diff options
86 files changed, 2159 insertions, 1680 deletions
diff --git a/Documentation/cpu-hotplug.txt b/Documentation/cpu-hotplug.txt index a0b005d2bd95..f9ad5e048b11 100644 --- a/Documentation/cpu-hotplug.txt +++ b/Documentation/cpu-hotplug.txt @@ -108,7 +108,7 @@ Never use anything other than cpumask_t to represent bitmap of CPUs. for_each_possible_cpu - Iterate over cpu_possible_mask for_each_online_cpu - Iterate over cpu_online_mask for_each_present_cpu - Iterate over cpu_present_mask - for_each_cpu_mask(x,mask) - Iterate over some random collection of cpu mask. + for_each_cpu(x,mask) - Iterate over some random collection of cpu mask. #include <linux/cpu.h> get_online_cpus() and put_online_cpus(): diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index ffe8e1b814e0..714411f62391 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -636,7 +636,7 @@ void smp_send_stop(void) cpumask_t mask; cpumask_copy(&mask, cpu_online_mask); - cpu_clear(smp_processor_id(), mask); + cpumask_clear_cpu(smp_processor_id(), &mask); smp_cross_call(&mask, IPI_CPU_STOP); } diff --git a/arch/blackfin/mach-bf561/smp.c b/arch/blackfin/mach-bf561/smp.c index 11789beca75a..8c0c80fd1a45 100644 --- a/arch/blackfin/mach-bf561/smp.c +++ b/arch/blackfin/mach-bf561/smp.c @@ -124,7 +124,7 @@ void platform_send_ipi(cpumask_t callmap, int irq) unsigned int cpu; int offset = (irq == IRQ_SUPPLE_0) ? 6 : 8; - for_each_cpu_mask(cpu, callmap) { + for_each_cpu(cpu, &callmap) { BUG_ON(cpu >= 2); SSYNC(); bfin_write_SICB_SYSCR(bfin_read_SICB_SYSCR() | (1 << (offset + cpu))); diff --git a/arch/ia64/include/asm/acpi.h b/arch/ia64/include/asm/acpi.h index a1d91ab4c5ef..aa0fdf125aba 100644 --- a/arch/ia64/include/asm/acpi.h +++ b/arch/ia64/include/asm/acpi.h @@ -117,7 +117,7 @@ static inline void arch_acpi_set_pdc_bits(u32 *buf) #ifdef CONFIG_ACPI_NUMA extern cpumask_t early_cpu_possible_map; #define for_each_possible_early_cpu(cpu) \ - for_each_cpu_mask((cpu), early_cpu_possible_map) + for_each_cpu((cpu), &early_cpu_possible_map) static inline void per_cpu_scan_finalize(int min_cpus, int reserve_cpus) { @@ -125,13 +125,13 @@ static inline void per_cpu_scan_finalize(int min_cpus, int reserve_cpus) int cpu; int next_nid = 0; - low_cpu = cpus_weight(early_cpu_possible_map); + low_cpu = cpumask_weight(&early_cpu_possible_map); high_cpu = max(low_cpu, min_cpus); high_cpu = min(high_cpu + reserve_cpus, NR_CPUS); for (cpu = low_cpu; cpu < high_cpu; cpu++) { - cpu_set(cpu, early_cpu_possible_map); + cpumask_set_cpu(cpu, &early_cpu_possible_map); if (node_cpuid[cpu].nid == NUMA_NO_NODE) { node_cpuid[cpu].nid = next_nid; next_nid++; diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c index 2c4498919d3c..35bf22cc71b7 100644 --- a/arch/ia64/kernel/acpi.c +++ b/arch/ia64/kernel/acpi.c @@ -483,7 +483,7 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) (pa->apic_id << 8) | (pa->local_sapic_eid); /* nid should be overridden as logical node id later */ node_cpuid[srat_num_cpus].nid = pxm; - cpu_set(srat_num_cpus, early_cpu_possible_map); + cpumask_set_cpu(srat_num_cpus, &early_cpu_possible_map); srat_num_cpus++; } diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c index cd44a57c73be..bc9501e36e77 100644 --- a/arch/ia64/kernel/iosapic.c +++ b/arch/ia64/kernel/iosapic.c @@ -690,7 +690,7 @@ skip_numa_setup: do { if (++cpu >= nr_cpu_ids) cpu = 0; - } while (!cpu_online(cpu) || !cpu_isset(cpu, domain)); + } while (!cpu_online(cpu) || !cpumask_test_cpu(cpu, &domain)); return cpu_physical_id(cpu); #else /* CONFIG_SMP */ diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c index 698d8fefde6c..eaa3199f98c8 100644 --- a/arch/ia64/kernel/irq_ia64.c +++ b/arch/ia64/kernel/irq_ia64.c @@ -109,13 +109,13 @@ static inline int find_unassigned_vector(cpumask_t domain) int pos, vector; cpumask_and(&mask, &domain, cpu_online_mask); - if (cpus_empty(mask)) + if (cpumask_empty(&mask)) return -EINVAL; for (pos = 0; pos < IA64_NUM_DEVICE_VECTORS; pos++) { vector = IA64_FIRST_DEVICE_VECTOR + pos; - cpus_and(mask, domain, vector_table[vector]); - if (!cpus_empty(mask)) + cpumask_and(&mask, &domain, &vector_table[vector]); + if (!cpumask_empty(&mask)) continue; return vector; } @@ -132,18 +132,18 @@ static int __bind_irq_vector(int irq, int vector, cpumask_t domain) BUG_ON((unsigned)vector >= IA64_NUM_VECTORS); cpumask_and(&mask, &domain, cpu_online_mask); - if (cpus_empty(mask)) + if (cpumask_empty(&mask)) return -EINVAL; - if ((cfg->vector == vector) && cpus_equal(cfg->domain, domain)) + if ((cfg->vector == vector) && cpumask_equal(&cfg->domain, &domain)) return 0; if (cfg->vector != IRQ_VECTOR_UNASSIGNED) return -EBUSY; - for_each_cpu_mask(cpu, mask) + for_each_cpu(cpu, &mask) per_cpu(vector_irq, cpu)[vector] = irq; cfg->vector = vector; cfg->domain = domain; irq_status[irq] = IRQ_USED; - cpus_or(vector_table[vector], vector_table[vector], domain); + cpumask_or(&vector_table[vector], &vector_table[vector], &domain); return 0; } @@ -161,7 +161,6 @@ int bind_irq_vector(int irq, int vector, cpumask_t domain) static void __clear_irq_vector(int irq) { int vector, cpu; - cpumask_t mask; cpumask_t domain; struct irq_cfg *cfg = &irq_cfg[irq]; @@ -169,13 +168,12 @@ static void __clear_irq_vector(int irq) BUG_ON(cfg->vector == IRQ_VECTOR_UNASSIGNED); vector = cfg->vector; domain = cfg->domain; - cpumask_and(&mask, &cfg->domain, cpu_online_mask); - for_each_cpu_mask(cpu, mask) + for_each_cpu_and(cpu, &cfg->domain, cpu_online_mask) per_cpu(vector_irq, cpu)[vector] = -1; cfg->vector = IRQ_VECTOR_UNASSIGNED; cfg->domain = CPU_MASK_NONE; irq_status[irq] = IRQ_UNUSED; - cpus_andnot(vector_table[vector], vector_table[vector], domain); + cpumask_andnot(&vector_table[vector], &vector_table[vector], &domain); } static void clear_irq_vector(int irq) @@ -244,7 +242,7 @@ void __setup_vector_irq(int cpu) per_cpu(vector_irq, cpu)[vector] = -1; /* Mark the inuse vectors */ for (irq = 0; irq < NR_IRQS; ++irq) { - if (!cpu_isset(cpu, irq_cfg[irq].domain)) + if (!cpumask_test_cpu(cpu, &irq_cfg[irq].domain)) continue; vector = irq_to_vector(irq); per_cpu(vector_irq, cpu)[vector] = irq; @@ -261,7 +259,7 @@ static enum vector_domain_type { static cpumask_t vector_allocation_domain(int cpu) { if (vector_domain_type == VECTOR_DOMAIN_PERCPU) - return cpumask_of_cpu(cpu); + return *cpumask_of(cpu); return CPU_MASK_ALL; } @@ -275,7 +273,7 @@ static int __irq_prepare_move(int irq, int cpu) return -EBUSY; if (cfg->vector == IRQ_VECTOR_UNASSIGNED || !cpu_online(cpu)) return -EINVAL; - if (cpu_isset(cpu, cfg->domain)) + if (cpumask_test_cpu(cpu, &cfg->domain)) return 0; domain = vector_allocation_domain(cpu); vector = find_unassigned_vector(domain); @@ -309,12 +307,12 @@ void irq_complete_move(unsigned irq) if (likely(!cfg->move_in_progress)) return; - if (unlikely(cpu_isset(smp_processor_id(), cfg->old_domain))) + if (unlikely(cpumask_test_cpu(smp_processor_id(), &cfg->old_domain))) return; cpumask_and(&cleanup_mask, &cfg->old_domain, cpu_online_mask); - cfg->move_cleanup_count = cpus_weight(cleanup_mask); - for_each_cpu_mask(i, cleanup_mask) + cfg->move_cleanup_count = cpumask_weight(&cleanup_mask); + for_each_cpu(i, &cleanup_mask) platform_send_ipi(i, IA64_IRQ_MOVE_VECTOR, IA64_IPI_DM_INT, 0); cfg->move_in_progress = 0; } @@ -340,12 +338,12 @@ static irqreturn_t smp_irq_move_cleanup_interrupt(int irq, void *dev_id) if (!cfg->move_cleanup_count) goto unlock; - if (!cpu_isset(me, cfg->old_domain)) + if (!cpumask_test_cpu(me, &cfg->old_domain)) goto unlock; spin_lock_irqsave(&vector_lock, flags); __this_cpu_write(vector_irq[vector], -1); - cpu_clear(me, vector_table[vector]); + cpumask_clear_cpu(me, &vector_table[vector]); spin_unlock_irqrestore(&vector_lock, flags); cfg->move_cleanup_count--; unlock: diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c index 8bfd36af46f8..dd5801eb4c69 100644 --- a/arch/ia64/kernel/mca.c +++ b/arch/ia64/kernel/mca.c @@ -1293,7 +1293,7 @@ ia64_mca_handler(struct pt_regs *regs, struct switch_stack *sw, monarch_cpu = cpu; sos->monarch = 1; } else { - cpu_set(cpu, mca_cpu); + cpumask_set_cpu(cpu, &mca_cpu); sos->monarch = 0; } mprintk(KERN_INFO "Entered OS MCA handler. PSP=%lx cpu=%d " @@ -1316,7 +1316,7 @@ ia64_mca_handler(struct pt_regs *regs, struct switch_stack *sw, */ ia64_mca_wakeup_all(); } else { - while (cpu_isset(cpu, mca_cpu)) + while (cpumask_test_cpu(cpu, &mca_cpu)) cpu_relax(); /* spin until monarch wakes us */ } @@ -1355,9 +1355,9 @@ ia64_mca_handler(struct pt_regs *regs, struct switch_stack *sw, * and put this cpu in the rendez loop. */ for_each_online_cpu(i) { - if (cpu_isset(i, mca_cpu)) { + if (cpumask_test_cpu(i, &mca_cpu)) { monarch_cpu = i; - cpu_clear(i, mca_cpu); /* wake next cpu */ + cpumask_clear_cpu(i, &mca_cpu); /* wake next cpu */ while (monarch_cpu != -1) cpu_relax(); /* spin until last cpu leaves */ set_curr_task(cpu, previous_current); @@ -1822,7 +1822,7 @@ format_mca_init_stack(void *mca_data, unsigned long offset, ti->cpu = cpu; p->stack = ti; p->state = TASK_UNINTERRUPTIBLE; - cpu_set(cpu, p->cpus_allowed); + cpumask_set_cpu(cpu, &p->cpus_allowed); INIT_LIST_HEAD(&p->tasks); p->parent = p->real_parent = p->group_leader = p; INIT_LIST_HEAD(&p->children); diff --git a/arch/ia64/kernel/msi_ia64.c b/arch/ia64/kernel/msi_ia64.c index 8ae36ea177d3..9dd7464f8c17 100644 --- a/arch/ia64/kernel/msi_ia64.c +++ b/arch/ia64/kernel/msi_ia64.c @@ -47,15 +47,14 @@ int ia64_setup_msi_irq(struct pci_dev *pdev, struct msi_desc *desc) struct msi_msg msg; unsigned long dest_phys_id; int irq, vector; - cpumask_t mask; irq = create_irq(); if (irq < 0) return irq; irq_set_msi_desc(irq, desc); - cpumask_and(&mask, &(irq_to_domain(irq)), cpu_online_mask); - dest_phys_id = cpu_physical_id(first_cpu(mask)); + dest_phys_id = cpu_physical_id(cpumask_any_and(&(irq_to_domain(irq)), + cpu_online_mask)); vector = irq_to_vector(irq); msg.address_hi = 0; @@ -171,10 +170,9 @@ msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_msg *msg) { struct irq_cfg *cfg = irq_cfg + irq; unsigned dest; - cpumask_t mask; - cpumask_and(&mask, &(irq_to_domain(irq)), cpu_online_mask); - dest = cpu_physical_id(first_cpu(mask)); + dest = cpu_physical_id(cpumask_first_and(&(irq_to_domain(irq)), + cpu_online_mask)); msg->address_hi = 0; msg->address_lo = diff --git a/arch/ia64/kernel/numa.c b/arch/ia64/kernel/numa.c index d288cde93606..92c376279c6d 100644 --- a/arch/ia64/kernel/numa.c +++ b/arch/ia64/kernel/numa.c @@ -39,7 +39,7 @@ void map_cpu_to_node(int cpu, int nid) } /* sanity check first */ oldnid = cpu_to_node_map[cpu]; - if (cpu_isset(cpu, node_to_cpu_mask[oldnid])) { + if (cpumask_test_cpu(cpu, &node_to_cpu_mask[oldnid])) { return; /* nothing to do */ } /* we don't have cpu-driven node hot add yet... @@ -47,16 +47,16 @@ void map_cpu_to_node(int cpu, int nid) if (!node_online(nid)) nid = first_online_node; cpu_to_node_map[cpu] = nid; - cpu_set(cpu, node_to_cpu_mask[nid]); + cpumask_set_cpu(cpu, &node_to_cpu_mask[nid]); return; } void unmap_cpu_from_node(int cpu, int nid) { - WARN_ON(!cpu_isset(cpu, node_to_cpu_mask[nid])); + WARN_ON(!cpumask_test_cpu(cpu, &node_to_cpu_mask[nid])); WARN_ON(cpu_to_node_map[cpu] != nid); cpu_to_node_map[cpu] = 0; - cpu_clear(cpu, node_to_cpu_mask[nid]); + cpumask_clear_cpu(cpu, &node_to_cpu_mask[nid]); } @@ -71,7 +71,7 @@ void __init build_cpu_to_node_map(void) int cpu, i, node; for(node=0; node < MAX_NUMNODES; node++) - cpus_clear(node_to_cpu_mask[node]); + cpumask_clear(&node_to_cpu_mask[node]); for_each_possible_early_cpu(cpu) { node = -1; diff --git a/arch/ia64/kernel/salinfo.c b/arch/ia64/kernel/salinfo.c index ee9719eebb1e..1eeffb7fbb16 100644 --- a/arch/ia64/kernel/salinfo.c +++ b/arch/ia64/kernel/salinfo.c @@ -256,7 +256,7 @@ salinfo_log_wakeup(int type, u8 *buffer, u64 size, int irqsafe) data_saved->buffer = buffer; } } - cpu_set(smp_processor_id(), data->cpu_event); + cpumask_set_cpu(smp_processor_id(), &data->cpu_event); if (irqsafe) { salinfo_work_to_do(data); spin_unlock_irqrestore(&data_saved_lock, flags); @@ -274,7 +274,7 @@ salinfo_timeout_check(struct salinfo_data *data) unsigned long flags; if (!data->open) return; - if (!cpus_empty(data->cpu_event)) { + if (!cpumask_empty(&data->cpu_event)) { spin_lock_irqsave(&data_saved_lock, flags); salinfo_work_to_do(data); spin_unlock_irqrestore(&data_saved_lock, flags); @@ -308,7 +308,7 @@ salinfo_event_read(struct file *file, char __user *buffer, size_t count, loff_t int i, n, cpu = -1; retry: - if (cpus_empty(data->cpu_event) && down_trylock(&data->mutex)) { + if (cpumask_empty(&data->cpu_event) && down_trylock(&data->mutex)) { if (file->f_flags & O_NONBLOCK) return -EAGAIN; if (down_interruptible(&data->mutex)) @@ -317,9 +317,9 @@ retry: n = data->cpu_check; for (i = 0; i < nr_cpu_ids; i++) { - if (cpu_isset(n, data->cpu_event)) { + if (cpumask_test_cpu(n, &data->cpu_event)) { if (!cpu_online(n)) { - cpu_clear(n, data->cpu_event); + cpumask_clear_cpu(n, &data->cpu_event); continue; } cpu = n; @@ -451,7 +451,7 @@ retry: call_on_cpu(cpu, salinfo_log_read_cpu, data); if (!data->log_size) { data->state = STATE_NO_DATA; - cpu_clear(cpu, data->cpu_event); + cpumask_clear_cpu(cpu, &data->cpu_event); } else { data->state = STATE_LOG_RECORD; } @@ -491,11 +491,11 @@ salinfo_log_clear(struct salinfo_data *data, int cpu) unsigned long flags; spin_lock_irqsave(&data_saved_lock, flags); data->state = STATE_NO_DATA; - if (!cpu_isset(cpu, data->cpu_event)) { + if (!cpumask_test_cpu(cpu, &data->cpu_event)) { spin_unlock_irqrestore(&data_saved_lock, flags); return 0; } - cpu_clear(cpu, data->cpu_event); + cpumask_clear_cpu(cpu, &data->cpu_event); if (data->saved_num) { shift1_data_saved(data, data->saved_num - 1); data->saved_num = 0; @@ -509,7 +509,7 @@ salinfo_log_clear(struct salinfo_data *data, int cpu) salinfo_log_new_read(cpu, data); if (data->state == STATE_LOG_RECORD) { spin_lock_irqsave(&data_saved_lock, flags); - cpu_set(cpu, data->cpu_event); + cpumask_set_cpu(cpu, &data->cpu_event); salinfo_work_to_do(data); spin_unlock_irqrestore(&data_saved_lock, flags); } @@ -581,7 +581,7 @@ salinfo_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu for (i = 0, data = salinfo_data; i < ARRAY_SIZE(salinfo_data); ++i, ++data) { - cpu_set(cpu, data->cpu_event); + cpumask_set_cpu(cpu, &data->cpu_event); salinfo_work_to_do(data); } spin_unlock_irqrestore(&data_saved_lock, flags); @@ -601,7 +601,7 @@ salinfo_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu shift1_data_saved(data, j); } } - cpu_clear(cpu, data->cpu_event); + cpumask_clear_cpu(cpu, &data->cpu_event); } spin_unlock_irqrestore(&data_saved_lock, flags); break; @@ -659,7 +659,7 @@ salinfo_init(void) /* we missed any events before now */ for_each_online_cpu(j) - cpu_set(j, data->cpu_event); + cpumask_set_cpu(j, &data->cpu_event); *sdir++ = dir; } diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index d86669bcdfb2..b9761389cb8d 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -562,8 +562,8 @@ setup_arch (char **cmdline_p) # ifdef CONFIG_ACPI_HOTPLUG_CPU prefill_possible_map(); # endif - per_cpu_scan_finalize((cpus_weight(early_cpu_possible_map) == 0 ? - 32 : cpus_weight(early_cpu_possible_map)), + per_cpu_scan_finalize((cpumask_weight(&early_cpu_possible_map) == 0 ? + 32 : cpumask_weight(&early_cpu_possible_map)), additional_cpus > 0 ? additional_cpus : 0); # endif #endif /* CONFIG_APCI_BOOT */ @@ -702,7 +702,8 @@ show_cpuinfo (struct seq_file *m, void *v) c->itc_freq / 1000000, c->itc_freq % 1000000, lpj*HZ/500000, (lpj*HZ/5000) % 100); #ifdef CONFIG_SMP - seq_printf(m, "siblings : %u\n", cpus_weight(cpu_core_map[cpunum])); + seq_printf(m, "siblings : %u\n", + cpumask_weight(&cpu_core_map[cpunum])); if (c->socket_id != -1) seq_printf(m, "physical id: %u\n", c->socket_id); if (c->threads_per_core > 1 || c->cores_per_socket > 1) @@ -933,8 +934,8 @@ cpu_init (void) * (must be done after per_cpu area is setup) */ if (smp_processor_id() == 0) { - cpu_set(0, per_cpu(cpu_sibling_map, 0)); - cpu_set(0, cpu_core_map[0]); + cpumask_set_cpu(0, &per_cpu(cpu_sibling_map, 0)); + cpumask_set_cpu(0, &cpu_core_map[0]); } else { /* * Set ar.k3 so that assembly code in MCA handler can compute diff --git a/arch/ia64/kernel/smp.c b/arch/ia64/kernel/smp.c index 9fcd4e63048f..7f706d4f84f7 100644 --- a/arch/ia64/kernel/smp.c +++ b/arch/ia64/kernel/smp.c @@ -262,11 +262,11 @@ smp_flush_tlb_cpumask(cpumask_t xcpumask) preempt_disable(); mycpu = smp_processor_id(); - for_each_cpu_mask(cpu, cpumask) + for_each_cpu(cpu, &cpumask) counts[cpu] = local_tlb_flush_counts[cpu].count & 0xffff; mb(); - for_each_cpu_mask(cpu, cpumask) { + for_each_cpu(cpu, &cpumask) { if (cpu == mycpu) flush_mycpu = 1; else @@ -276,7 +276,7 @@ smp_flush_tlb_cpumask(cpumask_t xcpumask) if (flush_mycpu) smp_local_flush_tlb(); - for_each_cpu_mask(cpu, cpumask) + for_each_cpu(cpu, &cpumask) while(counts[cpu] == (local_tlb_flush_counts[cpu].count & 0xffff)) udelay(FLUSH_DELAY); diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c index 547a48d78bd7..15051e9c2c6f 100644 --- a/arch/ia64/kernel/smpboot.c +++ b/arch/ia64/kernel/smpboot.c @@ -434,7 +434,7 @@ smp_callin (void) /* * Allow the master to continue. */ - cpu_set(cpuid, cpu_callin_map); + cpumask_set_cpu(cpuid, &cpu_callin_map); Dprintk("Stack on CPU %d at about %p\n",cpuid, &cpuid); } @@ -475,13 +475,13 @@ do_boot_cpu (int sapicid, int cpu, struct task_struct *idle) */ Dprintk("Waiting on callin_map ..."); for (timeout = 0; timeout < 100000; timeout++) { - if (cpu_isset(cpu, cpu_callin_map)) + if (cpumask_test_cpu(cpu, &cpu_callin_map)) break; /* It has booted */ udelay(100); } Dprintk("\n"); - if (!cpu_isset(cpu, cpu_callin_map)) { + if (!cpumask_test_cpu(cpu, &cpu_callin_map)) { printk(KERN_ERR "Processor 0x%x/0x%x is stuck.\n", cpu, sapicid); ia64_cpu_to_sapicid[cpu] = -1; set_cpu_online(cpu, false); /* was set in smp_callin() */ @@ -541,7 +541,7 @@ smp_prepare_cpus (unsigned int max_cpus) smp_setup_percpu_timer(); - cpu_set(0, cpu_callin_map); + cpumask_set_cpu(0, &cpu_callin_map); local_cpu_data->loops_per_jiffy = loops_per_jiffy; ia64_cpu_to_sapicid[0] = boot_cpu_id; @@ -565,7 +565,7 @@ smp_prepare_cpus (unsigned int max_cpus) void smp_prepare_boot_cpu(void) { set_cpu_online(smp_processor_id(), true); - cpu_set(smp_processor_id(), cpu_callin_map); + cpumask_set_cpu(smp_processor_id(), &cpu_callin_map); set_numa_node(cpu_to_node_map[smp_processor_id()]); per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE; paravirt_post_smp_prepare_boot_cpu(); @@ -577,10 +577,10 @@ clear_cpu_sibling_map(int cpu) { int i; - for_each_cpu_mask(i, per_cpu(cpu_sibling_map, cpu)) - cpu_clear(cpu, per_cpu(cpu_sibling_map, i)); - for_each_cpu_mask(i, cpu_core_map[cpu]) - cpu_clear(cpu, cpu_core_map[i]); + for_each_cpu(i, &per_cpu(cpu_sibling_map, cpu)) + cpumask_clear_cpu(cpu, &per_cpu(cpu_sibling_map, i)); + for_each_cpu(i, &cpu_core_map[cpu]) + cpumask_clear_cpu(cpu, &cpu_core_map[i]); per_cpu(cpu_sibling_map, cpu) = cpu_core_map[cpu] = CPU_MASK_NONE; } @@ -592,12 +592,12 @@ remove_siblinginfo(int cpu) if (cpu_data(cpu)->threads_per_core == 1 && cpu_data(cpu)->cores_per_socket == 1) { - cpu_clear(cpu, cpu_core_map[cpu]); - cpu_clear(cpu, per_cpu(cpu_sibling_map, cpu)); + cpumask_clear_cpu(cpu, &cpu_core_map[cpu]); + cpumask_clear_cpu(cpu, &per_cpu(cpu_sibling_map, cpu)); return; } - last = (cpus_weight(cpu_core_map[cpu]) == 1 ? 1 : 0); + last = (cpumask_weight(&cpu_core_map[cpu]) == 1 ? 1 : 0); /* remove it from all sibling map's */ clear_cpu_sibling_map(cpu); @@ -673,7 +673,7 @@ int __cpu_disable(void) remove_siblinginfo(cpu); fixup_irqs(); local_flush_tlb_all(); - cpu_clear(cpu, cpu_callin_map); + cpumask_clear_cpu(cpu, &cpu_callin_map); return 0; } @@ -718,11 +718,13 @@ static inline void set_cpu_sibling_map(int cpu) for_each_online_cpu(i) { if ((cpu_data(cpu)->socket_id == cpu_data(i)->socket_id)) { - cpu_set(i, cpu_core_map[cpu]); - cpu_set(cpu, cpu_core_map[i]); + cpumask_set_cpu(i, &cpu_core_map[cpu]); + cpumask_set_cpu(cpu, &cpu_core_map[i]); if (cpu_data(cpu)->core_id == cpu_data(i)->core_id) { - cpu_set(i, per_cpu(cpu_sibling_map, cpu)); - cpu_set(cpu, per_cpu(cpu_sibling_map, i)); + cpumask_set_cpu(i, + &per_cpu(cpu_sibling_map, cpu)); + cpumask_set_cpu(cpu, + &per_cpu(cpu_sibling_map, i)); } } } @@ -742,7 +744,7 @@ __cpu_up(unsigned int cpu, struct task_struct *tidle) * Already booted cpu? not valid anymore since we dont * do idle loop tightspin anymore. */ - if (cpu_isset(cpu, cpu_callin_map)) + if (cpumask_test_cpu(cpu, &cpu_callin_map)) return -EINVAL; per_cpu(cpu_state, cpu) = CPU_UP_PREPARE; @@ -753,8 +755,8 @@ __cpu_up(unsigned int cpu, struct task_struct *tidle) if (cpu_data(cpu)->threads_per_core == 1 && cpu_data(cpu)->cores_per_socket == 1) { - cpu_set(cpu, per_cpu(cpu_sibling_map, cpu)); - cpu_set(cpu, cpu_core_map[cpu]); + cpumask_set_cpu(cpu, &per_cpu(cpu_sibling_map, cpu)); + cpumask_set_cpu(cpu, &cpu_core_map[cpu]); return 0; } diff --git a/arch/ia64/kernel/topology.c b/arch/ia64/kernel/topology.c index 965ab42fabb0..c01fe8991244 100644 --- a/arch/ia64/kernel/topology.c +++ b/arch/ia64/kernel/topology.c @@ -148,7 +148,7 @@ static void cache_shared_cpu_map_setup(unsigned int cpu, if (cpu_data(cpu)->threads_per_core <= 1 && cpu_data(cpu)->cores_per_socket <= 1) { - cpu_set(cpu, this_leaf->shared_cpu_map); + cpumask_set_cpu(cpu, &this_leaf->shared_cpu_map); return; } @@ -164,7 +164,7 @@ static void cache_shared_cpu_map_setup(unsigned int cpu, if (cpu_data(cpu)->socket_id == cpu_data(j)->socket_id && cpu_data(j)->core_id == csi.log1_cid && cpu_data(j)->thread_id == csi.log1_tid) - cpu_set(j, this_leaf->shared_cpu_map); + cpumask_set_cpu(j, &this_leaf->shared_cpu_map); i++; } while (i < num_shared && @@ -177,7 +177,7 @@ static void cache_shared_cpu_map_setup(unsigned int cpu, static void cache_shared_cpu_map_setup(unsigned int cpu, struct cache_info * this_leaf) { - cpu_set(cpu, this_leaf->shared_cpu_map); + cpumask_set_cpu(cpu, &this_leaf->shared_cpu_map); return; } #endif diff --git a/arch/m32r/kernel/smpboot.c b/arch/m32r/kernel/smpboot.c index bb21f4f63170..a468467542f4 100644 --- a/arch/m32r/kernel/smpboot.c +++ b/arch/m32r/kernel/smpboot.c @@ -376,7 +376,7 @@ void __init smp_cpus_done(unsigned int max_cpus) if (!cpumask_equal(&cpu_callin_map, cpu_online_mask)) BUG(); - for (cpu_id = 0 ; cpu_id < num_online_cpus() ; cpu_id++) + for_each_online_cpu(cpu_id) show_cpu_info(cpu_id); /* diff --git a/arch/m68k/coldfire/m527x.c b/arch/m68k/coldfire/m527x.c index 2ba470735bed..c0b3e28f91df 100644 --- a/arch/m68k/coldfire/m527x.c +++ b/arch/m68k/coldfire/m527x.c @@ -92,7 +92,6 @@ static void __init m527x_uarts_init(void) static void __init m527x_fec_init(void) { - u16 par; u8 v; /* Set multi-function pins to ethernet mode for fec0 */ @@ -100,6 +99,8 @@ static void __init m527x_fec_init(void) v = readb(MCFGPIO_PAR_FECI2C); writeb(v | 0xf0, MCFGPIO_PAR_FECI2C); #else + u16 par; + par = readw(MCFGPIO_PAR_FECI2C); writew(par | 0xf00, MCFGPIO_PAR_FECI2C); v = readb(MCFGPIO_PAR_FEC0HL); diff --git a/arch/m68k/include/asm/m527xsim.h b/arch/m68k/include/asm/m527xsim.h index 1bebbe78055a..2c648a043f24 100644 --- a/arch/m68k/include/asm/m527xsim.h +++ b/arch/m68k/include/asm/m527xsim.h @@ -103,8 +103,10 @@ */ #define MCFFEC_BASE0 (MCF_IPSBAR + 0x1000) #define MCFFEC_SIZE0 0x800 +#ifdef CONFIG_M5275 #define MCFFEC_BASE1 (MCF_IPSBAR + 0x1800) #define MCFFEC_SIZE1 0x800 +#endif /* * QSPI module. diff --git a/arch/m68k/include/asm/m68360_pram.h b/arch/m68k/include/asm/m68360_pram.h index e6088bbce93d..c0cbd96f09bc 100644 --- a/arch/m68k/include/asm/m68360_pram.h +++ b/arch/m68k/include/asm/m68360_pram.h @@ -170,7 +170,7 @@ struct uart_pram { unsigned short frmer; /* Rx framing error counter */ unsigned short nosec; /* Rx noise counter */ unsigned short brkec; /* Rx break character counter */ - unsigned short brkln; /* Reaceive break length */ + unsigned short brkln; /* Receive break length */ unsigned short uaddr1; /* address character 1 */ unsigned short uaddr2; /* address character 2 */ @@ -338,7 +338,7 @@ struct ethernet_pram { unsigned long c_pres; /* preset CRC */ unsigned long c_mask; /* constant mask for CRC */ unsigned long crcec; /* CRC error counter */ - unsigned long alec; /* alighnment error counter */ + unsigned long alec; /* alignment error counter */ unsigned long disfc; /* discard frame counter */ unsigned short pads; /* short frame PAD characters */ unsigned short ret_lim; /* retry limit threshold */ diff --git a/arch/mips/bcm63xx/irq.c b/arch/mips/bcm63xx/irq.c index b94bf44d8d8e..e3e808a6c542 100644 --- a/arch/mips/bcm63xx/irq.c +++ b/arch/mips/bcm63xx/irq.c @@ -58,9 +58,9 @@ static inline int enable_irq_for_cpu(int cpu, struct irq_data *d, #ifdef CONFIG_SMP if (m) - enable &= cpu_isset(cpu, *m); + enable &= cpumask_test_cpu(cpu, m); else if (irqd_affinity_was_set(d)) - enable &= cpu_isset(cpu, *d->affinity); + enable &= cpumask_test_cpu(cpu, d->affinity); #endif return enable; } diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c index 8b1eeffa12ed..56f5d080ef9d 100644 --- a/arch/mips/cavium-octeon/smp.c +++ b/arch/mips/cavium-octeon/smp.c @@ -72,7 +72,7 @@ static inline void octeon_send_ipi_mask(const struct cpumask *mask, { unsigned int i; - for_each_cpu_mask(i, *mask) + for_each_cpu(i, mask) octeon_send_ipi_single(i, action); } @@ -239,7 +239,7 @@ static int octeon_cpu_disable(void) return -ENOTSUPP; set_cpu_online(cpu, false); - cpu_clear(cpu, cpu_callin_map); + cpumask_clear_cpu(cpu, &cpu_callin_map); octeon_fixup_irqs(); flush_cache_all(); diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h index eacf865d21c2..bb02fac9b4fa 100644 --- a/arch/mips/include/asm/smp.h +++ b/arch/mips/include/asm/smp.h @@ -88,7 +88,7 @@ static inline void arch_send_call_function_single_ipi(int cpu) { extern struct plat_smp_ops *mp_ops; /* private */ - mp_ops->send_ipi_mask(&cpumask_of_cpu(cpu), SMP_CALL_FUNCTION); + mp_ops->send_ipi_mask(cpumask_of(cpu), SMP_CALL_FUNCTION); } static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask) diff --git a/arch/mips/kernel/crash.c b/arch/mips/kernel/crash.c index d21264681e97..d434d5d5ae6e 100644 --- a/arch/mips/kernel/crash.c +++ b/arch/mips/kernel/crash.c @@ -25,9 +25,9 @@ static void crash_shutdown_secondary(void *ignore) return; local_irq_disable(); - if (!cpu_isset(cpu, cpus_in_crash)) + if (!cpumask_test_cpu(cpu, &cpus_in_crash)) crash_save_cpu(regs, cpu); - cpu_set(cpu, cpus_in_crash); + cpumask_set_cpu(cpu, &cpus_in_crash); while (!atomic_read(&kexec_ready_to_reboot)) cpu_relax(); @@ -50,7 +50,7 @@ static void crash_kexec_prepare_cpus(void) */ pr_emerg("Sending IPI to other cpus...\n"); msecs = 10000; - while ((cpus_weight(cpus_in_crash) < ncpus) && (--msecs > 0)) { + while ((cpumask_weight(&cpus_in_crash) < ncpus) && (--msecs > 0)) { cpu_relax(); mdelay(1); } @@ -66,5 +66,5 @@ void default_machine_crash_shutdown(struct pt_regs *regs) crashing_cpu = smp_processor_id(); crash_save_cpu(regs, crashing_cpu); crash_kexec_prepare_cpus(); - cpu_set(crashing_cpu, cpus_in_crash); + cpumask_set_cpu(crashing_cpu, &cpus_in_crash); } diff --git a/arch/mips/kernel/mips-mt-fpaff.c b/arch/mips/kernel/mips-mt-fpaff.c index 362bb3707e62..3e4491aa6d6b 100644 --- a/arch/mips/kernel/mips-mt-fpaff.c +++ b/arch/mips/kernel/mips-mt-fpaff.c @@ -114,8 +114,8 @@ asmlinkage long mipsmt_sys_sched_setaffinity(pid_t pid, unsigned int len, /* Compute new global allowed CPU set if necessary */ ti = task_thread_info(p); if (test_ti_thread_flag(ti, TIF_FPUBOUND) && - cpus_intersects(*new_mask, mt_fpu_cpumask)) { - cpus_and(*effective_mask, *new_mask, mt_fpu_cpumask); + cpumask_intersects(new_mask, &mt_fpu_cpumask)) { + cpumask_and(effective_mask, new_mask, &mt_fpu_cpumask); retval = set_cpus_allowed_ptr(p, effective_mask); } else { cpumask_copy(effective_mask, new_mask); diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index d295bd1e4996..f2975d4d1e44 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -49,7 +49,7 @@ void arch_cpu_idle_dead(void) { /* What the heck is this check doing ? */ - if (!cpu_isset(smp_processor_id(), cpu_callin_map)) + if (!cpumask_test_cpu(smp_processor_id(), &cpu_callin_map)) play_dead(); } #endif diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c index b8bd9340c9c7..fd528d7ea278 100644 --- a/arch/mips/kernel/smp-bmips.c +++ b/arch/mips/kernel/smp-bmips.c @@ -362,7 +362,7 @@ static int bmips_cpu_disable(void) pr_info("SMP: CPU%d is offline\n", cpu); set_cpu_online(cpu, false); - cpu_clear(cpu, cpu_callin_map); + cpumask_clear_cpu(cpu, &cpu_callin_map); clear_c0_status(IE_IRQ5); local_flush_tlb_all(); diff --git a/arch/mips/kernel/smp-cmp.c b/arch/mips/kernel/smp-cmp.c index e36a859af666..d5e0f949dc48 100644 --- a/arch/mips/kernel/smp-cmp.c +++ b/arch/mips/kernel/smp-cmp.c @@ -66,7 +66,7 @@ static void cmp_smp_finish(void) #ifdef CONFIG_MIPS_MT_FPAFF /* If we have an FPU, enroll ourselves in the FPU-full mask */ if (cpu_has_fpu) - cpu_set(smp_processor_id(), mt_fpu_cpumask); + cpumask_set_cpu(smp_processor_id(), &mt_fpu_cpumask); #endif /* CONFIG_MIPS_MT_FPAFF */ local_irq_enable(); @@ -110,7 +110,7 @@ void __init cmp_smp_setup(void) #ifdef CONFIG_MIPS_MT_FPAFF /* If we have an FPU, enroll ourselves in the FPU-full mask */ if (cpu_has_fpu) - cpu_set(0, mt_fpu_cpumask); + cpumask_set_cpu(0, &mt_fpu_cpumask); #endif /* CONFIG_MIPS_MT_FPAFF */ for (i = 1; i < NR_CPUS; i++) { diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c index d5589bedd0a4..7e011f95bb8e 100644 --- a/arch/mips/kernel/smp-cps.c +++ b/arch/mips/kernel/smp-cps.c @@ -290,7 +290,7 @@ static void cps_smp_finish(void) #ifdef CONFIG_MIPS_MT_FPAFF /* If we have an FPU, enroll ourselves in the FPU-full mask */ if (cpu_has_fpu) - cpu_set(smp_processor_id(), mt_fpu_cpumask); + cpumask_set_cpu(smp_processor_id(), &mt_fpu_cpumask); #endif /* CONFIG_MIPS_MT_FPAFF */ local_irq_enable(); @@ -313,7 +313,7 @@ static int cps_cpu_disable(void) atomic_sub(1 << cpu_vpe_id(¤t_cpu_data), &core_cfg->vpe_mask); smp_mb__after_atomic(); set_cpu_online(cpu, false); - cpu_clear(cpu, cpu_callin_map); + cpumask_clear_cpu(cpu, &cpu_callin_map); return 0; } diff --git a/arch/mips/kernel/smp-mt.c b/arch/mips/kernel/smp-mt.c index 17ea705f6c40..86311a164ef1 100644 --- a/arch/mips/kernel/smp-mt.c +++ b/arch/mips/kernel/smp-mt.c @@ -178,7 +178,7 @@ static void vsmp_smp_finish(void) #ifdef CONFIG_MIPS_MT_FPAFF /* If we have an FPU, enroll ourselves in the FPU-full mask */ if (cpu_has_fpu) - cpu_set(smp_processor_id(), mt_fpu_cpumask); + cpumask_set_cpu(smp_processor_id(), &mt_fpu_cpumask); #endif /* CONFIG_MIPS_MT_FPAFF */ local_irq_enable(); @@ -239,7 +239,7 @@ static void __init vsmp_smp_setup(void) #ifdef CONFIG_MIPS_MT_FPAFF /* If we have an FPU, enroll ourselves in the FPU-full mask */ if (cpu_has_fpu) - cpu_set(0, mt_fpu_cpumask); + cpumask_set_cpu(0, &mt_fpu_cpumask); #endif /* CONFIG_MIPS_MT_FPAFF */ if (!cpu_has_mipsmt) return; diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index 5b020bda3e05..193ace7955fb 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -75,30 +75,30 @@ static inline void set_cpu_sibling_map(int cpu) { int i; - cpu_set(cpu, cpu_sibling_setup_map); + cpumask_set_cpu(cpu, &cpu_sibling_setup_map); if (smp_num_siblings > 1) { - for_each_cpu_mask(i, cpu_sibling_setup_map) { + for_each_cpu(i, &cpu_sibling_setup_map) { if (cpu_data[cpu].package == cpu_data[i].package && cpu_data[cpu].core == cpu_data[i].core) { - cpu_set(i, cpu_sibling_map[cpu]); - cpu_set(cpu, cpu_sibling_map[i]); + cpumask_set_cpu(i, &cpu_sibling_map[cpu]); + cpumask_set_cpu(cpu, &cpu_sibling_map[i]); } } } else - cpu_set(cpu, cpu_sibling_map[cpu]); + cpumask_set_cpu(cpu, &cpu_sibling_map[cpu]); } static inline void set_cpu_core_map(int cpu) { int i; - cpu_set(cpu, cpu_core_setup_map); + cpumask_set_cpu(cpu, &cpu_core_setup_map); - for_each_cpu_mask(i, cpu_core_setup_map) { + for_each_cpu(i, &cpu_core_setup_map) { if (cpu_data[cpu].package == cpu_data[i].package) { - cpu_set(i, cpu_core_map[cpu]); - cpu_set(cpu, cpu_core_map[i]); + cpumask_set_cpu(i, &cpu_core_map[cpu]); + cpumask_set_cpu(cpu, &cpu_core_map[i]); } } } @@ -138,7 +138,7 @@ asmlinkage void start_secondary(void) cpu = smp_processor_id(); cpu_data[cpu].udelay_val = loops_per_jiffy; - cpu_set(cpu, cpu_coherent_mask); + cpumask_set_cpu(cpu, &cpu_coherent_mask); notify_cpu_starting(cpu); set_cpu_online(cpu, true); @@ -146,7 +146,7 @@ asmlinkage void start_secondary(void) set_cpu_sibling_map(cpu); set_cpu_core_map(cpu); - cpu_set(cpu, cpu_callin_map); + cpumask_set_cpu(cpu, &cpu_callin_map); synchronise_count_slave(cpu); @@ -208,7 +208,7 @@ void smp_prepare_boot_cpu(void) { set_cpu_possible(0, true); set_cpu_online(0, true); - cpu_set(0, cpu_callin_map); + cpumask_set_cpu(0, &cpu_callin_map); } int __cpu_up(unsigned int cpu, struct task_struct *tidle) @@ -218,7 +218,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle) /* * Trust is futile. We should really have timeouts ... */ - while (!cpu_isset(cpu, cpu_callin_map)) + while (!cpumask_test_cpu(cpu, &cpu_callin_map)) udelay(100); synchronise_count_master(cpu); diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index e334c641a81b..ba32e48d4697 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -1153,13 +1153,13 @@ static void mt_ase_fp_affinity(void) * restricted the allowed set to exclude any CPUs with FPUs, * we'll skip the procedure. */ - if (cpus_intersects(current->cpus_allowed, mt_fpu_cpumask)) { + if (cpumask_intersects(¤t->cpus_allowed, &mt_fpu_cpumask)) { cpumask_t tmask; current->thread.user_cpus_allowed = current->cpus_allowed; - cpus_and(tmask, current->cpus_allowed, - mt_fpu_cpumask); + cpumask_and(&tmask, ¤t->cpus_allowed, + &mt_fpu_cpumask); set_cpus_allowed_ptr(current, &tmask); set_thread_flag(TIF_FPUBOUND); } diff --git a/arch/mips/loongson/loongson-3/numa.c b/arch/mips/loongson/loongson-3/numa.c index 6cae0e75de27..12d14ed48778 100644 --- a/arch/mips/loongson/loongson-3/numa.c +++ b/arch/mips/loongson/loongson-3/numa.c @@ -233,7 +233,7 @@ static __init void prom_meminit(void) if (node_online(node)) { szmem(node); node_mem_init(node); - cpus_clear(__node_data[(node)]->cpumask); + cpumask_clear(&__node_data[(node)]->cpumask); } } for (cpu = 0; cpu < loongson_sysconf.nr_cpus; cpu++) { @@ -244,7 +244,7 @@ static __init void prom_meminit(void) if (loongson_sysconf.reserved_cpus_mask & (1<<cpu)) continue; - cpu_set(active_cpu, __node_data[(node)]->cpumask); + cpumask_set_cpu(active_cpu, &__node_data[(node)]->cpumask); pr_info("NUMA: set cpumask cpu %d on node %d\n", active_cpu, node); active_cpu++; diff --git a/arch/mips/loongson/loongson-3/smp.c b/arch/mips/loongson/loongson-3/smp.c index e2eb688b5434..e3c68b5da18d 100644 --- a/arch/mips/loongson/loongson-3/smp.c +++ b/arch/mips/loongson/loongson-3/smp.c @@ -408,7 +408,7 @@ static int loongson3_cpu_disable(void) return -EBUSY; set_cpu_online(cpu, false); - cpu_clear(cpu, cpu_callin_map); + cpumask_clear_cpu(cpu, &cpu_callin_map); local_irq_save(flags); fixup_irqs(); local_irq_restore(flags); diff --git a/arch/mips/paravirt/paravirt-smp.c b/arch/mips/paravirt/paravirt-smp.c index 0164b0c48352..42181c7105df 100644 --- a/arch/mips/paravirt/paravirt-smp.c +++ b/arch/mips/paravirt/paravirt-smp.c @@ -75,7 +75,7 @@ static void paravirt_send_ipi_mask(const struct cpumask *mask, unsigned int acti { unsigned int cpu; - for_each_cpu_mask(cpu, *mask) + for_each_cpu(cpu, mask) paravirt_send_ipi_single(cpu, action); } diff --git a/arch/mips/sgi-ip27/ip27-init.c b/arch/mips/sgi-ip27/ip27-init.c index ee736bd103f8..570098bfdf87 100644 --- a/arch/mips/sgi-ip27/ip27-init.c +++ b/arch/mips/sgi-ip27/ip27-init.c @@ -60,7 +60,7 @@ static void per_hub_init(cnodeid_t cnode) nasid_t nasid = COMPACT_TO_NASID_NODEID(cnode); int i; - cpu_set(smp_processor_id(), hub->h_cpus); + cpumask_set_cpu(smp_processor_id(), &hub->h_cpus); if (test_and_set_bit(cnode, hub_init_mask)) return; diff --git a/arch/mips/sgi-ip27/ip27-klnuma.c b/arch/mips/sgi-ip27/ip27-klnuma.c index ecbb62f339c5..bda90cf87e8c 100644 --- a/arch/mips/sgi-ip27/ip27-klnuma.c +++ b/arch/mips/sgi-ip27/ip27-klnuma.c @@ -29,8 +29,8 @@ static cpumask_t ktext_repmask; void __init setup_replication_mask(void) { /* Set only the master cnode's bit. The master cnode is always 0. */ - cpus_clear(ktext_repmask); - cpu_set(0, ktext_repmask); + cpumask_clear(&ktext_repmask); + cpumask_set_cpu(0, &ktext_repmask); #ifdef CONFIG_REPLICATE_KTEXT #ifndef CONFIG_MAPPED_KERNEL @@ -43,7 +43,7 @@ void __init setup_replication_mask(void) if (cnode == 0) continue; /* Advertise that we have a copy of the kernel */ - cpu_set(cnode, ktext_repmask); + cpumask_set_cpu(cnode, &ktext_repmask); } } #endif @@ -99,7 +99,7 @@ void __init replicate_kernel_text() client_nasid = COMPACT_TO_NASID_NODEID(cnode); /* Check if this node should get a copy of the kernel */ - if (cpu_isset(cnode, ktext_repmask)) { + if (cpumask_test_cpu(cnode, &ktext_repmask)) { server_nasid = client_nasid; copy_kernel(server_nasid); } @@ -124,7 +124,7 @@ unsigned long node_getfirstfree(cnodeid_t cnode) loadbase += 16777216; #endif offset = PAGE_ALIGN((unsigned long)(&_end)) - loadbase; - if ((cnode == 0) || (cpu_isset(cnode, ktext_repmask))) + if ((cnode == 0) || (cpumask_test_cpu(cnode, &ktext_repmask))) return TO_NODE(nasid, offset) >> PAGE_SHIFT; else return KDM_TO_PHYS(PAGE_ALIGN(SYMMON_STK_ADDR(nasid, 0))) >> PAGE_SHIFT; diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c index 0b68469e063f..8d0eb2643248 100644 --- a/arch/mips/sgi-ip27/ip27-memory.c +++ b/arch/mips/sgi-ip27/ip27-memory.c @@ -404,7 +404,7 @@ static void __init node_mem_init(cnodeid_t node) NODE_DATA(node)->node_start_pfn = start_pfn; NODE_DATA(node)->node_spanned_pages = end_pfn - start_pfn; - cpus_clear(hub_data(node)->h_cpus); + cpumask_clear(&hub_data(node)->h_cpus); slot_freepfn += PFN_UP(sizeof(struct pglist_data) + sizeof(struct hub_data)); diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c index cfe056fe7f5c..f3191db6e2e9 100644 --- a/arch/parisc/kernel/irq.c +++ b/arch/parisc/kernel/irq.c @@ -525,8 +525,8 @@ void do_cpu_irq_mask(struct pt_regs *regs) desc = irq_to_desc(irq); cpumask_copy(&dest, desc->irq_data.affinity); if (irqd_is_per_cpu(&desc->irq_data) && - !cpu_isset(smp_processor_id(), dest)) { - int cpu = first_cpu(dest); + !cpumask_test_cpu(smp_processor_id(), &dest)) { + int cpu = cpumask_first(&dest); printk(KERN_DEBUG "redirecting irq %d from CPU %d to %d\n", irq, smp_processor_id(), cpu); diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h index 4c8ad592ae33..5be6c4753667 100644 --- a/arch/powerpc/include/asm/cputhreads.h +++ b/arch/powerpc/include/asm/cputhreads.h @@ -25,7 +25,7 @@ extern cpumask_t threads_core_mask; #define threads_per_core 1 #define threads_per_subcore 1 #define threads_shift 0 -#define threads_core_mask (CPU_MASK_CPU0) +#define threads_core_mask (*get_cpu_mask(0)) #endif /* cpu_thread_mask_to_cores - Return a cpumask of one per cores diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index de2726a487b0..8e58c614c37d 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -115,7 +115,7 @@ config S390 select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE - select HAVE_BPF_JIT if PACK_STACK + select HAVE_BPF_JIT if PACK_STACK && HAVE_MARCH_Z9_109_FEATURES select HAVE_CMPXCHG_DOUBLE select HAVE_CMPXCHG_LOCAL select HAVE_DEBUG_KMEMLEAK diff --git a/arch/s390/include/asm/dma-mapping.h b/arch/s390/include/asm/dma-mapping.h index 709955ddaa4d..9d395961e713 100644 --- a/arch/s390/include/asm/dma-mapping.h +++ b/arch/s390/include/asm/dma-mapping.h @@ -42,7 +42,7 @@ static inline int dma_supported(struct device *dev, u64 mask) static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) { if (!dev->dma_mask) - return 0; + return false; return addr + size - 1 <= *dev->dma_mask; } diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index ef803c202d42..a648338c434a 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -7,6 +7,7 @@ #define PCI_BAR_COUNT 6 #include <linux/pci.h> +#include <linux/mutex.h> #include <asm-generic/pci.h> #include <asm-generic/pci-dma-compat.h> #include <asm/pci_clp.h> @@ -44,10 +45,6 @@ struct zpci_fmb { u64 rpcit_ops; u64 dma_rbytes; u64 dma_wbytes; - /* software counters */ - atomic64_t allocated_pages; - atomic64_t mapped_pages; - atomic64_t unmapped_pages; } __packed __aligned(16); enum zpci_state { @@ -80,6 +77,7 @@ struct zpci_dev { u8 pft; /* pci function type */ u16 domain; + struct mutex lock; u8 pfip[CLP_PFIP_NR_SEGMENTS]; /* pci function internal path */ u32 uid; /* user defined id */ u8 util_str[CLP_UTIL_STR_LEN]; /* utility string */ @@ -111,6 +109,10 @@ struct zpci_dev { /* Function measurement block */ struct zpci_fmb *fmb; u16 fmb_update; /* update interval */ + /* software counters */ + atomic64_t allocated_pages; + atomic64_t mapped_pages; + atomic64_t unmapped_pages; enum pci_bus_speed max_bus_speed; diff --git a/arch/s390/net/bpf_jit.S b/arch/s390/net/bpf_jit.S index ba44c9f55346..a1c917d881ec 100644 --- a/arch/s390/net/bpf_jit.S +++ b/arch/s390/net/bpf_jit.S @@ -1,134 +1,115 @@ /* * BPF Jit compiler for s390, help functions. * - * Copyright IBM Corp. 2012 + * Copyright IBM Corp. 2012,2015 * * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com> + * Michael Holzheu <holzheu@linux.vnet.ibm.com> */ + #include <linux/linkage.h> +#include "bpf_jit.h" /* * Calling convention: - * registers %r2, %r6-%r8, %r10-%r11, %r13, %r15 are call saved - * %r2: skb pointer - * %r3: offset parameter - * %r5: BPF A accumulator - * %r8: return address - * %r9: save register for skb pointer - * %r10: skb->data - * %r11: skb->len - skb->data_len (headlen) - * %r12: BPF X accumulator + * registers %r7-%r10, %r11,%r13, and %r15 are call saved + * + * Input (64 bit): + * %r3 (%b2) = offset into skb data + * %r6 (%b5) = return address + * %r7 (%b6) = skb pointer + * %r12 = skb data pointer + * + * Output: + * %r14= %b0 = return value (read skb value) + * + * Work registers: %r2,%r4,%r5,%r14 * * skb_copy_bits takes 4 parameters: * %r2 = skb pointer * %r3 = offset into skb data * %r4 = pointer to temp buffer * %r5 = length to copy + * Return value in %r2: 0 = ok + * + * bpf_internal_load_pointer_neg_helper takes 3 parameters: + * %r2 = skb pointer + * %r3 = offset into data + * %r4 = length to copy + * Return value in %r2: Pointer to data */ -#define SKBDATA %r8 - - /* A = *(u32 *) (skb->data+K+X) */ -ENTRY(sk_load_word_ind) - ar %r3,%r12 # offset += X - bmr %r8 # < 0 -> return with cc - - /* A = *(u32 *) (skb->data+K) */ -ENTRY(sk_load_word) - llgfr %r1,%r3 # extend offset - ahi %r3,4 # offset + 4 - clr %r11,%r3 # hlen <= offset + 4 ? - jl sk_load_word_slow - l %r5,0(%r1,%r10) # get word from skb - xr %r1,%r1 # set cc to zero - br %r8 -sk_load_word_slow: - lgr %r9,%r2 # save %r2 - lgr %r3,%r1 # offset - la %r4,160(%r15) # pointer to temp buffer - lghi %r5,4 # 4 bytes - brasl %r14,skb_copy_bits # get data from skb - l %r5,160(%r15) # load result from temp buffer - ltgr %r2,%r2 # set cc to (%r2 != 0) - lgr %r2,%r9 # restore %r2 - br %r8 +#define SKF_MAX_NEG_OFF -0x200000 /* SKF_LL_OFF from filter.h */ - /* A = *(u16 *) (skb->data+K+X) */ -ENTRY(sk_load_half_ind) - ar %r3,%r12 # offset += X - bmr %r8 # < 0 -> return with cc - - /* A = *(u16 *) (skb->data+K) */ -ENTRY(sk_load_half) - llgfr %r1,%r3 # extend offset - ahi %r3,2 # offset + 2 - clr %r11,%r3 # hlen <= offset + 2 ? - jl sk_load_half_slow - llgh %r5,0(%r1,%r10) # get half from skb - xr %r1,%r1 # set cc to zero - br %r8 - -sk_load_half_slow: - lgr %r9,%r2 # save %r2 - lgr %r3,%r1 # offset - la %r4,162(%r15) # pointer to temp buffer - lghi %r5,2 # 2 bytes - brasl %r14,skb_copy_bits # get data from skb - xc 160(2,%r15),160(%r15) - l %r5,160(%r15) # load result from temp buffer - ltgr %r2,%r2 # set cc to (%r2 != 0) - lgr %r2,%r9 # restore %r2 - br %r8 +/* + * Load SIZE bytes from SKB + */ +#define sk_load_common(NAME, SIZE, LOAD) \ +ENTRY(sk_load_##NAME); \ + ltgr %r3,%r3; /* Is offset negative? */ \ + jl sk_load_##NAME##_slow_neg; \ +ENTRY(sk_load_##NAME##_pos); \ + aghi %r3,SIZE; /* Offset + SIZE */ \ + clg %r3,STK_OFF_HLEN(%r15); /* Offset + SIZE > hlen? */ \ + jh sk_load_##NAME##_slow; \ + LOAD %r14,-SIZE(%r3,%r12); /* Get data from skb */ \ + b OFF_OK(%r6); /* Return */ \ + \ +sk_load_##NAME##_slow:; \ + lgr %r2,%r7; /* Arg1 = skb pointer */ \ + aghi %r3,-SIZE; /* Arg2 = offset */ \ + la %r4,STK_OFF_TMP(%r15); /* Arg3 = temp bufffer */ \ + lghi %r5,SIZE; /* Arg4 = size */ \ + brasl %r14,skb_copy_bits; /* Get data from skb */ \ + LOAD %r14,STK_OFF_TMP(%r15); /* Load from temp bufffer */ \ + ltgr %r2,%r2; /* Set cc to (%r2 != 0) */ \ + br %r6; /* Return */ - /* A = *(u8 *) (skb->data+K+X) */ -ENTRY(sk_load_byte_ind) - ar %r3,%r12 # offset += X - bmr %r8 # < 0 -> return with cc +sk_load_common(word, 4, llgf) /* r14 = *(u32 *) (skb->data+offset) */ +sk_load_common(half, 2, llgh) /* r14 = *(u16 *) (skb->data+offset) */ - /* A = *(u8 *) (skb->data+K) */ +/* + * Load 1 byte from SKB (optimized version) + */ + /* r14 = *(u8 *) (skb->data+offset) */ ENTRY(sk_load_byte) - llgfr %r1,%r3 # extend offset - clr %r11,%r3 # hlen < offset ? - jle sk_load_byte_slow - lhi %r5,0 - ic %r5,0(%r1,%r10) # get byte from skb - xr %r1,%r1 # set cc to zero - br %r8 + ltgr %r3,%r3 # Is offset negative? + jl sk_load_byte_slow_neg +ENTRY(sk_load_byte_pos) + clg %r3,STK_OFF_HLEN(%r15) # Offset >= hlen? + jnl sk_load_byte_slow + llgc %r14,0(%r3,%r12) # Get byte from skb + b OFF_OK(%r6) # Return OK sk_load_byte_slow: - lgr %r9,%r2 # save %r2 - lgr %r3,%r1 # offset - la %r4,163(%r15) # pointer to temp buffer - lghi %r5,1 # 1 byte - brasl %r14,skb_copy_bits # get data from skb - xc 160(3,%r15),160(%r15) - l %r5,160(%r15) # load result from temp buffer - ltgr %r2,%r2 # set cc to (%r2 != 0) - lgr %r2,%r9 # restore %r2 - br %r8 + lgr %r2,%r7 # Arg1 = skb pointer + # Arg2 = offset + la %r4,STK_OFF_TMP(%r15) # Arg3 = pointer to temp buffer + lghi %r5,1 # Arg4 = size (1 byte) + brasl %r14,skb_copy_bits # Get data from skb + llgc %r14,STK_OFF_TMP(%r15) # Load result from temp buffer + ltgr %r2,%r2 # Set cc to (%r2 != 0) + br %r6 # Return cc + +#define sk_negative_common(NAME, SIZE, LOAD) \ +sk_load_##NAME##_slow_neg:; \ + cgfi %r3,SKF_MAX_NEG_OFF; \ + jl bpf_error; \ + lgr %r2,%r7; /* Arg1 = skb pointer */ \ + /* Arg2 = offset */ \ + lghi %r4,SIZE; /* Arg3 = size */ \ + brasl %r14,bpf_internal_load_pointer_neg_helper; \ + ltgr %r2,%r2; \ + jz bpf_error; \ + LOAD %r14,0(%r2); /* Get data from pointer */ \ + xr %r3,%r3; /* Set cc to zero */ \ + br %r6; /* Return cc */ - /* X = (*(u8 *)(skb->data+K) & 0xf) << 2 */ -ENTRY(sk_load_byte_msh) - llgfr %r1,%r3 # extend offset - clr %r11,%r3 # hlen < offset ? - jle sk_load_byte_msh_slow - lhi %r12,0 - ic %r12,0(%r1,%r10) # get byte from skb - nill %r12,0x0f - sll %r12,2 - xr %r1,%r1 # set cc to zero - br %r8 +sk_negative_common(word, 4, llgf) +sk_negative_common(half, 2, llgh) +sk_negative_common(byte, 1, llgc) -sk_load_byte_msh_slow: - lgr %r9,%r2 # save %r2 - lgr %r3,%r1 # offset - la %r4,163(%r15) # pointer to temp buffer - lghi %r5,1 # 1 byte - brasl %r14,skb_copy_bits # get data from skb - xc 160(3,%r15),160(%r15) - l %r12,160(%r15) # load result from temp buffer - nill %r12,0x0f - sll %r12,2 - ltgr %r2,%r2 # set cc to (%r2 != 0) - lgr %r2,%r9 # restore %r2 - br %r8 +bpf_error: +# force a return 0 from jit handler + ltgr %r15,%r15 # Set condition code + br %r6 diff --git a/arch/s390/net/bpf_jit.h b/arch/s390/net/bpf_jit.h new file mode 100644 index 000000000000..ba8593a515ba --- /dev/null +++ b/arch/s390/net/bpf_jit.h @@ -0,0 +1,58 @@ +/* + * BPF Jit compiler defines + * + * Copyright IBM Corp. 2012,2015 + * + * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com> + * Michael Holzheu <holzheu@linux.vnet.ibm.com> + */ + +#ifndef __ARCH_S390_NET_BPF_JIT_H +#define __ARCH_S390_NET_BPF_JIT_H + +#ifndef __ASSEMBLY__ + +#include <linux/filter.h> +#include <linux/types.h> + +extern u8 sk_load_word_pos[], sk_load_half_pos[], sk_load_byte_pos[]; +extern u8 sk_load_word[], sk_load_half[], sk_load_byte[]; + +#endif /* __ASSEMBLY__ */ + +/* + * Stackframe layout (packed stack): + * + * ^ high + * +---------------+ | + * | old backchain | | + * +---------------+ | + * | r15 - r6 | | + * BFP -> +===============+ | + * | | | + * | BPF stack | | + * | | | + * +---------------+ | + * | 8 byte hlen | | + * R15+168 -> +---------------+ | + * | 4 byte align | | + * +---------------+ | + * | 4 byte temp | | + * | for bpf_jit.S | | + * R15+160 -> +---------------+ | + * | new backchain | | + * R15+152 -> +---------------+ | + * | + 152 byte SA | | + * R15 -> +---------------+ + low + * + * We get 160 bytes stack space from calling function, but only use + * 11 * 8 byte (old backchain + r15 - r6) for storing registers. + */ +#define STK_OFF (MAX_BPF_STACK + 8 + 4 + 4 + (160 - 11 * 8)) +#define STK_OFF_TMP 160 /* Offset of tmp buffer on stack */ +#define STK_OFF_HLEN 168 /* Offset of SKB header length on stack */ + +/* Offset to skip condition code check */ +#define OFF_OK 4 + +#endif /* __ARCH_S390_NET_BPF_JIT_H */ diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index bbd1981cc150..7690dc8e1ab5 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -1,817 +1,1209 @@ /* * BPF Jit compiler for s390. * - * Copyright IBM Corp. 2012 + * Minimum build requirements: + * + * - HAVE_MARCH_Z196_FEATURES: laal, laalg + * - HAVE_MARCH_Z10_FEATURES: msfi, cgrj, clgrj + * - HAVE_MARCH_Z9_109_FEATURES: alfi, llilf, clfi, oilf, nilf + * - PACK_STACK + * - 64BIT + * + * Copyright IBM Corp. 2012,2015 * * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com> + * Michael Holzheu <holzheu@linux.vnet.ibm.com> */ + +#define KMSG_COMPONENT "bpf_jit" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + #include <linux/netdevice.h> -#include <linux/if_vlan.h> #include <linux/filter.h> #include <linux/init.h> #include <asm/cacheflush.h> -#include <asm/facility.h> #include <asm/dis.h> +#include "bpf_jit.h" -/* - * Conventions: - * %r2 = skb pointer - * %r3 = offset parameter - * %r4 = scratch register / length parameter - * %r5 = BPF A accumulator - * %r8 = return address - * %r9 = save register for skb pointer - * %r10 = skb->data - * %r11 = skb->len - skb->data_len (headlen) - * %r12 = BPF X accumulator - * %r13 = literal pool pointer - * 0(%r15) - 63(%r15) scratch memory array with BPF_MEMWORDS - */ int bpf_jit_enable __read_mostly; +struct bpf_jit { + u32 seen; /* Flags to remember seen eBPF instructions */ + u32 seen_reg[16]; /* Array to remember which registers are used */ + u32 *addrs; /* Array with relative instruction addresses */ + u8 *prg_buf; /* Start of program */ + int size; /* Size of program and literal pool */ + int size_prg; /* Size of program */ + int prg; /* Current position in program */ + int lit_start; /* Start of literal pool */ + int lit; /* Current position in literal pool */ + int base_ip; /* Base address for literal pool */ + int ret0_ip; /* Address of return 0 */ + int exit_ip; /* Address of exit */ +}; + +#define BPF_SIZE_MAX 4096 /* Max size for program */ + +#define SEEN_SKB 1 /* skb access */ +#define SEEN_MEM 2 /* use mem[] for temporary storage */ +#define SEEN_RET0 4 /* ret0_ip points to a valid return 0 */ +#define SEEN_LITERAL 8 /* code uses literals */ +#define SEEN_FUNC 16 /* calls C functions */ +#define SEEN_STACK (SEEN_FUNC | SEEN_MEM | SEEN_SKB) + /* - * assembly code in arch/x86/net/bpf_jit.S + * s390 registers */ -extern u8 sk_load_word[], sk_load_half[], sk_load_byte[], sk_load_byte_msh[]; -extern u8 sk_load_word_ind[], sk_load_half_ind[], sk_load_byte_ind[]; +#define REG_W0 (__MAX_BPF_REG+0) /* Work register 1 (even) */ +#define REG_W1 (__MAX_BPF_REG+1) /* Work register 2 (odd) */ +#define REG_SKB_DATA (__MAX_BPF_REG+2) /* SKB data register */ +#define REG_L (__MAX_BPF_REG+3) /* Literal pool register */ +#define REG_15 (__MAX_BPF_REG+4) /* Register 15 */ +#define REG_0 REG_W0 /* Register 0 */ +#define REG_2 BPF_REG_1 /* Register 2 */ +#define REG_14 BPF_REG_0 /* Register 14 */ -struct bpf_jit { - unsigned int seen; - u8 *start; - u8 *prg; - u8 *mid; - u8 *lit; - u8 *end; - u8 *base_ip; - u8 *ret0_ip; - u8 *exit_ip; - unsigned int off_load_word; - unsigned int off_load_half; - unsigned int off_load_byte; - unsigned int off_load_bmsh; - unsigned int off_load_iword; - unsigned int off_load_ihalf; - unsigned int off_load_ibyte; +/* + * Mapping of BPF registers to s390 registers + */ +static const int reg2hex[] = { + /* Return code */ + [BPF_REG_0] = 14, + /* Function parameters */ + [BPF_REG_1] = 2, + [BPF_REG_2] = 3, + [BPF_REG_3] = 4, + [BPF_REG_4] = 5, + [BPF_REG_5] = 6, + /* Call saved registers */ + [BPF_REG_6] = 7, + [BPF_REG_7] = 8, + [BPF_REG_8] = 9, + [BPF_REG_9] = 10, + /* BPF stack pointer */ + [BPF_REG_FP] = 13, + /* SKB data pointer */ + [REG_SKB_DATA] = 12, + /* Work registers for s390x backend */ + [REG_W0] = 0, + [REG_W1] = 1, + [REG_L] = 11, + [REG_15] = 15, }; -#define BPF_SIZE_MAX 4096 /* Max size for program */ +static inline u32 reg(u32 dst_reg, u32 src_reg) +{ + return reg2hex[dst_reg] << 4 | reg2hex[src_reg]; +} + +static inline u32 reg_high(u32 reg) +{ + return reg2hex[reg] << 4; +} + +static inline void reg_set_seen(struct bpf_jit *jit, u32 b1) +{ + u32 r1 = reg2hex[b1]; + + if (!jit->seen_reg[r1] && r1 >= 6 && r1 <= 15) + jit->seen_reg[r1] = 1; +} + +#define REG_SET_SEEN(b1) \ +({ \ + reg_set_seen(jit, b1); \ +}) + +#define REG_SEEN(b1) jit->seen_reg[reg2hex[(b1)]] + +/* + * EMIT macros for code generation + */ + +#define _EMIT2(op) \ +({ \ + if (jit->prg_buf) \ + *(u16 *) (jit->prg_buf + jit->prg) = op; \ + jit->prg += 2; \ +}) -#define SEEN_DATAREF 1 /* might call external helpers */ -#define SEEN_XREG 2 /* ebx is used */ -#define SEEN_MEM 4 /* use mem[] for temporary storage */ -#define SEEN_RET0 8 /* pc_ret0 points to a valid return 0 */ -#define SEEN_LITERAL 16 /* code uses literals */ -#define SEEN_LOAD_WORD 32 /* code uses sk_load_word */ -#define SEEN_LOAD_HALF 64 /* code uses sk_load_half */ -#define SEEN_LOAD_BYTE 128 /* code uses sk_load_byte */ -#define SEEN_LOAD_BMSH 256 /* code uses sk_load_byte_msh */ -#define SEEN_LOAD_IWORD 512 /* code uses sk_load_word_ind */ -#define SEEN_LOAD_IHALF 1024 /* code uses sk_load_half_ind */ -#define SEEN_LOAD_IBYTE 2048 /* code uses sk_load_byte_ind */ - -#define EMIT2(op) \ -({ \ - if (jit->prg + 2 <= jit->mid) \ - *(u16 *) jit->prg = op; \ - jit->prg += 2; \ +#define EMIT2(op, b1, b2) \ +({ \ + _EMIT2(op | reg(b1, b2)); \ + REG_SET_SEEN(b1); \ + REG_SET_SEEN(b2); \ }) -#define EMIT4(op) \ -({ \ - if (jit->prg + 4 <= jit->mid) \ - *(u32 *) jit->prg = op; \ - jit->prg += 4; \ +#define _EMIT4(op) \ +({ \ + if (jit->prg_buf) \ + *(u32 *) (jit->prg_buf + jit->prg) = op; \ + jit->prg += 4; \ }) -#define EMIT4_DISP(op, disp) \ -({ \ - unsigned int __disp = (disp) & 0xfff; \ - EMIT4(op | __disp); \ +#define EMIT4(op, b1, b2) \ +({ \ + _EMIT4(op | reg(b1, b2)); \ + REG_SET_SEEN(b1); \ + REG_SET_SEEN(b2); \ }) -#define EMIT4_IMM(op, imm) \ -({ \ - unsigned int __imm = (imm) & 0xffff; \ - EMIT4(op | __imm); \ +#define EMIT4_RRF(op, b1, b2, b3) \ +({ \ + _EMIT4(op | reg_high(b3) << 8 | reg(b1, b2)); \ + REG_SET_SEEN(b1); \ + REG_SET_SEEN(b2); \ + REG_SET_SEEN(b3); \ }) -#define EMIT4_PCREL(op, pcrel) \ -({ \ - long __pcrel = ((pcrel) >> 1) & 0xffff; \ - EMIT4(op | __pcrel); \ +#define _EMIT4_DISP(op, disp) \ +({ \ + unsigned int __disp = (disp) & 0xfff; \ + _EMIT4(op | __disp); \ }) -#define EMIT6(op1, op2) \ -({ \ - if (jit->prg + 6 <= jit->mid) { \ - *(u32 *) jit->prg = op1; \ - *(u16 *) (jit->prg + 4) = op2; \ - } \ - jit->prg += 6; \ +#define EMIT4_DISP(op, b1, b2, disp) \ +({ \ + _EMIT4_DISP(op | reg_high(b1) << 16 | \ + reg_high(b2) << 8, disp); \ + REG_SET_SEEN(b1); \ + REG_SET_SEEN(b2); \ }) -#define EMIT6_DISP(op1, op2, disp) \ -({ \ - unsigned int __disp = (disp) & 0xfff; \ - EMIT6(op1 | __disp, op2); \ +#define EMIT4_IMM(op, b1, imm) \ +({ \ + unsigned int __imm = (imm) & 0xffff; \ + _EMIT4(op | reg_high(b1) << 16 | __imm); \ + REG_SET_SEEN(b1); \ }) -#define EMIT6_IMM(op, imm) \ -({ \ - unsigned int __imm = (imm); \ - EMIT6(op | (__imm >> 16), __imm & 0xffff); \ +#define EMIT4_PCREL(op, pcrel) \ +({ \ + long __pcrel = ((pcrel) >> 1) & 0xffff; \ + _EMIT4(op | __pcrel); \ }) -#define EMIT_CONST(val) \ -({ \ - unsigned int ret; \ - ret = (unsigned int) (jit->lit - jit->base_ip); \ - jit->seen |= SEEN_LITERAL; \ - if (jit->lit + 4 <= jit->end) \ - *(u32 *) jit->lit = val; \ - jit->lit += 4; \ - ret; \ +#define _EMIT6(op1, op2) \ +({ \ + if (jit->prg_buf) { \ + *(u32 *) (jit->prg_buf + jit->prg) = op1; \ + *(u16 *) (jit->prg_buf + jit->prg + 4) = op2; \ + } \ + jit->prg += 6; \ }) -#define EMIT_FN_CONST(bit, fn) \ -({ \ - unsigned int ret; \ - ret = (unsigned int) (jit->lit - jit->base_ip); \ - if (jit->seen & bit) { \ - jit->seen |= SEEN_LITERAL; \ - if (jit->lit + 8 <= jit->end) \ - *(void **) jit->lit = fn; \ - jit->lit += 8; \ - } \ - ret; \ +#define _EMIT6_DISP(op1, op2, disp) \ +({ \ + unsigned int __disp = (disp) & 0xfff; \ + _EMIT6(op1 | __disp, op2); \ }) -static void bpf_jit_fill_hole(void *area, unsigned int size) +#define EMIT6_DISP(op1, op2, b1, b2, b3, disp) \ +({ \ + _EMIT6_DISP(op1 | reg(b1, b2) << 16 | \ + reg_high(b3) << 8, op2, disp); \ + REG_SET_SEEN(b1); \ + REG_SET_SEEN(b2); \ + REG_SET_SEEN(b3); \ +}) + +#define _EMIT6_DISP_LH(op1, op2, disp) \ +({ \ + unsigned int __disp_h = ((u32)disp) & 0xff000; \ + unsigned int __disp_l = ((u32)disp) & 0x00fff; \ + _EMIT6(op1 | __disp_l, op2 | __disp_h >> 4); \ +}) + +#define EMIT6_DISP_LH(op1, op2, b1, b2, b3, disp) \ +({ \ + _EMIT6_DISP_LH(op1 | reg(b1, b2) << 16 | \ + reg_high(b3) << 8, op2, disp); \ + REG_SET_SEEN(b1); \ + REG_SET_SEEN(b2); \ + REG_SET_SEEN(b3); \ +}) + +#define EMIT6_PCREL(op1, op2, b1, b2, i, off, mask) \ +({ \ + /* Branch instruction needs 6 bytes */ \ + int rel = (addrs[i + off + 1] - (addrs[i + 1] - 6)) / 2;\ + _EMIT6(op1 | reg(b1, b2) << 16 | rel, op2 | mask); \ + REG_SET_SEEN(b1); \ + REG_SET_SEEN(b2); \ +}) + +#define _EMIT6_IMM(op, imm) \ +({ \ + unsigned int __imm = (imm); \ + _EMIT6(op | (__imm >> 16), __imm & 0xffff); \ +}) + +#define EMIT6_IMM(op, b1, imm) \ +({ \ + _EMIT6_IMM(op | reg_high(b1) << 16, imm); \ + REG_SET_SEEN(b1); \ +}) + +#define EMIT_CONST_U32(val) \ +({ \ + unsigned int ret; \ + ret = jit->lit - jit->base_ip; \ + jit->seen |= SEEN_LITERAL; \ + if (jit->prg_buf) \ + *(u32 *) (jit->prg_buf + jit->lit) = (u32) val; \ + jit->lit += 4; \ + ret; \ +}) + +#define EMIT_CONST_U64(val) \ +({ \ + unsigned int ret; \ + ret = jit->lit - jit->base_ip; \ + jit->seen |= SEEN_LITERAL; \ + if (jit->prg_buf) \ + *(u64 *) (jit->prg_buf + jit->lit) = (u64) val; \ + jit->lit += 8; \ + ret; \ +}) + +#define EMIT_ZERO(b1) \ +({ \ + /* llgfr %dst,%dst (zero extend to 64 bit) */ \ + EMIT4(0xb9160000, b1, b1); \ + REG_SET_SEEN(b1); \ +}) + +/* + * Fill whole space with illegal instructions + */ +static void jit_fill_hole(void *area, unsigned int size) { - /* Fill whole space with illegal instructions */ memset(area, 0, size); } -static void bpf_jit_prologue(struct bpf_jit *jit) +/* + * Save registers from "rs" (register start) to "re" (register end) on stack + */ +static void save_regs(struct bpf_jit *jit, u32 rs, u32 re) +{ + u32 off = 72 + (rs - 6) * 8; + + if (rs == re) + /* stg %rs,off(%r15) */ + _EMIT6(0xe300f000 | rs << 20 | off, 0x0024); + else + /* stmg %rs,%re,off(%r15) */ + _EMIT6_DISP(0xeb00f000 | rs << 20 | re << 16, 0x0024, off); +} + +/* + * Restore registers from "rs" (register start) to "re" (register end) on stack + */ +static void restore_regs(struct bpf_jit *jit, u32 rs, u32 re) { - /* Save registers and create stack frame if necessary */ - if (jit->seen & SEEN_DATAREF) { - /* stmg %r8,%r15,88(%r15) */ - EMIT6(0xeb8ff058, 0x0024); - /* lgr %r14,%r15 */ - EMIT4(0xb90400ef); - /* aghi %r15,<offset> */ - EMIT4_IMM(0xa7fb0000, (jit->seen & SEEN_MEM) ? -112 : -80); - /* stg %r14,152(%r15) */ - EMIT6(0xe3e0f098, 0x0024); - } else if ((jit->seen & SEEN_XREG) && (jit->seen & SEEN_LITERAL)) - /* stmg %r12,%r13,120(%r15) */ - EMIT6(0xebcdf078, 0x0024); - else if (jit->seen & SEEN_XREG) - /* stg %r12,120(%r15) */ - EMIT6(0xe3c0f078, 0x0024); - else if (jit->seen & SEEN_LITERAL) - /* stg %r13,128(%r15) */ - EMIT6(0xe3d0f080, 0x0024); + u32 off = 72 + (rs - 6) * 8; + + if (jit->seen & SEEN_STACK) + off += STK_OFF; + + if (rs == re) + /* lg %rs,off(%r15) */ + _EMIT6(0xe300f000 | rs << 20 | off, 0x0004); + else + /* lmg %rs,%re,off(%r15) */ + _EMIT6_DISP(0xeb00f000 | rs << 20 | re << 16, 0x0004, off); +} +/* + * Return first seen register (from start) + */ +static int get_start(struct bpf_jit *jit, int start) +{ + int i; + + for (i = start; i <= 15; i++) { + if (jit->seen_reg[i]) + return i; + } + return 0; +} + +/* + * Return last seen register (from start) (gap >= 2) + */ +static int get_end(struct bpf_jit *jit, int start) +{ + int i; + + for (i = start; i < 15; i++) { + if (!jit->seen_reg[i] && !jit->seen_reg[i + 1]) + return i - 1; + } + return jit->seen_reg[15] ? 15 : 14; +} + +#define REGS_SAVE 1 +#define REGS_RESTORE 0 +/* + * Save and restore clobbered registers (6-15) on stack. + * We save/restore registers in chunks with gap >= 2 registers. + */ +static void save_restore_regs(struct bpf_jit *jit, int op) +{ + + int re = 6, rs; + + do { + rs = get_start(jit, re); + if (!rs) + break; + re = get_end(jit, rs + 1); + if (op == REGS_SAVE) + save_regs(jit, rs, re); + else + restore_regs(jit, rs, re); + re++; + } while (re <= 15); +} + +/* + * Emit function prologue + * + * Save registers and create stack frame if necessary. + * See stack frame layout desription in "bpf_jit.h"! + */ +static void bpf_jit_prologue(struct bpf_jit *jit) +{ + /* Save registers */ + save_restore_regs(jit, REGS_SAVE); /* Setup literal pool */ if (jit->seen & SEEN_LITERAL) { /* basr %r13,0 */ - EMIT2(0x0dd0); + EMIT2(0x0d00, REG_L, REG_0); jit->base_ip = jit->prg; } - jit->off_load_word = EMIT_FN_CONST(SEEN_LOAD_WORD, sk_load_word); - jit->off_load_half = EMIT_FN_CONST(SEEN_LOAD_HALF, sk_load_half); - jit->off_load_byte = EMIT_FN_CONST(SEEN_LOAD_BYTE, sk_load_byte); - jit->off_load_bmsh = EMIT_FN_CONST(SEEN_LOAD_BMSH, sk_load_byte_msh); - jit->off_load_iword = EMIT_FN_CONST(SEEN_LOAD_IWORD, sk_load_word_ind); - jit->off_load_ihalf = EMIT_FN_CONST(SEEN_LOAD_IHALF, sk_load_half_ind); - jit->off_load_ibyte = EMIT_FN_CONST(SEEN_LOAD_IBYTE, sk_load_byte_ind); - - /* Filter needs to access skb data */ - if (jit->seen & SEEN_DATAREF) { - /* l %r11,<len>(%r2) */ - EMIT4_DISP(0x58b02000, offsetof(struct sk_buff, len)); - /* s %r11,<data_len>(%r2) */ - EMIT4_DISP(0x5bb02000, offsetof(struct sk_buff, data_len)); - /* lg %r10,<data>(%r2) */ - EMIT6_DISP(0xe3a02000, 0x0004, - offsetof(struct sk_buff, data)); + /* Setup stack and backchain */ + if (jit->seen & SEEN_STACK) { + /* lgr %bfp,%r15 (BPF frame pointer) */ + EMIT4(0xb9040000, BPF_REG_FP, REG_15); + /* aghi %r15,-STK_OFF */ + EMIT4_IMM(0xa70b0000, REG_15, -STK_OFF); + if (jit->seen & SEEN_FUNC) + /* stg %bfp,152(%r15) (backchain) */ + EMIT6_DISP_LH(0xe3000000, 0x0024, BPF_REG_FP, REG_0, + REG_15, 152); + } + /* + * For SKB access %b1 contains the SKB pointer. For "bpf_jit.S" + * we store the SKB header length on the stack and the SKB data + * pointer in REG_SKB_DATA. + */ + if (jit->seen & SEEN_SKB) { + /* Header length: llgf %w1,<len>(%b1) */ + EMIT6_DISP_LH(0xe3000000, 0x0016, REG_W1, REG_0, BPF_REG_1, + offsetof(struct sk_buff, len)); + /* s %w1,<data_len>(%b1) */ + EMIT4_DISP(0x5b000000, REG_W1, BPF_REG_1, + offsetof(struct sk_buff, data_len)); + /* stg %w1,ST_OFF_HLEN(%r0,%r15) */ + EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0, REG_15, + STK_OFF_HLEN); + /* lg %skb_data,data_off(%b1) */ + EMIT6_DISP_LH(0xe3000000, 0x0004, REG_SKB_DATA, REG_0, + BPF_REG_1, offsetof(struct sk_buff, data)); } + /* BPF compatibility: clear A (%b7) and X (%b8) registers */ + if (REG_SEEN(BPF_REG_7)) + /* lghi %b7,0 */ + EMIT4_IMM(0xa7090000, BPF_REG_7, 0); + if (REG_SEEN(BPF_REG_8)) + /* lghi %b8,0 */ + EMIT4_IMM(0xa7090000, BPF_REG_8, 0); } +/* + * Function epilogue + */ static void bpf_jit_epilogue(struct bpf_jit *jit) { /* Return 0 */ if (jit->seen & SEEN_RET0) { jit->ret0_ip = jit->prg; - /* lghi %r2,0 */ - EMIT4(0xa7290000); + /* lghi %b0,0 */ + EMIT4_IMM(0xa7090000, BPF_REG_0, 0); } jit->exit_ip = jit->prg; + /* Load exit code: lgr %r2,%b0 */ + EMIT4(0xb9040000, REG_2, BPF_REG_0); /* Restore registers */ - if (jit->seen & SEEN_DATAREF) - /* lmg %r8,%r15,<offset>(%r15) */ - EMIT6_DISP(0xeb8ff000, 0x0004, - (jit->seen & SEEN_MEM) ? 200 : 168); - else if ((jit->seen & SEEN_XREG) && (jit->seen & SEEN_LITERAL)) - /* lmg %r12,%r13,120(%r15) */ - EMIT6(0xebcdf078, 0x0004); - else if (jit->seen & SEEN_XREG) - /* lg %r12,120(%r15) */ - EMIT6(0xe3c0f078, 0x0004); - else if (jit->seen & SEEN_LITERAL) - /* lg %r13,128(%r15) */ - EMIT6(0xe3d0f080, 0x0004); + save_restore_regs(jit, REGS_RESTORE); /* br %r14 */ - EMIT2(0x07fe); + _EMIT2(0x07fe); } /* - * make sure we dont leak kernel information to user + * Compile one eBPF instruction into s390x code */ -static void bpf_jit_noleaks(struct bpf_jit *jit, struct sock_filter *filter) +static int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i) { - /* Clear temporary memory if (seen & SEEN_MEM) */ - if (jit->seen & SEEN_MEM) - /* xc 0(64,%r15),0(%r15) */ - EMIT6(0xd73ff000, 0xf000); - /* Clear X if (seen & SEEN_XREG) */ - if (jit->seen & SEEN_XREG) - /* lhi %r12,0 */ - EMIT4(0xa7c80000); - /* Clear A if the first register does not set it. */ - switch (filter[0].code) { - case BPF_LD | BPF_W | BPF_ABS: - case BPF_LD | BPF_H | BPF_ABS: - case BPF_LD | BPF_B | BPF_ABS: - case BPF_LD | BPF_W | BPF_LEN: - case BPF_LD | BPF_W | BPF_IND: - case BPF_LD | BPF_H | BPF_IND: - case BPF_LD | BPF_B | BPF_IND: - case BPF_LD | BPF_IMM: - case BPF_LD | BPF_MEM: - case BPF_MISC | BPF_TXA: - case BPF_RET | BPF_K: - /* first instruction sets A register */ - break; - default: /* A = 0 */ - /* lhi %r5,0 */ - EMIT4(0xa7580000); - } -} + struct bpf_insn *insn = &fp->insnsi[i]; + int jmp_off, last, insn_count = 1; + unsigned int func_addr, mask; + u32 dst_reg = insn->dst_reg; + u32 src_reg = insn->src_reg; + u32 *addrs = jit->addrs; + s32 imm = insn->imm; + s16 off = insn->off; -static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter, - unsigned int *addrs, int i, int last) -{ - unsigned int K; - int offset; - unsigned int mask; - u16 code; - - K = filter->k; - code = bpf_anc_helper(filter); - - switch (code) { - case BPF_ALU | BPF_ADD | BPF_X: /* A += X */ - jit->seen |= SEEN_XREG; - /* ar %r5,%r12 */ - EMIT2(0x1a5c); - break; - case BPF_ALU | BPF_ADD | BPF_K: /* A += K */ - if (!K) + switch (insn->code) { + /* + * BPF_MOV + */ + case BPF_ALU | BPF_MOV | BPF_X: /* dst = (u32) src */ + /* llgfr %dst,%src */ + EMIT4(0xb9160000, dst_reg, src_reg); + break; + case BPF_ALU64 | BPF_MOV | BPF_X: /* dst = src */ + /* lgr %dst,%src */ + EMIT4(0xb9040000, dst_reg, src_reg); + break; + case BPF_ALU | BPF_MOV | BPF_K: /* dst = (u32) imm */ + /* llilf %dst,imm */ + EMIT6_IMM(0xc00f0000, dst_reg, imm); + break; + case BPF_ALU64 | BPF_MOV | BPF_K: /* dst = imm */ + /* lgfi %dst,imm */ + EMIT6_IMM(0xc0010000, dst_reg, imm); + break; + /* + * BPF_LD 64 + */ + case BPF_LD | BPF_IMM | BPF_DW: /* dst = (u64) imm */ + { + /* 16 byte instruction that uses two 'struct bpf_insn' */ + u64 imm64; + + imm64 = (u64)(u32) insn[0].imm | ((u64)(u32) insn[1].imm) << 32; + /* lg %dst,<d(imm)>(%l) */ + EMIT6_DISP_LH(0xe3000000, 0x0004, dst_reg, REG_0, REG_L, + EMIT_CONST_U64(imm64)); + insn_count = 2; + break; + } + /* + * BPF_ADD + */ + case BPF_ALU | BPF_ADD | BPF_X: /* dst = (u32) dst + (u32) src */ + /* ar %dst,%src */ + EMIT2(0x1a00, dst_reg, src_reg); + EMIT_ZERO(dst_reg); + break; + case BPF_ALU64 | BPF_ADD | BPF_X: /* dst = dst + src */ + /* agr %dst,%src */ + EMIT4(0xb9080000, dst_reg, src_reg); + break; + case BPF_ALU | BPF_ADD | BPF_K: /* dst = (u32) dst + (u32) imm */ + if (!imm) break; - if (K <= 16383) - /* ahi %r5,<K> */ - EMIT4_IMM(0xa75a0000, K); - else if (test_facility(21)) - /* alfi %r5,<K> */ - EMIT6_IMM(0xc25b0000, K); - else - /* a %r5,<d(K)>(%r13) */ - EMIT4_DISP(0x5a50d000, EMIT_CONST(K)); + /* alfi %dst,imm */ + EMIT6_IMM(0xc20b0000, dst_reg, imm); + EMIT_ZERO(dst_reg); + break; + case BPF_ALU64 | BPF_ADD | BPF_K: /* dst = dst + imm */ + if (!imm) + break; + /* agfi %dst,imm */ + EMIT6_IMM(0xc2080000, dst_reg, imm); + break; + /* + * BPF_SUB + */ + case BPF_ALU | BPF_SUB | BPF_X: /* dst = (u32) dst - (u32) src */ + /* sr %dst,%src */ + EMIT2(0x1b00, dst_reg, src_reg); + EMIT_ZERO(dst_reg); break; - case BPF_ALU | BPF_SUB | BPF_X: /* A -= X */ - jit->seen |= SEEN_XREG; - /* sr %r5,%r12 */ - EMIT2(0x1b5c); + case BPF_ALU64 | BPF_SUB | BPF_X: /* dst = dst - src */ + /* sgr %dst,%src */ + EMIT4(0xb9090000, dst_reg, src_reg); break; - case BPF_ALU | BPF_SUB | BPF_K: /* A -= K */ - if (!K) + case BPF_ALU | BPF_SUB | BPF_K: /* dst = (u32) dst - (u32) imm */ + if (!imm) break; - if (K <= 16384) - /* ahi %r5,-K */ - EMIT4_IMM(0xa75a0000, -K); - else if (test_facility(21)) - /* alfi %r5,-K */ - EMIT6_IMM(0xc25b0000, -K); - else - /* s %r5,<d(K)>(%r13) */ - EMIT4_DISP(0x5b50d000, EMIT_CONST(K)); - break; - case BPF_ALU | BPF_MUL | BPF_X: /* A *= X */ - jit->seen |= SEEN_XREG; - /* msr %r5,%r12 */ - EMIT4(0xb252005c); - break; - case BPF_ALU | BPF_MUL | BPF_K: /* A *= K */ - if (K <= 16383) - /* mhi %r5,K */ - EMIT4_IMM(0xa75c0000, K); - else if (test_facility(34)) - /* msfi %r5,<K> */ - EMIT6_IMM(0xc2510000, K); - else - /* ms %r5,<d(K)>(%r13) */ - EMIT4_DISP(0x7150d000, EMIT_CONST(K)); + /* alfi %dst,-imm */ + EMIT6_IMM(0xc20b0000, dst_reg, -imm); + EMIT_ZERO(dst_reg); break; - case BPF_ALU | BPF_DIV | BPF_X: /* A /= X */ - jit->seen |= SEEN_XREG | SEEN_RET0; - /* ltr %r12,%r12 */ - EMIT2(0x12cc); - /* jz <ret0> */ - EMIT4_PCREL(0xa7840000, (jit->ret0_ip - jit->prg)); - /* lhi %r4,0 */ - EMIT4(0xa7480000); - /* dlr %r4,%r12 */ - EMIT4(0xb997004c); - break; - case BPF_ALU | BPF_DIV | BPF_K: /* A /= K */ - if (K == 1) + case BPF_ALU64 | BPF_SUB | BPF_K: /* dst = dst - imm */ + if (!imm) + break; + /* agfi %dst,-imm */ + EMIT6_IMM(0xc2080000, dst_reg, -imm); + break; + /* + * BPF_MUL + */ + case BPF_ALU | BPF_MUL | BPF_X: /* dst = (u32) dst * (u32) src */ + /* msr %dst,%src */ + EMIT4(0xb2520000, dst_reg, src_reg); + EMIT_ZERO(dst_reg); + break; + case BPF_ALU64 | BPF_MUL | BPF_X: /* dst = dst * src */ + /* msgr %dst,%src */ + EMIT4(0xb90c0000, dst_reg, src_reg); + break; + case BPF_ALU | BPF_MUL | BPF_K: /* dst = (u32) dst * (u32) imm */ + if (imm == 1) + break; + /* msfi %r5,imm */ + EMIT6_IMM(0xc2010000, dst_reg, imm); + EMIT_ZERO(dst_reg); + break; + case BPF_ALU64 | BPF_MUL | BPF_K: /* dst = dst * imm */ + if (imm == 1) break; - /* lhi %r4,0 */ - EMIT4(0xa7480000); - /* dl %r4,<d(K)>(%r13) */ - EMIT6_DISP(0xe340d000, 0x0097, EMIT_CONST(K)); - break; - case BPF_ALU | BPF_MOD | BPF_X: /* A %= X */ - jit->seen |= SEEN_XREG | SEEN_RET0; - /* ltr %r12,%r12 */ - EMIT2(0x12cc); + /* msgfi %dst,imm */ + EMIT6_IMM(0xc2000000, dst_reg, imm); + break; + /* + * BPF_DIV / BPF_MOD + */ + case BPF_ALU | BPF_DIV | BPF_X: /* dst = (u32) dst / (u32) src */ + case BPF_ALU | BPF_MOD | BPF_X: /* dst = (u32) dst % (u32) src */ + { + int rc_reg = BPF_OP(insn->code) == BPF_DIV ? REG_W1 : REG_W0; + + jit->seen |= SEEN_RET0; + /* ltr %src,%src (if src == 0 goto fail) */ + EMIT2(0x1200, src_reg, src_reg); + /* jz <ret0> */ + EMIT4_PCREL(0xa7840000, jit->ret0_ip - jit->prg); + /* lhi %w0,0 */ + EMIT4_IMM(0xa7080000, REG_W0, 0); + /* lr %w1,%dst */ + EMIT2(0x1800, REG_W1, dst_reg); + /* dlr %w0,%src */ + EMIT4(0xb9970000, REG_W0, src_reg); + /* llgfr %dst,%rc */ + EMIT4(0xb9160000, dst_reg, rc_reg); + break; + } + case BPF_ALU64 | BPF_DIV | BPF_X: /* dst = dst / (u32) src */ + case BPF_ALU64 | BPF_MOD | BPF_X: /* dst = dst % (u32) src */ + { + int rc_reg = BPF_OP(insn->code) == BPF_DIV ? REG_W1 : REG_W0; + + jit->seen |= SEEN_RET0; + /* ltgr %src,%src (if src == 0 goto fail) */ + EMIT4(0xb9020000, src_reg, src_reg); /* jz <ret0> */ - EMIT4_PCREL(0xa7840000, (jit->ret0_ip - jit->prg)); - /* lhi %r4,0 */ - EMIT4(0xa7480000); - /* dlr %r4,%r12 */ - EMIT4(0xb997004c); - /* lr %r5,%r4 */ - EMIT2(0x1854); - break; - case BPF_ALU | BPF_MOD | BPF_K: /* A %= K */ - if (K == 1) { - /* lhi %r5,0 */ - EMIT4(0xa7580000); + EMIT4_PCREL(0xa7840000, jit->ret0_ip - jit->prg); + /* lghi %w0,0 */ + EMIT4_IMM(0xa7090000, REG_W0, 0); + /* lgr %w1,%dst */ + EMIT4(0xb9040000, REG_W1, dst_reg); + /* llgfr %dst,%src (u32 cast) */ + EMIT4(0xb9160000, dst_reg, src_reg); + /* dlgr %w0,%dst */ + EMIT4(0xb9870000, REG_W0, dst_reg); + /* lgr %dst,%rc */ + EMIT4(0xb9040000, dst_reg, rc_reg); + break; + } + case BPF_ALU | BPF_DIV | BPF_K: /* dst = (u32) dst / (u32) imm */ + case BPF_ALU | BPF_MOD | BPF_K: /* dst = (u32) dst % (u32) imm */ + { + int rc_reg = BPF_OP(insn->code) == BPF_DIV ? REG_W1 : REG_W0; + + if (imm == 1) { + if (BPF_OP(insn->code) == BPF_MOD) + /* lhgi %dst,0 */ + EMIT4_IMM(0xa7090000, dst_reg, 0); break; } - /* lhi %r4,0 */ - EMIT4(0xa7480000); - /* dl %r4,<d(K)>(%r13) */ - EMIT6_DISP(0xe340d000, 0x0097, EMIT_CONST(K)); - /* lr %r5,%r4 */ - EMIT2(0x1854); - break; - case BPF_ALU | BPF_AND | BPF_X: /* A &= X */ - jit->seen |= SEEN_XREG; - /* nr %r5,%r12 */ - EMIT2(0x145c); - break; - case BPF_ALU | BPF_AND | BPF_K: /* A &= K */ - if (test_facility(21)) - /* nilf %r5,<K> */ - EMIT6_IMM(0xc05b0000, K); - else - /* n %r5,<d(K)>(%r13) */ - EMIT4_DISP(0x5450d000, EMIT_CONST(K)); - break; - case BPF_ALU | BPF_OR | BPF_X: /* A |= X */ - jit->seen |= SEEN_XREG; - /* or %r5,%r12 */ - EMIT2(0x165c); - break; - case BPF_ALU | BPF_OR | BPF_K: /* A |= K */ - if (test_facility(21)) - /* oilf %r5,<K> */ - EMIT6_IMM(0xc05d0000, K); - else - /* o %r5,<d(K)>(%r13) */ - EMIT4_DISP(0x5650d000, EMIT_CONST(K)); + /* lhi %w0,0 */ + EMIT4_IMM(0xa7080000, REG_W0, 0); + /* lr %w1,%dst */ + EMIT2(0x1800, REG_W1, dst_reg); + /* dl %w0,<d(imm)>(%l) */ + EMIT6_DISP_LH(0xe3000000, 0x0097, REG_W0, REG_0, REG_L, + EMIT_CONST_U32(imm)); + /* llgfr %dst,%rc */ + EMIT4(0xb9160000, dst_reg, rc_reg); + break; + } + case BPF_ALU64 | BPF_DIV | BPF_K: /* dst = dst / (u32) imm */ + case BPF_ALU64 | BPF_MOD | BPF_K: /* dst = dst % (u32) imm */ + { + int rc_reg = BPF_OP(insn->code) == BPF_DIV ? REG_W1 : REG_W0; + + if (imm == 1) { + if (BPF_OP(insn->code) == BPF_MOD) + /* lhgi %dst,0 */ + EMIT4_IMM(0xa7090000, dst_reg, 0); + break; + } + /* lghi %w0,0 */ + EMIT4_IMM(0xa7090000, REG_W0, 0); + /* lgr %w1,%dst */ + EMIT4(0xb9040000, REG_W1, dst_reg); + /* dlg %w0,<d(imm)>(%l) */ + EMIT6_DISP_LH(0xe3000000, 0x0087, REG_W0, REG_0, REG_L, + EMIT_CONST_U64((u32) imm)); + /* lgr %dst,%rc */ + EMIT4(0xb9040000, dst_reg, rc_reg); + break; + } + /* + * BPF_AND + */ + case BPF_ALU | BPF_AND | BPF_X: /* dst = (u32) dst & (u32) src */ + /* nr %dst,%src */ + EMIT2(0x1400, dst_reg, src_reg); + EMIT_ZERO(dst_reg); + break; + case BPF_ALU64 | BPF_AND | BPF_X: /* dst = dst & src */ + /* ngr %dst,%src */ + EMIT4(0xb9800000, dst_reg, src_reg); + break; + case BPF_ALU | BPF_AND | BPF_K: /* dst = (u32) dst & (u32) imm */ + /* nilf %dst,imm */ + EMIT6_IMM(0xc00b0000, dst_reg, imm); + EMIT_ZERO(dst_reg); break; - case BPF_ANC | SKF_AD_ALU_XOR_X: /* A ^= X; */ - case BPF_ALU | BPF_XOR | BPF_X: - jit->seen |= SEEN_XREG; - /* xr %r5,%r12 */ - EMIT2(0x175c); + case BPF_ALU64 | BPF_AND | BPF_K: /* dst = dst & imm */ + /* ng %dst,<d(imm)>(%l) */ + EMIT6_DISP_LH(0xe3000000, 0x0080, dst_reg, REG_0, REG_L, + EMIT_CONST_U64(imm)); break; - case BPF_ALU | BPF_XOR | BPF_K: /* A ^= K */ - if (!K) + /* + * BPF_OR + */ + case BPF_ALU | BPF_OR | BPF_X: /* dst = (u32) dst | (u32) src */ + /* or %dst,%src */ + EMIT2(0x1600, dst_reg, src_reg); + EMIT_ZERO(dst_reg); + break; + case BPF_ALU64 | BPF_OR | BPF_X: /* dst = dst | src */ + /* ogr %dst,%src */ + EMIT4(0xb9810000, dst_reg, src_reg); + break; + case BPF_ALU | BPF_OR | BPF_K: /* dst = (u32) dst | (u32) imm */ + /* oilf %dst,imm */ + EMIT6_IMM(0xc00d0000, dst_reg, imm); + EMIT_ZERO(dst_reg); + break; + case BPF_ALU64 | BPF_OR | BPF_K: /* dst = dst | imm */ + /* og %dst,<d(imm)>(%l) */ + EMIT6_DISP_LH(0xe3000000, 0x0081, dst_reg, REG_0, REG_L, + EMIT_CONST_U64(imm)); + break; + /* + * BPF_XOR + */ + case BPF_ALU | BPF_XOR | BPF_X: /* dst = (u32) dst ^ (u32) src */ + /* xr %dst,%src */ + EMIT2(0x1700, dst_reg, src_reg); + EMIT_ZERO(dst_reg); + break; + case BPF_ALU64 | BPF_XOR | BPF_X: /* dst = dst ^ src */ + /* xgr %dst,%src */ + EMIT4(0xb9820000, dst_reg, src_reg); + break; + case BPF_ALU | BPF_XOR | BPF_K: /* dst = (u32) dst ^ (u32) imm */ + if (!imm) break; - /* x %r5,<d(K)>(%r13) */ - EMIT4_DISP(0x5750d000, EMIT_CONST(K)); + /* xilf %dst,imm */ + EMIT6_IMM(0xc0070000, dst_reg, imm); + EMIT_ZERO(dst_reg); + break; + case BPF_ALU64 | BPF_XOR | BPF_K: /* dst = dst ^ imm */ + /* xg %dst,<d(imm)>(%l) */ + EMIT6_DISP_LH(0xe3000000, 0x0082, dst_reg, REG_0, REG_L, + EMIT_CONST_U64(imm)); + break; + /* + * BPF_LSH + */ + case BPF_ALU | BPF_LSH | BPF_X: /* dst = (u32) dst << (u32) src */ + /* sll %dst,0(%src) */ + EMIT4_DISP(0x89000000, dst_reg, src_reg, 0); + EMIT_ZERO(dst_reg); break; - case BPF_ALU | BPF_LSH | BPF_X: /* A <<= X; */ - jit->seen |= SEEN_XREG; - /* sll %r5,0(%r12) */ - EMIT4(0x8950c000); + case BPF_ALU64 | BPF_LSH | BPF_X: /* dst = dst << src */ + /* sllg %dst,%dst,0(%src) */ + EMIT6_DISP_LH(0xeb000000, 0x000d, dst_reg, dst_reg, src_reg, 0); break; - case BPF_ALU | BPF_LSH | BPF_K: /* A <<= K */ - if (K == 0) + case BPF_ALU | BPF_LSH | BPF_K: /* dst = (u32) dst << (u32) imm */ + if (imm == 0) break; - /* sll %r5,K */ - EMIT4_DISP(0x89500000, K); + /* sll %dst,imm(%r0) */ + EMIT4_DISP(0x89000000, dst_reg, REG_0, imm); + EMIT_ZERO(dst_reg); break; - case BPF_ALU | BPF_RSH | BPF_X: /* A >>= X; */ - jit->seen |= SEEN_XREG; - /* srl %r5,0(%r12) */ - EMIT4(0x8850c000); + case BPF_ALU64 | BPF_LSH | BPF_K: /* dst = dst << imm */ + if (imm == 0) + break; + /* sllg %dst,%dst,imm(%r0) */ + EMIT6_DISP_LH(0xeb000000, 0x000d, dst_reg, dst_reg, REG_0, imm); + break; + /* + * BPF_RSH + */ + case BPF_ALU | BPF_RSH | BPF_X: /* dst = (u32) dst >> (u32) src */ + /* srl %dst,0(%src) */ + EMIT4_DISP(0x88000000, dst_reg, src_reg, 0); + EMIT_ZERO(dst_reg); break; - case BPF_ALU | BPF_RSH | BPF_K: /* A >>= K; */ - if (K == 0) + case BPF_ALU64 | BPF_RSH | BPF_X: /* dst = dst >> src */ + /* srlg %dst,%dst,0(%src) */ + EMIT6_DISP_LH(0xeb000000, 0x000c, dst_reg, dst_reg, src_reg, 0); + break; + case BPF_ALU | BPF_RSH | BPF_K: /* dst = (u32) dst >> (u32) imm */ + if (imm == 0) break; - /* srl %r5,K */ - EMIT4_DISP(0x88500000, K); - break; - case BPF_ALU | BPF_NEG: /* A = -A */ - /* lcr %r5,%r5 */ - EMIT2(0x1355); - break; - case BPF_JMP | BPF_JA: /* ip += K */ - offset = addrs[i + K] + jit->start - jit->prg; - EMIT4_PCREL(0xa7f40000, offset); - break; - case BPF_JMP | BPF_JGT | BPF_K: /* ip += (A > K) ? jt : jf */ - mask = 0x200000; /* jh */ - goto kbranch; - case BPF_JMP | BPF_JGE | BPF_K: /* ip += (A >= K) ? jt : jf */ - mask = 0xa00000; /* jhe */ - goto kbranch; - case BPF_JMP | BPF_JEQ | BPF_K: /* ip += (A == K) ? jt : jf */ - mask = 0x800000; /* je */ -kbranch: /* Emit compare if the branch targets are different */ - if (filter->jt != filter->jf) { - if (test_facility(21)) - /* clfi %r5,<K> */ - EMIT6_IMM(0xc25f0000, K); - else - /* cl %r5,<d(K)>(%r13) */ - EMIT4_DISP(0x5550d000, EMIT_CONST(K)); - } -branch: if (filter->jt == filter->jf) { - if (filter->jt == 0) - break; - /* j <jt> */ - offset = addrs[i + filter->jt] + jit->start - jit->prg; - EMIT4_PCREL(0xa7f40000, offset); + /* srl %dst,imm(%r0) */ + EMIT4_DISP(0x88000000, dst_reg, REG_0, imm); + EMIT_ZERO(dst_reg); + break; + case BPF_ALU64 | BPF_RSH | BPF_K: /* dst = dst >> imm */ + if (imm == 0) break; - } - if (filter->jt != 0) { - /* brc <mask>,<jt> */ - offset = addrs[i + filter->jt] + jit->start - jit->prg; - EMIT4_PCREL(0xa7040000 | mask, offset); - } - if (filter->jf != 0) { - /* brc <mask^15>,<jf> */ - offset = addrs[i + filter->jf] + jit->start - jit->prg; - EMIT4_PCREL(0xa7040000 | (mask ^ 0xf00000), offset); - } + /* srlg %dst,%dst,imm(%r0) */ + EMIT6_DISP_LH(0xeb000000, 0x000c, dst_reg, dst_reg, REG_0, imm); break; - case BPF_JMP | BPF_JSET | BPF_K: /* ip += (A & K) ? jt : jf */ - mask = 0x700000; /* jnz */ - /* Emit test if the branch targets are different */ - if (filter->jt != filter->jf) { - if (K > 65535) { - /* lr %r4,%r5 */ - EMIT2(0x1845); - /* n %r4,<d(K)>(%r13) */ - EMIT4_DISP(0x5440d000, EMIT_CONST(K)); - } else - /* tmll %r5,K */ - EMIT4_IMM(0xa7510000, K); - } - goto branch; - case BPF_JMP | BPF_JGT | BPF_X: /* ip += (A > X) ? jt : jf */ - mask = 0x200000; /* jh */ - goto xbranch; - case BPF_JMP | BPF_JGE | BPF_X: /* ip += (A >= X) ? jt : jf */ - mask = 0xa00000; /* jhe */ - goto xbranch; - case BPF_JMP | BPF_JEQ | BPF_X: /* ip += (A == X) ? jt : jf */ - mask = 0x800000; /* je */ -xbranch: /* Emit compare if the branch targets are different */ - if (filter->jt != filter->jf) { - jit->seen |= SEEN_XREG; - /* clr %r5,%r12 */ - EMIT2(0x155c); - } - goto branch; - case BPF_JMP | BPF_JSET | BPF_X: /* ip += (A & X) ? jt : jf */ - mask = 0x700000; /* jnz */ - /* Emit test if the branch targets are different */ - if (filter->jt != filter->jf) { - jit->seen |= SEEN_XREG; - /* lr %r4,%r5 */ - EMIT2(0x1845); - /* nr %r4,%r12 */ - EMIT2(0x144c); + /* + * BPF_ARSH + */ + case BPF_ALU64 | BPF_ARSH | BPF_X: /* ((s64) dst) >>= src */ + /* srag %dst,%dst,0(%src) */ + EMIT6_DISP_LH(0xeb000000, 0x000a, dst_reg, dst_reg, src_reg, 0); + break; + case BPF_ALU64 | BPF_ARSH | BPF_K: /* ((s64) dst) >>= imm */ + if (imm == 0) + break; + /* srag %dst,%dst,imm(%r0) */ + EMIT6_DISP_LH(0xeb000000, 0x000a, dst_reg, dst_reg, REG_0, imm); + break; + /* + * BPF_NEG + */ + case BPF_ALU | BPF_NEG: /* dst = (u32) -dst */ + /* lcr %dst,%dst */ + EMIT2(0x1300, dst_reg, dst_reg); + EMIT_ZERO(dst_reg); + break; + case BPF_ALU64 | BPF_NEG: /* dst = -dst */ + /* lcgr %dst,%dst */ + EMIT4(0xb9130000, dst_reg, dst_reg); + break; + /* + * BPF_FROM_BE/LE + */ + case BPF_ALU | BPF_END | BPF_FROM_BE: + /* s390 is big endian, therefore only clear high order bytes */ + switch (imm) { + case 16: /* dst = (u16) cpu_to_be16(dst) */ + /* llghr %dst,%dst */ + EMIT4(0xb9850000, dst_reg, dst_reg); + break; + case 32: /* dst = (u32) cpu_to_be32(dst) */ + /* llgfr %dst,%dst */ + EMIT4(0xb9160000, dst_reg, dst_reg); + break; + case 64: /* dst = (u64) cpu_to_be64(dst) */ + break; } - goto branch; - case BPF_LD | BPF_W | BPF_ABS: /* A = *(u32 *) (skb->data+K) */ - jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_WORD; - offset = jit->off_load_word; - goto load_abs; - case BPF_LD | BPF_H | BPF_ABS: /* A = *(u16 *) (skb->data+K) */ - jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_HALF; - offset = jit->off_load_half; - goto load_abs; - case BPF_LD | BPF_B | BPF_ABS: /* A = *(u8 *) (skb->data+K) */ - jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_BYTE; - offset = jit->off_load_byte; -load_abs: if ((int) K < 0) - goto out; -call_fn: /* lg %r1,<d(function)>(%r13) */ - EMIT6_DISP(0xe310d000, 0x0004, offset); - /* l %r3,<d(K)>(%r13) */ - EMIT4_DISP(0x5830d000, EMIT_CONST(K)); - /* basr %r8,%r1 */ - EMIT2(0x0d81); - /* jnz <ret0> */ - EMIT4_PCREL(0xa7740000, (jit->ret0_ip - jit->prg)); break; - case BPF_LD | BPF_W | BPF_IND: /* A = *(u32 *) (skb->data+K+X) */ - jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_IWORD; - offset = jit->off_load_iword; - goto call_fn; - case BPF_LD | BPF_H | BPF_IND: /* A = *(u16 *) (skb->data+K+X) */ - jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_IHALF; - offset = jit->off_load_ihalf; - goto call_fn; - case BPF_LD | BPF_B | BPF_IND: /* A = *(u8 *) (skb->data+K+X) */ - jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_IBYTE; - offset = jit->off_load_ibyte; - goto call_fn; - case BPF_LDX | BPF_B | BPF_MSH: - /* X = (*(u8 *)(skb->data+K) & 0xf) << 2 */ - jit->seen |= SEEN_RET0; - if ((int) K < 0) { - /* j <ret0> */ - EMIT4_PCREL(0xa7f40000, (jit->ret0_ip - jit->prg)); + case BPF_ALU | BPF_END | BPF_FROM_LE: + switch (imm) { + case 16: /* dst = (u16) cpu_to_le16(dst) */ + /* lrvr %dst,%dst */ + EMIT4(0xb91f0000, dst_reg, dst_reg); + /* srl %dst,16(%r0) */ + EMIT4_DISP(0x88000000, dst_reg, REG_0, 16); + /* llghr %dst,%dst */ + EMIT4(0xb9850000, dst_reg, dst_reg); + break; + case 32: /* dst = (u32) cpu_to_le32(dst) */ + /* lrvr %dst,%dst */ + EMIT4(0xb91f0000, dst_reg, dst_reg); + /* llgfr %dst,%dst */ + EMIT4(0xb9160000, dst_reg, dst_reg); + break; + case 64: /* dst = (u64) cpu_to_le64(dst) */ + /* lrvgr %dst,%dst */ + EMIT4(0xb90f0000, dst_reg, dst_reg); break; } - jit->seen |= SEEN_DATAREF | SEEN_LOAD_BMSH; - offset = jit->off_load_bmsh; - goto call_fn; - case BPF_LD | BPF_W | BPF_LEN: /* A = skb->len; */ - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4); - /* l %r5,<d(len)>(%r2) */ - EMIT4_DISP(0x58502000, offsetof(struct sk_buff, len)); - break; - case BPF_LDX | BPF_W | BPF_LEN: /* X = skb->len; */ - jit->seen |= SEEN_XREG; - /* l %r12,<d(len)>(%r2) */ - EMIT4_DISP(0x58c02000, offsetof(struct sk_buff, len)); - break; - case BPF_LD | BPF_IMM: /* A = K */ - if (K <= 16383) - /* lhi %r5,K */ - EMIT4_IMM(0xa7580000, K); - else if (test_facility(21)) - /* llilf %r5,<K> */ - EMIT6_IMM(0xc05f0000, K); - else - /* l %r5,<d(K)>(%r13) */ - EMIT4_DISP(0x5850d000, EMIT_CONST(K)); - break; - case BPF_LDX | BPF_IMM: /* X = K */ - jit->seen |= SEEN_XREG; - if (K <= 16383) - /* lhi %r12,<K> */ - EMIT4_IMM(0xa7c80000, K); - else if (test_facility(21)) - /* llilf %r12,<K> */ - EMIT6_IMM(0xc0cf0000, K); - else - /* l %r12,<d(K)>(%r13) */ - EMIT4_DISP(0x58c0d000, EMIT_CONST(K)); break; - case BPF_LD | BPF_MEM: /* A = mem[K] */ + /* + * BPF_ST(X) + */ + case BPF_STX | BPF_MEM | BPF_B: /* *(u8 *)(dst + off) = src_reg */ + /* stcy %src,off(%dst) */ + EMIT6_DISP_LH(0xe3000000, 0x0072, src_reg, dst_reg, REG_0, off); + jit->seen |= SEEN_MEM; + break; + case BPF_STX | BPF_MEM | BPF_H: /* (u16 *)(dst + off) = src */ + /* sthy %src,off(%dst) */ + EMIT6_DISP_LH(0xe3000000, 0x0070, src_reg, dst_reg, REG_0, off); + jit->seen |= SEEN_MEM; + break; + case BPF_STX | BPF_MEM | BPF_W: /* *(u32 *)(dst + off) = src */ + /* sty %src,off(%dst) */ + EMIT6_DISP_LH(0xe3000000, 0x0050, src_reg, dst_reg, REG_0, off); + jit->seen |= SEEN_MEM; + break; + case BPF_STX | BPF_MEM | BPF_DW: /* (u64 *)(dst + off) = src */ + /* stg %src,off(%dst) */ + EMIT6_DISP_LH(0xe3000000, 0x0024, src_reg, dst_reg, REG_0, off); + jit->seen |= SEEN_MEM; + break; + case BPF_ST | BPF_MEM | BPF_B: /* *(u8 *)(dst + off) = imm */ + /* lhi %w0,imm */ + EMIT4_IMM(0xa7080000, REG_W0, (u8) imm); + /* stcy %w0,off(dst) */ + EMIT6_DISP_LH(0xe3000000, 0x0072, REG_W0, dst_reg, REG_0, off); + jit->seen |= SEEN_MEM; + break; + case BPF_ST | BPF_MEM | BPF_H: /* (u16 *)(dst + off) = imm */ + /* lhi %w0,imm */ + EMIT4_IMM(0xa7080000, REG_W0, (u16) imm); + /* sthy %w0,off(dst) */ + EMIT6_DISP_LH(0xe3000000, 0x0070, REG_W0, dst_reg, REG_0, off); jit->seen |= SEEN_MEM; - /* l %r5,<K>(%r15) */ - EMIT4_DISP(0x5850f000, - (jit->seen & SEEN_DATAREF) ? 160 + K*4 : K*4); - break; - case BPF_LDX | BPF_MEM: /* X = mem[K] */ - jit->seen |= SEEN_XREG | SEEN_MEM; - /* l %r12,<K>(%r15) */ - EMIT4_DISP(0x58c0f000, - (jit->seen & SEEN_DATAREF) ? 160 + K*4 : K*4); - break; - case BPF_MISC | BPF_TAX: /* X = A */ - jit->seen |= SEEN_XREG; - /* lr %r12,%r5 */ - EMIT2(0x18c5); - break; - case BPF_MISC | BPF_TXA: /* A = X */ - jit->seen |= SEEN_XREG; - /* lr %r5,%r12 */ - EMIT2(0x185c); - break; - case BPF_RET | BPF_K: - if (K == 0) { - jit->seen |= SEEN_RET0; - if (last) - break; - /* j <ret0> */ - EMIT4_PCREL(0xa7f40000, jit->ret0_ip - jit->prg); - } else { - if (K <= 16383) - /* lghi %r2,K */ - EMIT4_IMM(0xa7290000, K); - else - /* llgf %r2,<K>(%r13) */ - EMIT6_DISP(0xe320d000, 0x0016, EMIT_CONST(K)); - /* j <exit> */ - if (last && !(jit->seen & SEEN_RET0)) - break; - EMIT4_PCREL(0xa7f40000, jit->exit_ip - jit->prg); - } break; - case BPF_RET | BPF_A: - /* llgfr %r2,%r5 */ - EMIT4(0xb9160025); + case BPF_ST | BPF_MEM | BPF_W: /* *(u32 *)(dst + off) = imm */ + /* llilf %w0,imm */ + EMIT6_IMM(0xc00f0000, REG_W0, (u32) imm); + /* sty %w0,off(%dst) */ + EMIT6_DISP_LH(0xe3000000, 0x0050, REG_W0, dst_reg, REG_0, off); + jit->seen |= SEEN_MEM; + break; + case BPF_ST | BPF_MEM | BPF_DW: /* *(u64 *)(dst + off) = imm */ + /* lgfi %w0,imm */ + EMIT6_IMM(0xc0010000, REG_W0, imm); + /* stg %w0,off(%dst) */ + EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W0, dst_reg, REG_0, off); + jit->seen |= SEEN_MEM; + break; + /* + * BPF_STX XADD (atomic_add) + */ + case BPF_STX | BPF_XADD | BPF_W: /* *(u32 *)(dst + off) += src */ + /* laal %w0,%src,off(%dst) */ + EMIT6_DISP_LH(0xeb000000, 0x00fa, REG_W0, src_reg, + dst_reg, off); + jit->seen |= SEEN_MEM; + break; + case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */ + /* laalg %w0,%src,off(%dst) */ + EMIT6_DISP_LH(0xeb000000, 0x00ea, REG_W0, src_reg, + dst_reg, off); + jit->seen |= SEEN_MEM; + break; + /* + * BPF_LDX + */ + case BPF_LDX | BPF_MEM | BPF_B: /* dst = *(u8 *)(ul) (src + off) */ + /* llgc %dst,0(off,%src) */ + EMIT6_DISP_LH(0xe3000000, 0x0090, dst_reg, src_reg, REG_0, off); + jit->seen |= SEEN_MEM; + break; + case BPF_LDX | BPF_MEM | BPF_H: /* dst = *(u16 *)(ul) (src + off) */ + /* llgh %dst,0(off,%src) */ + EMIT6_DISP_LH(0xe3000000, 0x0091, dst_reg, src_reg, REG_0, off); + jit->seen |= SEEN_MEM; + break; + case BPF_LDX | BPF_MEM | BPF_W: /* dst = *(u32 *)(ul) (src + off) */ + /* llgf %dst,off(%src) */ + jit->seen |= SEEN_MEM; + EMIT6_DISP_LH(0xe3000000, 0x0016, dst_reg, src_reg, REG_0, off); + break; + case BPF_LDX | BPF_MEM | BPF_DW: /* dst = *(u64 *)(ul) (src + off) */ + /* lg %dst,0(off,%src) */ + jit->seen |= SEEN_MEM; + EMIT6_DISP_LH(0xe3000000, 0x0004, dst_reg, src_reg, REG_0, off); + break; + /* + * BPF_JMP / CALL + */ + case BPF_JMP | BPF_CALL: + { + /* + * b0 = (__bpf_call_base + imm)(b1, b2, b3, b4, b5) + */ + const u64 func = (u64)__bpf_call_base + imm; + + REG_SET_SEEN(BPF_REG_5); + jit->seen |= SEEN_FUNC; + /* lg %w1,<d(imm)>(%l) */ + EMIT6_DISP(0xe3000000, 0x0004, REG_W1, REG_0, REG_L, + EMIT_CONST_U64(func)); + /* basr %r14,%w1 */ + EMIT2(0x0d00, REG_14, REG_W1); + /* lgr %b0,%r2: load return value into %b0 */ + EMIT4(0xb9040000, BPF_REG_0, REG_2); + break; + } + case BPF_JMP | BPF_EXIT: /* return b0 */ + last = (i == fp->len - 1) ? 1 : 0; + if (last && !(jit->seen & SEEN_RET0)) + break; /* j <exit> */ EMIT4_PCREL(0xa7f40000, jit->exit_ip - jit->prg); break; - case BPF_ST: /* mem[K] = A */ - jit->seen |= SEEN_MEM; - /* st %r5,<K>(%r15) */ - EMIT4_DISP(0x5050f000, - (jit->seen & SEEN_DATAREF) ? 160 + K*4 : K*4); - break; - case BPF_STX: /* mem[K] = X : mov %ebx,off8(%rbp) */ - jit->seen |= SEEN_XREG | SEEN_MEM; - /* st %r12,<K>(%r15) */ - EMIT4_DISP(0x50c0f000, - (jit->seen & SEEN_DATAREF) ? 160 + K*4 : K*4); - break; - case BPF_ANC | SKF_AD_PROTOCOL: /* A = ntohs(skb->protocol); */ - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2); - /* lhi %r5,0 */ - EMIT4(0xa7580000); - /* icm %r5,3,<d(protocol)>(%r2) */ - EMIT4_DISP(0xbf532000, offsetof(struct sk_buff, protocol)); - break; - case BPF_ANC | SKF_AD_IFINDEX: /* if (!skb->dev) return 0; - * A = skb->dev->ifindex */ - BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4); - jit->seen |= SEEN_RET0; - /* lg %r1,<d(dev)>(%r2) */ - EMIT6_DISP(0xe3102000, 0x0004, offsetof(struct sk_buff, dev)); - /* ltgr %r1,%r1 */ - EMIT4(0xb9020011); - /* jz <ret0> */ - EMIT4_PCREL(0xa7840000, jit->ret0_ip - jit->prg); - /* l %r5,<d(ifindex)>(%r1) */ - EMIT4_DISP(0x58501000, offsetof(struct net_device, ifindex)); - break; - case BPF_ANC | SKF_AD_MARK: /* A = skb->mark */ - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); - /* l %r5,<d(mark)>(%r2) */ - EMIT4_DISP(0x58502000, offsetof(struct sk_buff, mark)); - break; - case BPF_ANC | SKF_AD_QUEUE: /* A = skb->queue_mapping */ - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2); - /* lhi %r5,0 */ - EMIT4(0xa7580000); - /* icm %r5,3,<d(queue_mapping)>(%r2) */ - EMIT4_DISP(0xbf532000, offsetof(struct sk_buff, queue_mapping)); - break; - case BPF_ANC | SKF_AD_HATYPE: /* if (!skb->dev) return 0; - * A = skb->dev->type */ - BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, type) != 2); - jit->seen |= SEEN_RET0; - /* lg %r1,<d(dev)>(%r2) */ - EMIT6_DISP(0xe3102000, 0x0004, offsetof(struct sk_buff, dev)); - /* ltgr %r1,%r1 */ - EMIT4(0xb9020011); - /* jz <ret0> */ - EMIT4_PCREL(0xa7840000, jit->ret0_ip - jit->prg); - /* lhi %r5,0 */ - EMIT4(0xa7580000); - /* icm %r5,3,<d(type)>(%r1) */ - EMIT4_DISP(0xbf531000, offsetof(struct net_device, type)); - break; - case BPF_ANC | SKF_AD_RXHASH: /* A = skb->hash */ - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4); - /* l %r5,<d(hash)>(%r2) */ - EMIT4_DISP(0x58502000, offsetof(struct sk_buff, hash)); - break; - case BPF_ANC | SKF_AD_VLAN_TAG: - case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2); - BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000); - /* lhi %r5,0 */ - EMIT4(0xa7580000); - /* icm %r5,3,<d(vlan_tci)>(%r2) */ - EMIT4_DISP(0xbf532000, offsetof(struct sk_buff, vlan_tci)); - if (code == (BPF_ANC | SKF_AD_VLAN_TAG)) { - /* nill %r5,0xefff */ - EMIT4_IMM(0xa5570000, ~VLAN_TAG_PRESENT); - } else { - /* nill %r5,0x1000 */ - EMIT4_IMM(0xa5570000, VLAN_TAG_PRESENT); - /* srl %r5,12 */ - EMIT4_DISP(0x88500000, 12); - } + /* + * Branch relative (number of skipped instructions) to offset on + * condition. + * + * Condition code to mask mapping: + * + * CC | Description | Mask + * ------------------------------ + * 0 | Operands equal | 8 + * 1 | First operand low | 4 + * 2 | First operand high | 2 + * 3 | Unused | 1 + * + * For s390x relative branches: ip = ip + off_bytes + * For BPF relative branches: insn = insn + off_insns + 1 + * + * For example for s390x with offset 0 we jump to the branch + * instruction itself (loop) and for BPF with offset 0 we + * branch to the instruction behind the branch. + */ + case BPF_JMP | BPF_JA: /* if (true) */ + mask = 0xf000; /* j */ + goto branch_oc; + case BPF_JMP | BPF_JSGT | BPF_K: /* ((s64) dst > (s64) imm) */ + mask = 0x2000; /* jh */ + goto branch_ks; + case BPF_JMP | BPF_JSGE | BPF_K: /* ((s64) dst >= (s64) imm) */ + mask = 0xa000; /* jhe */ + goto branch_ks; + case BPF_JMP | BPF_JGT | BPF_K: /* (dst_reg > imm) */ + mask = 0x2000; /* jh */ + goto branch_ku; + case BPF_JMP | BPF_JGE | BPF_K: /* (dst_reg >= imm) */ + mask = 0xa000; /* jhe */ + goto branch_ku; + case BPF_JMP | BPF_JNE | BPF_K: /* (dst_reg != imm) */ + mask = 0x7000; /* jne */ + goto branch_ku; + case BPF_JMP | BPF_JEQ | BPF_K: /* (dst_reg == imm) */ + mask = 0x8000; /* je */ + goto branch_ku; + case BPF_JMP | BPF_JSET | BPF_K: /* (dst_reg & imm) */ + mask = 0x7000; /* jnz */ + /* lgfi %w1,imm (load sign extend imm) */ + EMIT6_IMM(0xc0010000, REG_W1, imm); + /* ngr %w1,%dst */ + EMIT4(0xb9800000, REG_W1, dst_reg); + goto branch_oc; + + case BPF_JMP | BPF_JSGT | BPF_X: /* ((s64) dst > (s64) src) */ + mask = 0x2000; /* jh */ + goto branch_xs; + case BPF_JMP | BPF_JSGE | BPF_X: /* ((s64) dst >= (s64) src) */ + mask = 0xa000; /* jhe */ + goto branch_xs; + case BPF_JMP | BPF_JGT | BPF_X: /* (dst > src) */ + mask = 0x2000; /* jh */ + goto branch_xu; + case BPF_JMP | BPF_JGE | BPF_X: /* (dst >= src) */ + mask = 0xa000; /* jhe */ + goto branch_xu; + case BPF_JMP | BPF_JNE | BPF_X: /* (dst != src) */ + mask = 0x7000; /* jne */ + goto branch_xu; + case BPF_JMP | BPF_JEQ | BPF_X: /* (dst == src) */ + mask = 0x8000; /* je */ + goto branch_xu; + case BPF_JMP | BPF_JSET | BPF_X: /* (dst & src) */ + mask = 0x7000; /* jnz */ + /* ngrk %w1,%dst,%src */ + EMIT4_RRF(0xb9e40000, REG_W1, dst_reg, src_reg); + goto branch_oc; +branch_ks: + /* lgfi %w1,imm (load sign extend imm) */ + EMIT6_IMM(0xc0010000, REG_W1, imm); + /* cgrj %dst,%w1,mask,off */ + EMIT6_PCREL(0xec000000, 0x0064, dst_reg, REG_W1, i, off, mask); + break; +branch_ku: + /* lgfi %w1,imm (load sign extend imm) */ + EMIT6_IMM(0xc0010000, REG_W1, imm); + /* clgrj %dst,%w1,mask,off */ + EMIT6_PCREL(0xec000000, 0x0065, dst_reg, REG_W1, i, off, mask); + break; +branch_xs: + /* cgrj %dst,%src,mask,off */ + EMIT6_PCREL(0xec000000, 0x0064, dst_reg, src_reg, i, off, mask); + break; +branch_xu: + /* clgrj %dst,%src,mask,off */ + EMIT6_PCREL(0xec000000, 0x0065, dst_reg, src_reg, i, off, mask); + break; +branch_oc: + /* brc mask,jmp_off (branch instruction needs 4 bytes) */ + jmp_off = addrs[i + off + 1] - (addrs[i + 1] - 4); + EMIT4_PCREL(0xa7040000 | mask << 8, jmp_off); break; - case BPF_ANC | SKF_AD_PKTTYPE: - /* lhi %r5,0 */ - EMIT4(0xa7580000); - /* ic %r5,<d(pkt_type_offset)>(%r2) */ - EMIT4_DISP(0x43502000, PKT_TYPE_OFFSET()); - /* srl %r5,5 */ - EMIT4_DISP(0x88500000, 5); - break; - case BPF_ANC | SKF_AD_CPU: /* A = smp_processor_id() */ -#ifdef CONFIG_SMP - /* l %r5,<d(cpu_nr)> */ - EMIT4_DISP(0x58500000, offsetof(struct _lowcore, cpu_nr)); -#else - /* lhi %r5,0 */ - EMIT4(0xa7580000); -#endif + /* + * BPF_LD + */ + case BPF_LD | BPF_ABS | BPF_B: /* b0 = *(u8 *) (skb->data+imm) */ + case BPF_LD | BPF_IND | BPF_B: /* b0 = *(u8 *) (skb->data+imm+src) */ + if ((BPF_MODE(insn->code) == BPF_ABS) && (imm >= 0)) + func_addr = __pa(sk_load_byte_pos); + else + func_addr = __pa(sk_load_byte); + goto call_fn; + case BPF_LD | BPF_ABS | BPF_H: /* b0 = *(u16 *) (skb->data+imm) */ + case BPF_LD | BPF_IND | BPF_H: /* b0 = *(u16 *) (skb->data+imm+src) */ + if ((BPF_MODE(insn->code) == BPF_ABS) && (imm >= 0)) + func_addr = __pa(sk_load_half_pos); + else + func_addr = __pa(sk_load_half); + goto call_fn; + case BPF_LD | BPF_ABS | BPF_W: /* b0 = *(u32 *) (skb->data+imm) */ + case BPF_LD | BPF_IND | BPF_W: /* b0 = *(u32 *) (skb->data+imm+src) */ + if ((BPF_MODE(insn->code) == BPF_ABS) && (imm >= 0)) + func_addr = __pa(sk_load_word_pos); + else + func_addr = __pa(sk_load_word); + goto call_fn; +call_fn: + jit->seen |= SEEN_SKB | SEEN_RET0 | SEEN_FUNC; + REG_SET_SEEN(REG_14); /* Return address of possible func call */ + + /* + * Implicit input: + * BPF_REG_6 (R7) : skb pointer + * REG_SKB_DATA (R12): skb data pointer + * + * Calculated input: + * BPF_REG_2 (R3) : offset of byte(s) to fetch in skb + * BPF_REG_5 (R6) : return address + * + * Output: + * BPF_REG_0 (R14): data read from skb + * + * Scratch registers (BPF_REG_1-5) + */ + + /* Call function: llilf %w1,func_addr */ + EMIT6_IMM(0xc00f0000, REG_W1, func_addr); + + /* Offset: lgfi %b2,imm */ + EMIT6_IMM(0xc0010000, BPF_REG_2, imm); + if (BPF_MODE(insn->code) == BPF_IND) + /* agfr %b2,%src (%src is s32 here) */ + EMIT4(0xb9180000, BPF_REG_2, src_reg); + + /* basr %b5,%w1 (%b5 is call saved) */ + EMIT2(0x0d00, BPF_REG_5, REG_W1); + + /* + * Note: For fast access we jump directly after the + * jnz instruction from bpf_jit.S + */ + /* jnz <ret0> */ + EMIT4_PCREL(0xa7740000, jit->ret0_ip - jit->prg); break; default: /* too complex, give up */ - goto out; + pr_err("Unknown opcode %02x\n", insn->code); + return -1; + } + return insn_count; +} + +/* + * Compile eBPF program into s390x code + */ +static int bpf_jit_prog(struct bpf_jit *jit, struct bpf_prog *fp) +{ + int i, insn_count; + + jit->lit = jit->lit_start; + jit->prg = 0; + + bpf_jit_prologue(jit); + for (i = 0; i < fp->len; i += insn_count) { + insn_count = bpf_jit_insn(jit, fp, i); + if (insn_count < 0) + return -1; + jit->addrs[i + 1] = jit->prg; /* Next instruction address */ } - addrs[i] = jit->prg - jit->start; + bpf_jit_epilogue(jit); + + jit->lit_start = jit->prg; + jit->size = jit->lit; + jit->size_prg = jit->prg; return 0; -out: - return -1; } +/* + * Classic BPF function stub. BPF programs will be converted into + * eBPF and then bpf_int_jit_compile() will be called. + */ void bpf_jit_compile(struct bpf_prog *fp) { - struct bpf_binary_header *header = NULL; - unsigned long size, prg_len, lit_len; - struct bpf_jit jit, cjit; - unsigned int *addrs; - int pass, i; +} + +/* + * Compile eBPF program "fp" + */ +void bpf_int_jit_compile(struct bpf_prog *fp) +{ + struct bpf_binary_header *header; + struct bpf_jit jit; + int pass; if (!bpf_jit_enable) return; - addrs = kcalloc(fp->len, sizeof(*addrs), GFP_KERNEL); - if (addrs == NULL) + memset(&jit, 0, sizeof(jit)); + jit.addrs = kcalloc(fp->len + 1, sizeof(*jit.addrs), GFP_KERNEL); + if (jit.addrs == NULL) return; - memset(&jit, 0, sizeof(cjit)); - memset(&cjit, 0, sizeof(cjit)); - - for (pass = 0; pass < 10; pass++) { - jit.prg = jit.start; - jit.lit = jit.mid; - - bpf_jit_prologue(&jit); - bpf_jit_noleaks(&jit, fp->insns); - for (i = 0; i < fp->len; i++) { - if (bpf_jit_insn(&jit, fp->insns + i, addrs, i, - i == fp->len - 1)) - goto out; - } - bpf_jit_epilogue(&jit); - if (jit.start) { - WARN_ON(jit.prg > cjit.prg || jit.lit > cjit.lit); - if (memcmp(&jit, &cjit, sizeof(jit)) == 0) - break; - } else if (jit.prg == cjit.prg && jit.lit == cjit.lit) { - prg_len = jit.prg - jit.start; - lit_len = jit.lit - jit.mid; - size = prg_len + lit_len; - if (size >= BPF_SIZE_MAX) - goto out; - header = bpf_jit_binary_alloc(size, &jit.start, - 2, bpf_jit_fill_hole); - if (!header) - goto out; - jit.prg = jit.mid = jit.start + prg_len; - jit.lit = jit.end = jit.start + prg_len + lit_len; - jit.base_ip += (unsigned long) jit.start; - jit.exit_ip += (unsigned long) jit.start; - jit.ret0_ip += (unsigned long) jit.start; - } - cjit = jit; + /* + * Three initial passes: + * - 1/2: Determine clobbered registers + * - 3: Calculate program size and addrs arrray + */ + for (pass = 1; pass <= 3; pass++) { + if (bpf_jit_prog(&jit, fp)) + goto free_addrs; } + /* + * Final pass: Allocate and generate program + */ + if (jit.size >= BPF_SIZE_MAX) + goto free_addrs; + header = bpf_jit_binary_alloc(jit.size, &jit.prg_buf, 2, jit_fill_hole); + if (!header) + goto free_addrs; + if (bpf_jit_prog(&jit, fp)) + goto free_addrs; if (bpf_jit_enable > 1) { - bpf_jit_dump(fp->len, jit.end - jit.start, pass, jit.start); - if (jit.start) - print_fn_code(jit.start, jit.mid - jit.start); + bpf_jit_dump(fp->len, jit.size, pass, jit.prg_buf); + if (jit.prg_buf) + print_fn_code(jit.prg_buf, jit.size_prg); } - if (jit.start) { + if (jit.prg_buf) { set_memory_ro((unsigned long)header, header->pages); - fp->bpf_func = (void *) jit.start; + fp->bpf_func = (void *) jit.prg_buf; fp->jited = true; } -out: - kfree(addrs); +free_addrs: + kfree(jit.addrs); } +/* + * Free eBPF program + */ void bpf_jit_free(struct bpf_prog *fp) { unsigned long addr = (unsigned long)fp->bpf_func & PAGE_MASK; diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 98336200c7b2..598f023cf8a6 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -190,6 +190,11 @@ int zpci_fmb_enable_device(struct zpci_dev *zdev) return -ENOMEM; WARN_ON((u64) zdev->fmb & 0xf); + /* reset software counters */ + atomic64_set(&zdev->allocated_pages, 0); + atomic64_set(&zdev->mapped_pages, 0); + atomic64_set(&zdev->unmapped_pages, 0); + args.fmb_addr = virt_to_phys(zdev->fmb); return mod_pci(zdev, ZPCI_MOD_FC_SET_MEASURE, 0, &args); } @@ -822,6 +827,7 @@ int zpci_create_device(struct zpci_dev *zdev) if (rc) goto out; + mutex_init(&zdev->lock); if (zdev->state == ZPCI_FN_STATE_CONFIGURED) { rc = zpci_enable_device(zdev); if (rc) diff --git a/arch/s390/pci/pci_debug.c b/arch/s390/pci/pci_debug.c index c22d4402ae45..4129b0a5fd78 100644 --- a/arch/s390/pci/pci_debug.c +++ b/arch/s390/pci/pci_debug.c @@ -31,12 +31,25 @@ static char *pci_perf_names[] = { "Refresh operations", "DMA read bytes", "DMA write bytes", - /* software counters */ +}; + +static char *pci_sw_names[] = { "Allocated pages", "Mapped pages", "Unmapped pages", }; +static void pci_sw_counter_show(struct seq_file *m) +{ + struct zpci_dev *zdev = m->private; + atomic64_t *counter = &zdev->allocated_pages; + int i; + + for (i = 0; i < ARRAY_SIZE(pci_sw_names); i++, counter++) + seq_printf(m, "%26s:\t%llu\n", pci_sw_names[i], + atomic64_read(counter)); +} + static int pci_perf_show(struct seq_file *m, void *v) { struct zpci_dev *zdev = m->private; @@ -45,7 +58,10 @@ static int pci_perf_show(struct seq_file *m, void *v) if (!zdev) return 0; + + mutex_lock(&zdev->lock); if (!zdev->fmb) { + mutex_unlock(&zdev->lock); seq_puts(m, "FMB statistics disabled\n"); return 0; } @@ -65,12 +81,9 @@ static int pci_perf_show(struct seq_file *m, void *v) for (i = 4; i < 6; i++) seq_printf(m, "%26s:\t%llu\n", pci_perf_names[i], *(stat + i)); - /* software counters */ - for (i = 6; i < ARRAY_SIZE(pci_perf_names); i++) - seq_printf(m, "%26s:\t%llu\n", - pci_perf_names[i], - atomic64_read((atomic64_t *) (stat + i))); + pci_sw_counter_show(m); + mutex_unlock(&zdev->lock); return 0; } @@ -88,19 +101,17 @@ static ssize_t pci_perf_seq_write(struct file *file, const char __user *ubuf, if (rc) return rc; + mutex_lock(&zdev->lock); switch (val) { case 0: rc = zpci_fmb_disable_device(zdev); - if (rc) - return rc; break; case 1: rc = zpci_fmb_enable_device(zdev); - if (rc) - return rc; break; } - return count; + mutex_unlock(&zdev->lock); + return rc ? rc : count; } static int pci_perf_seq_open(struct inode *inode, struct file *filp) diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c index 4cbb29a4d615..6fd8d5836138 100644 --- a/arch/s390/pci/pci_dma.c +++ b/arch/s390/pci/pci_dma.c @@ -300,7 +300,7 @@ static dma_addr_t s390_dma_map_pages(struct device *dev, struct page *page, flags |= ZPCI_TABLE_PROTECTED; if (!dma_update_trans(zdev, pa, dma_addr, size, flags)) { - atomic64_add(nr_pages, &zdev->fmb->mapped_pages); + atomic64_add(nr_pages, &zdev->mapped_pages); return dma_addr + (offset & ~PAGE_MASK); } @@ -328,7 +328,7 @@ static void s390_dma_unmap_pages(struct device *dev, dma_addr_t dma_addr, zpci_err_hex(&dma_addr, sizeof(dma_addr)); } - atomic64_add(npages, &zdev->fmb->unmapped_pages); + atomic64_add(npages, &zdev->unmapped_pages); iommu_page_index = (dma_addr - zdev->start_dma) >> PAGE_SHIFT; dma_free_iommu(zdev, iommu_page_index, npages); } @@ -357,7 +357,7 @@ static void *s390_dma_alloc(struct device *dev, size_t size, return NULL; } - atomic64_add(size / PAGE_SIZE, &zdev->fmb->allocated_pages); + atomic64_add(size / PAGE_SIZE, &zdev->allocated_pages); if (dma_handle) *dma_handle = map; return (void *) pa; @@ -370,7 +370,7 @@ static void s390_dma_free(struct device *dev, size_t size, struct zpci_dev *zdev = get_zdev(to_pci_dev(dev)); size = PAGE_ALIGN(size); - atomic64_sub(size / PAGE_SIZE, &zdev->fmb->allocated_pages); + atomic64_sub(size / PAGE_SIZE, &zdev->allocated_pages); s390_dma_unmap_pages(dev, dma_handle, size, DMA_BIDIRECTIONAL, NULL); free_pages((unsigned long) pa, get_order(size)); } diff --git a/arch/sh/include/asm/mmu_context.h b/arch/sh/include/asm/mmu_context.h index b9d9489a5012..9f417feaf6e8 100644 --- a/arch/sh/include/asm/mmu_context.h +++ b/arch/sh/include/asm/mmu_context.h @@ -99,7 +99,7 @@ static inline int init_new_context(struct task_struct *tsk, { int i; - for (i = 0; i < num_online_cpus(); i++) + for_each_online_cpu(i) cpu_context(i, mm) = NO_CONTEXT; return 0; diff --git a/arch/sh/kernel/smp.c b/arch/sh/kernel/smp.c index fc5acfc93c92..de6be008fc01 100644 --- a/arch/sh/kernel/smp.c +++ b/arch/sh/kernel/smp.c @@ -363,7 +363,7 @@ void flush_tlb_mm(struct mm_struct *mm) smp_call_function(flush_tlb_mm_ipi, (void *)mm, 1); } else { int i; - for (i = 0; i < num_online_cpus(); i++) + for_each_online_cpu(i) if (smp_processor_id() != i) cpu_context(i, mm) = 0; } @@ -400,7 +400,7 @@ void flush_tlb_range(struct vm_area_struct *vma, smp_call_function(flush_tlb_range_ipi, (void *)&fd, 1); } else { int i; - for (i = 0; i < num_online_cpus(); i++) + for_each_online_cpu(i) if (smp_processor_id() != i) cpu_context(i, mm) = 0; } @@ -443,7 +443,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long page) smp_call_function(flush_tlb_page_ipi, (void *)&fd, 1); } else { int i; - for (i = 0; i < num_online_cpus(); i++) + for_each_online_cpu(i) if (smp_processor_id() != i) cpu_context(i, vma->vm_mm) = 0; } diff --git a/arch/sparc/kernel/time_32.c b/arch/sparc/kernel/time_32.c index 18147a5523d9..8caf45ee81d9 100644 --- a/arch/sparc/kernel/time_32.c +++ b/arch/sparc/kernel/time_32.c @@ -194,7 +194,7 @@ static __init int setup_timer_cs(void) static void percpu_ce_setup(enum clock_event_mode mode, struct clock_event_device *evt) { - int cpu = __first_cpu(evt->cpumask); + int cpu = cpumask_first(evt->cpumask); switch (mode) { case CLOCK_EVT_MODE_PERIODIC: @@ -214,7 +214,7 @@ static void percpu_ce_setup(enum clock_event_mode mode, static int percpu_ce_set_next_event(unsigned long delta, struct clock_event_device *evt) { - int cpu = __first_cpu(evt->cpumask); + int cpu = cpumask_first(evt->cpumask); unsigned int next = (unsigned int)delta; sparc_config.load_profile_irq(cpu, next); diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c index 7833b2ccdfbc..6873f006f7d0 100644 --- a/arch/tile/kernel/setup.c +++ b/arch/tile/kernel/setup.c @@ -774,7 +774,7 @@ static void __init zone_sizes_init(void) * though, there'll be no lowmem, so we just alloc_bootmem * the memmap. There will be no percpu memory either. */ - if (i != 0 && cpu_isset(i, isolnodes)) { + if (i != 0 && cpumask_test_cpu(i, &isolnodes)) { node_memmap_pfn[i] = alloc_bootmem_pfn(0, memmap_size, 0); BUG_ON(node_percpu[i] != 0); diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index d9d0bd2faaf4..ab3219b3fbda 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -171,8 +171,8 @@ update_clusterinfo(struct notifier_block *nfb, unsigned long action, void *hcpu) for_each_online_cpu(cpu) { if (x2apic_cluster(this_cpu) != x2apic_cluster(cpu)) continue; - __cpu_clear(this_cpu, per_cpu(cpus_in_cluster, cpu)); - __cpu_clear(cpu, per_cpu(cpus_in_cluster, this_cpu)); + cpumask_clear_cpu(this_cpu, per_cpu(cpus_in_cluster, cpu)); + cpumask_clear_cpu(cpu, per_cpu(cpus_in_cluster, this_cpu)); } free_cpumask_var(per_cpu(cpus_in_cluster, this_cpu)); free_cpumask_var(per_cpu(ipi_mask, this_cpu)); diff --git a/drivers/clocksource/dw_apb_timer.c b/drivers/clocksource/dw_apb_timer.c index f3656a6b0382..35a88097af3c 100644 --- a/drivers/clocksource/dw_apb_timer.c +++ b/drivers/clocksource/dw_apb_timer.c @@ -117,7 +117,8 @@ static void apbt_set_mode(enum clock_event_mode mode, unsigned long period; struct dw_apb_clock_event_device *dw_ced = ced_to_dw_apb_ced(evt); - pr_debug("%s CPU %d mode=%d\n", __func__, first_cpu(*evt->cpumask), + pr_debug("%s CPU %d mode=%d\n", __func__, + cpumask_first(evt->cpumask), mode); switch (mode) { diff --git a/drivers/cpuidle/coupled.c b/drivers/cpuidle/coupled.c index 73fe2f8d7f96..7936dce4b878 100644 --- a/drivers/cpuidle/coupled.c +++ b/drivers/cpuidle/coupled.c @@ -292,7 +292,7 @@ static inline int cpuidle_coupled_get_state(struct cpuidle_device *dev, */ smp_rmb(); - for_each_cpu_mask(i, coupled->coupled_cpus) + for_each_cpu(i, &coupled->coupled_cpus) if (cpu_online(i) && coupled->requested_state[i] < state) state = coupled->requested_state[i]; @@ -338,7 +338,7 @@ static void cpuidle_coupled_poke_others(int this_cpu, { int cpu; - for_each_cpu_mask(cpu, coupled->coupled_cpus) + for_each_cpu(cpu, &coupled->coupled_cpus) if (cpu != this_cpu && cpu_online(cpu)) cpuidle_coupled_poke(cpu); } @@ -638,7 +638,7 @@ int cpuidle_coupled_register_device(struct cpuidle_device *dev) if (cpumask_empty(&dev->coupled_cpus)) return 0; - for_each_cpu_mask(cpu, dev->coupled_cpus) { + for_each_cpu(cpu, &dev->coupled_cpus) { other_dev = per_cpu(cpuidle_devices, cpu); if (other_dev && other_dev->coupled) { coupled = other_dev->coupled; diff --git a/drivers/crypto/n2_core.c b/drivers/crypto/n2_core.c index afd136b45f49..10a9aeff1666 100644 --- a/drivers/crypto/n2_core.c +++ b/drivers/crypto/n2_core.c @@ -1754,7 +1754,7 @@ static int spu_mdesc_walk_arcs(struct mdesc_handle *mdesc, dev->dev.of_node->full_name); return -EINVAL; } - cpu_set(*id, p->sharing); + cpumask_set_cpu(*id, &p->sharing); table[*id] = p; } return 0; @@ -1776,7 +1776,7 @@ static int handle_exec_unit(struct spu_mdesc_info *ip, struct list_head *list, return -ENOMEM; } - cpus_clear(p->sharing); + cpumask_clear(&p->sharing); spin_lock_init(&p->lock); p->q_type = q_type; INIT_LIST_HEAD(&p->jobs); diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 48882c126245..e43d48956dea 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -33,6 +33,7 @@ #include <linux/export.h> #include <linux/irq.h> #include <linux/msi.h> +#include <linux/dma-contiguous.h> #include <asm/irq_remapping.h> #include <asm/io_apic.h> #include <asm/apic.h> @@ -126,6 +127,11 @@ static int __init alloc_passthrough_domain(void); * ****************************************************************************/ +static struct protection_domain *to_pdomain(struct iommu_domain *dom) +{ + return container_of(dom, struct protection_domain, domain); +} + static struct iommu_dev_data *alloc_dev_data(u16 devid) { struct iommu_dev_data *dev_data; @@ -1321,7 +1327,9 @@ static u64 *alloc_pte(struct protection_domain *domain, * This function checks if there is a PTE for a given dma address. If * there is one, it returns the pointer to it. */ -static u64 *fetch_pte(struct protection_domain *domain, unsigned long address) +static u64 *fetch_pte(struct protection_domain *domain, + unsigned long address, + unsigned long *page_size) { int level; u64 *pte; @@ -1329,8 +1337,9 @@ static u64 *fetch_pte(struct protection_domain *domain, unsigned long address) if (address > PM_LEVEL_SIZE(domain->mode)) return NULL; - level = domain->mode - 1; - pte = &domain->pt_root[PM_LEVEL_INDEX(level, address)]; + level = domain->mode - 1; + pte = &domain->pt_root[PM_LEVEL_INDEX(level, address)]; + *page_size = PTE_LEVEL_PAGE_SIZE(level); while (level > 0) { @@ -1339,19 +1348,9 @@ static u64 *fetch_pte(struct protection_domain *domain, unsigned long address) return NULL; /* Large PTE */ - if (PM_PTE_LEVEL(*pte) == 0x07) { - unsigned long pte_mask, __pte; - - /* - * If we have a series of large PTEs, make - * sure to return a pointer to the first one. - */ - pte_mask = PTE_PAGE_SIZE(*pte); - pte_mask = ~((PAGE_SIZE_PTE_COUNT(pte_mask) << 3) - 1); - __pte = ((unsigned long)pte) & pte_mask; - - return (u64 *)__pte; - } + if (PM_PTE_LEVEL(*pte) == 7 || + PM_PTE_LEVEL(*pte) == 0) + break; /* No level skipping support yet */ if (PM_PTE_LEVEL(*pte) != level) @@ -1360,8 +1359,21 @@ static u64 *fetch_pte(struct protection_domain *domain, unsigned long address) level -= 1; /* Walk to the next level */ - pte = IOMMU_PTE_PAGE(*pte); - pte = &pte[PM_LEVEL_INDEX(level, address)]; + pte = IOMMU_PTE_PAGE(*pte); + pte = &pte[PM_LEVEL_INDEX(level, address)]; + *page_size = PTE_LEVEL_PAGE_SIZE(level); + } + + if (PM_PTE_LEVEL(*pte) == 0x07) { + unsigned long pte_mask; + + /* + * If we have a series of large PTEs, make + * sure to return a pointer to the first one. + */ + *page_size = pte_mask = PTE_PAGE_SIZE(*pte); + pte_mask = ~((PAGE_SIZE_PTE_COUNT(pte_mask) << 3) - 1); + pte = (u64 *)(((unsigned long)pte) & pte_mask); } return pte; @@ -1383,13 +1395,14 @@ static int iommu_map_page(struct protection_domain *dom, u64 __pte, *pte; int i, count; + BUG_ON(!IS_ALIGNED(bus_addr, page_size)); + BUG_ON(!IS_ALIGNED(phys_addr, page_size)); + if (!(prot & IOMMU_PROT_MASK)) return -EINVAL; - bus_addr = PAGE_ALIGN(bus_addr); - phys_addr = PAGE_ALIGN(phys_addr); - count = PAGE_SIZE_PTE_COUNT(page_size); - pte = alloc_pte(dom, bus_addr, page_size, NULL, GFP_KERNEL); + count = PAGE_SIZE_PTE_COUNT(page_size); + pte = alloc_pte(dom, bus_addr, page_size, NULL, GFP_KERNEL); if (!pte) return -ENOMEM; @@ -1398,7 +1411,7 @@ static int iommu_map_page(struct protection_domain *dom, if (IOMMU_PTE_PRESENT(pte[i])) return -EBUSY; - if (page_size > PAGE_SIZE) { + if (count > 1) { __pte = PAGE_SIZE_PTE(phys_addr, page_size); __pte |= PM_LEVEL_ENC(7) | IOMMU_PTE_P | IOMMU_PTE_FC; } else @@ -1421,7 +1434,8 @@ static unsigned long iommu_unmap_page(struct protection_domain *dom, unsigned long bus_addr, unsigned long page_size) { - unsigned long long unmap_size, unmapped; + unsigned long long unmapped; + unsigned long unmap_size; u64 *pte; BUG_ON(!is_power_of_2(page_size)); @@ -1430,28 +1444,12 @@ static unsigned long iommu_unmap_page(struct protection_domain *dom, while (unmapped < page_size) { - pte = fetch_pte(dom, bus_addr); - - if (!pte) { - /* - * No PTE for this address - * move forward in 4kb steps - */ - unmap_size = PAGE_SIZE; - } else if (PM_PTE_LEVEL(*pte) == 0) { - /* 4kb PTE found for this address */ - unmap_size = PAGE_SIZE; - *pte = 0ULL; - } else { - int count, i; - - /* Large PTE found which maps this address */ - unmap_size = PTE_PAGE_SIZE(*pte); - - /* Only unmap from the first pte in the page */ - if ((unmap_size - 1) & bus_addr) - break; - count = PAGE_SIZE_PTE_COUNT(unmap_size); + pte = fetch_pte(dom, bus_addr, &unmap_size); + + if (pte) { + int i, count; + + count = PAGE_SIZE_PTE_COUNT(unmap_size); for (i = 0; i < count; i++) pte[i] = 0ULL; } @@ -1599,7 +1597,7 @@ static int alloc_new_range(struct dma_ops_domain *dma_dom, { int index = dma_dom->aperture_size >> APERTURE_RANGE_SHIFT; struct amd_iommu *iommu; - unsigned long i, old_size; + unsigned long i, old_size, pte_pgsize; #ifdef CONFIG_IOMMU_STRESS populate = false; @@ -1672,12 +1670,13 @@ static int alloc_new_range(struct dma_ops_domain *dma_dom, */ for (i = dma_dom->aperture[index]->offset; i < dma_dom->aperture_size; - i += PAGE_SIZE) { - u64 *pte = fetch_pte(&dma_dom->domain, i); + i += pte_pgsize) { + u64 *pte = fetch_pte(&dma_dom->domain, i, &pte_pgsize); if (!pte || !IOMMU_PTE_PRESENT(*pte)) continue; - dma_ops_reserve_addresses(dma_dom, i >> PAGE_SHIFT, 1); + dma_ops_reserve_addresses(dma_dom, i >> PAGE_SHIFT, + pte_pgsize >> 12); } update_domain(&dma_dom->domain); @@ -2422,16 +2421,6 @@ static int device_change_notifier(struct notifier_block *nb, dev_data = get_dev_data(dev); switch (action) { - case BUS_NOTIFY_UNBOUND_DRIVER: - - domain = domain_for_device(dev); - - if (!domain) - goto out; - if (dev_data->passthrough) - break; - detach_device(dev); - break; case BUS_NOTIFY_ADD_DEVICE: iommu_init_device(dev); @@ -2467,7 +2456,7 @@ static int device_change_notifier(struct notifier_block *nb, dev->archdata.dma_ops = &amd_iommu_dma_ops; break; - case BUS_NOTIFY_DEL_DEVICE: + case BUS_NOTIFY_REMOVED_DEVICE: iommu_uninit_device(dev); @@ -2923,38 +2912,42 @@ static void *alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr, gfp_t flag, struct dma_attrs *attrs) { - unsigned long flags; - void *virt_addr; - struct protection_domain *domain; - phys_addr_t paddr; u64 dma_mask = dev->coherent_dma_mask; + struct protection_domain *domain; + unsigned long flags; + struct page *page; INC_STATS_COUNTER(cnt_alloc_coherent); domain = get_domain(dev); if (PTR_ERR(domain) == -EINVAL) { - virt_addr = (void *)__get_free_pages(flag, get_order(size)); - *dma_addr = __pa(virt_addr); - return virt_addr; + page = alloc_pages(flag, get_order(size)); + *dma_addr = page_to_phys(page); + return page_address(page); } else if (IS_ERR(domain)) return NULL; + size = PAGE_ALIGN(size); dma_mask = dev->coherent_dma_mask; flag &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32); - flag |= __GFP_ZERO; - virt_addr = (void *)__get_free_pages(flag, get_order(size)); - if (!virt_addr) - return NULL; + page = alloc_pages(flag | __GFP_NOWARN, get_order(size)); + if (!page) { + if (!(flag & __GFP_WAIT)) + return NULL; - paddr = virt_to_phys(virt_addr); + page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT, + get_order(size)); + if (!page) + return NULL; + } if (!dma_mask) dma_mask = *dev->dma_mask; spin_lock_irqsave(&domain->lock, flags); - *dma_addr = __map_single(dev, domain->priv, paddr, + *dma_addr = __map_single(dev, domain->priv, page_to_phys(page), size, DMA_BIDIRECTIONAL, true, dma_mask); if (*dma_addr == DMA_ERROR_CODE) { @@ -2966,11 +2959,12 @@ static void *alloc_coherent(struct device *dev, size_t size, spin_unlock_irqrestore(&domain->lock, flags); - return virt_addr; + return page_address(page); out_free: - free_pages((unsigned long)virt_addr, get_order(size)); + if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT)) + __free_pages(page, get_order(size)); return NULL; } @@ -2982,11 +2976,15 @@ static void free_coherent(struct device *dev, size_t size, void *virt_addr, dma_addr_t dma_addr, struct dma_attrs *attrs) { - unsigned long flags; struct protection_domain *domain; + unsigned long flags; + struct page *page; INC_STATS_COUNTER(cnt_free_coherent); + page = virt_to_page(virt_addr); + size = PAGE_ALIGN(size); + domain = get_domain(dev); if (IS_ERR(domain)) goto free_mem; @@ -3000,7 +2998,8 @@ static void free_coherent(struct device *dev, size_t size, spin_unlock_irqrestore(&domain->lock, flags); free_mem: - free_pages((unsigned long)virt_addr, get_order(size)); + if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT)) + __free_pages(page, get_order(size)); } /* @@ -3236,42 +3235,45 @@ static int __init alloc_passthrough_domain(void) return 0; } -static int amd_iommu_domain_init(struct iommu_domain *dom) + +static struct iommu_domain *amd_iommu_domain_alloc(unsigned type) { - struct protection_domain *domain; + struct protection_domain *pdomain; - domain = protection_domain_alloc(); - if (!domain) - goto out_free; + /* We only support unmanaged domains for now */ + if (type != IOMMU_DOMAIN_UNMANAGED) + return NULL; - domain->mode = PAGE_MODE_3_LEVEL; - domain->pt_root = (void *)get_zeroed_page(GFP_KERNEL); - if (!domain->pt_root) + pdomain = protection_domain_alloc(); + if (!pdomain) goto out_free; - domain->iommu_domain = dom; - - dom->priv = domain; + pdomain->mode = PAGE_MODE_3_LEVEL; + pdomain->pt_root = (void *)get_zeroed_page(GFP_KERNEL); + if (!pdomain->pt_root) + goto out_free; - dom->geometry.aperture_start = 0; - dom->geometry.aperture_end = ~0ULL; - dom->geometry.force_aperture = true; + pdomain->domain.geometry.aperture_start = 0; + pdomain->domain.geometry.aperture_end = ~0ULL; + pdomain->domain.geometry.force_aperture = true; - return 0; + return &pdomain->domain; out_free: - protection_domain_free(domain); + protection_domain_free(pdomain); - return -ENOMEM; + return NULL; } -static void amd_iommu_domain_destroy(struct iommu_domain *dom) +static void amd_iommu_domain_free(struct iommu_domain *dom) { - struct protection_domain *domain = dom->priv; + struct protection_domain *domain; - if (!domain) + if (!dom) return; + domain = to_pdomain(dom); + if (domain->dev_cnt > 0) cleanup_domain(domain); @@ -3284,8 +3286,6 @@ static void amd_iommu_domain_destroy(struct iommu_domain *dom) free_gcr3_table(domain); protection_domain_free(domain); - - dom->priv = NULL; } static void amd_iommu_detach_device(struct iommu_domain *dom, @@ -3313,7 +3313,7 @@ static void amd_iommu_detach_device(struct iommu_domain *dom, static int amd_iommu_attach_device(struct iommu_domain *dom, struct device *dev) { - struct protection_domain *domain = dom->priv; + struct protection_domain *domain = to_pdomain(dom); struct iommu_dev_data *dev_data; struct amd_iommu *iommu; int ret; @@ -3340,7 +3340,7 @@ static int amd_iommu_attach_device(struct iommu_domain *dom, static int amd_iommu_map(struct iommu_domain *dom, unsigned long iova, phys_addr_t paddr, size_t page_size, int iommu_prot) { - struct protection_domain *domain = dom->priv; + struct protection_domain *domain = to_pdomain(dom); int prot = 0; int ret; @@ -3362,7 +3362,7 @@ static int amd_iommu_map(struct iommu_domain *dom, unsigned long iova, static size_t amd_iommu_unmap(struct iommu_domain *dom, unsigned long iova, size_t page_size) { - struct protection_domain *domain = dom->priv; + struct protection_domain *domain = to_pdomain(dom); size_t unmap_size; if (domain->mode == PAGE_MODE_NONE) @@ -3380,28 +3380,22 @@ static size_t amd_iommu_unmap(struct iommu_domain *dom, unsigned long iova, static phys_addr_t amd_iommu_iova_to_phys(struct iommu_domain *dom, dma_addr_t iova) { - struct protection_domain *domain = dom->priv; - unsigned long offset_mask; - phys_addr_t paddr; + struct protection_domain *domain = to_pdomain(dom); + unsigned long offset_mask, pte_pgsize; u64 *pte, __pte; if (domain->mode == PAGE_MODE_NONE) return iova; - pte = fetch_pte(domain, iova); + pte = fetch_pte(domain, iova, &pte_pgsize); if (!pte || !IOMMU_PTE_PRESENT(*pte)) return 0; - if (PM_PTE_LEVEL(*pte) == 0) - offset_mask = PAGE_SIZE - 1; - else - offset_mask = PTE_PAGE_SIZE(*pte) - 1; - - __pte = *pte & PM_ADDR_MASK; - paddr = (__pte & ~offset_mask) | (iova & offset_mask); + offset_mask = pte_pgsize - 1; + __pte = *pte & PM_ADDR_MASK; - return paddr; + return (__pte & ~offset_mask) | (iova & offset_mask); } static bool amd_iommu_capable(enum iommu_cap cap) @@ -3420,8 +3414,8 @@ static bool amd_iommu_capable(enum iommu_cap cap) static const struct iommu_ops amd_iommu_ops = { .capable = amd_iommu_capable, - .domain_init = amd_iommu_domain_init, - .domain_destroy = amd_iommu_domain_destroy, + .domain_alloc = amd_iommu_domain_alloc, + .domain_free = amd_iommu_domain_free, .attach_dev = amd_iommu_attach_device, .detach_dev = amd_iommu_detach_device, .map = amd_iommu_map, @@ -3483,7 +3477,7 @@ EXPORT_SYMBOL(amd_iommu_unregister_ppr_notifier); void amd_iommu_domain_direct_map(struct iommu_domain *dom) { - struct protection_domain *domain = dom->priv; + struct protection_domain *domain = to_pdomain(dom); unsigned long flags; spin_lock_irqsave(&domain->lock, flags); @@ -3504,7 +3498,7 @@ EXPORT_SYMBOL(amd_iommu_domain_direct_map); int amd_iommu_domain_enable_v2(struct iommu_domain *dom, int pasids) { - struct protection_domain *domain = dom->priv; + struct protection_domain *domain = to_pdomain(dom); unsigned long flags; int levels, ret; @@ -3616,7 +3610,7 @@ static int __amd_iommu_flush_page(struct protection_domain *domain, int pasid, int amd_iommu_flush_page(struct iommu_domain *dom, int pasid, u64 address) { - struct protection_domain *domain = dom->priv; + struct protection_domain *domain = to_pdomain(dom); unsigned long flags; int ret; @@ -3638,7 +3632,7 @@ static int __amd_iommu_flush_tlb(struct protection_domain *domain, int pasid) int amd_iommu_flush_tlb(struct iommu_domain *dom, int pasid) { - struct protection_domain *domain = dom->priv; + struct protection_domain *domain = to_pdomain(dom); unsigned long flags; int ret; @@ -3718,7 +3712,7 @@ static int __clear_gcr3(struct protection_domain *domain, int pasid) int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, int pasid, unsigned long cr3) { - struct protection_domain *domain = dom->priv; + struct protection_domain *domain = to_pdomain(dom); unsigned long flags; int ret; @@ -3732,7 +3726,7 @@ EXPORT_SYMBOL(amd_iommu_domain_set_gcr3); int amd_iommu_domain_clear_gcr3(struct iommu_domain *dom, int pasid) { - struct protection_domain *domain = dom->priv; + struct protection_domain *domain = to_pdomain(dom); unsigned long flags; int ret; @@ -3765,17 +3759,17 @@ EXPORT_SYMBOL(amd_iommu_complete_ppr); struct iommu_domain *amd_iommu_get_v2_domain(struct pci_dev *pdev) { - struct protection_domain *domain; + struct protection_domain *pdomain; - domain = get_domain(&pdev->dev); - if (IS_ERR(domain)) + pdomain = get_domain(&pdev->dev); + if (IS_ERR(pdomain)) return NULL; /* Only return IOMMUv2 domains */ - if (!(domain->flags & PD_IOMMUV2_MASK)) + if (!(pdomain->flags & PD_IOMMUV2_MASK)) return NULL; - return domain->iommu_domain; + return &pdomain->domain; } EXPORT_SYMBOL(amd_iommu_get_v2_domain); diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h index c4fffb710c58..05030e523771 100644 --- a/drivers/iommu/amd_iommu_types.h +++ b/drivers/iommu/amd_iommu_types.h @@ -282,6 +282,12 @@ #define PTE_PAGE_SIZE(pte) \ (1ULL << (1 + ffz(((pte) | 0xfffULL)))) +/* + * Takes a page-table level and returns the default page-size for this level + */ +#define PTE_LEVEL_PAGE_SIZE(level) \ + (1ULL << (12 + (9 * (level)))) + #define IOMMU_PTE_P (1ULL << 0) #define IOMMU_PTE_TV (1ULL << 1) #define IOMMU_PTE_U (1ULL << 59) @@ -400,6 +406,8 @@ struct iommu_domain; struct protection_domain { struct list_head list; /* for list of all protection domains */ struct list_head dev_list; /* List of all devices in this domain */ + struct iommu_domain domain; /* generic domain handle used by + iommu core code */ spinlock_t lock; /* mostly used to lock the page table*/ struct mutex api_lock; /* protect page tables in the iommu-api path */ u16 id; /* the domain id written to the device table */ @@ -411,10 +419,7 @@ struct protection_domain { bool updated; /* complete domain flush required */ unsigned dev_cnt; /* devices assigned to this domain */ unsigned dev_iommu[MAX_IOMMUS]; /* per-IOMMU reference count */ - void *priv; /* private data */ - struct iommu_domain *iommu_domain; /* Pointer to generic - domain structure */ - + void *priv; /* private data */ }; /* diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c index 6d5a5c44453b..a1cbba9056fd 100644 --- a/drivers/iommu/amd_iommu_v2.c +++ b/drivers/iommu/amd_iommu_v2.c @@ -417,7 +417,7 @@ static void mn_release(struct mmu_notifier *mn, struct mm_struct *mm) dev_state = pasid_state->device_state; run_inv_ctx_cb = !pasid_state->invalid; - if (run_inv_ctx_cb && pasid_state->device_state->inv_ctx_cb) + if (run_inv_ctx_cb && dev_state->inv_ctx_cb) dev_state->inv_ctx_cb(dev_state->pdev, pasid_state->pasid); unbind_pasid(pasid_state); diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index a3adde6519f0..9f7e1d34a32b 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -343,6 +343,7 @@ struct arm_smmu_domain { struct arm_smmu_cfg cfg; enum arm_smmu_domain_stage stage; struct mutex init_mutex; /* Protects smmu pointer */ + struct iommu_domain domain; }; static struct iommu_ops arm_smmu_ops; @@ -360,6 +361,11 @@ static struct arm_smmu_option_prop arm_smmu_options[] = { { 0, NULL}, }; +static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom) +{ + return container_of(dom, struct arm_smmu_domain, domain); +} + static void parse_driver_options(struct arm_smmu_device *smmu) { int i = 0; @@ -645,7 +651,7 @@ static irqreturn_t arm_smmu_context_fault(int irq, void *dev) u32 fsr, far, fsynr, resume; unsigned long iova; struct iommu_domain *domain = dev; - struct arm_smmu_domain *smmu_domain = domain->priv; + struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); struct arm_smmu_cfg *cfg = &smmu_domain->cfg; struct arm_smmu_device *smmu = smmu_domain->smmu; void __iomem *cb_base; @@ -730,6 +736,20 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain, stage1 = cfg->cbar != CBAR_TYPE_S2_TRANS; cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx); + if (smmu->version > ARM_SMMU_V1) { + /* + * CBA2R. + * *Must* be initialised before CBAR thanks to VMID16 + * architectural oversight affected some implementations. + */ +#ifdef CONFIG_64BIT + reg = CBA2R_RW64_64BIT; +#else + reg = CBA2R_RW64_32BIT; +#endif + writel_relaxed(reg, gr1_base + ARM_SMMU_GR1_CBA2R(cfg->cbndx)); + } + /* CBAR */ reg = cfg->cbar; if (smmu->version == ARM_SMMU_V1) @@ -747,16 +767,6 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain, } writel_relaxed(reg, gr1_base + ARM_SMMU_GR1_CBAR(cfg->cbndx)); - if (smmu->version > ARM_SMMU_V1) { - /* CBA2R */ -#ifdef CONFIG_64BIT - reg = CBA2R_RW64_64BIT; -#else - reg = CBA2R_RW64_32BIT; -#endif - writel_relaxed(reg, gr1_base + ARM_SMMU_GR1_CBA2R(cfg->cbndx)); - } - /* TTBRs */ if (stage1) { reg = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[0]; @@ -836,7 +846,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain, struct io_pgtable_ops *pgtbl_ops; struct io_pgtable_cfg pgtbl_cfg; enum io_pgtable_fmt fmt; - struct arm_smmu_domain *smmu_domain = domain->priv; + struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); struct arm_smmu_cfg *cfg = &smmu_domain->cfg; mutex_lock(&smmu_domain->init_mutex); @@ -958,7 +968,7 @@ out_unlock: static void arm_smmu_destroy_domain_context(struct iommu_domain *domain) { - struct arm_smmu_domain *smmu_domain = domain->priv; + struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); struct arm_smmu_device *smmu = smmu_domain->smmu; struct arm_smmu_cfg *cfg = &smmu_domain->cfg; void __iomem *cb_base; @@ -985,10 +995,12 @@ static void arm_smmu_destroy_domain_context(struct iommu_domain *domain) __arm_smmu_free_bitmap(smmu->context_map, cfg->cbndx); } -static int arm_smmu_domain_init(struct iommu_domain *domain) +static struct iommu_domain *arm_smmu_domain_alloc(unsigned type) { struct arm_smmu_domain *smmu_domain; + if (type != IOMMU_DOMAIN_UNMANAGED) + return NULL; /* * Allocate the domain and initialise some of its data structures. * We can't really do anything meaningful until we've added a @@ -996,17 +1008,17 @@ static int arm_smmu_domain_init(struct iommu_domain *domain) */ smmu_domain = kzalloc(sizeof(*smmu_domain), GFP_KERNEL); if (!smmu_domain) - return -ENOMEM; + return NULL; mutex_init(&smmu_domain->init_mutex); spin_lock_init(&smmu_domain->pgtbl_lock); - domain->priv = smmu_domain; - return 0; + + return &smmu_domain->domain; } -static void arm_smmu_domain_destroy(struct iommu_domain *domain) +static void arm_smmu_domain_free(struct iommu_domain *domain) { - struct arm_smmu_domain *smmu_domain = domain->priv; + struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); /* * Free the domain resources. We assume that all devices have @@ -1143,7 +1155,7 @@ static void arm_smmu_domain_remove_master(struct arm_smmu_domain *smmu_domain, static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) { int ret; - struct arm_smmu_domain *smmu_domain = domain->priv; + struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); struct arm_smmu_device *smmu; struct arm_smmu_master_cfg *cfg; @@ -1187,7 +1199,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) static void arm_smmu_detach_dev(struct iommu_domain *domain, struct device *dev) { - struct arm_smmu_domain *smmu_domain = domain->priv; + struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); struct arm_smmu_master_cfg *cfg; cfg = find_smmu_master_cfg(dev); @@ -1203,7 +1215,7 @@ static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova, { int ret; unsigned long flags; - struct arm_smmu_domain *smmu_domain = domain->priv; + struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); struct io_pgtable_ops *ops= smmu_domain->pgtbl_ops; if (!ops) @@ -1220,7 +1232,7 @@ static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova, { size_t ret; unsigned long flags; - struct arm_smmu_domain *smmu_domain = domain->priv; + struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); struct io_pgtable_ops *ops= smmu_domain->pgtbl_ops; if (!ops) @@ -1235,7 +1247,7 @@ static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova, static phys_addr_t arm_smmu_iova_to_phys_hard(struct iommu_domain *domain, dma_addr_t iova) { - struct arm_smmu_domain *smmu_domain = domain->priv; + struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); struct arm_smmu_device *smmu = smmu_domain->smmu; struct arm_smmu_cfg *cfg = &smmu_domain->cfg; struct io_pgtable_ops *ops= smmu_domain->pgtbl_ops; @@ -1281,7 +1293,7 @@ static phys_addr_t arm_smmu_iova_to_phys(struct iommu_domain *domain, { phys_addr_t ret; unsigned long flags; - struct arm_smmu_domain *smmu_domain = domain->priv; + struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); struct io_pgtable_ops *ops= smmu_domain->pgtbl_ops; if (!ops) @@ -1329,61 +1341,83 @@ static void __arm_smmu_release_pci_iommudata(void *data) kfree(data); } -static int arm_smmu_add_device(struct device *dev) +static int arm_smmu_add_pci_device(struct pci_dev *pdev) { - struct arm_smmu_device *smmu; - struct arm_smmu_master_cfg *cfg; + int i, ret; + u16 sid; struct iommu_group *group; - void (*releasefn)(void *) = NULL; - int ret; - - smmu = find_smmu_for_device(dev); - if (!smmu) - return -ENODEV; + struct arm_smmu_master_cfg *cfg; - group = iommu_group_alloc(); - if (IS_ERR(group)) { - dev_err(dev, "Failed to allocate IOMMU group\n"); + group = iommu_group_get_for_dev(&pdev->dev); + if (IS_ERR(group)) return PTR_ERR(group); - } - - if (dev_is_pci(dev)) { - struct pci_dev *pdev = to_pci_dev(dev); + cfg = iommu_group_get_iommudata(group); + if (!cfg) { cfg = kzalloc(sizeof(*cfg), GFP_KERNEL); if (!cfg) { ret = -ENOMEM; goto out_put_group; } - cfg->num_streamids = 1; - /* - * Assume Stream ID == Requester ID for now. - * We need a way to describe the ID mappings in FDT. - */ - pci_for_each_dma_alias(pdev, __arm_smmu_get_pci_sid, - &cfg->streamids[0]); - releasefn = __arm_smmu_release_pci_iommudata; - } else { - struct arm_smmu_master *master; - - master = find_smmu_master(smmu, dev->of_node); - if (!master) { - ret = -ENODEV; - goto out_put_group; - } + iommu_group_set_iommudata(group, cfg, + __arm_smmu_release_pci_iommudata); + } - cfg = &master->cfg; + if (cfg->num_streamids >= MAX_MASTER_STREAMIDS) { + ret = -ENOSPC; + goto out_put_group; } - iommu_group_set_iommudata(group, cfg, releasefn); - ret = iommu_group_add_device(group, dev); + /* + * Assume Stream ID == Requester ID for now. + * We need a way to describe the ID mappings in FDT. + */ + pci_for_each_dma_alias(pdev, __arm_smmu_get_pci_sid, &sid); + for (i = 0; i < cfg->num_streamids; ++i) + if (cfg->streamids[i] == sid) + break; + + /* Avoid duplicate SIDs, as this can lead to SMR conflicts */ + if (i == cfg->num_streamids) + cfg->streamids[cfg->num_streamids++] = sid; + return 0; out_put_group: iommu_group_put(group); return ret; } +static int arm_smmu_add_platform_device(struct device *dev) +{ + struct iommu_group *group; + struct arm_smmu_master *master; + struct arm_smmu_device *smmu = find_smmu_for_device(dev); + + if (!smmu) + return -ENODEV; + + master = find_smmu_master(smmu, dev->of_node); + if (!master) + return -ENODEV; + + /* No automatic group creation for platform devices */ + group = iommu_group_alloc(); + if (IS_ERR(group)) + return PTR_ERR(group); + + iommu_group_set_iommudata(group, &master->cfg, NULL); + return iommu_group_add_device(group, dev); +} + +static int arm_smmu_add_device(struct device *dev) +{ + if (dev_is_pci(dev)) + return arm_smmu_add_pci_device(to_pci_dev(dev)); + + return arm_smmu_add_platform_device(dev); +} + static void arm_smmu_remove_device(struct device *dev) { iommu_group_remove_device(dev); @@ -1392,7 +1426,7 @@ static void arm_smmu_remove_device(struct device *dev) static int arm_smmu_domain_get_attr(struct iommu_domain *domain, enum iommu_attr attr, void *data) { - struct arm_smmu_domain *smmu_domain = domain->priv; + struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); switch (attr) { case DOMAIN_ATTR_NESTING: @@ -1407,7 +1441,7 @@ static int arm_smmu_domain_set_attr(struct iommu_domain *domain, enum iommu_attr attr, void *data) { int ret = 0; - struct arm_smmu_domain *smmu_domain = domain->priv; + struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); mutex_lock(&smmu_domain->init_mutex); @@ -1435,8 +1469,8 @@ out_unlock: static struct iommu_ops arm_smmu_ops = { .capable = arm_smmu_capable, - .domain_init = arm_smmu_domain_init, - .domain_destroy = arm_smmu_domain_destroy, + .domain_alloc = arm_smmu_domain_alloc, + .domain_free = arm_smmu_domain_free, .attach_dev = arm_smmu_attach_dev, .detach_dev = arm_smmu_detach_dev, .map = arm_smmu_map, @@ -1633,6 +1667,15 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu) size = arm_smmu_id_size_to_bits((id >> ID2_OAS_SHIFT) & ID2_OAS_MASK); smmu->pa_size = size; + /* + * What the page table walker can address actually depends on which + * descriptor format is in use, but since a) we don't know that yet, + * and b) it can vary per context bank, this will have to do... + */ + if (dma_set_mask_and_coherent(smmu->dev, DMA_BIT_MASK(size))) + dev_warn(smmu->dev, + "failed to set DMA mask for table walker\n"); + if (smmu->version == ARM_SMMU_V1) { smmu->va_size = smmu->ipa_size; size = SZ_4K | SZ_2M | SZ_1G; diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c index dc14fec4ede1..3e898504a7c4 100644 --- a/drivers/iommu/exynos-iommu.c +++ b/drivers/iommu/exynos-iommu.c @@ -200,6 +200,7 @@ struct exynos_iommu_domain { short *lv2entcnt; /* free lv2 entry counter for each section */ spinlock_t lock; /* lock for this structure */ spinlock_t pgtablelock; /* lock for modifying page table @ pgtable */ + struct iommu_domain domain; /* generic domain data structure */ }; struct sysmmu_drvdata { @@ -214,6 +215,11 @@ struct sysmmu_drvdata { phys_addr_t pgtable; }; +static struct exynos_iommu_domain *to_exynos_domain(struct iommu_domain *dom) +{ + return container_of(dom, struct exynos_iommu_domain, domain); +} + static bool set_sysmmu_active(struct sysmmu_drvdata *data) { /* return true if the System MMU was not active previously @@ -696,58 +702,60 @@ static inline void pgtable_flush(void *vastart, void *vaend) virt_to_phys(vaend)); } -static int exynos_iommu_domain_init(struct iommu_domain *domain) +static struct iommu_domain *exynos_iommu_domain_alloc(unsigned type) { - struct exynos_iommu_domain *priv; + struct exynos_iommu_domain *exynos_domain; int i; - priv = kzalloc(sizeof(*priv), GFP_KERNEL); - if (!priv) - return -ENOMEM; + if (type != IOMMU_DOMAIN_UNMANAGED) + return NULL; + + exynos_domain = kzalloc(sizeof(*exynos_domain), GFP_KERNEL); + if (!exynos_domain) + return NULL; - priv->pgtable = (sysmmu_pte_t *)__get_free_pages(GFP_KERNEL, 2); - if (!priv->pgtable) + exynos_domain->pgtable = (sysmmu_pte_t *)__get_free_pages(GFP_KERNEL, 2); + if (!exynos_domain->pgtable) goto err_pgtable; - priv->lv2entcnt = (short *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 1); - if (!priv->lv2entcnt) + exynos_domain->lv2entcnt = (short *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 1); + if (!exynos_domain->lv2entcnt) goto err_counter; /* Workaround for System MMU v3.3 to prevent caching 1MiB mapping */ for (i = 0; i < NUM_LV1ENTRIES; i += 8) { - priv->pgtable[i + 0] = ZERO_LV2LINK; - priv->pgtable[i + 1] = ZERO_LV2LINK; - priv->pgtable[i + 2] = ZERO_LV2LINK; - priv->pgtable[i + 3] = ZERO_LV2LINK; - priv->pgtable[i + 4] = ZERO_LV2LINK; - priv->pgtable[i + 5] = ZERO_LV2LINK; - priv->pgtable[i + 6] = ZERO_LV2LINK; - priv->pgtable[i + 7] = ZERO_LV2LINK; + exynos_domain->pgtable[i + 0] = ZERO_LV2LINK; + exynos_domain->pgtable[i + 1] = ZERO_LV2LINK; + exynos_domain->pgtable[i + 2] = ZERO_LV2LINK; + exynos_domain->pgtable[i + 3] = ZERO_LV2LINK; + exynos_domain->pgtable[i + 4] = ZERO_LV2LINK; + exynos_domain->pgtable[i + 5] = ZERO_LV2LINK; + exynos_domain->pgtable[i + 6] = ZERO_LV2LINK; + exynos_domain->pgtable[i + 7] = ZERO_LV2LINK; } - pgtable_flush(priv->pgtable, priv->pgtable + NUM_LV1ENTRIES); + pgtable_flush(exynos_domain->pgtable, exynos_domain->pgtable + NUM_LV1ENTRIES); - spin_lock_init(&priv->lock); - spin_lock_init(&priv->pgtablelock); - INIT_LIST_HEAD(&priv->clients); + spin_lock_init(&exynos_domain->lock); + spin_lock_init(&exynos_domain->pgtablelock); + INIT_LIST_HEAD(&exynos_domain->clients); - domain->geometry.aperture_start = 0; - domain->geometry.aperture_end = ~0UL; - domain->geometry.force_aperture = true; + exynos_domain->domain.geometry.aperture_start = 0; + exynos_domain->domain.geometry.aperture_end = ~0UL; + exynos_domain->domain.geometry.force_aperture = true; - domain->priv = priv; - return 0; + return &exynos_domain->domain; err_counter: - free_pages((unsigned long)priv->pgtable, 2); + free_pages((unsigned long)exynos_domain->pgtable, 2); err_pgtable: - kfree(priv); - return -ENOMEM; + kfree(exynos_domain); + return NULL; } -static void exynos_iommu_domain_destroy(struct iommu_domain *domain) +static void exynos_iommu_domain_free(struct iommu_domain *domain) { - struct exynos_iommu_domain *priv = domain->priv; + struct exynos_iommu_domain *priv = to_exynos_domain(domain); struct exynos_iommu_owner *owner; unsigned long flags; int i; @@ -773,15 +781,14 @@ static void exynos_iommu_domain_destroy(struct iommu_domain *domain) free_pages((unsigned long)priv->pgtable, 2); free_pages((unsigned long)priv->lv2entcnt, 1); - kfree(domain->priv); - domain->priv = NULL; + kfree(priv); } static int exynos_iommu_attach_device(struct iommu_domain *domain, struct device *dev) { struct exynos_iommu_owner *owner = dev->archdata.iommu; - struct exynos_iommu_domain *priv = domain->priv; + struct exynos_iommu_domain *priv = to_exynos_domain(domain); phys_addr_t pagetable = virt_to_phys(priv->pgtable); unsigned long flags; int ret; @@ -812,7 +819,7 @@ static void exynos_iommu_detach_device(struct iommu_domain *domain, struct device *dev) { struct exynos_iommu_owner *owner; - struct exynos_iommu_domain *priv = domain->priv; + struct exynos_iommu_domain *priv = to_exynos_domain(domain); phys_addr_t pagetable = virt_to_phys(priv->pgtable); unsigned long flags; @@ -988,7 +995,7 @@ static int lv2set_page(sysmmu_pte_t *pent, phys_addr_t paddr, size_t size, static int exynos_iommu_map(struct iommu_domain *domain, unsigned long l_iova, phys_addr_t paddr, size_t size, int prot) { - struct exynos_iommu_domain *priv = domain->priv; + struct exynos_iommu_domain *priv = to_exynos_domain(domain); sysmmu_pte_t *entry; sysmmu_iova_t iova = (sysmmu_iova_t)l_iova; unsigned long flags; @@ -1042,7 +1049,7 @@ static void exynos_iommu_tlb_invalidate_entry(struct exynos_iommu_domain *priv, static size_t exynos_iommu_unmap(struct iommu_domain *domain, unsigned long l_iova, size_t size) { - struct exynos_iommu_domain *priv = domain->priv; + struct exynos_iommu_domain *priv = to_exynos_domain(domain); sysmmu_iova_t iova = (sysmmu_iova_t)l_iova; sysmmu_pte_t *ent; size_t err_pgsize; @@ -1119,7 +1126,7 @@ err: static phys_addr_t exynos_iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova) { - struct exynos_iommu_domain *priv = domain->priv; + struct exynos_iommu_domain *priv = to_exynos_domain(domain); sysmmu_pte_t *entry; unsigned long flags; phys_addr_t phys = 0; @@ -1171,8 +1178,8 @@ static void exynos_iommu_remove_device(struct device *dev) } static const struct iommu_ops exynos_iommu_ops = { - .domain_init = exynos_iommu_domain_init, - .domain_destroy = exynos_iommu_domain_destroy, + .domain_alloc = exynos_iommu_domain_alloc, + .domain_free = exynos_iommu_domain_free, .attach_dev = exynos_iommu_attach_device, .detach_dev = exynos_iommu_detach_device, .map = exynos_iommu_map, diff --git a/drivers/iommu/fsl_pamu_domain.c b/drivers/iommu/fsl_pamu_domain.c index ceebd287b660..1d452930c890 100644 --- a/drivers/iommu/fsl_pamu_domain.c +++ b/drivers/iommu/fsl_pamu_domain.c @@ -33,6 +33,11 @@ static struct kmem_cache *fsl_pamu_domain_cache; static struct kmem_cache *iommu_devinfo_cache; static DEFINE_SPINLOCK(device_domain_lock); +static struct fsl_dma_domain *to_fsl_dma_domain(struct iommu_domain *dom) +{ + return container_of(dom, struct fsl_dma_domain, iommu_domain); +} + static int __init iommu_init_mempool(void) { fsl_pamu_domain_cache = kmem_cache_create("fsl_pamu_domain", @@ -65,7 +70,7 @@ static phys_addr_t get_phys_addr(struct fsl_dma_domain *dma_domain, dma_addr_t i struct dma_window *win_ptr = &dma_domain->win_arr[0]; struct iommu_domain_geometry *geom; - geom = &dma_domain->iommu_domain->geometry; + geom = &dma_domain->iommu_domain.geometry; if (!win_cnt || !dma_domain->geom_size) { pr_debug("Number of windows/geometry not configured for the domain\n"); @@ -123,7 +128,7 @@ static int map_win(int liodn, struct fsl_dma_domain *dma_domain) { int ret; struct dma_window *wnd = &dma_domain->win_arr[0]; - phys_addr_t wnd_addr = dma_domain->iommu_domain->geometry.aperture_start; + phys_addr_t wnd_addr = dma_domain->iommu_domain.geometry.aperture_start; unsigned long flags; spin_lock_irqsave(&iommu_lock, flags); @@ -172,7 +177,7 @@ static int update_liodn(int liodn, struct fsl_dma_domain *dma_domain, u32 wnd_nr } else { phys_addr_t wnd_addr; - wnd_addr = dma_domain->iommu_domain->geometry.aperture_start; + wnd_addr = dma_domain->iommu_domain.geometry.aperture_start; ret = pamu_config_ppaace(liodn, wnd_addr, wnd->size, @@ -384,7 +389,7 @@ static void attach_device(struct fsl_dma_domain *dma_domain, int liodn, struct d static phys_addr_t fsl_pamu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova) { - struct fsl_dma_domain *dma_domain = domain->priv; + struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain); if (iova < domain->geometry.aperture_start || iova > domain->geometry.aperture_end) @@ -398,11 +403,9 @@ static bool fsl_pamu_capable(enum iommu_cap cap) return cap == IOMMU_CAP_CACHE_COHERENCY; } -static void fsl_pamu_domain_destroy(struct iommu_domain *domain) +static void fsl_pamu_domain_free(struct iommu_domain *domain) { - struct fsl_dma_domain *dma_domain = domain->priv; - - domain->priv = NULL; + struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain); /* remove all the devices from the device list */ detach_device(NULL, dma_domain); @@ -413,23 +416,24 @@ static void fsl_pamu_domain_destroy(struct iommu_domain *domain) kmem_cache_free(fsl_pamu_domain_cache, dma_domain); } -static int fsl_pamu_domain_init(struct iommu_domain *domain) +static struct iommu_domain *fsl_pamu_domain_alloc(unsigned type) { struct fsl_dma_domain *dma_domain; + if (type != IOMMU_DOMAIN_UNMANAGED) + return NULL; + dma_domain = iommu_alloc_dma_domain(); if (!dma_domain) { pr_debug("dma_domain allocation failed\n"); - return -ENOMEM; + return NULL; } - domain->priv = dma_domain; - dma_domain->iommu_domain = domain; /* defaul geometry 64 GB i.e. maximum system address */ - domain->geometry.aperture_start = 0; - domain->geometry.aperture_end = (1ULL << 36) - 1; - domain->geometry.force_aperture = true; + dma_domain->iommu_domain. geometry.aperture_start = 0; + dma_domain->iommu_domain.geometry.aperture_end = (1ULL << 36) - 1; + dma_domain->iommu_domain.geometry.force_aperture = true; - return 0; + return &dma_domain->iommu_domain; } /* Configure geometry settings for all LIODNs associated with domain */ @@ -499,7 +503,7 @@ static int disable_domain_win(struct fsl_dma_domain *dma_domain, u32 wnd_nr) static void fsl_pamu_window_disable(struct iommu_domain *domain, u32 wnd_nr) { - struct fsl_dma_domain *dma_domain = domain->priv; + struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain); unsigned long flags; int ret; @@ -530,7 +534,7 @@ static void fsl_pamu_window_disable(struct iommu_domain *domain, u32 wnd_nr) static int fsl_pamu_window_enable(struct iommu_domain *domain, u32 wnd_nr, phys_addr_t paddr, u64 size, int prot) { - struct fsl_dma_domain *dma_domain = domain->priv; + struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain); struct dma_window *wnd; int pamu_prot = 0; int ret; @@ -607,7 +611,7 @@ static int handle_attach_device(struct fsl_dma_domain *dma_domain, int num) { unsigned long flags; - struct iommu_domain *domain = dma_domain->iommu_domain; + struct iommu_domain *domain = &dma_domain->iommu_domain; int ret = 0; int i; @@ -653,7 +657,7 @@ static int handle_attach_device(struct fsl_dma_domain *dma_domain, static int fsl_pamu_attach_device(struct iommu_domain *domain, struct device *dev) { - struct fsl_dma_domain *dma_domain = domain->priv; + struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain); const u32 *liodn; u32 liodn_cnt; int len, ret = 0; @@ -691,7 +695,7 @@ static int fsl_pamu_attach_device(struct iommu_domain *domain, static void fsl_pamu_detach_device(struct iommu_domain *domain, struct device *dev) { - struct fsl_dma_domain *dma_domain = domain->priv; + struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain); const u32 *prop; int len; struct pci_dev *pdev = NULL; @@ -723,7 +727,7 @@ static void fsl_pamu_detach_device(struct iommu_domain *domain, static int configure_domain_geometry(struct iommu_domain *domain, void *data) { struct iommu_domain_geometry *geom_attr = data; - struct fsl_dma_domain *dma_domain = domain->priv; + struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain); dma_addr_t geom_size; unsigned long flags; @@ -813,7 +817,7 @@ static int configure_domain_dma_state(struct fsl_dma_domain *dma_domain, bool en static int fsl_pamu_set_domain_attr(struct iommu_domain *domain, enum iommu_attr attr_type, void *data) { - struct fsl_dma_domain *dma_domain = domain->priv; + struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain); int ret = 0; switch (attr_type) { @@ -838,7 +842,7 @@ static int fsl_pamu_set_domain_attr(struct iommu_domain *domain, static int fsl_pamu_get_domain_attr(struct iommu_domain *domain, enum iommu_attr attr_type, void *data) { - struct fsl_dma_domain *dma_domain = domain->priv; + struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain); int ret = 0; switch (attr_type) { @@ -999,7 +1003,7 @@ static void fsl_pamu_remove_device(struct device *dev) static int fsl_pamu_set_windows(struct iommu_domain *domain, u32 w_count) { - struct fsl_dma_domain *dma_domain = domain->priv; + struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain); unsigned long flags; int ret; @@ -1048,15 +1052,15 @@ static int fsl_pamu_set_windows(struct iommu_domain *domain, u32 w_count) static u32 fsl_pamu_get_windows(struct iommu_domain *domain) { - struct fsl_dma_domain *dma_domain = domain->priv; + struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain); return dma_domain->win_cnt; } static const struct iommu_ops fsl_pamu_ops = { .capable = fsl_pamu_capable, - .domain_init = fsl_pamu_domain_init, - .domain_destroy = fsl_pamu_domain_destroy, + .domain_alloc = fsl_pamu_domain_alloc, + .domain_free = fsl_pamu_domain_free, .attach_dev = fsl_pamu_attach_device, .detach_dev = fsl_pamu_detach_device, .domain_window_enable = fsl_pamu_window_enable, diff --git a/drivers/iommu/fsl_pamu_domain.h b/drivers/iommu/fsl_pamu_domain.h index c90293f99709..f2b0f741d3de 100644 --- a/drivers/iommu/fsl_pamu_domain.h +++ b/drivers/iommu/fsl_pamu_domain.h @@ -71,7 +71,7 @@ struct fsl_dma_domain { u32 stash_id; struct pamu_stash_attribute dma_stash; u32 snoop_id; - struct iommu_domain *iommu_domain; + struct iommu_domain iommu_domain; spinlock_t domain_lock; }; diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 4fc1f8a7f98e..a35927cd42e5 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -339,7 +339,7 @@ struct dmar_domain { DECLARE_BITMAP(iommu_bmp, DMAR_UNITS_SUPPORTED); /* bitmap of iommus this domain uses*/ - struct list_head devices; /* all devices' list */ + struct list_head devices; /* all devices' list */ struct iova_domain iovad; /* iova's that belong to this domain */ struct dma_pte *pgd; /* virtual address */ @@ -358,6 +358,9 @@ struct dmar_domain { 2 == 1GiB, 3 == 512GiB, 4 == 1TiB */ spinlock_t iommu_lock; /* protect iommu set in domain */ u64 max_addr; /* maximum mapped address */ + + struct iommu_domain domain; /* generic domain data structure for + iommu core */ }; /* PCI domain-device relationship */ @@ -449,6 +452,12 @@ static LIST_HEAD(device_domain_list); static const struct iommu_ops intel_iommu_ops; +/* Convert generic 'struct iommu_domain to private struct dmar_domain */ +static struct dmar_domain *to_dmar_domain(struct iommu_domain *dom) +{ + return container_of(dom, struct dmar_domain, domain); +} + static int __init intel_iommu_setup(char *str) { if (!str) @@ -595,12 +604,13 @@ static void domain_update_iommu_coherency(struct dmar_domain *domain) { struct dmar_drhd_unit *drhd; struct intel_iommu *iommu; - int i, found = 0; + bool found = false; + int i; domain->iommu_coherency = 1; for_each_set_bit(i, domain->iommu_bmp, g_num_of_iommus) { - found = 1; + found = true; if (!ecap_coherent(g_iommus[i]->ecap)) { domain->iommu_coherency = 0; break; @@ -1267,7 +1277,7 @@ static struct device_domain_info * iommu_support_dev_iotlb (struct dmar_domain *domain, struct intel_iommu *iommu, u8 bus, u8 devfn) { - int found = 0; + bool found = false; unsigned long flags; struct device_domain_info *info; struct pci_dev *pdev; @@ -1282,7 +1292,7 @@ iommu_support_dev_iotlb (struct dmar_domain *domain, struct intel_iommu *iommu, list_for_each_entry(info, &domain->devices, link) if (info->iommu == iommu && info->bus == bus && info->devfn == devfn) { - found = 1; + found = true; break; } spin_unlock_irqrestore(&device_domain_lock, flags); @@ -4269,7 +4279,7 @@ static void domain_remove_one_dev_info(struct dmar_domain *domain, struct device_domain_info *info, *tmp; struct intel_iommu *iommu; unsigned long flags; - int found = 0; + bool found = false; u8 bus, devfn; iommu = device_to_iommu(dev, &bus, &devfn); @@ -4301,7 +4311,7 @@ static void domain_remove_one_dev_info(struct dmar_domain *domain, * update iommu count and coherency */ if (info->iommu == iommu) - found = 1; + found = true; } spin_unlock_irqrestore(&device_domain_lock, flags); @@ -4339,44 +4349,45 @@ static int md_domain_init(struct dmar_domain *domain, int guest_width) return 0; } -static int intel_iommu_domain_init(struct iommu_domain *domain) +static struct iommu_domain *intel_iommu_domain_alloc(unsigned type) { struct dmar_domain *dmar_domain; + struct iommu_domain *domain; + + if (type != IOMMU_DOMAIN_UNMANAGED) + return NULL; dmar_domain = alloc_domain(DOMAIN_FLAG_VIRTUAL_MACHINE); if (!dmar_domain) { printk(KERN_ERR "intel_iommu_domain_init: dmar_domain == NULL\n"); - return -ENOMEM; + return NULL; } if (md_domain_init(dmar_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) { printk(KERN_ERR "intel_iommu_domain_init() failed\n"); domain_exit(dmar_domain); - return -ENOMEM; + return NULL; } domain_update_iommu_cap(dmar_domain); - domain->priv = dmar_domain; + domain = &dmar_domain->domain; domain->geometry.aperture_start = 0; domain->geometry.aperture_end = __DOMAIN_MAX_ADDR(dmar_domain->gaw); domain->geometry.force_aperture = true; - return 0; + return domain; } -static void intel_iommu_domain_destroy(struct iommu_domain *domain) +static void intel_iommu_domain_free(struct iommu_domain *domain) { - struct dmar_domain *dmar_domain = domain->priv; - - domain->priv = NULL; - domain_exit(dmar_domain); + domain_exit(to_dmar_domain(domain)); } static int intel_iommu_attach_device(struct iommu_domain *domain, struct device *dev) { - struct dmar_domain *dmar_domain = domain->priv; + struct dmar_domain *dmar_domain = to_dmar_domain(domain); struct intel_iommu *iommu; int addr_width; u8 bus, devfn; @@ -4441,16 +4452,14 @@ static int intel_iommu_attach_device(struct iommu_domain *domain, static void intel_iommu_detach_device(struct iommu_domain *domain, struct device *dev) { - struct dmar_domain *dmar_domain = domain->priv; - - domain_remove_one_dev_info(dmar_domain, dev); + domain_remove_one_dev_info(to_dmar_domain(domain), dev); } static int intel_iommu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t hpa, size_t size, int iommu_prot) { - struct dmar_domain *dmar_domain = domain->priv; + struct dmar_domain *dmar_domain = to_dmar_domain(domain); u64 max_addr; int prot = 0; int ret; @@ -4487,7 +4496,7 @@ static int intel_iommu_map(struct iommu_domain *domain, static size_t intel_iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size) { - struct dmar_domain *dmar_domain = domain->priv; + struct dmar_domain *dmar_domain = to_dmar_domain(domain); struct page *freelist = NULL; struct intel_iommu *iommu; unsigned long start_pfn, last_pfn; @@ -4535,7 +4544,7 @@ static size_t intel_iommu_unmap(struct iommu_domain *domain, static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova) { - struct dmar_domain *dmar_domain = domain->priv; + struct dmar_domain *dmar_domain = to_dmar_domain(domain); struct dma_pte *pte; int level = 0; u64 phys = 0; @@ -4594,8 +4603,8 @@ static void intel_iommu_remove_device(struct device *dev) static const struct iommu_ops intel_iommu_ops = { .capable = intel_iommu_capable, - .domain_init = intel_iommu_domain_init, - .domain_destroy = intel_iommu_domain_destroy, + .domain_alloc = intel_iommu_domain_alloc, + .domain_free = intel_iommu_domain_free, .attach_dev = intel_iommu_attach_device, .detach_dev = intel_iommu_detach_device, .map = intel_iommu_map, diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c index 14de1ab223c8..6c25b3c5b729 100644 --- a/drivers/iommu/intel_irq_remapping.c +++ b/drivers/iommu/intel_irq_remapping.c @@ -631,7 +631,7 @@ static int __init intel_enable_irq_remapping(void) { struct dmar_drhd_unit *drhd; struct intel_iommu *iommu; - int setup = 0; + bool setup = false; int eim = 0; if (x2apic_supported()) { @@ -697,7 +697,7 @@ static int __init intel_enable_irq_remapping(void) */ for_each_iommu(iommu, drhd) { iommu_set_irq_remapping(iommu, eim); - setup = 1; + setup = true; } if (!setup) @@ -856,7 +856,7 @@ static int __init parse_ioapics_under_ir(void) { struct dmar_drhd_unit *drhd; struct intel_iommu *iommu; - int ir_supported = 0; + bool ir_supported = false; int ioapic_idx; for_each_iommu(iommu, drhd) @@ -864,7 +864,7 @@ static int __init parse_ioapics_under_ir(void) if (ir_parse_ioapic_hpet_scope(drhd->hdr, iommu)) return -1; - ir_supported = 1; + ir_supported = true; } if (!ir_supported) @@ -917,7 +917,7 @@ static void disable_irq_remapping(void) static int reenable_irq_remapping(int eim) { struct dmar_drhd_unit *drhd; - int setup = 0; + bool setup = false; struct intel_iommu *iommu = NULL; for_each_iommu(iommu, drhd) @@ -933,7 +933,7 @@ static int reenable_irq_remapping(int eim) /* Set up interrupt remapping for iommu.*/ iommu_set_irq_remapping(iommu, eim); - setup = 1; + setup = true; } if (!setup) diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index b610a8dee238..4e460216bd16 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -116,6 +116,8 @@ #define ARM_32_LPAE_TCR_EAE (1 << 31) #define ARM_64_LPAE_S2_TCR_RES1 (1 << 31) +#define ARM_LPAE_TCR_EPD1 (1 << 23) + #define ARM_LPAE_TCR_TG0_4K (0 << 14) #define ARM_LPAE_TCR_TG0_64K (1 << 14) #define ARM_LPAE_TCR_TG0_16K (2 << 14) @@ -621,6 +623,9 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie) } reg |= (64ULL - cfg->ias) << ARM_LPAE_TCR_T0SZ_SHIFT; + + /* Disable speculative walks through TTBR1 */ + reg |= ARM_LPAE_TCR_EPD1; cfg->arm_lpae_s1_cfg.tcr = reg; /* MAIRs */ diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 72e683df0731..d4f527e56679 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -901,36 +901,24 @@ EXPORT_SYMBOL_GPL(iommu_set_fault_handler); struct iommu_domain *iommu_domain_alloc(struct bus_type *bus) { struct iommu_domain *domain; - int ret; if (bus == NULL || bus->iommu_ops == NULL) return NULL; - domain = kzalloc(sizeof(*domain), GFP_KERNEL); + domain = bus->iommu_ops->domain_alloc(IOMMU_DOMAIN_UNMANAGED); if (!domain) return NULL; - domain->ops = bus->iommu_ops; - - ret = domain->ops->domain_init(domain); - if (ret) - goto out_free; + domain->ops = bus->iommu_ops; + domain->type = IOMMU_DOMAIN_UNMANAGED; return domain; - -out_free: - kfree(domain); - - return NULL; } EXPORT_SYMBOL_GPL(iommu_domain_alloc); void iommu_domain_free(struct iommu_domain *domain) { - if (likely(domain->ops->domain_destroy != NULL)) - domain->ops->domain_destroy(domain); - - kfree(domain); + domain->ops->domain_free(domain); } EXPORT_SYMBOL_GPL(iommu_domain_free); @@ -1049,6 +1037,9 @@ int iommu_map(struct iommu_domain *domain, unsigned long iova, domain->ops->pgsize_bitmap == 0UL)) return -ENODEV; + if (unlikely(!(domain->type & __IOMMU_DOMAIN_PAGING))) + return -EINVAL; + /* find out the minimum page size supported */ min_pagesz = 1 << __ffs(domain->ops->pgsize_bitmap); @@ -1100,6 +1091,9 @@ size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size) domain->ops->pgsize_bitmap == 0UL)) return -ENODEV; + if (unlikely(!(domain->type & __IOMMU_DOMAIN_PAGING))) + return -EINVAL; + /* find out the minimum page size supported */ min_pagesz = 1 << __ffs(domain->ops->pgsize_bitmap); diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c index bc39bdf7b99b..1a67c531a07e 100644 --- a/drivers/iommu/ipmmu-vmsa.c +++ b/drivers/iommu/ipmmu-vmsa.c @@ -38,7 +38,7 @@ struct ipmmu_vmsa_device { struct ipmmu_vmsa_domain { struct ipmmu_vmsa_device *mmu; - struct iommu_domain *io_domain; + struct iommu_domain io_domain; struct io_pgtable_cfg cfg; struct io_pgtable_ops *iop; @@ -56,6 +56,11 @@ struct ipmmu_vmsa_archdata { static DEFINE_SPINLOCK(ipmmu_devices_lock); static LIST_HEAD(ipmmu_devices); +static struct ipmmu_vmsa_domain *to_vmsa_domain(struct iommu_domain *dom) +{ + return container_of(dom, struct ipmmu_vmsa_domain, io_domain); +} + #define TLB_LOOP_TIMEOUT 100 /* 100us */ /* ----------------------------------------------------------------------------- @@ -428,7 +433,7 @@ static irqreturn_t ipmmu_domain_irq(struct ipmmu_vmsa_domain *domain) * TODO: We need to look up the faulty device based on the I/O VA. Use * the IOMMU device for now. */ - if (!report_iommu_fault(domain->io_domain, mmu->dev, iova, 0)) + if (!report_iommu_fault(&domain->io_domain, mmu->dev, iova, 0)) return IRQ_HANDLED; dev_err_ratelimited(mmu->dev, @@ -448,7 +453,7 @@ static irqreturn_t ipmmu_irq(int irq, void *dev) return IRQ_NONE; io_domain = mmu->mapping->domain; - domain = io_domain->priv; + domain = to_vmsa_domain(io_domain); return ipmmu_domain_irq(domain); } @@ -457,25 +462,25 @@ static irqreturn_t ipmmu_irq(int irq, void *dev) * IOMMU Operations */ -static int ipmmu_domain_init(struct iommu_domain *io_domain) +static struct iommu_domain *ipmmu_domain_alloc(unsigned type) { struct ipmmu_vmsa_domain *domain; + if (type != IOMMU_DOMAIN_UNMANAGED) + return NULL; + domain = kzalloc(sizeof(*domain), GFP_KERNEL); if (!domain) - return -ENOMEM; + return NULL; spin_lock_init(&domain->lock); - io_domain->priv = domain; - domain->io_domain = io_domain; - - return 0; + return &domain->io_domain; } -static void ipmmu_domain_destroy(struct iommu_domain *io_domain) +static void ipmmu_domain_free(struct iommu_domain *io_domain) { - struct ipmmu_vmsa_domain *domain = io_domain->priv; + struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain); /* * Free the domain resources. We assume that all devices have already @@ -491,7 +496,7 @@ static int ipmmu_attach_device(struct iommu_domain *io_domain, { struct ipmmu_vmsa_archdata *archdata = dev->archdata.iommu; struct ipmmu_vmsa_device *mmu = archdata->mmu; - struct ipmmu_vmsa_domain *domain = io_domain->priv; + struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain); unsigned long flags; unsigned int i; int ret = 0; @@ -532,7 +537,7 @@ static void ipmmu_detach_device(struct iommu_domain *io_domain, struct device *dev) { struct ipmmu_vmsa_archdata *archdata = dev->archdata.iommu; - struct ipmmu_vmsa_domain *domain = io_domain->priv; + struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain); unsigned int i; for (i = 0; i < archdata->num_utlbs; ++i) @@ -546,7 +551,7 @@ static void ipmmu_detach_device(struct iommu_domain *io_domain, static int ipmmu_map(struct iommu_domain *io_domain, unsigned long iova, phys_addr_t paddr, size_t size, int prot) { - struct ipmmu_vmsa_domain *domain = io_domain->priv; + struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain); if (!domain) return -ENODEV; @@ -557,7 +562,7 @@ static int ipmmu_map(struct iommu_domain *io_domain, unsigned long iova, static size_t ipmmu_unmap(struct iommu_domain *io_domain, unsigned long iova, size_t size) { - struct ipmmu_vmsa_domain *domain = io_domain->priv; + struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain); return domain->iop->unmap(domain->iop, iova, size); } @@ -565,7 +570,7 @@ static size_t ipmmu_unmap(struct iommu_domain *io_domain, unsigned long iova, static phys_addr_t ipmmu_iova_to_phys(struct iommu_domain *io_domain, dma_addr_t iova) { - struct ipmmu_vmsa_domain *domain = io_domain->priv; + struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain); /* TODO: Is locking needed ? */ @@ -737,8 +742,8 @@ static void ipmmu_remove_device(struct device *dev) } static const struct iommu_ops ipmmu_ops = { - .domain_init = ipmmu_domain_init, - .domain_destroy = ipmmu_domain_destroy, + .domain_alloc = ipmmu_domain_alloc, + .domain_free = ipmmu_domain_free, .attach_dev = ipmmu_attach_device, .detach_dev = ipmmu_detach_device, .map = ipmmu_map, diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c index e1b05379ca0e..15a2063812fa 100644 --- a/drivers/iommu/msm_iommu.c +++ b/drivers/iommu/msm_iommu.c @@ -52,8 +52,14 @@ DEFINE_SPINLOCK(msm_iommu_lock); struct msm_priv { unsigned long *pgtable; struct list_head list_attached; + struct iommu_domain domain; }; +static struct msm_priv *to_msm_priv(struct iommu_domain *dom) +{ + return container_of(dom, struct msm_priv, domain); +} + static int __enable_clocks(struct msm_iommu_drvdata *drvdata) { int ret; @@ -79,7 +85,7 @@ static void __disable_clocks(struct msm_iommu_drvdata *drvdata) static int __flush_iotlb(struct iommu_domain *domain) { - struct msm_priv *priv = domain->priv; + struct msm_priv *priv = to_msm_priv(domain); struct msm_iommu_drvdata *iommu_drvdata; struct msm_iommu_ctx_drvdata *ctx_drvdata; int ret = 0; @@ -209,10 +215,14 @@ static void __program_context(void __iomem *base, int ctx, phys_addr_t pgtable) SET_M(base, ctx, 1); } -static int msm_iommu_domain_init(struct iommu_domain *domain) +static struct iommu_domain *msm_iommu_domain_alloc(unsigned type) { - struct msm_priv *priv = kzalloc(sizeof(*priv), GFP_KERNEL); + struct msm_priv *priv; + if (type != IOMMU_DOMAIN_UNMANAGED) + return NULL; + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) goto fail_nomem; @@ -224,20 +234,19 @@ static int msm_iommu_domain_init(struct iommu_domain *domain) goto fail_nomem; memset(priv->pgtable, 0, SZ_16K); - domain->priv = priv; - domain->geometry.aperture_start = 0; - domain->geometry.aperture_end = (1ULL << 32) - 1; - domain->geometry.force_aperture = true; + priv->domain.geometry.aperture_start = 0; + priv->domain.geometry.aperture_end = (1ULL << 32) - 1; + priv->domain.geometry.force_aperture = true; - return 0; + return &priv->domain; fail_nomem: kfree(priv); - return -ENOMEM; + return NULL; } -static void msm_iommu_domain_destroy(struct iommu_domain *domain) +static void msm_iommu_domain_free(struct iommu_domain *domain) { struct msm_priv *priv; unsigned long flags; @@ -245,20 +254,17 @@ static void msm_iommu_domain_destroy(struct iommu_domain *domain) int i; spin_lock_irqsave(&msm_iommu_lock, flags); - priv = domain->priv; - domain->priv = NULL; + priv = to_msm_priv(domain); - if (priv) { - fl_table = priv->pgtable; + fl_table = priv->pgtable; - for (i = 0; i < NUM_FL_PTE; i++) - if ((fl_table[i] & 0x03) == FL_TYPE_TABLE) - free_page((unsigned long) __va(((fl_table[i]) & - FL_BASE_MASK))); + for (i = 0; i < NUM_FL_PTE; i++) + if ((fl_table[i] & 0x03) == FL_TYPE_TABLE) + free_page((unsigned long) __va(((fl_table[i]) & + FL_BASE_MASK))); - free_pages((unsigned long)priv->pgtable, get_order(SZ_16K)); - priv->pgtable = NULL; - } + free_pages((unsigned long)priv->pgtable, get_order(SZ_16K)); + priv->pgtable = NULL; kfree(priv); spin_unlock_irqrestore(&msm_iommu_lock, flags); @@ -276,9 +282,9 @@ static int msm_iommu_attach_dev(struct iommu_domain *domain, struct device *dev) spin_lock_irqsave(&msm_iommu_lock, flags); - priv = domain->priv; + priv = to_msm_priv(domain); - if (!priv || !dev) { + if (!dev) { ret = -EINVAL; goto fail; } @@ -330,9 +336,9 @@ static void msm_iommu_detach_dev(struct iommu_domain *domain, int ret; spin_lock_irqsave(&msm_iommu_lock, flags); - priv = domain->priv; + priv = to_msm_priv(domain); - if (!priv || !dev) + if (!dev) goto fail; iommu_drvdata = dev_get_drvdata(dev->parent); @@ -382,11 +388,7 @@ static int msm_iommu_map(struct iommu_domain *domain, unsigned long va, goto fail; } - priv = domain->priv; - if (!priv) { - ret = -EINVAL; - goto fail; - } + priv = to_msm_priv(domain); fl_table = priv->pgtable; @@ -484,10 +486,7 @@ static size_t msm_iommu_unmap(struct iommu_domain *domain, unsigned long va, spin_lock_irqsave(&msm_iommu_lock, flags); - priv = domain->priv; - - if (!priv) - goto fail; + priv = to_msm_priv(domain); fl_table = priv->pgtable; @@ -566,7 +565,7 @@ static phys_addr_t msm_iommu_iova_to_phys(struct iommu_domain *domain, spin_lock_irqsave(&msm_iommu_lock, flags); - priv = domain->priv; + priv = to_msm_priv(domain); if (list_empty(&priv->list_attached)) goto fail; @@ -674,8 +673,8 @@ fail: static const struct iommu_ops msm_iommu_ops = { .capable = msm_iommu_capable, - .domain_init = msm_iommu_domain_init, - .domain_destroy = msm_iommu_domain_destroy, + .domain_alloc = msm_iommu_domain_alloc, + .domain_free = msm_iommu_domain_free, .attach_dev = msm_iommu_attach_dev, .detach_dev = msm_iommu_detach_dev, .map = msm_iommu_map, diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c index a4ba851825c2..a22c33d6a486 100644 --- a/drivers/iommu/omap-iommu.c +++ b/drivers/iommu/omap-iommu.c @@ -59,6 +59,7 @@ struct omap_iommu_domain { struct omap_iommu *iommu_dev; struct device *dev; spinlock_t lock; + struct iommu_domain domain; }; #define MMU_LOCK_BASE_SHIFT 10 @@ -80,6 +81,15 @@ static struct platform_driver omap_iommu_driver; static struct kmem_cache *iopte_cachep; /** + * to_omap_domain - Get struct omap_iommu_domain from generic iommu_domain + * @dom: generic iommu domain handle + **/ +static struct omap_iommu_domain *to_omap_domain(struct iommu_domain *dom) +{ + return container_of(dom, struct omap_iommu_domain, domain); +} + +/** * omap_iommu_save_ctx - Save registers for pm off-mode support * @dev: client device **/ @@ -901,7 +911,7 @@ static irqreturn_t iommu_fault_handler(int irq, void *data) u32 *iopgd, *iopte; struct omap_iommu *obj = data; struct iommu_domain *domain = obj->domain; - struct omap_iommu_domain *omap_domain = domain->priv; + struct omap_iommu_domain *omap_domain = to_omap_domain(domain); if (!omap_domain->iommu_dev) return IRQ_NONE; @@ -1113,7 +1123,7 @@ static u32 iotlb_init_entry(struct iotlb_entry *e, u32 da, u32 pa, int pgsz) static int omap_iommu_map(struct iommu_domain *domain, unsigned long da, phys_addr_t pa, size_t bytes, int prot) { - struct omap_iommu_domain *omap_domain = domain->priv; + struct omap_iommu_domain *omap_domain = to_omap_domain(domain); struct omap_iommu *oiommu = omap_domain->iommu_dev; struct device *dev = oiommu->dev; struct iotlb_entry e; @@ -1140,7 +1150,7 @@ static int omap_iommu_map(struct iommu_domain *domain, unsigned long da, static size_t omap_iommu_unmap(struct iommu_domain *domain, unsigned long da, size_t size) { - struct omap_iommu_domain *omap_domain = domain->priv; + struct omap_iommu_domain *omap_domain = to_omap_domain(domain); struct omap_iommu *oiommu = omap_domain->iommu_dev; struct device *dev = oiommu->dev; @@ -1152,7 +1162,7 @@ static size_t omap_iommu_unmap(struct iommu_domain *domain, unsigned long da, static int omap_iommu_attach_dev(struct iommu_domain *domain, struct device *dev) { - struct omap_iommu_domain *omap_domain = domain->priv; + struct omap_iommu_domain *omap_domain = to_omap_domain(domain); struct omap_iommu *oiommu; struct omap_iommu_arch_data *arch_data = dev->archdata.iommu; int ret = 0; @@ -1212,17 +1222,20 @@ static void _omap_iommu_detach_dev(struct omap_iommu_domain *omap_domain, static void omap_iommu_detach_dev(struct iommu_domain *domain, struct device *dev) { - struct omap_iommu_domain *omap_domain = domain->priv; + struct omap_iommu_domain *omap_domain = to_omap_domain(domain); spin_lock(&omap_domain->lock); _omap_iommu_detach_dev(omap_domain, dev); spin_unlock(&omap_domain->lock); } -static int omap_iommu_domain_init(struct iommu_domain *domain) +static struct iommu_domain *omap_iommu_domain_alloc(unsigned type) { struct omap_iommu_domain *omap_domain; + if (type != IOMMU_DOMAIN_UNMANAGED) + return NULL; + omap_domain = kzalloc(sizeof(*omap_domain), GFP_KERNEL); if (!omap_domain) { pr_err("kzalloc failed\n"); @@ -1244,25 +1257,21 @@ static int omap_iommu_domain_init(struct iommu_domain *domain) clean_dcache_area(omap_domain->pgtable, IOPGD_TABLE_SIZE); spin_lock_init(&omap_domain->lock); - domain->priv = omap_domain; + omap_domain->domain.geometry.aperture_start = 0; + omap_domain->domain.geometry.aperture_end = (1ULL << 32) - 1; + omap_domain->domain.geometry.force_aperture = true; - domain->geometry.aperture_start = 0; - domain->geometry.aperture_end = (1ULL << 32) - 1; - domain->geometry.force_aperture = true; - - return 0; + return &omap_domain->domain; fail_nomem: kfree(omap_domain); out: - return -ENOMEM; + return NULL; } -static void omap_iommu_domain_destroy(struct iommu_domain *domain) +static void omap_iommu_domain_free(struct iommu_domain *domain) { - struct omap_iommu_domain *omap_domain = domain->priv; - - domain->priv = NULL; + struct omap_iommu_domain *omap_domain = to_omap_domain(domain); /* * An iommu device is still attached @@ -1278,7 +1287,7 @@ static void omap_iommu_domain_destroy(struct iommu_domain *domain) static phys_addr_t omap_iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t da) { - struct omap_iommu_domain *omap_domain = domain->priv; + struct omap_iommu_domain *omap_domain = to_omap_domain(domain); struct omap_iommu *oiommu = omap_domain->iommu_dev; struct device *dev = oiommu->dev; u32 *pgd, *pte; @@ -1358,8 +1367,8 @@ static void omap_iommu_remove_device(struct device *dev) } static const struct iommu_ops omap_iommu_ops = { - .domain_init = omap_iommu_domain_init, - .domain_destroy = omap_iommu_domain_destroy, + .domain_alloc = omap_iommu_domain_alloc, + .domain_free = omap_iommu_domain_free, .attach_dev = omap_iommu_attach_dev, .detach_dev = omap_iommu_detach_dev, .map = omap_iommu_map, diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c index 9f74fddcd304..4015560bf486 100644 --- a/drivers/iommu/rockchip-iommu.c +++ b/drivers/iommu/rockchip-iommu.c @@ -80,6 +80,8 @@ struct rk_iommu_domain { u32 *dt; /* page directory table */ spinlock_t iommus_lock; /* lock for iommus list */ spinlock_t dt_lock; /* lock for modifying page directory table */ + + struct iommu_domain domain; }; struct rk_iommu { @@ -100,6 +102,11 @@ static inline void rk_table_flush(u32 *va, unsigned int count) outer_flush_range(pa_start, pa_end); } +static struct rk_iommu_domain *to_rk_domain(struct iommu_domain *dom) +{ + return container_of(dom, struct rk_iommu_domain, domain); +} + /** * Inspired by _wait_for in intel_drv.h * This is NOT safe for use in interrupt context. @@ -503,7 +510,7 @@ static irqreturn_t rk_iommu_irq(int irq, void *dev_id) static phys_addr_t rk_iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova) { - struct rk_iommu_domain *rk_domain = domain->priv; + struct rk_iommu_domain *rk_domain = to_rk_domain(domain); unsigned long flags; phys_addr_t pt_phys, phys = 0; u32 dte, pte; @@ -639,7 +646,7 @@ unwind: static int rk_iommu_map(struct iommu_domain *domain, unsigned long _iova, phys_addr_t paddr, size_t size, int prot) { - struct rk_iommu_domain *rk_domain = domain->priv; + struct rk_iommu_domain *rk_domain = to_rk_domain(domain); unsigned long flags; dma_addr_t iova = (dma_addr_t)_iova; u32 *page_table, *pte_addr; @@ -670,7 +677,7 @@ static int rk_iommu_map(struct iommu_domain *domain, unsigned long _iova, static size_t rk_iommu_unmap(struct iommu_domain *domain, unsigned long _iova, size_t size) { - struct rk_iommu_domain *rk_domain = domain->priv; + struct rk_iommu_domain *rk_domain = to_rk_domain(domain); unsigned long flags; dma_addr_t iova = (dma_addr_t)_iova; phys_addr_t pt_phys; @@ -726,7 +733,7 @@ static int rk_iommu_attach_device(struct iommu_domain *domain, struct device *dev) { struct rk_iommu *iommu; - struct rk_iommu_domain *rk_domain = domain->priv; + struct rk_iommu_domain *rk_domain = to_rk_domain(domain); unsigned long flags; int ret; phys_addr_t dte_addr; @@ -778,7 +785,7 @@ static void rk_iommu_detach_device(struct iommu_domain *domain, struct device *dev) { struct rk_iommu *iommu; - struct rk_iommu_domain *rk_domain = domain->priv; + struct rk_iommu_domain *rk_domain = to_rk_domain(domain); unsigned long flags; /* Allow 'virtual devices' (eg drm) to detach from domain */ @@ -804,13 +811,16 @@ static void rk_iommu_detach_device(struct iommu_domain *domain, dev_info(dev, "Detached from iommu domain\n"); } -static int rk_iommu_domain_init(struct iommu_domain *domain) +static struct iommu_domain *rk_iommu_domain_alloc(unsigned type) { struct rk_iommu_domain *rk_domain; + if (type != IOMMU_DOMAIN_UNMANAGED) + return NULL; + rk_domain = kzalloc(sizeof(*rk_domain), GFP_KERNEL); if (!rk_domain) - return -ENOMEM; + return NULL; /* * rk32xx iommus use a 2 level pagetable. @@ -827,17 +837,16 @@ static int rk_iommu_domain_init(struct iommu_domain *domain) spin_lock_init(&rk_domain->dt_lock); INIT_LIST_HEAD(&rk_domain->iommus); - domain->priv = rk_domain; + return &rk_domain->domain; - return 0; err_dt: kfree(rk_domain); - return -ENOMEM; + return NULL; } -static void rk_iommu_domain_destroy(struct iommu_domain *domain) +static void rk_iommu_domain_free(struct iommu_domain *domain) { - struct rk_iommu_domain *rk_domain = domain->priv; + struct rk_iommu_domain *rk_domain = to_rk_domain(domain); int i; WARN_ON(!list_empty(&rk_domain->iommus)); @@ -852,8 +861,7 @@ static void rk_iommu_domain_destroy(struct iommu_domain *domain) } free_page((unsigned long)rk_domain->dt); - kfree(domain->priv); - domain->priv = NULL; + kfree(rk_domain); } static bool rk_iommu_is_dev_iommu_master(struct device *dev) @@ -952,8 +960,8 @@ static void rk_iommu_remove_device(struct device *dev) } static const struct iommu_ops rk_iommu_ops = { - .domain_init = rk_iommu_domain_init, - .domain_destroy = rk_iommu_domain_destroy, + .domain_alloc = rk_iommu_domain_alloc, + .domain_free = rk_iommu_domain_free, .attach_dev = rk_iommu_attach_device, .detach_dev = rk_iommu_detach_device, .map = rk_iommu_map, diff --git a/drivers/iommu/shmobile-iommu.c b/drivers/iommu/shmobile-iommu.c index f1b00774e4de..a0287519a1d4 100644 --- a/drivers/iommu/shmobile-iommu.c +++ b/drivers/iommu/shmobile-iommu.c @@ -42,11 +42,17 @@ struct shmobile_iommu_domain { spinlock_t map_lock; spinlock_t attached_list_lock; struct list_head attached_list; + struct iommu_domain domain; }; static struct shmobile_iommu_archdata *ipmmu_archdata; static struct kmem_cache *l1cache, *l2cache; +static struct shmobile_iommu_domain *to_sh_domain(struct iommu_domain *dom) +{ + return container_of(dom, struct shmobile_iommu_domain, domain); +} + static int pgtable_alloc(struct shmobile_iommu_domain_pgtable *pgtable, struct kmem_cache *cache, size_t size) { @@ -82,31 +88,33 @@ static void pgtable_write(struct shmobile_iommu_domain_pgtable *pgtable, sizeof(val) * count, DMA_TO_DEVICE); } -static int shmobile_iommu_domain_init(struct iommu_domain *domain) +static struct iommu_domain *shmobile_iommu_domain_alloc(unsigned type) { struct shmobile_iommu_domain *sh_domain; int i, ret; - sh_domain = kmalloc(sizeof(*sh_domain), GFP_KERNEL); + if (type != IOMMU_DOMAIN_UNMANAGED) + return NULL; + + sh_domain = kzalloc(sizeof(*sh_domain), GFP_KERNEL); if (!sh_domain) - return -ENOMEM; + return NULL; ret = pgtable_alloc(&sh_domain->l1, l1cache, L1_SIZE); if (ret < 0) { kfree(sh_domain); - return ret; + return NULL; } for (i = 0; i < L1_LEN; i++) sh_domain->l2[i].pgtable = NULL; spin_lock_init(&sh_domain->map_lock); spin_lock_init(&sh_domain->attached_list_lock); INIT_LIST_HEAD(&sh_domain->attached_list); - domain->priv = sh_domain; - return 0; + return &sh_domain->domain; } -static void shmobile_iommu_domain_destroy(struct iommu_domain *domain) +static void shmobile_iommu_domain_free(struct iommu_domain *domain) { - struct shmobile_iommu_domain *sh_domain = domain->priv; + struct shmobile_iommu_domain *sh_domain = to_sh_domain(domain); int i; for (i = 0; i < L1_LEN; i++) { @@ -115,14 +123,13 @@ static void shmobile_iommu_domain_destroy(struct iommu_domain *domain) } pgtable_free(&sh_domain->l1, l1cache, L1_SIZE); kfree(sh_domain); - domain->priv = NULL; } static int shmobile_iommu_attach_device(struct iommu_domain *domain, struct device *dev) { struct shmobile_iommu_archdata *archdata = dev->archdata.iommu; - struct shmobile_iommu_domain *sh_domain = domain->priv; + struct shmobile_iommu_domain *sh_domain = to_sh_domain(domain); int ret = -EBUSY; if (!archdata) @@ -151,7 +158,7 @@ static void shmobile_iommu_detach_device(struct iommu_domain *domain, struct device *dev) { struct shmobile_iommu_archdata *archdata = dev->archdata.iommu; - struct shmobile_iommu_domain *sh_domain = domain->priv; + struct shmobile_iommu_domain *sh_domain = to_sh_domain(domain); if (!archdata) return; @@ -214,7 +221,7 @@ static int shmobile_iommu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t size, int prot) { struct shmobile_iommu_domain_pgtable l2 = { .pgtable = NULL }; - struct shmobile_iommu_domain *sh_domain = domain->priv; + struct shmobile_iommu_domain *sh_domain = to_sh_domain(domain); unsigned int l1index, l2index; int ret; @@ -258,7 +265,7 @@ static size_t shmobile_iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size) { struct shmobile_iommu_domain_pgtable l2 = { .pgtable = NULL }; - struct shmobile_iommu_domain *sh_domain = domain->priv; + struct shmobile_iommu_domain *sh_domain = to_sh_domain(domain); unsigned int l1index, l2index; uint32_t l2entry = 0; size_t ret = 0; @@ -298,7 +305,7 @@ done: static phys_addr_t shmobile_iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova) { - struct shmobile_iommu_domain *sh_domain = domain->priv; + struct shmobile_iommu_domain *sh_domain = to_sh_domain(domain); uint32_t l1entry = 0, l2entry = 0; unsigned int l1index, l2index; @@ -355,8 +362,8 @@ static int shmobile_iommu_add_device(struct device *dev) } static const struct iommu_ops shmobile_iommu_ops = { - .domain_init = shmobile_iommu_domain_init, - .domain_destroy = shmobile_iommu_domain_destroy, + .domain_alloc = shmobile_iommu_domain_alloc, + .domain_free = shmobile_iommu_domain_free, .attach_dev = shmobile_iommu_attach_device, .detach_dev = shmobile_iommu_detach_device, .map = shmobile_iommu_map, diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c index c48da057dbb1..37e708fdbb5a 100644 --- a/drivers/iommu/tegra-gart.c +++ b/drivers/iommu/tegra-gart.c @@ -63,11 +63,21 @@ struct gart_device { struct device *dev; }; +struct gart_domain { + struct iommu_domain domain; /* generic domain handle */ + struct gart_device *gart; /* link to gart device */ +}; + static struct gart_device *gart_handle; /* unique for a system */ #define GART_PTE(_pfn) \ (GART_ENTRY_PHYS_ADDR_VALID | ((_pfn) << PAGE_SHIFT)) +static struct gart_domain *to_gart_domain(struct iommu_domain *dom) +{ + return container_of(dom, struct gart_domain, domain); +} + /* * Any interaction between any block on PPSB and a block on APB or AHB * must have these read-back to ensure the APB/AHB bus transaction is @@ -156,20 +166,11 @@ static inline bool gart_iova_range_valid(struct gart_device *gart, static int gart_iommu_attach_dev(struct iommu_domain *domain, struct device *dev) { - struct gart_device *gart; + struct gart_domain *gart_domain = to_gart_domain(domain); + struct gart_device *gart = gart_domain->gart; struct gart_client *client, *c; int err = 0; - gart = gart_handle; - if (!gart) - return -EINVAL; - domain->priv = gart; - - domain->geometry.aperture_start = gart->iovmm_base; - domain->geometry.aperture_end = gart->iovmm_base + - gart->page_count * GART_PAGE_SIZE - 1; - domain->geometry.force_aperture = true; - client = devm_kzalloc(gart->dev, sizeof(*c), GFP_KERNEL); if (!client) return -ENOMEM; @@ -198,7 +199,8 @@ fail: static void gart_iommu_detach_dev(struct iommu_domain *domain, struct device *dev) { - struct gart_device *gart = domain->priv; + struct gart_domain *gart_domain = to_gart_domain(domain); + struct gart_device *gart = gart_domain->gart; struct gart_client *c; spin_lock(&gart->client_lock); @@ -216,33 +218,55 @@ out: spin_unlock(&gart->client_lock); } -static int gart_iommu_domain_init(struct iommu_domain *domain) +static struct iommu_domain *gart_iommu_domain_alloc(unsigned type) { - return 0; -} + struct gart_domain *gart_domain; + struct gart_device *gart; -static void gart_iommu_domain_destroy(struct iommu_domain *domain) -{ - struct gart_device *gart = domain->priv; + if (type != IOMMU_DOMAIN_UNMANAGED) + return NULL; + gart = gart_handle; if (!gart) - return; + return NULL; - spin_lock(&gart->client_lock); - if (!list_empty(&gart->client)) { - struct gart_client *c; + gart_domain = kzalloc(sizeof(*gart_domain), GFP_KERNEL); + if (!gart_domain) + return NULL; + + gart_domain->gart = gart; + gart_domain->domain.geometry.aperture_start = gart->iovmm_base; + gart_domain->domain.geometry.aperture_end = gart->iovmm_base + + gart->page_count * GART_PAGE_SIZE - 1; + gart_domain->domain.geometry.force_aperture = true; + + return &gart_domain->domain; +} + +static void gart_iommu_domain_free(struct iommu_domain *domain) +{ + struct gart_domain *gart_domain = to_gart_domain(domain); + struct gart_device *gart = gart_domain->gart; + + if (gart) { + spin_lock(&gart->client_lock); + if (!list_empty(&gart->client)) { + struct gart_client *c; - list_for_each_entry(c, &gart->client, list) - gart_iommu_detach_dev(domain, c->dev); + list_for_each_entry(c, &gart->client, list) + gart_iommu_detach_dev(domain, c->dev); + } + spin_unlock(&gart->client_lock); } - spin_unlock(&gart->client_lock); - domain->priv = NULL; + + kfree(gart_domain); } static int gart_iommu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t pa, size_t bytes, int prot) { - struct gart_device *gart = domain->priv; + struct gart_domain *gart_domain = to_gart_domain(domain); + struct gart_device *gart = gart_domain->gart; unsigned long flags; unsigned long pfn; @@ -265,7 +289,8 @@ static int gart_iommu_map(struct iommu_domain *domain, unsigned long iova, static size_t gart_iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t bytes) { - struct gart_device *gart = domain->priv; + struct gart_domain *gart_domain = to_gart_domain(domain); + struct gart_device *gart = gart_domain->gart; unsigned long flags; if (!gart_iova_range_valid(gart, iova, bytes)) @@ -281,7 +306,8 @@ static size_t gart_iommu_unmap(struct iommu_domain *domain, unsigned long iova, static phys_addr_t gart_iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova) { - struct gart_device *gart = domain->priv; + struct gart_domain *gart_domain = to_gart_domain(domain); + struct gart_device *gart = gart_domain->gart; unsigned long pte; phys_addr_t pa; unsigned long flags; @@ -310,8 +336,8 @@ static bool gart_iommu_capable(enum iommu_cap cap) static const struct iommu_ops gart_iommu_ops = { .capable = gart_iommu_capable, - .domain_init = gart_iommu_domain_init, - .domain_destroy = gart_iommu_domain_destroy, + .domain_alloc = gart_iommu_domain_alloc, + .domain_free = gart_iommu_domain_free, .attach_dev = gart_iommu_attach_dev, .detach_dev = gart_iommu_detach_dev, .map = gart_iommu_map, diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index 6e134c7c227f..c845d99ecf6b 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -6,6 +6,7 @@ * published by the Free Software Foundation. */ +#include <linux/bitops.h> #include <linux/err.h> #include <linux/iommu.h> #include <linux/kernel.h> @@ -24,6 +25,8 @@ struct tegra_smmu { struct tegra_mc *mc; const struct tegra_smmu_soc *soc; + unsigned long pfn_mask; + unsigned long *asids; struct mutex lock; @@ -31,7 +34,7 @@ struct tegra_smmu { }; struct tegra_smmu_as { - struct iommu_domain *domain; + struct iommu_domain domain; struct tegra_smmu *smmu; unsigned int use_count; struct page *count; @@ -40,6 +43,11 @@ struct tegra_smmu_as { u32 attr; }; +static struct tegra_smmu_as *to_smmu_as(struct iommu_domain *dom) +{ + return container_of(dom, struct tegra_smmu_as, domain); +} + static inline void smmu_writel(struct tegra_smmu *smmu, u32 value, unsigned long offset) { @@ -105,8 +113,6 @@ static inline u32 smmu_readl(struct tegra_smmu *smmu, unsigned long offset) #define SMMU_PDE_SHIFT 22 #define SMMU_PTE_SHIFT 12 -#define SMMU_PFN_MASK 0x000fffff - #define SMMU_PD_READABLE (1 << 31) #define SMMU_PD_WRITABLE (1 << 30) #define SMMU_PD_NONSECURE (1 << 29) @@ -224,30 +230,32 @@ static bool tegra_smmu_capable(enum iommu_cap cap) return false; } -static int tegra_smmu_domain_init(struct iommu_domain *domain) +static struct iommu_domain *tegra_smmu_domain_alloc(unsigned type) { struct tegra_smmu_as *as; unsigned int i; uint32_t *pd; + if (type != IOMMU_DOMAIN_UNMANAGED) + return NULL; + as = kzalloc(sizeof(*as), GFP_KERNEL); if (!as) - return -ENOMEM; + return NULL; as->attr = SMMU_PD_READABLE | SMMU_PD_WRITABLE | SMMU_PD_NONSECURE; - as->domain = domain; as->pd = alloc_page(GFP_KERNEL | __GFP_DMA); if (!as->pd) { kfree(as); - return -ENOMEM; + return NULL; } as->count = alloc_page(GFP_KERNEL); if (!as->count) { __free_page(as->pd); kfree(as); - return -ENOMEM; + return NULL; } /* clear PDEs */ @@ -264,14 +272,17 @@ static int tegra_smmu_domain_init(struct iommu_domain *domain) for (i = 0; i < SMMU_NUM_PDE; i++) pd[i] = 0; - domain->priv = as; + /* setup aperture */ + as->domain.geometry.aperture_start = 0; + as->domain.geometry.aperture_end = 0xffffffff; + as->domain.geometry.force_aperture = true; - return 0; + return &as->domain; } -static void tegra_smmu_domain_destroy(struct iommu_domain *domain) +static void tegra_smmu_domain_free(struct iommu_domain *domain) { - struct tegra_smmu_as *as = domain->priv; + struct tegra_smmu_as *as = to_smmu_as(domain); /* TODO: free page directory and page tables */ ClearPageReserved(as->pd); @@ -395,7 +406,7 @@ static int tegra_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) { struct tegra_smmu *smmu = dev->archdata.iommu; - struct tegra_smmu_as *as = domain->priv; + struct tegra_smmu_as *as = to_smmu_as(domain); struct device_node *np = dev->of_node; struct of_phandle_args args; unsigned int index = 0; @@ -428,7 +439,7 @@ static int tegra_smmu_attach_dev(struct iommu_domain *domain, static void tegra_smmu_detach_dev(struct iommu_domain *domain, struct device *dev) { - struct tegra_smmu_as *as = domain->priv; + struct tegra_smmu_as *as = to_smmu_as(domain); struct device_node *np = dev->of_node; struct tegra_smmu *smmu = as->smmu; struct of_phandle_args args; @@ -481,7 +492,7 @@ static u32 *as_get_pte(struct tegra_smmu_as *as, dma_addr_t iova, smmu_flush_tlb_section(smmu, as->id, iova); smmu_flush(smmu); } else { - page = pfn_to_page(pd[pde] & SMMU_PFN_MASK); + page = pfn_to_page(pd[pde] & smmu->pfn_mask); pt = page_address(page); } @@ -503,7 +514,7 @@ static void as_put_pte(struct tegra_smmu_as *as, dma_addr_t iova) u32 *pd = page_address(as->pd), *pt; struct page *page; - page = pfn_to_page(pd[pde] & SMMU_PFN_MASK); + page = pfn_to_page(pd[pde] & as->smmu->pfn_mask); pt = page_address(page); /* @@ -524,7 +535,7 @@ static void as_put_pte(struct tegra_smmu_as *as, dma_addr_t iova) static int tegra_smmu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t size, int prot) { - struct tegra_smmu_as *as = domain->priv; + struct tegra_smmu_as *as = to_smmu_as(domain); struct tegra_smmu *smmu = as->smmu; unsigned long offset; struct page *page; @@ -548,7 +559,7 @@ static int tegra_smmu_map(struct iommu_domain *domain, unsigned long iova, static size_t tegra_smmu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size) { - struct tegra_smmu_as *as = domain->priv; + struct tegra_smmu_as *as = to_smmu_as(domain); struct tegra_smmu *smmu = as->smmu; unsigned long offset; struct page *page; @@ -572,13 +583,13 @@ static size_t tegra_smmu_unmap(struct iommu_domain *domain, unsigned long iova, static phys_addr_t tegra_smmu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova) { - struct tegra_smmu_as *as = domain->priv; + struct tegra_smmu_as *as = to_smmu_as(domain); struct page *page; unsigned long pfn; u32 *pte; pte = as_get_pte(as, iova, &page); - pfn = *pte & SMMU_PFN_MASK; + pfn = *pte & as->smmu->pfn_mask; return PFN_PHYS(pfn); } @@ -633,8 +644,8 @@ static void tegra_smmu_remove_device(struct device *dev) static const struct iommu_ops tegra_smmu_ops = { .capable = tegra_smmu_capable, - .domain_init = tegra_smmu_domain_init, - .domain_destroy = tegra_smmu_domain_destroy, + .domain_alloc = tegra_smmu_domain_alloc, + .domain_free = tegra_smmu_domain_free, .attach_dev = tegra_smmu_attach_dev, .detach_dev = tegra_smmu_detach_dev, .add_device = tegra_smmu_add_device, @@ -702,6 +713,10 @@ struct tegra_smmu *tegra_smmu_probe(struct device *dev, smmu->dev = dev; smmu->mc = mc; + smmu->pfn_mask = BIT_MASK(mc->soc->num_address_bits - PAGE_SHIFT) - 1; + dev_dbg(dev, "address bits: %u, PFN mask: %#lx\n", + mc->soc->num_address_bits, smmu->pfn_mask); + value = SMMU_PTC_CONFIG_ENABLE | SMMU_PTC_CONFIG_INDEX_MAP(0x3f); if (soc->supports_request_limit) diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 4f2fb62e6f37..49875adb6b44 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -567,7 +567,7 @@ static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq) */ smp_wmb(); - for_each_cpu_mask(cpu, *mask) { + for_each_cpu(cpu, mask) { u64 cluster_id = cpu_logical_map(cpu) & ~0xffUL; u16 tlist; diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index bc48b7dc89ec..57f09cb54464 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -389,19 +389,19 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *cpumask, int i; cpumask_and(&tmp, cpumask, cpu_online_mask); - if (cpus_empty(tmp)) + if (cpumask_empty(&tmp)) return -EINVAL; /* Assumption : cpumask refers to a single CPU */ spin_lock_irqsave(&gic_lock, flags); /* Re-route this IRQ */ - gic_map_to_vpe(irq, first_cpu(tmp)); + gic_map_to_vpe(irq, cpumask_first(&tmp)); /* Update the pcpu_masks */ for (i = 0; i < NR_CPUS; i++) clear_bit(irq, pcpu_masks[i].pcpu_mask); - set_bit(irq, pcpu_masks[first_cpu(tmp)].pcpu_mask); + set_bit(irq, pcpu_masks[cpumask_first(&tmp)].pcpu_mask); cpumask_copy(d->affinity, cpumask); spin_unlock_irqrestore(&gic_lock, flags); diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c index a789a2054388..a3f7610002aa 100644 --- a/drivers/net/ethernet/tile/tilegx.c +++ b/drivers/net/ethernet/tile/tilegx.c @@ -1123,7 +1123,7 @@ static int alloc_percpu_mpipe_resources(struct net_device *dev, addr + i * sizeof(struct tile_net_comps); /* If this is a network cpu, create an iqueue. */ - if (cpu_isset(cpu, network_cpus_map)) { + if (cpumask_test_cpu(cpu, &network_cpus_map)) { order = get_order(NOTIF_RING_SIZE); page = homecache_alloc_pages(GFP_KERNEL, order, cpu); if (page == NULL) { @@ -1299,7 +1299,7 @@ static int tile_net_init_mpipe(struct net_device *dev) int first_ring, ring; int instance = mpipe_instance(dev); struct mpipe_data *md = &mpipe_data[instance]; - int network_cpus_count = cpus_weight(network_cpus_map); + int network_cpus_count = cpumask_weight(&network_cpus_map); if (!hash_default) { netdev_err(dev, "Networking requires hash_default!\n"); diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 26a51dc4278d..57fd66357b95 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -579,7 +579,8 @@ void dasd_kick_device(struct dasd_device *device) { dasd_get_device(device); /* queue call to dasd_kick_device to the kernel event daemon. */ - schedule_work(&device->kick_work); + if (!schedule_work(&device->kick_work)) + dasd_put_device(device); } EXPORT_SYMBOL(dasd_kick_device); @@ -599,7 +600,8 @@ void dasd_reload_device(struct dasd_device *device) { dasd_get_device(device); /* queue call to dasd_reload_device to the kernel event daemon. */ - schedule_work(&device->reload_device); + if (!schedule_work(&device->reload_device)) + dasd_put_device(device); } EXPORT_SYMBOL(dasd_reload_device); @@ -619,7 +621,8 @@ void dasd_restore_device(struct dasd_device *device) { dasd_get_device(device); /* queue call to dasd_restore_device to the kernel event daemon. */ - schedule_work(&device->restore_device); + if (!schedule_work(&device->restore_device)) + dasd_put_device(device); } /* @@ -2163,18 +2166,22 @@ static int _dasd_sleep_on(struct dasd_ccw_req *maincqr, int interruptible) cqr->intrc = -ENOLINK; continue; } - /* Don't try to start requests if device is stopped */ - if (interruptible) { - rc = wait_event_interruptible( - generic_waitq, !(device->stopped)); - if (rc == -ERESTARTSYS) { - cqr->status = DASD_CQR_FAILED; - maincqr->intrc = rc; - continue; - } - } else - wait_event(generic_waitq, !(device->stopped)); - + /* + * Don't try to start requests if device is stopped + * except path verification requests + */ + if (!test_bit(DASD_CQR_VERIFY_PATH, &cqr->flags)) { + if (interruptible) { + rc = wait_event_interruptible( + generic_waitq, !(device->stopped)); + if (rc == -ERESTARTSYS) { + cqr->status = DASD_CQR_FAILED; + maincqr->intrc = rc; + continue; + } + } else + wait_event(generic_waitq, !(device->stopped)); + } if (!cqr->callback) cqr->callback = dasd_wakeup_cb; @@ -2524,6 +2531,11 @@ static void __dasd_process_request_queue(struct dasd_block *block) __blk_end_request_all(req, -EIO); return; } + + /* if device ist stopped do not fetch new requests */ + if (basedev->stopped) + return; + /* Now we try to fetch requests from the request queue */ while ((req = blk_peek_request(queue))) { if (basedev->features & DASD_FEATURE_READONLY && diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index 49b48a887c66..6215f6455eb8 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -1628,7 +1628,8 @@ static void dasd_eckd_kick_validate_server(struct dasd_device *device) return; } /* queue call to do_validate_server to the kernel event daemon. */ - schedule_work(&device->kick_validate); + if (!schedule_work(&device->kick_validate)) + dasd_put_device(device); } static u32 get_fcx_max_data(struct dasd_device *device) diff --git a/drivers/s390/char/sclp_cmd.c b/drivers/s390/char/sclp_cmd.c index 6e14999f9e8f..7be782116dab 100644 --- a/drivers/s390/char/sclp_cmd.c +++ b/drivers/s390/char/sclp_cmd.c @@ -315,10 +315,29 @@ static int sclp_mem_change_state(unsigned long start, unsigned long size, rc |= sclp_assign_storage(incr->rn); else sclp_unassign_storage(incr->rn); + if (rc == 0) + incr->standby = online ? 0 : 1; } return rc ? -EIO : 0; } +static bool contains_standby_increment(unsigned long start, unsigned long end) +{ + struct memory_increment *incr; + unsigned long istart; + + list_for_each_entry(incr, &sclp_mem_list, list) { + istart = rn2addr(incr->rn); + if (end - 1 < istart) + continue; + if (start > istart + sclp_rzm - 1) + continue; + if (incr->standby) + return true; + } + return false; +} + static int sclp_mem_notifier(struct notifier_block *nb, unsigned long action, void *data) { @@ -334,8 +353,16 @@ static int sclp_mem_notifier(struct notifier_block *nb, for_each_clear_bit(id, sclp_storage_ids, sclp_max_storage_id + 1) sclp_attach_storage(id); switch (action) { - case MEM_ONLINE: case MEM_GOING_OFFLINE: + /* + * We do not allow to set memory blocks offline that contain + * standby memory. This is done to simplify the "memory online" + * case. + */ + if (contains_standby_increment(start, start + size)) + rc = -EPERM; + break; + case MEM_ONLINE: case MEM_CANCEL_OFFLINE: break; case MEM_GOING_ONLINE: @@ -361,6 +388,21 @@ static struct notifier_block sclp_mem_nb = { .notifier_call = sclp_mem_notifier, }; +static void __init align_to_block_size(unsigned long long *start, + unsigned long long *size) +{ + unsigned long long start_align, size_align, alignment; + + alignment = memory_block_size_bytes(); + start_align = roundup(*start, alignment); + size_align = rounddown(*start + *size, alignment) - start_align; + + pr_info("Standby memory at 0x%llx (%lluM of %lluM usable)\n", + *start, size_align >> 20, *size >> 20); + *start = start_align; + *size = size_align; +} + static void __init add_memory_merged(u16 rn) { static u16 first_rn, num; @@ -382,7 +424,9 @@ static void __init add_memory_merged(u16 rn) goto skip_add; if (memory_end_set && (start + size > memory_end)) size = memory_end - start; - add_memory(0, start, size); + align_to_block_size(&start, &size); + if (size) + add_memory(0, start, size); skip_add: first_rn = rn; num = 1; diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index a1cfbd3dda47..8eab107b53fb 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -6632,14 +6632,12 @@ static void fail_all_outstanding_cmds(struct ctlr_info *h) static void set_lockup_detected_for_all_cpus(struct ctlr_info *h, u32 value) { - int i, cpu; + int cpu; - cpu = cpumask_first(cpu_online_mask); - for (i = 0; i < num_online_cpus(); i++) { + for_each_online_cpu(cpu) { u32 *lockup_detected; lockup_detected = per_cpu_ptr(h->lockup_detected, cpu); *lockup_detected = value; - cpu = cpumask_next(cpu, cpu_online_mask); } wmb(); /* be sure the per-cpu variables are out to memory */ } diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 086549a665e2..27e285b92b5f 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -11,6 +11,7 @@ #include <linux/bitmap.h> #include <linux/bug.h> +/* Don't assign or return these: may not be this big! */ typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t; /** @@ -289,11 +290,11 @@ static inline void cpumask_clear_cpu(int cpu, struct cpumask *dstp) * @cpumask: the cpumask pointer * * Returns 1 if @cpu is set in @cpumask, else returns 0 - * - * No static inline type checking - see Subtlety (1) above. */ -#define cpumask_test_cpu(cpu, cpumask) \ - test_bit(cpumask_check(cpu), cpumask_bits((cpumask))) +static inline int cpumask_test_cpu(int cpu, const struct cpumask *cpumask) +{ + return test_bit(cpumask_check(cpu), cpumask_bits((cpumask))); +} /** * cpumask_test_and_set_cpu - atomically test and set a cpu in a cpumask @@ -609,9 +610,7 @@ static inline int cpulist_parse(const char *buf, struct cpumask *dstp) */ static inline size_t cpumask_size(void) { - /* FIXME: Once all cpumask assignments are eliminated, this - * can be nr_cpumask_bits */ - return BITS_TO_LONGS(NR_CPUS) * sizeof(long); + return BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long); } /* @@ -768,7 +767,7 @@ static inline const struct cpumask *get_cpu_mask(unsigned int cpu) #if NR_CPUS <= BITS_PER_LONG #define CPU_BITS_ALL \ { \ - [BITS_TO_LONGS(NR_CPUS)-1] = CPU_MASK_LAST_WORD \ + [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } #else /* NR_CPUS > BITS_PER_LONG */ @@ -776,7 +775,7 @@ static inline const struct cpumask *get_cpu_mask(unsigned int cpu) #define CPU_BITS_ALL \ { \ [0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL, \ - [BITS_TO_LONGS(NR_CPUS)-1] = CPU_MASK_LAST_WORD \ + [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } #endif /* NR_CPUS > BITS_PER_LONG */ @@ -797,32 +796,18 @@ cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask) nr_cpu_ids); } -/* - * - * From here down, all obsolete. Use cpumask_ variants! - * - */ -#ifndef CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS -#define cpumask_of_cpu(cpu) (*get_cpu_mask(cpu)) - -#define CPU_MASK_LAST_WORD BITMAP_LAST_WORD_MASK(NR_CPUS) - #if NR_CPUS <= BITS_PER_LONG - #define CPU_MASK_ALL \ (cpumask_t) { { \ - [BITS_TO_LONGS(NR_CPUS)-1] = CPU_MASK_LAST_WORD \ + [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } } - #else - #define CPU_MASK_ALL \ (cpumask_t) { { \ [0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL, \ - [BITS_TO_LONGS(NR_CPUS)-1] = CPU_MASK_LAST_WORD \ + [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } } - -#endif +#endif /* NR_CPUS > BITS_PER_LONG */ #define CPU_MASK_NONE \ (cpumask_t) { { \ @@ -834,143 +819,4 @@ cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask) [0] = 1UL \ } } -#if NR_CPUS == 1 -#define first_cpu(src) ({ (void)(src); 0; }) -#define next_cpu(n, src) ({ (void)(src); 1; }) -#define any_online_cpu(mask) 0 -#define for_each_cpu_mask(cpu, mask) \ - for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask) -#else /* NR_CPUS > 1 */ -int __first_cpu(const cpumask_t *srcp); -int __next_cpu(int n, const cpumask_t *srcp); - -#define first_cpu(src) __first_cpu(&(src)) -#define next_cpu(n, src) __next_cpu((n), &(src)) -#define any_online_cpu(mask) cpumask_any_and(&mask, cpu_online_mask) -#define for_each_cpu_mask(cpu, mask) \ - for ((cpu) = -1; \ - (cpu) = next_cpu((cpu), (mask)), \ - (cpu) < NR_CPUS; ) -#endif /* SMP */ - -#if NR_CPUS <= 64 - -#define for_each_cpu_mask_nr(cpu, mask) for_each_cpu_mask(cpu, mask) - -#else /* NR_CPUS > 64 */ - -int __next_cpu_nr(int n, const cpumask_t *srcp); -#define for_each_cpu_mask_nr(cpu, mask) \ - for ((cpu) = -1; \ - (cpu) = __next_cpu_nr((cpu), &(mask)), \ - (cpu) < nr_cpu_ids; ) - -#endif /* NR_CPUS > 64 */ - -#define cpus_addr(src) ((src).bits) - -#define cpu_set(cpu, dst) __cpu_set((cpu), &(dst)) -static inline void __cpu_set(int cpu, volatile cpumask_t *dstp) -{ - set_bit(cpu, dstp->bits); -} - -#define cpu_clear(cpu, dst) __cpu_clear((cpu), &(dst)) -static inline void __cpu_clear(int cpu, volatile cpumask_t *dstp) -{ - clear_bit(cpu, dstp->bits); -} - -#define cpus_setall(dst) __cpus_setall(&(dst), NR_CPUS) -static inline void __cpus_setall(cpumask_t *dstp, unsigned int nbits) -{ - bitmap_fill(dstp->bits, nbits); -} - -#define cpus_clear(dst) __cpus_clear(&(dst), NR_CPUS) -static inline void __cpus_clear(cpumask_t *dstp, unsigned int nbits) -{ - bitmap_zero(dstp->bits, nbits); -} - -/* No static inline type checking - see Subtlety (1) above. */ -#define cpu_isset(cpu, cpumask) test_bit((cpu), (cpumask).bits) - -#define cpu_test_and_set(cpu, cpumask) __cpu_test_and_set((cpu), &(cpumask)) -static inline int __cpu_test_and_set(int cpu, cpumask_t *addr) -{ - return test_and_set_bit(cpu, addr->bits); -} - -#define cpus_and(dst, src1, src2) __cpus_and(&(dst), &(src1), &(src2), NR_CPUS) -static inline int __cpus_and(cpumask_t *dstp, const cpumask_t *src1p, - const cpumask_t *src2p, unsigned int nbits) -{ - return bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits); -} - -#define cpus_or(dst, src1, src2) __cpus_or(&(dst), &(src1), &(src2), NR_CPUS) -static inline void __cpus_or(cpumask_t *dstp, const cpumask_t *src1p, - const cpumask_t *src2p, unsigned int nbits) -{ - bitmap_or(dstp->bits, src1p->bits, src2p->bits, nbits); -} - -#define cpus_xor(dst, src1, src2) __cpus_xor(&(dst), &(src1), &(src2), NR_CPUS) -static inline void __cpus_xor(cpumask_t *dstp, const cpumask_t *src1p, - const cpumask_t *src2p, unsigned int nbits) -{ - bitmap_xor(dstp->bits, src1p->bits, src2p->bits, nbits); -} - -#define cpus_andnot(dst, src1, src2) \ - __cpus_andnot(&(dst), &(src1), &(src2), NR_CPUS) -static inline int __cpus_andnot(cpumask_t *dstp, const cpumask_t *src1p, - const cpumask_t *src2p, unsigned int nbits) -{ - return bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits); -} - -#define cpus_equal(src1, src2) __cpus_equal(&(src1), &(src2), NR_CPUS) -static inline int __cpus_equal(const cpumask_t *src1p, - const cpumask_t *src2p, unsigned int nbits) -{ - return bitmap_equal(src1p->bits, src2p->bits, nbits); -} - -#define cpus_intersects(src1, src2) __cpus_intersects(&(src1), &(src2), NR_CPUS) -static inline int __cpus_intersects(const cpumask_t *src1p, - const cpumask_t *src2p, unsigned int nbits) -{ - return bitmap_intersects(src1p->bits, src2p->bits, nbits); -} - -#define cpus_subset(src1, src2) __cpus_subset(&(src1), &(src2), NR_CPUS) -static inline int __cpus_subset(const cpumask_t *src1p, - const cpumask_t *src2p, unsigned int nbits) -{ - return bitmap_subset(src1p->bits, src2p->bits, nbits); -} - -#define cpus_empty(src) __cpus_empty(&(src), NR_CPUS) -static inline int __cpus_empty(const cpumask_t *srcp, unsigned int nbits) -{ - return bitmap_empty(srcp->bits, nbits); -} - -#define cpus_weight(cpumask) __cpus_weight(&(cpumask), NR_CPUS) -static inline int __cpus_weight(const cpumask_t *srcp, unsigned int nbits) -{ - return bitmap_weight(srcp->bits, nbits); -} - -#define cpus_shift_left(dst, src, n) \ - __cpus_shift_left(&(dst), &(src), (n), NR_CPUS) -static inline void __cpus_shift_left(cpumask_t *dstp, - const cpumask_t *srcp, int n, int nbits) -{ - bitmap_shift_left(dstp->bits, srcp->bits, n, nbits); -} -#endif /* !CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS */ - #endif /* __LINUX_CPUMASK_H */ diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 38daa453f2e5..0546b8710ce3 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -51,9 +51,33 @@ struct iommu_domain_geometry { bool force_aperture; /* DMA only allowed in mappable range? */ }; +/* Domain feature flags */ +#define __IOMMU_DOMAIN_PAGING (1U << 0) /* Support for iommu_map/unmap */ +#define __IOMMU_DOMAIN_DMA_API (1U << 1) /* Domain for use in DMA-API + implementation */ +#define __IOMMU_DOMAIN_PT (1U << 2) /* Domain is identity mapped */ + +/* + * This are the possible domain-types + * + * IOMMU_DOMAIN_BLOCKED - All DMA is blocked, can be used to isolate + * devices + * IOMMU_DOMAIN_IDENTITY - DMA addresses are system physical addresses + * IOMMU_DOMAIN_UNMANAGED - DMA mappings managed by IOMMU-API user, used + * for VMs + * IOMMU_DOMAIN_DMA - Internally used for DMA-API implementations. + * This flag allows IOMMU drivers to implement + * certain optimizations for these domains + */ +#define IOMMU_DOMAIN_BLOCKED (0U) +#define IOMMU_DOMAIN_IDENTITY (__IOMMU_DOMAIN_PT) +#define IOMMU_DOMAIN_UNMANAGED (__IOMMU_DOMAIN_PAGING) +#define IOMMU_DOMAIN_DMA (__IOMMU_DOMAIN_PAGING | \ + __IOMMU_DOMAIN_DMA_API) + struct iommu_domain { + unsigned type; const struct iommu_ops *ops; - void *priv; iommu_fault_handler_t handler; void *handler_token; struct iommu_domain_geometry geometry; @@ -113,8 +137,11 @@ enum iommu_attr { */ struct iommu_ops { bool (*capable)(enum iommu_cap); - int (*domain_init)(struct iommu_domain *domain); - void (*domain_destroy)(struct iommu_domain *domain); + + /* Domain allocation and freeing by the iommu driver */ + struct iommu_domain *(*domain_alloc)(unsigned iommu_domain_type); + void (*domain_free)(struct iommu_domain *); + int (*attach_dev)(struct iommu_domain *domain, struct device *dev); void (*detach_dev)(struct iommu_domain *domain, struct device *dev); int (*map)(struct iommu_domain *domain, unsigned long iova, diff --git a/include/linux/smp.h b/include/linux/smp.h index be91db2a7017..c4414074bd88 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -18,7 +18,7 @@ struct call_single_data { struct llist_node llist; smp_call_func_t func; void *info; - u16 flags; + unsigned int flags; }; /* total number of cpus in this system (may exceed NR_CPUS) */ diff --git a/lib/Kconfig b/lib/Kconfig index f5440221d929..601965a948e8 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -396,10 +396,6 @@ config CPUMASK_OFFSTACK them on the stack. This is a bit more expensive, but avoids stack overflow. -config DISABLE_OBSOLETE_CPUMASK_FUNCTIONS - bool "Disable obsolete cpumask functions" if DEBUG_PER_CPU_MAPS - depends on BROKEN - config CPU_RMAP bool depends on SMP diff --git a/lib/cpumask.c b/lib/cpumask.c index 5ab1553fd076..830dd5dec40f 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -5,27 +5,6 @@ #include <linux/export.h> #include <linux/bootmem.h> -int __first_cpu(const cpumask_t *srcp) -{ - return min_t(int, NR_CPUS, find_first_bit(srcp->bits, NR_CPUS)); -} -EXPORT_SYMBOL(__first_cpu); - -int __next_cpu(int n, const cpumask_t *srcp) -{ - return min_t(int, NR_CPUS, find_next_bit(srcp->bits, NR_CPUS, n+1)); -} -EXPORT_SYMBOL(__next_cpu); - -#if NR_CPUS > 64 -int __next_cpu_nr(int n, const cpumask_t *srcp) -{ - return min_t(int, nr_cpu_ids, - find_next_bit(srcp->bits, nr_cpu_ids, n+1)); -} -EXPORT_SYMBOL(__next_cpu_nr); -#endif - /** * cpumask_next_and - get the next cpu in *src1p & *src2p * @n: the cpu prior to the place to search (ie. return will be > @n) @@ -90,13 +69,6 @@ bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) dump_stack(); } #endif - /* FIXME: Bandaid to save us from old primitives which go to NR_CPUS. */ - if (*mask) { - unsigned char *ptr = (unsigned char *)cpumask_bits(*mask); - unsigned int tail; - tail = BITS_TO_LONGS(NR_CPUS - nr_cpumask_bits) * sizeof(long); - memset(ptr + cpumask_size() - tail, 0, tail); - } return *mask != NULL; } |