diff options
Diffstat (limited to 'arch/powerpc')
| -rw-r--r-- | arch/powerpc/boot/Makefile | 3 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/irq_work.h | 1 | ||||
| -rw-r--r-- | arch/powerpc/kernel/setup-common.c | 11 | ||||
| -rw-r--r-- | arch/powerpc/kvm/book3s_hv.c | 12 | ||||
| -rw-r--r-- | arch/powerpc/mm/numa.c | 78 | ||||
| -rw-r--r-- | arch/powerpc/net/bpf_jit_comp.c | 3 | ||||
| -rw-r--r-- | arch/powerpc/perf/core-book3s.c | 25 | ||||
| -rw-r--r-- | arch/powerpc/platforms/powernv/opal-nvram.c | 14 | ||||
| -rw-r--r-- | arch/powerpc/sysdev/mpic.c | 2 |
9 files changed, 119 insertions, 30 deletions
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 9d47f2efa830..bb69f3955b59 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -92,7 +92,8 @@ $(addprefix $(obj)/,$(zlib-y)): \ libfdt := fdt.c fdt_ro.c fdt_wip.c fdt_sw.c fdt_rw.c fdt_strerror.c libfdtheader := fdt.h libfdt.h libfdt_internal.h -$(addprefix $(obj)/,$(libfdt) libfdt-wrapper.o simpleboot.o epapr.o opal.o): \ +$(addprefix $(obj)/,$(libfdt) libfdt-wrapper.o simpleboot.o epapr.o opal.o \ + treeboot-akebono.o treeboot-currituck.o treeboot-iss4xx.o): \ $(addprefix $(obj)/,$(libfdtheader)) src-wlib-y := string.S crt0.S crtsavres.S stdio.c decompress.c main.c \ diff --git a/arch/powerpc/include/asm/irq_work.h b/arch/powerpc/include/asm/irq_work.h index 744fd54de374..1bcc84903930 100644 --- a/arch/powerpc/include/asm/irq_work.h +++ b/arch/powerpc/include/asm/irq_work.h @@ -5,5 +5,6 @@ static inline bool arch_irq_work_has_interrupt(void) { return true; } +extern void arch_irq_work_raise(void); #endif /* _ASM_POWERPC_IRQ_WORK_H */ diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index f516ac508ae3..bf0f712ac0e0 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -228,14 +228,6 @@ static int show_cpuinfo(struct seq_file *m, void *v) unsigned short maj; unsigned short min; - /* We only show online cpus: disable preempt (overzealous, I - * knew) to prevent cpu going down. */ - preempt_disable(); - if (!cpu_online(cpu_id)) { - preempt_enable(); - return 0; - } - #ifdef CONFIG_SMP pvr = per_cpu(cpu_pvr, cpu_id); #else @@ -340,9 +332,6 @@ static int show_cpuinfo(struct seq_file *m, void *v) #ifdef CONFIG_SMP seq_printf(m, "\n"); #endif - - preempt_enable(); - /* If this is the last cpu, print the summary */ if (cpumask_next(cpu_id, cpu_online_mask) >= nr_cpu_ids) show_cpuinfo_summary(m); diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 218cba2f5699..0a2b247dbc6b 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -3107,15 +3107,17 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) goto up_out; psize = vma_kernel_pagesize(vma); - porder = __ilog2(psize); up_read(¤t->mm->mmap_sem); /* We can handle 4k, 64k or 16M pages in the VRMA */ - err = -EINVAL; - if (!(psize == 0x1000 || psize == 0x10000 || - psize == 0x1000000)) - goto out_srcu; + if (psize >= 0x1000000) + psize = 0x1000000; + else if (psize >= 0x10000) + psize = 0x10000; + else + psize = 0x1000; + porder = __ilog2(psize); /* Update VRMASD field in the LPCR */ senc = slb_pgsize_encoding(psize); diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index a51c188b81f3..6cff96e0d77b 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -551,7 +551,7 @@ static int numa_setup_cpu(unsigned long lcpu) nid = of_node_to_nid_single(cpu); out_present: - if (nid < 0 || !node_online(nid)) + if (nid < 0 || !node_possible(nid)) nid = first_online_node; map_cpu_to_node(lcpu, nid); @@ -904,6 +904,32 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn) NODE_DATA(nid)->node_spanned_pages = spanned_pages; } +static void __init find_possible_nodes(void) +{ + struct device_node *rtas; + u32 numnodes, i; + + if (min_common_depth <= 0) + return; + + rtas = of_find_node_by_path("/rtas"); + if (!rtas) + return; + + if (of_property_read_u32_index(rtas, + "ibm,max-associativity-domains", + min_common_depth, &numnodes)) + goto out; + + for (i = 0; i < numnodes; i++) { + if (!node_possible(i)) + node_set(i, node_possible_map); + } + +out: + of_node_put(rtas); +} + void __init initmem_init(void) { int nid, cpu; @@ -917,12 +943,15 @@ void __init initmem_init(void) memblock_dump_all(); /* - * Reduce the possible NUMA nodes to the online NUMA nodes, - * since we do not support node hotplug. This ensures that we - * lower the maximum NUMA node ID to what is actually present. + * Modify the set of possible NUMA nodes to reflect information + * available about the set of online nodes, and the set of nodes + * that we expect to make use of for this platform's affinity + * calculations. */ nodes_and(node_possible_map, node_possible_map, node_online_map); + find_possible_nodes(); + for_each_online_node(nid) { unsigned long start_pfn, end_pfn; @@ -1274,6 +1303,40 @@ static long vphn_get_associativity(unsigned long cpu, return rc; } +static inline int find_and_online_cpu_nid(int cpu) +{ + __be32 associativity[VPHN_ASSOC_BUFSIZE] = {0}; + int new_nid; + + /* Use associativity from first thread for all siblings */ + vphn_get_associativity(cpu, associativity); + new_nid = associativity_to_nid(associativity); + if (new_nid < 0 || !node_possible(new_nid)) + new_nid = first_online_node; + + if (NODE_DATA(new_nid) == NULL) { +#ifdef CONFIG_MEMORY_HOTPLUG + /* + * Need to ensure that NODE_DATA is initialized for a node from + * available memory (see memblock_alloc_try_nid). If unable to + * init the node, then default to nearest node that has memory + * installed. + */ + if (try_online_node(new_nid)) + new_nid = first_online_node; +#else + /* + * Default to using the nearest node that has memory installed. + * Otherwise, it would be necessary to patch the kernel MM code + * to deal with more memoryless-node error conditions. + */ + new_nid = first_online_node; +#endif + } + + return new_nid; +} + /* * Update the CPU maps and sysfs entries for a single CPU when its NUMA * characteristics change. This function doesn't perform any locking and is @@ -1339,7 +1402,6 @@ int arch_update_cpu_topology(void) { unsigned int cpu, sibling, changed = 0; struct topology_update_data *updates, *ud; - __be32 associativity[VPHN_ASSOC_BUFSIZE] = {0}; cpumask_t updated_cpus; struct device *dev; int weight, new_nid, i = 0; @@ -1374,11 +1436,7 @@ int arch_update_cpu_topology(void) continue; } - /* Use associativity from first thread for all siblings */ - vphn_get_associativity(cpu, associativity); - new_nid = associativity_to_nid(associativity); - if (new_nid < 0 || !node_online(new_nid)) - new_nid = first_online_node; + new_nid = find_and_online_cpu_nid(cpu); if (new_nid == numa_cpu_lookup_table[cpu]) { cpumask_andnot(&cpu_associativity_changes_mask, diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 7e706f36e364..9c58194c7ea5 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -329,6 +329,9 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4); PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, len)); break; + case BPF_LDX | BPF_W | BPF_ABS: /* A = *((u32 *)(seccomp_data + K)); */ + PPC_LWZ_OFFS(r_A, r_skb, K); + break; case BPF_LDX | BPF_W | BPF_LEN: /* X = skb->len; */ PPC_LWZ_OFFS(r_X, r_skb, offsetof(struct sk_buff, len)); break; diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index bf949623de90..771edffa2d40 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -448,6 +448,16 @@ static void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw) /* invalid entry */ continue; + /* + * BHRB rolling buffer could very much contain the kernel + * addresses at this point. Check the privileges before + * exporting it to userspace (avoid exposure of regions + * where we could have speculative execution) + */ + if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN) && + is_kernel_addr(addr)) + continue; + /* Branches are read most recent first (ie. mfbhrb 0 is * the most recent branch). * There are two types of valid entries: @@ -1188,6 +1198,7 @@ static void power_pmu_disable(struct pmu *pmu) */ write_mmcr0(cpuhw, val); mb(); + isync(); /* * Disable instruction sampling if it was enabled @@ -1196,12 +1207,26 @@ static void power_pmu_disable(struct pmu *pmu) mtspr(SPRN_MMCRA, cpuhw->mmcr[2] & ~MMCRA_SAMPLE_ENABLE); mb(); + isync(); } cpuhw->disabled = 1; cpuhw->n_added = 0; ebb_switch_out(mmcr0); + +#ifdef CONFIG_PPC64 + /* + * These are readable by userspace, may contain kernel + * addresses and are not switched by context switch, so clear + * them now to avoid leaking anything to userspace in general + * including to another process. + */ + if (ppmu->flags & PPMU_ARCH_207S) { + mtspr(SPRN_SDAR, 0); + mtspr(SPRN_SIAR, 0); + } +#endif } local_irq_restore(flags); diff --git a/arch/powerpc/platforms/powernv/opal-nvram.c b/arch/powerpc/platforms/powernv/opal-nvram.c index 1bceb95f422d..5584247f5029 100644 --- a/arch/powerpc/platforms/powernv/opal-nvram.c +++ b/arch/powerpc/platforms/powernv/opal-nvram.c @@ -44,6 +44,10 @@ static ssize_t opal_nvram_read(char *buf, size_t count, loff_t *index) return count; } +/* + * This can be called in the panic path with interrupts off, so use + * mdelay in that case. + */ static ssize_t opal_nvram_write(char *buf, size_t count, loff_t *index) { s64 rc = OPAL_BUSY; @@ -58,10 +62,16 @@ static ssize_t opal_nvram_write(char *buf, size_t count, loff_t *index) while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { rc = opal_write_nvram(__pa(buf), count, off); if (rc == OPAL_BUSY_EVENT) { - msleep(OPAL_BUSY_DELAY_MS); + if (in_interrupt() || irqs_disabled()) + mdelay(OPAL_BUSY_DELAY_MS); + else + msleep(OPAL_BUSY_DELAY_MS); opal_poll_events(NULL); } else if (rc == OPAL_BUSY) { - msleep(OPAL_BUSY_DELAY_MS); + if (in_interrupt() || irqs_disabled()) + mdelay(OPAL_BUSY_DELAY_MS); + else + msleep(OPAL_BUSY_DELAY_MS); } } diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c index b9aac951a90f..f37567ed640c 100644 --- a/arch/powerpc/sysdev/mpic.c +++ b/arch/powerpc/sysdev/mpic.c @@ -626,7 +626,7 @@ static inline u32 mpic_physmask(u32 cpumask) int i; u32 mask = 0; - for (i = 0; i < min(32, NR_CPUS); ++i, cpumask >>= 1) + for (i = 0; i < min(32, NR_CPUS) && cpu_possible(i); ++i, cpumask >>= 1) mask |= (cpumask & 1) << get_hard_smp_processor_id(i); return mask; } |