From f2f12b6fc032c7b1419fd6db84e2868b5f05a878 Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Wed, 6 Jun 2012 10:50:06 -0600 Subject: iommu/amd: Fix missing iommu_shutdown initialization in passthrough mode The iommu_shutdown callback is not initialized when the AMD IOMMU driver runs in passthrough mode. Fix that by moving the callback initialization before the check for passthrough mode. Signed-off-by: Shuah Khan Cc: stable@vger.kernel.org Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu_init.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/iommu') diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index 542024ba6dba..c04ddca7f12f 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -1641,6 +1641,8 @@ static int __init amd_iommu_init(void) amd_iommu_init_api(); + x86_platform.iommu_shutdown = disable_iommus; + if (iommu_pass_through) goto out; @@ -1649,8 +1651,6 @@ static int __init amd_iommu_init(void) else printk(KERN_INFO "AMD-Vi: Lazy IO/TLB flushing enabled\n"); - x86_platform.iommu_shutdown = disable_iommus; - out: return ret; -- cgit v1.2.3 From ff164324123c0fe181d8de7dadcc7b3fbe25f2cf Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Thu, 7 Jun 2012 15:15:59 +0200 Subject: x86/apic: Make cpu_mask_to_apicid() operations return error code Current cpu_mask_to_apicid() and cpu_mask_to_apicid_and() implementations have few shortcomings: 1. A value returned by cpu_mask_to_apicid() is written to hardware registers unconditionally. Should BAD_APICID get ever returned it will be written to a hardware too. But the value of BAD_APICID is not universal across all hardware in all modes and might cause unexpected results, i.e. interrupts might get routed to CPUs that are not configured to receive it. 2. Because the value of BAD_APICID is not universal it is counter- intuitive to return it for a hardware where it does not make sense (i.e. x2apic). 3. cpu_mask_to_apicid_and() operation is thought as an complement to cpu_mask_to_apicid() that only applies a AND mask on top of a cpumask being passed. Yet, as consequence of 18374d8 commit the two operations are inconsistent in that of: cpu_mask_to_apicid() should not get a offline CPU with the cpumask cpu_mask_to_apicid_and() should not fail and return BAD_APICID These limitations are impossible to realize just from looking at the operations prototypes. Most of these shortcomings are resolved by returning a error code instead of BAD_APICID. As the result, faults are reported back early rather than possibilities to cause a unexpected behaviour exist (in case of [1]). The only exception is setup_timer_IRQ0_pin() routine. Although obviously controversial to this fix, its existing behaviour is preserved to not break the fragile check_timer() and would better addressed in a separate fix. Signed-off-by: Alexander Gordeev Acked-by: Suresh Siddha Cc: Yinghai Lu Link: http://lkml.kernel.org/r/20120607131559.GF4759@dhcp-26-207.brq.redhat.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/apic.h | 44 ++++++++++++------ arch/x86/kernel/apic/apic.c | 33 +++++++------ arch/x86/kernel/apic/es7000_32.c | 21 +++++---- arch/x86/kernel/apic/io_apic.c | 88 +++++++++++++++++++++++------------ arch/x86/kernel/apic/numaq_32.c | 14 ++++-- arch/x86/kernel/apic/summit_32.c | 22 +++++---- arch/x86/kernel/apic/x2apic_cluster.c | 24 ++++++---- arch/x86/kernel/apic/x2apic_uv_x.c | 27 +++++++---- arch/x86/platform/uv/uv_irq.c | 7 ++- drivers/iommu/intel_irq_remapping.c | 13 ++++-- 10 files changed, 188 insertions(+), 105 deletions(-) (limited to 'drivers/iommu') diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index e3fecd50d5ca..ae91f9c7e360 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -331,9 +331,11 @@ struct apic { unsigned long (*set_apic_id)(unsigned int id); unsigned long apic_id_mask; - unsigned int (*cpu_mask_to_apicid)(const struct cpumask *cpumask); - unsigned int (*cpu_mask_to_apicid_and)(const struct cpumask *cpumask, - const struct cpumask *andmask); + int (*cpu_mask_to_apicid)(const struct cpumask *cpumask, + unsigned int *apicid); + int (*cpu_mask_to_apicid_and)(const struct cpumask *cpumask, + const struct cpumask *andmask, + unsigned int *apicid); /* ipi */ void (*send_IPI_mask)(const struct cpumask *mask, int vector); @@ -591,29 +593,45 @@ static inline int default_phys_pkg_id(int cpuid_apic, int index_msb) #endif -static inline unsigned int -flat_cpu_mask_to_apicid(const struct cpumask *cpumask) +static inline int +__flat_cpu_mask_to_apicid(unsigned long cpu_mask, unsigned int *apicid) { - return cpumask_bits(cpumask)[0] & APIC_ALL_CPUS; + cpu_mask &= APIC_ALL_CPUS; + if (likely(cpu_mask)) { + *apicid = (unsigned int)cpu_mask; + return 0; + } else { + return -EINVAL; + } } -static inline unsigned int +static inline int +flat_cpu_mask_to_apicid(const struct cpumask *cpumask, + unsigned int *apicid) +{ + return __flat_cpu_mask_to_apicid(cpumask_bits(cpumask)[0], apicid); +} + +static inline int flat_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask) + const struct cpumask *andmask, + unsigned int *apicid) { unsigned long mask1 = cpumask_bits(cpumask)[0]; unsigned long mask2 = cpumask_bits(andmask)[0]; unsigned long mask3 = cpumask_bits(cpu_online_mask)[0]; - return (unsigned int)(mask1 & mask2 & mask3); + return __flat_cpu_mask_to_apicid(mask1 & mask2 & mask3, apicid); } -extern unsigned int -default_cpu_mask_to_apicid(const struct cpumask *cpumask); +extern int +default_cpu_mask_to_apicid(const struct cpumask *cpumask, + unsigned int *apicid); -extern unsigned int +extern int default_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask); + const struct cpumask *andmask, + unsigned int *apicid); static inline bool flat_vector_allocation_domain(int cpu, struct cpumask *retmask) diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 96a2608252f1..b8d92606f84f 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -2123,24 +2123,26 @@ void default_init_apic_ldr(void) apic_write(APIC_LDR, val); } -unsigned int default_cpu_mask_to_apicid(const struct cpumask *cpumask) +static inline int __default_cpu_to_apicid(int cpu, unsigned int *apicid) { - int cpu; - - /* - * We're using fixed IRQ delivery, can only return one phys APIC ID. - * May as well be the first. - */ - cpu = cpumask_first(cpumask); - if (likely((unsigned)cpu < nr_cpu_ids)) - return per_cpu(x86_cpu_to_apicid, cpu); + if (likely((unsigned int)cpu < nr_cpu_ids)) { + *apicid = per_cpu(x86_cpu_to_apicid, cpu); + return 0; + } else { + return -EINVAL; + } +} - return BAD_APICID; +int default_cpu_mask_to_apicid(const struct cpumask *cpumask, + unsigned int *apicid) +{ + int cpu = cpumask_first(cpumask); + return __default_cpu_to_apicid(cpu, apicid); } -unsigned int -default_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask) +int default_cpu_mask_to_apicid_and(const struct cpumask *cpumask, + const struct cpumask *andmask, + unsigned int *apicid) { int cpu; @@ -2148,7 +2150,8 @@ default_cpu_mask_to_apicid_and(const struct cpumask *cpumask, if (cpumask_test_cpu(cpu, cpu_online_mask)) break; } - return per_cpu(x86_cpu_to_apicid, cpu); + + return __default_cpu_to_apicid(cpu, apicid); } /* diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c index 3c42865757e2..515ebb00a9fc 100644 --- a/arch/x86/kernel/apic/es7000_32.c +++ b/arch/x86/kernel/apic/es7000_32.c @@ -525,7 +525,8 @@ static int es7000_check_phys_apicid_present(int cpu_physical_apicid) return 1; } -static unsigned int es7000_cpu_mask_to_apicid(const struct cpumask *cpumask) +static int +es7000_cpu_mask_to_apicid(const struct cpumask *cpumask, unsigned int *dest_id) { unsigned int round = 0; int cpu, uninitialized_var(apicid); @@ -539,31 +540,33 @@ static unsigned int es7000_cpu_mask_to_apicid(const struct cpumask *cpumask) if (round && APIC_CLUSTER(apicid) != APIC_CLUSTER(new_apicid)) { WARN(1, "Not a valid mask!"); - return BAD_APICID; + return -EINVAL; } apicid = new_apicid; round++; } - return apicid; + *dest_id = apicid; + return 0; } -static unsigned int +static int es7000_cpu_mask_to_apicid_and(const struct cpumask *inmask, - const struct cpumask *andmask) + const struct cpumask *andmask, + unsigned int *apicid) { - int apicid = early_per_cpu(x86_cpu_to_logical_apicid, 0); + *apicid = early_per_cpu(x86_cpu_to_logical_apicid, 0); cpumask_var_t cpumask; if (!alloc_cpumask_var(&cpumask, GFP_ATOMIC)) - return apicid; + return 0; cpumask_and(cpumask, inmask, andmask); cpumask_and(cpumask, cpumask, cpu_online_mask); - apicid = es7000_cpu_mask_to_apicid(cpumask); + es7000_cpu_mask_to_apicid(cpumask, apicid); free_cpumask_var(cpumask); - return apicid; + return 0; } static int es7000_phys_pkg_id(int cpuid_apic, int index_msb) diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 4061a7dee5c9..0deb773404e5 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1359,7 +1359,14 @@ static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg, if (assign_irq_vector(irq, cfg, apic->target_cpus())) return; - dest = apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus()); + if (apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus(), + &dest)) { + pr_warn("Failed to obtain apicid for ioapic %d, pin %d\n", + mpc_ioapic_id(attr->ioapic), attr->ioapic_pin); + __clear_irq_vector(irq, cfg); + + return; + } apic_printk(APIC_VERBOSE,KERN_DEBUG "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> " @@ -1474,6 +1481,7 @@ static void __init setup_timer_IRQ0_pin(unsigned int ioapic_idx, unsigned int pin, int vector) { struct IO_APIC_route_entry entry; + unsigned int dest; if (irq_remapping_enabled) return; @@ -1484,9 +1492,12 @@ static void __init setup_timer_IRQ0_pin(unsigned int ioapic_idx, * We use logical delivery to get the timer IRQ * to the first CPU. */ + if (unlikely(apic->cpu_mask_to_apicid(apic->target_cpus(), &dest))) + dest = BAD_APICID; + entry.dest_mode = apic->irq_dest_mode; entry.mask = 0; /* don't mask IRQ for edge */ - entry.dest = apic->cpu_mask_to_apicid(apic->target_cpus()); + entry.dest = dest; entry.delivery_mode = apic->irq_delivery_mode; entry.polarity = 0; entry.trigger = 0; @@ -2245,16 +2256,25 @@ int __ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, unsigned int *dest_id) { struct irq_cfg *cfg = data->chip_data; + unsigned int irq = data->irq; + int err; if (!cpumask_intersects(mask, cpu_online_mask)) - return -1; + return -EINVAL; - if (assign_irq_vector(data->irq, data->chip_data, mask)) - return -1; + err = assign_irq_vector(irq, cfg, mask); + if (err) + return err; + + err = apic->cpu_mask_to_apicid_and(mask, cfg->domain, dest_id); + if (err) { + if (assign_irq_vector(irq, cfg, data->affinity)) + pr_err("Failed to recover vector for irq %d\n", irq); + return err; + } cpumask_copy(data->affinity, mask); - *dest_id = apic->cpu_mask_to_apicid_and(mask, cfg->domain); return 0; } @@ -3040,7 +3060,10 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, if (err) return err; - dest = apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus()); + err = apic->cpu_mask_to_apicid_and(cfg->domain, + apic->target_cpus(), &dest); + if (err) + return err; if (irq_remapped(cfg)) { compose_remapped_msi_msg(pdev, irq, dest, msg, hpet_id); @@ -3361,6 +3384,8 @@ static struct irq_chip ht_irq_chip = { int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev) { struct irq_cfg *cfg; + struct ht_irq_msg msg; + unsigned dest; int err; if (disable_apic) @@ -3368,36 +3393,37 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev) cfg = irq_cfg(irq); err = assign_irq_vector(irq, cfg, apic->target_cpus()); - if (!err) { - struct ht_irq_msg msg; - unsigned dest; + if (err) + return err; - dest = apic->cpu_mask_to_apicid_and(cfg->domain, - apic->target_cpus()); + err = apic->cpu_mask_to_apicid_and(cfg->domain, + apic->target_cpus(), &dest); + if (err) + return err; - msg.address_hi = HT_IRQ_HIGH_DEST_ID(dest); + msg.address_hi = HT_IRQ_HIGH_DEST_ID(dest); - msg.address_lo = - HT_IRQ_LOW_BASE | - HT_IRQ_LOW_DEST_ID(dest) | - HT_IRQ_LOW_VECTOR(cfg->vector) | - ((apic->irq_dest_mode == 0) ? - HT_IRQ_LOW_DM_PHYSICAL : - HT_IRQ_LOW_DM_LOGICAL) | - HT_IRQ_LOW_RQEOI_EDGE | - ((apic->irq_delivery_mode != dest_LowestPrio) ? - HT_IRQ_LOW_MT_FIXED : - HT_IRQ_LOW_MT_ARBITRATED) | - HT_IRQ_LOW_IRQ_MASKED; + msg.address_lo = + HT_IRQ_LOW_BASE | + HT_IRQ_LOW_DEST_ID(dest) | + HT_IRQ_LOW_VECTOR(cfg->vector) | + ((apic->irq_dest_mode == 0) ? + HT_IRQ_LOW_DM_PHYSICAL : + HT_IRQ_LOW_DM_LOGICAL) | + HT_IRQ_LOW_RQEOI_EDGE | + ((apic->irq_delivery_mode != dest_LowestPrio) ? + HT_IRQ_LOW_MT_FIXED : + HT_IRQ_LOW_MT_ARBITRATED) | + HT_IRQ_LOW_IRQ_MASKED; - write_ht_irq_msg(irq, &msg); + write_ht_irq_msg(irq, &msg); - irq_set_chip_and_handler_name(irq, &ht_irq_chip, - handle_edge_irq, "edge"); + irq_set_chip_and_handler_name(irq, &ht_irq_chip, + handle_edge_irq, "edge"); - dev_printk(KERN_DEBUG, &dev->dev, "irq %d for HT\n", irq); - } - return err; + dev_printk(KERN_DEBUG, &dev->dev, "irq %d for HT\n", irq); + + return 0; } #endif /* CONFIG_HT_IRQ */ diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c index eb2d466fd81a..2b55514c328b 100644 --- a/arch/x86/kernel/apic/numaq_32.c +++ b/arch/x86/kernel/apic/numaq_32.c @@ -406,16 +406,20 @@ static inline int numaq_check_phys_apicid_present(int phys_apicid) * We use physical apicids here, not logical, so just return the default * physical broadcast to stop people from breaking us */ -static unsigned int numaq_cpu_mask_to_apicid(const struct cpumask *cpumask) +static int +numaq_cpu_mask_to_apicid(const struct cpumask *cpumask, unsigned int *apicid) { - return 0x0F; + *apicid = 0x0F; + return 0; } -static inline unsigned int +static int numaq_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask) + const struct cpumask *andmask, + unsigned int *apicid) { - return 0x0F; + *apicid = 0x0F; + return 0; } /* No NUMA-Q box has a HT CPU, but it can't hurt to use the default code. */ diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c index 35d254c1fec2..5766d84f12d6 100644 --- a/arch/x86/kernel/apic/summit_32.c +++ b/arch/x86/kernel/apic/summit_32.c @@ -263,7 +263,8 @@ static int summit_check_phys_apicid_present(int physical_apicid) return 1; } -static unsigned int summit_cpu_mask_to_apicid(const struct cpumask *cpumask) +static int +summit_cpu_mask_to_apicid(const struct cpumask *cpumask, unsigned int *dest_id) { unsigned int round = 0; int cpu, apicid = 0; @@ -276,30 +277,33 @@ static unsigned int summit_cpu_mask_to_apicid(const struct cpumask *cpumask) if (round && APIC_CLUSTER(apicid) != APIC_CLUSTER(new_apicid)) { printk("%s: Not a valid mask!\n", __func__); - return BAD_APICID; + return -EINVAL; } apicid |= new_apicid; round++; } - return apicid; + *dest_id = apicid; + return 0; } -static unsigned int summit_cpu_mask_to_apicid_and(const struct cpumask *inmask, - const struct cpumask *andmask) +static int +summit_cpu_mask_to_apicid_and(const struct cpumask *inmask, + const struct cpumask *andmask, + unsigned int *apicid) { - int apicid = early_per_cpu(x86_cpu_to_logical_apicid, 0); + *apicid = early_per_cpu(x86_cpu_to_logical_apicid, 0); cpumask_var_t cpumask; if (!alloc_cpumask_var(&cpumask, GFP_ATOMIC)) - return apicid; + return 0; cpumask_and(cpumask, inmask, andmask); cpumask_and(cpumask, cpumask, cpu_online_mask); - apicid = summit_cpu_mask_to_apicid(cpumask); + summit_cpu_mask_to_apicid(cpumask, apicid); free_cpumask_var(cpumask); - return apicid; + return 0; } /* diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index 612622c47dfb..5f86f79335f4 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -96,24 +96,26 @@ static void x2apic_send_IPI_all(int vector) __x2apic_send_IPI_mask(cpu_online_mask, vector, APIC_DEST_ALLINC); } -static unsigned int x2apic_cpu_mask_to_apicid(const struct cpumask *cpumask) +static int +x2apic_cpu_mask_to_apicid(const struct cpumask *cpumask, unsigned int *apicid) { int cpu = cpumask_first(cpumask); - u32 dest = 0; int i; - if (cpu > nr_cpu_ids) - return BAD_APICID; + if (cpu >= nr_cpu_ids) + return -EINVAL; + *apicid = 0; for_each_cpu_and(i, cpumask, per_cpu(cpus_in_cluster, cpu)) - dest |= per_cpu(x86_cpu_to_logical_apicid, i); + *apicid |= per_cpu(x86_cpu_to_logical_apicid, i); - return dest; + return 0; } -static unsigned int +static int x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask) + const struct cpumask *andmask, + unsigned int *apicid) { u32 dest = 0; u16 cluster; @@ -128,7 +130,7 @@ x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask, } if (!dest) - return BAD_APICID; + return -EINVAL; for_each_cpu_and(i, cpumask, andmask) { if (!cpumask_test_cpu(i, cpu_online_mask)) @@ -138,7 +140,9 @@ x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask, dest |= per_cpu(x86_cpu_to_logical_apicid, i); } - return dest; + *apicid = dest; + + return 0; } static void init_x2apic_ldr(void) diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index df89a7d78748..2f3030fef31e 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -269,23 +269,31 @@ static void uv_init_apic_ldr(void) { } -static unsigned int uv_cpu_mask_to_apicid(const struct cpumask *cpumask) +static inline int __uv_cpu_to_apicid(int cpu, unsigned int *apicid) +{ + if (likely((unsigned int)cpu < nr_cpu_ids)) { + *apicid = per_cpu(x86_cpu_to_apicid, cpu) | uv_apicid_hibits; + return 0; + } else { + return -EINVAL; + } +} + +static int +uv_cpu_mask_to_apicid(const struct cpumask *cpumask, unsigned int *apicid) { /* * We're using fixed IRQ delivery, can only return one phys APIC ID. * May as well be the first. */ int cpu = cpumask_first(cpumask); - - if ((unsigned)cpu < nr_cpu_ids) - return per_cpu(x86_cpu_to_apicid, cpu) | uv_apicid_hibits; - else - return BAD_APICID; + return __uv_cpu_to_apicid(cpu, apicid); } -static unsigned int +static int uv_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask) + const struct cpumask *andmask, + unsigned int *apicid) { int cpu; @@ -297,7 +305,8 @@ uv_cpu_mask_to_apicid_and(const struct cpumask *cpumask, if (cpumask_test_cpu(cpu, cpu_online_mask)) break; } - return per_cpu(x86_cpu_to_apicid, cpu) | uv_apicid_hibits; + + return __uv_cpu_to_apicid(cpu, apicid); } static unsigned int x2apic_get_apic_id(unsigned long x) diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c index f25c2765a5c9..dd1ff39a464c 100644 --- a/arch/x86/platform/uv/uv_irq.c +++ b/arch/x86/platform/uv/uv_irq.c @@ -135,6 +135,7 @@ arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade, unsigned long mmr_value; struct uv_IO_APIC_route_entry *entry; int mmr_pnode, err; + unsigned int dest; BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != sizeof(unsigned long)); @@ -143,6 +144,10 @@ arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade, if (err != 0) return err; + err = apic->cpu_mask_to_apicid(eligible_cpu, &dest); + if (err != 0) + return err; + if (limit == UV_AFFINITY_CPU) irq_set_status_flags(irq, IRQ_NO_BALANCING); else @@ -159,7 +164,7 @@ arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade, entry->polarity = 0; entry->trigger = 0; entry->mask = 0; - entry->dest = apic->cpu_mask_to_apicid(eligible_cpu); + entry->dest = dest; mmr_pnode = uv_blade_to_pnode(mmr_blade); uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value); diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c index 6d347064b8b0..dafbad06390a 100644 --- a/drivers/iommu/intel_irq_remapping.c +++ b/drivers/iommu/intel_irq_remapping.c @@ -924,6 +924,7 @@ intel_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, struct irq_cfg *cfg = data->chip_data; unsigned int dest, irq = data->irq; struct irte irte; + int err; if (!cpumask_intersects(mask, cpu_online_mask)) return -EINVAL; @@ -931,10 +932,16 @@ intel_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, if (get_irte(irq, &irte)) return -EBUSY; - if (assign_irq_vector(irq, cfg, mask)) - return -EBUSY; + err = assign_irq_vector(irq, cfg, mask); + if (err) + return err; - dest = apic->cpu_mask_to_apicid_and(cfg->domain, mask); + err = apic->cpu_mask_to_apicid_and(cfg->domain, mask, &dest); + if (err) { + if (assign_irq_vector(irq, cfg, data->affinity)); + pr_err("Failed to recover vector for irq %d\n", irq); + return err; + } irte.vector = cfg->vector; irte.dest_id = IRTE_DEST(dest); -- cgit v1.2.3 From bf947fcb77ff858f223c49c76e2d130095fa2585 Mon Sep 17 00:00:00 2001 From: Donald Dutile Date: Mon, 4 Jun 2012 17:29:01 -0400 Subject: iommu/dmar: Replace printks with appropriate pr_*() Just some cleanup so next patch can keep the info printing the same way throughout the file. Replace printk(KERN_* with pr_*() functions. Signed-off-by: Donald Dutile Cc: iommu@lists.linux-foundation.org Cc: chrisw@redhat.com Cc: suresh.b.siddha@intel.com Cc: dwmw2@infradead.org Link: http://lkml.kernel.org/r/1338845342-12464-2-git-send-email-ddutile@redhat.com Signed-off-by: Ingo Molnar --- drivers/iommu/dmar.c | 83 ++++++++++++++++++++++------------------------------ 1 file changed, 35 insertions(+), 48 deletions(-) (limited to 'drivers/iommu') diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index 3a74e4410fc0..1e5a10de3471 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -83,15 +83,14 @@ static int __init dmar_parse_one_dev_scope(struct acpi_dmar_device_scope *scope, * ignore it */ if (!bus) { - printk(KERN_WARNING - PREFIX "Device scope bus [%d] not found\n", - scope->bus); + pr_warn(PREFIX "Device scope bus [%d] not found\n", + scope->bus); break; } pdev = pci_get_slot(bus, PCI_DEVFN(path->dev, path->fn)); if (!pdev) { - printk(KERN_WARNING PREFIX - "Device scope device [%04x:%02x:%02x.%02x] not found\n", + pr_warn(PREFIX "Device scope device" + "[%04x:%02x:%02x.%02x] not found\n", segment, bus->number, path->dev, path->fn); break; } @@ -100,9 +99,9 @@ static int __init dmar_parse_one_dev_scope(struct acpi_dmar_device_scope *scope, bus = pdev->subordinate; } if (!pdev) { - printk(KERN_WARNING PREFIX - "Device scope device [%04x:%02x:%02x.%02x] not found\n", - segment, scope->bus, path->dev, path->fn); + pr_warn(PREFIX + "Device scope device [%04x:%02x:%02x.%02x] not found\n", + segment, scope->bus, path->dev, path->fn); *dev = NULL; return 0; } @@ -110,8 +109,7 @@ static int __init dmar_parse_one_dev_scope(struct acpi_dmar_device_scope *scope, pdev->subordinate) || (scope->entry_type == \ ACPI_DMAR_SCOPE_TYPE_BRIDGE && !pdev->subordinate)) { pci_dev_put(pdev); - printk(KERN_WARNING PREFIX - "Device scope type does not match for %s\n", + pr_warn(PREFIX "Device scope type does not match for %s\n", pci_name(pdev)); return -EINVAL; } @@ -134,8 +132,7 @@ int __init dmar_parse_dev_scope(void *start, void *end, int *cnt, scope->entry_type == ACPI_DMAR_SCOPE_TYPE_BRIDGE) (*cnt)++; else if (scope->entry_type != ACPI_DMAR_SCOPE_TYPE_IOAPIC) { - printk(KERN_WARNING PREFIX - "Unsupported device scope\n"); + pr_warn(PREFIX "Unsupported device scope\n"); } start += scope->length; } @@ -261,25 +258,23 @@ dmar_table_print_dmar_entry(struct acpi_dmar_header *header) case ACPI_DMAR_TYPE_HARDWARE_UNIT: drhd = container_of(header, struct acpi_dmar_hardware_unit, header); - printk (KERN_INFO PREFIX - "DRHD base: %#016Lx flags: %#x\n", + pr_info(PREFIX "DRHD base: %#016Lx flags: %#x\n", (unsigned long long)drhd->address, drhd->flags); break; case ACPI_DMAR_TYPE_RESERVED_MEMORY: rmrr = container_of(header, struct acpi_dmar_reserved_memory, header); - printk (KERN_INFO PREFIX - "RMRR base: %#016Lx end: %#016Lx\n", + pr_info(PREFIX "RMRR base: %#016Lx end: %#016Lx\n", (unsigned long long)rmrr->base_address, (unsigned long long)rmrr->end_address); break; case ACPI_DMAR_TYPE_ATSR: atsr = container_of(header, struct acpi_dmar_atsr, header); - printk(KERN_INFO PREFIX "ATSR flags: %#x\n", atsr->flags); + pr_info(PREFIX "ATSR flags: %#x\n", atsr->flags); break; case ACPI_DMAR_HARDWARE_AFFINITY: rhsa = container_of(header, struct acpi_dmar_rhsa, header); - printk(KERN_INFO PREFIX "RHSA base: %#016Lx proximity domain: %#x\n", + pr_info(PREFIX "RHSA base: %#016Lx proximity domain: %#x\n", (unsigned long long)rhsa->base_address, rhsa->proximity_domain); break; @@ -299,7 +294,7 @@ static int __init dmar_table_detect(void) &dmar_tbl_size); if (ACPI_SUCCESS(status) && !dmar_tbl) { - printk (KERN_WARNING PREFIX "Unable to map DMAR\n"); + pr_warn(PREFIX "Unable to map DMAR\n"); status = AE_NOT_FOUND; } @@ -333,20 +328,18 @@ parse_dmar_table(void) return -ENODEV; if (dmar->width < PAGE_SHIFT - 1) { - printk(KERN_WARNING PREFIX "Invalid DMAR haw\n"); + pr_warn(PREFIX "Invalid DMAR haw\n"); return -EINVAL; } - printk (KERN_INFO PREFIX "Host address width %d\n", - dmar->width + 1); + pr_info(PREFIX "Host address width %d\n", dmar->width + 1); entry_header = (struct acpi_dmar_header *)(dmar + 1); while (((unsigned long)entry_header) < (((unsigned long)dmar) + dmar_tbl->length)) { /* Avoid looping forever on bad ACPI tables */ if (entry_header->length == 0) { - printk(KERN_WARNING PREFIX - "Invalid 0-length structure\n"); + pr_warn(PREFIX "Invalid 0-length structure\n"); ret = -EINVAL; break; } @@ -369,8 +362,7 @@ parse_dmar_table(void) #endif break; default: - printk(KERN_WARNING PREFIX - "Unknown DMAR structure type %d\n", + pr_warn(PREFIX "Unknown DMAR structure type %d\n", entry_header->type); ret = 0; /* for forward compatibility */ break; @@ -469,12 +461,12 @@ int __init dmar_table_init(void) ret = parse_dmar_table(); if (ret) { if (ret != -ENODEV) - printk(KERN_INFO PREFIX "parse DMAR table failure.\n"); + pr_info(PREFIX "parse DMAR table failure.\n"); return ret; } if (list_empty(&dmar_drhd_units)) { - printk(KERN_INFO PREFIX "No DMAR devices found\n"); + pr_info(PREFIX "No DMAR devices found\n"); return -ENODEV; } @@ -506,8 +498,7 @@ int __init check_zero_address(void) (((unsigned long)dmar) + dmar_tbl->length)) { /* Avoid looping forever on bad ACPI tables */ if (entry_header->length == 0) { - printk(KERN_WARNING PREFIX - "Invalid 0-length structure\n"); + pr_warn(PREFIX "Invalid 0-length structure\n"); return 0; } @@ -558,8 +549,8 @@ int __init detect_intel_iommu(void) if (ret && irq_remapping_enabled && cpu_has_x2apic && dmar->flags & 0x1) - printk(KERN_INFO - "Queued invalidation will be enabled to support x2apic and Intr-remapping.\n"); + pr_info("Queued invalidation will be enabled to " + "support x2apic and Intr-remapping.\n"); if (ret && !no_iommu && !iommu_detected && !dmar_disabled) { iommu_detected = 1; @@ -602,7 +593,7 @@ int alloc_iommu(struct dmar_drhd_unit *drhd) iommu->reg = ioremap(drhd->reg_base_addr, VTD_PAGE_SIZE); if (!iommu->reg) { - printk(KERN_ERR "IOMMU: can't map the region\n"); + pr_err("IOMMU: can't map the region\n"); goto error; } iommu->cap = dmar_readq(iommu->reg + DMAR_CAP_REG); @@ -615,15 +606,13 @@ int alloc_iommu(struct dmar_drhd_unit *drhd) agaw = iommu_calculate_agaw(iommu); if (agaw < 0) { - printk(KERN_ERR - "Cannot get a valid agaw for iommu (seq_id = %d)\n", - iommu->seq_id); + pr_err("Cannot get a valid agaw for iommu (seq_id = %d)\n", + iommu->seq_id); goto err_unmap; } msagaw = iommu_calculate_max_sagaw(iommu); if (msagaw < 0) { - printk(KERN_ERR - "Cannot get a valid max agaw for iommu (seq_id = %d)\n", + pr_err("Cannot get a valid max agaw for iommu (seq_id = %d)\n", iommu->seq_id); goto err_unmap; } @@ -640,7 +629,7 @@ int alloc_iommu(struct dmar_drhd_unit *drhd) iounmap(iommu->reg); iommu->reg = ioremap(drhd->reg_base_addr, map_size); if (!iommu->reg) { - printk(KERN_ERR "IOMMU: can't map the region\n"); + pr_err("IOMMU: can't map the region\n"); goto error; } } @@ -710,7 +699,7 @@ static int qi_check_fault(struct intel_iommu *iommu, int index) if (fault & DMA_FSTS_IQE) { head = readl(iommu->reg + DMAR_IQH_REG); if ((head >> DMAR_IQ_SHIFT) == index) { - printk(KERN_ERR "VT-d detected invalid descriptor: " + pr_err("VT-d detected invalid descriptor: " "low=%llx, high=%llx\n", (unsigned long long)qi->desc[index].low, (unsigned long long)qi->desc[index].high); @@ -1129,15 +1118,14 @@ static int dmar_fault_do_one(struct intel_iommu *iommu, int type, reason = dmar_get_fault_reason(fault_reason, &fault_type); if (fault_type == INTR_REMAP) - printk(KERN_ERR "INTR-REMAP: Request device [[%02x:%02x.%d] " + pr_err("INTR-REMAP: Request device [[%02x:%02x.%d] " "fault index %llx\n" "INTR-REMAP:[fault reason %02d] %s\n", (source_id >> 8), PCI_SLOT(source_id & 0xFF), PCI_FUNC(source_id & 0xFF), addr >> 48, fault_reason, reason); else - printk(KERN_ERR - "DMAR:[%s] Request device [%02x:%02x.%d] " + pr_err("DMAR:[%s] Request device [%02x:%02x.%d] " "fault addr %llx \n" "DMAR:[fault reason %02d] %s\n", (type ? "DMA Read" : "DMA Write"), @@ -1157,8 +1145,7 @@ irqreturn_t dmar_fault(int irq, void *dev_id) raw_spin_lock_irqsave(&iommu->register_lock, flag); fault_status = readl(iommu->reg + DMAR_FSTS_REG); if (fault_status) - printk(KERN_ERR "DRHD: handling fault status reg %x\n", - fault_status); + pr_err("DRHD: handling fault status reg %x\n", fault_status); /* TBD: ignore advanced fault log currently */ if (!(fault_status & DMA_FSTS_PPF)) @@ -1224,7 +1211,7 @@ int dmar_set_interrupt(struct intel_iommu *iommu) irq = create_irq(); if (!irq) { - printk(KERN_ERR "IOMMU: no free vectors\n"); + pr_err("IOMMU: no free vectors\n"); return -EINVAL; } @@ -1241,7 +1228,7 @@ int dmar_set_interrupt(struct intel_iommu *iommu) ret = request_irq(irq, dmar_fault, IRQF_NO_THREAD, iommu->name, iommu); if (ret) - printk(KERN_ERR "IOMMU: can't request irq\n"); + pr_err("IOMMU: can't request irq\n"); return ret; } @@ -1258,7 +1245,7 @@ int __init enable_drhd_fault_handling(void) ret = dmar_set_interrupt(iommu); if (ret) { - printk(KERN_ERR "DRHD %Lx: failed to enable fault, " + pr_err("DRHD %Lx: failed to enable fault, " " interrupt, ret %d\n", (unsigned long long)drhd->reg_base_addr, ret); return -1; -- cgit v1.2.3 From 6f5cf52114dd87f9ed091678f7dfc8ff21bbe2b3 Mon Sep 17 00:00:00 2001 From: Donald Dutile Date: Mon, 4 Jun 2012 17:29:02 -0400 Subject: iommu/dmar: Reserve mmio space used by the IOMMU, if the BIOS forgets to Intel-iommu initialization doesn't currently reserve the memory used for the IOMMU registers. This can allow the pci resource allocator to assign a device BAR to the same address as the IOMMU registers. This can cause some not so nice side affects when the driver ioremap's that region. Introduced two helper functions to map & unmap the IOMMU registers as well as simplify the init and exit paths. Signed-off-by: Donald Dutile Acked-by: Chris Wright Cc: iommu@lists.linux-foundation.org Cc: suresh.b.siddha@intel.com Cc: dwmw2@infradead.org Link: http://lkml.kernel.org/r/1338845342-12464-3-git-send-email-ddutile@redhat.com Signed-off-by: Ingo Molnar --- drivers/iommu/dmar.c | 111 +++++++++++++++++++++++++++++++++----------- include/linux/intel-iommu.h | 2 + 2 files changed, 86 insertions(+), 27 deletions(-) (limited to 'drivers/iommu') diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index 1e5a10de3471..9ab6ebf46f7a 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -570,14 +570,89 @@ int __init detect_intel_iommu(void) } +static void unmap_iommu(struct intel_iommu *iommu) +{ + iounmap(iommu->reg); + release_mem_region(iommu->reg_phys, iommu->reg_size); +} + +/** + * map_iommu: map the iommu's registers + * @iommu: the iommu to map + * @phys_addr: the physical address of the base resgister + * + * Memory map the iommu's registers. Start w/ a single page, and + * possibly expand if that turns out to be insufficent. + */ +static int map_iommu(struct intel_iommu *iommu, u64 phys_addr) +{ + int map_size, err=0; + + iommu->reg_phys = phys_addr; + iommu->reg_size = VTD_PAGE_SIZE; + + if (!request_mem_region(iommu->reg_phys, iommu->reg_size, iommu->name)) { + pr_err("IOMMU: can't reserve memory\n"); + err = -EBUSY; + goto out; + } + + iommu->reg = ioremap(iommu->reg_phys, iommu->reg_size); + if (!iommu->reg) { + pr_err("IOMMU: can't map the region\n"); + err = -ENOMEM; + goto release; + } + + iommu->cap = dmar_readq(iommu->reg + DMAR_CAP_REG); + iommu->ecap = dmar_readq(iommu->reg + DMAR_ECAP_REG); + + if (iommu->cap == (uint64_t)-1 && iommu->ecap == (uint64_t)-1) { + err = -EINVAL; + warn_invalid_dmar(phys_addr, " returns all ones"); + goto unmap; + } + + /* the registers might be more than one page */ + map_size = max_t(int, ecap_max_iotlb_offset(iommu->ecap), + cap_max_fault_reg_offset(iommu->cap)); + map_size = VTD_PAGE_ALIGN(map_size); + if (map_size > iommu->reg_size) { + iounmap(iommu->reg); + release_mem_region(iommu->reg_phys, iommu->reg_size); + iommu->reg_size = map_size; + if (!request_mem_region(iommu->reg_phys, iommu->reg_size, + iommu->name)) { + pr_err("IOMMU: can't reserve memory\n"); + err = -EBUSY; + goto out; + } + iommu->reg = ioremap(iommu->reg_phys, iommu->reg_size); + if (!iommu->reg) { + pr_err("IOMMU: can't map the region\n"); + err = -ENOMEM; + goto release; + } + } + err = 0; + goto out; + +unmap: + iounmap(iommu->reg); +release: + release_mem_region(iommu->reg_phys, iommu->reg_size); +out: + return err; +} + int alloc_iommu(struct dmar_drhd_unit *drhd) { struct intel_iommu *iommu; - int map_size; u32 ver; static int iommu_allocated = 0; int agaw = 0; int msagaw = 0; + int err; if (!drhd->reg_base_addr) { warn_invalid_dmar(0, ""); @@ -591,19 +666,13 @@ int alloc_iommu(struct dmar_drhd_unit *drhd) iommu->seq_id = iommu_allocated++; sprintf (iommu->name, "dmar%d", iommu->seq_id); - iommu->reg = ioremap(drhd->reg_base_addr, VTD_PAGE_SIZE); - if (!iommu->reg) { - pr_err("IOMMU: can't map the region\n"); + err = map_iommu(iommu, drhd->reg_base_addr); + if (err) { + pr_err("IOMMU: failed to map %s\n", iommu->name); goto error; } - iommu->cap = dmar_readq(iommu->reg + DMAR_CAP_REG); - iommu->ecap = dmar_readq(iommu->reg + DMAR_ECAP_REG); - - if (iommu->cap == (uint64_t)-1 && iommu->ecap == (uint64_t)-1) { - warn_invalid_dmar(drhd->reg_base_addr, " returns all ones"); - goto err_unmap; - } + err = -EINVAL; agaw = iommu_calculate_agaw(iommu); if (agaw < 0) { pr_err("Cannot get a valid agaw for iommu (seq_id = %d)\n", @@ -621,19 +690,6 @@ int alloc_iommu(struct dmar_drhd_unit *drhd) iommu->node = -1; - /* the registers might be more than one page */ - map_size = max_t(int, ecap_max_iotlb_offset(iommu->ecap), - cap_max_fault_reg_offset(iommu->cap)); - map_size = VTD_PAGE_ALIGN(map_size); - if (map_size > VTD_PAGE_SIZE) { - iounmap(iommu->reg); - iommu->reg = ioremap(drhd->reg_base_addr, map_size); - if (!iommu->reg) { - pr_err("IOMMU: can't map the region\n"); - goto error; - } - } - ver = readl(iommu->reg + DMAR_VER_REG); pr_info("IOMMU %d: reg_base_addr %llx ver %d:%d cap %llx ecap %llx\n", iommu->seq_id, @@ -648,10 +704,10 @@ int alloc_iommu(struct dmar_drhd_unit *drhd) return 0; err_unmap: - iounmap(iommu->reg); + unmap_iommu(iommu); error: kfree(iommu); - return -1; + return err; } void free_iommu(struct intel_iommu *iommu) @@ -662,7 +718,8 @@ void free_iommu(struct intel_iommu *iommu) free_dmar_iommu(iommu); if (iommu->reg) - iounmap(iommu->reg); + unmap_iommu(iommu); + kfree(iommu); } diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index e6ca56de9936..78e2ada50cd5 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -308,6 +308,8 @@ enum { struct intel_iommu { void __iomem *reg; /* Pointer to hardware regs, virtual addr */ + u64 reg_phys; /* physical address of hw register set */ + u64 reg_size; /* size of hw register set */ u64 cap; u64 ecap; u32 gcmd; /* Holds TE, EAFL. Don't need SRTP, SFL, WBF */ -- cgit v1.2.3 From e9071b0be5e7ce4903b7f7c370769d485774d3e3 Mon Sep 17 00:00:00 2001 From: Donald Dutile Date: Fri, 8 Jun 2012 17:13:11 -0400 Subject: iommu/dmar: Use pr_format() instead of PREFIX to tidy up pr_*() calls Joe Perches recommended getting rid of the redundant formatting of adding "PREFIX" to all the uses of pr_*() calls. The recommendation helps to reduce source and improve readibility. While cleaning up the PREFIX's, I saw that one of the pr_warn() was redundant in dmar_parse_one_dev_scope(), since the same message was printed after breaking out of the while loop for the same condition, !pdev. So, to avoid a duplicate message, I removed the one in the while loop. Reported-by: Joe Perches Signed-off-by: Donald Dutile Cc: iommu@lists.linux-foundation.org Cc: chrisw@redhat.com Cc: suresh.b.siddha@intel.com Cc: dwmw2@infradead.org Link: http://lkml.kernel.org/r/1339189991-13129-1-git-send-email-ddutile@redhat.com [ Small whitespace fixes. ] Signed-off-by: Ingo Molnar --- drivers/iommu/dmar.c | 54 +++++++++++++++++++++++----------------------------- 1 file changed, 24 insertions(+), 30 deletions(-) (limited to 'drivers/iommu') diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index 9ab6ebf46f7a..86e2f4a62b9a 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -26,6 +26,8 @@ * These routines are used by both DMA-remapping and Interrupt-remapping */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt /* has to precede printk.h */ + #include #include #include @@ -39,8 +41,6 @@ #include #include -#define PREFIX "DMAR: " - /* No locks are needed as DMA remapping hardware unit * list is constructed at boot time and hotplug of * these units are not supported by the architecture. @@ -83,15 +83,12 @@ static int __init dmar_parse_one_dev_scope(struct acpi_dmar_device_scope *scope, * ignore it */ if (!bus) { - pr_warn(PREFIX "Device scope bus [%d] not found\n", - scope->bus); + pr_warn("Device scope bus [%d] not found\n", scope->bus); break; } pdev = pci_get_slot(bus, PCI_DEVFN(path->dev, path->fn)); if (!pdev) { - pr_warn(PREFIX "Device scope device" - "[%04x:%02x:%02x.%02x] not found\n", - segment, bus->number, path->dev, path->fn); + /* warning will be printed below */ break; } path ++; @@ -99,8 +96,7 @@ static int __init dmar_parse_one_dev_scope(struct acpi_dmar_device_scope *scope, bus = pdev->subordinate; } if (!pdev) { - pr_warn(PREFIX - "Device scope device [%04x:%02x:%02x.%02x] not found\n", + pr_warn("Device scope device [%04x:%02x:%02x.%02x] not found\n", segment, scope->bus, path->dev, path->fn); *dev = NULL; return 0; @@ -109,8 +105,8 @@ static int __init dmar_parse_one_dev_scope(struct acpi_dmar_device_scope *scope, pdev->subordinate) || (scope->entry_type == \ ACPI_DMAR_SCOPE_TYPE_BRIDGE && !pdev->subordinate)) { pci_dev_put(pdev); - pr_warn(PREFIX "Device scope type does not match for %s\n", - pci_name(pdev)); + pr_warn("Device scope type does not match for %s\n", + pci_name(pdev)); return -EINVAL; } *dev = pdev; @@ -132,7 +128,7 @@ int __init dmar_parse_dev_scope(void *start, void *end, int *cnt, scope->entry_type == ACPI_DMAR_SCOPE_TYPE_BRIDGE) (*cnt)++; else if (scope->entry_type != ACPI_DMAR_SCOPE_TYPE_IOAPIC) { - pr_warn(PREFIX "Unsupported device scope\n"); + pr_warn("Unsupported device scope\n"); } start += scope->length; } @@ -258,23 +254,23 @@ dmar_table_print_dmar_entry(struct acpi_dmar_header *header) case ACPI_DMAR_TYPE_HARDWARE_UNIT: drhd = container_of(header, struct acpi_dmar_hardware_unit, header); - pr_info(PREFIX "DRHD base: %#016Lx flags: %#x\n", + pr_info("DRHD base: %#016Lx flags: %#x\n", (unsigned long long)drhd->address, drhd->flags); break; case ACPI_DMAR_TYPE_RESERVED_MEMORY: rmrr = container_of(header, struct acpi_dmar_reserved_memory, header); - pr_info(PREFIX "RMRR base: %#016Lx end: %#016Lx\n", + pr_info("RMRR base: %#016Lx end: %#016Lx\n", (unsigned long long)rmrr->base_address, (unsigned long long)rmrr->end_address); break; case ACPI_DMAR_TYPE_ATSR: atsr = container_of(header, struct acpi_dmar_atsr, header); - pr_info(PREFIX "ATSR flags: %#x\n", atsr->flags); + pr_info("ATSR flags: %#x\n", atsr->flags); break; case ACPI_DMAR_HARDWARE_AFFINITY: rhsa = container_of(header, struct acpi_dmar_rhsa, header); - pr_info(PREFIX "RHSA base: %#016Lx proximity domain: %#x\n", + pr_info("RHSA base: %#016Lx proximity domain: %#x\n", (unsigned long long)rhsa->base_address, rhsa->proximity_domain); break; @@ -294,7 +290,7 @@ static int __init dmar_table_detect(void) &dmar_tbl_size); if (ACPI_SUCCESS(status) && !dmar_tbl) { - pr_warn(PREFIX "Unable to map DMAR\n"); + pr_warn("Unable to map DMAR\n"); status = AE_NOT_FOUND; } @@ -328,18 +324,18 @@ parse_dmar_table(void) return -ENODEV; if (dmar->width < PAGE_SHIFT - 1) { - pr_warn(PREFIX "Invalid DMAR haw\n"); + pr_warn("Invalid DMAR haw\n"); return -EINVAL; } - pr_info(PREFIX "Host address width %d\n", dmar->width + 1); + pr_info("Host address width %d\n", dmar->width + 1); entry_header = (struct acpi_dmar_header *)(dmar + 1); while (((unsigned long)entry_header) < (((unsigned long)dmar) + dmar_tbl->length)) { /* Avoid looping forever on bad ACPI tables */ if (entry_header->length == 0) { - pr_warn(PREFIX "Invalid 0-length structure\n"); + pr_warn("Invalid 0-length structure\n"); ret = -EINVAL; break; } @@ -362,7 +358,7 @@ parse_dmar_table(void) #endif break; default: - pr_warn(PREFIX "Unknown DMAR structure type %d\n", + pr_warn("Unknown DMAR structure type %d\n", entry_header->type); ret = 0; /* for forward compatibility */ break; @@ -461,12 +457,12 @@ int __init dmar_table_init(void) ret = parse_dmar_table(); if (ret) { if (ret != -ENODEV) - pr_info(PREFIX "parse DMAR table failure.\n"); + pr_info("parse DMAR table failure.\n"); return ret; } if (list_empty(&dmar_drhd_units)) { - pr_info(PREFIX "No DMAR devices found\n"); + pr_info("No DMAR devices found\n"); return -ENODEV; } @@ -498,7 +494,7 @@ int __init check_zero_address(void) (((unsigned long)dmar) + dmar_tbl->length)) { /* Avoid looping forever on bad ACPI tables */ if (entry_header->length == 0) { - pr_warn(PREFIX "Invalid 0-length structure\n"); + pr_warn("Invalid 0-length structure\n"); return 0; } @@ -549,8 +545,7 @@ int __init detect_intel_iommu(void) if (ret && irq_remapping_enabled && cpu_has_x2apic && dmar->flags & 0x1) - pr_info("Queued invalidation will be enabled to " - "support x2apic and Intr-remapping.\n"); + pr_info("Queued invalidation will be enabled to support x2apic and Intr-remapping.\n"); if (ret && !no_iommu && !iommu_detected && !dmar_disabled) { iommu_detected = 1; @@ -580,9 +575,9 @@ static void unmap_iommu(struct intel_iommu *iommu) * map_iommu: map the iommu's registers * @iommu: the iommu to map * @phys_addr: the physical address of the base resgister - * + * * Memory map the iommu's registers. Start w/ a single page, and - * possibly expand if that turns out to be insufficent. + * possibly expand if that turns out to be insufficent. */ static int map_iommu(struct intel_iommu *iommu, u64 phys_addr) { @@ -1302,8 +1297,7 @@ int __init enable_drhd_fault_handling(void) ret = dmar_set_interrupt(iommu); if (ret) { - pr_err("DRHD %Lx: failed to enable fault, " - " interrupt, ret %d\n", + pr_err("DRHD %Lx: failed to enable fault, interrupt, ret %d\n", (unsigned long long)drhd->reg_base_addr, ret); return -1; } -- cgit v1.2.3 From ed88bed881c9948c4035828c5d63f60c7b015f86 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 12 Jun 2012 19:26:33 +0300 Subject: x86/apic/irq_remap: Silence a bogus pr_err() There is an extra semicolon here so the pr_err() message is printed when it is not intended. Signed-off-by: Dan Carpenter Acked-by: Yinghai Lu Cc: Alexander Gordeev Cc: Suresh Siddha Cc: Joerg Roedel Link: http://lkml.kernel.org/r/20120612162633.GA11077@elgon.mountain Signed-off-by: Ingo Molnar --- drivers/iommu/intel_irq_remapping.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/iommu') diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c index dafbad06390a..853902a1b7db 100644 --- a/drivers/iommu/intel_irq_remapping.c +++ b/drivers/iommu/intel_irq_remapping.c @@ -938,7 +938,7 @@ intel_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, err = apic->cpu_mask_to_apicid_and(cfg->domain, mask, &dest); if (err) { - if (assign_irq_vector(irq, cfg, data->affinity)); + if (assign_irq_vector(irq, cfg, data->affinity)) pr_err("Failed to recover vector for irq %d\n", irq); return err; } -- cgit v1.2.3 From b918c62e086b2130a7bae44110ca516ef10bfe5a Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 17 May 2012 18:51:11 -0700 Subject: PCI: replace struct pci_bus secondary/subordinate with busn_res Replace the struct pci_bus secondary/subordinate members with the struct resource busn_res. Later we'll build a resource tree of these bus numbers. [bhelgaas: changelog] Signed-off-by: Yinghai Lu Signed-off-by: Bjorn Helgaas --- arch/alpha/kernel/pci.c | 2 +- arch/arm/kernel/bios32.c | 2 +- arch/ia64/pci/pci.c | 2 +- arch/microblaze/pci/pci-common.c | 4 +-- arch/mips/pci/pci.c | 2 +- arch/powerpc/kernel/pci-common.c | 6 ++-- arch/powerpc/kernel/pci_64.c | 2 +- arch/powerpc/kernel/pci_of_scan.c | 2 +- arch/powerpc/platforms/powernv/pci-ioda.c | 8 ++--- arch/powerpc/platforms/pseries/pci_dlpar.c | 2 +- arch/sh/drivers/pci/pci.c | 2 +- arch/sparc/kernel/pci.c | 6 ++-- arch/tile/kernel/pci.c | 4 +-- arch/x86/pci/acpi.c | 2 +- arch/xtensa/kernel/pci.c | 2 +- drivers/iommu/intel-iommu.c | 2 +- drivers/net/ethernet/broadcom/tg3.c | 4 +-- drivers/parisc/dino.c | 10 +++--- drivers/parisc/iosapic.c | 2 +- drivers/parisc/lba_pci.c | 22 ++++++------ drivers/pci/hotplug/acpiphp_glue.c | 8 ++--- drivers/pci/hotplug/cpci_hotplug_pci.c | 6 ++-- drivers/pci/hotplug/pciehp_pci.c | 4 +-- drivers/pci/hotplug/shpchp_pci.c | 6 ++-- drivers/pci/hotplug/shpchp_sysfs.c | 6 ++-- drivers/pci/iov.c | 4 +-- drivers/pci/pci.c | 2 +- drivers/pci/probe.c | 58 +++++++++++++++--------------- drivers/pci/setup-bus.c | 24 ++++++------- drivers/pcmcia/cardbus.c | 2 +- drivers/pcmcia/yenta_socket.c | 26 +++++++------- 31 files changed, 117 insertions(+), 117 deletions(-) (limited to 'drivers/iommu') diff --git a/arch/alpha/kernel/pci.c b/arch/alpha/kernel/pci.c index 1a629636cc16..53229a496311 100644 --- a/arch/alpha/kernel/pci.c +++ b/arch/alpha/kernel/pci.c @@ -359,7 +359,7 @@ common_init_pci(void) hose, &resources); hose->bus = bus; hose->need_domain_info = need_domain_info; - next_busno = bus->subordinate + 1; + next_busno = bus->busn_res.end + 1; /* Don't allow 8-bit bus number overflow inside the hose - reserve some space for bridges. */ if (next_busno > 224) { diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c index 25552508c3fd..f07710849b58 100644 --- a/arch/arm/kernel/bios32.c +++ b/arch/arm/kernel/bios32.c @@ -461,7 +461,7 @@ static void __init pcibios_init_hw(struct hw_pci *hw, struct list_head *head) if (!sys->bus) panic("PCI: unable to scan bus!"); - busnr = sys->bus->subordinate + 1; + busnr = sys->bus->busn_res.end + 1; list_add(&sys->node, head); } else { diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c index 524df4295c90..3ca9bed7dc50 100644 --- a/arch/ia64/pci/pci.c +++ b/arch/ia64/pci/pci.c @@ -384,7 +384,7 @@ pci_acpi_scan_root(struct acpi_pci_root *root) return NULL; } - pbus->subordinate = pci_scan_child_bus(pbus); + pbus->busn_res.end = pci_scan_child_bus(pbus); return pbus; out3: diff --git a/arch/microblaze/pci/pci-common.c b/arch/microblaze/pci/pci-common.c index ed22bfc5db14..9b32483cd0c0 100644 --- a/arch/microblaze/pci/pci-common.c +++ b/arch/microblaze/pci/pci-common.c @@ -1506,10 +1506,10 @@ static void __devinit pcibios_scan_phb(struct pci_controller *hose) pci_free_resource_list(&resources); return; } - bus->secondary = hose->first_busno; + bus->busn_res.start = hose->first_busno; hose->bus = bus; - hose->last_busno = bus->subordinate; + hose->last_busno = bus->busn_res.end; } static int __init pcibios_init(void) diff --git a/arch/mips/pci/pci.c b/arch/mips/pci/pci.c index 271e8c4a54c7..0a9bf778edb5 100644 --- a/arch/mips/pci/pci.c +++ b/arch/mips/pci/pci.c @@ -102,7 +102,7 @@ static void __devinit pcibios_scanbus(struct pci_controller *hose) need_domain_info = need_domain_info || hose->index; hose->need_domain_info = need_domain_info; if (bus) { - next_busno = bus->subordinate + 1; + next_busno = bus->busn_res.end + 1; /* Don't allow 8-bit bus number overflow inside the hose - reserve some space for bridges. */ if (next_busno > 224) { diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 8e78e93c8185..3532b535698a 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -1646,7 +1646,7 @@ void __devinit pcibios_scan_phb(struct pci_controller *hose) pci_free_resource_list(&resources); return; } - bus->secondary = hose->first_busno; + bus->busn_res.start = hose->first_busno; hose->bus = bus; /* Get probe mode and perform scan */ @@ -1655,12 +1655,12 @@ void __devinit pcibios_scan_phb(struct pci_controller *hose) mode = ppc_md.pci_probe_mode(bus); pr_debug(" probe mode: %d\n", mode); if (mode == PCI_PROBE_DEVTREE) { - bus->subordinate = hose->last_busno; + bus->busn_res.end = hose->last_busno; of_scan_bus(node, bus); } if (mode == PCI_PROBE_NORMAL) - hose->last_busno = bus->subordinate = pci_scan_child_bus(bus); + hose->last_busno = bus->busn_res.end = pci_scan_child_bus(bus); /* Platform gets a chance to do some global fixups before * we proceed to resource allocation diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index 94a54f61d341..4ff190ff24a0 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -236,7 +236,7 @@ long sys_pciconfig_iobase(long which, unsigned long in_bus, for (ln = pci_root_buses.next; ln != &pci_root_buses; ln = ln->next) { bus = pci_bus_b(ln); - if (in_bus >= bus->number && in_bus <= bus->subordinate) + if (in_bus >= bus->number && in_bus <= bus->busn_res.end) break; bus = NULL; } diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c index 89dde171a6fa..a36281aa98f3 100644 --- a/arch/powerpc/kernel/pci_of_scan.c +++ b/arch/powerpc/kernel/pci_of_scan.c @@ -240,7 +240,7 @@ void __devinit of_scan_pci_bridge(struct pci_dev *dev) } bus->primary = dev->bus->number; - bus->subordinate = busrange[1]; + bus->busn_res.end = busrange[1]; bus->bridge_ctl = 0; /* parse ranges property */ diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index fbdd74dac3ac..9cda6a1ad0cf 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -589,7 +589,7 @@ static int __devinit pnv_ioda_configure_pe(struct pnv_phb *phb, dcomp = OPAL_IGNORE_RID_DEVICE_NUMBER; fcomp = OPAL_IGNORE_RID_FUNCTION_NUMBER; parent = pe->pbus->self; - count = pe->pbus->subordinate - pe->pbus->secondary + 1; + count = pe->pbus->busn_res.end - pe->pbus->busn_res.start + 1; switch(count) { case 1: bcomp = OpalPciBusAll; break; case 2: bcomp = OpalPciBus7Bits; break; @@ -816,11 +816,11 @@ static void __devinit pnv_ioda_setup_bus_PE(struct pci_dev *dev, pe->pdev = NULL; pe->tce32_seg = -1; pe->mve_number = -1; - pe->rid = bus->secondary << 8; + pe->rid = bus->busn_res.start << 8; pe->dma_weight = 0; - pe_info(pe, "Secondary busses %d..%d associated with PE\n", - bus->secondary, bus->subordinate); + pe_info(pe, "Secondary busses %pR associated with PE\n", + &bus->busn_res); if (pnv_ioda_configure_pe(phb, pe)) { /* XXX What do we do here ? */ diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c index 8b7bafa489c2..3ccebc83dc02 100644 --- a/arch/powerpc/platforms/pseries/pci_dlpar.c +++ b/arch/powerpc/platforms/pseries/pci_dlpar.c @@ -121,7 +121,7 @@ void pcibios_add_pci_devices(struct pci_bus * bus) if (!num) return; pcibios_setup_bus_devices(bus); - max = bus->secondary; + max = bus->busn_res.start; for (pass=0; pass < 2; pass++) list_for_each_entry(dev, &bus->devices, bus_list) { if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE || diff --git a/arch/sh/drivers/pci/pci.c b/arch/sh/drivers/pci/pci.c index 9d10a3cb8797..43068dcb451c 100644 --- a/arch/sh/drivers/pci/pci.c +++ b/arch/sh/drivers/pci/pci.c @@ -59,7 +59,7 @@ static void __devinit pcibios_scanbus(struct pci_channel *hose) need_domain_info = need_domain_info || hose->index; hose->need_domain_info = need_domain_info; if (bus) { - next_busno = bus->subordinate + 1; + next_busno = bus->busn_res.end + 1; /* Don't allow 8-bit bus number overflow inside the hose - reserve some space for bridges. */ if (next_busno > 224) { diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c index fdaf21811670..c85bfd788f74 100644 --- a/arch/sparc/kernel/pci.c +++ b/arch/sparc/kernel/pci.c @@ -535,7 +535,7 @@ static void __devinit of_scan_pci_bridge(struct pci_pbm_info *pbm, } bus->primary = dev->bus->number; - bus->subordinate = busrange[1]; + bus->busn_res.end = busrange[1]; bus->bridge_ctl = 0; /* parse ranges property, or cook one up by hand for Simba */ @@ -693,8 +693,8 @@ struct pci_bus * __devinit pci_scan_one_pbm(struct pci_pbm_info *pbm, pci_free_resource_list(&resources); return NULL; } - bus->secondary = pbm->pci_first_busno; - bus->subordinate = pbm->pci_last_busno; + bus->busn_res.start = pbm->pci_first_busno; + bus->busn_res.end = pbm->pci_last_busno; pci_of_scan_bus(pbm, node, bus); pci_bus_add_devices(bus); diff --git a/arch/tile/kernel/pci.c b/arch/tile/kernel/pci.c index b56d12bf5900..54cc8d77c90c 100644 --- a/arch/tile/kernel/pci.c +++ b/arch/tile/kernel/pci.c @@ -329,7 +329,7 @@ int __init pcibios_init(void) */ bus = pci_scan_bus(0, controller->ops, controller); controller->root_bus = bus; - controller->last_busno = bus->subordinate; + controller->last_busno = bus->busn_res.end; } } @@ -366,7 +366,7 @@ int __init pcibios_init(void) */ if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI && (PCI_SLOT(dev->devfn) == 0)) { - next_bus = dev->subordinate; + next_bus = dev->busn_res.end; controllers[i].mem_resources[0] = *next_bus->resource[0]; controllers[i].mem_resources[1] = diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index fc09c2754e08..350fe63c8a42 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -440,7 +440,7 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_pci_root *root) bus = pci_create_root_bus(NULL, busnum, &pci_root_ops, sd, &resources); if (bus) { - bus->subordinate = pci_scan_child_bus(bus); + bus->busn_res.end = pci_scan_child_bus(bus); pci_set_host_bridge_release( to_pci_host_bridge(bus->bridge), release_pci_root_info, info); diff --git a/arch/xtensa/kernel/pci.c b/arch/xtensa/kernel/pci.c index eb30e356f5be..9c57c1e6870c 100644 --- a/arch/xtensa/kernel/pci.c +++ b/arch/xtensa/kernel/pci.c @@ -187,7 +187,7 @@ static int __init pcibios_init(void) bus = pci_scan_root_bus(NULL, pci_ctrl->first_busno, pci_ctrl->ops, pci_ctrl, &resources); pci_ctrl->bus = bus; - pci_ctrl->last_busno = bus->subordinate; + pci_ctrl->last_busno = bus->busn_res.end; if (next_busno <= pci_ctrl->last_busno) next_busno = pci_ctrl->last_busno+1; } diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index b12af2ff8c54..2fb7d1598a68 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -661,7 +661,7 @@ static struct intel_iommu *device_to_iommu(int segment, u8 bus, u8 devfn) if (drhd->devices[i] && drhd->devices[i]->subordinate && drhd->devices[i]->subordinate->number <= bus && - drhd->devices[i]->subordinate->subordinate >= bus) + drhd->devices[i]->subordinate->busn_res.end >= bus) return drhd->iommu; } diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index edeeb516807a..09fa3c687a1f 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -14168,7 +14168,7 @@ static int __devinit tg3_get_invariants(struct tg3 *tp) if (bridge->subordinate && (bridge->subordinate->number <= tp->pdev->bus->number) && - (bridge->subordinate->subordinate >= + (bridge->subordinate->busn_res.end >= tp->pdev->bus->number)) { tg3_flag_set(tp, 5701_DMA_BUG); pci_dev_put(bridge); @@ -14196,7 +14196,7 @@ static int __devinit tg3_get_invariants(struct tg3 *tp) if (bridge && bridge->subordinate && (bridge->subordinate->number <= tp->pdev->bus->number) && - (bridge->subordinate->subordinate >= + (bridge->subordinate->busn_res.end >= tp->pdev->bus->number)) { tg3_flag_set(tp, 40BIT_DMA_BUG); pci_dev_put(bridge); diff --git a/drivers/parisc/dino.c b/drivers/parisc/dino.c index 432d4bbcc62a..70517b0f94e6 100644 --- a/drivers/parisc/dino.c +++ b/drivers/parisc/dino.c @@ -174,7 +174,7 @@ static int dino_cfg_read(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *val) { struct dino_device *d = DINO_DEV(parisc_walk_tree(bus->bridge)); - u32 local_bus = (bus->parent == NULL) ? 0 : bus->secondary; + u32 local_bus = (bus->parent == NULL) ? 0 : bus->busn_res.start; u32 v = DINO_CFG_TOK(local_bus, devfn, where & ~3); void __iomem *base_addr = d->hba.base_addr; unsigned long flags; @@ -209,7 +209,7 @@ static int dino_cfg_write(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 val) { struct dino_device *d = DINO_DEV(parisc_walk_tree(bus->bridge)); - u32 local_bus = (bus->parent == NULL) ? 0 : bus->secondary; + u32 local_bus = (bus->parent == NULL) ? 0 : bus->busn_res.start; u32 v = DINO_CFG_TOK(local_bus, devfn, where & ~3); void __iomem *base_addr = d->hba.base_addr; unsigned long flags; @@ -554,7 +554,7 @@ dino_fixup_bus(struct pci_bus *bus) struct dino_device *dino_dev = DINO_DEV(parisc_walk_tree(bus->bridge)); DBG(KERN_WARNING "%s(0x%p) bus %d platform_data 0x%p\n", - __func__, bus, bus->secondary, + __func__, bus, bus->busn_res.start, bus->bridge->platform_data); /* Firmware doesn't set up card-mode dino, so we have to */ @@ -998,12 +998,12 @@ static int __init dino_probe(struct parisc_device *dev) return 0; } - bus->subordinate = pci_scan_child_bus(bus); + bus->busn_res.end = pci_scan_child_bus(bus); /* This code *depends* on scanning being single threaded * if it isn't, this global bus number count will fail */ - dino_current_bus = bus->subordinate + 1; + dino_current_bus = bus->busn_res.end + 1; pci_bus_assign_resources(bus); pci_bus_add_devices(bus); return 0; diff --git a/drivers/parisc/iosapic.c b/drivers/parisc/iosapic.c index 1f9e9fefb8e7..83380c8fcb6b 100644 --- a/drivers/parisc/iosapic.c +++ b/drivers/parisc/iosapic.c @@ -532,7 +532,7 @@ iosapic_xlate_pin(struct iosapic_info *isi, struct pci_dev *pcidev) intr_slot = PCI_SLOT(pcidev->devfn); } DBG_IRT("iosapic_xlate_pin: bus %d slot %d pin %d\n", - pcidev->bus->secondary, intr_slot, intr_pin); + pcidev->bus->busn_res.start, intr_slot, intr_pin); return irt_find_irqline(isi, intr_slot, intr_pin); } diff --git a/drivers/parisc/lba_pci.c b/drivers/parisc/lba_pci.c index 052fa230bc77..cd8f9ce8720f 100644 --- a/drivers/parisc/lba_pci.c +++ b/drivers/parisc/lba_pci.c @@ -189,8 +189,8 @@ lba_dump_res(struct resource *r, int d) static int lba_device_present(u8 bus, u8 dfn, struct lba_device *d) { - u8 first_bus = d->hba.hba_bus->secondary; - u8 last_sub_bus = d->hba.hba_bus->subordinate; + u8 first_bus = d->hba.hba_bus->busn_res.start; + u8 last_sub_bus = d->hba.hba_bus->busn_res.end; if ((bus < first_bus) || (bus > last_sub_bus) || @@ -364,7 +364,7 @@ lba_rd_cfg(struct lba_device *d, u32 tok, u8 reg, u32 size) static int elroy_cfg_read(struct pci_bus *bus, unsigned int devfn, int pos, int size, u32 *data) { struct lba_device *d = LBA_DEV(parisc_walk_tree(bus->bridge)); - u32 local_bus = (bus->parent == NULL) ? 0 : bus->secondary; + u32 local_bus = (bus->parent == NULL) ? 0 : bus->busn_res.start; u32 tok = LBA_CFG_TOK(local_bus, devfn); void __iomem *data_reg = d->hba.base_addr + LBA_PCI_CFG_DATA; @@ -380,7 +380,7 @@ static int elroy_cfg_read(struct pci_bus *bus, unsigned int devfn, int pos, int return 0; } - if (LBA_SKIP_PROBE(d) && !lba_device_present(bus->secondary, devfn, d)) { + if (LBA_SKIP_PROBE(d) && !lba_device_present(bus->busn_res.start, devfn, d)) { DBG_CFG("%s(%x+%2x) -> -1 (b)\n", __func__, tok, pos); /* either don't want to look or know device isn't present. */ *data = ~0U; @@ -431,7 +431,7 @@ lba_wr_cfg(struct lba_device *d, u32 tok, u8 reg, u32 data, u32 size) static int elroy_cfg_write(struct pci_bus *bus, unsigned int devfn, int pos, int size, u32 data) { struct lba_device *d = LBA_DEV(parisc_walk_tree(bus->bridge)); - u32 local_bus = (bus->parent == NULL) ? 0 : bus->secondary; + u32 local_bus = (bus->parent == NULL) ? 0 : bus->busn_res.start; u32 tok = LBA_CFG_TOK(local_bus,devfn); if ((pos > 255) || (devfn > 255)) @@ -444,7 +444,7 @@ static int elroy_cfg_write(struct pci_bus *bus, unsigned int devfn, int pos, int return 0; } - if (LBA_SKIP_PROBE(d) && (!lba_device_present(bus->secondary, devfn, d))) { + if (LBA_SKIP_PROBE(d) && (!lba_device_present(bus->busn_res.start, devfn, d))) { DBG_CFG("%s(%x+%2x) = 0x%x (b)\n", __func__, tok, pos,data); return 1; /* New Workaround */ } @@ -481,7 +481,7 @@ static struct pci_ops elroy_cfg_ops = { static int mercury_cfg_read(struct pci_bus *bus, unsigned int devfn, int pos, int size, u32 *data) { struct lba_device *d = LBA_DEV(parisc_walk_tree(bus->bridge)); - u32 local_bus = (bus->parent == NULL) ? 0 : bus->secondary; + u32 local_bus = (bus->parent == NULL) ? 0 : bus->busn_res.start; u32 tok = LBA_CFG_TOK(local_bus, devfn); void __iomem *data_reg = d->hba.base_addr + LBA_PCI_CFG_DATA; @@ -514,7 +514,7 @@ static int mercury_cfg_write(struct pci_bus *bus, unsigned int devfn, int pos, i { struct lba_device *d = LBA_DEV(parisc_walk_tree(bus->bridge)); void __iomem *data_reg = d->hba.base_addr + LBA_PCI_CFG_DATA; - u32 local_bus = (bus->parent == NULL) ? 0 : bus->secondary; + u32 local_bus = (bus->parent == NULL) ? 0 : bus->busn_res.start; u32 tok = LBA_CFG_TOK(local_bus,devfn); if ((pos > 255) || (devfn > 255)) @@ -636,7 +636,7 @@ lba_fixup_bus(struct pci_bus *bus) struct lba_device *ldev = LBA_DEV(parisc_walk_tree(bus->bridge)); DBG("lba_fixup_bus(0x%p) bus %d platform_data 0x%p\n", - bus, bus->secondary, bus->bridge->platform_data); + bus, (int)bus->busn_res.start, bus->bridge->platform_data); /* ** Properly Setup MMIO resources for this bus. @@ -1511,7 +1511,7 @@ lba_driver_probe(struct parisc_device *dev) return 0; } - lba_bus->subordinate = pci_scan_child_bus(lba_bus); + lba_bus->busn_res.end = pci_scan_child_bus(lba_bus); /* This is in lieu of calling pci_assign_unassigned_resources() */ if (is_pdc_pat()) { @@ -1541,7 +1541,7 @@ lba_driver_probe(struct parisc_device *dev) lba_dev->flags |= LBA_FLAG_SKIP_PROBE; } - lba_next_bus = lba_bus->subordinate + 1; + lba_next_bus = lba_res->busn_res.end + 1; pci_bus_add_devices(lba_bus); /* Whew! Finally done! Tell services we got this one covered. */ diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index 806c44fa645a..62d0ae4dfcad 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -100,11 +100,11 @@ static int post_dock_fixups(struct notifier_block *nb, unsigned long val, PCI_PRIMARY_BUS, &buses); - if (((buses >> 8) & 0xff) != bus->secondary) { + if (((buses >> 8) & 0xff) != bus->busn_res.start) { buses = (buses & 0xff000000) | ((unsigned int)(bus->primary) << 0) - | ((unsigned int)(bus->secondary) << 8) - | ((unsigned int)(bus->subordinate) << 16); + | ((unsigned int)(bus->busn_res.start) << 8) + | ((unsigned int)(bus->busn_res.end) << 16); pci_write_config_dword(bus->self, PCI_PRIMARY_BUS, buses); } return NOTIFY_OK; @@ -692,7 +692,7 @@ static unsigned char acpiphp_max_busnr(struct pci_bus *bus) * bus->subordinate value because it could have * padding in it. */ - max = bus->secondary; + max = bus->busn_res.start; list_for_each(tmp, &bus->children) { n = pci_bus_max_busnr(pci_bus_b(tmp)); diff --git a/drivers/pci/hotplug/cpci_hotplug_pci.c b/drivers/pci/hotplug/cpci_hotplug_pci.c index ae853ccd0cd5..42f3a61db87c 100644 --- a/drivers/pci/hotplug/cpci_hotplug_pci.c +++ b/drivers/pci/hotplug/cpci_hotplug_pci.c @@ -292,8 +292,8 @@ int __ref cpci_configure_slot(struct slot *slot) (dev->hdr_type == PCI_HEADER_TYPE_CARDBUS)) { /* Find an unused bus number for the new bridge */ struct pci_bus *child; - unsigned char busnr, start = parent->secondary; - unsigned char end = parent->subordinate; + unsigned char busnr, start = parent->busn_res.start; + unsigned char end = parent->busn_res.end; for (busnr = start; busnr <= end; busnr++) { if (!pci_find_bus(pci_domain_nr(parent), @@ -312,7 +312,7 @@ int __ref cpci_configure_slot(struct slot *slot) pci_dev_put(dev); continue; } - child->subordinate = pci_do_scan_bus(child); + child->busn_res.end = pci_do_scan_bus(child); pci_bus_size_bridges(child); } pci_dev_put(dev); diff --git a/drivers/pci/hotplug/pciehp_pci.c b/drivers/pci/hotplug/pciehp_pci.c index 47d9dc06b109..b898f06b588d 100644 --- a/drivers/pci/hotplug/pciehp_pci.c +++ b/drivers/pci/hotplug/pciehp_pci.c @@ -37,8 +37,8 @@ static int __ref pciehp_add_bridge(struct pci_dev *dev) { struct pci_bus *parent = dev->bus; - int pass, busnr, start = parent->secondary; - int end = parent->subordinate; + int pass, busnr, start = parent->busn_res.start; + int end = parent->busn_res.end; for (busnr = start; busnr <= end; busnr++) { if (!pci_find_bus(pci_domain_nr(parent), busnr)) diff --git a/drivers/pci/hotplug/shpchp_pci.c b/drivers/pci/hotplug/shpchp_pci.c index df7e4bfadae3..d021eb031b3c 100644 --- a/drivers/pci/hotplug/shpchp_pci.c +++ b/drivers/pci/hotplug/shpchp_pci.c @@ -64,8 +64,8 @@ int __ref shpchp_configure_device(struct slot *p_slot) (dev->hdr_type == PCI_HEADER_TYPE_CARDBUS)) { /* Find an unused bus number for the new bridge */ struct pci_bus *child; - unsigned char busnr, start = parent->secondary; - unsigned char end = parent->subordinate; + unsigned char busnr, start = parent->busn_res.start; + unsigned char end = parent->busn_res.end; for (busnr = start; busnr <= end; busnr++) { if (!pci_find_bus(pci_domain_nr(parent), busnr)) @@ -84,7 +84,7 @@ int __ref shpchp_configure_device(struct slot *p_slot) pci_dev_put(dev); continue; } - child->subordinate = pci_do_scan_bus(child); + child->busn_res.end = pci_do_scan_bus(child); pci_bus_size_bridges(child); } pci_configure_slot(dev); diff --git a/drivers/pci/hotplug/shpchp_sysfs.c b/drivers/pci/hotplug/shpchp_sysfs.c index efa30da1ae8f..eeb23ceae4a8 100644 --- a/drivers/pci/hotplug/shpchp_sysfs.c +++ b/drivers/pci/hotplug/shpchp_sysfs.c @@ -73,13 +73,13 @@ static ssize_t show_ctrl (struct device *dev, struct device_attribute *attr, cha } } out += sprintf(out, "Free resources: bus numbers\n"); - for (busnr = bus->secondary; busnr <= bus->subordinate; busnr++) { + for (busnr = bus->busn_res.start; busnr <= bus->busn_res.end; busnr++) { if (!pci_find_bus(pci_domain_nr(bus), busnr)) break; } - if (busnr < bus->subordinate) + if (busnr < bus->busn_res.end) out += sprintf(out, "start = %8.8x, length = %8.8x\n", - busnr, (bus->subordinate - busnr)); + busnr, (int)(bus->busn_res.end - busnr)); return out - buf; } diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c index 6554e1a0f634..e873060fb35b 100644 --- a/drivers/pci/iov.c +++ b/drivers/pci/iov.c @@ -47,7 +47,7 @@ static struct pci_bus *virtfn_add_bus(struct pci_bus *bus, int busnr) if (!child) return NULL; - child->subordinate = busnr; + child->busn_res.end = busnr; child->dev.parent = bus->bridge; rc = pci_bus_add_child(child); if (rc) { @@ -327,7 +327,7 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn) iov->offset = offset; iov->stride = stride; - if (virtfn_bus(dev, nr_virtfn - 1) > dev->bus->subordinate) { + if (virtfn_bus(dev, nr_virtfn - 1) > dev->bus->busn_res.end) { dev_err(&dev->dev, "SR-IOV: bus number out of range\n"); return -ENOMEM; } diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 447e83472c01..aeda6e9c245c 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -110,7 +110,7 @@ unsigned char pci_bus_max_busnr(struct pci_bus* bus) struct list_head *tmp; unsigned char max, n; - max = bus->subordinate; + max = bus->busn_res.end; list_for_each(tmp, &bus->children) { n = pci_bus_max_busnr(pci_bus_b(tmp)); if(n > max) diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 658ac977cb56..651b096134dc 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -381,8 +381,8 @@ void __devinit pci_read_bridge_bases(struct pci_bus *child) if (pci_is_root_bus(child)) /* It's a host bus, nothing to read */ return; - dev_info(&dev->dev, "PCI bridge to [bus %02x-%02x]%s\n", - child->secondary, child->subordinate, + dev_info(&dev->dev, "PCI bridge to %pR%s\n", + &child->busn_res, dev->transparent ? " (subtractive decode)" : ""); pci_bus_remove_resources(child); @@ -599,9 +599,9 @@ static struct pci_bus *pci_alloc_child_bus(struct pci_bus *parent, * Set up the primary, secondary and subordinate * bus numbers. */ - child->number = child->secondary = busnr; - child->primary = parent->secondary; - child->subordinate = 0xff; + child->number = child->busn_res.start = busnr; + child->primary = parent->busn_res.start; + child->busn_res.end = 0xff; if (!bridge) return child; @@ -643,8 +643,8 @@ static void pci_fixup_parent_subordinate_busnr(struct pci_bus *child, int max) if (!pcibios_assign_all_busses()) return; - while (parent->parent && parent->subordinate < max) { - parent->subordinate = max; + while (parent->parent && parent->busn_res.end < max) { + parent->busn_res.end = max; pci_write_config_byte(parent->self, PCI_SUBORDINATE_BUS, max); parent = parent->parent; } @@ -718,15 +718,15 @@ int __devinit pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max, if (!child) goto out; child->primary = primary; - child->subordinate = subordinate; + child->busn_res.end = subordinate; child->bridge_ctl = bctl; } cmax = pci_scan_child_bus(child); if (cmax > max) max = cmax; - if (child->subordinate > max) - max = child->subordinate; + if (child->busn_res.end > max) + max = child->busn_res.end; } else { /* * We need to assign a number to this bus which we always @@ -759,8 +759,8 @@ int __devinit pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max, } buses = (buses & 0xff000000) | ((unsigned int)(child->primary) << 0) - | ((unsigned int)(child->secondary) << 8) - | ((unsigned int)(child->subordinate) << 16); + | ((unsigned int)(child->busn_res.start) << 8) + | ((unsigned int)(child->busn_res.end) << 16); /* * yenta.c forces a secondary latency timer of 176. @@ -805,8 +805,8 @@ int __devinit pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max, break; while (parent->parent) { if ((!pcibios_assign_all_busses()) && - (parent->subordinate > max) && - (parent->subordinate <= max+i)) { + (parent->busn_res.end > max) && + (parent->busn_res.end <= max+i)) { j = 1; } parent = parent->parent; @@ -827,7 +827,7 @@ int __devinit pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max, /* * Set the subordinate bus number to its real value. */ - child->subordinate = max; + child->busn_res.end = max; pci_write_config_byte(dev, PCI_SUBORDINATE_BUS, max); } @@ -837,19 +837,19 @@ int __devinit pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max, /* Has only triggered on CardBus, fixup is in yenta_socket */ while (bus->parent) { - if ((child->subordinate > bus->subordinate) || - (child->number > bus->subordinate) || + if ((child->busn_res.end > bus->busn_res.end) || + (child->number > bus->busn_res.end) || (child->number < bus->number) || - (child->subordinate < bus->number)) { - dev_info(&child->dev, "[bus %02x-%02x] %s " - "hidden behind%s bridge %s [bus %02x-%02x]\n", - child->number, child->subordinate, - (bus->number > child->subordinate && - bus->subordinate < child->number) ? + (child->busn_res.end < bus->number)) { + dev_info(&child->dev, "%pR %s " + "hidden behind%s bridge %s %pR\n", + &child->busn_res, + (bus->number > child->busn_res.end && + bus->busn_res.end < child->number) ? "wholly" : "partially", bus->self->transparent ? " transparent" : "", dev_name(&bus->dev), - bus->number, bus->subordinate); + &bus->busn_res); } bus = bus->parent; } @@ -1548,7 +1548,7 @@ EXPORT_SYMBOL_GPL(pcie_bus_configure_settings); unsigned int __devinit pci_scan_child_bus(struct pci_bus *bus) { - unsigned int devfn, pass, max = bus->secondary; + unsigned int devfn, pass, max = bus->busn_res.start; struct pci_dev *dev; dev_dbg(&bus->dev, "scanning bus\n"); @@ -1642,7 +1642,7 @@ struct pci_bus *pci_create_root_bus(struct device *parent, int bus, /* Create legacy_io and legacy_mem files for this bus */ pci_create_legacy_files(b); - b->number = b->secondary = bus; + b->number = b->busn_res.start = bus; if (parent) dev_info(parent, "PCI host bridge to bus %s\n", dev_name(&b->dev)); @@ -1693,7 +1693,7 @@ struct pci_bus * __devinit pci_scan_root_bus(struct device *parent, int bus, if (!b) return NULL; - b->subordinate = pci_scan_child_bus(b); + b->busn_res.end = pci_scan_child_bus(b); pci_bus_add_devices(b); return b; } @@ -1710,7 +1710,7 @@ struct pci_bus * __devinit pci_scan_bus_parented(struct device *parent, pci_add_resource(&resources, &iomem_resource); b = pci_create_root_bus(parent, bus, ops, sysdata, &resources); if (b) - b->subordinate = pci_scan_child_bus(b); + b->busn_res.end = pci_scan_child_bus(b); else pci_free_resource_list(&resources); return b; @@ -1727,7 +1727,7 @@ struct pci_bus * __devinit pci_scan_bus(int bus, struct pci_ops *ops, pci_add_resource(&resources, &iomem_resource); b = pci_create_root_bus(NULL, bus, ops, sysdata, &resources); if (b) { - b->subordinate = pci_scan_child_bus(b); + b->busn_res.end = pci_scan_child_bus(b); pci_bus_add_devices(b); } else { pci_free_resource_list(&resources); diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index 8fa2d4be88de..192172c87b77 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -404,8 +404,8 @@ void pci_setup_cardbus(struct pci_bus *bus) struct resource *res; struct pci_bus_region region; - dev_info(&bridge->dev, "CardBus bridge to [bus %02x-%02x]\n", - bus->secondary, bus->subordinate); + dev_info(&bridge->dev, "CardBus bridge to %pR\n", + &bus->busn_res); res = bus->resource[0]; pcibios_resource_to_bus(bridge, ®ion, res); @@ -553,8 +553,8 @@ static void __pci_setup_bridge(struct pci_bus *bus, unsigned long type) { struct pci_dev *bridge = bus->self; - dev_info(&bridge->dev, "PCI bridge to [bus %02x-%02x]\n", - bus->secondary, bus->subordinate); + dev_info(&bridge->dev, "PCI bridge to %pR\n", + &bus->busn_res); if (type & IORESOURCE_IO) pci_setup_bridge_io(bus); @@ -745,8 +745,8 @@ static void pbus_size_io(struct pci_bus *bus, resource_size_t min_size, if (!size0 && !size1) { if (b_res->start || b_res->end) dev_info(&bus->self->dev, "disabling bridge window " - "%pR to [bus %02x-%02x] (unused)\n", b_res, - bus->secondary, bus->subordinate); + "%pR to %pR (unused)\n", b_res, + &bus->busn_res); b_res->flags = 0; return; } @@ -757,8 +757,8 @@ static void pbus_size_io(struct pci_bus *bus, resource_size_t min_size, if (size1 > size0 && realloc_head) { add_to_list(realloc_head, bus->self, b_res, size1-size0, 4096); dev_printk(KERN_DEBUG, &bus->self->dev, "bridge window " - "%pR to [bus %02x-%02x] add_size %lx\n", b_res, - bus->secondary, bus->subordinate, size1-size0); + "%pR to %pR add_size %lx\n", b_res, + &bus->busn_res, size1-size0); } } @@ -863,8 +863,8 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask, if (!size0 && !size1) { if (b_res->start || b_res->end) dev_info(&bus->self->dev, "disabling bridge window " - "%pR to [bus %02x-%02x] (unused)\n", b_res, - bus->secondary, bus->subordinate); + "%pR to %pR (unused)\n", b_res, + &bus->busn_res); b_res->flags = 0; return 1; } @@ -874,8 +874,8 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask, if (size1 > size0 && realloc_head) { add_to_list(realloc_head, bus->self, b_res, size1-size0, min_align); dev_printk(KERN_DEBUG, &bus->self->dev, "bridge window " - "%pR to [bus %02x-%02x] add_size %llx\n", b_res, - bus->secondary, bus->subordinate, (unsigned long long)size1-size0); + "%pR to %pR add_size %llx\n", b_res, + &bus->busn_res, (unsigned long long)size1-size0); } return 1; } diff --git a/drivers/pcmcia/cardbus.c b/drivers/pcmcia/cardbus.c index 6e75153c5b4f..24caeaf50529 100644 --- a/drivers/pcmcia/cardbus.c +++ b/drivers/pcmcia/cardbus.c @@ -73,7 +73,7 @@ int __ref cb_alloc(struct pcmcia_socket *s) s->functions = pci_scan_slot(bus, PCI_DEVFN(0, 0)); pci_fixup_cardbus(bus); - max = bus->secondary; + max = bus->busn_res.start; for (pass = 0; pass < 2; pass++) list_for_each_entry(dev, &bus->devices, bus_list) if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE || diff --git a/drivers/pcmcia/yenta_socket.c b/drivers/pcmcia/yenta_socket.c index d07f9ac8c41d..667678db1153 100644 --- a/drivers/pcmcia/yenta_socket.c +++ b/drivers/pcmcia/yenta_socket.c @@ -1048,8 +1048,8 @@ static void yenta_config_init(struct yenta_socket *socket) config_writeb(socket, PCI_LATENCY_TIMER, 168); config_writel(socket, PCI_PRIMARY_BUS, (176 << 24) | /* sec. latency timer */ - (dev->subordinate->subordinate << 16) | /* subordinate bus */ - (dev->subordinate->secondary << 8) | /* secondary bus */ + ((unsigned int)dev->subordinate->busn_res.end << 16) | /* subordinate bus */ + ((unsigned int)dev->subordinate->busn_res.start << 8) | /* secondary bus */ dev->subordinate->primary); /* primary bus */ /* @@ -1086,14 +1086,14 @@ static void yenta_fixup_parent_bridge(struct pci_bus *cardbus_bridge) struct pci_bus *bridge_to_fix = cardbus_bridge->parent; /* Check bus numbers are already set up correctly: */ - if (bridge_to_fix->subordinate >= cardbus_bridge->subordinate) + if (bridge_to_fix->busn_res.end >= cardbus_bridge->busn_res.end) return; /* The subordinate number is ok, nothing to do */ if (!bridge_to_fix->parent) return; /* Root bridges are ok */ /* stay within the limits of the bus range of the parent: */ - upper_limit = bridge_to_fix->parent->subordinate; + upper_limit = bridge_to_fix->parent->busn_res.end; /* check the bus ranges of all silbling bridges to prevent overlap */ list_for_each(tmp, &bridge_to_fix->parent->children) { @@ -1104,36 +1104,36 @@ static void yenta_fixup_parent_bridge(struct pci_bus *cardbus_bridge) * current upper limit, set the new upper limit to * the bus number below the silbling's range: */ - if (silbling->secondary > bridge_to_fix->subordinate - && silbling->secondary <= upper_limit) - upper_limit = silbling->secondary - 1; + if (silbling->busn_res.start > bridge_to_fix->busn_res.end + && silbling->busn_res.start <= upper_limit) + upper_limit = silbling->busn_res.start - 1; } /* Show that the wanted subordinate number is not possible: */ - if (cardbus_bridge->subordinate > upper_limit) + if (cardbus_bridge->busn_res.end > upper_limit) dev_printk(KERN_WARNING, &cardbus_bridge->dev, "Upper limit for fixing this " "bridge's parent bridge: #%02x\n", upper_limit); /* If we have room to increase the bridge's subordinate number, */ - if (bridge_to_fix->subordinate < upper_limit) { + if (bridge_to_fix->busn_res.end < upper_limit) { /* use the highest number of the hidden bus, within limits */ unsigned char subordinate_to_assign = - min(cardbus_bridge->subordinate, upper_limit); + min_t(int, cardbus_bridge->busn_res.end, upper_limit); dev_printk(KERN_INFO, &bridge_to_fix->dev, "Raising subordinate bus# of parent " "bus (#%02x) from #%02x to #%02x\n", bridge_to_fix->number, - bridge_to_fix->subordinate, subordinate_to_assign); + (int)bridge_to_fix->busn_res.end, subordinate_to_assign); /* Save the new subordinate in the bus struct of the bridge */ - bridge_to_fix->subordinate = subordinate_to_assign; + bridge_to_fix->busn_res.end = subordinate_to_assign; /* and update the PCI config space with the new subordinate */ pci_write_config_byte(bridge_to_fix->self, - PCI_SUBORDINATE_BUS, bridge_to_fix->subordinate); + PCI_SUBORDINATE_BUS, bridge_to_fix->busn_res.end); } } -- cgit v1.2.3 From 7eb9ae0799b1e9f0b77733b432bc5f6f055b020b Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Thu, 14 Jun 2012 18:28:49 -0700 Subject: irq/apic: Use config_enabled(CONFIG_SMP) checks to clean up irq_set_affinity() for UP Move the ->irq_set_affinity() routines out of the #ifdef CONFIG_SMP sections and use config_enabled(CONFIG_SMP) checks inside those routines. Thus making those routines simple null stubs for !CONFIG_SMP and retaining those routines with no additional runtime overhead for CONFIG_SMP kernels. Cleans up the ifdef CONFIG_SMP in and around routines related to irq_set_affinity in io_apic and irq_remapping subsystems. Signed-off-by: Suresh Siddha Cc: torvalds@linux-foundation.org Cc: joerg.roedel@amd.com Cc: Sam Ravnborg Cc: Paul Gortmaker Link: http://lkml.kernel.org/r/1339723729.3475.63.camel@sbsiddha-desk.sc.intel.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/apic/io_apic.c | 180 ++++++++++++++++-------------------- drivers/iommu/intel_irq_remapping.c | 7 +- drivers/iommu/irq_remapping.c | 5 +- drivers/iommu/irq_remapping.h | 2 - include/linux/irq.h | 2 - 5 files changed, 86 insertions(+), 110 deletions(-) (limited to 'drivers/iommu') diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 7cbd397884f5..a951ef7decb1 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2224,81 +2224,6 @@ void send_cleanup_vector(struct irq_cfg *cfg) cfg->move_in_progress = 0; } -static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq_cfg *cfg) -{ - int apic, pin; - struct irq_pin_list *entry; - u8 vector = cfg->vector; - - for_each_irq_pin(entry, cfg->irq_2_pin) { - unsigned int reg; - - apic = entry->apic; - pin = entry->pin; - /* - * With interrupt-remapping, destination information comes - * from interrupt-remapping table entry. - */ - if (!irq_remapped(cfg)) - io_apic_write(apic, 0x11 + pin*2, dest); - reg = io_apic_read(apic, 0x10 + pin*2); - reg &= ~IO_APIC_REDIR_VECTOR_MASK; - reg |= vector; - io_apic_modify(apic, 0x10 + pin*2, reg); - } -} - -/* - * Either sets data->affinity to a valid value, and returns - * ->cpu_mask_to_apicid of that in dest_id, or returns -1 and - * leaves data->affinity untouched. - */ -int __ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, - unsigned int *dest_id) -{ - struct irq_cfg *cfg = data->chip_data; - unsigned int irq = data->irq; - int err; - - if (!cpumask_intersects(mask, cpu_online_mask)) - return -EINVAL; - - err = assign_irq_vector(irq, cfg, mask); - if (err) - return err; - - err = apic->cpu_mask_to_apicid_and(mask, cfg->domain, dest_id); - if (err) { - if (assign_irq_vector(irq, cfg, data->affinity)) - pr_err("Failed to recover vector for irq %d\n", irq); - return err; - } - - cpumask_copy(data->affinity, mask); - - return 0; -} - -static int -ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, - bool force) -{ - unsigned int dest, irq = data->irq; - unsigned long flags; - int ret; - - raw_spin_lock_irqsave(&ioapic_lock, flags); - ret = __ioapic_set_affinity(data, mask, &dest); - if (!ret) { - /* Only the high 8 bits are valid. */ - dest = SET_APIC_LOGICAL_ID(dest); - __target_IO_APIC_irq(irq, dest, data->chip_data); - ret = IRQ_SET_MASK_OK_NOCOPY; - } - raw_spin_unlock_irqrestore(&ioapic_lock, flags); - return ret; -} - asmlinkage void smp_irq_move_cleanup_interrupt(void) { unsigned vector, me; @@ -2386,6 +2311,87 @@ void irq_force_complete_move(int irq) static inline void irq_complete_move(struct irq_cfg *cfg) { } #endif +static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq_cfg *cfg) +{ + int apic, pin; + struct irq_pin_list *entry; + u8 vector = cfg->vector; + + for_each_irq_pin(entry, cfg->irq_2_pin) { + unsigned int reg; + + apic = entry->apic; + pin = entry->pin; + /* + * With interrupt-remapping, destination information comes + * from interrupt-remapping table entry. + */ + if (!irq_remapped(cfg)) + io_apic_write(apic, 0x11 + pin*2, dest); + reg = io_apic_read(apic, 0x10 + pin*2); + reg &= ~IO_APIC_REDIR_VECTOR_MASK; + reg |= vector; + io_apic_modify(apic, 0x10 + pin*2, reg); + } +} + +/* + * Either sets data->affinity to a valid value, and returns + * ->cpu_mask_to_apicid of that in dest_id, or returns -1 and + * leaves data->affinity untouched. + */ +int __ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, + unsigned int *dest_id) +{ + struct irq_cfg *cfg = data->chip_data; + unsigned int irq = data->irq; + int err; + + if (!config_enabled(CONFIG_SMP)) + return -1; + + if (!cpumask_intersects(mask, cpu_online_mask)) + return -EINVAL; + + err = assign_irq_vector(irq, cfg, mask); + if (err) + return err; + + err = apic->cpu_mask_to_apicid_and(mask, cfg->domain, dest_id); + if (err) { + if (assign_irq_vector(irq, cfg, data->affinity)) + pr_err("Failed to recover vector for irq %d\n", irq); + return err; + } + + cpumask_copy(data->affinity, mask); + + return 0; +} + +static int +ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, + bool force) +{ + unsigned int dest, irq = data->irq; + unsigned long flags; + int ret; + + if (!config_enabled(CONFIG_SMP)) + return -1; + + raw_spin_lock_irqsave(&ioapic_lock, flags); + ret = __ioapic_set_affinity(data, mask, &dest); + if (!ret) { + /* Only the high 8 bits are valid. */ + dest = SET_APIC_LOGICAL_ID(dest); + __target_IO_APIC_irq(irq, dest, data->chip_data); + ret = IRQ_SET_MASK_OK_NOCOPY; + } + raw_spin_unlock_irqrestore(&ioapic_lock, flags); + return ret; +} + static void ack_apic_edge(struct irq_data *data) { irq_complete_move(data->chip_data); @@ -2565,9 +2571,7 @@ static void irq_remap_modify_chip_defaults(struct irq_chip *chip) chip->irq_ack = ir_ack_apic_edge; chip->irq_eoi = ir_ack_apic_level; -#ifdef CONFIG_SMP chip->irq_set_affinity = set_remapped_irq_affinity; -#endif } #endif /* CONFIG_IRQ_REMAP */ @@ -2578,9 +2582,7 @@ static struct irq_chip ioapic_chip __read_mostly = { .irq_unmask = unmask_ioapic_irq, .irq_ack = ack_apic_edge, .irq_eoi = ack_apic_level, -#ifdef CONFIG_SMP .irq_set_affinity = ioapic_set_affinity, -#endif .irq_retrigger = ioapic_retrigger_irq, }; @@ -3099,7 +3101,6 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, return err; } -#ifdef CONFIG_SMP static int msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { @@ -3121,7 +3122,6 @@ msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) return IRQ_SET_MASK_OK_NOCOPY; } -#endif /* CONFIG_SMP */ /* * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices, @@ -3132,9 +3132,7 @@ static struct irq_chip msi_chip = { .irq_unmask = unmask_msi_irq, .irq_mask = mask_msi_irq, .irq_ack = ack_apic_edge, -#ifdef CONFIG_SMP .irq_set_affinity = msi_set_affinity, -#endif .irq_retrigger = ioapic_retrigger_irq, }; @@ -3219,7 +3217,6 @@ void native_teardown_msi_irq(unsigned int irq) } #ifdef CONFIG_DMAR_TABLE -#ifdef CONFIG_SMP static int dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) @@ -3244,16 +3241,12 @@ dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask, return IRQ_SET_MASK_OK_NOCOPY; } -#endif /* CONFIG_SMP */ - static struct irq_chip dmar_msi_type = { .name = "DMAR_MSI", .irq_unmask = dmar_msi_unmask, .irq_mask = dmar_msi_mask, .irq_ack = ack_apic_edge, -#ifdef CONFIG_SMP .irq_set_affinity = dmar_msi_set_affinity, -#endif .irq_retrigger = ioapic_retrigger_irq, }; @@ -3274,7 +3267,6 @@ int arch_setup_dmar_msi(unsigned int irq) #ifdef CONFIG_HPET_TIMER -#ifdef CONFIG_SMP static int hpet_msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { @@ -3297,16 +3289,12 @@ static int hpet_msi_set_affinity(struct irq_data *data, return IRQ_SET_MASK_OK_NOCOPY; } -#endif /* CONFIG_SMP */ - static struct irq_chip hpet_msi_type = { .name = "HPET_MSI", .irq_unmask = hpet_msi_unmask, .irq_mask = hpet_msi_mask, .irq_ack = ack_apic_edge, -#ifdef CONFIG_SMP .irq_set_affinity = hpet_msi_set_affinity, -#endif .irq_retrigger = ioapic_retrigger_irq, }; @@ -3341,8 +3329,6 @@ int arch_setup_hpet_msi(unsigned int irq, unsigned int id) */ #ifdef CONFIG_HT_IRQ -#ifdef CONFIG_SMP - static void target_ht_irq(unsigned int irq, unsigned int dest, u8 vector) { struct ht_irq_msg msg; @@ -3370,16 +3356,12 @@ ht_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) return IRQ_SET_MASK_OK_NOCOPY; } -#endif - static struct irq_chip ht_irq_chip = { .name = "PCI-HT", .irq_mask = mask_ht_irq, .irq_unmask = unmask_ht_irq, .irq_ack = ack_apic_edge, -#ifdef CONFIG_SMP .irq_set_affinity = ht_set_affinity, -#endif .irq_retrigger = ioapic_retrigger_irq, }; diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c index 853902a1b7db..e0b18f3ae9a8 100644 --- a/drivers/iommu/intel_irq_remapping.c +++ b/drivers/iommu/intel_irq_remapping.c @@ -902,7 +902,6 @@ static int intel_setup_ioapic_entry(int irq, return 0; } -#ifdef CONFIG_SMP /* * Migrate the IO-APIC irq in the presence of intr-remapping. * @@ -926,6 +925,9 @@ intel_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, struct irte irte; int err; + if (!config_enabled(CONFIG_SMP)) + return -EINVAL; + if (!cpumask_intersects(mask, cpu_online_mask)) return -EINVAL; @@ -963,7 +965,6 @@ intel_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, cpumask_copy(data->affinity, mask); return 0; } -#endif static void intel_compose_msi_msg(struct pci_dev *pdev, unsigned int irq, unsigned int dest, @@ -1065,9 +1066,7 @@ struct irq_remap_ops intel_irq_remap_ops = { .reenable = reenable_irq_remapping, .enable_faulting = enable_drhd_fault_handling, .setup_ioapic_entry = intel_setup_ioapic_entry, -#ifdef CONFIG_SMP .set_affinity = intel_ioapic_set_affinity, -#endif .free_irq = free_irte, .compose_msi_msg = intel_compose_msi_msg, .msi_alloc_irq = intel_msi_alloc_irq, diff --git a/drivers/iommu/irq_remapping.c b/drivers/iommu/irq_remapping.c index 40cda8e98d87..1d29b1c66e72 100644 --- a/drivers/iommu/irq_remapping.c +++ b/drivers/iommu/irq_remapping.c @@ -111,16 +111,15 @@ int setup_ioapic_remapped_entry(int irq, vector, attr); } -#ifdef CONFIG_SMP int set_remapped_irq_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { - if (!remap_ops || !remap_ops->set_affinity) + if (!config_enabled(CONFIG_SMP) || !remap_ops || + !remap_ops->set_affinity) return 0; return remap_ops->set_affinity(data, mask, force); } -#endif void free_remapped_irq(int irq) { diff --git a/drivers/iommu/irq_remapping.h b/drivers/iommu/irq_remapping.h index be9d72950c51..b12974cc1dfe 100644 --- a/drivers/iommu/irq_remapping.h +++ b/drivers/iommu/irq_remapping.h @@ -59,11 +59,9 @@ struct irq_remap_ops { unsigned int, int, struct io_apic_irq_attr *); -#ifdef CONFIG_SMP /* Set the CPU affinity of a remapped interrupt */ int (*set_affinity)(struct irq_data *data, const struct cpumask *mask, bool force); -#endif /* Free an IRQ */ int (*free_irq)(int); diff --git a/include/linux/irq.h b/include/linux/irq.h index 61f5cec031e0..47a937cd84af 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -150,9 +150,7 @@ struct irq_data { void *handler_data; void *chip_data; struct msi_desc *msi_desc; -#ifdef CONFIG_SMP cpumask_var_t affinity; -#endif }; /* -- cgit v1.2.3 From ac1534a55d1e87d59a21c09c570605933b551480 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 21 Jun 2012 14:52:40 +0200 Subject: iommu/amd: Initialize dma_ops for hotplug and sriov devices When a device is added to the system at runtime the AMD IOMMU driver initializes the necessary data structures to handle translation for it. But it forgets to change the per-device dma_ops to point to the AMD IOMMU driver. So mapping actually never happens and all DMA accesses end in an IO_PAGE_FAULT. Fix this. Reported-by: Stefan Assmann Cc: stable@vger.kernel.org Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'drivers/iommu') diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index a2e418cba0ff..dfe7d37c82c5 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -83,6 +83,8 @@ static struct iommu_ops amd_iommu_ops; static ATOMIC_NOTIFIER_HEAD(ppr_notifier); int amd_iommu_max_glx_val = -1; +static struct dma_map_ops amd_iommu_dma_ops; + /* * general struct to manage commands send to an IOMMU */ @@ -2267,6 +2269,13 @@ static int device_change_notifier(struct notifier_block *nb, list_add_tail(&dma_domain->list, &iommu_pd_list); spin_unlock_irqrestore(&iommu_pd_list_lock, flags); + dev_data = get_dev_data(dev); + + if (!dev_data->passthrough) + dev->archdata.dma_ops = &amd_iommu_dma_ops; + else + dev->archdata.dma_ops = &nommu_dma_ops; + break; case BUS_NOTIFY_DEL_DEVICE: -- cgit v1.2.3 From d72e31c9374627068df29da8085ca18c92ae35d3 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Wed, 30 May 2012 14:18:53 -0600 Subject: iommu: IOMMU Groups IOMMU device groups are currently a rather vague associative notion with assembly required by the user or user level driver provider to do anything useful. This patch intends to grow the IOMMU group concept into something a bit more consumable. To do this, we first create an object representing the group, struct iommu_group. This structure is allocated (iommu_group_alloc) and filled (iommu_group_add_device) by the iommu driver. The iommu driver is free to add devices to the group using it's own set of policies. This allows inclusion of devices based on physical hardware or topology limitations of the platform, as well as soft requirements, such as multi-function trust levels or peer-to-peer protection of the interconnects. Each device may only belong to a single iommu group, which is linked from struct device.iommu_group. IOMMU groups are maintained using kobject reference counting, allowing for automatic removal of empty, unreferenced groups. It is the responsibility of the iommu driver to remove devices from the group (iommu_group_remove_device). IOMMU groups also include a userspace representation in sysfs under /sys/kernel/iommu_groups. When allocated, each group is given a dynamically assign ID (int). The ID is managed by the core IOMMU group code to support multiple heterogeneous iommu drivers, which could potentially collide in group naming/numbering. This also keeps group IDs to small, easily managed values. A directory is created under /sys/kernel/iommu_groups for each group. A further subdirectory named "devices" contains links to each device within the group. The iommu_group file in the device's sysfs directory, which formerly contained a group number when read, is now a link to the iommu group. Example: $ ls -l /sys/kernel/iommu_groups/26/devices/ total 0 lrwxrwxrwx. 1 root root 0 Apr 17 12:57 0000:00:1e.0 -> ../../../../devices/pci0000:00/0000:00:1e.0 lrwxrwxrwx. 1 root root 0 Apr 17 12:57 0000:06:0d.0 -> ../../../../devices/pci0000:00/0000:00:1e.0/0000:06:0d.0 lrwxrwxrwx. 1 root root 0 Apr 17 12:57 0000:06:0d.1 -> ../../../../devices/pci0000:00/0000:00:1e.0/0000:06:0d.1 $ ls -l /sys/kernel/iommu_groups/26/devices/*/iommu_group [truncating perms/owner/timestamp] /sys/kernel/iommu_groups/26/devices/0000:00:1e.0/iommu_group -> ../../../kernel/iommu_groups/26 /sys/kernel/iommu_groups/26/devices/0000:06:0d.0/iommu_group -> ../../../../kernel/iommu_groups/26 /sys/kernel/iommu_groups/26/devices/0000:06:0d.1/iommu_group -> ../../../../kernel/iommu_groups/26 Groups also include several exported functions for use by user level driver providers, for example VFIO. These include: iommu_group_get(): Acquires a reference to a group from a device iommu_group_put(): Releases reference iommu_group_for_each_dev(): Iterates over group devices using callback iommu_group_[un]register_notifier(): Allows notification of device add and remove operations relevant to the group iommu_group_id(): Return the group number This patch also extends the IOMMU API to allow attaching groups to domains. This is currently a simple wrapper for iterating through devices within a group, but it's expected that the IOMMU API may eventually make groups a more integral part of domains. Groups intentionally do not try to manage group ownership. A user level driver provider must independently acquire ownership for each device within a group before making use of the group as a whole. This may change in the future if group usage becomes more pervasive across both DMA and IOMMU ops. Groups intentionally do not provide a mechanism for driver locking or otherwise manipulating driver matching/probing of devices within the group. Such interfaces are generic to devices and beyond the scope of IOMMU groups. If implemented, user level providers have ready access via iommu_group_for_each_dev and group notifiers. iommu_device_group() is removed here as it has no users. The replacement is: group = iommu_group_get(dev); id = iommu_group_id(group); iommu_group_put(group); AMD-Vi & Intel VT-d support re-added in following patches. Signed-off-by: Alex Williamson Acked-by: Benjamin Herrenschmidt Signed-off-by: Joerg Roedel --- .../ABI/testing/sysfs-kernel-iommu_groups | 14 + drivers/iommu/amd_iommu.c | 21 - drivers/iommu/intel-iommu.c | 49 -- drivers/iommu/iommu.c | 578 +++++++++++++++++++-- include/linux/iommu.h | 104 +++- 5 files changed, 663 insertions(+), 103 deletions(-) create mode 100644 Documentation/ABI/testing/sysfs-kernel-iommu_groups (limited to 'drivers/iommu') diff --git a/Documentation/ABI/testing/sysfs-kernel-iommu_groups b/Documentation/ABI/testing/sysfs-kernel-iommu_groups new file mode 100644 index 000000000000..9b31556cfdda --- /dev/null +++ b/Documentation/ABI/testing/sysfs-kernel-iommu_groups @@ -0,0 +1,14 @@ +What: /sys/kernel/iommu_groups/ +Date: May 2012 +KernelVersion: v3.5 +Contact: Alex Williamson +Description: /sys/kernel/iommu_groups/ contains a number of sub- + directories, each representing an IOMMU group. The + name of the sub-directory matches the iommu_group_id() + for the group, which is an integer value. Within each + subdirectory is another directory named "devices" with + links to the sysfs devices contained in this group. + The group directory also optionally contains a "name" + file if the IOMMU driver has chosen to register a more + common name for the group. +Users: diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index a2e418cba0ff..55283d6291c8 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -3227,26 +3227,6 @@ static int amd_iommu_domain_has_cap(struct iommu_domain *domain, return 0; } -static int amd_iommu_device_group(struct device *dev, unsigned int *groupid) -{ - struct iommu_dev_data *dev_data = dev->archdata.iommu; - struct pci_dev *pdev = to_pci_dev(dev); - u16 devid; - - if (!dev_data) - return -ENODEV; - - if (pdev->is_virtfn || !iommu_group_mf) - devid = dev_data->devid; - else - devid = calc_devid(pdev->bus->number, - PCI_DEVFN(PCI_SLOT(pdev->devfn), 0)); - - *groupid = amd_iommu_alias_table[devid]; - - return 0; -} - static struct iommu_ops amd_iommu_ops = { .domain_init = amd_iommu_domain_init, .domain_destroy = amd_iommu_domain_destroy, @@ -3256,7 +3236,6 @@ static struct iommu_ops amd_iommu_ops = { .unmap = amd_iommu_unmap, .iova_to_phys = amd_iommu_iova_to_phys, .domain_has_cap = amd_iommu_domain_has_cap, - .device_group = amd_iommu_device_group, .pgsize_bitmap = AMD_IOMMU_PGSIZES, }; diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index b12af2ff8c54..c62f2df25221 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -4090,54 +4090,6 @@ static int intel_iommu_domain_has_cap(struct iommu_domain *domain, return 0; } -/* - * Group numbers are arbitrary. Device with the same group number - * indicate the iommu cannot differentiate between them. To avoid - * tracking used groups we just use the seg|bus|devfn of the lowest - * level we're able to differentiate devices - */ -static int intel_iommu_device_group(struct device *dev, unsigned int *groupid) -{ - struct pci_dev *pdev = to_pci_dev(dev); - struct pci_dev *bridge; - union { - struct { - u8 devfn; - u8 bus; - u16 segment; - } pci; - u32 group; - } id; - - if (iommu_no_mapping(dev)) - return -ENODEV; - - id.pci.segment = pci_domain_nr(pdev->bus); - id.pci.bus = pdev->bus->number; - id.pci.devfn = pdev->devfn; - - if (!device_to_iommu(id.pci.segment, id.pci.bus, id.pci.devfn)) - return -ENODEV; - - bridge = pci_find_upstream_pcie_bridge(pdev); - if (bridge) { - if (pci_is_pcie(bridge)) { - id.pci.bus = bridge->subordinate->number; - id.pci.devfn = 0; - } else { - id.pci.bus = bridge->bus->number; - id.pci.devfn = bridge->devfn; - } - } - - if (!pdev->is_virtfn && iommu_group_mf) - id.pci.devfn = PCI_DEVFN(PCI_SLOT(id.pci.devfn), 0); - - *groupid = id.group; - - return 0; -} - static struct iommu_ops intel_iommu_ops = { .domain_init = intel_iommu_domain_init, .domain_destroy = intel_iommu_domain_destroy, @@ -4147,7 +4099,6 @@ static struct iommu_ops intel_iommu_ops = { .unmap = intel_iommu_unmap, .iova_to_phys = intel_iommu_iova_to_phys, .domain_has_cap = intel_iommu_domain_has_cap, - .device_group = intel_iommu_device_group, .pgsize_bitmap = INTEL_IOMMU_PGSIZES, }; diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 8b9ded88e6f5..0e928acd7dcf 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -26,60 +26,535 @@ #include #include #include +#include +#include +#include + +static struct kset *iommu_group_kset; +static struct ida iommu_group_ida; +static struct mutex iommu_group_mutex; + +struct iommu_group { + struct kobject kobj; + struct kobject *devices_kobj; + struct list_head devices; + struct mutex mutex; + struct blocking_notifier_head notifier; + void *iommu_data; + void (*iommu_data_release)(void *iommu_data); + char *name; + int id; +}; + +struct iommu_device { + struct list_head list; + struct device *dev; + char *name; +}; + +struct iommu_group_attribute { + struct attribute attr; + ssize_t (*show)(struct iommu_group *group, char *buf); + ssize_t (*store)(struct iommu_group *group, + const char *buf, size_t count); +}; + +#define IOMMU_GROUP_ATTR(_name, _mode, _show, _store) \ +struct iommu_group_attribute iommu_group_attr_##_name = \ + __ATTR(_name, _mode, _show, _store) -static ssize_t show_iommu_group(struct device *dev, - struct device_attribute *attr, char *buf) +#define to_iommu_group_attr(_attr) \ + container_of(_attr, struct iommu_group_attribute, attr) +#define to_iommu_group(_kobj) \ + container_of(_kobj, struct iommu_group, kobj) + +static ssize_t iommu_group_attr_show(struct kobject *kobj, + struct attribute *__attr, char *buf) { - unsigned int groupid; + struct iommu_group_attribute *attr = to_iommu_group_attr(__attr); + struct iommu_group *group = to_iommu_group(kobj); + ssize_t ret = -EIO; - if (iommu_device_group(dev, &groupid)) - return 0; + if (attr->show) + ret = attr->show(group, buf); + return ret; +} + +static ssize_t iommu_group_attr_store(struct kobject *kobj, + struct attribute *__attr, + const char *buf, size_t count) +{ + struct iommu_group_attribute *attr = to_iommu_group_attr(__attr); + struct iommu_group *group = to_iommu_group(kobj); + ssize_t ret = -EIO; - return sprintf(buf, "%u", groupid); + if (attr->store) + ret = attr->store(group, buf, count); + return ret; } -static DEVICE_ATTR(iommu_group, S_IRUGO, show_iommu_group, NULL); -static int add_iommu_group(struct device *dev, void *data) +static const struct sysfs_ops iommu_group_sysfs_ops = { + .show = iommu_group_attr_show, + .store = iommu_group_attr_store, +}; + +static int iommu_group_create_file(struct iommu_group *group, + struct iommu_group_attribute *attr) +{ + return sysfs_create_file(&group->kobj, &attr->attr); +} + +static void iommu_group_remove_file(struct iommu_group *group, + struct iommu_group_attribute *attr) +{ + sysfs_remove_file(&group->kobj, &attr->attr); +} + +static ssize_t iommu_group_show_name(struct iommu_group *group, char *buf) +{ + return sprintf(buf, "%s\n", group->name); +} + +static IOMMU_GROUP_ATTR(name, S_IRUGO, iommu_group_show_name, NULL); + +static void iommu_group_release(struct kobject *kobj) +{ + struct iommu_group *group = to_iommu_group(kobj); + + if (group->iommu_data_release) + group->iommu_data_release(group->iommu_data); + + mutex_lock(&iommu_group_mutex); + ida_remove(&iommu_group_ida, group->id); + mutex_unlock(&iommu_group_mutex); + + kfree(group->name); + kfree(group); +} + +static struct kobj_type iommu_group_ktype = { + .sysfs_ops = &iommu_group_sysfs_ops, + .release = iommu_group_release, +}; + +/** + * iommu_group_alloc - Allocate a new group + * @name: Optional name to associate with group, visible in sysfs + * + * This function is called by an iommu driver to allocate a new iommu + * group. The iommu group represents the minimum granularity of the iommu. + * Upon successful return, the caller holds a reference to the supplied + * group in order to hold the group until devices are added. Use + * iommu_group_put() to release this extra reference count, allowing the + * group to be automatically reclaimed once it has no devices or external + * references. + */ +struct iommu_group *iommu_group_alloc(void) { - unsigned int groupid; + struct iommu_group *group; + int ret; + + group = kzalloc(sizeof(*group), GFP_KERNEL); + if (!group) + return ERR_PTR(-ENOMEM); + + group->kobj.kset = iommu_group_kset; + mutex_init(&group->mutex); + INIT_LIST_HEAD(&group->devices); + BLOCKING_INIT_NOTIFIER_HEAD(&group->notifier); + + mutex_lock(&iommu_group_mutex); + +again: + if (unlikely(0 == ida_pre_get(&iommu_group_ida, GFP_KERNEL))) { + kfree(group); + mutex_unlock(&iommu_group_mutex); + return ERR_PTR(-ENOMEM); + } + + if (-EAGAIN == ida_get_new(&iommu_group_ida, &group->id)) + goto again; + + mutex_unlock(&iommu_group_mutex); - if (iommu_device_group(dev, &groupid) == 0) - return device_create_file(dev, &dev_attr_iommu_group); + ret = kobject_init_and_add(&group->kobj, &iommu_group_ktype, + NULL, "%d", group->id); + if (ret) { + mutex_lock(&iommu_group_mutex); + ida_remove(&iommu_group_ida, group->id); + mutex_unlock(&iommu_group_mutex); + kfree(group); + return ERR_PTR(ret); + } + + group->devices_kobj = kobject_create_and_add("devices", &group->kobj); + if (!group->devices_kobj) { + kobject_put(&group->kobj); /* triggers .release & free */ + return ERR_PTR(-ENOMEM); + } + + /* + * The devices_kobj holds a reference on the group kobject, so + * as long as that exists so will the group. We can therefore + * use the devices_kobj for reference counting. + */ + kobject_put(&group->kobj); + + return group; +} +EXPORT_SYMBOL_GPL(iommu_group_alloc); + +/** + * iommu_group_get_iommudata - retrieve iommu_data registered for a group + * @group: the group + * + * iommu drivers can store data in the group for use when doing iommu + * operations. This function provides a way to retrieve it. Caller + * should hold a group reference. + */ +void *iommu_group_get_iommudata(struct iommu_group *group) +{ + return group->iommu_data; +} +EXPORT_SYMBOL_GPL(iommu_group_get_iommudata); + +/** + * iommu_group_set_iommudata - set iommu_data for a group + * @group: the group + * @iommu_data: new data + * @release: release function for iommu_data + * + * iommu drivers can store data in the group for use when doing iommu + * operations. This function provides a way to set the data after + * the group has been allocated. Caller should hold a group reference. + */ +void iommu_group_set_iommudata(struct iommu_group *group, void *iommu_data, + void (*release)(void *iommu_data)) +{ + group->iommu_data = iommu_data; + group->iommu_data_release = release; +} +EXPORT_SYMBOL_GPL(iommu_group_set_iommudata); + +/** + * iommu_group_set_name - set name for a group + * @group: the group + * @name: name + * + * Allow iommu driver to set a name for a group. When set it will + * appear in a name attribute file under the group in sysfs. + */ +int iommu_group_set_name(struct iommu_group *group, const char *name) +{ + int ret; + + if (group->name) { + iommu_group_remove_file(group, &iommu_group_attr_name); + kfree(group->name); + group->name = NULL; + if (!name) + return 0; + } + + group->name = kstrdup(name, GFP_KERNEL); + if (!group->name) + return -ENOMEM; + + ret = iommu_group_create_file(group, &iommu_group_attr_name); + if (ret) { + kfree(group->name); + group->name = NULL; + return ret; + } return 0; } +EXPORT_SYMBOL_GPL(iommu_group_set_name); -static int remove_iommu_group(struct device *dev) +/** + * iommu_group_add_device - add a device to an iommu group + * @group: the group into which to add the device (reference should be held) + * @dev: the device + * + * This function is called by an iommu driver to add a device into a + * group. Adding a device increments the group reference count. + */ +int iommu_group_add_device(struct iommu_group *group, struct device *dev) { - unsigned int groupid; + int ret, i = 0; + struct iommu_device *device; + + device = kzalloc(sizeof(*device), GFP_KERNEL); + if (!device) + return -ENOMEM; + + device->dev = dev; - if (iommu_device_group(dev, &groupid) == 0) - device_remove_file(dev, &dev_attr_iommu_group); + ret = sysfs_create_link(&dev->kobj, &group->kobj, "iommu_group"); + if (ret) { + kfree(device); + return ret; + } + + device->name = kasprintf(GFP_KERNEL, "%s", kobject_name(&dev->kobj)); +rename: + if (!device->name) { + sysfs_remove_link(&dev->kobj, "iommu_group"); + kfree(device); + return -ENOMEM; + } + ret = sysfs_create_link_nowarn(group->devices_kobj, + &dev->kobj, device->name); + if (ret) { + kfree(device->name); + if (ret == -EEXIST && i >= 0) { + /* + * Account for the slim chance of collision + * and append an instance to the name. + */ + device->name = kasprintf(GFP_KERNEL, "%s.%d", + kobject_name(&dev->kobj), i++); + goto rename; + } + + sysfs_remove_link(&dev->kobj, "iommu_group"); + kfree(device); + return ret; + } + + kobject_get(group->devices_kobj); + + dev->iommu_group = group; + + mutex_lock(&group->mutex); + list_add_tail(&device->list, &group->devices); + mutex_unlock(&group->mutex); + + /* Notify any listeners about change to group. */ + blocking_notifier_call_chain(&group->notifier, + IOMMU_GROUP_NOTIFY_ADD_DEVICE, dev); return 0; } +EXPORT_SYMBOL_GPL(iommu_group_add_device); -static int iommu_device_notifier(struct notifier_block *nb, - unsigned long action, void *data) +/** + * iommu_group_remove_device - remove a device from it's current group + * @dev: device to be removed + * + * This function is called by an iommu driver to remove the device from + * it's current group. This decrements the iommu group reference count. + */ +void iommu_group_remove_device(struct device *dev) +{ + struct iommu_group *group = dev->iommu_group; + struct iommu_device *tmp_device, *device = NULL; + + /* Pre-notify listeners that a device is being removed. */ + blocking_notifier_call_chain(&group->notifier, + IOMMU_GROUP_NOTIFY_DEL_DEVICE, dev); + + mutex_lock(&group->mutex); + list_for_each_entry(tmp_device, &group->devices, list) { + if (tmp_device->dev == dev) { + device = tmp_device; + list_del(&device->list); + break; + } + } + mutex_unlock(&group->mutex); + + if (!device) + return; + + sysfs_remove_link(group->devices_kobj, device->name); + sysfs_remove_link(&dev->kobj, "iommu_group"); + + kfree(device->name); + kfree(device); + dev->iommu_group = NULL; + kobject_put(group->devices_kobj); +} +EXPORT_SYMBOL_GPL(iommu_group_remove_device); + +/** + * iommu_group_for_each_dev - iterate over each device in the group + * @group: the group + * @data: caller opaque data to be passed to callback function + * @fn: caller supplied callback function + * + * This function is called by group users to iterate over group devices. + * Callers should hold a reference count to the group during callback. + * The group->mutex is held across callbacks, which will block calls to + * iommu_group_add/remove_device. + */ +int iommu_group_for_each_dev(struct iommu_group *group, void *data, + int (*fn)(struct device *, void *)) +{ + struct iommu_device *device; + int ret = 0; + + mutex_lock(&group->mutex); + list_for_each_entry(device, &group->devices, list) { + ret = fn(device->dev, data); + if (ret) + break; + } + mutex_unlock(&group->mutex); + return ret; +} +EXPORT_SYMBOL_GPL(iommu_group_for_each_dev); + +/** + * iommu_group_get - Return the group for a device and increment reference + * @dev: get the group that this device belongs to + * + * This function is called by iommu drivers and users to get the group + * for the specified device. If found, the group is returned and the group + * reference in incremented, else NULL. + */ +struct iommu_group *iommu_group_get(struct device *dev) +{ + struct iommu_group *group = dev->iommu_group; + + if (group) + kobject_get(group->devices_kobj); + + return group; +} +EXPORT_SYMBOL_GPL(iommu_group_get); + +/** + * iommu_group_put - Decrement group reference + * @group: the group to use + * + * This function is called by iommu drivers and users to release the + * iommu group. Once the reference count is zero, the group is released. + */ +void iommu_group_put(struct iommu_group *group) +{ + if (group) + kobject_put(group->devices_kobj); +} +EXPORT_SYMBOL_GPL(iommu_group_put); + +/** + * iommu_group_register_notifier - Register a notifier for group changes + * @group: the group to watch + * @nb: notifier block to signal + * + * This function allows iommu group users to track changes in a group. + * See include/linux/iommu.h for actions sent via this notifier. Caller + * should hold a reference to the group throughout notifier registration. + */ +int iommu_group_register_notifier(struct iommu_group *group, + struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&group->notifier, nb); +} +EXPORT_SYMBOL_GPL(iommu_group_register_notifier); + +/** + * iommu_group_unregister_notifier - Unregister a notifier + * @group: the group to watch + * @nb: notifier block to signal + * + * Unregister a previously registered group notifier block. + */ +int iommu_group_unregister_notifier(struct iommu_group *group, + struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&group->notifier, nb); +} +EXPORT_SYMBOL_GPL(iommu_group_unregister_notifier); + +/** + * iommu_group_id - Return ID for a group + * @group: the group to ID + * + * Return the unique ID for the group matching the sysfs group number. + */ +int iommu_group_id(struct iommu_group *group) +{ + return group->id; +} +EXPORT_SYMBOL_GPL(iommu_group_id); + +static int add_iommu_group(struct device *dev, void *data) +{ + struct iommu_ops *ops = data; + + if (!ops->add_device) + return -ENODEV; + + WARN_ON(dev->iommu_group); + + ops->add_device(dev); + + return 0; +} + +static int iommu_bus_notifier(struct notifier_block *nb, + unsigned long action, void *data) { struct device *dev = data; + struct iommu_ops *ops = dev->bus->iommu_ops; + struct iommu_group *group; + unsigned long group_action = 0; + + /* + * ADD/DEL call into iommu driver ops if provided, which may + * result in ADD/DEL notifiers to group->notifier + */ + if (action == BUS_NOTIFY_ADD_DEVICE) { + if (ops->add_device) + return ops->add_device(dev); + } else if (action == BUS_NOTIFY_DEL_DEVICE) { + if (ops->remove_device && dev->iommu_group) { + ops->remove_device(dev); + return 0; + } + } - if (action == BUS_NOTIFY_ADD_DEVICE) - return add_iommu_group(dev, NULL); - else if (action == BUS_NOTIFY_DEL_DEVICE) - return remove_iommu_group(dev); + /* + * Remaining BUS_NOTIFYs get filtered and republished to the + * group, if anyone is listening + */ + group = iommu_group_get(dev); + if (!group) + return 0; + switch (action) { + case BUS_NOTIFY_BIND_DRIVER: + group_action = IOMMU_GROUP_NOTIFY_BIND_DRIVER; + break; + case BUS_NOTIFY_BOUND_DRIVER: + group_action = IOMMU_GROUP_NOTIFY_BOUND_DRIVER; + break; + case BUS_NOTIFY_UNBIND_DRIVER: + group_action = IOMMU_GROUP_NOTIFY_UNBIND_DRIVER; + break; + case BUS_NOTIFY_UNBOUND_DRIVER: + group_action = IOMMU_GROUP_NOTIFY_UNBOUND_DRIVER; + break; + } + + if (group_action) + blocking_notifier_call_chain(&group->notifier, + group_action, dev); + + iommu_group_put(group); return 0; } -static struct notifier_block iommu_device_nb = { - .notifier_call = iommu_device_notifier, +static struct notifier_block iommu_bus_nb = { + .notifier_call = iommu_bus_notifier, }; static void iommu_bus_init(struct bus_type *bus, struct iommu_ops *ops) { - bus_register_notifier(bus, &iommu_device_nb); - bus_for_each_dev(bus, NULL, NULL, add_iommu_group); + bus_register_notifier(bus, &iommu_bus_nb); + bus_for_each_dev(bus, NULL, ops, add_iommu_group); } /** @@ -192,6 +667,45 @@ void iommu_detach_device(struct iommu_domain *domain, struct device *dev) } EXPORT_SYMBOL_GPL(iommu_detach_device); +/* + * IOMMU groups are really the natrual working unit of the IOMMU, but + * the IOMMU API works on domains and devices. Bridge that gap by + * iterating over the devices in a group. Ideally we'd have a single + * device which represents the requestor ID of the group, but we also + * allow IOMMU drivers to create policy defined minimum sets, where + * the physical hardware may be able to distiguish members, but we + * wish to group them at a higher level (ex. untrusted multi-function + * PCI devices). Thus we attach each device. + */ +static int iommu_group_do_attach_device(struct device *dev, void *data) +{ + struct iommu_domain *domain = data; + + return iommu_attach_device(domain, dev); +} + +int iommu_attach_group(struct iommu_domain *domain, struct iommu_group *group) +{ + return iommu_group_for_each_dev(group, domain, + iommu_group_do_attach_device); +} +EXPORT_SYMBOL_GPL(iommu_attach_group); + +static int iommu_group_do_detach_device(struct device *dev, void *data) +{ + struct iommu_domain *domain = data; + + iommu_detach_device(domain, dev); + + return 0; +} + +void iommu_detach_group(struct iommu_domain *domain, struct iommu_group *group) +{ + iommu_group_for_each_dev(group, domain, iommu_group_do_detach_device); +} +EXPORT_SYMBOL_GPL(iommu_detach_group); + phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, unsigned long iova) { @@ -336,11 +850,15 @@ size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size) } EXPORT_SYMBOL_GPL(iommu_unmap); -int iommu_device_group(struct device *dev, unsigned int *groupid) +static int __init iommu_init(void) { - if (iommu_present(dev->bus) && dev->bus->iommu_ops->device_group) - return dev->bus->iommu_ops->device_group(dev, groupid); + iommu_group_kset = kset_create_and_add("iommu_groups", + NULL, kernel_kobj); + ida_init(&iommu_group_ida); + mutex_init(&iommu_group_mutex); - return -ENODEV; + BUG_ON(!iommu_group_kset); + + return 0; } -EXPORT_SYMBOL_GPL(iommu_device_group); +subsys_initcall(iommu_init); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 450293f6d68b..a71df92be992 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -26,6 +26,7 @@ #define IOMMU_CACHE (4) /* DMA cache coherency */ struct iommu_ops; +struct iommu_group; struct bus_type; struct device; struct iommu_domain; @@ -60,6 +61,8 @@ struct iommu_domain { * @iova_to_phys: translate iova to physical address * @domain_has_cap: domain capabilities query * @commit: commit iommu domain + * @add_device: add device to iommu grouping + * @remove_device: remove device from iommu grouping * @pgsize_bitmap: bitmap of supported page sizes */ struct iommu_ops { @@ -75,10 +78,18 @@ struct iommu_ops { unsigned long iova); int (*domain_has_cap)(struct iommu_domain *domain, unsigned long cap); - int (*device_group)(struct device *dev, unsigned int *groupid); + int (*add_device)(struct device *dev); + void (*remove_device)(struct device *dev); unsigned long pgsize_bitmap; }; +#define IOMMU_GROUP_NOTIFY_ADD_DEVICE 1 /* Device added */ +#define IOMMU_GROUP_NOTIFY_DEL_DEVICE 2 /* Pre Device removed */ +#define IOMMU_GROUP_NOTIFY_BIND_DRIVER 3 /* Pre Driver bind */ +#define IOMMU_GROUP_NOTIFY_BOUND_DRIVER 4 /* Post Driver bind */ +#define IOMMU_GROUP_NOTIFY_UNBIND_DRIVER 5 /* Pre Driver unbind */ +#define IOMMU_GROUP_NOTIFY_UNBOUND_DRIVER 6 /* Post Driver unbind */ + extern int bus_set_iommu(struct bus_type *bus, struct iommu_ops *ops); extern bool iommu_present(struct bus_type *bus); extern struct iommu_domain *iommu_domain_alloc(struct bus_type *bus); @@ -97,7 +108,29 @@ extern int iommu_domain_has_cap(struct iommu_domain *domain, unsigned long cap); extern void iommu_set_fault_handler(struct iommu_domain *domain, iommu_fault_handler_t handler, void *token); -extern int iommu_device_group(struct device *dev, unsigned int *groupid); + +extern int iommu_attach_group(struct iommu_domain *domain, + struct iommu_group *group); +extern void iommu_detach_group(struct iommu_domain *domain, + struct iommu_group *group); +extern struct iommu_group *iommu_group_alloc(void); +extern void *iommu_group_get_iommudata(struct iommu_group *group); +extern void iommu_group_set_iommudata(struct iommu_group *group, + void *iommu_data, + void (*release)(void *iommu_data)); +extern int iommu_group_set_name(struct iommu_group *group, const char *name); +extern int iommu_group_add_device(struct iommu_group *group, + struct device *dev); +extern void iommu_group_remove_device(struct device *dev); +extern int iommu_group_for_each_dev(struct iommu_group *group, void *data, + int (*fn)(struct device *, void *)); +extern struct iommu_group *iommu_group_get(struct device *dev); +extern void iommu_group_put(struct iommu_group *group); +extern int iommu_group_register_notifier(struct iommu_group *group, + struct notifier_block *nb); +extern int iommu_group_unregister_notifier(struct iommu_group *group, + struct notifier_block *nb); +extern int iommu_group_id(struct iommu_group *group); /** * report_iommu_fault() - report about an IOMMU fault to the IOMMU framework @@ -142,6 +175,7 @@ static inline int report_iommu_fault(struct iommu_domain *domain, #else /* CONFIG_IOMMU_API */ struct iommu_ops {}; +struct iommu_group {}; static inline bool iommu_present(struct bus_type *bus) { @@ -197,11 +231,75 @@ static inline void iommu_set_fault_handler(struct iommu_domain *domain, { } -static inline int iommu_device_group(struct device *dev, unsigned int *groupid) +int iommu_attach_group(struct iommu_domain *domain, struct iommu_group *group) +{ + return -ENODEV; +} + +void iommu_detach_group(struct iommu_domain *domain, struct iommu_group *group) +{ +} + +struct iommu_group *iommu_group_alloc(void) +{ + return ERR_PTR(-ENODEV); +} + +void *iommu_group_get_iommudata(struct iommu_group *group) +{ + return NULL; +} + +void iommu_group_set_iommudata(struct iommu_group *group, void *iommu_data, + void (*release)(void *iommu_data)) +{ +} + +int iommu_group_set_name(struct iommu_group *group, const char *name) +{ + return -ENODEV; +} + +int iommu_group_add_device(struct iommu_group *group, struct device *dev) +{ + return -ENODEV; +} + +void iommu_group_remove_device(struct device *dev) +{ +} + +int iommu_group_for_each_dev(struct iommu_group *group, void *data, + int (*fn)(struct device *, void *)) +{ + return -ENODEV; +} + +struct iommu_group *iommu_group_get(struct device *dev) +{ + return NULL; +} + +void iommu_group_put(struct iommu_group *group) +{ +} + +int iommu_group_register_notifier(struct iommu_group *group, + struct notifier_block *nb) { return -ENODEV; } +int iommu_group_unregister_notifier(struct iommu_group *group, + struct notifier_block *nb) +{ + return 0; +} + +int iommu_group_id(struct iommu_group *group) +{ + return -ENODEV; +} #endif /* CONFIG_IOMMU_API */ #endif /* __LINUX_IOMMU_H */ -- cgit v1.2.3 From 9dcd61303af862c279df86aa97fde7ce371be774 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Wed, 30 May 2012 14:19:07 -0600 Subject: amd_iommu: Support IOMMU groups Add IOMMU group support to AMD-Vi device init and uninit code. Existing notifiers make sure this gets called for each device. Signed-off-by: Alex Williamson Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu.c | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) (limited to 'drivers/iommu') diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 55283d6291c8..60ea92065d31 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -256,9 +256,11 @@ static bool check_device(struct device *dev) static int iommu_init_device(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); + struct pci_dev *dma_pdev, *pdev = to_pci_dev(dev); struct iommu_dev_data *dev_data; + struct iommu_group *group; u16 alias; + int ret; if (dev->archdata.iommu) return 0; @@ -279,8 +281,26 @@ static int iommu_init_device(struct device *dev) return -ENOTSUPP; } dev_data->alias_data = alias_data; + + dma_pdev = pci_get_bus_and_slot(alias >> 8, alias & 0xff); + } else + dma_pdev = pci_dev_get(pdev); + + group = iommu_group_get(&dma_pdev->dev); + pci_dev_put(dma_pdev); + if (!group) { + group = iommu_group_alloc(); + if (IS_ERR(group)) + return PTR_ERR(group); } + ret = iommu_group_add_device(group, dev); + + iommu_group_put(group); + + if (ret) + return ret; + if (pci_iommuv2_capable(pdev)) { struct amd_iommu *iommu; @@ -309,6 +329,8 @@ static void iommu_ignore_device(struct device *dev) static void iommu_uninit_device(struct device *dev) { + iommu_group_remove_device(dev); + /* * Nothing to do here - we keep dev_data around for unplugged devices * and reuse it when the device is re-plugged - not doing so would -- cgit v1.2.3 From abdfdde2534c48d7a761fc437ad3d840a5947dbc Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Wed, 30 May 2012 14:19:19 -0600 Subject: intel-iommu: Support IOMMU groups Add IOMMU group support to Intel VT-d code. This driver sets up devices ondemand, so make use of the add_device/remove_device callbacks in IOMMU API to manage setting up the groups. Signed-off-by: Alex Williamson Signed-off-by: Joerg Roedel --- drivers/iommu/intel-iommu.c | 43 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) (limited to 'drivers/iommu') diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index c62f2df25221..4a434528cd1c 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -4090,6 +4090,47 @@ static int intel_iommu_domain_has_cap(struct iommu_domain *domain, return 0; } +static int intel_iommu_add_device(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct pci_dev *bridge, *dma_pdev; + struct iommu_group *group; + int ret; + + if (!device_to_iommu(pci_domain_nr(pdev->bus), + pdev->bus->number, pdev->devfn)) + return -ENODEV; + + bridge = pci_find_upstream_pcie_bridge(pdev); + if (bridge) { + if (pci_is_pcie(bridge)) + dma_pdev = pci_get_domain_bus_and_slot( + pci_domain_nr(pdev->bus), + bridge->subordinate->number, 0); + else + dma_pdev = pci_dev_get(bridge); + } else + dma_pdev = pci_dev_get(pdev); + + group = iommu_group_get(&dma_pdev->dev); + pci_dev_put(dma_pdev); + if (!group) { + group = iommu_group_alloc(); + if (IS_ERR(group)) + return PTR_ERR(group); + } + + ret = iommu_group_add_device(group, dev); + + iommu_group_put(group); + return ret; +} + +static void intel_iommu_remove_device(struct device *dev) +{ + iommu_group_remove_device(dev); +} + static struct iommu_ops intel_iommu_ops = { .domain_init = intel_iommu_domain_init, .domain_destroy = intel_iommu_domain_destroy, @@ -4099,6 +4140,8 @@ static struct iommu_ops intel_iommu_ops = { .unmap = intel_iommu_unmap, .iova_to_phys = intel_iommu_iova_to_phys, .domain_has_cap = intel_iommu_domain_has_cap, + .add_device = intel_iommu_add_device, + .remove_device = intel_iommu_remove_device, .pgsize_bitmap = INTEL_IOMMU_PGSIZES, }; -- cgit v1.2.3 From 664b600331128146d8ddd3e004defe23ba5c47dc Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Wed, 30 May 2012 14:19:31 -0600 Subject: amd_iommu: Make use of DMA quirks and ACS checks in IOMMU groups Work around broken devices and adhere to ACS support when determining IOMMU grouping. Signed-off-by: Alex Williamson Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu.c | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'drivers/iommu') diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 60ea92065d31..49172393d6ec 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -254,6 +254,14 @@ static bool check_device(struct device *dev) return true; } +static void swap_pci_ref(struct pci_dev **from, struct pci_dev *to) +{ + pci_dev_put(*from); + *from = to; +} + +#define REQ_ACS_FLAGS (PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF) + static int iommu_init_device(struct device *dev) { struct pci_dev *dma_pdev, *pdev = to_pci_dev(dev); @@ -286,6 +294,23 @@ static int iommu_init_device(struct device *dev) } else dma_pdev = pci_dev_get(pdev); + swap_pci_ref(&dma_pdev, pci_get_dma_source(dma_pdev)); + + if (dma_pdev->multifunction && + !pci_acs_enabled(dma_pdev, REQ_ACS_FLAGS)) + swap_pci_ref(&dma_pdev, + pci_get_slot(dma_pdev->bus, + PCI_DEVFN(PCI_SLOT(dma_pdev->devfn), + 0))); + + while (!pci_is_root_bus(dma_pdev->bus)) { + if (pci_acs_path_enabled(dma_pdev->bus->self, + NULL, REQ_ACS_FLAGS)) + break; + + swap_pci_ref(&dma_pdev, pci_dev_get(dma_pdev->bus->self)); + } + group = iommu_group_get(&dma_pdev->dev); pci_dev_put(dma_pdev); if (!group) { -- cgit v1.2.3 From 783f157bc5a7fa30ee17b4099b27146bd1b68af4 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Wed, 30 May 2012 14:19:43 -0600 Subject: intel-iommu: Make use of DMA quirks and ACS checks in IOMMU groups Work around broken devices and adhere to ACS support when determining IOMMU grouping. Signed-off-by: Alex Williamson Signed-off-by: Joerg Roedel --- drivers/iommu/intel-iommu.c | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'drivers/iommu') diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 4a434528cd1c..ebf2b310cdde 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -4090,6 +4090,14 @@ static int intel_iommu_domain_has_cap(struct iommu_domain *domain, return 0; } +static void swap_pci_ref(struct pci_dev **from, struct pci_dev *to) +{ + pci_dev_put(*from); + *from = to; +} + +#define REQ_ACS_FLAGS (PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF) + static int intel_iommu_add_device(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); @@ -4112,6 +4120,23 @@ static int intel_iommu_add_device(struct device *dev) } else dma_pdev = pci_dev_get(pdev); + swap_pci_ref(&dma_pdev, pci_get_dma_source(dma_pdev)); + + if (dma_pdev->multifunction && + !pci_acs_enabled(dma_pdev, REQ_ACS_FLAGS)) + swap_pci_ref(&dma_pdev, + pci_get_slot(dma_pdev->bus, + PCI_DEVFN(PCI_SLOT(dma_pdev->devfn), + 0))); + + while (!pci_is_root_bus(dma_pdev->bus)) { + if (pci_acs_path_enabled(dma_pdev->bus->self, + NULL, REQ_ACS_FLAGS)) + break; + + swap_pci_ref(&dma_pdev, pci_dev_get(dma_pdev->bus->self)); + } + group = iommu_group_get(&dma_pdev->dev); pci_dev_put(dma_pdev); if (!group) { -- cgit v1.2.3 From 4e0ee78f2af96676c9dca898c13250f62c513058 Mon Sep 17 00:00:00 2001 From: Hiroshi Doyu Date: Mon, 25 Jun 2012 14:23:54 +0300 Subject: iommu: Add DMA window parser, of_get_dma_window() This code was based on: "arch/microblaze/kernel/prom_parse.c" "arch/powerpc/kernel/prom_parse.c" Can replace "of_parse_dma_window()" in the above. This supports different formats flexibly. "prefix" can be configured if any. "busno" and "index" are optionally specified. Set NULL and 0 if not used. Signed-off-by: Hiroshi DOYU Acked-by: Stephen Warren Signed-off-by: Joerg Roedel --- drivers/iommu/Kconfig | 4 +++ drivers/iommu/Makefile | 1 + drivers/iommu/of_iommu.c | 90 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/of_iommu.h | 21 +++++++++++ 4 files changed, 116 insertions(+) create mode 100644 drivers/iommu/of_iommu.c create mode 100644 include/linux/of_iommu.h (limited to 'drivers/iommu') diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index 340893727538..4826af62a9de 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -13,6 +13,10 @@ menuconfig IOMMU_SUPPORT if IOMMU_SUPPORT +config OF_IOMMU + def_bool y + depends on OF + # MSM IOMMU support config MSM_IOMMU bool "MSM IOMMU Support" diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile index 76e54ef796de..14a4d5fc94fa 100644 --- a/drivers/iommu/Makefile +++ b/drivers/iommu/Makefile @@ -1,4 +1,5 @@ obj-$(CONFIG_IOMMU_API) += iommu.o +obj-$(CONFIG_OF_IOMMU) += of_iommu.o obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o msm_iommu_dev.o obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o obj-$(CONFIG_AMD_IOMMU_V2) += amd_iommu_v2.o diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c new file mode 100644 index 000000000000..ee249bc959f8 --- /dev/null +++ b/drivers/iommu/of_iommu.c @@ -0,0 +1,90 @@ +/* + * OF helpers for IOMMU + * + * Copyright (c) 2012, NVIDIA CORPORATION. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + */ + +#include +#include +#include + +/** + * of_get_dma_window - Parse *dma-window property and returns 0 if found. + * + * @dn: device node + * @prefix: prefix for property name if any + * @index: index to start to parse + * @busno: Returns busno if supported. Otherwise pass NULL + * @addr: Returns address that DMA starts + * @size: Returns the range that DMA can handle + * + * This supports different formats flexibly. "prefix" can be + * configured if any. "busno" and "index" are optionally + * specified. Set 0(or NULL) if not used. + */ +int of_get_dma_window(struct device_node *dn, const char *prefix, int index, + unsigned long *busno, dma_addr_t *addr, size_t *size) +{ + const __be32 *dma_window, *end; + int bytes, cur_index = 0; + char propname[NAME_MAX], addrname[NAME_MAX], sizename[NAME_MAX]; + + if (!dn || !addr || !size) + return -EINVAL; + + if (!prefix) + prefix = ""; + + snprintf(propname, sizeof(propname), "%sdma-window", prefix); + snprintf(addrname, sizeof(addrname), "%s#dma-address-cells", prefix); + snprintf(sizename, sizeof(sizename), "%s#dma-size-cells", prefix); + + dma_window = of_get_property(dn, propname, &bytes); + if (!dma_window) + return -ENODEV; + end = dma_window + bytes / sizeof(*dma_window); + + while (dma_window < end) { + u32 cells; + const void *prop; + + /* busno is one cell if supported */ + if (busno) + *busno = be32_to_cpup(dma_window++); + + prop = of_get_property(dn, addrname, NULL); + if (!prop) + prop = of_get_property(dn, "#address-cells", NULL); + + cells = prop ? be32_to_cpup(prop) : of_n_addr_cells(dn); + if (!cells) + return -EINVAL; + *addr = of_read_number(dma_window, cells); + dma_window += cells; + + prop = of_get_property(dn, sizename, NULL); + cells = prop ? be32_to_cpup(prop) : of_n_size_cells(dn); + if (!cells) + return -EINVAL; + *size = of_read_number(dma_window, cells); + dma_window += cells; + + if (cur_index++ == index) + break; + } + return 0; +} +EXPORT_SYMBOL_GPL(of_get_dma_window); diff --git a/include/linux/of_iommu.h b/include/linux/of_iommu.h new file mode 100644 index 000000000000..51a560f34bca --- /dev/null +++ b/include/linux/of_iommu.h @@ -0,0 +1,21 @@ +#ifndef __OF_IOMMU_H +#define __OF_IOMMU_H + +#ifdef CONFIG_OF_IOMMU + +extern int of_get_dma_window(struct device_node *dn, const char *prefix, + int index, unsigned long *busno, dma_addr_t *addr, + size_t *size); + +#else + +static inline int of_get_dma_window(struct device_node *dn, const char *prefix, + int index, unsigned long *busno, dma_addr_t *addr, + size_t *size) +{ + return -EINVAL; +} + +#endif /* CONFIG_OF_IOMMU */ + +#endif /* __OF_IOMMU_H */ -- cgit v1.2.3 From 0760e8faa960f8ee991fa4acb802db4e20661281 Mon Sep 17 00:00:00 2001 From: Hiroshi Doyu Date: Mon, 25 Jun 2012 14:23:55 +0300 Subject: iommu/tegra: smmu: Add device tree support for SMMU The necessary info is expected to pass from DT. For more precise resource reservation, there shouldn't be any overlapping of register range between SMMU and MC. SMMU register offset needs to be calculated correctly, based on its register bank. Signed-off-by: Hiroshi DOYU Acked-by: Stephen Warren Acked-by: Grant Likely Signed-off-by: Joerg Roedel --- .../bindings/iommu/nvidia,tegra30-smmu.txt | 21 +++ drivers/iommu/Kconfig | 2 +- drivers/iommu/tegra-smmu.c | 149 +++++++++++++-------- 3 files changed, 117 insertions(+), 55 deletions(-) create mode 100644 Documentation/devicetree/bindings/iommu/nvidia,tegra30-smmu.txt (limited to 'drivers/iommu') diff --git a/Documentation/devicetree/bindings/iommu/nvidia,tegra30-smmu.txt b/Documentation/devicetree/bindings/iommu/nvidia,tegra30-smmu.txt new file mode 100644 index 000000000000..89fb5434b730 --- /dev/null +++ b/Documentation/devicetree/bindings/iommu/nvidia,tegra30-smmu.txt @@ -0,0 +1,21 @@ +NVIDIA Tegra 30 IOMMU H/W, SMMU (System Memory Management Unit) + +Required properties: +- compatible : "nvidia,tegra30-smmu" +- reg : Should contain 3 register banks(address and length) for each + of the SMMU register blocks. +- interrupts : Should contain MC General interrupt. +- nvidia,#asids : # of ASIDs +- dma-window : IOVA start address and length. +- nvidia,ahb : phandle to the ahb bus connected to SMMU. + +Example: + smmu { + compatible = "nvidia,tegra30-smmu"; + reg = <0x7000f010 0x02c + 0x7000f1f0 0x010 + 0x7000f228 0x05c>; + nvidia,#asids = <4>; /* # of ASIDs */ + dma-window = <0 0x40000000>; /* IOVA start & length */ + nvidia,ahb = <&ahb>; + }; diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index 4826af62a9de..9f69b561f5db 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -158,7 +158,7 @@ config TEGRA_IOMMU_GART config TEGRA_IOMMU_SMMU bool "Tegra SMMU IOMMU Support" - depends on ARCH_TEGRA_3x_SOC + depends on ARCH_TEGRA_3x_SOC && TEGRA_AHB select IOMMU_API help Enables support for remapping discontiguous physical memory diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index ecd679043d77..2c92b8c3514e 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -30,12 +30,15 @@ #include #include #include +#include +#include #include #include #include #include +#include /* bitmap of the page sizes currently supported */ #define SMMU_IOMMU_PGSIZES (SZ_4K) @@ -111,12 +114,6 @@ #define SMMU_PDE_NEXT_SHIFT 28 -/* AHB Arbiter Registers */ -#define AHB_XBAR_CTRL 0xe0 -#define AHB_XBAR_CTRL_SMMU_INIT_DONE_DONE 1 -#define AHB_XBAR_CTRL_SMMU_INIT_DONE_SHIFT 17 - -#define SMMU_NUM_ASIDS 4 #define SMMU_TLB_FLUSH_VA_SECTION__MASK 0xffc00000 #define SMMU_TLB_FLUSH_VA_SECTION__SHIFT 12 /* right shift */ #define SMMU_TLB_FLUSH_VA_GROUP__MASK 0xffffc000 @@ -136,6 +133,7 @@ #define SMMU_PAGE_SHIFT 12 #define SMMU_PAGE_SIZE (1 << SMMU_PAGE_SHIFT) +#define SMMU_PAGE_MASK ((1 << SMMU_PAGE_SHIFT) - 1) #define SMMU_PDIR_COUNT 1024 #define SMMU_PDIR_SIZE (sizeof(unsigned long) * SMMU_PDIR_COUNT) @@ -177,6 +175,8 @@ #define SMMU_ASID_DISABLE 0 #define SMMU_ASID_ASID(n) ((n) & ~SMMU_ASID_ENABLE(0)) +#define NUM_SMMU_REG_BANKS 3 + #define smmu_client_enable_hwgrp(c, m) smmu_client_set_hwgrp(c, m, 1) #define smmu_client_disable_hwgrp(c) smmu_client_set_hwgrp(c, 0, 0) #define __smmu_client_enable_hwgrp(c, m) __smmu_client_set_hwgrp(c, m, 1) @@ -235,7 +235,7 @@ struct smmu_as { * Per SMMU device - IOMMU device */ struct smmu_device { - void __iomem *regs, *regs_ahbarb; + void __iomem *regs[NUM_SMMU_REG_BANKS]; unsigned long iovmm_base; /* remappable base address */ unsigned long page_count; /* total remappable size */ spinlock_t lock; @@ -252,29 +252,47 @@ struct smmu_device { unsigned long translation_enable_1; unsigned long translation_enable_2; unsigned long asid_security; + + struct device_node *ahb; }; static struct smmu_device *smmu_handle; /* unique for a system */ /* - * SMMU/AHB register accessors + * SMMU register accessors */ static inline u32 smmu_read(struct smmu_device *smmu, size_t offs) { - return readl(smmu->regs + offs); -} -static inline void smmu_write(struct smmu_device *smmu, u32 val, size_t offs) -{ - writel(val, smmu->regs + offs); + BUG_ON(offs < 0x10); + if (offs < 0x3c) + return readl(smmu->regs[0] + offs - 0x10); + BUG_ON(offs < 0x1f0); + if (offs < 0x200) + return readl(smmu->regs[1] + offs - 0x1f0); + BUG_ON(offs < 0x228); + if (offs < 0x284) + return readl(smmu->regs[2] + offs - 0x228); + BUG(); } -static inline u32 ahb_read(struct smmu_device *smmu, size_t offs) -{ - return readl(smmu->regs_ahbarb + offs); -} -static inline void ahb_write(struct smmu_device *smmu, u32 val, size_t offs) +static inline void smmu_write(struct smmu_device *smmu, u32 val, size_t offs) { - writel(val, smmu->regs_ahbarb + offs); + BUG_ON(offs < 0x10); + if (offs < 0x3c) { + writel(val, smmu->regs[0] + offs - 0x10); + return; + } + BUG_ON(offs < 0x1f0); + if (offs < 0x200) { + writel(val, smmu->regs[1] + offs - 0x1f0); + return; + } + BUG_ON(offs < 0x228); + if (offs < 0x284) { + writel(val, smmu->regs[2] + offs - 0x228); + return; + } + BUG(); } #define VA_PAGE_TO_PA(va, page) \ @@ -370,7 +388,7 @@ static void smmu_flush_regs(struct smmu_device *smmu, int enable) FLUSH_SMMU_REGS(smmu); } -static void smmu_setup_regs(struct smmu_device *smmu) +static int smmu_setup_regs(struct smmu_device *smmu) { int i; u32 val; @@ -398,10 +416,7 @@ static void smmu_setup_regs(struct smmu_device *smmu) smmu_flush_regs(smmu, 1); - val = ahb_read(smmu, AHB_XBAR_CTRL); - val |= AHB_XBAR_CTRL_SMMU_INIT_DONE_DONE << - AHB_XBAR_CTRL_SMMU_INIT_DONE_SHIFT; - ahb_write(smmu, val, AHB_XBAR_CTRL); + return tegra_ahb_enable_smmu(smmu->ahb); } static void flush_ptc_and_tlb(struct smmu_device *smmu, @@ -873,52 +888,72 @@ static int tegra_smmu_resume(struct device *dev) { struct smmu_device *smmu = dev_get_drvdata(dev); unsigned long flags; + int err; spin_lock_irqsave(&smmu->lock, flags); - smmu_setup_regs(smmu); + err = smmu_setup_regs(smmu); spin_unlock_irqrestore(&smmu->lock, flags); - return 0; + return err; } static int tegra_smmu_probe(struct platform_device *pdev) { struct smmu_device *smmu; - struct resource *regs, *regs2, *window; struct device *dev = &pdev->dev; - int i, err = 0; + int i, asids, err = 0; + dma_addr_t base; + size_t size; + const void *prop; if (smmu_handle) return -EIO; BUILD_BUG_ON(PAGE_SHIFT != SMMU_PAGE_SHIFT); - regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); - regs2 = platform_get_resource(pdev, IORESOURCE_MEM, 1); - window = platform_get_resource(pdev, IORESOURCE_MEM, 2); - if (!regs || !regs2 || !window) { - dev_err(dev, "No SMMU resources\n"); - return -ENODEV; - } - smmu = devm_kzalloc(dev, sizeof(*smmu), GFP_KERNEL); if (!smmu) { dev_err(dev, "failed to allocate smmu_device\n"); return -ENOMEM; } - smmu->dev = dev; - smmu->num_as = SMMU_NUM_ASIDS; - smmu->iovmm_base = (unsigned long)window->start; - smmu->page_count = resource_size(window) >> SMMU_PAGE_SHIFT; - smmu->regs = devm_ioremap(dev, regs->start, resource_size(regs)); - smmu->regs_ahbarb = devm_ioremap(dev, regs2->start, - resource_size(regs2)); - if (!smmu->regs || !smmu->regs_ahbarb) { - dev_err(dev, "failed to remap SMMU registers\n"); - err = -ENXIO; - goto fail; + for (i = 0; i < ARRAY_SIZE(smmu->regs); i++) { + struct resource *res; + + res = platform_get_resource(pdev, IORESOURCE_MEM, i); + if (!res) + return -ENODEV; + smmu->regs[i] = devm_request_and_ioremap(&pdev->dev, res); + if (!smmu->regs[i]) + return -EBUSY; } + err = of_get_dma_window(dev->of_node, NULL, 0, NULL, &base, &size); + if (err) + return -ENODEV; + + if (size & SMMU_PAGE_MASK) + return -EINVAL; + + size >>= SMMU_PAGE_SHIFT; + if (!size) + return -EINVAL; + + prop = of_get_property(dev->of_node, "nvidia,#asids", NULL); + if (!prop) + return -ENODEV; + asids = be32_to_cpup(prop); + if (!asids) + return -ENODEV; + + smmu->ahb = of_parse_phandle(dev->of_node, "nvidia,ahb", 0); + if (!smmu->ahb) + return -ENODEV; + + smmu->dev = dev; + smmu->num_as = asids; + smmu->iovmm_base = base; + smmu->page_count = size; + smmu->translation_enable_0 = ~0; smmu->translation_enable_1 = ~0; smmu->translation_enable_2 = ~0; @@ -945,7 +980,9 @@ static int tegra_smmu_probe(struct platform_device *pdev) INIT_LIST_HEAD(&as->client); } spin_lock_init(&smmu->lock); - smmu_setup_regs(smmu); + err = smmu_setup_regs(smmu); + if (err) + goto fail; platform_set_drvdata(pdev, smmu); smmu->avp_vector_page = alloc_page(GFP_KERNEL); @@ -958,10 +995,6 @@ static int tegra_smmu_probe(struct platform_device *pdev) fail: if (smmu->avp_vector_page) __free_page(smmu->avp_vector_page); - if (smmu->regs) - devm_iounmap(dev, smmu->regs); - if (smmu->regs_ahbarb) - devm_iounmap(dev, smmu->regs_ahbarb); if (smmu && smmu->as) { for (i = 0; i < smmu->num_as; i++) { if (smmu->as[i].pdir_page) { @@ -993,8 +1026,6 @@ static int tegra_smmu_remove(struct platform_device *pdev) __free_page(smmu->avp_vector_page); if (smmu->regs) devm_iounmap(dev, smmu->regs); - if (smmu->regs_ahbarb) - devm_iounmap(dev, smmu->regs_ahbarb); devm_kfree(dev, smmu); smmu_handle = NULL; return 0; @@ -1005,6 +1036,14 @@ const struct dev_pm_ops tegra_smmu_pm_ops = { .resume = tegra_smmu_resume, }; +#ifdef CONFIG_OF +static struct of_device_id tegra_smmu_of_match[] __devinitdata = { + { .compatible = "nvidia,tegra30-smmu", }, + { }, +}; +MODULE_DEVICE_TABLE(of, tegra_smmu_of_match); +#endif + static struct platform_driver tegra_smmu_driver = { .probe = tegra_smmu_probe, .remove = tegra_smmu_remove, @@ -1012,6 +1051,7 @@ static struct platform_driver tegra_smmu_driver = { .owner = THIS_MODULE, .name = "tegra-smmu", .pm = &tegra_smmu_pm_ops, + .of_match_table = of_match_ptr(tegra_smmu_of_match), }, }; @@ -1031,4 +1071,5 @@ module_exit(tegra_smmu_exit); MODULE_DESCRIPTION("IOMMU API for SMMU in Tegra30"); MODULE_AUTHOR("Hiroshi DOYU "); +MODULE_ALIAS("platform:tegra-smmu"); MODULE_LICENSE("GPL v2"); -- cgit v1.2.3 From a3b24915456b63c9002e94152e122b07de5566f2 Mon Sep 17 00:00:00 2001 From: Hiroshi Doyu Date: Mon, 25 Jun 2012 14:23:56 +0300 Subject: iommu/tegra: smmu: Simplify allocation at once To simplify the code, alloc necessary data at once. Signed-off-by: Hiroshi DOYU Acked-by: Stephen Warren Signed-off-by: Joerg Roedel --- drivers/iommu/tegra-smmu.c | 29 +++++++++-------------------- 1 file changed, 9 insertions(+), 20 deletions(-) (limited to 'drivers/iommu') diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index 2c92b8c3514e..98fcc7268eaf 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -241,8 +241,6 @@ struct smmu_device { spinlock_t lock; char *name; struct device *dev; - int num_as; - struct smmu_as *as; /* Run-time allocated array */ struct page *avp_vector_page; /* dummy page shared by all AS's */ /* @@ -254,6 +252,9 @@ struct smmu_device { unsigned long asid_security; struct device_node *ahb; + + int num_as; + struct smmu_as as[0]; /* Run-time allocated array */ }; static struct smmu_device *smmu_handle; /* unique for a system */ @@ -902,15 +903,18 @@ static int tegra_smmu_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; int i, asids, err = 0; dma_addr_t base; - size_t size; - const void *prop; + size_t bytes, size; if (smmu_handle) return -EIO; BUILD_BUG_ON(PAGE_SHIFT != SMMU_PAGE_SHIFT); - smmu = devm_kzalloc(dev, sizeof(*smmu), GFP_KERNEL); + if (of_property_read_u32(dev->of_node, "nvidia,#asids", &asids)) + return -ENODEV; + + bytes = sizeof(*smmu) + asids * sizeof(*smmu->as); + smmu = devm_kzalloc(dev, bytes, GFP_KERNEL); if (!smmu) { dev_err(dev, "failed to allocate smmu_device\n"); return -ENOMEM; @@ -938,13 +942,6 @@ static int tegra_smmu_probe(struct platform_device *pdev) if (!size) return -EINVAL; - prop = of_get_property(dev->of_node, "nvidia,#asids", NULL); - if (!prop) - return -ENODEV; - asids = be32_to_cpup(prop); - if (!asids) - return -ENODEV; - smmu->ahb = of_parse_phandle(dev->of_node, "nvidia,ahb", 0); if (!smmu->ahb) return -ENODEV; @@ -959,14 +956,6 @@ static int tegra_smmu_probe(struct platform_device *pdev) smmu->translation_enable_2 = ~0; smmu->asid_security = 0; - smmu->as = devm_kzalloc(dev, - sizeof(smmu->as[0]) * smmu->num_as, GFP_KERNEL); - if (!smmu->as) { - dev_err(dev, "failed to allocate smmu_as\n"); - err = -ENOMEM; - goto fail; - } - for (i = 0; i < smmu->num_as; i++) { struct smmu_as *as = &smmu->as[i]; -- cgit v1.2.3 From 0547c2f56e6e4795d5366ba3b8483b668920a947 Mon Sep 17 00:00:00 2001 From: Hiroshi Doyu Date: Mon, 25 Jun 2012 14:23:57 +0300 Subject: iommu/tegra: smmu: Remove unnecessary cleanups with devm_*() Remove unnecessary cleanup procedures with devm_*() functions. Signed-off-by: Hiroshi DOYU Acked-by: Stephen Warren Signed-off-by: Joerg Roedel --- drivers/iommu/tegra-smmu.c | 37 ++++++------------------------------- 1 file changed, 6 insertions(+), 31 deletions(-) (limited to 'drivers/iommu') diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index 98fcc7268eaf..cc6aba45e49a 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -971,51 +971,26 @@ static int tegra_smmu_probe(struct platform_device *pdev) spin_lock_init(&smmu->lock); err = smmu_setup_regs(smmu); if (err) - goto fail; + return err; platform_set_drvdata(pdev, smmu); smmu->avp_vector_page = alloc_page(GFP_KERNEL); if (!smmu->avp_vector_page) - goto fail; + return -ENOMEM; smmu_handle = smmu; return 0; - -fail: - if (smmu->avp_vector_page) - __free_page(smmu->avp_vector_page); - if (smmu && smmu->as) { - for (i = 0; i < smmu->num_as; i++) { - if (smmu->as[i].pdir_page) { - ClearPageReserved(smmu->as[i].pdir_page); - __free_page(smmu->as[i].pdir_page); - } - } - devm_kfree(dev, smmu->as); - } - devm_kfree(dev, smmu); - return err; } static int tegra_smmu_remove(struct platform_device *pdev) { struct smmu_device *smmu = platform_get_drvdata(pdev); - struct device *dev = smmu->dev; + int i; smmu_write(smmu, SMMU_CONFIG_DISABLE, SMMU_CONFIG); - platform_set_drvdata(pdev, NULL); - if (smmu->as) { - int i; - - for (i = 0; i < smmu->num_as; i++) - free_pdir(&smmu->as[i]); - devm_kfree(dev, smmu->as); - } - if (smmu->avp_vector_page) - __free_page(smmu->avp_vector_page); - if (smmu->regs) - devm_iounmap(dev, smmu->regs); - devm_kfree(dev, smmu); + for (i = 0; i < smmu->num_as; i++) + free_pdir(&smmu->as[i]); + __free_page(smmu->avp_vector_page); smmu_handle = NULL; return 0; } -- cgit v1.2.3 From ff7636292aac6cae2ee3a553d5424ea49c8a8263 Mon Sep 17 00:00:00 2001 From: Hiroshi Doyu Date: Mon, 25 Jun 2012 14:23:58 +0300 Subject: iommu/tegra: smmu: Fix uninitialized var warning For the compiler warning, uninitizlized var when getting value by a pointer. Signed-off-by: Hiroshi DOYU Signed-off-by: Joerg Roedel --- drivers/iommu/tegra-smmu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/iommu') diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index cc6aba45e49a..becfc614cf94 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -902,8 +902,8 @@ static int tegra_smmu_probe(struct platform_device *pdev) struct smmu_device *smmu; struct device *dev = &pdev->dev; int i, asids, err = 0; - dma_addr_t base; - size_t bytes, size; + dma_addr_t uninitialized_var(base); + size_t bytes, uninitialized_var(size); if (smmu_handle) return -EIO; -- cgit v1.2.3 From 8f53dc724a83a0082184fa27df80c25c7df47340 Mon Sep 17 00:00:00 2001 From: Hiroshi DOYU Date: Wed, 27 Jun 2012 12:54:01 +0300 Subject: iommu/tegra: smmu: Fix unsleepable memory allocation allo_pdir() is called in smmu_iommu_domain_init() with spin_lock held. memory allocations in it have to be atomic/unsleepable. Signed-off-by: Hiroshi DOYU Reported-by: Chris Wright Acked-by: Chris Wright Cc: stable@vger.kernel.org Signed-off-by: Joerg Roedel --- drivers/iommu/tegra-smmu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/iommu') diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index ecd679043d77..3f3d09d560ea 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -550,13 +550,13 @@ static int alloc_pdir(struct smmu_as *as) return 0; as->pte_count = devm_kzalloc(smmu->dev, - sizeof(as->pte_count[0]) * SMMU_PDIR_COUNT, GFP_KERNEL); + sizeof(as->pte_count[0]) * SMMU_PDIR_COUNT, GFP_ATOMIC); if (!as->pte_count) { dev_err(smmu->dev, "failed to allocate smmu_device PTE cunters\n"); return -ENOMEM; } - as->pdir_page = alloc_page(GFP_KERNEL | __GFP_DMA); + as->pdir_page = alloc_page(GFP_ATOMIC | __GFP_DMA); if (!as->pdir_page) { dev_err(smmu->dev, "failed to allocate smmu_device page directory\n"); -- cgit v1.2.3 From 3775d4818d72081e2afa2aed2442a2b9ecfc5eab Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 27 Jun 2012 12:09:18 +0300 Subject: iommu/amd: fix type bug in flush code write_file_bool() modifies 32 bits of data, so "amd_iommu_unmap_flush" needs to be 32 bits as well or we'll corrupt memory. Fortunately it looks like the data is aligned with a gap after the declaration so this is harmless in production. Signed-off-by: Dan Carpenter Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu.c | 2 +- drivers/iommu/amd_iommu_init.c | 2 +- drivers/iommu/amd_iommu_types.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'drivers/iommu') diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index dfe7d37c82c5..625626391f2d 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -404,7 +404,7 @@ static void amd_iommu_stats_init(void) return; de_fflush = debugfs_create_bool("fullflush", 0444, stats_dir, - (u32 *)&amd_iommu_unmap_flush); + &amd_iommu_unmap_flush); amd_iommu_stats_add(&compl_wait); amd_iommu_stats_add(&cnt_map_single); diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index c04ddca7f12f..a33612f3206f 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -129,7 +129,7 @@ u16 amd_iommu_last_bdf; /* largest PCI device id we have to handle */ LIST_HEAD(amd_iommu_unity_map); /* a list of required unity mappings we find in ACPI */ -bool amd_iommu_unmap_flush; /* if true, flush on every unmap */ +u32 amd_iommu_unmap_flush; /* if true, flush on every unmap */ LIST_HEAD(amd_iommu_list); /* list of all AMD IOMMUs in the system */ diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h index 24355559a2ad..c1b1d489817e 100644 --- a/drivers/iommu/amd_iommu_types.h +++ b/drivers/iommu/amd_iommu_types.h @@ -652,7 +652,7 @@ extern unsigned long *amd_iommu_pd_alloc_bitmap; * If true, the addresses will be flushed on unmap time, not when * they are reused */ -extern bool amd_iommu_unmap_flush; +extern u32 amd_iommu_unmap_flush; /* Smallest number of PASIDs supported by any IOMMU in the system */ extern u32 amd_iommu_max_pasids; -- cgit v1.2.3 From 0cd76dd13bdd2f7f02a2dc931e808e92b191082f Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 26 Jan 2012 19:40:52 +0100 Subject: iommu: Add domain-attribute handlers This patch introduces an extension to the iommu-api to get and set attributes for an iommu_domain. Two functions are introduced for this: * iommu_domain_get_attr() * iommu_domain_set_attr() These functions will be used to make the iommu-api suitable for GART-like IOMMUs and to implement hardware-specifc api-extensions. Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 20 ++++++++++++++++++++ include/linux/iommu.h | 28 +++++++++++++++++++++++++++- 2 files changed, 47 insertions(+), 1 deletion(-) (limited to 'drivers/iommu') diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 8b9ded88e6f5..c39972d8ded3 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -344,3 +344,23 @@ int iommu_device_group(struct device *dev, unsigned int *groupid) return -ENODEV; } EXPORT_SYMBOL_GPL(iommu_device_group); + +int iommu_domain_get_attr(struct iommu_domain *domain, + enum iommu_attr attr, void *data) +{ + if (!domain->ops->domain_get_attr) + return -EINVAL; + + return domain->ops->domain_get_attr(domain, attr, data); +} +EXPORT_SYMBOL_GPL(iommu_domain_get_attr); + +int iommu_domain_set_attr(struct iommu_domain *domain, + enum iommu_attr attr, void *data) +{ + if (!domain->ops->domain_set_attr) + return -EINVAL; + + return domain->ops->domain_set_attr(domain, attr, data); +} +EXPORT_SYMBOL_GPL(iommu_domain_set_attr); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 450293f6d68b..0eef096183e8 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -47,6 +47,10 @@ struct iommu_domain { #define IOMMU_CAP_CACHE_COHERENCY 0x1 #define IOMMU_CAP_INTR_REMAP 0x2 /* isolates device intrs */ +enum iommu_attr { + DOMAIN_ATTR_MAX, +}; + #ifdef CONFIG_IOMMU_API /** @@ -59,7 +63,8 @@ struct iommu_domain { * @unmap: unmap a physically contiguous memory region from an iommu domain * @iova_to_phys: translate iova to physical address * @domain_has_cap: domain capabilities query - * @commit: commit iommu domain + * @domain_get_attr: Query domain attributes + * @domain_set_attr: Change domain attributes * @pgsize_bitmap: bitmap of supported page sizes */ struct iommu_ops { @@ -76,6 +81,10 @@ struct iommu_ops { int (*domain_has_cap)(struct iommu_domain *domain, unsigned long cap); int (*device_group)(struct device *dev, unsigned int *groupid); + int (*domain_get_attr)(struct iommu_domain *domain, + enum iommu_attr attr, void *data); + int (*domain_set_attr)(struct iommu_domain *domain, + enum iommu_attr attr, void *data); unsigned long pgsize_bitmap; }; @@ -99,6 +108,11 @@ extern void iommu_set_fault_handler(struct iommu_domain *domain, iommu_fault_handler_t handler, void *token); extern int iommu_device_group(struct device *dev, unsigned int *groupid); +extern int iommu_domain_get_attr(struct iommu_domain *domain, enum iommu_attr, + void *data); +extern int iommu_domain_set_attr(struct iommu_domain *domain, enum iommu_attr, + void *data); + /** * report_iommu_fault() - report about an IOMMU fault to the IOMMU framework * @domain: the iommu domain where the fault has happened @@ -202,6 +216,18 @@ static inline int iommu_device_group(struct device *dev, unsigned int *groupid) return -ENODEV; } +static inline int iommu_domain_get_attr(struct iommu_domain *domain, + enum iommu_attr attr, void *data) +{ + return -EINVAL; +} + +static inline int iommu_domain_set_attr(struct iommu_domain *domain, + enum iommu_attr attr, void *data) +{ + return -EINVAL; +} + #endif /* CONFIG_IOMMU_API */ #endif /* __LINUX_IOMMU_H */ -- cgit v1.2.3 From 0ff64f80e075ae036a4c80c7d7752b1e07fed792 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 26 Jan 2012 19:40:53 +0100 Subject: iommu/amd: Implement DOMAIN_ATTR_GEOMETRY attribute Implement the attribute itself and add the code for the AMD IOMMU driver. Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu.c | 4 ++++ drivers/iommu/iommu.c | 19 ++++++++++++++++--- include/linux/iommu.h | 8 ++++++++ 3 files changed, 28 insertions(+), 3 deletions(-) (limited to 'drivers/iommu') diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index a2e418cba0ff..259a6beddece 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -3069,6 +3069,10 @@ static int amd_iommu_domain_init(struct iommu_domain *dom) dom->priv = domain; + dom->geometry.aperture_start = 0; + dom->geometry.aperture_end = ~0ULL; + dom->geometry.force_aperture = true; + return 0; out_free: diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index c39972d8ded3..ed5e0a553ca7 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -348,10 +348,23 @@ EXPORT_SYMBOL_GPL(iommu_device_group); int iommu_domain_get_attr(struct iommu_domain *domain, enum iommu_attr attr, void *data) { - if (!domain->ops->domain_get_attr) - return -EINVAL; + struct iommu_domain_geometry *geometry; + int ret = 0; + + switch (attr) { + case DOMAIN_ATTR_GEOMETRY: + geometry = data; + *geometry = domain->geometry; + + break; + default: + if (!domain->ops->domain_get_attr) + return -EINVAL; - return domain->ops->domain_get_attr(domain, attr, data); + ret = domain->ops->domain_get_attr(domain, attr, data); + } + + return ret; } EXPORT_SYMBOL_GPL(iommu_domain_get_attr); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 0eef096183e8..f7df4aa527f3 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -37,11 +37,18 @@ struct iommu_domain; typedef int (*iommu_fault_handler_t)(struct iommu_domain *, struct device *, unsigned long, int, void *); +struct iommu_domain_geometry { + dma_addr_t aperture_start; /* First address that can be mapped */ + dma_addr_t aperture_end; /* Last address that can be mapped */ + bool force_aperture; /* DMA only allowed in mappable range? */ +}; + struct iommu_domain { struct iommu_ops *ops; void *priv; iommu_fault_handler_t handler; void *handler_token; + struct iommu_domain_geometry geometry; }; #define IOMMU_CAP_CACHE_COHERENCY 0x1 @@ -49,6 +56,7 @@ struct iommu_domain { enum iommu_attr { DOMAIN_ATTR_MAX, + DOMAIN_ATTR_GEOMETRY, }; #ifdef CONFIG_IOMMU_API -- cgit v1.2.3 From 8a0e715b73c4a54d6ef294ce314dab22c6b62a10 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 26 Jan 2012 19:40:54 +0100 Subject: iommu/vt-d: Implement DOMAIN_ATTR_GEOMETRY attribute Implement the attribute for the Intel IOMMU driver. Signed-off-by: Joerg Roedel --- drivers/iommu/intel-iommu.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'drivers/iommu') diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index b12af2ff8c54..6cb0791b3264 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -3932,6 +3932,10 @@ static int intel_iommu_domain_init(struct iommu_domain *domain) domain_update_iommu_cap(dmar_domain); domain->priv = dmar_domain; + domain->geometry.aperture_start = 0; + domain->geometry.aperture_end = __DOMAIN_MAX_ADDR(dmar_domain->gaw); + domain->geometry.force_aperture = true; + return 0; } -- cgit v1.2.3 From 2c6edb0cc43688a12571a35728a06e2748d55af3 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 26 Jan 2012 19:40:55 +0100 Subject: iommu/omap: Implement DOMAIN_ATTR_GEOMETRY attribute Implement the attribute for the OMAP IOMMU driver. Signed-off-by: Joerg Roedel --- drivers/iommu/omap-iommu.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'drivers/iommu') diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c index e70ee2b59df9..d0b1234581be 100644 --- a/drivers/iommu/omap-iommu.c +++ b/drivers/iommu/omap-iommu.c @@ -1148,6 +1148,10 @@ static int omap_iommu_domain_init(struct iommu_domain *domain) domain->priv = omap_domain; + domain->geometry.aperture_start = 0; + domain->geometry.aperture_end = (1ULL << 32) - 1; + domain->geometry.force_aperture = true; + return 0; fail_nomem: -- cgit v1.2.3 From 4be6a290b87af9136b482d5c22574f070ffdbdb8 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 26 Jan 2012 19:40:56 +0100 Subject: iommu/msm: Implement DOMAIN_ATTR_GEOMETRY attribute Implement the attribute for the MSM IOMMU driver. Acked-by: David Brown Signed-off-by: Joerg Roedel --- drivers/iommu/msm_iommu.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'drivers/iommu') diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c index cee307e86606..6a8870a31668 100644 --- a/drivers/iommu/msm_iommu.c +++ b/drivers/iommu/msm_iommu.c @@ -226,6 +226,11 @@ static int msm_iommu_domain_init(struct iommu_domain *domain) 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; + return 0; fail_nomem: -- cgit v1.2.3 From 23349902edec4d3d932bca1bb99261477139a36a Mon Sep 17 00:00:00 2001 From: Hiroshi DOYU Date: Thu, 26 Jan 2012 19:40:57 +0100 Subject: iommu/tegra: Implement DOMAIN_ATTR_GEOMETRY attribute Implement the attribute for the Tegra IOMMU drivers. Signed-off-by: Hiroshi DOYU Signed-off-by: Joerg Roedel --- drivers/iommu/tegra-gart.c | 5 +++++ drivers/iommu/tegra-smmu.c | 5 +++++ 2 files changed, 10 insertions(+) (limited to 'drivers/iommu') diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c index 0c0a37792218..c16e8fc8a4bd 100644 --- a/drivers/iommu/tegra-gart.c +++ b/drivers/iommu/tegra-gart.c @@ -165,6 +165,11 @@ static int gart_iommu_attach_dev(struct iommu_domain *domain, 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; diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index ecd679043d77..96e73d56451a 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -807,6 +807,11 @@ found: spin_unlock_irqrestore(&as->lock, flags); domain->priv = as; + domain->geometry.aperture_start = smmu->iovmm_base; + domain->geometry.aperture_end = smmu->iovmm_base + + smmu->page_count * SMMU_PAGE_SIZE - 1; + domain->geometry.force_aperture = true; + dev_dbg(smmu->dev, "smmu_as@%p\n", as); return 0; -- cgit v1.2.3 From 3177bb76a8c510cbc737425a74e777a9aa253065 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 11 Jul 2012 12:41:10 +0200 Subject: iommu/exynos: Implement DOMAIN_ATTR_GEOMETRY attribute Implement the attribute for the Samsung Exynos IOMMU driver. Signed-off-by: Joerg Roedel --- drivers/iommu/exynos-iommu.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'drivers/iommu') diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c index 9a114b9ff170..5c40937e9988 100644 --- a/drivers/iommu/exynos-iommu.c +++ b/drivers/iommu/exynos-iommu.c @@ -732,6 +732,10 @@ static int exynos_iommu_domain_init(struct iommu_domain *domain) spin_lock_init(&priv->pgtablelock); INIT_LIST_HEAD(&priv->clients); + dom->geometry.aperture_start = 0; + dom->geometry.aperture_end = ~0UL; + dom->geometry.force_aperture = true; + domain->priv = priv; return 0; -- cgit v1.2.3 From 0bdbf4ccef4f87016e2fa0c0b34f7a025f364c3d Mon Sep 17 00:00:00 2001 From: Hiroshi DOYU Date: Mon, 2 Jul 2012 14:26:37 +0300 Subject: iommu/tegra: smmu: Remove unnecessary sanity check at alloc_pdir() alloc_pdir() is called with smmu->as[?].pdir_page == NULL. No need to check pdir_page again inside alloc_pdir(). Signed-off-by: Hiroshi DOYU Acked-by: Stephen Warren Signed-off-by: Joerg Roedel --- drivers/iommu/tegra-smmu.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'drivers/iommu') diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index becfc614cf94..68441fcca261 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -562,9 +562,6 @@ static int alloc_pdir(struct smmu_as *as) u32 val; struct smmu_device *smmu = as->smmu; - if (as->pdir_page) - return 0; - as->pte_count = devm_kzalloc(smmu->dev, sizeof(as->pte_count[0]) * SMMU_PDIR_COUNT, GFP_KERNEL); if (!as->pte_count) { -- cgit v1.2.3 From 9e971a03af736acc6f96c200c2626d3bcb3d6927 Mon Sep 17 00:00:00 2001 From: Hiroshi DOYU Date: Mon, 2 Jul 2012 14:26:38 +0300 Subject: iommu/tegra: smmu: Fix unsleepable memory allocation at alloc_pdir() alloc_pdir() is called from smmu_iommu_domain_init() with spin_lock held. memory allocations in alloc_pdir() had to be atomic. Instead of converting into atomic allocation, this patch once releases a lock, does the allocation, holds the lock again and then sees if it's raced or not in order to avoid introducing mutex and preallocation. Signed-off-by: Hiroshi DOYU Reported-by: Chris Wright Cc: Chris Wright Acked-by: Stephen Warren Signed-off-by: Joerg Roedel --- drivers/iommu/tegra-smmu.c | 77 +++++++++++++++++++++++++++------------------- 1 file changed, 45 insertions(+), 32 deletions(-) (limited to 'drivers/iommu') diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index 68441fcca261..68a15a0d5b8a 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -555,28 +555,39 @@ static inline void put_signature(struct smmu_as *as, /* * Caller must lock/unlock as */ -static int alloc_pdir(struct smmu_as *as) +static int alloc_pdir(struct smmu_as *as, unsigned long *flags) { unsigned long *pdir; - int pdn; + int pdn, err = 0; u32 val; struct smmu_device *smmu = as->smmu; + struct page *page; + unsigned int *cnt; - as->pte_count = devm_kzalloc(smmu->dev, - sizeof(as->pte_count[0]) * SMMU_PDIR_COUNT, GFP_KERNEL); - if (!as->pte_count) { - dev_err(smmu->dev, - "failed to allocate smmu_device PTE cunters\n"); - return -ENOMEM; + /* + * do the allocation outside the as->lock + */ + spin_unlock_irqrestore(&as->lock, *flags); + cnt = devm_kzalloc(smmu->dev, + sizeof(cnt[0]) * SMMU_PDIR_COUNT, GFP_KERNEL); + page = alloc_page(GFP_KERNEL | __GFP_DMA); + spin_lock_irqsave(&as->lock, *flags); + + if (as->pdir_page) { + /* We raced, free the redundant */ + err = -EAGAIN; + goto err_out; } - as->pdir_page = alloc_page(GFP_KERNEL | __GFP_DMA); - if (!as->pdir_page) { - dev_err(smmu->dev, - "failed to allocate smmu_device page directory\n"); - devm_kfree(smmu->dev, as->pte_count); - as->pte_count = NULL; - return -ENOMEM; + + if (!page || !cnt) { + dev_err(smmu->dev, "failed to allocate at %s\n", __func__); + err = -ENOMEM; + goto err_out; } + + as->pdir_page = page; + as->pte_count = cnt; + SetPageReserved(as->pdir_page); pdir = page_address(as->pdir_page); @@ -593,6 +604,12 @@ static int alloc_pdir(struct smmu_as *as) FLUSH_SMMU_REGS(as->smmu); return 0; + +err_out: + devm_kfree(smmu->dev, cnt); + if (page) + __free_page(page); + return err; } static void __smmu_iommu_unmap(struct smmu_as *as, dma_addr_t iova) @@ -784,29 +801,29 @@ out: static int smmu_iommu_domain_init(struct iommu_domain *domain) { - int i; + int i, err = -ENODEV; unsigned long flags; struct smmu_as *as; struct smmu_device *smmu = smmu_handle; /* Look for a free AS with lock held */ for (i = 0; i < smmu->num_as; i++) { - struct smmu_as *tmp = &smmu->as[i]; - - spin_lock_irqsave(&tmp->lock, flags); - if (!tmp->pdir_page) { - as = tmp; - goto found; + as = &smmu->as[i]; + spin_lock_irqsave(&as->lock, flags); + if (!as->pdir_page) { + err = alloc_pdir(as, &flags); + if (!err) + goto found; } - spin_unlock_irqrestore(&tmp->lock, flags); + spin_unlock_irqrestore(&as->lock, flags); + if (err != -EAGAIN) + break; } - dev_err(smmu->dev, "no free AS\n"); - return -ENODEV; + if (i == smmu->num_as) + dev_err(smmu->dev, "no free AS\n"); + return err; found: - if (alloc_pdir(as) < 0) - goto err_alloc_pdir; - spin_lock(&smmu->lock); /* Update PDIR register */ @@ -822,10 +839,6 @@ found: dev_dbg(smmu->dev, "smmu_as@%p\n", as); return 0; - -err_alloc_pdir: - spin_unlock_irqrestore(&as->lock, flags); - return -ENODEV; } static void smmu_iommu_domain_destroy(struct iommu_domain *domain) -- cgit v1.2.3 From f9a4f063a88297e361fd6676986cf3e39b22de72 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 17 Jul 2012 11:47:14 +0200 Subject: iommu/tegra: Don't call alloc_pdir with as->lock Instead of taking as->lock before calling alloc_pdir() and releasing it in that function to allocate memory, just take the lock only in the alloc_pdir function and run the loop without any lock held. This simplifies the complicated lock->unlock->alloc->lock->unlock sequence into alloc->lock->unlock. Signed-off-by: Joerg Roedel --- drivers/iommu/tegra-smmu.c | 29 ++++++++++++++++------------- 1 file changed, 16 insertions(+), 13 deletions(-) (limited to 'drivers/iommu') diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index 68a15a0d5b8a..541d210cb421 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -553,11 +553,11 @@ static inline void put_signature(struct smmu_as *as, #endif /* - * Caller must lock/unlock as + * Caller must not hold as->lock */ -static int alloc_pdir(struct smmu_as *as, unsigned long *flags) +static int alloc_pdir(struct smmu_as *as) { - unsigned long *pdir; + unsigned long *pdir, flags; int pdn, err = 0; u32 val; struct smmu_device *smmu = as->smmu; @@ -565,13 +565,14 @@ static int alloc_pdir(struct smmu_as *as, unsigned long *flags) unsigned int *cnt; /* - * do the allocation outside the as->lock + * do the allocation, then grab as->lock */ - spin_unlock_irqrestore(&as->lock, *flags); cnt = devm_kzalloc(smmu->dev, - sizeof(cnt[0]) * SMMU_PDIR_COUNT, GFP_KERNEL); + sizeof(cnt[0]) * SMMU_PDIR_COUNT, + GFP_KERNEL); page = alloc_page(GFP_KERNEL | __GFP_DMA); - spin_lock_irqsave(&as->lock, *flags); + + spin_lock_irqsave(&as->lock, flags); if (as->pdir_page) { /* We raced, free the redundant */ @@ -603,9 +604,13 @@ static int alloc_pdir(struct smmu_as *as, unsigned long *flags) smmu_write(smmu, val, SMMU_TLB_FLUSH); FLUSH_SMMU_REGS(as->smmu); + spin_unlock_irqrestore(&as->lock, flags); + return 0; err_out: + spin_unlock_irqrestore(&as->lock, flags); + devm_kfree(smmu->dev, cnt); if (page) __free_page(page); @@ -809,13 +814,11 @@ static int smmu_iommu_domain_init(struct iommu_domain *domain) /* Look for a free AS with lock held */ for (i = 0; i < smmu->num_as; i++) { as = &smmu->as[i]; - spin_lock_irqsave(&as->lock, flags); if (!as->pdir_page) { - err = alloc_pdir(as, &flags); + err = alloc_pdir(as); if (!err) goto found; } - spin_unlock_irqrestore(&as->lock, flags); if (err != -EAGAIN) break; } @@ -824,7 +827,7 @@ static int smmu_iommu_domain_init(struct iommu_domain *domain) return err; found: - spin_lock(&smmu->lock); + spin_lock_irqsave(&smmu->lock, flags); /* Update PDIR register */ smmu_write(smmu, SMMU_PTB_ASID_CUR(as->asid), SMMU_PTB_ASID); @@ -832,12 +835,12 @@ found: SMMU_MK_PDIR(as->pdir_page, as->pdir_attr), SMMU_PTB_DATA); FLUSH_SMMU_REGS(smmu); - spin_unlock(&smmu->lock); + spin_unlock_irqrestore(&smmu->lock, flags); - spin_unlock_irqrestore(&as->lock, flags); domain->priv = as; dev_dbg(smmu->dev, "smmu_as@%p\n", as); + return 0; } -- cgit v1.2.3 From 98f1ad258254d89ffb550a36d59caf9127a9d53f Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Fri, 6 Jul 2012 13:28:37 +0200 Subject: iommu/amd: Fix sparse warnings A few sparse warnings fire in drivers/iommu/amd_iommu_init.c. Fix most of them with this patch. Also fix the sparse warnings in drivers/iommu/irq_remapping.c while at it. Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu.c | 2 +- drivers/iommu/amd_iommu_init.c | 16 +++++----------- drivers/iommu/amd_iommu_types.h | 8 +++++++- drivers/iommu/amd_iommu_v2.c | 2 +- drivers/iommu/irq_remapping.c | 5 +++++ 5 files changed, 19 insertions(+), 14 deletions(-) (limited to 'drivers/iommu') diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 625626391f2d..7f8e7a8bf504 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -2073,7 +2073,7 @@ out_err: /* FIXME: Move this to PCI code */ #define PCI_PRI_TLP_OFF (1 << 15) -bool pci_pri_tlp_required(struct pci_dev *pdev) +static bool pci_pri_tlp_required(struct pci_dev *pdev) { u16 status; int pos; diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index a33612f3206f..55f2033ea69b 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -190,12 +190,6 @@ static u32 dev_table_size; /* size of the device table */ static u32 alias_table_size; /* size of the alias table */ static u32 rlookup_table_size; /* size if the rlookup table */ -/* - * This function flushes all internal caches of - * the IOMMU used by this driver. - */ -extern void iommu_flush_all_caches(struct amd_iommu *iommu); - static int amd_iommu_enable_interrupts(void); static inline void update_last_devid(u16 devid) @@ -358,7 +352,7 @@ static void iommu_disable(struct amd_iommu *iommu) * mapping and unmapping functions for the IOMMU MMIO space. Each AMD IOMMU in * the system has one. */ -static u8 * __init iommu_map_mmio_space(u64 address) +static u8 __iomem * __init iommu_map_mmio_space(u64 address) { if (!request_mem_region(address, MMIO_REGION_LENGTH, "amd_iommu")) { pr_err("AMD-Vi: Can not reserve memory region %llx for mmio\n", @@ -367,7 +361,7 @@ static u8 * __init iommu_map_mmio_space(u64 address) return NULL; } - return ioremap_nocache(address, MMIO_REGION_LENGTH); + return (u8 __iomem *)ioremap_nocache(address, MMIO_REGION_LENGTH); } static void __init iommu_unmap_mmio_space(struct amd_iommu *iommu) @@ -1217,7 +1211,7 @@ static int __init init_exclusion_range(struct ivmd_header *m) /* called for unity map ACPI definition */ static int __init init_unity_map_range(struct ivmd_header *m) { - struct unity_map_entry *e = 0; + struct unity_map_entry *e = NULL; char *s; e = kzalloc(sizeof(*e), GFP_KERNEL); @@ -1727,8 +1721,8 @@ __setup("amd_iommu=", parse_amd_iommu_options); IOMMU_INIT_FINISH(amd_iommu_detect, gart_iommu_hole_init, - 0, - 0); + NULL, + NULL); bool amd_iommu_v2_supported(void) { diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h index c1b1d489817e..848fc8e37948 100644 --- a/drivers/iommu/amd_iommu_types.h +++ b/drivers/iommu/amd_iommu_types.h @@ -487,7 +487,7 @@ struct amd_iommu { /* physical address of MMIO space */ u64 mmio_phys; /* virtual address of MMIO space */ - u8 *mmio_base; + u8 __iomem *mmio_base; /* capabilities of that IOMMU read from ACPI */ u32 cap; @@ -664,6 +664,12 @@ extern bool amd_iommu_force_isolation; /* Max levels of glxval supported */ extern int amd_iommu_max_glx_val; +/* + * This function flushes all internal caches of + * the IOMMU used by this driver. + */ +extern void iommu_flush_all_caches(struct amd_iommu *iommu); + /* takes bus and device/function and returns the device id * FIXME: should that be in generic PCI code? */ static inline u16 calc_devid(u8 bus, u8 devfn) diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c index 036fe9bf157e..77c28b721741 100644 --- a/drivers/iommu/amd_iommu_v2.c +++ b/drivers/iommu/amd_iommu_v2.c @@ -81,7 +81,7 @@ struct fault { u16 flags; }; -struct device_state **state_table; +static struct device_state **state_table; static spinlock_t state_lock; /* List and lock for all pasid_states */ diff --git a/drivers/iommu/irq_remapping.c b/drivers/iommu/irq_remapping.c index 40cda8e98d87..92769963eac9 100644 --- a/drivers/iommu/irq_remapping.c +++ b/drivers/iommu/irq_remapping.c @@ -1,6 +1,11 @@ #include #include +#include #include +#include + +#include +#include #include "irq_remapping.h" -- cgit v1.2.3 From 02f3b3f5449cd0d9c4fb2c6f85f2973adefb7c72 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 11 Jun 2012 17:45:25 +0200 Subject: iommu/amd: Use acpi_get_table instead of acpi_table_parse This makes it easier to propagate errors while parsing the IVRS table and makes the amd_iommu_init_err hack obsolete. Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu_init.c | 118 +++++++++++++++++++++++------------------ 1 file changed, 66 insertions(+), 52 deletions(-) (limited to 'drivers/iommu') diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index 55f2033ea69b..de7a6cedcc45 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -26,6 +26,8 @@ #include #include #include +#include +#include #include #include #include @@ -122,7 +124,7 @@ struct ivmd_header { bool amd_iommu_dump; -static int __initdata amd_iommu_detected; +static bool amd_iommu_detected; static bool __initdata amd_iommu_disabled; u16 amd_iommu_last_bdf; /* largest PCI device id we have @@ -148,11 +150,6 @@ bool amd_iommu_v2_present __read_mostly; bool amd_iommu_force_isolation __read_mostly; -/* - * The ACPI table parsing functions set this variable on an error - */ -static int __initdata amd_iommu_init_err; - /* * List of protection domains - used during resume */ @@ -457,11 +454,9 @@ static int __init find_last_devid_acpi(struct acpi_table_header *table) */ for (i = 0; i < table->length; ++i) checksum += p[i]; - if (checksum != 0) { + if (checksum != 0) /* ACPI table corrupt */ - amd_iommu_init_err = -ENODEV; - return 0; - } + return -ENODEV; p += IVRS_HEADER_LENGTH; @@ -1087,16 +1082,12 @@ static int __init init_iommu_all(struct acpi_table_header *table) h->mmio_phys); iommu = kzalloc(sizeof(struct amd_iommu), GFP_KERNEL); - if (iommu == NULL) { - amd_iommu_init_err = -ENOMEM; - return 0; - } + if (iommu == NULL) + return -ENOMEM; ret = init_iommu_one(iommu, h); - if (ret) { - amd_iommu_init_err = ret; - return 0; - } + if (ret) + return ret; break; default: break; @@ -1477,9 +1468,15 @@ static void __init free_on_init_error(void) */ int __init amd_iommu_init_hardware(void) { + struct acpi_table_header *ivrs_base; + acpi_size ivrs_size; + acpi_status status; int i, ret = 0; - if (!amd_iommu_detected) + if (no_iommu || (iommu_detected && !gart_iommu_aperture)) + return -ENODEV; + + if (amd_iommu_disabled || !amd_iommu_detected) return -ENODEV; if (amd_iommu_dev_table != NULL) { @@ -1487,16 +1484,21 @@ int __init amd_iommu_init_hardware(void) return 0; } + status = acpi_get_table_with_size("IVRS", 0, &ivrs_base, &ivrs_size); + if (status == AE_NOT_FOUND) + return -ENODEV; + else if (ACPI_FAILURE(status)) { + const char *err = acpi_format_exception(status); + pr_err("AMD-Vi: IVRS table error: %s\n", err); + return -EINVAL; + } + /* * First parse ACPI tables to find the largest Bus/Dev/Func * we need to handle. Upon this information the shared data * structures for the IOMMUs in the system will be allocated */ - if (acpi_table_parse("IVRS", find_last_devid_acpi) != 0) - return -ENODEV; - - ret = amd_iommu_init_err; - if (ret) + if (find_last_devid_acpi(ivrs_base)) goto out; dev_table_size = tbl_size(DEV_TABLE_ENTRY_SIZE); @@ -1553,22 +1555,13 @@ int __init amd_iommu_init_hardware(void) * now the data structures are allocated and basically initialized * start the real acpi table scan */ - ret = -ENODEV; - if (acpi_table_parse("IVRS", init_iommu_all) != 0) - goto free; - - if (amd_iommu_init_err) { - ret = amd_iommu_init_err; - goto free; - } - - if (acpi_table_parse("IVRS", init_memory_definitions) != 0) + ret = init_iommu_all(ivrs_base); + if (ret) goto free; - if (amd_iommu_init_err) { - ret = amd_iommu_init_err; + ret = init_memory_definitions(ivrs_base); + if (ret) goto free; - } ret = amd_iommu_init_devices(); if (ret) @@ -1581,12 +1574,16 @@ int __init amd_iommu_init_hardware(void) register_syscore_ops(&amd_iommu_syscore_ops); out: + /* Don't leak any ACPI memory */ + early_acpi_os_unmap_memory((char __iomem *)ivrs_base, ivrs_size); + ivrs_base = NULL; + return ret; free: free_on_init_error(); - return ret; + goto out; } static int amd_iommu_enable_interrupts(void) @@ -1604,6 +1601,26 @@ out: return ret; } +static bool detect_ivrs(void) +{ + struct acpi_table_header *ivrs_base; + acpi_size ivrs_size; + acpi_status status; + + status = acpi_get_table_with_size("IVRS", 0, &ivrs_base, &ivrs_size); + if (status == AE_NOT_FOUND) + return false; + else if (ACPI_FAILURE(status)) { + const char *err = acpi_format_exception(status); + pr_err("AMD-Vi: IVRS table error: %s\n", err); + return false; + } + + early_acpi_os_unmap_memory((char __iomem *)ivrs_base, ivrs_size); + + return true; +} + /* * This is the core init function for AMD IOMMU hardware in the system. * This function is called from the generic x86 DMA layer initialization @@ -1663,29 +1680,26 @@ free: * IOMMUs * ****************************************************************************/ -static int __init early_amd_iommu_detect(struct acpi_table_header *table) -{ - return 0; -} - int __init amd_iommu_detect(void) { + if (no_iommu || (iommu_detected && !gart_iommu_aperture)) return -ENODEV; if (amd_iommu_disabled) return -ENODEV; - if (acpi_table_parse("IVRS", early_amd_iommu_detect) == 0) { - iommu_detected = 1; - amd_iommu_detected = 1; - x86_init.iommu.iommu_init = amd_iommu_init; + if (!detect_ivrs()) + return -ENODEV; - /* Make sure ACS will be enabled */ - pci_request_acs(); - return 1; - } - return -ENODEV; + amd_iommu_detected = true; + iommu_detected = 1; + x86_init.iommu.iommu_init = amd_iommu_init; + + /* Make sure ACS will be enabled */ + pci_request_acs(); + + return 0; } /**************************************************************************** -- cgit v1.2.3 From 23c742db217113585ccc6c4a9b6ff96d642b6158 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 12 Jun 2012 11:47:34 +0200 Subject: iommu/amd: Split out PCI related parts of IOMMU initialization For interrupt remapping the relevant IOMMU initialization needs to run earlier at boot when the PCI subsystem is not yet initialized. To support that this patch splits the parts of IOMMU initialization which need PCI accesses out of the initial setup path so that this can be done later. Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu_init.c | 224 +++++++++++++++++++++------------------- drivers/iommu/amd_iommu_types.h | 5 +- 2 files changed, 121 insertions(+), 108 deletions(-) (limited to 'drivers/iommu') diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index de7a6cedcc45..c3d650dea240 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -714,90 +714,6 @@ static void __init set_device_exclusion_range(u16 devid, struct ivmd_header *m) } } -/* - * This function reads some important data from the IOMMU PCI space and - * initializes the driver data structure with it. It reads the hardware - * capabilities and the first/last device entries - */ -static void __init init_iommu_from_pci(struct amd_iommu *iommu) -{ - int cap_ptr = iommu->cap_ptr; - u32 range, misc, low, high; - int i, j; - - pci_read_config_dword(iommu->dev, cap_ptr + MMIO_CAP_HDR_OFFSET, - &iommu->cap); - pci_read_config_dword(iommu->dev, cap_ptr + MMIO_RANGE_OFFSET, - &range); - pci_read_config_dword(iommu->dev, cap_ptr + MMIO_MISC_OFFSET, - &misc); - - iommu->first_device = calc_devid(MMIO_GET_BUS(range), - MMIO_GET_FD(range)); - iommu->last_device = calc_devid(MMIO_GET_BUS(range), - MMIO_GET_LD(range)); - iommu->evt_msi_num = MMIO_MSI_NUM(misc); - - if (!(iommu->cap & (1 << IOMMU_CAP_IOTLB))) - amd_iommu_iotlb_sup = false; - - /* read extended feature bits */ - low = readl(iommu->mmio_base + MMIO_EXT_FEATURES); - high = readl(iommu->mmio_base + MMIO_EXT_FEATURES + 4); - - iommu->features = ((u64)high << 32) | low; - - if (iommu_feature(iommu, FEATURE_GT)) { - int glxval; - u32 pasids; - u64 shift; - - shift = iommu->features & FEATURE_PASID_MASK; - shift >>= FEATURE_PASID_SHIFT; - pasids = (1 << shift); - - amd_iommu_max_pasids = min(amd_iommu_max_pasids, pasids); - - glxval = iommu->features & FEATURE_GLXVAL_MASK; - glxval >>= FEATURE_GLXVAL_SHIFT; - - if (amd_iommu_max_glx_val == -1) - amd_iommu_max_glx_val = glxval; - else - amd_iommu_max_glx_val = min(amd_iommu_max_glx_val, glxval); - } - - if (iommu_feature(iommu, FEATURE_GT) && - iommu_feature(iommu, FEATURE_PPR)) { - iommu->is_iommu_v2 = true; - amd_iommu_v2_present = true; - } - - if (!is_rd890_iommu(iommu->dev)) - return; - - /* - * Some rd890 systems may not be fully reconfigured by the BIOS, so - * it's necessary for us to store this information so it can be - * reprogrammed on resume - */ - - pci_read_config_dword(iommu->dev, iommu->cap_ptr + 4, - &iommu->stored_addr_lo); - pci_read_config_dword(iommu->dev, iommu->cap_ptr + 8, - &iommu->stored_addr_hi); - - /* Low bit locks writes to configuration space */ - iommu->stored_addr_lo &= ~1; - - for (i = 0; i < 6; i++) - for (j = 0; j < 0x12; j++) - iommu->stored_l1[i][j] = iommu_read_l1(iommu, i, j); - - for (i = 0; i < 0x83; i++) - iommu->stored_l2[i] = iommu_read_l2(iommu, i); -} - /* * Takes a pointer to an AMD IOMMU entry in the ACPI table and * initializes the hardware and our data structures with it. @@ -1014,13 +930,7 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h) /* * Copy data from ACPI table entry to the iommu struct */ - iommu->dev = pci_get_bus_and_slot(PCI_BUS(h->devid), h->devid & 0xff); - if (!iommu->dev) - return 1; - - iommu->root_pdev = pci_get_bus_and_slot(iommu->dev->bus->number, - PCI_DEVFN(0, 0)); - + iommu->devid = h->devid; iommu->cap_ptr = h->cap_ptr; iommu->pci_seg = h->pci_seg; iommu->mmio_phys = h->mmio_phys; @@ -1038,20 +948,10 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h) iommu->int_enabled = false; - init_iommu_from_pci(iommu); init_iommu_from_acpi(iommu, h); init_iommu_devices(iommu); - if (iommu_feature(iommu, FEATURE_PPR)) { - iommu->ppr_log = alloc_ppr_log(iommu); - if (!iommu->ppr_log) - return -ENOMEM; - } - - if (iommu->cap & (1UL << IOMMU_CAP_NPCACHE)) - amd_iommu_np_cache = true; - - return pci_enable_device(iommu->dev); + return 0; } /* @@ -1100,6 +1000,121 @@ static int __init init_iommu_all(struct acpi_table_header *table) return 0; } +static int iommu_init_pci(struct amd_iommu *iommu) +{ + int cap_ptr = iommu->cap_ptr; + u32 range, misc, low, high; + + iommu->dev = pci_get_bus_and_slot(PCI_BUS(iommu->devid), + iommu->devid & 0xff); + if (!iommu->dev) + return -ENODEV; + + pci_read_config_dword(iommu->dev, cap_ptr + MMIO_CAP_HDR_OFFSET, + &iommu->cap); + pci_read_config_dword(iommu->dev, cap_ptr + MMIO_RANGE_OFFSET, + &range); + pci_read_config_dword(iommu->dev, cap_ptr + MMIO_MISC_OFFSET, + &misc); + + iommu->first_device = calc_devid(MMIO_GET_BUS(range), + MMIO_GET_FD(range)); + iommu->last_device = calc_devid(MMIO_GET_BUS(range), + MMIO_GET_LD(range)); + + if (!(iommu->cap & (1 << IOMMU_CAP_IOTLB))) + amd_iommu_iotlb_sup = false; + + /* read extended feature bits */ + low = readl(iommu->mmio_base + MMIO_EXT_FEATURES); + high = readl(iommu->mmio_base + MMIO_EXT_FEATURES + 4); + + iommu->features = ((u64)high << 32) | low; + + if (iommu_feature(iommu, FEATURE_GT)) { + int glxval; + u32 pasids; + u64 shift; + + shift = iommu->features & FEATURE_PASID_MASK; + shift >>= FEATURE_PASID_SHIFT; + pasids = (1 << shift); + + amd_iommu_max_pasids = min(amd_iommu_max_pasids, pasids); + + glxval = iommu->features & FEATURE_GLXVAL_MASK; + glxval >>= FEATURE_GLXVAL_SHIFT; + + if (amd_iommu_max_glx_val == -1) + amd_iommu_max_glx_val = glxval; + else + amd_iommu_max_glx_val = min(amd_iommu_max_glx_val, glxval); + } + + if (iommu_feature(iommu, FEATURE_GT) && + iommu_feature(iommu, FEATURE_PPR)) { + iommu->is_iommu_v2 = true; + amd_iommu_v2_present = true; + } + + if (iommu_feature(iommu, FEATURE_PPR)) { + iommu->ppr_log = alloc_ppr_log(iommu); + if (!iommu->ppr_log) + return -ENOMEM; + } + + if (iommu->cap & (1UL << IOMMU_CAP_NPCACHE)) + amd_iommu_np_cache = true; + + if (is_rd890_iommu(iommu->dev)) { + int i, j; + + iommu->root_pdev = pci_get_bus_and_slot(iommu->dev->bus->number, + PCI_DEVFN(0, 0)); + + /* + * Some rd890 systems may not be fully reconfigured by the + * BIOS, so it's necessary for us to store this information so + * it can be reprogrammed on resume + */ + pci_read_config_dword(iommu->dev, iommu->cap_ptr + 4, + &iommu->stored_addr_lo); + pci_read_config_dword(iommu->dev, iommu->cap_ptr + 8, + &iommu->stored_addr_hi); + + /* Low bit locks writes to configuration space */ + iommu->stored_addr_lo &= ~1; + + for (i = 0; i < 6; i++) + for (j = 0; j < 0x12; j++) + iommu->stored_l1[i][j] = iommu_read_l1(iommu, i, j); + + for (i = 0; i < 0x83; i++) + iommu->stored_l2[i] = iommu_read_l2(iommu, i); + } + + return pci_enable_device(iommu->dev); +} + +static int amd_iommu_init_pci(void) +{ + struct amd_iommu *iommu; + int ret = 0; + + for_each_iommu(iommu) { + ret = iommu_init_pci(iommu); + if (ret) + break; + } + + /* Make sure ACS will be enabled */ + pci_request_acs(); + + ret = amd_iommu_init_devices(); + + return ret; +} + /**************************************************************************** * * The following functions initialize the MSI interrupts for all IOMMUs @@ -1563,7 +1578,7 @@ int __init amd_iommu_init_hardware(void) if (ret) goto free; - ret = amd_iommu_init_devices(); + ret = amd_iommu_init_pci(); if (ret) goto free; @@ -1696,9 +1711,6 @@ int __init amd_iommu_detect(void) iommu_detected = 1; x86_init.iommu.iommu_init = amd_iommu_init; - /* Make sure ACS will be enabled */ - pci_request_acs(); - return 0; } diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h index 848fc8e37948..d0dab865a8b8 100644 --- a/drivers/iommu/amd_iommu_types.h +++ b/drivers/iommu/amd_iommu_types.h @@ -501,6 +501,9 @@ struct amd_iommu { /* IOMMUv2 */ bool is_iommu_v2; + /* PCI device id of the IOMMU device */ + u16 devid; + /* * Capability pointer. There could be more than one IOMMU per PCI * device function if there are more than one AMD IOMMU capability @@ -530,8 +533,6 @@ struct amd_iommu { u32 evt_buf_size; /* event buffer virtual address */ u8 *evt_buf; - /* MSI number for event interrupt */ - u16 evt_msi_num; /* Base of the PPR log, if present */ u8 *ppr_log; -- cgit v1.2.3 From 4d121c3256edc66fe8a8e7f975eba72add120a26 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 14 Jun 2012 12:21:55 +0200 Subject: iommu/amd: Move informational prinks out of iommu_enable This function will be called before the PCI subsystem is initialized. Therefore dev_name doen't work and IOMMU information can't be printed to the klog as before. Move the code to print that information to a later point where PCI initializtion has already happened. Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu_init.c | 44 ++++++++++++++++++++++++++---------------- 1 file changed, 27 insertions(+), 17 deletions(-) (limited to 'drivers/iommu') diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index c3d650dea240..b18034a8fdb3 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -312,23 +312,6 @@ static void iommu_set_inv_tlb_timeout(struct amd_iommu *iommu, int timeout) /* Function to enable the hardware */ static void iommu_enable(struct amd_iommu *iommu) { - static const char * const feat_str[] = { - "PreF", "PPR", "X2APIC", "NX", "GT", "[5]", - "IA", "GA", "HE", "PC", NULL - }; - int i; - - printk(KERN_INFO "AMD-Vi: Enabling IOMMU at %s cap 0x%hx", - dev_name(&iommu->dev->dev), iommu->cap_ptr); - - if (iommu->cap & (1 << IOMMU_CAP_EFR)) { - printk(KERN_CONT " extended features: "); - for (i = 0; feat_str[i]; ++i) - if (iommu_feature(iommu, (1ULL << i))) - printk(KERN_CONT " %s", feat_str[i]); - } - printk(KERN_CONT "\n"); - iommu_feature_enable(iommu, CONTROL_IOMMU_EN); } @@ -1096,6 +1079,31 @@ static int iommu_init_pci(struct amd_iommu *iommu) return pci_enable_device(iommu->dev); } +static void print_iommu_info(void) +{ + static const char * const feat_str[] = { + "PreF", "PPR", "X2APIC", "NX", "GT", "[5]", + "IA", "GA", "HE", "PC" + }; + struct amd_iommu *iommu; + + for_each_iommu(iommu) { + int i; + + pr_info("AMD-Vi: Found IOMMU at %s cap 0x%hx\n", + dev_name(&iommu->dev->dev), iommu->cap_ptr); + + if (iommu->cap & (1 << IOMMU_CAP_EFR)) { + pr_info("AMD-Vi: Extended features: "); + for (i = 0; ARRAY_SIZE(feat_str); ++i) { + if (iommu_feature(iommu, (1ULL << i))) + pr_cont(" %s", feat_str[i]); + } + } + pr_cont("\n"); + } +} + static int amd_iommu_init_pci(void) { struct amd_iommu *iommu; @@ -1112,6 +1120,8 @@ static int amd_iommu_init_pci(void) ret = amd_iommu_init_devices(); + print_iommu_info(); + return ret; } -- cgit v1.2.3 From 643511b37eb72d831646bacafaeace1eeadf5a54 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 12 Jun 2012 12:09:35 +0200 Subject: iommu/amd: Introduce early_amd_iommu_init routine Split out the code to parse the ACPI table and setup relevant data structures into a new function. Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu.c | 1 - drivers/iommu/amd_iommu_init.c | 38 +++++++++++++++++++++++--------------- 2 files changed, 23 insertions(+), 16 deletions(-) (limited to 'drivers/iommu') diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 7f8e7a8bf504..0d0dc8598c72 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -384,7 +384,6 @@ DECLARE_STATS_COUNTER(invalidate_iotlb); DECLARE_STATS_COUNTER(invalidate_iotlb_all); DECLARE_STATS_COUNTER(pri_requests); - static struct dentry *stats_dir; static struct dentry *de_fflush; diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index b18034a8fdb3..a5dbefb8e260 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -1491,17 +1491,14 @@ static void __init free_on_init_error(void) * After everything is set up the IOMMUs are enabled and the necessary * hotplug and suspend notifiers are registered. */ -int __init amd_iommu_init_hardware(void) +static int __init early_amd_iommu_init(void) { struct acpi_table_header *ivrs_base; acpi_size ivrs_size; acpi_status status; int i, ret = 0; - if (no_iommu || (iommu_detected && !gart_iommu_aperture)) - return -ENODEV; - - if (amd_iommu_disabled || !amd_iommu_detected) + if (!amd_iommu_detected) return -ENODEV; if (amd_iommu_dev_table != NULL) { @@ -1588,16 +1585,6 @@ int __init amd_iommu_init_hardware(void) if (ret) goto free; - ret = amd_iommu_init_pci(); - if (ret) - goto free; - - enable_iommus(); - - amd_iommu_init_notifier(); - - register_syscore_ops(&amd_iommu_syscore_ops); - out: /* Don't leak any ACPI memory */ early_acpi_os_unmap_memory((char __iomem *)ivrs_base, ivrs_size); @@ -1611,6 +1598,27 @@ free: goto out; } +int __init amd_iommu_init_hardware(void) +{ + int ret = 0; + + ret = early_amd_iommu_init(); + if (ret) + return ret; + + ret = amd_iommu_init_pci(); + if (ret) + return ret; + + enable_iommus(); + + amd_iommu_init_notifier(); + + register_syscore_ops(&amd_iommu_syscore_ops); + + return ret; +} + static int amd_iommu_enable_interrupts(void) { struct amd_iommu *iommu; -- cgit v1.2.3 From 11ee5ac47b78d7e117c84147596a124ce6421a3a Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 12 Jun 2012 16:30:06 +0200 Subject: iommu/amd: Split enable_iommus() routine Split the enable_iommus() routine so that a part of it can run in early code. Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu_init.c | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) (limited to 'drivers/iommu') diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index a5dbefb8e260..b82cf447724e 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -1379,7 +1379,7 @@ static void iommu_apply_resume_quirks(struct amd_iommu *iommu) * This function finally enables all IOMMUs found in the system after * they have been initialized */ -static void enable_iommus(void) +static void early_enable_iommus(void) { struct amd_iommu *iommu; @@ -1389,14 +1389,29 @@ static void enable_iommus(void) iommu_set_device_table(iommu); iommu_enable_command_buffer(iommu); iommu_enable_event_buffer(iommu); - iommu_enable_ppr_log(iommu); - iommu_enable_gt(iommu); iommu_set_exclusion_range(iommu); iommu_enable(iommu); iommu_flush_all_caches(iommu); } } +static void enable_iommus_v2(void) +{ + struct amd_iommu *iommu; + + for_each_iommu(iommu) { + iommu_enable_ppr_log(iommu); + iommu_enable_gt(iommu); + } +} + +static void enable_iommus(void) +{ + early_enable_iommus(); + + enable_iommus_v2(); +} + static void disable_iommus(void) { struct amd_iommu *iommu; -- cgit v1.2.3 From 62410eeb40ef355fa47f63886542f4dacef13ba9 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 12 Jun 2012 16:42:43 +0200 Subject: iommu/amd: Move unmap_flush message to amd_iommu_init_dma_ops() The message belongs there anyway, so move it to that function. Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu.c | 5 +++++ drivers/iommu/amd_iommu_init.c | 8 -------- 2 files changed, 5 insertions(+), 8 deletions(-) (limited to 'drivers/iommu') diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 0d0dc8598c72..584ea85ab2f0 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -2971,6 +2971,11 @@ int __init amd_iommu_init_dma_ops(void) amd_iommu_stats_init(); + if (amd_iommu_unmap_flush) + pr_info("AMD-Vi: IO/TLB flush on unmap enabled\n"); + else + pr_info("AMD-Vi: Lazy IO/TLB flushing enabled\n"); + return 0; free_domains: diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index b82cf447724e..966d8ac9e147 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -1702,14 +1702,6 @@ static int __init amd_iommu_init(void) x86_platform.iommu_shutdown = disable_iommus; - if (iommu_pass_through) - goto out; - - if (amd_iommu_unmap_flush) - printk(KERN_INFO "AMD-Vi: IO/TLB flush on unmap enabled\n"); - else - printk(KERN_INFO "AMD-Vi: Lazy IO/TLB flushing enabled\n"); - out: return ret; -- cgit v1.2.3 From b9b1ce707d81ec63c04e4fd8c34699ada950e6dc Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 12 Jun 2012 16:51:12 +0200 Subject: iommu/amd: Introduce amd_iommu_init_dma routine This function will initialize everthing necessary so that devices can do DMA. This includes dma_ops and iommu_ops. Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu_init.c | 27 ++++++++++++++++++++------- 1 file changed, 20 insertions(+), 7 deletions(-) (limited to 'drivers/iommu') diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index 966d8ac9e147..53828b61e9ac 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -1627,8 +1627,6 @@ int __init amd_iommu_init_hardware(void) enable_iommus(); - amd_iommu_init_notifier(); - register_syscore_ops(&amd_iommu_syscore_ops); return ret; @@ -1669,6 +1667,25 @@ static bool detect_ivrs(void) return true; } +static int amd_iommu_init_dma(void) +{ + int ret; + + if (iommu_pass_through) + ret = amd_iommu_init_passthrough(); + else + ret = amd_iommu_init_dma_ops(); + + if (ret) + return ret; + + amd_iommu_init_api(); + + amd_iommu_init_notifier(); + + return 0; +} + /* * This is the core init function for AMD IOMMU hardware in the system. * This function is called from the generic x86 DMA layer initialization @@ -1690,11 +1707,7 @@ static int __init amd_iommu_init(void) if (ret) goto free; - if (iommu_pass_through) - ret = amd_iommu_init_passthrough(); - else - ret = amd_iommu_init_dma_ops(); - + ret = amd_iommu_init_dma(); if (ret) goto free; -- cgit v1.2.3 From 2c0ae1720c09c6f8fc8c6bcece29dc80b08ca1af Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 12 Jun 2012 15:59:30 +0200 Subject: iommu/amd: Convert iommu initialization to state machine This step makes it very easy to keep track about the current intialization state of the iommu driver. With this change we can initialize the IOMMU hardware to a point where it can remap interrupts and later resume the initializion to enable dma remapping. Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu_init.c | 173 ++++++++++++++++++++++++++--------------- 1 file changed, 109 insertions(+), 64 deletions(-) (limited to 'drivers/iommu') diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index 53828b61e9ac..500e7f15f5c2 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -187,7 +187,23 @@ static u32 dev_table_size; /* size of the device table */ static u32 alias_table_size; /* size of the alias table */ static u32 rlookup_table_size; /* size if the rlookup table */ +enum iommu_init_state { + IOMMU_START_STATE, + IOMMU_IVRS_DETECTED, + IOMMU_ACPI_FINISHED, + IOMMU_ENABLED, + IOMMU_PCI_INIT, + IOMMU_INTERRUPTS_EN, + IOMMU_DMA_OPS, + IOMMU_INITIALIZED, + IOMMU_NOT_FOUND, + IOMMU_INIT_ERROR, +}; + +static enum iommu_init_state init_state = IOMMU_START_STATE; + static int amd_iommu_enable_interrupts(void); +static int __init iommu_go_to_state(enum iommu_init_state state); static inline void update_last_devid(u16 devid) { @@ -1104,7 +1120,7 @@ static void print_iommu_info(void) } } -static int amd_iommu_init_pci(void) +static int __init amd_iommu_init_pci(void) { struct amd_iommu *iommu; int ret = 0; @@ -1516,11 +1532,6 @@ static int __init early_amd_iommu_init(void) if (!amd_iommu_detected) return -ENODEV; - if (amd_iommu_dev_table != NULL) { - /* Hardware already initialized */ - return 0; - } - status = acpi_get_table_with_size("IVRS", 0, &ivrs_base, &ivrs_size); if (status == AE_NOT_FOUND) return -ENODEV; @@ -1535,7 +1546,8 @@ static int __init early_amd_iommu_init(void) * we need to handle. Upon this information the shared data * structures for the IOMMUs in the system will be allocated */ - if (find_last_devid_acpi(ivrs_base)) + ret = find_last_devid_acpi(ivrs_base); + if (ret) goto out; dev_table_size = tbl_size(DEV_TABLE_ENTRY_SIZE); @@ -1556,20 +1568,20 @@ static int __init early_amd_iommu_init(void) amd_iommu_alias_table = (void *)__get_free_pages(GFP_KERNEL, get_order(alias_table_size)); if (amd_iommu_alias_table == NULL) - goto free; + goto out; /* IOMMU rlookup table - find the IOMMU for a specific device */ amd_iommu_rlookup_table = (void *)__get_free_pages( GFP_KERNEL | __GFP_ZERO, get_order(rlookup_table_size)); if (amd_iommu_rlookup_table == NULL) - goto free; + goto out; amd_iommu_pd_alloc_bitmap = (void *)__get_free_pages( GFP_KERNEL | __GFP_ZERO, get_order(MAX_DOMAIN_ID/8)); if (amd_iommu_pd_alloc_bitmap == NULL) - goto free; + goto out; /* init the device table */ init_device_table(); @@ -1594,41 +1606,17 @@ static int __init early_amd_iommu_init(void) */ ret = init_iommu_all(ivrs_base); if (ret) - goto free; + goto out; ret = init_memory_definitions(ivrs_base); if (ret) - goto free; + goto out; out: /* Don't leak any ACPI memory */ early_acpi_os_unmap_memory((char __iomem *)ivrs_base, ivrs_size); ivrs_base = NULL; - return ret; - -free: - free_on_init_error(); - - goto out; -} - -int __init amd_iommu_init_hardware(void) -{ - int ret = 0; - - ret = early_amd_iommu_init(); - if (ret) - return ret; - - ret = amd_iommu_init_pci(); - if (ret) - return ret; - - enable_iommus(); - - register_syscore_ops(&amd_iommu_syscore_ops); - return ret; } @@ -1686,44 +1674,99 @@ static int amd_iommu_init_dma(void) return 0; } -/* - * This is the core init function for AMD IOMMU hardware in the system. - * This function is called from the generic x86 DMA layer initialization - * code. +/**************************************************************************** * - * The function calls amd_iommu_init_hardware() to setup and enable the - * IOMMU hardware if this has not happened yet. After that the driver - * registers for the DMA-API and for the IOMMU-API as necessary. - */ -static int __init amd_iommu_init(void) + * AMD IOMMU Initialization State Machine + * + ****************************************************************************/ + +static int __init state_next(void) { int ret = 0; - ret = amd_iommu_init_hardware(); - if (ret) - goto out; - - ret = amd_iommu_enable_interrupts(); - if (ret) - goto free; + switch (init_state) { + case IOMMU_START_STATE: + if (!detect_ivrs()) { + init_state = IOMMU_NOT_FOUND; + ret = -ENODEV; + } else { + init_state = IOMMU_IVRS_DETECTED; + } + break; + case IOMMU_IVRS_DETECTED: + ret = early_amd_iommu_init(); + init_state = ret ? IOMMU_INIT_ERROR : IOMMU_ACPI_FINISHED; + break; + case IOMMU_ACPI_FINISHED: + early_enable_iommus(); + register_syscore_ops(&amd_iommu_syscore_ops); + x86_platform.iommu_shutdown = disable_iommus; + init_state = IOMMU_ENABLED; + break; + case IOMMU_ENABLED: + ret = amd_iommu_init_pci(); + init_state = ret ? IOMMU_INIT_ERROR : IOMMU_PCI_INIT; + enable_iommus_v2(); + break; + case IOMMU_PCI_INIT: + ret = amd_iommu_enable_interrupts(); + init_state = ret ? IOMMU_INIT_ERROR : IOMMU_INTERRUPTS_EN; + break; + case IOMMU_INTERRUPTS_EN: + ret = amd_iommu_init_dma(); + init_state = ret ? IOMMU_INIT_ERROR : IOMMU_DMA_OPS; + break; + case IOMMU_DMA_OPS: + init_state = IOMMU_INITIALIZED; + break; + case IOMMU_INITIALIZED: + /* Nothing to do */ + break; + case IOMMU_NOT_FOUND: + case IOMMU_INIT_ERROR: + /* Error states => do nothing */ + ret = -EINVAL; + break; + default: + /* Unknown state */ + BUG(); + } - ret = amd_iommu_init_dma(); - if (ret) - goto free; + return ret; +} - amd_iommu_init_api(); +static int __init iommu_go_to_state(enum iommu_init_state state) +{ + int ret = 0; - x86_platform.iommu_shutdown = disable_iommus; + while (init_state != state) { + ret = state_next(); + if (init_state == IOMMU_NOT_FOUND || + init_state == IOMMU_INIT_ERROR) + break; + } -out: return ret; +} -free: - disable_iommus(); - free_on_init_error(); - goto out; +/* + * This is the core init function for AMD IOMMU hardware in the system. + * This function is called from the generic x86 DMA layer initialization + * code. + */ +static int __init amd_iommu_init(void) +{ + int ret; + + ret = iommu_go_to_state(IOMMU_INITIALIZED); + if (ret) { + disable_iommus(); + free_on_init_error(); + } + + return ret; } /**************************************************************************** @@ -1735,6 +1778,7 @@ free: ****************************************************************************/ int __init amd_iommu_detect(void) { + int ret; if (no_iommu || (iommu_detected && !gart_iommu_aperture)) return -ENODEV; @@ -1742,8 +1786,9 @@ int __init amd_iommu_detect(void) if (amd_iommu_disabled) return -ENODEV; - if (!detect_ivrs()) - return -ENODEV; + ret = iommu_go_to_state(IOMMU_IVRS_DETECTED); + if (ret) + return ret; amd_iommu_detected = true; iommu_detected = 1; -- cgit v1.2.3 From 2c13d47a1a7ee8808796016c617aef25fd1d1925 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 19 Jul 2012 10:56:10 +0200 Subject: iommu/amd: Add missing spin_lock initialization Add missing spin_lock initialization in amd_iommu_bind_pasid() function and make lockdep happy again. Cc: stable@vger.kernel.org # >= v3.3 Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu_v2.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'drivers/iommu') diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c index 036fe9bf157e..a1f1bc876043 100644 --- a/drivers/iommu/amd_iommu_v2.c +++ b/drivers/iommu/amd_iommu_v2.c @@ -681,6 +681,8 @@ int amd_iommu_bind_pasid(struct pci_dev *pdev, int pasid, atomic_set(&pasid_state->count, 1); init_waitqueue_head(&pasid_state->wq); + spin_lock_init(&pasid_state->lock); + pasid_state->task = task; pasid_state->mm = get_task_mm(task); pasid_state->device_state = dev_state; -- cgit v1.2.3 From 2c9195e990297068d0f1f1bd8e2f1d09538009da Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 19 Jul 2012 13:42:54 +0200 Subject: iommu/amd: Fix hotplug with iommu=pt This did not work because devices are not put into the pt_domain. Fix this. Cc: stable@vger.kernel.org Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) (limited to 'drivers/iommu') diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 625626391f2d..3f365ab9f7c7 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -2254,6 +2254,18 @@ static int device_change_notifier(struct notifier_block *nb, iommu_init_device(dev); + /* + * dev_data is still NULL and + * got initialized in iommu_init_device + */ + dev_data = get_dev_data(dev); + + if (iommu_pass_through || dev_data->iommu_v2) { + dev_data->passthrough = true; + attach_device(dev, pt_domain); + break; + } + domain = domain_for_device(dev); /* allocate a protection domain if a device is added */ @@ -2271,10 +2283,7 @@ static int device_change_notifier(struct notifier_block *nb, dev_data = get_dev_data(dev); - if (!dev_data->passthrough) - dev->archdata.dma_ops = &amd_iommu_dma_ops; - else - dev->archdata.dma_ops = &nommu_dma_ops; + dev->archdata.dma_ops = &amd_iommu_dma_ops; break; case BUS_NOTIFY_DEL_DEVICE: -- cgit v1.2.3 From 07db04098d1e2f238959c858a0d63243157695f9 Mon Sep 17 00:00:00 2001 From: Masanari Iida Date: Sun, 22 Jul 2012 02:21:32 +0900 Subject: iommu: Fix typo in iommu Correct spelling typo in debug messages and comments in drivers/iommu. Signed-off-by: Masanari Iida Signed-off-by: Jiri Kosina --- drivers/iommu/amd_iommu_v2.c | 2 +- drivers/iommu/exynos-iommu.c | 2 +- drivers/iommu/iova.c | 14 +++++++------- 3 files changed, 9 insertions(+), 9 deletions(-) (limited to 'drivers/iommu') diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c index 036fe9bf157e..be03238ad815 100644 --- a/drivers/iommu/amd_iommu_v2.c +++ b/drivers/iommu/amd_iommu_v2.c @@ -924,7 +924,7 @@ static int __init amd_iommu_v2_init(void) pr_info("AMD IOMMUv2 driver by Joerg Roedel \n"); if (!amd_iommu_v2_supported()) { - pr_info("AMD IOMMUv2 functionality not available on this sytem\n"); + pr_info("AMD IOMMUv2 functionality not available on this system\n"); /* * Load anyway to provide the symbols to other modules * which may use AMD IOMMUv2 optionally. diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c index 9a114b9ff170..4407d5eff05e 100644 --- a/drivers/iommu/exynos-iommu.c +++ b/drivers/iommu/exynos-iommu.c @@ -317,7 +317,7 @@ static int default_fault_handler(enum exynos_sysmmu_inttype itype, if ((itype >= SYSMMU_FAULTS_NUM) || (itype < SYSMMU_PAGEFAULT)) itype = SYSMMU_FAULT_UNKNOWN; - pr_err("%s occured at 0x%lx(Page table base: 0x%lx)\n", + pr_err("%s occurred at 0x%lx(Page table base: 0x%lx)\n", sysmmu_fault_name[itype], fault_addr, pgtable_base); ent = section_entry(__va(pgtable_base), fault_addr); diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c index c5c274ab5c5a..67da6cff74e8 100644 --- a/drivers/iommu/iova.c +++ b/drivers/iommu/iova.c @@ -198,10 +198,10 @@ iova_insert_rbtree(struct rb_root *root, struct iova *iova) /** * alloc_iova - allocates an iova - * @iovad - iova domain in question - * @size - size of page frames to allocate - * @limit_pfn - max limit address - * @size_aligned - set if size_aligned address range is required + * @iovad: - iova domain in question + * @size: - size of page frames to allocate + * @limit_pfn: - max limit address + * @size_aligned: - set if size_aligned address range is required * This function allocates an iova in the range limit_pfn to IOVA_START_PFN * looking from limit_pfn instead from IOVA_START_PFN. If the size_aligned * flag is set then the allocated address iova->pfn_lo will be naturally @@ -238,8 +238,8 @@ alloc_iova(struct iova_domain *iovad, unsigned long size, /** * find_iova - find's an iova for a given pfn - * @iovad - iova domain in question. - * pfn - page frame number + * @iovad: - iova domain in question. + * @pfn: - page frame number * This function finds and returns an iova belonging to the * given doamin which matches the given pfn. */ @@ -260,7 +260,7 @@ struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn) /* We are not holding the lock while this iova * is referenced by the caller as the same thread * which called this function also calls __free_iova() - * and it is by desing that only one thread can possibly + * and it is by design that only one thread can possibly * reference a particular iova and hence no conflict. */ return iova; -- cgit v1.2.3