diff options
Diffstat (limited to 'arch/powerpc/platforms/pseries')
| -rw-r--r-- | arch/powerpc/platforms/pseries/dtl.c | 4 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/firmware.c | 3 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/hotplug-cpu.c | 173 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/hotplug-memory.c | 10 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/ibmebus.c | 3 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/iommu.c | 514 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/lpar.c | 18 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/msi.c | 296 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/pci_dlpar.c | 4 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/pseries.h | 2 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/ras.c | 2 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/setup.c | 2 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/svm.c | 6 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/vas.c | 2 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/vio.c | 8 |
15 files changed, 725 insertions, 322 deletions
diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c index 982f069e4c31..352af5b14a0f 100644 --- a/arch/powerpc/platforms/pseries/dtl.c +++ b/arch/powerpc/platforms/pseries/dtl.c @@ -11,10 +11,10 @@ #include <linux/spinlock.h> #include <asm/smp.h> #include <linux/uaccess.h> +#include <linux/debugfs.h> #include <asm/firmware.h> #include <asm/dtl.h> #include <asm/lppaca.h> -#include <asm/debugfs.h> #include <asm/plpar_wrappers.h> #include <asm/machdep.h> @@ -338,7 +338,7 @@ static int dtl_init(void) /* set up common debugfs structure */ - dtl_dir = debugfs_create_dir("dtl", powerpc_debugfs_root); + dtl_dir = debugfs_create_dir("dtl", arch_debugfs_dir); debugfs_create_x8("dtl_event_mask", 0600, dtl_dir, &dtl_event_mask); debugfs_create_u32("dtl_buf_entries", 0400, dtl_dir, &dtl_buf_entries); diff --git a/arch/powerpc/platforms/pseries/firmware.c b/arch/powerpc/platforms/pseries/firmware.c index 4c7b7f5a2ebc..f162156b7b68 100644 --- a/arch/powerpc/platforms/pseries/firmware.c +++ b/arch/powerpc/platforms/pseries/firmware.c @@ -119,10 +119,11 @@ struct vec5_fw_feature { static __initdata struct vec5_fw_feature vec5_fw_features_table[] = { - {FW_FEATURE_TYPE1_AFFINITY, OV5_TYPE1_AFFINITY}, + {FW_FEATURE_FORM1_AFFINITY, OV5_FORM1_AFFINITY}, {FW_FEATURE_PRRN, OV5_PRRN}, {FW_FEATURE_DRMEM_V2, OV5_DRMEM_V2}, {FW_FEATURE_DRC_INFO, OV5_DRC_INFO}, + {FW_FEATURE_FORM2_AFFINITY, OV5_FORM2_AFFINITY}, }; static void __init fw_vec5_feature_init(const char *vec5, unsigned long len) diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index 7e970f81d8ff..d646c22e94ab 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -39,6 +39,12 @@ /* This version can't take the spinlock, because it never returns */ static int rtas_stop_self_token = RTAS_UNKNOWN_SERVICE; +/* + * Record the CPU ids used on each nodes. + * Protected by cpu_add_remove_lock. + */ +static cpumask_var_t node_recorded_ids_map[MAX_NUMNODES]; + static void rtas_stop_self(void) { static struct rtas_args args; @@ -139,72 +145,148 @@ static void pseries_cpu_die(unsigned int cpu) paca_ptrs[cpu]->cpu_start = 0; } +/** + * find_cpu_id_range - found a linear ranger of @nthreads free CPU ids. + * @nthreads : the number of threads (cpu ids) + * @assigned_node : the node it belongs to or NUMA_NO_NODE if free ids from any + * node can be peek. + * @cpu_mask: the returned CPU mask. + * + * Returns 0 on success. + */ +static int find_cpu_id_range(unsigned int nthreads, int assigned_node, + cpumask_var_t *cpu_mask) +{ + cpumask_var_t candidate_mask; + unsigned int cpu, node; + int rc = -ENOSPC; + + if (!zalloc_cpumask_var(&candidate_mask, GFP_KERNEL)) + return -ENOMEM; + + cpumask_clear(*cpu_mask); + for (cpu = 0; cpu < nthreads; cpu++) + cpumask_set_cpu(cpu, *cpu_mask); + + BUG_ON(!cpumask_subset(cpu_present_mask, cpu_possible_mask)); + + /* Get a bitmap of unoccupied slots. */ + cpumask_xor(candidate_mask, cpu_possible_mask, cpu_present_mask); + + if (assigned_node != NUMA_NO_NODE) { + /* + * Remove free ids previously assigned on the other nodes. We + * can walk only online nodes because once a node became online + * it is not turned offlined back. + */ + for_each_online_node(node) { + if (node == assigned_node) + continue; + cpumask_andnot(candidate_mask, candidate_mask, + node_recorded_ids_map[node]); + } + } + + if (cpumask_empty(candidate_mask)) + goto out; + + while (!cpumask_empty(*cpu_mask)) { + if (cpumask_subset(*cpu_mask, candidate_mask)) + /* Found a range where we can insert the new cpu(s) */ + break; + cpumask_shift_left(*cpu_mask, *cpu_mask, nthreads); + } + + if (!cpumask_empty(*cpu_mask)) + rc = 0; + +out: + free_cpumask_var(candidate_mask); + return rc; +} + /* * Update cpu_present_mask and paca(s) for a new cpu node. The wrinkle - * here is that a cpu device node may represent up to two logical cpus + * here is that a cpu device node may represent multiple logical cpus * in the SMT case. We must honor the assumption in other code that * the logical ids for sibling SMT threads x and y are adjacent, such * that x^1 == y and y^1 == x. */ static int pseries_add_processor(struct device_node *np) { - unsigned int cpu; - cpumask_var_t candidate_mask, tmp; - int err = -ENOSPC, len, nthreads, i; + int len, nthreads, node, cpu, assigned_node; + int rc = 0; + cpumask_var_t cpu_mask; const __be32 *intserv; intserv = of_get_property(np, "ibm,ppc-interrupt-server#s", &len); if (!intserv) return 0; - zalloc_cpumask_var(&candidate_mask, GFP_KERNEL); - zalloc_cpumask_var(&tmp, GFP_KERNEL); - nthreads = len / sizeof(u32); - for (i = 0; i < nthreads; i++) - cpumask_set_cpu(i, tmp); - cpu_maps_update_begin(); + if (!alloc_cpumask_var(&cpu_mask, GFP_KERNEL)) + return -ENOMEM; - BUG_ON(!cpumask_subset(cpu_present_mask, cpu_possible_mask)); + /* + * Fetch from the DT nodes read by dlpar_configure_connector() the NUMA + * node id the added CPU belongs to. + */ + node = of_node_to_nid(np); + if (node < 0 || !node_possible(node)) + node = first_online_node; - /* Get a bitmap of unoccupied slots. */ - cpumask_xor(candidate_mask, cpu_possible_mask, cpu_present_mask); - if (cpumask_empty(candidate_mask)) { - /* If we get here, it most likely means that NR_CPUS is - * less than the partition's max processors setting. + BUG_ON(node == NUMA_NO_NODE); + assigned_node = node; + + cpu_maps_update_begin(); + + rc = find_cpu_id_range(nthreads, node, &cpu_mask); + if (rc && nr_node_ids > 1) { + /* + * Try again, considering the free CPU ids from the other node. */ - printk(KERN_ERR "Cannot add cpu %pOF; this system configuration" - " supports %d logical cpus.\n", np, - num_possible_cpus()); - goto out_unlock; + node = NUMA_NO_NODE; + rc = find_cpu_id_range(nthreads, NUMA_NO_NODE, &cpu_mask); } - while (!cpumask_empty(tmp)) - if (cpumask_subset(tmp, candidate_mask)) - /* Found a range where we can insert the new cpu(s) */ - break; - else - cpumask_shift_left(tmp, tmp, nthreads); - - if (cpumask_empty(tmp)) { - printk(KERN_ERR "Unable to find space in cpu_present_mask for" - " processor %pOFn with %d thread(s)\n", np, - nthreads); - goto out_unlock; + if (rc) { + pr_err("Cannot add cpu %pOF; this system configuration" + " supports %d logical cpus.\n", np, num_possible_cpus()); + goto out; } - for_each_cpu(cpu, tmp) { + for_each_cpu(cpu, cpu_mask) { BUG_ON(cpu_present(cpu)); set_cpu_present(cpu, true); set_hard_smp_processor_id(cpu, be32_to_cpu(*intserv++)); } - err = 0; -out_unlock: + + /* Record the newly used CPU ids for the associate node. */ + cpumask_or(node_recorded_ids_map[assigned_node], + node_recorded_ids_map[assigned_node], cpu_mask); + + /* + * If node is set to NUMA_NO_NODE, CPU ids have be reused from + * another node, remove them from its mask. + */ + if (node == NUMA_NO_NODE) { + cpu = cpumask_first(cpu_mask); + pr_warn("Reusing free CPU ids %d-%d from another node\n", + cpu, cpu + nthreads - 1); + for_each_online_node(node) { + if (node == assigned_node) + continue; + cpumask_andnot(node_recorded_ids_map[node], + node_recorded_ids_map[node], + cpu_mask); + } + } + +out: cpu_maps_update_done(); - free_cpumask_var(candidate_mask); - free_cpumask_var(tmp); - return err; + free_cpumask_var(cpu_mask); + return rc; } /* @@ -498,6 +580,8 @@ static ssize_t dlpar_cpu_add(u32 drc_index) return saved_rc; } + update_numa_distance(dn); + rc = dlpar_online_cpu(dn); if (rc) { saved_rc = rc; @@ -908,6 +992,7 @@ static struct notifier_block pseries_smp_nb = { static int __init pseries_cpu_hotplug_init(void) { int qcss_tok; + unsigned int node; #ifdef CONFIG_ARCH_CPU_PROBE_RELEASE ppc_md.cpu_probe = dlpar_cpu_probe; @@ -929,8 +1014,18 @@ static int __init pseries_cpu_hotplug_init(void) smp_ops->cpu_die = pseries_cpu_die; /* Processors can be added/removed only on LPAR */ - if (firmware_has_feature(FW_FEATURE_LPAR)) + if (firmware_has_feature(FW_FEATURE_LPAR)) { + for_each_node(node) { + alloc_bootmem_cpumask_var(&node_recorded_ids_map[node]); + + /* Record ids of CPU added at boot time */ + cpumask_or(node_recorded_ids_map[node], + node_recorded_ids_map[node], + cpumask_of_node(node)); + } + of_reconfig_notifier_register(&pseries_smp_nb); + } return 0; } diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 377d852f5a9a..44246ba59768 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -180,6 +180,8 @@ static int update_lmb_associativity_index(struct drmem_lmb *lmb) return -ENODEV; } + update_numa_distance(lmb_node); + dr_node = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory"); if (!dr_node) { dlpar_free_cc_nodes(lmb_node); @@ -211,13 +213,11 @@ static int update_lmb_associativity_index(struct drmem_lmb *lmb) static struct memory_block *lmb_to_memblock(struct drmem_lmb *lmb) { unsigned long section_nr; - struct mem_section *mem_sect; struct memory_block *mem_block; section_nr = pfn_to_section_nr(PFN_DOWN(lmb->base_addr)); - mem_sect = __nr_to_section(section_nr); - mem_block = find_memory_block(mem_sect); + mem_block = find_memory_block(section_nr); return mem_block; } @@ -979,6 +979,10 @@ static int pseries_memory_notifier(struct notifier_block *nb, case OF_RECONFIG_DETACH_NODE: err = pseries_remove_mem_node(rd->dn); break; + case OF_RECONFIG_UPDATE_PROPERTY: + if (!strcmp(rd->dn->name, + "ibm,dynamic-reconfiguration-memory")) + drmem_update_lmbs(rd->prop); } return notifier_from_errno(err); } diff --git a/arch/powerpc/platforms/pseries/ibmebus.c b/arch/powerpc/platforms/pseries/ibmebus.c index c6c79ef55e13..7ee3ed7d6cc2 100644 --- a/arch/powerpc/platforms/pseries/ibmebus.c +++ b/arch/powerpc/platforms/pseries/ibmebus.c @@ -366,14 +366,13 @@ static int ibmebus_bus_device_probe(struct device *dev) return error; } -static int ibmebus_bus_device_remove(struct device *dev) +static void ibmebus_bus_device_remove(struct device *dev) { struct platform_device *of_dev = to_platform_device(dev); struct platform_driver *drv = to_platform_driver(dev->driver); if (dev->driver && drv->remove) drv->remove(of_dev); - return 0; } static void ibmebus_bus_device_shutdown(struct device *dev) diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 0c55b991f665..dab5c56ffd0e 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -53,28 +53,31 @@ enum { DDW_EXT_QUERY_OUT_SIZE = 2 }; -static struct iommu_table_group *iommu_pseries_alloc_group(int node) +static struct iommu_table *iommu_pseries_alloc_table(int node) { - struct iommu_table_group *table_group; struct iommu_table *tbl; - table_group = kzalloc_node(sizeof(struct iommu_table_group), GFP_KERNEL, - node); - if (!table_group) - return NULL; - tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL, node); if (!tbl) - goto free_group; + return NULL; INIT_LIST_HEAD_RCU(&tbl->it_group_list); kref_init(&tbl->it_kref); + return tbl; +} + +static struct iommu_table_group *iommu_pseries_alloc_group(int node) +{ + struct iommu_table_group *table_group; - table_group->tables[0] = tbl; + table_group = kzalloc_node(sizeof(*table_group), GFP_KERNEL, node); + if (!table_group) + return NULL; - return table_group; + table_group->tables[0] = iommu_pseries_alloc_table(node); + if (table_group->tables[0]) + return table_group; -free_group: kfree(table_group); return NULL; } @@ -107,6 +110,8 @@ static int tce_build_pSeries(struct iommu_table *tbl, long index, u64 proto_tce; __be64 *tcep; u64 rpn; + const unsigned long tceshift = tbl->it_page_shift; + const unsigned long pagesize = IOMMU_PAGE_SIZE(tbl); proto_tce = TCE_PCI_READ; // Read allowed @@ -117,10 +122,10 @@ static int tce_build_pSeries(struct iommu_table *tbl, long index, while (npages--) { /* can't move this out since we might cross MEMBLOCK boundary */ - rpn = __pa(uaddr) >> TCE_SHIFT; - *tcep = cpu_to_be64(proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT); + rpn = __pa(uaddr) >> tceshift; + *tcep = cpu_to_be64(proto_tce | rpn << tceshift); - uaddr += TCE_PAGE_SIZE; + uaddr += pagesize; tcep++; } return 0; @@ -146,7 +151,7 @@ static unsigned long tce_get_pseries(struct iommu_table *tbl, long index) return be64_to_cpu(*tcep); } -static void tce_free_pSeriesLP(unsigned long liobn, long, long); +static void tce_free_pSeriesLP(unsigned long liobn, long, long, long); static void tce_freemulti_pSeriesLP(struct iommu_table*, long, long); static int tce_build_pSeriesLP(unsigned long liobn, long tcenum, long tceshift, @@ -166,12 +171,12 @@ static int tce_build_pSeriesLP(unsigned long liobn, long tcenum, long tceshift, proto_tce |= TCE_PCI_WRITE; while (npages--) { - tce = proto_tce | (rpn & TCE_RPN_MASK) << tceshift; + tce = proto_tce | rpn << tceshift; rc = plpar_tce_put((u64)liobn, (u64)tcenum << tceshift, tce); if (unlikely(rc == H_NOT_ENOUGH_RESOURCES)) { ret = (int)rc; - tce_free_pSeriesLP(liobn, tcenum_start, + tce_free_pSeriesLP(liobn, tcenum_start, tceshift, (npages_start - (npages + 1))); break; } @@ -205,10 +210,11 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, long tcenum_start = tcenum, npages_start = npages; int ret = 0; unsigned long flags; + const unsigned long tceshift = tbl->it_page_shift; if ((npages == 1) || !firmware_has_feature(FW_FEATURE_PUT_TCE_IND)) { return tce_build_pSeriesLP(tbl->it_index, tcenum, - tbl->it_page_shift, npages, uaddr, + tceshift, npages, uaddr, direction, attrs); } @@ -225,13 +231,13 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, if (!tcep) { local_irq_restore(flags); return tce_build_pSeriesLP(tbl->it_index, tcenum, - tbl->it_page_shift, + tceshift, npages, uaddr, direction, attrs); } __this_cpu_write(tce_page, tcep); } - rpn = __pa(uaddr) >> TCE_SHIFT; + rpn = __pa(uaddr) >> tceshift; proto_tce = TCE_PCI_READ; if (direction != DMA_TO_DEVICE) proto_tce |= TCE_PCI_WRITE; @@ -245,12 +251,12 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, limit = min_t(long, npages, 4096/TCE_ENTRY_SIZE); for (l = 0; l < limit; l++) { - tcep[l] = cpu_to_be64(proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT); + tcep[l] = cpu_to_be64(proto_tce | rpn << tceshift); rpn++; } rc = plpar_tce_put_indirect((u64)tbl->it_index, - (u64)tcenum << 12, + (u64)tcenum << tceshift, (u64)__pa(tcep), limit); @@ -277,12 +283,13 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, return ret; } -static void tce_free_pSeriesLP(unsigned long liobn, long tcenum, long npages) +static void tce_free_pSeriesLP(unsigned long liobn, long tcenum, long tceshift, + long npages) { u64 rc; while (npages--) { - rc = plpar_tce_put((u64)liobn, (u64)tcenum << 12, 0); + rc = plpar_tce_put((u64)liobn, (u64)tcenum << tceshift, 0); if (rc && printk_ratelimit()) { printk("tce_free_pSeriesLP: plpar_tce_put failed. rc=%lld\n", rc); @@ -301,9 +308,11 @@ static void tce_freemulti_pSeriesLP(struct iommu_table *tbl, long tcenum, long n u64 rc; if (!firmware_has_feature(FW_FEATURE_STUFF_TCE)) - return tce_free_pSeriesLP(tbl->it_index, tcenum, npages); + return tce_free_pSeriesLP(tbl->it_index, tcenum, + tbl->it_page_shift, npages); - rc = plpar_tce_stuff((u64)tbl->it_index, (u64)tcenum << 12, 0, npages); + rc = plpar_tce_stuff((u64)tbl->it_index, + (u64)tcenum << tbl->it_page_shift, 0, npages); if (rc && printk_ratelimit()) { printk("tce_freemulti_pSeriesLP: plpar_tce_stuff failed\n"); @@ -319,7 +328,8 @@ static unsigned long tce_get_pSeriesLP(struct iommu_table *tbl, long tcenum) u64 rc; unsigned long tce_ret; - rc = plpar_tce_get((u64)tbl->it_index, (u64)tcenum << 12, &tce_ret); + rc = plpar_tce_get((u64)tbl->it_index, + (u64)tcenum << tbl->it_page_shift, &tce_ret); if (rc && printk_ratelimit()) { printk("tce_get_pSeriesLP: plpar_tce_get failed. rc=%lld\n", rc); @@ -339,7 +349,7 @@ struct dynamic_dma_window_prop { __be32 window_shift; /* ilog2(tce_window_size) */ }; -struct direct_window { +struct dma_win { struct device_node *device; const struct dynamic_dma_window_prop *prop; struct list_head list; @@ -359,12 +369,13 @@ struct ddw_create_response { u32 addr_lo; }; -static LIST_HEAD(direct_window_list); +static LIST_HEAD(dma_win_list); /* prevents races between memory on/offline and window creation */ -static DEFINE_SPINLOCK(direct_window_list_lock); +static DEFINE_SPINLOCK(dma_win_list_lock); /* protects initializing window twice for same device */ -static DEFINE_MUTEX(direct_window_init_mutex); +static DEFINE_MUTEX(dma_win_init_mutex); #define DIRECT64_PROPNAME "linux,direct64-ddr-window-info" +#define DMA64_PROPNAME "linux,dma64-ddr-window-info" static int tce_clearrange_multi_pSeriesLP(unsigned long start_pfn, unsigned long num_pfn, const void *arg) @@ -491,6 +502,24 @@ static int tce_setrange_multi_pSeriesLP_walk(unsigned long start_pfn, return tce_setrange_multi_pSeriesLP(start_pfn, num_pfn, arg); } +static void iommu_table_setparms_common(struct iommu_table *tbl, unsigned long busno, + unsigned long liobn, unsigned long win_addr, + unsigned long window_size, unsigned long page_shift, + void *base, struct iommu_table_ops *table_ops) +{ + tbl->it_busno = busno; + tbl->it_index = liobn; + tbl->it_offset = win_addr >> page_shift; + tbl->it_size = window_size >> page_shift; + tbl->it_page_shift = page_shift; + tbl->it_base = (unsigned long)base; + tbl->it_blocksize = 16; + tbl->it_type = TCE_PCI; + tbl->it_ops = table_ops; +} + +struct iommu_table_ops iommu_table_pseries_ops; + static void iommu_table_setparms(struct pci_controller *phb, struct device_node *dn, struct iommu_table *tbl) @@ -499,8 +528,13 @@ static void iommu_table_setparms(struct pci_controller *phb, const unsigned long *basep; const u32 *sizep; - node = phb->dn; + /* Test if we are going over 2GB of DMA space */ + if (phb->dma_window_base_cur + phb->dma_window_size > SZ_2G) { + udbg_printf("PCI_DMA: Unexpected number of IOAs under this PHB.\n"); + panic("PCI_DMA: Unexpected number of IOAs under this PHB.\n"); + } + node = phb->dn; basep = of_get_property(node, "linux,tce-base", NULL); sizep = of_get_property(node, "linux,tce-size", NULL); if (basep == NULL || sizep == NULL) { @@ -509,33 +543,18 @@ static void iommu_table_setparms(struct pci_controller *phb, return; } - tbl->it_base = (unsigned long)__va(*basep); + iommu_table_setparms_common(tbl, phb->bus->number, 0, phb->dma_window_base_cur, + phb->dma_window_size, IOMMU_PAGE_SHIFT_4K, + __va(*basep), &iommu_table_pseries_ops); if (!is_kdump_kernel()) memset((void *)tbl->it_base, 0, *sizep); - tbl->it_busno = phb->bus->number; - tbl->it_page_shift = IOMMU_PAGE_SHIFT_4K; - - /* Units of tce entries */ - tbl->it_offset = phb->dma_window_base_cur >> tbl->it_page_shift; - - /* Test if we are going over 2GB of DMA space */ - if (phb->dma_window_base_cur + phb->dma_window_size > 0x80000000ul) { - udbg_printf("PCI_DMA: Unexpected number of IOAs under this PHB.\n"); - panic("PCI_DMA: Unexpected number of IOAs under this PHB.\n"); - } - phb->dma_window_base_cur += phb->dma_window_size; - - /* Set the tce table size - measured in entries */ - tbl->it_size = phb->dma_window_size >> tbl->it_page_shift; - - tbl->it_index = 0; - tbl->it_blocksize = 16; - tbl->it_type = TCE_PCI; } +struct iommu_table_ops iommu_table_lpar_multi_ops; + /* * iommu_table_setparms_lpar * @@ -547,17 +566,13 @@ static void iommu_table_setparms_lpar(struct pci_controller *phb, struct iommu_table_group *table_group, const __be32 *dma_window) { - unsigned long offset, size; + unsigned long offset, size, liobn; - of_parse_dma_window(dn, dma_window, &tbl->it_index, &offset, &size); + of_parse_dma_window(dn, dma_window, &liobn, &offset, &size); + + iommu_table_setparms_common(tbl, phb->bus->number, liobn, offset, size, IOMMU_PAGE_SHIFT_4K, NULL, + &iommu_table_lpar_multi_ops); - tbl->it_busno = phb->bus->number; - tbl->it_page_shift = IOMMU_PAGE_SHIFT_4K; - tbl->it_base = 0; - tbl->it_blocksize = 16; - tbl->it_type = TCE_PCI; - tbl->it_offset = offset >> tbl->it_page_shift; - tbl->it_size = size >> tbl->it_page_shift; table_group->tce32_start = offset; table_group->tce32_size = size; @@ -637,7 +652,7 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus) tbl = pci->table_group->tables[0]; iommu_table_setparms(pci->phb, dn, tbl); - tbl->it_ops = &iommu_table_pseries_ops; + if (!iommu_init_table(tbl, pci->phb->node, 0, 0)) panic("Failed to initialize iommu table"); @@ -698,7 +713,10 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) pr_debug("pci_dma_bus_setup_pSeriesLP: setting up bus %pOF\n", dn); - /* Find nearest ibm,dma-window, walking up the device tree */ + /* + * Find nearest ibm,dma-window (default DMA window), walking up the + * device tree + */ for (pdn = dn; pdn != NULL; pdn = pdn->parent) { dma_window = of_get_property(pdn, "ibm,dma-window", NULL); if (dma_window != NULL) @@ -720,7 +738,7 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) tbl = ppci->table_group->tables[0]; iommu_table_setparms_lpar(ppci->phb, pdn, tbl, ppci->table_group, dma_window); - tbl->it_ops = &iommu_table_lpar_multi_ops; + if (!iommu_init_table(tbl, ppci->phb->node, 0, 0)) panic("Failed to initialize iommu table"); iommu_register_group(ppci->table_group, @@ -750,7 +768,7 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev) PCI_DN(dn)->table_group = iommu_pseries_alloc_group(phb->node); tbl = PCI_DN(dn)->table_group->tables[0]; iommu_table_setparms(phb, dn, tbl); - tbl->it_ops = &iommu_table_pseries_ops; + if (!iommu_init_table(tbl, phb->node, 0, 0)) panic("Failed to initialize iommu table"); @@ -785,17 +803,10 @@ static int __init disable_ddw_setup(char *str) early_param("disable_ddw", disable_ddw_setup); -static void remove_dma_window(struct device_node *np, u32 *ddw_avail, - struct property *win) +static void clean_dma_window(struct device_node *np, struct dynamic_dma_window_prop *dwp) { - struct dynamic_dma_window_prop *dwp; - u64 liobn; int ret; - dwp = win->value; - liobn = (u64)be32_to_cpu(dwp->liobn); - - /* clear the whole window, note the arg is in kernel pages */ ret = tce_clearrange_multi_pSeriesLP(0, 1ULL << (be32_to_cpu(dwp->window_shift) - PAGE_SHIFT), dwp); if (ret) @@ -804,94 +815,136 @@ static void remove_dma_window(struct device_node *np, u32 *ddw_avail, else pr_debug("%pOF successfully cleared tces in window.\n", np); +} + +/* + * Call only if DMA window is clean. + */ +static void __remove_dma_window(struct device_node *np, u32 *ddw_avail, u64 liobn) +{ + int ret; ret = rtas_call(ddw_avail[DDW_REMOVE_PE_DMA_WIN], 1, 1, NULL, liobn); if (ret) - pr_warn("%pOF: failed to remove direct window: rtas returned " + pr_warn("%pOF: failed to remove DMA window: rtas returned " "%d to ibm,remove-pe-dma-window(%x) %llx\n", np, ret, ddw_avail[DDW_REMOVE_PE_DMA_WIN], liobn); else - pr_debug("%pOF: successfully removed direct window: rtas returned " + pr_debug("%pOF: successfully removed DMA window: rtas returned " "%d to ibm,remove-pe-dma-window(%x) %llx\n", np, ret, ddw_avail[DDW_REMOVE_PE_DMA_WIN], liobn); } -static void remove_ddw(struct device_node *np, bool remove_prop) +static void remove_dma_window(struct device_node *np, u32 *ddw_avail, + struct property *win) +{ + struct dynamic_dma_window_prop *dwp; + u64 liobn; + + dwp = win->value; + liobn = (u64)be32_to_cpu(dwp->liobn); + + clean_dma_window(np, dwp); + __remove_dma_window(np, ddw_avail, liobn); +} + +static int remove_ddw(struct device_node *np, bool remove_prop, const char *win_name) { struct property *win; u32 ddw_avail[DDW_APPLICABLE_SIZE]; int ret = 0; + win = of_find_property(np, win_name, NULL); + if (!win) + return -EINVAL; + ret = of_property_read_u32_array(np, "ibm,ddw-applicable", &ddw_avail[0], DDW_APPLICABLE_SIZE); if (ret) - return; + return 0; - win = of_find_property(np, DIRECT64_PROPNAME, NULL); - if (!win) - return; if (win->length >= sizeof(struct dynamic_dma_window_prop)) remove_dma_window(np, ddw_avail, win); if (!remove_prop) - return; + return 0; ret = of_remove_property(np, win); if (ret) - pr_warn("%pOF: failed to remove direct window property: %d\n", + pr_warn("%pOF: failed to remove DMA window property: %d\n", np, ret); + return 0; } -static u64 find_existing_ddw(struct device_node *pdn, int *window_shift) +static bool find_existing_ddw(struct device_node *pdn, u64 *dma_addr, int *window_shift) { - struct direct_window *window; - const struct dynamic_dma_window_prop *direct64; - u64 dma_addr = 0; + struct dma_win *window; + const struct dynamic_dma_window_prop *dma64; + bool found = false; - spin_lock(&direct_window_list_lock); + spin_lock(&dma_win_list_lock); /* check if we already created a window and dupe that config if so */ - list_for_each_entry(window, &direct_window_list, list) { + list_for_each_entry(window, &dma_win_list, list) { if (window->device == pdn) { - direct64 = window->prop; - dma_addr = be64_to_cpu(direct64->dma_base); - *window_shift = be32_to_cpu(direct64->window_shift); + dma64 = window->prop; + *dma_addr = be64_to_cpu(dma64->dma_base); + *window_shift = be32_to_cpu(dma64->window_shift); + found = true; break; } } - spin_unlock(&direct_window_list_lock); + spin_unlock(&dma_win_list_lock); - return dma_addr; + return found; } -static int find_existing_ddw_windows(void) +static struct dma_win *ddw_list_new_entry(struct device_node *pdn, + const struct dynamic_dma_window_prop *dma64) { - int len; - struct device_node *pdn; - struct direct_window *window; - const struct dynamic_dma_window_prop *direct64; + struct dma_win *window; - if (!firmware_has_feature(FW_FEATURE_LPAR)) - return 0; + window = kzalloc(sizeof(*window), GFP_KERNEL); + if (!window) + return NULL; - for_each_node_with_property(pdn, DIRECT64_PROPNAME) { - direct64 = of_get_property(pdn, DIRECT64_PROPNAME, &len); - if (!direct64) - continue; + window->device = pdn; + window->prop = dma64; - window = kzalloc(sizeof(*window), GFP_KERNEL); - if (!window || len < sizeof(struct dynamic_dma_window_prop)) { - kfree(window); - remove_ddw(pdn, true); + return window; +} + +static void find_existing_ddw_windows_named(const char *name) +{ + int len; + struct device_node *pdn; + struct dma_win *window; + const struct dynamic_dma_window_prop *dma64; + + for_each_node_with_property(pdn, name) { + dma64 = of_get_property(pdn, name, &len); + if (!dma64 || len < sizeof(*dma64)) { + remove_ddw(pdn, true, name); continue; } - window->device = pdn; - window->prop = direct64; - spin_lock(&direct_window_list_lock); - list_add(&window->list, &direct_window_list); - spin_unlock(&direct_window_list_lock); + window = ddw_list_new_entry(pdn, dma64); + if (!window) + break; + + spin_lock(&dma_win_list_lock); + list_add(&window->list, &dma_win_list); + spin_unlock(&dma_win_list_lock); } +} + +static int find_existing_ddw_windows(void) +{ + if (!firmware_has_feature(FW_FEATURE_LPAR)) + return 0; + + find_existing_ddw_windows_named(DIRECT64_PROPNAME); + find_existing_ddw_windows_named(DMA64_PROPNAME); return 0; } @@ -1130,6 +1183,35 @@ static int iommu_get_page_shift(u32 query_page_size) return 0; } +static struct property *ddw_property_create(const char *propname, u32 liobn, u64 dma_addr, + u32 page_shift, u32 window_shift) +{ + struct dynamic_dma_window_prop *ddwprop; + struct property *win64; + + win64 = kzalloc(sizeof(*win64), GFP_KERNEL); + if (!win64) + return NULL; + + win64->name = kstrdup(propname, GFP_KERNEL); + ddwprop = kzalloc(sizeof(*ddwprop), GFP_KERNEL); + win64->value = ddwprop; + win64->length = sizeof(*ddwprop); + if (!win64->name || !win64->value) { + kfree(win64->name); + kfree(win64->value); + kfree(win64); + return NULL; + } + + ddwprop->liobn = cpu_to_be32(liobn); + ddwprop->dma_base = cpu_to_be64(dma_addr); + ddwprop->tce_shift = cpu_to_be32(page_shift); + ddwprop->window_shift = cpu_to_be32(window_shift); + + return win64; +} + /* * If the PE supports dynamic dma windows, and there is space for a table * that can map all pages in a linear offset, then setup such a table, @@ -1139,34 +1221,39 @@ static int iommu_get_page_shift(u32 query_page_size) * pdn: the parent pe node with the ibm,dma_window property * Future: also check if we can remap the base window for our base page size * - * returns the dma offset for use by the direct mapped DMA code. + * returns true if can map all pages (direct mapping), false otherwise.. */ -static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) +static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn) { int len = 0, ret; int max_ram_len = order_base_2(ddw_memory_hotplug_max()); struct ddw_query_response query; struct ddw_create_response create; int page_shift; - u64 dma_addr; + u64 win_addr; + const char *win_name; struct device_node *dn; u32 ddw_avail[DDW_APPLICABLE_SIZE]; - struct direct_window *window; + struct dma_win *window; struct property *win64; - struct dynamic_dma_window_prop *ddwprop; + bool ddw_enabled = false; struct failed_ddw_pdn *fpdn; - bool default_win_removed = false; + bool default_win_removed = false, direct_mapping = false; bool pmem_present; + struct pci_dn *pci = PCI_DN(pdn); + struct iommu_table *tbl = pci->table_group->tables[0]; dn = of_find_node_by_type(NULL, "ibm,pmemory"); pmem_present = dn != NULL; of_node_put(dn); - mutex_lock(&direct_window_init_mutex); + mutex_lock(&dma_win_init_mutex); - dma_addr = find_existing_ddw(pdn, &len); - if (dma_addr != 0) + if (find_existing_ddw(pdn, &dev->dev.archdata.dma_offset, &len)) { + direct_mapping = (len >= max_ram_len); + ddw_enabled = true; goto out_unlock; + } /* * If we already went through this for a previous function of @@ -1240,12 +1327,12 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) page_shift = iommu_get_page_shift(query.page_size); if (!page_shift) { - dev_dbg(&dev->dev, "no supported direct page size in mask %x", - query.page_size); + dev_dbg(&dev->dev, "no supported page size in mask %x", + query.page_size); goto out_failed; } - /* verify the window * number of ptes will map the partition */ - /* check largest block * page size > max memory hotplug addr */ + + /* * The "ibm,pmemory" can appear anywhere in the address space. * Assuming it is still backed by page structs, try MAX_PHYSMEM_BITS @@ -1261,81 +1348,127 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) dev_info(&dev->dev, "Skipping ibm,pmemory"); } + /* check if the available block * number of ptes will map everything */ if (query.largest_available_block < (1ULL << (len - page_shift))) { dev_dbg(&dev->dev, "can't map partition max 0x%llx with %llu %llu-sized pages\n", 1ULL << len, query.largest_available_block, 1ULL << page_shift); - goto out_failed; - } - win64 = kzalloc(sizeof(struct property), GFP_KERNEL); - if (!win64) { - dev_info(&dev->dev, - "couldn't allocate property for 64bit dma window\n"); - goto out_failed; - } - win64->name = kstrdup(DIRECT64_PROPNAME, GFP_KERNEL); - win64->value = ddwprop = kmalloc(sizeof(*ddwprop), GFP_KERNEL); - win64->length = sizeof(*ddwprop); - if (!win64->name || !win64->value) { - dev_info(&dev->dev, - "couldn't allocate property name and value\n"); - goto out_free_prop; + + /* DDW + IOMMU on single window may fail if there is any allocation */ + if (default_win_removed && iommu_table_in_use(tbl)) { + dev_dbg(&dev->dev, "current IOMMU table in use, can't be replaced.\n"); + goto out_failed; + } + + len = order_base_2(query.largest_available_block << page_shift); + win_name = DMA64_PROPNAME; + } else { + direct_mapping = true; + win_name = DIRECT64_PROPNAME; } ret = create_ddw(dev, ddw_avail, &create, page_shift, len); if (ret != 0) - goto out_free_prop; - - ddwprop->liobn = cpu_to_be32(create.liobn); - ddwprop->dma_base = cpu_to_be64(((u64)create.addr_hi << 32) | - create.addr_lo); - ddwprop->tce_shift = cpu_to_be32(page_shift); - ddwprop->window_shift = cpu_to_be32(len); + goto out_failed; dev_dbg(&dev->dev, "created tce table LIOBN 0x%x for %pOF\n", create.liobn, dn); - window = kzalloc(sizeof(*window), GFP_KERNEL); - if (!window) - goto out_clear_window; + win_addr = ((u64)create.addr_hi << 32) | create.addr_lo; + win64 = ddw_property_create(win_name, create.liobn, win_addr, page_shift, len); - ret = walk_system_ram_range(0, memblock_end_of_DRAM() >> PAGE_SHIFT, - win64->value, tce_setrange_multi_pSeriesLP_walk); - if (ret) { - dev_info(&dev->dev, "failed to map direct window for %pOF: %d\n", - dn, ret); - goto out_free_window; + if (!win64) { + dev_info(&dev->dev, + "couldn't allocate property, property name, or value\n"); + goto out_remove_win; } ret = of_add_property(pdn, win64); if (ret) { - dev_err(&dev->dev, "unable to add dma window property for %pOF: %d", - pdn, ret); - goto out_free_window; + dev_err(&dev->dev, "unable to add DMA window property for %pOF: %d", + pdn, ret); + goto out_free_prop; } - window->device = pdn; - window->prop = ddwprop; - spin_lock(&direct_window_list_lock); - list_add(&window->list, &direct_window_list); - spin_unlock(&direct_window_list_lock); + window = ddw_list_new_entry(pdn, win64->value); + if (!window) + goto out_del_prop; + + if (direct_mapping) { + /* DDW maps the whole partition, so enable direct DMA mapping */ + ret = walk_system_ram_range(0, memblock_end_of_DRAM() >> PAGE_SHIFT, + win64->value, tce_setrange_multi_pSeriesLP_walk); + if (ret) { + dev_info(&dev->dev, "failed to map DMA window for %pOF: %d\n", + dn, ret); + + /* Make sure to clean DDW if any TCE was set*/ + clean_dma_window(pdn, win64->value); + goto out_del_list; + } + } else { + struct iommu_table *newtbl; + int i; + + for (i = 0; i < ARRAY_SIZE(pci->phb->mem_resources); i++) { + const unsigned long mask = IORESOURCE_MEM_64 | IORESOURCE_MEM; + + /* Look for MMIO32 */ + if ((pci->phb->mem_resources[i].flags & mask) == IORESOURCE_MEM) + break; + } + + if (i == ARRAY_SIZE(pci->phb->mem_resources)) + goto out_del_list; + + /* New table for using DDW instead of the default DMA window */ + newtbl = iommu_pseries_alloc_table(pci->phb->node); + if (!newtbl) { + dev_dbg(&dev->dev, "couldn't create new IOMMU table\n"); + goto out_del_list; + } + + iommu_table_setparms_common(newtbl, pci->phb->bus->number, create.liobn, win_addr, + 1UL << len, page_shift, NULL, &iommu_table_lpar_multi_ops); + iommu_init_table(newtbl, pci->phb->node, pci->phb->mem_resources[i].start, + pci->phb->mem_resources[i].end); - dma_addr = be64_to_cpu(ddwprop->dma_base); + pci->table_group->tables[1] = newtbl; + + /* Keep default DMA window stuct if removed */ + if (default_win_removed) { + tbl->it_size = 0; + kfree(tbl->it_map); + } + + set_iommu_table_base(&dev->dev, newtbl); + } + + spin_lock(&dma_win_list_lock); + list_add(&window->list, &dma_win_list); + spin_unlock(&dma_win_list_lock); + + dev->dev.archdata.dma_offset = win_addr; + ddw_enabled = true; goto out_unlock; -out_free_window: +out_del_list: kfree(window); -out_clear_window: - remove_ddw(pdn, true); +out_del_prop: + of_remove_property(pdn, win64); out_free_prop: kfree(win64->name); kfree(win64->value); kfree(win64); +out_remove_win: + /* DDW is clean, so it's ok to call this directly. */ + __remove_dma_window(pdn, ddw_avail, create.liobn); + out_failed: if (default_win_removed) reset_dma_window(dev, pdn); @@ -1347,17 +1480,17 @@ out_failed: list_add(&fpdn->list, &failed_ddw_pdn_list); out_unlock: - mutex_unlock(&direct_window_init_mutex); + mutex_unlock(&dma_win_init_mutex); /* * If we have persistent memory and the window size is only as big * as RAM, then we failed to create a window to cover persistent * memory and need to set the DMA limit. */ - if (pmem_present && dma_addr && (len == max_ram_len)) - dev->dev.bus_dma_limit = dma_addr + (1ULL << len); + if (pmem_present && ddw_enabled && direct_mapping && len == max_ram_len) + dev->dev.bus_dma_limit = dev->dev.archdata.dma_offset + (1ULL << len); - return dma_addr; + return ddw_enabled && direct_mapping; } static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) @@ -1399,7 +1532,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) tbl = pci->table_group->tables[0]; iommu_table_setparms_lpar(pci->phb, pdn, tbl, pci->table_group, dma_window); - tbl->it_ops = &iommu_table_lpar_multi_ops; + iommu_init_table(tbl, pci->phb->node, 0, 0); iommu_register_group(pci->table_group, pci_domain_nr(pci->phb->bus), 0); @@ -1436,11 +1569,8 @@ static bool iommu_bypass_supported_pSeriesLP(struct pci_dev *pdev, u64 dma_mask) break; } - if (pdn && PCI_DN(pdn)) { - pdev->dev.archdata.dma_offset = enable_ddw(pdev, pdn); - if (pdev->dev.archdata.dma_offset) - return true; - } + if (pdn && PCI_DN(pdn)) + return enable_ddw(pdev, pdn); return false; } @@ -1448,29 +1578,29 @@ static bool iommu_bypass_supported_pSeriesLP(struct pci_dev *pdev, u64 dma_mask) static int iommu_mem_notifier(struct notifier_block *nb, unsigned long action, void *data) { - struct direct_window *window; + struct dma_win *window; struct memory_notify *arg = data; int ret = 0; switch (action) { case MEM_GOING_ONLINE: - spin_lock(&direct_window_list_lock); - list_for_each_entry(window, &direct_window_list, list) { + spin_lock(&dma_win_list_lock); + list_for_each_entry(window, &dma_win_list, list) { ret |= tce_setrange_multi_pSeriesLP(arg->start_pfn, arg->nr_pages, window->prop); /* XXX log error */ } - spin_unlock(&direct_window_list_lock); + spin_unlock(&dma_win_list_lock); break; case MEM_CANCEL_ONLINE: case MEM_OFFLINE: - spin_lock(&direct_window_list_lock); - list_for_each_entry(window, &direct_window_list, list) { + spin_lock(&dma_win_list_lock); + list_for_each_entry(window, &dma_win_list, list) { ret |= tce_clearrange_multi_pSeriesLP(arg->start_pfn, arg->nr_pages, window->prop); /* XXX log error */ } - spin_unlock(&direct_window_list_lock); + spin_unlock(&dma_win_list_lock); break; default: break; @@ -1491,7 +1621,7 @@ static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long acti struct of_reconfig_data *rd = data; struct device_node *np = rd->dn; struct pci_dn *pci = PCI_DN(np); - struct direct_window *window; + struct dma_win *window; switch (action) { case OF_RECONFIG_DETACH_NODE: @@ -1502,20 +1632,22 @@ static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long acti * we have to remove the property when releasing * the device node. */ - remove_ddw(np, false); + if (remove_ddw(np, false, DIRECT64_PROPNAME)) + remove_ddw(np, false, DMA64_PROPNAME); + if (pci && pci->table_group) iommu_pseries_free_group(pci->table_group, np->full_name); - spin_lock(&direct_window_list_lock); - list_for_each_entry(window, &direct_window_list, list) { + spin_lock(&dma_win_list_lock); + list_for_each_entry(window, &dma_win_list, list) { if (window->device == np) { list_del(&window->list); kfree(window); break; } } - spin_unlock(&direct_window_list_lock); + spin_unlock(&dma_win_list_lock); break; default: err = NOTIFY_DONE; diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index dab356e3ff87..3df6bdfea475 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -22,6 +22,8 @@ #include <linux/workqueue.h> #include <linux/proc_fs.h> #include <linux/pgtable.h> +#include <linux/debugfs.h> + #include <asm/processor.h> #include <asm/mmu.h> #include <asm/page.h> @@ -39,7 +41,6 @@ #include <asm/kexec.h> #include <asm/fadump.h> #include <asm/asm-prototypes.h> -#include <asm/debugfs.h> #include <asm/dtl.h> #include "pseries.h" @@ -261,7 +262,7 @@ static int cpu_relative_dispatch_distance(int last_disp_cpu, int cur_disp_cpu) if (!last_disp_cpu_assoc || !cur_disp_cpu_assoc) return -EIO; - return cpu_distance(last_disp_cpu_assoc, cur_disp_cpu_assoc); + return cpu_relative_distance(last_disp_cpu_assoc, cur_disp_cpu_assoc); } static int cpu_home_node_dispatch_distance(int disp_cpu) @@ -281,7 +282,7 @@ static int cpu_home_node_dispatch_distance(int disp_cpu) if (!disp_cpu_assoc || !vcpu_assoc) return -EIO; - return cpu_distance(disp_cpu_assoc, vcpu_assoc); + return cpu_relative_distance(disp_cpu_assoc, vcpu_assoc); } static void update_vcpu_disp_stat(int disp_cpu) @@ -801,7 +802,8 @@ static long pSeries_lpar_hpte_remove(unsigned long hpte_group) return -1; } -static void manual_hpte_clear_all(void) +/* Called during kexec sequence with MMU off */ +static notrace void manual_hpte_clear_all(void) { unsigned long size_bytes = 1UL << ppc64_pft_size; unsigned long hpte_count = size_bytes >> 4; @@ -834,7 +836,8 @@ static void manual_hpte_clear_all(void) } } -static int hcall_hpte_clear_all(void) +/* Called during kexec sequence with MMU off */ +static notrace int hcall_hpte_clear_all(void) { int rc; @@ -845,7 +848,8 @@ static int hcall_hpte_clear_all(void) return rc; } -static void pseries_hpte_clear_all(void) +/* Called during kexec sequence with MMU off */ +static notrace void pseries_hpte_clear_all(void) { int rc; @@ -2016,7 +2020,7 @@ static int __init vpa_debugfs_init(void) if (!firmware_has_feature(FW_FEATURE_SPLPAR)) return 0; - vpa_dir = debugfs_create_dir("vpa", powerpc_debugfs_root); + vpa_dir = debugfs_create_dir("vpa", arch_debugfs_dir); /* set up the per-cpu vpa file*/ for_each_possible_cpu(i) { diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c index 637300330507..1b305e411862 100644 --- a/arch/powerpc/platforms/pseries/msi.c +++ b/arch/powerpc/platforms/pseries/msi.c @@ -13,6 +13,7 @@ #include <asm/hw_irq.h> #include <asm/ppc-pci.h> #include <asm/machdep.h> +#include <asm/xive.h> #include "pseries.h" @@ -110,21 +111,6 @@ static int rtas_query_irq_number(struct pci_dn *pdn, int offset) return rtas_ret[0]; } -static void rtas_teardown_msi_irqs(struct pci_dev *pdev) -{ - struct msi_desc *entry; - - for_each_pci_msi_entry(entry, pdev) { - if (!entry->irq) - continue; - - irq_set_msi_desc(entry->irq, NULL); - irq_dispose_mapping(entry->irq); - } - - rtas_disable_msi(pdev); -} - static int check_req(struct pci_dev *pdev, int nvec, char *prop_name) { struct device_node *dn; @@ -164,12 +150,12 @@ static int check_req_msix(struct pci_dev *pdev, int nvec) /* Quota calculation */ -static struct device_node *find_pe_total_msi(struct pci_dev *dev, int *total) +static struct device_node *__find_pe_total_msi(struct device_node *node, int *total) { struct device_node *dn; const __be32 *p; - dn = of_node_get(pci_device_to_OF_node(dev)); + dn = of_node_get(node); while (dn) { p = of_get_property(dn, "ibm,pe-total-#msi", NULL); if (p) { @@ -185,6 +171,11 @@ static struct device_node *find_pe_total_msi(struct pci_dev *dev, int *total) return NULL; } +static struct device_node *find_pe_total_msi(struct pci_dev *dev, int *total) +{ + return __find_pe_total_msi(pci_device_to_OF_node(dev), total); +} + static struct device_node *find_pe_dn(struct pci_dev *dev, int *total) { struct device_node *dn; @@ -368,12 +359,11 @@ static void rtas_hack_32bit_msi_gen2(struct pci_dev *pdev) pci_write_config_dword(pdev, pdev->msi_cap + PCI_MSI_ADDRESS_HI, 0); } -static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec_in, int type) +static int rtas_prepare_msi_irqs(struct pci_dev *pdev, int nvec_in, int type, + msi_alloc_info_t *arg) { struct pci_dn *pdn; - int hwirq, virq, i, quota, rc; - struct msi_desc *entry; - struct msi_msg msg; + int quota, rc; int nvec = nvec_in; int use_32bit_msi_hack = 0; @@ -451,53 +441,229 @@ again: return rc; } - i = 0; - for_each_pci_msi_entry(entry, pdev) { - hwirq = rtas_query_irq_number(pdn, i++); - if (hwirq < 0) { - pr_debug("rtas_msi: error (%d) getting hwirq\n", rc); - return hwirq; - } + return 0; +} - /* - * Depending on the number of online CPUs in the original - * kernel, it is likely for CPU #0 to be offline in a kdump - * kernel. The associated IRQs in the affinity mappings - * provided by irq_create_affinity_masks() are thus not - * started by irq_startup(), as per-design for managed IRQs. - * This can be a problem with multi-queue block devices driven - * by blk-mq : such a non-started IRQ is very likely paired - * with the single queue enforced by blk-mq during kdump (see - * blk_mq_alloc_tag_set()). This causes the device to remain - * silent and likely hangs the guest at some point. - * - * We don't really care for fine-grained affinity when doing - * kdump actually : simply ignore the pre-computed affinity - * masks in this case and let the default mask with all CPUs - * be used when creating the IRQ mappings. - */ - if (is_kdump_kernel()) - virq = irq_create_mapping(NULL, hwirq); - else - virq = irq_create_mapping_affinity(NULL, hwirq, - entry->affinity); +static int pseries_msi_ops_prepare(struct irq_domain *domain, struct device *dev, + int nvec, msi_alloc_info_t *arg) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct msi_desc *desc = first_pci_msi_entry(pdev); + int type = desc->msi_attrib.is_msix ? PCI_CAP_ID_MSIX : PCI_CAP_ID_MSI; - if (!virq) { - pr_debug("rtas_msi: Failed mapping hwirq %d\n", hwirq); - return -ENOSPC; - } + return rtas_prepare_msi_irqs(pdev, nvec, type, arg); +} + +/* + * ->msi_free() is called before irq_domain_free_irqs_top() when the + * handler data is still available. Use that to clear the XIVE + * controller data. + */ +static void pseries_msi_ops_msi_free(struct irq_domain *domain, + struct msi_domain_info *info, + unsigned int irq) +{ + if (xive_enabled()) + xive_irq_free_data(irq); +} + +/* + * RTAS can not disable one MSI at a time. It's all or nothing. Do it + * at the end after all IRQs have been freed. + */ +static void pseries_msi_domain_free_irqs(struct irq_domain *domain, + struct device *dev) +{ + if (WARN_ON_ONCE(!dev_is_pci(dev))) + return; + + __msi_domain_free_irqs(domain, dev); + + rtas_disable_msi(to_pci_dev(dev)); +} + +static struct msi_domain_ops pseries_pci_msi_domain_ops = { + .msi_prepare = pseries_msi_ops_prepare, + .msi_free = pseries_msi_ops_msi_free, + .domain_free_irqs = pseries_msi_domain_free_irqs, +}; + +static void pseries_msi_shutdown(struct irq_data *d) +{ + d = d->parent_data; + if (d->chip->irq_shutdown) + d->chip->irq_shutdown(d); +} + +static void pseries_msi_mask(struct irq_data *d) +{ + pci_msi_mask_irq(d); + irq_chip_mask_parent(d); +} + +static void pseries_msi_unmask(struct irq_data *d) +{ + pci_msi_unmask_irq(d); + irq_chip_unmask_parent(d); +} - dev_dbg(&pdev->dev, "rtas_msi: allocated virq %d\n", virq); - irq_set_msi_desc(virq, entry); +static struct irq_chip pseries_pci_msi_irq_chip = { + .name = "pSeries-PCI-MSI", + .irq_shutdown = pseries_msi_shutdown, + .irq_mask = pseries_msi_mask, + .irq_unmask = pseries_msi_unmask, + .irq_eoi = irq_chip_eoi_parent, +}; + +static struct msi_domain_info pseries_msi_domain_info = { + .flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | + MSI_FLAG_MULTI_PCI_MSI | MSI_FLAG_PCI_MSIX), + .ops = &pseries_pci_msi_domain_ops, + .chip = &pseries_pci_msi_irq_chip, +}; + +static void pseries_msi_compose_msg(struct irq_data *data, struct msi_msg *msg) +{ + __pci_read_msi_msg(irq_data_get_msi_desc(data), msg); +} + +static struct irq_chip pseries_msi_irq_chip = { + .name = "pSeries-MSI", + .irq_shutdown = pseries_msi_shutdown, + .irq_mask = irq_chip_mask_parent, + .irq_unmask = irq_chip_unmask_parent, + .irq_eoi = irq_chip_eoi_parent, + .irq_set_affinity = irq_chip_set_affinity_parent, + .irq_compose_msi_msg = pseries_msi_compose_msg, +}; + +static int pseries_irq_parent_domain_alloc(struct irq_domain *domain, unsigned int virq, + irq_hw_number_t hwirq) +{ + struct irq_fwspec parent_fwspec; + int ret; + + parent_fwspec.fwnode = domain->parent->fwnode; + parent_fwspec.param_count = 2; + parent_fwspec.param[0] = hwirq; + parent_fwspec.param[1] = IRQ_TYPE_EDGE_RISING; + + ret = irq_domain_alloc_irqs_parent(domain, virq, 1, &parent_fwspec); + if (ret) + return ret; + + return 0; +} + +static int pseries_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *arg) +{ + struct pci_controller *phb = domain->host_data; + msi_alloc_info_t *info = arg; + struct msi_desc *desc = info->desc; + struct pci_dev *pdev = msi_desc_to_pci_dev(desc); + int hwirq; + int i, ret; + + hwirq = rtas_query_irq_number(pci_get_pdn(pdev), desc->msi_attrib.entry_nr); + if (hwirq < 0) { + dev_err(&pdev->dev, "Failed to query HW IRQ: %d\n", hwirq); + return hwirq; + } + + dev_dbg(&pdev->dev, "%s bridge %pOF %d/%x #%d\n", __func__, + phb->dn, virq, hwirq, nr_irqs); + + for (i = 0; i < nr_irqs; i++) { + ret = pseries_irq_parent_domain_alloc(domain, virq + i, hwirq + i); + if (ret) + goto out; + + irq_domain_set_hwirq_and_chip(domain, virq + i, hwirq + i, + &pseries_msi_irq_chip, domain->host_data); + } + + return 0; + +out: + /* TODO: handle RTAS cleanup in ->msi_finish() ? */ + irq_domain_free_irqs_parent(domain, virq, i - 1); + return ret; +} + +static void pseries_irq_domain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) +{ + struct irq_data *d = irq_domain_get_irq_data(domain, virq); + struct pci_controller *phb = irq_data_get_irq_chip_data(d); + + pr_debug("%s bridge %pOF %d #%d\n", __func__, phb->dn, virq, nr_irqs); + + /* XIVE domain data is cleared through ->msi_free() */ +} - /* Read config space back so we can restore after reset */ - __pci_read_msi_msg(entry, &msg); - entry->msg = msg; +static const struct irq_domain_ops pseries_irq_domain_ops = { + .alloc = pseries_irq_domain_alloc, + .free = pseries_irq_domain_free, +}; + +static int __pseries_msi_allocate_domains(struct pci_controller *phb, + unsigned int count) +{ + struct irq_domain *parent = irq_get_default_host(); + + phb->fwnode = irq_domain_alloc_named_id_fwnode("pSeries-MSI", + phb->global_number); + if (!phb->fwnode) + return -ENOMEM; + + phb->dev_domain = irq_domain_create_hierarchy(parent, 0, count, + phb->fwnode, + &pseries_irq_domain_ops, phb); + if (!phb->dev_domain) { + pr_err("PCI: failed to create IRQ domain bridge %pOF (domain %d)\n", + phb->dn, phb->global_number); + irq_domain_free_fwnode(phb->fwnode); + return -ENOMEM; + } + + phb->msi_domain = pci_msi_create_irq_domain(of_node_to_fwnode(phb->dn), + &pseries_msi_domain_info, + phb->dev_domain); + if (!phb->msi_domain) { + pr_err("PCI: failed to create MSI IRQ domain bridge %pOF (domain %d)\n", + phb->dn, phb->global_number); + irq_domain_free_fwnode(phb->fwnode); + irq_domain_remove(phb->dev_domain); + return -ENOMEM; } return 0; } +int pseries_msi_allocate_domains(struct pci_controller *phb) +{ + int count; + + if (!__find_pe_total_msi(phb->dn, &count)) { + pr_err("PCI: failed to find MSIs for bridge %pOF (domain %d)\n", + phb->dn, phb->global_number); + return -ENOSPC; + } + + return __pseries_msi_allocate_domains(phb, count); +} + +void pseries_msi_free_domains(struct pci_controller *phb) +{ + if (phb->msi_domain) + irq_domain_remove(phb->msi_domain); + if (phb->dev_domain) + irq_domain_remove(phb->dev_domain); + if (phb->fwnode) + irq_domain_free_fwnode(phb->fwnode); +} + static void rtas_msi_pci_irq_fixup(struct pci_dev *pdev) { /* No LSI -> leave MSIs (if any) configured */ @@ -518,8 +684,6 @@ static void rtas_msi_pci_irq_fixup(struct pci_dev *pdev) static int rtas_msi_init(void) { - struct pci_controller *phb; - query_token = rtas_token("ibm,query-interrupt-source-number"); change_token = rtas_token("ibm,change-msi"); @@ -531,16 +695,6 @@ static int rtas_msi_init(void) pr_debug("rtas_msi: Registering RTAS MSI callbacks.\n"); - WARN_ON(pseries_pci_controller_ops.setup_msi_irqs); - pseries_pci_controller_ops.setup_msi_irqs = rtas_setup_msi_irqs; - pseries_pci_controller_ops.teardown_msi_irqs = rtas_teardown_msi_irqs; - - list_for_each_entry(phb, &hose_list, list_node) { - WARN_ON(phb->controller_ops.setup_msi_irqs); - phb->controller_ops.setup_msi_irqs = rtas_setup_msi_irqs; - phb->controller_ops.teardown_msi_irqs = rtas_teardown_msi_irqs; - } - WARN_ON(ppc_md.pci_irq_fixup); ppc_md.pci_irq_fixup = rtas_msi_pci_irq_fixup; diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c index a8f9140a24fa..90c9d3531694 100644 --- a/arch/powerpc/platforms/pseries/pci_dlpar.c +++ b/arch/powerpc/platforms/pseries/pci_dlpar.c @@ -33,6 +33,8 @@ struct pci_controller *init_phb_dynamic(struct device_node *dn) pci_devs_phb_init_dynamic(phb); + pseries_msi_allocate_domains(phb); + /* Create EEH devices for the PHB */ eeh_phb_pe_create(phb); @@ -74,6 +76,8 @@ int remove_phb_dynamic(struct pci_controller *phb) } } + pseries_msi_free_domains(phb); + /* Remove the PCI bus and unregister the bridge device from sysfs */ phb->bus = NULL; pci_remove_bus(b); diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h index 1f051a786fb3..3544778e06d0 100644 --- a/arch/powerpc/platforms/pseries/pseries.h +++ b/arch/powerpc/platforms/pseries/pseries.h @@ -85,6 +85,8 @@ struct pci_host_bridge; int pseries_root_bridge_prepare(struct pci_host_bridge *bridge); extern struct pci_controller_ops pseries_pci_controller_ops; +int pseries_msi_allocate_domains(struct pci_controller *phb); +void pseries_msi_free_domains(struct pci_controller *phb); unsigned long pseries_memory_block_size(void); diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index 167f2e1b8d39..56092dccfdb8 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -783,7 +783,7 @@ static int recover_mce(struct pt_regs *regs, struct machine_check_event *evt) { int recovered = 0; - if (!(regs->msr & MSR_RI)) { + if (regs_is_unrecoverable(regs)) { /* If MSR_RI isn't set, we cannot recover */ pr_err("Machine check interrupt unrecoverable: MSR(RI=0)\n"); recovered = 0; diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 0dfaa6ab44cc..f79126f16258 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -486,6 +486,8 @@ static void __init pSeries_discover_phbs(void) /* create pci_dn's for DT nodes under this PHB */ pci_devs_phb_init_dynamic(phb); + + pseries_msi_allocate_domains(phb); } of_node_put(root); diff --git a/arch/powerpc/platforms/pseries/svm.c b/arch/powerpc/platforms/pseries/svm.c index 1d829e257996..87f001b4c4e4 100644 --- a/arch/powerpc/platforms/pseries/svm.c +++ b/arch/powerpc/platforms/pseries/svm.c @@ -63,6 +63,9 @@ void __init svm_swiotlb_init(void) int set_memory_encrypted(unsigned long addr, int numpages) { + if (!mem_encrypt_active()) + return 0; + if (!PAGE_ALIGNED(addr)) return -EINVAL; @@ -73,6 +76,9 @@ int set_memory_encrypted(unsigned long addr, int numpages) int set_memory_decrypted(unsigned long addr, int numpages) { + if (!mem_encrypt_active()) + return 0; + if (!PAGE_ALIGNED(addr)) return -EINVAL; diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c index b5c1cf1bc64d..b043e3936d21 100644 --- a/arch/powerpc/platforms/pseries/vas.c +++ b/arch/powerpc/platforms/pseries/vas.c @@ -184,7 +184,7 @@ static int h_get_nx_fault(u32 winid, u64 buffer) * Note: The hypervisor forwards an interrupt for each fault request. * So one fault CRB to process for each H_GET_NX_FAULT hcall. */ -irqreturn_t pseries_vas_fault_thread_fn(int irq, void *data) +static irqreturn_t pseries_vas_fault_thread_fn(int irq, void *data) { struct pseries_vas_window *txwin = data; struct coprocessor_request_block crb; diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c index e00f3725ec96..feafcb582e1b 100644 --- a/arch/powerpc/platforms/pseries/vio.c +++ b/arch/powerpc/platforms/pseries/vio.c @@ -560,7 +560,8 @@ static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist, for_each_sg(sglist, sgl, nelems, count) alloc_size += roundup(sgl->length, IOMMU_PAGE_SIZE(tbl)); - if (vio_cmo_alloc(viodev, alloc_size)) + ret = vio_cmo_alloc(viodev, alloc_size); + if (ret) goto out_fail; ret = ppc_iommu_map_sg(dev, tbl, sglist, nelems, dma_get_mask(dev), direction, attrs); @@ -577,7 +578,7 @@ out_deallocate: vio_cmo_dealloc(viodev, alloc_size); out_fail: atomic_inc(&viodev->cmo.allocs_failed); - return 0; + return ret; } static void vio_dma_iommu_unmap_sg(struct device *dev, @@ -1257,7 +1258,7 @@ static int vio_bus_probe(struct device *dev) } /* convert from struct device to struct vio_dev and pass to driver. */ -static int vio_bus_remove(struct device *dev) +static void vio_bus_remove(struct device *dev) { struct vio_dev *viodev = to_vio_dev(dev); struct vio_driver *viodrv = to_vio_driver(dev->driver); @@ -1276,7 +1277,6 @@ static int vio_bus_remove(struct device *dev) vio_cmo_bus_remove(viodev); put_device(devptr); - return 0; } static void vio_bus_shutdown(struct device *dev) |