_setup_phb_io_space(struct pci_controller *hose) static int __init pcibios_init(void) { struct pci_controller *hose, *tmp; +#ifndef CONFIG_PPC_PCI_BUS_NUM_DOMAIN_DEPENDENT int next_busno = 0; +#endif printk(KERN_INFO "PCI: Probing PCI hardware\n"); @@ -242,14 +250,20 @@ static int __init pcibios_init(void) /* Scan all of the recorded PCI controllers. */ list_for_each_entry_safe(hose, tmp, &hose_list, list_node) { +#ifndef CONFIG_PPC_PCI_BUS_NUM_DOMAIN_DEPENDENT if (pci_assign_all_buses) hose->first_busno = next_busno; +#endif hose->last_busno = 0xff; pcibios_scan_phb(hose); pci_bus_add_devices(hose->bus); +#ifndef CONFIG_PPC_PCI_BUS_NUM_DOMAIN_DEPENDENT if (pci_assign_all_buses || next_busno <= hose->last_busno) next_busno = hose->last_busno + pcibios_assign_bus_offset; +#endif } + +#if defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_CHRP) pci_bus_count = next_busno; /* OpenFirmware based machines need a map of OF bus @@ -258,6 +272,7 @@ static int __init pcibios_init(void) */ if (pci_assign_all_buses) pcibios_make_OF_bus_map(); +#endif /* Call common code to handle resource allocation */ pcibios_resource_survey(); diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index 19b03ddf5631..0c7cfb9fab04 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -286,6 +286,7 @@ int pcibus_to_node(struct pci_bus *bus) EXPORT_SYMBOL(pcibus_to_node); #endif +#ifdef CONFIG_PPC_PMAC int pci_device_from_OF_node(struct device_node *np, u8 *bus, u8 *devfn) { if (!PCI_DN(np)) @@ -294,3 +295,4 @@ int pci_device_from_OF_node(struct device_node *np, u8 *bus, u8 *devfn) *devfn = PCI_DN(np)->devfn; return 0; } +#endif diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c index 938ab8838ab5..7a35fc25a304 100644 --- a/arch/powerpc/kernel/pci_dn.c +++ b/arch/powerpc/kernel/pci_dn.c @@ -259,7 +259,7 @@ void remove_sriov_vf_pdns(struct pci_dev *pdev) if (edev) { /* * We allocate pci_dn's for the totalvfs count, - * but only only the vfs that were activated + * but only the vfs that were activated * have a configured PE. */ if (edev->pe) diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index feae8509b59c..a730b951b64b 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -44,7 +44,7 @@ #include <asm/iommu.h> #include <asm/btext.h> #include <asm/sections.h> -#include <asm/machdep.h> +#include <asm/setup.h> #include <asm/pci-bridge.h> #include <asm/kexec.h> #include <asm/opal.h> @@ -54,6 +54,7 @@ #include <asm/dt_cpu_ftrs.h> #include <asm/drmem.h> #include <asm/ultravisor.h> +#include <asm/prom.h> #include <mm/mmu_decl.h> @@ -751,6 +752,13 @@ void __init early_init_devtree(void *params) early_init_dt_scan_root(); early_init_dt_scan_memory_ppc(); + /* + * As generic code authors expect to be able to use static keys + * in early_param() handlers, we initialize the static keys just + * before parsing early params (it's fine to call jump_label_init() + * more than once). + */ + jump_label_init(); parse_early_param(); /* make sure we've parsed cmdline for mem= before this */ diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 13d6cb188835..a6669c40c1db 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -42,7 +42,7 @@ #include <asm/iommu.h> #include <asm/btext.h> #include <asm/sections.h> -#include <asm/machdep.h> +#include <asm/setup.h> #include <asm/asm-prototypes.h> #include <asm/ultravisor-api.h> diff --git a/arch/powerpc/kernel/ptrace/ptrace-vsx.c b/arch/powerpc/kernel/ptrace/ptrace-vsx.c index 1da4303128ef..7df08004c47d 100644 --- a/arch/powerpc/kernel/ptrace/ptrace-vsx.c +++ b/arch/powerpc/kernel/ptrace/ptrace-vsx.c @@ -71,7 +71,7 @@ int fpr_set(struct task_struct *target, const struct user_regset *regset, } /* - * Currently to set and and get all the vsx state, you need to call + * Currently to set and get all the vsx state, you need to call * the fp and VMX calls as well. This only get/sets the lower 32 * 128bit VSX registers. */ diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 5761f08dae95..2b2d0b0fbb30 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -113,7 +113,6 @@ void __init setup_tlb_core_data(void) * Should we panic instead? */ WARN_ONCE(smt_enabled_at_boot >= 2 && - !mmu_has_feature(MMU_FTR_USE_TLBRSRV) && book3e_htw_mode != PPC_HTW_E6500, "%s: unsupported MMU configuration\n", __func__); } diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 472596a109e2..86bb5bb4c143 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -377,9 +377,12 @@ static long notrace __unsafe_restore_sigcontext(struct task_struct *tsk, sigset_ unsafe_get_user(set->sig[0], &sc->oldmask, efault_out); /* - * Force reload of FP/VEC. - * This has to be done before copying stuff into tsk->thread.fpr/vr - * for the reasons explained in the previous comment. + * Force reload of FP/VEC/VSX so userspace sees any changes. + * Clear these bits from the user process' MSR before copying into the + * thread struct. If we are rescheduled or preempted and another task + * uses FP/VEC/VSX, and this process has the MSR bits set, then the + * context switch code will save the current CPU state into the + * thread_struct - possibly overwriting the data we are updating here. */ regs_set_return_msr(regs, regs->msr & ~(MSR_FP | MSR_FE0 | MSR_FE1 | MSR_VEC | MSR_VSX)); diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index bcefab484ea6..6b850c157a62 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -35,6 +35,7 @@ #include <linux/stackprotector.h> #include <linux/pgtable.h> #include <linux/clockchips.h> +#include <linux/kexec.h> #include <asm/ptrace.h> #include <linux/atomic.h> @@ -55,7 +56,6 @@ #endif #include <asm/vdso.h> #include <asm/debug.h> -#include <asm/kexec.h> #include <asm/cpu_has_feature.h> #include <asm/ftrace.h> #include <asm/kup.h> @@ -619,20 +619,6 @@ void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *)) } #endif -#ifdef CONFIG_NMI_IPI -static void crash_stop_this_cpu(struct pt_regs *regs) -#else -static void crash_stop_this_cpu(void *dummy) -#endif -{ - /* - * Just busy wait here and avoid marking CPU as offline to ensure - * register data is captured appropriately. - */ - while (1) - cpu_relax(); -} - void crash_smp_send_stop(void) { static bool stopped = false; @@ -651,11 +637,14 @@ void crash_smp_send_stop(void) stopped = true; -#ifdef CONFIG_NMI_IPI - smp_send_nmi_ipi(NMI_IPI_ALL_OTHERS, crash_stop_this_cpu, 1000000); -#else - smp_call_function(crash_stop_this_cpu, NULL, 0); -#endif /* CONFIG_NMI_IPI */ +#ifdef CONFIG_KEXEC_CORE + if (kexec_crash_image) { + crash_kexec_prepare(); + return; + } +#endif + + smp_send_stop(); } #ifdef CONFIG_NMI_IPI diff --git a/arch/powerpc/kernel/syscall.c b/arch/powerpc/kernel/syscall.c new file mode 100644 index 000000000000..81ace9e8b72b --- /dev/null +++ b/arch/powerpc/kernel/syscall.c @@ -0,0 +1,190 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include <linux/compat.h> +#include <linux/context_tracking.h> +#include <linux/randomize_kstack.h> + +#include <asm/interrupt.h> +#include <asm/kup.h> +#include <asm/syscall.h> +#include <asm/time.h> +#include <asm/tm.h> +#include <asm/unistd.h> + + +typedef long (*syscall_fn)(long, long, long, long, long, long); + +/* Has to run notrace because it is entered not completely "reconciled" */ +notrace long system_call_exception(long r3, long r4, long r5, + long r6, long r7, long r8, + unsigned long r0, struct pt_regs *regs) +{ + long ret; + syscall_fn f; + + kuap_lock(); + + add_random_kstack_offset(); + regs->orig_gpr3 = r3; + + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) + BUG_ON(irq_soft_mask_return() != IRQS_ALL_DISABLED); + + trace_hardirqs_off(); /* finish reconciling */ + + CT_WARN_ON(ct_state() == CONTEXT_KERNEL); + user_exit_irqoff(); + + BUG_ON(regs_is_unrecoverable(regs)); + BUG_ON(!(regs->msr & MSR_PR)); + BUG_ON(arch_irq_disabled_regs(regs)); + +#ifdef CONFIG_PPC_PKEY + if (mmu_has_feature(MMU_FTR_PKEY)) { + unsigned long amr, iamr; + bool flush_needed = false; + /* + * When entering from userspace we mostly have the AMR/IAMR + * different from kernel default values. Hence don't compare. + */ + amr = mfspr(SPRN_AMR); + iamr = mfspr(SPRN_IAMR); + regs->amr = amr; + regs->iamr = iamr; + if (mmu_has_feature(MMU_FTR_BOOK3S_KUAP)) { + mtspr(SPRN_AMR, AMR_KUAP_BLOCKED); + flush_needed = true; + } + if (mmu_has_feature(MMU_FTR_BOOK3S_KUEP)) { + mtspr(SPRN_IAMR, AMR_KUEP_BLOCKED); + flush_needed = true; + } + if (flush_needed) + isync(); + } else +#endif + kuap_assert_locked(); + + booke_restore_dbcr0(); + + account_cpu_user_entry(); + + account_stolen_time(); + + /* + * This is not required for the syscall exit path, but makes the + * stack frame look nicer. If this was initialised in the first stack + * frame, or if the unwinder was taught the first stack frame always + * returns to user with IRQS_ENABLED, this store could be avoided! + */ + irq_soft_mask_regs_set_state(regs, IRQS_ENABLED); + + /* + * If system call is called with TM active, set _TIF_RESTOREALL to + * prevent RFSCV being used to return to userspace, because POWER9 + * TM implementation has problems with this instruction returning to + * transactional state. Final register values are not relevant because + * the transaction will be aborted upon return anyway. Or in the case + * of unsupported_scv SIGILL fault, the return state does not much + * matter because it's an edge case. + */ + if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) && + unlikely(MSR_TM_TRANSACTIONAL(regs->msr))) + set_bits(_TIF_RESTOREALL, ¤t_thread_info()->flags); + + /* + * If the system call was made with a transaction active, doom it and + * return without performing the system call. Unless it was an + * unsupported scv vector, in which case it's treated like an illegal + * instruction. + */ +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (unlikely(MSR_TM_TRANSACTIONAL(regs->msr)) && + !trap_is_unsupported_scv(regs)) { + /* Enable TM in the kernel, and disable EE (for scv) */ + hard_irq_disable(); + mtmsr(mfmsr() | MSR_TM); + + /* tabort, this dooms the transaction, nothing else */ + asm volatile(".long 0x7c00071d | ((%0) << 16)" + :: "r"(TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT)); + + /* + * Userspace will never see the return value. Execution will + * resume after the tbegin. of the aborted transaction with the + * checkpointed register state. A context switch could occur + * or signal delivered to the process before resuming the + * doomed transaction context, but that should all be handled + * as expected. + */ + return -ENOSYS; + } +#endif // CONFIG_PPC_TRANSACTIONAL_MEM + + local_irq_enable(); + + if (unlikely(read_thread_flags() & _TIF_SYSCALL_DOTRACE)) { + if (unlikely(trap_is_unsupported_scv(regs))) { + /* Unsupported scv vector */ + _exception(SIGILL, regs, ILL_ILLOPC, regs->nip); + return regs->gpr[3]; + } + /* + * We use the return value of do_syscall_trace_enter() as the + * syscall number. If the syscall was rejected for any reason + * do_syscall_trace_enter() returns an invalid syscall number + * and the test against NR_syscalls will fail and the return + * value to be used is in regs->gpr[3]. + */ + r0 = do_syscall_trace_enter(regs); + if (unlikely(r0 >= NR_syscalls)) + return regs->gpr[3]; + r3 = regs->gpr[3]; + r4 = regs->gpr[4]; + r5 = regs->gpr[5]; + r6 = regs->gpr[6]; + r7 = regs->gpr[7]; + r8 = regs->gpr[8]; + + } else if (unlikely(r0 >= NR_syscalls)) { + if (unlikely(trap_is_unsupported_scv(regs))) { + /* Unsupported scv vector */ + _exception(SIGILL, regs, ILL_ILLOPC, regs->nip); + return regs->gpr[3]; + } + return -ENOSYS; + } + + /* May be faster to do array_index_nospec? */ + barrier_nospec(); + + if (unlikely(is_compat_task())) { + f = (void *)compat_sys_call_table[r0]; + + r3 &= 0x00000000ffffffffULL; + r4 &= 0x00000000ffffffffULL; + r5 &= 0x00000000ffffffffULL; + r6 &= 0x00000000ffffffffULL; + r7 &= 0x00000000ffffffffULL; + r8 &= 0x00000000ffffffffULL; + + } else { + f = (void *)sys_call_table[r0]; + } + + ret = f(r3, r4, r5, r6, r7, r8); + + /* + * Ultimately, this value will get limited by KSTACK_OFFSET_MAX(), + * so the maximum stack offset is 1k bytes (10 bits). + * + * The actual entropy will be further reduced by the compiler when + * applying stack alignment constraints: the powerpc architecture + * may have two kinds of stack alignment (16-bytes and 8-bytes). + * + * So the resulting 6 or 7 bits of entropy is seen in SP[9:4] or SP[9:3]. + */ + choose_random_kstack_offset(mftb()); + + return ret; +} diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c index 2a893e06e4f1..cb158c32b50b 100644 --- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -69,8 +69,8 @@ ftrace_modify_code(unsigned long ip, ppc_inst_t old, ppc_inst_t new) /* Make sure it is what we expect it to be */ if (!ppc_inst_equal(replaced, old)) { - pr_err("%p: replaced (%s) != old (%s)", - (void *)ip, ppc_inst_as_str(replaced), ppc_inst_as_str(old)); + pr_err("%p: replaced (%08lx) != old (%08lx)", (void *)ip, + ppc_inst_as_ulong(replaced), ppc_inst_as_ulong(old)); return -EINVAL; } @@ -125,9 +125,9 @@ __ftrace_make_nop(struct module *mod, return -EFAULT; } - /* Make sure that that this is still a 24bit jump */ + /* Make sure that this is still a 24bit jump */ if (!is_bl_op(op)) { - pr_err("Not expected bl: opcode is %s\n", ppc_inst_as_str(op)); + pr_err("Not expected bl: opcode is %08lx\n", ppc_inst_as_ulong(op)); return -EINVAL; } @@ -159,8 +159,8 @@ __ftrace_make_nop(struct module *mod, /* We expect either a mflr r0, or a std r0, LRSAVE(r1) */ if (!ppc_inst_equal(op, ppc_inst(PPC_RAW_MFLR(_R0))) && !ppc_inst_equal(op, ppc_inst(PPC_INST_STD_LR))) { - pr_err("Unexpected instruction %s around bl _mcount\n", - ppc_inst_as_str(op)); + pr_err("Unexpected instruction %08lx around bl _mcount\n", + ppc_inst_as_ulong(op)); return -EINVAL; } } else if (IS_ENABLED(CONFIG_PPC64)) { @@ -174,7 +174,8 @@ __ftrace_make_nop(struct module *mod, } if (!ppc_inst_equal(op, ppc_inst(PPC_INST_LD_TOC))) { - pr_err("Expected %08lx found %s\n", PPC_INST_LD_TOC, ppc_inst_as_str(op)); + pr_err("Expected %08lx found %08lx\n", PPC_INST_LD_TOC, + ppc_inst_as_ulong(op)); return -EINVAL; } } @@ -310,9 +311,9 @@ static int __ftrace_make_nop_kernel(struct dyn_ftrace *rec, unsigned long addr) return -EFAULT; } - /* Make sure that that this is still a 24bit jump */ + /* Make sure that this is still a 24bit jump */ if (!is_bl_op(op)) { - pr_err("Not expected bl: opcode is %s\n", ppc_inst_as_str(op)); + pr_err("Not expected bl: opcode is %08lx\n", ppc_inst_as_ulong(op)); return -EINVAL; } @@ -416,8 +417,8 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) return -EFAULT; if (!expected_nop_sequence(ip, op[0], op[1])) { - pr_err("Unexpected call sequence at %p: %s %s\n", - ip, ppc_inst_as_str(op[0]), ppc_inst_as_str(op[1])); + pr_err("Unexpected call sequence at %p: %08lx %08lx\n", ip, + ppc_inst_as_ulong(op[0]), ppc_inst_as_ulong(op[1])); return -EINVAL; } @@ -486,7 +487,8 @@ static int __ftrace_make_call_kernel(struct dyn_ftrace *rec, unsigned long addr) } if (!ppc_inst_equal(op, ppc_inst(PPC_RAW_NOP()))) { - pr_err("Unexpected call sequence at %p: %s\n", ip, ppc_inst_as_str(op)); + pr_err("Unexpected call sequence at %p: %08lx\n", + ip, ppc_inst_as_ulong(op)); return -EINVAL; } @@ -562,9 +564,9 @@ __ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, return -EFAULT; } - /* Make sure that that this is still a 24bit jump */ + /* Make sure that this is still a 24bit jump */ if (!is_bl_op(op)) { - pr_err("Not expected bl: opcode is %s\n", ppc_inst_as_str(op)); + pr_err("Not expected bl: opcode is %08lx\n", ppc_inst_as_ulong(op)); return -EINVAL; } diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 3aaa50e5c72f..dadfcef5d6db 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -1676,7 +1676,7 @@ DEFINE_INTERRUPT_HANDLER(vsx_unavailable_exception) die("Unrecoverable VSX Unavailable Exception", regs, SIGABRT); } -#ifdef CONFIG_PPC64 +#ifdef CONFIG_PPC_BOOK3S_64 static void tm_unavailable(struct pt_regs *regs) { #ifdef CONFIG_PPC_TRANSACTIONAL_MEM diff --git a/arch/powerpc/kernel/vdso/cacheflush.S b/arch/powerpc/kernel/vdso/cacheflush.S index d4e43ab2d5df..0085ae464dac 100644 --- a/arch/powerpc/kernel/vdso/cacheflush.S +++ b/arch/powerpc/kernel/vdso/cacheflush.S @@ -91,6 +91,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) 3: crclr cr0*4+so sync + icbi 0,r1 isync li r3,0 blr diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index 7d28b9553654..dbcc4a793f0b 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -91,6 +91,10 @@ static cpumask_t wd_smp_cpus_pending; static cpumask_t wd_smp_cpus_stuck; static u64 wd_smp_last_reset_tb; +#ifdef CONFIG_PPC_PSERIES +static u64 wd_timeout_pct; +#endif + /* * Try to take the exclusive watchdog action / NMI IPI / printing lock. * wd_smp_lock must be held. If this fails, we should return and wait @@ -353,7 +357,7 @@ static void watchdog_timer_interrupt(int cpu) if (__wd_nmi_output && xchg(&__wd_nmi_output, 0)) { /* * Something has called printk from NMI context. It might be - * stuck, so this this triggers a flush that will get that + * stuck, so this triggers a flush that will get that * printk output to the console. * * See wd_lockup_ipi. @@ -527,7 +531,13 @@ static int stop_watchdog_on_cpu(unsigned int cpu) static void watchdog_calc_timeouts(void) { - wd_panic_timeout_tb = watchdog_thresh * ppc_tb_freq; + u64 threshold = watchdog_thresh; + +#ifdef CONFIG_PPC_PSERIES + threshold += (READ_ONCE(wd_timeout_pct) * threshold) / 100; +#endif + + wd_panic_timeout_tb = threshold * ppc_tb_freq; /* Have the SMP detector trigger a bit later */ wd_smp_panic_timeout_tb = wd_panic_timeout_tb * 3 / 2; @@ -570,3 +580,12 @@ int __init watchdog_nmi_probe(void) } return 0; } + +#ifdef CONFIG_PPC_PSERIES +void watchdog_nmi_set_timeout_pct(u64 pct) +{ + pr_info("Set the NMI watchdog timeout factor to %llu%%\n", pct); + WRITE_ONCE(wd_timeout_pct, pct); + lockup_detector_reconfigure(); +} +#endif |