From 1fd0f52583a85b21a394201b007bc1ee104b235d Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Thu, 2 Oct 2008 14:12:51 +0000 Subject: powerpc: Fix domain numbers in /proc on 64-bit The code to properly expose domain numbers in /proc is somewhat bogus on ppc64 as it depends on the "buid" field being non-0, but that field is really pseries specific. This removes that code and makes ppc64 use the same code as 32-bit which effectively decides whether to expose domains based on ppc_pci_flags set by the platform, and sets the default for 64-bit to enable domains and enable compatibility for domain 0 (which strips the domain number for domain 0 to help with X servers). Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/pci-common.c | 10 ++++------ arch/powerpc/kernel/pci_64.c | 5 +++++ 2 files changed, 9 insertions(+), 6 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index f36936d9fda..607b4319120 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -53,8 +53,9 @@ static int global_phb_number; /* Global phb counter */ /* ISA Memory physical address */ resource_size_t isa_mem_base; -/* Default PCI flags is 0 */ -unsigned int ppc_pci_flags; +/* Default PCI flags is 0 on ppc32, modified at boot on ppc64 */ +unsigned int ppc_pci_flags = 0; + static struct dma_mapping_ops *pci_dma_ops; @@ -853,15 +854,12 @@ void __devinit pci_process_bridge_OF_ranges(struct pci_controller *hose, int pci_proc_domain(struct pci_bus *bus) { struct pci_controller *hose = pci_bus_to_host(bus); -#ifdef CONFIG_PPC64 - return hose->buid != 0; -#else + if (!(ppc_pci_flags & PPC_PCI_ENABLE_PROC_DOMAINS)) return 0; if (ppc_pci_flags & PPC_PCI_COMPAT_DOMAIN_0) return hose->global_number != 0; return 1; -#endif } void pcibios_resource_to_bus(struct pci_dev *dev, struct pci_bus_region *region, diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index 3502b9101e6..b771e3a2013 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -388,6 +388,11 @@ static int __init pcibios_init(void) if (pci_probe_only) ppc_pci_flags |= PPC_PCI_PROBE_ONLY; + /* On ppc64, we always enable PCI domains and we keep domain 0 + * backward compatible in /proc for video cards + */ + ppc_pci_flags |= PPC_PCI_ENABLE_PROC_DOMAINS | PPC_PCI_COMPAT_DOMAIN_0; + /* Scan all of the recorded PCI controllers. */ list_for_each_entry_safe(hose, tmp, &hose_list, list_node) { scan_phb(hose); -- cgit v1.2.3-70-g09d2 From a6a8e009b118b4906cbb4b382f8cc17195cff860 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Tue, 14 Oct 2008 18:25:28 +0000 Subject: powerpc: Silence software timebase sync When no hardware method is provided to sync the timebase registers across the machine, and the platform doesn't sync them for us, then we use a generic software implementation. Currently, the code for that has many printks, and they don't have log levels. Most of the printks are only useful for debugging the code, and since we haven't had any problems with it for years, this turns them into pr_debug. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/smp-tbsync.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/smp-tbsync.c b/arch/powerpc/kernel/smp-tbsync.c index bc892e69b4f..a5e54526403 100644 --- a/arch/powerpc/kernel/smp-tbsync.c +++ b/arch/powerpc/kernel/smp-tbsync.c @@ -113,7 +113,7 @@ void __devinit smp_generic_give_timebase(void) { int i, score, score2, old, min=0, max=5000, offset=1000; - printk("Synchronizing timebase\n"); + pr_debug("Software timebase sync\n"); /* if this fails then this kernel won't work anyway... */ tbsync = kzalloc( sizeof(*tbsync), GFP_KERNEL ); @@ -123,13 +123,13 @@ void __devinit smp_generic_give_timebase(void) while (!tbsync->ack) barrier(); - printk("Got ack\n"); + pr_debug("Got ack\n"); /* binary search */ for (old = -1; old != offset ; offset = (min+max) / 2) { score = start_contest(kSetAndTest, offset, NUM_ITER); - printk("score %d, offset %d\n", score, offset ); + pr_debug("score %d, offset %d\n", score, offset ); if( score > 0 ) max = offset; @@ -140,8 +140,8 @@ void __devinit smp_generic_give_timebase(void) score = start_contest(kSetAndTest, min, NUM_ITER); score2 = start_contest(kSetAndTest, max, NUM_ITER); - printk("Min %d (score %d), Max %d (score %d)\n", - min, score, max, score2); + pr_debug("Min %d (score %d), Max %d (score %d)\n", + min, score, max, score2); score = abs(score); score2 = abs(score2); offset = (score < score2) ? min : max; @@ -155,7 +155,7 @@ void __devinit smp_generic_give_timebase(void) if (score2 <= score || score2 < 20) break; } - printk("Final offset: %d (%d/%d)\n", offset, score2, NUM_ITER ); + pr_debug("Final offset: %d (%d/%d)\n", offset, score2, NUM_ITER ); /* exiting */ tbsync->cmd = kExit; -- cgit v1.2.3-70-g09d2 From 409001948d9f221c94a61c3ee96de112755fc04d Mon Sep 17 00:00:00 2001 From: Brian King Date: Wed, 22 Oct 2008 05:53:45 +0000 Subject: powerpc: Update page-in counter for CMM A new field has been added to the VPA as a method for the client OS to communicate to firmware the number of page-ins it is performing when running collaborative memory overcommit. The hypervisor will use this information to better determine if a partition is experiencing memory pressure and needs more memory allocated to it. Signed-off-by: Brian King Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/lppaca.h | 3 ++- arch/powerpc/kernel/paca.c | 1 + arch/powerpc/mm/fault.c | 12 ++++++++++-- 3 files changed, 13 insertions(+), 3 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h index 2fe268b1033..25aaa97facd 100644 --- a/arch/powerpc/include/asm/lppaca.h +++ b/arch/powerpc/include/asm/lppaca.h @@ -133,7 +133,8 @@ struct lppaca { //============================================================================= // CACHE_LINE_4-5 0x0180 - 0x027F Contains PMC interrupt data //============================================================================= - u8 pmc_save_area[256]; // PMC interrupt Area x00-xFF + u32 page_ins; // CMO Hint - # page ins by OS x00-x04 + u8 pmc_save_area[252]; // PMC interrupt Area x04-xFF } __attribute__((__aligned__(0x400))); extern struct lppaca lppaca[]; diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 48a347133f4..c744b327bca 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -37,6 +37,7 @@ struct lppaca lppaca[] = { .end_of_quantum = 0xfffffffffffffffful, .slb_count = 64, .vmxregs_in_use = 0, + .page_ins = 0, }, }; diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 565b7a237c8..b18bc0f023c 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -30,6 +30,7 @@ #include #include +#include #include #include #include @@ -318,9 +319,16 @@ good_area: goto do_sigbus; BUG(); } - if (ret & VM_FAULT_MAJOR) + if (ret & VM_FAULT_MAJOR) { current->maj_flt++; - else +#ifdef CONFIG_PPC_SMLPAR + if (firmware_has_feature(FW_FEATURE_CMO)) { + preempt_disable(); + get_lppaca()->page_ins++; + preempt_enable(); + } +#endif + } else current->min_flt++; up_read(&mm->mmap_sem); return 0; -- cgit v1.2.3-70-g09d2 From b0494bc8ee449f0534afa92a51e2e3bb27bab69b Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 27 Oct 2008 19:48:22 +0000 Subject: powerpc/pci: Cleanup debug printk's This removes the various DBG() macro from the powerpc PCI code and makes it use the standard pr_debug instead. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/pci-common.c | 77 ++++++++++++++++------------------ arch/powerpc/kernel/pci_32.c | 12 ++---- arch/powerpc/kernel/pci_64.c | 90 +++++++++++++++++++--------------------- 3 files changed, 82 insertions(+), 97 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 607b4319120..09ac98e2a50 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -38,13 +38,6 @@ #include #include -#ifdef DEBUG -#include -#define DBG(fmt...) printk(fmt) -#else -#define DBG(fmt...) -#endif - static DEFINE_SPINLOCK(hose_spinlock); /* XXX kill that some day ... */ @@ -215,8 +208,8 @@ void __devinit pcibios_setup_new_device(struct pci_dev *dev) sd->of_node = pci_device_to_OF_node(dev); - DBG("PCI: device %s OF node: %s\n", pci_name(dev), - sd->of_node ? sd->of_node->full_name : ""); + pr_debug("PCI: device %s OF node: %s\n", pci_name(dev), + sd->of_node ? sd->of_node->full_name : ""); sd->dma_ops = pci_dma_ops; #ifdef CONFIG_PPC32 @@ -253,7 +246,7 @@ int pci_read_irq_line(struct pci_dev *pci_dev) return -1; #endif - DBG("Try to map irq for %s...\n", pci_name(pci_dev)); + pr_debug("PCI: Try to map irq for %s...\n", pci_name(pci_dev)); #ifdef DEBUG memset(&oirq, 0xff, sizeof(oirq)); @@ -277,26 +270,26 @@ int pci_read_irq_line(struct pci_dev *pci_dev) line == 0xff || line == 0) { return -1; } - DBG(" -> no map ! Using line %d (pin %d) from PCI config\n", - line, pin); + pr_debug(" No map ! Using line %d (pin %d) from PCI config\n", + line, pin); virq = irq_create_mapping(NULL, line); if (virq != NO_IRQ) set_irq_type(virq, IRQ_TYPE_LEVEL_LOW); } else { - DBG(" -> got one, spec %d cells (0x%08x 0x%08x...) on %s\n", - oirq.size, oirq.specifier[0], oirq.specifier[1], + pr_debug(" Got one, spec %d cells (0x%08x 0x%08x...) on %s\n", + oirq.size, oirq.specifier[0], oirq.specifier[1], oirq.controller->full_name); virq = irq_create_of_mapping(oirq.controller, oirq.specifier, oirq.size); } if(virq == NO_IRQ) { - DBG(" -> failed to map !\n"); + pr_debug(" Failed to map !\n"); return -1; } - DBG(" -> mapped to linux irq %d\n", virq); + pr_debug(" Mapped to linux irq %d\n", virq); pci_dev->irq = virq; @@ -452,8 +445,8 @@ pgprot_t pci_phys_mem_access_prot(struct file *file, pci_dev_put(pdev); } - DBG("non-PCI map for %llx, prot: %lx\n", - (unsigned long long)offset, prot); + pr_debug("PCI: Non-PCI map for %llx, prot: %lx\n", + (unsigned long long)offset, prot); return __pgprot(prot); } @@ -1196,10 +1189,10 @@ static int __init reparent_resources(struct resource *parent, *pp = NULL; for (p = res->child; p != NULL; p = p->sibling) { p->parent = res; - DBG(KERN_INFO "PCI: reparented %s [%llx..%llx] under %s\n", - p->name, - (unsigned long long)p->start, - (unsigned long long)p->end, res->name); + pr_debug("PCI: Reparented %s [%llx..%llx] under %s\n", + p->name, + (unsigned long long)p->start, + (unsigned long long)p->end, res->name); } return 0; } @@ -1269,14 +1262,14 @@ void pcibios_allocate_bus_resources(struct pci_bus *bus) } } - DBG("PCI: %s (bus %d) bridge rsrc %d: %016llx-%016llx " - "[0x%x], parent %p (%s)\n", - bus->self ? pci_name(bus->self) : "PHB", - bus->number, i, - (unsigned long long)res->start, - (unsigned long long)res->end, - (unsigned int)res->flags, - pr, (pr && pr->name) ? pr->name : "nil"); + pr_debug("PCI: %s (bus %d) bridge rsrc %d: %016llx-%016llx " + "[0x%x], parent %p (%s)\n", + bus->self ? pci_name(bus->self) : "PHB", + bus->number, i, + (unsigned long long)res->start, + (unsigned long long)res->end, + (unsigned int)res->flags, + pr, (pr && pr->name) ? pr->name : "nil"); if (pr && !(pr->flags & IORESOURCE_UNSET)) { if (request_resource(pr, res) == 0) @@ -1303,11 +1296,11 @@ static inline void __devinit alloc_resource(struct pci_dev *dev, int idx) { struct resource *pr, *r = &dev->resource[idx]; - DBG("PCI: Allocating %s: Resource %d: %016llx..%016llx [%x]\n", - pci_name(dev), idx, - (unsigned long long)r->start, - (unsigned long long)r->end, - (unsigned int)r->flags); + pr_debug("PCI: Allocating %s: Resource %d: %016llx..%016llx [%x]\n", + pci_name(dev), idx, + (unsigned long long)r->start, + (unsigned long long)r->end, + (unsigned int)r->flags); pr = pci_find_parent_resource(dev, r); if (!pr || (pr->flags & IORESOURCE_UNSET) || @@ -1315,10 +1308,11 @@ static inline void __devinit alloc_resource(struct pci_dev *dev, int idx) printk(KERN_WARNING "PCI: Cannot allocate resource region %d" " of device %s, will remap\n", idx, pci_name(dev)); if (pr) - DBG("PCI: parent is %p: %016llx-%016llx [%x]\n", pr, - (unsigned long long)pr->start, - (unsigned long long)pr->end, - (unsigned int)pr->flags); + pr_debug("PCI: parent is %p: %016llx-%016llx [%x]\n", + pr, + (unsigned long long)pr->start, + (unsigned long long)pr->end, + (unsigned int)pr->flags); /* We'll assign a new address later */ r->flags |= IORESOURCE_UNSET; r->end -= r->start; @@ -1356,7 +1350,8 @@ static void __init pcibios_allocate_resources(int pass) * but keep it unregistered. */ u32 reg; - DBG("PCI: Switching off ROM of %s\n", pci_name(dev)); + pr_debug("PCI: Switching off ROM of %s\n", + pci_name(dev)); r->flags &= ~IORESOURCE_ROM_ENABLE; pci_read_config_dword(dev, dev->rom_base_reg, ®); pci_write_config_dword(dev, dev->rom_base_reg, @@ -1381,7 +1376,7 @@ void __init pcibios_resource_survey(void) } if (!(ppc_pci_flags & PPC_PCI_PROBE_ONLY)) { - DBG("PCI: Assigning unassigned resouces...\n"); + pr_debug("PCI: Assigning unassigned resouces...\n"); pci_assign_unassigned_resources(); } diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index 131b1dfa68c..fdcc898e58d 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -26,12 +26,6 @@ #undef DEBUG -#ifdef DEBUG -#define DBG(x...) printk(x) -#else -#define DBG(x...) -#endif - unsigned long isa_io_base = 0; unsigned long pci_dram_offset = 0; int pcibios_assign_bus_offset = 1; @@ -275,14 +269,14 @@ pci_busdev_to_OF_node(struct pci_bus *bus, int devfn) if (!have_of) return NULL; - DBG("pci_busdev_to_OF_node(%d,0x%x)\n", bus->number, devfn); + pr_debug("pci_busdev_to_OF_node(%d,0x%x)\n", bus->number, devfn); parent = scan_OF_for_pci_bus(bus); if (parent == NULL) return NULL; - DBG(" parent is %s\n", parent ? parent->full_name : ""); + pr_debug(" parent is %s\n", parent ? parent->full_name : ""); np = scan_OF_for_pci_dev(parent, devfn); of_node_put(parent); - DBG(" result is %s\n", np ? np->full_name : ""); + pr_debug(" result is %s\n", np ? np->full_name : ""); /* XXX most callers don't release the returned node * mostly because ppc64 doesn't increase the refcount, diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index b771e3a2013..ffada88a448 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -32,13 +32,6 @@ #include #include -#ifdef DEBUG -#include -#define DBG(fmt...) printk(fmt) -#else -#define DBG(fmt...) -#endif - unsigned long pci_probe_only = 1; /* pci_io_base -- the base address from which io bars are offsets. @@ -102,7 +95,7 @@ static void pci_parse_of_addrs(struct device_node *node, struct pci_dev *dev) addrs = of_get_property(node, "assigned-addresses", &proplen); if (!addrs) return; - DBG(" parse addresses (%d bytes) @ %p\n", proplen, addrs); + pr_debug(" parse addresses (%d bytes) @ %p\n", proplen, addrs); for (; proplen >= 20; proplen -= 20, addrs += 5) { flags = pci_parse_of_flags(addrs[0]); if (!flags) @@ -112,8 +105,9 @@ static void pci_parse_of_addrs(struct device_node *node, struct pci_dev *dev) if (!size) continue; i = addrs[0] & 0xff; - DBG(" base: %llx, size: %llx, i: %x\n", - (unsigned long long)base, (unsigned long long)size, i); + pr_debug(" base: %llx, size: %llx, i: %x\n", + (unsigned long long)base, + (unsigned long long)size, i); if (PCI_BASE_ADDRESS_0 <= i && i <= PCI_BASE_ADDRESS_5) { res = &dev->resource[(i - PCI_BASE_ADDRESS_0) >> 2]; @@ -144,7 +138,7 @@ struct pci_dev *of_create_pci_dev(struct device_node *node, if (type == NULL) type = ""; - DBG(" create device, devfn: %x, type: %s\n", devfn, type); + pr_debug(" create device, devfn: %x, type: %s\n", devfn, type); dev->bus = bus; dev->sysdata = node; @@ -165,8 +159,8 @@ struct pci_dev *of_create_pci_dev(struct device_node *node, dev->class = get_int_prop(node, "class-code", 0); dev->revision = get_int_prop(node, "revision-id", 0); - DBG(" class: 0x%x\n", dev->class); - DBG(" revision: 0x%x\n", dev->revision); + pr_debug(" class: 0x%x\n", dev->class); + pr_debug(" revision: 0x%x\n", dev->revision); dev->current_state = 4; /* unknown power state */ dev->error_state = pci_channel_io_normal; @@ -187,7 +181,7 @@ struct pci_dev *of_create_pci_dev(struct device_node *node, pci_parse_of_addrs(node, dev); - DBG(" adding to system ...\n"); + pr_debug(" adding to system ...\n"); pci_device_add(dev, bus); @@ -203,11 +197,12 @@ void __devinit of_scan_bus(struct device_node *node, int reglen, devfn; struct pci_dev *dev; - DBG("of_scan_bus(%s) bus no %d... \n", node->full_name, bus->number); + pr_debug("of_scan_bus(%s) bus no %d... \n", + node->full_name, bus->number); /* Scan direct children */ for_each_child_of_node(node, child) { - DBG(" * %s\n", child->full_name); + pr_debug(" * %s\n", child->full_name); reg = of_get_property(child, "reg", ®len); if (reg == NULL || reglen < 20) continue; @@ -217,7 +212,7 @@ void __devinit of_scan_bus(struct device_node *node, dev = of_create_pci_dev(child, bus, devfn); if (!dev) continue; - DBG(" dev header type: %x\n", dev->hdr_type); + pr_debug(" dev header type: %x\n", dev->hdr_type); } /* Ally all fixups */ @@ -245,7 +240,7 @@ void __devinit of_scan_pci_bridge(struct device_node *node, unsigned int flags; u64 size; - DBG("of_scan_pci_bridge(%s)\n", node->full_name); + pr_debug("of_scan_pci_bridge(%s)\n", node->full_name); /* parse bus-range property */ busrange = of_get_property(node, "bus-range", &len); @@ -309,12 +304,12 @@ void __devinit of_scan_pci_bridge(struct device_node *node, } sprintf(bus->name, "PCI Bus %04x:%02x", pci_domain_nr(bus), bus->number); - DBG(" bus name: %s\n", bus->name); + pr_debug(" bus name: %s\n", bus->name); mode = PCI_PROBE_NORMAL; if (ppc_md.pci_probe_mode) mode = ppc_md.pci_probe_mode(bus); - DBG(" probe mode: %d\n", mode); + pr_debug(" probe mode: %d\n", mode); if (mode == PCI_PROBE_DEVTREE) of_scan_bus(node, bus); @@ -329,7 +324,8 @@ void __devinit scan_phb(struct pci_controller *hose) struct device_node *node = hose->dn; int i, mode; - DBG("PCI: Scanning PHB %s\n", node ? node->full_name : ""); + pr_debug("PCI: Scanning PHB %s\n", + node ? node->full_name : ""); /* Create an empty bus for the toplevel */ bus = pci_create_bus(hose->parent, hose->first_busno, hose->ops, node); @@ -345,26 +341,26 @@ void __devinit scan_phb(struct pci_controller *hose) pcibios_map_io_space(bus); /* Wire up PHB bus resources */ - DBG("PCI: PHB IO resource = %016lx-%016lx [%lx]\n", - hose->io_resource.start, hose->io_resource.end, - hose->io_resource.flags); + pr_debug("PCI: PHB IO resource = %016lx-%016lx [%lx]\n", + hose->io_resource.start, hose->io_resource.end, + hose->io_resource.flags); bus->resource[0] = &hose->io_resource; for (i = 0; i < 3; ++i) { - DBG("PCI: PHB MEM resource %d = %016lx-%016lx [%lx]\n", i, - hose->mem_resources[i].start, - hose->mem_resources[i].end, - hose->mem_resources[i].flags); + pr_debug("PCI: PHB MEM resource %d = %016lx-%016lx [%lx]\n", i, + hose->mem_resources[i].start, + hose->mem_resources[i].end, + hose->mem_resources[i].flags); bus->resource[i+1] = &hose->mem_resources[i]; } - DBG("PCI: PHB MEM offset = %016lx\n", hose->pci_mem_offset); - DBG("PCI: PHB IO offset = %08lx\n", + pr_debug("PCI: PHB MEM offset = %016lx\n", hose->pci_mem_offset); + pr_debug("PCI: PHB IO offset = %08lx\n", (unsigned long)hose->io_base_virt - _IO_BASE); /* Get probe mode and perform scan */ mode = PCI_PROBE_NORMAL; if (node && ppc_md.pci_probe_mode) mode = ppc_md.pci_probe_mode(bus); - DBG(" probe mode: %d\n", mode); + pr_debug(" probe mode: %d\n", mode); if (mode == PCI_PROBE_DEVTREE) { bus->subordinate = hose->last_busno; of_scan_bus(node, bus); @@ -427,8 +423,8 @@ int pcibios_unmap_io_space(struct pci_bus *bus) if (bus->self) { struct resource *res = bus->resource[0]; - DBG("IO unmapping for PCI-PCI bridge %s\n", - pci_name(bus->self)); + pr_debug("IO unmapping for PCI-PCI bridge %s\n", + pci_name(bus->self)); __flush_hash_table_range(&init_mm, res->start + _IO_BASE, res->end + _IO_BASE + 1); @@ -442,8 +438,8 @@ int pcibios_unmap_io_space(struct pci_bus *bus) if (hose->io_base_alloc == 0) return 0; - DBG("IO unmapping for PHB %s\n", hose->dn->full_name); - DBG(" alloc=0x%p\n", hose->io_base_alloc); + pr_debug("IO unmapping for PHB %s\n", hose->dn->full_name); + pr_debug(" alloc=0x%p\n", hose->io_base_alloc); /* This is a PHB, we fully unmap the IO area */ vunmap(hose->io_base_alloc); @@ -468,11 +464,11 @@ int __devinit pcibios_map_io_space(struct pci_bus *bus) * thus HPTEs will be faulted in when needed */ if (bus->self) { - DBG("IO mapping for PCI-PCI bridge %s\n", - pci_name(bus->self)); - DBG(" virt=0x%016lx...0x%016lx\n", - bus->resource[0]->start + _IO_BASE, - bus->resource[0]->end + _IO_BASE); + pr_debug("IO mapping for PCI-PCI bridge %s\n", + pci_name(bus->self)); + pr_debug(" virt=0x%016lx...0x%016lx\n", + bus->resource[0]->start + _IO_BASE, + bus->resource[0]->end + _IO_BASE); return 0; } @@ -501,11 +497,11 @@ int __devinit pcibios_map_io_space(struct pci_bus *bus) hose->io_base_virt = (void __iomem *)(area->addr + hose->io_base_phys - phys_page); - DBG("IO mapping for PHB %s\n", hose->dn->full_name); - DBG(" phys=0x%016lx, virt=0x%p (alloc=0x%p)\n", - hose->io_base_phys, hose->io_base_virt, hose->io_base_alloc); - DBG(" size=0x%016lx (alloc=0x%016lx)\n", - hose->pci_io_size, size_page); + pr_debug("IO mapping for PHB %s\n", hose->dn->full_name); + pr_debug(" phys=0x%016lx, virt=0x%p (alloc=0x%p)\n", + hose->io_base_phys, hose->io_base_virt, hose->io_base_alloc); + pr_debug(" size=0x%016lx (alloc=0x%016lx)\n", + hose->pci_io_size, size_page); /* Establish the mapping */ if (__ioremap_at(phys_page, area->addr, size_page, @@ -517,8 +513,8 @@ int __devinit pcibios_map_io_space(struct pci_bus *bus) hose->io_resource.start += io_virt_offset; hose->io_resource.end += io_virt_offset; - DBG(" hose->io_resource=0x%016lx...0x%016lx\n", - hose->io_resource.start, hose->io_resource.end); + pr_debug(" hose->io_resource=0x%016lx...0x%016lx\n", + hose->io_resource.start, hose->io_resource.end); return 0; } -- cgit v1.2.3-70-g09d2 From 53280323350621985b3f2f8ffe649215304bcc5f Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 27 Oct 2008 19:48:29 +0000 Subject: powerpc/pci: Use common PHB resource hookup The 32-bit and 64-bit powerpc PCI code used to set up the resource pointers of the root bus of a given PHB in completely different places. This unifies this in large part, by making 32-bit use a routine very similar to what 64-bit does when initially scanning the PCI busses. The actual setup of the PHB resources itself is then moved to a common function in pci-common.c. This should cause no functional change on 64-bit. On 32-bit, the effect is that the PHB resources are going to be setup a bit earlier, instead of being setup from pcibios_fixup_bus(). Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/pci-bridge.h | 1 + arch/powerpc/kernel/pci-common.c | 58 ++++++++++++++++++++++++++ arch/powerpc/kernel/pci_32.c | 78 +++++++++++++++-------------------- arch/powerpc/kernel/pci_64.c | 19 ++------- 4 files changed, 96 insertions(+), 60 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index 9047af7baa6..2dfa8a3d8c7 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -290,6 +290,7 @@ extern void pci_process_bridge_OF_ranges(struct pci_controller *hose, /* Allocate & free a PCI host bridge structure */ extern struct pci_controller *pcibios_alloc_controller(struct device_node *dev); extern void pcibios_free_controller(struct pci_controller *phb); +extern void pcibios_setup_phb_resources(struct pci_controller *hose); #ifdef CONFIG_PCI extern unsigned long pci_address_to_pio(phys_addr_t address); diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 09ac98e2a50..6d46bfabdbe 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -1421,3 +1421,61 @@ int pcibios_enable_device(struct pci_dev *dev, int mask) return pci_enable_resources(dev, mask); } + +void __devinit pcibios_setup_phb_resources(struct pci_controller *hose) +{ + struct pci_bus *bus = hose->bus; + struct resource *res; + int i; + + /* Hookup PHB IO resource */ + bus->resource[0] = res = &hose->io_resource; + + if (!res->flags) { + printk(KERN_WARNING "PCI: I/O resource not set for host" + " bridge %s (domain %d)\n", + hose->dn->full_name, hose->global_number); +#ifdef CONFIG_PPC32 + /* Workaround for lack of IO resource only on 32-bit */ + res->start = (unsigned long)hose->io_base_virt - isa_io_base; + res->end = res->start + IO_SPACE_LIMIT; + res->flags = IORESOURCE_IO; +#endif /* CONFIG_PPC32 */ + } + + pr_debug("PCI: PHB IO resource = %016llx-%016llx [%lx]\n", + (unsigned long long)res->start, + (unsigned long long)res->end, + (unsigned long)res->flags); + + /* Hookup PHB Memory resources */ + for (i = 0; i < 3; ++i) { + res = &hose->mem_resources[i]; + if (!res->flags) { + if (i > 0) + continue; + printk(KERN_ERR "PCI: Memory resource 0 not set for " + "host bridge %s (domain %d)\n", + hose->dn->full_name, hose->global_number); +#ifdef CONFIG_PPC32 + /* Workaround for lack of MEM resource only on 32-bit */ + res->start = hose->pci_mem_offset; + res->end = (resource_size_t)-1LL; + res->flags = IORESOURCE_MEM; +#endif /* CONFIG_PPC32 */ + } + bus->resource[i+1] = res; + + pr_debug("PCI: PHB MEM resource %d = %016llx-%016llx [%lx]\n", i, + (unsigned long long)res->start, + (unsigned long long)res->end, + (unsigned long)res->flags); + } + + pr_debug("PCI: PHB MEM offset = %016llx\n", + (unsigned long long)hose->pci_mem_offset); + pr_debug("PCI: PHB IO offset = %08lx\n", + (unsigned long)hose->io_base_virt - _IO_BASE); + +} + diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index fdcc898e58d..88304035827 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -373,10 +373,41 @@ void pcibios_make_OF_bus_map(void) } #endif /* CONFIG_PPC_OF */ +static void __devinit pcibios_scan_phb(struct pci_controller *hose) +{ + struct pci_bus *bus; + struct device_node *node = hose->dn; + unsigned long io_offset; + struct resource *res = &hose->io_resource; + + pr_debug("PCI: Scanning PHB %s\n", + node ? node->full_name : ""); + + /* Create an empty bus for the toplevel */ + bus = pci_create_bus(hose->parent, hose->first_busno, hose->ops, hose); + if (bus == NULL) { + printk(KERN_ERR "Failed to create bus for PCI domain %04x\n", + hose->global_number); + return; + } + bus->secondary = hose->first_busno; + hose->bus = bus; + + /* Fixup IO space offset */ + io_offset = (unsigned long)hose->io_base_virt - isa_io_base; + res->start = (res->start + io_offset) & 0xffffffffu; + res->end = (res->end + io_offset) & 0xffffffffu; + + /* Wire up PHB bus resources */ + pcibios_setup_phb_resources(hose); + + /* Scan children */ + hose->last_busno = bus->subordinate = pci_scan_child_bus(bus); +} + static int __init pcibios_init(void) { struct pci_controller *hose, *tmp; - struct pci_bus *bus; int next_busno = 0; printk(KERN_INFO "PCI: Probing PCI hardware\n"); @@ -389,12 +420,8 @@ static int __init pcibios_init(void) if (pci_assign_all_buses) hose->first_busno = next_busno; hose->last_busno = 0xff; - bus = pci_scan_bus_parented(hose->parent, hose->first_busno, - hose->ops, hose); - if (bus) { - pci_bus_add_devices(bus); - hose->last_busno = bus->subordinate; - } + pcibios_scan_phb(hose); + pci_bus_add_devices(hose->bus); if (pci_assign_all_buses || next_busno <= hose->last_busno) next_busno = hose->last_busno + pcibios_assign_bus_offset; } @@ -421,45 +448,8 @@ subsys_initcall(pcibios_init); void __devinit pcibios_do_bus_setup(struct pci_bus *bus) { - struct pci_controller *hose = (struct pci_controller *) bus->sysdata; - unsigned long io_offset; - struct resource *res; - int i; struct pci_dev *dev; - /* Hookup PHB resources */ - io_offset = (unsigned long)hose->io_base_virt - isa_io_base; - if (bus->parent == NULL) { - /* This is a host bridge - fill in its resources */ - hose->bus = bus; - - bus->resource[0] = res = &hose->io_resource; - if (!res->flags) { - if (io_offset) - printk(KERN_ERR "I/O resource not set for host" - " bridge %d\n", hose->global_number); - res->start = 0; - res->end = IO_SPACE_LIMIT; - res->flags = IORESOURCE_IO; - } - res->start = (res->start + io_offset) & 0xffffffffu; - res->end = (res->end + io_offset) & 0xffffffffu; - - for (i = 0; i < 3; ++i) { - res = &hose->mem_resources[i]; - if (!res->flags) { - if (i > 0) - continue; - printk(KERN_ERR "Memory resource not set for " - "host bridge %d\n", hose->global_number); - res->start = hose->pci_mem_offset; - res->end = ~0U; - res->flags = IORESOURCE_MEM; - } - bus->resource[i+1] = res; - } - } - if (ppc_md.pci_dma_bus_setup) ppc_md.pci_dma_bus_setup(bus); diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index ffada88a448..f5fc547284b 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -322,7 +322,7 @@ void __devinit scan_phb(struct pci_controller *hose) { struct pci_bus *bus; struct device_node *node = hose->dn; - int i, mode; + int mode; pr_debug("PCI: Scanning PHB %s\n", node ? node->full_name : ""); @@ -341,20 +341,7 @@ void __devinit scan_phb(struct pci_controller *hose) pcibios_map_io_space(bus); /* Wire up PHB bus resources */ - pr_debug("PCI: PHB IO resource = %016lx-%016lx [%lx]\n", - hose->io_resource.start, hose->io_resource.end, - hose->io_resource.flags); - bus->resource[0] = &hose->io_resource; - for (i = 0; i < 3; ++i) { - pr_debug("PCI: PHB MEM resource %d = %016lx-%016lx [%lx]\n", i, - hose->mem_resources[i].start, - hose->mem_resources[i].end, - hose->mem_resources[i].flags); - bus->resource[i+1] = &hose->mem_resources[i]; - } - pr_debug("PCI: PHB MEM offset = %016lx\n", hose->pci_mem_offset); - pr_debug("PCI: PHB IO offset = %08lx\n", - (unsigned long)hose->io_base_virt - _IO_BASE); + pcibios_setup_phb_resources(hose); /* Get probe mode and perform scan */ mode = PCI_PROBE_NORMAL; @@ -376,7 +363,7 @@ static int __init pcibios_init(void) printk(KERN_INFO "PCI: Probing PCI hardware\n"); - /* For now, override phys_mem_access_prot. If we need it, + /* For now, override phys_mem_access_prot. If we need it,g * later, we may move that initialization to each ppc_md */ ppc_md.phys_mem_access_prot = pci_phys_mem_access_prot; -- cgit v1.2.3-70-g09d2 From ab56ced9c57b66862c687f3158045d15133f02d6 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 27 Oct 2008 19:48:33 +0000 Subject: powerpc/pci: Remove pcibios_do_bus_setup() The function pcibios_do_bus_setup() was used by pcibios_fixup_bus() to perform setup that is different between the 32-bit and 64-bit code. This difference no longer exists, thus the function is removed and the setup now done directly from pci-common.c. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/pci.h | 1 - arch/powerpc/kernel/pci-common.c | 16 +++++++++++----- arch/powerpc/kernel/pci_32.c | 11 ----------- arch/powerpc/kernel/pci_64.c | 11 ----------- 4 files changed, 11 insertions(+), 28 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h index 57a2a494886..55542ac3ead 100644 --- a/arch/powerpc/include/asm/pci.h +++ b/arch/powerpc/include/asm/pci.h @@ -235,7 +235,6 @@ extern void pci_resource_to_user(const struct pci_dev *dev, int bar, const struct resource *rsrc, resource_size_t *start, resource_size_t *end); -extern void pcibios_do_bus_setup(struct pci_bus *bus); extern void pcibios_fixup_of_probed_bus(struct pci_bus *bus); diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 6d46bfabdbe..780db386c1f 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -1076,18 +1076,24 @@ static void __devinit pcibios_fixup_bridge(struct pci_bus *bus) static void __devinit __pcibios_fixup_bus(struct pci_bus *bus) { - struct pci_dev *dev = bus->self; + struct pci_dev *dev; - pr_debug("PCI: Fixup bus %d (%s)\n", bus->number, dev ? pci_name(dev) : "PHB"); + pr_debug("PCI: Fixup bus %d (%s)\n", + bus->number, bus->self ? pci_name(bus->self) : "PHB"); /* Fixup PCI<->PCI bridges. Host bridges are handled separately, for * now differently between 32 and 64 bits. */ - if (dev != NULL) + if (bus->self != NULL) pcibios_fixup_bridge(bus); - /* Additional setup that is different between 32 and 64 bits for now */ - pcibios_do_bus_setup(bus); + /* Setup bus DMA mappings */ + if (ppc_md.pci_dma_bus_setup) + ppc_md.pci_dma_bus_setup(bus); + + /* Setup DMA for all PCI devices on that bus */ + list_for_each_entry(dev, &bus->devices, bus_list) + pcibios_setup_new_device(dev); /* Platform specific bus fixups */ if (ppc_md.pcibios_fixup_bus) diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index 88304035827..7ad11e592f2 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -446,17 +446,6 @@ static int __init pcibios_init(void) subsys_initcall(pcibios_init); -void __devinit pcibios_do_bus_setup(struct pci_bus *bus) -{ - struct pci_dev *dev; - - if (ppc_md.pci_dma_bus_setup) - ppc_md.pci_dma_bus_setup(bus); - - list_for_each_entry(dev, &bus->devices, bus_list) - pcibios_setup_new_device(dev); -} - /* the next one is stolen from the alpha port... */ void __init pcibios_update_irq(struct pci_dev *dev, int irq) diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index f5fc547284b..e6e8813c364 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -507,17 +507,6 @@ int __devinit pcibios_map_io_space(struct pci_bus *bus) } EXPORT_SYMBOL_GPL(pcibios_map_io_space); -void __devinit pcibios_do_bus_setup(struct pci_bus *bus) -{ - struct pci_dev *dev; - - if (ppc_md.pci_dma_bus_setup) - ppc_md.pci_dma_bus_setup(bus); - - list_for_each_entry(dev, &bus->devices, bus_list) - pcibios_setup_new_device(dev); -} - unsigned long pci_address_to_pio(phys_addr_t address) { struct pci_controller *hose, *tmp; -- cgit v1.2.3-70-g09d2 From 8b8da35804bb89eee23f9bcd5638e1f754bd4c91 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 27 Oct 2008 19:48:37 +0000 Subject: powerpc/pci: Split pcibios_fixup_bus() into bus setup and device setup Currently, our PCI code uses the pcibios_fixup_bus() callback, which is called by the generic code when probing PCI buses, for two different things. One is to set up things related to the bus itself, such as reading bridge resources for P2P bridges, fixing them up, or setting up the iommu's associated with bridges on some platforms. The other is some setup for each individual device under that bridge, mostly setting up DMA mappings and interrupts. The problem is that this approach doesn't work well with PCI hotplug when an existing bus is re-probed for new children. We fix this problem by splitting pcibios_fixup_bus into two routines: pcibios_setup_bus_self() is now called to setup the bus itself pcibios_setup_bus_devices() is now called to setup devices pcibios_fixup_bus() is then modified to call these two after reading the bridge bases, and the OF based PCI probe is modified to avoid calling into the first one when rescanning an existing bridge. [paulus@samba.org - fixed eeh.h for 32-bit compile now that pci-common.c is including it unconditionally.] Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/eeh.h | 8 +++--- arch/powerpc/include/asm/pci.h | 5 ++-- arch/powerpc/kernel/pci-common.c | 54 +++++++++++++++++++++------------------- arch/powerpc/kernel/pci_64.c | 27 ++++++++++++++++---- 4 files changed, 58 insertions(+), 36 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index b886bec6701..66ea9b8b95c 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -17,8 +17,8 @@ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ -#ifndef _PPC64_EEH_H -#define _PPC64_EEH_H +#ifndef _POWERPC_EEH_H +#define _POWERPC_EEH_H #ifdef __KERNEL__ #include @@ -110,6 +110,7 @@ static inline void eeh_remove_bus_device(struct pci_dev *dev) { } #define EEH_IO_ERROR_VALUE(size) (-1UL) #endif /* CONFIG_EEH */ +#ifdef CONFIG_PPC64 /* * MMIO read/write operations with EEH support. */ @@ -207,5 +208,6 @@ static inline void eeh_readsl(const volatile void __iomem *addr, void * buf, eeh_check_failure(addr, *(u32*)buf); } +#endif /* CONFIG_PPC64 */ #endif /* __KERNEL__ */ -#endif /* _PPC64_EEH_H */ +#endif /* _POWERPC_EEH_H */ diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h index 55542ac3ead..32e03e6d25c 100644 --- a/arch/powerpc/include/asm/pci.h +++ b/arch/powerpc/include/asm/pci.h @@ -221,6 +221,7 @@ extern void of_scan_pci_bridge(struct device_node *node, struct pci_dev *dev); extern void of_scan_bus(struct device_node *node, struct pci_bus *bus); +extern void of_rescan_bus(struct device_node *node, struct pci_bus *bus); extern int pci_read_irq_line(struct pci_dev *dev); @@ -235,8 +236,8 @@ extern void pci_resource_to_user(const struct pci_dev *dev, int bar, const struct resource *rsrc, resource_size_t *start, resource_size_t *end); -extern void pcibios_fixup_of_probed_bus(struct pci_bus *bus); - +extern void pcibios_setup_bus_devices(struct pci_bus *bus); +extern void pcibios_setup_bus_self(struct pci_bus *bus); #endif /* __KERNEL__ */ #endif /* __ASM_POWERPC_PCI_H */ diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 780db386c1f..0eaabd41474 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -37,6 +37,7 @@ #include #include #include +#include static DEFINE_SPINLOCK(hose_spinlock); @@ -1074,31 +1075,17 @@ static void __devinit pcibios_fixup_bridge(struct pci_bus *bus) } } -static void __devinit __pcibios_fixup_bus(struct pci_bus *bus) +void __devinit pcibios_setup_bus_devices(struct pci_bus *bus) { struct pci_dev *dev; pr_debug("PCI: Fixup bus %d (%s)\n", bus->number, bus->self ? pci_name(bus->self) : "PHB"); - /* Fixup PCI<->PCI bridges. Host bridges are handled separately, for - * now differently between 32 and 64 bits. - */ - if (bus->self != NULL) - pcibios_fixup_bridge(bus); - - /* Setup bus DMA mappings */ - if (ppc_md.pci_dma_bus_setup) - ppc_md.pci_dma_bus_setup(bus); - /* Setup DMA for all PCI devices on that bus */ list_for_each_entry(dev, &bus->devices, bus_list) pcibios_setup_new_device(dev); - /* Platform specific bus fixups */ - if (ppc_md.pcibios_fixup_bus) - ppc_md.pcibios_fixup_bus(bus); - /* Read default IRQs and fixup if necessary */ list_for_each_entry(dev, &bus->devices, bus_list) { pci_read_irq_line(dev); @@ -1107,25 +1094,39 @@ static void __devinit __pcibios_fixup_bus(struct pci_bus *bus) } } +void __devinit pcibios_setup_bus_self(struct pci_bus *bus) +{ + /* Fix up the bus resources */ + if (bus->self != NULL) + pcibios_fixup_bridge(bus); + + /* Platform specific bus fixups. This is currently only used + * by fsl_pci and I'm hoping getting rid of it at some point + */ + if (ppc_md.pcibios_fixup_bus) + ppc_md.pcibios_fixup_bus(bus); + + /* Setup bus DMA mappings */ + if (ppc_md.pci_dma_bus_setup) + ppc_md.pci_dma_bus_setup(bus); +} + void __devinit pcibios_fixup_bus(struct pci_bus *bus) { /* When called from the generic PCI probe, read PCI<->PCI bridge - * bases before proceeding + * bases. This isn't called when generating the PCI tree from + * the OF device-tree. */ if (bus->self != NULL) pci_read_bridge_bases(bus); - __pcibios_fixup_bus(bus); -} -EXPORT_SYMBOL(pcibios_fixup_bus); -/* When building a bus from the OF tree rather than probing, we need a - * slightly different version of the fixup which doesn't read the - * bridge bases using config space accesses - */ -void __devinit pcibios_fixup_of_probed_bus(struct pci_bus *bus) -{ - __pcibios_fixup_bus(bus); + /* Now fixup the bus bus */ + pcibios_setup_bus_self(bus); + + /* Now fixup devices on that bus */ + pcibios_setup_bus_devices(bus); } +EXPORT_SYMBOL(pcibios_fixup_bus); static int skip_isa_ioresource_align(struct pci_dev *dev) { @@ -1392,6 +1393,7 @@ void __init pcibios_resource_survey(void) } #ifdef CONFIG_HOTPLUG + /* This is used by the pSeries hotplug driver to allocate resource * of newly plugged busses. We can try to consolidate with the * rest of the code later, for now, keep it as-is diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index e6e8813c364..39fadc6e149 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -189,8 +189,8 @@ struct pci_dev *of_create_pci_dev(struct device_node *node, } EXPORT_SYMBOL(of_create_pci_dev); -void __devinit of_scan_bus(struct device_node *node, - struct pci_bus *bus) +static void __devinit __of_scan_bus(struct device_node *node, + struct pci_bus *bus, int rescan_existing) { struct device_node *child; const u32 *reg; @@ -215,8 +215,12 @@ void __devinit of_scan_bus(struct device_node *node, pr_debug(" dev header type: %x\n", dev->hdr_type); } - /* Ally all fixups */ - pcibios_fixup_of_probed_bus(bus); + /* Apply all fixups necessary. We don't fixup the bus "self" + * for an existing bridge that is being rescanned + */ + if (!rescan_existing) + pcibios_setup_bus_self(bus); + pcibios_setup_bus_devices(bus); /* Now scan child busses */ list_for_each_entry(dev, &bus->devices, bus_list) { @@ -228,7 +232,20 @@ void __devinit of_scan_bus(struct device_node *node, } } } -EXPORT_SYMBOL(of_scan_bus); + +void __devinit of_scan_bus(struct device_node *node, + struct pci_bus *bus) +{ + __of_scan_bus(node, bus, 0); +} +EXPORT_SYMBOL_GPL(of_scan_bus); + +void __devinit of_rescan_bus(struct device_node *node, + struct pci_bus *bus) +{ + __of_scan_bus(node, bus, 1); +} +EXPORT_SYMBOL_GPL(of_rescan_bus); void __devinit of_scan_pci_bridge(struct device_node *node, struct pci_dev *dev) -- cgit v1.2.3-70-g09d2 From b5ae5f911d221ad85090d6805ab9ab020f6e4703 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 27 Oct 2008 19:48:44 +0000 Subject: powerpc/pci: Make pcibios_allocate_bus_resources more robust To properly fix PCI hotplug, it's useful to be able to make the fixup passes on all devices whether they were just hot plugged or already there. However, pcibios_allocate_bus_resources() wouldn't cope well with being called twice for a given bus. This makes it ignore resources that have already been allocated, along with adding a bit of debug output. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/pci-common.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 0eaabd41474..f965397a610 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -1243,9 +1243,12 @@ void pcibios_allocate_bus_resources(struct pci_bus *bus) int i; struct resource *res, *pr; + pr_debug("PCI: Allocating bus resources for %04x:%02x...\n", + pci_domain_nr(bus), bus->number); + for (i = 0; i < PCI_BUS_NUM_RESOURCES; ++i) { if ((res = bus->resource[i]) == NULL || !res->flags - || res->start > res->end) + || res->start > res->end || res->parent) continue; if (bus->parent == NULL) pr = (res->flags & IORESOURCE_IO) ? -- cgit v1.2.3-70-g09d2 From fd6852c8fa060bd45c82a2593e18f933f6c6204f Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 27 Oct 2008 19:48:52 +0000 Subject: powerpc/pci: Fix various pseries PCI hotplug issues The pseries PCI hotplug code has a number of issues, ranging from incorrect resource setup to crashes, depending on what is added, when, whether it contains a bridge, etc etc.... This fixes a whole bunch of these, while actually simplifying the code a bit, using more generic code in the process and factoring out common code between adding of a PHB, a slot or a device. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/pci-bridge.h | 3 - arch/powerpc/include/asm/pci.h | 5 +- arch/powerpc/kernel/pci-common.c | 41 +++++++- arch/powerpc/kernel/rtas_pci.c | 48 --------- arch/powerpc/platforms/pseries/pci_dlpar.c | 163 ++++++++++++++--------------- drivers/pci/hotplug/rpadlpar_core.c | 69 ++++++------ 6 files changed, 150 insertions(+), 179 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index 2dfa8a3d8c7..fa8b3b72443 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -241,9 +241,6 @@ extern void pcibios_remove_pci_devices(struct pci_bus *bus); /** Discover new pci devices under this bus, and add them */ extern void pcibios_add_pci_devices(struct pci_bus *bus); -extern void pcibios_fixup_new_pci_devices(struct pci_bus *bus); - -extern int pcibios_remove_root_bus(struct pci_controller *phb); static inline struct pci_controller *pci_bus_to_host(const struct pci_bus *bus) { diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h index 32e03e6d25c..1c721a632d8 100644 --- a/arch/powerpc/include/asm/pci.h +++ b/arch/powerpc/include/asm/pci.h @@ -204,15 +204,14 @@ static inline struct resource *pcibios_select_root(struct pci_dev *pdev, return root; } -extern void pcibios_setup_new_device(struct pci_dev *dev); - extern void pcibios_claim_one_bus(struct pci_bus *b); -extern void pcibios_allocate_bus_resources(struct pci_bus *bus); +extern void pcibios_finish_adding_to_bus(struct pci_bus *bus); extern void pcibios_resource_survey(void); extern struct pci_controller *init_phb_dynamic(struct device_node *dn); +extern int remove_phb_dynamic(struct pci_controller *phb); extern struct pci_dev *of_create_pci_dev(struct device_node *node, struct pci_bus *bus, int devfn); diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index f965397a610..f3fd7eb90a7 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -203,7 +203,7 @@ char __devinit *pcibios_setup(char *str) return str; } -void __devinit pcibios_setup_new_device(struct pci_dev *dev) +static void __devinit pcibios_setup_new_device(struct pci_dev *dev) { struct dev_archdata *sd = &dev->dev.archdata; @@ -221,7 +221,6 @@ void __devinit pcibios_setup_new_device(struct pci_dev *dev) if (ppc_md.pci_dma_dev_setup) ppc_md.pci_dma_dev_setup(dev); } -EXPORT_SYMBOL(pcibios_setup_new_device); /* * Reads the interrupt pin to determine if interrupt is use by card. @@ -1397,9 +1396,10 @@ void __init pcibios_resource_survey(void) #ifdef CONFIG_HOTPLUG -/* This is used by the pSeries hotplug driver to allocate resource +/* This is used by the PCI hotplug driver to allocate resource * of newly plugged busses. We can try to consolidate with the - * rest of the code later, for now, keep it as-is + * rest of the code later, for now, keep it as-is as our main + * resource allocation function doesn't deal with sub-trees yet. */ void __devinit pcibios_claim_one_bus(struct pci_bus *bus) { @@ -1414,6 +1414,14 @@ void __devinit pcibios_claim_one_bus(struct pci_bus *bus) if (r->parent || !r->start || !r->flags) continue; + + pr_debug("PCI: Claiming %s: " + "Resource %d: %016llx..%016llx [%x]\n", + pci_name(dev), i, + (unsigned long long)r->start, + (unsigned long long)r->end, + (unsigned int)r->flags); + pci_claim_resource(dev, i); } } @@ -1422,6 +1430,31 @@ void __devinit pcibios_claim_one_bus(struct pci_bus *bus) pcibios_claim_one_bus(child_bus); } EXPORT_SYMBOL_GPL(pcibios_claim_one_bus); + + +/* pcibios_finish_adding_to_bus + * + * This is to be called by the hotplug code after devices have been + * added to a bus, this include calling it for a PHB that is just + * being added + */ +void pcibios_finish_adding_to_bus(struct pci_bus *bus) +{ + pr_debug("PCI: Finishing adding to hotplug bus %04x:%02x\n", + pci_domain_nr(bus), bus->number); + + /* Allocate bus and devices resources */ + pcibios_allocate_bus_resources(bus); + pcibios_claim_one_bus(bus); + + /* Add new devices to global lists. Register in proc, sysfs. */ + pci_bus_add_devices(bus); + + /* Fixup EEH */ + eeh_add_device_tree_late(bus); +} +EXPORT_SYMBOL_GPL(pcibios_finish_adding_to_bus); + #endif /* CONFIG_HOTPLUG */ int pcibios_enable_device(struct pci_dev *dev, int mask) diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c index 589a2797eac..8869001ab5d 100644 --- a/arch/powerpc/kernel/rtas_pci.c +++ b/arch/powerpc/kernel/rtas_pci.c @@ -301,51 +301,3 @@ void __init find_and_init_phbs(void) #endif /* CONFIG_PPC32 */ } } - -/* RPA-specific bits for removing PHBs */ -int pcibios_remove_root_bus(struct pci_controller *phb) -{ - struct pci_bus *b = phb->bus; - struct resource *res; - int rc, i; - - res = b->resource[0]; - if (!res->flags) { - printk(KERN_ERR "%s: no IO resource for PHB %s\n", __func__, - b->name); - return 1; - } - - rc = pcibios_unmap_io_space(b); - if (rc) { - printk(KERN_ERR "%s: failed to unmap IO on bus %s\n", - __func__, b->name); - return 1; - } - - if (release_resource(res)) { - printk(KERN_ERR "%s: failed to release IO on bus %s\n", - __func__, b->name); - return 1; - } - - for (i = 1; i < 3; ++i) { - res = b->resource[i]; - if (!res->flags && i == 0) { - printk(KERN_ERR "%s: no MEM resource for PHB %s\n", - __func__, b->name); - return 1; - } - if (res->flags && release_resource(res)) { - printk(KERN_ERR - "%s: failed to release IO %d on bus %s\n", - __func__, i, b->name); - return 1; - } - } - - pcibios_free_controller(phb); - - return 0; -} -EXPORT_SYMBOL(pcibios_remove_root_bus); diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c index 7190493e9bd..5e1ed3d60ee 100644 --- a/arch/powerpc/platforms/pseries/pci_dlpar.c +++ b/arch/powerpc/platforms/pseries/pci_dlpar.c @@ -25,6 +25,8 @@ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ +#undef DEBUG + #include #include #include @@ -69,74 +71,25 @@ EXPORT_SYMBOL_GPL(pcibios_find_pci_bus); * Remove all of the PCI devices under this bus both from the * linux pci device tree, and from the powerpc EEH address cache. */ -void -pcibios_remove_pci_devices(struct pci_bus *bus) +void pcibios_remove_pci_devices(struct pci_bus *bus) { - struct pci_dev *dev, *tmp; + struct pci_dev *dev, *tmp; + struct pci_bus *child_bus; + + /* First go down child busses */ + list_for_each_entry(child_bus, &bus->children, node) + pcibios_remove_pci_devices(child_bus); + pr_debug("PCI: Removing devices on bus %04x:%02x\n", + pci_domain_nr(bus), bus->number); list_for_each_entry_safe(dev, tmp, &bus->devices, bus_list) { + pr_debug(" * Removing %s...\n", pci_name(dev)); eeh_remove_bus_device(dev); - pci_remove_bus_device(dev); - } + pci_remove_bus_device(dev); + } } EXPORT_SYMBOL_GPL(pcibios_remove_pci_devices); -/* Must be called before pci_bus_add_devices */ -void -pcibios_fixup_new_pci_devices(struct pci_bus *bus) -{ - struct pci_dev *dev; - - list_for_each_entry(dev, &bus->devices, bus_list) { - /* Skip already-added devices */ - if (!dev->is_added) { - int i; - - /* Fill device archdata and setup iommu table */ - pcibios_setup_new_device(dev); - - pci_read_irq_line(dev); - for (i = 0; i < PCI_NUM_RESOURCES; i++) { - struct resource *r = &dev->resource[i]; - - if (r->parent || !r->start || !r->flags) - continue; - pci_claim_resource(dev, i); - } - } - } -} -EXPORT_SYMBOL_GPL(pcibios_fixup_new_pci_devices); - -static int -pcibios_pci_config_bridge(struct pci_dev *dev) -{ - u8 sec_busno; - struct pci_bus *child_bus; - - /* Get busno of downstream bus */ - pci_read_config_byte(dev, PCI_SECONDARY_BUS, &sec_busno); - - /* Add to children of PCI bridge dev->bus */ - child_bus = pci_add_new_bus(dev->bus, dev, sec_busno); - if (!child_bus) { - printk (KERN_ERR "%s: could not add second bus\n", __func__); - return -EIO; - } - sprintf(child_bus->name, "PCI Bus #%02x", child_bus->number); - - pci_scan_child_bus(child_bus); - - /* Fixup new pci devices */ - pcibios_fixup_new_pci_devices(child_bus); - - /* Make the discovered devices available */ - pci_bus_add_devices(child_bus); - - eeh_add_device_tree_late(child_bus); - return 0; -} - /** * pcibios_add_pci_devices - adds new pci devices to bus * @@ -147,10 +100,9 @@ pcibios_pci_config_bridge(struct pci_dev *dev) * is how this routine differs from other, similar pcibios * routines.) */ -void -pcibios_add_pci_devices(struct pci_bus * bus) +void pcibios_add_pci_devices(struct pci_bus * bus) { - int slotno, num, mode; + int slotno, num, mode, pass, max; struct pci_dev *dev; struct device_node *dn = pci_bus_to_OF_node(bus); @@ -162,26 +114,23 @@ pcibios_add_pci_devices(struct pci_bus * bus) if (mode == PCI_PROBE_DEVTREE) { /* use ofdt-based probe */ - of_scan_bus(dn, bus); - if (!list_empty(&bus->devices)) { - pcibios_fixup_new_pci_devices(bus); - pci_bus_add_devices(bus); - eeh_add_device_tree_late(bus); - } + of_rescan_bus(dn, bus); } else if (mode == PCI_PROBE_NORMAL) { /* use legacy probe */ slotno = PCI_SLOT(PCI_DN(dn->child)->devfn); num = pci_scan_slot(bus, PCI_DEVFN(slotno, 0)); - if (num) { - pcibios_fixup_new_pci_devices(bus); - pci_bus_add_devices(bus); - eeh_add_device_tree_late(bus); + if (!num) + return; + pcibios_setup_bus_devices(bus); + max = bus->secondary; + for (pass=0; pass < 2; pass++) + list_for_each_entry(dev, &bus->devices, bus_list) { + if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE || + dev->hdr_type == PCI_HEADER_TYPE_CARDBUS) + max = pci_scan_bridge(bus, dev, max, pass); } - - list_for_each_entry(dev, &bus->devices, bus_list) - if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) - pcibios_pci_config_bridge(dev); } + pcibios_finish_adding_to_bus(bus); } EXPORT_SYMBOL_GPL(pcibios_add_pci_devices); @@ -190,6 +139,8 @@ struct pci_controller * __devinit init_phb_dynamic(struct device_node *dn) struct pci_controller *phb; int primary; + pr_debug("PCI: Initializing new hotplug PHB %s\n", dn->full_name); + primary = list_empty(&hose_list); phb = pcibios_alloc_controller(dn); if (!phb) @@ -203,11 +154,59 @@ struct pci_controller * __devinit init_phb_dynamic(struct device_node *dn) eeh_add_device_tree_early(dn); scan_phb(phb); - pcibios_allocate_bus_resources(phb->bus); - pcibios_fixup_new_pci_devices(phb->bus); - pci_bus_add_devices(phb->bus); - eeh_add_device_tree_late(phb->bus); + pcibios_finish_adding_to_bus(phb->bus); return phb; } EXPORT_SYMBOL_GPL(init_phb_dynamic); + +/* RPA-specific bits for removing PHBs */ +int remove_phb_dynamic(struct pci_controller *phb) +{ + struct pci_bus *b = phb->bus; + struct resource *res; + int rc, i; + + pr_debug("PCI: Removing PHB %04x:%02x... \n", + pci_domain_nr(b), b->number); + + /* We cannot to remove a root bus that has children */ + if (!(list_empty(&b->children) && list_empty(&b->devices))) + return -EBUSY; + + /* We -know- there aren't any child devices anymore at this stage + * and thus, we can safely unmap the IO space as it's not in use + */ + res = &phb->io_resource; + if (res->flags & IORESOURCE_IO) { + rc = pcibios_unmap_io_space(b); + if (rc) { + printk(KERN_ERR "%s: failed to unmap IO on bus %s\n", + __func__, b->name); + return 1; + } + } + + /* Unregister the bridge device from sysfs and remove the PCI bus */ + device_unregister(b->bridge); + phb->bus = NULL; + pci_remove_bus(b); + + /* Now release the IO resource */ + if (res->flags & IORESOURCE_IO) + release_resource(res); + + /* Release memory resources */ + for (i = 0; i < 3; ++i) { + res = &phb->mem_resources[i]; + if (!(res->flags & IORESOURCE_MEM)) + continue; + release_resource(res); + } + + /* Free pci_controller data structure */ + pcibios_free_controller(phb); + + return 0; +} +EXPORT_SYMBOL_GPL(remove_phb_dynamic); diff --git a/drivers/pci/hotplug/rpadlpar_core.c b/drivers/pci/hotplug/rpadlpar_core.c index 9c2a22fed18..4e3e0382c16 100644 --- a/drivers/pci/hotplug/rpadlpar_core.c +++ b/drivers/pci/hotplug/rpadlpar_core.c @@ -14,6 +14,9 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ + +#undef DEBUG + #include #include #include @@ -151,20 +154,20 @@ static void dlpar_pci_add_bus(struct device_node *dn) return; } + /* Scan below the new bridge */ if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE || dev->hdr_type == PCI_HEADER_TYPE_CARDBUS) of_scan_pci_bridge(dn, dev); - pcibios_fixup_new_pci_devices(dev->subordinate); - - /* Claim new bus resources */ - pcibios_claim_one_bus(dev->bus); - /* Map IO space for child bus, which may or may not succeed */ pcibios_map_io_space(dev->subordinate); - /* Add new devices to global lists. Register in proc, sysfs. */ - pci_bus_add_devices(phb->bus); + /* Finish adding it : resource allocation, adding devices, etc... + * Note that we need to perform the finish pass on the -parent- + * bus of the EADS bridge so the bridge device itself gets + * properly added + */ + pcibios_finish_adding_to_bus(phb->bus); } static int dlpar_add_pci_slot(char *drc_name, struct device_node *dn) @@ -203,27 +206,6 @@ static int dlpar_add_pci_slot(char *drc_name, struct device_node *dn) return 0; } -static int dlpar_remove_root_bus(struct pci_controller *phb) -{ - struct pci_bus *phb_bus; - int rc; - - phb_bus = phb->bus; - if (!(list_empty(&phb_bus->children) && - list_empty(&phb_bus->devices))) { - return -EBUSY; - } - - rc = pcibios_remove_root_bus(phb); - if (rc) - return -EIO; - - device_unregister(phb_bus->bridge); - pci_remove_bus(phb_bus); - - return 0; -} - static int dlpar_remove_phb(char *drc_name, struct device_node *dn) { struct slot *slot; @@ -235,18 +217,15 @@ static int dlpar_remove_phb(char *drc_name, struct device_node *dn) /* If pci slot is hotplugable, use hotplug to remove it */ slot = find_php_slot(dn); - if (slot) { - if (rpaphp_deregister_slot(slot)) { - printk(KERN_ERR - "%s: unable to remove hotplug slot %s\n", - __func__, drc_name); - return -EIO; - } + if (slot && rpaphp_deregister_slot(slot)) { + printk(KERN_ERR "%s: unable to remove hotplug slot %s\n", + __func__, drc_name); + return -EIO; } pdn = dn->data; BUG_ON(!pdn || !pdn->phb); - rc = dlpar_remove_root_bus(pdn->phb); + rc = remove_phb_dynamic(pdn->phb); if (rc < 0) return rc; @@ -378,26 +357,38 @@ int dlpar_remove_pci_slot(char *drc_name, struct device_node *dn) if (!bus) return -EINVAL; - /* If pci slot is hotplugable, use hotplug to remove it */ + pr_debug("PCI: Removing PCI slot below EADS bridge %s\n", + bus->self ? pci_name(bus->self) : ""); + slot = find_php_slot(dn); if (slot) { + pr_debug("PCI: Removing hotplug slot for %04x:%02x...\n", + pci_domain_nr(bus), bus->number); + if (rpaphp_deregister_slot(slot)) { printk(KERN_ERR "%s: unable to remove hotplug slot %s\n", __func__, drc_name); return -EIO; } - } else - pcibios_remove_pci_devices(bus); + } + + /* Remove all devices below slot */ + pcibios_remove_pci_devices(bus); + /* Unmap PCI IO space */ if (pcibios_unmap_io_space(bus)) { printk(KERN_ERR "%s: failed to unmap bus range\n", __func__); return -ERANGE; } + /* Remove the EADS bridge device itself */ BUG_ON(!bus->self); + pr_debug("PCI: Now removing bridge device %s\n", pci_name(bus->self)); + eeh_remove_bus_device(bus->self); pci_remove_bus_device(bus->self); + return 0; } -- cgit v1.2.3-70-g09d2 From 7eef440a545c7f812ed10b49d4a10a351df9cad6 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 27 Oct 2008 19:48:56 +0000 Subject: powerpc/pci: Cosmetic cleanups of pci-common.c This does a few cosmetic cleanups, moving a couple of things around but without actually changing what the code does. (There is a minor change in ordering of operations in pcibios_setup_bus_devices but it should have no impact). Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/pci-common.c | 77 +++++++++++++++++++--------------------- 1 file changed, 36 insertions(+), 41 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index f3fd7eb90a7..91c3f52e33a 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -203,25 +203,6 @@ char __devinit *pcibios_setup(char *str) return str; } -static void __devinit pcibios_setup_new_device(struct pci_dev *dev) -{ - struct dev_archdata *sd = &dev->dev.archdata; - - sd->of_node = pci_device_to_OF_node(dev); - - pr_debug("PCI: device %s OF node: %s\n", pci_name(dev), - sd->of_node ? sd->of_node->full_name : ""); - - sd->dma_ops = pci_dma_ops; -#ifdef CONFIG_PPC32 - sd->dma_data = (void *)PCI_DRAM_OFFSET; -#endif - set_dev_node(&dev->dev, pcibus_to_node(dev->bus)); - - if (ppc_md.pci_dma_dev_setup) - ppc_md.pci_dma_dev_setup(dev); -} - /* * Reads the interrupt pin to determine if interrupt is use by card. * If the interrupt is used, then gets the interrupt line from the @@ -1074,33 +1055,14 @@ static void __devinit pcibios_fixup_bridge(struct pci_bus *bus) } } -void __devinit pcibios_setup_bus_devices(struct pci_bus *bus) -{ - struct pci_dev *dev; - - pr_debug("PCI: Fixup bus %d (%s)\n", - bus->number, bus->self ? pci_name(bus->self) : "PHB"); - - /* Setup DMA for all PCI devices on that bus */ - list_for_each_entry(dev, &bus->devices, bus_list) - pcibios_setup_new_device(dev); - - /* Read default IRQs and fixup if necessary */ - list_for_each_entry(dev, &bus->devices, bus_list) { - pci_read_irq_line(dev); - if (ppc_md.pci_irq_fixup) - ppc_md.pci_irq_fixup(dev); - } -} - void __devinit pcibios_setup_bus_self(struct pci_bus *bus) { - /* Fix up the bus resources */ + /* Fix up the bus resources for P2P bridges */ if (bus->self != NULL) pcibios_fixup_bridge(bus); /* Platform specific bus fixups. This is currently only used - * by fsl_pci and I'm hoping getting rid of it at some point + * by fsl_pci and I'm hoping to get rid of it at some point */ if (ppc_md.pcibios_fixup_bus) ppc_md.pcibios_fixup_bus(bus); @@ -1110,10 +1072,43 @@ void __devinit pcibios_setup_bus_self(struct pci_bus *bus) ppc_md.pci_dma_bus_setup(bus); } +void __devinit pcibios_setup_bus_devices(struct pci_bus *bus) +{ + struct pci_dev *dev; + + pr_debug("PCI: Fixup bus devices %d (%s)\n", + bus->number, bus->self ? pci_name(bus->self) : "PHB"); + + list_for_each_entry(dev, &bus->devices, bus_list) { + struct dev_archdata *sd = &dev->dev.archdata; + + /* Setup OF node pointer in archdata */ + sd->of_node = pci_device_to_OF_node(dev); + + /* Fixup NUMA node as it may not be setup yet by the generic + * code and is needed by the DMA init + */ + set_dev_node(&dev->dev, pcibus_to_node(dev->bus)); + + /* Hook up default DMA ops */ + sd->dma_ops = pci_dma_ops; + sd->dma_data = (void *)PCI_DRAM_OFFSET; + + /* Additional platform DMA/iommu setup */ + if (ppc_md.pci_dma_dev_setup) + ppc_md.pci_dma_dev_setup(dev); + + /* Read default IRQs and fixup if necessary */ + pci_read_irq_line(dev); + if (ppc_md.pci_irq_fixup) + ppc_md.pci_irq_fixup(dev); + } +} + void __devinit pcibios_fixup_bus(struct pci_bus *bus) { /* When called from the generic PCI probe, read PCI<->PCI bridge - * bases. This isn't called when generating the PCI tree from + * bases. This is -not- called when generating the PCI tree from * the OF device-tree. */ if (bus->self != NULL) -- cgit v1.2.3-70-g09d2 From 597bc5c00b666fe123abb0af64f6e86f7ab72a90 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Mon, 27 Oct 2008 23:56:03 +0000 Subject: powerpc: Improve resolution of VDSO clock_gettime Currently the clock_gettime implementation in the VDSO produces a result with microsecond resolution for the cases that are handled without a system call, i.e. CLOCK_REALTIME and CLOCK_MONOTONIC. The nanoseconds field of the result is obtained by computing a microseconds value and multiplying by 1000. This changes the code in the VDSO to do the computation for clock_gettime with nanosecond resolution. That means that the resolution of the result will ultimately depend on the timebase frequency. Because the timestamp in the VDSO datapage (stamp_xsec, the real time corresponding to the timebase count in tb_orig_stamp) is in units of 2^-20 seconds, it doesn't have sufficient resolution for computing a result with nanosecond resolution. Therefore this adds a copy of xtime to the VDSO datapage and updates it in update_gtod() along with the other time-related fields. Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/vdso_datapage.h | 3 + arch/powerpc/kernel/asm-offsets.c | 1 + arch/powerpc/kernel/time.c | 1 + arch/powerpc/kernel/vdso32/gettimeofday.S | 208 ++++++++++++++++++------------ arch/powerpc/kernel/vdso64/gettimeofday.S | 141 ++++++++++---------- 5 files changed, 206 insertions(+), 148 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h index f01393224b5..13c2c283e17 100644 --- a/arch/powerpc/include/asm/vdso_datapage.h +++ b/arch/powerpc/include/asm/vdso_datapage.h @@ -39,6 +39,7 @@ #ifndef __ASSEMBLY__ #include +#include #define SYSCALL_MAP_SIZE ((__NR_syscalls + 31) / 32) @@ -83,6 +84,7 @@ struct vdso_data { __u32 icache_log_block_size; /* L1 i-cache log block size */ __s32 wtom_clock_sec; /* Wall to monotonic clock */ __s32 wtom_clock_nsec; + struct timespec stamp_xtime; /* xtime as at tb_orig_stamp */ __u32 syscall_map_64[SYSCALL_MAP_SIZE]; /* map of syscalls */ __u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */ }; @@ -102,6 +104,7 @@ struct vdso_data { __u32 tz_dsttime; /* Type of dst correction 0x5C */ __s32 wtom_clock_sec; /* Wall to monotonic clock */ __s32 wtom_clock_nsec; + struct timespec stamp_xtime; /* xtime as at tb_orig_stamp */ __u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */ __u32 dcache_block_size; /* L1 d-cache block size */ __u32 icache_block_size; /* L1 i-cache block size */ diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 75c5dd0138f..050abfd5c17 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -306,6 +306,7 @@ int main(void) DEFINE(CFG_SYSCALL_MAP32, offsetof(struct vdso_data, syscall_map_32)); DEFINE(WTOM_CLOCK_SEC, offsetof(struct vdso_data, wtom_clock_sec)); DEFINE(WTOM_CLOCK_NSEC, offsetof(struct vdso_data, wtom_clock_nsec)); + DEFINE(STAMP_XTIME, offsetof(struct vdso_data, stamp_xtime)); DEFINE(CFG_ICACHE_BLOCKSZ, offsetof(struct vdso_data, icache_block_size)); DEFINE(CFG_DCACHE_BLOCKSZ, offsetof(struct vdso_data, dcache_block_size)); DEFINE(CFG_ICACHE_LOGBLOCKSZ, offsetof(struct vdso_data, icache_log_block_size)); diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index e2ee66b5831..8389c5be149 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -456,6 +456,7 @@ static inline void update_gtod(u64 new_tb_stamp, u64 new_stamp_xsec, vdso_data->tb_to_xs = new_tb_to_xs; vdso_data->wtom_clock_sec = wall_to_monotonic.tv_sec; vdso_data->wtom_clock_nsec = wall_to_monotonic.tv_nsec; + vdso_data->stamp_xtime = xtime; smp_wmb(); ++(vdso_data->tb_update_count); } diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S index 72ca26df457..ee038d4bf25 100644 --- a/arch/powerpc/kernel/vdso32/gettimeofday.S +++ b/arch/powerpc/kernel/vdso32/gettimeofday.S @@ -16,6 +16,13 @@ #include #include +/* Offset for the low 32-bit part of a field of long type */ +#ifdef CONFIG_PPC64 +#define LOPART 4 +#else +#define LOPART 0 +#endif + .text /* * Exact prototype of gettimeofday @@ -90,101 +97,53 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime) mflr r12 /* r12 saves lr */ .cfi_register lr,r12 - mr r10,r3 /* r10 saves id */ mr r11,r4 /* r11 saves tp */ bl __get_datapage@local /* get data page */ mr r9,r3 /* datapage ptr in r9 */ - beq cr1,50f /* if monotonic -> jump there */ - - /* - * CLOCK_REALTIME - */ - - bl __do_get_xsec@local /* get xsec from tb & kernel */ - bne- 98f /* out of line -> do syscall */ - - /* seconds are xsec >> 20 */ - rlwinm r5,r4,12,20,31 - rlwimi r5,r3,12,0,19 - stw r5,TSPC32_TV_SEC(r11) - /* get remaining xsec and convert to nsec. we scale - * up remaining xsec by 12 bits and get the top 32 bits - * of the multiplication, then we multiply by 1000 - */ - rlwinm r5,r4,12,0,19 - lis r6,1000000@h - ori r6,r6,1000000@l - mulhwu r5,r5,r6 - mulli r5,r5,1000 - stw r5,TSPC32_TV_NSEC(r11) - mtlr r12 - crclr cr0*4+so - li r3,0 - blr +50: bl __do_get_tspec@local /* get sec/nsec from tb & kernel */ + bne cr1,80f /* not monotonic -> all done */ /* * CLOCK_MONOTONIC */ -50: bl __do_get_xsec@local /* get xsec from tb & kernel */ - bne- 98f /* out of line -> do syscall */ - - /* seconds are xsec >> 20 */ - rlwinm r6,r4,12,20,31 - rlwimi r6,r3,12,0,19 - - /* get remaining xsec and convert to nsec. we scale - * up remaining xsec by 12 bits and get the top 32 bits - * of the multiplication, then we multiply by 1000 - */ - rlwinm r7,r4,12,0,19 - lis r5,1000000@h - ori r5,r5,1000000@l - mulhwu r7,r7,r5 - mulli r7,r7,1000 - /* now we must fixup using wall to monotonic. We need to snapshot * that value and do the counter trick again. Fortunately, we still * have the counter value in r8 that was returned by __do_get_xsec. - * At this point, r6,r7 contain our sec/nsec values, r3,r4 and r5 - * can be used + * At this point, r3,r4 contain our sec/nsec values, r5 and r6 + * can be used, r7 contains NSEC_PER_SEC. */ - lwz r3,WTOM_CLOCK_SEC(r9) - lwz r4,WTOM_CLOCK_NSEC(r9) + lwz r5,WTOM_CLOCK_SEC(r9) + lwz r6,WTOM_CLOCK_NSEC(r9) - /* We now have our result in r3,r4. We create a fake dependency - * on that result and re-check the counter + /* We now have our offset in r5,r6. We create a fake dependency + * on that value and re-check the counter */ - or r5,r4,r3 - xor r0,r5,r5 + or r0,r6,r5 + xor r0,r0,r0 add r9,r9,r0 -#ifdef CONFIG_PPC64 - lwz r0,(CFG_TB_UPDATE_COUNT+4)(r9) -#else - lwz r0,(CFG_TB_UPDATE_COUNT)(r9) -#endif + lwz r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9) cmpl cr0,r8,r0 /* check if updated */ bne- 50b - /* Calculate and store result. Note that this mimmics the C code, + /* Calculate and store result. Note that this mimics the C code, * which may cause funny results if nsec goes negative... is that * possible at all ? */ - add r3,r3,r6 - add r4,r4,r7 - lis r5,NSEC_PER_SEC@h - ori r5,r5,NSEC_PER_SEC@l - cmpl cr0,r4,r5 - cmpli cr1,r4,0 + add r3,r3,r5 + add r4,r4,r6 + cmpw cr0,r4,r7 + cmpwi cr1,r4,0 blt 1f - subf r4,r5,r4 + subf r4,r7,r4 addi r3,r3,1 -1: bge cr1,1f +1: bge cr1,80f addi r3,r3,-1 - add r4,r4,r5 -1: stw r3,TSPC32_TV_SEC(r11) + add r4,r4,r7 + +80: stw r3,TSPC32_TV_SEC(r11) stw r4,TSPC32_TV_NSEC(r11) mtlr r12 @@ -195,10 +154,6 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime) /* * syscall fallback */ -98: - mtlr r12 - mr r3,r10 - mr r4,r11 99: li r0,__NR_clock_gettime sc @@ -254,11 +209,7 @@ __do_get_xsec: /* Check for update count & load values. We use the low * order 32 bits of the update count */ -#ifdef CONFIG_PPC64 -1: lwz r8,(CFG_TB_UPDATE_COUNT+4)(r9) -#else -1: lwz r8,(CFG_TB_UPDATE_COUNT)(r9) -#endif +1: lwz r8,(CFG_TB_UPDATE_COUNT+LOPART)(r9) andi. r0,r8,1 /* pending update ? loop */ bne- 1b xor r0,r8,r8 /* create dependency */ @@ -305,11 +256,7 @@ __do_get_xsec: or r6,r4,r3 xor r0,r6,r6 add r9,r9,r0 -#ifdef CONFIG_PPC64 - lwz r0,(CFG_TB_UPDATE_COUNT+4)(r9) -#else - lwz r0,(CFG_TB_UPDATE_COUNT)(r9) -#endif + lwz r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9) cmpl cr0,r8,r0 /* check if updated */ bne- 1b @@ -322,3 +269,98 @@ __do_get_xsec: */ 3: blr .cfi_endproc + +/* + * This is the core of clock_gettime(), it returns the current + * time in seconds and nanoseconds in r3 and r4. + * It expects the datapage ptr in r9 and doesn't clobber it. + * It clobbers r0, r5, r6, r10 and returns NSEC_PER_SEC in r7. + * On return, r8 contains the counter value that can be reused. + * This clobbers cr0 but not any other cr field. + */ +__do_get_tspec: + .cfi_startproc + /* Check for update count & load values. We use the low + * order 32 bits of the update count + */ +1: lwz r8,(CFG_TB_UPDATE_COUNT+LOPART)(r9) + andi. r0,r8,1 /* pending update ? loop */ + bne- 1b + xor r0,r8,r8 /* create dependency */ + add r9,r9,r0 + + /* Load orig stamp (offset to TB) */ + lwz r5,CFG_TB_ORIG_STAMP(r9) + lwz r6,(CFG_TB_ORIG_STAMP+4)(r9) + + /* Get a stable TB value */ +2: mftbu r3 + mftbl r4 + mftbu r0 + cmpl cr0,r3,r0 + bne- 2b + + /* Subtract tb orig stamp and shift left 12 bits. + */ + subfc r7,r6,r4 + subfe r0,r5,r3 + slwi r0,r0,12 + rlwimi. r0,r7,12,20,31 + slwi r7,r7,12 + + /* Load scale factor & do multiplication */ + lwz r5,CFG_TB_TO_XS(r9) /* load values */ + lwz r6,(CFG_TB_TO_XS+4)(r9) + mulhwu r3,r7,r6 + mullw r10,r7,r5 + mulhwu r4,r7,r5 + addc r10,r3,r10 + li r3,0 + + beq+ 4f /* skip high part computation if 0 */ + mulhwu r3,r0,r5 + mullw r7,r0,r5 + mulhwu r5,r0,r6 + mullw r6,r0,r6 + adde r4,r4,r7 + addze r3,r3 + addc r4,r4,r5 + addze r3,r3 + addc r10,r10,r6 + +4: addze r4,r4 /* add in carry */ + lis r7,NSEC_PER_SEC@h + ori r7,r7,NSEC_PER_SEC@l + mulhwu r4,r4,r7 /* convert to nanoseconds */ + + /* At this point, we have seconds & nanoseconds since the xtime + * stamp in r3+CA and r4. Load & add the xtime stamp. + */ +#ifdef CONFIG_PPC64 + lwz r5,STAMP_XTIME+TSPC64_TV_SEC+LOPART(r9) + lwz r6,STAMP_XTIME+TSPC64_TV_NSEC+LOPART(r9) +#else + lwz r5,STAMP_XTIME+TSPC32_TV_SEC(r9) + lwz r6,STAMP_XTIME+TSPC32_TV_NSEC(r9) +#endif + add r4,r4,r6 + adde r3,r3,r5 + + /* We now have our result in r3,r4. We create a fake dependency + * on that result and re-check the counter + */ + or r6,r4,r3 + xor r0,r6,r6 + add r9,r9,r0 + lwz r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9) + cmpl cr0,r8,r0 /* check if updated */ + bne- 1b + + /* check for nanosecond overflow and adjust if necessary */ + cmpw r4,r7 + bltlr /* all done if no overflow */ + subf r4,r7,r4 /* adjust if overflow */ + addi r3,r3,1 + + blr + .cfi_endproc diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S index c6401f9e37f..262cd5857a5 100644 --- a/arch/powerpc/kernel/vdso64/gettimeofday.S +++ b/arch/powerpc/kernel/vdso64/gettimeofday.S @@ -75,90 +75,49 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime) mflr r12 /* r12 saves lr */ .cfi_register lr,r12 - mr r10,r3 /* r10 saves id */ mr r11,r4 /* r11 saves tp */ bl V_LOCAL_FUNC(__get_datapage) /* get data page */ - beq cr1,50f /* if monotonic -> jump there */ - - /* - * CLOCK_REALTIME - */ - - bl V_LOCAL_FUNC(__do_get_xsec) /* get xsec from tb & kernel */ - - lis r7,15 /* r7 = 1000000 = USEC_PER_SEC */ - ori r7,r7,16960 - rldicl r5,r4,44,20 /* r5 = sec = xsec / XSEC_PER_SEC */ - rldicr r6,r5,20,43 /* r6 = sec * XSEC_PER_SEC */ - std r5,TSPC64_TV_SEC(r11) /* store sec in tv */ - subf r0,r6,r4 /* r0 = xsec = (xsec - r6) */ - mulld r0,r0,r7 /* usec = (xsec * USEC_PER_SEC) / - * XSEC_PER_SEC - */ - rldicl r0,r0,44,20 - mulli r0,r0,1000 /* nsec = usec * 1000 */ - std r0,TSPC64_TV_NSEC(r11) /* store nsec in tp */ - - mtlr r12 - crclr cr0*4+so - li r3,0 - blr +50: bl V_LOCAL_FUNC(__do_get_tspec) /* get time from tb & kernel */ + bne cr1,80f /* if not monotonic, all done */ /* * CLOCK_MONOTONIC */ -50: bl V_LOCAL_FUNC(__do_get_xsec) /* get xsec from tb & kernel */ - - lis r7,15 /* r7 = 1000000 = USEC_PER_SEC */ - ori r7,r7,16960 - rldicl r5,r4,44,20 /* r5 = sec = xsec / XSEC_PER_SEC */ - rldicr r6,r5,20,43 /* r6 = sec * XSEC_PER_SEC */ - subf r0,r6,r4 /* r0 = xsec = (xsec - r6) */ - mulld r0,r0,r7 /* usec = (xsec * USEC_PER_SEC) / - * XSEC_PER_SEC - */ - rldicl r6,r0,44,20 - mulli r6,r6,1000 /* nsec = usec * 1000 */ - /* now we must fixup using wall to monotonic. We need to snapshot * that value and do the counter trick again. Fortunately, we still - * have the counter value in r8 that was returned by __do_get_xsec. - * At this point, r5,r6 contain our sec/nsec values. - * can be used + * have the counter value in r8 that was returned by __do_get_tspec. + * At this point, r4,r5 contain our sec/nsec values. */ - lwa r4,WTOM_CLOCK_SEC(r3) - lwa r7,WTOM_CLOCK_NSEC(r3) + lwa r6,WTOM_CLOCK_SEC(r3) + lwa r9,WTOM_CLOCK_NSEC(r3) - /* We now have our result in r4,r7. We create a fake dependency + /* We now have our result in r6,r9. We create a fake dependency * on that result and re-check the counter */ - or r9,r4,r7 - xor r0,r9,r9 + or r0,r6,r9 + xor r0,r0,r0 add r3,r3,r0 ld r0,CFG_TB_UPDATE_COUNT(r3) cmpld cr0,r0,r8 /* check if updated */ bne- 50b - /* Calculate and store result. Note that this mimmics the C code, - * which may cause funny results if nsec goes negative... is that - * possible at all ? + /* Add wall->monotonic offset and check for overflow or underflow. */ - add r4,r4,r5 - add r7,r7,r6 - lis r9,NSEC_PER_SEC@h - ori r9,r9,NSEC_PER_SEC@l - cmpl cr0,r7,r9 - cmpli cr1,r7,0 + add r4,r4,r6 + add r5,r5,r9 + cmpd cr0,r5,r7 + cmpdi cr1,r5,0 blt 1f - subf r7,r9,r7 + subf r5,r7,r5 addi r4,r4,1 -1: bge cr1,1f +1: bge cr1,80f addi r4,r4,-1 - add r7,r7,r9 -1: std r4,TSPC64_TV_SEC(r11) - std r7,TSPC64_TV_NSEC(r11) + add r5,r5,r7 + +80: std r4,TSPC64_TV_SEC(r11) + std r5,TSPC64_TV_NSEC(r11) mtlr r12 crclr cr0*4+so @@ -168,10 +127,6 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime) /* * syscall fallback */ -98: - mtlr r12 - mr r3,r10 - mr r4,r11 99: li r0,__NR_clock_gettime sc @@ -253,3 +208,59 @@ V_FUNCTION_BEGIN(__do_get_xsec) blr .cfi_endproc V_FUNCTION_END(__do_get_xsec) + +/* + * This is the core of clock_gettime(), it returns the current + * time in seconds and nanoseconds in r4 and r5. + * It expects the datapage ptr in r3 and doesn't clobber it. + * It clobbers r0 and r6 and returns NSEC_PER_SEC in r7. + * On return, r8 contains the counter value that can be reused. + * This clobbers cr0 but not any other cr field. + */ +V_FUNCTION_BEGIN(__do_get_tspec) + .cfi_startproc + /* check for update count & load values */ +1: ld r8,CFG_TB_UPDATE_COUNT(r3) + andi. r0,r8,1 /* pending update ? loop */ + bne- 1b + xor r0,r8,r8 /* create dependency */ + add r3,r3,r0 + + /* Get TB & offset it. We use the MFTB macro which will generate + * workaround code for Cell. + */ + MFTB(r7) + ld r9,CFG_TB_ORIG_STAMP(r3) + subf r7,r9,r7 + + /* Scale result */ + ld r5,CFG_TB_TO_XS(r3) + sldi r7,r7,12 /* compute time since stamp_xtime */ + mulhdu r6,r7,r5 /* in units of 2^-32 seconds */ + + /* Add stamp since epoch */ + ld r4,STAMP_XTIME+TSPC64_TV_SEC(r3) + ld r5,STAMP_XTIME+TSPC64_TV_NSEC(r3) + or r0,r4,r5 + or r0,r0,r6 + xor r0,r0,r0 + add r3,r3,r0 + ld r0,CFG_TB_UPDATE_COUNT(r3) + cmpld r0,r8 /* check if updated */ + bne- 1b /* reload if so */ + + /* convert to seconds & nanoseconds and add to stamp */ + lis r7,NSEC_PER_SEC@h + ori r7,r7,NSEC_PER_SEC@l + mulhwu r0,r6,r7 /* compute nanoseconds and */ + srdi r6,r6,32 /* seconds since stamp_xtime */ + clrldi r0,r0,32 + add r5,r5,r0 /* add nanoseconds together */ + cmpd r5,r7 /* overflow? */ + add r4,r4,r6 + bltlr /* all done if no overflow */ + subf r5,r7,r5 /* if overflow, adjust */ + addi r4,r4,1 + blr + .cfi_endproc +V_FUNCTION_END(__do_get_tspec) -- cgit v1.2.3-70-g09d2 From 3cc698789a3f44dabc5eed389b6c123caf787c0f Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Tue, 28 Oct 2008 00:18:11 +0000 Subject: powerpc: Eliminate unused do_gtod variable Since we started using the generic timekeeping code, we haven't had a powerpc-specific version of do_gettimeofday, and hence there is now nothing that reads the do_gtod variable in arch/powerpc/kernel/time.c. This therefore removes it and the code that sets it. Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/time.h | 20 -------------------- arch/powerpc/kernel/time.c | 35 ----------------------------------- 2 files changed, 55 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h index febd581ec9b..27ccb764fda 100644 --- a/arch/powerpc/include/asm/time.h +++ b/arch/powerpc/include/asm/time.h @@ -48,26 +48,6 @@ extern unsigned long ppc_proc_freq; extern unsigned long ppc_tb_freq; #define DEFAULT_TB_FREQ 125000000UL -/* - * By putting all of this stuff into a single struct we - * reduce the number of cache lines touched by do_gettimeofday. - * Both by collecting all of the data in one cache line and - * by touching only one TOC entry on ppc64. - */ -struct gettimeofday_vars { - u64 tb_to_xs; - u64 stamp_xsec; - u64 tb_orig_stamp; -}; - -struct gettimeofday_struct { - unsigned long tb_ticks_per_sec; - struct gettimeofday_vars vars[2]; - struct gettimeofday_vars * volatile varp; - unsigned var_idx; - unsigned tb_to_us; -}; - struct div_result { u64 result_high; u64 result_low; diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 8389c5be149..e1f3a514042 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -164,8 +164,6 @@ static u64 tb_to_ns_scale __read_mostly; static unsigned tb_to_ns_shift __read_mostly; static unsigned long boot_tb __read_mostly; -static struct gettimeofday_struct do_gtod; - extern struct timezone sys_tz; static long timezone_offset; @@ -415,31 +413,9 @@ void udelay(unsigned long usecs) } EXPORT_SYMBOL(udelay); - -/* - * There are two copies of tb_to_xs and stamp_xsec so that no - * lock is needed to access and use these values in - * do_gettimeofday. We alternate the copies and as long as a - * reasonable time elapses between changes, there will never - * be inconsistent values. ntpd has a minimum of one minute - * between updates. - */ static inline void update_gtod(u64 new_tb_stamp, u64 new_stamp_xsec, u64 new_tb_to_xs) { - unsigned temp_idx; - struct gettimeofday_vars *temp_varp; - - temp_idx = (do_gtod.var_idx == 0); - temp_varp = &do_gtod.vars[temp_idx]; - - temp_varp->tb_to_xs = new_tb_to_xs; - temp_varp->tb_orig_stamp = new_tb_stamp; - temp_varp->stamp_xsec = new_stamp_xsec; - smp_mb(); - do_gtod.varp = temp_varp; - do_gtod.var_idx = temp_idx; - /* * tb_update_count is used to allow the userspace gettimeofday code * to assure itself that it sees a consistent view of the tb_to_xs and @@ -515,9 +491,7 @@ static int __init iSeries_tb_recal(void) tb_ticks_per_sec = new_tb_ticks_per_sec; calc_cputime_factors(); div128_by_32( XSEC_PER_SEC, 0, tb_ticks_per_sec, &divres ); - do_gtod.tb_ticks_per_sec = tb_ticks_per_sec; tb_to_xs = divres.result_low; - do_gtod.varp->tb_to_xs = tb_to_xs; vdso_data->tb_ticks_per_sec = tb_ticks_per_sec; vdso_data->tb_to_xs = tb_to_xs; } @@ -989,15 +963,6 @@ void __init time_init(void) sys_tz.tz_dsttime = 0; } - do_gtod.varp = &do_gtod.vars[0]; - do_gtod.var_idx = 0; - do_gtod.varp->tb_orig_stamp = tb_last_jiffy; - __get_cpu_var(last_jiffy) = tb_last_jiffy; - do_gtod.varp->stamp_xsec = (u64) xtime.tv_sec * XSEC_PER_SEC; - do_gtod.tb_ticks_per_sec = tb_ticks_per_sec; - do_gtod.varp->tb_to_xs = tb_to_xs; - do_gtod.tb_to_us = tb_to_us; - vdso_data->tb_orig_stamp = tb_last_jiffy; vdso_data->tb_update_count = 0; vdso_data->tb_ticks_per_sec = tb_ticks_per_sec; -- cgit v1.2.3-70-g09d2 From 54018178ef05e32f140158cb7d7770b66042d131 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 12 Nov 2008 18:20:37 +0000 Subject: powerpc: Use for_each_node_with_property() in of_irq_map_init() Signed-off-by: Michael Ellerman Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/prom_parse.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/prom_parse.c b/arch/powerpc/kernel/prom_parse.c index bc1fb27368a..2a1c02c5696 100644 --- a/arch/powerpc/kernel/prom_parse.c +++ b/arch/powerpc/kernel/prom_parse.c @@ -731,10 +731,7 @@ void of_irq_map_init(unsigned int flags) if (flags & OF_IMAP_NO_PHANDLE) { struct device_node *np; - for(np = NULL; (np = of_find_all_nodes(np)) != NULL;) { - if (of_get_property(np, "interrupt-controller", NULL) - == NULL) - continue; + for_each_node_with_property(np, "interrupt-controller") { /* Skip /chosen/interrupt-controller */ if (strcmp(np->name, "chosen") == 0) continue; -- cgit v1.2.3-70-g09d2 From 25ddd738c2ebffb6c2d3cf29c91b986d1bb39c99 Mon Sep 17 00:00:00 2001 From: Milton Miller Date: Fri, 14 Nov 2008 20:11:49 +0000 Subject: powerpc: Provide a separate handler for each IPI action With the new generic smp call function helpers, I noticed the code in smp_message_recv was a single function call in many cases. While getting the message number from the ipi data is easy, we can reduce the path length by a function and data-dependent switch by registering seperate IPI actions for these simple calls. Originally I left the ipi action array exposed, but then I realized the registration code should be common too. The three users each had their own name array, so I made a fourth to convert all users to use a common one. Signed-off-by: Milton Miller Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/smp.h | 7 +++++ arch/powerpc/kernel/smp.c | 59 ++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 66 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index 1866cec4f96..c25f73d1d84 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -81,6 +81,13 @@ extern int cpu_to_core_id(int cpu); #define PPC_MSG_CALL_FUNC_SINGLE 2 #define PPC_MSG_DEBUGGER_BREAK 3 +/* + * irq controllers that have dedicated ipis per message and don't + * need additional code in the action handler may use this + */ +extern int smp_request_message_ipi(int virq, int message); +extern const char *smp_ipi_name[]; + void smp_init_iSeries(void); void smp_init_pSeries(void); void smp_init_cell(void); diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index ff9f7010097..a59d8d72bb9 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -123,6 +123,65 @@ void smp_message_recv(int msg) } } +static irqreturn_t call_function_action(int irq, void *data) +{ + generic_smp_call_function_interrupt(); + return IRQ_HANDLED; +} + +static irqreturn_t reschedule_action(int irq, void *data) +{ + /* we just need the return path side effect of checking need_resched */ + return IRQ_HANDLED; +} + +static irqreturn_t call_function_single_action(int irq, void *data) +{ + generic_smp_call_function_single_interrupt(); + return IRQ_HANDLED; +} + +static irqreturn_t debug_ipi_action(int irq, void *data) +{ + smp_message_recv(PPC_MSG_DEBUGGER_BREAK); + return IRQ_HANDLED; +} + +static irq_handler_t smp_ipi_action[] = { + [PPC_MSG_CALL_FUNCTION] = call_function_action, + [PPC_MSG_RESCHEDULE] = reschedule_action, + [PPC_MSG_CALL_FUNC_SINGLE] = call_function_single_action, + [PPC_MSG_DEBUGGER_BREAK] = debug_ipi_action, +}; + +const char *smp_ipi_name[] = { + [PPC_MSG_CALL_FUNCTION] = "ipi call function", + [PPC_MSG_RESCHEDULE] = "ipi reschedule", + [PPC_MSG_CALL_FUNC_SINGLE] = "ipi call function single", + [PPC_MSG_DEBUGGER_BREAK] = "ipi debugger", +}; + +/* optional function to request ipi, for controllers with >= 4 ipis */ +int smp_request_message_ipi(int virq, int msg) +{ + int err; + + if (msg < 0 || msg > PPC_MSG_DEBUGGER_BREAK) { + return -EINVAL; + } +#if !defined(CONFIG_DEBUGGER) && !defined(CONFIG_KEXEC) + if (msg == PPC_MSG_DEBUGGER_BREAK) { + return 1; + } +#endif + err = request_irq(virq, smp_ipi_action[msg], IRQF_DISABLED|IRQF_PERCPU, + smp_ipi_name[msg], 0); + WARN(err < 0, "unable to request_irq %d for %s (rc %d)\n", + virq, smp_ipi_name[msg], err); + + return err; +} + void smp_send_reschedule(int cpu) { if (likely(smp_ops)) -- cgit v1.2.3-70-g09d2 From 1b98326b91eb9eea346945779e1f245aa66b17ce Mon Sep 17 00:00:00 2001 From: Kumar Gala Date: Wed, 19 Nov 2008 04:39:53 +0000 Subject: powerpc: Add MSR[CE, DE] to the MSR bits we print on show_regs() Signed-off-by: Kumar Gala Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/process.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 957bded0020..b0383236dd0 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -467,6 +467,8 @@ static struct regbit { {MSR_VEC, "VEC"}, {MSR_VSX, "VSX"}, {MSR_ME, "ME"}, + {MSR_CE, "CE"}, + {MSR_DE, "DE"}, {MSR_IR, "IR"}, {MSR_DR, "DR"}, {0, NULL} -- cgit v1.2.3-70-g09d2 From c4d04be11f99cc9ce4e3801a5da235727db704a9 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 20 Nov 2008 03:24:07 +0000 Subject: powerpc: Allow the max stack trace depth to be configured On my screen, when something crashes, I only have space for maybe 16 functions of the stack trace before the information above it scrolls off the screen. It's easy to hack the kernel to print out only that much, but it's harder to remember to do it. This introduces a config option for it so that I can keep the setting in my config. Signed-off-by: Johannes Berg Signed-off-by: Paul Mackerras --- arch/powerpc/Kconfig.debug | 9 +++++++++ arch/powerpc/kernel/process.c | 2 +- 2 files changed, 10 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug index 15eb27861fc..08f7cc0a195 100644 --- a/arch/powerpc/Kconfig.debug +++ b/arch/powerpc/Kconfig.debug @@ -2,6 +2,15 @@ menu "Kernel hacking" source "lib/Kconfig.debug" +config PRINT_STACK_DEPTH + int "Stack depth to print" if DEBUG_KERNEL + default 64 + help + This option allows you to set the stack depth that the kernel + prints in stack traces. This can be useful if your display is + too small and stack traces cause important information to + scroll off the screen. + config DEBUG_STACKOVERFLOW bool "Check for stack overflows" depends on DEBUG_KERNEL diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index b0383236dd0..51b201ddf9a 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1000,7 +1000,7 @@ unsigned long get_wchan(struct task_struct *p) return 0; } -static int kstack_depth_to_print = 64; +static int kstack_depth_to_print = CONFIG_PRINT_STACK_DEPTH; void show_stack(struct task_struct *tsk, unsigned long *stack) { -- cgit v1.2.3-70-g09d2 From 15e09c0ecaab4a1b4a7ed69db536c38948b92279 Mon Sep 17 00:00:00 2001 From: Becky Bruce Date: Thu, 20 Nov 2008 06:49:16 +0000 Subject: powerpc: Add sync_*_for_* to dma_ops We need to swap these out once we start using swiotlb, so add them to dma_ops. Create CONFIG_PPC_NEED_DMA_SYNC_OPS Kconfig option; this is currently enabled automatically if we're CONFIG_NOT_COHERENT_CACHE. In the future, this will also be enabled for builds that need swiotlb. If PPC_NEED_DMA_SYNC_OPS is not defined, the dma_sync_*_for_* ops compile to nothing. Otherwise, they access the dma_ops pointers for the sync ops. This patch also changes dma_sync_single_range_* to actually sync the range - previously it was using a generous dma_sync_single. dma_sync_single_* is now implemented as a dma_sync_single_range with an offset of 0. Signed-off-by: Becky Bruce Signed-off-by: Paul Mackerras --- arch/powerpc/Kconfig | 4 ++ arch/powerpc/include/asm/dma-mapping.h | 93 ++++++++++++++++++++++------------ arch/powerpc/kernel/dma.c | 26 ++++++++++ 3 files changed, 92 insertions(+), 31 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 525c13a4de9..be4f99b7cbb 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -285,6 +285,10 @@ config IOMMU_VMERGE config IOMMU_HELPER def_bool PPC64 +config PPC_NEED_DMA_SYNC_OPS + def_bool y + depends on NOT_COHERENT_CACHE + config HOTPLUG_CPU bool "Support for enabling/disabling CPUs" depends on SMP && HOTPLUG && EXPERIMENTAL && (PPC_PSERIES || PPC_PMAC) diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h index 3c4a2c21d60..9063184fa6f 100644 --- a/arch/powerpc/include/asm/dma-mapping.h +++ b/arch/powerpc/include/asm/dma-mapping.h @@ -76,6 +76,22 @@ struct dma_mapping_ops { dma_addr_t dma_address, size_t size, enum dma_data_direction direction, struct dma_attrs *attrs); +#ifdef CONFIG_PPC_NEED_DMA_SYNC_OPS + void (*sync_single_range_for_cpu)(struct device *hwdev, + dma_addr_t dma_handle, unsigned long offset, + size_t size, + enum dma_data_direction direction); + void (*sync_single_range_for_device)(struct device *hwdev, + dma_addr_t dma_handle, unsigned long offset, + size_t size, + enum dma_data_direction direction); + void (*sync_sg_for_cpu)(struct device *hwdev, + struct scatterlist *sg, int nelems, + enum dma_data_direction direction); + void (*sync_sg_for_device)(struct device *hwdev, + struct scatterlist *sg, int nelems, + enum dma_data_direction direction); +#endif }; /* @@ -282,47 +298,78 @@ static inline void dma_unmap_sg(struct device *dev, struct scatterlist *sg, dma_unmap_sg_attrs(dev, sg, nhwentries, direction, NULL); } +#ifdef CONFIG_PPC_NEED_DMA_SYNC_OPS static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size, enum dma_data_direction direction) { - BUG_ON(direction == DMA_NONE); - __dma_sync(bus_to_virt(dma_handle), size, direction); + struct dma_mapping_ops *dma_ops = get_dma_ops(dev); + + BUG_ON(!dma_ops); + dma_ops->sync_single_range_for_cpu(dev, dma_handle, 0, + size, direction); } static inline void dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle, size_t size, enum dma_data_direction direction) { - BUG_ON(direction == DMA_NONE); - __dma_sync(bus_to_virt(dma_handle), size, direction); + struct dma_mapping_ops *dma_ops = get_dma_ops(dev); + + BUG_ON(!dma_ops); + dma_ops->sync_single_range_for_device(dev, dma_handle, + 0, size, direction); } static inline void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction direction) { - struct scatterlist *sg; - int i; - - BUG_ON(direction == DMA_NONE); + struct dma_mapping_ops *dma_ops = get_dma_ops(dev); - for_each_sg(sgl, sg, nents, i) - __dma_sync_page(sg_page(sg), sg->offset, sg->length, direction); + BUG_ON(!dma_ops); + dma_ops->sync_sg_for_cpu(dev, sgl, nents, direction); } static inline void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction direction) { - struct scatterlist *sg; - int i; + struct dma_mapping_ops *dma_ops = get_dma_ops(dev); - BUG_ON(direction == DMA_NONE); + BUG_ON(!dma_ops); + dma_ops->sync_sg_for_device(dev, sgl, nents, direction); +} + +static inline void dma_sync_single_range_for_cpu(struct device *dev, + dma_addr_t dma_handle, unsigned long offset, size_t size, + enum dma_data_direction direction) +{ + struct dma_mapping_ops *dma_ops = get_dma_ops(dev); - for_each_sg(sgl, sg, nents, i) - __dma_sync_page(sg_page(sg), sg->offset, sg->length, direction); + BUG_ON(!dma_ops); + dma_ops->sync_single_range_for_cpu(dev, dma_handle, + offset, size, direction); +} + +static inline void dma_sync_single_range_for_device(struct device *dev, + dma_addr_t dma_handle, unsigned long offset, size_t size, + enum dma_data_direction direction) +{ + struct dma_mapping_ops *dma_ops = get_dma_ops(dev); + + BUG_ON(!dma_ops); + dma_ops->sync_single_range_for_device(dev, dma_handle, offset, + size, direction); } +#else /* CONFIG_PPC_NEED_DMA_SYNC_OPS */ +#define dma_sync_single_for_cpu(d, h, s, dir) ((void)0) +#define dma_sync_single_for_device(d, h, s, dir) ((void)0) +#define dma_sync_single_range_for_cpu(d, h, o, s, dir) ((void)0) +#define dma_sync_single_range_for_device(d, h, o, s, dir) ((void)0) +#define dma_sync_sg_for_cpu(d, s, n, dir) ((void)0) +#define dma_sync_sg_for_device(d, s, n, dir) ((void)0) +#endif static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { @@ -356,22 +403,6 @@ static inline int dma_get_cache_alignment(void) #endif } -static inline void dma_sync_single_range_for_cpu(struct device *dev, - dma_addr_t dma_handle, unsigned long offset, size_t size, - enum dma_data_direction direction) -{ - /* just sync everything for now */ - dma_sync_single_for_cpu(dev, dma_handle, offset + size, direction); -} - -static inline void dma_sync_single_range_for_device(struct device *dev, - dma_addr_t dma_handle, unsigned long offset, size_t size, - enum dma_data_direction direction) -{ - /* just sync everything for now */ - dma_sync_single_for_device(dev, dma_handle, offset + size, direction); -} - static inline void dma_cache_sync(struct device *dev, void *vaddr, size_t size, enum dma_data_direction direction) { diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c index 3a6eaa876ee..1c5c8a6fc12 100644 --- a/arch/powerpc/kernel/dma.c +++ b/arch/powerpc/kernel/dma.c @@ -120,6 +120,26 @@ static inline void dma_direct_unmap_page(struct device *dev, { } +#ifdef CONFIG_NOT_COHERENT_CACHE +static inline void dma_direct_sync_sg(struct device *dev, + struct scatterlist *sgl, int nents, + enum dma_data_direction direction) +{ + struct scatterlist *sg; + int i; + + for_each_sg(sgl, sg, nents, i) + __dma_sync_page(sg_page(sg), sg->offset, sg->length, direction); +} + +static inline void dma_direct_sync_single_range(struct device *dev, + dma_addr_t dma_handle, unsigned long offset, size_t size, + enum dma_data_direction direction) +{ + __dma_sync(bus_to_virt(dma_handle+offset), size, direction); +} +#endif + struct dma_mapping_ops dma_direct_ops = { .alloc_coherent = dma_direct_alloc_coherent, .free_coherent = dma_direct_free_coherent, @@ -128,5 +148,11 @@ struct dma_mapping_ops dma_direct_ops = { .dma_supported = dma_direct_dma_supported, .map_page = dma_direct_map_page, .unmap_page = dma_direct_unmap_page, +#ifdef CONFIG_NOT_COHERENT_CACHE + .sync_single_range_for_cpu = dma_direct_sync_single_range, + .sync_single_range_for_device = dma_direct_sync_single_range, + .sync_sg_for_cpu = dma_direct_sync_sg, + .sync_sg_for_device = dma_direct_sync_sg, +#endif }; EXPORT_SYMBOL(dma_direct_ops); -- cgit v1.2.3-70-g09d2 From 786b32f892dc341b607445bdef29d8e41a840925 Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Sun, 23 Nov 2008 00:48:56 +0000 Subject: powerpc: Eliminate NULL test and memset after alloc_bootmem As noted by Akinobu Mita in commit b1fceac2 ("x86: remove unnecessary memset and NULL check after alloc_bootmem()"), alloc_bootmem and related functions never return NULL and always return a zeroed region of memory. Thus a NULL test or memset after calls to these functions is unnecessary. This was fixed using the following semantic patch. (http://www.emn.fr/x-info/coccinelle/) // @@ expression E; statement S; @@ E = \(alloc_bootmem\|alloc_bootmem_low\|alloc_bootmem_pages\|alloc_bootmem_low_pages\|alloc_bootmem_node\|alloc_bootmem_low_pages_node\|alloc_bootmem_pages_node\)(...) ... when != E ( - BUG_ON (E == NULL); | - if (E == NULL) S ) @@ expression E,E1; @@ E = \(alloc_bootmem\|alloc_bootmem_low\|alloc_bootmem_pages\|alloc_bootmem_low_pages\|alloc_bootmem_node\|alloc_bootmem_low_pages_node\|alloc_bootmem_pages_node\)(...) ... when != E - memset(E,0,E1); // Signed-off-by: Julia Lawall Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/setup_64.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 169d74cef15..93c875ae985 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -606,8 +606,6 @@ void __init setup_per_cpu_areas(void) for_each_possible_cpu(i) { ptr = alloc_bootmem_pages_node(NODE_DATA(cpu_to_node(i)), size); - if (!ptr) - panic("Cannot allocate cpu data for CPU %d\n", i); paca[i].data_offset = ptr - __per_cpu_start; memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start); -- cgit v1.2.3-70-g09d2 From 6358d6cb328a772eb6f02c870da61709d539480f Mon Sep 17 00:00:00 2001 From: Sebastien Dugue Date: Thu, 27 Nov 2008 01:19:18 +0000 Subject: powerpc/ibmebus: Get rid of the IRQ mapping in ibmebus_free_irq() ibmebus_free_irq() frees the IRQ but does not remove its mapping, which results in stale entries in the map. This fixes it by adding a call to irq_dispose_mapping() in ibmebus_free_irq(). Signed-off-by: Sebastien Dugue Cc: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/ibmebus.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c index 64299d28f36..7c6537777b2 100644 --- a/arch/powerpc/kernel/ibmebus.c +++ b/arch/powerpc/kernel/ibmebus.c @@ -231,6 +231,7 @@ void ibmebus_free_irq(u32 ist, void *dev_id) unsigned int irq = irq_find_mapping(NULL, ist); free_irq(irq, dev_id); + irq_dispose_mapping(irq); } EXPORT_SYMBOL(ibmebus_free_irq); -- cgit v1.2.3-70-g09d2 From 6a800f36acd5bf06b5fe2cb27c4d0524d60c3df5 Mon Sep 17 00:00:00 2001 From: Liu Yu Date: Tue, 28 Oct 2008 11:50:21 +0800 Subject: powerpc: Add SPE/EFP math emulation for E500v1/v2 processors. This patch add the handlers of SPE/EFP exceptions. The code is used to emulate float point arithmetic, when MSR(SPE) is enabled and receive EFP data interrupt or EFP round interrupt. This patch has no conflict with or dependence on FP math-emu. The code has been tested by TestFloat. Now the code doesn't support SPE/EFP instructions emulation (it won't be called when receive program interrupt), but it could be easily added. Signed-off-by: Liu Yu Signed-off-by: Kumar Gala --- arch/powerpc/include/asm/processor.h | 6 + arch/powerpc/include/asm/sfp-machine.h | 36 +- arch/powerpc/kernel/head_fsl_booke.S | 7 +- arch/powerpc/kernel/traps.c | 62 ++- arch/powerpc/math-emu/Makefile | 2 + arch/powerpc/math-emu/math_efp.c | 720 +++++++++++++++++++++++++++++++++ 6 files changed, 813 insertions(+), 20 deletions(-) create mode 100644 arch/powerpc/math-emu/math_efp.c (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 101ed87f7d8..cd7a47860e5 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -207,6 +207,11 @@ struct thread_struct { #define INIT_SP_LIMIT \ (_ALIGN_UP(sizeof(init_thread_info), 16) + (unsigned long) &init_stack) +#ifdef CONFIG_SPE +#define SPEFSCR_INIT .spefscr = SPEFSCR_FINVE | SPEFSCR_FDBZE | SPEFSCR_FUNFE | SPEFSCR_FOVFE, +#else +#define SPEFSCR_INIT +#endif #ifdef CONFIG_PPC32 #define INIT_THREAD { \ @@ -215,6 +220,7 @@ struct thread_struct { .fs = KERNEL_DS, \ .pgdir = swapper_pg_dir, \ .fpexc_mode = MSR_FE0 | MSR_FE1, \ + SPEFSCR_INIT \ } #else #define INIT_THREAD { \ diff --git a/arch/powerpc/include/asm/sfp-machine.h b/arch/powerpc/include/asm/sfp-machine.h index 88af036b1fe..3d9f831c3c5 100644 --- a/arch/powerpc/include/asm/sfp-machine.h +++ b/arch/powerpc/include/asm/sfp-machine.h @@ -97,6 +97,20 @@ #define _FP_KEEPNANFRACP 1 +#ifdef FP_EX_BOOKE_E500_SPE +#define FP_EX_INEXACT (1 << 21) +#define FP_EX_INVALID (1 << 20) +#define FP_EX_DIVZERO (1 << 19) +#define FP_EX_UNDERFLOW (1 << 18) +#define FP_EX_OVERFLOW (1 << 17) +#define FP_INHIBIT_RESULTS 0 + +#define __FPU_FPSCR (current->thread.spefscr) +#define __FPU_ENABLED_EXC \ +({ \ + (__FPU_FPSCR >> 2) & 0x1f; \ +}) +#else /* Exception flags. We use the bit positions of the appropriate bits in the FPSCR, which also correspond to the FE_* bits. This makes everything easier ;-). */ @@ -111,6 +125,18 @@ #define FP_EX_DIVZERO (1 << (31 - 5)) #define FP_EX_INEXACT (1 << (31 - 6)) +#define __FPU_FPSCR (current->thread.fpscr.val) + +/* We only actually write to the destination register + * if exceptions signalled (if any) will not trap. + */ +#define __FPU_ENABLED_EXC \ +({ \ + (__FPU_FPSCR >> 3) & 0x1f; \ +}) + +#endif + /* * If one NaN is signaling and the other is not, * we choose that one, otherwise we choose X. @@ -135,16 +161,6 @@ #include #include -#define __FPU_FPSCR (current->thread.fpscr.val) - -/* We only actually write to the destination register - * if exceptions signalled (if any) will not trap. - */ -#define __FPU_ENABLED_EXC \ -({ \ - (__FPU_FPSCR >> 3) & 0x1f; \ -}) - #define __FPU_TRAP_P(bits) \ ((__FPU_ENABLED_EXC & (bits)) != 0) diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S index 590304c24da..837e3cc9cc8 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -685,12 +685,13 @@ interrupt_base: /* SPE Floating Point Data */ #ifdef CONFIG_SPE EXCEPTION(0x2030, SPEFloatingPointData, SPEFloatingPointException, EXC_XFER_EE); -#else - EXCEPTION(0x2040, SPEFloatingPointData, unknown_exception, EXC_XFER_EE) -#endif /* CONFIG_SPE */ /* SPE Floating Point Round */ + EXCEPTION(0x2050, SPEFloatingPointRound, SPEFloatingPointRoundException, EXC_XFER_EE) +#else + EXCEPTION(0x2040, SPEFloatingPointData, unknown_exception, EXC_XFER_EE) EXCEPTION(0x2050, SPEFloatingPointRound, unknown_exception, EXC_XFER_EE) +#endif /* CONFIG_SPE */ /* Performance Monitor */ EXCEPTION(0x2060, PerformanceMonitor, performance_monitor_exception, EXC_XFER_STD) diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index f5def6cf5cd..5457e957568 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -1160,37 +1160,85 @@ void CacheLockingException(struct pt_regs *regs, unsigned long address, #ifdef CONFIG_SPE void SPEFloatingPointException(struct pt_regs *regs) { + extern int do_spe_mathemu(struct pt_regs *regs); unsigned long spefscr; int fpexc_mode; int code = 0; + int err; + + preempt_disable(); + if (regs->msr & MSR_SPE) + giveup_spe(current); + preempt_enable(); spefscr = current->thread.spefscr; fpexc_mode = current->thread.fpexc_mode; - /* Hardware does not neccessarily set sticky - * underflow/overflow/invalid flags */ if ((spefscr & SPEFSCR_FOVF) && (fpexc_mode & PR_FP_EXC_OVF)) { code = FPE_FLTOVF; - spefscr |= SPEFSCR_FOVFS; } else if ((spefscr & SPEFSCR_FUNF) && (fpexc_mode & PR_FP_EXC_UND)) { code = FPE_FLTUND; - spefscr |= SPEFSCR_FUNFS; } else if ((spefscr & SPEFSCR_FDBZ) && (fpexc_mode & PR_FP_EXC_DIV)) code = FPE_FLTDIV; else if ((spefscr & SPEFSCR_FINV) && (fpexc_mode & PR_FP_EXC_INV)) { code = FPE_FLTINV; - spefscr |= SPEFSCR_FINVS; } else if ((spefscr & (SPEFSCR_FG | SPEFSCR_FX)) && (fpexc_mode & PR_FP_EXC_RES)) code = FPE_FLTRES; - current->thread.spefscr = spefscr; + err = do_spe_mathemu(regs); + if (err == 0) { + regs->nip += 4; /* skip emulated instruction */ + emulate_single_step(regs); + return; + } + + if (err == -EFAULT) { + /* got an error reading the instruction */ + _exception(SIGSEGV, regs, SEGV_ACCERR, regs->nip); + } else if (err == -EINVAL) { + /* didn't recognize the instruction */ + printk(KERN_ERR "unrecognized spe instruction " + "in %s at %lx\n", current->comm, regs->nip); + } else { + _exception(SIGFPE, regs, code, regs->nip); + } - _exception(SIGFPE, regs, code, regs->nip); return; } + +void SPEFloatingPointRoundException(struct pt_regs *regs) +{ + extern int speround_handler(struct pt_regs *regs); + int err; + + preempt_disable(); + if (regs->msr & MSR_SPE) + giveup_spe(current); + preempt_enable(); + + regs->nip -= 4; + err = speround_handler(regs); + if (err == 0) { + regs->nip += 4; /* skip emulated instruction */ + emulate_single_step(regs); + return; + } + + if (err == -EFAULT) { + /* got an error reading the instruction */ + _exception(SIGSEGV, regs, SEGV_ACCERR, regs->nip); + } else if (err == -EINVAL) { + /* didn't recognize the instruction */ + printk(KERN_ERR "unrecognized spe instruction " + "in %s at %lx\n", current->comm, regs->nip); + } else { + _exception(SIGFPE, regs, 0, regs->nip); + return; + } +} #endif /* diff --git a/arch/powerpc/math-emu/Makefile b/arch/powerpc/math-emu/Makefile index 03aa98dd9f0..f9e506a735a 100644 --- a/arch/powerpc/math-emu/Makefile +++ b/arch/powerpc/math-emu/Makefile @@ -11,6 +11,8 @@ obj-$(CONFIG_MATH_EMULATION) += fabs.o fadd.o fadds.o fcmpo.o fcmpu.o \ mcrfs.o mffs.o mtfsb0.o mtfsb1.o \ mtfsf.o mtfsfi.o stfiwx.o stfs.o +obj-$(CONFIG_SPE) += math_efp.o + CFLAGS_fabs.o = -fno-builtin-fabs CFLAGS_math.o = -fno-builtin-fabs diff --git a/arch/powerpc/math-emu/math_efp.c b/arch/powerpc/math-emu/math_efp.c new file mode 100644 index 00000000000..41f4ef30e48 --- /dev/null +++ b/arch/powerpc/math-emu/math_efp.c @@ -0,0 +1,720 @@ +/* + * arch/powerpc/math-emu/math_efp.c + * + * Copyright (C) 2006-2008 Freescale Semiconductor, Inc. All rights reserved. + * + * Author: Ebony Zhu, + * Yu Liu, + * + * Derived from arch/alpha/math-emu/math.c + * arch/powerpc/math-emu/math.c + * + * Description: + * This file is the exception handler to make E500 SPE instructions + * fully comply with IEEE-754 floating point standard. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include + +#include +#include + +#define FP_EX_BOOKE_E500_SPE +#include + +#include +#include +#include + +#define EFAPU 0x4 + +#define VCT 0x4 +#define SPFP 0x6 +#define DPFP 0x7 + +#define EFSADD 0x2c0 +#define EFSSUB 0x2c1 +#define EFSABS 0x2c4 +#define EFSNABS 0x2c5 +#define EFSNEG 0x2c6 +#define EFSMUL 0x2c8 +#define EFSDIV 0x2c9 +#define EFSCMPGT 0x2cc +#define EFSCMPLT 0x2cd +#define EFSCMPEQ 0x2ce +#define EFSCFD 0x2cf +#define EFSCFSI 0x2d1 +#define EFSCTUI 0x2d4 +#define EFSCTSI 0x2d5 +#define EFSCTUF 0x2d6 +#define EFSCTSF 0x2d7 +#define EFSCTUIZ 0x2d8 +#define EFSCTSIZ 0x2da + +#define EVFSADD 0x280 +#define EVFSSUB 0x281 +#define EVFSABS 0x284 +#define EVFSNABS 0x285 +#define EVFSNEG 0x286 +#define EVFSMUL 0x288 +#define EVFSDIV 0x289 +#define EVFSCMPGT 0x28c +#define EVFSCMPLT 0x28d +#define EVFSCMPEQ 0x28e +#define EVFSCTUI 0x294 +#define EVFSCTSI 0x295 +#define EVFSCTUF 0x296 +#define EVFSCTSF 0x297 +#define EVFSCTUIZ 0x298 +#define EVFSCTSIZ 0x29a + +#define EFDADD 0x2e0 +#define EFDSUB 0x2e1 +#define EFDABS 0x2e4 +#define EFDNABS 0x2e5 +#define EFDNEG 0x2e6 +#define EFDMUL 0x2e8 +#define EFDDIV 0x2e9 +#define EFDCTUIDZ 0x2ea +#define EFDCTSIDZ 0x2eb +#define EFDCMPGT 0x2ec +#define EFDCMPLT 0x2ed +#define EFDCMPEQ 0x2ee +#define EFDCFS 0x2ef +#define EFDCTUI 0x2f4 +#define EFDCTSI 0x2f5 +#define EFDCTUF 0x2f6 +#define EFDCTSF 0x2f7 +#define EFDCTUIZ 0x2f8 +#define EFDCTSIZ 0x2fa + +#define AB 2 +#define XA 3 +#define XB 4 +#define XCR 5 +#define NOTYPE 0 + +#define SIGN_BIT_S (1UL << 31) +#define SIGN_BIT_D (1ULL << 63) +#define FP_EX_MASK (FP_EX_INEXACT | FP_EX_INVALID | FP_EX_DIVZERO | \ + FP_EX_UNDERFLOW | FP_EX_OVERFLOW) + +union dw_union { + u64 dp[1]; + u32 wp[2]; +}; + +static unsigned long insn_type(unsigned long speinsn) +{ + unsigned long ret = NOTYPE; + + switch (speinsn & 0x7ff) { + case EFSABS: ret = XA; break; + case EFSADD: ret = AB; break; + case EFSCFD: ret = XB; break; + case EFSCMPEQ: ret = XCR; break; + case EFSCMPGT: ret = XCR; break; + case EFSCMPLT: ret = XCR; break; + case EFSCTSF: ret = XB; break; + case EFSCTSI: ret = XB; break; + case EFSCTSIZ: ret = XB; break; + case EFSCTUF: ret = XB; break; + case EFSCTUI: ret = XB; break; + case EFSCTUIZ: ret = XB; break; + case EFSDIV: ret = AB; break; + case EFSMUL: ret = AB; break; + case EFSNABS: ret = XA; break; + case EFSNEG: ret = XA; break; + case EFSSUB: ret = AB; break; + case EFSCFSI: ret = XB; break; + + case EVFSABS: ret = XA; break; + case EVFSADD: ret = AB; break; + case EVFSCMPEQ: ret = XCR; break; + case EVFSCMPGT: ret = XCR; break; + case EVFSCMPLT: ret = XCR; break; + case EVFSCTSF: ret = XB; break; + case EVFSCTSI: ret = XB; break; + case EVFSCTSIZ: ret = XB; break; + case EVFSCTUF: ret = XB; break; + case EVFSCTUI: ret = XB; break; + case EVFSCTUIZ: ret = XB; break; + case EVFSDIV: ret = AB; break; + case EVFSMUL: ret = AB; break; + case EVFSNABS: ret = XA; break; + case EVFSNEG: ret = XA; break; + case EVFSSUB: ret = AB; break; + + case EFDABS: ret = XA; break; + case EFDADD: ret = AB; break; + case EFDCFS: ret = XB; break; + case EFDCMPEQ: ret = XCR; break; + case EFDCMPGT: ret = XCR; break; + case EFDCMPLT: ret = XCR; break; + case EFDCTSF: ret = XB; break; + case EFDCTSI: ret = XB; break; + case EFDCTSIDZ: ret = XB; break; + case EFDCTSIZ: ret = XB; break; + case EFDCTUF: ret = XB; break; + case EFDCTUI: ret = XB; break; + case EFDCTUIDZ: ret = XB; break; + case EFDCTUIZ: ret = XB; break; + case EFDDIV: ret = AB; break; + case EFDMUL: ret = AB; break; + case EFDNABS: ret = XA; break; + case EFDNEG: ret = XA; break; + case EFDSUB: ret = AB; break; + + default: + printk(KERN_ERR "\nOoops! SPE instruction no type found."); + printk(KERN_ERR "\ninst code: %08lx\n", speinsn); + } + + return ret; +} + +int do_spe_mathemu(struct pt_regs *regs) +{ + FP_DECL_EX; + int IR, cmp; + + unsigned long type, func, fc, fa, fb, src, speinsn; + union dw_union vc, va, vb; + + if (get_user(speinsn, (unsigned int __user *) regs->nip)) + return -EFAULT; + if ((speinsn >> 26) != EFAPU) + return -EINVAL; /* not an spe instruction */ + + type = insn_type(speinsn); + if (type == NOTYPE) + return -ENOSYS; + + func = speinsn & 0x7ff; + fc = (speinsn >> 21) & 0x1f; + fa = (speinsn >> 16) & 0x1f; + fb = (speinsn >> 11) & 0x1f; + src = (speinsn >> 5) & 0x7; + + vc.wp[0] = current->thread.evr[fc]; + vc.wp[1] = regs->gpr[fc]; + va.wp[0] = current->thread.evr[fa]; + va.wp[1] = regs->gpr[fa]; + vb.wp[0] = current->thread.evr[fb]; + vb.wp[1] = regs->gpr[fb]; + + __FPU_FPSCR = mfspr(SPRN_SPEFSCR); + +#ifdef DEBUG + printk("speinsn:%08lx spefscr:%08lx\n", speinsn, __FPU_FPSCR); + printk("vc: %08x %08x\n", vc.wp[0], vc.wp[1]); + printk("va: %08x %08x\n", va.wp[0], va.wp[1]); + printk("vb: %08x %08x\n", vb.wp[0], vb.wp[1]); +#endif + + switch (src) { + case SPFP: { + FP_DECL_S(SA); FP_DECL_S(SB); FP_DECL_S(SR); + + switch (type) { + case AB: + case XCR: + FP_UNPACK_SP(SA, va.wp + 1); + case XB: + FP_UNPACK_SP(SB, vb.wp + 1); + break; + case XA: + FP_UNPACK_SP(SA, va.wp + 1); + break; + } + +#ifdef DEBUG + printk("SA: %ld %08lx %ld (%ld)\n", SA_s, SA_f, SA_e, SA_c); + printk("SB: %ld %08lx %ld (%ld)\n", SB_s, SB_f, SB_e, SB_c); +#endif + + switch (func) { + case EFSABS: + vc.wp[1] = va.wp[1] & ~SIGN_BIT_S; + goto update_regs; + + case EFSNABS: + vc.wp[1] = va.wp[1] | SIGN_BIT_S; + goto update_regs; + + case EFSNEG: + vc.wp[1] = va.wp[1] ^ SIGN_BIT_S; + goto update_regs; + + case EFSADD: + FP_ADD_S(SR, SA, SB); + goto pack_s; + + case EFSSUB: + FP_SUB_S(SR, SA, SB); + goto pack_s; + + case EFSMUL: + FP_MUL_S(SR, SA, SB); + goto pack_s; + + case EFSDIV: + FP_DIV_S(SR, SA, SB); + goto pack_s; + + case EFSCMPEQ: + cmp = 0; + goto cmp_s; + + case EFSCMPGT: + cmp = 1; + goto cmp_s; + + case EFSCMPLT: + cmp = -1; + goto cmp_s; + + case EFSCTSF: + case EFSCTUF: + if (!((vb.wp[1] >> 23) == 0xff && ((vb.wp[1] & 0x7fffff) > 0))) { + /* NaN */ + if (((vb.wp[1] >> 23) & 0xff) == 0) { + /* denorm */ + vc.wp[1] = 0x0; + } else if ((vb.wp[1] >> 31) == 0) { + /* positive normal */ + vc.wp[1] = (func == EFSCTSF) ? + 0x7fffffff : 0xffffffff; + } else { /* negative normal */ + vc.wp[1] = (func == EFSCTSF) ? + 0x80000000 : 0x0; + } + } else { /* rB is NaN */ + vc.wp[1] = 0x0; + } + goto update_regs; + + case EFSCFD: { + FP_DECL_D(DB); + FP_CLEAR_EXCEPTIONS; + FP_UNPACK_DP(DB, vb.dp); +#ifdef DEBUG + printk("DB: %ld %08lx %08lx %ld (%ld)\n", + DB_s, DB_f1, DB_f0, DB_e, DB_c); +#endif + FP_CONV(S, D, 1, 2, SR, DB); + goto pack_s; + } + + case EFSCTSI: + case EFSCTSIZ: + case EFSCTUI: + case EFSCTUIZ: + if (func & 0x4) { + _FP_ROUND(1, SB); + } else { + _FP_ROUND_ZERO(1, SB); + } + FP_TO_INT_S(vc.wp[1], SB, 32, ((func & 0x3) != 0)); + goto update_regs; + + default: + goto illegal; + } + break; + +pack_s: +#ifdef DEBUG + printk("SR: %ld %08lx %ld (%ld)\n", SR_s, SR_f, SR_e, SR_c); +#endif + FP_PACK_SP(vc.wp + 1, SR); + goto update_regs; + +cmp_s: + FP_CMP_S(IR, SA, SB, 3); + if (IR == 3 && (FP_ISSIGNAN_S(SA) || FP_ISSIGNAN_S(SB))) + FP_SET_EXCEPTION(FP_EX_INVALID); + if (IR == cmp) { + IR = 0x4; + } else { + IR = 0; + } + goto update_ccr; + } + + case DPFP: { + FP_DECL_D(DA); FP_DECL_D(DB); FP_DECL_D(DR); + + switch (type) { + case AB: + case XCR: + FP_UNPACK_DP(DA, va.dp); + case XB: + FP_UNPACK_DP(DB, vb.dp); + break; + case XA: + FP_UNPACK_DP(DA, va.dp); + break; + } + +#ifdef DEBUG + printk("DA: %ld %08lx %08lx %ld (%ld)\n", + DA_s, DA_f1, DA_f0, DA_e, DA_c); + printk("DB: %ld %08lx %08lx %ld (%ld)\n", + DB_s, DB_f1, DB_f0, DB_e, DB_c); +#endif + + switch (func) { + case EFDABS: + vc.dp[0] = va.dp[0] & ~SIGN_BIT_D; + goto update_regs; + + case EFDNABS: + vc.dp[0] = va.dp[0] | SIGN_BIT_D; + goto update_regs; + + case EFDNEG: + vc.dp[0] = va.dp[0] ^ SIGN_BIT_D; + goto update_regs; + + case EFDADD: + FP_ADD_D(DR, DA, DB); + goto pack_d; + + case EFDSUB: + FP_SUB_D(DR, DA, DB); + goto pack_d; + + case EFDMUL: + FP_MUL_D(DR, DA, DB); + goto pack_d; + + case EFDDIV: + FP_DIV_D(DR, DA, DB); + goto pack_d; + + case EFDCMPEQ: + cmp = 0; + goto cmp_d; + + case EFDCMPGT: + cmp = 1; + goto cmp_d; + + case EFDCMPLT: + cmp = -1; + goto cmp_d; + + case EFDCTSF: + case EFDCTUF: + if (!((vb.wp[0] >> 20) == 0x7ff && + ((vb.wp[0] & 0xfffff) > 0 || (vb.wp[1] > 0)))) { + /* not a NaN */ + if (((vb.wp[0] >> 20) & 0x7ff) == 0) { + /* denorm */ + vc.wp[1] = 0x0; + } else if ((vb.wp[0] >> 31) == 0) { + /* positive normal */ + vc.wp[1] = (func == EFDCTSF) ? + 0x7fffffff : 0xffffffff; + } else { /* negative normal */ + vc.wp[1] = (func == EFDCTSF) ? + 0x80000000 : 0x0; + } + } else { /* NaN */ + vc.wp[1] = 0x0; + } + goto update_regs; + + case EFDCFS: { + FP_DECL_S(SB); + FP_CLEAR_EXCEPTIONS; + FP_UNPACK_SP(SB, vb.wp + 1); +#ifdef DEBUG + printk("SB: %ld %08lx %ld (%ld)\n", + SB_s, SB_f, SB_e, SB_c); +#endif + FP_CONV(D, S, 2, 1, DR, SB); + goto pack_d; + } + + case EFDCTUIDZ: + case EFDCTSIDZ: + _FP_ROUND_ZERO(2, DB); + FP_TO_INT_D(vc.dp[0], DB, 64, ((func & 0x1) == 0)); + goto update_regs; + + case EFDCTUI: + case EFDCTSI: + case EFDCTUIZ: + case EFDCTSIZ: + if (func & 0x4) { + _FP_ROUND(2, DB); + } else { + _FP_ROUND_ZERO(2, DB); + } + FP_TO_INT_D(vc.wp[1], DB, 32, ((func & 0x3) != 0)); + goto update_regs; + + default: + goto illegal; + } + break; + +pack_d: +#ifdef DEBUG + printk("DR: %ld %08lx %08lx %ld (%ld)\n", + DR_s, DR_f1, DR_f0, DR_e, DR_c); +#endif + FP_PACK_DP(vc.dp, DR); + goto update_regs; + +cmp_d: + FP_CMP_D(IR, DA, DB, 3); + if (IR == 3 && (FP_ISSIGNAN_D(DA) || FP_ISSIGNAN_D(DB))) + FP_SET_EXCEPTION(FP_EX_INVALID); + if (IR == cmp) { + IR = 0x4; + } else { + IR = 0; + } + goto update_ccr; + + } + + case VCT: { + FP_DECL_S(SA0); FP_DECL_S(SB0); FP_DECL_S(SR0); + FP_DECL_S(SA1); FP_DECL_S(SB1); FP_DECL_S(SR1); + int IR0, IR1; + + switch (type) { + case AB: + case XCR: + FP_UNPACK_SP(SA0, va.wp); + FP_UNPACK_SP(SA1, va.wp + 1); + case XB: + FP_UNPACK_SP(SB0, vb.wp); + FP_UNPACK_SP(SB1, vb.wp + 1); + break; + case XA: + FP_UNPACK_SP(SA0, va.wp); + FP_UNPACK_SP(SA1, va.wp + 1); + break; + } + +#ifdef DEBUG + printk("SA0: %ld %08lx %ld (%ld)\n", SA0_s, SA0_f, SA0_e, SA0_c); + printk("SA1: %ld %08lx %ld (%ld)\n", SA1_s, SA1_f, SA1_e, SA1_c); + printk("SB0: %ld %08lx %ld (%ld)\n", SB0_s, SB0_f, SB0_e, SB0_c); + printk("SB1: %ld %08lx %ld (%ld)\n", SB1_s, SB1_f, SB1_e, SB1_c); +#endif + + switch (func) { + case EVFSABS: + vc.wp[0] = va.wp[0] & ~SIGN_BIT_S; + vc.wp[1] = va.wp[1] & ~SIGN_BIT_S; + goto update_regs; + + case EVFSNABS: + vc.wp[0] = va.wp[0] | SIGN_BIT_S; + vc.wp[1] = va.wp[1] | SIGN_BIT_S; + goto update_regs; + + case EVFSNEG: + vc.wp[0] = va.wp[0] ^ SIGN_BIT_S; + vc.wp[1] = va.wp[1] ^ SIGN_BIT_S; + goto update_regs; + + case EVFSADD: + FP_ADD_S(SR0, SA0, SB0); + FP_ADD_S(SR1, SA1, SB1); + goto pack_vs; + + case EVFSSUB: + FP_SUB_S(SR0, SA0, SB0); + FP_SUB_S(SR1, SA1, SB1); + goto pack_vs; + + case EVFSMUL: + FP_MUL_S(SR0, SA0, SB0); + FP_MUL_S(SR1, SA1, SB1); + goto pack_vs; + + case EVFSDIV: + FP_DIV_S(SR0, SA0, SB0); + FP_DIV_S(SR1, SA1, SB1); + goto pack_vs; + + case EVFSCMPEQ: + cmp = 0; + goto cmp_vs; + + case EVFSCMPGT: + cmp = 1; + goto cmp_vs; + + case EVFSCMPLT: + cmp = -1; + goto cmp_vs; + + case EVFSCTSF: + __asm__ __volatile__ ("mtspr 512, %4\n" + "efsctsf %0, %2\n" + "efsctsf %1, %3\n" + : "=r" (vc.wp[0]), "=r" (vc.wp[1]) + : "r" (vb.wp[0]), "r" (vb.wp[1]), "r" (0)); + goto update_regs; + + case EVFSCTUF: + __asm__ __volatile__ ("mtspr 512, %4\n" + "efsctuf %0, %2\n" + "efsctuf %1, %3\n" + : "=r" (vc.wp[0]), "=r" (vc.wp[1]) + : "r" (vb.wp[0]), "r" (vb.wp[1]), "r" (0)); + goto update_regs; + + case EVFSCTUI: + case EVFSCTSI: + case EVFSCTUIZ: + case EVFSCTSIZ: + if (func & 0x4) { + _FP_ROUND(1, SB0); + _FP_ROUND(1, SB1); + } else { + _FP_ROUND_ZERO(1, SB0); + _FP_ROUND_ZERO(1, SB1); + } + FP_TO_INT_S(vc.wp[0], SB0, 32, ((func & 0x3) != 0)); + FP_TO_INT_S(vc.wp[1], SB1, 32, ((func & 0x3) != 0)); + goto update_regs; + + default: + goto illegal; + } + break; + +pack_vs: +#ifdef DEBUG + printk("SR0: %ld %08lx %ld (%ld)\n", SR0_s, SR0_f, SR0_e, SR0_c); + printk("SR1: %ld %08lx %ld (%ld)\n", SR1_s, SR1_f, SR1_e, SR1_c); +#endif + FP_PACK_SP(vc.wp, SR0); + FP_PACK_SP(vc.wp + 1, SR1); + goto update_regs; + +cmp_vs: + { + int ch, cl; + + FP_CMP_S(IR0, SA0, SB0, 3); + FP_CMP_S(IR1, SA1, SB1, 3); + if (IR0 == 3 && (FP_ISSIGNAN_S(SA0) || FP_ISSIGNAN_S(SB0))) + FP_SET_EXCEPTION(FP_EX_INVALID); + if (IR1 == 3 && (FP_ISSIGNAN_S(SA1) || FP_ISSIGNAN_S(SB1))) + FP_SET_EXCEPTION(FP_EX_INVALID); + ch = (IR0 == cmp) ? 1 : 0; + cl = (IR1 == cmp) ? 1 : 0; + IR = (ch << 3) | (cl << 2) | ((ch | cl) << 1) | + ((ch & cl) << 0); + goto update_ccr; + } + } + default: + return -EINVAL; + } + +update_ccr: + regs->ccr &= ~(15 << ((7 - ((speinsn >> 23) & 0x7)) << 2)); + regs->ccr |= (IR << ((7 - ((speinsn >> 23) & 0x7)) << 2)); + +update_regs: + __FPU_FPSCR &= ~FP_EX_MASK; + __FPU_FPSCR |= (FP_CUR_EXCEPTIONS & FP_EX_MASK); + mtspr(SPRN_SPEFSCR, __FPU_FPSCR); + + current->thread.evr[fc] = vc.wp[0]; + regs->gpr[fc] = vc.wp[1]; + +#ifdef DEBUG + printk("ccr = %08lx\n", regs->ccr); + printk("cur exceptions = %08x spefscr = %08lx\n", + FP_CUR_EXCEPTIONS, __FPU_FPSCR); + printk("vc: %08x %08x\n", vc.wp[0], vc.wp[1]); + printk("va: %08x %08x\n", va.wp[0], va.wp[1]); + printk("vb: %08x %08x\n", vb.wp[0], vb.wp[1]); +#endif + + return 0; + +illegal: + printk(KERN_ERR "\nOoops! IEEE-754 compliance handler encountered un-supported instruction.\ninst code: %08lx\n", speinsn); + return -ENOSYS; +} + +int speround_handler(struct pt_regs *regs) +{ + union dw_union fgpr; + int s_lo, s_hi; + unsigned long speinsn, type, fc; + + if (get_user(speinsn, (unsigned int __user *) regs->nip)) + return -EFAULT; + if ((speinsn >> 26) != 4) + return -EINVAL; /* not an spe instruction */ + + type = insn_type(speinsn & 0x7ff); + if (type == XCR) return -ENOSYS; + + fc = (speinsn >> 21) & 0x1f; + s_lo = regs->gpr[fc] & SIGN_BIT_S; + s_hi = current->thread.evr[fc] & SIGN_BIT_S; + fgpr.wp[0] = current->thread.evr[fc]; + fgpr.wp[1] = regs->gpr[fc]; + + __FPU_FPSCR = mfspr(SPRN_SPEFSCR); + + switch ((speinsn >> 5) & 0x7) { + /* Since SPE instructions on E500 core can handle round to nearest + * and round toward zero with IEEE-754 complied, we just need + * to handle round toward +Inf and round toward -Inf by software. + */ + case SPFP: + if ((FP_ROUNDMODE) == FP_RND_PINF) { + if (!s_lo) fgpr.wp[1]++; /* Z > 0, choose Z1 */ + } else { /* round to -Inf */ + if (s_lo) fgpr.wp[1]++; /* Z < 0, choose Z2 */ + } + break; + + case DPFP: + if (FP_ROUNDMODE == FP_RND_PINF) { + if (!s_hi) fgpr.dp[0]++; /* Z > 0, choose Z1 */ + } else { /* round to -Inf */ + if (s_hi) fgpr.dp[0]++; /* Z < 0, choose Z2 */ + } + break; + + case VCT: + if (FP_ROUNDMODE == FP_RND_PINF) { + if (!s_lo) fgpr.wp[1]++; /* Z_low > 0, choose Z1 */ + if (!s_hi) fgpr.wp[0]++; /* Z_high word > 0, choose Z1 */ + } else { /* round to -Inf */ + if (s_lo) fgpr.wp[1]++; /* Z_low < 0, choose Z2 */ + if (s_hi) fgpr.wp[0]++; /* Z_high < 0, choose Z2 */ + } + break; + + default: + return -EINVAL; + } + + current->thread.evr[fc] = fgpr.wp[0]; + regs->gpr[fc] = fgpr.wp[1]; + + return 0; +} -- cgit v1.2.3-70-g09d2 From b3898895355f73973eb3aef3489e999d3fb8e2bc Mon Sep 17 00:00:00 2001 From: Trent Piepho Date: Wed, 19 Nov 2008 03:13:14 -0800 Subject: powerpc: Better setup of boot page TLB entry The initial TLB mapping for the kernel boot didn't set the memory coherent attribute, MAS2[M], in SMP mode. If this code supported booting a secondary processor, which it doesn't yet, but if it did, then when a secondary processor boots, it would probably signal the primary processor by setting a variable called something like __secondary_hold_acknowledge. However, due to the lack of the M bit, the primary processor would not snoop the transaction (even if a transaction were broadcast). If primary CPU's L1 D-cache had a copy, it would not be flushed and the CPU would never see the ack. Which would have resulted in the primary CPU spinning for a long time, perhaps a full second before it gives up, while it would have waited for the ack from the secondary CPU that it wouldn't have been able to see because of the stale cache. The value of MAS2 for the boot page TLB1 entry is a compile time constant, so there is no need to calculate it in powerpc assembly language. Also, from the MPC8572 manual section 6.12.5.3, "Bits that represent offsets within a page are ignored and should be cleared." Existing code didn't clear them, this code does. The same when the page of KERNELBASE is found; we don't need to use asm to mask the lower 12 bits off. In the code that computes the address to rfi from, don't hard code the offset to 24 bytes, but have the assembler figure that out for us. Signed-off-by: Trent Piepho Signed-off-by: Kumar Gala --- arch/powerpc/include/asm/mmu-fsl-booke.h | 2 ++ arch/powerpc/kernel/head_fsl_booke.S | 22 +++++++++++++--------- 2 files changed, 15 insertions(+), 9 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/mmu-fsl-booke.h b/arch/powerpc/include/asm/mmu-fsl-booke.h index 925d93cf64d..5588a41f439 100644 --- a/arch/powerpc/include/asm/mmu-fsl-booke.h +++ b/arch/powerpc/include/asm/mmu-fsl-booke.h @@ -40,6 +40,8 @@ #define MAS2_M 0x00000004 #define MAS2_G 0x00000002 #define MAS2_E 0x00000001 +#define MAS2_EPN_MASK(size) (~0 << (2*(size) + 10)) +#define MAS2_VAL(addr, size, flags) ((addr) & MAS2_EPN_MASK(size) | (flags)) #define MAS3_RPN 0xFFFFF000 #define MAS3_U0 0x00000200 diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S index 837e3cc9cc8..8942d7a82fa 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -235,36 +235,40 @@ skpinv: addi r6,r6,1 /* Increment */ tlbivax 0,r9 TLBSYNC +/* The mapping only needs to be cache-coherent on SMP */ +#ifdef CONFIG_SMP +#define M_IF_SMP MAS2_M +#else +#define M_IF_SMP 0 +#endif + /* 6. Setup KERNELBASE mapping in TLB1[0] */ lis r6,0x1000 /* Set MAS0(TLBSEL) = TLB1(1), ESEL = 0 */ mtspr SPRN_MAS0,r6 lis r6,(MAS1_VALID|MAS1_IPROT)@h ori r6,r6,(MAS1_TSIZE(BOOKE_PAGESZ_64M))@l mtspr SPRN_MAS1,r6 - li r7,0 - lis r6,PAGE_OFFSET@h - ori r6,r6,PAGE_OFFSET@l - rlwimi r6,r7,0,20,31 + lis r6,MAS2_VAL(PAGE_OFFSET, BOOKE_PAGESZ_64M, M_IF_SMP)@h + ori r6,r6,MAS2_VAL(PAGE_OFFSET, BOOKE_PAGESZ_64M, M_IF_SMP)@l mtspr SPRN_MAS2,r6 mtspr SPRN_MAS3,r8 tlbwe /* 7. Jump to KERNELBASE mapping */ - lis r6,KERNELBASE@h - ori r6,r6,KERNELBASE@l - rlwimi r6,r7,0,20,31 + lis r6,(KERNELBASE & ~0xfff)@h + ori r6,r6,(KERNELBASE & ~0xfff)@l lis r7,MSR_KERNEL@h ori r7,r7,MSR_KERNEL@l bl 1f /* Find our address */ 1: mflr r9 rlwimi r6,r9,0,20,31 - addi r6,r6,24 + addi r6,r6,(2f - 1b) mtspr SPRN_SRR0,r6 mtspr SPRN_SRR1,r7 rfi /* start execution out of TLB1[0] entry */ /* 8. Clear out the temp mapping */ - lis r7,0x1000 /* Set MAS0(TLBSEL) = 1 */ +2: lis r7,0x1000 /* Set MAS0(TLBSEL) = 1 */ rlwimi r7,r5,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r5) */ mtspr SPRN_MAS0,r7 tlbre -- cgit v1.2.3-70-g09d2 From 06b90969a7564fad888f67e9f7f4c3a51a16ef1d Mon Sep 17 00:00:00 2001 From: Kumar Gala Date: Mon, 1 Dec 2008 14:38:32 -0600 Subject: powerpc/85xx: minor head_fsl_booke.S cleanup Removed unused branch labels Signed-off-by: Kumar Gala --- arch/powerpc/kernel/head_fsl_booke.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S index 8942d7a82fa..2b576058025 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -751,7 +751,7 @@ finish_tlb_load: iseleq r12, r12, r10 #ifdef CONFIG_PTE_64BIT -2: rlwimi r12, r13, 24, 0, 7 /* grab RPN[32:39] */ + rlwimi r12, r13, 24, 0, 7 /* grab RPN[32:39] */ rlwimi r12, r11, 24, 8, 19 /* grab RPN[40:51] */ mtspr SPRN_MAS3, r12 BEGIN_FTR_SECTION @@ -759,7 +759,7 @@ BEGIN_FTR_SECTION mtspr SPRN_MAS7, r10 END_FTR_SECTION_IFSET(CPU_FTR_BIG_PHYS) #else -2: rlwimi r11, r12, 0, 20, 31 /* Extract RPN from PTE and merge with perms */ + rlwimi r11, r12, 0, 20, 31 /* Extract RPN from PTE and merge with perms */ mtspr SPRN_MAS3, r11 #endif #ifdef CONFIG_E200 -- cgit v1.2.3-70-g09d2 From d5b26db2cfcf09f28f4839c8c3484279cd5ea5b3 Mon Sep 17 00:00:00 2001 From: Kumar Gala Date: Wed, 19 Nov 2008 09:35:56 -0600 Subject: powerpc/85xx: Add support for SMP initialization Added 85xx specifc smp_ops structure. We use ePAPR style boot release and the MPIC for IPIs at this point. Additionally added routines for secondary cpu entry and initializtion. Signed-off-by: Andy Fleming Signed-off-by: Trent Piepho Signed-off-by: Kumar Gala --- arch/powerpc/kernel/head_fsl_booke.S | 70 +++++++++++++++++++++++ arch/powerpc/platforms/85xx/Makefile | 2 + arch/powerpc/platforms/85xx/smp.c | 104 +++++++++++++++++++++++++++++++++++ 3 files changed, 176 insertions(+) create mode 100644 arch/powerpc/platforms/85xx/smp.c (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S index 2b576058025..9a4639c459e 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -92,6 +92,7 @@ _ENTRY(_start); * if needed */ +_ENTRY(__early_start) /* 1. Find the index of the entry we're executing in */ bl invstr /* Find our address */ invstr: mflr r6 /* Make it accessible */ @@ -348,6 +349,15 @@ skpinv: addi r6,r6,1 /* Increment */ mtspr SPRN_DBSR,r2 #endif +#ifdef CONFIG_SMP + /* Check to see if we're the second processor, and jump + * to the secondary_start code if so + */ + mfspr r24,SPRN_PIR + cmpwi r24,0 + bne __secondary_start +#endif + /* * This is where the main kernel code starts. */ @@ -739,6 +749,9 @@ finish_tlb_load: rlwimi r12, r11, 26, 24, 31 /* extract ...WIMGE from pte */ #else rlwimi r12, r11, 26, 27, 31 /* extract WIMGE from pte */ +#endif +#ifdef CONFIG_SMP + ori r12, r12, MAS2_M #endif mtspr SPRN_MAS2, r12 @@ -1042,6 +1055,63 @@ _GLOBAL(flush_dcache_L1) blr +#ifdef CONFIG_SMP +/* When we get here, r24 needs to hold the CPU # */ + .globl __secondary_start +__secondary_start: + lis r3,__secondary_hold_acknowledge@h + ori r3,r3,__secondary_hold_acknowledge@l + stw r24,0(r3) + + li r3,0 + mr r4,r24 /* Why? */ + bl call_setup_cpu + + lis r3,tlbcam_index@ha + lwz r3,tlbcam_index@l(r3) + mtctr r3 + li r26,0 /* r26 safe? */ + + /* Load each CAM entry */ +1: mr r3,r26 + bl loadcam_entry + addi r26,r26,1 + bdnz 1b + + /* get current_thread_info and current */ + lis r1,secondary_ti@ha + lwz r1,secondary_ti@l(r1) + lwz r2,TI_TASK(r1) + + /* stack */ + addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD + li r0,0 + stw r0,0(r1) + + /* ptr to current thread */ + addi r4,r2,THREAD /* address of our thread_struct */ + mtspr SPRN_SPRG3,r4 + + /* Setup the defaults for TLB entries */ + li r4,(MAS4_TSIZED(BOOKE_PAGESZ_4K))@l + mtspr SPRN_MAS4,r4 + + /* Jump to start_secondary */ + lis r4,MSR_KERNEL@h + ori r4,r4,MSR_KERNEL@l + lis r3,start_secondary@h + ori r3,r3,start_secondary@l + mtspr SPRN_SRR0,r3 + mtspr SPRN_SRR1,r4 + sync + rfi + sync + + .globl __secondary_hold_acknowledge +__secondary_hold_acknowledge: + .long -1 +#endif + /* * We put a few things here that have to be page-aligned. This stuff * goes at the beginning of the data segment, which is page-aligned. diff --git a/arch/powerpc/platforms/85xx/Makefile b/arch/powerpc/platforms/85xx/Makefile index cb3054e1001..f0798c09980 100644 --- a/arch/powerpc/platforms/85xx/Makefile +++ b/arch/powerpc/platforms/85xx/Makefile @@ -1,6 +1,8 @@ # # Makefile for the PowerPC 85xx linux kernel. # +obj-$(CONFIG_SMP) += smp.o + obj-$(CONFIG_MPC8540_ADS) += mpc85xx_ads.o obj-$(CONFIG_MPC8560_ADS) += mpc85xx_ads.o obj-$(CONFIG_MPC85xx_CDS) += mpc85xx_cds.o diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c new file mode 100644 index 00000000000..d652c713f49 --- /dev/null +++ b/arch/powerpc/platforms/85xx/smp.c @@ -0,0 +1,104 @@ +/* + * Author: Andy Fleming + * Kumar Gala + * + * Copyright 2006-2008 Freescale Semiconductor Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +#include + +extern volatile unsigned long __secondary_hold_acknowledge; +extern void __early_start(void); + +#define BOOT_ENTRY_ADDR_UPPER 0 +#define BOOT_ENTRY_ADDR_LOWER 1 +#define BOOT_ENTRY_R3_UPPER 2 +#define BOOT_ENTRY_R3_LOWER 3 +#define BOOT_ENTRY_RESV 4 +#define BOOT_ENTRY_PIR 5 +#define BOOT_ENTRY_R6_UPPER 6 +#define BOOT_ENTRY_R6_LOWER 7 +#define NUM_BOOT_ENTRY 8 +#define SIZE_BOOT_ENTRY (NUM_BOOT_ENTRY * sizeof(u32)) + +static void __init +smp_85xx_kick_cpu(int nr) +{ + unsigned long flags; + const u64 *cpu_rel_addr; + __iomem u32 *bptr_vaddr; + struct device_node *np; + int n = 0; + + WARN_ON (nr < 0 || nr >= NR_CPUS); + + pr_debug("smp_85xx_kick_cpu: kick CPU #%d\n", nr); + + local_irq_save(flags); + + np = of_get_cpu_node(nr, NULL); + cpu_rel_addr = of_get_property(np, "cpu-release-addr", NULL); + + if (cpu_rel_addr == NULL) { + printk(KERN_ERR "No cpu-release-addr for cpu %d\n", nr); + return; + } + + /* Map the spin table */ + bptr_vaddr = ioremap(*cpu_rel_addr, SIZE_BOOT_ENTRY); + + out_be32(bptr_vaddr + BOOT_ENTRY_PIR, nr); + out_be32(bptr_vaddr + BOOT_ENTRY_ADDR_LOWER, __pa(__early_start)); + + /* Wait a bit for the CPU to ack. */ + while ((__secondary_hold_acknowledge != nr) && (++n < 1000)) + mdelay(1); + + iounmap(bptr_vaddr); + + local_irq_restore(flags); + + pr_debug("waited %d msecs for CPU #%d.\n", n, nr); +} + +static void __init +smp_85xx_setup_cpu(int cpu_nr) +{ + mpic_setup_this_cpu(); + + /* Clear any pending timer interrupts */ + mtspr(SPRN_TSR, TSR_ENW | TSR_WIS | TSR_DIS | TSR_FIS); + + /* Enable decrementer interrupt */ + mtspr(SPRN_TCR, TCR_DIE); +} + +struct smp_ops_t smp_85xx_ops = { + .message_pass = smp_mpic_message_pass, + .probe = smp_mpic_probe, + .kick_cpu = smp_85xx_kick_cpu, + .setup_cpu = smp_85xx_setup_cpu, +}; + +void __init +mpc85xx_smp_init(void) +{ + smp_ops = &smp_85xx_ops; +} -- cgit v1.2.3-70-g09d2 From 6b82b3e4b54b2fce2ca11976c535012b836b2016 Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Tue, 9 Dec 2008 09:47:29 +0000 Subject: powerpc: Remove `have_of' global variable The `have_of' variable is a relic from the arch/ppc time, it isn't useful nowadays. Signed-off-by: Anton Vorontsov Acked-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/processor.h | 2 -- arch/powerpc/kernel/pci-common.c | 2 -- arch/powerpc/kernel/pci_32.c | 7 +------ arch/powerpc/kernel/setup_32.c | 2 -- arch/powerpc/kernel/setup_64.c | 1 - fs/proc/proc_devtree.c | 3 +-- 6 files changed, 2 insertions(+), 15 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index cd7a47860e5..d3466490104 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -69,8 +69,6 @@ extern int _prep_type; #ifdef __KERNEL__ -extern int have_of; - struct task_struct; void start_thread(struct pt_regs *regs, unsigned long fdptr, unsigned long sp); void release_thread(struct task_struct *); diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 91c3f52e33a..1a32db331a5 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -160,8 +160,6 @@ EXPORT_SYMBOL(pci_domain_nr); */ struct pci_controller* pci_find_hose_for_OF_device(struct device_node* node) { - if (!have_of) - return NULL; while(node) { struct pci_controller *hose, *tmp; list_for_each_entry_safe(hose, tmp, &hose_list, list_node) diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index 7ad11e592f2..132cd80afa2 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -266,9 +266,6 @@ pci_busdev_to_OF_node(struct pci_bus *bus, int devfn) { struct device_node *parent, *np; - if (!have_of) - return NULL; - pr_debug("pci_busdev_to_OF_node(%d,0x%x)\n", bus->number, devfn); parent = scan_OF_for_pci_bus(bus); if (parent == NULL) @@ -309,8 +306,6 @@ pci_device_from_OF_node(struct device_node* node, u8* bus, u8* devfn) struct pci_controller* hose; struct pci_dev* dev = NULL; - if (!have_of) - return -ENODEV; /* Make sure it's really a PCI device */ hose = pci_find_hose_for_OF_device(node); if (!hose || !hose->dn) @@ -431,7 +426,7 @@ static int __init pcibios_init(void) * numbers vs. kernel bus numbers since we may have to * remap them. */ - if (pci_assign_all_buses && have_of) + if (pci_assign_all_buses) pcibios_make_OF_bus_map(); /* Call common code to handle resource allocation */ diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index c1a27626a94..cc4679ed952 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -53,8 +53,6 @@ unsigned long ISA_DMA_THRESHOLD; unsigned int DMA_MODE_READ; unsigned int DMA_MODE_WRITE; -int have_of = 1; - #ifdef CONFIG_VGA_CONSOLE unsigned long vgacon_remap_base; EXPORT_SYMBOL(vgacon_remap_base); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 93c875ae985..ce48f5c5c54 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -70,7 +70,6 @@ #define DBG(fmt...) #endif -int have_of = 1; int boot_cpuid = 0; u64 ppc64_pft_size; diff --git a/fs/proc/proc_devtree.c b/fs/proc/proc_devtree.c index d777789b7a8..de2bba5a344 100644 --- a/fs/proc/proc_devtree.c +++ b/fs/proc/proc_devtree.c @@ -218,8 +218,7 @@ void proc_device_tree_add_node(struct device_node *np, void __init proc_device_tree_init(void) { struct device_node *root; - if ( !have_of ) - return; + proc_device_tree = proc_mkdir("device-tree", NULL); if (proc_device_tree == 0) return; -- cgit v1.2.3-70-g09d2 From 13a9801eb669d567ab2c8f8db5e50557fef5f636 Mon Sep 17 00:00:00 2001 From: Nathan Lynch Date: Wed, 10 Dec 2008 14:28:41 +0000 Subject: powerpc: Move smp_hw_index to 32-bit code smp_hw_index isn't used on 64-bit, so move it from smp.c to setup_32.c. Signed-off-by: Nathan Lynch Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/setup_32.c | 2 ++ arch/powerpc/kernel/smp.c | 1 - 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index cc4679ed952..086c23c1ee5 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -49,6 +49,8 @@ int boot_cpuid; EXPORT_SYMBOL_GPL(boot_cpuid); int boot_cpuid_phys; +int smp_hw_index[NR_CPUS]; + unsigned long ISA_DMA_THRESHOLD; unsigned int DMA_MODE_READ; unsigned int DMA_MODE_WRITE; diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index a59d8d72bb9..ffcb1779a22 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -57,7 +57,6 @@ #define DBG(fmt...) #endif -int smp_hw_index[NR_CPUS]; struct thread_info *secondary_ti; cpumask_t cpu_possible_map = CPU_MASK_NONE; -- cgit v1.2.3-70-g09d2 From edc72ac4a0894247a6d3f1157a8ec8d603fff52d Mon Sep 17 00:00:00 2001 From: Nathan Lynch Date: Thu, 11 Dec 2008 09:14:25 +0000 Subject: powerpc/pseries: Check for GIQ indicator before calling set-indicator Since "Factor out cpu joining/unjoining the GIQ" (b4963255ad5a426f04a0bb15c4315fa4bb40cde9) the WARN_ON in xics_set_cpu_giq() is being triggered during boot on JS20 because the GIQ indicator is not available on that platform. While the warning is harmless and the system runs normally, it's nicer to check for the existence of the indicator before trying to manipulate it. Implement rtas_indicator_present(), which searches the /rtas/rtas-indicators property for the given indicator token, and use this function in xics_set_cpu_giq(). Also use a WARN statement in xics_set_cpu_giq to get better information on failure. Signed-off-by: Nathan Lynch Acked-by: Milton Miller Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/rtas.h | 1 + arch/powerpc/kernel/rtas.c | 26 ++++++++++++++++++++++++++ arch/powerpc/platforms/pseries/xics.c | 15 ++++++++++++--- 3 files changed, 39 insertions(+), 3 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h index 8eaa7b28d9d..e0175beb446 100644 --- a/arch/powerpc/include/asm/rtas.h +++ b/arch/powerpc/include/asm/rtas.h @@ -168,6 +168,7 @@ extern void rtas_os_term(char *str); extern int rtas_get_sensor(int sensor, int index, int *state); extern int rtas_get_power_level(int powerdomain, int *level); extern int rtas_set_power_level(int powerdomain, int level, int *setlevel); +extern bool rtas_indicator_present(int token, int *maxindex); extern int rtas_set_indicator(int indicator, int index, int new_value); extern int rtas_set_indicator_fast(int indicator, int index, int new_value); extern void rtas_progress(char *s, unsigned short hex); diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 1f8505c2354..fdfe14c4bde 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -566,6 +566,32 @@ int rtas_get_sensor(int sensor, int index, int *state) } EXPORT_SYMBOL(rtas_get_sensor); +bool rtas_indicator_present(int token, int *maxindex) +{ + int proplen, count, i; + const struct indicator_elem { + u32 token; + u32 maxindex; + } *indicators; + + indicators = of_get_property(rtas.dev, "rtas-indicators", &proplen); + if (!indicators) + return false; + + count = proplen / sizeof(struct indicator_elem); + + for (i = 0; i < count; i++) { + if (indicators[i].token != token) + continue; + if (maxindex) + *maxindex = indicators[i].maxindex; + return true; + } + + return false; +} +EXPORT_SYMBOL(rtas_indicator_present); + int rtas_set_indicator(int indicator, int index, int new_value) { int token = rtas_token("set-indicator"); diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c index 75a289ba66b..f7a69021b7b 100644 --- a/arch/powerpc/platforms/pseries/xics.c +++ b/arch/powerpc/platforms/pseries/xics.c @@ -744,9 +744,18 @@ static void xics_set_cpu_priority(unsigned char cppr) /* Have the calling processor join or leave the specified global queue */ static void xics_set_cpu_giq(unsigned int gserver, unsigned int join) { - int status = rtas_set_indicator_fast(GLOBAL_INTERRUPT_QUEUE, - (1UL << interrupt_server_size) - 1 - gserver, join); - WARN_ON(status < 0); + int index; + int status; + + if (!rtas_indicator_present(GLOBAL_INTERRUPT_QUEUE, NULL)) + return; + + index = (1UL << interrupt_server_size) - 1 - gserver; + + status = rtas_set_indicator_fast(GLOBAL_INTERRUPT_QUEUE, index, join); + + WARN(status < 0, "set-indicator(%d, %d, %u) returned %d\n", + GLOBAL_INTERRUPT_QUEUE, index, join, status); } void xics_setup_cpu(void) -- cgit v1.2.3-70-g09d2 From aab0d375e01d8c16e7e5b9bd915dfaa0a815418f Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Thu, 4 Dec 2008 10:02:56 -0800 Subject: powerpc: struct device - replace bus_id with dev_name(), dev_set_name() Acked-by: Geoff Levand Signed-off-by: Kay Sievers Signed-off-by: Greg Kroah-Hartman Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/ibmebus.c | 2 +- arch/powerpc/kernel/of_device.c | 18 +++++++----------- arch/powerpc/kernel/vio.c | 12 ++++++------ arch/powerpc/platforms/85xx/mpc85xx_mds.c | 6 +++--- arch/powerpc/platforms/ps3/system-bus.c | 28 ++++++++++++---------------- 5 files changed, 29 insertions(+), 37 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c index 7c6537777b2..6e3f6249365 100644 --- a/arch/powerpc/kernel/ibmebus.c +++ b/arch/powerpc/kernel/ibmebus.c @@ -47,7 +47,7 @@ #include static struct device ibmebus_bus_device = { /* fake "parent" device */ - .bus_id = "ibmebus", + .init_name = "ibmebus", }; struct bus_type ibmebus_bus_type; diff --git a/arch/powerpc/kernel/of_device.c b/arch/powerpc/kernel/of_device.c index f3c9cae01dd..fa983a59c4c 100644 --- a/arch/powerpc/kernel/of_device.c +++ b/arch/powerpc/kernel/of_device.c @@ -14,7 +14,6 @@ static void of_device_make_bus_id(struct of_device *dev) { static atomic_t bus_no_reg_magic; struct device_node *node = dev->node; - char *name = dev->dev.bus_id; const u32 *reg; u64 addr; int magic; @@ -27,14 +26,12 @@ static void of_device_make_bus_id(struct of_device *dev) reg = of_get_property(node, "dcr-reg", NULL); if (reg) { #ifdef CONFIG_PPC_DCR_NATIVE - snprintf(name, BUS_ID_SIZE, "d%x.%s", - *reg, node->name); + dev_set_name(&dev->dev, "d%x.%s", *reg, node->name); #else /* CONFIG_PPC_DCR_NATIVE */ addr = of_translate_dcr_address(node, *reg, NULL); if (addr != OF_BAD_ADDR) { - snprintf(name, BUS_ID_SIZE, - "D%llx.%s", (unsigned long long)addr, - node->name); + dev_set_name(&dev->dev, "D%llx.%s", + (unsigned long long)addr, node->name); return; } #endif /* !CONFIG_PPC_DCR_NATIVE */ @@ -48,9 +45,8 @@ static void of_device_make_bus_id(struct of_device *dev) if (reg) { addr = of_translate_address(node, reg); if (addr != OF_BAD_ADDR) { - snprintf(name, BUS_ID_SIZE, - "%llx.%s", (unsigned long long)addr, - node->name); + dev_set_name(&dev->dev, "%llx.%s", + (unsigned long long)addr, node->name); return; } } @@ -60,7 +56,7 @@ static void of_device_make_bus_id(struct of_device *dev) * counter (and pray...) */ magic = atomic_add_return(1, &bus_no_reg_magic); - snprintf(name, BUS_ID_SIZE, "%s.%d", node->name, magic - 1); + dev_set_name(&dev->dev, "%s.%d", node->name, magic - 1); } struct of_device *of_device_alloc(struct device_node *np, @@ -80,7 +76,7 @@ struct of_device *of_device_alloc(struct device_node *np, dev->dev.archdata.of_node = np; if (bus_id) - strlcpy(dev->dev.bus_id, bus_id, BUS_ID_SIZE); + dev_set_name(&dev->dev, bus_id); else of_device_make_bus_id(dev); diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index a11e6bc59b3..94aa7b011b2 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -41,9 +41,9 @@ static struct bus_type vio_bus_type; static struct vio_dev vio_bus_device = { /* fake "parent" device */ - .name = vio_bus_device.dev.bus_id, + .name = "vio", .type = "", - .dev.bus_id = "vio", + .dev.init_name = "vio", .dev.bus = &vio_bus_type, }; @@ -1216,7 +1216,7 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node) viodev->irq = irq_of_parse_and_map(of_node, 0); - snprintf(viodev->dev.bus_id, BUS_ID_SIZE, "%x", *unit_address); + dev_set_name(&viodev->dev, "%x", *unit_address); viodev->name = of_node->name; viodev->type = of_node->type; viodev->unit_address = *unit_address; @@ -1243,7 +1243,7 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node) /* register with generic device framework */ if (device_register(&viodev->dev)) { printk(KERN_ERR "%s: failed to register device %s\n", - __func__, viodev->dev.bus_id); + __func__, dev_name(&viodev->dev)); /* XXX free TCE table */ kfree(viodev); return NULL; @@ -1400,13 +1400,13 @@ static struct vio_dev *vio_find_name(const char *name) struct vio_dev *vio_find_node(struct device_node *vnode) { const uint32_t *unit_address; - char kobj_name[BUS_ID_SIZE]; + char kobj_name[20]; /* construct the kobject name from the device node */ unit_address = of_get_property(vnode, "reg", NULL); if (!unit_address) return NULL; - snprintf(kobj_name, BUS_ID_SIZE, "%x", *unit_address); + snprintf(kobj_name, sizeof(kobj_name), "%x", *unit_address); return vio_find_name(kobj_name); } diff --git a/arch/powerpc/platforms/85xx/mpc85xx_mds.c b/arch/powerpc/platforms/85xx/mpc85xx_mds.c index b915bf587b3..658a36fab3a 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_mds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_mds.c @@ -231,7 +231,7 @@ static void __init mpc85xx_mds_setup_arch(void) static int __init board_fixups(void) { - char phy_id[BUS_ID_SIZE]; + char phy_id[20]; char *compstrs[2] = {"fsl,gianfar-mdio", "fsl,ucc-mdio"}; struct device_node *mdio; struct resource res; @@ -241,14 +241,14 @@ static int __init board_fixups(void) mdio = of_find_compatible_node(NULL, NULL, compstrs[i]); of_address_to_resource(mdio, 0, &res); - snprintf(phy_id, BUS_ID_SIZE, "%llx:%02x", + snprintf(phy_id, sizeof(phy_id), "%llx:%02x", (unsigned long long)res.start, 1); phy_register_fixup_for_id(phy_id, mpc8568_fixup_125_clock); phy_register_fixup_for_id(phy_id, mpc8568_mds_phy_fixups); /* Register a workaround for errata */ - snprintf(phy_id, BUS_ID_SIZE, "%llx:%02x", + snprintf(phy_id, sizeof(phy_id), "%llx:%02x", (unsigned long long)res.start, 7); phy_register_fixup_for_id(phy_id, mpc8568_mds_phy_fixups); diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c index d3da1e6e73b..ee0d2291162 100644 --- a/arch/powerpc/platforms/ps3/system-bus.c +++ b/arch/powerpc/platforms/ps3/system-bus.c @@ -31,7 +31,7 @@ #include "platform.h" static struct device ps3_system_bus = { - .bus_id = "ps3_system", + .init_name = "ps3_system", }; /* FIXME: need device usage counters! */ @@ -356,12 +356,12 @@ static int ps3_system_bus_match(struct device *_dev, if (result) pr_info("%s:%d: dev=%u.%u(%s), drv=%u.%u(%s): match\n", __func__, __LINE__, - dev->match_id, dev->match_sub_id, dev->core.bus_id, + dev->match_id, dev->match_sub_id, dev_name(&dev->core), drv->match_id, drv->match_sub_id, drv->core.name); else pr_debug("%s:%d: dev=%u.%u(%s), drv=%u.%u(%s): miss\n", __func__, __LINE__, - dev->match_id, dev->match_sub_id, dev->core.bus_id, + dev->match_id, dev->match_sub_id, dev_name(&dev->core), drv->match_id, drv->match_sub_id, drv->core.name); return result; @@ -383,9 +383,9 @@ static int ps3_system_bus_probe(struct device *_dev) result = drv->probe(dev); else pr_debug("%s:%d: %s no probe method\n", __func__, __LINE__, - dev->core.bus_id); + dev_name(&dev->core)); - pr_debug(" <- %s:%d: %s\n", __func__, __LINE__, dev->core.bus_id); + pr_debug(" <- %s:%d: %s\n", __func__, __LINE__, dev_name(&dev->core)); return result; } @@ -407,7 +407,7 @@ static int ps3_system_bus_remove(struct device *_dev) dev_dbg(&dev->core, "%s:%d %s: no remove method\n", __func__, __LINE__, drv->core.name); - pr_debug(" <- %s:%d: %s\n", __func__, __LINE__, dev->core.bus_id); + pr_debug(" <- %s:%d: %s\n", __func__, __LINE__, dev_name(&dev->core)); return result; } @@ -432,7 +432,7 @@ static void ps3_system_bus_shutdown(struct device *_dev) BUG_ON(!drv); dev_dbg(&dev->core, "%s:%d: %s -> %s\n", __func__, __LINE__, - dev->core.bus_id, drv->core.name); + dev_name(&dev->core), drv->core.name); if (drv->shutdown) drv->shutdown(dev); @@ -744,22 +744,18 @@ int ps3_system_bus_device_register(struct ps3_system_bus_device *dev) switch (dev->dev_type) { case PS3_DEVICE_TYPE_IOC0: dev->core.archdata.dma_ops = &ps3_ioc0_dma_ops; - snprintf(dev->core.bus_id, sizeof(dev->core.bus_id), - "ioc0_%02x", ++dev_ioc0_count); + dev_set_name(&dev->core, "ioc0_%02x", ++dev_ioc0_count); break; case PS3_DEVICE_TYPE_SB: dev->core.archdata.dma_ops = &ps3_sb_dma_ops; - snprintf(dev->core.bus_id, sizeof(dev->core.bus_id), - "sb_%02x", ++dev_sb_count); + dev_set_name(&dev->core, "sb_%02x", ++dev_sb_count); break; case PS3_DEVICE_TYPE_VUART: - snprintf(dev->core.bus_id, sizeof(dev->core.bus_id), - "vuart_%02x", ++dev_vuart_count); + dev_set_name(&dev->core, "vuart_%02x", ++dev_vuart_count); break; case PS3_DEVICE_TYPE_LPM: - snprintf(dev->core.bus_id, sizeof(dev->core.bus_id), - "lpm_%02x", ++dev_lpm_count); + dev_set_name(&dev->core, "lpm_%02x", ++dev_lpm_count); break; default: BUG(); @@ -768,7 +764,7 @@ int ps3_system_bus_device_register(struct ps3_system_bus_device *dev) dev->core.archdata.of_node = NULL; set_dev_node(&dev->core, 0); - pr_debug("%s:%d add %s\n", __func__, __LINE__, dev->core.bus_id); + pr_debug("%s:%d add %s\n", __func__, __LINE__, dev_name(&dev->core)); result = device_register(&dev->core); return result; -- cgit v1.2.3-70-g09d2 From e523f723d69cde44e10116d7f49b277da0c6702c Mon Sep 17 00:00:00 2001 From: Nathan Lynch Date: Wed, 10 Dec 2008 14:46:04 +0000 Subject: powerpc: Add of_find_next_cache_node() We have more than one piece of code that looks up cache nodes manually using the "l2-cache" property. Add a common helper routine which does this and handles ePAPR's "next-level-cache" property as well as powermac. Signed-off-by: Nathan Lynch Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/prom.h | 3 +++ arch/powerpc/kernel/prom.c | 31 +++++++++++++++++++++++++++++++ 2 files changed, 34 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index eb3bd2e1c7f..6ff04185d2a 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -253,6 +253,9 @@ extern void kdump_move_device_tree(void); /* CPU OF node matching */ struct device_node *of_get_cpu_node(int cpu, unsigned int *thread); +/* cache lookup */ +struct device_node *of_find_next_cache_node(struct device_node *np); + /* Get the MAC address */ extern const void *of_get_mac_address(struct device_node *np); diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 3a2dc7e6586..d8266dd61dd 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -1270,6 +1270,37 @@ struct device_node *of_find_node_by_phandle(phandle handle) } EXPORT_SYMBOL(of_find_node_by_phandle); +/** + * of_find_next_cache_node - Find a node's subsidiary cache + * @np: node of type "cpu" or "cache" + * + * Returns a node pointer with refcount incremented, use + * of_node_put() on it when done. Caller should hold a reference + * to np. + */ +struct device_node *of_find_next_cache_node(struct device_node *np) +{ + struct device_node *child; + const phandle *handle; + + handle = of_get_property(np, "l2-cache", NULL); + if (!handle) + handle = of_get_property(np, "next-level-cache", NULL); + + if (handle) + return of_find_node_by_phandle(*handle); + + /* OF on pmac has nodes instead of properties named "l2-cache" + * beneath CPU nodes. + */ + if (!strcmp(np->type, "cpu")) + for_each_child_of_node(np, child) + if (!strcmp(child->type, "cache")) + return child; + + return NULL; +} + /** * of_find_all_nodes - Get next node in global list * @prev: Previous node or NULL to start iteration -- cgit v1.2.3-70-g09d2 From b2ea25b958968c152c6fac0594f2c9aa8b59eb8d Mon Sep 17 00:00:00 2001 From: Nathan Lynch Date: Wed, 10 Dec 2008 20:16:07 +0000 Subject: powerpc: Convert cpu_to_l2cache() to of_find_next_cache_node() The smp code uses cache information to populate cpu_core_map; change it to use common code for cache lookup. Signed-off-by: Nathan Lynch Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/smp.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index ffcb1779a22..8ac3f721d23 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -466,8 +466,7 @@ out: static struct device_node *cpu_to_l2cache(int cpu) { struct device_node *np; - const phandle *php; - phandle ph; + struct device_node *cache; if (!cpu_present(cpu)) return NULL; @@ -476,13 +475,11 @@ static struct device_node *cpu_to_l2cache(int cpu) if (np == NULL) return NULL; - php = of_get_property(np, "l2-cache", NULL); - if (php == NULL) - return NULL; - ph = *php; + cache = of_find_next_cache_node(np); + of_node_put(np); - return of_find_node_by_phandle(ph); + return cache; } /* Activate a secondary processor. */ -- cgit v1.2.3-70-g09d2 From 13ba3c0092b4db272d1f643206c1b55f4fe415a6 Mon Sep 17 00:00:00 2001 From: Nathan Lynch Date: Wed, 10 Dec 2008 14:46:06 +0000 Subject: powerpc: Convert sysfs cache code to of_find_next_cache_node() Using the common code means that more complete cache information will provided in sysfs on platforms that don't use the l2-cache property convention. Signed-off-by: Nathan Lynch Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/sysfs.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 20885a38237..0c64f10087b 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -566,7 +566,6 @@ static bool cache_is_unified(struct device_node *np) static struct cache_desc * __cpuinit create_cache_index_info(struct device_node *np, struct kobject *parent, int index, int level) { - const phandle *next_cache_phandle; struct device_node *next_cache; struct cache_desc *new, **end; @@ -591,11 +590,7 @@ static struct cache_desc * __cpuinit create_cache_index_info(struct device_node while (*end) end = &(*end)->next; - next_cache_phandle = of_get_property(np, "l2-cache", NULL); - if (!next_cache_phandle) - goto out; - - next_cache = of_find_node_by_phandle(*next_cache_phandle); + next_cache = of_find_next_cache_node(np); if (!next_cache) goto out; -- cgit v1.2.3-70-g09d2 From 6d2170be4561293a6aa821c773687bd3f18e8206 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Thu, 18 Dec 2008 19:13:22 +0000 Subject: powerpc/4xx: Extended DCR support v2 This adds supports to the "extended" DCR addressing via the indirect mfdcrx/mtdcrx instructions supported by some 4xx cores (440H6 and later). I enabled the feature for now only on AMCC 460 chips. Signed-off-by: Benjamin Herrenschmidt Acked-by: Josh Boyer Acked-by: Kumar Gala Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/cputable.h | 7 ++-- arch/powerpc/include/asm/dcr-native.h | 63 ++++++++++++++++++++++++++++------- arch/powerpc/kernel/cputable.c | 4 +-- arch/powerpc/sysdev/dcr-low.S | 8 ++++- 4 files changed, 65 insertions(+), 17 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index f3d9d741716..31888322d76 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -164,6 +164,7 @@ extern const char *powerpc_base_platform; #define CPU_FTR_NEED_PAIRED_STWCX ASM_CONST(0x0000000004000000) #define CPU_FTR_LWSYNC ASM_CONST(0x0000000008000000) #define CPU_FTR_NOEXECUTE ASM_CONST(0x0000000010000000) +#define CPU_FTR_INDEXED_DCR ASM_CONST(0x0000000020000000) /* * Add the 64-bit processor unique features in the top half of the word; @@ -369,6 +370,8 @@ extern const char *powerpc_base_platform; #define CPU_FTRS_8XX (CPU_FTR_USE_TB) #define CPU_FTRS_40X (CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE) #define CPU_FTRS_44X (CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE) +#define CPU_FTRS_440x6 (CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE | \ + CPU_FTR_INDEXED_DCR) #define CPU_FTRS_E200 (CPU_FTR_USE_TB | CPU_FTR_SPE_COMP | \ CPU_FTR_NODSISRALIGN | CPU_FTR_COHERENT_ICACHE | \ CPU_FTR_UNIFIED_ID_CACHE | CPU_FTR_NOEXECUTE) @@ -455,7 +458,7 @@ enum { CPU_FTRS_40X | #endif #ifdef CONFIG_44x - CPU_FTRS_44X | + CPU_FTRS_44X | CPU_FTRS_440x6 | #endif #ifdef CONFIG_E200 CPU_FTRS_E200 | @@ -495,7 +498,7 @@ enum { CPU_FTRS_40X & #endif #ifdef CONFIG_44x - CPU_FTRS_44X & + CPU_FTRS_44X & CPU_FTRS_440x6 & #endif #ifdef CONFIG_E200 CPU_FTRS_E200 & diff --git a/arch/powerpc/include/asm/dcr-native.h b/arch/powerpc/include/asm/dcr-native.h index 72d2b72c739..7d2e6235726 100644 --- a/arch/powerpc/include/asm/dcr-native.h +++ b/arch/powerpc/include/asm/dcr-native.h @@ -23,6 +23,7 @@ #ifndef __ASSEMBLY__ #include +#include typedef struct { unsigned int base; @@ -39,23 +40,45 @@ static inline bool dcr_map_ok_native(dcr_host_native_t host) #define dcr_read_native(host, dcr_n) mfdcr(dcr_n + host.base) #define dcr_write_native(host, dcr_n, value) mtdcr(dcr_n + host.base, value) -/* Device Control Registers */ -void __mtdcr(int reg, unsigned int val); -unsigned int __mfdcr(int reg); +/* Table based DCR accessors */ +extern void __mtdcr(unsigned int reg, unsigned int val); +extern unsigned int __mfdcr(unsigned int reg); + +/* mfdcrx/mtdcrx instruction based accessors. We hand code + * the opcodes in order not to depend on newer binutils + */ +static inline unsigned int mfdcrx(unsigned int reg) +{ + unsigned int ret; + asm volatile(".long 0x7c000206 | (%0 << 21) | (%1 << 16)" + : "=r" (ret) : "r" (reg)); + return ret; +} + +static inline void mtdcrx(unsigned int reg, unsigned int val) +{ + asm volatile(".long 0x7c000306 | (%0 << 21) | (%1 << 16)" + : : "r" (val), "r" (reg)); +} + #define mfdcr(rn) \ ({unsigned int rval; \ - if (__builtin_constant_p(rn)) \ + if (__builtin_constant_p(rn) && rn < 1024) \ asm volatile("mfdcr %0," __stringify(rn) \ : "=r" (rval)); \ + else if (likely(cpu_has_feature(CPU_FTR_INDEXED_DCR))) \ + rval = mfdcrx(rn); \ else \ rval = __mfdcr(rn); \ rval;}) #define mtdcr(rn, v) \ do { \ - if (__builtin_constant_p(rn)) \ + if (__builtin_constant_p(rn) && rn < 1024) \ asm volatile("mtdcr " __stringify(rn) ",%0" \ : : "r" (v)); \ + else if (likely(cpu_has_feature(CPU_FTR_INDEXED_DCR))) \ + mtdcrx(rn, v); \ else \ __mtdcr(rn, v); \ } while (0) @@ -69,8 +92,13 @@ static inline unsigned __mfdcri(int base_addr, int base_data, int reg) unsigned int val; spin_lock_irqsave(&dcr_ind_lock, flags); - __mtdcr(base_addr, reg); - val = __mfdcr(base_data); + if (cpu_has_feature(CPU_FTR_INDEXED_DCR)) { + mtdcrx(base_addr, reg); + val = mfdcrx(base_data); + } else { + __mtdcr(base_addr, reg); + val = __mfdcr(base_data); + } spin_unlock_irqrestore(&dcr_ind_lock, flags); return val; } @@ -81,8 +109,13 @@ static inline void __mtdcri(int base_addr, int base_data, int reg, unsigned long flags; spin_lock_irqsave(&dcr_ind_lock, flags); - __mtdcr(base_addr, reg); - __mtdcr(base_data, val); + if (cpu_has_feature(CPU_FTR_INDEXED_DCR)) { + mtdcrx(base_addr, reg); + mtdcrx(base_data, val); + } else { + __mtdcr(base_addr, reg); + __mtdcr(base_data, val); + } spin_unlock_irqrestore(&dcr_ind_lock, flags); } @@ -93,9 +126,15 @@ static inline void __dcri_clrset(int base_addr, int base_data, int reg, unsigned int val; spin_lock_irqsave(&dcr_ind_lock, flags); - __mtdcr(base_addr, reg); - val = (__mfdcr(base_data) & ~clr) | set; - __mtdcr(base_data, val); + if (cpu_has_feature(CPU_FTR_INDEXED_DCR)) { + mtdcrx(base_addr, reg); + val = (mfdcrx(base_data) & ~clr) | set; + mtdcrx(base_data, val); + } else { + __mtdcr(base_addr, reg); + val = (__mfdcr(base_data) & ~clr) | set; + __mtdcr(base_data, val); + } spin_unlock_irqrestore(&dcr_ind_lock, flags); } diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 7e8719504f3..921a2298d8e 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -1509,7 +1509,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .pvr_mask = 0xffff0002, .pvr_value = 0x13020002, .cpu_name = "460EX", - .cpu_features = CPU_FTRS_44X, + .cpu_features = CPU_FTRS_440x6, .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, .icache_bsize = 32, .dcache_bsize = 32, @@ -1521,7 +1521,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .pvr_mask = 0xffff0002, .pvr_value = 0x13020000, .cpu_name = "460GT", - .cpu_features = CPU_FTRS_44X, + .cpu_features = CPU_FTRS_440x6, .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, .icache_bsize = 32, .dcache_bsize = 32, diff --git a/arch/powerpc/sysdev/dcr-low.S b/arch/powerpc/sysdev/dcr-low.S index 2078f39e2f1..d3098ef1404 100644 --- a/arch/powerpc/sysdev/dcr-low.S +++ b/arch/powerpc/sysdev/dcr-low.S @@ -11,14 +11,20 @@ #include #include +#include #define DCR_ACCESS_PROLOG(table) \ + cmpli cr0,r3,1024; \ rlwinm r3,r3,4,18,27; \ lis r5,table@h; \ ori r5,r5,table@l; \ add r3,r3,r5; \ + bge- 1f; \ mtctr r3; \ - bctr + bctr; \ +1: trap; \ + EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0; \ + blr _GLOBAL(__mfdcr) DCR_ACCESS_PROLOG(__mfdcr_table) -- cgit v1.2.3-70-g09d2 From 5e696617c425eb97bd943d781f3941fb1e8f0e5b Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Thu, 18 Dec 2008 19:13:24 +0000 Subject: powerpc/mm: Split mmu_context handling This splits the mmu_context handling between 32-bit hash based processors, 64-bit hash based processors and everybody else. This is preliminary work for adding SMP support for BookE processors. Signed-off-by: Benjamin Herrenschmidt Acked-by: Kumar Gala Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/mmu_context.h | 260 ++++----------------------- arch/powerpc/kernel/asm-offsets.c | 1 + arch/powerpc/kernel/head_32.S | 12 +- arch/powerpc/kernel/ppc_ksyms.c | 3 +- arch/powerpc/kernel/swsusp.c | 2 +- arch/powerpc/mm/Makefile | 7 +- arch/powerpc/mm/mmu_context_32.c | 84 --------- arch/powerpc/mm/mmu_context_64.c | 70 -------- arch/powerpc/mm/mmu_context_hash32.c | 103 +++++++++++ arch/powerpc/mm/mmu_context_hash64.c | 78 ++++++++ arch/powerpc/mm/mmu_context_nohash.c | 162 +++++++++++++++++ arch/powerpc/platforms/Kconfig.cputype | 10 +- arch/powerpc/platforms/powermac/cpufreq_32.c | 2 +- drivers/macintosh/via-pmu.c | 4 +- 14 files changed, 407 insertions(+), 391 deletions(-) delete mode 100644 arch/powerpc/mm/mmu_context_32.c delete mode 100644 arch/powerpc/mm/mmu_context_64.c create mode 100644 arch/powerpc/mm/mmu_context_hash32.c create mode 100644 arch/powerpc/mm/mmu_context_hash64.c create mode 100644 arch/powerpc/mm/mmu_context_nohash.c (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index b570209b71a..ab4f19263c4 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -2,240 +2,26 @@ #define __ASM_POWERPC_MMU_CONTEXT_H #ifdef __KERNEL__ +#include +#include +#include +#include #include #include #include - -#ifndef CONFIG_PPC64 -#include -#include - -/* - * On 32-bit PowerPC 6xx/7xx/7xxx CPUs, we use a set of 16 VSIDs - * (virtual segment identifiers) for each context. Although the - * hardware supports 24-bit VSIDs, and thus >1 million contexts, - * we only use 32,768 of them. That is ample, since there can be - * at most around 30,000 tasks in the system anyway, and it means - * that we can use a bitmap to indicate which contexts are in use. - * Using a bitmap means that we entirely avoid all of the problems - * that we used to have when the context number overflowed, - * particularly on SMP systems. - * -- paulus. - */ - -/* - * This function defines the mapping from contexts to VSIDs (virtual - * segment IDs). We use a skew on both the context and the high 4 bits - * of the 32-bit virtual address (the "effective segment ID") in order - * to spread out the entries in the MMU hash table. Note, if this - * function is changed then arch/ppc/mm/hashtable.S will have to be - * changed to correspond. - */ -#define CTX_TO_VSID(ctx, va) (((ctx) * (897 * 16) + ((va) >> 28) * 0x111) \ - & 0xffffff) - -/* - The MPC8xx has only 16 contexts. We rotate through them on each - task switch. A better way would be to keep track of tasks that - own contexts, and implement an LRU usage. That way very active - tasks don't always have to pay the TLB reload overhead. The - kernel pages are mapped shared, so the kernel can run on behalf - of any task that makes a kernel entry. Shared does not mean they - are not protected, just that the ASID comparison is not performed. - -- Dan - - The IBM4xx has 256 contexts, so we can just rotate through these - as a way of "switching" contexts. If the TID of the TLB is zero, - the PID/TID comparison is disabled, so we can use a TID of zero - to represent all kernel pages as shared among all contexts. - -- Dan - */ - -static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) -{ -} - -#ifdef CONFIG_8xx -#define NO_CONTEXT 16 -#define LAST_CONTEXT 15 -#define FIRST_CONTEXT 0 - -#elif defined(CONFIG_4xx) -#define NO_CONTEXT 256 -#define LAST_CONTEXT 255 -#define FIRST_CONTEXT 1 - -#elif defined(CONFIG_E200) || defined(CONFIG_E500) -#define NO_CONTEXT 256 -#define LAST_CONTEXT 255 -#define FIRST_CONTEXT 1 - -#else - -/* PPC 6xx, 7xx CPUs */ -#define NO_CONTEXT ((unsigned long) -1) -#define LAST_CONTEXT 32767 -#define FIRST_CONTEXT 1 -#endif - -/* - * Set the current MMU context. - * On 32-bit PowerPCs (other than the 8xx embedded chips), this is done by - * loading up the segment registers for the user part of the address space. - * - * Since the PGD is immediately available, it is much faster to simply - * pass this along as a second parameter, which is required for 8xx and - * can be used for debugging on all processors (if you happen to have - * an Abatron). - */ -extern void set_context(unsigned long contextid, pgd_t *pgd); - -/* - * Bitmap of contexts in use. - * The size of this bitmap is LAST_CONTEXT + 1 bits. - */ -extern unsigned long context_map[]; - -/* - * This caches the next context number that we expect to be free. - * Its use is an optimization only, we can't rely on this context - * number to be free, but it usually will be. - */ -extern unsigned long next_mmu_context; - -/* - * If we don't have sufficient contexts to give one to every task - * that could be in the system, we need to be able to steal contexts. - * These variables support that. - */ -#if LAST_CONTEXT < 30000 -#define FEW_CONTEXTS 1 -extern atomic_t nr_free_contexts; -extern struct mm_struct *context_mm[LAST_CONTEXT+1]; -extern void steal_context(void); -#endif - -/* - * Get a new mmu context for the address space described by `mm'. - */ -static inline void get_mmu_context(struct mm_struct *mm) -{ - unsigned long ctx; - - if (mm->context.id != NO_CONTEXT) - return; -#ifdef FEW_CONTEXTS - while (atomic_dec_if_positive(&nr_free_contexts) < 0) - steal_context(); -#endif - ctx = next_mmu_context; - while (test_and_set_bit(ctx, context_map)) { - ctx = find_next_zero_bit(context_map, LAST_CONTEXT+1, ctx); - if (ctx > LAST_CONTEXT) - ctx = 0; - } - next_mmu_context = (ctx + 1) & LAST_CONTEXT; - mm->context.id = ctx; -#ifdef FEW_CONTEXTS - context_mm[ctx] = mm; -#endif -} +#include /* - * Set up the context for a new address space. + * Most if the context management is out of line */ -static inline int init_new_context(struct task_struct *t, struct mm_struct *mm) -{ - mm->context.id = NO_CONTEXT; - return 0; -} - -/* - * We're finished using the context for an address space. - */ -static inline void destroy_context(struct mm_struct *mm) -{ - preempt_disable(); - if (mm->context.id != NO_CONTEXT) { - clear_bit(mm->context.id, context_map); - mm->context.id = NO_CONTEXT; -#ifdef FEW_CONTEXTS - atomic_inc(&nr_free_contexts); -#endif - } - preempt_enable(); -} - -static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, - struct task_struct *tsk) -{ -#ifdef CONFIG_ALTIVEC - if (cpu_has_feature(CPU_FTR_ALTIVEC)) - asm volatile ("dssall;\n" -#ifndef CONFIG_POWER4 - "sync;\n" /* G4 needs a sync here, G5 apparently not */ -#endif - : : ); -#endif /* CONFIG_ALTIVEC */ - - tsk->thread.pgdir = next->pgd; - - if (!cpu_isset(smp_processor_id(), next->cpu_vm_mask)) - cpu_set(smp_processor_id(), next->cpu_vm_mask); - - /* No need to flush userspace segments if the mm doesnt change */ - if (prev == next) - return; - - /* Setup new userspace context */ - get_mmu_context(next); - set_context(next->context.id, next->pgd); -} - -#define deactivate_mm(tsk,mm) do { } while (0) - -/* - * After we have set current->mm to a new value, this activates - * the context for the new mm so we see the new mappings. - */ -#define activate_mm(active_mm, mm) switch_mm(active_mm, mm, current) - extern void mmu_context_init(void); - - -#else - -#include -#include -#include - -/* - * Copyright (C) 2001 PPC 64 Team, IBM Corp - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -static inline void enter_lazy_tlb(struct mm_struct *mm, - struct task_struct *tsk) -{ -} - -/* - * The proto-VSID space has 2^35 - 1 segments available for user mappings. - * Each segment contains 2^28 bytes. Each context maps 2^44 bytes, - * so we can support 2^19-1 contexts (19 == 35 + 28 - 44). - */ -#define NO_CONTEXT 0 -#define MAX_CONTEXT ((1UL << 19) - 1) - extern int init_new_context(struct task_struct *tsk, struct mm_struct *mm); extern void destroy_context(struct mm_struct *mm); +extern void switch_mmu_context(struct mm_struct *prev, struct mm_struct *next); extern void switch_stab(struct task_struct *tsk, struct mm_struct *mm); extern void switch_slb(struct task_struct *tsk, struct mm_struct *mm); +extern void set_context(unsigned long id, pgd_t *pgd); /* * switch_mm is the entry point called from the architecture independent @@ -244,22 +30,39 @@ extern void switch_slb(struct task_struct *tsk, struct mm_struct *mm); static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) { - if (!cpu_isset(smp_processor_id(), next->cpu_vm_mask)) - cpu_set(smp_processor_id(), next->cpu_vm_mask); + /* Mark this context has been used on the new CPU */ + cpu_set(smp_processor_id(), next->cpu_vm_mask); + + /* 32-bit keeps track of the current PGDIR in the thread struct */ +#ifdef CONFIG_PPC32 + tsk->thread.pgdir = next->pgd; +#endif /* CONFIG_PPC32 */ - /* No need to flush userspace segments if the mm doesnt change */ + /* Nothing else to do if we aren't actually switching */ if (prev == next) return; + /* We must stop all altivec streams before changing the HW + * context + */ #ifdef CONFIG_ALTIVEC if (cpu_has_feature(CPU_FTR_ALTIVEC)) asm volatile ("dssall"); #endif /* CONFIG_ALTIVEC */ + /* The actual HW switching method differs between the various + * sub architectures. + */ +#ifdef CONFIG_PPC_STD_MMU_64 if (cpu_has_feature(CPU_FTR_SLB)) switch_slb(tsk, next); else switch_stab(tsk, next); +#else + /* Out of line for now */ + switch_mmu_context(prev, next); +#endif + } #define deactivate_mm(tsk,mm) do { } while (0) @@ -277,6 +80,11 @@ static inline void activate_mm(struct mm_struct *prev, struct mm_struct *next) local_irq_restore(flags); } -#endif /* CONFIG_PPC64 */ +/* We don't currently use enter_lazy_tlb() for anything */ +static inline void enter_lazy_tlb(struct mm_struct *mm, + struct task_struct *tsk) +{ +} + #endif /* __KERNEL__ */ #endif /* __ASM_POWERPC_MMU_CONTEXT_H */ diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 050abfd5c17..c05ab1d3e62 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -60,6 +60,7 @@ int main(void) { DEFINE(THREAD, offsetof(struct task_struct, thread)); DEFINE(MM, offsetof(struct task_struct, mm)); + DEFINE(MMCONTEXTID, offsetof(struct mm_struct, context.id)); #ifdef CONFIG_PPC64 DEFINE(AUDITCONTEXT, offsetof(struct task_struct, audit_context)); #else diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index 0c326823c6d..be9f9e5470e 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -31,6 +31,7 @@ #include #include #include +#include /* 601 only have IBAT; cr0.eq is set on 601 when using this macro */ #define LOAD_BAT(n, reg, RA, RB) \ @@ -1070,9 +1071,14 @@ start_here: RFI /* + * void switch_mmu_context(struct mm_struct *prev, struct mm_struct *next); + * * Set up the segment registers for a new context. */ -_ENTRY(set_context) +_ENTRY(switch_mmu_context) + lwz r3,MMCONTEXTID(r4) + cmpwi cr0,r3,0 + blt- 4f mulli r3,r3,897 /* multiply context by skew factor */ rlwinm r3,r3,4,8,27 /* VSID = (context & 0xfffff) << 4 */ addis r3,r3,0x6000 /* Set Ks, Ku bits */ @@ -1083,6 +1089,7 @@ _ENTRY(set_context) /* Context switch the PTE pointer for the Abatron BDI2000. * The PGDIR is passed as second argument. */ + lwz r4,MM_PGD(r4) lis r5, KERNELBASE@h lwz r5, 0xf0(r5) stw r4, 0x4(r5) @@ -1098,6 +1105,9 @@ _ENTRY(set_context) sync isync blr +4: trap + EMIT_BUG_ENTRY 4b,__FILE__,__LINE__,0 + blr /* * An undocumented "feature" of 604e requires that the v bit diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index 260089dccfb..341b3d3048e 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -174,8 +174,7 @@ EXPORT_SYMBOL(cacheable_memcpy); #endif #ifdef CONFIG_PPC32 -EXPORT_SYMBOL(next_mmu_context); -EXPORT_SYMBOL(set_context); +EXPORT_SYMBOL(switch_mmu_context); #endif #ifdef CONFIG_PPC_STD_MMU_32 diff --git a/arch/powerpc/kernel/swsusp.c b/arch/powerpc/kernel/swsusp.c index 77b7b34b595..560c9611950 100644 --- a/arch/powerpc/kernel/swsusp.c +++ b/arch/powerpc/kernel/swsusp.c @@ -34,6 +34,6 @@ void save_processor_state(void) void restore_processor_state(void) { #ifdef CONFIG_PPC32 - set_context(current->active_mm->context.id, current->active_mm->pgd); + switch_mmu_context(NULL, current->active_mm); #endif } diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile index 148de35c9ee..923bd3fa7d6 100644 --- a/arch/powerpc/mm/Makefile +++ b/arch/powerpc/mm/Makefile @@ -8,15 +8,16 @@ endif obj-y := fault.o mem.o pgtable.o \ init_$(CONFIG_WORD_SIZE).o \ - pgtable_$(CONFIG_WORD_SIZE).o \ - mmu_context_$(CONFIG_WORD_SIZE).o + pgtable_$(CONFIG_WORD_SIZE).o +obj-$(CONFIG_PPC_MMU_NOHASH) += mmu_context_nohash.o hash-$(CONFIG_PPC_NATIVE) := hash_native_64.o obj-$(CONFIG_PPC64) += hash_utils_64.o \ slb_low.o slb.o stab.o \ gup.o mmap.o $(hash-y) obj-$(CONFIG_PPC_STD_MMU_32) += ppc_mmu_32.o obj-$(CONFIG_PPC_STD_MMU) += hash_low_$(CONFIG_WORD_SIZE).o \ - tlb_hash$(CONFIG_WORD_SIZE).o + tlb_hash$(CONFIG_WORD_SIZE).o \ + mmu_context_hash$(CONFIG_WORD_SIZE).o obj-$(CONFIG_40x) += 40x_mmu.o obj-$(CONFIG_44x) += 44x_mmu.o obj-$(CONFIG_FSL_BOOKE) += fsl_booke_mmu.o diff --git a/arch/powerpc/mm/mmu_context_32.c b/arch/powerpc/mm/mmu_context_32.c deleted file mode 100644 index cc32ba41d90..00000000000 --- a/arch/powerpc/mm/mmu_context_32.c +++ /dev/null @@ -1,84 +0,0 @@ -/* - * This file contains the routines for handling the MMU on those - * PowerPC implementations where the MMU substantially follows the - * architecture specification. This includes the 6xx, 7xx, 7xxx, - * 8260, and POWER3 implementations but excludes the 8xx and 4xx. - * -- paulus - * - * Derived from arch/ppc/mm/init.c: - * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) - * - * Modifications by Paul Mackerras (PowerMac) (paulus@cs.anu.edu.au) - * and Cort Dougan (PReP) (cort@cs.nmt.edu) - * Copyright (C) 1996 Paul Mackerras - * - * Derived from "arch/i386/mm/init.c" - * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - */ - -#include -#include - -#include -#include - -unsigned long next_mmu_context; -unsigned long context_map[LAST_CONTEXT / BITS_PER_LONG + 1]; -#ifdef FEW_CONTEXTS -atomic_t nr_free_contexts; -struct mm_struct *context_mm[LAST_CONTEXT+1]; -void steal_context(void); -#endif /* FEW_CONTEXTS */ - -/* - * Initialize the context management stuff. - */ -void __init -mmu_context_init(void) -{ - /* - * Some processors have too few contexts to reserve one for - * init_mm, and require using context 0 for a normal task. - * Other processors reserve the use of context zero for the kernel. - * This code assumes FIRST_CONTEXT < 32. - */ - context_map[0] = (1 << FIRST_CONTEXT) - 1; - next_mmu_context = FIRST_CONTEXT; -#ifdef FEW_CONTEXTS - atomic_set(&nr_free_contexts, LAST_CONTEXT - FIRST_CONTEXT + 1); -#endif /* FEW_CONTEXTS */ -} - -#ifdef FEW_CONTEXTS -/* - * Steal a context from a task that has one at the moment. - * This is only used on 8xx and 4xx and we presently assume that - * they don't do SMP. If they do then this will have to check - * whether the MM we steal is in use. - * We also assume that this is only used on systems that don't - * use an MMU hash table - this is true for 8xx and 4xx. - * This isn't an LRU system, it just frees up each context in - * turn (sort-of pseudo-random replacement :). This would be the - * place to implement an LRU scheme if anyone was motivated to do it. - * -- paulus - */ -void -steal_context(void) -{ - struct mm_struct *mm; - - /* free up context `next_mmu_context' */ - /* if we shouldn't free context 0, don't... */ - if (next_mmu_context < FIRST_CONTEXT) - next_mmu_context = FIRST_CONTEXT; - mm = context_mm[next_mmu_context]; - flush_tlb_mm(mm); - destroy_context(mm); -} -#endif /* FEW_CONTEXTS */ diff --git a/arch/powerpc/mm/mmu_context_64.c b/arch/powerpc/mm/mmu_context_64.c deleted file mode 100644 index 1db38ba1f54..00000000000 --- a/arch/powerpc/mm/mmu_context_64.c +++ /dev/null @@ -1,70 +0,0 @@ -/* - * MMU context allocation for 64-bit kernels. - * - * Copyright (C) 2004 Anton Blanchard, IBM Corp. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - */ - -#include -#include -#include -#include -#include -#include -#include -#include - -#include - -static DEFINE_SPINLOCK(mmu_context_lock); -static DEFINE_IDR(mmu_context_idr); - -int init_new_context(struct task_struct *tsk, struct mm_struct *mm) -{ - int index; - int err; - -again: - if (!idr_pre_get(&mmu_context_idr, GFP_KERNEL)) - return -ENOMEM; - - spin_lock(&mmu_context_lock); - err = idr_get_new_above(&mmu_context_idr, NULL, 1, &index); - spin_unlock(&mmu_context_lock); - - if (err == -EAGAIN) - goto again; - else if (err) - return err; - - if (index > MAX_CONTEXT) { - spin_lock(&mmu_context_lock); - idr_remove(&mmu_context_idr, index); - spin_unlock(&mmu_context_lock); - return -ENOMEM; - } - - /* The old code would re-promote on fork, we don't do that - * when using slices as it could cause problem promoting slices - * that have been forced down to 4K - */ - if (slice_mm_new_context(mm)) - slice_set_user_psize(mm, mmu_virtual_psize); - mm->context.id = index; - - return 0; -} - -void destroy_context(struct mm_struct *mm) -{ - spin_lock(&mmu_context_lock); - idr_remove(&mmu_context_idr, mm->context.id); - spin_unlock(&mmu_context_lock); - - mm->context.id = NO_CONTEXT; -} diff --git a/arch/powerpc/mm/mmu_context_hash32.c b/arch/powerpc/mm/mmu_context_hash32.c new file mode 100644 index 00000000000..0dfba2bf7f3 --- /dev/null +++ b/arch/powerpc/mm/mmu_context_hash32.c @@ -0,0 +1,103 @@ +/* + * This file contains the routines for handling the MMU on those + * PowerPC implementations where the MMU substantially follows the + * architecture specification. This includes the 6xx, 7xx, 7xxx, + * 8260, and POWER3 implementations but excludes the 8xx and 4xx. + * -- paulus + * + * Derived from arch/ppc/mm/init.c: + * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) + * + * Modifications by Paul Mackerras (PowerMac) (paulus@cs.anu.edu.au) + * and Cort Dougan (PReP) (cort@cs.nmt.edu) + * Copyright (C) 1996 Paul Mackerras + * + * Derived from "arch/i386/mm/init.c" + * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + */ + +#include +#include + +#include +#include + +/* + * On 32-bit PowerPC 6xx/7xx/7xxx CPUs, we use a set of 16 VSIDs + * (virtual segment identifiers) for each context. Although the + * hardware supports 24-bit VSIDs, and thus >1 million contexts, + * we only use 32,768 of them. That is ample, since there can be + * at most around 30,000 tasks in the system anyway, and it means + * that we can use a bitmap to indicate which contexts are in use. + * Using a bitmap means that we entirely avoid all of the problems + * that we used to have when the context number overflowed, + * particularly on SMP systems. + * -- paulus. + */ +#define NO_CONTEXT ((unsigned long) -1) +#define LAST_CONTEXT 32767 +#define FIRST_CONTEXT 1 + +/* + * This function defines the mapping from contexts to VSIDs (virtual + * segment IDs). We use a skew on both the context and the high 4 bits + * of the 32-bit virtual address (the "effective segment ID") in order + * to spread out the entries in the MMU hash table. Note, if this + * function is changed then arch/ppc/mm/hashtable.S will have to be + * changed to correspond. + * + * + * CTX_TO_VSID(ctx, va) (((ctx) * (897 * 16) + ((va) >> 28) * 0x111) \ + * & 0xffffff) + */ + +static unsigned long next_mmu_context; +static unsigned long context_map[LAST_CONTEXT / BITS_PER_LONG + 1]; + + +/* + * Set up the context for a new address space. + */ +int init_new_context(struct task_struct *t, struct mm_struct *mm) +{ + unsigned long ctx = next_mmu_context; + + while (test_and_set_bit(ctx, context_map)) { + ctx = find_next_zero_bit(context_map, LAST_CONTEXT+1, ctx); + if (ctx > LAST_CONTEXT) + ctx = 0; + } + next_mmu_context = (ctx + 1) & LAST_CONTEXT; + mm->context.id = ctx; + + return 0; +} + +/* + * We're finished using the context for an address space. + */ +void destroy_context(struct mm_struct *mm) +{ + preempt_disable(); + if (mm->context.id != NO_CONTEXT) { + clear_bit(mm->context.id, context_map); + mm->context.id = NO_CONTEXT; + } + preempt_enable(); +} + +/* + * Initialize the context management stuff. + */ +void __init mmu_context_init(void) +{ + /* Reserve context 0 for kernel use */ + context_map[0] = (1 << FIRST_CONTEXT) - 1; + next_mmu_context = FIRST_CONTEXT; +} diff --git a/arch/powerpc/mm/mmu_context_hash64.c b/arch/powerpc/mm/mmu_context_hash64.c new file mode 100644 index 00000000000..dbeb86ac90c --- /dev/null +++ b/arch/powerpc/mm/mmu_context_hash64.c @@ -0,0 +1,78 @@ +/* + * MMU context allocation for 64-bit kernels. + * + * Copyright (C) 2004 Anton Blanchard, IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +static DEFINE_SPINLOCK(mmu_context_lock); +static DEFINE_IDR(mmu_context_idr); + +/* + * The proto-VSID space has 2^35 - 1 segments available for user mappings. + * Each segment contains 2^28 bytes. Each context maps 2^44 bytes, + * so we can support 2^19-1 contexts (19 == 35 + 28 - 44). + */ +#define NO_CONTEXT 0 +#define MAX_CONTEXT ((1UL << 19) - 1) + +int init_new_context(struct task_struct *tsk, struct mm_struct *mm) +{ + int index; + int err; + +again: + if (!idr_pre_get(&mmu_context_idr, GFP_KERNEL)) + return -ENOMEM; + + spin_lock(&mmu_context_lock); + err = idr_get_new_above(&mmu_context_idr, NULL, 1, &index); + spin_unlock(&mmu_context_lock); + + if (err == -EAGAIN) + goto again; + else if (err) + return err; + + if (index > MAX_CONTEXT) { + spin_lock(&mmu_context_lock); + idr_remove(&mmu_context_idr, index); + spin_unlock(&mmu_context_lock); + return -ENOMEM; + } + + /* The old code would re-promote on fork, we don't do that + * when using slices as it could cause problem promoting slices + * that have been forced down to 4K + */ + if (slice_mm_new_context(mm)) + slice_set_user_psize(mm, mmu_virtual_psize); + mm->context.id = index; + + return 0; +} + +void destroy_context(struct mm_struct *mm) +{ + spin_lock(&mmu_context_lock); + idr_remove(&mmu_context_idr, mm->context.id); + spin_unlock(&mmu_context_lock); + + mm->context.id = NO_CONTEXT; +} diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c new file mode 100644 index 00000000000..00e02150abe --- /dev/null +++ b/arch/powerpc/mm/mmu_context_nohash.c @@ -0,0 +1,162 @@ +/* + * This file contains the routines for handling the MMU on those + * PowerPC implementations where the MMU is not using the hash + * table, such as 8xx, 4xx, BookE's etc... + * + * Copyright 2008 Ben Herrenschmidt + * IBM Corp. + * + * Derived from previous arch/powerpc/mm/mmu_context.c + * and arch/powerpc/include/asm/mmu_context.h + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + */ + +#include +#include + +#include +#include + +/* + * The MPC8xx has only 16 contexts. We rotate through them on each + * task switch. A better way would be to keep track of tasks that + * own contexts, and implement an LRU usage. That way very active + * tasks don't always have to pay the TLB reload overhead. The + * kernel pages are mapped shared, so the kernel can run on behalf + * of any task that makes a kernel entry. Shared does not mean they + * are not protected, just that the ASID comparison is not performed. + * -- Dan + * + * The IBM4xx has 256 contexts, so we can just rotate through these + * as a way of "switching" contexts. If the TID of the TLB is zero, + * the PID/TID comparison is disabled, so we can use a TID of zero + * to represent all kernel pages as shared among all contexts. + * -- Dan + */ + +#ifdef CONFIG_8xx +#define NO_CONTEXT 16 +#define LAST_CONTEXT 15 +#define FIRST_CONTEXT 0 + +#elif defined(CONFIG_4xx) +#define NO_CONTEXT 256 +#define LAST_CONTEXT 255 +#define FIRST_CONTEXT 1 + +#elif defined(CONFIG_E200) || defined(CONFIG_E500) +#define NO_CONTEXT 256 +#define LAST_CONTEXT 255 +#define FIRST_CONTEXT 1 + +#else +#error Unsupported processor type +#endif + +static unsigned long next_mmu_context; +static unsigned long context_map[LAST_CONTEXT / BITS_PER_LONG + 1]; +static atomic_t nr_free_contexts; +static struct mm_struct *context_mm[LAST_CONTEXT+1]; +static void steal_context(void); + +/* Steal a context from a task that has one at the moment. + * This is only used on 8xx and 4xx and we presently assume that + * they don't do SMP. If they do then this will have to check + * whether the MM we steal is in use. + * We also assume that this is only used on systems that don't + * use an MMU hash table - this is true for 8xx and 4xx. + * This isn't an LRU system, it just frees up each context in + * turn (sort-of pseudo-random replacement :). This would be the + * place to implement an LRU scheme if anyone was motivated to do it. + * -- paulus + */ +static void steal_context(void) +{ + struct mm_struct *mm; + + /* free up context `next_mmu_context' */ + /* if we shouldn't free context 0, don't... */ + if (next_mmu_context < FIRST_CONTEXT) + next_mmu_context = FIRST_CONTEXT; + mm = context_mm[next_mmu_context]; + flush_tlb_mm(mm); + destroy_context(mm); +} + + +/* + * Get a new mmu context for the address space described by `mm'. + */ +static inline void get_mmu_context(struct mm_struct *mm) +{ + unsigned long ctx; + + if (mm->context.id != NO_CONTEXT) + return; + + while (atomic_dec_if_positive(&nr_free_contexts) < 0) + steal_context(); + + ctx = next_mmu_context; + while (test_and_set_bit(ctx, context_map)) { + ctx = find_next_zero_bit(context_map, LAST_CONTEXT+1, ctx); + if (ctx > LAST_CONTEXT) + ctx = 0; + } + next_mmu_context = (ctx + 1) & LAST_CONTEXT; + mm->context.id = ctx; + context_mm[ctx] = mm; +} + +void switch_mmu_context(struct mm_struct *prev, struct mm_struct *next) +{ + get_mmu_context(next); + + set_context(next->context.id, next->pgd); +} + +/* + * Set up the context for a new address space. + */ +int init_new_context(struct task_struct *t, struct mm_struct *mm) +{ + mm->context.id = NO_CONTEXT; + return 0; +} + +/* + * We're finished using the context for an address space. + */ +void destroy_context(struct mm_struct *mm) +{ + preempt_disable(); + if (mm->context.id != NO_CONTEXT) { + clear_bit(mm->context.id, context_map); + mm->context.id = NO_CONTEXT; + atomic_inc(&nr_free_contexts); + } + preempt_enable(); +} + + +/* + * Initialize the context management stuff. + */ +void __init mmu_context_init(void) +{ + /* + * Some processors have too few contexts to reserve one for + * init_mm, and require using context 0 for a normal task. + * Other processors reserve the use of context zero for the kernel. + * This code assumes FIRST_CONTEXT < 32. + */ + context_map[0] = (1 << FIRST_CONTEXT) - 1; + next_mmu_context = FIRST_CONTEXT; + atomic_set(&nr_free_contexts, LAST_CONTEXT - FIRST_CONTEXT + 1); +} + diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 548efa55c8f..db61dafb924 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -195,13 +195,21 @@ config SPE config PPC_STD_MMU bool - depends on 6xx || POWER3 || POWER4 || PPC64 + depends on 6xx || PPC64 default y config PPC_STD_MMU_32 def_bool y depends on PPC_STD_MMU && PPC32 +config PPC_STD_MMU_64 + def_bool y + depends on PPC_STD_MMU && PPC64 + +config PPC_MMU_NOHASH + def_bool y + depends on !PPC_STD_MMU + config PPC_MM_SLICES bool default y if HUGETLB_PAGE || PPC_64K_PAGES diff --git a/arch/powerpc/platforms/powermac/cpufreq_32.c b/arch/powerpc/platforms/powermac/cpufreq_32.c index 792d3ce8112..65c585b8b00 100644 --- a/arch/powerpc/platforms/powermac/cpufreq_32.c +++ b/arch/powerpc/platforms/powermac/cpufreq_32.c @@ -310,7 +310,7 @@ static int pmu_set_cpu_speed(int low_speed) _set_L3CR(save_l3cr); /* Restore userland MMU context */ - set_context(current->active_mm->context.id, current->active_mm->pgd); + switch_mmu_context(NULL, current->active_mm); #ifdef DEBUG_FREQ printk(KERN_DEBUG "HID1, after: %x\n", mfspr(SPRN_HID1)); diff --git a/drivers/macintosh/via-pmu.c b/drivers/macintosh/via-pmu.c index d524dc245a2..b40fb9b6c86 100644 --- a/drivers/macintosh/via-pmu.c +++ b/drivers/macintosh/via-pmu.c @@ -1814,7 +1814,7 @@ static int powerbook_sleep_grackle(void) _set_L2CR(save_l2cr); /* Restore userland MMU context */ - set_context(current->active_mm->context.id, current->active_mm->pgd); + switch_mmu_context(NULL, current->active_mm); /* Power things up */ pmu_unlock(); @@ -1903,7 +1903,7 @@ powerbook_sleep_Core99(void) _set_L3CR(save_l3cr); /* Restore userland MMU context */ - set_context(current->active_mm->context.id, current->active_mm->pgd); + switch_mmu_context(NULL, current->active_mm); /* Tell PMU we are ready */ pmu_unlock(); -- cgit v1.2.3-70-g09d2 From 7c03d653cd257793dc40520c94e229b5fd0578e7 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Thu, 18 Dec 2008 19:13:32 +0000 Subject: powerpc/mm: Introduce MMU features We're soon running out of CPU features and I need to add some new ones for various MMU related bits, so this patch separates the MMU features from the CPU features. I moved over the 32-bit MMU related ones, added base features for MMU type families, but didn't move over any 64-bit only feature yet. Signed-off-by: Benjamin Herrenschmidt Acked-by: Kumar Gala Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/cputable.h | 85 ++++++++++------------ arch/powerpc/include/asm/feature-fixups.h | 30 ++++++++ arch/powerpc/include/asm/mmu.h | 41 +++++++++++ arch/powerpc/kernel/cputable.c | 113 ++++++++++++++++++++++++++++++ arch/powerpc/kernel/head_32.S | 8 +-- arch/powerpc/kernel/head_fsl_booke.S | 4 +- arch/powerpc/kernel/module.c | 6 ++ arch/powerpc/kernel/setup_32.c | 4 ++ arch/powerpc/kernel/setup_64.c | 2 + arch/powerpc/kernel/swsusp_32.S | 6 +- arch/powerpc/kernel/vdso.c | 10 +++ arch/powerpc/kernel/vdso32/vdso32.lds.S | 3 + arch/powerpc/kernel/vdso64/vdso64.lds.S | 3 + arch/powerpc/kernel/vmlinux.lds.S | 6 ++ arch/powerpc/mm/ppc_mmu_32.c | 2 +- arch/powerpc/platforms/powermac/sleep.S | 5 +- 16 files changed, 268 insertions(+), 60 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index 31888322d76..4911104791c 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -82,6 +82,7 @@ struct cpu_spec { char *cpu_name; unsigned long cpu_features; /* Kernel features */ unsigned int cpu_user_features; /* Userland features */ + unsigned int mmu_features; /* MMU features */ /* cache line sizes */ unsigned int icache_bsize; @@ -144,17 +145,14 @@ extern const char *powerpc_base_platform; #define CPU_FTR_USE_TB ASM_CONST(0x0000000000000040) #define CPU_FTR_L2CSR ASM_CONST(0x0000000000000080) #define CPU_FTR_601 ASM_CONST(0x0000000000000100) -#define CPU_FTR_HPTE_TABLE ASM_CONST(0x0000000000000200) #define CPU_FTR_CAN_NAP ASM_CONST(0x0000000000000400) #define CPU_FTR_L3CR ASM_CONST(0x0000000000000800) #define CPU_FTR_L3_DISABLE_NAP ASM_CONST(0x0000000000001000) #define CPU_FTR_NAP_DISABLE_L2_PR ASM_CONST(0x0000000000002000) #define CPU_FTR_DUAL_PLL_750FX ASM_CONST(0x0000000000004000) #define CPU_FTR_NO_DPM ASM_CONST(0x0000000000008000) -#define CPU_FTR_HAS_HIGH_BATS ASM_CONST(0x0000000000010000) #define CPU_FTR_NEED_COHERENT ASM_CONST(0x0000000000020000) #define CPU_FTR_NO_BTIC ASM_CONST(0x0000000000040000) -#define CPU_FTR_BIG_PHYS ASM_CONST(0x0000000000080000) #define CPU_FTR_NODSISRALIGN ASM_CONST(0x0000000000100000) #define CPU_FTR_PPC_LE ASM_CONST(0x0000000000200000) #define CPU_FTR_REAL_LE ASM_CONST(0x0000000000400000) @@ -266,107 +264,99 @@ extern const char *powerpc_base_platform; !defined(CONFIG_POWER3) && !defined(CONFIG_POWER4) && \ !defined(CONFIG_BOOKE)) -#define CPU_FTRS_PPC601 (CPU_FTR_COMMON | CPU_FTR_601 | CPU_FTR_HPTE_TABLE | \ +#define CPU_FTRS_PPC601 (CPU_FTR_COMMON | CPU_FTR_601 | \ CPU_FTR_COHERENT_ICACHE | CPU_FTR_UNIFIED_ID_CACHE) #define CPU_FTRS_603 (CPU_FTR_COMMON | \ CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | \ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE) #define CPU_FTRS_604 (CPU_FTR_COMMON | \ - CPU_FTR_USE_TB | CPU_FTR_HPTE_TABLE | CPU_FTR_PPC_LE) + CPU_FTR_USE_TB | CPU_FTR_PPC_LE) #define CPU_FTRS_740_NOTAU (CPU_FTR_COMMON | \ CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | CPU_FTR_L2CR | \ - CPU_FTR_HPTE_TABLE | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE) + CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE) #define CPU_FTRS_740 (CPU_FTR_COMMON | \ CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | CPU_FTR_L2CR | \ - CPU_FTR_TAU | CPU_FTR_HPTE_TABLE | CPU_FTR_MAYBE_CAN_NAP | \ + CPU_FTR_TAU | CPU_FTR_MAYBE_CAN_NAP | \ CPU_FTR_PPC_LE) #define CPU_FTRS_750 (CPU_FTR_COMMON | \ CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | CPU_FTR_L2CR | \ - CPU_FTR_TAU | CPU_FTR_HPTE_TABLE | CPU_FTR_MAYBE_CAN_NAP | \ + CPU_FTR_TAU | CPU_FTR_MAYBE_CAN_NAP | \ CPU_FTR_PPC_LE) -#define CPU_FTRS_750CL (CPU_FTRS_750 | CPU_FTR_HAS_HIGH_BATS) +#define CPU_FTRS_750CL (CPU_FTRS_750) #define CPU_FTRS_750FX1 (CPU_FTRS_750 | CPU_FTR_DUAL_PLL_750FX | CPU_FTR_NO_DPM) #define CPU_FTRS_750FX2 (CPU_FTRS_750 | CPU_FTR_NO_DPM) -#define CPU_FTRS_750FX (CPU_FTRS_750 | CPU_FTR_DUAL_PLL_750FX | \ - CPU_FTR_HAS_HIGH_BATS) +#define CPU_FTRS_750FX (CPU_FTRS_750 | CPU_FTR_DUAL_PLL_750FX) #define CPU_FTRS_750GX (CPU_FTRS_750FX) #define CPU_FTRS_7400_NOTAU (CPU_FTR_COMMON | \ CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | CPU_FTR_L2CR | \ - CPU_FTR_ALTIVEC_COMP | CPU_FTR_HPTE_TABLE | \ + CPU_FTR_ALTIVEC_COMP | \ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE) #define CPU_FTRS_7400 (CPU_FTR_COMMON | \ CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | CPU_FTR_L2CR | \ - CPU_FTR_TAU | CPU_FTR_ALTIVEC_COMP | CPU_FTR_HPTE_TABLE | \ + CPU_FTR_TAU | CPU_FTR_ALTIVEC_COMP | \ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE) #define CPU_FTRS_7450_20 (CPU_FTR_COMMON | \ CPU_FTR_USE_TB | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \ - CPU_FTR_L3CR | CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \ + CPU_FTR_L3CR | CPU_FTR_SPEC7450 | \ CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX) #define CPU_FTRS_7450_21 (CPU_FTR_COMMON | \ CPU_FTR_USE_TB | \ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \ - CPU_FTR_L3CR | CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \ + CPU_FTR_L3CR | CPU_FTR_SPEC7450 | \ CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_L3_DISABLE_NAP | \ CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX) #define CPU_FTRS_7450_23 (CPU_FTR_COMMON | \ CPU_FTR_USE_TB | CPU_FTR_NEED_PAIRED_STWCX | \ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \ - CPU_FTR_L3CR | CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \ + CPU_FTR_L3CR | CPU_FTR_SPEC7450 | \ CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE) #define CPU_FTRS_7455_1 (CPU_FTR_COMMON | \ CPU_FTR_USE_TB | CPU_FTR_NEED_PAIRED_STWCX | \ CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | CPU_FTR_L3CR | \ - CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | CPU_FTR_HAS_HIGH_BATS | \ - CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE) + CPU_FTR_SPEC7450 | CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE) #define CPU_FTRS_7455_20 (CPU_FTR_COMMON | \ CPU_FTR_USE_TB | CPU_FTR_NEED_PAIRED_STWCX | \ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \ - CPU_FTR_L3CR | CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \ + CPU_FTR_L3CR | CPU_FTR_SPEC7450 | \ CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_L3_DISABLE_NAP | \ - CPU_FTR_NEED_COHERENT | CPU_FTR_HAS_HIGH_BATS | CPU_FTR_PPC_LE) + CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE) #define CPU_FTRS_7455 (CPU_FTR_COMMON | \ CPU_FTR_USE_TB | \ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \ - CPU_FTR_L3CR | CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \ - CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_HAS_HIGH_BATS | \ + CPU_FTR_L3CR | CPU_FTR_SPEC7450 | CPU_FTR_NAP_DISABLE_L2_PR | \ CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX) #define CPU_FTRS_7447_10 (CPU_FTR_COMMON | \ CPU_FTR_USE_TB | \ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \ - CPU_FTR_L3CR | CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \ - CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_HAS_HIGH_BATS | \ + CPU_FTR_L3CR | CPU_FTR_SPEC7450 | CPU_FTR_NAP_DISABLE_L2_PR | \ CPU_FTR_NEED_COHERENT | CPU_FTR_NO_BTIC | CPU_FTR_PPC_LE | \ CPU_FTR_NEED_PAIRED_STWCX) #define CPU_FTRS_7447 (CPU_FTR_COMMON | \ CPU_FTR_USE_TB | \ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \ - CPU_FTR_L3CR | CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \ - CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_HAS_HIGH_BATS | \ + CPU_FTR_L3CR | CPU_FTR_SPEC7450 | CPU_FTR_NAP_DISABLE_L2_PR | \ CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX) #define CPU_FTRS_7447A (CPU_FTR_COMMON | \ CPU_FTR_USE_TB | \ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \ - CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \ - CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_HAS_HIGH_BATS | \ + CPU_FTR_SPEC7450 | CPU_FTR_NAP_DISABLE_L2_PR | \ CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX) #define CPU_FTRS_7448 (CPU_FTR_COMMON | \ CPU_FTR_USE_TB | \ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \ - CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \ - CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_HAS_HIGH_BATS | \ + CPU_FTR_SPEC7450 | CPU_FTR_NAP_DISABLE_L2_PR | \ CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX) #define CPU_FTRS_82XX (CPU_FTR_COMMON | \ CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB) #define CPU_FTRS_G2_LE (CPU_FTR_COMMON | CPU_FTR_MAYBE_CAN_DOZE | \ - CPU_FTR_USE_TB | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_HAS_HIGH_BATS) + CPU_FTR_USE_TB | CPU_FTR_MAYBE_CAN_NAP) #define CPU_FTRS_E300 (CPU_FTR_MAYBE_CAN_DOZE | \ - CPU_FTR_USE_TB | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_HAS_HIGH_BATS | \ + CPU_FTR_USE_TB | CPU_FTR_MAYBE_CAN_NAP | \ CPU_FTR_COMMON) #define CPU_FTRS_E300C2 (CPU_FTR_MAYBE_CAN_DOZE | \ - CPU_FTR_USE_TB | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_HAS_HIGH_BATS | \ + CPU_FTR_USE_TB | CPU_FTR_MAYBE_CAN_NAP | \ CPU_FTR_COMMON | CPU_FTR_FPU_UNAVAILABLE) -#define CPU_FTRS_CLASSIC32 (CPU_FTR_COMMON | \ - CPU_FTR_USE_TB | CPU_FTR_HPTE_TABLE) +#define CPU_FTRS_CLASSIC32 (CPU_FTR_COMMON | CPU_FTR_USE_TB) #define CPU_FTRS_8XX (CPU_FTR_USE_TB) #define CPU_FTRS_40X (CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE) #define CPU_FTRS_44X (CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE) @@ -379,55 +369,54 @@ extern const char *powerpc_base_platform; CPU_FTR_SPE_COMP | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_NODSISRALIGN | \ CPU_FTR_NOEXECUTE) #define CPU_FTRS_E500_2 (CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | \ - CPU_FTR_SPE_COMP | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_BIG_PHYS | \ + CPU_FTR_SPE_COMP | CPU_FTR_MAYBE_CAN_NAP | \ CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE) #define CPU_FTRS_E500MC (CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | \ - CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_BIG_PHYS | CPU_FTR_NODSISRALIGN | \ + CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_NODSISRALIGN | \ CPU_FTR_L2CSR | CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE) #define CPU_FTRS_GENERIC_32 (CPU_FTR_COMMON | CPU_FTR_NODSISRALIGN) /* 64-bit CPUs */ #define CPU_FTRS_POWER3 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ - CPU_FTR_HPTE_TABLE | CPU_FTR_IABR | CPU_FTR_PPC_LE) + CPU_FTR_IABR | CPU_FTR_PPC_LE) #define CPU_FTRS_RS64 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ - CPU_FTR_HPTE_TABLE | CPU_FTR_IABR | \ + CPU_FTR_IABR | \ CPU_FTR_MMCRA | CPU_FTR_CTRL) #define CPU_FTRS_POWER4 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ - CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ + CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ CPU_FTR_MMCRA | CPU_FTR_CP_USE_DCBTZ) #define CPU_FTRS_PPC970 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ - CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ + CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ CPU_FTR_ALTIVEC_COMP | CPU_FTR_CAN_NAP | CPU_FTR_MMCRA | \ CPU_FTR_CP_USE_DCBTZ) #define CPU_FTRS_POWER5 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ - CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ + CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ CPU_FTR_MMCRA | CPU_FTR_SMT | \ CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \ CPU_FTR_PURR) #define CPU_FTRS_POWER6 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ - CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ + CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ CPU_FTR_MMCRA | CPU_FTR_SMT | \ CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \ CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \ CPU_FTR_DSCR | CPU_FTR_UNALIGNED_LD_STD) #define CPU_FTRS_POWER7 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ - CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ + CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ CPU_FTR_MMCRA | CPU_FTR_SMT | \ CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \ CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \ CPU_FTR_DSCR | CPU_FTR_SAO) #define CPU_FTRS_CELL (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ - CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ + CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \ CPU_FTR_PAUSE_ZERO | CPU_FTR_CI_LARGE_PAGE | \ CPU_FTR_CELL_TB_BUG | CPU_FTR_CP_USE_DCBTZ | \ CPU_FTR_UNALIGNED_LD_STD) #define CPU_FTRS_PA6T (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ - CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | \ + CPU_FTR_PPCAS_ARCH_V2 | \ CPU_FTR_ALTIVEC_COMP | CPU_FTR_CI_LARGE_PAGE | \ CPU_FTR_PURR | CPU_FTR_REAL_LE | CPU_FTR_NO_SLBIE_B) -#define CPU_FTRS_COMPATIBLE (CPU_FTR_USE_TB | \ - CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2) +#define CPU_FTRS_COMPATIBLE (CPU_FTR_USE_TB | CPU_FTR_PPCAS_ARCH_V2) #ifdef __powerpc64__ #define CPU_FTRS_POSSIBLE \ diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h index a1029967620..e4094a5cb05 100644 --- a/arch/powerpc/include/asm/feature-fixups.h +++ b/arch/powerpc/include/asm/feature-fixups.h @@ -81,6 +81,36 @@ label##5: \ #define ALT_FTR_SECTION_END_IFCLR(msk) \ ALT_FTR_SECTION_END_NESTED_IFCLR(msk, 97) +/* MMU feature dependent sections */ +#define BEGIN_MMU_FTR_SECTION_NESTED(label) START_FTR_SECTION(label) +#define BEGIN_MMU_FTR_SECTION START_FTR_SECTION(97) + +#define END_MMU_FTR_SECTION_NESTED(msk, val, label) \ + FTR_SECTION_ELSE_NESTED(label) \ + MAKE_FTR_SECTION_ENTRY(msk, val, label, __mmu_ftr_fixup) + +#define END_MMU_FTR_SECTION(msk, val) \ + END_MMU_FTR_SECTION_NESTED(msk, val, 97) + +#define END_MMU_FTR_SECTION_IFSET(msk) END_MMU_FTR_SECTION((msk), (msk)) +#define END_MMU_FTR_SECTION_IFCLR(msk) END_MMU_FTR_SECTION((msk), 0) + +/* MMU feature sections with alternatives, use BEGIN_FTR_SECTION to start */ +#define MMU_FTR_SECTION_ELSE_NESTED(label) FTR_SECTION_ELSE_NESTED(label) +#define MMU_FTR_SECTION_ELSE MMU_FTR_SECTION_ELSE_NESTED(97) +#define ALT_MMU_FTR_SECTION_END_NESTED(msk, val, label) \ + MAKE_FTR_SECTION_ENTRY(msk, val, label, __mmu_ftr_fixup) +#define ALT_MMU_FTR_SECTION_END_NESTED_IFSET(msk, label) \ + ALT_MMU_FTR_SECTION_END_NESTED(msk, msk, label) +#define ALT_MMU_FTR_SECTION_END_NESTED_IFCLR(msk, label) \ + ALT_MMU_FTR_SECTION_END_NESTED(msk, 0, label) +#define ALT_MMU_FTR_SECTION_END(msk, val) \ + ALT_MMU_FTR_SECTION_END_NESTED(msk, val, 97) +#define ALT_MMU_FTR_SECTION_END_IFSET(msk) \ + ALT_MMU_FTR_SECTION_END_NESTED_IFSET(msk, 97) +#define ALT_MMU_FTR_SECTION_END_IFCLR(msk) \ + ALT_MMU_FTR_SECTION_END_NESTED_IFCLR(msk, 97) + /* Firmware feature dependent sections */ #define BEGIN_FW_FTR_SECTION_NESTED(label) START_FTR_SECTION(label) #define BEGIN_FW_FTR_SECTION START_FTR_SECTION(97) diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index 4c0e1b4f975..dc8c0aef5e6 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -2,6 +2,47 @@ #define _ASM_POWERPC_MMU_H_ #ifdef __KERNEL__ +#include +#include + +/* + * MMU features bit definitions + */ + +/* + * First half is MMU families + */ +#define MMU_FTR_HPTE_TABLE ASM_CONST(0x00000001) +#define MMU_FTR_TYPE_8xx ASM_CONST(0x00000002) +#define MMU_FTR_TYPE_40x ASM_CONST(0x00000004) +#define MMU_FTR_TYPE_44x ASM_CONST(0x00000008) +#define MMU_FTR_TYPE_FSL_E ASM_CONST(0x00000010) + +/* + * This is individual features + */ + +/* Enable use of high BAT registers */ +#define MMU_FTR_USE_HIGH_BATS ASM_CONST(0x00010000) + +/* Enable >32-bit physical addresses on 32-bit processor, only used + * by CONFIG_6xx currently as BookE supports that from day 1 + */ +#define MMU_FTR_BIG_PHYS ASM_CONST(0x00020000) + +#ifndef __ASSEMBLY__ +#include + +static inline int mmu_has_feature(unsigned long feature) +{ + return (cur_cpu_spec->mmu_features & feature); +} + +extern unsigned int __start___mmu_ftr_fixup, __stop___mmu_ftr_fixup; + +#endif /* !__ASSEMBLY__ */ + + #ifdef CONFIG_PPC64 /* 64-bit classic hash table MMU */ # include diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 921a2298d8e..923f87aff20 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -19,6 +19,7 @@ #include #include #include /* for PTRRELOC on ARCH=ppc */ +#include struct cpu_spec* cur_cpu_spec = NULL; EXPORT_SYMBOL(cur_cpu_spec); @@ -94,6 +95,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER3 (630)", .cpu_features = CPU_FTRS_POWER3, .cpu_user_features = COMMON_USER_PPC64|PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -109,6 +111,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER3 (630+)", .cpu_features = CPU_FTRS_POWER3, .cpu_user_features = COMMON_USER_PPC64|PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -124,6 +127,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "RS64-II (northstar)", .cpu_features = CPU_FTRS_RS64, .cpu_user_features = COMMON_USER_PPC64, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -139,6 +143,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "RS64-III (pulsar)", .cpu_features = CPU_FTRS_RS64, .cpu_user_features = COMMON_USER_PPC64, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -154,6 +159,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "RS64-III (icestar)", .cpu_features = CPU_FTRS_RS64, .cpu_user_features = COMMON_USER_PPC64, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -169,6 +175,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "RS64-IV (sstar)", .cpu_features = CPU_FTRS_RS64, .cpu_user_features = COMMON_USER_PPC64, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -184,6 +191,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER4 (gp)", .cpu_features = CPU_FTRS_POWER4, .cpu_user_features = COMMON_USER_POWER4, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -199,6 +207,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER4+ (gq)", .cpu_features = CPU_FTRS_POWER4, .cpu_user_features = COMMON_USER_POWER4, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -215,6 +224,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_PPC970, .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -233,6 +243,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_PPC970, .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -251,6 +262,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_PPC970, .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -269,6 +281,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_PPC970, .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -287,6 +300,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_PPC970, .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 8, @@ -303,6 +317,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER5 (gr)", .cpu_features = CPU_FTRS_POWER5, .cpu_user_features = COMMON_USER_POWER5, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, @@ -323,6 +338,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER5+ (gs)", .cpu_features = CPU_FTRS_POWER5, .cpu_user_features = COMMON_USER_POWER5_PLUS, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, @@ -339,6 +355,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER5+ (gs)", .cpu_features = CPU_FTRS_POWER5, .cpu_user_features = COMMON_USER_POWER5_PLUS, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, @@ -356,6 +373,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER5+", .cpu_features = CPU_FTRS_POWER5, .cpu_user_features = COMMON_USER_POWER5_PLUS, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 128, .dcache_bsize = 128, .machine_check = machine_check_generic, @@ -369,6 +387,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_POWER6, .cpu_user_features = COMMON_USER_POWER6 | PPC_FEATURE_POWER6_EXT, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, @@ -388,6 +407,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER6 (architected)", .cpu_features = CPU_FTRS_POWER6, .cpu_user_features = COMMON_USER_POWER6, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 128, .dcache_bsize = 128, .machine_check = machine_check_generic, @@ -400,6 +420,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER7 (architected)", .cpu_features = CPU_FTRS_POWER7, .cpu_user_features = COMMON_USER_POWER7, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 128, .dcache_bsize = 128, .machine_check = machine_check_generic, @@ -412,6 +433,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER7 (raw)", .cpu_features = CPU_FTRS_POWER7, .cpu_user_features = COMMON_USER_POWER7, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, @@ -434,6 +456,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_user_features = COMMON_USER_PPC64 | PPC_FEATURE_CELL | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_SMT, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 4, @@ -449,6 +472,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "PA6T", .cpu_features = CPU_FTRS_PA6T, .cpu_user_features = COMMON_USER_PA6T, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 64, .dcache_bsize = 64, .num_pmcs = 6, @@ -466,6 +490,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "POWER4 (compatible)", .cpu_features = CPU_FTRS_COMPATIBLE, .cpu_user_features = COMMON_USER_PPC64, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 128, .dcache_bsize = 128, .num_pmcs = 6, @@ -483,6 +508,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_PPC601, .cpu_user_features = COMMON_USER | PPC_FEATURE_601_INSTR | PPC_FEATURE_UNIFIED_CACHE | PPC_FEATURE_NO_TB, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_generic, @@ -494,6 +520,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "603", .cpu_features = CPU_FTRS_603, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = 0, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_603, @@ -506,6 +533,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "603e", .cpu_features = CPU_FTRS_603, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = 0, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_603, @@ -518,6 +546,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "603ev", .cpu_features = CPU_FTRS_603, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = 0, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_603, @@ -530,6 +559,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "604", .cpu_features = CPU_FTRS_604, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 2, @@ -543,6 +573,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "604e", .cpu_features = CPU_FTRS_604, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -556,6 +587,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "604r", .cpu_features = CPU_FTRS_604, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -569,6 +601,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "604ev", .cpu_features = CPU_FTRS_604, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -582,6 +615,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "740/750", .cpu_features = CPU_FTRS_740_NOTAU, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -595,6 +629,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "750CX", .cpu_features = CPU_FTRS_750, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -608,6 +643,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "750CX", .cpu_features = CPU_FTRS_750, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -622,6 +658,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "750CXe", .cpu_features = CPU_FTRS_750, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -636,6 +673,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "750CXe", .cpu_features = CPU_FTRS_750, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -650,6 +688,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "750CL", .cpu_features = CPU_FTRS_750CL, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -664,6 +703,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "745/755", .cpu_features = CPU_FTRS_750, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -678,6 +718,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "750FX", .cpu_features = CPU_FTRS_750FX1, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -692,6 +733,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "750FX", .cpu_features = CPU_FTRS_750FX2, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -706,6 +748,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "750FX", .cpu_features = CPU_FTRS_750FX, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -720,6 +763,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "750GX", .cpu_features = CPU_FTRS_750GX, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -734,6 +778,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "740/750", .cpu_features = CPU_FTRS_740, .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -749,6 +794,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_7400_NOTAU, .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -764,6 +810,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_7400, .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -779,6 +826,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_7400, .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -794,6 +842,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_7450_20, .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 6, @@ -811,6 +860,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_7450_21, .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 6, @@ -828,6 +878,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_7450_23, .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 6, @@ -845,6 +896,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_7455_1, .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 6, @@ -862,6 +914,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_7455_20, .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 6, @@ -879,6 +932,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_7455, .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 6, @@ -896,6 +950,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_7447_10, .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 6, @@ -913,6 +968,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_7447_10, .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 6, @@ -929,6 +985,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "7447/7457", .cpu_features = CPU_FTRS_7447, .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 6, @@ -946,6 +1003,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_7447A, .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 6, @@ -963,6 +1021,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_7448, .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_PPC_LE, + .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 6, @@ -979,6 +1038,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "82xx", .cpu_features = CPU_FTRS_82XX, .cpu_user_features = COMMON_USER, + .mmu_features = 0, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_603, @@ -991,6 +1051,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "G2_LE", .cpu_features = CPU_FTRS_G2_LE, .cpu_user_features = COMMON_USER, + .mmu_features = MMU_FTR_USE_HIGH_BATS, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_603, @@ -1003,6 +1064,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "e300c1", .cpu_features = CPU_FTRS_E300, .cpu_user_features = COMMON_USER, + .mmu_features = MMU_FTR_USE_HIGH_BATS, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_603, @@ -1015,6 +1077,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "e300c2", .cpu_features = CPU_FTRS_E300C2, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, + .mmu_features = MMU_FTR_USE_HIGH_BATS, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_603, @@ -1027,6 +1090,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "e300c3", .cpu_features = CPU_FTRS_E300, .cpu_user_features = COMMON_USER, + .mmu_features = MMU_FTR_USE_HIGH_BATS, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_603, @@ -1041,6 +1105,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "e300c4", .cpu_features = CPU_FTRS_E300, .cpu_user_features = COMMON_USER, + .mmu_features = MMU_FTR_USE_HIGH_BATS, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_603, @@ -1056,6 +1121,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "(generic PPC)", .cpu_features = CPU_FTRS_CLASSIC32, .cpu_user_features = COMMON_USER, + .mmu_features = MMU_FTR_HPTE_TABLE, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_generic, @@ -1071,6 +1137,7 @@ static struct cpu_spec __initdata cpu_specs[] = { * if the 8xx code is there.... */ .cpu_features = CPU_FTRS_8XX, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, + .mmu_features = MMU_FTR_TYPE_8xx, .icache_bsize = 16, .dcache_bsize = 16, .platform = "ppc823", @@ -1083,6 +1150,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "403GC", .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 16, .dcache_bsize = 16, .machine_check = machine_check_4xx, @@ -1095,6 +1163,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | PPC_FEATURE_NO_TB, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 16, .dcache_bsize = 16, .machine_check = machine_check_4xx, @@ -1106,6 +1175,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "403G ??", .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 16, .dcache_bsize = 16, .machine_check = machine_check_4xx, @@ -1118,6 +1188,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1130,6 +1201,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1142,6 +1214,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1154,6 +1227,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1166,6 +1240,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1178,6 +1253,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1190,6 +1266,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1202,6 +1279,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1213,6 +1291,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "405LP", .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1225,6 +1304,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1237,6 +1317,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1249,6 +1330,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1261,6 +1343,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1273,6 +1356,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1286,6 +1370,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1298,6 +1383,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_40X, .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, + .mmu_features = MMU_FTR_TYPE_40x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1312,6 +1398,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "440GR Rev. A", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1323,6 +1410,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "440EP Rev. A", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_440ep, @@ -1335,6 +1423,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "440GR Rev. B", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1346,6 +1435,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "440EP Rev. C", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_440ep, @@ -1358,6 +1448,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "440EP Rev. B", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_440ep, @@ -1370,6 +1461,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "440GRX", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_440grx, @@ -1382,6 +1474,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "440EPX", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_440epx, @@ -1394,6 +1487,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "440GP Rev. B", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1405,6 +1499,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "440GP Rev. C", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1416,6 +1511,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "440GX Rev. A", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_440gx, @@ -1428,6 +1524,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "440GX Rev. B", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_440gx, @@ -1440,6 +1537,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "440GX Rev. C", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_440gx, @@ -1452,6 +1550,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "440GX Rev. F", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_440gx, @@ -1464,6 +1563,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "440SP Rev. A", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1475,6 +1575,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "440SPe Rev. A", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_440spe, @@ -1487,6 +1588,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "440SPe Rev. B", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_440spe, @@ -1499,6 +1601,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "440 in Virtex-5 FXT", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_440x5, @@ -1511,6 +1614,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "460EX", .cpu_features = CPU_FTRS_440x6, .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_460ex, @@ -1523,6 +1627,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "460GT", .cpu_features = CPU_FTRS_440x6, .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .cpu_setup = __setup_cpu_460gt, @@ -1535,6 +1640,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "(generic 44x PPC)", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE, + .mmu_features = MMU_FTR_TYPE_44x, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_4xx, @@ -1551,6 +1657,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_EFP_SINGLE | PPC_FEATURE_UNIFIED_CACHE, + .mmu_features = MMU_FTR_TYPE_FSL_E, .dcache_bsize = 32, .machine_check = machine_check_e200, .platform = "ppc5554", @@ -1565,6 +1672,7 @@ static struct cpu_spec __initdata cpu_specs[] = { PPC_FEATURE_HAS_SPE_COMP | PPC_FEATURE_HAS_EFP_SINGLE_COMP | PPC_FEATURE_UNIFIED_CACHE, + .mmu_features = MMU_FTR_TYPE_FSL_E, .dcache_bsize = 32, .machine_check = machine_check_e200, .platform = "ppc5554", @@ -1577,6 +1685,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_EFP_SINGLE | PPC_FEATURE_UNIFIED_CACHE, + .mmu_features = MMU_FTR_TYPE_FSL_E, .dcache_bsize = 32, .machine_check = machine_check_e200, .platform = "ppc5554", @@ -1591,6 +1700,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_SPE_COMP | PPC_FEATURE_HAS_EFP_SINGLE_COMP, + .mmu_features = MMU_FTR_TYPE_FSL_E, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -1608,6 +1718,7 @@ static struct cpu_spec __initdata cpu_specs[] = { PPC_FEATURE_HAS_SPE_COMP | PPC_FEATURE_HAS_EFP_SINGLE_COMP | PPC_FEATURE_HAS_EFP_DOUBLE_COMP, + .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, @@ -1622,6 +1733,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_name = "e500mc", .cpu_features = CPU_FTRS_E500MC, .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, + .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS, .icache_bsize = 64, .dcache_bsize = 64, .num_pmcs = 4, @@ -1638,6 +1750,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_SPE_COMP | PPC_FEATURE_HAS_EFP_SINGLE_COMP, + .mmu_features = MMU_FTR_TYPE_FSL_E, .icache_bsize = 32, .dcache_bsize = 32, .machine_check = machine_check_e500, diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index be9f9e5470e..26606192465 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -990,12 +990,12 @@ load_up_mmu: LOAD_BAT(1,r3,r4,r5) LOAD_BAT(2,r3,r4,r5) LOAD_BAT(3,r3,r4,r5) -BEGIN_FTR_SECTION +BEGIN_MMU_FTR_SECTION LOAD_BAT(4,r3,r4,r5) LOAD_BAT(5,r3,r4,r5) LOAD_BAT(6,r3,r4,r5) LOAD_BAT(7,r3,r4,r5) -END_FTR_SECTION_IFSET(CPU_FTR_HAS_HIGH_BATS) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) blr /* @@ -1141,7 +1141,7 @@ clear_bats: mtspr SPRN_IBAT2L,r10 mtspr SPRN_IBAT3U,r10 mtspr SPRN_IBAT3L,r10 -BEGIN_FTR_SECTION +BEGIN_MMU_FTR_SECTION /* Here's a tweak: at this point, CPU setup have * not been called yet, so HIGH_BAT_EN may not be * set in HID0 for the 745x processors. However, it @@ -1164,7 +1164,7 @@ BEGIN_FTR_SECTION mtspr SPRN_IBAT6L,r10 mtspr SPRN_IBAT7U,r10 mtspr SPRN_IBAT7L,r10 -END_FTR_SECTION_IFSET(CPU_FTR_HAS_HIGH_BATS) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) blr flush_tlbs: diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S index 9a4639c459e..11b549acc03 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -767,10 +767,10 @@ finish_tlb_load: rlwimi r12, r13, 24, 0, 7 /* grab RPN[32:39] */ rlwimi r12, r11, 24, 8, 19 /* grab RPN[40:51] */ mtspr SPRN_MAS3, r12 -BEGIN_FTR_SECTION +BEGIN_MMU_FTR_SECTION srwi r10, r13, 8 /* grab RPN[8:31] */ mtspr SPRN_MAS7, r10 -END_FTR_SECTION_IFSET(CPU_FTR_BIG_PHYS) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_BIG_PHYS) #else rlwimi r11, r12, 0, 20, 31 /* Extract RPN from PTE and merge with perms */ mtspr SPRN_MAS3, r11 diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c index 7ff29247526..43e7e3a7f13 100644 --- a/arch/powerpc/kernel/module.c +++ b/arch/powerpc/kernel/module.c @@ -78,6 +78,12 @@ int module_finalize(const Elf_Ehdr *hdr, (void *)sect->sh_addr, (void *)sect->sh_addr + sect->sh_size); + sect = find_section(hdr, sechdrs, "__mmu_ftr_fixup"); + if (sect != NULL) + do_feature_fixups(cur_cpu_spec->mmu_features, + (void *)sect->sh_addr, + (void *)sect->sh_addr + sect->sh_size); + #ifdef CONFIG_PPC64 sect = find_section(hdr, sechdrs, "__fw_ftr_fixup"); if (sect != NULL) diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 086c23c1ee5..b14c2a3e218 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -97,6 +97,10 @@ notrace unsigned long __init early_init(unsigned long dt_ptr) PTRRELOC(&__start___ftr_fixup), PTRRELOC(&__stop___ftr_fixup)); + do_feature_fixups(spec->mmu_features, + PTRRELOC(&__start___mmu_ftr_fixup), + PTRRELOC(&__stop___mmu_ftr_fixup)); + do_lwsync_fixups(spec->cpu_features, PTRRELOC(&__start___lwsync_fixup), PTRRELOC(&__stop___lwsync_fixup)); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index ce48f5c5c54..d8bd2161e73 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -361,6 +361,8 @@ void __init setup_system(void) */ do_feature_fixups(cur_cpu_spec->cpu_features, &__start___ftr_fixup, &__stop___ftr_fixup); + do_feature_fixups(cur_cpu_spec->mmu_features, + &__start___mmu_ftr_fixup, &__stop___mmu_ftr_fixup); do_feature_fixups(powerpc_firmware_features, &__start___fw_ftr_fixup, &__stop___fw_ftr_fixup); do_lwsync_fixups(cur_cpu_spec->cpu_features, diff --git a/arch/powerpc/kernel/swsusp_32.S b/arch/powerpc/kernel/swsusp_32.S index 77fc76607ab..b47d8ceffb5 100644 --- a/arch/powerpc/kernel/swsusp_32.S +++ b/arch/powerpc/kernel/swsusp_32.S @@ -5,7 +5,7 @@ #include #include #include - +#include /* * Structure for storing CPU registers on the save area. @@ -279,7 +279,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) mtibatl 3,r4 #endif -BEGIN_FTR_SECTION +BEGIN_MMU_FTR_SECTION li r4,0 mtspr SPRN_DBAT4U,r4 mtspr SPRN_DBAT4L,r4 @@ -297,7 +297,7 @@ BEGIN_FTR_SECTION mtspr SPRN_IBAT6L,r4 mtspr SPRN_IBAT7U,r4 mtspr SPRN_IBAT7L,r4 -END_FTR_SECTION_IFSET(CPU_FTR_HAS_HIGH_BATS) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) /* Flush all TLBs */ lis r4,0x1000 diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index 65639a43e64..e619d424f73 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -567,6 +567,11 @@ static __init int vdso_fixup_features(struct lib32_elfinfo *v32, do_feature_fixups(cur_cpu_spec->cpu_features, start64, start64 + size64); + start64 = find_section64(v64->hdr, "__mmu_ftr_fixup", &size64); + if (start64) + do_feature_fixups(cur_cpu_spec->mmu_features, + start64, start64 + size64); + start64 = find_section64(v64->hdr, "__fw_ftr_fixup", &size64); if (start64) do_feature_fixups(powerpc_firmware_features, @@ -583,6 +588,11 @@ static __init int vdso_fixup_features(struct lib32_elfinfo *v32, do_feature_fixups(cur_cpu_spec->cpu_features, start32, start32 + size32); + start32 = find_section32(v32->hdr, "__mmu_ftr_fixup", &size32); + if (start32) + do_feature_fixups(cur_cpu_spec->mmu_features, + start32, start32 + size32); + #ifdef CONFIG_PPC64 start32 = find_section32(v32->hdr, "__fw_ftr_fixup", &size32); if (start32) diff --git a/arch/powerpc/kernel/vdso32/vdso32.lds.S b/arch/powerpc/kernel/vdso32/vdso32.lds.S index be3b6a41dc0..904ef1360dd 100644 --- a/arch/powerpc/kernel/vdso32/vdso32.lds.S +++ b/arch/powerpc/kernel/vdso32/vdso32.lds.S @@ -33,6 +33,9 @@ SECTIONS . = ALIGN(8); __ftr_fixup : { *(__ftr_fixup) } + . = ALIGN(8); + __mmu_ftr_fixup : { *(__mmu_ftr_fixup) } + . = ALIGN(8); __lwsync_fixup : { *(__lwsync_fixup) } diff --git a/arch/powerpc/kernel/vdso64/vdso64.lds.S b/arch/powerpc/kernel/vdso64/vdso64.lds.S index d0b2526dd38..0e615404e24 100644 --- a/arch/powerpc/kernel/vdso64/vdso64.lds.S +++ b/arch/powerpc/kernel/vdso64/vdso64.lds.S @@ -34,6 +34,9 @@ SECTIONS . = ALIGN(8); __ftr_fixup : { *(__ftr_fixup) } + . = ALIGN(8); + __mmu_ftr_fixup : { *(__mmu_ftr_fixup) } + . = ALIGN(8); __lwsync_fixup : { *(__lwsync_fixup) } diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 2412c056baa..47bf15cd2c9 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -152,6 +152,12 @@ SECTIONS __stop___ftr_fixup = .; } . = ALIGN(8); + __mmu_ftr_fixup : AT(ADDR(__mmu_ftr_fixup) - LOAD_OFFSET) { + __start___mmu_ftr_fixup = .; + *(__mmu_ftr_fixup) + __stop___mmu_ftr_fixup = .; + } + . = ALIGN(8); __lwsync_fixup : AT(ADDR(__lwsync_fixup) - LOAD_OFFSET) { __start___lwsync_fixup = .; *(__lwsync_fixup) diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c index 6aa12081377..9d97db7b7cf 100644 --- a/arch/powerpc/mm/ppc_mmu_32.c +++ b/arch/powerpc/mm/ppc_mmu_32.c @@ -192,7 +192,7 @@ void __init MMU_init_hw(void) extern unsigned int hash_page[]; extern unsigned int flush_hash_patch_A[], flush_hash_patch_B[]; - if (!cpu_has_feature(CPU_FTR_HPTE_TABLE)) { + if (!mmu_has_feature(MMU_FTR_HPTE_TABLE)) { /* * Put a blr (procedure return) instruction at the * start of hash_page, since we can still get DSI diff --git a/arch/powerpc/platforms/powermac/sleep.S b/arch/powerpc/platforms/powermac/sleep.S index adee28da353..1c2802fabd5 100644 --- a/arch/powerpc/platforms/powermac/sleep.S +++ b/arch/powerpc/platforms/powermac/sleep.S @@ -17,6 +17,7 @@ #include #include #include +#include #define MAGIC 0x4c617273 /* 'Lars' */ @@ -323,7 +324,7 @@ grackle_wake_up: lwz r4,SL_IBAT3+4(r1) mtibatl 3,r4 -BEGIN_FTR_SECTION +BEGIN_MMU_FTR_SECTION li r4,0 mtspr SPRN_DBAT4U,r4 mtspr SPRN_DBAT4L,r4 @@ -341,7 +342,7 @@ BEGIN_FTR_SECTION mtspr SPRN_IBAT6L,r4 mtspr SPRN_IBAT7U,r4 mtspr SPRN_IBAT7L,r4 -END_FTR_SECTION_IFSET(CPU_FTR_HAS_HIGH_BATS) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) /* Flush all TLBs */ lis r4,0x1000 -- cgit v1.2.3-70-g09d2 From f048aace29e007f2b642097e2da8231e0e9cce2d Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Thu, 18 Dec 2008 19:13:38 +0000 Subject: powerpc/mm: Add SMP support to no-hash TLB handling This commit moves the whole no-hash TLB handling out of line into a new tlb_nohash.c file, and implements some basic SMP support using IPIs and/or broadcast tlbivax instructions. Note that I'm using local invalidations for D->I cache coherency. At worst, if another processor is trying to execute the same and has the old entry in its TLB, it will just take a fault and re-do the TLB flush locally (it won't re-do the cache flush in any case). Signed-off-by: Benjamin Herrenschmidt Acked-by: Kumar Gala Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/highmem.h | 4 +- arch/powerpc/include/asm/mmu.h | 16 +++ arch/powerpc/include/asm/tlbflush.h | 84 +++++++-------- arch/powerpc/kernel/misc_32.S | 9 ++ arch/powerpc/kernel/ppc_ksyms.c | 6 -- arch/powerpc/mm/Makefile | 2 +- arch/powerpc/mm/fault.c | 2 +- arch/powerpc/mm/mem.c | 2 +- arch/powerpc/mm/tlb_hash32.c | 4 + arch/powerpc/mm/tlb_nohash.c | 209 ++++++++++++++++++++++++++++++++++++ 10 files changed, 281 insertions(+), 57 deletions(-) create mode 100644 arch/powerpc/mm/tlb_nohash.c (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/highmem.h b/arch/powerpc/include/asm/highmem.h index 7dc52eca8b6..fd97e501aa6 100644 --- a/arch/powerpc/include/asm/highmem.h +++ b/arch/powerpc/include/asm/highmem.h @@ -85,7 +85,7 @@ static inline void *kmap_atomic_prot(struct page *page, enum km_type type, pgpro BUG_ON(!pte_none(*(kmap_pte-idx))); #endif __set_pte_at(&init_mm, vaddr, kmap_pte-idx, mk_pte(page, prot)); - local_flush_tlb_page(vaddr); + local_flush_tlb_page(NULL, vaddr); return (void*) vaddr; } @@ -113,7 +113,7 @@ static inline void kunmap_atomic(void *kvaddr, enum km_type type) * this pte without first remap it */ pte_clear(&init_mm, vaddr, kmap_pte-idx); - local_flush_tlb_page(vaddr); + local_flush_tlb_page(NULL, vaddr); #endif pagefault_enable(); } diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index dc8c0aef5e6..6e763991131 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -30,6 +30,22 @@ */ #define MMU_FTR_BIG_PHYS ASM_CONST(0x00020000) +/* Enable use of broadcast TLB invalidations. We don't always set it + * on processors that support it due to other constraints with the + * use of such invalidations + */ +#define MMU_FTR_USE_TLBIVAX_BCAST ASM_CONST(0x00040000) + +/* Enable use of tlbilx invalidate-by-PID variant. + */ +#define MMU_FTR_USE_TLBILX_PID ASM_CONST(0x00080000) + +/* This indicates that the processor cannot handle multiple outstanding + * broadcast tlbivax or tlbsync. This makes the code use a spinlock + * around such invalidate forms. + */ +#define MMU_FTR_LOCK_BCAST_INVAL ASM_CONST(0x00100000) + #ifndef __ASSEMBLY__ #include diff --git a/arch/powerpc/include/asm/tlbflush.h b/arch/powerpc/include/asm/tlbflush.h index 9ed363d3de4..8c39b27c1ed 100644 --- a/arch/powerpc/include/asm/tlbflush.h +++ b/arch/powerpc/include/asm/tlbflush.h @@ -6,7 +6,9 @@ * * - flush_tlb_mm(mm) flushes the specified mm context TLB's * - flush_tlb_page(vma, vmaddr) flushes one page - * - local_flush_tlb_page(vmaddr) flushes one page on the local processor + * - local_flush_tlb_mm(mm) flushes the specified mm context on + * the local processor + * - local_flush_tlb_page(vma, vmaddr) flushes one page on the local processor * - flush_tlb_page_nohash(vma, vmaddr) flushes one page if SW loaded TLB * - flush_tlb_range(vma, start, end) flushes a range of pages * - flush_tlb_kernel_range(start, end) flushes a range of kernel pages @@ -18,7 +20,7 @@ */ #ifdef __KERNEL__ -#if defined(CONFIG_4xx) || defined(CONFIG_8xx) || defined(CONFIG_FSL_BOOKE) +#ifdef CONFIG_PPC_MMU_NOHASH /* * TLB flushing for software loaded TLB chips * @@ -31,10 +33,10 @@ #define MMU_NO_CONTEXT ((unsigned int)-1) -extern void _tlbie(unsigned long address, unsigned int pid); extern void _tlbil_all(void); extern void _tlbil_pid(unsigned int pid); extern void _tlbil_va(unsigned long address, unsigned int pid); +extern void _tlbivax_bcast(unsigned long address, unsigned int pid); #if defined(CONFIG_40x) || defined(CONFIG_8xx) #define _tlbia() asm volatile ("tlbia; sync" : : : "memory") @@ -42,48 +44,26 @@ extern void _tlbil_va(unsigned long address, unsigned int pid); extern void _tlbia(void); #endif -static inline void local_flush_tlb_mm(struct mm_struct *mm) -{ - _tlbil_pid(mm->context.id); -} - -static inline void flush_tlb_mm(struct mm_struct *mm) -{ - _tlbil_pid(mm->context.id); -} - -static inline void local_flush_tlb_page(unsigned long vmaddr) -{ - _tlbil_va(vmaddr, 0); -} - -static inline void flush_tlb_page(struct vm_area_struct *vma, - unsigned long vmaddr) -{ - _tlbil_va(vmaddr, vma ? vma->vm_mm->context.id : 0); -} +extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end); +extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); -static inline void flush_tlb_page_nohash(struct vm_area_struct *vma, - unsigned long vmaddr) -{ - flush_tlb_page(vma, vmaddr); -} +extern void local_flush_tlb_mm(struct mm_struct *mm); +extern void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr); -static inline void flush_tlb_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end) -{ - _tlbil_pid(vma->vm_mm->context.id); -} +#ifdef CONFIG_SMP +extern void flush_tlb_mm(struct mm_struct *mm); +extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr); +#else +#define flush_tlb_mm(mm) local_flush_tlb_mm(mm) +#define flush_tlb_page(vma,addr) local_flush_tlb_page(vma,addr) +#endif +#define flush_tlb_page_nohash(vma,addr) flush_tlb_page(vma,addr) -static inline void flush_tlb_kernel_range(unsigned long start, - unsigned long end) -{ - _tlbil_pid(0); -} +#elif defined(CONFIG_PPC_STD_MMU_32) -#elif defined(CONFIG_PPC32) /* - * TLB flushing for "classic" hash-MMMU 32-bit CPUs, 6xx, 7xx, 7xxx + * TLB flushing for "classic" hash-MMU 32-bit CPUs, 6xx, 7xx, 7xxx */ extern void _tlbie(unsigned long address); extern void _tlbia(void); @@ -94,14 +74,20 @@ extern void flush_tlb_page_nohash(struct vm_area_struct *vma, unsigned long addr extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); -static inline void local_flush_tlb_page(unsigned long vmaddr) +static inline void local_flush_tlb_page(struct vm_area_struct *vma, + unsigned long vmaddr) { - flush_tlb_page(NULL, vmaddr); + flush_tlb_page(vma, vmaddr); +} +static inline void local_flush_tlb_mm(struct mm_struct *mm) +{ + flush_tlb_mm(mm); } -#else +#elif defined(CONFIG_PPC_STD_MMU_64) + /* - * TLB flushing for 64-bit has-MMU CPUs + * TLB flushing for 64-bit hash-MMU CPUs */ #include @@ -151,11 +137,16 @@ extern void flush_hash_page(unsigned long va, real_pte_t pte, int psize, extern void flush_hash_range(unsigned long number, int local); +static inline void local_flush_tlb_mm(struct mm_struct *mm) +{ +} + static inline void flush_tlb_mm(struct mm_struct *mm) { } -static inline void local_flush_tlb_page(unsigned long vmaddr) +static inline void local_flush_tlb_page(struct vm_area_struct *vma, + unsigned long vmaddr) { } @@ -183,7 +174,8 @@ static inline void flush_tlb_kernel_range(unsigned long start, extern void __flush_hash_table_range(struct mm_struct *mm, unsigned long start, unsigned long end); - +#else +#error Unsupported MMU type #endif #endif /*__KERNEL__ */ diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 5c33bc14bd9..2c2ab89f0b6 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -29,6 +29,7 @@ #include #include #include +#include .text @@ -496,6 +497,14 @@ _GLOBAL(_tlbil_va) blr #endif /* CONFIG_FSL_BOOKE */ +/* + * Nobody implements this yet + */ +_GLOBAL(_tlbivax_bcast) +1: trap + EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0; + blr + /* * Flush instruction cache. diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index 341b3d3048e..dcec1325d34 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -116,12 +116,6 @@ EXPORT_SYMBOL(giveup_spe); #ifndef CONFIG_PPC64 EXPORT_SYMBOL(flush_instruction_cache); -EXPORT_SYMBOL(flush_tlb_kernel_range); -EXPORT_SYMBOL(flush_tlb_page); -EXPORT_SYMBOL(_tlbie); -#if defined(CONFIG_4xx) || defined(CONFIG_8xx) || defined(CONFIG_FSL_BOOKE) -EXPORT_SYMBOL(_tlbil_va); -#endif #endif EXPORT_SYMBOL(__flush_icache_range); EXPORT_SYMBOL(flush_dcache_range); diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile index 923bd3fa7d6..af987df8d5a 100644 --- a/arch/powerpc/mm/Makefile +++ b/arch/powerpc/mm/Makefile @@ -9,7 +9,7 @@ endif obj-y := fault.o mem.o pgtable.o \ init_$(CONFIG_WORD_SIZE).o \ pgtable_$(CONFIG_WORD_SIZE).o -obj-$(CONFIG_PPC_MMU_NOHASH) += mmu_context_nohash.o +obj-$(CONFIG_PPC_MMU_NOHASH) += mmu_context_nohash.o tlb_nohash.o hash-$(CONFIG_PPC_NATIVE) := hash_native_64.o obj-$(CONFIG_PPC64) += hash_utils_64.o \ slb_low.o slb.o stab.o \ diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 7df0409107a..87f1f955dea 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -284,7 +284,7 @@ good_area: } pte_update(ptep, 0, _PAGE_HWEXEC | _PAGE_ACCESSED); - _tlbie(address, mm->context.id); + local_flush_tlb_page(vma, address); pte_unmap_unlock(ptep, ptl); up_read(&mm->mmap_sem); return 0; diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index b9e1a1da6e5..8fee696fb79 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -488,7 +488,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, * we invalidate the TLB here, thus avoiding dcbst * misbehaviour. */ - _tlbie(address, 0 /* 8xx doesn't care about PID */); + _tlbil_va(address, 0 /* 8xx doesn't care about PID */); #endif /* The _PAGE_USER test should really be _PAGE_EXEC, but * older glibc versions execute some code from no-exec diff --git a/arch/powerpc/mm/tlb_hash32.c b/arch/powerpc/mm/tlb_hash32.c index f9a47fee392..65190587a36 100644 --- a/arch/powerpc/mm/tlb_hash32.c +++ b/arch/powerpc/mm/tlb_hash32.c @@ -137,6 +137,7 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end) flush_range(&init_mm, start, end); FINISH_FLUSH; } +EXPORT_SYMBOL(flush_tlb_kernel_range); /* * Flush all the (user) entries for the address space described by mm. @@ -160,6 +161,7 @@ void flush_tlb_mm(struct mm_struct *mm) flush_range(mp->vm_mm, mp->vm_start, mp->vm_end); FINISH_FLUSH; } +EXPORT_SYMBOL(flush_tlb_mm); void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr) { @@ -176,6 +178,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr) flush_hash_pages(mm->context.id, vmaddr, pmd_val(*pmd), 1); FINISH_FLUSH; } +EXPORT_SYMBOL(flush_tlb_page); /* * For each address in the range, find the pte for the address @@ -188,3 +191,4 @@ void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, flush_range(vma->vm_mm, start, end); FINISH_FLUSH; } +EXPORT_SYMBOL(flush_tlb_range); diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c new file mode 100644 index 00000000000..803a64c02b0 --- /dev/null +++ b/arch/powerpc/mm/tlb_nohash.c @@ -0,0 +1,209 @@ +/* + * This file contains the routines for TLB flushing. + * On machines where the MMU does not use a hash table to store virtual to + * physical translations (ie, SW loaded TLBs or Book3E compilant processors, + * this does -not- include 603 however which shares the implementation with + * hash based processors) + * + * -- BenH + * + * Copyright 2008 Ben Herrenschmidt + * IBM Corp. + * + * Derived from arch/ppc/mm/init.c: + * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) + * + * Modifications by Paul Mackerras (PowerMac) (paulus@cs.anu.edu.au) + * and Cort Dougan (PReP) (cort@cs.nmt.edu) + * Copyright (C) 1996 Paul Mackerras + * + * Derived from "arch/i386/mm/init.c" + * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + */ + +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#include "mmu_decl.h" + +/* + * Base TLB flushing operations: + * + * - flush_tlb_mm(mm) flushes the specified mm context TLB's + * - flush_tlb_page(vma, vmaddr) flushes one page + * - flush_tlb_range(vma, start, end) flushes a range of pages + * - flush_tlb_kernel_range(start, end) flushes kernel pages + * + * - local_* variants of page and mm only apply to the current + * processor + */ + +/* + * These are the base non-SMP variants of page and mm flushing + */ +void local_flush_tlb_mm(struct mm_struct *mm) +{ + unsigned int pid; + + preempt_disable(); + pid = mm->context.id; + if (pid != MMU_NO_CONTEXT) + _tlbil_pid(pid); + preempt_enable(); +} +EXPORT_SYMBOL(local_flush_tlb_mm); + +void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr) +{ + unsigned int pid; + + preempt_disable(); + pid = vma ? vma->vm_mm->context.id : 0; + if (pid != MMU_NO_CONTEXT) + _tlbil_va(vmaddr, pid); + preempt_enable(); +} +EXPORT_SYMBOL(local_flush_tlb_page); + + +/* + * And here are the SMP non-local implementations + */ +#ifdef CONFIG_SMP + +static DEFINE_SPINLOCK(tlbivax_lock); + +struct tlb_flush_param { + unsigned long addr; + unsigned int pid; +}; + +static void do_flush_tlb_mm_ipi(void *param) +{ + struct tlb_flush_param *p = param; + + _tlbil_pid(p ? p->pid : 0); +} + +static void do_flush_tlb_page_ipi(void *param) +{ + struct tlb_flush_param *p = param; + + _tlbil_va(p->addr, p->pid); +} + + +/* Note on invalidations and PID: + * + * We snapshot the PID with preempt disabled. At this point, it can still + * change either because: + * - our context is being stolen (PID -> NO_CONTEXT) on another CPU + * - we are invaliating some target that isn't currently running here + * and is concurrently acquiring a new PID on another CPU + * - some other CPU is re-acquiring a lost PID for this mm + * etc... + * + * However, this shouldn't be a problem as we only guarantee + * invalidation of TLB entries present prior to this call, so we + * don't care about the PID changing, and invalidating a stale PID + * is generally harmless. + */ + +void flush_tlb_mm(struct mm_struct *mm) +{ + cpumask_t cpu_mask; + unsigned int pid; + + preempt_disable(); + pid = mm->context.id; + if (unlikely(pid == MMU_NO_CONTEXT)) + goto no_context; + cpu_mask = mm->cpu_vm_mask; + cpu_clear(smp_processor_id(), cpu_mask); + if (!cpus_empty(cpu_mask)) { + struct tlb_flush_param p = { .pid = pid }; + smp_call_function_mask(cpu_mask, do_flush_tlb_mm_ipi, &p, 1); + } + _tlbil_pid(pid); + no_context: + preempt_enable(); +} +EXPORT_SYMBOL(flush_tlb_mm); + +void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr) +{ + cpumask_t cpu_mask; + unsigned int pid; + + preempt_disable(); + pid = vma ? vma->vm_mm->context.id : 0; + if (unlikely(pid == MMU_NO_CONTEXT)) + goto bail; + cpu_mask = vma->vm_mm->cpu_vm_mask; + cpu_clear(smp_processor_id(), cpu_mask); + if (!cpus_empty(cpu_mask)) { + /* If broadcast tlbivax is supported, use it */ + if (mmu_has_feature(MMU_FTR_USE_TLBIVAX_BCAST)) { + int lock = mmu_has_feature(MMU_FTR_LOCK_BCAST_INVAL); + if (lock) + spin_lock(&tlbivax_lock); + _tlbivax_bcast(vmaddr, pid); + if (lock) + spin_unlock(&tlbivax_lock); + goto bail; + } else { + struct tlb_flush_param p = { .pid = pid, .addr = vmaddr }; + smp_call_function_mask(cpu_mask, + do_flush_tlb_page_ipi, &p, 1); + } + } + _tlbil_va(vmaddr, pid); + bail: + preempt_enable(); +} +EXPORT_SYMBOL(flush_tlb_page); + +#endif /* CONFIG_SMP */ + +/* + * Flush kernel TLB entries in the given range + */ +void flush_tlb_kernel_range(unsigned long start, unsigned long end) +{ +#ifdef CONFIG_SMP + preempt_disable(); + smp_call_function(do_flush_tlb_mm_ipi, NULL, 1); + _tlbil_pid(0); + preempt_enable(); +#endif + _tlbil_pid(0); +} +EXPORT_SYMBOL(flush_tlb_kernel_range); + +/* + * Currently, for range flushing, we just do a full mm flush. This should + * be optimized based on a threshold on the size of the range, since + * some implementation can stack multiple tlbivax before a tlbsync but + * for now, we keep it that way + */ +void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end) + +{ + flush_tlb_mm(vma->vm_mm); +} +EXPORT_SYMBOL(flush_tlb_range); -- cgit v1.2.3-70-g09d2 From 2a4aca1144394653269720ffbb5a325a77abd5fa Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Thu, 18 Dec 2008 19:13:42 +0000 Subject: powerpc/mm: Split low level tlb invalidate for nohash processors Currently, the various forms of low level TLB invalidations are all implemented in misc_32.S for 32-bit processors, in a fairly scary mess of #ifdef's and with interesting duplication such as a whole bunch of code for FSL _tlbie and _tlbia which are no longer used. This moves things around such that _tlbie is now defined in hash_low_32.S and is only used by the 32-bit hash code, and all nohash CPUs use the various _tlbil_* forms that are now moved to a new file, tlb_nohash_low.S. I moved all the definitions for that stuff out of include/asm/tlbflush.h as they are really internal mm stuff, into mm/mmu_decl.h The code should have no functional changes. I kept some variants inline for trivial forms on things like 40x and 8xx. Signed-off-by: Benjamin Herrenschmidt Acked-by: Kumar Gala Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/tlbflush.h | 14 --- arch/powerpc/kernel/misc_32.S | 233 ------------------------------------ arch/powerpc/kvm/powerpc.c | 2 +- arch/powerpc/mm/Makefile | 3 +- arch/powerpc/mm/hash_low_32.S | 76 ++++++++++++ arch/powerpc/mm/mmu_decl.h | 48 ++++++++ arch/powerpc/mm/tlb_nohash_low.S | 165 +++++++++++++++++++++++++ 7 files changed, 292 insertions(+), 249 deletions(-) create mode 100644 arch/powerpc/mm/tlb_nohash_low.S (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/tlbflush.h b/arch/powerpc/include/asm/tlbflush.h index 8c39b27c1ed..abbe3419d1d 100644 --- a/arch/powerpc/include/asm/tlbflush.h +++ b/arch/powerpc/include/asm/tlbflush.h @@ -33,17 +33,6 @@ #define MMU_NO_CONTEXT ((unsigned int)-1) -extern void _tlbil_all(void); -extern void _tlbil_pid(unsigned int pid); -extern void _tlbil_va(unsigned long address, unsigned int pid); -extern void _tlbivax_bcast(unsigned long address, unsigned int pid); - -#if defined(CONFIG_40x) || defined(CONFIG_8xx) -#define _tlbia() asm volatile ("tlbia; sync" : : : "memory") -#else /* CONFIG_44x || CONFIG_FSL_BOOKE */ -extern void _tlbia(void); -#endif - extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); @@ -65,9 +54,6 @@ extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr); /* * TLB flushing for "classic" hash-MMU 32-bit CPUs, 6xx, 7xx, 7xxx */ -extern void _tlbie(unsigned long address); -extern void _tlbia(void); - extern void flush_tlb_mm(struct mm_struct *mm); extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr); extern void flush_tlb_page_nohash(struct vm_area_struct *vma, unsigned long addr); diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 2c2ab89f0b6..ae0d084b6a2 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -272,239 +272,6 @@ _GLOBAL(real_writeb) #endif /* CONFIG_40x */ -/* - * Flush MMU TLB - */ -#ifndef CONFIG_FSL_BOOKE -_GLOBAL(_tlbil_all) -_GLOBAL(_tlbil_pid) -#endif -_GLOBAL(_tlbia) -#if defined(CONFIG_40x) - sync /* Flush to memory before changing mapping */ - tlbia - isync /* Flush shadow TLB */ -#elif defined(CONFIG_44x) - li r3,0 - sync - - /* Load high watermark */ - lis r4,tlb_44x_hwater@ha - lwz r5,tlb_44x_hwater@l(r4) - -1: tlbwe r3,r3,PPC44x_TLB_PAGEID - addi r3,r3,1 - cmpw 0,r3,r5 - ble 1b - - isync -#elif defined(CONFIG_FSL_BOOKE) - /* Invalidate all entries in TLB0 */ - li r3, 0x04 - tlbivax 0,3 - /* Invalidate all entries in TLB1 */ - li r3, 0x0c - tlbivax 0,3 - msync -#ifdef CONFIG_SMP - tlbsync -#endif /* CONFIG_SMP */ -#else /* !(CONFIG_40x || CONFIG_44x || CONFIG_FSL_BOOKE) */ -#if defined(CONFIG_SMP) - rlwinm r8,r1,0,0,(31-THREAD_SHIFT) - lwz r8,TI_CPU(r8) - oris r8,r8,10 - mfmsr r10 - SYNC - rlwinm r0,r10,0,17,15 /* clear bit 16 (MSR_EE) */ - rlwinm r0,r0,0,28,26 /* clear DR */ - mtmsr r0 - SYNC_601 - isync - lis r9,mmu_hash_lock@h - ori r9,r9,mmu_hash_lock@l - tophys(r9,r9) -10: lwarx r7,0,r9 - cmpwi 0,r7,0 - bne- 10b - stwcx. r8,0,r9 - bne- 10b - sync - tlbia - sync - TLBSYNC - li r0,0 - stw r0,0(r9) /* clear mmu_hash_lock */ - mtmsr r10 - SYNC_601 - isync -#else /* CONFIG_SMP */ - sync - tlbia - sync -#endif /* CONFIG_SMP */ -#endif /* ! defined(CONFIG_40x) */ - blr - -/* - * Flush MMU TLB for a particular address - */ -#ifndef CONFIG_FSL_BOOKE -_GLOBAL(_tlbil_va) -#endif -_GLOBAL(_tlbie) -#if defined(CONFIG_40x) - /* We run the search with interrupts disabled because we have to change - * the PID and I don't want to preempt when that happens. - */ - mfmsr r5 - mfspr r6,SPRN_PID - wrteei 0 - mtspr SPRN_PID,r4 - tlbsx. r3, 0, r3 - mtspr SPRN_PID,r6 - wrtee r5 - bne 10f - sync - /* There are only 64 TLB entries, so r3 < 64, which means bit 25 is clear. - * Since 25 is the V bit in the TLB_TAG, loading this value will invalidate - * the TLB entry. */ - tlbwe r3, r3, TLB_TAG - isync -10: - -#elif defined(CONFIG_44x) - mfspr r5,SPRN_MMUCR - rlwimi r5,r4,0,24,31 /* Set TID */ - - /* We have to run the search with interrupts disabled, even critical - * and debug interrupts (in fact the only critical exceptions we have - * are debug and machine check). Otherwise an interrupt which causes - * a TLB miss can clobber the MMUCR between the mtspr and the tlbsx. */ - mfmsr r4 - lis r6,(MSR_EE|MSR_CE|MSR_ME|MSR_DE)@ha - addi r6,r6,(MSR_EE|MSR_CE|MSR_ME|MSR_DE)@l - andc r6,r4,r6 - mtmsr r6 - mtspr SPRN_MMUCR,r5 - tlbsx. r3, 0, r3 - mtmsr r4 - bne 10f - sync - /* There are only 64 TLB entries, so r3 < 64, - * which means bit 22, is clear. Since 22 is - * the V bit in the TLB_PAGEID, loading this - * value will invalidate the TLB entry. - */ - tlbwe r3, r3, PPC44x_TLB_PAGEID - isync -10: -#elif defined(CONFIG_FSL_BOOKE) - rlwinm r4, r3, 0, 0, 19 - ori r5, r4, 0x08 /* TLBSEL = 1 */ - tlbivax 0, r4 - tlbivax 0, r5 - msync -#if defined(CONFIG_SMP) - tlbsync -#endif /* CONFIG_SMP */ -#else /* !(CONFIG_40x || CONFIG_44x || CONFIG_FSL_BOOKE) */ -#if defined(CONFIG_SMP) - rlwinm r8,r1,0,0,(31-THREAD_SHIFT) - lwz r8,TI_CPU(r8) - oris r8,r8,11 - mfmsr r10 - SYNC - rlwinm r0,r10,0,17,15 /* clear bit 16 (MSR_EE) */ - rlwinm r0,r0,0,28,26 /* clear DR */ - mtmsr r0 - SYNC_601 - isync - lis r9,mmu_hash_lock@h - ori r9,r9,mmu_hash_lock@l - tophys(r9,r9) -10: lwarx r7,0,r9 - cmpwi 0,r7,0 - bne- 10b - stwcx. r8,0,r9 - bne- 10b - eieio - tlbie r3 - sync - TLBSYNC - li r0,0 - stw r0,0(r9) /* clear mmu_hash_lock */ - mtmsr r10 - SYNC_601 - isync -#else /* CONFIG_SMP */ - tlbie r3 - sync -#endif /* CONFIG_SMP */ -#endif /* ! CONFIG_40x */ - blr - -#if defined(CONFIG_FSL_BOOKE) -/* - * Flush MMU TLB, but only on the local processor (no broadcast) - */ -_GLOBAL(_tlbil_all) -#define MMUCSR0_TLBFI (MMUCSR0_TLB0FI | MMUCSR0_TLB1FI | \ - MMUCSR0_TLB2FI | MMUCSR0_TLB3FI) - li r3,(MMUCSR0_TLBFI)@l - mtspr SPRN_MMUCSR0, r3 -1: - mfspr r3,SPRN_MMUCSR0 - andi. r3,r3,MMUCSR0_TLBFI@l - bne 1b - blr - -/* - * Flush MMU TLB for a particular process id, but only on the local processor - * (no broadcast) - */ -_GLOBAL(_tlbil_pid) -/* we currently do an invalidate all since we don't have per pid invalidate */ - li r3,(MMUCSR0_TLBFI)@l - mtspr SPRN_MMUCSR0, r3 -1: - mfspr r3,SPRN_MMUCSR0 - andi. r3,r3,MMUCSR0_TLBFI@l - bne 1b - msync - isync - blr - -/* - * Flush MMU TLB for a particular address, but only on the local processor - * (no broadcast) - */ -_GLOBAL(_tlbil_va) - mfmsr r10 - wrteei 0 - slwi r4,r4,16 - mtspr SPRN_MAS6,r4 /* assume AS=0 for now */ - tlbsx 0,r3 - mfspr r4,SPRN_MAS1 /* check valid */ - andis. r3,r4,MAS1_VALID@h - beq 1f - rlwinm r4,r4,0,1,31 - mtspr SPRN_MAS1,r4 - tlbwe - msync - isync -1: wrtee r10 - blr -#endif /* CONFIG_FSL_BOOKE */ - -/* - * Nobody implements this yet - */ -_GLOBAL(_tlbivax_bcast) -1: trap - EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0; - blr - /* * Flush instruction cache. diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index fda9baada13..eb955d755c9 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -330,7 +330,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) /* XXX It would be nice to differentiate between heavyweight exit and * sched_out here, since we could avoid the TLB flush for heavyweight * exits. */ - _tlbia(); + _tlbil_all(); } int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu, diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile index af987df8d5a..953cc4a1cde 100644 --- a/arch/powerpc/mm/Makefile +++ b/arch/powerpc/mm/Makefile @@ -9,7 +9,8 @@ endif obj-y := fault.o mem.o pgtable.o \ init_$(CONFIG_WORD_SIZE).o \ pgtable_$(CONFIG_WORD_SIZE).o -obj-$(CONFIG_PPC_MMU_NOHASH) += mmu_context_nohash.o tlb_nohash.o +obj-$(CONFIG_PPC_MMU_NOHASH) += mmu_context_nohash.o tlb_nohash.o \ + tlb_nohash_low.o hash-$(CONFIG_PPC_NATIVE) := hash_native_64.o obj-$(CONFIG_PPC64) += hash_utils_64.o \ slb_low.o slb.o stab.o \ diff --git a/arch/powerpc/mm/hash_low_32.S b/arch/powerpc/mm/hash_low_32.S index c5536b8b37a..c8eac22a8f0 100644 --- a/arch/powerpc/mm/hash_low_32.S +++ b/arch/powerpc/mm/hash_low_32.S @@ -633,3 +633,79 @@ _GLOBAL(flush_hash_patch_B) SYNC_601 isync blr + +/* + * Flush an entry from the TLB + */ +_GLOBAL(_tlbie) +#ifdef CONFIG_SMP + rlwinm r8,r1,0,0,(31-THREAD_SHIFT) + lwz r8,TI_CPU(r8) + oris r8,r8,11 + mfmsr r10 + SYNC + rlwinm r0,r10,0,17,15 /* clear bit 16 (MSR_EE) */ + rlwinm r0,r0,0,28,26 /* clear DR */ + mtmsr r0 + SYNC_601 + isync + lis r9,mmu_hash_lock@h + ori r9,r9,mmu_hash_lock@l + tophys(r9,r9) +10: lwarx r7,0,r9 + cmpwi 0,r7,0 + bne- 10b + stwcx. r8,0,r9 + bne- 10b + eieio + tlbie r3 + sync + TLBSYNC + li r0,0 + stw r0,0(r9) /* clear mmu_hash_lock */ + mtmsr r10 + SYNC_601 + isync +#else /* CONFIG_SMP */ + tlbie r3 + sync +#endif /* CONFIG_SMP */ + blr + +/* + * Flush the entire TLB. 603/603e only + */ +_GLOBAL(_tlbia) +#if defined(CONFIG_SMP) + rlwinm r8,r1,0,0,(31-THREAD_SHIFT) + lwz r8,TI_CPU(r8) + oris r8,r8,10 + mfmsr r10 + SYNC + rlwinm r0,r10,0,17,15 /* clear bit 16 (MSR_EE) */ + rlwinm r0,r0,0,28,26 /* clear DR */ + mtmsr r0 + SYNC_601 + isync + lis r9,mmu_hash_lock@h + ori r9,r9,mmu_hash_lock@l + tophys(r9,r9) +10: lwarx r7,0,r9 + cmpwi 0,r7,0 + bne- 10b + stwcx. r8,0,r9 + bne- 10b + sync + tlbia + sync + TLBSYNC + li r0,0 + stw r0,0(r9) /* clear mmu_hash_lock */ + mtmsr r10 + SYNC_601 + isync +#else /* CONFIG_SMP */ + sync + tlbia + sync +#endif /* CONFIG_SMP */ diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h index b4344fd30f2..4314b39b6fa 100644 --- a/arch/powerpc/mm/mmu_decl.h +++ b/arch/powerpc/mm/mmu_decl.h @@ -22,10 +22,58 @@ #include #include +#ifdef CONFIG_PPC_MMU_NOHASH + +/* + * On 40x and 8xx, we directly inline tlbia and tlbivax + */ +#if defined(CONFIG_40x) || defined(CONFIG_8xx) +static inline void _tlbil_all(void) +{ + asm volatile ("sync; tlbia; isync" : : : "memory") +} +static inline void _tlbil_pid(unsigned int pid) +{ + asm volatile ("sync; tlbia; isync" : : : "memory") +} +#else /* CONFIG_40x || CONFIG_8xx */ +extern void _tlbil_all(void); +extern void _tlbil_pid(unsigned int pid); +#endif /* !(CONFIG_40x || CONFIG_8xx) */ + +/* + * On 8xx, we directly inline tlbie, on others, it's extern + */ +#ifdef CONFIG_8xx +static inline void _tlbil_va(unsigned long address, unsigned int pid) +{ + asm volatile ("tlbie %0; sync" : : "r" (address) : "memory") +} +#else /* CONFIG_8xx */ +extern void _tlbil_va(unsigned long address, unsigned int pid); +#endif /* CONIFG_8xx */ + +/* + * As of today, we don't support tlbivax broadcast on any + * implementation. When that becomes the case, this will be + * an extern. + */ +static inline void _tlbivax_bcast(unsigned long address, unsigned int pid) +{ + BUG(); +} + +#else /* CONFIG_PPC_MMU_NOHASH */ + extern void hash_preload(struct mm_struct *mm, unsigned long ea, unsigned long access, unsigned long trap); +extern void _tlbie(unsigned long address); +extern void _tlbia(void); + +#endif /* CONFIG_PPC_MMU_NOHASH */ + #ifdef CONFIG_PPC32 extern void mapin_ram(void); extern int map_page(unsigned long va, phys_addr_t pa, int flags); diff --git a/arch/powerpc/mm/tlb_nohash_low.S b/arch/powerpc/mm/tlb_nohash_low.S new file mode 100644 index 00000000000..763c59fe007 --- /dev/null +++ b/arch/powerpc/mm/tlb_nohash_low.S @@ -0,0 +1,165 @@ +/* + * This file contains low-level functions for performing various + * types of TLB invalidations on various processors with no hash + * table. + * + * This file implements the following functions for all no-hash + * processors. Some aren't implemented for some variants. Some + * are inline in tlbflush.h + * + * - tlbil_va + * - tlbil_pid + * - tlbil_all + * - tlbivax_bcast (not yet) + * + * Code mostly moved over from misc_32.S + * + * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) + * + * Partially rewritten by Cort Dougan (cort@cs.nmt.edu) + * Paul Mackerras, Kumar Gala and Benjamin Herrenschmidt. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + */ + +#include +#include +#include +#include +#include +#include +#include + +#if defined(CONFIG_40x) + +/* + * 40x implementation needs only tlbil_va + */ +_GLOBAL(_tlbil_va) + /* We run the search with interrupts disabled because we have to change + * the PID and I don't want to preempt when that happens. + */ + mfmsr r5 + mfspr r6,SPRN_PID + wrteei 0 + mtspr SPRN_PID,r4 + tlbsx. r3, 0, r3 + mtspr SPRN_PID,r6 + wrtee r5 + bne 1f + sync + /* There are only 64 TLB entries, so r3 < 64, which means bit 25 is + * clear. Since 25 is the V bit in the TLB_TAG, loading this value + * will invalidate the TLB entry. */ + tlbwe r3, r3, TLB_TAG + isync +1: blr + +#elif defined(CONFIG_8xx) + +/* + * Nothing to do for 8xx, everything is inline + */ + +#elif defined(CONFIG_44x) + +/* + * 440 implementation uses tlbsx/we for tlbil_va and a full sweep + * of the TLB for everything else. + */ +_GLOBAL(_tlbil_va) + mfspr r5,SPRN_MMUCR + rlwimi r5,r4,0,24,31 /* Set TID */ + + /* We have to run the search with interrupts disabled, even critical + * and debug interrupts (in fact the only critical exceptions we have + * are debug and machine check). Otherwise an interrupt which causes + * a TLB miss can clobber the MMUCR between the mtspr and the tlbsx. */ + mfmsr r4 + lis r6,(MSR_EE|MSR_CE|MSR_ME|MSR_DE)@ha + addi r6,r6,(MSR_EE|MSR_CE|MSR_ME|MSR_DE)@l + andc r6,r4,r6 + mtmsr r6 + mtspr SPRN_MMUCR,r5 + tlbsx. r3, 0, r3 + mtmsr r4 + bne 1f + sync + /* There are only 64 TLB entries, so r3 < 64, + * which means bit 22, is clear. Since 22 is + * the V bit in the TLB_PAGEID, loading this + * value will invalidate the TLB entry. + */ + tlbwe r3, r3, PPC44x_TLB_PAGEID + isync +1: blr + +_GLOBAL(_tlbil_all) +_GLOBAL(_tlbil_pid) + li r3,0 + sync + + /* Load high watermark */ + lis r4,tlb_44x_hwater@ha + lwz r5,tlb_44x_hwater@l(r4) + +1: tlbwe r3,r3,PPC44x_TLB_PAGEID + addi r3,r3,1 + cmpw 0,r3,r5 + ble 1b + + isync + blr + +#elif defined(CONFIG_FSL_BOOKE) +/* + * FSL BookE implementations. Currently _pid and _all are the + * same. This will change when tlbilx is actually supported and + * performs invalidate-by-PID. This change will be driven by + * mmu_features conditional + */ + +/* + * Flush MMU TLB on the local processor + */ +_GLOBAL(_tlbil_pid) +_GLOBAL(_tlbil_all) +#define MMUCSR0_TLBFI (MMUCSR0_TLB0FI | MMUCSR0_TLB1FI | \ + MMUCSR0_TLB2FI | MMUCSR0_TLB3FI) + li r3,(MMUCSR0_TLBFI)@l + mtspr SPRN_MMUCSR0, r3 +1: + mfspr r3,SPRN_MMUCSR0 + andi. r3,r3,MMUCSR0_TLBFI@l + bne 1b + msync + isync + blr + +/* + * Flush MMU TLB for a particular address, but only on the local processor + * (no broadcast) + */ +_GLOBAL(_tlbil_va) + mfmsr r10 + wrteei 0 + slwi r4,r4,16 + mtspr SPRN_MAS6,r4 /* assume AS=0 for now */ + tlbsx 0,r3 + mfspr r4,SPRN_MAS1 /* check valid */ + andis. r3,r4,MAS1_VALID@h + beq 1f + rlwinm r4,r4,0,1,31 + mtspr SPRN_MAS1,r4 + tlbwe + msync + isync +1: wrtee r10 + blr +#elif +#error Unsupported processor type ! +#endif -- cgit v1.2.3-70-g09d2 From 77520351805cc19ba37394ae33f862ef6d3c2a23 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Thu, 18 Dec 2008 19:13:48 +0000 Subject: powerpc/mm: Runtime allocation of mmu context maps for nohash CPUs This makes the MMU context code used for CPUs with no hash table (except 603) dynamically allocate the various maps used to track the state of contexts. Only the main free map and CPU 0 stale map are allocated at boot time. Other CPU maps are allocated when those CPUs are brought up and freed if they are unplugged. This also moves the initialization of the MMU context management slightly later during the boot process, which should be fine as it's really only needed when userland if first started anyways. Signed-off-by: Benjamin Herrenschmidt Acked-by: Kumar Gala Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/setup_32.c | 5 ++ arch/powerpc/mm/init_32.c | 4 - arch/powerpc/mm/mmu_context_nohash.c | 161 ++++++++++++++++++++++++----------- 3 files changed, 116 insertions(+), 54 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index b14c2a3e218..d72ef39f2b3 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -38,6 +38,7 @@ #include #include #include +#include #include "setup.h" @@ -330,4 +331,8 @@ void __init setup_arch(char **cmdline_p) if ( ppc_md.progress ) ppc_md.progress("arch: exit", 0x3eab); paging_init(); + + /* Initialize the MMU context management stuff */ + mmu_context_init(); + } diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c index 388ceda632f..578294c3b1c 100644 --- a/arch/powerpc/mm/init_32.c +++ b/arch/powerpc/mm/init_32.c @@ -35,7 +35,6 @@ #include #include #include -#include #include #include #include @@ -180,9 +179,6 @@ void __init MMU_init(void) if (ppc_md.progress) ppc_md.progress("MMU:setio", 0x302); - /* Initialize the context management stuff */ - mmu_context_init(); - if (ppc_md.progress) ppc_md.progress("MMU:exit", 0x211); diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c index 8b5de52de0a..52a0cfc38b6 100644 --- a/arch/powerpc/mm/mmu_context_nohash.c +++ b/arch/powerpc/mm/mmu_context_nohash.c @@ -28,54 +28,30 @@ #undef DEBUG #define DEBUG_STEAL_ONLY #undef DEBUG_MAP_CONSISTENCY +/*#define DEBUG_CLAMP_LAST_CONTEXT 15 */ #include #include #include +#include +#include +#include +#include #include #include -#include - -/* - * The MPC8xx has only 16 contexts. We rotate through them on each - * task switch. A better way would be to keep track of tasks that - * own contexts, and implement an LRU usage. That way very active - * tasks don't always have to pay the TLB reload overhead. The - * kernel pages are mapped shared, so the kernel can run on behalf - * of any task that makes a kernel entry. Shared does not mean they - * are not protected, just that the ASID comparison is not performed. - * -- Dan - * - * The IBM4xx has 256 contexts, so we can just rotate through these - * as a way of "switching" contexts. If the TID of the TLB is zero, - * the PID/TID comparison is disabled, so we can use a TID of zero - * to represent all kernel pages as shared among all contexts. - * -- Dan - */ - -#ifdef CONFIG_8xx -#define LAST_CONTEXT 15 -#define FIRST_CONTEXT 0 - -#elif defined(CONFIG_4xx) -#define LAST_CONTEXT 255 -#define FIRST_CONTEXT 1 - -#elif defined(CONFIG_E200) || defined(CONFIG_E500) -#define LAST_CONTEXT 255 -#define FIRST_CONTEXT 1 - -#else -#error Unsupported processor type -#endif +static unsigned int first_context, last_context; static unsigned int next_context, nr_free_contexts; -static unsigned long context_map[LAST_CONTEXT / BITS_PER_LONG + 1]; -static unsigned long stale_map[NR_CPUS][LAST_CONTEXT / BITS_PER_LONG + 1]; -static struct mm_struct *context_mm[LAST_CONTEXT+1]; +static unsigned long *context_map; +static unsigned long *stale_map[NR_CPUS]; +static struct mm_struct **context_mm; static spinlock_t context_lock = SPIN_LOCK_UNLOCKED; +#define CTX_MAP_SIZE \ + (sizeof(unsigned long) * (last_context / BITS_PER_LONG + 1)) + + /* Steal a context from a task that has one at the moment. * * This is used when we are running out of available PID numbers @@ -98,7 +74,7 @@ static unsigned int steal_context_smp(unsigned int id) unsigned int cpu, max; again: - max = LAST_CONTEXT - FIRST_CONTEXT; + max = last_context - first_context; /* Attempt to free next_context first and then loop until we manage */ while (max--) { @@ -110,8 +86,8 @@ static unsigned int steal_context_smp(unsigned int id) */ if (mm->context.active) { id++; - if (id > LAST_CONTEXT) - id = FIRST_CONTEXT; + if (id > last_context) + id = first_context; continue; } pr_debug("[%d] steal context %d from mm @%p\n", @@ -169,7 +145,7 @@ static void context_check_map(void) unsigned int id, nrf, nact; nrf = nact = 0; - for (id = FIRST_CONTEXT; id <= LAST_CONTEXT; id++) { + for (id = first_context; id <= last_context; id++) { int used = test_bit(id, context_map); if (!used) nrf++; @@ -187,6 +163,8 @@ static void context_check_map(void) if (nact > num_online_cpus()) pr_err("MMU: More active contexts than CPUs ! (%d vs %d)\n", nact, num_online_cpus()); + if (first_context > 0 && !test_bit(0, context_map)) + pr_err("MMU: Context 0 has been freed !!!\n"); } #else static void context_check_map(void) { } @@ -209,6 +187,10 @@ void switch_mmu_context(struct mm_struct *prev, struct mm_struct *next) /* Mark us active and the previous one not anymore */ next->context.active++; if (prev) { +#ifndef DEBUG_STEAL_ONLY + pr_debug(" old context %p active was: %d\n", + prev, prev->context.active); +#endif WARN_ON(prev->context.active < 1); prev->context.active--; } @@ -221,8 +203,8 @@ void switch_mmu_context(struct mm_struct *prev, struct mm_struct *next) /* We really don't have a context, let's try to acquire one */ id = next_context; - if (id > LAST_CONTEXT) - id = FIRST_CONTEXT; + if (id > last_context) + id = first_context; map = context_map; /* No more free contexts, let's try to steal one */ @@ -240,9 +222,9 @@ void switch_mmu_context(struct mm_struct *prev, struct mm_struct *next) /* We know there's at least one free context, try to find it */ while (__test_and_set_bit(id, map)) { - id = find_next_zero_bit(map, LAST_CONTEXT+1, id); - if (id > LAST_CONTEXT) - id = FIRST_CONTEXT; + id = find_next_zero_bit(map, last_context+1, id); + if (id > last_context) + id = first_context; } stolen: next_context = id + 1; @@ -311,6 +293,42 @@ void destroy_context(struct mm_struct *mm) spin_unlock(&context_lock); } +#ifdef CONFIG_SMP + +static int __cpuinit mmu_context_cpu_notify(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + unsigned int cpu = (unsigned int)(long)hcpu; + + /* We don't touch CPU 0 map, it's allocated at aboot and kept + * around forever + */ + if (cpu == 0) + return NOTIFY_OK; + + switch (action) { + case CPU_ONLINE: + case CPU_ONLINE_FROZEN: + pr_debug("MMU: Allocating stale context map for CPU %d\n", cpu); + stale_map[cpu] = kzalloc(CTX_MAP_SIZE, GFP_KERNEL); + break; +#ifdef CONFIG_HOTPLUG_CPU + case CPU_DEAD: + case CPU_DEAD_FROZEN: + pr_debug("MMU: Freeing stale context map for CPU %d\n", cpu); + kfree(stale_map[cpu]); + stale_map[cpu] = NULL; + break; +#endif + } + return NOTIFY_OK; +} + +static struct notifier_block __cpuinitdata mmu_context_cpu_nb = { + .notifier_call = mmu_context_cpu_notify, +}; + +#endif /* CONFIG_SMP */ /* * Initialize the context management stuff. @@ -323,14 +341,57 @@ void __init mmu_context_init(void) */ init_mm.context.active = NR_CPUS; + /* + * The MPC8xx has only 16 contexts. We rotate through them on each + * task switch. A better way would be to keep track of tasks that + * own contexts, and implement an LRU usage. That way very active + * tasks don't always have to pay the TLB reload overhead. The + * kernel pages are mapped shared, so the kernel can run on behalf + * of any task that makes a kernel entry. Shared does not mean they + * are not protected, just that the ASID comparison is not performed. + * -- Dan + * + * The IBM4xx has 256 contexts, so we can just rotate through these + * as a way of "switching" contexts. If the TID of the TLB is zero, + * the PID/TID comparison is disabled, so we can use a TID of zero + * to represent all kernel pages as shared among all contexts. + * -- Dan + */ + if (mmu_has_feature(MMU_FTR_TYPE_8xx)) { + first_context = 0; + last_context = 15; + } else { + first_context = 1; + last_context = 255; + } + +#ifdef DEBUG_CLAMP_LAST_CONTEXT + last_context = DEBUG_CLAMP_LAST_CONTEXT; +#endif + /* + * Allocate the maps used by context management + */ + context_map = alloc_bootmem(CTX_MAP_SIZE); + context_mm = alloc_bootmem(sizeof(void *) * (last_context + 1)); + stale_map[0] = alloc_bootmem(CTX_MAP_SIZE); + +#ifdef CONFIG_SMP + register_cpu_notifier(&mmu_context_cpu_nb); +#endif + + printk(KERN_INFO + "MMU: Allocated %d bytes of context maps for %d contexts\n", + 2 * CTX_MAP_SIZE + (sizeof(void *) * (last_context + 1)), + last_context - first_context + 1); + /* * Some processors have too few contexts to reserve one for * init_mm, and require using context 0 for a normal task. * Other processors reserve the use of context zero for the kernel. - * This code assumes FIRST_CONTEXT < 32. + * This code assumes first_context < 32. */ - context_map[0] = (1 << FIRST_CONTEXT) - 1; - next_context = FIRST_CONTEXT; - nr_free_contexts = LAST_CONTEXT - FIRST_CONTEXT + 1; + context_map[0] = (1 << first_context) - 1; + next_context = first_context; + nr_free_contexts = last_context - first_context + 1; } -- cgit v1.2.3-70-g09d2 From 64b3d0e8122b422e879b23d42f9e0e8efbbf9744 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Thu, 18 Dec 2008 19:13:51 +0000 Subject: powerpc/mm: Rework usage of _PAGE_COHERENT/NO_CACHE/GUARDED Currently, we never set _PAGE_COHERENT in the PTEs, we just OR it in in the hash code based on some CPU feature bit. We also manipulate _PAGE_NO_CACHE and _PAGE_GUARDED by hand in all sorts of places. This changes the logic so that instead, the PTE now contains _PAGE_COHERENT for all normal RAM pages thay have I = 0 on platforms that need it. The hash code clears it if the feature bit is not set. It also adds some clean accessors to setup various valid combinations of access flags and change various bits of code to use them instead. This should help having the PTE actually containing the bit combinations that we really want. I also removed _PAGE_GUARDED from _PAGE_BASE on 44x and instead set it explicitely from the TLB miss. I will ultimately remove it completely as it appears that it might not be needed after all but in the meantime, having it in the TLB miss makes things a lot easier. Signed-off-by: Benjamin Herrenschmidt Acked-by: Kumar Gala Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/pgtable-ppc32.h | 42 +++++++++++++------------------- arch/powerpc/include/asm/pgtable-ppc64.h | 13 ---------- arch/powerpc/include/asm/pgtable.h | 26 ++++++++++++++++++++ arch/powerpc/kernel/head_44x.S | 1 + arch/powerpc/kernel/pci-common.c | 24 +++++++----------- arch/powerpc/mm/hash_low_32.S | 4 +-- arch/powerpc/mm/mem.c | 4 +-- arch/powerpc/platforms/cell/spufs/file.c | 27 +++++++------------- drivers/video/controlfb.c | 4 +-- 9 files changed, 68 insertions(+), 77 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/pgtable-ppc32.h b/arch/powerpc/include/asm/pgtable-ppc32.h index 6ab7c67cb5a..f69a4d97772 100644 --- a/arch/powerpc/include/asm/pgtable-ppc32.h +++ b/arch/powerpc/include/asm/pgtable-ppc32.h @@ -228,9 +228,10 @@ extern int icache_44x_need_flush; * - FILE *must* be in the bottom three bits because swap cache * entries use the top 29 bits for TLB2. * - * - CACHE COHERENT bit (M) has no effect on PPC440 core, because it - * doesn't support SMP. So we can use this as software bit, like - * DIRTY. + * - CACHE COHERENT bit (M) has no effect on original PPC440 cores, + * because it doesn't support SMP. However, some later 460 variants + * have -some- form of SMP support and so I keep the bit there for + * future use * * With the PPC 44x Linux implementation, the 0-11th LSBs of the PTE are used * for memory protection related functions (see PTE structure in @@ -436,20 +437,23 @@ extern int icache_44x_need_flush; _PAGE_USER | _PAGE_ACCESSED | \ _PAGE_RW | _PAGE_HWWRITE | _PAGE_DIRTY | \ _PAGE_EXEC | _PAGE_HWEXEC) + /* - * Note: the _PAGE_COHERENT bit automatically gets set in the hardware - * PTE if CONFIG_SMP is defined (hash_page does this); there is no need - * to have it in the Linux PTE, and in fact the bit could be reused for - * another purpose. -- paulus. + * We define 2 sets of base prot bits, one for basic pages (ie, + * cacheable kernel and user pages) and one for non cacheable + * pages. We always set _PAGE_COHERENT when SMP is enabled or + * the processor might need it for DMA coherency. */ - -#ifdef CONFIG_44x -#define _PAGE_BASE (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_GUARDED) +#if defined(CONFIG_SMP) || defined(CONFIG_PPC_STD_MMU) +#define _PAGE_BASE (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_COHERENT) #else #define _PAGE_BASE (_PAGE_PRESENT | _PAGE_ACCESSED) #endif +#define _PAGE_BASE_NC (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_NO_CACHE) + #define _PAGE_WRENABLE (_PAGE_RW | _PAGE_DIRTY | _PAGE_HWWRITE) #define _PAGE_KERNEL (_PAGE_BASE | _PAGE_SHARED | _PAGE_WRENABLE) +#define _PAGE_KERNEL_NC (_PAGE_BASE_NC | _PAGE_SHARED | _PAGE_WRENABLE) #ifdef CONFIG_PPC_STD_MMU /* On standard PPC MMU, no user access implies kernel read/write access, @@ -459,7 +463,7 @@ extern int icache_44x_need_flush; #define _PAGE_KERNEL_RO (_PAGE_BASE | _PAGE_SHARED) #endif -#define _PAGE_IO (_PAGE_KERNEL | _PAGE_NO_CACHE | _PAGE_GUARDED) +#define _PAGE_IO (_PAGE_KERNEL_NC | _PAGE_GUARDED) #define _PAGE_RAM (_PAGE_KERNEL | _PAGE_HWEXEC) #if defined(CONFIG_KGDB) || defined(CONFIG_XMON) || defined(CONFIG_BDI_SWITCH) ||\ @@ -552,9 +556,6 @@ static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED; static inline int pte_file(pte_t pte) { return pte_val(pte) & _PAGE_FILE; } static inline int pte_special(pte_t pte) { return pte_val(pte) & _PAGE_SPECIAL; } -static inline void pte_uncache(pte_t pte) { pte_val(pte) |= _PAGE_NO_CACHE; } -static inline void pte_cache(pte_t pte) { pte_val(pte) &= ~_PAGE_NO_CACHE; } - static inline pte_t pte_wrprotect(pte_t pte) { pte_val(pte) &= ~(_PAGE_RW | _PAGE_HWWRITE); return pte; } static inline pte_t pte_mkclean(pte_t pte) { @@ -693,10 +694,11 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, #endif } + static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { -#if defined(CONFIG_PTE_64BIT) && defined(CONFIG_SMP) +#if defined(CONFIG_PTE_64BIT) && defined(CONFIG_SMP) && defined(CONFIG_DEBUG_VM) WARN_ON(pte_present(*ptep)); #endif __set_pte_at(mm, addr, ptep, pte); @@ -760,16 +762,6 @@ static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry, int dirty) __changed; \ }) -/* - * Macro to mark a page protection value as "uncacheable". - */ -#define pgprot_noncached(prot) (__pgprot(pgprot_val(prot) | _PAGE_NO_CACHE | _PAGE_GUARDED)) - -struct file; -extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, - unsigned long size, pgprot_t vma_prot); -#define __HAVE_PHYS_MEM_ACCESS_PROT - #define __HAVE_ARCH_PTE_SAME #define pte_same(A,B) (((pte_val(A) ^ pte_val(B)) & ~_PAGE_HASHPTE) == 0) diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h index 1f0a330f03f..b0f18be81d9 100644 --- a/arch/powerpc/include/asm/pgtable-ppc64.h +++ b/arch/powerpc/include/asm/pgtable-ppc64.h @@ -245,9 +245,6 @@ static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED;} static inline int pte_file(pte_t pte) { return pte_val(pte) & _PAGE_FILE;} static inline int pte_special(pte_t pte) { return pte_val(pte) & _PAGE_SPECIAL; } -static inline void pte_uncache(pte_t pte) { pte_val(pte) |= _PAGE_NO_CACHE; } -static inline void pte_cache(pte_t pte) { pte_val(pte) &= ~_PAGE_NO_CACHE; } - static inline pte_t pte_wrprotect(pte_t pte) { pte_val(pte) &= ~(_PAGE_RW); return pte; } static inline pte_t pte_mkclean(pte_t pte) { @@ -405,16 +402,6 @@ static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry, int dirty) __changed; \ }) -/* - * Macro to mark a page protection value as "uncacheable". - */ -#define pgprot_noncached(prot) (__pgprot(pgprot_val(prot) | _PAGE_NO_CACHE | _PAGE_GUARDED)) - -struct file; -extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, - unsigned long size, pgprot_t vma_prot); -#define __HAVE_PHYS_MEM_ACCESS_PROT - #define __HAVE_ARCH_PTE_SAME #define pte_same(A,B) (((pte_val(A) ^ pte_val(B)) & ~_PAGE_HPTEFLAGS) == 0) diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index dbb8ca172e4..07f55e60169 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -16,6 +16,32 @@ struct mm_struct; #endif #ifndef __ASSEMBLY__ + +/* + * Macro to mark a page protection value as "uncacheable". + */ + +#define _PAGE_CACHE_CTL (_PAGE_COHERENT | _PAGE_GUARDED | _PAGE_NO_CACHE | \ + _PAGE_WRITETHRU) + +#define pgprot_noncached(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \ + _PAGE_NO_CACHE | _PAGE_GUARDED)) + +#define pgprot_noncached_wc(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \ + _PAGE_NO_CACHE)) + +#define pgprot_cached(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \ + _PAGE_COHERENT)) + +#define pgprot_cached_wthru(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \ + _PAGE_COHERENT | _PAGE_WRITETHRU)) + + +struct file; +extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, + unsigned long size, pgprot_t vma_prot); +#define __HAVE_PHYS_MEM_ACCESS_PROT + /* * ZERO_PAGE is a global shared page that is always zero: used * for zero-mapped memory areas etc.. diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S index f3a1ea9d7fe..26237357a88 100644 --- a/arch/powerpc/kernel/head_44x.S +++ b/arch/powerpc/kernel/head_44x.S @@ -570,6 +570,7 @@ finish_tlb_load: rlwimi r10,r12,29,30,30 /* DIRTY -> SW position */ and r11,r12,r10 /* Mask PTE bits to keep */ andi. r10,r12,_PAGE_USER /* User page ? */ + ori r11,r11,_PAGE_GUARDED /* 440 errata, needs G set */ beq 1f /* nope, leave U bits empty */ rlwimi r11,r11,3,26,28 /* yes, copy S bits to U */ 1: tlbwe r11,r13,PPC44x_TLB_ATTRIB /* Write ATTRIB */ diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 1a32db331a5..2538030954d 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -370,13 +370,10 @@ static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp, } /* XXX would be nice to have a way to ask for write-through */ - prot |= _PAGE_NO_CACHE; if (write_combine) - prot &= ~_PAGE_GUARDED; + return pgprot_noncached_wc(prot); else - prot |= _PAGE_GUARDED; - - return __pgprot(prot); + return pgprot_noncached(prot); } /* @@ -387,19 +384,17 @@ static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp, pgprot_t pci_phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, - pgprot_t protection) + pgprot_t prot) { struct pci_dev *pdev = NULL; struct resource *found = NULL; - unsigned long prot = pgprot_val(protection); resource_size_t offset = ((resource_size_t)pfn) << PAGE_SHIFT; int i; if (page_is_ram(pfn)) - return __pgprot(prot); - - prot |= _PAGE_NO_CACHE | _PAGE_GUARDED; + return prot; + prot = pgprot_noncached(prot); for_each_pci_dev(pdev) { for (i = 0; i <= PCI_ROM_RESOURCE; i++) { struct resource *rp = &pdev->resource[i]; @@ -420,14 +415,14 @@ pgprot_t pci_phys_mem_access_prot(struct file *file, } if (found) { if (found->flags & IORESOURCE_PREFETCH) - prot &= ~_PAGE_GUARDED; + prot = pgprot_noncached_wc(prot); pci_dev_put(pdev); } pr_debug("PCI: Non-PCI map for %llx, prot: %lx\n", - (unsigned long long)offset, prot); + (unsigned long long)offset, pgprot_val(prot)); - return __pgprot(prot); + return prot; } @@ -583,8 +578,7 @@ int pci_mmap_legacy_page_range(struct pci_bus *bus, pr_debug(" -> mapping phys %llx\n", (unsigned long long)offset); vma->vm_pgoff = offset >> PAGE_SHIFT; - vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot) - | _PAGE_NO_CACHE | _PAGE_GUARDED); + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); return remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, vma->vm_end - vma->vm_start, vma->vm_page_prot); diff --git a/arch/powerpc/mm/hash_low_32.S b/arch/powerpc/mm/hash_low_32.S index c8eac22a8f0..28845604a10 100644 --- a/arch/powerpc/mm/hash_low_32.S +++ b/arch/powerpc/mm/hash_low_32.S @@ -323,8 +323,8 @@ _GLOBAL(create_hpte) ori r8,r8,0xe14 /* clear out reserved bits and M */ andc r8,r5,r8 /* PP = user? (rw&dirty? 2: 3): 0 */ BEGIN_FTR_SECTION - ori r8,r8,_PAGE_COHERENT /* set M (coherence required) */ -END_FTR_SECTION_IFSET(CPU_FTR_NEED_COHERENT) + rlwinm r8,r8,0,~_PAGE_COHERENT /* clear M (coherence not required) */ +END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT) #ifdef CONFIG_PTE_64BIT /* Put the XPN bits into the PTE */ rlwimi r8,r10,8,20,22 diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 8fee696fb79..53b06ebb3f2 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -102,8 +102,8 @@ pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, return ppc_md.phys_mem_access_prot(file, pfn, size, vma_prot); if (!page_is_ram(pfn)) - vma_prot = __pgprot(pgprot_val(vma_prot) - | _PAGE_GUARDED | _PAGE_NO_CACHE); + vma_prot = pgprot_noncached(vma_prot); + return vma_prot; } EXPORT_SYMBOL(phys_mem_access_prot); diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c index 1b26071a86c..7106b63d401 100644 --- a/arch/powerpc/platforms/cell/spufs/file.c +++ b/arch/powerpc/platforms/cell/spufs/file.c @@ -273,12 +273,10 @@ spufs_mem_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return VM_FAULT_NOPAGE; if (ctx->state == SPU_STATE_SAVED) { - vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot) - & ~_PAGE_NO_CACHE); + vma->vm_page_prot = pgprot_cached(vma->vm_page_prot); pfn = vmalloc_to_pfn(ctx->csa.lscsa->ls + offset); } else { - vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot) - | _PAGE_NO_CACHE); + vma->vm_page_prot = pgprot_noncached_wc(vma->vm_page_prot); pfn = (ctx->spu->local_store_phys + offset) >> PAGE_SHIFT; } vm_insert_pfn(vma, address, pfn); @@ -338,8 +336,7 @@ static int spufs_mem_mmap(struct file *file, struct vm_area_struct *vma) return -EINVAL; vma->vm_flags |= VM_IO | VM_PFNMAP; - vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot) - | _PAGE_NO_CACHE); + vma->vm_page_prot = pgprot_noncached_wc(vma->vm_page_prot); vma->vm_ops = &spufs_mem_mmap_vmops; return 0; @@ -452,8 +449,7 @@ static int spufs_cntl_mmap(struct file *file, struct vm_area_struct *vma) return -EINVAL; vma->vm_flags |= VM_IO | VM_PFNMAP; - vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot) - | _PAGE_NO_CACHE | _PAGE_GUARDED); + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); vma->vm_ops = &spufs_cntl_mmap_vmops; return 0; @@ -1155,8 +1151,7 @@ static int spufs_signal1_mmap(struct file *file, struct vm_area_struct *vma) return -EINVAL; vma->vm_flags |= VM_IO | VM_PFNMAP; - vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot) - | _PAGE_NO_CACHE | _PAGE_GUARDED); + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); vma->vm_ops = &spufs_signal1_mmap_vmops; return 0; @@ -1292,8 +1287,7 @@ static int spufs_signal2_mmap(struct file *file, struct vm_area_struct *vma) return -EINVAL; vma->vm_flags |= VM_IO | VM_PFNMAP; - vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot) - | _PAGE_NO_CACHE | _PAGE_GUARDED); + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); vma->vm_ops = &spufs_signal2_mmap_vmops; return 0; @@ -1414,8 +1408,7 @@ static int spufs_mss_mmap(struct file *file, struct vm_area_struct *vma) return -EINVAL; vma->vm_flags |= VM_IO | VM_PFNMAP; - vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot) - | _PAGE_NO_CACHE | _PAGE_GUARDED); + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); vma->vm_ops = &spufs_mss_mmap_vmops; return 0; @@ -1476,8 +1469,7 @@ static int spufs_psmap_mmap(struct file *file, struct vm_area_struct *vma) return -EINVAL; vma->vm_flags |= VM_IO | VM_PFNMAP; - vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot) - | _PAGE_NO_CACHE | _PAGE_GUARDED); + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); vma->vm_ops = &spufs_psmap_mmap_vmops; return 0; @@ -1536,8 +1528,7 @@ static int spufs_mfc_mmap(struct file *file, struct vm_area_struct *vma) return -EINVAL; vma->vm_flags |= VM_IO | VM_PFNMAP; - vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot) - | _PAGE_NO_CACHE | _PAGE_GUARDED); + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); vma->vm_ops = &spufs_mfc_mmap_vmops; return 0; diff --git a/drivers/video/controlfb.c b/drivers/video/controlfb.c index b0be7eac32d..49fcbe8f18a 100644 --- a/drivers/video/controlfb.c +++ b/drivers/video/controlfb.c @@ -298,10 +298,10 @@ static int controlfb_mmap(struct fb_info *info, return -EINVAL; start = info->fix.mmio_start; len = PAGE_ALIGN((start & ~PAGE_MASK)+info->fix.mmio_len); - pgprot_val(vma->vm_page_prot) |= _PAGE_NO_CACHE|_PAGE_GUARDED; + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); } else { /* framebuffer */ - pgprot_val(vma->vm_page_prot) |= _PAGE_WRITETHRU; + vma->vm_page_prot = pgprot_cached_wthru(vma->vm_page_prot); } start &= PAGE_MASK; if ((vma->vm_end - vma->vm_start + off) > len) -- cgit v1.2.3-70-g09d2 From 9dce3ce5c55c848f00429005a46fd6246cfabfbe Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Thu, 18 Dec 2008 19:13:54 +0000 Subject: powerpc/44x: 44x TLB doesn't need "Guarded" set for all pages After discussing with chip designers, it appears that it's not necessary to set G everywhere on 440 cores. The various core errata related to prefetch should be sorted out by firmware by disabling icache prefetching in CCR0. We add the workaround to the kernel however just in case oooold firmwares don't do it. This is valid for -all- 4xx core variants. Later ones hard wire the absence of prefetch but it doesn't harm to clear the bits in CCR0 (they should already be cleared anyway). We still leave G=1 on the linear mapping for now, we need to stop over-mapping RAM to be able to remove it. Signed-off-by: Benjamin Herrenschmidt Acked-by: Kumar Gala Acked-by: Josh Boyer Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/head_44x.S | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S index 26237357a88..bd4fe9e7278 100644 --- a/arch/powerpc/kernel/head_44x.S +++ b/arch/powerpc/kernel/head_44x.S @@ -68,6 +68,17 @@ _ENTRY(_start); mr r27,r7 li r24,0 /* CPU number */ +/* + * In case the firmware didn't do it, we apply some workarounds + * that are good for all 440 core variants here + */ + mfspr r3,SPRN_CCR0 + rlwinm r3,r3,0,0,27 /* disable icache prefetch */ + isync + mtspr SPRN_CCR0,r3 + isync + sync + /* * Set up the initial MMU state * @@ -570,7 +581,6 @@ finish_tlb_load: rlwimi r10,r12,29,30,30 /* DIRTY -> SW position */ and r11,r12,r10 /* Mask PTE bits to keep */ andi. r10,r12,_PAGE_USER /* User page ? */ - ori r11,r11,_PAGE_GUARDED /* 440 errata, needs G set */ beq 1f /* nope, leave U bits empty */ rlwimi r11,r11,3,26,28 /* yes, copy S bits to U */ 1: tlbwe r11,r13,PPC44x_TLB_ATTRIB /* Write ATTRIB */ -- cgit v1.2.3-70-g09d2 From 2e8e4f5b80e101da588af650de0ff6b3c475d6b3 Mon Sep 17 00:00:00 2001 From: Dale Farnsworth Date: Tue, 16 Dec 2008 06:22:59 +0000 Subject: powerpc: Setup OF properties for ppc32 kexec Refactor the setting of kexec OF properties, moving the common code from machine_kexec_64.c to machine_kexec.c where it can be used on both ppc64 and ppc32. This is needed for kexec to work on ppc32 platforms. Signed-off-by: Dale Farnsworth Signed-off-by: Anton Vorontsov Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/machine_kexec.c | 34 ++++++++++++++++++++++++++++++++++ arch/powerpc/kernel/machine_kexec_64.c | 24 +++++------------------- 2 files changed, 39 insertions(+), 19 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c index ac2a21f45c7..037ade74a99 100644 --- a/arch/powerpc/kernel/machine_kexec.c +++ b/arch/powerpc/kernel/machine_kexec.c @@ -13,8 +13,10 @@ #include #include #include +#include #include #include +#include void machine_crash_shutdown(struct pt_regs *regs) { @@ -118,3 +120,35 @@ int overlaps_crashkernel(unsigned long start, unsigned long size) { return (start + size) > crashk_res.start && start <= crashk_res.end; } + +/* Values we need to export to the second kernel via the device tree. */ +static unsigned long kernel_end; + +static struct property kernel_end_prop = { + .name = "linux,kernel-end", + .length = sizeof(unsigned long), + .value = &kernel_end, +}; + +static int __init kexec_setup(void) +{ + struct device_node *node; + struct property *prop; + + node = of_find_node_by_path("/chosen"); + if (!node) + return -ENOENT; + + /* remove any stale properties so ours can be found */ + prop = of_find_property(node, kernel_end_prop.name, NULL); + if (prop) + prom_remove_property(node, prop); + + /* information needed by userspace when using default_machine_kexec */ + kernel_end = __pa(_end); + prom_add_property(node, &kernel_end_prop); + + of_node_put(node); + return 0; +} +late_initcall(kexec_setup); diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c index 3c4ca046e85..a89bce834a5 100644 --- a/arch/powerpc/kernel/machine_kexec_64.c +++ b/arch/powerpc/kernel/machine_kexec_64.c @@ -289,7 +289,7 @@ void default_machine_kexec(struct kimage *image) } /* Values we need to export to the second kernel via the device tree. */ -static unsigned long htab_base, kernel_end; +static unsigned long htab_base; static struct property htab_base_prop = { .name = "linux,htab-base", @@ -303,25 +303,20 @@ static struct property htab_size_prop = { .value = &htab_size_bytes, }; -static struct property kernel_end_prop = { - .name = "linux,kernel-end", - .length = sizeof(unsigned long), - .value = &kernel_end, -}; - static void __init export_htab_values(void) { struct device_node *node; struct property *prop; + /* On machines with no htab htab_address is NULL */ + if (!htab_address) + return; + node = of_find_node_by_path("/chosen"); if (!node) return; /* remove any stale propertys so ours can be found */ - prop = of_find_property(node, kernel_end_prop.name, NULL); - if (prop) - prom_remove_property(node, prop); prop = of_find_property(node, htab_base_prop.name, NULL); if (prop) prom_remove_property(node, prop); @@ -329,19 +324,10 @@ static void __init export_htab_values(void) if (prop) prom_remove_property(node, prop); - /* information needed by userspace when using default_machine_kexec */ - kernel_end = __pa(_end); - prom_add_property(node, &kernel_end_prop); - - /* On machines with no htab htab_address is NULL */ - if (NULL == htab_address) - goto out; - htab_base = __pa(htab_address); prom_add_property(node, &htab_base_prop); prom_add_property(node, &htab_size_prop); - out: of_node_put(node); } -- cgit v1.2.3-70-g09d2 From 77733f8a33488307e7d4b9077d174647ecea92e1 Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Tue, 16 Dec 2008 06:23:05 +0000 Subject: powerpc: Make default kexec/crash_kernel ops implicit This removes the need for each platform to specify default kexec and crash kernel ops, thus effectively adds a working kexec support for most 6xx/7xx/7xxx-based boards. Platforms that can't cope with default ops will explode in some weird way (a hang or reboot is most likely), which means that the board's kexec support should be fixed or blacklisted via dummy _prepare callback returning -ENOSYS. Signed-off-by: Anton Vorontsov Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/machine_kexec.c | 21 +++++++++------------ 1 file changed, 9 insertions(+), 12 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c index 037ade74a99..4f797c0b714 100644 --- a/arch/powerpc/kernel/machine_kexec.c +++ b/arch/powerpc/kernel/machine_kexec.c @@ -22,6 +22,8 @@ void machine_crash_shutdown(struct pt_regs *regs) { if (ppc_md.machine_crash_shutdown) ppc_md.machine_crash_shutdown(regs); + else + default_machine_crash_shutdown(regs); } /* @@ -33,11 +35,8 @@ int machine_kexec_prepare(struct kimage *image) { if (ppc_md.machine_kexec_prepare) return ppc_md.machine_kexec_prepare(image); - /* - * Fail if platform doesn't provide its own machine_kexec_prepare - * implementation. - */ - return -ENOSYS; + else + return default_machine_kexec_prepare(image); } void machine_kexec_cleanup(struct kimage *image) @@ -54,13 +53,11 @@ void machine_kexec(struct kimage *image) { if (ppc_md.machine_kexec) ppc_md.machine_kexec(image); - else { - /* - * Fall back to normal restart if platform doesn't provide - * its own kexec function, and user insist to kexec... - */ - machine_restart(NULL); - } + else + default_machine_kexec(image); + + /* Fall back to normal restart if we're still alive. */ + machine_restart(NULL); for(;;); } -- cgit v1.2.3-70-g09d2 From 322b439455ea62e6480e300c77b258e872896381 Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Wed, 17 Dec 2008 10:08:55 +0000 Subject: powerpc: Prepare xmon_save_regs for use with kdump Today the arch/powerpc/xmon/setjmp.S file contains only the xmon_save_regs function. We want to use it for kdump purposes, so let's move the file into arch/powerpc/kernel/ and give the function a more generic name (ppc_save_regs). Signed-off-by: Anton Vorontsov Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/reg.h | 4 ++ arch/powerpc/kernel/Makefile | 4 ++ arch/powerpc/kernel/ppc_save_regs.S | 74 +++++++++++++++++++++++++++++++++++++ arch/powerpc/xmon/Makefile | 2 +- arch/powerpc/xmon/setjmp.S | 74 ------------------------------------- arch/powerpc/xmon/xmon.c | 5 +-- 6 files changed, 85 insertions(+), 78 deletions(-) create mode 100644 arch/powerpc/kernel/ppc_save_regs.S delete mode 100644 arch/powerpc/xmon/setjmp.S (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index c6d1ab65077..f484a343efb 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -783,6 +783,10 @@ extern void scom970_write(unsigned int address, unsigned long value); #define __get_SP() ({unsigned long sp; \ asm volatile("mr %0,1": "=r" (sp)); sp;}) +struct pt_regs; + +extern void ppc_save_regs(struct pt_regs *regs); + #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_REG_H */ diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 92673b43858..616c8891d85 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -102,6 +102,10 @@ endif obj-$(CONFIG_PPC64) += $(obj64-y) +ifneq ($(CONFIG_XMON),) +obj-y += ppc_save_regs.o +endif + extra-$(CONFIG_PPC_FPU) += fpu.o extra-$(CONFIG_PPC64) += entry_64.o diff --git a/arch/powerpc/kernel/ppc_save_regs.S b/arch/powerpc/kernel/ppc_save_regs.S new file mode 100644 index 00000000000..5113bd2285e --- /dev/null +++ b/arch/powerpc/kernel/ppc_save_regs.S @@ -0,0 +1,74 @@ +/* + * Copyright (C) 1996 Paul Mackerras. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * NOTE: assert(sizeof(buf) > 23 * sizeof(long)) + */ +#include +#include +#include + +/* + * Grab the register values as they are now. + * This won't do a particularily good job because we really + * want our caller's caller's registers, and our caller has + * already executed its prologue. + * ToDo: We could reach back into the caller's save area to do + * a better job of representing the caller's state (note that + * that will be different for 32-bit and 64-bit, because of the + * different ABIs, though). + */ +_GLOBAL(ppc_save_regs) + PPC_STL r0,0*SZL(r3) + PPC_STL r2,2*SZL(r3) + PPC_STL r3,3*SZL(r3) + PPC_STL r4,4*SZL(r3) + PPC_STL r5,5*SZL(r3) + PPC_STL r6,6*SZL(r3) + PPC_STL r7,7*SZL(r3) + PPC_STL r8,8*SZL(r3) + PPC_STL r9,9*SZL(r3) + PPC_STL r10,10*SZL(r3) + PPC_STL r11,11*SZL(r3) + PPC_STL r12,12*SZL(r3) + PPC_STL r13,13*SZL(r3) + PPC_STL r14,14*SZL(r3) + PPC_STL r15,15*SZL(r3) + PPC_STL r16,16*SZL(r3) + PPC_STL r17,17*SZL(r3) + PPC_STL r18,18*SZL(r3) + PPC_STL r19,19*SZL(r3) + PPC_STL r20,20*SZL(r3) + PPC_STL r21,21*SZL(r3) + PPC_STL r22,22*SZL(r3) + PPC_STL r23,23*SZL(r3) + PPC_STL r24,24*SZL(r3) + PPC_STL r25,25*SZL(r3) + PPC_STL r26,26*SZL(r3) + PPC_STL r27,27*SZL(r3) + PPC_STL r28,28*SZL(r3) + PPC_STL r29,29*SZL(r3) + PPC_STL r30,30*SZL(r3) + PPC_STL r31,31*SZL(r3) + /* go up one stack frame for SP */ + PPC_LL r4,0(r1) + PPC_STL r4,1*SZL(r3) + /* get caller's LR */ + PPC_LL r0,LRSAVE(r4) + PPC_STL r0,_NIP-STACK_FRAME_OVERHEAD(r3) + PPC_STL r0,_LINK-STACK_FRAME_OVERHEAD(r3) + mfmsr r0 + PPC_STL r0,_MSR-STACK_FRAME_OVERHEAD(r3) + mfctr r0 + PPC_STL r0,_CTR-STACK_FRAME_OVERHEAD(r3) + mfxer r0 + PPC_STL r0,_XER-STACK_FRAME_OVERHEAD(r3) + mfcr r0 + PPC_STL r0,_CCR-STACK_FRAME_OVERHEAD(r3) + li r0,0 + PPC_STL r0,_TRAP-STACK_FRAME_OVERHEAD(r3) + blr diff --git a/arch/powerpc/xmon/Makefile b/arch/powerpc/xmon/Makefile index 51d97588e76..9cb03b71b9d 100644 --- a/arch/powerpc/xmon/Makefile +++ b/arch/powerpc/xmon/Makefile @@ -4,7 +4,7 @@ ifdef CONFIG_PPC64 EXTRA_CFLAGS += -mno-minimal-toc endif -obj-y += xmon.o setjmp.o start.o nonstdio.o +obj-y += xmon.o start.o nonstdio.o ifdef CONFIG_XMON_DISASSEMBLY obj-y += ppc-dis.o ppc-opc.o diff --git a/arch/powerpc/xmon/setjmp.S b/arch/powerpc/xmon/setjmp.S deleted file mode 100644 index 04c0b305ad4..00000000000 --- a/arch/powerpc/xmon/setjmp.S +++ /dev/null @@ -1,74 +0,0 @@ -/* - * Copyright (C) 1996 Paul Mackerras. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - * NOTE: assert(sizeof(buf) > 23 * sizeof(long)) - */ -#include -#include -#include - -/* - * Grab the register values as they are now. - * This won't do a particularily good job because we really - * want our caller's caller's registers, and our caller has - * already executed its prologue. - * ToDo: We could reach back into the caller's save area to do - * a better job of representing the caller's state (note that - * that will be different for 32-bit and 64-bit, because of the - * different ABIs, though). - */ -_GLOBAL(xmon_save_regs) - PPC_STL r0,0*SZL(r3) - PPC_STL r2,2*SZL(r3) - PPC_STL r3,3*SZL(r3) - PPC_STL r4,4*SZL(r3) - PPC_STL r5,5*SZL(r3) - PPC_STL r6,6*SZL(r3) - PPC_STL r7,7*SZL(r3) - PPC_STL r8,8*SZL(r3) - PPC_STL r9,9*SZL(r3) - PPC_STL r10,10*SZL(r3) - PPC_STL r11,11*SZL(r3) - PPC_STL r12,12*SZL(r3) - PPC_STL r13,13*SZL(r3) - PPC_STL r14,14*SZL(r3) - PPC_STL r15,15*SZL(r3) - PPC_STL r16,16*SZL(r3) - PPC_STL r17,17*SZL(r3) - PPC_STL r18,18*SZL(r3) - PPC_STL r19,19*SZL(r3) - PPC_STL r20,20*SZL(r3) - PPC_STL r21,21*SZL(r3) - PPC_STL r22,22*SZL(r3) - PPC_STL r23,23*SZL(r3) - PPC_STL r24,24*SZL(r3) - PPC_STL r25,25*SZL(r3) - PPC_STL r26,26*SZL(r3) - PPC_STL r27,27*SZL(r3) - PPC_STL r28,28*SZL(r3) - PPC_STL r29,29*SZL(r3) - PPC_STL r30,30*SZL(r3) - PPC_STL r31,31*SZL(r3) - /* go up one stack frame for SP */ - PPC_LL r4,0(r1) - PPC_STL r4,1*SZL(r3) - /* get caller's LR */ - PPC_LL r0,LRSAVE(r4) - PPC_STL r0,_NIP-STACK_FRAME_OVERHEAD(r3) - PPC_STL r0,_LINK-STACK_FRAME_OVERHEAD(r3) - mfmsr r0 - PPC_STL r0,_MSR-STACK_FRAME_OVERHEAD(r3) - mfctr r0 - PPC_STL r0,_CTR-STACK_FRAME_OVERHEAD(r3) - mfxer r0 - PPC_STL r0,_XER-STACK_FRAME_OVERHEAD(r3) - mfcr r0 - PPC_STL r0,_CCR-STACK_FRAME_OVERHEAD(r3) - li r0,0 - PPC_STL r0,_TRAP-STACK_FRAME_OVERHEAD(r3) - blr diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 076368c8b8a..8dfad7d9a00 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -41,6 +41,7 @@ #include #include #include +#include #ifdef CONFIG_PPC64 #include @@ -159,8 +160,6 @@ static int xmon_no_auto_backtrace; extern void xmon_enter(void); extern void xmon_leave(void); -extern void xmon_save_regs(struct pt_regs *); - #ifdef CONFIG_PPC64 #define REG "%.16lx" #define REGS_PER_LINE 4 @@ -532,7 +531,7 @@ int xmon(struct pt_regs *excp) struct pt_regs regs; if (excp == NULL) { - xmon_save_regs(®s); + ppc_save_regs(®s); excp = ®s; } -- cgit v1.2.3-70-g09d2 From 73753313884e8d063d9bf9d3e36325743ca006ba Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Wed, 17 Dec 2008 10:09:01 +0000 Subject: powerpc/32/kdump: Implement crash_setup_regs() using ppc_save_regs() This replaces the dummy crash_setup_regs function with full-fledged crash_setup_regs implementation. On PPC32 we simply use the new ppc_save_regs function to dump the registers. Signed-off-by: Anton Vorontsov Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/kexec.h | 15 ++++++--------- arch/powerpc/kernel/Makefile | 2 +- 2 files changed, 7 insertions(+), 10 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h index 3736d9b3328..6dbffc98170 100644 --- a/arch/powerpc/include/asm/kexec.h +++ b/arch/powerpc/include/asm/kexec.h @@ -33,12 +33,12 @@ #ifndef __ASSEMBLY__ #include +#include typedef void (*crash_shutdown_t)(void); #ifdef CONFIG_KEXEC -#ifdef __powerpc64__ /* * This function is responsible for capturing register states if coming * via panic or invoking dump using sysrq-trigger. @@ -48,6 +48,7 @@ static inline void crash_setup_regs(struct pt_regs *newregs, { if (oldregs) memcpy(newregs, oldregs, sizeof(*newregs)); +#ifdef __powerpc64__ else { /* FIXME Merge this with xmon_save_regs ?? */ unsigned long tmp1, tmp2; @@ -100,15 +101,11 @@ static inline void crash_setup_regs(struct pt_regs *newregs, : "b" (newregs) : "memory"); } -} #else -/* - * Provide a dummy definition to avoid build failures. Will remain - * empty till crash dump support is enabled. - */ -static inline void crash_setup_regs(struct pt_regs *newregs, - struct pt_regs *oldregs) { } -#endif /* !__powerpc64 __ */ + else + ppc_save_regs(newregs); +#endif /* __powerpc64__ */ +} extern void kexec_smp_wait(void); /* get and clear naca physid, wait for master to copy new code to 0 */ diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 616c8891d85..089209aa213 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -102,7 +102,7 @@ endif obj-$(CONFIG_PPC64) += $(obj64-y) -ifneq ($(CONFIG_XMON),) +ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC),) obj-y += ppc_save_regs.o endif -- cgit v1.2.3-70-g09d2 From 6f29c3298b18216198631cbee01c349adecb225d Mon Sep 17 00:00:00 2001 From: Dale Farnsworth Date: Wed, 17 Dec 2008 10:09:06 +0000 Subject: powerpc/32: Setup OF properties for kdump Refactor the setting of kdump OF properties, moving the common code from machine_kexec_64.c to machine_kexec.c where it can be used on both ppc64 and ppc32. This will be needed for kdump to work on ppc32 platforms. Signed-off-by: Dale Farnsworth Signed-off-by: Anton Vorontsov Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/machine_kexec.c | 36 ++++++++++++++++++++++ arch/powerpc/kernel/machine_kexec_64.c | 56 +++------------------------------- 2 files changed, 40 insertions(+), 52 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c index 4f797c0b714..b3abebb7ee6 100644 --- a/arch/powerpc/kernel/machine_kexec.c +++ b/arch/powerpc/kernel/machine_kexec.c @@ -120,6 +120,7 @@ int overlaps_crashkernel(unsigned long start, unsigned long size) /* Values we need to export to the second kernel via the device tree. */ static unsigned long kernel_end; +static unsigned long crashk_size; static struct property kernel_end_prop = { .name = "linux,kernel-end", @@ -127,6 +128,39 @@ static struct property kernel_end_prop = { .value = &kernel_end, }; +static struct property crashk_base_prop = { + .name = "linux,crashkernel-base", + .length = sizeof(unsigned long), + .value = &crashk_res.start, +}; + +static struct property crashk_size_prop = { + .name = "linux,crashkernel-size", + .length = sizeof(unsigned long), + .value = &crashk_size, +}; + +static void __init export_crashk_values(struct device_node *node) +{ + struct property *prop; + + /* There might be existing crash kernel properties, but we can't + * be sure what's in them, so remove them. */ + prop = of_find_property(node, "linux,crashkernel-base", NULL); + if (prop) + prom_remove_property(node, prop); + + prop = of_find_property(node, "linux,crashkernel-size", NULL); + if (prop) + prom_remove_property(node, prop); + + if (crashk_res.start != 0) { + prom_add_property(node, &crashk_base_prop); + crashk_size = crashk_res.end - crashk_res.start + 1; + prom_add_property(node, &crashk_size_prop); + } +} + static int __init kexec_setup(void) { struct device_node *node; @@ -145,6 +179,8 @@ static int __init kexec_setup(void) kernel_end = __pa(_end); prom_add_property(node, &kernel_end_prop); + export_crashk_values(node); + of_node_put(node); return 0; } diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c index a89bce834a5..49e705fcee6 100644 --- a/arch/powerpc/kernel/machine_kexec_64.c +++ b/arch/powerpc/kernel/machine_kexec_64.c @@ -303,18 +303,18 @@ static struct property htab_size_prop = { .value = &htab_size_bytes, }; -static void __init export_htab_values(void) +static int __init export_htab_values(void) { struct device_node *node; struct property *prop; /* On machines with no htab htab_address is NULL */ if (!htab_address) - return; + return -ENODEV; node = of_find_node_by_path("/chosen"); if (!node) - return; + return -ENODEV; /* remove any stale propertys so ours can be found */ prop = of_find_property(node, htab_base_prop.name, NULL); @@ -329,54 +329,6 @@ static void __init export_htab_values(void) prom_add_property(node, &htab_size_prop); of_node_put(node); -} - -static struct property crashk_base_prop = { - .name = "linux,crashkernel-base", - .length = sizeof(unsigned long), - .value = &crashk_res.start, -}; - -static unsigned long crashk_size; - -static struct property crashk_size_prop = { - .name = "linux,crashkernel-size", - .length = sizeof(unsigned long), - .value = &crashk_size, -}; - -static void __init export_crashk_values(void) -{ - struct device_node *node; - struct property *prop; - - node = of_find_node_by_path("/chosen"); - if (!node) - return; - - /* There might be existing crash kernel properties, but we can't - * be sure what's in them, so remove them. */ - prop = of_find_property(node, "linux,crashkernel-base", NULL); - if (prop) - prom_remove_property(node, prop); - - prop = of_find_property(node, "linux,crashkernel-size", NULL); - if (prop) - prom_remove_property(node, prop); - - if (crashk_res.start != 0) { - prom_add_property(node, &crashk_base_prop); - crashk_size = crashk_res.end - crashk_res.start + 1; - prom_add_property(node, &crashk_size_prop); - } - - of_node_put(node); -} - -static int __init kexec_setup(void) -{ - export_htab_values(); - export_crashk_values(); return 0; } -__initcall(kexec_setup); +late_initcall(export_htab_values); -- cgit v1.2.3-70-g09d2 From ccdcef72c249c289898b164eada89a61855b9287 Mon Sep 17 00:00:00 2001 From: Dale Farnsworth Date: Wed, 17 Dec 2008 10:09:13 +0000 Subject: powerpc/32: Add the ability for a classic ppc kernel to be loaded at 32M Add the ability for a classic ppc kernel to be loaded at an address of 32MB. This done by fixing a few places that assume we are loaded at address 0, and by changing several uses of KERNELBASE to use PAGE_OFFSET, instead. Signed-off-by: Dale Farnsworth Signed-off-by: Anton Vorontsov Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/ppc_asm.h | 4 ++-- arch/powerpc/kernel/head_32.S | 11 ++++++----- arch/powerpc/mm/init_32.c | 2 +- arch/powerpc/mm/pgtable_32.c | 4 ++-- arch/powerpc/mm/ppc_mmu_32.c | 8 ++++---- 5 files changed, 15 insertions(+), 14 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index c4a029ccb4d..1a0d628eb11 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -425,14 +425,14 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601) #define fromreal(rd) tovirt(rd,rd) #define tophys(rd,rs) \ -0: addis rd,rs,-KERNELBASE@h; \ +0: addis rd,rs,-PAGE_OFFSET@h; \ .section ".vtop_fixup","aw"; \ .align 1; \ .long 0b; \ .previous #define tovirt(rd,rs) \ -0: addis rd,rs,KERNELBASE@h; \ +0: addis rd,rs,PAGE_OFFSET@h; \ .section ".ptov_fixup","aw"; \ .align 1; \ .long 0b; \ diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index 26606192465..a1c4cfd25de 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -183,7 +183,8 @@ __after_mmu_off: bl reloc_offset mr r26,r3 addis r4,r3,KERNELBASE@h /* current address of _start */ - cmpwi 0,r4,0 /* are we already running at 0? */ + lis r5,PHYSICAL_START@h + cmplw 0,r4,r5 /* already running at PHYSICAL_START? */ bne relocate_kernel /* * we now have the 1st 16M of ram mapped with the bats. @@ -811,13 +812,13 @@ giveup_altivec: /* * This code is jumped to from the startup code to copy - * the kernel image to physical address 0. + * the kernel image to physical address PHYSICAL_START. */ relocate_kernel: addis r9,r26,klimit@ha /* fetch klimit */ lwz r25,klimit@l(r9) addis r25,r25,-KERNELBASE@h - li r3,0 /* Destination base address */ + lis r3,PHYSICAL_START@h /* Destination base address */ li r6,0 /* Destination offset */ li r5,0x4000 /* # bytes of memory to copy */ bl copy_and_flush /* copy the first 0x4000 bytes */ @@ -1188,11 +1189,11 @@ mmu_off: /* * Use the first pair of BAT registers to map the 1st 16MB - * of RAM to KERNELBASE. From this point on we can't safely + * of RAM to PAGE_OFFSET. From this point on we can't safely * call OF any more. */ initial_bats: - lis r11,KERNELBASE@h + lis r11,PAGE_OFFSET@h mfspr r9,SPRN_PVR rlwinm r9,r9,16,16,31 /* r9 = 1 for 601, 4 for 604 */ cmpwi 0,r9,1 diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c index 578294c3b1c..666a5e8a5be 100644 --- a/arch/powerpc/mm/init_32.c +++ b/arch/powerpc/mm/init_32.c @@ -48,7 +48,7 @@ #if defined(CONFIG_KERNEL_START_BOOL) || defined(CONFIG_LOWMEM_SIZE_BOOL) /* The ammount of lowmem must be within 0xF0000000 - KERNELBASE. */ -#if (CONFIG_LOWMEM_SIZE > (0xF0000000 - KERNELBASE)) +#if (CONFIG_LOWMEM_SIZE > (0xF0000000 - PAGE_OFFSET)) #error "You must adjust CONFIG_LOWMEM_SIZE or CONFIG_START_KERNEL" #endif #endif diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index cd5609759d4..8cba46fc9e3 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -269,7 +269,7 @@ int map_page(unsigned long va, phys_addr_t pa, int flags) } /* - * Map in a big chunk of physical memory starting at KERNELBASE. + * Map in a big chunk of physical memory starting at PAGE_OFFSET. */ void __init mapin_ram(void) { @@ -278,7 +278,7 @@ void __init mapin_ram(void) int ktext; s = mmu_mapin_ram(); - v = KERNELBASE + s; + v = PAGE_OFFSET + s; p = memstart_addr + s; for (; s < total_lowmem; s += PAGE_SIZE) { ktext = ((char *) v >= _stext && (char *) v < etext); diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c index 9d97db7b7cf..45d925360b8 100644 --- a/arch/powerpc/mm/ppc_mmu_32.c +++ b/arch/powerpc/mm/ppc_mmu_32.c @@ -95,16 +95,16 @@ unsigned long __init mmu_mapin_ram(void) break; } - setbat(2, KERNELBASE, 0, bl, _PAGE_RAM); - done = (unsigned long)bat_addrs[2].limit - KERNELBASE + 1; + setbat(2, PAGE_OFFSET, 0, bl, _PAGE_RAM); + done = (unsigned long)bat_addrs[2].limit - PAGE_OFFSET + 1; if ((done < tot) && !bat_addrs[3].limit) { /* use BAT3 to cover a bit more */ tot -= done; for (bl = 128<<10; bl < max_size; bl <<= 1) if (bl * 2 > tot) break; - setbat(3, KERNELBASE+done, done, bl, _PAGE_RAM); - done = (unsigned long)bat_addrs[3].limit - KERNELBASE + 1; + setbat(3, PAGE_OFFSET+done, done, bl, _PAGE_RAM); + done = (unsigned long)bat_addrs[3].limit - PAGE_OFFSET + 1; } return done; -- cgit v1.2.3-70-g09d2 From f8f50b1bddd49eb171398cfc543c957884dc6e35 Mon Sep 17 00:00:00 2001 From: Dale Farnsworth Date: Wed, 17 Dec 2008 10:09:26 +0000 Subject: powerpc/32: Wire up the trampoline code for kdump Wire up the trampoline code for ppc32 to relay exceptions from the vectors at address 0 to vectors at address 32MB, and modify Kconfig to enable Kdump support for all classic powerpcs. Signed-off-by: Dale Farnsworth Signed-off-by: Anton Vorontsov Signed-off-by: Paul Mackerras --- arch/powerpc/Kconfig | 2 +- arch/powerpc/include/asm/kdump.h | 13 +++++++++++++ arch/powerpc/kernel/setup_32.c | 2 ++ 3 files changed, 16 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index be4f99b7cbb..f7f5448f863 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -326,7 +326,7 @@ config KEXEC config CRASH_DUMP bool "Build a kdump crash kernel" - depends on PPC_MULTIPLATFORM && PPC64 && RELOCATABLE + depends on (PPC64 && RELOCATABLE) || 6xx help Build a kernel suitable for use as a kdump capture kernel. The same kernel binary can be used as production kernel and dump diff --git a/arch/powerpc/include/asm/kdump.h b/arch/powerpc/include/asm/kdump.h index b07ebb9784d..5ebfe5d3c61 100644 --- a/arch/powerpc/include/asm/kdump.h +++ b/arch/powerpc/include/asm/kdump.h @@ -1,6 +1,8 @@ #ifndef _PPC64_KDUMP_H #define _PPC64_KDUMP_H +#include + /* Kdump kernel runs at 32 MB, change at your peril. */ #define KDUMP_KERNELBASE 0x2000000 @@ -11,8 +13,19 @@ #ifdef CONFIG_CRASH_DUMP +/* + * On PPC64 translation is disabled during trampoline setup, so we use + * physical addresses. Though on PPC32 translation is already enabled, + * so we can't do the same. Luckily create_trampoline() creates relative + * branches, so we can just add the PAGE_OFFSET and don't worry about it. + */ +#ifdef __powerpc64__ #define KDUMP_TRAMPOLINE_START 0x0100 #define KDUMP_TRAMPOLINE_END 0x3000 +#else +#define KDUMP_TRAMPOLINE_START (0x0100 + PAGE_OFFSET) +#define KDUMP_TRAMPOLINE_END (0x3000 + PAGE_OFFSET) +#endif /* __powerpc64__ */ #define KDUMP_MIN_TCE_ENTRIES 2048 diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index d72ef39f2b3..9e1ca745d8f 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -126,6 +126,8 @@ notrace void __init machine_init(unsigned long dt_ptr) probe_machine(); + setup_kdump_trampoline(); + #ifdef CONFIG_6xx if (cpu_has_feature(CPU_FTR_CAN_DOZE) || cpu_has_feature(CPU_FTR_CAN_NAP)) -- cgit v1.2.3-70-g09d2 From fc5243d98ac2575ad14a974b3c097e9ba874c03d Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Thu, 25 Dec 2008 13:38:35 +0100 Subject: [S390] arch_setup_additional_pages arguments arch_setup_additional_pages currently gets two arguments, the binary format descripton and an indication if the process uses an executable stack or not. The second argument is not used by anybody, it could be removed without replacement. What actually does make sense is to pass an indication if the process uses the elf interpreter or not. The glibc code will not use anything from the vdso if the process does not use the dynamic linker, so for statically linked binaries the architecture backend can choose not to map the vdso. Acked-by: Ingo Molnar Signed-off-by: Martin Schwidefsky --- arch/powerpc/include/asm/elf.h | 2 +- arch/powerpc/kernel/vdso.c | 3 +-- arch/sh/include/asm/elf.h | 2 +- arch/sh/kernel/vsyscall/vsyscall.c | 3 +-- arch/x86/include/asm/elf.h | 2 +- arch/x86/vdso/vdso32-setup.c | 2 +- arch/x86/vdso/vma.c | 2 +- fs/binfmt_elf.c | 2 +- 8 files changed, 8 insertions(+), 10 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h index d812929390e..cd46f023ec6 100644 --- a/arch/powerpc/include/asm/elf.h +++ b/arch/powerpc/include/asm/elf.h @@ -267,7 +267,7 @@ extern int ucache_bsize; #define ARCH_HAS_SETUP_ADDITIONAL_PAGES struct linux_binprm; extern int arch_setup_additional_pages(struct linux_binprm *bprm, - int executable_stack); + int uses_interp); #define VDSO_AUX_ENT(a,b) NEW_AUX_ENT(a,b); #endif /* __KERNEL__ */ diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index 65639a43e64..f7ec7d0888f 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -184,8 +184,7 @@ static void dump_vdso_pages(struct vm_area_struct * vma) * This is called from binfmt_elf, we create the special vma for the * vDSO and insert it into the mm struct tree */ -int arch_setup_additional_pages(struct linux_binprm *bprm, - int executable_stack) +int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { struct mm_struct *mm = current->mm; struct page **vdso_pagelist; diff --git a/arch/sh/include/asm/elf.h b/arch/sh/include/asm/elf.h index 9eb9036a1bd..9381397ebeb 100644 --- a/arch/sh/include/asm/elf.h +++ b/arch/sh/include/asm/elf.h @@ -204,7 +204,7 @@ do { \ #define ARCH_HAS_SETUP_ADDITIONAL_PAGES struct linux_binprm; extern int arch_setup_additional_pages(struct linux_binprm *bprm, - int executable_stack); + int uses_interp); extern unsigned int vdso_enabled; extern void __kernel_vsyscall; diff --git a/arch/sh/kernel/vsyscall/vsyscall.c b/arch/sh/kernel/vsyscall/vsyscall.c index 95f4de0800e..3f7e415be86 100644 --- a/arch/sh/kernel/vsyscall/vsyscall.c +++ b/arch/sh/kernel/vsyscall/vsyscall.c @@ -59,8 +59,7 @@ int __init vsyscall_init(void) } /* Setup a VMA at program startup for the vsyscall page */ -int arch_setup_additional_pages(struct linux_binprm *bprm, - int executable_stack) +int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { struct mm_struct *mm = current->mm; unsigned long addr; diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 40ca1bea791..f51a3ddde01 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -325,7 +325,7 @@ struct linux_binprm; #define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1 extern int arch_setup_additional_pages(struct linux_binprm *bprm, - int executable_stack); + int uses_interp); extern int syscall32_setup_pages(struct linux_binprm *, int exstack); #define compat_arch_setup_additional_pages syscall32_setup_pages diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c index 513f330c583..1241f118ab5 100644 --- a/arch/x86/vdso/vdso32-setup.c +++ b/arch/x86/vdso/vdso32-setup.c @@ -310,7 +310,7 @@ int __init sysenter_setup(void) } /* Setup a VMA at program startup for the vsyscall page */ -int arch_setup_additional_pages(struct linux_binprm *bprm, int exstack) +int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { struct mm_struct *mm = current->mm; unsigned long addr; diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c index 257ba4a10ab..9c98cc6ba97 100644 --- a/arch/x86/vdso/vma.c +++ b/arch/x86/vdso/vma.c @@ -98,7 +98,7 @@ static unsigned long vdso_addr(unsigned long start, unsigned len) /* Setup a VMA at program startup for the vsyscall page. Not called for compat tasks */ -int arch_setup_additional_pages(struct linux_binprm *bprm, int exstack) +int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { struct mm_struct *mm = current->mm; unsigned long addr; diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 8fcfa398d35..95a76ff9e01 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -949,7 +949,7 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs) set_binfmt(&elf_format); #ifdef ARCH_HAS_SETUP_ADDITIONAL_PAGES - retval = arch_setup_additional_pages(bprm, executable_stack); + retval = arch_setup_additional_pages(bprm, !!elf_interpreter); if (retval < 0) { send_sig(SIGKILL, current, 0); goto out; -- cgit v1.2.3-70-g09d2 From 6ca4f7494bde078b2b730e28e4ea1dc36a772f70 Mon Sep 17 00:00:00 2001 From: Hollis Blanchard Date: Wed, 26 Nov 2008 10:19:26 -0600 Subject: powerpc: Force memory size to be a multiple of PAGE_SIZE Ensure that total memory size is page-aligned, because otherwise mark_bootmem() gets upset. This error case was triggered by using 64 KiB pages in the kernel while arch/powerpc/boot/4xx.c arbitrarily reduced the amount of memory by 4096 (to work around a chip bug that affects the last 256 bytes of physical memory). Signed-off-by: Hollis Blanchard Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/prom.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index d8266dd61dd..6f73c739f1e 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -1160,6 +1160,8 @@ static inline void __init phyp_dump_reserve_mem(void) {} void __init early_init_devtree(void *params) { + unsigned long limit; + DBG(" -> early_init_devtree(%p)\n", params); /* Setup flat device-tree pointer */ @@ -1200,7 +1202,19 @@ void __init early_init_devtree(void *params) early_reserve_mem(); phyp_dump_reserve_mem(); - lmb_enforce_memory_limit(memory_limit); + limit = memory_limit; + if (! limit) { + unsigned long memsize; + + /* Ensure that total memory size is page-aligned, because + * otherwise mark_bootmem() gets upset. */ + lmb_analyze(); + memsize = lmb_phys_mem_size(); + if ((memsize & PAGE_MASK) != memsize) + limit = memsize & PAGE_MASK; + } + lmb_enforce_memory_limit(limit); + lmb_analyze(); DBG("Phys. mem: %lx\n", lmb_phys_mem_size()); -- cgit v1.2.3-70-g09d2 From ca9153a3a2a7556d091dfe080e42b0e67881fff6 Mon Sep 17 00:00:00 2001 From: Ilya Yanok Date: Thu, 11 Dec 2008 04:55:41 +0300 Subject: powerpc/44x: Support 16K/64K base page sizes on 44x This adds support for 16k and 64k page sizes on PowerPC 44x processors. The PGDIR table is much smaller than a page when using 16k or 64k pages (512 and 32 bytes respectively) so we allocate the PGDIR with kzalloc() instead of __get_free_pages(). One PTE table covers rather a large memory area when using 16k or 64k pages (32MB or 512MB respectively), so we can easily put FIXMAP and PKMAP in the area covered by one PTE table. Signed-off-by: Yuri Tikhonov Signed-off-by: Vladimir Panfilov Signed-off-by: Ilya Yanok Acked-by: Josh Boyer Signed-off-by: Paul Mackerras --- arch/powerpc/Kconfig | 58 ++++++++++++++++++++++++++-------- arch/powerpc/include/asm/highmem.h | 19 +++++++++-- arch/powerpc/include/asm/mmu-44x.h | 17 ++++++++++ arch/powerpc/include/asm/page.h | 13 +++++--- arch/powerpc/include/asm/page_32.h | 7 ++-- arch/powerpc/kernel/asm-offsets.c | 4 +++ arch/powerpc/kernel/head_44x.S | 23 ++++++++------ arch/powerpc/kernel/misc_32.S | 12 +++---- arch/powerpc/mm/pgtable_32.c | 23 ++++++++------ arch/powerpc/platforms/Kconfig.cputype | 2 +- 10 files changed, 130 insertions(+), 48 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index f7f5448f863..1af22579e3d 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -405,23 +405,53 @@ config PPC_HAS_HASH_64K depends on PPC64 default n -config PPC_64K_PAGES - bool "64k page size" - depends on PPC64 - select PPC_HAS_HASH_64K +choice + prompt "Page size" + default PPC_4K_PAGES help - This option changes the kernel logical page size to 64k. On machines - without processor support for 64k pages, the kernel will simulate - them by loading each individual 4k page on demand transparently, - while on hardware with such support, it will be used to map - normal application pages. + Select the kernel logical page size. Increasing the page size + will reduce software overhead at each page boundary, allow + hardware prefetch mechanisms to be more effective, and allow + larger dma transfers increasing IO efficiency and reducing + overhead. However the utilization of memory will increase. + For example, each cached file will using a multiple of the + page size to hold its contents and the difference between the + end of file and the end of page is wasted. + + Some dedicated systems, such as software raid serving with + accelerated calculations, have shown significant increases. + + If you configure a 64 bit kernel for 64k pages but the + processor does not support them, then the kernel will simulate + them with 4k pages, loading them on demand, but with the + reduced software overhead and larger internal fragmentation. + For the 32 bit kernel, a large page option will not be offered + unless it is supported by the configured processor. + + If unsure, choose 4K_PAGES. + +config PPC_4K_PAGES + bool "4k page size" + +config PPC_16K_PAGES + bool "16k page size" if 44x + +config PPC_64K_PAGES + bool "64k page size" if 44x || PPC_STD_MMU_64 + select PPC_HAS_HASH_64K if PPC_STD_MMU_64 + +endchoice config FORCE_MAX_ZONEORDER int "Maximum zone order" - range 9 64 if PPC_64K_PAGES - default "9" if PPC_64K_PAGES - range 13 64 if PPC64 && !PPC_64K_PAGES - default "13" if PPC64 && !PPC_64K_PAGES + range 9 64 if PPC_STD_MMU_64 && PPC_64K_PAGES + default "9" if PPC_STD_MMU_64 && PPC_64K_PAGES + range 13 64 if PPC_STD_MMU_64 && !PPC_64K_PAGES + default "13" if PPC_STD_MMU_64 && !PPC_64K_PAGES + range 9 64 if PPC_STD_MMU_32 && PPC_16K_PAGES + default "9" if PPC_STD_MMU_32 && PPC_16K_PAGES + range 7 64 if PPC_STD_MMU_32 && PPC_64K_PAGES + default "7" if PPC_STD_MMU_32 && PPC_64K_PAGES range 11 64 default "11" help @@ -441,7 +471,7 @@ config FORCE_MAX_ZONEORDER config PPC_SUBPAGE_PROT bool "Support setting protections for 4k subpages" - depends on PPC_64K_PAGES + depends on PPC_STD_MMU_64 && PPC_64K_PAGES help This option adds support for a system call to allow user programs to set access permissions (read/write, readonly, or no access) diff --git a/arch/powerpc/include/asm/highmem.h b/arch/powerpc/include/asm/highmem.h index fd97e501aa6..04e4a620952 100644 --- a/arch/powerpc/include/asm/highmem.h +++ b/arch/powerpc/include/asm/highmem.h @@ -38,9 +38,24 @@ extern pte_t *pkmap_page_table; * easily, subsequent pte tables have to be allocated in one physical * chunk of RAM. */ -#define LAST_PKMAP (1 << PTE_SHIFT) -#define LAST_PKMAP_MASK (LAST_PKMAP-1) +/* + * We use one full pte table with 4K pages. And with 16K/64K pages pte + * table covers enough memory (32MB and 512MB resp.) that both FIXMAP + * and PKMAP can be placed in single pte table. We use 1024 pages for + * PKMAP in case of 16K/64K pages. + */ +#ifdef CONFIG_PPC_4K_PAGES +#define PKMAP_ORDER PTE_SHIFT +#else +#define PKMAP_ORDER 10 +#endif +#define LAST_PKMAP (1 << PKMAP_ORDER) +#ifndef CONFIG_PPC_4K_PAGES +#define PKMAP_BASE (FIXADDR_START - PAGE_SIZE*(LAST_PKMAP + 1)) +#else #define PKMAP_BASE ((FIXADDR_START - PAGE_SIZE*(LAST_PKMAP + 1)) & PMD_MASK) +#endif +#define LAST_PKMAP_MASK (LAST_PKMAP-1) #define PKMAP_NR(virt) ((virt-PKMAP_BASE) >> PAGE_SHIFT) #define PKMAP_ADDR(nr) (PKMAP_BASE + ((nr) << PAGE_SHIFT)) diff --git a/arch/powerpc/include/asm/mmu-44x.h b/arch/powerpc/include/asm/mmu-44x.h index b21af32ac6d..8a97cfb08b7 100644 --- a/arch/powerpc/include/asm/mmu-44x.h +++ b/arch/powerpc/include/asm/mmu-44x.h @@ -4,6 +4,8 @@ * PPC440 support */ +#include + #define PPC44x_MMUCR_TID 0x000000ff #define PPC44x_MMUCR_STS 0x00010000 @@ -74,4 +76,19 @@ typedef struct { /* Size of the TLBs used for pinning in lowmem */ #define PPC_PIN_SIZE (1 << 28) /* 256M */ +#if (PAGE_SHIFT == 12) +#define PPC44x_TLBE_SIZE PPC44x_TLB_4K +#elif (PAGE_SHIFT == 14) +#define PPC44x_TLBE_SIZE PPC44x_TLB_16K +#elif (PAGE_SHIFT == 16) +#define PPC44x_TLBE_SIZE PPC44x_TLB_64K +#else +#error "Unsupported PAGE_SIZE" +#endif + +#define PPC44x_PGD_OFF_SHIFT (32 - PGDIR_SHIFT + PGD_T_LOG2) +#define PPC44x_PGD_OFF_MASK_BIT (PGDIR_SHIFT - PGD_T_LOG2) +#define PPC44x_PTE_ADD_SHIFT (32 - PGDIR_SHIFT + PTE_SHIFT + PTE_T_LOG2) +#define PPC44x_PTE_ADD_MASK_BIT (32 - PTE_T_LOG2 - PTE_SHIFT) + #endif /* _ASM_POWERPC_MMU_44X_H_ */ diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index c0b8d4a29a9..197d569f5bd 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -19,12 +19,15 @@ #include /* - * On PPC32 page size is 4K. For PPC64 we support either 4K or 64K software + * On regular PPC32 page size is 4K (but we support 4K/16K/64K pages + * on PPC44x). For PPC64 we support either 4K or 64K software * page size. When using 64K pages however, whether we are really supporting * 64K pages in HW or not is irrelevant to those definitions. */ -#ifdef CONFIG_PPC_64K_PAGES +#if defined(CONFIG_PPC_64K_PAGES) #define PAGE_SHIFT 16 +#elif defined(CONFIG_PPC_16K_PAGES) +#define PAGE_SHIFT 14 #else #define PAGE_SHIFT 12 #endif @@ -151,7 +154,7 @@ typedef struct { pte_basic_t pte; } pte_t; /* 64k pages additionally define a bigger "real PTE" type that gathers * the "second half" part of the PTE for pseudo 64k pages */ -#ifdef CONFIG_PPC_64K_PAGES +#if defined(CONFIG_PPC_64K_PAGES) && defined(CONFIG_PPC_STD_MMU_64) typedef struct { pte_t pte; unsigned long hidx; } real_pte_t; #else typedef struct { pte_t pte; } real_pte_t; @@ -191,10 +194,10 @@ typedef pte_basic_t pte_t; #define pte_val(x) (x) #define __pte(x) (x) -#ifdef CONFIG_PPC_64K_PAGES +#if defined(CONFIG_PPC_64K_PAGES) && defined(CONFIG_PPC_STD_MMU_64) typedef struct { pte_t pte; unsigned long hidx; } real_pte_t; #else -typedef unsigned long real_pte_t; +typedef pte_t real_pte_t; #endif diff --git a/arch/powerpc/include/asm/page_32.h b/arch/powerpc/include/asm/page_32.h index d77072a32cc..1458d950038 100644 --- a/arch/powerpc/include/asm/page_32.h +++ b/arch/powerpc/include/asm/page_32.h @@ -19,6 +19,8 @@ #define PTE_FLAGS_OFFSET 0 #endif +#define PTE_SHIFT (PAGE_SHIFT - PTE_T_LOG2) /* full page */ + #ifndef __ASSEMBLY__ /* * The basic type of a PTE - 64 bits for those CPUs with > 32 bit @@ -26,10 +28,8 @@ */ #ifdef CONFIG_PTE_64BIT typedef unsigned long long pte_basic_t; -#define PTE_SHIFT (PAGE_SHIFT - 3) /* 512 ptes per page */ #else typedef unsigned long pte_basic_t; -#define PTE_SHIFT (PAGE_SHIFT - 2) /* 1024 ptes per page */ #endif struct page; @@ -39,6 +39,9 @@ extern void copy_page(void *to, void *from); #include +#define PGD_T_LOG2 (__builtin_ffs(sizeof(pgd_t)) - 1) +#define PTE_T_LOG2 (__builtin_ffs(sizeof(pte_t)) - 1) + #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_PAGE_32_H */ diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index c05ab1d3e62..661d07d2146 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -380,6 +380,10 @@ int main(void) DEFINE(VCPU_FAULT_DEAR, offsetof(struct kvm_vcpu, arch.fault_dear)); DEFINE(VCPU_FAULT_ESR, offsetof(struct kvm_vcpu, arch.fault_esr)); #endif +#ifdef CONFIG_44x + DEFINE(PGD_T_LOG2, PGD_T_LOG2); + DEFINE(PTE_T_LOG2, PTE_T_LOG2); +#endif return 0; } diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S index bd4fe9e7278..b56fecc93a1 100644 --- a/arch/powerpc/kernel/head_44x.S +++ b/arch/powerpc/kernel/head_44x.S @@ -402,12 +402,14 @@ interrupt_base: rlwimi r13,r12,10,30,30 /* Load the PTE */ - rlwinm r12, r10, 13, 19, 29 /* Compute pgdir/pmd offset */ + /* Compute pgdir/pmd offset */ + rlwinm r12, r10, PPC44x_PGD_OFF_SHIFT, PPC44x_PGD_OFF_MASK_BIT, 29 lwzx r11, r12, r11 /* Get pgd/pmd entry */ rlwinm. r12, r11, 0, 0, 20 /* Extract pt base address */ beq 2f /* Bail if no table */ - rlwimi r12, r10, 23, 20, 28 /* Compute pte address */ + /* Compute pte address */ + rlwimi r12, r10, PPC44x_PTE_ADD_SHIFT, PPC44x_PTE_ADD_MASK_BIT, 28 lwz r11, 0(r12) /* Get high word of pte entry */ lwz r12, 4(r12) /* Get low word of pte entry */ @@ -496,12 +498,14 @@ tlb_44x_patch_hwater_D: /* Make up the required permissions */ li r13,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_HWEXEC - rlwinm r12, r10, 13, 19, 29 /* Compute pgdir/pmd offset */ + /* Compute pgdir/pmd offset */ + rlwinm r12, r10, PPC44x_PGD_OFF_SHIFT, PPC44x_PGD_OFF_MASK_BIT, 29 lwzx r11, r12, r11 /* Get pgd/pmd entry */ rlwinm. r12, r11, 0, 0, 20 /* Extract pt base address */ beq 2f /* Bail if no table */ - rlwimi r12, r10, 23, 20, 28 /* Compute pte address */ + /* Compute pte address */ + rlwimi r12, r10, PPC44x_PTE_ADD_SHIFT, PPC44x_PTE_ADD_MASK_BIT, 28 lwz r11, 0(r12) /* Get high word of pte entry */ lwz r12, 4(r12) /* Get low word of pte entry */ @@ -565,15 +569,16 @@ tlb_44x_patch_hwater_I: */ finish_tlb_load: /* Combine RPN & ERPN an write WS 0 */ - rlwimi r11,r12,0,0,19 + rlwimi r11,r12,0,0,31-PAGE_SHIFT tlbwe r11,r13,PPC44x_TLB_XLAT /* * Create WS1. This is the faulting address (EPN), * page size, and valid flag. */ - li r11,PPC44x_TLB_VALID | PPC44x_TLB_4K - rlwimi r10,r11,0,20,31 /* Insert valid and page size*/ + li r11,PPC44x_TLB_VALID | PPC44x_TLBE_SIZE + /* Insert valid and page size */ + rlwimi r10,r11,0,PPC44x_PTE_ADD_MASK_BIT,31 tlbwe r10,r13,PPC44x_TLB_PAGEID /* Write PAGEID */ /* And WS 2 */ @@ -645,12 +650,12 @@ _GLOBAL(set_context) * goes at the beginning of the data segment, which is page-aligned. */ .data - .align 12 + .align PAGE_SHIFT .globl sdata sdata: .globl empty_zero_page empty_zero_page: - .space 4096 + .space PAGE_SIZE /* * To support >32-bit physical addresses, we use an 8KB pgdir. diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index ae0d084b6a2..15f28e0de78 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -426,8 +426,8 @@ _GLOBAL(__flush_dcache_icache) BEGIN_FTR_SECTION blr END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) - rlwinm r3,r3,0,0,19 /* Get page base address */ - li r4,4096/L1_CACHE_BYTES /* Number of lines in a page */ + rlwinm r3,r3,0,0,31-PAGE_SHIFT /* Get page base address */ + li r4,PAGE_SIZE/L1_CACHE_BYTES /* Number of lines in a page */ mtctr r4 mr r6,r3 0: dcbst 0,r3 /* Write line to ram */ @@ -467,8 +467,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) rlwinm r0,r10,0,28,26 /* clear DR */ mtmsr r0 isync - rlwinm r3,r3,0,0,19 /* Get page base address */ - li r4,4096/L1_CACHE_BYTES /* Number of lines in a page */ + rlwinm r3,r3,0,0,31-PAGE_SHIFT /* Get page base address */ + li r4,PAGE_SIZE/L1_CACHE_BYTES /* Number of lines in a page */ mtctr r4 mr r6,r3 0: dcbst 0,r3 /* Write line to ram */ @@ -492,7 +492,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) * void clear_pages(void *page, int order) ; */ _GLOBAL(clear_pages) - li r0,4096/L1_CACHE_BYTES + li r0,PAGE_SIZE/L1_CACHE_BYTES slw r0,r0,r4 mtctr r0 #ifdef CONFIG_8xx @@ -550,7 +550,7 @@ _GLOBAL(copy_page) dcbt r5,r4 li r11,L1_CACHE_BYTES+4 #endif /* MAX_COPY_PREFETCH */ - li r0,4096/L1_CACHE_BYTES - MAX_COPY_PREFETCH + li r0,PAGE_SIZE/L1_CACHE_BYTES - MAX_COPY_PREFETCH crclr 4*cr0+eq 2: mtctr r0 diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index 8cba46fc9e3..38ff35f2142 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -68,24 +68,29 @@ extern unsigned long p_mapped_by_tlbcam(unsigned long pa); #define p_mapped_by_tlbcam(x) (0UL) #endif /* HAVE_TLBCAM */ -#ifdef CONFIG_PTE_64BIT -/* Some processors use an 8kB pgdir because they have 8-byte Linux PTEs. */ -#define PGDIR_ORDER 1 -#else -#define PGDIR_ORDER 0 -#endif +#define PGDIR_ORDER (32 + PGD_T_LOG2 - PGDIR_SHIFT) pgd_t *pgd_alloc(struct mm_struct *mm) { pgd_t *ret; - ret = (pgd_t *)__get_free_pages(GFP_KERNEL|__GFP_ZERO, PGDIR_ORDER); + /* pgdir take page or two with 4K pages and a page fraction otherwise */ +#ifndef CONFIG_PPC_4K_PAGES + ret = (pgd_t *)kzalloc(1 << PGDIR_ORDER, GFP_KERNEL); +#else + ret = (pgd_t *)__get_free_pages(GFP_KERNEL|__GFP_ZERO, + PGDIR_ORDER - PAGE_SHIFT); +#endif return ret; } void pgd_free(struct mm_struct *mm, pgd_t *pgd) { - free_pages((unsigned long)pgd, PGDIR_ORDER); +#ifndef CONFIG_PPC_4K_PAGES + kfree((void *)pgd); +#else + free_pages((unsigned long)pgd, PGDIR_ORDER - PAGE_SHIFT); +#endif } __init_refok pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) @@ -385,7 +390,7 @@ void kernel_map_pages(struct page *page, int numpages, int enable) #endif /* CONFIG_DEBUG_PAGEALLOC */ static int fixmaps; -unsigned long FIXADDR_TOP = 0xfffff000; +unsigned long FIXADDR_TOP = (-PAGE_SIZE); EXPORT_SYMBOL(FIXADDR_TOP); void __set_fixmap (enum fixed_addresses idx, phys_addr_t phys, pgprot_t flags) diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index db61dafb924..3d0c776f888 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -212,7 +212,7 @@ config PPC_MMU_NOHASH config PPC_MM_SLICES bool - default y if HUGETLB_PAGE || PPC_64K_PAGES + default y if HUGETLB_PAGE || (PPC_STD_MMU_64 && PPC_64K_PAGES) default n config VIRT_CPU_ACCOUNTING -- cgit v1.2.3-70-g09d2