diff options
Diffstat (limited to 'arch/powerpc')
27 files changed, 159 insertions, 68 deletions
diff --git a/arch/powerpc/include/asm/cache.h b/arch/powerpc/include/asm/cache.h index b3388d95f451..45e3137ccd71 100644 --- a/arch/powerpc/include/asm/cache.h +++ b/arch/powerpc/include/asm/cache.h @@ -107,22 +107,22 @@ extern void _set_L3CR(unsigned long); static inline void dcbz(void *addr) { - __asm__ __volatile__ ("dcbz %y0" : : "Z"(*(u8 *)addr) : "memory"); + __asm__ __volatile__ ("dcbz 0, %0" : : "r"(addr) : "memory"); } static inline void dcbi(void *addr) { - __asm__ __volatile__ ("dcbi %y0" : : "Z"(*(u8 *)addr) : "memory"); + __asm__ __volatile__ ("dcbi 0, %0" : : "r"(addr) : "memory"); } static inline void dcbf(void *addr) { - __asm__ __volatile__ ("dcbf %y0" : : "Z"(*(u8 *)addr) : "memory"); + __asm__ __volatile__ ("dcbf 0, %0" : : "r"(addr) : "memory"); } static inline void dcbst(void *addr) { - __asm__ __volatile__ ("dcbst %y0" : : "Z"(*(u8 *)addr) : "memory"); + __asm__ __volatile__ ("dcbst 0, %0" : : "r"(addr) : "memory"); } #endif /* !__ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index 463c63a9fcf1..11112023e327 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -302,9 +302,14 @@ #define H_SCM_UNBIND_MEM 0x3F0 #define H_SCM_QUERY_BLOCK_MEM_BINDING 0x3F4 #define H_SCM_QUERY_LOGICAL_MEM_BINDING 0x3F8 -#define H_SCM_MEM_QUERY 0x3FC -#define H_SCM_BLOCK_CLEAR 0x400 -#define MAX_HCALL_OPCODE H_SCM_BLOCK_CLEAR +#define H_SCM_UNBIND_ALL 0x3FC +#define H_SCM_HEALTH 0x400 +#define H_SCM_PERFORMANCE_STATS 0x418 +#define MAX_HCALL_OPCODE H_SCM_PERFORMANCE_STATS + +/* Scope args for H_SCM_UNBIND_ALL */ +#define H_UNBIND_SCOPE_ALL (0x1) +#define H_UNBIND_SCOPE_DRC (0x2) /* H_VIOCTL functions */ #define H_GET_VIOA_DUMP_SIZE 0x01 diff --git a/arch/powerpc/include/asm/pmc.h b/arch/powerpc/include/asm/pmc.h index dc9a1ca70edf..c6bbe9778d3c 100644 --- a/arch/powerpc/include/asm/pmc.h +++ b/arch/powerpc/include/asm/pmc.h @@ -27,11 +27,10 @@ static inline void ppc_set_pmu_inuse(int inuse) #ifdef CONFIG_PPC_PSERIES get_lppaca()->pmcregs_in_use = inuse; #endif - } else { + } #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE - get_paca()->pmcregs_in_use = inuse; + get_paca()->pmcregs_in_use = inuse; #endif - } #endif } diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index 68473c3c471c..b0720c7c3fcf 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -49,6 +49,7 @@ #define __ARCH_WANT_SYS_FORK #define __ARCH_WANT_SYS_VFORK #define __ARCH_WANT_SYS_CLONE +#define __ARCH_WANT_SYS_CLONE3 #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_UNISTD_H_ */ diff --git a/arch/powerpc/include/uapi/asm/bpf_perf_event.h b/arch/powerpc/include/uapi/asm/bpf_perf_event.h index b551b741653d..5e1e648aeec4 100644 --- a/arch/powerpc/include/uapi/asm/bpf_perf_event.h +++ b/arch/powerpc/include/uapi/asm/bpf_perf_event.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__ASM_BPF_PERF_EVENT_H__ #define _UAPI__ASM_BPF_PERF_EVENT_H__ diff --git a/arch/powerpc/include/uapi/asm/kvm_para.h b/arch/powerpc/include/uapi/asm/kvm_para.h index 01555c6ae0f5..be48c2215fa2 100644 --- a/arch/powerpc/include/uapi/asm/kvm_para.h +++ b/arch/powerpc/include/uapi/asm/kvm_para.h @@ -31,7 +31,7 @@ * Struct fields are always 32 or 64 bit aligned, depending on them being 32 * or 64 bit wide respectively. * - * See Documentation/virtual/kvm/ppc-pv.txt + * See Documentation/virt/kvm/ppc-pv.txt */ struct kvm_vcpu_arch_shared { __u64 scratch1; diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c index 7107ad86de65..92045ed64976 100644 --- a/arch/powerpc/kernel/align.c +++ b/arch/powerpc/kernel/align.c @@ -176,9 +176,11 @@ static int emulate_spe(struct pt_regs *regs, unsigned int reg, ret |= __get_user_inatomic(temp.v[1], p++); ret |= __get_user_inatomic(temp.v[2], p++); ret |= __get_user_inatomic(temp.v[3], p++); + /* fall through */ case 4: ret |= __get_user_inatomic(temp.v[4], p++); ret |= __get_user_inatomic(temp.v[5], p++); + /* fall through */ case 2: ret |= __get_user_inatomic(temp.v[6], p++); ret |= __get_user_inatomic(temp.v[7], p++); @@ -259,9 +261,11 @@ static int emulate_spe(struct pt_regs *regs, unsigned int reg, ret |= __put_user_inatomic(data.v[1], p++); ret |= __put_user_inatomic(data.v[2], p++); ret |= __put_user_inatomic(data.v[3], p++); + /* fall through */ case 4: ret |= __put_user_inatomic(data.v[4], p++); ret |= __put_user_inatomic(data.v[5], p++); + /* fall through */ case 2: ret |= __put_user_inatomic(data.v[6], p++); ret |= __put_user_inatomic(data.v[7], p++); diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 85fdb6d879f1..54fab22c9a43 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -597,6 +597,14 @@ ppc_clone: stw r0,_TRAP(r1) /* register set saved */ b sys_clone + .globl ppc_clone3 +ppc_clone3: + SAVE_NVGPRS(r1) + lwz r0,_TRAP(r1) + rlwinm r0,r0,0,0,30 /* clear LSB to indicate full */ + stw r0,_TRAP(r1) /* register set saved */ + b sys_clone3 + .globl ppc_swapcontext ppc_swapcontext: SAVE_NVGPRS(r1) diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index d9105fcf4021..0a0b5310f54a 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -487,6 +487,11 @@ _GLOBAL(ppc_clone) bl sys_clone b .Lsyscall_exit +_GLOBAL(ppc_clone3) + bl save_nvgprs + bl sys_clone3 + b .Lsyscall_exit + _GLOBAL(ppc32_swapcontext) bl save_nvgprs bl compat_sys_swapcontext diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index eee5bef736c8..6ba3cc2ef8ab 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1531,7 +1531,7 @@ EXC_COMMON(trap_0b_common, 0xb00, unknown_exception) * * Call convention: * - * syscall register convention is in Documentation/powerpc/syscall64-abi.txt + * syscall register convention is in Documentation/powerpc/syscall64-abi.rst * * For hypercalls, the register convention is as follows: * r0 volatile diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 8fc4de0d22b4..7a84c9f1778e 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -101,21 +101,8 @@ static void check_if_tm_restore_required(struct task_struct *tsk) } } -static bool tm_active_with_fp(struct task_struct *tsk) -{ - return MSR_TM_ACTIVE(tsk->thread.regs->msr) && - (tsk->thread.ckpt_regs.msr & MSR_FP); -} - -static bool tm_active_with_altivec(struct task_struct *tsk) -{ - return MSR_TM_ACTIVE(tsk->thread.regs->msr) && - (tsk->thread.ckpt_regs.msr & MSR_VEC); -} #else static inline void check_if_tm_restore_required(struct task_struct *tsk) { } -static inline bool tm_active_with_fp(struct task_struct *tsk) { return false; } -static inline bool tm_active_with_altivec(struct task_struct *tsk) { return false; } #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ bool strict_msr_control; @@ -252,7 +239,7 @@ EXPORT_SYMBOL(enable_kernel_fp); static int restore_fp(struct task_struct *tsk) { - if (tsk->thread.load_fp || tm_active_with_fp(tsk)) { + if (tsk->thread.load_fp) { load_fp_state(¤t->thread.fp_state); current->thread.load_fp++; return 1; @@ -334,8 +321,7 @@ EXPORT_SYMBOL_GPL(flush_altivec_to_thread); static int restore_altivec(struct task_struct *tsk) { - if (cpu_has_feature(CPU_FTR_ALTIVEC) && - (tsk->thread.load_vec || tm_active_with_altivec(tsk))) { + if (cpu_has_feature(CPU_FTR_ALTIVEC) && (tsk->thread.load_vec)) { load_vr_state(&tsk->thread.vr_state); tsk->thread.used_vr = 1; tsk->thread.load_vec++; @@ -497,13 +483,14 @@ void giveup_all(struct task_struct *tsk) if (!tsk->thread.regs) return; + check_if_tm_restore_required(tsk); + usermsr = tsk->thread.regs->msr; if ((usermsr & msr_all_available) == 0) return; msr_check_and_set(msr_all_available); - check_if_tm_restore_required(tsk); WARN_ON((usermsr & MSR_VSX) && !((usermsr & MSR_FP) && (usermsr & MSR_VEC))); diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index f50b708d6d77..98600b276f76 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -1198,6 +1198,9 @@ SYSCALL_DEFINE0(rt_sigreturn) goto bad; if (MSR_TM_ACTIVE(msr_hi<<32)) { + /* Trying to start TM on non TM system */ + if (!cpu_has_feature(CPU_FTR_TM)) + goto bad; /* We only recheckpoint on return if we're * transaction. */ diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 2f80e270c7b0..117515564ec7 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -771,6 +771,11 @@ SYSCALL_DEFINE0(rt_sigreturn) if (MSR_TM_ACTIVE(msr)) { /* We recheckpoint on return. */ struct ucontext __user *uc_transact; + + /* Trying to start TM on non TM system */ + if (!cpu_has_feature(CPU_FTR_TM)) + goto badframe; + if (__get_user(uc_transact, &uc->uc_link)) goto badframe; if (restore_tm_sigcontexts(current, &uc->uc_mcontext, diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 3331749aab20..43f736ed47f2 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -516,4 +516,4 @@ 432 common fsmount sys_fsmount 433 common fspick sys_fspick 434 common pidfd_open sys_pidfd_open -# 435 reserved for clone3 +435 nospu clone3 ppc_clone3 diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c index 653936177857..18f244aad7aa 100644 --- a/arch/powerpc/kvm/book3s_32_mmu.c +++ b/arch/powerpc/kvm/book3s_32_mmu.c @@ -239,6 +239,7 @@ static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr, case 2: case 6: pte->may_write = true; + /* fall through */ case 3: case 5: case 7: diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index e99a14798ab0..c4b606fe73eb 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -660,8 +660,10 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu, } tce = be64_to_cpu(tce); - if (kvmppc_tce_to_ua(vcpu->kvm, tce, &ua)) - return H_PARAMETER; + if (kvmppc_tce_to_ua(vcpu->kvm, tce, &ua)) { + ret = H_PARAMETER; + goto unlock_exit; + } list_for_each_entry_lockless(stit, &stt->iommu_tables, next) { ret = kvmppc_tce_iommu_map(vcpu->kvm, stt, diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c index f50bbeedfc66..b4f20f13b860 100644 --- a/arch/powerpc/kvm/book3s_64_vio_hv.c +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c @@ -556,8 +556,10 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu, unsigned long tce = be64_to_cpu(((u64 *)tces)[i]); ua = 0; - if (kvmppc_rm_tce_to_ua(vcpu->kvm, tce, &ua, NULL)) - return H_PARAMETER; + if (kvmppc_rm_tce_to_ua(vcpu->kvm, tce, &ua, NULL)) { + ret = H_PARAMETER; + goto unlock_exit; + } list_for_each_entry_lockless(stit, &stt->iommu_tables, next) { ret = kvmppc_rm_tce_iommu_map(vcpu->kvm, stt, diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index ec1804f822af..cde3f5a4b3e4 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -3569,9 +3569,18 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, mtspr(SPRN_DEC, vcpu->arch.dec_expires - mftb()); if (kvmhv_on_pseries()) { + /* + * We need to save and restore the guest visible part of the + * psscr (i.e. using SPRN_PSSCR_PR) since the hypervisor + * doesn't do this for us. Note only required if pseries since + * this is done in kvmhv_load_hv_regs_and_go() below otherwise. + */ + unsigned long host_psscr; /* call our hypervisor to load up HV regs and go */ struct hv_guest_state hvregs; + host_psscr = mfspr(SPRN_PSSCR_PR); + mtspr(SPRN_PSSCR_PR, vcpu->arch.psscr); kvmhv_save_hv_regs(vcpu, &hvregs); hvregs.lpcr = lpcr; vcpu->arch.regs.msr = vcpu->arch.shregs.msr; @@ -3590,6 +3599,8 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, vcpu->arch.shregs.msr = vcpu->arch.regs.msr; vcpu->arch.shregs.dar = mfspr(SPRN_DAR); vcpu->arch.shregs.dsisr = mfspr(SPRN_DSISR); + vcpu->arch.psscr = mfspr(SPRN_PSSCR_PR); + mtspr(SPRN_PSSCR_PR, host_psscr); /* H_CEDE has to be handled now, not later */ if (trap == BOOK3S_INTERRUPT_SYSCALL && !vcpu->arch.nested && @@ -3654,6 +3665,8 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, vcpu->arch.vpa.dirty = 1; save_pmu = lp->pmcregs_in_use; } + /* Must save pmu if this guest is capable of running nested guests */ + save_pmu |= nesting_enabled(vcpu->kvm); kvmhv_save_guest_pmu(vcpu, save_pmu); diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index 6ca0d7376a9f..e3ba67095895 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -1986,10 +1986,8 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type) xive->single_escalation = xive_native_has_single_escalation(); - if (ret) { - kfree(xive); + if (ret) return ret; - } return 0; } diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c index 5596c8ec221a..a998823f68a3 100644 --- a/arch/powerpc/kvm/book3s_xive_native.c +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -1090,9 +1090,9 @@ static int kvmppc_xive_native_create(struct kvm_device *dev, u32 type) xive->ops = &kvmppc_xive_native_ops; if (ret) - kfree(xive); + return ret; - return ret; + return 0; } /* diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 0dba7eb24f92..3e566c2e6066 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -50,6 +50,11 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *v) return !!(v->arch.pending_exceptions) || kvm_request_pending(v); } +bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu) +{ + return kvm_arch_vcpu_runnable(vcpu); +} + bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu) { return false; @@ -452,16 +457,6 @@ err_out: return -EINVAL; } -bool kvm_arch_has_vcpu_debugfs(void) -{ - return false; -} - -int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu) -{ - return 0; -} - void kvm_arch_destroy_vm(struct kvm *kvm) { unsigned int i; diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c index 9a5963e07a82..b8ad14bb1170 100644 --- a/arch/powerpc/mm/book3s64/hash_utils.c +++ b/arch/powerpc/mm/book3s64/hash_utils.c @@ -1899,11 +1899,20 @@ void hash__setup_initial_memory_limit(phys_addr_t first_memblock_base, * * For guests on platforms before POWER9, we clamp the it limit to 1G * to avoid some funky things such as RTAS bugs etc... + * + * On POWER9 we limit to 1TB in case the host erroneously told us that + * the RMA was >1TB. Effective address bits 0:23 are treated as zero + * (meaning the access is aliased to zero i.e. addr = addr % 1TB) + * for virtual real mode addressing and so it doesn't make sense to + * have an area larger than 1TB as it can't be addressed. */ if (!early_cpu_has_feature(CPU_FTR_HVMODE)) { ppc64_rma_size = first_memblock_size; if (!early_cpu_has_feature(CPU_FTR_ARCH_300)) ppc64_rma_size = min_t(u64, ppc64_rma_size, 0x40000000); + else + ppc64_rma_size = min_t(u64, ppc64_rma_size, + 1UL << SID_SHIFT_1T); /* Finally limit subsequent allocations */ memblock_set_current_limit(ppc64_rma_size); diff --git a/arch/powerpc/mm/kasan/kasan_init_32.c b/arch/powerpc/mm/kasan/kasan_init_32.c index 0d62be3cba47..74f4555a62ba 100644 --- a/arch/powerpc/mm/kasan/kasan_init_32.c +++ b/arch/powerpc/mm/kasan/kasan_init_32.c @@ -21,7 +21,7 @@ static void kasan_populate_pte(pte_t *ptep, pgprot_t prot) __set_pte_at(&init_mm, va, ptep, pfn_pte(PHYS_PFN(pa), prot), 0); } -static int kasan_init_shadow_page_tables(unsigned long k_start, unsigned long k_end) +static int __ref kasan_init_shadow_page_tables(unsigned long k_start, unsigned long k_end) { pmd_t *pmd; unsigned long k_cur, k_next; @@ -35,7 +35,10 @@ static int kasan_init_shadow_page_tables(unsigned long k_start, unsigned long k_ if ((void *)pmd_page_vaddr(*pmd) != kasan_early_shadow_pte) continue; - new = pte_alloc_one_kernel(&init_mm); + if (slab_is_available()) + new = pte_alloc_one_kernel(&init_mm); + else + new = memblock_alloc(PTE_FRAG_SIZE, PTE_FRAG_SIZE); if (!new) return -ENOMEM; diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 9259337d7374..9191a66b3bc5 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -239,7 +239,7 @@ void __init paging_init(void) #ifdef CONFIG_ZONE_DMA max_zone_pfns[ZONE_DMA] = min(max_low_pfn, - ((1UL << ARCH_ZONE_DMA_BITS) - 1) >> PAGE_SHIFT); + 1UL << (ARCH_ZONE_DMA_BITS - PAGE_SHIFT)); #endif max_zone_pfns[ZONE_NORMAL] = max_low_pfn; #ifdef CONFIG_HIGHMEM diff --git a/arch/powerpc/mm/nohash/tlb.c b/arch/powerpc/mm/nohash/tlb.c index d4acf6fa0596..bf60983a58c7 100644 --- a/arch/powerpc/mm/nohash/tlb.c +++ b/arch/powerpc/mm/nohash/tlb.c @@ -630,7 +630,6 @@ static void early_init_this_mmu(void) #ifdef CONFIG_PPC_FSL_BOOK3E if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) { unsigned int num_cams; - int __maybe_unused cpu = smp_processor_id(); bool map = true; /* use a quarter of the TLBCAM for bolted linear map */ diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index c8ec670ee924..a5ac371a3f06 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -11,6 +11,7 @@ #include <linux/sched.h> #include <linux/libnvdimm.h> #include <linux/platform_device.h> +#include <linux/delay.h> #include <asm/plpar_wrappers.h> @@ -43,8 +44,9 @@ struct papr_scm_priv { static int drc_pmem_bind(struct papr_scm_priv *p) { unsigned long ret[PLPAR_HCALL_BUFSIZE]; - uint64_t rc, token; uint64_t saved = 0; + uint64_t token; + int64_t rc; /* * When the hypervisor cannot map all the requested memory in a single @@ -64,6 +66,10 @@ static int drc_pmem_bind(struct papr_scm_priv *p) } while (rc == H_BUSY); if (rc) { + /* H_OVERLAP needs a separate error path */ + if (rc == H_OVERLAP) + return -EBUSY; + dev_err(&p->pdev->dev, "bind err: %lld\n", rc); return -ENXIO; } @@ -78,22 +84,36 @@ static int drc_pmem_bind(struct papr_scm_priv *p) static int drc_pmem_unbind(struct papr_scm_priv *p) { unsigned long ret[PLPAR_HCALL_BUFSIZE]; - uint64_t rc, token; + uint64_t token = 0; + int64_t rc; - token = 0; + dev_dbg(&p->pdev->dev, "unbind drc %x\n", p->drc_index); - /* NB: unbind has the same retry requirements mentioned above */ + /* NB: unbind has the same retry requirements as drc_pmem_bind() */ do { - rc = plpar_hcall(H_SCM_UNBIND_MEM, ret, p->drc_index, - p->bound_addr, p->blocks, token); + + /* Unbind of all SCM resources associated with drcIndex */ + rc = plpar_hcall(H_SCM_UNBIND_ALL, ret, H_UNBIND_SCOPE_DRC, + p->drc_index, token); token = ret[0]; - cond_resched(); + + /* Check if we are stalled for some time */ + if (H_IS_LONG_BUSY(rc)) { + msleep(get_longbusy_msecs(rc)); + rc = H_BUSY; + } else if (rc == H_BUSY) { + cond_resched(); + } + } while (rc == H_BUSY); if (rc) dev_err(&p->pdev->dev, "unbind error: %lld\n", rc); + else + dev_dbg(&p->pdev->dev, "unbind drc %x complete\n", + p->drc_index); - return !!rc; + return rc == H_SUCCESS ? 0 : -ENXIO; } static int papr_scm_meta_get(struct papr_scm_priv *p, @@ -255,12 +275,32 @@ static const struct attribute_group *papr_scm_dimm_groups[] = { NULL, }; +static inline int papr_scm_node(int node) +{ + int min_dist = INT_MAX, dist; + int nid, min_node; + + if ((node == NUMA_NO_NODE) || node_online(node)) + return node; + + min_node = first_online_node; + for_each_online_node(nid) { + dist = node_distance(node, nid); + if (dist < min_dist) { + min_dist = dist; + min_node = nid; + } + } + return min_node; +} + static int papr_scm_nvdimm_init(struct papr_scm_priv *p) { struct device *dev = &p->pdev->dev; struct nd_mapping_desc mapping; struct nd_region_desc ndr_desc; unsigned long dimm_flags; + int target_nid, online_nid; p->bus_desc.ndctl = papr_scm_ndctl; p->bus_desc.module = THIS_MODULE; @@ -299,8 +339,10 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p) memset(&ndr_desc, 0, sizeof(ndr_desc)); ndr_desc.attr_groups = region_attr_groups; - ndr_desc.numa_node = dev_to_node(&p->pdev->dev); - ndr_desc.target_node = ndr_desc.numa_node; + target_nid = dev_to_node(&p->pdev->dev); + online_nid = papr_scm_node(target_nid); + ndr_desc.numa_node = online_nid; + ndr_desc.target_node = target_nid; ndr_desc.res = &p->res; ndr_desc.of_node = p->dn; ndr_desc.provider_data = p; @@ -318,6 +360,9 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p) ndr_desc.res, p->dn); goto err; } + if (target_nid != online_nid) + dev_info(dev, "Region registered with target node %d and online node %d", + target_nid, online_nid); return 0; @@ -389,6 +434,14 @@ static int papr_scm_probe(struct platform_device *pdev) /* request the hypervisor to bind this region to somewhere in memory */ rc = drc_pmem_bind(p); + + /* If phyp says drc memory still bound then force unbound and retry */ + if (rc == -EBUSY) { + dev_warn(&pdev->dev, "Retrying bind after unbinding\n"); + drc_pmem_unbind(p); + rc = drc_pmem_bind(p); + } + if (rc) goto err; diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c index 082c7e1c20f0..1cdb39575eae 100644 --- a/arch/powerpc/sysdev/xive/common.c +++ b/arch/powerpc/sysdev/xive/common.c @@ -479,7 +479,7 @@ static int xive_find_target_in_mask(const struct cpumask *mask, * Now go through the entire mask until we find a valid * target. */ - for (;;) { + do { /* * We re-check online as the fallback case passes us * an untested affinity mask @@ -487,12 +487,11 @@ static int xive_find_target_in_mask(const struct cpumask *mask, if (cpu_online(cpu) && xive_try_pick_target(cpu)) return cpu; cpu = cpumask_next(cpu, mask); - if (cpu == first) - break; /* Wrap around */ if (cpu >= nr_cpu_ids) cpu = cpumask_first(mask); - } + } while (cpu != first); + return -1; } |