From 31fe5bf66a09c36e95b4c04291249b251b52f2d4 Mon Sep 17 00:00:00 2001 From: Segher Boessenkool Date: Thu, 17 May 2007 01:12:16 +1000 Subject: [POWERPC] Fix VDSO compile warning Maybe the type should have been char[] instead of __u8[] in the first place, but this will do. Signed-off-by: Segher Boessenkool Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/vdso.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index 4245579..cef01e4 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -670,7 +670,7 @@ static int __init vdso_init(void) /* * Fill up the "systemcfg" stuff for backward compatiblity */ - strcpy(vdso_data->eye_catcher, "SYSTEMCFG:PPC64"); + strcpy((char *)vdso_data->eye_catcher, "SYSTEMCFG:PPC64"); vdso_data->version.major = SYSTEMCFG_MAJOR; vdso_data->version.minor = SYSTEMCFG_MINOR; vdso_data->processor = mfspr(SPRN_PVR); -- cgit v1.1 From 3d5134ee8341bffc4f539049abb9e90d469b448d Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 4 Jun 2007 15:15:36 +1000 Subject: [POWERPC] Rewrite IO allocation & mapping on powerpc64 This rewrites pretty much from scratch the handling of MMIO and PIO space allocations on powerpc64. The main goals are: - Get rid of imalloc and use more common code where possible - Simplify the current mess so that PIO space is allocated and mapped in a single place for PCI bridges - Handle allocation constraints of PIO for all bridges including hot plugged ones within the 2GB space reserved for IO ports, so that devices on hotplugged busses will now work with drivers that assume IO ports fit in an int. - Cleanup and separate tracking of the ISA space in the reserved low 64K of IO space. No ISA -> Nothing mapped there. I booted a cell blade with IDE on PIO and MMIO and a dual G5 so far, that's it :-) With this patch, all allocations are done using the code in mm/vmalloc.c, though we use the low level __get_vm_area with explicit start/stop constraints in order to manage separate areas for vmalloc/vmap, ioremap, and PCI IOs. This greatly simplifies a lot of things, as you can see in the diffstat of that patch :-) A new pair of functions pcibios_map/unmap_io_space() now replace all of the previous code that used to manipulate PCI IOs space. The allocation is done at mapping time, which is now called from scan_phb's, just before the devices are probed (instead of after, which is by itself a bug fix). The only other caller is the PCI hotplug code for hot adding PCI-PCI bridges (slots). imalloc is gone, as is the "sub-allocation" thing, but I do beleive that hotplug should still work in the sense that the space allocation is always done by the PHB, but if you unmap a child bus of this PHB (which seems to be possible), then the code should properly tear down all the HPTE mappings for that area of the PHB allocated IO space. I now always reserve the first 64K of IO space for the bridge with the ISA bus on it. I have moved the code for tracking ISA in a separate file which should also make it smarter if we ever are capable of hot unplugging or re-plugging an ISA bridge. This should have a side effect on platforms like powermac where VGA IOs will no longer work. This is done on purpose though as they would have worked semi-randomly before. The idea at this point is to isolate drivers that might need to access those and fix them by providing a proper function to obtain an offset to the legacy IOs of a given bus. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/Makefile | 2 +- arch/powerpc/kernel/isa-bridge.c | 271 +++++++++++++++++++++++++++++ arch/powerpc/kernel/of_platform.c | 8 - arch/powerpc/kernel/pci_64.c | 358 ++++++++++++++------------------------ arch/powerpc/kernel/rtas_pci.c | 7 +- 5 files changed, 400 insertions(+), 246 deletions(-) create mode 100644 arch/powerpc/kernel/isa-bridge.c (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 3e779f0..08ce7de 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -65,7 +65,7 @@ obj-$(CONFIG_PPC_UDBG_16550) += legacy_serial.o udbg_16550.o module-$(CONFIG_PPC64) += module_64.o obj-$(CONFIG_MODULES) += $(module-y) -pci64-$(CONFIG_PPC64) += pci_64.o pci_dn.o +pci64-$(CONFIG_PPC64) += pci_64.o pci_dn.o isa-bridge.o pci32-$(CONFIG_PPC32) := pci_32.o obj-$(CONFIG_PCI) += $(pci64-y) $(pci32-y) obj-$(CONFIG_PCI_MSI) += msi.o diff --git a/arch/powerpc/kernel/isa-bridge.c b/arch/powerpc/kernel/isa-bridge.c new file mode 100644 index 0000000..f0f49d1 --- /dev/null +++ b/arch/powerpc/kernel/isa-bridge.c @@ -0,0 +1,271 @@ +/* + * Routines for tracking a legacy ISA bridge + * + * Copyrigh 2007 Benjamin Herrenschmidt , IBM Corp. + * + * Some bits and pieces moved over from pci_64.c + * + * Copyrigh 2003 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. + */ + +#define DEBUG + +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include + +unsigned long isa_io_base; /* NULL if no ISA bus */ +EXPORT_SYMBOL(isa_io_base); + +/* Cached ISA bridge dev. */ +static struct device_node *isa_bridge_devnode; +struct pci_dev *isa_bridge_pcidev; +EXPORT_SYMBOL_GPL(isa_bridge_pcidev); + +#define ISA_SPACE_MASK 0x1 +#define ISA_SPACE_IO 0x1 + +static void __devinit pci_process_ISA_OF_ranges(struct device_node *isa_node, + unsigned long phb_io_base_phys) +{ + /* We should get some saner parsing here and remove these structs */ + struct pci_address { + u32 a_hi; + u32 a_mid; + u32 a_lo; + }; + + struct isa_address { + u32 a_hi; + u32 a_lo; + }; + + struct isa_range { + struct isa_address isa_addr; + struct pci_address pci_addr; + unsigned int size; + }; + + const struct isa_range *range; + unsigned long pci_addr; + unsigned int isa_addr; + unsigned int size; + int rlen = 0; + + range = of_get_property(isa_node, "ranges", &rlen); + if (range == NULL || (rlen < sizeof(struct isa_range))) + goto inval_range; + + /* From "ISA Binding to 1275" + * The ranges property is laid out as an array of elements, + * each of which comprises: + * cells 0 - 1: an ISA address + * cells 2 - 4: a PCI address + * (size depending on dev->n_addr_cells) + * cell 5: the size of the range + */ + if ((range->isa_addr.a_hi && ISA_SPACE_MASK) != ISA_SPACE_IO) { + range++; + rlen -= sizeof(struct isa_range); + if (rlen < sizeof(struct isa_range)) + goto inval_range; + } + if ((range->isa_addr.a_hi && ISA_SPACE_MASK) != ISA_SPACE_IO) + goto inval_range; + + isa_addr = range->isa_addr.a_lo; + pci_addr = (unsigned long) range->pci_addr.a_mid << 32 | + range->pci_addr.a_lo; + + /* Assume these are both zero. Note: We could fix that and + * do a proper parsing instead ... oh well, that will do for + * now as nobody uses fancy mappings for ISA bridges + */ + if ((pci_addr != 0) || (isa_addr != 0)) { + printk(KERN_ERR "unexpected isa to pci mapping: %s\n", + __FUNCTION__); + return; + } + + /* Align size and make sure it's cropped to 64K */ + size = PAGE_ALIGN(range->size); + if (size > 0x10000) + size = 0x10000; + + printk(KERN_ERR "no ISA IO ranges or unexpected isa range," + "mapping 64k\n"); + + __ioremap_at(phb_io_base_phys, (void *)ISA_IO_BASE, + size, _PAGE_NO_CACHE|_PAGE_GUARDED); + return; + +inval_range: + printk(KERN_ERR "no ISA IO ranges or unexpected isa range," + "mapping 64k\n"); + __ioremap_at(phb_io_base_phys, (void *)ISA_IO_BASE, + 0x10000, _PAGE_NO_CACHE|_PAGE_GUARDED); +} + + +/** + * isa_bridge_find_early - Find and map the ISA IO space early before + * main PCI discovery. This is optionally called by + * the arch code when adding PCI PHBs to get early + * access to ISA IO ports + */ +void __init isa_bridge_find_early(struct pci_controller *hose) +{ + struct device_node *np, *parent = NULL, *tmp; + + /* If we already have an ISA bridge, bail off */ + if (isa_bridge_devnode != NULL) + return; + + /* For each "isa" node in the system. Note : we do a search by + * type and not by name. It might be better to do by name but that's + * what the code used to do and I don't want to break too much at + * once. We can look into changing that separately + */ + for_each_node_by_type(np, "isa") { + /* Look for our hose being a parent */ + for (parent = of_get_parent(np); parent;) { + if (parent == hose->arch_data) { + of_node_put(parent); + break; + } + tmp = parent; + parent = of_get_parent(parent); + of_node_put(tmp); + } + if (parent != NULL) + break; + } + if (np == NULL) + return; + isa_bridge_devnode = np; + + /* Now parse the "ranges" property and setup the ISA mapping */ + pci_process_ISA_OF_ranges(np, hose->io_base_phys); + + /* Set the global ISA io base to indicate we have an ISA bridge */ + isa_io_base = ISA_IO_BASE; + + pr_debug("ISA bridge (early) is %s\n", np->full_name); +} + +/** + * isa_bridge_find_late - Find and map the ISA IO space upon discovery of + * a new ISA bridge + */ +static void __devinit isa_bridge_find_late(struct pci_dev *pdev, + struct device_node *devnode) +{ + struct pci_controller *hose = pci_bus_to_host(pdev->bus); + + /* Store ISA device node and PCI device */ + isa_bridge_devnode = of_node_get(devnode); + isa_bridge_pcidev = pdev; + + /* Now parse the "ranges" property and setup the ISA mapping */ + pci_process_ISA_OF_ranges(devnode, hose->io_base_phys); + + /* Set the global ISA io base to indicate we have an ISA bridge */ + isa_io_base = ISA_IO_BASE; + + pr_debug("ISA bridge (late) is %s on %s\n", + devnode->full_name, pci_name(pdev)); +} + +/** + * isa_bridge_remove - Remove/unmap an ISA bridge + */ +static void isa_bridge_remove(void) +{ + pr_debug("ISA bridge removed !\n"); + + /* Clear the global ISA io base to indicate that we have no more + * ISA bridge. Note that drivers don't quite handle that, though + * we should probably do something about it. But do we ever really + * have ISA bridges being removed on machines using legacy devices ? + */ + isa_io_base = ISA_IO_BASE; + + /* Clear references to the bridge */ + of_node_put(isa_bridge_devnode); + isa_bridge_devnode = NULL; + isa_bridge_pcidev = NULL; + + /* Unmap the ISA area */ + __iounmap_at((void *)ISA_IO_BASE, 0x10000); +} + +/** + * isa_bridge_notify - Get notified of PCI devices addition/removal + */ +static int __devinit isa_bridge_notify(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct device *dev = data; + struct pci_dev *pdev = to_pci_dev(dev); + struct device_node *devnode = pci_device_to_OF_node(pdev); + + switch(action) { + case BUS_NOTIFY_ADD_DEVICE: + /* Check if we have an early ISA device, without PCI dev */ + if (isa_bridge_devnode && isa_bridge_devnode == devnode && + !isa_bridge_pcidev) { + pr_debug("ISA bridge PCI attached: %s\n", + pci_name(pdev)); + isa_bridge_pcidev = pdev; + } + + /* Check if we have no ISA device, and this happens to be one, + * register it as such if it has an OF device + */ + if (!isa_bridge_devnode && devnode && devnode->type && + !strcmp(devnode->type, "isa")) + isa_bridge_find_late(pdev, devnode); + + return 0; + case BUS_NOTIFY_DEL_DEVICE: + /* Check if this our existing ISA device */ + if (pdev == isa_bridge_pcidev || + (devnode && devnode == isa_bridge_devnode)) + isa_bridge_remove(); + return 0; + } + return 0; +} + +static struct notifier_block isa_bridge_notifier = { + .notifier_call = isa_bridge_notify +}; + +/** + * isa_bridge_init - register to be notified of ISA bridge addition/removal + * + */ +static int __init isa_bridge_init(void) +{ + if (firmware_has_feature(FW_FEATURE_ISERIES)) + return 0; + bus_register_notifier(&pci_bus_type, &isa_bridge_notifier); + return 0; +} +arch_initcall(isa_bridge_init); diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c index d454f61..9536ed7 100644 --- a/arch/powerpc/kernel/of_platform.c +++ b/arch/powerpc/kernel/of_platform.c @@ -427,14 +427,6 @@ static int __devinit of_pci_phb_probe(struct of_device *dev, /* Process "ranges" property */ pci_process_bridge_OF_ranges(phb, dev->node, 0); - /* Setup IO space. We use the non-dynamic version of that code here, - * which doesn't quite support unplugging. Next kernel release will - * have a better fix for this. - * Note also that we don't do ISA, this will also be fixed with a - * more massive rework. - */ - pci_setup_phb_io(phb, pci_io_base == 0); - /* Init pci_dn data structures */ pci_devs_phb_init_dynamic(phb); diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index 249cca2..6ae67eb 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -11,7 +11,7 @@ * 2 of the License, or (at your option) any later version. */ -#undef DEBUG +#define DEBUG #include #include @@ -22,6 +22,7 @@ #include #include #include +#include #include #include @@ -41,35 +42,26 @@ unsigned long pci_probe_only = 1; int pci_assign_all_buses = 0; -static int pci_initial_scan_done; static void fixup_resource(struct resource *res, struct pci_dev *dev); static void do_bus_setup(struct pci_bus *bus); -static void phbs_remap_io(void); /* pci_io_base -- the base address from which io bars are offsets. * This is the lowest I/O base address (so bar values are always positive), * and it *must* be the start of ISA space if an ISA bus exists because - * ISA drivers use hard coded offsets. If no ISA bus exists a dummy - * page is mapped and isa_io_limit prevents access to it. + * ISA drivers use hard coded offsets. If no ISA bus exists nothing + * is mapped on the first 64K of IO space */ -unsigned long isa_io_base; /* NULL if no ISA bus */ -EXPORT_SYMBOL(isa_io_base); -unsigned long pci_io_base; +unsigned long pci_io_base = ISA_IO_BASE; EXPORT_SYMBOL(pci_io_base); -void iSeries_pcibios_init(void); - LIST_HEAD(hose_list); static struct dma_mapping_ops *pci_dma_ops; +/* XXX kill that some day ... */ int global_phb_number; /* Global phb counter */ -/* Cached ISA bridge dev. */ -struct pci_dev *ppc64_isabridge_dev = NULL; -EXPORT_SYMBOL_GPL(ppc64_isabridge_dev); - void set_pci_dma_ops(struct dma_mapping_ops *dma_ops) { pci_dma_ops = dma_ops; @@ -100,7 +92,7 @@ void pcibios_resource_to_bus(struct pci_dev *dev, struct pci_bus_region *region return; if (res->flags & IORESOURCE_IO) - offset = (unsigned long)hose->io_base_virt - pci_io_base; + offset = (unsigned long)hose->io_base_virt - _IO_BASE; if (res->flags & IORESOURCE_MEM) offset = hose->pci_mem_offset; @@ -119,7 +111,7 @@ void pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res, return; if (res->flags & IORESOURCE_IO) - offset = (unsigned long)hose->io_base_virt - pci_io_base; + offset = (unsigned long)hose->io_base_virt - _IO_BASE; if (res->flags & IORESOURCE_MEM) offset = hose->pci_mem_offset; @@ -156,7 +148,7 @@ void pcibios_align_resource(void *data, struct resource *res, if (res->flags & IORESOURCE_IO) { unsigned long offset = (unsigned long)hose->io_base_virt - - pci_io_base; + _IO_BASE; /* Make sure we start at our min on all hoses */ if (start - offset < PCIBIOS_MIN_IO) start = PCIBIOS_MIN_IO + offset; @@ -535,10 +527,16 @@ void __devinit scan_phb(struct pci_controller *hose) bus->secondary = hose->first_busno; hose->bus = bus; + if (!firmware_has_feature(FW_FEATURE_ISERIES)) + pcibios_map_io_space(bus); + bus->resource[0] = res = &hose->io_resource; - if (res->flags && request_resource(&ioport_resource, res)) + if (res->flags && request_resource(&ioport_resource, res)) { printk(KERN_ERR "Failed to request PCI IO region " "on PCI domain %04x\n", hose->global_number); + DBG("res->start = 0x%016lx, res->end = 0x%016lx\n", + res->start, res->end); + } for (i = 0; i < 3; ++i) { res = &hose->mem_resources[i]; @@ -596,17 +594,6 @@ static int __init pcibios_init(void) if (ppc_md.pcibios_fixup) ppc_md.pcibios_fixup(); - /* Cache the location of the ISA bridge (if we have one) */ - ppc64_isabridge_dev = pci_get_class(PCI_CLASS_BRIDGE_ISA << 8, NULL); - if (ppc64_isabridge_dev != NULL) - printk(KERN_DEBUG "ISA bridge at %s\n", pci_name(ppc64_isabridge_dev)); - - if (!firmware_has_feature(FW_FEATURE_ISERIES)) - /* map in PCI I/O space */ - phbs_remap_io(); - - pci_initial_scan_done = 1; - printk(KERN_DEBUG "PCI: Probing PCI hardware done\n"); return 0; @@ -711,7 +698,7 @@ static struct resource *__pci_mmap_make_offset(struct pci_dev *dev, #endif res_bit = IORESOURCE_MEM; } else { - io_offset = (unsigned long)hose->io_base_virt - pci_io_base; + io_offset = (unsigned long)hose->io_base_virt - _IO_BASE; *offset += io_offset; res_bit = IORESOURCE_IO; } @@ -881,76 +868,6 @@ void pcibios_add_platform_entries(struct pci_dev *pdev) device_create_file(&pdev->dev, &dev_attr_devspec); } -#define ISA_SPACE_MASK 0x1 -#define ISA_SPACE_IO 0x1 - -static void __devinit pci_process_ISA_OF_ranges(struct device_node *isa_node, - unsigned long phb_io_base_phys, - void __iomem * phb_io_base_virt) -{ - /* Remove these asap */ - - struct pci_address { - u32 a_hi; - u32 a_mid; - u32 a_lo; - }; - - struct isa_address { - u32 a_hi; - u32 a_lo; - }; - - struct isa_range { - struct isa_address isa_addr; - struct pci_address pci_addr; - unsigned int size; - }; - - const struct isa_range *range; - unsigned long pci_addr; - unsigned int isa_addr; - unsigned int size; - int rlen = 0; - - range = of_get_property(isa_node, "ranges", &rlen); - if (range == NULL || (rlen < sizeof(struct isa_range))) { - printk(KERN_ERR "no ISA ranges or unexpected isa range size," - "mapping 64k\n"); - __ioremap_explicit(phb_io_base_phys, - (unsigned long)phb_io_base_virt, - 0x10000, _PAGE_NO_CACHE | _PAGE_GUARDED); - return; - } - - /* From "ISA Binding to 1275" - * The ranges property is laid out as an array of elements, - * each of which comprises: - * cells 0 - 1: an ISA address - * cells 2 - 4: a PCI address - * (size depending on dev->n_addr_cells) - * cell 5: the size of the range - */ - if ((range->isa_addr.a_hi && ISA_SPACE_MASK) == ISA_SPACE_IO) { - isa_addr = range->isa_addr.a_lo; - pci_addr = (unsigned long) range->pci_addr.a_mid << 32 | - range->pci_addr.a_lo; - - /* Assume these are both zero */ - if ((pci_addr != 0) || (isa_addr != 0)) { - printk(KERN_ERR "unexpected isa to pci mapping: %s\n", - __FUNCTION__); - return; - } - - size = PAGE_ALIGN(range->size); - - __ioremap_explicit(phb_io_base_phys, - (unsigned long) phb_io_base_virt, - size, _PAGE_NO_CACHE | _PAGE_GUARDED); - } -} - void __devinit pci_process_bridge_OF_ranges(struct pci_controller *hose, struct device_node *dev, int prim) { @@ -1045,155 +962,122 @@ void __devinit pci_process_bridge_OF_ranges(struct pci_controller *hose, } } -void __devinit pci_setup_phb_io(struct pci_controller *hose, int primary) +#ifdef CONFIG_HOTPLUG + +int pcibios_unmap_io_space(struct pci_bus *bus) { - unsigned long size = hose->pci_io_size; - unsigned long io_virt_offset; - struct resource *res; - struct device_node *isa_dn; + struct pci_controller *hose; - if (size == 0) - return; + WARN_ON(bus == NULL); - hose->io_base_virt = reserve_phb_iospace(size); - DBG("phb%d io_base_phys 0x%lx io_base_virt 0x%lx\n", - hose->global_number, hose->io_base_phys, - (unsigned long) hose->io_base_virt); - - if (primary) { - pci_io_base = (unsigned long)hose->io_base_virt; - isa_dn = of_find_node_by_type(NULL, "isa"); - if (isa_dn) { - isa_io_base = pci_io_base; - pci_process_ISA_OF_ranges(isa_dn, hose->io_base_phys, - hose->io_base_virt); - of_node_put(isa_dn); - } - } + /* If this is not a PHB, we only flush the hash table over + * the area mapped by this bridge. We don't play with the PTE + * mappings since we might have to deal with sub-page alignemnts + * so flushing the hash table is the only sane way to make sure + * that no hash entries are covering that removed bridge area + * while still allowing other busses overlapping those pages + */ + if (bus->self) { + struct resource *res = bus->resource[0]; - io_virt_offset = (unsigned long)hose->io_base_virt - pci_io_base; - res = &hose->io_resource; - res->start += io_virt_offset; - res->end += io_virt_offset; + DBG("IO unmapping for PCI-PCI bridge %s\n", + pci_name(bus->self)); - /* If this is called after the initial PCI scan, then we need to - * proceed to IO mappings now - */ - if (pci_initial_scan_done) - __ioremap_explicit(hose->io_base_phys, - (unsigned long)hose->io_base_virt, - hose->pci_io_size, - _PAGE_NO_CACHE | _PAGE_GUARDED); -} + __flush_hash_table_range(&init_mm, res->start + _IO_BASE, + res->end - res->start + 1); + return 0; + } -void __devinit pci_setup_phb_io_dynamic(struct pci_controller *hose, - int primary) -{ - unsigned long size = hose->pci_io_size; - unsigned long io_virt_offset; - struct resource *res; + /* Get the host bridge */ + hose = pci_bus_to_host(bus); - if (size == 0) - return; + /* Check if we have IOs allocated */ + if (hose->io_base_alloc == 0) + return 0; - hose->io_base_virt = __ioremap(hose->io_base_phys, size, - _PAGE_NO_CACHE | _PAGE_GUARDED); - DBG("phb%d io_base_phys 0x%lx io_base_virt 0x%lx\n", - hose->global_number, hose->io_base_phys, - (unsigned long) hose->io_base_virt); + DBG("IO unmapping for PHB %s\n", + ((struct device_node *)hose->arch_data)->full_name); + DBG(" alloc=0x%p\n", hose->io_base_alloc); - if (primary) - pci_io_base = (unsigned long)hose->io_base_virt; + /* This is a PHB, we fully unmap the IO area */ + vunmap(hose->io_base_alloc); - io_virt_offset = (unsigned long)hose->io_base_virt - pci_io_base; - res = &hose->io_resource; - res->start += io_virt_offset; - res->end += io_virt_offset; + return 0; } +EXPORT_SYMBOL_GPL(pcibios_unmap_io_space); +#endif /* CONFIG_HOTPLUG */ -static int get_bus_io_range(struct pci_bus *bus, unsigned long *start_phys, - unsigned long *start_virt, unsigned long *size) +int __devinit pcibios_map_io_space(struct pci_bus *bus) { - struct pci_controller *hose = pci_bus_to_host(bus); - struct resource *res; - - if (bus->self) - res = bus->resource[0]; - else - /* Root Bus */ - res = &hose->io_resource; - - if (res->end == 0 && res->start == 0) - return 1; + struct vm_struct *area; + unsigned long phys_page; + unsigned long size_page; + unsigned long io_virt_offset; + struct pci_controller *hose; - *start_virt = pci_io_base + res->start; - *start_phys = *start_virt + hose->io_base_phys - - (unsigned long) hose->io_base_virt; + WARN_ON(bus == NULL); - if (res->end > res->start) - *size = res->end - res->start + 1; - else { - printk("%s(): unexpected region 0x%lx->0x%lx\n", - __FUNCTION__, res->start, res->end); - return 1; + /* If this not a PHB, nothing to do, page tables still exist and + * 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); + return 0; } - return 0; -} - -int unmap_bus_range(struct pci_bus *bus) -{ - unsigned long start_phys; - unsigned long start_virt; - unsigned long size; - - if (!bus) { - printk(KERN_ERR "%s() expected bus\n", __FUNCTION__); - return 1; - } - - if (get_bus_io_range(bus, &start_phys, &start_virt, &size)) - return 1; - if (__iounmap_explicit((void __iomem *) start_virt, size)) - return 1; + /* Get the host bridge */ + hose = pci_bus_to_host(bus); + phys_page = _ALIGN_DOWN(hose->io_base_phys, PAGE_SIZE); + size_page = _ALIGN_UP(hose->pci_io_size, PAGE_SIZE); - return 0; -} -EXPORT_SYMBOL(unmap_bus_range); + /* Make sure IO area address is clear */ + hose->io_base_alloc = NULL; -int remap_bus_range(struct pci_bus *bus) -{ - unsigned long start_phys; - unsigned long start_virt; - unsigned long size; + /* If there's no IO to map on that bus, get away too */ + if (hose->pci_io_size == 0 || hose->io_base_phys == 0) + return 0; - if (!bus) { - printk(KERN_ERR "%s() expected bus\n", __FUNCTION__); - return 1; - } - - - if (get_bus_io_range(bus, &start_phys, &start_virt, &size)) - return 1; - if (start_phys == 0) - return 1; - printk(KERN_DEBUG "mapping IO %lx -> %lx, size: %lx\n", start_phys, start_virt, size); - if (__ioremap_explicit(start_phys, start_virt, size, - _PAGE_NO_CACHE | _PAGE_GUARDED)) - return 1; + /* Let's allocate some IO space for that guy. We don't pass + * VM_IOREMAP because we don't care about alignment tricks that + * the core does in that case. Maybe we should due to stupid card + * with incomplete address decoding but I'd rather not deal with + * those outside of the reserved 64K legacy region. + */ + area = __get_vm_area(size_page, 0, PHB_IO_BASE, PHB_IO_END); + if (area == NULL) + return -ENOMEM; + hose->io_base_alloc = area->addr; + hose->io_base_virt = (void __iomem *)(area->addr + + hose->io_base_phys - phys_page); + + DBG("IO mapping for PHB %s\n", + ((struct device_node *)hose->arch_data)->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); + + /* Establish the mapping */ + if (__ioremap_at(phys_page, area->addr, size_page, + _PAGE_NO_CACHE | _PAGE_GUARDED) == NULL) + return -ENOMEM; + + /* Fixup hose IO resource */ + io_virt_offset = (unsigned long)hose->io_base_virt - _IO_BASE; + 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); return 0; } -EXPORT_SYMBOL(remap_bus_range); - -static void phbs_remap_io(void) -{ - struct pci_controller *hose, *tmp; - - list_for_each_entry_safe(hose, tmp, &hose_list, list_node) - remap_bus_range(hose->bus); -} +EXPORT_SYMBOL_GPL(pcibios_map_io_space); static void __devinit fixup_resource(struct resource *res, struct pci_dev *dev) { @@ -1201,8 +1085,7 @@ static void __devinit fixup_resource(struct resource *res, struct pci_dev *dev) unsigned long offset; if (res->flags & IORESOURCE_IO) { - offset = (unsigned long)hose->io_base_virt - pci_io_base; - + offset = (unsigned long)hose->io_base_virt - _IO_BASE; res->start += offset; res->end += offset; } else if (res->flags & IORESOURCE_MEM) { @@ -1217,9 +1100,20 @@ void __devinit pcibios_fixup_device_resources(struct pci_dev *dev, /* Update device resources. */ int i; - for (i = 0; i < PCI_NUM_RESOURCES; i++) - if (dev->resource[i].flags) - fixup_resource(&dev->resource[i], dev); + DBG("%s: Fixup resources:\n", pci_name(dev)); + for (i = 0; i < PCI_NUM_RESOURCES; i++) { + struct resource *res = &dev->resource[i]; + if (!res->flags) + continue; + + DBG(" 0x%02x < %08lx:0x%016lx...0x%016lx\n", + i, res->flags, res->start, res->end); + + fixup_resource(res, dev); + + DBG(" > %08lx:0x%016lx...0x%016lx\n", + res->flags, res->start, res->end); + } } EXPORT_SYMBOL(pcibios_fixup_device_resources); @@ -1360,7 +1254,7 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar, return; if (rsrc->flags & IORESOURCE_IO) - offset = (unsigned long)hose->io_base_virt - pci_io_base; + offset = (unsigned long)hose->io_base_virt - _IO_BASE; /* We pass a fully fixed up address to userland for MMIO instead of * a BAR value because X is lame and expects to be able to use that @@ -1410,7 +1304,7 @@ unsigned long pci_address_to_pio(phys_addr_t address) if (address >= hose->io_base_phys && address < (hose->io_base_phys + hose->pci_io_size)) { unsigned long base = - (unsigned long)hose->io_base_virt - pci_io_base; + (unsigned long)hose->io_base_virt - _IO_BASE; return base + (address - hose->io_base_phys); } } diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c index f228682..a5de621 100644 --- a/arch/powerpc/kernel/rtas_pci.c +++ b/arch/powerpc/kernel/rtas_pci.c @@ -278,10 +278,8 @@ void __init find_and_init_phbs(void) { struct device_node *node; struct pci_controller *phb; - unsigned int index; struct device_node *root = of_find_node_by_path("/"); - index = 0; for (node = of_get_next_child(root, NULL); node != NULL; node = of_get_next_child(root, node)) { @@ -295,8 +293,7 @@ void __init find_and_init_phbs(void) continue; rtas_setup_phb(phb); pci_process_bridge_OF_ranges(phb, node, 0); - pci_setup_phb_io(phb, index == 0); - index++; + isa_bridge_find_early(phb); } of_node_put(root); @@ -335,7 +332,7 @@ int pcibios_remove_root_bus(struct pci_controller *phb) return 1; } - rc = unmap_bus_range(b); + rc = pcibios_unmap_io_space(b); if (rc) { printk(KERN_ERR "%s: failed to unmap IO on bus %s\n", __FUNCTION__, b->name); -- cgit v1.1 From 0b3d5c48a98f7bd2d38962f5a67b480ac5656fb9 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 4 Jun 2007 15:15:39 +1000 Subject: [POWERPC] Disable broken PPC_PTRACE_GETFPREGS on 32 bits The handling of PPC_PTRACE_GETFPREGS is broken on 32 bits kernel, it will only return half of the registers. Since that call didn't initially exist for 32 bits kernel (added recently), rather than fixing it, let's just remove it. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/ptrace.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index bf76562..36db6f5 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -434,6 +434,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) break; } +#ifdef CONFIG_PPC64 case PPC_PTRACE_GETFPREGS: { /* Get FPRs 0 - 31. */ int i; unsigned long *reg = &((unsigned long *)child->thread.fpr)[0]; @@ -467,6 +468,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) } break; } +#endif /* CONFIG_PPC64 */ #ifdef CONFIG_ALTIVEC case PTRACE_GETVRREGS: -- cgit v1.1 From acd89828484db6371202f5d292781ae6f832eda2 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 4 Jun 2007 15:15:41 +1000 Subject: [POWERPC] ptrace cleanups The powerpc ptrace code has some weirdness, like a ptrace-common.h file that is actually ppc64 only and some of the 32 bits code ifdef'ed inside ptrace.c. There are also separate implementations for things like get/set_vrregs for 32 and 64 bits which is totally unnecessary. This patch cleans that up a bit by having a ptrace-common.h which contains really common code (and makes a lot more code common), and ptrace-ppc32.h and ptrace-ppc64.h files that contain the few remaining different bits. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/ptrace-common.h | 89 ++++++++-------- arch/powerpc/kernel/ptrace-ppc32.h | 100 ++++++++++++++++++ arch/powerpc/kernel/ptrace-ppc64.h | 51 ++++++++++ arch/powerpc/kernel/ptrace.c | 198 +----------------------------------- arch/powerpc/kernel/ptrace32.c | 1 + 5 files changed, 197 insertions(+), 242 deletions(-) create mode 100644 arch/powerpc/kernel/ptrace-ppc32.h create mode 100644 arch/powerpc/kernel/ptrace-ppc64.h (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/ptrace-common.h b/arch/powerpc/kernel/ptrace-common.h index 8797ae7..f0746ec 100644 --- a/arch/powerpc/kernel/ptrace-common.h +++ b/arch/powerpc/kernel/ptrace-common.h @@ -1,5 +1,6 @@ /* * Copyright (c) 2002 Stephen Rothwell, IBM Coproration + * Copyright (c) 2007 Benjamin Herrenschmidt, IBM Coproration * Extracted from ptrace.c and ptrace32.c * * This file is subject to the terms and conditions of the GNU General @@ -7,15 +8,8 @@ * this archive for more details. */ -#ifndef _PPC64_PTRACE_COMMON_H -#define _PPC64_PTRACE_COMMON_H - -#include - -/* - * Set of msr bits that gdb can change on behalf of a process. - */ -#define MSR_DEBUGCHANGE (MSR_FE0 | MSR_SE | MSR_BE | MSR_FE1) +#ifndef _POWERPC_PTRACE_COMMON_H +#define _POWERPC_PTRACE_COMMON_H /* * Get contents of register REGNO in task TASK. @@ -24,18 +18,18 @@ static inline unsigned long get_reg(struct task_struct *task, int regno) { unsigned long tmp = 0; - /* - * Put the correct FP bits in, they might be wrong as a result - * of our lazy FP restore. - */ + if (task->thread.regs == NULL) + return -EIO; + if (regno == PT_MSR) { tmp = ((unsigned long *)task->thread.regs)[PT_MSR]; - tmp |= task->thread.fpexc_mode; - } else if (regno < (sizeof(struct pt_regs) / sizeof(unsigned long))) { - tmp = ((unsigned long *)task->thread.regs)[regno]; + return PT_MUNGE_MSR(tmp, task); } - return tmp; + if (regno < (sizeof(struct pt_regs) / sizeof(unsigned long))) + return ((unsigned long *)task->thread.regs)[regno]; + + return -EIO; } /* @@ -44,7 +38,10 @@ static inline unsigned long get_reg(struct task_struct *task, int regno) static inline int put_reg(struct task_struct *task, int regno, unsigned long data) { - if (regno < PT_SOFTE) { + if (task->thread.regs == NULL) + return -EIO; + + if (regno <= PT_MAX_PUT_REG) { if (regno == PT_MSR) data = (data & MSR_DEBUGCHANGE) | (task->thread.regs->msr & ~MSR_DEBUGCHANGE); @@ -54,21 +51,6 @@ static inline int put_reg(struct task_struct *task, int regno, return -EIO; } -static inline void set_single_step(struct task_struct *task) -{ - struct pt_regs *regs = task->thread.regs; - if (regs != NULL) - regs->msr |= MSR_SE; - set_tsk_thread_flag(task, TIF_SINGLESTEP); -} - -static inline void clear_single_step(struct task_struct *task) -{ - struct pt_regs *regs = task->thread.regs; - if (regs != NULL) - regs->msr &= ~MSR_SE; - clear_tsk_thread_flag(task, TIF_SINGLESTEP); -} #ifdef CONFIG_ALTIVEC /* @@ -137,25 +119,36 @@ static inline int set_vrregs(struct task_struct *task, return 0; } -#endif +#endif /* CONFIG_ALTIVEC */ -static inline int ptrace_set_debugreg(struct task_struct *task, - unsigned long addr, unsigned long data) +static inline void set_single_step(struct task_struct *task) { - /* We only support one DABR and no IABRS at the moment */ - if (addr > 0) - return -EINVAL; + struct pt_regs *regs = task->thread.regs; - /* The bottom 3 bits are flags */ - if ((data & ~0x7UL) >= TASK_SIZE) - return -EIO; + if (regs != NULL) { +#if defined(CONFIG_40x) || defined(CONFIG_BOOKE) + task->thread.dbcr0 = DBCR0_IDM | DBCR0_IC; + regs->msr |= MSR_DE; +#else + regs->msr |= MSR_SE; +#endif + } + set_tsk_thread_flag(task, TIF_SINGLESTEP); +} - /* Ensure translation is on */ - if (data && !(data & DABR_TRANSLATION)) - return -EIO; +static inline void clear_single_step(struct task_struct *task) +{ + struct pt_regs *regs = task->thread.regs; - task->thread.dabr = data; - return 0; + if (regs != NULL) { +#if defined(CONFIG_40x) || defined(CONFIG_BOOKE) + task->thread.dbcr0 = 0; + regs->msr &= ~MSR_DE; +#else + regs->msr &= ~MSR_SE; +#endif + } + clear_tsk_thread_flag(task, TIF_SINGLESTEP); } -#endif /* _PPC64_PTRACE_COMMON_H */ +#endif /* _POWERPC_PTRACE_COMMON_H */ diff --git a/arch/powerpc/kernel/ptrace-ppc32.h b/arch/powerpc/kernel/ptrace-ppc32.h new file mode 100644 index 0000000..24d7a2f --- /dev/null +++ b/arch/powerpc/kernel/ptrace-ppc32.h @@ -0,0 +1,100 @@ +/* + * Copyright (c) 2007 Benjamin Herrenschmidt, IBM Coproration + * Extracted from ptrace.c and ptrace32.c + * + * This file is subject to the terms and conditions of the GNU General + * Public License. See the file README.legal in the main directory of + * this archive for more details. + */ + +#ifndef _POWERPC_PTRACE_PPC32_H +#define _POWERPC_PTRACE_PPC32_H + +/* + * Set of msr bits that gdb can change on behalf of a process. + */ +#if defined(CONFIG_40x) || defined(CONFIG_BOOKE) +#define MSR_DEBUGCHANGE 0 +#else +#define MSR_DEBUGCHANGE (MSR_SE | MSR_BE) +#endif + +/* + * Max register writeable via put_reg + */ +#define PT_MAX_PUT_REG PT_MQ + +/* + * Munging of MSR on return from get_regs + * + * Nothing to do on ppc32 + */ +#define PT_MUNGE_MSR(msr, task) (msr) + + +#ifdef CONFIG_SPE + +/* + * For get_evrregs/set_evrregs functions 'data' has the following layout: + * + * struct { + * u32 evr[32]; + * u64 acc; + * u32 spefscr; + * } + */ + +/* + * Get contents of SPE register state in task TASK. + */ +static inline int get_evrregs(unsigned long *data, struct task_struct *task) +{ + int i; + + if (!access_ok(VERIFY_WRITE, data, 35 * sizeof(unsigned long))) + return -EFAULT; + + /* copy SPEFSCR */ + if (__put_user(task->thread.spefscr, &data[34])) + return -EFAULT; + + /* copy SPE registers EVR[0] .. EVR[31] */ + for (i = 0; i < 32; i++, data++) + if (__put_user(task->thread.evr[i], data)) + return -EFAULT; + + /* copy ACC */ + if (__put_user64(task->thread.acc, (unsigned long long *)data)) + return -EFAULT; + + return 0; +} + +/* + * Write contents of SPE register state into task TASK. + */ +static inline int set_evrregs(struct task_struct *task, unsigned long *data) +{ + int i; + + if (!access_ok(VERIFY_READ, data, 35 * sizeof(unsigned long))) + return -EFAULT; + + /* copy SPEFSCR */ + if (__get_user(task->thread.spefscr, &data[34])) + return -EFAULT; + + /* copy SPE registers EVR[0] .. EVR[31] */ + for (i = 0; i < 32; i++, data++) + if (__get_user(task->thread.evr[i], data)) + return -EFAULT; + /* copy ACC */ + if (__get_user64(task->thread.acc, (unsigned long long*)data)) + return -EFAULT; + + return 0; +} +#endif /* CONFIG_SPE */ + + +#endif /* _POWERPC_PTRACE_PPC32_H */ diff --git a/arch/powerpc/kernel/ptrace-ppc64.h b/arch/powerpc/kernel/ptrace-ppc64.h new file mode 100644 index 0000000..e450ce0 --- /dev/null +++ b/arch/powerpc/kernel/ptrace-ppc64.h @@ -0,0 +1,51 @@ +/* + * Copyright (c) 2002 Stephen Rothwell, IBM Coproration + * Extracted from ptrace.c and ptrace32.c + * + * This file is subject to the terms and conditions of the GNU General + * Public License. See the file README.legal in the main directory of + * this archive for more details. + */ + +#ifndef _POWERPC_PTRACE_PPC64_H +#define _POWERPC_PTRACE_PPC64_H + +/* + * Set of msr bits that gdb can change on behalf of a process. + */ +#define MSR_DEBUGCHANGE (MSR_FE0 | MSR_SE | MSR_BE | MSR_FE1) + +/* + * Max register writeable via put_reg + */ +#define PT_MAX_PUT_REG PT_CCR + +/* + * Munging of MSR on return from get_regs + * + * Put the correct FP bits in, they might be wrong as a result + * of our lazy FP restore. + */ + +#define PT_MUNGE_MSR(msr, task) ({ (msr) | (task)->thread.fpexc_mode; }) + +static inline int ptrace_set_debugreg(struct task_struct *task, + unsigned long addr, unsigned long data) +{ + /* We only support one DABR and no IABRS at the moment */ + if (addr > 0) + return -EINVAL; + + /* The bottom 3 bits are flags */ + if ((data & ~0x7UL) >= TASK_SIZE) + return -EIO; + + /* Ensure translation is on */ + if (data && !(data & DABR_TRANSLATION)) + return -EIO; + + task->thread.dabr = data; + return 0; +} + +#endif /* _POWERPC_PTRACE_PPC64_H */ diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 36db6f5..da53b0d 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -36,208 +36,18 @@ #include #ifdef CONFIG_PPC64 -#include "ptrace-common.h" -#endif - -#ifdef CONFIG_PPC32 -/* - * Set of msr bits that gdb can change on behalf of a process. - */ -#if defined(CONFIG_40x) || defined(CONFIG_BOOKE) -#define MSR_DEBUGCHANGE 0 +#include "ptrace-ppc64.h" #else -#define MSR_DEBUGCHANGE (MSR_SE | MSR_BE) +#include "ptrace-ppc32.h" #endif -#endif /* CONFIG_PPC32 */ + +#include "ptrace-common.h" /* * does not yet catch signals sent when the child dies. * in exit.c or in signal.c. */ -#ifdef CONFIG_PPC32 -/* - * Get contents of register REGNO in task TASK. - */ -static inline unsigned long get_reg(struct task_struct *task, int regno) -{ - if (regno < sizeof(struct pt_regs) / sizeof(unsigned long) - && task->thread.regs != NULL) - return ((unsigned long *)task->thread.regs)[regno]; - return (0); -} - -/* - * Write contents of register REGNO in task TASK. - */ -static inline int put_reg(struct task_struct *task, int regno, - unsigned long data) -{ - if (regno <= PT_MQ && task->thread.regs != NULL) { - if (regno == PT_MSR) - data = (data & MSR_DEBUGCHANGE) - | (task->thread.regs->msr & ~MSR_DEBUGCHANGE); - ((unsigned long *)task->thread.regs)[regno] = data; - return 0; - } - return -EIO; -} - -#ifdef CONFIG_ALTIVEC -/* - * Get contents of AltiVec register state in task TASK - */ -static inline int get_vrregs(unsigned long __user *data, struct task_struct *task) -{ - int i, j; - - if (!access_ok(VERIFY_WRITE, data, 133 * sizeof(unsigned long))) - return -EFAULT; - - /* copy AltiVec registers VR[0] .. VR[31] */ - for (i = 0; i < 32; i++) - for (j = 0; j < 4; j++, data++) - if (__put_user(task->thread.vr[i].u[j], data)) - return -EFAULT; - - /* copy VSCR */ - for (i = 0; i < 4; i++, data++) - if (__put_user(task->thread.vscr.u[i], data)) - return -EFAULT; - - /* copy VRSAVE */ - if (__put_user(task->thread.vrsave, data)) - return -EFAULT; - - return 0; -} - -/* - * Write contents of AltiVec register state into task TASK. - */ -static inline int set_vrregs(struct task_struct *task, unsigned long __user *data) -{ - int i, j; - - if (!access_ok(VERIFY_READ, data, 133 * sizeof(unsigned long))) - return -EFAULT; - - /* copy AltiVec registers VR[0] .. VR[31] */ - for (i = 0; i < 32; i++) - for (j = 0; j < 4; j++, data++) - if (__get_user(task->thread.vr[i].u[j], data)) - return -EFAULT; - - /* copy VSCR */ - for (i = 0; i < 4; i++, data++) - if (__get_user(task->thread.vscr.u[i], data)) - return -EFAULT; - - /* copy VRSAVE */ - if (__get_user(task->thread.vrsave, data)) - return -EFAULT; - - return 0; -} -#endif - -#ifdef CONFIG_SPE - -/* - * For get_evrregs/set_evrregs functions 'data' has the following layout: - * - * struct { - * u32 evr[32]; - * u64 acc; - * u32 spefscr; - * } - */ - -/* - * Get contents of SPE register state in task TASK. - */ -static inline int get_evrregs(unsigned long *data, struct task_struct *task) -{ - int i; - - if (!access_ok(VERIFY_WRITE, data, 35 * sizeof(unsigned long))) - return -EFAULT; - - /* copy SPEFSCR */ - if (__put_user(task->thread.spefscr, &data[34])) - return -EFAULT; - - /* copy SPE registers EVR[0] .. EVR[31] */ - for (i = 0; i < 32; i++, data++) - if (__put_user(task->thread.evr[i], data)) - return -EFAULT; - - /* copy ACC */ - if (__put_user64(task->thread.acc, (unsigned long long *)data)) - return -EFAULT; - - return 0; -} - -/* - * Write contents of SPE register state into task TASK. - */ -static inline int set_evrregs(struct task_struct *task, unsigned long *data) -{ - int i; - - if (!access_ok(VERIFY_READ, data, 35 * sizeof(unsigned long))) - return -EFAULT; - - /* copy SPEFSCR */ - if (__get_user(task->thread.spefscr, &data[34])) - return -EFAULT; - - /* copy SPE registers EVR[0] .. EVR[31] */ - for (i = 0; i < 32; i++, data++) - if (__get_user(task->thread.evr[i], data)) - return -EFAULT; - /* copy ACC */ - if (__get_user64(task->thread.acc, (unsigned long long*)data)) - return -EFAULT; - - return 0; -} -#endif /* CONFIG_SPE */ - -static inline void -set_single_step(struct task_struct *task) -{ - struct pt_regs *regs = task->thread.regs; - - if (regs != NULL) { -#if defined(CONFIG_40x) || defined(CONFIG_BOOKE) - task->thread.dbcr0 = DBCR0_IDM | DBCR0_IC; - regs->msr |= MSR_DE; -#else - regs->msr |= MSR_SE; -#endif - } - set_tsk_thread_flag(task, TIF_SINGLESTEP); -} - -static inline void -clear_single_step(struct task_struct *task) -{ - struct pt_regs *regs = task->thread.regs; - - if (regs != NULL) { -#if defined(CONFIG_40x) || defined(CONFIG_BOOKE) - task->thread.dbcr0 = 0; - regs->msr &= ~MSR_DE; -#else - regs->msr &= ~MSR_SE; -#endif - } - clear_tsk_thread_flag(task, TIF_SINGLESTEP); -} -#endif /* CONFIG_PPC32 */ - /* * Called by kernel/ptrace.c when detaching.. * diff --git a/arch/powerpc/kernel/ptrace32.c b/arch/powerpc/kernel/ptrace32.c index 9b9a230..1bf1f45 100644 --- a/arch/powerpc/kernel/ptrace32.c +++ b/arch/powerpc/kernel/ptrace32.c @@ -33,6 +33,7 @@ #include #include +#include "ptrace-ppc64.h" #include "ptrace-common.h" /* -- cgit v1.1 From e17666ba48f78ff10162d7448e7c92d668d8faf6 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 4 Jun 2007 15:15:43 +1000 Subject: [POWERPC] ptrace updates & new, better requests The powerpc ptrace interface is dodgy at best. We have defined our "own" versions of GETREGS/SETREGS/GETFPREGS/SETFPREGS that strangely take arguments in reverse order from other archs (in addition to having different request numbers) and have subtle issue, like not accessing all of the registers in their respective categories. This patch moves the implementation of those to a separate function in order to facilitate their deprecation in the future, and provides new ptrace requests that mirror the x86 and sparc ones and use the same numbers: PTRACE_GETREGS : returns an entire pt_regs (the whole thing, not only the 32 GPRs, though that doesn't include the FPRs etc... There's a compat version for 32 bits that returns a 32 bits compatible pt_regs (44 uints) PTRACE_SETREGS : sets an entire pt_regs (the whole thing, not only the 32 GPRs, though that doesn't include the FPRs etc... Some registers cannot be written to and will just be dropped, this is the same as with POKEUSR, that is anything above MQ on 32 bits and CCR on 64 bits. There is a compat version as well. PTRACE_GETFPREGS : returns all the FP registers -including- the FPSCR that is 33 doubles (regardless of 32/64 bits) PTRACE_SETFPREGS : sets all the FP registers -including- the FPSCR that is 33 doubles (regardless of 32/64 bits) And two that only exist on 64 bits kernels: PTRACE_GETREGS64 : Same as PTRACE_GETREGS, except there is no compat function, a 32 bits process will obtain the full 64 bits registers PTRACE_SETREGS64 : Same as PTRACE_SETREGS, except there is no compat function, a 32 bits process will set the full 64 bits registers The two later ones makes things easier to have a 32 bits debugger on a 64 bits program (or on a 32 bits program that uses the full 64 bits of the GPRs, which is possible though has issues that will be fixed in a later patch). Finally, while at it, the patch removes a whole bunch of code duplication between ptrace32.c and ptrace.c, in large part by having the former call into the later for all requests that don't need any special "compat" treatment. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/ptrace-common.h | 23 ++++ arch/powerpc/kernel/ptrace.c | 148 +++++++++++++++++--------- arch/powerpc/kernel/ptrace32.c | 204 +++++++++++++++--------------------- 3 files changed, 209 insertions(+), 166 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/ptrace-common.h b/arch/powerpc/kernel/ptrace-common.h index f0746ec..2188453 100644 --- a/arch/powerpc/kernel/ptrace-common.h +++ b/arch/powerpc/kernel/ptrace-common.h @@ -52,6 +52,29 @@ static inline int put_reg(struct task_struct *task, int regno, } +static inline int get_fpregs(void __user *data, + struct task_struct *task, + int has_fpscr) +{ + unsigned int count = has_fpscr ? 33 : 32; + + if (copy_to_user(data, task->thread.fpr, count * sizeof(double))) + return -EFAULT; + return 0; +} + +static inline int set_fpregs(void __user *data, + struct task_struct *task, + int has_fpscr) +{ + unsigned int count = has_fpscr ? 33 : 32; + + if (copy_from_user(task->thread.fpr, data, count * sizeof(double))) + return -EFAULT; + return 0; +} + + #ifdef CONFIG_ALTIVEC /* * Get/set all the altivec registers vr0..vr31, vscr, vrsave, in one go. diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index da53b0d..230d5f5 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -59,6 +59,62 @@ void ptrace_disable(struct task_struct *child) clear_single_step(child); } +/* + * Here are the old "legacy" powerpc specific getregs/setregs ptrace calls, + * we mark them as obsolete now, they will be removed in a future version + */ +static long arch_ptrace_old(struct task_struct *child, long request, long addr, + long data) +{ + int ret = -EPERM; + + switch(request) { + case PPC_PTRACE_GETREGS: { /* Get GPRs 0 - 31. */ + int i; + unsigned long *reg = &((unsigned long *)child->thread.regs)[0]; + unsigned long __user *tmp = (unsigned long __user *)addr; + + for (i = 0; i < 32; i++) { + ret = put_user(*reg, tmp); + if (ret) + break; + reg++; + tmp++; + } + break; + } + + case PPC_PTRACE_SETREGS: { /* Set GPRs 0 - 31. */ + int i; + unsigned long *reg = &((unsigned long *)child->thread.regs)[0]; + unsigned long __user *tmp = (unsigned long __user *)addr; + + for (i = 0; i < 32; i++) { + ret = get_user(*reg, tmp); + if (ret) + break; + reg++; + tmp++; + } + break; + } + + case PPC_PTRACE_GETFPREGS: { /* Get FPRs 0 - 31. */ + flush_fp_to_thread(child); + ret = get_fpregs((void __user *)addr, child, 0); + break; + } + + case PPC_PTRACE_SETFPREGS: { /* Get FPRs 0 - 31. */ + flush_fp_to_thread(child); + ret = set_fpregs((void __user *)addr, child, 0); + break; + } + + } + return ret; +} + long arch_ptrace(struct task_struct *child, long request, long addr, long data) { int ret = -EPERM; @@ -214,71 +270,58 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) ret = ptrace_detach(child, data); break; - case PPC_PTRACE_GETREGS: { /* Get GPRs 0 - 31. */ - int i; - unsigned long *reg = &((unsigned long *)child->thread.regs)[0]; - unsigned long __user *tmp = (unsigned long __user *)addr; - - for (i = 0; i < 32; i++) { - ret = put_user(*reg, tmp); - if (ret) - break; - reg++; - tmp++; +#ifdef CONFIG_PPC64 + case PTRACE_GETREGS64: +#endif + case PTRACE_GETREGS: { /* Get all pt_regs from the child. */ + int ui; + if (!access_ok(VERIFY_WRITE, (void __user *)data, + sizeof(struct pt_regs))) { + ret = -EIO; + break; + } + ret = 0; + for (ui = 0; ui < PT_REGS_COUNT; ui ++) { + ret |= __put_user(get_reg(child, ui), + (unsigned long __user *) data); + data += sizeof(long); } break; } - case PPC_PTRACE_SETREGS: { /* Set GPRs 0 - 31. */ - int i; - unsigned long *reg = &((unsigned long *)child->thread.regs)[0]; - unsigned long __user *tmp = (unsigned long __user *)addr; - - for (i = 0; i < 32; i++) { - ret = get_user(*reg, tmp); +#ifdef CONFIG_PPC64 + case PTRACE_SETREGS64: +#endif + case PTRACE_SETREGS: { /* Set all gp regs in the child. */ + unsigned long tmp; + int ui; + if (!access_ok(VERIFY_READ, (void __user *)data, + sizeof(struct pt_regs))) { + ret = -EIO; + break; + } + ret = 0; + for (ui = 0; ui < PT_REGS_COUNT; ui ++) { + ret = __get_user(tmp, (unsigned long __user *) data); if (ret) break; - reg++; - tmp++; + put_reg(child, ui, tmp); + data += sizeof(long); } break; } -#ifdef CONFIG_PPC64 - case PPC_PTRACE_GETFPREGS: { /* Get FPRs 0 - 31. */ - int i; - unsigned long *reg = &((unsigned long *)child->thread.fpr)[0]; - unsigned long __user *tmp = (unsigned long __user *)addr; - + case PTRACE_GETFPREGS: { /* Get the child FPU state (FPR0...31 + FPSCR) */ flush_fp_to_thread(child); - - for (i = 0; i < 32; i++) { - ret = put_user(*reg, tmp); - if (ret) - break; - reg++; - tmp++; - } + ret = get_fpregs((void __user *)data, child, 1); break; } - case PPC_PTRACE_SETFPREGS: { /* Get FPRs 0 - 31. */ - int i; - unsigned long *reg = &((unsigned long *)child->thread.fpr)[0]; - unsigned long __user *tmp = (unsigned long __user *)addr; - + case PTRACE_SETFPREGS: { /* Set the child FPU state (FPR0...31 + FPSCR) */ flush_fp_to_thread(child); - - for (i = 0; i < 32; i++) { - ret = get_user(*reg, tmp); - if (ret) - break; - reg++; - tmp++; - } + ret = set_fpregs((void __user *)data, child, 1); break; } -#endif /* CONFIG_PPC64 */ #ifdef CONFIG_ALTIVEC case PTRACE_GETVRREGS: @@ -311,11 +354,18 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) break; #endif + /* Old reverse args ptrace callss */ + case PPC_PTRACE_GETREGS: /* Get GPRs 0 - 31. */ + case PPC_PTRACE_SETREGS: /* Set GPRs 0 - 31. */ + case PPC_PTRACE_GETFPREGS: /* Get FPRs 0 - 31. */ + case PPC_PTRACE_SETFPREGS: /* Get FPRs 0 - 31. */ + ret = arch_ptrace_old(child, request, addr, data); + break; + default: ret = ptrace_request(child, request, addr, data); break; } - return ret; } diff --git a/arch/powerpc/kernel/ptrace32.c b/arch/powerpc/kernel/ptrace32.c index 1bf1f45..98b1580 100644 --- a/arch/powerpc/kernel/ptrace32.c +++ b/arch/powerpc/kernel/ptrace32.c @@ -41,6 +41,50 @@ * in exit.c or in signal.c. */ +/* + * Here are the old "legacy" powerpc specific getregs/setregs ptrace calls, + * we mark them as obsolete now, they will be removed in a future version + */ +static long compat_ptrace_old(struct task_struct *child, long request, + long addr, long data) +{ + int ret = -EPERM; + + switch(request) { + case PPC_PTRACE_GETREGS: { /* Get GPRs 0 - 31. */ + int i; + unsigned long *reg = &((unsigned long *)child->thread.regs)[0]; + unsigned int __user *tmp = (unsigned int __user *)addr; + + for (i = 0; i < 32; i++) { + ret = put_user(*reg, tmp); + if (ret) + break; + reg++; + tmp++; + } + break; + } + + case PPC_PTRACE_SETREGS: { /* Set GPRs 0 - 31. */ + int i; + unsigned long *reg = &((unsigned long *)child->thread.regs)[0]; + unsigned int __user *tmp = (unsigned int __user *)addr; + + for (i = 0; i < 32; i++) { + ret = get_user(*reg, tmp); + if (ret) + break; + reg++; + tmp++; + } + break; + } + + } + return ret; +} + long compat_sys_ptrace(int request, int pid, unsigned long addr, unsigned long data) { @@ -280,52 +324,6 @@ long compat_sys_ptrace(int request, int pid, unsigned long addr, break; } - case PTRACE_SYSCALL: /* continue and stop at next (return from) syscall */ - case PTRACE_CONT: { /* restart after signal. */ - ret = -EIO; - if (!valid_signal(data)) - break; - if (request == PTRACE_SYSCALL) - set_tsk_thread_flag(child, TIF_SYSCALL_TRACE); - else - clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE); - child->exit_code = data; - /* make sure the single step bit is not set. */ - clear_single_step(child); - wake_up_process(child); - ret = 0; - break; - } - - /* - * make the child exit. Best I can do is send it a sigkill. - * perhaps it should be put in the status that it wants to - * exit. - */ - case PTRACE_KILL: { - ret = 0; - if (child->exit_state == EXIT_ZOMBIE) /* already dead */ - break; - child->exit_code = SIGKILL; - /* make sure the single step bit is not set. */ - clear_single_step(child); - wake_up_process(child); - break; - } - - case PTRACE_SINGLESTEP: { /* set the trap flag. */ - ret = -EIO; - if (!valid_signal(data)) - break; - clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE); - set_single_step(child); - child->exit_code = data; - /* give it a chance to run. */ - wake_up_process(child); - ret = 0; - break; - } - case PTRACE_GET_DEBUGREG: { ret = -EINVAL; /* We only support one DABR and no IABRS at the moment */ @@ -335,95 +333,67 @@ long compat_sys_ptrace(int request, int pid, unsigned long addr, break; } - case PTRACE_SET_DEBUGREG: - ret = ptrace_set_debugreg(child, addr, data); - break; - - case PTRACE_DETACH: - ret = ptrace_detach(child, data); + case PTRACE_GETEVENTMSG: + ret = put_user(child->ptrace_message, (unsigned int __user *) data); break; - case PPC_PTRACE_GETREGS: { /* Get GPRs 0 - 31. */ - int i; - unsigned long *reg = &((unsigned long *)child->thread.regs)[0]; - unsigned int __user *tmp = (unsigned int __user *)addr; - - for (i = 0; i < 32; i++) { - ret = put_user(*reg, tmp); - if (ret) - break; - reg++; - tmp++; + case PTRACE_GETREGS: { /* Get all pt_regs from the child. */ + int ui; + if (!access_ok(VERIFY_WRITE, (void __user *)data, + PT_REGS_COUNT * sizeof(int))) { + ret = -EIO; + break; } - break; - } - - case PPC_PTRACE_SETREGS: { /* Set GPRs 0 - 31. */ - int i; - unsigned long *reg = &((unsigned long *)child->thread.regs)[0]; - unsigned int __user *tmp = (unsigned int __user *)addr; - - for (i = 0; i < 32; i++) { - ret = get_user(*reg, tmp); - if (ret) - break; - reg++; - tmp++; + ret = 0; + for (ui = 0; ui < PT_REGS_COUNT; ui ++) { + ret |= __put_user(get_reg(child, ui), + (unsigned int __user *) data); + data += sizeof(int); } break; } - case PPC_PTRACE_GETFPREGS: { /* Get FPRs 0 - 31. */ - int i; - unsigned long *reg = &((unsigned long *)child->thread.fpr)[0]; - unsigned int __user *tmp = (unsigned int __user *)addr; - - flush_fp_to_thread(child); - - for (i = 0; i < 32; i++) { - ret = put_user(*reg, tmp); - if (ret) - break; - reg++; - tmp++; + case PTRACE_SETREGS: { /* Set all gp regs in the child. */ + unsigned long tmp; + int ui; + if (!access_ok(VERIFY_READ, (void __user *)data, + PT_REGS_COUNT * sizeof(int))) { + ret = -EIO; + break; } - break; - } - - case PPC_PTRACE_SETFPREGS: { /* Get FPRs 0 - 31. */ - int i; - unsigned long *reg = &((unsigned long *)child->thread.fpr)[0]; - unsigned int __user *tmp = (unsigned int __user *)addr; - - flush_fp_to_thread(child); - - for (i = 0; i < 32; i++) { - ret = get_user(*reg, tmp); + ret = 0; + for (ui = 0; ui < PT_REGS_COUNT; ui ++) { + ret = __get_user(tmp, (unsigned int __user *) data); if (ret) break; - reg++; - tmp++; + put_reg(child, ui, tmp); + data += sizeof(int); } break; } - case PTRACE_GETEVENTMSG: - ret = put_user(child->ptrace_message, (unsigned int __user *) data); - break; - -#ifdef CONFIG_ALTIVEC + case PTRACE_GETFPREGS: + case PTRACE_SETFPREGS: case PTRACE_GETVRREGS: - /* Get the child altivec register state. */ - flush_altivec_to_thread(child); - ret = get_vrregs((unsigned long __user *)data, child); + case PTRACE_SETVRREGS: + case PTRACE_GETREGS64: + case PTRACE_SETREGS64: + case PPC_PTRACE_GETFPREGS: + case PPC_PTRACE_SETFPREGS: + case PTRACE_KILL: + case PTRACE_SINGLESTEP: + case PTRACE_DETACH: + case PTRACE_SET_DEBUGREG: + case PTRACE_SYSCALL: + case PTRACE_CONT: + ret = arch_ptrace(child, request, addr, data); break; - case PTRACE_SETVRREGS: - /* Set the child altivec register state. */ - flush_altivec_to_thread(child); - ret = set_vrregs(child, (unsigned long __user *)data); + /* Old reverse args ptrace callss */ + case PPC_PTRACE_GETREGS: /* Get GPRs 0 - 31. */ + case PPC_PTRACE_SETREGS: /* Set GPRs 0 - 31. */ + ret = compat_ptrace_old(child, request, addr, data); break; -#endif default: ret = ptrace_request(child, request, addr, data); -- cgit v1.1 From 865418d8e78b9c11c964157740b2596d6ffe9dfa Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 4 Jun 2007 15:15:44 +1000 Subject: [POWERPC] Uninline common ptrace bits This folds back the ptrace-common.h bits back into ptrace.c and removes that file. The FSL SPE bits from ptrace-ppc32.h are folded back in as well. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/ptrace-common.h | 177 --------------------------- arch/powerpc/kernel/ptrace-ppc32.h | 65 ---------- arch/powerpc/kernel/ptrace.c | 233 +++++++++++++++++++++++++++++++++++- arch/powerpc/kernel/ptrace32.c | 11 +- 4 files changed, 232 insertions(+), 254 deletions(-) delete mode 100644 arch/powerpc/kernel/ptrace-common.h (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/ptrace-common.h b/arch/powerpc/kernel/ptrace-common.h deleted file mode 100644 index 2188453..0000000 --- a/arch/powerpc/kernel/ptrace-common.h +++ /dev/null @@ -1,177 +0,0 @@ -/* - * Copyright (c) 2002 Stephen Rothwell, IBM Coproration - * Copyright (c) 2007 Benjamin Herrenschmidt, IBM Coproration - * Extracted from ptrace.c and ptrace32.c - * - * This file is subject to the terms and conditions of the GNU General - * Public License. See the file README.legal in the main directory of - * this archive for more details. - */ - -#ifndef _POWERPC_PTRACE_COMMON_H -#define _POWERPC_PTRACE_COMMON_H - -/* - * Get contents of register REGNO in task TASK. - */ -static inline unsigned long get_reg(struct task_struct *task, int regno) -{ - unsigned long tmp = 0; - - if (task->thread.regs == NULL) - return -EIO; - - if (regno == PT_MSR) { - tmp = ((unsigned long *)task->thread.regs)[PT_MSR]; - return PT_MUNGE_MSR(tmp, task); - } - - if (regno < (sizeof(struct pt_regs) / sizeof(unsigned long))) - return ((unsigned long *)task->thread.regs)[regno]; - - return -EIO; -} - -/* - * Write contents of register REGNO in task TASK. - */ -static inline int put_reg(struct task_struct *task, int regno, - unsigned long data) -{ - if (task->thread.regs == NULL) - return -EIO; - - if (regno <= PT_MAX_PUT_REG) { - if (regno == PT_MSR) - data = (data & MSR_DEBUGCHANGE) - | (task->thread.regs->msr & ~MSR_DEBUGCHANGE); - ((unsigned long *)task->thread.regs)[regno] = data; - return 0; - } - return -EIO; -} - - -static inline int get_fpregs(void __user *data, - struct task_struct *task, - int has_fpscr) -{ - unsigned int count = has_fpscr ? 33 : 32; - - if (copy_to_user(data, task->thread.fpr, count * sizeof(double))) - return -EFAULT; - return 0; -} - -static inline int set_fpregs(void __user *data, - struct task_struct *task, - int has_fpscr) -{ - unsigned int count = has_fpscr ? 33 : 32; - - if (copy_from_user(task->thread.fpr, data, count * sizeof(double))) - return -EFAULT; - return 0; -} - - -#ifdef CONFIG_ALTIVEC -/* - * Get/set all the altivec registers vr0..vr31, vscr, vrsave, in one go. - * The transfer totals 34 quadword. Quadwords 0-31 contain the - * corresponding vector registers. Quadword 32 contains the vscr as the - * last word (offset 12) within that quadword. Quadword 33 contains the - * vrsave as the first word (offset 0) within the quadword. - * - * This definition of the VMX state is compatible with the current PPC32 - * ptrace interface. This allows signal handling and ptrace to use the - * same structures. This also simplifies the implementation of a bi-arch - * (combined (32- and 64-bit) gdb. - */ - -/* - * Get contents of AltiVec register state in task TASK - */ -static inline int get_vrregs(unsigned long __user *data, - struct task_struct *task) -{ - unsigned long regsize; - - /* copy AltiVec registers VR[0] .. VR[31] */ - regsize = 32 * sizeof(vector128); - if (copy_to_user(data, task->thread.vr, regsize)) - return -EFAULT; - data += (regsize / sizeof(unsigned long)); - - /* copy VSCR */ - regsize = 1 * sizeof(vector128); - if (copy_to_user(data, &task->thread.vscr, regsize)) - return -EFAULT; - data += (regsize / sizeof(unsigned long)); - - /* copy VRSAVE */ - if (put_user(task->thread.vrsave, (u32 __user *)data)) - return -EFAULT; - - return 0; -} - -/* - * Write contents of AltiVec register state into task TASK. - */ -static inline int set_vrregs(struct task_struct *task, - unsigned long __user *data) -{ - unsigned long regsize; - - /* copy AltiVec registers VR[0] .. VR[31] */ - regsize = 32 * sizeof(vector128); - if (copy_from_user(task->thread.vr, data, regsize)) - return -EFAULT; - data += (regsize / sizeof(unsigned long)); - - /* copy VSCR */ - regsize = 1 * sizeof(vector128); - if (copy_from_user(&task->thread.vscr, data, regsize)) - return -EFAULT; - data += (regsize / sizeof(unsigned long)); - - /* copy VRSAVE */ - if (get_user(task->thread.vrsave, (u32 __user *)data)) - return -EFAULT; - - return 0; -} -#endif /* CONFIG_ALTIVEC */ - -static inline void set_single_step(struct task_struct *task) -{ - struct pt_regs *regs = task->thread.regs; - - if (regs != NULL) { -#if defined(CONFIG_40x) || defined(CONFIG_BOOKE) - task->thread.dbcr0 = DBCR0_IDM | DBCR0_IC; - regs->msr |= MSR_DE; -#else - regs->msr |= MSR_SE; -#endif - } - set_tsk_thread_flag(task, TIF_SINGLESTEP); -} - -static inline void clear_single_step(struct task_struct *task) -{ - struct pt_regs *regs = task->thread.regs; - - if (regs != NULL) { -#if defined(CONFIG_40x) || defined(CONFIG_BOOKE) - task->thread.dbcr0 = 0; - regs->msr &= ~MSR_DE; -#else - regs->msr &= ~MSR_SE; -#endif - } - clear_tsk_thread_flag(task, TIF_SINGLESTEP); -} - -#endif /* _POWERPC_PTRACE_COMMON_H */ diff --git a/arch/powerpc/kernel/ptrace-ppc32.h b/arch/powerpc/kernel/ptrace-ppc32.h index 24d7a2f..f1fd5b8 100644 --- a/arch/powerpc/kernel/ptrace-ppc32.h +++ b/arch/powerpc/kernel/ptrace-ppc32.h @@ -32,69 +32,4 @@ #define PT_MUNGE_MSR(msr, task) (msr) -#ifdef CONFIG_SPE - -/* - * For get_evrregs/set_evrregs functions 'data' has the following layout: - * - * struct { - * u32 evr[32]; - * u64 acc; - * u32 spefscr; - * } - */ - -/* - * Get contents of SPE register state in task TASK. - */ -static inline int get_evrregs(unsigned long *data, struct task_struct *task) -{ - int i; - - if (!access_ok(VERIFY_WRITE, data, 35 * sizeof(unsigned long))) - return -EFAULT; - - /* copy SPEFSCR */ - if (__put_user(task->thread.spefscr, &data[34])) - return -EFAULT; - - /* copy SPE registers EVR[0] .. EVR[31] */ - for (i = 0; i < 32; i++, data++) - if (__put_user(task->thread.evr[i], data)) - return -EFAULT; - - /* copy ACC */ - if (__put_user64(task->thread.acc, (unsigned long long *)data)) - return -EFAULT; - - return 0; -} - -/* - * Write contents of SPE register state into task TASK. - */ -static inline int set_evrregs(struct task_struct *task, unsigned long *data) -{ - int i; - - if (!access_ok(VERIFY_READ, data, 35 * sizeof(unsigned long))) - return -EFAULT; - - /* copy SPEFSCR */ - if (__get_user(task->thread.spefscr, &data[34])) - return -EFAULT; - - /* copy SPE registers EVR[0] .. EVR[31] */ - for (i = 0; i < 32; i++, data++) - if (__get_user(task->thread.evr[i], data)) - return -EFAULT; - /* copy ACC */ - if (__get_user64(task->thread.acc, (unsigned long long*)data)) - return -EFAULT; - - return 0; -} -#endif /* CONFIG_SPE */ - - #endif /* _POWERPC_PTRACE_PPC32_H */ diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 230d5f5..875bfda 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -41,14 +41,235 @@ #include "ptrace-ppc32.h" #endif -#include "ptrace-common.h" - /* * does not yet catch signals sent when the child dies. * in exit.c or in signal.c. */ /* + * Get contents of register REGNO in task TASK. + */ +unsigned long ptrace_get_reg(struct task_struct *task, int regno) +{ + unsigned long tmp = 0; + + if (task->thread.regs == NULL) + return -EIO; + + if (regno == PT_MSR) { + tmp = ((unsigned long *)task->thread.regs)[PT_MSR]; + return PT_MUNGE_MSR(tmp, task); + } + + if (regno < (sizeof(struct pt_regs) / sizeof(unsigned long))) + return ((unsigned long *)task->thread.regs)[regno]; + + return -EIO; +} + +/* + * Write contents of register REGNO in task TASK. + */ +int ptrace_put_reg(struct task_struct *task, int regno, unsigned long data) +{ + if (task->thread.regs == NULL) + return -EIO; + + if (regno <= PT_MAX_PUT_REG) { + if (regno == PT_MSR) + data = (data & MSR_DEBUGCHANGE) + | (task->thread.regs->msr & ~MSR_DEBUGCHANGE); + ((unsigned long *)task->thread.regs)[regno] = data; + return 0; + } + return -EIO; +} + + +static int get_fpregs(void __user *data, struct task_struct *task, + int has_fpscr) +{ + unsigned int count = has_fpscr ? 33 : 32; + + if (copy_to_user(data, task->thread.fpr, count * sizeof(double))) + return -EFAULT; + return 0; +} + +static int set_fpregs(void __user *data, struct task_struct *task, + int has_fpscr) +{ + unsigned int count = has_fpscr ? 33 : 32; + + if (copy_from_user(task->thread.fpr, data, count * sizeof(double))) + return -EFAULT; + return 0; +} + + +#ifdef CONFIG_ALTIVEC +/* + * Get/set all the altivec registers vr0..vr31, vscr, vrsave, in one go. + * The transfer totals 34 quadword. Quadwords 0-31 contain the + * corresponding vector registers. Quadword 32 contains the vscr as the + * last word (offset 12) within that quadword. Quadword 33 contains the + * vrsave as the first word (offset 0) within the quadword. + * + * This definition of the VMX state is compatible with the current PPC32 + * ptrace interface. This allows signal handling and ptrace to use the + * same structures. This also simplifies the implementation of a bi-arch + * (combined (32- and 64-bit) gdb. + */ + +/* + * Get contents of AltiVec register state in task TASK + */ +static int get_vrregs(unsigned long __user *data, struct task_struct *task) +{ + unsigned long regsize; + + /* copy AltiVec registers VR[0] .. VR[31] */ + regsize = 32 * sizeof(vector128); + if (copy_to_user(data, task->thread.vr, regsize)) + return -EFAULT; + data += (regsize / sizeof(unsigned long)); + + /* copy VSCR */ + regsize = 1 * sizeof(vector128); + if (copy_to_user(data, &task->thread.vscr, regsize)) + return -EFAULT; + data += (regsize / sizeof(unsigned long)); + + /* copy VRSAVE */ + if (put_user(task->thread.vrsave, (u32 __user *)data)) + return -EFAULT; + + return 0; +} + +/* + * Write contents of AltiVec register state into task TASK. + */ +static int set_vrregs(struct task_struct *task, unsigned long __user *data) +{ + unsigned long regsize; + + /* copy AltiVec registers VR[0] .. VR[31] */ + regsize = 32 * sizeof(vector128); + if (copy_from_user(task->thread.vr, data, regsize)) + return -EFAULT; + data += (regsize / sizeof(unsigned long)); + + /* copy VSCR */ + regsize = 1 * sizeof(vector128); + if (copy_from_user(&task->thread.vscr, data, regsize)) + return -EFAULT; + data += (regsize / sizeof(unsigned long)); + + /* copy VRSAVE */ + if (get_user(task->thread.vrsave, (u32 __user *)data)) + return -EFAULT; + + return 0; +} +#endif /* CONFIG_ALTIVEC */ + +#ifdef CONFIG_SPE + +/* + * For get_evrregs/set_evrregs functions 'data' has the following layout: + * + * struct { + * u32 evr[32]; + * u64 acc; + * u32 spefscr; + * } + */ + +/* + * Get contents of SPE register state in task TASK. + */ +static int get_evrregs(unsigned long *data, struct task_struct *task) +{ + int i; + + if (!access_ok(VERIFY_WRITE, data, 35 * sizeof(unsigned long))) + return -EFAULT; + + /* copy SPEFSCR */ + if (__put_user(task->thread.spefscr, &data[34])) + return -EFAULT; + + /* copy SPE registers EVR[0] .. EVR[31] */ + for (i = 0; i < 32; i++, data++) + if (__put_user(task->thread.evr[i], data)) + return -EFAULT; + + /* copy ACC */ + if (__put_user64(task->thread.acc, (unsigned long long *)data)) + return -EFAULT; + + return 0; +} + +/* + * Write contents of SPE register state into task TASK. + */ +static int set_evrregs(struct task_struct *task, unsigned long *data) +{ + int i; + + if (!access_ok(VERIFY_READ, data, 35 * sizeof(unsigned long))) + return -EFAULT; + + /* copy SPEFSCR */ + if (__get_user(task->thread.spefscr, &data[34])) + return -EFAULT; + + /* copy SPE registers EVR[0] .. EVR[31] */ + for (i = 0; i < 32; i++, data++) + if (__get_user(task->thread.evr[i], data)) + return -EFAULT; + /* copy ACC */ + if (__get_user64(task->thread.acc, (unsigned long long*)data)) + return -EFAULT; + + return 0; +} +#endif /* CONFIG_SPE */ + + +static void set_single_step(struct task_struct *task) +{ + struct pt_regs *regs = task->thread.regs; + + if (regs != NULL) { +#if defined(CONFIG_40x) || defined(CONFIG_BOOKE) + task->thread.dbcr0 = DBCR0_IDM | DBCR0_IC; + regs->msr |= MSR_DE; +#else + regs->msr |= MSR_SE; +#endif + } + set_tsk_thread_flag(task, TIF_SINGLESTEP); +} + +static void clear_single_step(struct task_struct *task) +{ + struct pt_regs *regs = task->thread.regs; + + if (regs != NULL) { +#if defined(CONFIG_40x) || defined(CONFIG_BOOKE) + task->thread.dbcr0 = 0; + regs->msr &= ~MSR_DE; +#else + regs->msr &= ~MSR_SE; +#endif + } + clear_tsk_thread_flag(task, TIF_SINGLESTEP); +} + +/* * Called by kernel/ptrace.c when detaching.. * * Make sure single step bits etc are not set. @@ -154,7 +375,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) CHECK_FULL_REGS(child->thread.regs); #endif if (index < PT_FPR0) { - tmp = get_reg(child, (int) index); + tmp = ptrace_get_reg(child, (int) index); } else { flush_fp_to_thread(child); tmp = ((unsigned long *)child->thread.fpr)[index - PT_FPR0]; @@ -195,7 +416,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) if (index == PT_ORIG_R3) break; if (index < PT_FPR0) { - ret = put_reg(child, index, data); + ret = ptrace_put_reg(child, index, data); } else { flush_fp_to_thread(child); ((unsigned long *)child->thread.fpr)[index - PT_FPR0] = data; @@ -282,7 +503,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) } ret = 0; for (ui = 0; ui < PT_REGS_COUNT; ui ++) { - ret |= __put_user(get_reg(child, ui), + ret |= __put_user(ptrace_get_reg(child, ui), (unsigned long __user *) data); data += sizeof(long); } @@ -305,7 +526,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) ret = __get_user(tmp, (unsigned long __user *) data); if (ret) break; - put_reg(child, ui, tmp); + ptrace_put_reg(child, ui, tmp); data += sizeof(long); } break; diff --git a/arch/powerpc/kernel/ptrace32.c b/arch/powerpc/kernel/ptrace32.c index 98b1580..4511b42 100644 --- a/arch/powerpc/kernel/ptrace32.c +++ b/arch/powerpc/kernel/ptrace32.c @@ -34,7 +34,6 @@ #include #include "ptrace-ppc64.h" -#include "ptrace-common.h" /* * does not yet catch signals sent when the child dies. @@ -168,7 +167,7 @@ long compat_sys_ptrace(int request, int pid, unsigned long addr, break; if (index < PT_FPR0) { - tmp = get_reg(child, index); + tmp = ptrace_get_reg(child, index); } else { flush_fp_to_thread(child); /* @@ -215,7 +214,7 @@ long compat_sys_ptrace(int request, int pid, unsigned long addr, flush_fp_to_thread(child); tmp = ((unsigned long int *)child->thread.fpr)[numReg - PT_FPR0]; } else { /* register within PT_REGS struct */ - tmp = get_reg(child, numReg); + tmp = ptrace_get_reg(child, numReg); } reg32bits = ((u32*)&tmp)[part]; ret = put_user(reg32bits, (u32 __user *)data); @@ -274,7 +273,7 @@ long compat_sys_ptrace(int request, int pid, unsigned long addr, if (index == PT_ORIG_R3) break; if (index < PT_FPR0) { - ret = put_reg(child, index, data); + ret = ptrace_put_reg(child, index, data); } else { flush_fp_to_thread(child); /* @@ -346,7 +345,7 @@ long compat_sys_ptrace(int request, int pid, unsigned long addr, } ret = 0; for (ui = 0; ui < PT_REGS_COUNT; ui ++) { - ret |= __put_user(get_reg(child, ui), + ret |= __put_user(ptrace_get_reg(child, ui), (unsigned int __user *) data); data += sizeof(int); } @@ -366,7 +365,7 @@ long compat_sys_ptrace(int request, int pid, unsigned long addr, ret = __get_user(tmp, (unsigned int __user *) data); if (ret) break; - put_reg(child, ui, tmp); + ptrace_put_reg(child, ui, tmp); data += sizeof(int); } break; -- cgit v1.1 From 1b6610d6fcb8dc23631cf48f09aa02e6649e379d Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 4 Jun 2007 15:15:45 +1000 Subject: [POWERPC] Remove some useless ifdef's in ptrace CHECK_FULL_REGS() exist on both 32 and 64 bits, so there's no need to make it conditional on CONFIG_PPC32. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/ptrace.c | 4 ---- 1 file changed, 4 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 875bfda..c9c330d 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -371,9 +371,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) #endif break; -#ifdef CONFIG_PPC32 CHECK_FULL_REGS(child->thread.regs); -#endif if (index < PT_FPR0) { tmp = ptrace_get_reg(child, (int) index); } else { @@ -410,9 +408,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) #endif break; -#ifdef CONFIG_PPC32 CHECK_FULL_REGS(child->thread.regs); -#endif if (index == PT_ORIG_R3) break; if (index < PT_FPR0) { -- cgit v1.1 From 912000e73ee8fcb97831b123c9c3a7274b71cab7 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 4 Jun 2007 15:15:46 +1000 Subject: [POWERPC] Allow ptrace write to pt_regs trap and orig_r3 This patch allows a ptracer to write to the "trap" and "orig_r3" words of the pt_regs. This, along with a subsequent patch to the signal restart code, should enable gdb to properly handle syscall restarting after executing a separate function (at least when there's no restart block). This patch also removes ptrace32.c code toying directly with the registers and makes it use the ptrace_get/put_reg() accessors for everything so that the logic for checking what is permitted is in only one place. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/ptrace.c | 9 ++++++--- arch/powerpc/kernel/ptrace32.c | 27 ++++++++++++++------------- 2 files changed, 20 insertions(+), 16 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index c9c330d..dd4837c 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -75,10 +75,15 @@ int ptrace_put_reg(struct task_struct *task, int regno, unsigned long data) if (task->thread.regs == NULL) return -EIO; - if (regno <= PT_MAX_PUT_REG) { + if (regno <= PT_MAX_PUT_REG || regno == PT_TRAP) { if (regno == PT_MSR) data = (data & MSR_DEBUGCHANGE) | (task->thread.regs->msr & ~MSR_DEBUGCHANGE); + /* We prevent mucking around with the reserved area of trap + * which are used internally by the kernel + */ + if (regno == PT_TRAP) + data &= 0xfff0; ((unsigned long *)task->thread.regs)[regno] = data; return 0; } @@ -409,8 +414,6 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) break; CHECK_FULL_REGS(child->thread.regs); - if (index == PT_ORIG_R3) - break; if (index < PT_FPR0) { ret = ptrace_put_reg(child, index, data); } else { diff --git a/arch/powerpc/kernel/ptrace32.c b/arch/powerpc/kernel/ptrace32.c index 4511b42..aae6a98 100644 --- a/arch/powerpc/kernel/ptrace32.c +++ b/arch/powerpc/kernel/ptrace32.c @@ -206,7 +206,9 @@ long compat_sys_ptrace(int request, int pid, unsigned long addr, else part = 0; /* want the 1st half of the register (left-most). */ - /* Validate the input - check to see if address is on the wrong boundary or beyond the end of the user area */ + /* Validate the input - check to see if address is on the wrong boundary + * or beyond the end of the user area + */ if ((addr & 3) || numReg > PT_FPSCR) break; @@ -270,8 +272,6 @@ long compat_sys_ptrace(int request, int pid, unsigned long addr, if ((addr & 3) || (index > PT_FPSCR32)) break; - if (index == PT_ORIG_R3) - break; if (index < PT_FPR0) { ret = ptrace_put_reg(child, index, data); } else { @@ -302,24 +302,25 @@ long compat_sys_ptrace(int request, int pid, unsigned long addr, /* Determine which register the user wants */ index = (u64)addr >> 2; numReg = index / 2; + /* * Validate the input - check to see if address is on the * wrong boundary or beyond the end of the user area */ if ((addr & 3) || (numReg > PT_FPSCR)) break; - /* Insure it is a register we let them change */ - if ((numReg == PT_ORIG_R3) - || ((numReg > PT_CCR) && (numReg < PT_FPR0))) - break; - if (numReg >= PT_FPR0) { + if (numReg < PT_FPR0) { + unsigned long freg = ptrace_get_reg(child, numReg); + if (index % 2) + freg = (freg & ~0xfffffffful) | (data & 0xfffffffful); + else + freg = (freg & 0xfffffffful) | (data << 32); + ret = ptrace_put_reg(child, numReg, freg); + } else { flush_fp_to_thread(child); + ((unsigned int *)child->thread.regs)[index] = data; + ret = 0; } - if (numReg == PT_MSR) - data = (data & MSR_DEBUGCHANGE) - | (child->thread.regs->msr & ~MSR_DEBUGCHANGE); - ((u32*)child->thread.regs)[index] = data; - ret = 0; break; } -- cgit v1.1 From abd0650541604d6c028bcbf5002e4a68aaf56e90 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 4 Jun 2007 15:15:47 +1000 Subject: [POWERPC] ptrace shouldn't touch FP exec mode One of the gratuitous difference between 32 and 64-bit ptrace is whether you can whack the MSR:FE0 and FE1 bits from ptrace. This patch forbids it unconditionally. In addition, the 64-bit kernels used to return the exception mode in the MSR on reads, but 32-bit kernels didn't. This patch makes it return those bits on both. Finally, since ptrace-ppc32.h and ptrace-ppc64.h are mostly empty now, and since the previous patch made ptrace32.c no longer need the MSR_DEBUGCHANGE definition, we just remove those 2 files and move back the remaining bits to ptrace.c (they were short lived heh ?). Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/ptrace-ppc32.h | 35 -------------------------- arch/powerpc/kernel/ptrace-ppc64.h | 51 -------------------------------------- arch/powerpc/kernel/ptrace.c | 45 ++++++++++++++++++++++++++++----- arch/powerpc/kernel/ptrace32.c | 2 -- 4 files changed, 39 insertions(+), 94 deletions(-) delete mode 100644 arch/powerpc/kernel/ptrace-ppc32.h delete mode 100644 arch/powerpc/kernel/ptrace-ppc64.h (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/ptrace-ppc32.h b/arch/powerpc/kernel/ptrace-ppc32.h deleted file mode 100644 index f1fd5b8..0000000 --- a/arch/powerpc/kernel/ptrace-ppc32.h +++ /dev/null @@ -1,35 +0,0 @@ -/* - * Copyright (c) 2007 Benjamin Herrenschmidt, IBM Coproration - * Extracted from ptrace.c and ptrace32.c - * - * This file is subject to the terms and conditions of the GNU General - * Public License. See the file README.legal in the main directory of - * this archive for more details. - */ - -#ifndef _POWERPC_PTRACE_PPC32_H -#define _POWERPC_PTRACE_PPC32_H - -/* - * Set of msr bits that gdb can change on behalf of a process. - */ -#if defined(CONFIG_40x) || defined(CONFIG_BOOKE) -#define MSR_DEBUGCHANGE 0 -#else -#define MSR_DEBUGCHANGE (MSR_SE | MSR_BE) -#endif - -/* - * Max register writeable via put_reg - */ -#define PT_MAX_PUT_REG PT_MQ - -/* - * Munging of MSR on return from get_regs - * - * Nothing to do on ppc32 - */ -#define PT_MUNGE_MSR(msr, task) (msr) - - -#endif /* _POWERPC_PTRACE_PPC32_H */ diff --git a/arch/powerpc/kernel/ptrace-ppc64.h b/arch/powerpc/kernel/ptrace-ppc64.h deleted file mode 100644 index e450ce0..0000000 --- a/arch/powerpc/kernel/ptrace-ppc64.h +++ /dev/null @@ -1,51 +0,0 @@ -/* - * Copyright (c) 2002 Stephen Rothwell, IBM Coproration - * Extracted from ptrace.c and ptrace32.c - * - * This file is subject to the terms and conditions of the GNU General - * Public License. See the file README.legal in the main directory of - * this archive for more details. - */ - -#ifndef _POWERPC_PTRACE_PPC64_H -#define _POWERPC_PTRACE_PPC64_H - -/* - * Set of msr bits that gdb can change on behalf of a process. - */ -#define MSR_DEBUGCHANGE (MSR_FE0 | MSR_SE | MSR_BE | MSR_FE1) - -/* - * Max register writeable via put_reg - */ -#define PT_MAX_PUT_REG PT_CCR - -/* - * Munging of MSR on return from get_regs - * - * Put the correct FP bits in, they might be wrong as a result - * of our lazy FP restore. - */ - -#define PT_MUNGE_MSR(msr, task) ({ (msr) | (task)->thread.fpexc_mode; }) - -static inline int ptrace_set_debugreg(struct task_struct *task, - unsigned long addr, unsigned long data) -{ - /* We only support one DABR and no IABRS at the moment */ - if (addr > 0) - return -EINVAL; - - /* The bottom 3 bits are flags */ - if ((data & ~0x7UL) >= TASK_SIZE) - return -EIO; - - /* Ensure translation is on */ - if (data && !(data & DABR_TRANSLATION)) - return -EIO; - - task->thread.dabr = data; - return 0; -} - -#endif /* _POWERPC_PTRACE_PPC64_H */ diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index dd4837c..75bc744 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -35,16 +35,28 @@ #include #include -#ifdef CONFIG_PPC64 -#include "ptrace-ppc64.h" +/* + * does not yet catch signals sent when the child dies. + * in exit.c or in signal.c. + */ + +/* + * Set of msr bits that gdb can change on behalf of a process. + */ +#if defined(CONFIG_40x) || defined(CONFIG_BOOKE) +#define MSR_DEBUGCHANGE 0 #else -#include "ptrace-ppc32.h" +#define MSR_DEBUGCHANGE (MSR_SE | MSR_BE) #endif /* - * does not yet catch signals sent when the child dies. - * in exit.c or in signal.c. + * Max register writeable via put_reg */ +#ifdef CONFIG_PPC32 +#define PT_MAX_PUT_REG PT_MQ +#else +#define PT_MAX_PUT_REG PT_CCR +#endif /* * Get contents of register REGNO in task TASK. @@ -58,7 +70,7 @@ unsigned long ptrace_get_reg(struct task_struct *task, int regno) if (regno == PT_MSR) { tmp = ((unsigned long *)task->thread.regs)[PT_MSR]; - return PT_MUNGE_MSR(tmp, task); + return tmp | task->thread.fpexc_mode; } if (regno < (sizeof(struct pt_regs) / sizeof(unsigned long))) @@ -274,6 +286,27 @@ static void clear_single_step(struct task_struct *task) clear_tsk_thread_flag(task, TIF_SINGLESTEP); } +#ifdef CONFIG_PPC64 +static int ptrace_set_debugreg(struct task_struct *task, unsigned long addr, + unsigned long data) +{ + /* We only support one DABR and no IABRS at the moment */ + if (addr > 0) + return -EINVAL; + + /* The bottom 3 bits are flags */ + if ((data & ~0x7UL) >= TASK_SIZE) + return -EIO; + + /* Ensure translation is on */ + if (data && !(data & DABR_TRANSLATION)) + return -EIO; + + task->thread.dabr = data; + return 0; +} +#endif + /* * Called by kernel/ptrace.c when detaching.. * diff --git a/arch/powerpc/kernel/ptrace32.c b/arch/powerpc/kernel/ptrace32.c index aae6a98..9e6baea 100644 --- a/arch/powerpc/kernel/ptrace32.c +++ b/arch/powerpc/kernel/ptrace32.c @@ -33,8 +33,6 @@ #include #include -#include "ptrace-ppc64.h" - /* * does not yet catch signals sent when the child dies. * in exit.c or in signal.c. -- cgit v1.1 From 6d110da8c3c62167c54eb5e32bb80916a1a23362 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 4 Jun 2007 15:15:47 +1000 Subject: [POWERPC] powerpc: ptrace can set DABR on both 32 and 64 bits Allow ptrace to set dabr in the thread structure for both 32 and 64 bits, though only 64 bits actually uses that field, it's actually defined in both. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/ptrace.c | 4 ---- 1 file changed, 4 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 75bc744..0fb5395 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -286,7 +286,6 @@ static void clear_single_step(struct task_struct *task) clear_tsk_thread_flag(task, TIF_SINGLESTEP); } -#ifdef CONFIG_PPC64 static int ptrace_set_debugreg(struct task_struct *task, unsigned long addr, unsigned long data) { @@ -305,7 +304,6 @@ static int ptrace_set_debugreg(struct task_struct *task, unsigned long addr, task->thread.dabr = data; return 0; } -#endif /* * Called by kernel/ptrace.c when detaching.. @@ -503,7 +501,6 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) break; } -#ifdef CONFIG_PPC64 case PTRACE_GET_DEBUGREG: { ret = -EINVAL; /* We only support one DABR and no IABRS at the moment */ @@ -517,7 +514,6 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) case PTRACE_SET_DEBUGREG: ret = ptrace_set_debugreg(child, addr, data); break; -#endif case PTRACE_DETACH: ret = ptrace_detach(child, data); -- cgit v1.1 From 791cc501d422be96d6e3098faf6471ba29f4dd33 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 4 Jun 2007 15:15:48 +1000 Subject: [POWERPC] Always apply DABR changes on context switches This patch removes the #ifdef CONFIG_PPC64 around setting the DABR. The actual setting of the SPR inside of the set_dabr() function is dependent on CONFIG_PPC64 || CONFIG_6xx but you can always provide a ppc_md hook to override that. We should improve support for different HW breakpoints facilities but this is a first step. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/process.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 6e2f035..84f000a 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -219,22 +219,26 @@ void discard_lazy_cpu_state(void) } #endif /* CONFIG_SMP */ -#ifdef CONFIG_PPC_MERGE /* XXX for now */ int set_dabr(unsigned long dabr) { +#ifdef CONFIG_PPC_MERGE /* XXX for now */ if (ppc_md.set_dabr) return ppc_md.set_dabr(dabr); +#endif + /* XXX should we have a CPU_FTR_HAS_DABR ? */ +#if defined(CONFIG_PPC64) || defined(CONFIG_6xx) mtspr(SPRN_DABR, dabr); +#endif return 0; } -#endif #ifdef CONFIG_PPC64 DEFINE_PER_CPU(struct cpu_usage, cpu_usage_array); -static DEFINE_PER_CPU(unsigned long, current_dabr); #endif +static DEFINE_PER_CPU(unsigned long, current_dabr); + struct task_struct *__switch_to(struct task_struct *prev, struct task_struct *new) { @@ -299,12 +303,10 @@ struct task_struct *__switch_to(struct task_struct *prev, #endif /* CONFIG_SMP */ -#ifdef CONFIG_PPC64 /* for now */ if (unlikely(__get_cpu_var(current_dabr) != new->thread.dabr)) { set_dabr(new->thread.dabr); __get_cpu_var(current_dabr) = new->thread.dabr; } -#endif /* CONFIG_PPC64 */ new_thread = &new->thread; old_thread = ¤t->thread; @@ -473,12 +475,10 @@ void flush_thread(void) discard_lazy_cpu_state(); -#ifdef CONFIG_PPC64 /* for now */ if (current->thread.dabr) { current->thread.dabr = 0; set_dabr(0); } -#endif } void -- cgit v1.1 From 22e38f29328296d9d4cc33e46fd32a63e807abaf Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 4 Jun 2007 15:15:49 +1000 Subject: [POWERPC] Make syscall restart code more common This patch moves the code in signal_32.c and signal_64.c for handling syscall restart into a common signal.c file and converge around a single implementation that is based on the 32 bits one, using trap, ccr and r3 rather than the special "result" field for deciding what to do. The "result" field is now pretty much deprecated. We still set it for the sake of whatever might rely on it in userland but we no longer use it's content. This, along with a previous patch that enables ptracers to write to "trap" and "orig_r3" should allow gdb to properly handle syscall restarting. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/Makefile | 3 +- arch/powerpc/kernel/signal.c | 65 +++++++++++++++++++++++++++++++++++++++++ arch/powerpc/kernel/signal.h | 16 ++++++++++ arch/powerpc/kernel/signal_32.c | 28 +++--------------- arch/powerpc/kernel/signal_64.c | 59 +++++-------------------------------- 5 files changed, 94 insertions(+), 77 deletions(-) create mode 100644 arch/powerpc/kernel/signal.c create mode 100644 arch/powerpc/kernel/signal.h (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 08ce7de..eb6a33e 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -12,7 +12,8 @@ endif obj-y := semaphore.o cputable.o ptrace.o syscalls.o \ irq.o align.o signal_32.o pmc.o vdso.o \ - init_task.o process.o systbl.o idle.o + init_task.o process.o systbl.o idle.o \ + signal.o obj-y += vdso32/ obj-$(CONFIG_PPC64) += setup_64.o binfmt_elf32.o sys_ppc32.o \ signal_64.o ptrace32.o \ diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c new file mode 100644 index 0000000..88a1254 --- /dev/null +++ b/arch/powerpc/kernel/signal.c @@ -0,0 +1,65 @@ +/* + * Common signal handling code for both 32 and 64 bits + * + * Copyright (c) 2007 Benjamin Herrenschmidt, IBM Coproration + * Extracted from signal_32.c and signal_64.c + * + * This file is subject to the terms and conditions of the GNU General + * Public License. See the file README.legal in the main directory of + * this archive for more details. + */ + +#include +#include +#include + +void check_syscall_restart(struct pt_regs *regs, struct k_sigaction *ka, + int has_handler) +{ + unsigned long ret = regs->gpr[3]; + int restart = 1; + + /* syscall ? */ + if (TRAP(regs) != 0x0C00) + return; + + /* error signalled ? */ + if (!(regs->ccr & 0x10000000)) + return; + + switch (ret) { + case ERESTART_RESTARTBLOCK: + case ERESTARTNOHAND: + /* ERESTARTNOHAND means that the syscall should only be + * restarted if there was no handler for the signal, and since + * we only get here if there is a handler, we dont restart. + */ + restart = !has_handler; + break; + case ERESTARTSYS: + /* ERESTARTSYS means to restart the syscall if there is no + * handler or the handler was registered with SA_RESTART + */ + restart = !has_handler || (ka->sa.sa_flags & SA_RESTART) != 0; + break; + case ERESTARTNOINTR: + /* ERESTARTNOINTR means that the syscall should be + * called again after the signal handler returns. + */ + break; + default: + return; + } + if (restart) { + if (ret == ERESTART_RESTARTBLOCK) + regs->gpr[0] = __NR_restart_syscall; + else + regs->gpr[3] = regs->orig_gpr3; + regs->nip -= 4; + regs->result = 0; + } else { + regs->result = -EINTR; + regs->gpr[3] = EINTR; + regs->ccr |= 0x10000000; + } +} diff --git a/arch/powerpc/kernel/signal.h b/arch/powerpc/kernel/signal.h new file mode 100644 index 0000000..1e8dfb8 --- /dev/null +++ b/arch/powerpc/kernel/signal.h @@ -0,0 +1,16 @@ +/* + * Copyright (c) 2007 Benjamin Herrenschmidt, IBM Coproration + * Extracted from signal_32.c and signal_64.c + * + * This file is subject to the terms and conditions of the GNU General + * Public License. See the file README.legal in the main directory of + * this archive for more details. + */ + +#ifndef _POWERPC_ARCH_SIGNAL_H +#define _POWERPC_ARCH_SIGNAL_H + +extern void check_syscall_restart(struct pt_regs *regs, struct k_sigaction *ka, + int has_handler); + +#endif /* _POWERPC_ARCH_SIGNAL_H */ diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index dd1dca5..e5cc803 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -51,6 +51,8 @@ #include #endif +#include "signal.h" + #undef DEBUG_SIG #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) @@ -1156,30 +1158,8 @@ int do_signal(sigset_t *oldset, struct pt_regs *regs) #ifdef CONFIG_PPC32 no_signal: #endif - if (TRAP(regs) == 0x0C00 /* System Call! */ - && regs->ccr & 0x10000000 /* error signalled */ - && ((ret = regs->gpr[3]) == ERESTARTSYS - || ret == ERESTARTNOHAND || ret == ERESTARTNOINTR - || ret == ERESTART_RESTARTBLOCK)) { - - if (signr > 0 - && (ret == ERESTARTNOHAND || ret == ERESTART_RESTARTBLOCK - || (ret == ERESTARTSYS - && !(ka.sa.sa_flags & SA_RESTART)))) { - /* make the system call return an EINTR error */ - regs->result = -EINTR; - regs->gpr[3] = EINTR; - /* note that the cr0.SO bit is already set */ - } else { - regs->nip -= 4; /* Back up & retry system call */ - regs->result = 0; - regs->trap = 0; - if (ret == ERESTART_RESTARTBLOCK) - regs->gpr[0] = __NR_restart_syscall; - else - regs->gpr[3] = regs->orig_gpr3; - } - } + /* Is there any syscall restart business here ? */ + check_syscall_restart(regs, &ka, signr > 0); if (signr == 0) { /* No signal to deliver -- put the saved sigmask back */ diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 1ce0ae3..5d2faf0fb 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -34,6 +34,8 @@ #include #include +#include "signal.h" + #define DEBUG_SIG 0 #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) @@ -463,41 +465,6 @@ static int handle_signal(unsigned long sig, struct k_sigaction *ka, return ret; } -static inline void syscall_restart(struct pt_regs *regs, struct k_sigaction *ka) -{ - switch ((int)regs->result) { - case -ERESTART_RESTARTBLOCK: - case -ERESTARTNOHAND: - /* ERESTARTNOHAND means that the syscall should only be - * restarted if there was no handler for the signal, and since - * we only get here if there is a handler, we dont restart. - */ - regs->result = -EINTR; - regs->gpr[3] = EINTR; - regs->ccr |= 0x10000000; - break; - case -ERESTARTSYS: - /* ERESTARTSYS means to restart the syscall if there is no - * handler or the handler was registered with SA_RESTART - */ - if (!(ka->sa.sa_flags & SA_RESTART)) { - regs->result = -EINTR; - regs->gpr[3] = EINTR; - regs->ccr |= 0x10000000; - break; - } - /* fallthrough */ - case -ERESTARTNOINTR: - /* ERESTARTNOINTR means that the syscall should be - * called again after the signal handler returns. - */ - regs->gpr[3] = regs->orig_gpr3; - regs->nip -= 4; - regs->result = 0; - break; - } -} - /* * Note that 'init' is a special process: it doesn't get signals it doesn't * want to handle. Thus you cannot kill init even with a SIGKILL even by @@ -522,13 +489,13 @@ int do_signal(sigset_t *oldset, struct pt_regs *regs) oldset = ¤t->blocked; signr = get_signal_to_deliver(&info, &ka, regs, NULL); + + /* Is there any syscall restart business here ? */ + check_syscall_restart(regs, &ka, signr > 0); + if (signr > 0) { int ret; - /* Whee! Actually deliver the signal. */ - if (TRAP(regs) == 0x0C00) - syscall_restart(regs, &ka); - /* * Reenable the DABR before delivering the signal to * user space. The DABR will have been cleared if it @@ -537,6 +504,7 @@ int do_signal(sigset_t *oldset, struct pt_regs *regs) if (current->thread.dabr) set_dabr(current->thread.dabr); + /* Whee! Actually deliver the signal. */ ret = handle_signal(signr, &ka, &info, oldset, regs); /* If a signal was successfully delivered, the saved sigmask is in @@ -547,19 +515,6 @@ int do_signal(sigset_t *oldset, struct pt_regs *regs) return ret; } - if (TRAP(regs) == 0x0C00) { /* System Call! */ - if ((int)regs->result == -ERESTARTNOHAND || - (int)regs->result == -ERESTARTSYS || - (int)regs->result == -ERESTARTNOINTR) { - regs->gpr[3] = regs->orig_gpr3; - regs->nip -= 4; /* Back up & retry system call */ - regs->result = 0; - } else if ((int)regs->result == -ERESTART_RESTARTBLOCK) { - regs->gpr[0] = __NR_restart_syscall; - regs->nip -= 4; - regs->result = 0; - } - } /* No signal to deliver -- put the saved sigmask back */ if (test_thread_flag(TIF_RESTORE_SIGMASK)) { clear_thread_flag(TIF_RESTORE_SIGMASK); -- cgit v1.1 From 69d15f6b352a681f1db9bc70219a3e8e9d503dbf Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 4 Jun 2007 15:15:50 +1000 Subject: [POWERPC] Consolidate sys_sigaltstack sys_sigaltstack is the same on 32bit and 64 and we can consolidate it to signal.c. The only difference is that the 32bit code uses ints for the unused register paramaters and 64bit unsigned long. I've changed it to unsigned long because it's the same width on 32bit. (I also wonder who came up with this awkward calling convention.. :)) Signed-off-by: Christoph Hellwig Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/signal.c | 7 +++++++ arch/powerpc/kernel/signal_32.c | 8 -------- arch/powerpc/kernel/signal_64.c | 8 -------- 3 files changed, 7 insertions(+), 16 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index 88a1254..325d260a 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -63,3 +63,10 @@ void check_syscall_restart(struct pt_regs *regs, struct k_sigaction *ka, regs->ccr |= 0x10000000; } } + +long sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss, + unsigned long r5, unsigned long r6, unsigned long r7, + unsigned long r8, struct pt_regs *regs) +{ + return do_sigaltstack(uss, uoss, regs->gpr[1]); +} diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index e5cc803..f5713bf 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -253,14 +253,6 @@ long sys_sigsuspend(old_sigset_t mask) return -ERESTARTNOHAND; } -#ifdef CONFIG_PPC32 -long sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss, int r5, - int r6, int r7, int r8, struct pt_regs *regs) -{ - return do_sigaltstack(uss, uoss, regs->gpr[1]); -} -#endif - long sys_sigaction(int sig, struct old_sigaction __user *act, struct old_sigaction __user *oact) { diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 5d2faf0fb..817f1cf 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -66,14 +66,6 @@ struct rt_sigframe { char abigap[288]; } __attribute__ ((aligned (16))); -long sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss, unsigned long r5, - unsigned long r6, unsigned long r7, unsigned long r8, - struct pt_regs *regs) -{ - return do_sigaltstack(uss, uoss, regs->gpr[1]); -} - - /* * Set up the sigcontext for the signal frame. */ -- cgit v1.1 From db277e9a67b9d81b9d6cd74edf0c3e1a0ef2aa4b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 4 Jun 2007 15:15:51 +1000 Subject: [POWERPC] Consolidate restore_sigmask restore_sigmask is exactly the same on 32 and 64bit, so move it to common code. Also move _BLOCKABLE to signal.h to avoid defining it multiple times. Signed-off-by: Christoph Hellwig Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/signal.c | 15 +++++++++++++++ arch/powerpc/kernel/signal.h | 3 +++ arch/powerpc/kernel/signal_32.c | 19 ------------------- arch/powerpc/kernel/signal_64.c | 15 --------------- 4 files changed, 18 insertions(+), 34 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index 325d260a..f92856b 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -13,6 +13,21 @@ #include #include +#include "signal.h" + + +/* + * Restore the user process's signal mask + */ +void restore_sigmask(sigset_t *set) +{ + sigdelsetmask(set, ~_BLOCKABLE); + spin_lock_irq(¤t->sighand->siglock); + current->blocked = *set; + recalc_sigpending(); + spin_unlock_irq(¤t->sighand->siglock); +} + void check_syscall_restart(struct pt_regs *regs, struct k_sigaction *ka, int has_handler) { diff --git a/arch/powerpc/kernel/signal.h b/arch/powerpc/kernel/signal.h index 1e8dfb8..4b091d8 100644 --- a/arch/powerpc/kernel/signal.h +++ b/arch/powerpc/kernel/signal.h @@ -10,6 +10,9 @@ #ifndef _POWERPC_ARCH_SIGNAL_H #define _POWERPC_ARCH_SIGNAL_H +#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) + +extern void restore_sigmask(sigset_t *set); extern void check_syscall_restart(struct pt_regs *regs, struct k_sigaction *ka, int has_handler); diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index f5713bf..1d899a5 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -55,8 +55,6 @@ #undef DEBUG_SIG -#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) - #ifdef CONFIG_PPC64 #define do_signal do_signal32 #define sys_sigsuspend compat_sys_sigsuspend @@ -697,23 +695,6 @@ int compat_sys_sigaltstack(u32 __new, u32 __old, int r5, } #endif /* CONFIG_PPC64 */ - -/* - * Restore the user process's signal mask - */ -#ifdef CONFIG_PPC64 -extern void restore_sigmask(sigset_t *set); -#else /* CONFIG_PPC64 */ -static void restore_sigmask(sigset_t *set) -{ - sigdelsetmask(set, ~_BLOCKABLE); - spin_lock_irq(¤t->sighand->siglock); - current->blocked = *set; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); -} -#endif - /* * Set up a signal frame for a "real-time" signal handler * (one which gets siginfo). diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 817f1cf..7e9c4b7 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -38,8 +38,6 @@ #define DEBUG_SIG 0 -#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) - #define GP_REGS_SIZE min(sizeof(elf_gregset_t), sizeof(struct pt_regs)) #define FP_REGS_SIZE sizeof(elf_fpregset_t) @@ -243,19 +241,6 @@ static long setup_trampoline(unsigned int syscall, unsigned int __user *tramp) } /* - * Restore the user process's signal mask (also used by signal32.c) - */ -void restore_sigmask(sigset_t *set) -{ - sigdelsetmask(set, ~_BLOCKABLE); - spin_lock_irq(¤t->sighand->siglock); - current->blocked = *set; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); -} - - -/* * Handle {get,set,swap}_context operations */ int sys_swapcontext(struct ucontext __user *old_ctx, -- cgit v1.1 From f478f5430c8a599f46c41e8172a507a5772a6b69 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 4 Jun 2007 15:15:52 +1000 Subject: [POWERPC] Consolidate do_signal do_signal has exactly the same behaviour on 32bit and 64bit and 32bit compat on 64bit for handling 32bit signals. Consolidate all these into one common function in signal.c. The only odd left over is the try_to_free in the 32bit version that no other architecture has in mainline (only in i386 for some odd SuSE release). We should probably get rid of it in a separate patch. Signed-off-by: Christoph Hellwig Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/signal.c | 107 +++++++++++++++++++++++++++++++++++++++- arch/powerpc/kernel/signal.h | 14 +++++- arch/powerpc/kernel/signal_32.c | 88 +-------------------------------- arch/powerpc/kernel/signal_64.c | 86 +------------------------------- 4 files changed, 120 insertions(+), 175 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index f92856b..640b5f3 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -9,6 +9,7 @@ * this archive for more details. */ +#include #include #include #include @@ -16,6 +17,19 @@ #include "signal.h" +#ifdef CONFIG_PPC64 +static inline int is_32bit_task(void) +{ + return test_thread_flag(TIF_32BIT); +} +#else +static inline int is_32bit_task(void) +{ + return 1; +} +#endif + + /* * Restore the user process's signal mask */ @@ -28,8 +42,8 @@ void restore_sigmask(sigset_t *set) spin_unlock_irq(¤t->sighand->siglock); } -void check_syscall_restart(struct pt_regs *regs, struct k_sigaction *ka, - int has_handler) +static void check_syscall_restart(struct pt_regs *regs, struct k_sigaction *ka, + int has_handler) { unsigned long ret = regs->gpr[3]; int restart = 1; @@ -79,6 +93,95 @@ void check_syscall_restart(struct pt_regs *regs, struct k_sigaction *ka, } } +int do_signal(sigset_t *oldset, struct pt_regs *regs) +{ + siginfo_t info; + int signr; + struct k_sigaction ka; + int ret; + int is32 = is_32bit_task(); + +#ifdef CONFIG_PPC32 + if (try_to_freeze()) { + signr = 0; + if (!signal_pending(current)) + goto no_signal; + } +#endif + + if (test_thread_flag(TIF_RESTORE_SIGMASK)) + oldset = ¤t->saved_sigmask; + else if (!oldset) + oldset = ¤t->blocked; + + signr = get_signal_to_deliver(&info, &ka, regs, NULL); + +#ifdef CONFIG_PPC32 +no_signal: +#endif + /* Is there any syscall restart business here ? */ + check_syscall_restart(regs, &ka, signr > 0); + + if (signr <= 0) { + /* No signal to deliver -- put the saved sigmask back */ + if (test_thread_flag(TIF_RESTORE_SIGMASK)) { + clear_thread_flag(TIF_RESTORE_SIGMASK); + sigprocmask(SIG_SETMASK, ¤t->saved_sigmask, NULL); + } + return 0; /* no signals delivered */ + } + +#ifdef CONFIG_PPC64 + /* + * Reenable the DABR before delivering the signal to + * user space. The DABR will have been cleared if it + * triggered inside the kernel. + */ + if (current->thread.dabr) + set_dabr(current->thread.dabr); +#endif + + if (is32) { + unsigned int newsp; + + if ((ka.sa.sa_flags & SA_ONSTACK) && + current->sas_ss_size && !on_sig_stack(regs->gpr[1])) + newsp = current->sas_ss_sp + current->sas_ss_size; + else + newsp = regs->gpr[1]; + + if (ka.sa.sa_flags & SA_SIGINFO) + ret = handle_rt_signal32(signr, &ka, &info, oldset, + regs, newsp); + else + ret = handle_signal32(signr, &ka, &info, oldset, + regs, newsp); +#ifdef CONFIG_PPC64 + } else { + ret = handle_rt_signal64(signr, &ka, &info, oldset, regs); +#endif + } + + if (ret) { + spin_lock_irq(¤t->sighand->siglock); + sigorsets(¤t->blocked, ¤t->blocked, + &ka.sa.sa_mask); + if (!(ka.sa.sa_flags & SA_NODEFER)) + sigaddset(¤t->blocked, signr); + recalc_sigpending(); + spin_unlock_irq(¤t->sighand->siglock); + + /* + * A signal was successfully delivered; the saved sigmask is in + * its frame, and we can clear the TIF_RESTORE_SIGMASK flag. + */ + if (test_thread_flag(TIF_RESTORE_SIGMASK)) + clear_thread_flag(TIF_RESTORE_SIGMASK); + } + + return ret; +} + long sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss, unsigned long r5, unsigned long r6, unsigned long r7, unsigned long r8, struct pt_regs *regs) diff --git a/arch/powerpc/kernel/signal.h b/arch/powerpc/kernel/signal.h index 4b091d8..190d432 100644 --- a/arch/powerpc/kernel/signal.h +++ b/arch/powerpc/kernel/signal.h @@ -13,7 +13,17 @@ #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) extern void restore_sigmask(sigset_t *set); -extern void check_syscall_restart(struct pt_regs *regs, struct k_sigaction *ka, - int has_handler); + +extern int handle_signal32(unsigned long sig, struct k_sigaction *ka, + siginfo_t *info, sigset_t *oldset, + struct pt_regs *regs, unsigned long newsp); + +extern int handle_rt_signal32(unsigned long sig, struct k_sigaction *ka, + siginfo_t *info, sigset_t *oldset, + struct pt_regs *regs, unsigned long newsp); + +extern int handle_rt_signal64(int signr, struct k_sigaction *ka, + siginfo_t *info, sigset_t *set, + struct pt_regs *regs); #endif /* _POWERPC_ARCH_SIGNAL_H */ diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 1d899a5..32481e7 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -56,7 +56,6 @@ #undef DEBUG_SIG #ifdef CONFIG_PPC64 -#define do_signal do_signal32 #define sys_sigsuspend compat_sys_sigsuspend #define sys_rt_sigsuspend compat_sys_rt_sigsuspend #define sys_rt_sigreturn compat_sys_rt_sigreturn @@ -231,8 +230,6 @@ static inline int restore_general_regs(struct pt_regs *regs, #endif /* CONFIG_PPC64 */ -int do_signal(sigset_t *oldset, struct pt_regs *regs); - /* * Atomically swap in the new signal mask, and wait for a signal. */ @@ -699,7 +696,7 @@ int compat_sys_sigaltstack(u32 __new, u32 __old, int r5, * Set up a signal frame for a "real-time" signal handler * (one which gets siginfo). */ -static int handle_rt_signal(unsigned long sig, struct k_sigaction *ka, +int handle_rt_signal32(unsigned long sig, struct k_sigaction *ka, siginfo_t *info, sigset_t *oldset, struct pt_regs *regs, unsigned long newsp) { @@ -990,7 +987,7 @@ int sys_debug_setcontext(struct ucontext __user *ctx, /* * OK, we're invoking a handler */ -static int handle_signal(unsigned long sig, struct k_sigaction *ka, +int handle_signal32(unsigned long sig, struct k_sigaction *ka, siginfo_t *info, sigset_t *oldset, struct pt_regs *regs, unsigned long newsp) { @@ -1101,84 +1098,3 @@ badframe: force_sig(SIGSEGV, current); return 0; } - -/* - * Note that 'init' is a special process: it doesn't get signals it doesn't - * want to handle. Thus you cannot kill init even with a SIGKILL even by - * mistake. - */ -int do_signal(sigset_t *oldset, struct pt_regs *regs) -{ - siginfo_t info; - struct k_sigaction ka; - unsigned int newsp; - int signr, ret; - -#ifdef CONFIG_PPC32 - if (try_to_freeze()) { - signr = 0; - if (!signal_pending(current)) - goto no_signal; - } -#endif - - if (test_thread_flag(TIF_RESTORE_SIGMASK)) - oldset = ¤t->saved_sigmask; - else if (!oldset) - oldset = ¤t->blocked; - - signr = get_signal_to_deliver(&info, &ka, regs, NULL); -#ifdef CONFIG_PPC32 -no_signal: -#endif - /* Is there any syscall restart business here ? */ - check_syscall_restart(regs, &ka, signr > 0); - - if (signr == 0) { - /* No signal to deliver -- put the saved sigmask back */ - if (test_thread_flag(TIF_RESTORE_SIGMASK)) { - clear_thread_flag(TIF_RESTORE_SIGMASK); - sigprocmask(SIG_SETMASK, ¤t->saved_sigmask, NULL); - } - return 0; /* no signals delivered */ - } - - if ((ka.sa.sa_flags & SA_ONSTACK) && current->sas_ss_size - && !on_sig_stack(regs->gpr[1])) - newsp = current->sas_ss_sp + current->sas_ss_size; - else - newsp = regs->gpr[1]; - newsp &= ~0xfUL; - -#ifdef CONFIG_PPC64 - /* - * Reenable the DABR before delivering the signal to - * user space. The DABR will have been cleared if it - * triggered inside the kernel. - */ - if (current->thread.dabr) - set_dabr(current->thread.dabr); -#endif - - /* Whee! Actually deliver the signal. */ - if (ka.sa.sa_flags & SA_SIGINFO) - ret = handle_rt_signal(signr, &ka, &info, oldset, regs, newsp); - else - ret = handle_signal(signr, &ka, &info, oldset, regs, newsp); - - if (ret) { - spin_lock_irq(¤t->sighand->siglock); - sigorsets(¤t->blocked, ¤t->blocked, - &ka.sa.sa_mask); - if (!(ka.sa.sa_flags & SA_NODEFER)) - sigaddset(¤t->blocked, signr); - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); - /* A signal was successfully delivered; the saved sigmask is in - its frame, and we can clear the TIF_RESTORE_SIGMASK flag */ - if (test_thread_flag(TIF_RESTORE_SIGMASK)) - clear_thread_flag(TIF_RESTORE_SIGMASK); - } - - return ret; -} diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 7e9c4b7..c17903c 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -334,7 +334,7 @@ badframe: return 0; } -static int setup_rt_frame(int signr, struct k_sigaction *ka, siginfo_t *info, +int handle_rt_signal64(int signr, struct k_sigaction *ka, siginfo_t *info, sigset_t *set, struct pt_regs *regs) { /* Handler is *really* a pointer to the function descriptor for @@ -417,87 +417,3 @@ badframe: force_sigsegv(signr, current); return 0; } - - -/* - * OK, we're invoking a handler - */ -static int handle_signal(unsigned long sig, struct k_sigaction *ka, - siginfo_t *info, sigset_t *oldset, struct pt_regs *regs) -{ - int ret; - - /* Set up Signal Frame */ - ret = setup_rt_frame(sig, ka, info, oldset, regs); - - if (ret) { - spin_lock_irq(¤t->sighand->siglock); - sigorsets(¤t->blocked, ¤t->blocked, &ka->sa.sa_mask); - if (!(ka->sa.sa_flags & SA_NODEFER)) - sigaddset(¤t->blocked,sig); - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); - } - - return ret; -} - -/* - * Note that 'init' is a special process: it doesn't get signals it doesn't - * want to handle. Thus you cannot kill init even with a SIGKILL even by - * mistake. - */ -int do_signal(sigset_t *oldset, struct pt_regs *regs) -{ - siginfo_t info; - int signr; - struct k_sigaction ka; - - /* - * If the current thread is 32 bit - invoke the - * 32 bit signal handling code - */ - if (test_thread_flag(TIF_32BIT)) - return do_signal32(oldset, regs); - - if (test_thread_flag(TIF_RESTORE_SIGMASK)) - oldset = ¤t->saved_sigmask; - else if (!oldset) - oldset = ¤t->blocked; - - signr = get_signal_to_deliver(&info, &ka, regs, NULL); - - /* Is there any syscall restart business here ? */ - check_syscall_restart(regs, &ka, signr > 0); - - if (signr > 0) { - int ret; - - /* - * Reenable the DABR before delivering the signal to - * user space. The DABR will have been cleared if it - * triggered inside the kernel. - */ - if (current->thread.dabr) - set_dabr(current->thread.dabr); - - /* Whee! Actually deliver the signal. */ - ret = handle_signal(signr, &ka, &info, oldset, regs); - - /* If a signal was successfully delivered, the saved sigmask is in - its frame, and we can clear the TIF_RESTORE_SIGMASK flag */ - if (ret && test_thread_flag(TIF_RESTORE_SIGMASK)) - clear_thread_flag(TIF_RESTORE_SIGMASK); - - return ret; - } - - /* No signal to deliver -- put the saved sigmask back */ - if (test_thread_flag(TIF_RESTORE_SIGMASK)) { - clear_thread_flag(TIF_RESTORE_SIGMASK); - sigprocmask(SIG_SETMASK, ¤t->saved_sigmask, NULL); - } - - return 0; -} -EXPORT_SYMBOL(do_signal); -- cgit v1.1 From 5f9f375a62d3fd3d7f0d5adc23039ade523e62ba Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 4 Jun 2007 15:15:53 +1000 Subject: [POWERPC] Remove obsolete freezer bits The powerpc signal code still had some obsolete freezer bits that have long been removed from x86 (it's now done in generic code). Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/signal.c | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index 640b5f3..a9c148a 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -9,7 +9,6 @@ * this archive for more details. */ -#include #include #include #include @@ -101,14 +100,6 @@ int do_signal(sigset_t *oldset, struct pt_regs *regs) int ret; int is32 = is_32bit_task(); -#ifdef CONFIG_PPC32 - if (try_to_freeze()) { - signr = 0; - if (!signal_pending(current)) - goto no_signal; - } -#endif - if (test_thread_flag(TIF_RESTORE_SIGMASK)) oldset = ¤t->saved_sigmask; else if (!oldset) @@ -116,9 +107,6 @@ int do_signal(sigset_t *oldset, struct pt_regs *regs) signr = get_signal_to_deliver(&info, &ka, regs, NULL); -#ifdef CONFIG_PPC32 -no_signal: -#endif /* Is there any syscall restart business here ? */ check_syscall_restart(regs, &ka, signr > 0); -- cgit v1.1 From a3f61dc0a5335334958ec3b97d0b1946b4ae5375 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 4 Jun 2007 17:22:48 +1000 Subject: [POWERPC] Merge creation of signal frame The code for creating signal frames was still duplicated and split in strange ways between 32 and 64 bits, including the SA_ONSTACK handling being in do_signal on 32 bits but inside handle_rt_signal on 64 bits etc... This moves the 64 bits get_sigframe() to the generic signal.c, cleans it a bit, moves the access_ok() call done by all callers to it as well, and adapts/cleanups the 3 different signal handling cases to use that common function. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/signal.c | 39 +++++++++++++++++++++++-------- arch/powerpc/kernel/signal.h | 6 +++-- arch/powerpc/kernel/signal_32.c | 52 +++++++++++++++++++---------------------- arch/powerpc/kernel/signal_64.c | 24 ++----------------- 4 files changed, 59 insertions(+), 62 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index a9c148a..dee2750 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -11,6 +11,7 @@ #include #include +#include #include #include "signal.h" @@ -28,6 +29,32 @@ static inline int is_32bit_task(void) } #endif +/* + * Allocate space for the signal frame + */ +void __user * get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, + size_t frame_size) +{ + unsigned long oldsp, newsp; + + /* Default to using normal stack */ + oldsp = regs->gpr[1]; + + /* Check for alt stack */ + if ((ka->sa.sa_flags & SA_ONSTACK) && + current->sas_ss_size && !on_sig_stack(oldsp)) + oldsp = (current->sas_ss_sp + current->sas_ss_size); + + /* Get aligned frame */ + newsp = (oldsp - frame_size) & ~0xFUL; + + /* Check access */ + if (!access_ok(VERIFY_WRITE, (void __user *)newsp, oldsp - newsp)) + return NULL; + + return (void __user *)newsp; +} + /* * Restore the user process's signal mask @@ -130,20 +157,12 @@ int do_signal(sigset_t *oldset, struct pt_regs *regs) #endif if (is32) { - unsigned int newsp; - - if ((ka.sa.sa_flags & SA_ONSTACK) && - current->sas_ss_size && !on_sig_stack(regs->gpr[1])) - newsp = current->sas_ss_sp + current->sas_ss_size; - else - newsp = regs->gpr[1]; - if (ka.sa.sa_flags & SA_SIGINFO) ret = handle_rt_signal32(signr, &ka, &info, oldset, - regs, newsp); + regs); else ret = handle_signal32(signr, &ka, &info, oldset, - regs, newsp); + regs); #ifdef CONFIG_PPC64 } else { ret = handle_rt_signal64(signr, &ka, &info, oldset, regs); diff --git a/arch/powerpc/kernel/signal.h b/arch/powerpc/kernel/signal.h index 190d432..c284f75 100644 --- a/arch/powerpc/kernel/signal.h +++ b/arch/powerpc/kernel/signal.h @@ -12,15 +12,17 @@ #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) +extern void __user * get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, + size_t frame_size); extern void restore_sigmask(sigset_t *set); extern int handle_signal32(unsigned long sig, struct k_sigaction *ka, siginfo_t *info, sigset_t *oldset, - struct pt_regs *regs, unsigned long newsp); + struct pt_regs *regs); extern int handle_rt_signal32(unsigned long sig, struct k_sigaction *ka, siginfo_t *info, sigset_t *oldset, - struct pt_regs *regs, unsigned long newsp); + struct pt_regs *regs); extern int handle_rt_signal64(int signr, struct k_sigaction *ka, siginfo_t *info, sigset_t *set, diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 32481e7..590057e 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -282,14 +282,17 @@ long sys_sigaction(int sig, struct old_sigaction __user *act, /* * When we have signals to deliver, we set up on the * user stack, going down from the original stack pointer: - * a sigregs struct + * an ABI gap of 56 words + * an mcontext struct * a sigcontext struct * a gap of __SIGNAL_FRAMESIZE bytes * - * Each of these things must be a multiple of 16 bytes in size. + * Each of these things must be a multiple of 16 bytes in size. The following + * structure represent all of this except the __SIGNAL_FRAMESIZE gap * */ -struct sigregs { +struct sigframe { + struct sigcontext sctx; /* the sigcontext */ struct mcontext mctx; /* all the register values */ /* * Programs using the rs6000/xcoff abi can save up to 19 gp @@ -698,21 +701,16 @@ int compat_sys_sigaltstack(u32 __new, u32 __old, int r5, */ int handle_rt_signal32(unsigned long sig, struct k_sigaction *ka, siginfo_t *info, sigset_t *oldset, - struct pt_regs *regs, unsigned long newsp) + struct pt_regs *regs) { struct rt_sigframe __user *rt_sf; struct mcontext __user *frame; - unsigned long origsp = newsp; + unsigned long newsp = 0; /* Set up Signal Frame */ /* Put a Real Time Context onto stack */ - newsp -= sizeof(*rt_sf); - rt_sf = (struct rt_sigframe __user *)newsp; - - /* create a stack frame for the caller of the handler */ - newsp -= __SIGNAL_FRAMESIZE + 16; - - if (!access_ok(VERIFY_WRITE, (void __user *)newsp, origsp - newsp)) + rt_sf = get_sigframe(ka, regs, sizeof(*rt_sf)); + if (unlikely(rt_sf == NULL)) goto badframe; /* Put the siginfo & fill in most of the ucontext */ @@ -742,8 +740,12 @@ int handle_rt_signal32(unsigned long sig, struct k_sigaction *ka, current->thread.fpscr.val = 0; /* turn off all fp exceptions */ + /* create a stack frame for the caller of the handler */ + newsp = ((unsigned long)rt_sf) - (__SIGNAL_FRAMESIZE + 16); if (put_user(regs->gpr[1], (u32 __user *)newsp)) goto badframe; + + /* Fill registers for signal handler */ regs->gpr[1] = newsp; regs->gpr[3] = sig; regs->gpr[4] = (unsigned long) &rt_sf->info; @@ -988,26 +990,17 @@ int sys_debug_setcontext(struct ucontext __user *ctx, * OK, we're invoking a handler */ int handle_signal32(unsigned long sig, struct k_sigaction *ka, - siginfo_t *info, sigset_t *oldset, struct pt_regs *regs, - unsigned long newsp) + siginfo_t *info, sigset_t *oldset, struct pt_regs *regs) { struct sigcontext __user *sc; - struct sigregs __user *frame; - unsigned long origsp = newsp; + struct sigframe __user *frame; + unsigned long newsp = 0; /* Set up Signal Frame */ - newsp -= sizeof(struct sigregs); - frame = (struct sigregs __user *) newsp; - - /* Put a sigcontext on the stack */ - newsp -= sizeof(*sc); - sc = (struct sigcontext __user *) newsp; - - /* create a stack frame for the caller of the handler */ - newsp -= __SIGNAL_FRAMESIZE; - - if (!access_ok(VERIFY_WRITE, (void __user *) newsp, origsp - newsp)) + frame = get_sigframe(ka, regs, sizeof(*frame)); + if (unlikely(frame == NULL)) goto badframe; + sc = (struct sigcontext __user *) &frame->sctx; #if _NSIG != 64 #error "Please adjust handle_signal()" @@ -1019,7 +1012,7 @@ int handle_signal32(unsigned long sig, struct k_sigaction *ka, #else || __put_user(oldset->sig[1], &sc->_unused[3]) #endif - || __put_user(to_user_ptr(frame), &sc->regs) + || __put_user(to_user_ptr(&frame->mctx), &sc->regs) || __put_user(sig, &sc->signal)) goto badframe; @@ -1035,8 +1028,11 @@ int handle_signal32(unsigned long sig, struct k_sigaction *ka, current->thread.fpscr.val = 0; /* turn off all fp exceptions */ + /* create a stack frame for the caller of the handler */ + newsp = ((unsigned long)frame) - __SIGNAL_FRAMESIZE; if (put_user(regs->gpr[1], (u32 __user *)newsp)) goto badframe; + regs->gpr[1] = newsp; regs->gpr[3] = sig; regs->gpr[4] = (unsigned long) sc; diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index c17903c..5004a97 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -196,25 +196,6 @@ static long restore_sigcontext(struct pt_regs *regs, sigset_t *set, int sig, } /* - * Allocate space for the signal frame - */ -static inline void __user * get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, - size_t frame_size) -{ - unsigned long newsp; - - /* Default to using normal stack */ - newsp = regs->gpr[1]; - - if ((ka->sa.sa_flags & SA_ONSTACK) && current->sas_ss_size) { - if (! on_sig_stack(regs->gpr[1])) - newsp = (current->sas_ss_sp + current->sas_ss_size); - } - - return (void __user *)((newsp - frame_size) & -16ul); -} - -/* * Setup the trampoline code on the stack */ static long setup_trampoline(unsigned int syscall, unsigned int __user *tramp) @@ -348,8 +329,7 @@ int handle_rt_signal64(int signr, struct k_sigaction *ka, siginfo_t *info, long err = 0; frame = get_sigframe(ka, regs, sizeof(*frame)); - - if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame))) + if (unlikely(frame == NULL)) goto badframe; err |= __put_user(&frame->info, &frame->pinfo); @@ -386,7 +366,7 @@ int handle_rt_signal64(int signr, struct k_sigaction *ka, siginfo_t *info, funct_desc_ptr = (func_descr_t __user *) ka->sa.sa_handler; /* Allocate a dummy caller frame for the signal handler. */ - newsp = (unsigned long)frame - __SIGNAL_FRAMESIZE; + newsp = ((unsigned long)frame) - __SIGNAL_FRAMESIZE; err |= put_user(regs->gpr[1], (unsigned long __user *)newsp); /* Set up "regs" so we "return" to the signal handler. */ -- cgit v1.1 From 0edc4ffd0e50d1ab0f387d37457210bc8bf8f8da Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 4 Jun 2007 15:15:55 +1000 Subject: [POWERPC] Remove #ifdef around set_dabr in signal code set_dabr() and thread.dabr exist on 32 bits as well nowadays (they actually may do something even, depending on what CPU you have). So this removes the ifdef. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/signal.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index dee2750..88d8977 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -146,7 +146,6 @@ int do_signal(sigset_t *oldset, struct pt_regs *regs) return 0; /* no signals delivered */ } -#ifdef CONFIG_PPC64 /* * Reenable the DABR before delivering the signal to * user space. The DABR will have been cleared if it @@ -154,7 +153,6 @@ int do_signal(sigset_t *oldset, struct pt_regs *regs) */ if (current->thread.dabr) set_dabr(current->thread.dabr); -#endif if (is32) { if (ka.sa.sa_flags & SA_SIGINFO) -- cgit v1.1 From 2f97cd3912428f5044fa7715293a69349fc455fa Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 4 Jun 2007 15:15:56 +1000 Subject: [POWERPC] Less ifdef's in signal.c/signal.h This patch moves things around a little bit in the new common signal.c and signal.h files to remove the last #ifdef in the middle of the common do_signal(). Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/signal.c | 15 --------------- arch/powerpc/kernel/signal.h | 24 ++++++++++++++++++++++++ 2 files changed, 24 insertions(+), 15 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index 88d8977..c434d6c 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -16,19 +16,6 @@ #include "signal.h" - -#ifdef CONFIG_PPC64 -static inline int is_32bit_task(void) -{ - return test_thread_flag(TIF_32BIT); -} -#else -static inline int is_32bit_task(void) -{ - return 1; -} -#endif - /* * Allocate space for the signal frame */ @@ -161,10 +148,8 @@ int do_signal(sigset_t *oldset, struct pt_regs *regs) else ret = handle_signal32(signr, &ka, &info, oldset, regs); -#ifdef CONFIG_PPC64 } else { ret = handle_rt_signal64(signr, &ka, &info, oldset, regs); -#endif } if (ret) { diff --git a/arch/powerpc/kernel/signal.h b/arch/powerpc/kernel/signal.h index c284f75..77efb3d 100644 --- a/arch/powerpc/kernel/signal.h +++ b/arch/powerpc/kernel/signal.h @@ -24,8 +24,32 @@ extern int handle_rt_signal32(unsigned long sig, struct k_sigaction *ka, siginfo_t *info, sigset_t *oldset, struct pt_regs *regs); + +#ifdef CONFIG_PPC64 + +static inline int is_32bit_task(void) +{ + return test_thread_flag(TIF_32BIT); +} + extern int handle_rt_signal64(int signr, struct k_sigaction *ka, siginfo_t *info, sigset_t *set, struct pt_regs *regs); +#else /* CONFIG_PPC64 */ + +static inline int is_32bit_task(void) +{ + return 1; +} + +static inline int handle_rt_signal64(int signr, struct k_sigaction *ka, + siginfo_t *info, sigset_t *set, + struct pt_regs *regs) +{ + return -EFAULT; +} + +#endif /* !defined(CONFIG_PPC64) */ + #endif /* _POWERPC_ARCH_SIGNAL_H */ -- cgit v1.1 From d8c391a5593aca5bea002bcaaec16c7bbd6ec853 Mon Sep 17 00:00:00 2001 From: Jake Moilanen Date: Fri, 8 Jun 2007 07:27:11 +1000 Subject: [POWERPC] Donate idle CPU cycles on dedicated partitions A Power6 can give up CPU cycles on a dedicated CPU (as opposed to a shared CPU) to other shared processors if the administrator asks for it (via the HMC). This enables that to work properly on P6. This just involves setting a bit in the CAS structure as well as the VPA. To donate cycles, a CPU has to have all SMT threads idle and have the donate bit set in the VPA. Then call H_CEDE. The reason why shared processors just aren't used is because dedicated CPUs are guaranteed an actual processor, yet the system is still able to increase the capacity of the shared CPU pool. Also rename the VPA's cpuctls_task_attrs field to a more accurate name. Signed-off-by: Jake Moilanen Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/prom_init.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index d6047c4..a1d582e 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -635,6 +635,7 @@ static void __init early_cmdline_parse(void) /* ibm,dynamic-reconfiguration-memory property supported */ #define OV5_DRCONF_MEMORY 0x20 #define OV5_LARGE_PAGES 0x10 /* large pages supported */ +#define OV5_DONATE_DEDICATE_CPU 0x02 /* donate dedicated CPU support */ /* PCIe/MSI support. Without MSI full PCIe is not supported */ #ifdef CONFIG_PCI_MSI #define OV5_MSI 0x01 /* PCIe/MSI support */ @@ -685,7 +686,8 @@ static unsigned char ibm_architecture_vec[] = { /* option vector 5: PAPR/OF options */ 3 - 2, /* length */ 0, /* don't ignore, don't halt */ - OV5_LPAR | OV5_SPLPAR | OV5_LARGE_PAGES | OV5_DRCONF_MEMORY | OV5_MSI, + OV5_LPAR | OV5_SPLPAR | OV5_LARGE_PAGES | OV5_DRCONF_MEMORY | + OV5_DONATE_DEDICATE_CPU | OV5_MSI, }; /* Old method - ELF header with PT_NOTE sections */ -- cgit v1.1 From f21f49ea639ac3f24824177dac1268af75a2d373 Mon Sep 17 00:00:00 2001 From: David Gibson Date: Wed, 13 Jun 2007 14:52:54 +1000 Subject: [POWERPC] Remove the dregs of APUS support from arch/powerpc APUS (the Amiga Power-Up System) is not supported under arch/powerpc and it's unlikely it ever will be. Therefore, this patch removes the fragments of APUS support code from arch/powerpc which have been copied from arch/ppc. A few APUS references are left in asm-powerpc in .h files which are still used from arch/ppc. Signed-off-by: David Gibson Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/head_32.S | 122 ++---------------------------------------- arch/powerpc/kernel/irq.c | 1 - 2 files changed, 3 insertions(+), 120 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index c897203..7d73a13 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -9,7 +9,6 @@ * rewritten by Paul Mackerras. * Copyright (C) 1996 Paul Mackerras. * MPC8xx modifications Copyright (C) 1997 Dan Malek (dmalek@jlc.net). - * Amiga/APUS changes by Jesper Skov (jskov@cygnus.co.uk). * * This file contains the low-level support and setup for the * PowerPC platform, including trap and interrupt dispatch. @@ -32,10 +31,6 @@ #include #include -#ifdef CONFIG_APUS -#include -#endif - /* 601 only have IBAT; cr0.eq is set on 601 when using this macro */ #define LOAD_BAT(n, reg, RA, RB) \ /* see the comment for clear_bats() -- Cort */ \ @@ -92,11 +87,6 @@ _start: * r4: virtual address of boot_infos_t * r5: 0 * - * APUS - * r3: 'APUS' - * r4: physical address of memory base - * Linux/m68k style BootInfo structure at &_end. - * * PREP * This is jumped to on prep systems right after the kernel is relocated * to its proper place in memory by the boot loader. The expected layout @@ -150,14 +140,6 @@ __start: */ bl early_init -#ifdef CONFIG_APUS -/* On APUS the __va/__pa constants need to be set to the correct - * values before continuing. - */ - mr r4,r30 - bl fix_mem_constants -#endif /* CONFIG_APUS */ - /* Switch MMU off, clear BATs and flush TLB. At this point, r3 contains * the physical address we are running at, returned by early_init() */ @@ -167,7 +149,7 @@ __after_mmu_off: bl flush_tlbs bl initial_bats -#if !defined(CONFIG_APUS) && defined(CONFIG_BOOTX_TEXT) +#if defined(CONFIG_BOOTX_TEXT) bl setup_disp_bat #endif @@ -183,7 +165,6 @@ __after_mmu_off: #endif /* CONFIG_6xx */ -#ifndef CONFIG_APUS /* * We need to run with _start at physical address 0. * On CHRP, we are loaded at 0x10000 since OF on CHRP uses @@ -196,7 +177,6 @@ __after_mmu_off: addis r4,r3,KERNELBASE@h /* current address of _start */ cmpwi 0,r4,0 /* are we already running at 0? */ bne relocate_kernel -#endif /* CONFIG_APUS */ /* * we now have the 1st 16M of ram mapped with the bats. * prep needs the mmu to be turned on here, but pmac already has it on. @@ -881,85 +861,6 @@ _GLOBAL(copy_and_flush) addi r6,r6,4 blr -#ifdef CONFIG_APUS -/* - * On APUS the physical base address of the kernel is not known at compile - * time, which means the __pa/__va constants used are incorrect. In the - * __init section is recorded the virtual addresses of instructions using - * these constants, so all that has to be done is fix these before - * continuing the kernel boot. - * - * r4 = The physical address of the kernel base. - */ -fix_mem_constants: - mr r10,r4 - addis r10,r10,-KERNELBASE@h /* virt_to_phys constant */ - neg r11,r10 /* phys_to_virt constant */ - - lis r12,__vtop_table_begin@h - ori r12,r12,__vtop_table_begin@l - add r12,r12,r10 /* table begin phys address */ - lis r13,__vtop_table_end@h - ori r13,r13,__vtop_table_end@l - add r13,r13,r10 /* table end phys address */ - subi r12,r12,4 - subi r13,r13,4 -1: lwzu r14,4(r12) /* virt address of instruction */ - add r14,r14,r10 /* phys address of instruction */ - lwz r15,0(r14) /* instruction, now insert top */ - rlwimi r15,r10,16,16,31 /* half of vp const in low half */ - stw r15,0(r14) /* of instruction and restore. */ - dcbst r0,r14 /* write it to memory */ - sync - icbi r0,r14 /* flush the icache line */ - cmpw r12,r13 - bne 1b - sync /* additional sync needed on g4 */ - isync - -/* - * Map the memory where the exception handlers will - * be copied to when hash constants have been patched. - */ -#ifdef CONFIG_APUS_FAST_EXCEPT - lis r8,0xfff0 -#else - lis r8,0 -#endif - ori r8,r8,0x2 /* 128KB, supervisor */ - mtspr SPRN_DBAT3U,r8 - mtspr SPRN_DBAT3L,r8 - - lis r12,__ptov_table_begin@h - ori r12,r12,__ptov_table_begin@l - add r12,r12,r10 /* table begin phys address */ - lis r13,__ptov_table_end@h - ori r13,r13,__ptov_table_end@l - add r13,r13,r10 /* table end phys address */ - subi r12,r12,4 - subi r13,r13,4 -1: lwzu r14,4(r12) /* virt address of instruction */ - add r14,r14,r10 /* phys address of instruction */ - lwz r15,0(r14) /* instruction, now insert top */ - rlwimi r15,r11,16,16,31 /* half of pv const in low half*/ - stw r15,0(r14) /* of instruction and restore. */ - dcbst r0,r14 /* write it to memory */ - sync - icbi r0,r14 /* flush the icache line */ - cmpw r12,r13 - bne 1b - - sync /* additional sync needed on g4 */ - isync /* No speculative loading until now */ - blr - -/*********************************************************************** - * Please note that on APUS the exception handlers are located at the - * physical address 0xfff0000. For this reason, the exception handlers - * cannot use relative branches to access the code below. - ***********************************************************************/ -#endif /* CONFIG_APUS */ - #ifdef CONFIG_SMP #ifdef CONFIG_GEMINI .globl __secondary_start_gemini @@ -1135,19 +1036,6 @@ start_here: bl __save_cpu_setup bl MMU_init -#ifdef CONFIG_APUS - /* Copy exception code to exception vector base on APUS. */ - lis r4,KERNELBASE@h -#ifdef CONFIG_APUS_FAST_EXCEPT - lis r3,0xfff0 /* Copy to 0xfff00000 */ -#else - lis r3,0 /* Copy to 0x00000000 */ -#endif - li r5,0x4000 /* # bytes of memory to copy */ - li r6,0 - bl copy_and_flush /* copy the first 0x4000 bytes */ -#endif /* CONFIG_APUS */ - /* * Go back to running unmapped so we can load up new values * for SDR1 (hash table pointer) and the segment registers @@ -1324,11 +1212,7 @@ initial_bats: #else ori r8,r8,2 /* R/W access */ #endif /* CONFIG_SMP */ -#ifdef CONFIG_APUS - ori r11,r11,BL_8M<<2|0x2 /* set up 8MB BAT registers for 604 */ -#else ori r11,r11,BL_256M<<2|0x2 /* set up BAT registers for 604 */ -#endif /* CONFIG_APUS */ mtspr SPRN_DBAT0L,r8 /* N.B. 6xx (not 601) have valid */ mtspr SPRN_DBAT0U,r11 /* bit in upper BAT register */ @@ -1338,7 +1222,7 @@ initial_bats: blr -#if !defined(CONFIG_APUS) && defined(CONFIG_BOOTX_TEXT) +#ifdef CONFIG_BOOTX_TEXT setup_disp_bat: /* * setup the display bat prepared for us in prom.c @@ -1362,7 +1246,7 @@ setup_disp_bat: 1: mtspr SPRN_IBAT3L,r8 mtspr SPRN_IBAT3U,r11 blr -#endif /* !defined(CONFIG_APUS) && defined(CONFIG_BOOTX_TEXT) */ +#endif /* CONFIG_BOOTX_TEXT */ #ifdef CONFIG_8260 /* Jump into the system reset for the rom. diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 42c8ed6..b74b0fd 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -7,7 +7,6 @@ * Copyright (C) 1996-2001 Cort Dougan * Adapted for Power Macintosh by Paul Mackerras * Copyright (C) 1996 Paul Mackerras (paulus@cs.anu.edu.au) - * Amiga/APUS changes by Jesper Skov (jskov@cygnus.co.uk). * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License -- cgit v1.1 From 4508dc21feb189159d4cc1d5b79c5a55fad5f2ed Mon Sep 17 00:00:00 2001 From: David Gibson Date: Wed, 13 Jun 2007 14:52:57 +1000 Subject: [POWERPC] Merge CPU features pertaining to icache coherency Currently the powerpc kernel has a 64-bit only feature, COHERENT_ICACHE used for those CPUS which maintain icache/dcache coherency in hardware (POWER5, essentially). It also has a feature, SPLIT_ID_CACHE, which is used on CPUs which have separate i and d-caches, which is to say everything except 601 and Freescale E200. In nearly all the places we check the SPLIT_ID_CACHE, what we actually care about is whether the i and d-caches are coherent (which they will be, trivially, if they're the same cache). This tries to clarify the situation a little. The COHERENT_ICACHE feature becomes availble on 32-bit and is set for all CPUs where i and d-cache are effectively coherent, whether this is due to special logic (POWER5) or because they're unified. We check this, instead of SPLIT_ID_CACHE nearly everywhere. The SPLIT_ID_CACHE feature itself is replaced by a UNIFIED_ID_CACHE feature with reversed sense, set only on 601 and Freescale E200. In the two places (one Freescale BookE specific) where we really care whether it's a unified cache, not whether they're coherent, we check this feature. The CPUs with unified cache are so few, we could consider replacing this feature bit with explicit checks against the PVR. This will make unifying the 32-bit and 64-bit cache flush code a little more straightforward. Signed-off-by: David Gibson Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/misc_32.S | 10 +++++----- arch/powerpc/kernel/setup_32.c | 12 +++++------- 2 files changed, 10 insertions(+), 12 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 98decf8..e708ab7 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -392,7 +392,7 @@ BEGIN_FTR_SECTION mtspr SPRN_L1CSR0,r3 isync blr -END_FTR_SECTION_IFCLR(CPU_FTR_SPLIT_ID_CACHE) +END_FTR_SECTION_IFSET(CPU_FTR_UNIFIED_ID_CACHE) mfspr r3,SPRN_L1CSR1 ori r3,r3,L1CSR1_ICFI|L1CSR1_ICLFR mtspr SPRN_L1CSR1,r3 @@ -419,7 +419,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_SPLIT_ID_CACHE) _GLOBAL(__flush_icache_range) BEGIN_FTR_SECTION blr /* for 601, do nothing */ -END_FTR_SECTION_IFCLR(CPU_FTR_SPLIT_ID_CACHE) +END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) li r5,L1_CACHE_BYTES-1 andc r3,r3,r5 subf r4,r3,r4 @@ -514,8 +514,8 @@ _GLOBAL(invalidate_dcache_range) */ _GLOBAL(__flush_dcache_icache) BEGIN_FTR_SECTION - blr /* for 601, do nothing */ -END_FTR_SECTION_IFCLR(CPU_FTR_SPLIT_ID_CACHE) + 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 */ mtctr r4 @@ -543,7 +543,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_SPLIT_ID_CACHE) _GLOBAL(__flush_dcache_icache_phys) BEGIN_FTR_SECTION blr /* for 601, do nothing */ -END_FTR_SECTION_IFCLR(CPU_FTR_SPLIT_ID_CACHE) +END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) mfmsr r10 rlwinm r0,r10,0,28,26 /* clear DR */ mtmsr r0 diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 35f8f44..7ec6ba5 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -262,13 +262,11 @@ void __init setup_arch(char **cmdline_p) * Systems with OF can look in the properties on the cpu node(s) * for a possibly more accurate value. */ - if (cpu_has_feature(CPU_FTR_SPLIT_ID_CACHE)) { - dcache_bsize = cur_cpu_spec->dcache_bsize; - icache_bsize = cur_cpu_spec->icache_bsize; - ucache_bsize = 0; - } else - ucache_bsize = dcache_bsize = icache_bsize - = cur_cpu_spec->dcache_bsize; + dcache_bsize = cur_cpu_spec->dcache_bsize; + icache_bsize = cur_cpu_spec->icache_bsize; + ucache_bsize = 0; + if (cpu_has_feature(CPU_FTR_UNIFIED_ID_CACHE)) + ucache_bsize = icache_bsize = dcache_bsize; /* reboot on panic */ panic_timeout = 180; -- cgit v1.1 From ee46a90b599952bb1a9dc67f894710017e7cc409 Mon Sep 17 00:00:00 2001 From: Milton Miller Date: Wed, 11 Apr 2007 18:32:17 +1000 Subject: [POWERPC] kexec: Send slaves to new kernel earlier With this, when kexec-ing, we copy the code and start the slaves on their journey to the next kernel's spin loop as soon as we copy the kexec image into place. The kernel doesn't know exactly which slaves are spinning in kexec_wait. This allows us to pass more than max-cpus to the next kernel. But it also means that we might leave some behind. Moving the code here means they have the time it takes us to clear the hash table to wake up and move on. Moving the code any earlier would reuqire walking the image description to search for the code, which could span multiple pages. Signed-off-by: Milton Miller Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/misc_64.S | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index 519861d..bbb3ba5 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -646,6 +646,19 @@ _GLOBAL(kexec_sequence) /* turn off mmu */ bl real_mode + /* copy 0x100 bytes starting at start to 0 */ + li r3,0 + mr r4,r30 /* start, aka phys mem offset */ + li r5,0x100 + li r6,0 + bl .copy_and_flush /* (dest, src, copy limit, start offset) */ +1: /* assume normal blr return */ + + /* release other cpus to the new kernel secondary start at 0x60 */ + mflr r5 + li r6,1 + stw r6,kexec_flag-1b(5) + /* clear out hardware hash page table and tlb */ ld r5,0(r27) /* deref function descriptor */ mtctr r5 @@ -676,19 +689,6 @@ _GLOBAL(kexec_sequence) * are the boot cpu ????? * other device tree differences (prop sizes, va vs pa, etc)... */ - - /* copy 0x100 bytes starting at start to 0 */ - li r3,0 - mr r4,r30 - li r5,0x100 - li r6,0 - bl .copy_and_flush /* (dest, src, copy limit, start offset) */ -1: /* assume normal blr return */ - - /* release other cpus to the new kernel secondary start at 0x60 */ - mflr r5 - li r6,1 - stw r6,kexec_flag-1b(5) mr r3,r25 # my phys cpu mr r4,r30 # start, aka phys mem offset mtlr 4 -- cgit v1.1 From df211c8a478e16232ebbc16e650b19163183fcb6 Mon Sep 17 00:00:00 2001 From: Nathan Lynch Date: Wed, 23 May 2007 10:51:25 +1000 Subject: [POWERPC] Remove spinlock from struct cpu_purr_data cpu_purr_data is a per-cpu array used to account for stolen time on partitioned systems. It used to be the case that cpus accessed each others' cpu_purr_data, so each entry was protected by a spinlock. However, the code was reworked ("Simplify stolen time calculation") with the result that each cpu accesses its own cpu_purr_data and not those of other cpus. This means we can get rid of the spinlock as long as we're careful to disable interrupts when accessing cpu_purr_data in process context. Signed-off-by: Nathan Lynch Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/time.c | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 2c8564d..0a8a820 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -222,19 +222,28 @@ struct cpu_purr_data { int initialized; /* thread is running */ u64 tb; /* last TB value read */ u64 purr; /* last PURR value read */ - spinlock_t lock; }; +/* + * Each entry in the cpu_purr_data array is manipulated only by its + * "owner" cpu -- usually in the timer interrupt but also occasionally + * in process context for cpu online. As long as cpus do not touch + * each others' cpu_purr_data, disabling local interrupts is + * sufficient to serialize accesses. + */ static DEFINE_PER_CPU(struct cpu_purr_data, cpu_purr_data); static void snapshot_tb_and_purr(void *data) { + unsigned long flags; struct cpu_purr_data *p = &__get_cpu_var(cpu_purr_data); + local_irq_save(flags); p->tb = mftb(); p->purr = mfspr(SPRN_PURR); wmb(); p->initialized = 1; + local_irq_restore(flags); } /* @@ -242,15 +251,14 @@ static void snapshot_tb_and_purr(void *data) */ void snapshot_timebases(void) { - int cpu; - if (!cpu_has_feature(CPU_FTR_PURR)) return; - for_each_possible_cpu(cpu) - spin_lock_init(&per_cpu(cpu_purr_data, cpu).lock); on_each_cpu(snapshot_tb_and_purr, NULL, 0, 1); } +/* + * Must be called with interrupts disabled. + */ void calculate_steal_time(void) { u64 tb, purr; @@ -262,7 +270,6 @@ void calculate_steal_time(void) pme = &per_cpu(cpu_purr_data, smp_processor_id()); if (!pme->initialized) return; /* this can happen in early boot */ - spin_lock(&pme->lock); tb = mftb(); purr = mfspr(SPRN_PURR); stolen = (tb - pme->tb) - (purr - pme->purr); @@ -270,7 +277,6 @@ void calculate_steal_time(void) account_steal_time(current, stolen); pme->tb = tb; pme->purr = purr; - spin_unlock(&pme->lock); } /* @@ -284,12 +290,12 @@ static void snapshot_purr(void) if (!cpu_has_feature(CPU_FTR_PURR)) return; + local_irq_save(flags); pme = &per_cpu(cpu_purr_data, smp_processor_id()); - spin_lock_irqsave(&pme->lock, flags); pme->tb = mftb(); pme->purr = mfspr(SPRN_PURR); pme->initialized = 1; - spin_unlock_irqrestore(&pme->lock, flags); + local_irq_restore(flags); } #endif /* CONFIG_PPC_SPLPAR */ -- cgit v1.1 From 35923f12e42a3baf4ac6da7c05cf5f7478e5a7c6 Mon Sep 17 00:00:00 2001 From: Olof Johansson Date: Mon, 4 Jun 2007 14:47:04 +1000 Subject: [POWERPC] Uninline and export virq_to_hw() Uninline virq_to_hw and export it so modules can use it. The alternative would be to export the irq_map array instead, but it's an infrequently called function, and keeping the array unexported seems considerably cleaner. Signed-off-by: Olof Johansson Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/irq.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index b74b0fd..0a76989 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -411,6 +411,12 @@ struct irq_map_entry irq_map[NR_IRQS]; static unsigned int irq_virq_count = NR_IRQS; static struct irq_host *irq_default_host; +irq_hw_number_t virq_to_hw(unsigned int virq) +{ + return irq_map[virq].hwirq; +} +EXPORT_SYMBOL_GPL(virq_to_hw); + struct irq_host *irq_alloc_host(unsigned int revmap_type, unsigned int revmap_arg, struct irq_host_ops *ops, -- cgit v1.1 From 6fde40f3f1a9641ea0a41471cea77f34c0cbb36f Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Mon, 4 Jun 2007 22:59:59 +1000 Subject: [POWERPC] Split virq setup logic out into irq_setup_virq() A future patch will need the logic at the end of irq_create_mapping() which setups a virq and installs it in the irq_map. So split it out into a new function irq_setup_virq(). Signed-off-by: Michael Ellerman Acked-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/irq.c | 32 +++++++++++++++++++++----------- 1 file changed, 21 insertions(+), 11 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 0a76989..d806b18 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -596,6 +596,25 @@ static void irq_radix_rdunlock(unsigned long flags) local_irq_restore(flags); } +static int irq_setup_virq(struct irq_host *host, unsigned int virq, + irq_hw_number_t hwirq) +{ + /* Clear IRQ_NOREQUEST flag */ + get_irq_desc(virq)->status &= ~IRQ_NOREQUEST; + + /* map it */ + smp_wmb(); + irq_map[virq].hwirq = hwirq; + smp_mb(); + + if (host->ops->map(host, virq, hwirq)) { + pr_debug("irq: -> mapping failed, freeing\n"); + irq_free_virt(virq, 1); + return -1; + } + + return 0; +} unsigned int irq_create_mapping(struct irq_host *host, irq_hw_number_t hwirq) @@ -644,18 +663,9 @@ unsigned int irq_create_mapping(struct irq_host *host, } pr_debug("irq: -> obtained virq %d\n", virq); - /* Clear IRQ_NOREQUEST flag */ - get_irq_desc(virq)->status &= ~IRQ_NOREQUEST; - - /* map it */ - smp_wmb(); - irq_map[virq].hwirq = hwirq; - smp_mb(); - if (host->ops->map(host, virq, hwirq)) { - pr_debug("irq: -> mapping failed, freeing\n"); - irq_free_virt(virq, 1); + if (irq_setup_virq(host, virq, hwirq)) return NO_IRQ; - } + return virq; } EXPORT_SYMBOL_GPL(irq_create_mapping); -- cgit v1.1 From ee51de5645edee4124db6a479d2e135ebe436748 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Mon, 4 Jun 2007 23:00:00 +1000 Subject: [POWERPC] Add irq_create_direct_mapping() This patch adds irq_create_direct_mapping(). This routine is an alternative to irq_create_mapping(), for irq controllers that can use linux virq numbers directly as hardware numbers. Signed-off-by: Michael Ellerman Acked-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/irq.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index d806b18..a335156 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -616,6 +616,30 @@ static int irq_setup_virq(struct irq_host *host, unsigned int virq, return 0; } +unsigned int irq_create_direct_mapping(struct irq_host *host) +{ + unsigned int virq; + + if (host == NULL) + host = irq_default_host; + + BUG_ON(host == NULL); + WARN_ON(host->revmap_type != IRQ_HOST_MAP_NOMAP); + + virq = irq_alloc_virt(host, 1, 0); + if (virq == NO_IRQ) { + pr_debug("irq: create_direct virq allocation failed\n"); + return NO_IRQ; + } + + pr_debug("irq: create_direct obtained virq %d\n", virq); + + if (irq_setup_virq(host, virq, virq)) + return NO_IRQ; + + return virq; +} + unsigned int irq_create_mapping(struct irq_host *host, irq_hw_number_t hwirq) { -- cgit v1.1 From 4cefebb1b497a84d61f2fa29d497df75a84b69d4 Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Fri, 8 Jun 2007 13:18:50 +1000 Subject: [POWERPC] Fix stolen time for SMT without LPAR For POWERPC, stolen time accounts for cycles lost to the hypervisor or PURR cycles attributed to the other SMT thread. Hence, when a PURR is available, we should still calculate stolen time, irrespective of being virtualised. Signed-off-by: Michael Neuling Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/time.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 0a8a820..43c687a 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -214,7 +214,6 @@ static void account_process_time(struct pt_regs *regs) run_posix_cpu_timers(current); } -#ifdef CONFIG_PPC_SPLPAR /* * Stuff for accounting stolen time. */ @@ -279,6 +278,7 @@ void calculate_steal_time(void) pme->purr = purr; } +#ifdef CONFIG_PPC_SPLPAR /* * Must be called before the cpu is added to the online map when * a cpu is being brought up at runtime. -- cgit v1.1 From 5a26f6bbb767d7ad23311a1e81cfdd2bebefb855 Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Fri, 8 Jun 2007 14:00:35 +1000 Subject: [POWERPC] Do firmware feature fixups after features are initialised On pSeries the firmware features are not setup until ppc_md.init_early, so we can't do the firmware feature sections fixups till after this. Currently firmware feature sections is only used on iSeries which inits the firmware features much earlier. This is a bug in waiting on pSeries. Signed-off-by: Michael Neuling Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/setup_64.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 6018178..bc43bba 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -350,13 +350,11 @@ void __init setup_system(void) { DBG(" -> setup_system()\n"); - /* Apply the CPUs-specific and firmware specific fixups to kernel - * text (nop out sections not relevant to this CPU or this firmware) + /* Apply CPUs-specific fixups to kernel text (nop out sections + * not relevant to this CPU) */ do_feature_fixups(cur_cpu_spec->cpu_features, &__start___ftr_fixup, &__stop___ftr_fixup); - do_feature_fixups(powerpc_firmware_features, - &__start___fw_ftr_fixup, &__stop___fw_ftr_fixup); /* * Unflatten the device-tree passed by prom_init or kexec @@ -394,6 +392,12 @@ void __init setup_system(void) if (ppc_md.init_early) ppc_md.init_early(); + /* Apply firmware specific fixups to kernel text (nop out + * sections not relevant to this firmware) + */ + do_feature_fixups(powerpc_firmware_features, + &__start___fw_ftr_fixup, &__stop___fw_ftr_fixup); + /* * We can discover serial ports now since the above did setup the * hash table management for us, thus ioremap works. We do that early -- cgit v1.1 From 443481050168e98f91737a02b6428c93f1a1c652 Mon Sep 17 00:00:00 2001 From: Geoff Levand Date: Sat, 16 Jun 2007 08:06:14 +1000 Subject: [POWERPC] Output params value in early_init_devtree Add a printout of the params value to early_init_devtree. This value is handy to have for comparison when debugging the bootwrapper code. Signed-off-by: Geoff Levand Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/prom.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index af42dda..6f32bebd 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -1005,7 +1005,7 @@ static void __init early_reserve_mem(void) void __init early_init_devtree(void *params) { - DBG(" -> early_init_devtree()\n"); + DBG(" -> early_init_devtree(%p)\n", params); /* Setup flat device-tree pointer */ initial_boot_params = params; -- cgit v1.1 From 75423b7ba5eacc0a003b19e51af6a38feeed43ee Mon Sep 17 00:00:00 2001 From: Geoff Levand Date: Sat, 16 Jun 2007 08:06:23 +1000 Subject: [POWERPC] Correct __secondary_hold comment Remove references to pSeries and OpenFirmware in the __secondary_hold usage comment. __secondary_hold is a generic routine and can be used by other platforms. Signed-off-by: Geoff Levand Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/head_64.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 1111fce..8cdd48e 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -103,8 +103,8 @@ __secondary_hold_acknowledge: . = 0x60 /* - * The following code is used on pSeries to hold secondary processors - * in a spin loop after they have been freed from OpenFirmware, but + * The following code is used to hold secondary processors + * in a spin loop after they have entered the kernel, but * before the bulk of the kernel has been relocated. This code * is relocated to physical address 0x60 before prom_init is run. * All of it must fit below the first exception vector at 0x100. -- cgit v1.1 From 71712b455374a73af042fcfb5002fef5fd25ba44 Mon Sep 17 00:00:00 2001 From: Tony Breeds Date: Fri, 22 Jun 2007 16:54:30 +1000 Subject: [POWERPC] Move iSeries_tb_recal into its own late_initcall. Currently iSeries will recalibrate the cputime_factors in the first settimeofday() call. It seems the reason for doing this is to ensure a resaonable time delta after time_init(). On current kernels (with udev), this call is made 40-60 seconds into the boot process, by moving it to a late initcall it is called approximately 5 seconds after time_init() is called. This is sufficient to recalibrate the timebase. Signed-off-by: Tony Breeds CC: Stephen Rothwell Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/time.c | 30 +++++++++++++++++++----------- 1 file changed, 19 insertions(+), 11 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 43c687a..66d2db7 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -77,9 +77,8 @@ /* keep track of when we need to update the rtc */ time_t last_rtc_update; #ifdef CONFIG_PPC_ISERIES -unsigned long iSeries_recal_titan = 0; -unsigned long iSeries_recal_tb = 0; -static unsigned long first_settimeofday = 1; +static unsigned long __initdata iSeries_recal_titan; +static signed long __initdata iSeries_recal_tb; #endif /* The decrementer counts down by 128 every 128ns on a 601. */ @@ -556,10 +555,15 @@ EXPORT_SYMBOL(profile_pc); * returned by the service processor for the timebase frequency. */ -static void iSeries_tb_recal(void) +static int __init iSeries_tb_recal(void) { struct div_result divres; unsigned long titan, tb; + + /* Make sure we only run on iSeries */ + if (!firmware_has_feature(FW_FEATURE_ISERIES)) + return -ENODEV; + tb = get_tb(); titan = HvCallXm_loadTod(); if ( iSeries_recal_titan ) { @@ -600,8 +604,18 @@ static void iSeries_tb_recal(void) } iSeries_recal_titan = titan; iSeries_recal_tb = tb; + + return 0; } -#endif +late_initcall(iSeries_tb_recal); + +/* Called from platform early init */ +void __init iSeries_time_init_early(void) +{ + iSeries_recal_tb = get_tb(); + iSeries_recal_titan = HvCallXm_loadTod(); +} +#endif /* CONFIG_PPC_ISERIES */ /* * For iSeries shared processors, we have to let the hypervisor @@ -765,12 +779,6 @@ int do_settimeofday(struct timespec *tv) * to the RTC again, or write to the RTC but then they don't call * settimeofday to perform this operation. */ -#ifdef CONFIG_PPC_ISERIES - if (firmware_has_feature(FW_FEATURE_ISERIES) && first_settimeofday) { - iSeries_tb_recal(); - first_settimeofday = 0; - } -#endif /* Make userspace gettimeofday spin until we're done. */ ++vdso_data->tb_update_count; -- cgit v1.1 From 131208c5bb51b794ee73013aeb3396bd015fb79e Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 27 Jun 2007 16:02:55 +1000 Subject: [POWERPC] Turn off debugging in arch/powerpc/kernel/pci_64.c Commit 3d5134ee8341bffc4f539049abb9e90d469b448d left debugging turned on in arch/powerpc/kernel/pci_64.c. This turns it off again. Signed-off-by: Michael Ellerman Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/pci_64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index 6ae67eb..9fa2ecb 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -11,7 +11,7 @@ * 2 of the License, or (at your option) any later version. */ -#define DEBUG +#undef DEBUG #include #include -- cgit v1.1 From 6d8ff10c3ab1e3d4a40788442f1369e868103e43 Mon Sep 17 00:00:00 2001 From: York Sun Date: Mon, 4 Jun 2007 11:56:42 -0500 Subject: [POWERPC] Let subordinate transparent bridges be transparent. In pcibios_fixup_bus(), bridges that are subordinate to transparent bridges were still relocating their IORESOURCE_IO and IO_RESOURCE_MEM start and end values. Fix this by preventing the transparent bridge from relocating the start and end values, thus allowing the subordinate non-transparent bridge full molestation rights. Signed-off-by: York Sun Signed-off-by: Andy Fleming Signed-off-by: Jon Loeliger Signed-off-by: Kumar Gala --- arch/powerpc/kernel/pci_32.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index e66064b..7738a28 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -1370,7 +1370,7 @@ void __init pcibios_fixup_bus(struct pci_bus *bus) for (i = 0; i < 4; ++i) { if ((res = bus->resource[i]) == NULL) continue; - if (!res->flags) + if (!res->flags || bus->self->transparent) continue; if (io_offset && (res->flags & IORESOURCE_IO)) { res->start += io_offset; -- cgit v1.1 From 6a506238b33efd93e60c1585d654b37e292183de Mon Sep 17 00:00:00 2001 From: Kumar Gala Date: Wed, 27 Jun 2007 01:14:04 -0500 Subject: [POWERPC] Removed dead code related to PCI on ppc32 There are no in kernel users of any off these functions and some of them were not even EXPORT_SYMBOL: - pci_bus_io_base() - pci_bus_io_base_phys() - pci_bus_mem_base_phys() - pci_resource_to_bus() - phys_to_bus() - pci_phys_to_bus() - pci_bus_to_phys() - pci_init_resource() - resource_fixup() Signed-off-by: Kumar Gala --- arch/powerpc/kernel/pci_32.c | 112 ---------------------------------------- arch/powerpc/kernel/ppc_ksyms.c | 3 -- 2 files changed, 115 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index 7738a28..2d4a1c4 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -1319,12 +1319,6 @@ pcibios_init(void) subsys_initcall(pcibios_init); -unsigned long resource_fixup(struct pci_dev * dev, struct resource * res, - unsigned long start, unsigned long size) -{ - return start; -} - void __init pcibios_fixup_bus(struct pci_bus *bus) { struct pci_controller *hose = (struct pci_controller *) bus->sysdata; @@ -1508,53 +1502,6 @@ pci_bus_to_hose(int bus) return NULL; } -void __iomem * -pci_bus_io_base(unsigned int bus) -{ - struct pci_controller *hose; - - hose = pci_bus_to_hose(bus); - if (!hose) - return NULL; - return hose->io_base_virt; -} - -unsigned long -pci_bus_io_base_phys(unsigned int bus) -{ - struct pci_controller *hose; - - hose = pci_bus_to_hose(bus); - if (!hose) - return 0; - return hose->io_base_phys; -} - -unsigned long -pci_bus_mem_base_phys(unsigned int bus) -{ - struct pci_controller *hose; - - hose = pci_bus_to_hose(bus); - if (!hose) - return 0; - return hose->pci_mem_offset; -} - -unsigned long -pci_resource_to_bus(struct pci_dev *pdev, struct resource *res) -{ - /* Hack alert again ! See comments in chrp_pci.c - */ - struct pci_controller* hose = - (struct pci_controller *)pdev->sysdata; - if (hose && res->flags & IORESOURCE_MEM) - return res->start - hose->pci_mem_offset; - /* We may want to do something with IOs here... */ - return res->start; -} - - static struct resource *__pci_mmap_make_offset(struct pci_dev *dev, resource_size_t *offset, enum pci_mmap_state mmap_state) @@ -1725,53 +1672,6 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, return ret; } -/* Obsolete functions. Should be removed once the symbios driver - * is fixed - */ -unsigned long -phys_to_bus(unsigned long pa) -{ - struct pci_controller *hose; - int i; - - for (hose = hose_head; hose; hose = hose->next) { - for (i = 0; i < 3; ++i) { - if (pa >= hose->mem_resources[i].start - && pa <= hose->mem_resources[i].end) { - /* - * XXX the hose->pci_mem_offset really - * only applies to mem_resources[0]. - * We need a way to store an offset for - * the others. -- paulus - */ - if (i == 0) - pa -= hose->pci_mem_offset; - return pa; - } - } - } - /* hmmm, didn't find it */ - return 0; -} - -unsigned long -pci_phys_to_bus(unsigned long pa, int busnr) -{ - struct pci_controller* hose = pci_bus_to_hose(busnr); - if (!hose) - return pa; - return pa - hose->pci_mem_offset; -} - -unsigned long -pci_bus_to_phys(unsigned int ba, int busnr) -{ - struct pci_controller* hose = pci_bus_to_hose(busnr); - if (!hose) - return ba; - return ba + hose->pci_mem_offset; -} - /* Provide information on locations of various I/O regions in physical * memory. Do this on a per-card basis so that we choose the right * root bridge. @@ -1853,18 +1753,6 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar, *end = rsrc->end - offset; } -void __init pci_init_resource(struct resource *res, resource_size_t start, - resource_size_t end, int flags, char *name) -{ - res->start = start; - res->end = end; - res->flags = flags; - res->name = name; - res->parent = NULL; - res->sibling = NULL; - res->child = NULL; -} - unsigned long pci_address_to_pio(phys_addr_t address) { struct pci_controller* hose = hose_head; diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index c96fa9b..c58f2de 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -106,9 +106,6 @@ EXPORT_SYMBOL(isa_mem_base); EXPORT_SYMBOL(pci_dram_offset); EXPORT_SYMBOL(pci_alloc_consistent); EXPORT_SYMBOL(pci_free_consistent); -EXPORT_SYMBOL(pci_bus_io_base); -EXPORT_SYMBOL(pci_bus_io_base_phys); -EXPORT_SYMBOL(pci_bus_mem_base_phys); EXPORT_SYMBOL(pci_bus_to_hose); #endif /* CONFIG_PCI */ -- cgit v1.1 From 5516b540e98de6f7474a4e7149470ad6a0bbc54a Mon Sep 17 00:00:00 2001 From: Kumar Gala Date: Wed, 27 Jun 2007 01:17:57 -0500 Subject: [POWERPC] Use global_number in ppc32 pci_controller Make the pci_controller struct use global_number for the PHB domain number instead of index to match what ppc64 does and reuse its pci_domain_nr code. Introduced a pci-common.c to handle shared code between ppc32 & ppc64. Signed-off-by: Kumar Gala --- arch/powerpc/kernel/Makefile | 2 +- arch/powerpc/kernel/pci-common.c | 53 ++++++++++++++++++++++++++++++++++++++++ arch/powerpc/kernel/pci_32.c | 6 ++--- arch/powerpc/kernel/pci_64.c | 16 ------------ 4 files changed, 57 insertions(+), 20 deletions(-) create mode 100644 arch/powerpc/kernel/pci-common.c (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index eb6a33e..42c42ec 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -68,7 +68,7 @@ obj-$(CONFIG_MODULES) += $(module-y) pci64-$(CONFIG_PPC64) += pci_64.o pci_dn.o isa-bridge.o pci32-$(CONFIG_PPC32) := pci_32.o -obj-$(CONFIG_PCI) += $(pci64-y) $(pci32-y) +obj-$(CONFIG_PCI) += $(pci64-y) $(pci32-y) pci-common.o obj-$(CONFIG_PCI_MSI) += msi.o kexec-$(CONFIG_PPC64) := machine_kexec_64.o kexec-$(CONFIG_PPC32) := machine_kexec_32.o diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c new file mode 100644 index 0000000..3ca8cfb --- /dev/null +++ b/arch/powerpc/kernel/pci-common.c @@ -0,0 +1,53 @@ +/* + * Contains common pci routines for ALL ppc platform + * + * 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. + */ + +#undef DEBUG + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include + +#ifdef DEBUG +#include +#define DBG(fmt...) printk(fmt) +#else +#define DBG(fmt...) +#endif + +/* + * Return the domain number for this bus. + */ +int pci_domain_nr(struct pci_bus *bus) +{ + if (firmware_has_feature(FW_FEATURE_ISERIES)) + return 0; + else { + struct pci_controller *hose = pci_bus_to_host(bus); + + return hose->global_number; + } +} + +EXPORT_SYMBOL(pci_domain_nr); diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index 2d4a1c4..56deb31 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -620,7 +620,7 @@ pcibios_alloc_controller(void) *hose_tail = hose; hose_tail = &hose->next; - hose->index = next_controller_index++; + hose->global_number = next_controller_index++; return hose; } @@ -1336,7 +1336,7 @@ void __init pcibios_fixup_bus(struct pci_bus *bus) if (!res->flags) { if (io_offset) printk(KERN_ERR "I/O resource not set for host" - " bridge %d\n", hose->index); + " bridge %d\n", hose->global_number); res->start = 0; res->end = IO_SPACE_LIMIT; res->flags = IORESOURCE_IO; @@ -1350,7 +1350,7 @@ void __init pcibios_fixup_bus(struct pci_bus *bus) if (i > 0) continue; printk(KERN_ERR "Memory resource not set for " - "host bridge %d\n", hose->index); + "host bridge %d\n", hose->global_number); res->start = hose->pci_mem_offset; res->end = ~0U; res->flags = IORESOURCE_MEM; diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index 9fa2ecb..57bdcd8 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -636,22 +636,6 @@ int pcibios_enable_device(struct pci_dev *dev, int mask) return 0; } -/* - * Return the domain number for this bus. - */ -int pci_domain_nr(struct pci_bus *bus) -{ - if (firmware_has_feature(FW_FEATURE_ISERIES)) - return 0; - else { - struct pci_controller *hose = pci_bus_to_host(bus); - - return hose->global_number; - } -} - -EXPORT_SYMBOL(pci_domain_nr); - /* Decide whether to display the domain number in /proc */ int pci_proc_domain(struct pci_bus *bus) { -- cgit v1.1 From dbf8471f5294b27ba9b6232ffc177dcd4e0a2fa5 Mon Sep 17 00:00:00 2001 From: Kumar Gala Date: Wed, 27 Jun 2007 01:56:50 -0500 Subject: [POWERPC] Merge ppc32 and ppc64 pcibios_alloc_controller() prototypes Make the ppc32 pcibios_alloc_controller take a device node to match the ppc64 prototypes and have it set arch_data. Signed-off-by: Kumar Gala --- arch/powerpc/kernel/pci_32.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index 56deb31..df3251c 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -610,7 +610,7 @@ pcibios_enable_resources(struct pci_dev *dev, int mask) static int next_controller_index; struct pci_controller * __init -pcibios_alloc_controller(void) +pcibios_alloc_controller(struct device_node *dev) { struct pci_controller *hose; @@ -621,6 +621,7 @@ pcibios_alloc_controller(void) hose_tail = &hose->next; hose->global_number = next_controller_index++; + hose->arch_data = dev; return hose; } -- cgit v1.1 From 0b1d40c4d4dd8f276d8d9730204b3a0a17ab0d61 Mon Sep 17 00:00:00 2001 From: Kumar Gala Date: Wed, 27 Jun 2007 10:27:33 -0500 Subject: [POWERPC] Move pci_bus_to_hose users to pci_bus_to_host In the places we can move to using pci_bus_to_host, this allows us to make pci_bus_to_host static and remove its export. Signed-off-by: Kumar Gala --- arch/powerpc/kernel/pci_32.c | 8 ++++---- arch/powerpc/kernel/ppc_ksyms.c | 1 - 2 files changed, 4 insertions(+), 5 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index df3251c..c81ffa2 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -766,7 +766,7 @@ static struct device_node *scan_OF_for_pci_bus(struct pci_bus *bus) /* Are we a root bus ? */ if (bus->self == NULL || bus->parent == NULL) { - struct pci_controller *hose = pci_bus_to_hose(bus->number); + struct pci_controller *hose = pci_bus_to_host(bus); if (hose == NULL) return NULL; return of_node_get(hose->arch_data); @@ -1492,7 +1492,7 @@ int pcibios_enable_device(struct pci_dev *dev, int mask) return 0; } -struct pci_controller* +static struct pci_controller* pci_bus_to_hose(int bus) { struct pci_controller* hose = hose_head; @@ -1507,7 +1507,7 @@ static struct resource *__pci_mmap_make_offset(struct pci_dev *dev, resource_size_t *offset, enum pci_mmap_state mmap_state) { - struct pci_controller *hose = pci_bus_to_hose(dev->bus->number); + struct pci_controller *hose = pci_bus_to_host(dev->bus); unsigned long io_offset = 0; int i, res_bit; @@ -1719,7 +1719,7 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar, const struct resource *rsrc, resource_size_t *start, resource_size_t *end) { - struct pci_controller *hose = pci_bus_to_hose(dev->bus->number); + struct pci_controller *hose = pci_bus_to_host(dev->bus); resource_size_t offset = 0; if (hose == NULL) diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index c58f2de..e973c32 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -106,7 +106,6 @@ EXPORT_SYMBOL(isa_mem_base); EXPORT_SYMBOL(pci_dram_offset); EXPORT_SYMBOL(pci_alloc_consistent); EXPORT_SYMBOL(pci_free_consistent); -EXPORT_SYMBOL(pci_bus_to_hose); #endif /* CONFIG_PCI */ EXPORT_SYMBOL(start_thread); -- cgit v1.1 From 58083dade53cd434e134cd26ae5e89061f6de1ff Mon Sep 17 00:00:00 2001 From: Kumar Gala Date: Wed, 27 Jun 2007 11:07:51 -0500 Subject: [POWERPC] Move common PCI code out of pci_32/pci_64 Moved the low hanging fruit that was either identical or close to it between ppc32 & ppc64 for PCI into pci-common.c Signed-off-by: Kumar Gala --- arch/powerpc/kernel/pci-common.c | 314 +++++++++++++++++++++++++++++++++++++++ arch/powerpc/kernel/pci_32.c | 294 ------------------------------------ arch/powerpc/kernel/pci_64.c | 309 -------------------------------------- 3 files changed, 314 insertions(+), 603 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 3ca8cfb..b518b88 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -51,3 +51,317 @@ int pci_domain_nr(struct pci_bus *bus) } EXPORT_SYMBOL(pci_domain_nr); + +#ifdef CONFIG_PPC_OF +static ssize_t pci_show_devspec(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct pci_dev *pdev; + struct device_node *np; + + pdev = to_pci_dev (dev); + np = pci_device_to_OF_node(pdev); + if (np == NULL || np->full_name == NULL) + return 0; + return sprintf(buf, "%s", np->full_name); +} +static DEVICE_ATTR(devspec, S_IRUGO, pci_show_devspec, NULL); +#endif /* CONFIG_PPC_OF */ + +/* Add sysfs properties */ +void pcibios_add_platform_entries(struct pci_dev *pdev) +{ +#ifdef CONFIG_PPC_OF + device_create_file(&pdev->dev, &dev_attr_devspec); +#endif /* CONFIG_PPC_OF */ +} + +char __init *pcibios_setup(char *str) +{ + return str; +} + +/* + * Reads the interrupt pin to determine if interrupt is use by card. + * If the interrupt is used, then gets the interrupt line from the + * openfirmware and sets it in the pci_dev and pci_config line. + */ +int pci_read_irq_line(struct pci_dev *pci_dev) +{ + struct of_irq oirq; + unsigned int virq; + + DBG("Try to map irq for %s...\n", pci_name(pci_dev)); + +#ifdef DEBUG + memset(&oirq, 0xff, sizeof(oirq)); +#endif + /* Try to get a mapping from the device-tree */ + if (of_irq_map_pci(pci_dev, &oirq)) { + u8 line, pin; + + /* If that fails, lets fallback to what is in the config + * space and map that through the default controller. We + * also set the type to level low since that's what PCI + * interrupts are. If your platform does differently, then + * either provide a proper interrupt tree or don't use this + * function. + */ + if (pci_read_config_byte(pci_dev, PCI_INTERRUPT_PIN, &pin)) + return -1; + if (pin == 0) + return -1; + if (pci_read_config_byte(pci_dev, PCI_INTERRUPT_LINE, &line) || + line == 0xff) { + return -1; + } + DBG(" -> no map ! Using irq line %d from PCI config\n", line); + + 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], + oirq.controller->full_name); + + virq = irq_create_of_mapping(oirq.controller, oirq.specifier, + oirq.size); + } + if(virq == NO_IRQ) { + DBG(" -> failed to map !\n"); + return -1; + } + + DBG(" -> mapped to linux irq %d\n", virq); + + pci_dev->irq = virq; + + return 0; +} +EXPORT_SYMBOL(pci_read_irq_line); + +/* + * Platform support for /proc/bus/pci/X/Y mmap()s, + * modelled on the sparc64 implementation by Dave Miller. + * -- paulus. + */ + +/* + * Adjust vm_pgoff of VMA such that it is the physical page offset + * corresponding to the 32-bit pci bus offset for DEV requested by the user. + * + * Basically, the user finds the base address for his device which he wishes + * to mmap. They read the 32-bit value from the config space base register, + * add whatever PAGE_SIZE multiple offset they wish, and feed this into the + * offset parameter of mmap on /proc/bus/pci/XXX for that device. + * + * Returns negative error code on failure, zero on success. + */ +static struct resource *__pci_mmap_make_offset(struct pci_dev *dev, + resource_size_t *offset, + enum pci_mmap_state mmap_state) +{ + struct pci_controller *hose = pci_bus_to_host(dev->bus); + unsigned long io_offset = 0; + int i, res_bit; + + if (hose == 0) + return NULL; /* should never happen */ + + /* If memory, add on the PCI bridge address offset */ + if (mmap_state == pci_mmap_mem) { +#if 0 /* See comment in pci_resource_to_user() for why this is disabled */ + *offset += hose->pci_mem_offset; +#endif + res_bit = IORESOURCE_MEM; + } else { + io_offset = (unsigned long)hose->io_base_virt - _IO_BASE; + *offset += io_offset; + res_bit = IORESOURCE_IO; + } + + /* + * Check that the offset requested corresponds to one of the + * resources of the device. + */ + for (i = 0; i <= PCI_ROM_RESOURCE; i++) { + struct resource *rp = &dev->resource[i]; + int flags = rp->flags; + + /* treat ROM as memory (should be already) */ + if (i == PCI_ROM_RESOURCE) + flags |= IORESOURCE_MEM; + + /* Active and same type? */ + if ((flags & res_bit) == 0) + continue; + + /* In the range of this resource? */ + if (*offset < (rp->start & PAGE_MASK) || *offset > rp->end) + continue; + + /* found it! construct the final physical address */ + if (mmap_state == pci_mmap_io) + *offset += hose->io_base_phys - io_offset; + return rp; + } + + return NULL; +} + +/* + * Set vm_page_prot of VMA, as appropriate for this architecture, for a pci + * device mapping. + */ +static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp, + pgprot_t protection, + enum pci_mmap_state mmap_state, + int write_combine) +{ + unsigned long prot = pgprot_val(protection); + + /* Write combine is always 0 on non-memory space mappings. On + * memory space, if the user didn't pass 1, we check for a + * "prefetchable" resource. This is a bit hackish, but we use + * this to workaround the inability of /sysfs to provide a write + * combine bit + */ + if (mmap_state != pci_mmap_mem) + write_combine = 0; + else if (write_combine == 0) { + if (rp->flags & IORESOURCE_PREFETCH) + write_combine = 1; + } + + /* XXX would be nice to have a way to ask for write-through */ + prot |= _PAGE_NO_CACHE; + if (write_combine) + prot &= ~_PAGE_GUARDED; + else + prot |= _PAGE_GUARDED; + + return __pgprot(prot); +} + +/* + * This one is used by /dev/mem and fbdev who have no clue about the + * PCI device, it tries to find the PCI device first and calls the + * above routine + */ +pgprot_t pci_phys_mem_access_prot(struct file *file, + unsigned long pfn, + unsigned long size, + pgprot_t protection) +{ + struct pci_dev *pdev = NULL; + struct resource *found = NULL; + unsigned long prot = pgprot_val(protection); + unsigned long offset = pfn << PAGE_SHIFT; + int i; + + if (page_is_ram(pfn)) + return __pgprot(prot); + + prot |= _PAGE_NO_CACHE | _PAGE_GUARDED; + + for_each_pci_dev(pdev) { + for (i = 0; i <= PCI_ROM_RESOURCE; i++) { + struct resource *rp = &pdev->resource[i]; + int flags = rp->flags; + + /* Active and same type? */ + if ((flags & IORESOURCE_MEM) == 0) + continue; + /* In the range of this resource? */ + if (offset < (rp->start & PAGE_MASK) || + offset > rp->end) + continue; + found = rp; + break; + } + if (found) + break; + } + if (found) { + if (found->flags & IORESOURCE_PREFETCH) + prot &= ~_PAGE_GUARDED; + pci_dev_put(pdev); + } + + DBG("non-PCI map for %lx, prot: %lx\n", offset, prot); + + return __pgprot(prot); +} + + +/* + * Perform the actual remap of the pages for a PCI device mapping, as + * appropriate for this architecture. The region in the process to map + * is described by vm_start and vm_end members of VMA, the base physical + * address is found in vm_pgoff. + * The pci device structure is provided so that architectures may make mapping + * decisions on a per-device or per-bus basis. + * + * Returns a negative error code on failure, zero on success. + */ +int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, + enum pci_mmap_state mmap_state, int write_combine) +{ + resource_size_t offset = vma->vm_pgoff << PAGE_SHIFT; + struct resource *rp; + int ret; + + rp = __pci_mmap_make_offset(dev, &offset, mmap_state); + if (rp == NULL) + return -EINVAL; + + vma->vm_pgoff = offset >> PAGE_SHIFT; + vma->vm_page_prot = __pci_mmap_set_pgprot(dev, rp, + vma->vm_page_prot, + mmap_state, write_combine); + + ret = remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, + vma->vm_end - vma->vm_start, vma->vm_page_prot); + + return ret; +} + +void pci_resource_to_user(const struct pci_dev *dev, int bar, + const struct resource *rsrc, + resource_size_t *start, resource_size_t *end) +{ + struct pci_controller *hose = pci_bus_to_host(dev->bus); + resource_size_t offset = 0; + + if (hose == NULL) + return; + + if (rsrc->flags & IORESOURCE_IO) + offset = (unsigned long)hose->io_base_virt - _IO_BASE; + + /* We pass a fully fixed up address to userland for MMIO instead of + * a BAR value because X is lame and expects to be able to use that + * to pass to /dev/mem ! + * + * That means that we'll have potentially 64 bits values where some + * userland apps only expect 32 (like X itself since it thinks only + * Sparc has 64 bits MMIO) but if we don't do that, we break it on + * 32 bits CHRPs :-( + * + * Hopefully, the sysfs insterface is immune to that gunk. Once X + * has been fixed (and the fix spread enough), we can re-enable the + * 2 lines below and pass down a BAR value to userland. In that case + * we'll also have to re-enable the matching code in + * __pci_mmap_make_offset(). + * + * BenH. + */ +#if 0 + else if (rsrc->flags & IORESOURCE_MEM) + offset = hose->pci_mem_offset; +#endif + + *start = rsrc->start - offset; + *end = rsrc->end - offset; +} diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index c81ffa2..3dd931e 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -1028,34 +1028,12 @@ pci_create_OF_bus_map(void) } } -static ssize_t pci_show_devspec(struct device *dev, struct device_attribute *attr, char *buf) -{ - struct pci_dev *pdev; - struct device_node *np; - - pdev = to_pci_dev (dev); - np = pci_device_to_OF_node(pdev); - if (np == NULL || np->full_name == NULL) - return 0; - return sprintf(buf, "%s", np->full_name); -} -static DEVICE_ATTR(devspec, S_IRUGO, pci_show_devspec, NULL); - #else /* CONFIG_PPC_OF */ void pcibios_make_OF_bus_map(void) { } #endif /* CONFIG_PPC_OF */ -/* Add sysfs properties */ -void pcibios_add_platform_entries(struct pci_dev *pdev) -{ -#ifdef CONFIG_PPC_OF - device_create_file(&pdev->dev, &dev_attr_devspec); -#endif /* CONFIG_PPC_OF */ -} - - #ifdef CONFIG_PPC_PMAC /* * This set of routines checks for PCI<->PCI bridges that have closed @@ -1390,11 +1368,6 @@ void __init pcibios_fixup_bus(struct pci_bus *bus) } } -char __init *pcibios_setup(char *str) -{ - return str; -} - /* the next one is stolen from the alpha port... */ void __init pcibios_update_irq(struct pci_dev *dev, int irq) @@ -1403,64 +1376,6 @@ pcibios_update_irq(struct pci_dev *dev, int irq) /* XXX FIXME - update OF device tree node interrupt property */ } -#ifdef CONFIG_PPC_MERGE -/* XXX This is a copy of the ppc64 version. This is temporary until we start - * merging the 2 PCI layers - */ -/* - * Reads the interrupt pin to determine if interrupt is use by card. - * If the interrupt is used, then gets the interrupt line from the - * openfirmware and sets it in the pci_dev and pci_config line. - */ -int pci_read_irq_line(struct pci_dev *pci_dev) -{ - struct of_irq oirq; - unsigned int virq; - - DBG("Try to map irq for %s...\n", pci_name(pci_dev)); - - /* Try to get a mapping from the device-tree */ - if (of_irq_map_pci(pci_dev, &oirq)) { - u8 line, pin; - - /* If that fails, lets fallback to what is in the config - * space and map that through the default controller. We - * also set the type to level low since that's what PCI - * interrupts are. If your platform does differently, then - * either provide a proper interrupt tree or don't use this - * function. - */ - if (pci_read_config_byte(pci_dev, PCI_INTERRUPT_PIN, &pin)) - return -1; - if (pin == 0) - return -1; - if (pci_read_config_byte(pci_dev, PCI_INTERRUPT_LINE, &line) || - line == 0xff) { - return -1; - } - DBG(" -> no map ! Using irq line %d from PCI config\n", line); - - 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...) on %s\n", - oirq.size, oirq.specifier[0], oirq.controller->full_name); - - virq = irq_create_of_mapping(oirq.controller, oirq.specifier, - oirq.size); - } - if(virq == NO_IRQ) { - DBG(" -> failed to map !\n"); - return -1; - } - pci_dev->irq = virq; - - return 0; -} -EXPORT_SYMBOL(pci_read_irq_line); -#endif /* CONFIG_PPC_MERGE */ - int pcibios_enable_device(struct pci_dev *dev, int mask) { u16 cmd, old_cmd; @@ -1503,176 +1418,6 @@ pci_bus_to_hose(int bus) return NULL; } -static struct resource *__pci_mmap_make_offset(struct pci_dev *dev, - resource_size_t *offset, - enum pci_mmap_state mmap_state) -{ - struct pci_controller *hose = pci_bus_to_host(dev->bus); - unsigned long io_offset = 0; - int i, res_bit; - - if (hose == 0) - return NULL; /* should never happen */ - - /* If memory, add on the PCI bridge address offset */ - if (mmap_state == pci_mmap_mem) { -#if 0 /* See comment in pci_resource_to_user() for why this is disabled */ - *offset += hose->pci_mem_offset; -#endif - res_bit = IORESOURCE_MEM; - } else { - io_offset = hose->io_base_virt - (void __iomem *)_IO_BASE; - *offset += io_offset; - res_bit = IORESOURCE_IO; - } - - /* - * Check that the offset requested corresponds to one of the - * resources of the device. - */ - for (i = 0; i <= PCI_ROM_RESOURCE; i++) { - struct resource *rp = &dev->resource[i]; - int flags = rp->flags; - - /* treat ROM as memory (should be already) */ - if (i == PCI_ROM_RESOURCE) - flags |= IORESOURCE_MEM; - - /* Active and same type? */ - if ((flags & res_bit) == 0) - continue; - - /* In the range of this resource? */ - if (*offset < (rp->start & PAGE_MASK) || *offset > rp->end) - continue; - - /* found it! construct the final physical address */ - if (mmap_state == pci_mmap_io) - *offset += hose->io_base_phys - io_offset; - return rp; - } - - return NULL; -} - -/* - * Set vm_page_prot of VMA, as appropriate for this architecture, for a pci - * device mapping. - */ -static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp, - pgprot_t protection, - enum pci_mmap_state mmap_state, - int write_combine) -{ - unsigned long prot = pgprot_val(protection); - - /* Write combine is always 0 on non-memory space mappings. On - * memory space, if the user didn't pass 1, we check for a - * "prefetchable" resource. This is a bit hackish, but we use - * this to workaround the inability of /sysfs to provide a write - * combine bit - */ - if (mmap_state != pci_mmap_mem) - write_combine = 0; - else if (write_combine == 0) { - if (rp->flags & IORESOURCE_PREFETCH) - write_combine = 1; - } - - /* XXX would be nice to have a way to ask for write-through */ - prot |= _PAGE_NO_CACHE; - if (write_combine) - prot &= ~_PAGE_GUARDED; - else - prot |= _PAGE_GUARDED; - - return __pgprot(prot); -} - -/* - * This one is used by /dev/mem and fbdev who have no clue about the - * PCI device, it tries to find the PCI device first and calls the - * above routine - */ -pgprot_t pci_phys_mem_access_prot(struct file *file, - unsigned long pfn, - unsigned long size, - pgprot_t protection) -{ - struct pci_dev *pdev = NULL; - struct resource *found = NULL; - unsigned long prot = pgprot_val(protection); - unsigned long offset = pfn << PAGE_SHIFT; - int i; - - if (page_is_ram(pfn)) - return __pgprot(prot); - - prot |= _PAGE_NO_CACHE | _PAGE_GUARDED; - - for_each_pci_dev(pdev) { - for (i = 0; i <= PCI_ROM_RESOURCE; i++) { - struct resource *rp = &pdev->resource[i]; - int flags = rp->flags; - - /* Active and same type? */ - if ((flags & IORESOURCE_MEM) == 0) - continue; - /* In the range of this resource? */ - if (offset < (rp->start & PAGE_MASK) || - offset > rp->end) - continue; - found = rp; - break; - } - if (found) - break; - } - if (found) { - if (found->flags & IORESOURCE_PREFETCH) - prot &= ~_PAGE_GUARDED; - pci_dev_put(pdev); - } - - DBG("non-PCI map for %lx, prot: %lx\n", offset, prot); - - return __pgprot(prot); -} - - -/* - * Perform the actual remap of the pages for a PCI device mapping, as - * appropriate for this architecture. The region in the process to map - * is described by vm_start and vm_end members of VMA, the base physical - * address is found in vm_pgoff. - * The pci device structure is provided so that architectures may make mapping - * decisions on a per-device or per-bus basis. - * - * Returns a negative error code on failure, zero on success. - */ -int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, - enum pci_mmap_state mmap_state, - int write_combine) -{ - resource_size_t offset = vma->vm_pgoff << PAGE_SHIFT; - struct resource *rp; - int ret; - - rp = __pci_mmap_make_offset(dev, &offset, mmap_state); - if (rp == NULL) - return -EINVAL; - - vma->vm_pgoff = offset >> PAGE_SHIFT; - vma->vm_page_prot = __pci_mmap_set_pgprot(dev, rp, - vma->vm_page_prot, - mmap_state, write_combine); - - ret = remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, - vma->vm_end - vma->vm_start, vma->vm_page_prot); - - return ret; -} - /* Provide information on locations of various I/O regions in physical * memory. Do this on a per-card basis so that we choose the right * root bridge. @@ -1715,45 +1460,6 @@ long sys_pciconfig_iobase(long which, unsigned long bus, unsigned long devfn) return result; } -void pci_resource_to_user(const struct pci_dev *dev, int bar, - const struct resource *rsrc, - resource_size_t *start, resource_size_t *end) -{ - struct pci_controller *hose = pci_bus_to_host(dev->bus); - resource_size_t offset = 0; - - if (hose == NULL) - return; - - if (rsrc->flags & IORESOURCE_IO) - offset = (unsigned long)hose->io_base_virt - _IO_BASE; - - /* We pass a fully fixed up address to userland for MMIO instead of - * a BAR value because X is lame and expects to be able to use that - * to pass to /dev/mem ! - * - * That means that we'll have potentially 64 bits values where some - * userland apps only expect 32 (like X itself since it thinks only - * Sparc has 64 bits MMIO) but if we don't do that, we break it on - * 32 bits CHRPs :-( - * - * Hopefully, the sysfs insterface is immune to that gunk. Once X - * has been fixed (and the fix spread enough), we can re-enable the - * 2 lines below and pass down a BAR value to userland. In that case - * we'll also have to re-enable the matching code in - * __pci_mmap_make_offset(). - * - * BenH. - */ -#if 0 - else if (rsrc->flags & IORESOURCE_MEM) - offset = hose->pci_mem_offset; -#endif - - *start = rsrc->start - offset; - *end = rsrc->end - offset; -} - unsigned long pci_address_to_pio(phys_addr_t address) { struct pci_controller* hose = hose_head; diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index 57bdcd8..384d275 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -601,11 +601,6 @@ static int __init pcibios_init(void) subsys_initcall(pcibios_init); -char __init *pcibios_setup(char *str) -{ - return str; -} - int pcibios_enable_device(struct pci_dev *dev, int mask) { u16 cmd, oldcmd; @@ -647,211 +642,6 @@ int pci_proc_domain(struct pci_bus *bus) } } -/* - * Platform support for /proc/bus/pci/X/Y mmap()s, - * modelled on the sparc64 implementation by Dave Miller. - * -- paulus. - */ - -/* - * Adjust vm_pgoff of VMA such that it is the physical page offset - * corresponding to the 32-bit pci bus offset for DEV requested by the user. - * - * Basically, the user finds the base address for his device which he wishes - * to mmap. They read the 32-bit value from the config space base register, - * add whatever PAGE_SIZE multiple offset they wish, and feed this into the - * offset parameter of mmap on /proc/bus/pci/XXX for that device. - * - * Returns negative error code on failure, zero on success. - */ -static struct resource *__pci_mmap_make_offset(struct pci_dev *dev, - resource_size_t *offset, - enum pci_mmap_state mmap_state) -{ - struct pci_controller *hose = pci_bus_to_host(dev->bus); - unsigned long io_offset = 0; - int i, res_bit; - - if (hose == 0) - return NULL; /* should never happen */ - - /* If memory, add on the PCI bridge address offset */ - if (mmap_state == pci_mmap_mem) { -#if 0 /* See comment in pci_resource_to_user() for why this is disabled */ - *offset += hose->pci_mem_offset; -#endif - res_bit = IORESOURCE_MEM; - } else { - io_offset = (unsigned long)hose->io_base_virt - _IO_BASE; - *offset += io_offset; - res_bit = IORESOURCE_IO; - } - - /* - * Check that the offset requested corresponds to one of the - * resources of the device. - */ - for (i = 0; i <= PCI_ROM_RESOURCE; i++) { - struct resource *rp = &dev->resource[i]; - int flags = rp->flags; - - /* treat ROM as memory (should be already) */ - if (i == PCI_ROM_RESOURCE) - flags |= IORESOURCE_MEM; - - /* Active and same type? */ - if ((flags & res_bit) == 0) - continue; - - /* In the range of this resource? */ - if (*offset < (rp->start & PAGE_MASK) || *offset > rp->end) - continue; - - /* found it! construct the final physical address */ - if (mmap_state == pci_mmap_io) - *offset += hose->io_base_phys - io_offset; - return rp; - } - - return NULL; -} - -/* - * Set vm_page_prot of VMA, as appropriate for this architecture, for a pci - * device mapping. - */ -static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp, - pgprot_t protection, - enum pci_mmap_state mmap_state, - int write_combine) -{ - unsigned long prot = pgprot_val(protection); - - /* Write combine is always 0 on non-memory space mappings. On - * memory space, if the user didn't pass 1, we check for a - * "prefetchable" resource. This is a bit hackish, but we use - * this to workaround the inability of /sysfs to provide a write - * combine bit - */ - if (mmap_state != pci_mmap_mem) - write_combine = 0; - else if (write_combine == 0) { - if (rp->flags & IORESOURCE_PREFETCH) - write_combine = 1; - } - - /* XXX would be nice to have a way to ask for write-through */ - prot |= _PAGE_NO_CACHE; - if (write_combine) - prot &= ~_PAGE_GUARDED; - else - prot |= _PAGE_GUARDED; - - return __pgprot(prot); -} - -/* - * This one is used by /dev/mem and fbdev who have no clue about the - * PCI device, it tries to find the PCI device first and calls the - * above routine - */ -pgprot_t pci_phys_mem_access_prot(struct file *file, - unsigned long pfn, - unsigned long size, - pgprot_t protection) -{ - struct pci_dev *pdev = NULL; - struct resource *found = NULL; - unsigned long prot = pgprot_val(protection); - unsigned long offset = pfn << PAGE_SHIFT; - int i; - - if (page_is_ram(pfn)) - return __pgprot(prot); - - prot |= _PAGE_NO_CACHE | _PAGE_GUARDED; - - for_each_pci_dev(pdev) { - for (i = 0; i <= PCI_ROM_RESOURCE; i++) { - struct resource *rp = &pdev->resource[i]; - int flags = rp->flags; - - /* Active and same type? */ - if ((flags & IORESOURCE_MEM) == 0) - continue; - /* In the range of this resource? */ - if (offset < (rp->start & PAGE_MASK) || - offset > rp->end) - continue; - found = rp; - break; - } - if (found) - break; - } - if (found) { - if (found->flags & IORESOURCE_PREFETCH) - prot &= ~_PAGE_GUARDED; - pci_dev_put(pdev); - } - - DBG("non-PCI map for %lx, prot: %lx\n", offset, prot); - - return __pgprot(prot); -} - - -/* - * Perform the actual remap of the pages for a PCI device mapping, as - * appropriate for this architecture. The region in the process to map - * is described by vm_start and vm_end members of VMA, the base physical - * address is found in vm_pgoff. - * The pci device structure is provided so that architectures may make mapping - * decisions on a per-device or per-bus basis. - * - * Returns a negative error code on failure, zero on success. - */ -int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, - enum pci_mmap_state mmap_state, int write_combine) -{ - resource_size_t offset = vma->vm_pgoff << PAGE_SHIFT; - struct resource *rp; - int ret; - - rp = __pci_mmap_make_offset(dev, &offset, mmap_state); - if (rp == NULL) - return -EINVAL; - - vma->vm_pgoff = offset >> PAGE_SHIFT; - vma->vm_page_prot = __pci_mmap_set_pgprot(dev, rp, - vma->vm_page_prot, - mmap_state, write_combine); - - ret = remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, - vma->vm_end - vma->vm_start, vma->vm_page_prot); - - return ret; -} - -static ssize_t pci_show_devspec(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct pci_dev *pdev; - struct device_node *np; - - pdev = to_pci_dev (dev); - np = pci_device_to_OF_node(pdev); - if (np == NULL || np->full_name == NULL) - return 0; - return sprintf(buf, "%s", np->full_name); -} -static DEVICE_ATTR(devspec, S_IRUGO, pci_show_devspec, NULL); - -void pcibios_add_platform_entries(struct pci_dev *pdev) -{ - device_create_file(&pdev->dev, &dev_attr_devspec); -} - void __devinit pci_process_bridge_OF_ranges(struct pci_controller *hose, struct device_node *dev, int prim) { @@ -1167,105 +957,6 @@ void __devinit pcibios_fixup_bus(struct pci_bus *bus) } EXPORT_SYMBOL(pcibios_fixup_bus); -/* - * Reads the interrupt pin to determine if interrupt is use by card. - * If the interrupt is used, then gets the interrupt line from the - * openfirmware and sets it in the pci_dev and pci_config line. - */ -int pci_read_irq_line(struct pci_dev *pci_dev) -{ - struct of_irq oirq; - unsigned int virq; - - DBG("Try to map irq for %s...\n", pci_name(pci_dev)); - -#ifdef DEBUG - memset(&oirq, 0xff, sizeof(oirq)); -#endif - /* Try to get a mapping from the device-tree */ - if (of_irq_map_pci(pci_dev, &oirq)) { - u8 line, pin; - - /* If that fails, lets fallback to what is in the config - * space and map that through the default controller. We - * also set the type to level low since that's what PCI - * interrupts are. If your platform does differently, then - * either provide a proper interrupt tree or don't use this - * function. - */ - if (pci_read_config_byte(pci_dev, PCI_INTERRUPT_PIN, &pin)) - return -1; - if (pin == 0) - return -1; - if (pci_read_config_byte(pci_dev, PCI_INTERRUPT_LINE, &line) || - line == 0xff) { - return -1; - } - DBG(" -> no map ! Using irq line %d from PCI config\n", line); - - 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], - oirq.controller->full_name); - - virq = irq_create_of_mapping(oirq.controller, oirq.specifier, - oirq.size); - } - if(virq == NO_IRQ) { - DBG(" -> failed to map !\n"); - return -1; - } - - DBG(" -> mapped to linux irq %d\n", virq); - - pci_dev->irq = virq; - - return 0; -} -EXPORT_SYMBOL(pci_read_irq_line); - -void pci_resource_to_user(const struct pci_dev *dev, int bar, - const struct resource *rsrc, - resource_size_t *start, resource_size_t *end) -{ - struct pci_controller *hose = pci_bus_to_host(dev->bus); - resource_size_t offset = 0; - - if (hose == NULL) - return; - - if (rsrc->flags & IORESOURCE_IO) - offset = (unsigned long)hose->io_base_virt - _IO_BASE; - - /* We pass a fully fixed up address to userland for MMIO instead of - * a BAR value because X is lame and expects to be able to use that - * to pass to /dev/mem ! - * - * That means that we'll have potentially 64 bits values where some - * userland apps only expect 32 (like X itself since it thinks only - * Sparc has 64 bits MMIO) but if we don't do that, we break it on - * 32 bits CHRPs :-( - * - * Hopefully, the sysfs insterface is immune to that gunk. Once X - * has been fixed (and the fix spread enough), we can re-enable the - * 2 lines below and pass down a BAR value to userland. In that case - * we'll also have to re-enable the matching code in - * __pci_mmap_make_offset(). - * - * BenH. - */ -#if 0 - else if (rsrc->flags & IORESOURCE_MEM) - offset = hose->pci_mem_offset; -#endif - - *start = rsrc->start - offset; - *end = rsrc->end - offset; -} - struct pci_controller* pci_find_hose_for_OF_device(struct device_node* node) { if (!have_of) -- cgit v1.1 From a4c9e328279d55622d56507629d6b8942e8cc9c9 Mon Sep 17 00:00:00 2001 From: Kumar Gala Date: Wed, 27 Jun 2007 13:09:43 -0500 Subject: [POWERPC] Use ppc64 style list management for pci_controller on ppc32 Use the ppc64 style list management and allocation functions for pci_controllers. This makes the pci_controller structs just a bit more common between ppc32 & ppc64. Signed-off-by: Kumar Gala --- arch/powerpc/kernel/pci-common.c | 78 ++++++++++++++++++++++++++++++++++++++++ arch/powerpc/kernel/pci_32.c | 61 ++++++------------------------- arch/powerpc/kernel/pci_64.c | 66 ---------------------------------- 3 files changed, 88 insertions(+), 117 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index b518b88..295cbb1 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -36,6 +36,62 @@ #define DBG(fmt...) #endif +static DEFINE_SPINLOCK(hose_spinlock); + +/* XXX kill that some day ... */ +int global_phb_number; /* Global phb counter */ + +extern struct list_head hose_list; + +/* + * pci_controller(phb) initialized common variables. + */ +static void __devinit pci_setup_pci_controller(struct pci_controller *hose) +{ + memset(hose, 0, sizeof(struct pci_controller)); + + spin_lock(&hose_spinlock); + hose->global_number = global_phb_number++; + list_add_tail(&hose->list_node, &hose_list); + spin_unlock(&hose_spinlock); +} + +struct pci_controller * pcibios_alloc_controller(struct device_node *dev) +{ + struct pci_controller *phb; + + if (mem_init_done) + phb = kmalloc(sizeof(struct pci_controller), GFP_KERNEL); + else + phb = alloc_bootmem(sizeof (struct pci_controller)); + if (phb == NULL) + return NULL; + pci_setup_pci_controller(phb); + phb->arch_data = dev; + phb->is_dynamic = mem_init_done; +#ifdef CONFIG_PPC64 + if (dev) { + int nid = of_node_to_nid(dev); + + if (nid < 0 || !node_online(nid)) + nid = -1; + + PHB_SET_NODE(phb, nid); + } +#endif + return phb; +} + +void pcibios_free_controller(struct pci_controller *phb) +{ + spin_lock(&hose_spinlock); + list_del(&phb->list_node); + spin_unlock(&hose_spinlock); + + if (phb->is_dynamic) + kfree(phb); +} + /* * Return the domain number for this bus. */ @@ -53,6 +109,28 @@ int pci_domain_nr(struct pci_bus *bus) EXPORT_SYMBOL(pci_domain_nr); #ifdef CONFIG_PPC_OF + +/* This routine is meant to be used early during boot, when the + * PCI bus numbers have not yet been assigned, and you need to + * issue PCI config cycles to an OF device. + * It could also be used to "fix" RTAS config cycles if you want + * to set pci_assign_all_buses to 1 and still use RTAS for PCI + * config cycles. + */ +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) + if (hose->arch_data == node) + return hose; + node = node->parent; + } + return NULL; +} + static ssize_t pci_show_devspec(struct device *dev, struct device_attribute *attr, char *buf) { diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index 3dd931e..10d8a35 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -55,8 +55,7 @@ static u8* pci_to_OF_bus_map; */ int pci_assign_all_buses; -struct pci_controller* hose_head; -struct pci_controller** hose_tail = &hose_head; +LIST_HEAD(hose_list); static int pci_bus_count; @@ -607,25 +606,6 @@ pcibios_enable_resources(struct pci_dev *dev, int mask) return 0; } -static int next_controller_index; - -struct pci_controller * __init -pcibios_alloc_controller(struct device_node *dev) -{ - struct pci_controller *hose; - - hose = (struct pci_controller *)alloc_bootmem(sizeof(*hose)); - memset(hose, 0, sizeof(struct pci_controller)); - - *hose_tail = hose; - hose_tail = &hose->next; - - hose->global_number = next_controller_index++; - hose->arch_data = dev; - - return hose; -} - #ifdef CONFIG_PPC_OF /* * Functions below are used on OpenFirmware machines. @@ -671,7 +651,7 @@ void pcibios_make_OF_bus_map(void) { int i; - struct pci_controller* hose; + struct pci_controller *hose, *tmp; struct property *map_prop; struct device_node *dn; @@ -688,7 +668,7 @@ pcibios_make_OF_bus_map(void) pci_to_OF_bus_map[i] = 0xff; /* For each hose, we begin searching bridges */ - for(hose=hose_head; hose; hose=hose->next) { + list_for_each_entry_safe(hose, tmp, &hose_list, list_node) { struct device_node* node; node = (struct device_node *)hose->arch_data; if (!node) @@ -819,27 +799,6 @@ pci_device_to_OF_node(struct pci_dev *dev) } EXPORT_SYMBOL(pci_device_to_OF_node); -/* This routine is meant to be used early during boot, when the - * PCI bus numbers have not yet been assigned, and you need to - * issue PCI config cycles to an OF device. - * It could also be used to "fix" RTAS config cycles if you want - * to set pci_assign_all_buses to 1 and still use RTAS for PCI - * config cycles. - */ -struct pci_controller* pci_find_hose_for_OF_device(struct device_node* node) -{ - if (!have_of) - return NULL; - while(node) { - struct pci_controller* hose; - for (hose=hose_head;hose;hose=hose->next) - if (hose->arch_data == node) - return hose; - node=node->parent; - } - return NULL; -} - static int find_OF_pci_device_filter(struct device_node* node, void* data) { @@ -1248,14 +1207,14 @@ pcibios_fixup_p2p_bridges(void) static int __init pcibios_init(void) { - struct pci_controller *hose; + struct pci_controller *hose, *tmp; struct pci_bus *bus; - int next_busno; + int next_busno = 0; printk(KERN_INFO "PCI: Probing PCI hardware\n"); /* Scan all of the recorded PCI controllers. */ - for (next_busno = 0, hose = hose_head; hose; hose = hose->next) { + list_for_each_entry_safe(hose, tmp, &hose_list, list_node) { if (pci_assign_all_buses) hose->first_busno = next_busno; hose->last_busno = 0xff; @@ -1410,9 +1369,9 @@ int pcibios_enable_device(struct pci_dev *dev, int mask) static struct pci_controller* pci_bus_to_hose(int bus) { - struct pci_controller* hose = hose_head; + struct pci_controller *hose, *tmp; - for (; hose; hose = hose->next) + list_for_each_entry_safe(hose, tmp, &hose_list, list_node) if (bus >= hose->first_busno && bus <= hose->last_busno) return hose; return NULL; @@ -1462,9 +1421,9 @@ long sys_pciconfig_iobase(long which, unsigned long bus, unsigned long devfn) unsigned long pci_address_to_pio(phys_addr_t address) { - struct pci_controller* hose = hose_head; + struct pci_controller *hose, *tmp; - for (; hose; hose = hose->next) { + list_for_each_entry_safe(hose, tmp, &hose_list, list_node) { unsigned int size = hose->io_resource.end - hose->io_resource.start + 1; if (address >= hose->io_base_phys && diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index 384d275..3b0f49e 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -59,9 +59,6 @@ LIST_HEAD(hose_list); static struct dma_mapping_ops *pci_dma_ops; -/* XXX kill that some day ... */ -int global_phb_number; /* Global phb counter */ - void set_pci_dma_ops(struct dma_mapping_ops *dma_ops) { pci_dma_ops = dma_ops; @@ -172,55 +169,6 @@ void pcibios_align_resource(void *data, struct resource *res, res->start = start; } -static DEFINE_SPINLOCK(hose_spinlock); - -/* - * pci_controller(phb) initialized common variables. - */ -static void __devinit pci_setup_pci_controller(struct pci_controller *hose) -{ - memset(hose, 0, sizeof(struct pci_controller)); - - spin_lock(&hose_spinlock); - hose->global_number = global_phb_number++; - list_add_tail(&hose->list_node, &hose_list); - spin_unlock(&hose_spinlock); -} - -struct pci_controller * pcibios_alloc_controller(struct device_node *dev) -{ - struct pci_controller *phb; - - if (mem_init_done) - phb = kmalloc(sizeof(struct pci_controller), GFP_KERNEL); - else - phb = alloc_bootmem(sizeof (struct pci_controller)); - if (phb == NULL) - return NULL; - pci_setup_pci_controller(phb); - phb->arch_data = dev; - phb->is_dynamic = mem_init_done; - if (dev) { - int nid = of_node_to_nid(dev); - - if (nid < 0 || !node_online(nid)) - nid = -1; - - PHB_SET_NODE(phb, nid); - } - return phb; -} - -void pcibios_free_controller(struct pci_controller *phb) -{ - spin_lock(&hose_spinlock); - list_del(&phb->list_node); - spin_unlock(&hose_spinlock); - - if (phb->is_dynamic) - kfree(phb); -} - void __devinit pcibios_claim_one_bus(struct pci_bus *b) { struct pci_dev *dev; @@ -957,20 +905,6 @@ void __devinit pcibios_fixup_bus(struct pci_bus *bus) } EXPORT_SYMBOL(pcibios_fixup_bus); -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) - if (hose->arch_data == node) - return hose; - node = node->parent; - } - return NULL; -} - unsigned long pci_address_to_pio(phys_addr_t address) { struct pci_controller *hose, *tmp; -- cgit v1.1 From cf1d8a8a7b6616fbfd14f2d4646024f4ff1c3c8b Mon Sep 17 00:00:00 2001 From: Kumar Gala Date: Thu, 28 Jun 2007 22:56:24 -0500 Subject: [POWERPC] Add copyright header to pci-common.c based on pci_{32,64}.c Signed-off-by: Kumar Gala --- arch/powerpc/kernel/pci-common.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 295cbb1..faf5ef3 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -1,5 +1,14 @@ /* * Contains common pci routines for ALL ppc platform + * (based on pci_32.c and pci_64.c) + * + * Port for PPC64 David Engebretsen, IBM Corp. + * Contains common pci routines for ppc64 platform, pSeries and iSeries brands. + * + * Copyright (C) 2003 Anton Blanchard , IBM + * Rework, based on alpha PCI code. + * + * Common pmac/prep/chrp pci routines. -- Cort * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License -- cgit v1.1 From 327e22df9ff2e70a88ada88f9833ef682482bddd Mon Sep 17 00:00:00 2001 From: Jon Loeliger Date: Mon, 4 Jun 2007 14:28:44 -0500 Subject: [POWERPC] Replace use of GET_64BIT(prop, i) with of_read_number(). Remove uses of hack GET_64BIT() property macro and use the more general of_read_number() function from prom.h as suggested by Milton. Signed-off-by: Jon Loeliger Signed-off-by: Kumar Gala --- arch/powerpc/kernel/pci_64.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index 3b0f49e..93b2920 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -231,7 +231,6 @@ static unsigned int pci_parse_of_flags(u32 addr0) return flags; } -#define GET_64BIT(prop, i) ((((u64) (prop)[(i)]) << 32) | (prop)[(i)+1]) static void pci_parse_of_addrs(struct device_node *node, struct pci_dev *dev) { @@ -250,8 +249,8 @@ static void pci_parse_of_addrs(struct device_node *node, struct pci_dev *dev) flags = pci_parse_of_flags(addrs[0]); if (!flags) continue; - base = GET_64BIT(addrs, 1); - size = GET_64BIT(addrs, 3); + base = of_read_number(&addrs[1], 2); + size = of_read_number(&addrs[3], 2); if (!size) continue; i = addrs[0] & 0xff; @@ -417,7 +416,7 @@ void __devinit of_scan_pci_bridge(struct device_node *node, i = 1; for (; len >= 32; len -= 32, ranges += 8) { flags = pci_parse_of_flags(ranges[0]); - size = GET_64BIT(ranges, 6); + size = of_read_number(&ranges[6], 2); if (flags == 0 || size == 0) continue; if (flags & IORESOURCE_IO) { @@ -436,7 +435,7 @@ void __devinit of_scan_pci_bridge(struct device_node *node, res = bus->resource[i]; ++i; } - res->start = GET_64BIT(ranges, 1); + res->start = of_read_number(&ranges[1], 2); res->end = res->start + size - 1; res->flags = flags; fixup_resource(res, dev); -- cgit v1.1 From b3710f5a1802876717600afad10156e54d5fdb18 Mon Sep 17 00:00:00 2001 From: Kumar Gala Date: Tue, 3 Jul 2007 02:51:24 -0500 Subject: [POWERPC] Kill pcibios_enable_resources() pcibios_enable_resources isn't used anywhere and not exported. Signed-off-by: Kumar Gala --- arch/powerpc/kernel/pci_32.c | 34 ---------------------------------- 1 file changed, 34 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index 10d8a35..0adf077 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -572,40 +572,6 @@ pcibios_assign_resources(void) } } - -int -pcibios_enable_resources(struct pci_dev *dev, int mask) -{ - u16 cmd, old_cmd; - int idx; - struct resource *r; - - pci_read_config_word(dev, PCI_COMMAND, &cmd); - old_cmd = cmd; - for (idx=0; idx<6; idx++) { - /* Only set up the requested stuff */ - if (!(mask & (1<resource[idx]; - if (r->flags & IORESOURCE_UNSET) { - printk(KERN_ERR "PCI: Device %s not available because of resource collisions\n", pci_name(dev)); - return -EINVAL; - } - if (r->flags & IORESOURCE_IO) - cmd |= PCI_COMMAND_IO; - if (r->flags & IORESOURCE_MEM) - cmd |= PCI_COMMAND_MEMORY; - } - if (dev->resource[PCI_ROM_RESOURCE].start) - cmd |= PCI_COMMAND_MEMORY; - if (cmd != old_cmd) { - printk("PCI: Enabling device %s (%04x -> %04x)\n", pci_name(dev), old_cmd, cmd); - pci_write_config_word(dev, PCI_COMMAND, cmd); - } - return 0; -} - #ifdef CONFIG_PPC_OF /* * Functions below are used on OpenFirmware machines. -- cgit v1.1 From 74a0ba61b1ca96d6bb98889a7d95cd057165da49 Mon Sep 17 00:00:00 2001 From: Kumar Gala Date: Mon, 9 Jul 2007 23:49:09 -0500 Subject: [POWERPC] Move inline asm eieio to using eieio inline function Use the eieio function so we can redefine what eieio does rather than direct inline asm. This is part code clean up and partially because not all PPCs have eieio (book-e has mbar that maps to eieio). Signed-off-by: Kumar Gala --- arch/powerpc/kernel/io.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/io.c b/arch/powerpc/kernel/io.c index 34ae114..e31aca92 100644 --- a/arch/powerpc/kernel/io.c +++ b/arch/powerpc/kernel/io.c @@ -35,7 +35,7 @@ void _insb(const volatile u8 __iomem *port, void *buf, long count) asm volatile("sync"); do { tmp = *port; - asm volatile("eieio"); + eieio(); *tbuf++ = tmp; } while (--count != 0); asm volatile("twi 0,%0,0; isync" : : "r" (tmp)); @@ -66,7 +66,7 @@ void _insw_ns(const volatile u16 __iomem *port, void *buf, long count) asm volatile("sync"); do { tmp = *port; - asm volatile("eieio"); + eieio(); *tbuf++ = tmp; } while (--count != 0); asm volatile("twi 0,%0,0; isync" : : "r" (tmp)); @@ -97,7 +97,7 @@ void _insl_ns(const volatile u32 __iomem *port, void *buf, long count) asm volatile("sync"); do { tmp = *port; - asm volatile("eieio"); + eieio(); *tbuf++ = tmp; } while (--count != 0); asm volatile("twi 0,%0,0; isync" : : "r" (tmp)); @@ -155,21 +155,21 @@ void _memcpy_fromio(void *dest, const volatile void __iomem *src, __asm__ __volatile__ ("sync" : : : "memory"); while(n && (!IO_CHECK_ALIGN(vsrc, 4) || !IO_CHECK_ALIGN(dest, 4))) { *((u8 *)dest) = *((volatile u8 *)vsrc); - __asm__ __volatile__ ("eieio" : : : "memory"); + eieio(); vsrc++; dest++; n--; } while(n > 4) { *((u32 *)dest) = *((volatile u32 *)vsrc); - __asm__ __volatile__ ("eieio" : : : "memory"); + eieio(); vsrc += 4; dest += 4; n -= 4; } while(n) { *((u8 *)dest) = *((volatile u8 *)vsrc); - __asm__ __volatile__ ("eieio" : : : "memory"); + eieio(); vsrc++; dest++; n--; -- cgit v1.1 From ca747ddf29773d552fc0e0dcde0d92b807cd6b85 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 29 May 2007 21:49:01 +1000 Subject: [POWERPC] Remove unused do_signal export do_signal is never used in modular code (obviously), and no other architecture exports it either. Signed-off-by: Christoph Hellwig Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/ppc_ksyms.c | 1 - 1 file changed, 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index e973c32..a20f195 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -67,7 +67,6 @@ EXPORT_SYMBOL(ISA_DMA_THRESHOLD); EXPORT_SYMBOL(DMA_MODE_READ); EXPORT_SYMBOL(DMA_MODE_WRITE); -EXPORT_SYMBOL(do_signal); EXPORT_SYMBOL(transfer_to_handler); EXPORT_SYMBOL(do_IRQ); EXPORT_SYMBOL(machine_check_exception); -- cgit v1.1 From 333e615483afc5203d1cae1490e50982d6eefbea Mon Sep 17 00:00:00 2001 From: Roland Dreier Date: Sat, 16 Jun 2007 05:36:32 +1000 Subject: [POWERPC] Add cputable entry for PowerPC 440SPe Rev. B When adding the cputable entry for 440SPe Rev. B, we also need to adjust the existing entries for 440SP Rev. A and 440SPe Rev. B so that they look more bits of the PVR. The 440SPe Rev. B has PVR 53421891, which would match the current 440SP Rev. A pattern of 53xxx891. To distinguish between 440SP and 440SPe, we need to use the first three digits of the PVR, which are respectively 532 and 534. Signed-off-by: Roland Dreier Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/cputable.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index b2b5d66..157e6e3 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -1178,8 +1178,8 @@ static struct cpu_spec cpu_specs[] = { .platform = "ppc440", }, { /* 440SP Rev. A */ - .pvr_mask = 0xff000fff, - .pvr_value = 0x53000891, + .pvr_mask = 0xfff00fff, + .pvr_value = 0x53200891, .cpu_name = "440SP Rev. A", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE, @@ -1188,9 +1188,19 @@ static struct cpu_spec cpu_specs[] = { .platform = "ppc440", }, { /* 440SPe Rev. A */ - .pvr_mask = 0xff000fff, - .pvr_value = 0x53000890, - .cpu_name = "440SPe Rev. A", + .pvr_mask = 0xfff00fff, + .pvr_value = 0x53400890, + .cpu_name = "440SPe Rev. A", + .cpu_features = CPU_FTRS_44X, + .cpu_user_features = COMMON_USER_BOOKE, + .icache_bsize = 32, + .dcache_bsize = 32, + .platform = "ppc440", + }, + { /* 440SPe Rev. B */ + .pvr_mask = 0xfff00fff, + .pvr_value = 0x53400891, + .cpu_name = "440SPe Rev. B", .cpu_features = CPU_FTRS_44X, .cpu_user_features = COMMON_USER_BOOKE, .icache_bsize = 32, -- cgit v1.1 From 972d17c9dbad378da61baa17f4c3ea6e154b186a Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Tue, 19 Jun 2007 16:07:56 +1000 Subject: [POWERPC] Check for the root node in of_detach_node() It's not sensible to call of_detach_node() on the root node, but we should check for it just to be safe. Signed-off-by: Michael Ellerman Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/prom.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 6f32bebd..cc9632c 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -1432,6 +1432,8 @@ void of_detach_node(const struct device_node *np) write_lock(&devtree_lock); parent = np->parent; + if (!parent) + goto out_unlock; if (allnodes == np) allnodes = np->allnext; @@ -1455,6 +1457,7 @@ void of_detach_node(const struct device_node *np) prevsib->sibling = np->sibling; } +out_unlock: write_unlock(&devtree_lock); } -- cgit v1.1 From d3b814bb1e8b0c63449a3430196c20cbe24a3e67 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Tue, 19 Jun 2007 16:07:58 +1000 Subject: [POWERPC] Generalise device_node flag interface The struct device_node currently has a _flags variable, although it's only used for one flag - OF_DYNAMIC. Generalise the flag accessors so we can use them with other flags in future. Signed-off-by: Michael Ellerman Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/prom.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index cc9632c..bcd1c5e 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -1375,7 +1375,7 @@ static void of_node_release(struct kref *kref) struct device_node *node = kref_to_device_node(kref); struct property *prop = node->properties; - if (!OF_IS_DYNAMIC(node)) + if (!of_node_check_flag(node, OF_DYNAMIC)) return; while (prop) { struct property *next = prop->next; -- cgit v1.1 From 6a281856c02d2291df2f7d9df5bfdee2e7bdd747 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Tue, 19 Jun 2007 16:08:00 +1000 Subject: [POWERPC] Add a warning to help trackdown device_node refcounting bugs When the refcount for a device node goes to 0, we call the destructor - of_node_release(). This should only happen if we've already detached the node from the device tree. So add a flag OF_DETACHED which tracks detached-ness, and if we find ourselves in of_node_release() without it set, issue a warning and don't free the device_node. To avoid warning continuously reinitialise the kref to a sane value. Signed-off-by: Michael Ellerman Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/prom.c | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index bcd1c5e..6d5e601 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -1375,8 +1375,17 @@ static void of_node_release(struct kref *kref) struct device_node *node = kref_to_device_node(kref); struct property *prop = node->properties; + /* We should never be releasing nodes that haven't been detached. */ + if (!of_node_check_flag(node, OF_DETACHED)) { + printk("WARNING: Bad of_node_put() on %s\n", node->full_name); + dump_stack(); + kref_init(&node->kref); + return; + } + if (!of_node_check_flag(node, OF_DYNAMIC)) return; + while (prop) { struct property *next = prop->next; kfree(prop->name); @@ -1457,6 +1466,8 @@ void of_detach_node(const struct device_node *np) prevsib->sibling = np->sibling; } + of_node_set_flag(np, OF_DETACHED); + out_unlock: write_unlock(&devtree_lock); } -- cgit v1.1 From db0dbae9d9680bce69fe1ce775709e60c8ee9c29 Mon Sep 17 00:00:00 2001 From: Wade Farnsworth Date: Wed, 20 Jun 2007 10:15:10 +1000 Subject: [POWERPC] Add a check for keyboard/mouse device nodes in check_legacy_ioport() The device tree for the MPC8641 HPCN does not implement the device type property for I8042 nodes. In addition to checking the I8042 node's device type, also match the keyboard and/or mouse nodes' compatible property. Signed-off-by: Wade Farnsworth Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/setup-common.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index ed07a19..38c4b73 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -486,6 +486,14 @@ int check_legacy_ioport(unsigned long base_port) switch(base_port) { case I8042_DATA_REG: + if (!(np = of_find_compatible_node(NULL, NULL, "pnpPNP,303"))) + np = of_find_compatible_node(NULL, NULL, "pnpPNP,f03"); + if (np) { + parent = of_get_parent(np); + of_node_put(np); + np = parent; + break; + } np = of_find_node_by_type(NULL, "8042"); break; case FDC_BASE: /* FDC1 */ -- cgit v1.1 From 94a3807c2a547283bb2fb1728609ad51c09d5f79 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 20 Jun 2007 10:54:19 +1000 Subject: [POWERPC] Make the debugfs "powerpc" dir globally accessible The prom.c debugging code creates a "powerpc" directory in debugfs, which is nice, but doesn't allow any other debugging code to stick things under "powerpc" in debugfs. So make it global. While we're there we should make the prom.c debugging code depend on CONFIG_DEBUG_FS, because it doesn't work otherwise. Signed-off-by: Michael Ellerman Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/prom.c | 9 +++------ arch/powerpc/kernel/setup-common.c | 13 +++++++++++++ 2 files changed, 16 insertions(+), 6 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 6d5e601..0782afc 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -52,6 +52,7 @@ #include #include #include +#include #ifdef DEBUG #define DBG(fmt...) printk(KERN_ERR fmt) @@ -1730,22 +1731,18 @@ struct device_node *of_get_cpu_node(int cpu, unsigned int *thread) } EXPORT_SYMBOL(of_get_cpu_node); -#ifdef DEBUG +#if defined(CONFIG_DEBUG_FS) && defined(DEBUG) static struct debugfs_blob_wrapper flat_dt_blob; static int __init export_flat_device_tree(void) { struct dentry *d; - d = debugfs_create_dir("powerpc", NULL); - if (!d) - return 1; - flat_dt_blob.data = initial_boot_params; flat_dt_blob.size = initial_boot_params->totalsize; d = debugfs_create_blob("flat-device-tree", S_IFREG | S_IRUSR, - d, &flat_dt_blob); + powerpc_debugfs_root, &flat_dt_blob); if (!d) return 1; diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 38c4b73..4924c48 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -32,6 +32,7 @@ #include #include #include +#include #include #include #include @@ -579,3 +580,15 @@ static int __init check_cache_coherency(void) late_initcall(check_cache_coherency); #endif /* CONFIG_CHECK_CACHE_COHERENCY */ + +#ifdef CONFIG_DEBUG_FS +struct dentry *powerpc_debugfs_root; + +static int powerpc_debugfs_init(void) +{ + powerpc_debugfs_root = debugfs_create_dir("powerpc", NULL); + + return powerpc_debugfs_root == NULL; +} +arch_initcall(powerpc_debugfs_init); +#endif -- cgit v1.1 From fc9069fe56d9594b7a6da0b9f9ca0eafd756260f Mon Sep 17 00:00:00 2001 From: Tony Breeds Date: Wed, 4 Jul 2007 14:04:31 +1000 Subject: [POWERPC] Modify sched_clock() to make CONFIG_PRINTK_TIME more sane When booting a current kernel with CONFIG_PRINTK_TIME enabled you'll see messages like: [ 0.000000] time_init: decrementer frequency = 188.044000 MHz [ 0.000000] time_init: processor frequency = 1504.352000 MHz [3712914.436297] Console: colour dummy device 80x25 This cause by the initialisation of tb_to_ns_scale in time_init(), suddenly the multiplication in sched_clock() now does something :). This patch modifies sched_clock() to report the offset since the machine booted so the same printk's now look like: [ 0.000000] time_init: decrementer frequency = 188.044000 MHz [ 0.000000] time_init: processor frequency = 1504.352000 MHz [ 0.000135] Console: colour dummy device 80x25 Effectivly including the uptime in printk()s. This patch makes tb_to_ns_scale and tb_to_ns_shift static and read_mostly for good measure. Signed-off-by: Tony Breeds Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/time.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 66d2db7..e5df167 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -112,8 +112,9 @@ u64 ticklen_to_xs; /* 0.64 fraction */ DEFINE_SPINLOCK(rtc_lock); EXPORT_SYMBOL_GPL(rtc_lock); -u64 tb_to_ns_scale; -unsigned tb_to_ns_shift; +static u64 tb_to_ns_scale __read_mostly; +static unsigned tb_to_ns_shift __read_mostly; +static unsigned long boot_tb __read_mostly; struct gettimeofday_struct do_gtod; @@ -755,7 +756,7 @@ unsigned long long sched_clock(void) { if (__USE_RTC()) return get_rtc(); - return mulhdu(get_tb(), tb_to_ns_scale) << tb_to_ns_shift; + return mulhdu(get_tb() - boot_tb, tb_to_ns_scale) << tb_to_ns_shift; } int do_settimeofday(struct timespec *tv) @@ -974,6 +975,8 @@ void __init time_init(void) } tb_to_ns_scale = scale; tb_to_ns_shift = shift; + /* Save the current timebase to pretty up CONFIG_PRINTK_TIME */ + boot_tb = get_tb(); tm = get_boot_time(); -- cgit v1.1 From bd67fcf9ba8474e8eef649a79aba5b3479b01272 Mon Sep 17 00:00:00 2001 From: Tony Breeds Date: Wed, 4 Jul 2007 14:04:31 +1000 Subject: [POWERPC] Add __read_mostly support for powerpc Signed-off-by: Tony Breeds Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/vmlinux.lds.S | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 21c39ff..ae4acd8 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -7,6 +7,7 @@ #define PROVIDE32(x) PROVIDE(x) #endif #include +#include ENTRY(_stext) @@ -211,6 +212,11 @@ SECTIONS *(.data.cacheline_aligned) } + . = ALIGN(L1_CACHE_BYTES); + .data.read_mostly : { + *(.data.read_mostly) + } + . = ALIGN(PAGE_SIZE); __data_nosave : { __nosave_begin = .; -- cgit v1.1 From 12654f776487952e7c0b9b3864ea1de08b1740f9 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 5 Jul 2007 19:35:33 +1000 Subject: [POWERPC] arch/powerpc/kernel/sysfs.c: Move NUMA exports With !CONFIG_NUMA, these are static inlines in the header file so don't generate exports for them in that case. Signed-off-by: Johannes Berg Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/sysfs.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 68991c2..55d29ed 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -442,12 +442,14 @@ int sysfs_add_device_to_node(struct sys_device *dev, int nid) return sysfs_create_link(&node->sysdev.kobj, &dev->kobj, kobject_name(&dev->kobj)); } +EXPORT_SYMBOL_GPL(sysfs_add_device_to_node); void sysfs_remove_device_from_node(struct sys_device *dev, int nid) { struct node *node = &node_devices[nid]; sysfs_remove_link(&node->sysdev.kobj, kobject_name(&dev->kobj)); } +EXPORT_SYMBOL_GPL(sysfs_remove_device_from_node); #else static void register_nodes(void) @@ -457,9 +459,6 @@ static void register_nodes(void) #endif -EXPORT_SYMBOL_GPL(sysfs_add_device_to_node); -EXPORT_SYMBOL_GPL(sysfs_remove_device_from_node); - /* Only valid if CPU is present. */ static ssize_t show_physical_id(struct sys_device *dev, char *buf) { -- cgit v1.1 From 70584578ab3e940ac9d7820f268f9adc9884e407 Mon Sep 17 00:00:00 2001 From: Sonny Rao Date: Tue, 10 Jul 2007 03:31:44 +1000 Subject: [POWERPC] Check for NULL ppc_md.init_IRQ() before calling Check to make sure ppc_md.init_IRQ has been set before calling it. Signed-off-by: Sonny Rao Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/irq.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index a335156..2fc8786 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -336,7 +336,8 @@ void do_IRQ(struct pt_regs *regs) void __init init_IRQ(void) { - ppc_md.init_IRQ(); + if (ppc_md.init_IRQ) + ppc_md.init_IRQ(); #ifdef CONFIG_PPC64 irq_ctx_init(); #endif -- cgit v1.1 From 1f945a86a8250b66fda47cf1fc8f3daf5d0f8969 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Mon, 9 Jul 2007 11:37:34 -0700 Subject: [POWERPC] Remove unnecessary #undef printk from prom.c Signed-off-by: Mathieu Desnoyers Signed-off-by: Andrew Morton Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/prom.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 0782afc..37ff99b 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -1056,8 +1056,6 @@ void __init early_init_devtree(void *params) DBG(" <- early_init_devtree()\n"); } -#undef printk - int of_n_addr_cells(struct device_node* np) { const int *ip; -- cgit v1.1 From 31a12cece7c71c47e61ab8ed45bbff5aac4c1931 Mon Sep 17 00:00:00 2001 From: Mike Wolf Date: Tue, 10 Jul 2007 13:13:47 -0500 Subject: [POWERPC] Oprofile support for Power 5++ This adds a new oprofile cpu type for Power 5 revision 3 chips. The new name is ppc64/power5++ and is used so that the performance counters can be set up correctly. Signed-off-by: Mike Wolf Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/cputable.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 157e6e3..b1f8000 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -294,6 +294,21 @@ static struct cpu_spec cpu_specs[] = { .oprofile_mmcra_sipr = MMCRA_SIPR, .platform = "power5", }, + { /* Power5++ */ + .pvr_mask = 0xffffff00, + .pvr_value = 0x003b0300, + .cpu_name = "POWER5+ (gs)", + .cpu_features = CPU_FTRS_POWER5, + .cpu_user_features = COMMON_USER_POWER5_PLUS, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .oprofile_cpu_type = "ppc64/power5++", + .oprofile_type = PPC_OPROFILE_POWER4, + .oprofile_mmcra_sihv = MMCRA_SIHV, + .oprofile_mmcra_sipr = MMCRA_SIPR, + .platform = "power5+", + }, { /* Power5 GS */ .pvr_mask = 0xffff0000, .pvr_value = 0x003b0000, -- cgit v1.1