diff options
Diffstat (limited to 'arch/ia64')
98 files changed, 1088 insertions, 742 deletions
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 0f3076a..db274da 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -70,6 +70,15 @@ config DMA_IS_DMA32 bool default y +config DMA_IS_NORMAL + bool + depends on IA64_SGI_SN2 + default y + +config AUDIT_ARCH + bool + default y + choice prompt "System type" default IA64_GENERIC @@ -77,6 +86,7 @@ choice config IA64_GENERIC bool "generic" select ACPI + select PCI select NUMA select ACPI_NUMA help @@ -252,7 +262,7 @@ config NR_CPUS int "Maximum number of CPUs (2-1024)" range 2 1024 depends on SMP - default "64" + default "1024" help You should set this to the number of CPUs in your system, but keep in mind that a kernel compiled for, e.g., 2 CPUs will boot but @@ -270,10 +280,12 @@ config HOTPLUG_CPU can be controlled through /sys/devices/system/cpu/cpu#. Say N if you want to disable CPU hotplug. +config ARCH_ENABLE_MEMORY_HOTPLUG + def_bool y + config SCHED_SMT bool "SMT scheduler support" depends on SMP - default off help Improves the CPU scheduler's decision making when dealing with Intel IA64 chips with MultiThreading at a cost of slightly increased @@ -346,7 +358,7 @@ config NUMA config NODES_SHIFT int "Max num nodes shift(3-10)" range 3 10 - default "8" + default "10" depends on NEED_MULTIPLE_NODES help This option specifies the maximum number of nodes in your SSI system. @@ -374,6 +386,10 @@ config HAVE_ARCH_EARLY_PFN_TO_NID def_bool y depends on NEED_MULTIPLE_NODES +config HAVE_ARCH_NODEDATA_EXTENSION + def_bool y + depends on NUMA + config IA32_SUPPORT bool "Support for Linux/x86 binaries" help @@ -449,6 +465,8 @@ config PCI_DOMAINS bool default PCI +source "drivers/pci/pcie/Kconfig" + source "drivers/pci/Kconfig" source "drivers/pci/hotplug/Kconfig" @@ -483,6 +501,10 @@ config GENERIC_PENDING_IRQ depends on GENERIC_HARDIRQS && SMP default y +config IRQ_PER_CPU + bool + default y + source "arch/ia64/hp/sim/Kconfig" menu "Instrumentation Support" diff --git a/arch/ia64/Makefile b/arch/ia64/Makefile index 80ea750..21033ed 100644 --- a/arch/ia64/Makefile +++ b/arch/ia64/Makefile @@ -71,6 +71,8 @@ all: compressed unwcheck compressed: vmlinux.gz +vmlinuz: vmlinux.gz + vmlinux.gz: vmlinux $(Q)$(MAKE) $(build)=$(boot) $@ diff --git a/arch/ia64/configs/sn2_defconfig b/arch/ia64/configs/sn2_defconfig index 9ea3539..0f14a82 100644 --- a/arch/ia64/configs/sn2_defconfig +++ b/arch/ia64/configs/sn2_defconfig @@ -363,7 +363,7 @@ CONFIG_BLK_DEV_IDECD=y # CONFIG_IDE_GENERIC=y CONFIG_BLK_DEV_IDEPCI=y -# CONFIG_IDEPCI_SHARE_IRQ is not set +CONFIG_IDEPCI_SHARE_IRQ=y # CONFIG_BLK_DEV_OFFBOARD is not set # CONFIG_BLK_DEV_GENERIC is not set # CONFIG_BLK_DEV_OPTI621 is not set diff --git a/arch/ia64/configs/tiger_defconfig b/arch/ia64/configs/tiger_defconfig index 766bf49..9d1cffb 100644 --- a/arch/ia64/configs/tiger_defconfig +++ b/arch/ia64/configs/tiger_defconfig @@ -114,7 +114,7 @@ CONFIG_IA64_CYCLONE=y CONFIG_IOSAPIC=y CONFIG_FORCE_MAX_ZONEORDER=17 CONFIG_SMP=y -CONFIG_NR_CPUS=4 +CONFIG_NR_CPUS=16 CONFIG_HOTPLUG_CPU=y CONFIG_PERMIT_BSP_REMOVE=y CONFIG_FORCE_CPEI_RETARGET=y diff --git a/arch/ia64/defconfig b/arch/ia64/defconfig index 6cba55d..9001b3f 100644 --- a/arch/ia64/defconfig +++ b/arch/ia64/defconfig @@ -366,7 +366,7 @@ CONFIG_BLK_DEV_IDESCSI=m # CONFIG_IDE_GENERIC is not set # CONFIG_BLK_DEV_IDEPNP is not set CONFIG_BLK_DEV_IDEPCI=y -# CONFIG_IDEPCI_SHARE_IRQ is not set +CONFIG_IDEPCI_SHARE_IRQ=y # CONFIG_BLK_DEV_OFFBOARD is not set CONFIG_BLK_DEV_GENERIC=y # CONFIG_BLK_DEV_OPTI621 is not set diff --git a/arch/ia64/dig/setup.c b/arch/ia64/dig/setup.c index 38aa9c1..9196b33 100644 --- a/arch/ia64/dig/setup.c +++ b/arch/ia64/dig/setup.c @@ -8,14 +8,13 @@ * Copyright (C) 1999 Walt Drummond <drummond@valinux.com> * Copyright (C) 1999 Vijay Chander <vijay@engr.sgi.com> */ -#include <linux/config.h> #include <linux/init.h> #include <linux/delay.h> #include <linux/kernel.h> #include <linux/kdev_t.h> #include <linux/string.h> -#include <linux/tty.h> +#include <linux/screen_info.h> #include <linux/console.h> #include <linux/timex.h> #include <linux/sched.h> diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c index bdccd0b..db8e1fc 100644 --- a/arch/ia64/hp/common/sba_iommu.c +++ b/arch/ia64/hp/common/sba_iommu.c @@ -19,7 +19,6 @@ ** */ -#include <linux/config.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/module.h> @@ -1958,7 +1957,7 @@ sba_map_ioc_to_node(struct ioc *ioc, acpi_handle handle) if (pxm < 0) return; - node = pxm_to_nid_map[pxm]; + node = pxm_to_node(pxm); if (node >= MAX_NUMNODES || !node_online(node)) return; @@ -1999,7 +1998,7 @@ acpi_sba_ioc_add(struct acpi_device *device) if (!iovp_shift) iovp_shift = min(PAGE_SHIFT, 16); } - ACPI_MEM_FREE(dev_info); + kfree(dev_info); /* * default anything not caught above or specified on cmdline to 4k diff --git a/arch/ia64/hp/sim/boot/bootloader.c b/arch/ia64/hp/sim/boot/bootloader.c index 51a7b7b..c5e9baa 100644 --- a/arch/ia64/hp/sim/boot/bootloader.c +++ b/arch/ia64/hp/sim/boot/bootloader.c @@ -11,7 +11,6 @@ */ struct task_struct; /* forward declaration for elf.h */ -#include <linux/config.h> #include <linux/elf.h> #include <linux/init.h> #include <linux/kernel.h> diff --git a/arch/ia64/hp/sim/boot/fw-emu.c b/arch/ia64/hp/sim/boot/fw-emu.c index 30fdfb1..5a0a7af 100644 --- a/arch/ia64/hp/sim/boot/fw-emu.c +++ b/arch/ia64/hp/sim/boot/fw-emu.c @@ -4,7 +4,6 @@ * Copyright (C) 1998-2001 Hewlett-Packard Co * David Mosberger-Tang <davidm@hpl.hp.com> */ -#include <linux/config.h> #ifdef CONFIG_PCI # include <linux/pci.h> diff --git a/arch/ia64/hp/sim/hpsim_console.c b/arch/ia64/hp/sim/hpsim_console.c index 5deff21..6e149c8 100644 --- a/arch/ia64/hp/sim/hpsim_console.c +++ b/arch/ia64/hp/sim/hpsim_console.c @@ -5,7 +5,6 @@ * David Mosberger-Tang <davidm@hpl.hp.com> * Copyright (C) 1999 Vijay Chander <vijay@engr.sgi.com> */ -#include <linux/config.h> #include <linux/init.h> #include <linux/kernel.h> diff --git a/arch/ia64/hp/sim/hpsim_irq.c b/arch/ia64/hp/sim/hpsim_irq.c index c0d25a2..8145547 100644 --- a/arch/ia64/hp/sim/hpsim_irq.c +++ b/arch/ia64/hp/sim/hpsim_irq.c @@ -44,8 +44,8 @@ hpsim_irq_init (void) int i; for (i = 0; i < NR_IRQS; ++i) { - idesc = irq_descp(i); - if (idesc->handler == &no_irq_type) - idesc->handler = &irq_type_hp_sim; + idesc = irq_desc + i; + if (idesc->chip == &no_irq_type) + idesc->chip = &irq_type_hp_sim; } } diff --git a/arch/ia64/hp/sim/hpsim_setup.c b/arch/ia64/hp/sim/hpsim_setup.c index 694fc86..f229719 100644 --- a/arch/ia64/hp/sim/hpsim_setup.c +++ b/arch/ia64/hp/sim/hpsim_setup.c @@ -5,7 +5,6 @@ * David Mosberger-Tang <davidm@hpl.hp.com> * Copyright (C) 1999 Vijay Chander <vijay@engr.sgi.com> */ -#include <linux/config.h> #include <linux/console.h> #include <linux/init.h> #include <linux/kdev_t.h> diff --git a/arch/ia64/hp/sim/simeth.c b/arch/ia64/hp/sim/simeth.c index 0639ec0..b5195be 100644 --- a/arch/ia64/hp/sim/simeth.c +++ b/arch/ia64/hp/sim/simeth.c @@ -4,7 +4,6 @@ * Copyright (C) 1999-2001, 2003 Hewlett-Packard Co * Stephane Eranian <eranian@hpl.hp.com> */ -#include <linux/config.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/types.h> diff --git a/arch/ia64/hp/sim/simscsi.c b/arch/ia64/hp/sim/simscsi.c index a3fe975..8f0a16a7 100644 --- a/arch/ia64/hp/sim/simscsi.c +++ b/arch/ia64/hp/sim/simscsi.c @@ -151,7 +151,7 @@ static void simscsi_sg_readwrite (struct scsi_cmnd *sc, int mode, unsigned long offset) { int list_len = sc->use_sg; - struct scatterlist *sl = (struct scatterlist *)sc->buffer; + struct scatterlist *sl = (struct scatterlist *)sc->request_buffer; struct disk_stat stat; struct disk_req req; @@ -244,7 +244,8 @@ static void simscsi_fillresult(struct scsi_cmnd *sc, char *buf, unsigned len) if (scatterlen == 0) memcpy(sc->request_buffer, buf, len); - else for (slp = (struct scatterlist *)sc->buffer; scatterlen-- > 0 && len > 0; slp++) { + else for (slp = (struct scatterlist *)sc->request_buffer; + scatterlen-- > 0 && len > 0; slp++) { unsigned thislen = min(len, slp->length); memcpy(page_address(slp->page) + slp->offset, buf, thislen); diff --git a/arch/ia64/hp/sim/simserial.c b/arch/ia64/hp/sim/simserial.c index 0e5c6ae..0daacc2 100644 --- a/arch/ia64/hp/sim/simserial.c +++ b/arch/ia64/hp/sim/simserial.c @@ -16,7 +16,6 @@ * 07/30/02 D. Mosberger Replace sti()/cli() with explicit spinlocks & local irq masking */ -#include <linux/config.h> #include <linux/init.h> #include <linux/errno.h> #include <linux/sched.h> @@ -47,7 +46,7 @@ #define NR_PORTS 1 /* only one port for now */ -#define IRQ_T(info) ((info->flags & ASYNC_SHARE_IRQ) ? SA_SHIRQ : SA_INTERRUPT) +#define IRQ_T(info) ((info->flags & ASYNC_SHARE_IRQ) ? IRQF_SHARED : IRQF_DISABLED) #define SSC_GETCHAR 21 diff --git a/arch/ia64/ia32/Makefile b/arch/ia64/ia32/Makefile index 61cb60a..baad8c7 100644 --- a/arch/ia64/ia32/Makefile +++ b/arch/ia64/ia32/Makefile @@ -4,6 +4,7 @@ obj-y := ia32_entry.o sys_ia32.o ia32_signal.o \ ia32_support.o ia32_traps.o binfmt_elf32.o ia32_ldt.o +obj-$(CONFIG_AUDIT) += audit.o # Don't let GCC uses f16-f31 so that save_ia32_fpstate_live() and # restore_ia32_fpstate_live() can be sure the live register contain user-level state. diff --git a/arch/ia64/ia32/audit.c b/arch/ia64/ia32/audit.c new file mode 100644 index 0000000..92d7d0c --- /dev/null +++ b/arch/ia64/ia32/audit.c @@ -0,0 +1,37 @@ +#include <asm-i386/unistd.h> + +unsigned ia32_dir_class[] = { +#include <asm-generic/audit_dir_write.h> +~0U +}; + +unsigned ia32_chattr_class[] = { +#include <asm-generic/audit_change_attr.h> +~0U +}; + +unsigned ia32_write_class[] = { +#include <asm-generic/audit_write.h> +~0U +}; + +unsigned ia32_read_class[] = { +#include <asm-generic/audit_read.h> +~0U +}; + +int ia32_classify_syscall(unsigned syscall) +{ + switch(syscall) { + case __NR_open: + return 2; + case __NR_openat: + return 3; + case __NR_socketcall: + return 4; + case __NR_execve: + return 5; + default: + return 1; + } +} diff --git a/arch/ia64/ia32/binfmt_elf32.c b/arch/ia64/ia32/binfmt_elf32.c index da03c06..daa6b91 100644 --- a/arch/ia64/ia32/binfmt_elf32.c +++ b/arch/ia64/ia32/binfmt_elf32.c @@ -9,7 +9,6 @@ * 04/13/01 D. Mosberger dropped saving tssd in ar.k1---it's not needed * 09/14/01 D. Mosberger fixed memory management for gdt/tss page */ -#include <linux/config.h> #include <linux/types.h> #include <linux/mm.h> diff --git a/arch/ia64/ia32/ia32priv.h b/arch/ia64/ia32/ia32priv.h index ccb98ed..703a67c 100644 --- a/arch/ia64/ia32/ia32priv.h +++ b/arch/ia64/ia32/ia32priv.h @@ -1,7 +1,6 @@ #ifndef _ASM_IA64_IA32_PRIV_H #define _ASM_IA64_IA32_PRIV_H -#include <linux/config.h> #include <asm/ia32.h> diff --git a/arch/ia64/ia32/sys_ia32.c b/arch/ia64/ia32/sys_ia32.c index 5366b3b..6aa3c51 100644 --- a/arch/ia64/ia32/sys_ia32.c +++ b/arch/ia64/ia32/sys_ia32.c @@ -14,7 +14,6 @@ * environment. */ -#include <linux/config.h> #include <linux/kernel.h> #include <linux/syscalls.h> #include <linux/sysctl.h> diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile index 09a0dbc..ad8215a 100644 --- a/arch/ia64/kernel/Makefile +++ b/arch/ia64/kernel/Makefile @@ -29,6 +29,7 @@ obj-$(CONFIG_CPU_FREQ) += cpufreq/ obj-$(CONFIG_IA64_MCA_RECOVERY) += mca_recovery.o obj-$(CONFIG_KPROBES) += kprobes.o jprobes.o obj-$(CONFIG_IA64_UNCACHED_ALLOCATOR) += uncached.o +obj-$(CONFIG_AUDIT) += audit.o mca_recovery-y += mca_drv.o mca_drv_asm.o # The gate DSO image is built using a special linker script. @@ -44,7 +45,8 @@ CPPFLAGS_gate.lds := -P -C -U$(ARCH) quiet_cmd_gate = GATE $@ cmd_gate = $(CC) -nostdlib $(GATECFLAGS_$(@F)) -Wl,-T,$(filter-out FORCE,$^) -o $@ -GATECFLAGS_gate.so = -shared -s -Wl,-soname=linux-gate.so.1 +GATECFLAGS_gate.so = -shared -s -Wl,-soname=linux-gate.so.1 \ + $(call ld-option, -Wl$(comma)--hash-style=sysv) $(obj)/gate.so: $(obj)/gate.lds $(obj)/gate.o FORCE $(call if_changed,gate) diff --git a/arch/ia64/kernel/acpi-ext.c b/arch/ia64/kernel/acpi-ext.c index fff8292..b7515bc 100644 --- a/arch/ia64/kernel/acpi-ext.c +++ b/arch/ia64/kernel/acpi-ext.c @@ -8,7 +8,6 @@ * published by the Free Software Foundation. */ -#include <linux/config.h> #include <linux/module.h> #include <linux/types.h> #include <linux/acpi.h> @@ -51,7 +50,7 @@ static acpi_status hp_ccsr_locate(acpi_handle obj, u64 *base, u64 *length) memcpy(length, vendor->byte_data + 8, sizeof(*length)); exit: - acpi_os_free(buffer.pointer); + kfree(buffer.pointer); return status; } diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c index 58c93a3..0176556 100644 --- a/arch/ia64/kernel/acpi.c +++ b/arch/ia64/kernel/acpi.c @@ -32,7 +32,6 @@ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ -#include <linux/config.h> #include <linux/module.h> #include <linux/init.h> #include <linux/kernel.h> @@ -56,7 +55,7 @@ #define BAD_MADT_ENTRY(entry, end) ( \ (!entry) || (unsigned long)entry + sizeof(*entry) > end || \ - ((acpi_table_entry_header *)entry)->length != sizeof(*entry)) + ((acpi_table_entry_header *)entry)->length < sizeof(*entry)) #define PREFIX "ACPI: " @@ -68,8 +67,6 @@ EXPORT_SYMBOL(pm_power_off); unsigned char acpi_kbd_controller_present = 1; unsigned char acpi_legacy_devices; -static unsigned int __initdata acpi_madt_rev; - unsigned int acpi_cpei_override; unsigned int acpi_cpei_phys_cpuid; @@ -243,6 +240,8 @@ acpi_parse_iosapic(acpi_table_entry_header * header, const unsigned long end) return iosapic_init(iosapic->address, iosapic->global_irq_base); } +static unsigned int __initdata acpi_madt_rev; + static int __init acpi_parse_plat_int_src(acpi_table_entry_header * header, const unsigned long end) @@ -415,9 +414,6 @@ static int __initdata srat_num_cpus; /* number of cpus */ static u32 __devinitdata pxm_flag[PXM_FLAG_LEN]; #define pxm_bit_set(bit) (set_bit(bit,(void *)pxm_flag)) #define pxm_bit_test(bit) (test_bit(bit,(void *)pxm_flag)) -/* maps to convert between proximity domain and logical node ID */ -int __devinitdata pxm_to_nid_map[MAX_PXM_DOMAINS]; -int __initdata nid_to_pxm_map[MAX_NUMNODES]; static struct acpi_table_slit __initdata *slit_table; static int get_processor_proximity_domain(struct acpi_table_processor_affinity *pa) @@ -533,22 +529,17 @@ void __init acpi_numa_arch_fixup(void) * MCD - This can probably be dropped now. No need for pxm ID to node ID * mapping with sparse node numbering iff MAX_PXM_DOMAINS <= MAX_NUMNODES. */ - /* calculate total number of nodes in system from PXM bitmap */ - memset(pxm_to_nid_map, -1, sizeof(pxm_to_nid_map)); - memset(nid_to_pxm_map, -1, sizeof(nid_to_pxm_map)); nodes_clear(node_online_map); for (i = 0; i < MAX_PXM_DOMAINS; i++) { if (pxm_bit_test(i)) { - int nid = num_online_nodes(); - pxm_to_nid_map[i] = nid; - nid_to_pxm_map[nid] = i; + int nid = acpi_map_pxm_to_node(i); node_set_online(nid); } } /* set logical node id in memory chunk structure */ for (i = 0; i < num_node_memblks; i++) - node_memblk[i].nid = pxm_to_nid_map[node_memblk[i].nid]; + node_memblk[i].nid = pxm_to_node(node_memblk[i].nid); /* assign memory bank numbers for each chunk on each node */ for_each_online_node(i) { @@ -562,7 +553,7 @@ void __init acpi_numa_arch_fixup(void) /* set logical node id in cpu structure */ for (i = 0; i < srat_num_cpus; i++) - node_cpuid[i].nid = pxm_to_nid_map[node_cpuid[i].nid]; + node_cpuid[i].nid = pxm_to_node(node_cpuid[i].nid); printk(KERN_INFO "Number of logical nodes in system = %d\n", num_online_nodes()); @@ -575,11 +566,11 @@ void __init acpi_numa_arch_fixup(void) for (i = 0; i < slit_table->localities; i++) { if (!pxm_bit_test(i)) continue; - node_from = pxm_to_nid_map[i]; + node_from = pxm_to_node(i); for (j = 0; j < slit_table->localities; j++) { if (!pxm_bit_test(j)) continue; - node_to = pxm_to_nid_map[j]; + node_to = pxm_to_node(j); node_distance(node_from, node_to) = slit_table->entry[i * slit_table->localities + j]; } @@ -626,7 +617,7 @@ EXPORT_SYMBOL(acpi_unregister_gsi); static int __init acpi_parse_fadt(unsigned long phys_addr, unsigned long size) { struct acpi_table_header *fadt_header; - struct fadt_descriptor_rev2 *fadt; + struct fadt_descriptor *fadt; if (!phys_addr || !size) return -EINVAL; @@ -635,7 +626,7 @@ static int __init acpi_parse_fadt(unsigned long phys_addr, unsigned long size) if (fadt_header->revision != 3) return -ENODEV; /* Only deal with ACPI 2.0 FADT */ - fadt = (struct fadt_descriptor_rev2 *)fadt_header; + fadt = (struct fadt_descriptor *)fadt_header; if (!(fadt->iapc_boot_arch & BAF_8042_KEYBOARD_CONTROLLER)) acpi_kbd_controller_present = 0; @@ -785,9 +776,9 @@ int acpi_map_cpu2node(acpi_handle handle, int cpu, long physid) /* * Assuming that the container driver would have set the proximity - * domain and would have initialized pxm_to_nid_map[pxm_id] && pxm_flag + * domain and would have initialized pxm_to_node(pxm_id) && pxm_flag */ - node_cpuid[cpu].nid = (pxm_id < 0) ? 0 : pxm_to_nid_map[pxm_id]; + node_cpuid[cpu].nid = (pxm_id < 0) ? 0 : pxm_to_node(pxm_id); node_cpuid[cpu].phys_id = physid; #endif @@ -865,7 +856,7 @@ int acpi_map_lsapic(acpi_handle handle, int *pcpu) obj = buffer.pointer; if (obj->type != ACPI_TYPE_BUFFER || obj->buffer.length < sizeof(*lsapic)) { - acpi_os_free(buffer.pointer); + kfree(buffer.pointer); return -EINVAL; } @@ -873,13 +864,13 @@ int acpi_map_lsapic(acpi_handle handle, int *pcpu) if ((lsapic->header.type != ACPI_MADT_LSAPIC) || (!lsapic->flags.enabled)) { - acpi_os_free(buffer.pointer); + kfree(buffer.pointer); return -EINVAL; } physid = ((lsapic->id << 8) | (lsapic->eid)); - acpi_os_free(buffer.pointer); + kfree(buffer.pointer); buffer.length = ACPI_ALLOCATE_BUFFER; buffer.pointer = NULL; @@ -943,20 +934,20 @@ acpi_map_iosapic(acpi_handle handle, u32 depth, void *context, void **ret) obj = buffer.pointer; if (obj->type != ACPI_TYPE_BUFFER || obj->buffer.length < sizeof(*iosapic)) { - acpi_os_free(buffer.pointer); + kfree(buffer.pointer); return AE_OK; } iosapic = (struct acpi_table_iosapic *)obj->buffer.pointer; if (iosapic->header.type != ACPI_MADT_IOSAPIC) { - acpi_os_free(buffer.pointer); + kfree(buffer.pointer); return AE_OK; } gsi_base = iosapic->global_irq_base; - acpi_os_free(buffer.pointer); + kfree(buffer.pointer); /* * OK, it's an IOSAPIC MADT entry, look for a _PXM value to tell @@ -966,7 +957,7 @@ acpi_map_iosapic(acpi_handle handle, u32 depth, void *context, void **ret) if (pxm < 0) return AE_OK; - node = pxm_to_nid_map[pxm]; + node = pxm_to_node(pxm); if (node >= MAX_NUMNODES || !node_online(node) || cpus_empty(node_to_cpumask(node))) diff --git a/arch/ia64/kernel/asm-offsets.c b/arch/ia64/kernel/asm-offsets.c index 7722565..75a2a2c 100644 --- a/arch/ia64/kernel/asm-offsets.c +++ b/arch/ia64/kernel/asm-offsets.c @@ -5,7 +5,6 @@ */ #define ASM_OFFSETS_C 1 -#include <linux/config.h> #include <linux/sched.h> @@ -217,16 +216,24 @@ void foo(void) DEFINE(IA64_MCA_CPU_INIT_STACK_OFFSET, offsetof (struct ia64_mca_cpu, init_stack)); BLANK(); - DEFINE(IA64_SAL_OS_STATE_COMMON_OFFSET, - offsetof (struct ia64_sal_os_state, sal_ra)); DEFINE(IA64_SAL_OS_STATE_OS_GP_OFFSET, offsetof (struct ia64_sal_os_state, os_gp)); - DEFINE(IA64_SAL_OS_STATE_PAL_MIN_STATE_OFFSET, - offsetof (struct ia64_sal_os_state, pal_min_state)); DEFINE(IA64_SAL_OS_STATE_PROC_STATE_PARAM_OFFSET, offsetof (struct ia64_sal_os_state, proc_state_param)); + DEFINE(IA64_SAL_OS_STATE_SAL_RA_OFFSET, + offsetof (struct ia64_sal_os_state, sal_ra)); + DEFINE(IA64_SAL_OS_STATE_SAL_GP_OFFSET, + offsetof (struct ia64_sal_os_state, sal_gp)); + DEFINE(IA64_SAL_OS_STATE_PAL_MIN_STATE_OFFSET, + offsetof (struct ia64_sal_os_state, pal_min_state)); + DEFINE(IA64_SAL_OS_STATE_OS_STATUS_OFFSET, + offsetof (struct ia64_sal_os_state, os_status)); + DEFINE(IA64_SAL_OS_STATE_CONTEXT_OFFSET, + offsetof (struct ia64_sal_os_state, context)); DEFINE(IA64_SAL_OS_STATE_SIZE, sizeof (struct ia64_sal_os_state)); + BLANK(); + DEFINE(IA64_PMSA_GR_OFFSET, offsetof (struct pal_min_state_area_s, pmsa_gr)); DEFINE(IA64_PMSA_BANK1_GR_OFFSET, diff --git a/arch/ia64/kernel/audit.c b/arch/ia64/kernel/audit.c new file mode 100644 index 0000000..0468255 --- /dev/null +++ b/arch/ia64/kernel/audit.c @@ -0,0 +1,64 @@ +#include <linux/init.h> +#include <linux/types.h> +#include <linux/audit.h> +#include <asm/unistd.h> + +static unsigned dir_class[] = { +#include <asm-generic/audit_dir_write.h> +~0U +}; + +static unsigned read_class[] = { +#include <asm-generic/audit_read.h> +~0U +}; + +static unsigned write_class[] = { +#include <asm-generic/audit_write.h> +~0U +}; + +static unsigned chattr_class[] = { +#include <asm-generic/audit_change_attr.h> +~0U +}; + +int audit_classify_syscall(int abi, unsigned syscall) +{ +#ifdef CONFIG_IA32_SUPPORT + extern int ia32_classify_syscall(unsigned); + if (abi == AUDIT_ARCH_I386) + return ia32_classify_syscall(syscall); +#endif + switch(syscall) { + case __NR_open: + return 2; + case __NR_openat: + return 3; + case __NR_execve: + return 5; + default: + return 0; + } +} + +static int __init audit_classes_init(void) +{ +#ifdef CONFIG_IA32_SUPPORT + extern __u32 ia32_dir_class[]; + extern __u32 ia32_write_class[]; + extern __u32 ia32_read_class[]; + extern __u32 ia32_chattr_class[]; + audit_register_class(AUDIT_CLASS_WRITE_32, ia32_write_class); + audit_register_class(AUDIT_CLASS_READ_32, ia32_read_class); + audit_register_class(AUDIT_CLASS_DIR_WRITE_32, ia32_dir_class); + audit_register_class(AUDIT_CLASS_CHATTR_32, ia32_chattr_class); +#endif + audit_register_class(AUDIT_CLASS_WRITE, write_class); + audit_register_class(AUDIT_CLASS_READ, read_class); + audit_register_class(AUDIT_CLASS_DIR_WRITE, dir_class); + audit_register_class(AUDIT_CLASS_CHATTR, chattr_class); + return 0; +} + +__initcall(audit_classes_init); diff --git a/arch/ia64/kernel/cpufreq/acpi-cpufreq.c b/arch/ia64/kernel/cpufreq/acpi-cpufreq.c index 5a1bf81..86faf22 100644 --- a/arch/ia64/kernel/cpufreq/acpi-cpufreq.c +++ b/arch/ia64/kernel/cpufreq/acpi-cpufreq.c @@ -9,7 +9,6 @@ * Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> */ -#include <linux/config.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c index 12cfedc..bb8770a 100644 --- a/arch/ia64/kernel/efi.c +++ b/arch/ia64/kernel/efi.c @@ -8,6 +8,8 @@ * Copyright (C) 1999-2003 Hewlett-Packard Co. * David Mosberger-Tang <davidm@hpl.hp.com> * Stephane Eranian <eranian@hpl.hp.com> + * (c) Copyright 2006 Hewlett-Packard Development Company, L.P. + * Bjorn Helgaas <bjorn.helgaas@hp.com> * * All EFI Runtime Services are not implemented yet as EFI only * supports physical mode addressing on SoftSDV. This is to be fixed @@ -18,7 +20,6 @@ * Goutham Rao: <goutham.rao@intel.com> * Skip non-WB memory and ignore empty memory ranges. */ -#include <linux/config.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/init.h> @@ -622,28 +623,20 @@ efi_get_iobase (void) return 0; } -static efi_memory_desc_t * -efi_memory_descriptor (unsigned long phys_addr) +static struct kern_memdesc * +kern_memory_descriptor (unsigned long phys_addr) { - void *efi_map_start, *efi_map_end, *p; - efi_memory_desc_t *md; - u64 efi_desc_size; - - efi_map_start = __va(ia64_boot_param->efi_memmap); - efi_map_end = efi_map_start + ia64_boot_param->efi_memmap_size; - efi_desc_size = ia64_boot_param->efi_memdesc_size; + struct kern_memdesc *md; - for (p = efi_map_start; p < efi_map_end; p += efi_desc_size) { - md = p; - - if (phys_addr - md->phys_addr < (md->num_pages << EFI_PAGE_SHIFT)) + for (md = kern_memmap; md->start != ~0UL; md++) { + if (phys_addr - md->start < (md->num_pages << EFI_PAGE_SHIFT)) return md; } - return 0; + return NULL; } -static int -efi_memmap_has_mmio (void) +static efi_memory_desc_t * +efi_memory_descriptor (unsigned long phys_addr) { void *efi_map_start, *efi_map_end, *p; efi_memory_desc_t *md; @@ -656,10 +649,10 @@ efi_memmap_has_mmio (void) for (p = efi_map_start; p < efi_map_end; p += efi_desc_size) { md = p; - if (md->type == EFI_MEMORY_MAPPED_IO) - return 1; + if (phys_addr - md->phys_addr < (md->num_pages << EFI_PAGE_SHIFT)) + return md; } - return 0; + return NULL; } u32 @@ -683,71 +676,125 @@ efi_mem_attributes (unsigned long phys_addr) } EXPORT_SYMBOL(efi_mem_attributes); -/* - * Determines whether the memory at phys_addr supports the desired - * attribute (WB, UC, etc). If this returns 1, the caller can safely - * access size bytes at phys_addr with the specified attribute. - */ -int -efi_mem_attribute_range (unsigned long phys_addr, unsigned long size, u64 attr) +u64 +efi_mem_attribute (unsigned long phys_addr, unsigned long size) { unsigned long end = phys_addr + size; efi_memory_desc_t *md = efi_memory_descriptor(phys_addr); + u64 attr; + + if (!md) + return 0; + + /* + * EFI_MEMORY_RUNTIME is not a memory attribute; it just tells + * the kernel that firmware needs this region mapped. + */ + attr = md->attribute & ~EFI_MEMORY_RUNTIME; + do { + unsigned long md_end = efi_md_end(md); + + if (end <= md_end) + return attr; + + md = efi_memory_descriptor(md_end); + if (!md || (md->attribute & ~EFI_MEMORY_RUNTIME) != attr) + return 0; + } while (md); + return 0; +} + +u64 +kern_mem_attribute (unsigned long phys_addr, unsigned long size) +{ + unsigned long end = phys_addr + size; + struct kern_memdesc *md; + u64 attr; /* - * Some firmware doesn't report MMIO regions in the EFI memory - * map. The Intel BigSur (a.k.a. HP i2000) has this problem. - * On those platforms, we have to assume UC is valid everywhere. + * This is a hack for ioremap calls before we set up kern_memmap. + * Maybe we should do efi_memmap_init() earlier instead. */ - if (!md || (md->attribute & attr) != attr) { - if (attr == EFI_MEMORY_UC && !efi_memmap_has_mmio()) - return 1; + if (!kern_memmap) { + attr = efi_mem_attribute(phys_addr, size); + if (attr & EFI_MEMORY_WB) + return EFI_MEMORY_WB; return 0; } + md = kern_memory_descriptor(phys_addr); + if (!md) + return 0; + + attr = md->attribute; do { - unsigned long md_end = efi_md_end(md); + unsigned long md_end = kmd_end(md); if (end <= md_end) - return 1; + return attr; - md = efi_memory_descriptor(md_end); - if (!md || (md->attribute & attr) != attr) + md = kern_memory_descriptor(md_end); + if (!md || md->attribute != attr) return 0; } while (md); return 0; } +EXPORT_SYMBOL(kern_mem_attribute); -/* - * For /dev/mem, we only allow read & write system calls to access - * write-back memory, because read & write don't allow the user to - * control access size. - */ int valid_phys_addr_range (unsigned long phys_addr, unsigned long size) { - return efi_mem_attribute_range(phys_addr, size, EFI_MEMORY_WB); + u64 attr; + + /* + * /dev/mem reads and writes use copy_to_user(), which implicitly + * uses a granule-sized kernel identity mapping. It's really + * only safe to do this for regions in kern_memmap. For more + * details, see Documentation/ia64/aliasing.txt. + */ + attr = kern_mem_attribute(phys_addr, size); + if (attr & EFI_MEMORY_WB || attr & EFI_MEMORY_UC) + return 1; + return 0; } -/* - * We allow mmap of anything in the EFI memory map that supports - * either write-back or uncacheable access. For uncacheable regions, - * the supported access sizes are system-dependent, and the user is - * responsible for using the correct size. - * - * Note that this doesn't currently allow access to hot-added memory, - * because that doesn't appear in the boot-time EFI memory map. - */ int -valid_mmap_phys_addr_range (unsigned long phys_addr, unsigned long size) +valid_mmap_phys_addr_range (unsigned long pfn, unsigned long size) { - if (efi_mem_attribute_range(phys_addr, size, EFI_MEMORY_WB)) - return 1; + /* + * MMIO regions are often missing from the EFI memory map. + * We must allow mmap of them for programs like X, so we + * currently can't do any useful validation. + */ + return 1; +} - if (efi_mem_attribute_range(phys_addr, size, EFI_MEMORY_UC)) - return 1; +pgprot_t +phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, + pgprot_t vma_prot) +{ + unsigned long phys_addr = pfn << PAGE_SHIFT; + u64 attr; - return 0; + /* + * For /dev/mem mmap, we use user mappings, but if the region is + * in kern_memmap (and hence may be covered by a kernel mapping), + * we must use the same attribute as the kernel mapping. + */ + attr = kern_mem_attribute(phys_addr, size); + if (attr & EFI_MEMORY_WB) + return pgprot_cacheable(vma_prot); + else if (attr & EFI_MEMORY_UC) + return pgprot_noncached(vma_prot); + + /* + * Some chipsets don't support UC access to memory. If + * WB is supported, we prefer that. + */ + if (efi_mem_attribute(phys_addr, size) & EFI_MEMORY_WB) + return pgprot_cacheable(vma_prot); + + return pgprot_noncached(vma_prot); } int __init @@ -876,7 +923,7 @@ find_memmap_space (void) void efi_memmap_init(unsigned long *s, unsigned long *e) { - struct kern_memdesc *k, *prev = 0; + struct kern_memdesc *k, *prev = NULL; u64 contig_low=0, contig_high=0; u64 as, ae, lim; void *efi_map_start, *efi_map_end, *p, *q; diff --git a/arch/ia64/kernel/efi_stub.S b/arch/ia64/kernel/efi_stub.S index 5a7fe70..a56e161 100644 --- a/arch/ia64/kernel/efi_stub.S +++ b/arch/ia64/kernel/efi_stub.S @@ -61,7 +61,7 @@ GLOBAL_ENTRY(efi_call_phys) or loc3=loc3,r17 mov b6=r2 ;; - andcm r16=loc3,r16 // get psr with IT, DT, and RT bits cleared + andcm r16=loc3,r16 // get psr with IT, DT, and RT bits cleared br.call.sptk.many rp=ia64_switch_mode_phys .ret0: mov out4=in5 mov out0=in1 diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S index bcb80ca..fef0657 100644 --- a/arch/ia64/kernel/entry.S +++ b/arch/ia64/kernel/entry.S @@ -31,7 +31,6 @@ * pNonSys: !pSys */ -#include <linux/config.h> #include <asm/asmmacro.h> #include <asm/cache.h> @@ -1584,7 +1583,7 @@ sys_call_table: data8 sys_keyctl data8 sys_ioprio_set data8 sys_ioprio_get // 1275 - data8 sys_ni_syscall + data8 sys_move_pages data8 sys_inotify_init data8 sys_inotify_add_watch data8 sys_inotify_rm_watch @@ -1606,8 +1605,8 @@ sys_call_table: data8 sys_ni_syscall // 1295 reserved for ppoll data8 sys_unshare data8 sys_splice - data8 sys_set_robust_list - data8 sys_get_robust_list + data8 sys_ni_syscall // reserved for set_robust_list + data8 sys_ni_syscall // reserved for get_robust_list data8 sys_sync_file_range // 1300 data8 sys_tee data8 sys_vmsplice diff --git a/arch/ia64/kernel/entry.h b/arch/ia64/kernel/entry.h index 78eeb07..b83edac 100644 --- a/arch/ia64/kernel/entry.h +++ b/arch/ia64/kernel/entry.h @@ -1,4 +1,3 @@ -#include <linux/config.h> /* * Preserved registers that are shared between code in ivt.S and @@ -23,6 +22,7 @@ #define PT(f) (IA64_PT_REGS_##f##_OFFSET) #define SW(f) (IA64_SWITCH_STACK_##f##_OFFSET) +#define SOS(f) (IA64_SAL_OS_STATE_##f##_OFFSET) #define PT_REGS_SAVES(off) \ .unwabi 3, 'i'; \ diff --git a/arch/ia64/kernel/gate.S b/arch/ia64/kernel/gate.S index 86064ca..3274850 100644 --- a/arch/ia64/kernel/gate.S +++ b/arch/ia64/kernel/gate.S @@ -6,7 +6,6 @@ * David Mosberger-Tang <davidm@hpl.hp.com> */ -#include <linux/config.h> #include <asm/asmmacro.h> #include <asm/errno.h> diff --git a/arch/ia64/kernel/gate.lds.S b/arch/ia64/kernel/gate.lds.S index 7c99e6e..6d19833 100644 --- a/arch/ia64/kernel/gate.lds.S +++ b/arch/ia64/kernel/gate.lds.S @@ -4,7 +4,6 @@ * in one page). This script controls its layout. */ -#include <linux/config.h> #include <asm/system.h> @@ -13,6 +12,7 @@ SECTIONS . = GATE_ADDR + SIZEOF_HEADERS; .hash : { *(.hash) } :readable + .gnu.hash : { *(.gnu.hash) } .dynsym : { *(.dynsym) } .dynstr : { *(.dynstr) } .gnu.version : { *(.gnu.version) } diff --git a/arch/ia64/kernel/head.S b/arch/ia64/kernel/head.S index f1778a8..44d540e 100644 --- a/arch/ia64/kernel/head.S +++ b/arch/ia64/kernel/head.S @@ -19,7 +19,6 @@ * Support for CPU Hotplug */ -#include <linux/config.h> #include <asm/asmmacro.h> #include <asm/fpu.h> @@ -198,6 +197,11 @@ start_ap: ;; srlz.i ;; + { + flushrs // must be first insn in group + srlz.i + } + ;; /* * Save the region registers, predicate before they get clobbered */ @@ -854,7 +858,6 @@ END(__ia64_init_fpu) */ GLOBAL_ENTRY(ia64_switch_mode_phys) { - alloc r2=ar.pfs,0,0,0,0 rsm psr.i | psr.ic // disable interrupts and interrupt collection mov r15=ip } @@ -903,7 +906,6 @@ END(ia64_switch_mode_phys) */ GLOBAL_ENTRY(ia64_switch_mode_virt) { - alloc r2=ar.pfs,0,0,0,0 rsm psr.i | psr.ic // disable interrupts and interrupt collection mov r15=ip } diff --git a/arch/ia64/kernel/ia64_ksyms.c b/arch/ia64/kernel/ia64_ksyms.c index bbcfd08..3ead20f 100644 --- a/arch/ia64/kernel/ia64_ksyms.c +++ b/arch/ia64/kernel/ia64_ksyms.c @@ -5,7 +5,6 @@ * All other exports should be put directly after the definition. */ -#include <linux/config.h> #include <linux/module.h> #include <linux/string.h> @@ -63,7 +62,7 @@ EXPORT_SYMBOL(__udivdi3); EXPORT_SYMBOL(__moddi3); EXPORT_SYMBOL(__umoddi3); -#if defined(CONFIG_MD_RAID5) || defined(CONFIG_MD_RAID5_MODULE) +#if defined(CONFIG_MD_RAID456) || defined(CONFIG_MD_RAID456_MODULE) extern void xor_ia64_2(void); extern void xor_ia64_3(void); extern void xor_ia64_4(void); diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c index d58c1c5..9bf15fe 100644 --- a/arch/ia64/kernel/iosapic.c +++ b/arch/ia64/kernel/iosapic.c @@ -79,7 +79,6 @@ * describeinterrupts. Now we use "IRQ" only for Linux IRQ's. ISA IRQ * (isa_irq) is the only exception in this source code. */ -#include <linux/config.h> #include <linux/acpi.h> #include <linux/init.h> @@ -456,7 +455,7 @@ iosapic_startup_edge_irq (unsigned int irq) static void iosapic_ack_edge_irq (unsigned int irq) { - irq_desc_t *idesc = irq_descp(irq); + irq_desc_t *idesc = irq_desc + irq; move_native_irq(irq); /* @@ -659,14 +658,14 @@ register_intr (unsigned int gsi, int vector, unsigned char delivery, else irq_type = &irq_type_iosapic_level; - idesc = irq_descp(vector); - if (idesc->handler != irq_type) { - if (idesc->handler != &no_irq_type) + idesc = irq_desc + vector; + if (idesc->chip != irq_type) { + if (idesc->chip != &no_irq_type) printk(KERN_WARNING "%s: changing vector %d from %s to %s\n", __FUNCTION__, vector, - idesc->handler->typename, irq_type->typename); - idesc->handler = irq_type; + idesc->chip->typename, irq_type->typename); + idesc->chip = irq_type; } return 0; } @@ -793,14 +792,14 @@ again: return -ENOSPC; } - spin_lock_irqsave(&irq_descp(vector)->lock, flags); + spin_lock_irqsave(&irq_desc[vector].lock, flags); spin_lock(&iosapic_lock); { if (gsi_to_vector(gsi) > 0) { if (list_empty(&iosapic_intr_info[vector].rtes)) free_irq_vector(vector); spin_unlock(&iosapic_lock); - spin_unlock_irqrestore(&irq_descp(vector)->lock, + spin_unlock_irqrestore(&irq_desc[vector].lock, flags); goto again; } @@ -810,7 +809,7 @@ again: polarity, trigger); if (err < 0) { spin_unlock(&iosapic_lock); - spin_unlock_irqrestore(&irq_descp(vector)->lock, + spin_unlock_irqrestore(&irq_desc[vector].lock, flags); return err; } @@ -825,7 +824,7 @@ again: set_rte(gsi, vector, dest, mask); } spin_unlock(&iosapic_lock); - spin_unlock_irqrestore(&irq_descp(vector)->lock, flags); + spin_unlock_irqrestore(&irq_desc[vector].lock, flags); printk(KERN_INFO "GSI %u (%s, %s) -> CPU %d (0x%04x) vector %d\n", gsi, (trigger == IOSAPIC_EDGE ? "edge" : "level"), @@ -860,7 +859,7 @@ iosapic_unregister_intr (unsigned int gsi) } vector = irq_to_vector(irq); - idesc = irq_descp(irq); + idesc = irq_desc + irq; spin_lock_irqsave(&idesc->lock, flags); spin_lock(&iosapic_lock); { @@ -903,7 +902,7 @@ iosapic_unregister_intr (unsigned int gsi) BUG_ON(iosapic_intr_info[vector].count); /* Clear the interrupt controller descriptor */ - idesc->handler = &no_irq_type; + idesc->chip = &no_irq_type; /* Clear the interrupt information */ memset(&iosapic_intr_info[vector], 0, diff --git a/arch/ia64/kernel/irq.c b/arch/ia64/kernel/irq.c index 9c72ea3f..7852382 100644 --- a/arch/ia64/kernel/irq.c +++ b/arch/ia64/kernel/irq.c @@ -76,7 +76,7 @@ int show_interrupts(struct seq_file *p, void *v) seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]); } #endif - seq_printf(p, " %14s", irq_desc[i].handler->typename); + seq_printf(p, " %14s", irq_desc[i].chip->typename); seq_printf(p, " %s", action->name); for (action=action->next; action; action = action->next) @@ -100,7 +100,7 @@ void set_irq_affinity_info (unsigned int irq, int hwid, int redir) cpu_set(cpu_logical_id(hwid), mask); if (irq < NR_IRQS) { - irq_affinity[irq] = mask; + irq_desc[irq].affinity = mask; irq_redir[irq] = (char) (redir & 0xff); } } @@ -120,7 +120,7 @@ static void migrate_irqs(void) int irq, new_cpu; for (irq=0; irq < NR_IRQS; irq++) { - desc = irq_descp(irq); + desc = irq_desc + irq; /* * No handling for now. @@ -131,7 +131,7 @@ static void migrate_irqs(void) if (desc->status == IRQ_PER_CPU) continue; - cpus_and(mask, irq_affinity[irq], cpu_online_map); + cpus_and(mask, irq_desc[irq].affinity, cpu_online_map); if (any_online_cpu(mask) == NR_CPUS) { /* * Save it for phase 2 processing @@ -144,15 +144,15 @@ static void migrate_irqs(void) /* * Al three are essential, currently WARN_ON.. maybe panic? */ - if (desc->handler && desc->handler->disable && - desc->handler->enable && desc->handler->set_affinity) { - desc->handler->disable(irq); - desc->handler->set_affinity(irq, mask); - desc->handler->enable(irq); + if (desc->chip && desc->chip->disable && + desc->chip->enable && desc->chip->set_affinity) { + desc->chip->disable(irq); + desc->chip->set_affinity(irq, mask); + desc->chip->enable(irq); } else { - WARN_ON((!(desc->handler) || !(desc->handler->disable) || - !(desc->handler->enable) || - !(desc->handler->set_affinity))); + WARN_ON((!(desc->chip) || !(desc->chip->disable) || + !(desc->chip->enable) || + !(desc->chip->set_affinity))); } } } diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c index 6c4d59f..a041367 100644 --- a/arch/ia64/kernel/irq_ia64.c +++ b/arch/ia64/kernel/irq_ia64.c @@ -14,7 +14,6 @@ * Added CPU Hotplug handling for IPF. */ -#include <linux/config.h> #include <linux/module.h> #include <linux/jiffies.h> @@ -46,6 +45,10 @@ #define IRQ_DEBUG 0 +/* These can be overridden in platform_irq_init */ +int ia64_first_device_vector = IA64_DEF_FIRST_DEVICE_VECTOR; +int ia64_last_device_vector = IA64_DEF_LAST_DEVICE_VECTOR; + /* default base addr of IPI table */ void __iomem *ipi_base_addr = ((void __iomem *) (__IA64_UNCACHED_OFFSET | IA64_IPI_DEFAULT_BASE_ADDR)); @@ -60,7 +63,7 @@ __u8 isa_irq_to_vector_map[16] = { }; EXPORT_SYMBOL(isa_irq_to_vector_map); -static unsigned long ia64_vector_mask[BITS_TO_LONGS(IA64_NUM_DEVICE_VECTORS)]; +static unsigned long ia64_vector_mask[BITS_TO_LONGS(IA64_MAX_DEVICE_VECTORS)]; int assign_irq_vector (int irq) @@ -89,6 +92,19 @@ free_irq_vector (int vector) printk(KERN_WARNING "%s: double free!\n", __FUNCTION__); } +int +reserve_irq_vector (int vector) +{ + int pos; + + if (vector < IA64_FIRST_DEVICE_VECTOR || + vector > IA64_LAST_DEVICE_VECTOR) + return -EINVAL; + + pos = vector - IA64_FIRST_DEVICE_VECTOR; + return test_and_set_bit(pos, ia64_vector_mask); +} + #ifdef CONFIG_SMP # define IS_RESCHEDULE(vec) (vec == IA64_IPI_RESCHEDULE) #else @@ -219,7 +235,7 @@ extern irqreturn_t handle_IPI (int irq, void *dev_id, struct pt_regs *regs); static struct irqaction ipi_irqaction = { .handler = handle_IPI, - .flags = SA_INTERRUPT, + .flags = IRQF_DISABLED, .name = "IPI" }; #endif @@ -232,9 +248,9 @@ register_percpu_irq (ia64_vector vec, struct irqaction *action) for (irq = 0; irq < NR_IRQS; ++irq) if (irq_to_vector(irq) == vec) { - desc = irq_descp(irq); + desc = irq_desc + irq; desc->status |= IRQ_PER_CPU; - desc->handler = &irq_type_ia64_lsapic; + desc->chip = &irq_type_ia64_lsapic; if (action) setup_irq(irq, action); } diff --git a/arch/ia64/kernel/irq_lsapic.c b/arch/ia64/kernel/irq_lsapic.c index ea14e6a..1ab58b0 100644 --- a/arch/ia64/kernel/irq_lsapic.c +++ b/arch/ia64/kernel/irq_lsapic.c @@ -26,6 +26,13 @@ lsapic_noop (unsigned int irq) /* nuthing to do... */ } +static int lsapic_retrigger(unsigned int irq) +{ + ia64_resend_irq(irq); + + return 1; +} + struct hw_interrupt_type irq_type_ia64_lsapic = { .typename = "LSAPIC", .startup = lsapic_noop_startup, @@ -33,5 +40,6 @@ struct hw_interrupt_type irq_type_ia64_lsapic = { .enable = lsapic_noop, .disable = lsapic_noop, .ack = lsapic_noop, - .end = lsapic_noop + .end = lsapic_noop, + .retrigger = lsapic_retrigger, }; diff --git a/arch/ia64/kernel/ivt.S b/arch/ia64/kernel/ivt.S index 829a43c..6b7fcbd 100644 --- a/arch/ia64/kernel/ivt.S +++ b/arch/ia64/kernel/ivt.S @@ -38,7 +38,6 @@ * Table is based upon EAS2.6 (Oct 1999) */ -#include <linux/config.h> #include <asm/asmmacro.h> #include <asm/break.h> diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c index f9039f8..781960f 100644 --- a/arch/ia64/kernel/kprobes.c +++ b/arch/ia64/kernel/kprobes.c @@ -23,7 +23,6 @@ * <anil.s.keshavamurthy@intel.com> adapted from i386 */ -#include <linux/config.h> #include <linux/kprobes.h> #include <linux/ptrace.h> #include <linux/string.h> @@ -449,11 +448,20 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) return 0; } +void __kprobes flush_insn_slot(struct kprobe *p) +{ + unsigned long arm_addr; + + arm_addr = ((unsigned long)&p->opcode.bundle) & ~0xFULL; + flush_icache_range(arm_addr, arm_addr + sizeof(bundle_t)); +} + void __kprobes arch_arm_kprobe(struct kprobe *p) { unsigned long addr = (unsigned long)p->addr; unsigned long arm_addr = addr & ~0xFULL; + flush_insn_slot(p); memcpy((char *)arm_addr, &p->ainsn.insn.bundle, sizeof(bundle_t)); flush_icache_range(arm_addr, arm_addr + sizeof(bundle_t)); } diff --git a/arch/ia64/kernel/machvec.c b/arch/ia64/kernel/machvec.c index 4b0b71d..d4a546a 100644 --- a/arch/ia64/kernel/machvec.c +++ b/arch/ia64/kernel/machvec.c @@ -1,4 +1,3 @@ -#include <linux/config.h> #include <linux/module.h> #include <asm/machvec.h> diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c index 6a08806..2fbe453 100644 --- a/arch/ia64/kernel/mca.c +++ b/arch/ia64/kernel/mca.c @@ -55,7 +55,6 @@ * 2005-10-07 Keith Owens <kaos@sgi.com> * Add notify_die() hooks. */ -#include <linux/config.h> #include <linux/types.h> #include <linux/init.h> #include <linux/sched.h> @@ -679,7 +678,7 @@ copy_reg(const u64 *fr, u64 fnat, u64 *tr, u64 *tnat) */ static void -ia64_mca_modify_comm(const task_t *previous_current) +ia64_mca_modify_comm(const struct task_struct *previous_current) { char *p, comm[sizeof(current->comm)]; if (previous_current->pid) @@ -710,7 +709,7 @@ ia64_mca_modify_comm(const task_t *previous_current) * that we can do backtrace on the MCA/INIT handler code itself. */ -static task_t * +static struct task_struct * ia64_mca_modify_original_stack(struct pt_regs *regs, const struct switch_stack *sw, struct ia64_sal_os_state *sos, @@ -720,7 +719,7 @@ ia64_mca_modify_original_stack(struct pt_regs *regs, ia64_va va; extern char ia64_leave_kernel[]; /* Need asm address, not function descriptor */ const pal_min_state_area_t *ms = sos->pal_min_state; - task_t *previous_current; + struct task_struct *previous_current; struct pt_regs *old_regs; struct switch_stack *old_sw; unsigned size = sizeof(struct pt_regs) + @@ -1024,7 +1023,7 @@ ia64_mca_handler(struct pt_regs *regs, struct switch_stack *sw, pal_processor_state_info_t *psp = (pal_processor_state_info_t *) &sos->proc_state_param; int recover, cpu = smp_processor_id(); - task_t *previous_current; + struct task_struct *previous_current; struct ia64_mca_notify_die nd = { .sos = sos, .monarch_cpu = &monarch_cpu }; @@ -1353,7 +1352,7 @@ ia64_init_handler(struct pt_regs *regs, struct switch_stack *sw, { static atomic_t slaves; static atomic_t monarchs; - task_t *previous_current; + struct task_struct *previous_current; int cpu = smp_processor_id(); struct ia64_mca_notify_die nd = { .sos = sos, .monarch_cpu = &monarch_cpu }; @@ -1458,38 +1457,38 @@ __setup("disable_cpe_poll", ia64_mca_disable_cpe_polling); static struct irqaction cmci_irqaction = { .handler = ia64_mca_cmc_int_handler, - .flags = SA_INTERRUPT, + .flags = IRQF_DISABLED, .name = "cmc_hndlr" }; static struct irqaction cmcp_irqaction = { .handler = ia64_mca_cmc_int_caller, - .flags = SA_INTERRUPT, + .flags = IRQF_DISABLED, .name = "cmc_poll" }; static struct irqaction mca_rdzv_irqaction = { .handler = ia64_mca_rendez_int_handler, - .flags = SA_INTERRUPT, + .flags = IRQF_DISABLED, .name = "mca_rdzv" }; static struct irqaction mca_wkup_irqaction = { .handler = ia64_mca_wakeup_int_handler, - .flags = SA_INTERRUPT, + .flags = IRQF_DISABLED, .name = "mca_wkup" }; #ifdef CONFIG_ACPI static struct irqaction mca_cpe_irqaction = { .handler = ia64_mca_cpe_int_handler, - .flags = SA_INTERRUPT, + .flags = IRQF_DISABLED, .name = "cpe_hndlr" }; static struct irqaction mca_cpep_irqaction = { .handler = ia64_mca_cpe_int_caller, - .flags = SA_INTERRUPT, + .flags = IRQF_DISABLED, .name = "cpe_poll" }; #endif /* CONFIG_ACPI */ @@ -1788,7 +1787,7 @@ ia64_mca_late_init(void) cpe_poll_enabled = 0; for (irq = 0; irq < NR_IRQS; ++irq) if (irq_to_vector(irq) == cpe_vector) { - desc = irq_descp(irq); + desc = irq_desc + irq; desc->status |= IRQ_PER_CPU; setup_irq(irq, &mca_cpe_irqaction); ia64_cpe_irq = irq; diff --git a/arch/ia64/kernel/mca_asm.S b/arch/ia64/kernel/mca_asm.S index 6dff024..9604749 100644 --- a/arch/ia64/kernel/mca_asm.S +++ b/arch/ia64/kernel/mca_asm.S @@ -19,7 +19,6 @@ // 12/08/05 Keith Owens <kaos@sgi.com> // Use per cpu MCA/INIT stacks for all data. // -#include <linux/config.h> #include <linux/threads.h> #include <asm/asmmacro.h> @@ -159,7 +158,7 @@ ia64_os_mca_spin: GET_IA64_MCA_DATA(r2) // Using MCA stack, struct ia64_sal_os_state, variable proc_state_param ;; - add r3=IA64_MCA_CPU_MCA_STACK_OFFSET+MCA_SOS_OFFSET+IA64_SAL_OS_STATE_PROC_STATE_PARAM_OFFSET, r2 + add r3=IA64_MCA_CPU_MCA_STACK_OFFSET+MCA_SOS_OFFSET+SOS(PROC_STATE_PARAM), r2 ;; ld8 r18=[r3] // Get processor state parameter on existing PALE_CHECK. ;; @@ -479,9 +478,11 @@ ia64_state_save: st8 [temp2]=r11,16 // rv_rc mov r11=cr.iipa ;; - st8 [temp1]=r18,16 // proc_state_param - st8 [temp2]=r19,16 // monarch + st8 [temp1]=r18 // proc_state_param + st8 [temp2]=r19 // monarch mov r6=IA64_KR(CURRENT) + add temp1=SOS(SAL_RA), regs + add temp2=SOS(SAL_GP), regs ;; st8 [temp1]=r12,16 // sal_ra st8 [temp2]=r10,16 // sal_gp @@ -503,12 +504,14 @@ ia64_state_save: st8 [temp2]=r11,16 // cr.iipa mov r12=cr.iim ;; - st8 [temp1]=r12,16 // cr.iim + st8 [temp1]=r12 // cr.iim (p1) mov r12=IA64_MCA_COLD_BOOT (p2) mov r12=IA64_INIT_WARM_BOOT mov r6=cr.iha + add temp1=SOS(OS_STATUS), regs ;; - st8 [temp2]=r6,16 // cr.iha + st8 [temp2]=r6 // cr.iha + add temp2=SOS(CONTEXT), regs st8 [temp1]=r12 // os_status, default is cold boot mov r6=IA64_MCA_SAME_CONTEXT ;; @@ -820,8 +823,8 @@ ia64_state_restore: // Restore the SAL to OS state. The previous code left regs at pt_regs. add regs=MCA_SOS_OFFSET-MCA_PT_REGS_OFFSET, regs ;; - add temp1=IA64_SAL_OS_STATE_COMMON_OFFSET, regs - add temp2=IA64_SAL_OS_STATE_COMMON_OFFSET+8, regs + add temp1=SOS(SAL_RA), regs + add temp2=SOS(SAL_GP), regs ;; ld8 r12=[temp1],16 // sal_ra ld8 r9=[temp2],16 // sal_gp @@ -842,8 +845,10 @@ ia64_state_restore: ;; mov cr.itir=temp3 mov cr.iipa=temp4 - ld8 temp3=[temp1],16 // cr.iim - ld8 temp4=[temp2],16 // cr.iha + ld8 temp3=[temp1] // cr.iim + ld8 temp4=[temp2] // cr.iha + add temp1=SOS(OS_STATUS), regs + add temp2=SOS(CONTEXT), regs ;; mov cr.iim=temp3 mov cr.iha=temp4 @@ -916,7 +921,7 @@ ia64_state_restore: ia64_new_stack: add regs=MCA_PT_REGS_OFFSET, r3 - add temp2=MCA_SOS_OFFSET+IA64_SAL_OS_STATE_PAL_MIN_STATE_OFFSET, r3 + add temp2=MCA_SOS_OFFSET+SOS(PAL_MIN_STATE), r3 mov b0=r2 // save return address GET_IA64_MCA_DATA(temp1) invala @@ -1020,7 +1025,7 @@ ia64_old_stack: ia64_set_kernel_registers: add temp3=MCA_SP_OFFSET, r3 - add temp4=MCA_SOS_OFFSET+IA64_SAL_OS_STATE_OS_GP_OFFSET, r3 + add temp4=MCA_SOS_OFFSET+SOS(OS_GP), r3 mov b0=r2 // save return address GET_IA64_MCA_DATA(temp1) ;; diff --git a/arch/ia64/kernel/mca_drv.c b/arch/ia64/kernel/mca_drv.c index ca6666b..8db6e0c 100644 --- a/arch/ia64/kernel/mca_drv.c +++ b/arch/ia64/kernel/mca_drv.c @@ -8,7 +8,6 @@ * Copyright (C) 2005 Keith Owens <kaos@sgi.com> * Copyright (C) 2006 Russ Anderson <rja@sgi.com> */ -#include <linux/config.h> #include <linux/types.h> #include <linux/init.h> #include <linux/sched.h> diff --git a/arch/ia64/kernel/mca_drv_asm.S b/arch/ia64/kernel/mca_drv_asm.S index e6a580d..f2d4900 100644 --- a/arch/ia64/kernel/mca_drv_asm.S +++ b/arch/ia64/kernel/mca_drv_asm.S @@ -5,7 +5,6 @@ * Copyright (C) 2004 FUJITSU LIMITED * Copyright (C) Hidetoshi Seto (seto.hidetoshi@jp.fujitsu.com) */ -#include <linux/config.h> #include <linux/threads.h> #include <asm/asmmacro.h> diff --git a/arch/ia64/kernel/minstate.h b/arch/ia64/kernel/minstate.h index 85ed541..c9ac8ba 100644 --- a/arch/ia64/kernel/minstate.h +++ b/arch/ia64/kernel/minstate.h @@ -1,4 +1,3 @@ -#include <linux/config.h> #include <asm/cache.h> diff --git a/arch/ia64/kernel/module.c b/arch/ia64/kernel/module.c index 3a30cfc..158e3c5 100644 --- a/arch/ia64/kernel/module.c +++ b/arch/ia64/kernel/module.c @@ -25,7 +25,6 @@ SEGREL64LSB */ -#include <linux/config.h> #include <linux/kernel.h> #include <linux/sched.h> diff --git a/arch/ia64/kernel/numa.c b/arch/ia64/kernel/numa.c index 0766493..1cc360c 100644 --- a/arch/ia64/kernel/numa.c +++ b/arch/ia64/kernel/numa.c @@ -19,7 +19,6 @@ * Copyright (C) 2004 Silicon Graphics, Inc. * Jesse Barnes <jbarnes@sgi.com> */ -#include <linux/config.h> #include <linux/topology.h> #include <linux/module.h> #include <asm/processor.h> diff --git a/arch/ia64/kernel/pal.S b/arch/ia64/kernel/pal.S index 5018c7f..ebaf1e6 100644 --- a/arch/ia64/kernel/pal.S +++ b/arch/ia64/kernel/pal.S @@ -217,12 +217,7 @@ GLOBAL_ENTRY(ia64_pal_call_phys_stacked) .body ;; ld8 loc2 = [loc2] // loc2 <- entry point - mov out0 = in0 // first argument - mov out1 = in1 // copy arg2 - mov out2 = in2 // copy arg3 - mov out3 = in3 // copy arg3 - ;; - mov loc3 = psr // save psr + mov loc3 = psr // save psr ;; mov loc4=ar.rsc // save RSE configuration dep.z loc2=loc2,0,61 // convert pal entry point to physical @@ -236,18 +231,23 @@ GLOBAL_ENTRY(ia64_pal_call_phys_stacked) ;; andcm r16=loc3,r16 // removes bits to clear from psr br.call.sptk.many rp=ia64_switch_mode_phys -.ret6: + + mov out0 = in0 // first argument + mov out1 = in1 // copy arg2 + mov out2 = in2 // copy arg3 + mov out3 = in3 // copy arg3 mov loc5 = r19 mov loc6 = r20 + br.call.sptk.many rp=b7 // now make the call -.ret7: + mov ar.rsc=0 // put RSE in enforced lazy, LE mode mov r16=loc3 // r16= original psr mov r19=loc5 mov r20=loc6 br.call.sptk.many rp=ia64_switch_mode_virt // return to virtual mode -.ret8: mov psr.l = loc3 // restore init PSR + mov psr.l = loc3 // restore init PSR mov ar.pfs = loc1 mov rp = loc0 ;; diff --git a/arch/ia64/kernel/palinfo.c b/arch/ia64/kernel/palinfo.c index 859fb37..0b546e2 100644 --- a/arch/ia64/kernel/palinfo.c +++ b/arch/ia64/kernel/palinfo.c @@ -17,7 +17,6 @@ * 10/23/2001 S.Eranian updated pal_perf_mon_info bug fixes * 03/24/2004 Ashok Raj updated to work with CPU Hotplug */ -#include <linux/config.h> #include <linux/types.h> #include <linux/errno.h> #include <linux/init.h> @@ -567,29 +566,23 @@ version_info(char *page) pal_version_u_t min_ver, cur_ver; char *p = page; - /* The PAL_VERSION call is advertised as being able to support - * both physical and virtual mode calls. This seems to be a documentation - * bug rather than firmware bug. In fact, it does only support physical mode. - * So now the code reflects this fact and the pal_version() has been updated - * accordingly. - */ - if (ia64_pal_version(&min_ver, &cur_ver) != 0) return 0; + if (ia64_pal_version(&min_ver, &cur_ver) != 0) + return 0; p += sprintf(p, "PAL_vendor : 0x%02x (min=0x%02x)\n" - "PAL_A : %x.%x.%x (min=%x.%x.%x)\n" - "PAL_B : %x.%x.%x (min=%x.%x.%x)\n", - cur_ver.pal_version_s.pv_pal_vendor, min_ver.pal_version_s.pv_pal_vendor, - - cur_ver.pal_version_s.pv_pal_a_model>>4, - cur_ver.pal_version_s.pv_pal_a_model&0xf, cur_ver.pal_version_s.pv_pal_a_rev, - min_ver.pal_version_s.pv_pal_a_model>>4, - min_ver.pal_version_s.pv_pal_a_model&0xf, min_ver.pal_version_s.pv_pal_a_rev, - - cur_ver.pal_version_s.pv_pal_b_model>>4, - cur_ver.pal_version_s.pv_pal_b_model&0xf, cur_ver.pal_version_s.pv_pal_b_rev, - min_ver.pal_version_s.pv_pal_b_model>>4, - min_ver.pal_version_s.pv_pal_b_model&0xf, min_ver.pal_version_s.pv_pal_b_rev); + "PAL_A : %02x.%02x (min=%02x.%02x)\n" + "PAL_B : %02x.%02x (min=%02x.%02x)\n", + cur_ver.pal_version_s.pv_pal_vendor, + min_ver.pal_version_s.pv_pal_vendor, + cur_ver.pal_version_s.pv_pal_a_model, + cur_ver.pal_version_s.pv_pal_a_rev, + min_ver.pal_version_s.pv_pal_a_model, + min_ver.pal_version_s.pv_pal_a_rev, + cur_ver.pal_version_s.pv_pal_b_model, + cur_ver.pal_version_s.pv_pal_b_rev, + min_ver.pal_version_s.pv_pal_b_model, + min_ver.pal_version_s.pv_pal_b_rev); return p - page; } @@ -959,9 +952,9 @@ remove_palinfo_proc_entries(unsigned int hcpu) } } +#ifdef CONFIG_HOTPLUG_CPU static int palinfo_cpu_callback(struct notifier_block *nfb, - unsigned long action, - void *hcpu) + unsigned long action, void *hcpu) { unsigned int hotcpu = (unsigned long)hcpu; @@ -969,11 +962,9 @@ static int palinfo_cpu_callback(struct notifier_block *nfb, case CPU_ONLINE: create_palinfo_proc_entries(hotcpu); break; -#ifdef CONFIG_HOTPLUG_CPU case CPU_DEAD: remove_palinfo_proc_entries(hotcpu); break; -#endif } return NOTIFY_OK; } @@ -983,6 +974,7 @@ static struct notifier_block palinfo_cpu_notifier = .notifier_call = palinfo_cpu_callback, .priority = 0, }; +#endif static int __init palinfo_init(void) @@ -998,7 +990,7 @@ palinfo_init(void) } /* Register for future delivery via notify registration */ - register_cpu_notifier(&palinfo_cpu_notifier); + register_hotcpu_notifier(&palinfo_cpu_notifier); return 0; } @@ -1021,7 +1013,7 @@ palinfo_exit(void) /* * Unregister from cpu notifier callbacks */ - unregister_cpu_notifier(&palinfo_cpu_notifier); + unregister_hotcpu_notifier(&palinfo_cpu_notifier); } module_init(palinfo_init); diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index 077f212..84a7e52 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -19,7 +19,6 @@ * http://www.hpl.hp.com/research/linux/perfmon */ -#include <linux/config.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/sched.h> @@ -532,7 +531,6 @@ static ctl_table pfm_sysctl_root[] = { static struct ctl_table_header *pfm_sysctl_header; static int pfm_context_unload(pfm_context_t *ctx, void *arg, int count, struct pt_regs *regs); -static int pfm_flush(struct file *filp); #define pfm_get_cpu_var(v) __ia64_per_cpu_var(v) #define pfm_get_cpu_data(a,b) per_cpu(a, b) @@ -595,10 +593,11 @@ pfm_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, } -static struct super_block * -pfmfs_get_sb(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) +static int +pfmfs_get_sb(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, + struct vfsmount *mnt) { - return get_sb_pseudo(fs_type, "pfm:", NULL, PFMFS_MAGIC); + return get_sb_pseudo(fs_type, "pfm:", NULL, PFMFS_MAGIC, mnt); } static struct file_system_type pfm_fs_type = { @@ -1773,7 +1772,7 @@ pfm_syswide_cleanup_other_cpu(pfm_context_t *ctx) * When caller is self-monitoring, the context is unloaded. */ static int -pfm_flush(struct file *filp) +pfm_flush(struct file *filp, fl_owner_t id) { pfm_context_t *ctx; struct task_struct *task; @@ -4937,13 +4936,15 @@ abort_locked: if (likely(ctx)) { DPRINT(("context unlocked\n")); UNPROTECT_CTX(ctx, flags); - fput(file); } /* copy argument back to user, if needed */ if (call_made && PFM_CMD_RW_ARG(cmd) && copy_to_user(arg, args_k, base_sz*count)) ret = -EFAULT; error_args: + if (file) + fput(file); + kfree(args_k); DPRINT(("cmd=%s ret=%ld\n", PFM_CMD_NAME(cmd), ret)); @@ -6165,7 +6166,7 @@ pfm_load_regs (struct task_struct *task) /* * will replay the PMU interrupt */ - if (need_irq_resend) hw_resend_irq(NULL, IA64_PERFMON_VECTOR); + if (need_irq_resend) ia64_resend_irq(IA64_PERFMON_VECTOR); pfm_stats[smp_processor_id()].pfm_replay_ovfl_intr_count++; } @@ -6305,7 +6306,7 @@ pfm_load_regs (struct task_struct *task) /* * will replay the PMU interrupt */ - if (need_irq_resend) hw_resend_irq(NULL, IA64_PERFMON_VECTOR); + if (need_irq_resend) ia64_resend_irq(IA64_PERFMON_VECTOR); pfm_stats[smp_processor_id()].pfm_replay_ovfl_intr_count++; } @@ -6440,7 +6441,7 @@ pfm_flush_pmds(struct task_struct *task, pfm_context_t *ctx) static struct irqaction perfmon_irqaction = { .handler = pfm_interrupt_handler, - .flags = SA_INTERRUPT, + .flags = IRQF_DISABLED, .name = "perfmon" }; diff --git a/arch/ia64/kernel/perfmon_default_smpl.c b/arch/ia64/kernel/perfmon_default_smpl.c index 344941d..ff80eab 100644 --- a/arch/ia64/kernel/perfmon_default_smpl.c +++ b/arch/ia64/kernel/perfmon_default_smpl.c @@ -8,7 +8,6 @@ #include <linux/kernel.h> #include <linux/types.h> #include <linux/module.h> -#include <linux/config.h> #include <linux/init.h> #include <asm/delay.h> #include <linux/smp.h> diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index 355d579..ea914cc 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -9,7 +9,6 @@ * Add notify_die() hooks. */ #define __KERNEL_SYSCALLS__ /* see <asm/unistd.h> */ -#include <linux/config.h> #include <linux/cpu.h> #include <linux/pm.h> @@ -272,9 +271,9 @@ cpu_idle (void) /* endless idle loop with no priority at all */ while (1) { if (can_do_pal_halt) - clear_thread_flag(TIF_POLLING_NRFLAG); + current_thread_info()->status &= ~TS_POLLING; else - set_thread_flag(TIF_POLLING_NRFLAG); + current_thread_info()->status |= TS_POLLING; if (!need_resched()) { void (*idle)(void); diff --git a/arch/ia64/kernel/ptrace.c b/arch/ia64/kernel/ptrace.c index e61e15e..aa705e4 100644 --- a/arch/ia64/kernel/ptrace.c +++ b/arch/ia64/kernel/ptrace.c @@ -6,7 +6,6 @@ * * Derived from the x86 and Alpha versions. */ -#include <linux/config.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/slab.h> diff --git a/arch/ia64/kernel/sal.c b/arch/ia64/kernel/sal.c index 056f7a6..642fdc7 100644 --- a/arch/ia64/kernel/sal.c +++ b/arch/ia64/kernel/sal.c @@ -6,7 +6,6 @@ * Copyright (C) 1999 VA Linux Systems * Copyright (C) 1999 Walt Drummond <drummond@valinux.com> */ -#include <linux/config.h> #include <linux/kernel.h> #include <linux/init.h> @@ -227,7 +226,7 @@ static int sal_cache_flush_drops_interrupts; static void __init check_sal_cache_flush (void) { - unsigned long flags, itv; + unsigned long flags; int cpu; u64 vector; @@ -238,9 +237,6 @@ check_sal_cache_flush (void) * Schedule a timer interrupt, wait until it's reported, and see if * SAL_CACHE_FLUSH drops it. */ - itv = ia64_get_itv(); - BUG_ON((itv & (1 << 16)) == 0); - ia64_set_itv(IA64_TIMER_VECTOR); ia64_set_itm(ia64_get_itc() + 1000); @@ -260,7 +256,6 @@ check_sal_cache_flush (void) ia64_eoi(); } - ia64_set_itv(itv); local_irq_restore(flags); put_cpu(); } diff --git a/arch/ia64/kernel/salinfo.c b/arch/ia64/kernel/salinfo.c index 663a186..9065f0f 100644 --- a/arch/ia64/kernel/salinfo.c +++ b/arch/ia64/kernel/salinfo.c @@ -572,7 +572,7 @@ static struct file_operations salinfo_data_fops = { }; #ifdef CONFIG_HOTPLUG_CPU -static int +static int __devinit salinfo_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu) { unsigned int i, cpu = (unsigned long)hcpu; @@ -673,9 +673,7 @@ salinfo_init(void) salinfo_timer.function = &salinfo_timeout; add_timer(&salinfo_timer); -#ifdef CONFIG_HOTPLUG_CPU - register_cpu_notifier(&salinfo_cpu_notifier); -#endif + register_hotcpu_notifier(&salinfo_cpu_notifier); return 0; } diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index 3f7067c..84f93c0 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -22,7 +22,6 @@ * 06/24/99 W.Drummond added boot_cpu_data. * 05/28/05 Z. Menyhart Dynamic stride size for "flush_icache_range()" */ -#include <linux/config.h> #include <linux/module.h> #include <linux/init.h> @@ -36,7 +35,7 @@ #include <linux/seq_file.h> #include <linux/string.h> #include <linux/threads.h> -#include <linux/tty.h> +#include <linux/screen_info.h> #include <linux/dmi.h> #include <linux/serial.h> #include <linux/serial_core.h> @@ -260,6 +259,7 @@ reserve_memory (void) n++; num_rsvd_regions = n; + BUG_ON(IA64_MAX_RSVD_REGIONS + 1 < n); sort_regions(rsvd_region, num_rsvd_regions); } diff --git a/arch/ia64/kernel/signal.c b/arch/ia64/kernel/signal.c index 1d7903e..77f8b49 100644 --- a/arch/ia64/kernel/signal.c +++ b/arch/ia64/kernel/signal.c @@ -7,7 +7,6 @@ * Derived from i386 and Alpha versions. */ -#include <linux/config.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/mm.h> diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c index 44e9547..6203ed4 100644 --- a/arch/ia64/kernel/smpboot.c +++ b/arch/ia64/kernel/smpboot.c @@ -21,7 +21,6 @@ * 05/01/30 Suresh Siddha <suresh.b.siddha@intel.com> * Setup cpu_sibling_map and cpu_core_map */ -#include <linux/config.h> #include <linux/module.h> #include <linux/acpi.h> @@ -125,7 +124,7 @@ extern void __devinit calibrate_delay (void); extern void start_ap (void); extern unsigned long ia64_iobase; -task_t *task_for_booting_cpu; +struct task_struct *task_for_booting_cpu; /* * State for each CPU @@ -677,16 +676,16 @@ int migrate_platform_irqs(unsigned int cpu) new_cpei_cpu = any_online_cpu(cpu_online_map); mask = cpumask_of_cpu(new_cpei_cpu); set_cpei_target_cpu(new_cpei_cpu); - desc = irq_descp(ia64_cpe_irq); + desc = irq_desc + ia64_cpe_irq; /* * Switch for now, immediatly, we need to do fake intr * as other interrupts, but need to study CPEI behaviour with * polling before making changes. */ if (desc) { - desc->handler->disable(ia64_cpe_irq); - desc->handler->set_affinity(ia64_cpe_irq, mask); - desc->handler->enable(ia64_cpe_irq); + desc->chip->disable(ia64_cpe_irq); + desc->chip->set_affinity(ia64_cpe_irq, mask); + desc->chip->enable(ia64_cpe_irq); printk ("Re-targetting CPEI to cpu %d\n", new_cpei_cpu); } } diff --git a/arch/ia64/kernel/sys_ia64.c b/arch/ia64/kernel/sys_ia64.c index c7b943f..9ef62a3 100644 --- a/arch/ia64/kernel/sys_ia64.c +++ b/arch/ia64/kernel/sys_ia64.c @@ -5,7 +5,6 @@ * Copyright (C) 1999-2000, 2002-2003, 2005 Hewlett-Packard Co * David Mosberger-Tang <davidm@hpl.hp.com> */ -#include <linux/config.h> #include <linux/errno.h> #include <linux/fs.h> #include <linux/mm.h> @@ -164,10 +163,25 @@ sys_pipe (void) return retval; } +int ia64_mmap_check(unsigned long addr, unsigned long len, + unsigned long flags) +{ + unsigned long roff; + + /* + * Don't permit mappings into unmapped space, the virtual page table + * of a region, or across a region boundary. Note: RGN_MAP_LIMIT is + * equal to 2^n-PAGE_SIZE (for some integer n <= 61) and len > 0. + */ + roff = REGION_OFFSET(addr); + if ((len > RGN_MAP_LIMIT) || (roff > (RGN_MAP_LIMIT - len))) + return -EINVAL; + return 0; +} + static inline unsigned long do_mmap2 (unsigned long addr, unsigned long len, int prot, int flags, int fd, unsigned long pgoff) { - unsigned long roff; struct file *file = NULL; flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE); @@ -189,17 +203,6 @@ do_mmap2 (unsigned long addr, unsigned long len, int prot, int flags, int fd, un goto out; } - /* - * Don't permit mappings into unmapped space, the virtual page table of a region, - * or across a region boundary. Note: RGN_MAP_LIMIT is equal to 2^n-PAGE_SIZE - * (for some integer n <= 61) and len > 0. - */ - roff = REGION_OFFSET(addr); - if ((len > RGN_MAP_LIMIT) || (roff > (RGN_MAP_LIMIT - len))) { - addr = -EINVAL; - goto out; - } - down_write(¤t->mm->mmap_sem); addr = do_mmap_pgoff(file, addr, len, prot, flags, pgoff); up_write(¤t->mm->mmap_sem); diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c index 4995890..6928ef0 100644 --- a/arch/ia64/kernel/time.c +++ b/arch/ia64/kernel/time.c @@ -8,7 +8,6 @@ * Copyright (C) 1999-2000 VA Linux Systems * Copyright (C) 1999-2000 Walt Drummond <drummond@valinux.com> */ -#include <linux/config.h> #include <linux/cpu.h> #include <linux/init.h> @@ -232,7 +231,7 @@ ia64_init_itm (void) static struct irqaction timer_irqaction = { .handler = timer_interrupt, - .flags = SA_INTERRUPT, + .flags = IRQF_DISABLED, .name = "timer" }; diff --git a/arch/ia64/kernel/topology.c b/arch/ia64/kernel/topology.c index 4f3a16b..f648c61 100644 --- a/arch/ia64/kernel/topology.c +++ b/arch/ia64/kernel/topology.c @@ -13,7 +13,6 @@ * Populate cpu cache entries in sysfs for cpu cache info */ -#include <linux/config.h> #include <linux/cpu.h> #include <linux/kernel.h> #include <linux/mm.h> @@ -26,19 +25,10 @@ #include <asm/numa.h> #include <asm/cpu.h> -#ifdef CONFIG_NUMA -static struct node *sysfs_nodes; -#endif static struct ia64_cpu *sysfs_cpus; int arch_register_cpu(int num) { - struct node *parent = NULL; - -#ifdef CONFIG_NUMA - parent = &sysfs_nodes[cpu_to_node(num)]; -#endif /* CONFIG_NUMA */ - #if defined (CONFIG_ACPI) && defined (CONFIG_HOTPLUG_CPU) /* * If CPEI cannot be re-targetted, and this is @@ -48,21 +38,14 @@ int arch_register_cpu(int num) sysfs_cpus[num].cpu.no_control = 1; #endif - return register_cpu(&sysfs_cpus[num].cpu, num, parent); + return register_cpu(&sysfs_cpus[num].cpu, num); } #ifdef CONFIG_HOTPLUG_CPU void arch_unregister_cpu(int num) { - struct node *parent = NULL; - -#ifdef CONFIG_NUMA - int node = cpu_to_node(num); - parent = &sysfs_nodes[node]; -#endif /* CONFIG_NUMA */ - - return unregister_cpu(&sysfs_cpus[num].cpu, parent); + return unregister_cpu(&sysfs_cpus[num].cpu); } EXPORT_SYMBOL(arch_register_cpu); EXPORT_SYMBOL(arch_unregister_cpu); @@ -74,26 +57,18 @@ static int __init topology_init(void) int i, err = 0; #ifdef CONFIG_NUMA - sysfs_nodes = kzalloc(sizeof(struct node) * MAX_NUMNODES, GFP_KERNEL); - if (!sysfs_nodes) { - err = -ENOMEM; - goto out; - } - /* * MCD - Do we want to register all ONLINE nodes, or all POSSIBLE nodes? */ for_each_online_node(i) { - if ((err = register_node(&sysfs_nodes[i], i, 0))) + if ((err = register_one_node(i))) goto out; } #endif sysfs_cpus = kzalloc(sizeof(struct ia64_cpu) * NR_CPUS, GFP_KERNEL); - if (!sysfs_cpus) { - err = -ENOMEM; - goto out; - } + if (!sysfs_cpus) + panic("kzalloc in topology_init failed - NR_CPUS too big?"); for_each_present_cpu(i) { if((err = arch_register_cpu(i))) @@ -166,7 +141,7 @@ static void cache_shared_cpu_map_setup( unsigned int cpu, num_shared = (int) csi.num_shared; do { - for_each_cpu(j) + for_each_possible_cpu(j) if (cpu_data(cpu)->socket_id == cpu_data(j)->socket_id && cpu_data(j)->core_id == csi.log1_cid && cpu_data(j)->thread_id == csi.log1_tid) @@ -426,7 +401,7 @@ static int __cpuinit cache_remove_dev(struct sys_device * sys_dev) * When a cpu is hot-plugged, do a check and initiate * cache kobject if necessary */ -static int cache_cpu_callback(struct notifier_block *nfb, +static int __cpuinit cache_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { unsigned int cpu = (unsigned long)hcpu; @@ -444,7 +419,7 @@ static int cache_cpu_callback(struct notifier_block *nfb, return NOTIFY_OK; } -static struct notifier_block cache_cpu_notifier = +static struct notifier_block __cpuinitdata cache_cpu_notifier = { .notifier_call = cache_cpu_callback }; @@ -458,7 +433,7 @@ static int __cpuinit cache_sysfs_init(void) (void *)(long)i); } - register_cpu_notifier(&cache_cpu_notifier); + register_hotcpu_notifier(&cache_cpu_notifier); return 0; } diff --git a/arch/ia64/kernel/traps.c b/arch/ia64/kernel/traps.c index 7c1ddc8..fffa9e0 100644 --- a/arch/ia64/kernel/traps.c +++ b/arch/ia64/kernel/traps.c @@ -7,7 +7,6 @@ * 05/12/00 grao <goutham.rao@intel.com> : added isr in siginfo for SIGFPE */ -#include <linux/config.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/sched.h> @@ -118,11 +117,8 @@ die (const char *str, struct pt_regs *regs, long err) die.lock_owner = -1; spin_unlock_irq(&die.lock); - if (panic_on_oops) { - printk(KERN_EMERG "Fatal exception: panic in 5 seconds\n"); - ssleep(5); + if (panic_on_oops) panic("Fatal exception"); - } do_exit(SIGSEGV); } diff --git a/arch/ia64/kernel/uncached.c b/arch/ia64/kernel/uncached.c index fcd2bad..4c73a67 100644 --- a/arch/ia64/kernel/uncached.c +++ b/arch/ia64/kernel/uncached.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2001-2005 Silicon Graphics, Inc. All rights reserved. + * Copyright (C) 2001-2006 Silicon Graphics, Inc. All rights reserved. * * This program is free software; you can redistribute it and/or modify it * under the terms of version 2 of the GNU General Public License @@ -29,68 +29,86 @@ #include <asm/tlbflush.h> #include <asm/sn/arch.h> -#define DEBUG 0 -#if DEBUG -#define dprintk printk -#else -#define dprintk(x...) do { } while (0) -#endif +extern void __init efi_memmap_walk_uc(efi_freemem_callback_t, void *); -void __init efi_memmap_walk_uc (efi_freemem_callback_t callback); +struct uncached_pool { + struct gen_pool *pool; + struct mutex add_chunk_mutex; /* serialize adding a converted chunk */ + int nchunks_added; /* #of converted chunks added to pool */ + atomic_t status; /* smp called function's return status*/ +}; -#define MAX_UNCACHED_GRANULES 5 -static int allocated_granules; +#define MAX_CONVERTED_CHUNKS_PER_NODE 2 -struct gen_pool *uncached_pool[MAX_NUMNODES]; +struct uncached_pool uncached_pools[MAX_NUMNODES]; static void uncached_ipi_visibility(void *data) { int status; + struct uncached_pool *uc_pool = (struct uncached_pool *)data; status = ia64_pal_prefetch_visibility(PAL_VISIBILITY_PHYSICAL); if ((status != PAL_VISIBILITY_OK) && (status != PAL_VISIBILITY_OK_REMOTE_NEEDED)) - printk(KERN_DEBUG "pal_prefetch_visibility() returns %i on " - "CPU %i\n", status, raw_smp_processor_id()); + atomic_inc(&uc_pool->status); } static void uncached_ipi_mc_drain(void *data) { int status; + struct uncached_pool *uc_pool = (struct uncached_pool *)data; + status = ia64_pal_mc_drain(); - if (status) - printk(KERN_WARNING "ia64_pal_mc_drain() failed with %i on " - "CPU %i\n", status, raw_smp_processor_id()); + if (status != PAL_STATUS_SUCCESS) + atomic_inc(&uc_pool->status); } -static unsigned long -uncached_get_new_chunk(struct gen_pool *poolp) +/* + * Add a new chunk of uncached memory pages to the specified pool. + * + * @pool: pool to add new chunk of uncached memory to + * @nid: node id of node to allocate memory from, or -1 + * + * This is accomplished by first allocating a granule of cached memory pages + * and then converting them to uncached memory pages. + */ +static int uncached_add_chunk(struct uncached_pool *uc_pool, int nid) { struct page *page; - void *tmp; - int status, i; - unsigned long addr, node; + int status, i, nchunks_added = uc_pool->nchunks_added; + unsigned long c_addr, uc_addr; - if (allocated_granules >= MAX_UNCACHED_GRANULES) + if (mutex_lock_interruptible(&uc_pool->add_chunk_mutex) != 0) + return -1; /* interrupted by a signal */ + + if (uc_pool->nchunks_added > nchunks_added) { + /* someone added a new chunk while we were waiting */ + mutex_unlock(&uc_pool->add_chunk_mutex); return 0; + } + + if (uc_pool->nchunks_added >= MAX_CONVERTED_CHUNKS_PER_NODE) { + mutex_unlock(&uc_pool->add_chunk_mutex); + return -1; + } + + /* attempt to allocate a granule's worth of cached memory pages */ - node = poolp->private; - page = alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, + page = alloc_pages_node(nid, GFP_KERNEL | __GFP_ZERO, IA64_GRANULE_SHIFT-PAGE_SHIFT); + if (!page) { + mutex_unlock(&uc_pool->add_chunk_mutex); + return -1; + } - dprintk(KERN_INFO "get_new_chunk page %p, addr %lx\n", - page, (unsigned long)(page-vmem_map) << PAGE_SHIFT); + /* convert the memory pages from cached to uncached */ - /* - * Do magic if no mem on local node! XXX - */ - if (!page) - return 0; - tmp = page_address(page); + c_addr = (unsigned long)page_address(page); + uc_addr = c_addr - PAGE_OFFSET + __IA64_UNCACHED_OFFSET; /* * There's a small race here where it's possible for someone to @@ -100,76 +118,98 @@ uncached_get_new_chunk(struct gen_pool *poolp) for (i = 0; i < (IA64_GRANULE_SIZE / PAGE_SIZE); i++) SetPageUncached(&page[i]); - flush_tlb_kernel_range(tmp, tmp + IA64_GRANULE_SIZE); + flush_tlb_kernel_range(uc_addr, uc_adddr + IA64_GRANULE_SIZE); status = ia64_pal_prefetch_visibility(PAL_VISIBILITY_PHYSICAL); + if (status == PAL_VISIBILITY_OK_REMOTE_NEEDED) { + atomic_set(&uc_pool->status, 0); + status = smp_call_function(uncached_ipi_visibility, uc_pool, + 0, 1); + if (status || atomic_read(&uc_pool->status)) + goto failed; + } else if (status != PAL_VISIBILITY_OK) + goto failed; - dprintk(KERN_INFO "pal_prefetch_visibility() returns %i on cpu %i\n", - status, raw_smp_processor_id()); - - if (!status) { - status = smp_call_function(uncached_ipi_visibility, NULL, 0, 1); - if (status) - printk(KERN_WARNING "smp_call_function failed for " - "uncached_ipi_visibility! (%i)\n", status); - } + preempt_disable(); if (ia64_platform_is("sn2")) - sn_flush_all_caches((unsigned long)tmp, IA64_GRANULE_SIZE); + sn_flush_all_caches(uc_addr, IA64_GRANULE_SIZE); else - flush_icache_range((unsigned long)tmp, - (unsigned long)tmp+IA64_GRANULE_SIZE); + flush_icache_range(uc_addr, uc_addr + IA64_GRANULE_SIZE); - ia64_pal_mc_drain(); - status = smp_call_function(uncached_ipi_mc_drain, NULL, 0, 1); + /* flush the just introduced uncached translation from the TLB */ + local_flush_tlb_all(); + + preempt_enable(); + + status = ia64_pal_mc_drain(); + if (status != PAL_STATUS_SUCCESS) + goto failed; + atomic_set(&uc_pool->status, 0); + status = smp_call_function(uncached_ipi_mc_drain, uc_pool, 0, 1); + if (status || atomic_read(&uc_pool->status)) + goto failed; + + /* + * The chunk of memory pages has been converted to uncached so now we + * can add it to the pool. + */ + status = gen_pool_add(uc_pool->pool, uc_addr, IA64_GRANULE_SIZE, nid); if (status) - printk(KERN_WARNING "smp_call_function failed for " - "uncached_ipi_mc_drain! (%i)\n", status); + goto failed; + + uc_pool->nchunks_added++; + mutex_unlock(&uc_pool->add_chunk_mutex); + return 0; - addr = (unsigned long)tmp - PAGE_OFFSET + __IA64_UNCACHED_OFFSET; + /* failed to convert or add the chunk so give it back to the kernel */ +failed: + for (i = 0; i < (IA64_GRANULE_SIZE / PAGE_SIZE); i++) + ClearPageUncached(&page[i]); - allocated_granules++; - return addr; + free_pages(c_addr, IA64_GRANULE_SHIFT-PAGE_SHIFT); + mutex_unlock(&uc_pool->add_chunk_mutex); + return -1; } /* * uncached_alloc_page * + * @starting_nid: node id of node to start with, or -1 + * * Allocate 1 uncached page. Allocates on the requested node. If no * uncached pages are available on the requested node, roundrobin starting - * with higher nodes. + * with the next higher node. */ -unsigned long -uncached_alloc_page(int nid) +unsigned long uncached_alloc_page(int starting_nid) { - unsigned long maddr; + unsigned long uc_addr; + struct uncached_pool *uc_pool; + int nid; - maddr = gen_pool_alloc(uncached_pool[nid], PAGE_SIZE); + if (unlikely(starting_nid >= MAX_NUMNODES)) + return 0; - dprintk(KERN_DEBUG "uncached_alloc_page returns %lx on node %i\n", - maddr, nid); + if (starting_nid < 0) + starting_nid = numa_node_id(); + nid = starting_nid; - /* - * If no memory is availble on our local node, try the - * remaining nodes in the system. - */ - if (!maddr) { - int i; - - for (i = MAX_NUMNODES - 1; i >= 0; i--) { - if (i == nid || !node_online(i)) - continue; - maddr = gen_pool_alloc(uncached_pool[i], PAGE_SIZE); - dprintk(KERN_DEBUG "uncached_alloc_page alternate search " - "returns %lx on node %i\n", maddr, i); - if (maddr) { - break; - } - } - } + do { + if (!node_online(nid)) + continue; + uc_pool = &uncached_pools[nid]; + if (uc_pool->pool == NULL) + continue; + do { + uc_addr = gen_pool_alloc(uc_pool->pool, PAGE_SIZE); + if (uc_addr != 0) + return uc_addr; + } while (uncached_add_chunk(uc_pool, nid) == 0); - return maddr; + } while ((nid = (nid + 1) % MAX_NUMNODES) != starting_nid); + + return 0; } EXPORT_SYMBOL(uncached_alloc_page); @@ -177,21 +217,22 @@ EXPORT_SYMBOL(uncached_alloc_page); /* * uncached_free_page * + * @uc_addr: uncached address of page to free + * * Free a single uncached page. */ -void -uncached_free_page(unsigned long maddr) +void uncached_free_page(unsigned long uc_addr) { - int node; + int nid = paddr_to_nid(uc_addr - __IA64_UNCACHED_OFFSET); + struct gen_pool *pool = uncached_pools[nid].pool; - node = paddr_to_nid(maddr - __IA64_UNCACHED_OFFSET); + if (unlikely(pool == NULL)) + return; - dprintk(KERN_DEBUG "uncached_free_page(%lx) on node %i\n", maddr, node); + if ((uc_addr & (0XFUL << 60)) != __IA64_UNCACHED_OFFSET) + panic("uncached_free_page invalid address %lx\n", uc_addr); - if ((maddr & (0XFUL << 60)) != __IA64_UNCACHED_OFFSET) - panic("uncached_free_page invalid address %lx\n", maddr); - - gen_pool_free(uncached_pool[node], maddr, PAGE_SIZE); + gen_pool_free(pool, uc_addr, PAGE_SIZE); } EXPORT_SYMBOL(uncached_free_page); @@ -199,43 +240,40 @@ EXPORT_SYMBOL(uncached_free_page); /* * uncached_build_memmap, * + * @uc_start: uncached starting address of a chunk of uncached memory + * @uc_end: uncached ending address of a chunk of uncached memory + * @arg: ignored, (NULL argument passed in on call to efi_memmap_walk_uc()) + * * Called at boot time to build a map of pages that can be used for * memory special operations. */ -static int __init -uncached_build_memmap(unsigned long start, unsigned long end, void *arg) +static int __init uncached_build_memmap(unsigned long uc_start, + unsigned long uc_end, void *arg) { - long length = end - start; - int node; - - dprintk(KERN_ERR "uncached_build_memmap(%lx %lx)\n", start, end); + int nid = paddr_to_nid(uc_start - __IA64_UNCACHED_OFFSET); + struct gen_pool *pool = uncached_pools[nid].pool; + size_t size = uc_end - uc_start; touch_softlockup_watchdog(); - memset((char *)start, 0, length); - node = paddr_to_nid(start - __IA64_UNCACHED_OFFSET); - - for (; start < end ; start += PAGE_SIZE) { - dprintk(KERN_INFO "sticking %lx into the pool!\n", start); - gen_pool_free(uncached_pool[node], start, PAGE_SIZE); + if (pool != NULL) { + memset((char *)uc_start, 0, size); + (void) gen_pool_add(pool, uc_start, size, nid); } - return 0; } -static int __init uncached_init(void) { - int i; +static int __init uncached_init(void) +{ + int nid; - for (i = 0; i < MAX_NUMNODES; i++) { - if (!node_online(i)) - continue; - uncached_pool[i] = gen_pool_create(0, IA64_GRANULE_SHIFT, - &uncached_get_new_chunk, i); + for_each_online_node(nid) { + uncached_pools[nid].pool = gen_pool_create(PAGE_SHIFT, nid); + mutex_init(&uncached_pools[nid].add_chunk_mutex); } - efi_memmap_walk_uc(uncached_build_memmap); - + efi_memmap_walk_uc(uncached_build_memmap, NULL); return 0; } diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S index 783600f..5b0d5f6 100644 --- a/arch/ia64/kernel/vmlinux.lds.S +++ b/arch/ia64/kernel/vmlinux.lds.S @@ -1,4 +1,3 @@ -#include <linux/config.h> #include <asm/cache.h> #include <asm/ptrace.h> diff --git a/arch/ia64/lib/Makefile b/arch/ia64/lib/Makefile index d8536a2..38fa6e4 100644 --- a/arch/ia64/lib/Makefile +++ b/arch/ia64/lib/Makefile @@ -14,7 +14,7 @@ lib-y := __divsi3.o __udivsi3.o __modsi3.o __umodsi3.o \ lib-$(CONFIG_ITANIUM) += copy_page.o copy_user.o memcpy.o lib-$(CONFIG_MCKINLEY) += copy_page_mck.o memcpy_mck.o lib-$(CONFIG_PERFMON) += carta_random.o -lib-$(CONFIG_MD_RAID5) += xor.o +lib-$(CONFIG_MD_RAID456) += xor.o AFLAGS___divdi3.o = AFLAGS___udivdi3.o = -DUNSIGNED diff --git a/arch/ia64/lib/clear_page.S b/arch/ia64/lib/clear_page.S index d498706..2d814e7 100644 --- a/arch/ia64/lib/clear_page.S +++ b/arch/ia64/lib/clear_page.S @@ -8,7 +8,6 @@ * 2/12/02 kchen Tuned for both Itanium and McKinley * 3/08/02 davidm Some more tweaking */ -#include <linux/config.h> #include <asm/asmmacro.h> #include <asm/page.h> diff --git a/arch/ia64/lib/io.c b/arch/ia64/lib/io.c index 8949e44..bcd16f8a 100644 --- a/arch/ia64/lib/io.c +++ b/arch/ia64/lib/io.c @@ -1,4 +1,3 @@ -#include <linux/config.h> #include <linux/module.h> #include <linux/types.h> diff --git a/arch/ia64/lib/memcpy_mck.S b/arch/ia64/lib/memcpy_mck.S index 9e534d5..ab0f876 100644 --- a/arch/ia64/lib/memcpy_mck.S +++ b/arch/ia64/lib/memcpy_mck.S @@ -13,7 +13,6 @@ * Copyright (C) 2002 Intel Corp. * Copyright (C) 2002 Ken Chen <kenneth.w.chen@intel.com> */ -#include <linux/config.h> #include <asm/asmmacro.h> #include <asm/page.h> diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c index 84fd1c1..e004143 100644 --- a/arch/ia64/mm/contig.c +++ b/arch/ia64/mm/contig.c @@ -14,7 +14,6 @@ * Routines used by ia64 machines with contiguous (or virtually contiguous) * memory. */ -#include <linux/config.h> #include <linux/bootmem.h> #include <linux/efi.h> #include <linux/mm.h> @@ -28,6 +27,7 @@ #ifdef CONFIG_VIRTUAL_MEM_MAP static unsigned long num_dma_physpages; +static unsigned long max_gap; #endif /** @@ -46,9 +46,15 @@ show_mem (void) printk("Free swap: %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10)); i = max_mapnr; - while (i-- > 0) { - if (!pfn_valid(i)) + for (i = 0; i < max_mapnr; i++) { + if (!pfn_valid(i)) { +#ifdef CONFIG_VIRTUAL_MEM_MAP + if (max_gap < LARGE_GAP) + continue; + i = vmemmap_find_next_valid_pfn(0, i) - 1; +#endif continue; + } total++; if (PageReserved(mem_map+i)) reserved++; @@ -235,7 +241,6 @@ paging_init (void) unsigned long zones_size[MAX_NR_ZONES]; #ifdef CONFIG_VIRTUAL_MEM_MAP unsigned long zholes_size[MAX_NR_ZONES]; - unsigned long max_gap; #endif /* initialize mem_map[] */ @@ -267,7 +272,6 @@ paging_init (void) } } - max_gap = 0; efi_memmap_walk(find_largest_hole, (u64 *)&max_gap); if (max_gap < LARGE_GAP) { vmem_map = (struct page *) 0; @@ -278,7 +282,8 @@ paging_init (void) /* allocate virtual_mem_map */ - map_size = PAGE_ALIGN(max_low_pfn * sizeof(struct page)); + map_size = PAGE_ALIGN(ALIGN(max_low_pfn, MAX_ORDER_NR_PAGES) * + sizeof(struct page)); vmalloc_end -= map_size; vmem_map = (struct page *) vmalloc_end; efi_memmap_walk(create_mem_map_page_table, NULL); diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c index b6bcc9f..d260bff 100644 --- a/arch/ia64/mm/discontig.c +++ b/arch/ia64/mm/discontig.c @@ -33,7 +33,6 @@ */ struct early_node_data { struct ia64_node_data *node_data; - pg_data_t *pgdat; unsigned long pernode_addr; unsigned long pernode_size; struct bootmem_data bootmem_data; @@ -46,6 +45,8 @@ struct early_node_data { static struct early_node_data mem_data[MAX_NUMNODES] __initdata; static nodemask_t memory_less_mask __initdata; +static pg_data_t *pgdat_list[MAX_NUMNODES]; + /* * To prevent cache aliasing effects, align per-node structures so that they * start at addresses that are strided by node number. @@ -99,7 +100,7 @@ static int __init build_node_maps(unsigned long start, unsigned long len, * acpi_boot_init() (which builds the node_to_cpu_mask array) hasn't been * called yet. Note that node 0 will also count all non-existent cpus. */ -static int __init early_nr_cpus_node(int node) +static int __meminit early_nr_cpus_node(int node) { int cpu, n = 0; @@ -114,7 +115,7 @@ static int __init early_nr_cpus_node(int node) * compute_pernodesize - compute size of pernode data * @node: the node id. */ -static unsigned long __init compute_pernodesize(int node) +static unsigned long __meminit compute_pernodesize(int node) { unsigned long pernodesize = 0, cpus; @@ -175,13 +176,13 @@ static void __init fill_pernode(int node, unsigned long pernode, pernode += PERCPU_PAGE_SIZE * cpus; pernode += node * L1_CACHE_BYTES; - mem_data[node].pgdat = __va(pernode); + pgdat_list[node] = __va(pernode); pernode += L1_CACHE_ALIGN(sizeof(pg_data_t)); mem_data[node].node_data = __va(pernode); pernode += L1_CACHE_ALIGN(sizeof(struct ia64_node_data)); - mem_data[node].pgdat->bdata = bdp; + pgdat_list[node]->bdata = bdp; pernode += L1_CACHE_ALIGN(sizeof(pg_data_t)); cpu_data = per_cpu_node_setup(cpu_data, node); @@ -268,7 +269,7 @@ static int __init find_pernode_space(unsigned long start, unsigned long len, static int __init free_node_bootmem(unsigned long start, unsigned long len, int node) { - free_bootmem_node(mem_data[node].pgdat, start, len); + free_bootmem_node(pgdat_list[node], start, len); return 0; } @@ -287,7 +288,7 @@ static void __init reserve_pernode_space(void) int node; for_each_online_node(node) { - pg_data_t *pdp = mem_data[node].pgdat; + pg_data_t *pdp = pgdat_list[node]; if (node_isset(node, memory_less_mask)) continue; @@ -307,6 +308,27 @@ static void __init reserve_pernode_space(void) } } +static void __meminit scatter_node_data(void) +{ + pg_data_t **dst; + int node; + + /* + * for_each_online_node() can't be used at here. + * node_online_map is not set for hot-added nodes at this time, + * because we are halfway through initialization of the new node's + * structures. If for_each_online_node() is used, a new node's + * pg_data_ptrs will be not initialized. Insted of using it, + * pgdat_list[] is checked. + */ + for_each_node(node) { + if (pgdat_list[node]) { + dst = LOCAL_DATA_ADDR(pgdat_list[node])->pg_data_ptrs; + memcpy(dst, pgdat_list, sizeof(pgdat_list)); + } + } +} + /** * initialize_pernode_data - fixup per-cpu & per-node pointers * @@ -317,17 +339,10 @@ static void __init reserve_pernode_space(void) */ static void __init initialize_pernode_data(void) { - pg_data_t *pgdat_list[MAX_NUMNODES]; int cpu, node; - for_each_online_node(node) - pgdat_list[node] = mem_data[node].pgdat; + scatter_node_data(); - /* Copy the pg_data_t list to each node and init the node field */ - for_each_online_node(node) { - memcpy(mem_data[node].node_data->pg_data_ptrs, pgdat_list, - sizeof(pgdat_list)); - } #ifdef CONFIG_SMP /* Set the node_data pointer for each per-cpu struct */ for (cpu = 0; cpu < NR_CPUS; cpu++) { @@ -372,7 +387,7 @@ static void __init *memory_less_node_alloc(int nid, unsigned long pernodesize) if (bestnode == -1) bestnode = anynode; - ptr = __alloc_bootmem_node(mem_data[bestnode].pgdat, pernodesize, + ptr = __alloc_bootmem_node(pgdat_list[bestnode], pernodesize, PERCPU_PAGE_SIZE, __pa(MAX_DMA_ADDRESS)); return ptr; @@ -476,7 +491,7 @@ void __init find_memory(void) pernodesize = mem_data[node].pernode_size; map = pernode + pernodesize; - init_bootmem_node(mem_data[node].pgdat, + init_bootmem_node(pgdat_list[node], map>>PAGE_SHIFT, bdp->node_boot_start>>PAGE_SHIFT, bdp->node_low_pfn); @@ -519,68 +534,6 @@ void __cpuinit *per_cpu_init(void) } #endif /* CONFIG_SMP */ -#ifdef CONFIG_VIRTUAL_MEM_MAP -static inline int find_next_valid_pfn_for_pgdat(pg_data_t *pgdat, int i) -{ - unsigned long end_address, hole_next_pfn; - unsigned long stop_address; - - end_address = (unsigned long) &vmem_map[pgdat->node_start_pfn + i]; - end_address = PAGE_ALIGN(end_address); - - stop_address = (unsigned long) &vmem_map[ - pgdat->node_start_pfn + pgdat->node_spanned_pages]; - - do { - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - - pgd = pgd_offset_k(end_address); - if (pgd_none(*pgd)) { - end_address += PGDIR_SIZE; - continue; - } - - pud = pud_offset(pgd, end_address); - if (pud_none(*pud)) { - end_address += PUD_SIZE; - continue; - } - - pmd = pmd_offset(pud, end_address); - if (pmd_none(*pmd)) { - end_address += PMD_SIZE; - continue; - } - - pte = pte_offset_kernel(pmd, end_address); -retry_pte: - if (pte_none(*pte)) { - end_address += PAGE_SIZE; - pte++; - if ((end_address < stop_address) && - (end_address != ALIGN(end_address, 1UL << PMD_SHIFT))) - goto retry_pte; - continue; - } - /* Found next valid vmem_map page */ - break; - } while (end_address < stop_address); - - end_address = min(end_address, stop_address); - end_address = end_address - (unsigned long) vmem_map + sizeof(struct page) - 1; - hole_next_pfn = end_address / sizeof(struct page); - return hole_next_pfn - pgdat->node_start_pfn; -} -#else -static inline int find_next_valid_pfn_for_pgdat(pg_data_t *pgdat, int i) -{ - return i + 1; -} -#endif - /** * show_mem - give short summary of memory stats * @@ -610,7 +563,8 @@ void show_mem(void) if (pfn_valid(pgdat->node_start_pfn + i)) page = pfn_to_page(pgdat->node_start_pfn + i); else { - i = find_next_valid_pfn_for_pgdat(pgdat, i) - 1; + i = vmemmap_find_next_valid_pfn(pgdat->node_id, + i) - 1; continue; } if (PageReserved(page)) @@ -736,7 +690,8 @@ void __init paging_init(void) efi_memmap_walk(filter_rsvd_memory, count_node_pages); #ifdef CONFIG_VIRTUAL_MEM_MAP - vmalloc_end -= PAGE_ALIGN(max_low_pfn * sizeof(struct page)); + vmalloc_end -= PAGE_ALIGN(ALIGN(max_low_pfn, MAX_ORDER_NR_PAGES) * + sizeof(struct page)); vmem_map = (struct page *) vmalloc_end; efi_memmap_walk(create_mem_map_page_table, NULL); printk("Virtual mem_map starts at 0x%p\n", vmem_map); @@ -786,3 +741,21 @@ void __init paging_init(void) zero_page_memmap_ptr = virt_to_page(ia64_imva(empty_zero_page)); } + +pg_data_t *arch_alloc_nodedata(int nid) +{ + unsigned long size = compute_pernodesize(nid); + + return kzalloc(size, GFP_KERNEL); +} + +void arch_free_nodedata(pg_data_t *pgdat) +{ + kfree(pgdat); +} + +void arch_refresh_nodedata(int update_node, pg_data_t *update_pgdat) +{ + pgdat_list[update_node] = update_pgdat; + scatter_node_data(); +} diff --git a/arch/ia64/mm/extable.c b/arch/ia64/mm/extable.c index 6d259e3..71c50dd 100644 --- a/arch/ia64/mm/extable.c +++ b/arch/ia64/mm/extable.c @@ -5,7 +5,6 @@ * David Mosberger-Tang <davidm@hpl.hp.com> */ -#include <linux/config.h> #include <linux/sort.h> #include <asm/uaccess.h> diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index d98ec49..14ef7cc 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -19,6 +19,40 @@ extern void die (char *, struct pt_regs *, long); +#ifdef CONFIG_KPROBES +ATOMIC_NOTIFIER_HEAD(notify_page_fault_chain); + +/* Hook to register for page fault notifications */ +int register_page_fault_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_register(¬ify_page_fault_chain, nb); +} + +int unregister_page_fault_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister(¬ify_page_fault_chain, nb); +} + +static inline int notify_page_fault(enum die_val val, const char *str, + struct pt_regs *regs, long err, int trap, int sig) +{ + struct die_args args = { + .regs = regs, + .str = str, + .err = err, + .trapnr = trap, + .signr = sig + }; + return atomic_notifier_call_chain(¬ify_page_fault_chain, val, &args); +} +#else +static inline int notify_page_fault(enum die_val val, const char *str, + struct pt_regs *regs, long err, int trap, int sig) +{ + return NOTIFY_DONE; +} +#endif + /* * Return TRUE if ADDRESS points at a page in the kernel's mapped segment * (inside region 5, on ia64) and that page is present. @@ -84,7 +118,7 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re /* * This is to handle the kprobes on user space access instructions */ - if (notify_die(DIE_PAGE_FAULT, "page fault", regs, code, TRAP_BRKPT, + if (notify_page_fault(DIE_PAGE_FAULT, "page fault", regs, code, TRAP_BRKPT, SIGSEGV) == NOTIFY_STOP) return; diff --git a/arch/ia64/mm/hugetlbpage.c b/arch/ia64/mm/hugetlbpage.c index 8d50671..eee5c1cf 100644 --- a/arch/ia64/mm/hugetlbpage.c +++ b/arch/ia64/mm/hugetlbpage.c @@ -8,7 +8,6 @@ * Feb, 2004: dynamic hugetlb page size via boot parameter */ -#include <linux/config.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/mm.h> diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index cafa877..30617cc 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -4,7 +4,6 @@ * Copyright (C) 1998-2003 Hewlett-Packard Co * David Mosberger-Tang <davidm@hpl.hp.com> */ -#include <linux/config.h> #include <linux/kernel.h> #include <linux/init.h> @@ -416,6 +415,61 @@ ia64_mmu_init (void *my_cpu_data) } #ifdef CONFIG_VIRTUAL_MEM_MAP +int vmemmap_find_next_valid_pfn(int node, int i) +{ + unsigned long end_address, hole_next_pfn; + unsigned long stop_address; + pg_data_t *pgdat = NODE_DATA(node); + + end_address = (unsigned long) &vmem_map[pgdat->node_start_pfn + i]; + end_address = PAGE_ALIGN(end_address); + + stop_address = (unsigned long) &vmem_map[ + pgdat->node_start_pfn + pgdat->node_spanned_pages]; + + do { + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + pgd = pgd_offset_k(end_address); + if (pgd_none(*pgd)) { + end_address += PGDIR_SIZE; + continue; + } + + pud = pud_offset(pgd, end_address); + if (pud_none(*pud)) { + end_address += PUD_SIZE; + continue; + } + + pmd = pmd_offset(pud, end_address); + if (pmd_none(*pmd)) { + end_address += PMD_SIZE; + continue; + } + + pte = pte_offset_kernel(pmd, end_address); +retry_pte: + if (pte_none(*pte)) { + end_address += PAGE_SIZE; + pte++; + if ((end_address < stop_address) && + (end_address != ALIGN(end_address, 1UL << PMD_SHIFT))) + goto retry_pte; + continue; + } + /* Found next valid vmem_map page */ + break; + } while (end_address < stop_address); + + end_address = min(end_address, stop_address); + end_address = end_address - (unsigned long) vmem_map + sizeof(struct page) - 1; + hole_next_pfn = end_address / sizeof(struct page); + return hole_next_pfn - pgdat->node_start_pfn; +} int __init create_mem_map_page_table (u64 start, u64 end, void *arg) @@ -652,7 +706,7 @@ void online_page(struct page *page) num_physpages++; } -int add_memory(u64 start, u64 size) +int arch_add_memory(int nid, u64 start, u64 size) { pg_data_t *pgdat; struct zone *zone; @@ -660,7 +714,7 @@ int add_memory(u64 start, u64 size) unsigned long nr_pages = size >> PAGE_SHIFT; int ret; - pgdat = NODE_DATA(0); + pgdat = NODE_DATA(nid); zone = pgdat->node_zones + ZONE_NORMAL; ret = __add_pages(zone, start_pfn, nr_pages); @@ -676,4 +730,5 @@ int remove_memory(u64 start, u64 size) { return -EINVAL; } +EXPORT_SYMBOL_GPL(remove_memory); #endif diff --git a/arch/ia64/mm/ioremap.c b/arch/ia64/mm/ioremap.c index 643ccc6..4280c07 100644 --- a/arch/ia64/mm/ioremap.c +++ b/arch/ia64/mm/ioremap.c @@ -11,6 +11,7 @@ #include <linux/module.h> #include <linux/efi.h> #include <asm/io.h> +#include <asm/meminit.h> static inline void __iomem * __ioremap (unsigned long offset, unsigned long size) @@ -21,16 +22,29 @@ __ioremap (unsigned long offset, unsigned long size) void __iomem * ioremap (unsigned long offset, unsigned long size) { - if (efi_mem_attribute_range(offset, size, EFI_MEMORY_WB)) - return phys_to_virt(offset); + u64 attr; + unsigned long gran_base, gran_size; - if (efi_mem_attribute_range(offset, size, EFI_MEMORY_UC)) + /* + * For things in kern_memmap, we must use the same attribute + * as the rest of the kernel. For more details, see + * Documentation/ia64/aliasing.txt. + */ + attr = kern_mem_attribute(offset, size); + if (attr & EFI_MEMORY_WB) + return (void __iomem *) phys_to_virt(offset); + else if (attr & EFI_MEMORY_UC) return __ioremap(offset, size); /* - * Someday this should check ACPI resources so we - * can do the right thing for hot-plugged regions. + * Some chipsets don't support UC access to memory. If + * WB is supported for the whole granule, we prefer that. */ + gran_base = GRANULEROUNDDOWN(offset); + gran_size = GRANULEROUNDUP(offset + size) - gran_base; + if (efi_mem_attribute(gran_base, gran_size) & EFI_MEMORY_WB) + return (void __iomem *) phys_to_virt(offset); + return __ioremap(offset, size); } EXPORT_SYMBOL(ioremap); @@ -38,6 +52,9 @@ EXPORT_SYMBOL(ioremap); void __iomem * ioremap_nocache (unsigned long offset, unsigned long size) { + if (kern_mem_attribute(offset, size) & EFI_MEMORY_WB) + return NULL; + return __ioremap(offset, size); } EXPORT_SYMBOL(ioremap_nocache); diff --git a/arch/ia64/mm/numa.c b/arch/ia64/mm/numa.c index 4e5c8b3..64e4c21 100644 --- a/arch/ia64/mm/numa.c +++ b/arch/ia64/mm/numa.c @@ -10,7 +10,6 @@ * 2002/08/07 Erich Focht <efocht@ess.nec.de> */ -#include <linux/config.h> #include <linux/cpu.h> #include <linux/kernel.h> #include <linux/mm.h> diff --git a/arch/ia64/mm/tlb.c b/arch/ia64/mm/tlb.c index 4dbbca0..ffad762 100644 --- a/arch/ia64/mm/tlb.c +++ b/arch/ia64/mm/tlb.c @@ -11,7 +11,6 @@ * Rohit Seth <rohit.seth@intel.com> * Ken Chen <kenneth.w.chen@intel.com> */ -#include <linux/config.h> #include <linux/module.h> #include <linux/init.h> #include <linux/kernel.h> diff --git a/arch/ia64/oprofile/perfmon.c b/arch/ia64/oprofile/perfmon.c index b7975a4..bc41dd3 100644 --- a/arch/ia64/oprofile/perfmon.c +++ b/arch/ia64/oprofile/perfmon.c @@ -8,7 +8,6 @@ */ #include <linux/kernel.h> -#include <linux/config.h> #include <linux/oprofile.h> #include <linux/sched.h> #include <asm/perfmon.h> diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c index ab829a2..60b45e7 100644 --- a/arch/ia64/pci/pci.c +++ b/arch/ia64/pci/pci.c @@ -10,7 +10,6 @@ * * Note: Above list of copyright holders is incomplete... */ -#include <linux/config.h> #include <linux/acpi.h> #include <linux/types.h> @@ -352,7 +351,7 @@ pci_acpi_scan_root(struct acpi_device *device, int domain, int bus) pxm = acpi_get_pxm(controller->acpi_handle); #ifdef CONFIG_NUMA if (pxm >= 0) - controller->node = pxm_to_nid_map[pxm]; + controller->node = pxm_to_node(pxm); #endif acpi_walk_resources(device->handle, METHOD_NAME__CRS, count_window, @@ -568,7 +567,7 @@ pcibios_disable_device (struct pci_dev *dev) void pcibios_align_resource (void *data, struct resource *res, - unsigned long size, unsigned long align) + resource_size_t size, resource_size_t align) { } @@ -602,8 +601,6 @@ pci_mmap_page_range (struct pci_dev *dev, struct vm_area_struct *vma, * Leave vm_pgoff as-is, the PCI space address is the physical * address on this platform. */ - vma->vm_flags |= (VM_SHM | VM_RESERVED | VM_IO); - if (write_combine && efi_range_is_wc(vma->vm_start, vma->vm_end - vma->vm_start)) vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot); @@ -645,18 +642,30 @@ char *ia64_pci_get_legacy_mem(struct pci_bus *bus) int pci_mmap_legacy_page_range(struct pci_bus *bus, struct vm_area_struct *vma) { + unsigned long size = vma->vm_end - vma->vm_start; + pgprot_t prot; char *addr; + /* + * Avoid attribute aliasing. See Documentation/ia64/aliasing.txt + * for more details. + */ + if (!valid_mmap_phys_addr_range(vma->vm_pgoff, size)) + return -EINVAL; + prot = phys_mem_access_prot(NULL, vma->vm_pgoff, size, + vma->vm_page_prot); + if (pgprot_val(prot) != pgprot_val(pgprot_noncached(vma->vm_page_prot))) + return -EINVAL; + addr = pci_get_legacy_mem(bus); if (IS_ERR(addr)) return PTR_ERR(addr); vma->vm_pgoff += (unsigned long)addr >> PAGE_SHIFT; - vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); - vma->vm_flags |= (VM_SHM | VM_RESERVED | VM_IO); + vma->vm_page_prot = prot; if (remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, - vma->vm_end - vma->vm_start, vma->vm_page_prot)) + size, vma->vm_page_prot)) return -EAGAIN; return 0; diff --git a/arch/ia64/sn/kernel/bte.c b/arch/ia64/sn/kernel/bte.c index e952ef4..27dee45 100644 --- a/arch/ia64/sn/kernel/bte.c +++ b/arch/ia64/sn/kernel/bte.c @@ -6,7 +6,6 @@ * Copyright (c) 2000-2006 Silicon Graphics, Inc. All Rights Reserved. */ -#include <linux/config.h> #include <linux/module.h> #include <asm/sn/nodepda.h> #include <asm/sn/addrs.h> diff --git a/arch/ia64/sn/kernel/huberror.c b/arch/ia64/sn/kernel/huberror.c index 56ab6ba..96fb81e 100644 --- a/arch/ia64/sn/kernel/huberror.c +++ b/arch/ia64/sn/kernel/huberror.c @@ -178,7 +178,7 @@ void hubiio_crb_error_handler(struct hubdev_info *hubdev_info) */ void hub_error_init(struct hubdev_info *hubdev_info) { - if (request_irq(SGI_II_ERROR, (void *)hub_eint_handler, SA_SHIRQ, + if (request_irq(SGI_II_ERROR, (void *)hub_eint_handler, IRQF_SHARED, "SN_hub_error", (void *)hubdev_info)) printk("hub_error_init: Failed to request_irq for 0x%p\n", hubdev_info); @@ -196,7 +196,7 @@ void hub_error_init(struct hubdev_info *hubdev_info) void ice_error_init(struct hubdev_info *hubdev_info) { if (request_irq - (SGI_TIO_ERROR, (void *)hub_eint_handler, SA_SHIRQ, "SN_TIO_error", + (SGI_TIO_ERROR, (void *)hub_eint_handler, IRQF_SHARED, "SN_TIO_error", (void *)hubdev_info)) printk("ice_error_init: request_irq() error hubdev_info 0x%p\n", hubdev_info); diff --git a/arch/ia64/sn/kernel/io_init.c b/arch/ia64/sn/kernel/io_init.c index 5101ac4..dc09a6a 100644 --- a/arch/ia64/sn/kernel/io_init.c +++ b/arch/ia64/sn/kernel/io_init.c @@ -58,7 +58,7 @@ static int max_pcibus_number = 255; /* Default highest pci bus number */ */ static dma_addr_t -sn_default_pci_map(struct pci_dev *pdev, unsigned long paddr, size_t size) +sn_default_pci_map(struct pci_dev *pdev, unsigned long paddr, size_t size, int type) { return 0; } @@ -457,13 +457,6 @@ void sn_pci_fixup_slot(struct pci_dev *dev) pcidev_info->pdi_sn_irq_info = NULL; kfree(sn_irq_info); } - - /* - * MSI currently not supported on altix. Remove this when - * the MSI abstraction patches are integrated into the kernel - * (sometime after 2.6.16 releases) - */ - dev->no_msi = 1; } /* diff --git a/arch/ia64/sn/kernel/irq.c b/arch/ia64/sn/kernel/irq.c index c265e02..7bb6ad1 100644 --- a/arch/ia64/sn/kernel/irq.c +++ b/arch/ia64/sn/kernel/irq.c @@ -26,11 +26,11 @@ static void unregister_intr_pda(struct sn_irq_info *sn_irq_info); int sn_force_interrupt_flag = 1; extern int sn_ioif_inited; -static struct list_head **sn_irq_lh; -static spinlock_t sn_irq_info_lock = SPIN_LOCK_UNLOCKED; /* non-IRQ lock */ +struct list_head **sn_irq_lh; +static DEFINE_SPINLOCK(sn_irq_info_lock); /* non-IRQ lock */ -static inline u64 sn_intr_alloc(nasid_t local_nasid, int local_widget, - u64 sn_irq_info, +u64 sn_intr_alloc(nasid_t local_nasid, int local_widget, + struct sn_irq_info *sn_irq_info, int req_irq, nasid_t req_nasid, int req_slice) { @@ -40,12 +40,13 @@ static inline u64 sn_intr_alloc(nasid_t local_nasid, int local_widget, SAL_CALL_NOLOCK(ret_stuff, (u64) SN_SAL_IOIF_INTERRUPT, (u64) SAL_INTR_ALLOC, (u64) local_nasid, - (u64) local_widget, (u64) sn_irq_info, (u64) req_irq, + (u64) local_widget, __pa(sn_irq_info), (u64) req_irq, (u64) req_nasid, (u64) req_slice); + return ret_stuff.status; } -static inline void sn_intr_free(nasid_t local_nasid, int local_widget, +void sn_intr_free(nasid_t local_nasid, int local_widget, struct sn_irq_info *sn_irq_info) { struct ia64_sal_retval ret_stuff; @@ -112,73 +113,91 @@ static void sn_end_irq(unsigned int irq) static void sn_irq_info_free(struct rcu_head *head); -static void sn_set_affinity_irq(unsigned int irq, cpumask_t mask) +struct sn_irq_info *sn_retarget_vector(struct sn_irq_info *sn_irq_info, + nasid_t nasid, int slice) { - struct sn_irq_info *sn_irq_info, *sn_irq_info_safe; - int cpuid, cpuphys; + int vector; + int cpuphys; + int64_t bridge; + int local_widget, status; + nasid_t local_nasid; + struct sn_irq_info *new_irq_info; + struct sn_pcibus_provider *pci_provider; - cpuid = first_cpu(mask); - cpuphys = cpu_physical_id(cpuid); + new_irq_info = kmalloc(sizeof(struct sn_irq_info), GFP_ATOMIC); + if (new_irq_info == NULL) + return NULL; - list_for_each_entry_safe(sn_irq_info, sn_irq_info_safe, - sn_irq_lh[irq], list) { - u64 bridge; - int local_widget, status; - nasid_t local_nasid; - struct sn_irq_info *new_irq_info; - struct sn_pcibus_provider *pci_provider; - - new_irq_info = kmalloc(sizeof(struct sn_irq_info), GFP_ATOMIC); - if (new_irq_info == NULL) - break; - memcpy(new_irq_info, sn_irq_info, sizeof(struct sn_irq_info)); - - bridge = (u64) new_irq_info->irq_bridge; - if (!bridge) { - kfree(new_irq_info); - break; /* irq is not a device interrupt */ - } + memcpy(new_irq_info, sn_irq_info, sizeof(struct sn_irq_info)); + + bridge = (u64) new_irq_info->irq_bridge; + if (!bridge) { + kfree(new_irq_info); + return NULL; /* irq is not a device interrupt */ + } - local_nasid = NASID_GET(bridge); + local_nasid = NASID_GET(bridge); - if (local_nasid & 1) - local_widget = TIO_SWIN_WIDGETNUM(bridge); - else - local_widget = SWIN_WIDGETNUM(bridge); + if (local_nasid & 1) + local_widget = TIO_SWIN_WIDGETNUM(bridge); + else + local_widget = SWIN_WIDGETNUM(bridge); - /* Free the old PROM new_irq_info structure */ - sn_intr_free(local_nasid, local_widget, new_irq_info); - /* Update kernels new_irq_info with new target info */ - unregister_intr_pda(new_irq_info); + vector = sn_irq_info->irq_irq; + /* Free the old PROM new_irq_info structure */ + sn_intr_free(local_nasid, local_widget, new_irq_info); + /* Update kernels new_irq_info with new target info */ + unregister_intr_pda(new_irq_info); - /* allocate a new PROM new_irq_info struct */ - status = sn_intr_alloc(local_nasid, local_widget, - __pa(new_irq_info), irq, - cpuid_to_nasid(cpuid), - cpuid_to_slice(cpuid)); + /* allocate a new PROM new_irq_info struct */ + status = sn_intr_alloc(local_nasid, local_widget, + new_irq_info, vector, + nasid, slice); - /* SAL call failed */ - if (status) { - kfree(new_irq_info); - break; - } + /* SAL call failed */ + if (status) { + kfree(new_irq_info); + return NULL; + } - new_irq_info->irq_cpuid = cpuid; - register_intr_pda(new_irq_info); + cpuphys = nasid_slice_to_cpuid(nasid, slice); + new_irq_info->irq_cpuid = cpuphys; + register_intr_pda(new_irq_info); - pci_provider = sn_pci_provider[new_irq_info->irq_bridge_type]; - if (pci_provider && pci_provider->target_interrupt) - (pci_provider->target_interrupt)(new_irq_info); + pci_provider = sn_pci_provider[new_irq_info->irq_bridge_type]; - spin_lock(&sn_irq_info_lock); - list_replace_rcu(&sn_irq_info->list, &new_irq_info->list); - spin_unlock(&sn_irq_info_lock); - call_rcu(&sn_irq_info->rcu, sn_irq_info_free); + /* + * If this represents a line interrupt, target it. If it's + * an msi (irq_int_bit < 0), it's already targeted. + */ + if (new_irq_info->irq_int_bit >= 0 && + pci_provider && pci_provider->target_interrupt) + (pci_provider->target_interrupt)(new_irq_info); + + spin_lock(&sn_irq_info_lock); + list_replace_rcu(&sn_irq_info->list, &new_irq_info->list); + spin_unlock(&sn_irq_info_lock); + call_rcu(&sn_irq_info->rcu, sn_irq_info_free); #ifdef CONFIG_SMP - set_irq_affinity_info((irq & 0xff), cpuphys, 0); + set_irq_affinity_info((vector & 0xff), cpuphys, 0); #endif - } + + return new_irq_info; +} + +static void sn_set_affinity_irq(unsigned int irq, cpumask_t mask) +{ + struct sn_irq_info *sn_irq_info, *sn_irq_info_safe; + nasid_t nasid; + int slice; + + nasid = cpuid_to_nasid(first_cpu(mask)); + slice = cpuid_to_slice(first_cpu(mask)); + + list_for_each_entry_safe(sn_irq_info, sn_irq_info_safe, + sn_irq_lh[irq], list) + (void)sn_retarget_vector(sn_irq_info, nasid, slice); } struct hw_interrupt_type irq_type_sn = { @@ -202,9 +221,12 @@ void sn_irq_init(void) int i; irq_desc_t *base_desc = irq_desc; + ia64_first_device_vector = IA64_SN2_FIRST_DEVICE_VECTOR; + ia64_last_device_vector = IA64_SN2_LAST_DEVICE_VECTOR; + for (i = 0; i < NR_IRQS; i++) { - if (base_desc[i].handler == &no_irq_type) { - base_desc[i].handler = &irq_type_sn; + if (base_desc[i].chip == &no_irq_type) { + base_desc[i].chip = &irq_type_sn; } } } @@ -285,6 +307,7 @@ void sn_irq_fixup(struct pci_dev *pci_dev, struct sn_irq_info *sn_irq_info) /* link it into the sn_irq[irq] list */ spin_lock(&sn_irq_info_lock); list_add_rcu(&sn_irq_info->list, sn_irq_lh[sn_irq_info->irq_irq]); + reserve_irq_vector(sn_irq_info->irq_irq); spin_unlock(&sn_irq_info_lock); register_intr_pda(sn_irq_info); @@ -310,8 +333,11 @@ void sn_irq_unfixup(struct pci_dev *pci_dev) spin_lock(&sn_irq_info_lock); list_del_rcu(&sn_irq_info->list); spin_unlock(&sn_irq_info_lock); + if (list_empty(sn_irq_lh[sn_irq_info->irq_irq])) + free_irq_vector(sn_irq_info->irq_irq); call_rcu(&sn_irq_info->rcu, sn_irq_info_free); pci_dev_put(pci_dev); + } static inline void diff --git a/arch/ia64/sn/kernel/setup.c b/arch/ia64/sn/kernel/setup.c index 30988df..5f2dcba 100644 --- a/arch/ia64/sn/kernel/setup.c +++ b/arch/ia64/sn/kernel/setup.c @@ -6,14 +6,13 @@ * Copyright (C) 1999,2001-2006 Silicon Graphics, Inc. All rights reserved. */ -#include <linux/config.h> #include <linux/module.h> #include <linux/init.h> #include <linux/delay.h> #include <linux/kernel.h> #include <linux/kdev_t.h> #include <linux/string.h> -#include <linux/tty.h> +#include <linux/screen_info.h> #include <linux/console.h> #include <linux/timex.h> #include <linux/sched.h> @@ -139,7 +138,7 @@ static int __init pxm_to_nasid(int pxm) int i; int nid; - nid = pxm_to_nid_map[pxm]; + nid = pxm_to_node(pxm); for (i = 0; i < num_node_memblks; i++) { if (node_memblk[i].nid == nid) { return NASID_GET(node_memblk[i].start_paddr); @@ -458,7 +457,7 @@ void __init sn_setup(char **cmdline_p) * support here so we don't have to listen to failed keyboard probe * messages. */ - if (version <= 0x0209 && acpi_kbd_controller_present) { + if (is_shub1() && version <= 0x0209 && acpi_kbd_controller_present) { printk(KERN_INFO "Disabling legacy keyboard support as prom " "is too old and doesn't provide FADT\n"); acpi_kbd_controller_present = 0; @@ -566,7 +565,7 @@ static void __init sn_init_pdas(char **cmdline_p) * Also sets up a few fields in the nodepda. Also known as * platform_cpu_init() by the ia64 machvec code. */ -void __init sn_cpu_init(void) +void __cpuinit sn_cpu_init(void) { int cpuid; int cpuphyid; @@ -577,7 +576,8 @@ void __init sn_cpu_init(void) int i; static int wars_have_been_checked; - if (smp_processor_id() == 0 && IS_MEDUSA()) { + cpuid = smp_processor_id(); + if (cpuid == 0 && IS_MEDUSA()) { if (ia64_sn_is_fake_prom()) sn_prom_type = 2; else @@ -597,6 +597,12 @@ void __init sn_cpu_init(void) sn_hub_info->as_shift = sn_hub_info->nasid_shift - 2; /* + * Don't check status. The SAL call is not supported on all PROMs + * but a failure is harmless. + */ + (void) ia64_sn_set_cpu_number(cpuid); + + /* * The boot cpu makes this call again after platform initialization is * complete. */ @@ -607,7 +613,6 @@ void __init sn_cpu_init(void) if (ia64_sn_get_prom_feature_set(i, &sn_prom_features[i]) != 0) break; - cpuid = smp_processor_id(); cpuphyid = get_sapicid(); if (ia64_sn_get_sapic_info(cpuphyid, &nasid, &subnode, &slice)) @@ -704,7 +709,7 @@ void __init build_cnode_tables(void) * cnode == node for all C & M bricks. */ for_each_online_node(node) { - nasid = pxm_to_nasid(nid_to_pxm_map[node]); + nasid = pxm_to_nasid(node_to_pxm(node)); sn_cnodeid_to_nasid[node] = nasid; physical_node_map[nasid] = node; } diff --git a/arch/ia64/sn/kernel/sn2/cache.c b/arch/ia64/sn/kernel/sn2/cache.c index bc3cfa1..2862cb3 100644 --- a/arch/ia64/sn/kernel/sn2/cache.c +++ b/arch/ia64/sn/kernel/sn2/cache.c @@ -3,11 +3,12 @@ * License. See the file "COPYING" in the main directory of this archive * for more details. * - * Copyright (C) 2001-2003 Silicon Graphics, Inc. All rights reserved. + * Copyright (C) 2001-2003, 2006 Silicon Graphics, Inc. All rights reserved. * */ #include <linux/module.h> #include <asm/pgalloc.h> +#include <asm/sn/arch.h> /** * sn_flush_all_caches - flush a range of address from all caches (incl. L4) @@ -17,18 +18,24 @@ * Flush a range of addresses from all caches including L4. * All addresses fully or partially contained within * @flush_addr to @flush_addr + @bytes are flushed - * from the all caches. + * from all caches. */ void sn_flush_all_caches(long flush_addr, long bytes) { - flush_icache_range(flush_addr, flush_addr+bytes); + unsigned long addr = flush_addr; + + /* SHub1 requires a cached address */ + if (is_shub1() && (addr & RGN_BITS) == RGN_BASE(RGN_UNCACHED)) + addr = (addr - RGN_BASE(RGN_UNCACHED)) + RGN_BASE(RGN_KERNEL); + + flush_icache_range(addr, addr + bytes); /* * The last call may have returned before the caches * were actually flushed, so we call it again to make * sure. */ - flush_icache_range(flush_addr, flush_addr+bytes); + flush_icache_range(addr, addr + bytes); mb(); } EXPORT_SYMBOL(sn_flush_all_caches); diff --git a/arch/ia64/sn/kernel/sn2/prominfo_proc.c b/arch/ia64/sn/kernel/sn2/prominfo_proc.c index 6ae276d..4dcce3d 100644 --- a/arch/ia64/sn/kernel/sn2/prominfo_proc.c +++ b/arch/ia64/sn/kernel/sn2/prominfo_proc.c @@ -8,7 +8,6 @@ * Module to export the system's Firmware Interface Tables, including * PROM revision numbers and banners, in /proc */ -#include <linux/config.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/proc_fs.h> diff --git a/arch/ia64/sn/kernel/sn2/sn_hwperf.c b/arch/ia64/sn/kernel/sn2/sn_hwperf.c index 739c948..9a8a293 100644 --- a/arch/ia64/sn/kernel/sn2/sn_hwperf.c +++ b/arch/ia64/sn/kernel/sn2/sn_hwperf.c @@ -51,6 +51,8 @@ static nasid_t sn_hwperf_master_nasid = INVALID_NASID; static int sn_hwperf_init(void); static DECLARE_MUTEX(sn_hwperf_init_mutex); +#define cnode_possible(n) ((n) < num_cnodes) + static int sn_hwperf_enum_objects(int *nobj, struct sn_hwperf_object_info **ret) { int e; @@ -127,14 +129,14 @@ static int sn_hwperf_geoid_to_cnode(char *location) } } - return node_possible(cnode) ? cnode : -1; + return cnode_possible(cnode) ? cnode : -1; } static int sn_hwperf_obj_to_cnode(struct sn_hwperf_object_info * obj) { if (!SN_HWPERF_IS_NODE(obj) && !SN_HWPERF_IS_IONODE(obj)) BUG(); - if (!obj->sn_hwp_this_part) + if (SN_HWPERF_FOREIGN(obj)) return -1; return sn_hwperf_geoid_to_cnode(obj->location); } @@ -199,12 +201,12 @@ static void print_pci_topology(struct seq_file *s) static inline int sn_hwperf_has_cpus(cnodeid_t node) { - return node_online(node) && nr_cpus_node(node); + return node < MAX_NUMNODES && node_online(node) && nr_cpus_node(node); } static inline int sn_hwperf_has_mem(cnodeid_t node) { - return node_online(node) && NODE_DATA(node)->node_present_pages; + return node < MAX_NUMNODES && node_online(node) && NODE_DATA(node)->node_present_pages; } static struct sn_hwperf_object_info * @@ -237,7 +239,7 @@ static int sn_hwperf_get_nearest_node_objdata(struct sn_hwperf_object_info *objb int found_mem = 0; int found_cpu = 0; - if (!node_possible(node)) + if (!cnode_possible(node)) return -EINVAL; if (sn_hwperf_has_cpus(node)) { @@ -442,7 +444,7 @@ static int sn_topology_show(struct seq_file *s, void *d) seq_printf(s, "%s %d %s %s asic %s", slabname, ordinal, obj->location, obj->sn_hwp_this_part ? "local" : "shared", obj->name); - if (!SN_HWPERF_IS_NODE(obj) && !SN_HWPERF_IS_IONODE(obj)) + if (ordinal < 0 || (!SN_HWPERF_IS_NODE(obj) && !SN_HWPERF_IS_IONODE(obj))) seq_putc(s, '\n'); else { cnodeid_t near_mem = -1; @@ -468,22 +470,24 @@ static int sn_topology_show(struct seq_file *s, void *d) /* * CPUs on this node, if any */ - cpumask = node_to_cpumask(ordinal); - for_each_online_cpu(i) { - if (cpu_isset(i, cpumask)) { - slice = 'a' + cpuid_to_slice(i); - c = cpu_data(i); - seq_printf(s, "cpu %d %s%c local" - " freq %luMHz, arch ia64", - i, obj->location, slice, - c->proc_freq / 1000000); - for_each_online_cpu(j) { - seq_printf(s, j ? ":%d" : ", dist %d", - node_distance( - cpu_to_node(i), - cpu_to_node(j))); + if (!SN_HWPERF_IS_IONODE(obj)) { + cpumask = node_to_cpumask(ordinal); + for_each_online_cpu(i) { + if (cpu_isset(i, cpumask)) { + slice = 'a' + cpuid_to_slice(i); + c = cpu_data(i); + seq_printf(s, "cpu %d %s%c local" + " freq %luMHz, arch ia64", + i, obj->location, slice, + c->proc_freq / 1000000); + for_each_online_cpu(j) { + seq_printf(s, j ? ":%d" : ", dist %d", + node_distance( + cpu_to_node(i), + cpu_to_node(j))); + } + seq_putc(s, '\n'); } - seq_putc(s, '\n'); } } } @@ -523,7 +527,7 @@ static int sn_topology_show(struct seq_file *s, void *d) if (obj->sn_hwp_this_part && p->sn_hwp_this_part) /* both ends local to this partition */ seq_puts(s, " local"); - else if (!obj->sn_hwp_this_part && !p->sn_hwp_this_part) + else if (SN_HWPERF_FOREIGN(p)) /* both ends of the link in foreign partiton */ seq_puts(s, " foreign"); else @@ -776,7 +780,7 @@ sn_hwperf_ioctl(struct inode *in, struct file *fp, u32 op, u64 arg) case SN_HWPERF_GET_NODE_NASID: if (a.sz != sizeof(u64) || - (node = a.arg) < 0 || !node_possible(node)) { + (node = a.arg) < 0 || !cnode_possible(node)) { r = -EINVAL; goto error; } diff --git a/arch/ia64/sn/kernel/sn2/sn_proc_fs.c b/arch/ia64/sn/kernel/sn2/sn_proc_fs.c index 5100261..43ddc2e 100644 --- a/arch/ia64/sn/kernel/sn2/sn_proc_fs.c +++ b/arch/ia64/sn/kernel/sn2/sn_proc_fs.c @@ -5,7 +5,6 @@ * * Copyright (C) 2000-2005 Silicon Graphics, Inc. All rights reserved. */ -#include <linux/config.h> #ifdef CONFIG_PROC_FS #include <linux/proc_fs.h> diff --git a/arch/ia64/sn/kernel/xpc_channel.c b/arch/ia64/sn/kernel/xpc_channel.c index 8255a9b..1f35408 100644 --- a/arch/ia64/sn/kernel/xpc_channel.c +++ b/arch/ia64/sn/kernel/xpc_channel.c @@ -202,7 +202,7 @@ xpc_setup_infrastructure(struct xpc_partition *part) init_waitqueue_head(&part->channel_mgr_wq); sprintf(part->IPI_owner, "xpc%02d", partid); - ret = request_irq(SGI_XPC_NOTIFY, xpc_notify_IRQ_handler, SA_SHIRQ, + ret = request_irq(SGI_XPC_NOTIFY, xpc_notify_IRQ_handler, IRQF_SHARED, part->IPI_owner, (void *) (u64) partid); if (ret != 0) { dev_err(xpc_chan, "can't register NOTIFY IRQ handler, " @@ -279,8 +279,8 @@ xpc_pull_remote_cachelines(struct xpc_partition *part, void *dst, return part->reason; } - bte_ret = xp_bte_copy((u64) src, (u64) ia64_tpa((u64) dst), - (u64) cnt, (BTE_NORMAL | BTE_WACQUIRE), NULL); + bte_ret = xp_bte_copy((u64) src, (u64) dst, (u64) cnt, + (BTE_NORMAL | BTE_WACQUIRE), NULL); if (bte_ret == BTE_SUCCESS) { return xpcSuccess; } diff --git a/arch/ia64/sn/kernel/xpc_main.c b/arch/ia64/sn/kernel/xpc_main.c index 99b123a..4d026f9 100644 --- a/arch/ia64/sn/kernel/xpc_main.c +++ b/arch/ia64/sn/kernel/xpc_main.c @@ -480,7 +480,7 @@ xpc_activating(void *__partid) partid_t partid = (u64) __partid; struct xpc_partition *part = &xpc_partitions[partid]; unsigned long irq_flags; - struct sched_param param = { sched_priority: MAX_RT_PRIO - 1 }; + struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 }; int ret; @@ -1052,6 +1052,8 @@ xpc_do_exit(enum xpc_retval reason) if (xpc_sysctl) { unregister_sysctl_table(xpc_sysctl); } + + kfree(xpc_remote_copy_buffer_base); } @@ -1212,24 +1214,20 @@ xpc_init(void) partid_t partid; struct xpc_partition *part; pid_t pid; + size_t buf_size; if (!ia64_platform_is("sn2")) { return -ENODEV; } - /* - * xpc_remote_copy_buffer is used as a temporary buffer for bte_copy'ng - * various portions of a partition's reserved page. Its size is based - * on the size of the reserved page header and part_nasids mask. So we - * need to ensure that the other items will fit as well. - */ - if (XPC_RP_VARS_SIZE > XPC_RP_HEADER_SIZE + XP_NASID_MASK_BYTES) { - dev_err(xpc_part, "xpc_remote_copy_buffer is not big enough\n"); - return -EPERM; - } - DBUG_ON((u64) xpc_remote_copy_buffer != - L1_CACHE_ALIGN((u64) xpc_remote_copy_buffer)); + + buf_size = max(XPC_RP_VARS_SIZE, + XPC_RP_HEADER_SIZE + XP_NASID_MASK_BYTES); + xpc_remote_copy_buffer = xpc_kmalloc_cacheline_aligned(buf_size, + GFP_KERNEL, &xpc_remote_copy_buffer_base); + if (xpc_remote_copy_buffer == NULL) + return -ENOMEM; snprintf(xpc_part->bus_id, BUS_ID_SIZE, "part"); snprintf(xpc_chan->bus_id, BUS_ID_SIZE, "chan"); @@ -1293,6 +1291,8 @@ xpc_init(void) if (xpc_sysctl) { unregister_sysctl_table(xpc_sysctl); } + + kfree(xpc_remote_copy_buffer_base); return -EBUSY; } @@ -1311,6 +1311,8 @@ xpc_init(void) if (xpc_sysctl) { unregister_sysctl_table(xpc_sysctl); } + + kfree(xpc_remote_copy_buffer_base); return -EBUSY; } @@ -1362,6 +1364,8 @@ xpc_init(void) if (xpc_sysctl) { unregister_sysctl_table(xpc_sysctl); } + + kfree(xpc_remote_copy_buffer_base); return -EBUSY; } diff --git a/arch/ia64/sn/kernel/xpc_partition.c b/arch/ia64/sn/kernel/xpc_partition.c index 2a89cfc..57c723f 100644 --- a/arch/ia64/sn/kernel/xpc_partition.c +++ b/arch/ia64/sn/kernel/xpc_partition.c @@ -71,19 +71,15 @@ struct xpc_partition xpc_partitions[XP_MAX_PARTITIONS + 1]; * Generic buffer used to store a local copy of portions of a remote * partition's reserved page (either its header and part_nasids mask, * or its vars). - * - * xpc_discovery runs only once and is a seperate thread that is - * very likely going to be processing in parallel with receiving - * interrupts. */ -char ____cacheline_aligned xpc_remote_copy_buffer[XPC_RP_HEADER_SIZE + - XP_NASID_MASK_BYTES]; +char *xpc_remote_copy_buffer; +void *xpc_remote_copy_buffer_base; /* * Guarantee that the kmalloc'd memory is cacheline aligned. */ -static void * +void * xpc_kmalloc_cacheline_aligned(size_t size, gfp_t flags, void **base) { /* see if kmalloc will give us cachline aligned memory by default */ @@ -148,7 +144,7 @@ xpc_get_rsvd_page_pa(int nasid) } } - bte_res = xp_bte_copy(rp_pa, ia64_tpa(buf), buf_len, + bte_res = xp_bte_copy(rp_pa, buf, buf_len, (BTE_NOTIFY | BTE_WACQUIRE), NULL); if (bte_res != BTE_SUCCESS) { dev_dbg(xpc_part, "xp_bte_copy failed %i\n", bte_res); @@ -447,7 +443,7 @@ xpc_check_remote_hb(void) /* pull the remote_hb cache line */ bres = xp_bte_copy(part->remote_vars_pa, - ia64_tpa((u64) remote_vars), + (u64) remote_vars, XPC_RP_VARS_SIZE, (BTE_NOTIFY | BTE_WACQUIRE), NULL); if (bres != BTE_SUCCESS) { @@ -498,8 +494,7 @@ xpc_get_remote_rp(int nasid, u64 *discovered_nasids, /* pull over the reserved page header and part_nasids mask */ - - bres = xp_bte_copy(*remote_rp_pa, ia64_tpa((u64) remote_rp), + bres = xp_bte_copy(*remote_rp_pa, (u64) remote_rp, XPC_RP_HEADER_SIZE + xp_nasid_mask_bytes, (BTE_NOTIFY | BTE_WACQUIRE), NULL); if (bres != BTE_SUCCESS) { @@ -554,11 +549,8 @@ xpc_get_remote_vars(u64 remote_vars_pa, struct xpc_vars *remote_vars) return xpcVarsNotSet; } - /* pull over the cross partition variables */ - - bres = xp_bte_copy(remote_vars_pa, ia64_tpa((u64) remote_vars), - XPC_RP_VARS_SIZE, + bres = xp_bte_copy(remote_vars_pa, (u64) remote_vars, XPC_RP_VARS_SIZE, (BTE_NOTIFY | BTE_WACQUIRE), NULL); if (bres != BTE_SUCCESS) { return xpc_map_bte_errors(bres); @@ -1239,7 +1231,7 @@ xpc_initiate_partid_to_nasids(partid_t partid, void *nasid_mask) part_nasid_pa = (u64) XPC_RP_PART_NASIDS(part->remote_rp_pa); - bte_res = xp_bte_copy(part_nasid_pa, ia64_tpa((u64) nasid_mask), + bte_res = xp_bte_copy(part_nasid_pa, (u64) nasid_mask, xp_nasid_mask_bytes, (BTE_NOTIFY | BTE_WACQUIRE), NULL); return xpc_map_bte_errors(bte_res); diff --git a/arch/ia64/sn/kernel/xpnet.c b/arch/ia64/sn/kernel/xpnet.c index e5c6d3c..007703c 100644 --- a/arch/ia64/sn/kernel/xpnet.c +++ b/arch/ia64/sn/kernel/xpnet.c @@ -22,7 +22,6 @@ */ -#include <linux/config.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/pci.h> diff --git a/arch/ia64/sn/pci/pci_dma.c b/arch/ia64/sn/pci/pci_dma.c index b4b84c2..7a291a2 100644 --- a/arch/ia64/sn/pci/pci_dma.c +++ b/arch/ia64/sn/pci/pci_dma.c @@ -11,7 +11,7 @@ #include <linux/module.h> #include <asm/dma.h> -#include <asm/sn/pcibr_provider.h> +#include <asm/sn/intr.h> #include <asm/sn/pcibus_provider_defs.h> #include <asm/sn/pcidev.h> #include <asm/sn/sn_sal.h> @@ -113,7 +113,8 @@ void *sn_dma_alloc_coherent(struct device *dev, size_t size, * resources. */ - *dma_handle = provider->dma_map_consistent(pdev, phys_addr, size); + *dma_handle = provider->dma_map_consistent(pdev, phys_addr, size, + SN_DMA_ADDR_PHYS); if (!*dma_handle) { printk(KERN_ERR "%s: out of ATEs\n", __FUNCTION__); free_pages((unsigned long)cpuaddr, get_order(size)); @@ -176,7 +177,7 @@ dma_addr_t sn_dma_map_single(struct device *dev, void *cpu_addr, size_t size, BUG_ON(dev->bus != &pci_bus_type); phys_addr = __pa(cpu_addr); - dma_addr = provider->dma_map(pdev, phys_addr, size); + dma_addr = provider->dma_map(pdev, phys_addr, size, SN_DMA_ADDR_PHYS); if (!dma_addr) { printk(KERN_ERR "%s: out of ATEs\n", __FUNCTION__); return 0; @@ -260,7 +261,8 @@ int sn_dma_map_sg(struct device *dev, struct scatterlist *sg, int nhwentries, for (i = 0; i < nhwentries; i++, sg++) { phys_addr = SG_ENT_PHYS_ADDRESS(sg); sg->dma_address = provider->dma_map(pdev, - phys_addr, sg->length); + phys_addr, sg->length, + SN_DMA_ADDR_PHYS); if (!sg->dma_address) { printk(KERN_ERR "%s: out of ATEs\n", __FUNCTION__); diff --git a/arch/ia64/sn/pci/pcibr/pcibr_dma.c b/arch/ia64/sn/pci/pcibr/pcibr_dma.c index 9f86bb6..a86c7b9 100644 --- a/arch/ia64/sn/pci/pcibr/pcibr_dma.c +++ b/arch/ia64/sn/pci/pcibr/pcibr_dma.c @@ -41,7 +41,7 @@ extern int sn_ioif_inited; static dma_addr_t pcibr_dmamap_ate32(struct pcidev_info *info, - u64 paddr, size_t req_size, u64 flags) + u64 paddr, size_t req_size, u64 flags, int dma_flags) { struct pcidev_info *pcidev_info = info->pdi_host_pcidev_info; @@ -81,9 +81,12 @@ pcibr_dmamap_ate32(struct pcidev_info *info, if (IS_PCIX(pcibus_info)) ate_flags &= ~(PCI32_ATE_PREF); - xio_addr = - IS_PIC_SOFT(pcibus_info) ? PHYS_TO_DMA(paddr) : - PHYS_TO_TIODMA(paddr); + if (SN_DMA_ADDRTYPE(dma_flags == SN_DMA_ADDR_PHYS)) + xio_addr = IS_PIC_SOFT(pcibus_info) ? PHYS_TO_DMA(paddr) : + PHYS_TO_TIODMA(paddr); + else + xio_addr = paddr; + offset = IOPGOFF(xio_addr); ate = ate_flags | (xio_addr - offset); @@ -91,6 +94,13 @@ pcibr_dmamap_ate32(struct pcidev_info *info, if (IS_PIC_SOFT(pcibus_info)) { ate |= (pcibus_info->pbi_hub_xid << PIC_ATE_TARGETID_SHFT); } + + /* + * If we're mapping for MSI, set the MSI bit in the ATE + */ + if (dma_flags & SN_DMA_MSI) + ate |= PCI32_ATE_MSI; + ate_write(pcibus_info, ate_index, ate_count, ate); /* @@ -105,20 +115,27 @@ pcibr_dmamap_ate32(struct pcidev_info *info, if (pcibus_info->pbi_devreg[internal_device] & PCIBR_DEV_SWAP_DIR) ATE_SWAP_ON(pci_addr); + return pci_addr; } static dma_addr_t pcibr_dmatrans_direct64(struct pcidev_info * info, u64 paddr, - u64 dma_attributes) + u64 dma_attributes, int dma_flags) { struct pcibus_info *pcibus_info = (struct pcibus_info *) ((info->pdi_host_pcidev_info)->pdi_pcibus_info); u64 pci_addr; /* Translate to Crosstalk View of Physical Address */ - pci_addr = (IS_PIC_SOFT(pcibus_info) ? PHYS_TO_DMA(paddr) : - PHYS_TO_TIODMA(paddr)) | dma_attributes; + if (SN_DMA_ADDRTYPE(dma_flags) == SN_DMA_ADDR_PHYS) + pci_addr = IS_PIC_SOFT(pcibus_info) ? + PHYS_TO_DMA(paddr) : + PHYS_TO_TIODMA(paddr) | dma_attributes; + else + pci_addr = IS_PIC_SOFT(pcibus_info) ? + paddr : + paddr | dma_attributes; /* Handle Bus mode */ if (IS_PCIX(pcibus_info)) @@ -130,7 +147,9 @@ pcibr_dmatrans_direct64(struct pcidev_info * info, u64 paddr, ((u64) pcibus_info-> pbi_hub_xid << PIC_PCI64_ATTR_TARG_SHFT); } else - pci_addr |= TIOCP_PCI64_CMDTYPE_MEM; + pci_addr |= (dma_flags & SN_DMA_MSI) ? + TIOCP_PCI64_CMDTYPE_MSI : + TIOCP_PCI64_CMDTYPE_MEM; /* If PCI mode, func zero uses VCHAN0, every other func uses VCHAN1 */ if (!IS_PCIX(pcibus_info) && PCI_FUNC(info->pdi_linux_pcidev->devfn)) @@ -141,7 +160,7 @@ pcibr_dmatrans_direct64(struct pcidev_info * info, u64 paddr, static dma_addr_t pcibr_dmatrans_direct32(struct pcidev_info * info, - u64 paddr, size_t req_size, u64 flags) + u64 paddr, size_t req_size, u64 flags, int dma_flags) { struct pcidev_info *pcidev_info = info->pdi_host_pcidev_info; struct pcibus_info *pcibus_info = (struct pcibus_info *)pcidev_info-> @@ -156,8 +175,14 @@ pcibr_dmatrans_direct32(struct pcidev_info * info, return 0; } - xio_addr = IS_PIC_SOFT(pcibus_info) ? PHYS_TO_DMA(paddr) : - PHYS_TO_TIODMA(paddr); + if (dma_flags & SN_DMA_MSI) + return 0; + + if (SN_DMA_ADDRTYPE(dma_flags) == SN_DMA_ADDR_PHYS) + xio_addr = IS_PIC_SOFT(pcibus_info) ? PHYS_TO_DMA(paddr) : + PHYS_TO_TIODMA(paddr); + else + xio_addr = paddr; xio_base = pcibus_info->pbi_dir_xbase; offset = xio_addr - xio_base; @@ -327,7 +352,7 @@ void sn_dma_flush(u64 addr) */ dma_addr_t -pcibr_dma_map(struct pci_dev * hwdev, unsigned long phys_addr, size_t size) +pcibr_dma_map(struct pci_dev * hwdev, unsigned long phys_addr, size_t size, int dma_flags) { dma_addr_t dma_handle; struct pcidev_info *pcidev_info = SN_PCIDEV_INFO(hwdev); @@ -344,11 +369,11 @@ pcibr_dma_map(struct pci_dev * hwdev, unsigned long phys_addr, size_t size) */ dma_handle = pcibr_dmatrans_direct64(pcidev_info, phys_addr, - PCI64_ATTR_PREF); + PCI64_ATTR_PREF, dma_flags); } else { /* Handle 32-63 bit cards via direct mapping */ dma_handle = pcibr_dmatrans_direct32(pcidev_info, phys_addr, - size, 0); + size, 0, dma_flags); if (!dma_handle) { /* * It is a 32 bit card and we cannot do direct mapping, @@ -356,7 +381,8 @@ pcibr_dma_map(struct pci_dev * hwdev, unsigned long phys_addr, size_t size) */ dma_handle = pcibr_dmamap_ate32(pcidev_info, phys_addr, - size, PCI32_ATE_PREF); + size, PCI32_ATE_PREF, + dma_flags); } } @@ -365,18 +391,18 @@ pcibr_dma_map(struct pci_dev * hwdev, unsigned long phys_addr, size_t size) dma_addr_t pcibr_dma_map_consistent(struct pci_dev * hwdev, unsigned long phys_addr, - size_t size) + size_t size, int dma_flags) { dma_addr_t dma_handle; struct pcidev_info *pcidev_info = SN_PCIDEV_INFO(hwdev); if (hwdev->dev.coherent_dma_mask == ~0UL) { dma_handle = pcibr_dmatrans_direct64(pcidev_info, phys_addr, - PCI64_ATTR_BAR); + PCI64_ATTR_BAR, dma_flags); } else { dma_handle = (dma_addr_t) pcibr_dmamap_ate32(pcidev_info, phys_addr, size, - PCI32_ATE_BAR); + PCI32_ATE_BAR, dma_flags); } return dma_handle; diff --git a/arch/ia64/sn/pci/pcibr/pcibr_provider.c b/arch/ia64/sn/pci/pcibr/pcibr_provider.c index ab1211e..838c93c 100644 --- a/arch/ia64/sn/pci/pcibr/pcibr_provider.c +++ b/arch/ia64/sn/pci/pcibr/pcibr_provider.c @@ -139,7 +139,7 @@ pcibr_bus_fixup(struct pcibus_bussoft *prom_bussoft, struct pci_controller *cont * register the bridge's error interrupt handler */ if (request_irq(SGI_PCIASIC_ERROR, (void *)pcibr_error_intr_handler, - SA_SHIRQ, "PCIBR error", (void *)(soft))) { + IRQF_SHARED, "PCIBR error", (void *)(soft))) { printk(KERN_WARNING "pcibr cannot allocate interrupt for error handler\n"); } diff --git a/arch/ia64/sn/pci/tioca_provider.c b/arch/ia64/sn/pci/tioca_provider.c index be01769..c36b0f5 100644 --- a/arch/ia64/sn/pci/tioca_provider.c +++ b/arch/ia64/sn/pci/tioca_provider.c @@ -515,11 +515,17 @@ tioca_dma_unmap(struct pci_dev *pdev, dma_addr_t bus_addr, int dir) * use the GART mapped mode. */ static u64 -tioca_dma_map(struct pci_dev *pdev, u64 paddr, size_t byte_count) +tioca_dma_map(struct pci_dev *pdev, u64 paddr, size_t byte_count, int dma_flags) { u64 mapaddr; /* + * Not supported for now ... + */ + if (dma_flags & SN_DMA_MSI) + return 0; + + /* * If card is 64 or 48 bit addresable, use a direct mapping. 32 * bit direct is so restrictive w.r.t. where the memory resides that * we don't use it even though CA has some support. @@ -589,7 +595,7 @@ tioca_bus_fixup(struct pcibus_bussoft *prom_bussoft, struct pci_controller *cont /* sanity check prom rev */ - if (sn_sal_rev() < 0x0406) { + if (is_shub1() && sn_sal_rev() < 0x0406) { printk (KERN_ERR "%s: SGI prom rev 4.06 or greater required " "for tioca support\n", __FUNCTION__); @@ -640,7 +646,7 @@ tioca_bus_fixup(struct pcibus_bussoft *prom_bussoft, struct pci_controller *cont if (request_irq(SGI_TIOCA_ERROR, tioca_error_intr_handler, - SA_SHIRQ, "TIOCA error", (void *)tioca_common)) + IRQF_SHARED, "TIOCA error", (void *)tioca_common)) printk(KERN_WARNING "%s: Unable to get irq %d. " "Error interrupts won't be routed for TIOCA bus %d\n", diff --git a/arch/ia64/sn/pci/tioce_provider.c b/arch/ia64/sn/pci/tioce_provider.c index 8332956..af7171a 100644 --- a/arch/ia64/sn/pci/tioce_provider.c +++ b/arch/ia64/sn/pci/tioce_provider.c @@ -3,7 +3,7 @@ * License. See the file "COPYING" in the main directory of this archive * for more details. * - * Copyright (C) 2003-2005 Silicon Graphics, Inc. All Rights Reserved. + * Copyright (C) 2003-2006 Silicon Graphics, Inc. All Rights Reserved. */ #include <linux/types.h> @@ -74,7 +74,7 @@ tioce_mmr_war_pre(struct tioce_kernel *kern, void *mmr_addr) else mmr_war_offset = 0x158; - readq_relaxed((void *)(mmr_base + mmr_war_offset)); + readq_relaxed((void __iomem *)(mmr_base + mmr_war_offset)); } } @@ -92,8 +92,8 @@ tioce_mmr_war_post(struct tioce_kernel *kern, void *mmr_addr) if (mmr_offset < 0x45000) { if (mmr_offset == 0x100) - readq_relaxed((void *)(mmr_base + 0x38)); - readq_relaxed((void *)(mmr_base + 0xb050)); + readq_relaxed((void __iomem *)(mmr_base + 0x38)); + readq_relaxed((void __iomem *)(mmr_base + 0xb050)); } } @@ -170,7 +170,8 @@ tioce_mmr_war_post(struct tioce_kernel *kern, void *mmr_addr) (ATE_PAGE((start)+(len)-1, pagesize) - ATE_PAGE(start, pagesize) + 1) #define ATE_VALID(ate) ((ate) & (1UL << 63)) -#define ATE_MAKE(addr, ps) (((addr) & ~ATE_PAGEMASK(ps)) | (1UL << 63)) +#define ATE_MAKE(addr, ps, msi) \ + (((addr) & ~ATE_PAGEMASK(ps)) | (1UL << 63) | ((msi)?(1UL << 62):0)) /* * Flavors of ate-based mapping supported by tioce_alloc_map() @@ -196,15 +197,17 @@ tioce_mmr_war_post(struct tioce_kernel *kern, void *mmr_addr) * * 63 - must be 1 to indicate d64 mode to CE hardware * 62 - barrier bit ... controlled with tioce_dma_barrier() - * 61 - 0 since this is not an MSI transaction + * 61 - msi bit ... specified through dma_flags * 60:54 - reserved, MBZ */ static u64 -tioce_dma_d64(unsigned long ct_addr) +tioce_dma_d64(unsigned long ct_addr, int dma_flags) { u64 bus_addr; bus_addr = ct_addr | (1UL << 63); + if (dma_flags & SN_DMA_MSI) + bus_addr |= (1UL << 61); return bus_addr; } @@ -261,7 +264,7 @@ pcidev_to_tioce(struct pci_dev *pdev, struct tioce **base, */ static u64 tioce_alloc_map(struct tioce_kernel *ce_kern, int type, int port, - u64 ct_addr, int len) + u64 ct_addr, int len, int dma_flags) { int i; int j; @@ -270,6 +273,7 @@ tioce_alloc_map(struct tioce_kernel *ce_kern, int type, int port, int entries; int nates; u64 pagesize; + int msi_capable, msi_wanted; u64 *ate_shadow; u64 *ate_reg; u64 addr; @@ -291,6 +295,7 @@ tioce_alloc_map(struct tioce_kernel *ce_kern, int type, int port, ate_reg = ce_mmr->ce_ure_ate3240; pagesize = ce_kern->ce_ate3240_pagesize; bus_base = TIOCE_M32_MIN; + msi_capable = 1; break; case TIOCE_ATE_M40: first = 0; @@ -299,6 +304,7 @@ tioce_alloc_map(struct tioce_kernel *ce_kern, int type, int port, ate_reg = ce_mmr->ce_ure_ate40; pagesize = MB(64); bus_base = TIOCE_M40_MIN; + msi_capable = 0; break; case TIOCE_ATE_M40S: /* @@ -311,11 +317,16 @@ tioce_alloc_map(struct tioce_kernel *ce_kern, int type, int port, ate_reg = ce_mmr->ce_ure_ate3240; pagesize = GB(16); bus_base = TIOCE_M40S_MIN; + msi_capable = 0; break; default: return 0; } + msi_wanted = dma_flags & SN_DMA_MSI; + if (msi_wanted && !msi_capable) + return 0; + nates = ATE_NPAGES(ct_addr, len, pagesize); if (nates > entries) return 0; @@ -344,7 +355,7 @@ tioce_alloc_map(struct tioce_kernel *ce_kern, int type, int port, for (j = 0; j < nates; j++) { u64 ate; - ate = ATE_MAKE(addr, pagesize); + ate = ATE_MAKE(addr, pagesize, msi_wanted); ate_shadow[i + j] = ate; tioce_mmr_storei(ce_kern, &ate_reg[i + j], ate); addr += pagesize; @@ -371,7 +382,7 @@ tioce_alloc_map(struct tioce_kernel *ce_kern, int type, int port, * Map @paddr into 32-bit bus space of the CE associated with @pcidev_info. */ static u64 -tioce_dma_d32(struct pci_dev *pdev, u64 ct_addr) +tioce_dma_d32(struct pci_dev *pdev, u64 ct_addr, int dma_flags) { int dma_ok; int port; @@ -381,6 +392,9 @@ tioce_dma_d32(struct pci_dev *pdev, u64 ct_addr) u64 ct_lower; dma_addr_t bus_addr; + if (dma_flags & SN_DMA_MSI) + return 0; + ct_upper = ct_addr & ~0x3fffffffUL; ct_lower = ct_addr & 0x3fffffffUL; @@ -507,7 +521,7 @@ tioce_dma_unmap(struct pci_dev *pdev, dma_addr_t bus_addr, int dir) */ static u64 tioce_do_dma_map(struct pci_dev *pdev, u64 paddr, size_t byte_count, - int barrier) + int barrier, int dma_flags) { unsigned long flags; u64 ct_addr; @@ -523,15 +537,18 @@ tioce_do_dma_map(struct pci_dev *pdev, u64 paddr, size_t byte_count, if (dma_mask < 0x7fffffffUL) return 0; - ct_addr = PHYS_TO_TIODMA(paddr); + if (SN_DMA_ADDRTYPE(dma_flags) == SN_DMA_ADDR_PHYS) + ct_addr = PHYS_TO_TIODMA(paddr); + else + ct_addr = paddr; /* * If the device can generate 64 bit addresses, create a D64 map. - * Since this should never fail, bypass the rest of the checks. */ if (dma_mask == ~0UL) { - mapaddr = tioce_dma_d64(ct_addr); - goto dma_map_done; + mapaddr = tioce_dma_d64(ct_addr, dma_flags); + if (mapaddr) + goto dma_map_done; } pcidev_to_tioce(pdev, NULL, &ce_kern, &port); @@ -574,18 +591,22 @@ tioce_do_dma_map(struct pci_dev *pdev, u64 paddr, size_t byte_count, if (byte_count > MB(64)) { mapaddr = tioce_alloc_map(ce_kern, TIOCE_ATE_M40S, - port, ct_addr, byte_count); + port, ct_addr, byte_count, + dma_flags); if (!mapaddr) mapaddr = tioce_alloc_map(ce_kern, TIOCE_ATE_M40, -1, - ct_addr, byte_count); + ct_addr, byte_count, + dma_flags); } else { mapaddr = tioce_alloc_map(ce_kern, TIOCE_ATE_M40, -1, - ct_addr, byte_count); + ct_addr, byte_count, + dma_flags); if (!mapaddr) mapaddr = tioce_alloc_map(ce_kern, TIOCE_ATE_M40S, - port, ct_addr, byte_count); + port, ct_addr, byte_count, + dma_flags); } } @@ -593,7 +614,7 @@ tioce_do_dma_map(struct pci_dev *pdev, u64 paddr, size_t byte_count, * 32-bit direct is the next mode to try */ if (!mapaddr && dma_mask >= 0xffffffffUL) - mapaddr = tioce_dma_d32(pdev, ct_addr); + mapaddr = tioce_dma_d32(pdev, ct_addr, dma_flags); /* * Last resort, try 32-bit ATE-based map. @@ -601,7 +622,7 @@ tioce_do_dma_map(struct pci_dev *pdev, u64 paddr, size_t byte_count, if (!mapaddr) mapaddr = tioce_alloc_map(ce_kern, TIOCE_ATE_M32, -1, ct_addr, - byte_count); + byte_count, dma_flags); spin_unlock_irqrestore(&ce_kern->ce_lock, flags); @@ -622,9 +643,9 @@ dma_map_done: * in the address. */ static u64 -tioce_dma(struct pci_dev *pdev, u64 paddr, size_t byte_count) +tioce_dma(struct pci_dev *pdev, u64 paddr, size_t byte_count, int dma_flags) { - return tioce_do_dma_map(pdev, paddr, byte_count, 0); + return tioce_do_dma_map(pdev, paddr, byte_count, 0, dma_flags); } /** @@ -636,9 +657,9 @@ tioce_dma(struct pci_dev *pdev, u64 paddr, size_t byte_count) * Simply call tioce_do_dma_map() to create a map with the barrier bit set * in the address. */ static u64 -tioce_dma_consistent(struct pci_dev *pdev, u64 paddr, size_t byte_count) +tioce_dma_consistent(struct pci_dev *pdev, u64 paddr, size_t byte_count, int dma_flags) { - return tioce_do_dma_map(pdev, paddr, byte_count, 1); + return tioce_do_dma_map(pdev, paddr, byte_count, 1, dma_flags); } /** @@ -696,7 +717,7 @@ tioce_reserve_m32(struct tioce_kernel *ce_kern, u64 base, u64 limit) while (ate_index <= last_ate) { u64 ate; - ate = ATE_MAKE(0xdeadbeef, ps); + ate = ATE_MAKE(0xdeadbeef, ps, 0); ce_kern->ce_ate3240_shadow[ate_index] = ate; tioce_mmr_storei(ce_kern, &ce_mmr->ce_ure_ate3240[ate_index], ate); @@ -1002,11 +1023,11 @@ tioce_bus_fixup(struct pcibus_bussoft *prom_bussoft, struct pci_controller *cont tioce_mmr_seti(tioce_kern, &tioce_mmr->ce_adm_int_status_alias, ~0ULL); tioce_mmr_seti(tioce_kern, &tioce_mmr->ce_adm_error_summary_alias, ~0ULL); - tioce_mmr_seti(tioce_kern, &tioce_mmr->ce_dre_comp_err_addr, ~0ULL); + tioce_mmr_seti(tioce_kern, &tioce_mmr->ce_dre_comp_err_addr, 0ULL); if (request_irq(SGI_PCIASIC_ERROR, tioce_error_intr_handler, - SA_SHIRQ, "TIOCE error", (void *)tioce_common)) + IRQF_SHARED, "TIOCE error", (void *)tioce_common)) printk(KERN_WARNING "%s: Unable to get irq %d. " "Error interrupts won't be routed for " |
