diff options
Diffstat (limited to 'arch')
78 files changed, 1108 insertions, 6645 deletions
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index 8c71daf94a5..9fee37e2596 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -75,6 +75,7 @@ osf_set_program_attributes(unsigned long text_start, unsigned long text_len, lock_kernel(); mm = current->mm; mm->end_code = bss_start + bss_len; + mm->start_brk = bss_start + bss_len; mm->brk = bss_start + bss_len; #if 0 printk("set_program_attributes(%lx %lx %lx %lx)\n", diff --git a/arch/alpha/kernel/pci.c b/arch/alpha/kernel/pci.c index c107cc08daf..78357798b6f 100644 --- a/arch/alpha/kernel/pci.c +++ b/arch/alpha/kernel/pci.c @@ -71,25 +71,13 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82378, quirk_i static void __init quirk_cypress(struct pci_dev *dev) { - /* The Notorious Cy82C693 chip. */ - - /* The Cypress IDE controller doesn't support native mode, but it - has programmable addresses of IDE command/control registers. - This violates PCI specifications, confuses the IDE subsystem and - causes resource conflicts between the primary HD_CMD register and - the floppy controller. Ugh. Fix that. */ - if (dev->class >> 8 == PCI_CLASS_STORAGE_IDE) { - dev->resource[0].flags = 0; - dev->resource[1].flags = 0; - } - /* The Cypress bridge responds on the PCI bus in the address range 0xffff0000-0xffffffff (conventional x86 BIOS ROM). There is no way to turn this off. The bridge also supports several extended BIOS ranges (disabled after power-up), and some consoles do turn them on. So if we use a large direct-map window, or a large SG window, we must avoid the entire 0xfff00000-0xffffffff region. */ - else if (dev->class >> 8 == PCI_CLASS_BRIDGE_ISA) { + if (dev->class >> 8 == PCI_CLASS_BRIDGE_ISA) { if (__direct_map_base + __direct_map_size >= 0xfff00000UL) __direct_map_size = 0xfff00000UL - __direct_map_base; else { @@ -391,7 +379,7 @@ pcibios_set_master(struct pci_dev *dev) pci_write_config_byte(dev, PCI_LATENCY_TIMER, 64); } -static void __init +void __init pcibios_claim_one_bus(struct pci_bus *b) { struct pci_dev *dev; @@ -405,7 +393,8 @@ pcibios_claim_one_bus(struct pci_bus *b) if (r->parent || !r->start || !r->flags) continue; - pci_claim_resource(dev, i); + if (pci_probe_only || (r->flags & IORESOURCE_PCI_FIXED)) + pci_claim_resource(dev, i); } } @@ -444,8 +433,7 @@ common_init_pci(void) } } - if (pci_probe_only) - pcibios_claim_console_setup(); + pcibios_claim_console_setup(); pci_assign_unassigned_resources(); pci_fixup_irqs(alpha_mv.pci_swizzle, alpha_mv.pci_map_irq); diff --git a/arch/alpha/kernel/sys_nautilus.c b/arch/alpha/kernel/sys_nautilus.c index 920196bcbb6..a7f23b5ab81 100644 --- a/arch/alpha/kernel/sys_nautilus.c +++ b/arch/alpha/kernel/sys_nautilus.c @@ -187,6 +187,7 @@ nautilus_machine_check(unsigned long vector, unsigned long la_ptr) } extern void free_reserved_mem(void *, void *); +extern void pcibios_claim_one_bus(struct pci_bus *); static struct resource irongate_mem = { .name = "Irongate PCI MEM", @@ -205,6 +206,7 @@ nautilus_init_pci(void) /* Scan our single hose. */ bus = pci_scan_bus(0, alpha_mv.pci_ops, hose); hose->bus = bus; + pcibios_claim_one_bus(bus); irongate = pci_get_bus_and_slot(0, 0); bus->self = irongate; diff --git a/arch/arm/mach-lh7a40x/arch-kev7a400.c b/arch/arm/mach-lh7a40x/arch-kev7a400.c index 6d26661d99f..2ef7d0097b3 100644 --- a/arch/arm/mach-lh7a40x/arch-kev7a400.c +++ b/arch/arm/mach-lh7a40x/arch-kev7a400.c @@ -75,10 +75,9 @@ static void kev7a400_cpld_handler (unsigned int irq, struct irq_desc *desc) { u32 mask = CPLD_LATCHED_INTS; irq = IRQ_KEV7A400_CPLD; - for (; mask; mask >>= 1, ++irq) { + for (; mask; mask >>= 1, ++irq) if (mask & 1) - desc[irq].handle (irq, desc); - } + desc_handle_irq(irq, desc); } void __init lh7a40x_init_board_irq (void) diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index 746cbb7c8e9..1b8229d9c9d 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -32,6 +32,7 @@ config CPU_ARM7TDMI depends on !MMU select CPU_32v4T select CPU_ABRT_LV4T + select CPU_PABRT_NOIFAR select CPU_CACHE_V4 help A 32-bit RISC microprocessor based on the ARM7 processor core @@ -85,6 +86,7 @@ config CPU_ARM740T depends on !MMU select CPU_32v4T select CPU_ABRT_LV4T + select CPU_PABRT_NOIFAR select CPU_CACHE_V3 # although the core is v4t select CPU_CP15_MPU help @@ -101,6 +103,7 @@ config CPU_ARM9TDMI depends on !MMU select CPU_32v4T select CPU_ABRT_NOMMU + select CPU_PABRT_NOIFAR select CPU_CACHE_V4 help A 32-bit RISC microprocessor based on the ARM9 processor core @@ -200,6 +203,7 @@ config CPU_ARM940T depends on !MMU select CPU_32v4T select CPU_ABRT_NOMMU + select CPU_PABRT_NOIFAR select CPU_CACHE_VIVT select CPU_CP15_MPU help @@ -217,6 +221,7 @@ config CPU_ARM946E depends on !MMU select CPU_32v5 select CPU_ABRT_NOMMU + select CPU_PABRT_NOIFAR select CPU_CACHE_VIVT select CPU_CP15_MPU help @@ -351,6 +356,7 @@ config CPU_XSC3 default y select CPU_32v5 select CPU_ABRT_EV5T + select CPU_PABRT_NOIFAR select CPU_CACHE_VIVT select CPU_CP15_MMU select CPU_TLB_V4WBI if MMU diff --git a/arch/arm/mm/proc-arm1020.S b/arch/arm/mm/proc-arm1020.S index 32fd7ea533f..5673f4d6113 100644 --- a/arch/arm/mm/proc-arm1020.S +++ b/arch/arm/mm/proc-arm1020.S @@ -471,6 +471,7 @@ arm1020_crval: .type arm1020_processor_functions, #object arm1020_processor_functions: .word v4t_early_abort + .word pabort_noifar .word cpu_arm1020_proc_init .word cpu_arm1020_proc_fin .word cpu_arm1020_reset @@ -478,7 +479,6 @@ arm1020_processor_functions: .word cpu_arm1020_dcache_clean_area .word cpu_arm1020_switch_mm .word cpu_arm1020_set_pte_ext - .word pabort_noifar .size arm1020_processor_functions, . - arm1020_processor_functions .section ".rodata" diff --git a/arch/arm/mm/proc-arm1020e.S b/arch/arm/mm/proc-arm1020e.S index fe2b0ae7027..4343fdb0e9e 100644 --- a/arch/arm/mm/proc-arm1020e.S +++ b/arch/arm/mm/proc-arm1020e.S @@ -452,6 +452,7 @@ arm1020e_crval: .type arm1020e_processor_functions, #object arm1020e_processor_functions: .word v4t_early_abort + .word pabort_noifar .word cpu_arm1020e_proc_init .word cpu_arm1020e_proc_fin .word cpu_arm1020e_reset @@ -459,7 +460,6 @@ arm1020e_processor_functions: .word cpu_arm1020e_dcache_clean_area .word cpu_arm1020e_switch_mm .word cpu_arm1020e_set_pte_ext - .word pabort_noifar .size arm1020e_processor_functions, . - arm1020e_processor_functions .section ".rodata" diff --git a/arch/arm/mm/proc-arm1022.S b/arch/arm/mm/proc-arm1022.S index 06dde678e19..2a4ea1659e9 100644 --- a/arch/arm/mm/proc-arm1022.S +++ b/arch/arm/mm/proc-arm1022.S @@ -435,6 +435,7 @@ arm1022_crval: .type arm1022_processor_functions, #object arm1022_processor_functions: .word v4t_early_abort + .word pabort_noifar .word cpu_arm1022_proc_init .word cpu_arm1022_proc_fin .word cpu_arm1022_reset @@ -442,7 +443,6 @@ arm1022_processor_functions: .word cpu_arm1022_dcache_clean_area .word cpu_arm1022_switch_mm .word cpu_arm1022_set_pte_ext - .word pabort_noifar .size arm1022_processor_functions, . - arm1022_processor_functions .section ".rodata" diff --git a/arch/arm/mm/proc-arm1026.S b/arch/arm/mm/proc-arm1026.S index f5506e6e681..77a1babd421 100644 --- a/arch/arm/mm/proc-arm1026.S +++ b/arch/arm/mm/proc-arm1026.S @@ -430,6 +430,7 @@ arm1026_crval: .type arm1026_processor_functions, #object arm1026_processor_functions: .word v5t_early_abort + .word pabort_noifar .word cpu_arm1026_proc_init .word cpu_arm1026_proc_fin .word cpu_arm1026_reset @@ -437,7 +438,6 @@ arm1026_processor_functions: .word cpu_arm1026_dcache_clean_area .word cpu_arm1026_switch_mm .word cpu_arm1026_set_pte_ext - .word pabort_noifar .size arm1026_processor_functions, . - arm1026_processor_functions .section .rodata diff --git a/arch/arm/mm/proc-arm6_7.S b/arch/arm/mm/proc-arm6_7.S index 14b6a95c8d4..c371fc87776 100644 --- a/arch/arm/mm/proc-arm6_7.S +++ b/arch/arm/mm/proc-arm6_7.S @@ -293,6 +293,7 @@ __arm7_setup: mov r0, #0 .type arm6_processor_functions, #object ENTRY(arm6_processor_functions) .word cpu_arm6_data_abort + .word pabort_noifar .word cpu_arm6_proc_init .word cpu_arm6_proc_fin .word cpu_arm6_reset @@ -300,7 +301,6 @@ ENTRY(arm6_processor_functions) .word cpu_arm6_dcache_clean_area .word cpu_arm6_switch_mm .word cpu_arm6_set_pte_ext - .word pabort_noifar .size arm6_processor_functions, . - arm6_processor_functions /* @@ -310,6 +310,7 @@ ENTRY(arm6_processor_functions) .type arm7_processor_functions, #object ENTRY(arm7_processor_functions) .word cpu_arm7_data_abort + .word pabort_noifar .word cpu_arm7_proc_init .word cpu_arm7_proc_fin .word cpu_arm7_reset @@ -317,7 +318,6 @@ ENTRY(arm7_processor_functions) .word cpu_arm7_dcache_clean_area .word cpu_arm7_switch_mm .word cpu_arm7_set_pte_ext - .word pabort_noifar .size arm7_processor_functions, . - arm7_processor_functions .section ".rodata" diff --git a/arch/arm/mm/proc-arm720.S b/arch/arm/mm/proc-arm720.S index ca5e7aac2da..d64f8e6f75a 100644 --- a/arch/arm/mm/proc-arm720.S +++ b/arch/arm/mm/proc-arm720.S @@ -198,6 +198,7 @@ arm720_crval: .type arm720_processor_functions, #object ENTRY(arm720_processor_functions) .word v4t_late_abort + .word pabort_noifar .word cpu_arm720_proc_init .word cpu_arm720_proc_fin .word cpu_arm720_reset @@ -205,7 +206,6 @@ ENTRY(arm720_processor_functions) .word cpu_arm720_dcache_clean_area .word cpu_arm720_switch_mm .word cpu_arm720_set_pte_ext - .word pabort_noifar .size arm720_processor_functions, . - arm720_processor_functions .section ".rodata" diff --git a/arch/arm/mm/proc-arm740.S b/arch/arm/mm/proc-arm740.S index 7069f495cf9..3a57376c8bc 100644 --- a/arch/arm/mm/proc-arm740.S +++ b/arch/arm/mm/proc-arm740.S @@ -126,6 +126,7 @@ __arm740_setup: .type arm740_processor_functions, #object ENTRY(arm740_processor_functions) .word v4t_late_abort + .word pabort_noifar .word cpu_arm740_proc_init .word cpu_arm740_proc_fin .word cpu_arm740_reset diff --git a/arch/arm/mm/proc-arm7tdmi.S b/arch/arm/mm/proc-arm7tdmi.S index d091c257182..7b3ecdeb537 100644 --- a/arch/arm/mm/proc-arm7tdmi.S +++ b/arch/arm/mm/proc-arm7tdmi.S @@ -64,6 +64,7 @@ __arm7tdmi_setup: .type arm7tdmi_processor_functions, #object ENTRY(arm7tdmi_processor_functions) .word v4t_late_abort + .word pabort_noifar .word cpu_arm7tdmi_proc_init .word cpu_arm7tdmi_proc_fin .word cpu_arm7tdmi_reset diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S index 0170d4f466e..28cdb060df4 100644 --- a/arch/arm/mm/proc-arm920.S +++ b/arch/arm/mm/proc-arm920.S @@ -417,6 +417,7 @@ arm920_crval: .type arm920_processor_functions, #object arm920_processor_functions: .word v4t_early_abort + .word pabort_noifar .word cpu_arm920_proc_init .word cpu_arm920_proc_fin .word cpu_arm920_reset @@ -424,7 +425,6 @@ arm920_processor_functions: .word cpu_arm920_dcache_clean_area .word cpu_arm920_switch_mm .word cpu_arm920_set_pte_ext - .word pabort_noifar .size arm920_processor_functions, . - arm920_processor_functions .section ".rodata" diff --git a/arch/arm/mm/proc-arm922.S b/arch/arm/mm/proc-arm922.S index b7952493d40..94ddcb4a4b7 100644 --- a/arch/arm/mm/proc-arm922.S +++ b/arch/arm/mm/proc-arm922.S @@ -421,6 +421,7 @@ arm922_crval: .type arm922_processor_functions, #object arm922_processor_functions: .word v4t_early_abort + .word pabort_noifar .word cpu_arm922_proc_init .word cpu_arm922_proc_fin .word cpu_arm922_reset @@ -428,7 +429,6 @@ arm922_processor_functions: .word cpu_arm922_dcache_clean_area .word cpu_arm922_switch_mm .word cpu_arm922_set_pte_ext - .word pabort_noifar .size arm922_processor_functions, . - arm922_processor_functions .section ".rodata" diff --git a/arch/arm/mm/proc-arm925.S b/arch/arm/mm/proc-arm925.S index e2988eba4cf..065087afb77 100644 --- a/arch/arm/mm/proc-arm925.S +++ b/arch/arm/mm/proc-arm925.S @@ -484,6 +484,7 @@ arm925_crval: .type arm925_processor_functions, #object arm925_processor_functions: .word v4t_early_abort + .word pabort_noifar .word cpu_arm925_proc_init .word cpu_arm925_proc_fin .word cpu_arm925_reset @@ -491,7 +492,6 @@ arm925_processor_functions: .word cpu_arm925_dcache_clean_area .word cpu_arm925_switch_mm .word cpu_arm925_set_pte_ext - .word pabort_noifar .size arm925_processor_functions, . - arm925_processor_functions .section ".rodata" diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S index 62f7d1dfe01..997db8472b5 100644 --- a/arch/arm/mm/proc-arm926.S +++ b/arch/arm/mm/proc-arm926.S @@ -437,6 +437,7 @@ arm926_crval: .type arm926_processor_functions, #object arm926_processor_functions: .word v5tj_early_abort + .word pabort_noifar .word cpu_arm926_proc_init .word cpu_arm926_proc_fin .word cpu_arm926_reset @@ -444,7 +445,6 @@ arm926_processor_functions: .word cpu_arm926_dcache_clean_area .word cpu_arm926_switch_mm .word cpu_arm926_set_pte_ext - .word pabort_noifar .size arm926_processor_functions, . - arm926_processor_functions .section ".rodata" diff --git a/arch/arm/mm/proc-arm940.S b/arch/arm/mm/proc-arm940.S index 786c593778f..44ead902bd5 100644 --- a/arch/arm/mm/proc-arm940.S +++ b/arch/arm/mm/proc-arm940.S @@ -321,6 +321,7 @@ __arm940_setup: .type arm940_processor_functions, #object ENTRY(arm940_processor_functions) .word nommu_early_abort + .word pabort_noifar .word cpu_arm940_proc_init .word cpu_arm940_proc_fin .word cpu_arm940_reset diff --git a/arch/arm/mm/proc-arm946.S b/arch/arm/mm/proc-arm946.S index a60c1421d45..2218b0c0133 100644 --- a/arch/arm/mm/proc-arm946.S +++ b/arch/arm/mm/proc-arm946.S @@ -376,6 +376,7 @@ __arm946_setup: .type arm946_processor_functions, #object ENTRY(arm946_processor_functions) .word nommu_early_abort + .word pabort_noifar .word cpu_arm946_proc_init .word cpu_arm946_proc_fin .word cpu_arm946_reset diff --git a/arch/arm/mm/proc-arm9tdmi.S b/arch/arm/mm/proc-arm9tdmi.S index 4848eeac86b..c85c1f50e39 100644 --- a/arch/arm/mm/proc-arm9tdmi.S +++ b/arch/arm/mm/proc-arm9tdmi.S @@ -64,6 +64,7 @@ __arm9tdmi_setup: .type arm9tdmi_processor_functions, #object ENTRY(arm9tdmi_processor_functions) .word nommu_early_abort + .word pabort_noifar .word cpu_arm9tdmi_proc_init .word cpu_arm9tdmi_proc_fin .word cpu_arm9tdmi_reset diff --git a/arch/arm/mm/proc-feroceon.S b/arch/arm/mm/proc-feroceon.S index 2f169b28e93..90e7594e29b 100644 --- a/arch/arm/mm/proc-feroceon.S +++ b/arch/arm/mm/proc-feroceon.S @@ -423,6 +423,7 @@ feroceon_crval: .type feroceon_processor_functions, #object feroceon_processor_functions: .word v5t_early_abort + .word pabort_noifar .word cpu_feroceon_proc_init .word cpu_feroceon_proc_fin .word cpu_feroceon_reset @@ -430,7 +431,6 @@ feroceon_processor_functions: .word cpu_feroceon_dcache_clean_area .word cpu_feroceon_switch_mm .word cpu_feroceon_set_pte_ext - .word pabort_noifar .size feroceon_processor_functions, . - feroceon_processor_functions .section ".rodata" diff --git a/arch/arm/mm/proc-sa110.S b/arch/arm/mm/proc-sa110.S index 4db3d6299a2..9818195dbf1 100644 --- a/arch/arm/mm/proc-sa110.S +++ b/arch/arm/mm/proc-sa110.S @@ -216,6 +216,7 @@ sa110_crval: .type sa110_processor_functions, #object ENTRY(sa110_processor_functions) .word v4_early_abort + .word pabort_noifar .word cpu_sa110_proc_init .word cpu_sa110_proc_fin .word cpu_sa110_reset @@ -223,7 +224,6 @@ ENTRY(sa110_processor_functions) .word cpu_sa110_dcache_clean_area .word cpu_sa110_switch_mm .word cpu_sa110_set_pte_ext - .word pabort_noifar .size sa110_processor_functions, . - sa110_processor_functions .section ".rodata" diff --git a/arch/arm/mm/proc-sa1100.S b/arch/arm/mm/proc-sa1100.S index 3cdef043760..c5fe27ad289 100644 --- a/arch/arm/mm/proc-sa1100.S +++ b/arch/arm/mm/proc-sa1100.S @@ -231,6 +231,7 @@ sa1100_crval: .type sa1100_processor_functions, #object ENTRY(sa1100_processor_functions) .word v4_early_abort + .word pabort_noifar .word cpu_sa1100_proc_init .word cpu_sa1100_proc_fin .word cpu_sa1100_reset @@ -238,7 +239,6 @@ ENTRY(sa1100_processor_functions) .word cpu_sa1100_dcache_clean_area .word cpu_sa1100_switch_mm .word cpu_sa1100_set_pte_ext - .word pabort_noifar .size sa1100_processor_functions, . - sa1100_processor_functions .section ".rodata" diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S index bf760ea2f78..5702ec58b2a 100644 --- a/arch/arm/mm/proc-v6.S +++ b/arch/arm/mm/proc-v6.S @@ -219,6 +219,7 @@ v6_crval: .type v6_processor_functions, #object ENTRY(v6_processor_functions) .word v6_early_abort + .word pabort_noifar .word cpu_v6_proc_init .word cpu_v6_proc_fin .word cpu_v6_reset @@ -226,7 +227,6 @@ ENTRY(v6_processor_functions) .word cpu_v6_dcache_clean_area .word cpu_v6_switch_mm .word cpu_v6_set_pte_ext - .word pabort_noifar .size v6_processor_functions, . - v6_processor_functions .type cpu_arch_name, #object diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index a1d7331cd64..b49f9a4c82c 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -205,6 +205,7 @@ __v7_setup_stack: .type v7_processor_functions, #object ENTRY(v7_processor_functions) .word v7_early_abort + .word pabort_ifar .word cpu_v7_proc_init .word cpu_v7_proc_fin .word cpu_v7_reset @@ -212,7 +213,6 @@ ENTRY(v7_processor_functions) .word cpu_v7_dcache_clean_area .word cpu_v7_switch_mm .word cpu_v7_set_pte_ext - .word pabort_ifar .size v7_processor_functions, . - v7_processor_functions .type cpu_arch_name, #object diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S index d95921a2ab9..3533741a76f 100644 --- a/arch/arm/mm/proc-xsc3.S +++ b/arch/arm/mm/proc-xsc3.S @@ -450,6 +450,7 @@ xsc3_crval: .type xsc3_processor_functions, #object ENTRY(xsc3_processor_functions) .word v5t_early_abort + .word pabort_noifar .word cpu_xsc3_proc_init .word cpu_xsc3_proc_fin .word cpu_xsc3_reset diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S index 1a6d89823df..2dd85273976 100644 --- a/arch/arm/mm/proc-xscale.S +++ b/arch/arm/mm/proc-xscale.S @@ -527,6 +527,7 @@ xscale_crval: .type xscale_processor_functions, #object ENTRY(xscale_processor_functions) .word v5t_early_abort + .word pabort_noifar .word cpu_xscale_proc_init .word cpu_xscale_proc_fin .word cpu_xscale_reset @@ -534,7 +535,6 @@ ENTRY(xscale_processor_functions) .word cpu_xscale_dcache_clean_area .word cpu_xscale_switch_mm .word cpu_xscale_set_pte_ext - .word pabort_noifar .size xscale_processor_functions, . - xscale_processor_functions .section ".rodata" diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index ed21737a00c..cd13e138bd0 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -266,17 +266,6 @@ config IOSAPIC depends on !IA64_HP_SIM default y -config IA64_SGI_SN_XP - tristate "Support communication between SGI SSIs" - depends on IA64_GENERIC || IA64_SGI_SN2 - select IA64_UNCACHED_ALLOCATOR - help - An SGI machine can be divided into multiple Single System - Images which act independently of each other and have - hardware based memory protection from the others. Enabling - this feature will allow for direct communication between SSIs - based on a network adapter and DMA messaging. - config FORCE_MAX_ZONEORDER int "MAX_ORDER (11 - 17)" if !HUGETLB_PAGE range 11 17 if !HUGETLB_PAGE diff --git a/arch/ia64/kernel/crash.c b/arch/ia64/kernel/crash.c index 90ef338cf46..f065093f8e9 100644 --- a/arch/ia64/kernel/crash.c +++ b/arch/ia64/kernel/crash.c @@ -194,8 +194,8 @@ kdump_init_notifier(struct notifier_block *self, unsigned long val, void *data) unw_init_running(kdump_cpu_freeze, NULL); break; case DIE_MCA_MONARCH_LEAVE: - /* die_register->signr indicate if MCA is recoverable */ - if (kdump_on_fatal_mca && !args->signr) { + /* *(nd->data) indicate if MCA is recoverable */ + if (kdump_on_fatal_mca && !(*(nd->data))) { atomic_set(&kdump_in_progress, 1); *(nd->monarch_cpu) = -1; machine_kdump_on_init(); diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S index b0be4a28017..e49ad8c5dc6 100644 --- a/arch/ia64/kernel/entry.S +++ b/arch/ia64/kernel/entry.S @@ -570,6 +570,7 @@ GLOBAL_ENTRY(ia64_trace_syscall) br.call.sptk.many rp=syscall_trace_leave // give parent a chance to catch return value .ret3: (pUStk) cmp.eq.unc p6,p0=r0,r0 // p6 <- pUStk +(pUStk) rsm psr.i // disable interrupts br.cond.sptk .work_pending_syscall_end strace_error: diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c index e51bced3b0f..705176b434b 100644 --- a/arch/ia64/kernel/mca.c +++ b/arch/ia64/kernel/mca.c @@ -109,6 +109,20 @@ # define IA64_MCA_DEBUG(fmt...) #endif +#define NOTIFY_INIT(event, regs, arg, spin) \ +do { \ + if ((notify_die((event), "INIT", (regs), (arg), 0, 0) \ + == NOTIFY_STOP) && ((spin) == 1)) \ + ia64_mca_spin(__func__); \ +} while (0) + +#define NOTIFY_MCA(event, regs, arg, spin) \ +do { \ + if ((notify_die((event), "MCA", (regs), (arg), 0, 0) \ + == NOTIFY_STOP) && ((spin) == 1)) \ + ia64_mca_spin(__func__); \ +} while (0) + /* Used by mca_asm.S */ DEFINE_PER_CPU(u64, ia64_mca_data); /* == __per_cpu_mca[smp_processor_id()] */ DEFINE_PER_CPU(u64, ia64_mca_per_cpu_pte); /* PTE to map per-CPU area */ @@ -766,9 +780,8 @@ ia64_mca_rendez_int_handler(int rendez_irq, void *arg) /* Mask all interrupts */ local_irq_save(flags); - if (notify_die(DIE_MCA_RENDZVOUS_ENTER, "MCA", get_irq_regs(), - (long)&nd, 0, 0) == NOTIFY_STOP) - ia64_mca_spin(__func__); + + NOTIFY_MCA(DIE_MCA_RENDZVOUS_ENTER, get_irq_regs(), (long)&nd, 1); ia64_mc_info.imi_rendez_checkin[cpu] = IA64_MCA_RENDEZ_CHECKIN_DONE; /* Register with the SAL monarch that the slave has @@ -776,17 +789,13 @@ ia64_mca_rendez_int_handler(int rendez_irq, void *arg) */ ia64_sal_mc_rendez(); - if (notify_die(DIE_MCA_RENDZVOUS_PROCESS, "MCA", get_irq_regs(), - (long)&nd, 0, 0) == NOTIFY_STOP) - ia64_mca_spin(__func__); + NOTIFY_MCA(DIE_MCA_RENDZVOUS_PROCESS, get_irq_regs(), (long)&nd, 1); /* Wait for the monarch cpu to exit. */ while (monarch_cpu != -1) cpu_relax(); /* spin until monarch leaves */ - if (notify_die(DIE_MCA_RENDZVOUS_LEAVE, "MCA", get_irq_regs(), - (long)&nd, 0, 0) == NOTIFY_STOP) - ia64_mca_spin(__func__); + NOTIFY_MCA(DIE_MCA_RENDZVOUS_LEAVE, get_irq_regs(), (long)&nd, 1); ia64_mc_info.imi_rendez_checkin[cpu] = IA64_MCA_RENDEZ_CHECKIN_NOTDONE; /* Enable all interrupts */ @@ -1256,7 +1265,7 @@ ia64_mca_handler(struct pt_regs *regs, struct switch_stack *sw, int recover, cpu = smp_processor_id(); struct task_struct *previous_current; struct ia64_mca_notify_die nd = - { .sos = sos, .monarch_cpu = &monarch_cpu }; + { .sos = sos, .monarch_cpu = &monarch_cpu, .data = &recover }; static atomic_t mca_count; static cpumask_t mca_cpu; @@ -1272,9 +1281,7 @@ ia64_mca_handler(struct pt_regs *regs, struct switch_stack *sw, previous_current = ia64_mca_modify_original_stack(regs, sw, sos, "MCA"); - if (notify_die(DIE_MCA_MONARCH_ENTER, "MCA", regs, (long)&nd, 0, 0) - == NOTIFY_STOP) - ia64_mca_spin(__func__); + NOTIFY_MCA(DIE_MCA_MONARCH_ENTER, regs, (long)&nd, 1); ia64_mc_info.imi_rendez_checkin[cpu] = IA64_MCA_RENDEZ_CHECKIN_CONCURRENT_MCA; if (sos->monarch) { @@ -1288,13 +1295,12 @@ ia64_mca_handler(struct pt_regs *regs, struct switch_stack *sw, * does not work. */ ia64_mca_wakeup_all(); - if (notify_die(DIE_MCA_MONARCH_PROCESS, "MCA", regs, (long)&nd, 0, 0) - == NOTIFY_STOP) - ia64_mca_spin(__func__); } else { while (cpu_isset(cpu, mca_cpu)) cpu_relax(); /* spin until monarch wakes us */ - } + } + + NOTIFY_MCA(DIE_MCA_MONARCH_PROCESS, regs, (long)&nd, 1); /* Get the MCA error record and log it */ ia64_mca_log_sal_error_record(SAL_INFO_TYPE_MCA); @@ -1320,9 +1326,7 @@ ia64_mca_handler(struct pt_regs *regs, struct switch_stack *sw, mca_insert_tr(0x2); /*Reload dynamic itrs*/ } - if (notify_die(DIE_MCA_MONARCH_LEAVE, "MCA", regs, (long)&nd, 0, recover) - == NOTIFY_STOP) - ia64_mca_spin(__func__); + NOTIFY_MCA(DIE_MCA_MONARCH_LEAVE, regs, (long)&nd, 1); if (atomic_dec_return(&mca_count) > 0) { int i; @@ -1643,7 +1647,7 @@ ia64_init_handler(struct pt_regs *regs, struct switch_stack *sw, struct ia64_mca_notify_die nd = { .sos = sos, .monarch_cpu = &monarch_cpu }; - (void) notify_die(DIE_INIT_ENTER, "INIT", regs, (long)&nd, 0, 0); + NOTIFY_INIT(DIE_INIT_ENTER, regs, (long)&nd, 0); mprintk(KERN_INFO "Entered OS INIT handler. PSP=%lx cpu=%d monarch=%ld\n", sos->proc_state_param, cpu, sos->monarch); @@ -1680,17 +1684,15 @@ ia64_init_handler(struct pt_regs *regs, struct switch_stack *sw, ia64_mc_info.imi_rendez_checkin[cpu] = IA64_MCA_RENDEZ_CHECKIN_INIT; while (monarch_cpu == -1) cpu_relax(); /* spin until monarch enters */ - if (notify_die(DIE_INIT_SLAVE_ENTER, "INIT", regs, (long)&nd, 0, 0) - == NOTIFY_STOP) - ia64_mca_spin(__func__); - if (notify_die(DIE_INIT_SLAVE_PROCESS, "INIT", regs, (long)&nd, 0, 0) - == NOTIFY_STOP) - ia64_mca_spin(__func__); + + NOTIFY_INIT(DIE_INIT_SLAVE_ENTER, regs, (long)&nd, 1); + NOTIFY_INIT(DIE_INIT_SLAVE_PROCESS, regs, (long)&nd, 1); + while (monarch_cpu != -1) cpu_relax(); /* spin until monarch leaves */ - if (notify_die(DIE_INIT_SLAVE_LEAVE, "INIT", regs, (long)&nd, 0, 0) - == NOTIFY_STOP) - ia64_mca_spin(__func__); + + NOTIFY_INIT(DIE_INIT_SLAVE_LEAVE, regs, (long)&nd, 1); + mprintk("Slave on cpu %d returning to normal service.\n", cpu); set_curr_task(cpu, previous_current); ia64_mc_info.imi_rendez_checkin[cpu] = IA64_MCA_RENDEZ_CHECKIN_NOTDONE; @@ -1699,9 +1701,7 @@ ia64_init_handler(struct pt_regs *regs, struct switch_stack *sw, } monarch_cpu = cpu; - if (notify_die(DIE_INIT_MONARCH_ENTER, "INIT", regs, (long)&nd, 0, 0) - == NOTIFY_STOP) - ia64_mca_spin(__func__); + NOTIFY_INIT(DIE_INIT_MONARCH_ENTER, regs, (long)&nd, 1); /* * Wait for a bit. On some machines (e.g., HP's zx2000 and zx6000, INIT can be @@ -1716,12 +1716,9 @@ ia64_init_handler(struct pt_regs *regs, struct switch_stack *sw, * to default_monarch_init_process() above and just print all the * tasks. */ - if (notify_die(DIE_INIT_MONARCH_PROCESS, "INIT", regs, (long)&nd, 0, 0) - == NOTIFY_STOP) - ia64_mca_spin(__func__); - if (notify_die(DIE_INIT_MONARCH_LEAVE, "INIT", regs, (long)&nd, 0, 0) - == NOTIFY_STOP) - ia64_mca_spin(__func__); + NOTIFY_INIT(DIE_INIT_MONARCH_PROCESS, regs, (long)&nd, 1); + NOTIFY_INIT(DIE_INIT_MONARCH_LEAVE, regs, (long)&nd, 1); + mprintk("\nINIT dump complete. Monarch on cpu %d returning to normal service.\n", cpu); atomic_dec(&monarchs); set_curr_task(cpu, previous_current); @@ -1953,7 +1950,7 @@ ia64_mca_init(void) printk(KERN_INFO "Increasing MCA rendezvous timeout from " "%ld to %ld milliseconds\n", timeout, isrv.v0); timeout = isrv.v0; - (void) notify_die(DIE_MCA_NEW_TIMEOUT, "MCA", NULL, timeout, 0, 0); + NOTIFY_MCA(DIE_MCA_NEW_TIMEOUT, NULL, timeout, 0); continue; } printk(KERN_ERR "Failed to register rendezvous interrupt " diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index d1d24f4598d..c8e403752a0 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -5511,7 +5511,7 @@ stop_monitoring: } static int -pfm_do_interrupt_handler(int irq, void *arg, struct pt_regs *regs) +pfm_do_interrupt_handler(void *arg, struct pt_regs *regs) { struct task_struct *task; pfm_context_t *ctx; @@ -5591,7 +5591,7 @@ pfm_interrupt_handler(int irq, void *arg) start_cycles = ia64_get_itc(); - ret = pfm_do_interrupt_handler(irq, arg, regs); + ret = pfm_do_interrupt_handler(arg, regs); total_cycles = ia64_get_itc(); diff --git a/arch/ia64/sn/kernel/Makefile b/arch/ia64/sn/kernel/Makefile index 688a3c27e0f..0591038735a 100644 --- a/arch/ia64/sn/kernel/Makefile +++ b/arch/ia64/sn/kernel/Makefile @@ -4,7 +4,7 @@ # License. See the file "COPYING" in the main directory of this archive # for more details. # -# Copyright (C) 1999,2001-2006 Silicon Graphics, Inc. All Rights Reserved. +# Copyright (C) 1999,2001-2006,2008 Silicon Graphics, Inc. All Rights Reserved. # EXTRA_CFLAGS += -Iarch/ia64/sn/include @@ -15,9 +15,4 @@ obj-y += setup.o bte.o bte_error.o irq.o mca.o idle.o \ sn2/ obj-$(CONFIG_IA64_GENERIC) += machvec.o obj-$(CONFIG_SGI_TIOCX) += tiocx.o -obj-$(CONFIG_IA64_SGI_SN_XP) += xp.o -xp-y := xp_main.o xp_nofault.o -obj-$(CONFIG_IA64_SGI_SN_XP) += xpc.o -xpc-y := xpc_main.o xpc_channel.o xpc_partition.o -obj-$(CONFIG_IA64_SGI_SN_XP) += xpnet.o obj-$(CONFIG_PCI_MSI) += msi_sn.o diff --git a/arch/ia64/sn/kernel/huberror.c b/arch/ia64/sn/kernel/huberror.c index 0101c7924a4..08b0d9bb62e 100644 --- a/arch/ia64/sn/kernel/huberror.c +++ b/arch/ia64/sn/kernel/huberror.c @@ -187,8 +187,8 @@ void hub_error_init(struct hubdev_info *hubdev_info) { if (request_irq(SGI_II_ERROR, hub_eint_handler, IRQF_SHARED, - "SN_hub_error", (void *)hubdev_info)) { - printk("hub_error_init: Failed to request_irq for 0x%p\n", + "SN_hub_error", hubdev_info)) { + printk(KERN_ERR "hub_error_init: Failed to request_irq for 0x%p\n", hubdev_info); return; } diff --git a/arch/ia64/sn/kernel/xp_main.c b/arch/ia64/sn/kernel/xp_main.c deleted file mode 100644 index b7ea46645e1..00000000000 --- a/arch/ia64/sn/kernel/xp_main.c +++ /dev/null @@ -1,290 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (c) 2004-2005 Silicon Graphics, Inc. All Rights Reserved. - */ - - -/* - * Cross Partition (XP) base. - * - * XP provides a base from which its users can interact - * with XPC, yet not be dependent on XPC. - * - */ - - -#include <linux/kernel.h> -#include <linux/interrupt.h> -#include <linux/module.h> -#include <linux/mutex.h> -#include <asm/sn/intr.h> -#include <asm/sn/sn_sal.h> -#include <asm/sn/xp.h> - - -/* - * Target of nofault PIO read. - */ -u64 xp_nofault_PIOR_target; - - -/* - * xpc_registrations[] keeps track of xpc_connect()'s done by the kernel-level - * users of XPC. - */ -struct xpc_registration xpc_registrations[XPC_NCHANNELS]; - - -/* - * Initialize the XPC interface to indicate that XPC isn't loaded. - */ -static enum xpc_retval xpc_notloaded(void) { return xpcNotLoaded; } - -struct xpc_interface xpc_interface = { - (void (*)(int)) xpc_notloaded, - (void (*)(int)) xpc_notloaded, - (enum xpc_retval (*)(partid_t, int, u32, void **)) xpc_notloaded, - (enum xpc_retval (*)(partid_t, int, void *)) xpc_notloaded, - (enum xpc_retval (*)(partid_t, int, void *, xpc_notify_func, void *)) - xpc_notloaded, - (void (*)(partid_t, int, void *)) xpc_notloaded, - (enum xpc_retval (*)(partid_t, void *)) xpc_notloaded -}; - - -/* - * XPC calls this when it (the XPC module) has been loaded. - */ -void -xpc_set_interface(void (*connect)(int), - void (*disconnect)(int), - enum xpc_retval (*allocate)(partid_t, int, u32, void **), - enum xpc_retval (*send)(partid_t, int, void *), - enum xpc_retval (*send_notify)(partid_t, int, void *, - xpc_notify_func, void *), - void (*received)(partid_t, int, void *), - enum xpc_retval (*partid_to_nasids)(partid_t, void *)) -{ - xpc_interface.connect = connect; - xpc_interface.disconnect = disconnect; - xpc_interface.allocate = allocate; - xpc_interface.send = send; - xpc_interface.send_notify = send_notify; - xpc_interface.received = received; - xpc_interface.partid_to_nasids = partid_to_nasids; -} - - -/* - * XPC calls this when it (the XPC module) is being unloaded. - */ -void -xpc_clear_interface(void) -{ - xpc_interface.connect = (void (*)(int)) xpc_notloaded; - xpc_interface.disconnect = (void (*)(int)) xpc_notloaded; - xpc_interface.allocate = (enum xpc_retval (*)(partid_t, int, u32, - void **)) xpc_notloaded; - xpc_interface.send = (enum xpc_retval (*)(partid_t, int, void *)) - xpc_notloaded; - xpc_interface.send_notify = (enum xpc_retval (*)(partid_t, int, void *, - xpc_notify_func, void *)) xpc_notloaded; - xpc_interface.received = (void (*)(partid_t, int, void *)) - xpc_notloaded; - xpc_interface.partid_to_nasids = (enum xpc_retval (*)(partid_t, void *)) - xpc_notloaded; -} - - -/* - * Register for automatic establishment of a channel connection whenever - * a partition comes up. - * - * Arguments: - * - * ch_number - channel # to register for connection. - * func - function to call for asynchronous notification of channel - * state changes (i.e., connection, disconnection, error) and - * the arrival of incoming messages. - * key - pointer to optional user-defined value that gets passed back - * to the user on any callouts made to func. - * payload_size - size in bytes of the XPC message's payload area which - * contains a user-defined message. The user should make - * this large enough to hold their largest message. - * nentries - max #of XPC message entries a message queue can contain. - * The actual number, which is determined when a connection - * is established and may be less then requested, will be - * passed to the user via the xpcConnected callout. - * assigned_limit - max number of kthreads allowed to be processing - * messages (per connection) at any given instant. - * idle_limit - max number of kthreads allowed to be idle at any given - * instant. - */ -enum xpc_retval -xpc_connect(int ch_number, xpc_channel_func func, void *key, u16 payload_size, - u16 nentries, u32 assigned_limit, u32 idle_limit) -{ - struct xpc_registration *registration; - - - DBUG_ON(ch_number < 0 || ch_number >= XPC_NCHANNELS); - DBUG_ON(payload_size == 0 || nentries == 0); - DBUG_ON(func == NULL); - DBUG_ON(assigned_limit == 0 || idle_limit > assigned_limit); - - registration = &xpc_registrations[ch_number]; - - if (mutex_lock_interruptible(®istration->mutex) != 0) { - return xpcInterrupted; - } - - /* if XPC_CHANNEL_REGISTERED(ch_number) */ - if (registration->func != NULL) { - mutex_unlock(®istration->mutex); - return xpcAlreadyRegistered; - } - - /* register the channel for connection */ - registration->msg_size = XPC_MSG_SIZE(payload_size); - registration->nentries = nentries; - registration->assigned_limit = assigned_limit; - registration->idle_limit = idle_limit; - registration->key = key; - registration->func = func; - - mutex_unlock(®istration->mutex); - - xpc_interface.connect(ch_number); - - return xpcSuccess; -} - - -/* - * Remove the registration for automatic connection of the specified channel - * when a partition comes up. - * - * Before returning this xpc_disconnect() will wait for all connections on the - * specified channel have been closed/torndown. So the caller can be assured - * that they will not be receiving any more callouts from XPC to their - * function registered via xpc_connect(). - * - * Arguments: - * - * ch_number - channel # to unregister. - */ -void -xpc_disconnect(int ch_number) -{ - struct xpc_registration *registration; - - - DBUG_ON(ch_number < 0 || ch_number >= XPC_NCHANNELS); - - registration = &xpc_registrations[ch_number]; - - /* - * We've decided not to make this a down_interruptible(), since we - * figured XPC's users will just turn around and call xpc_disconnect() - * again anyways, so we might as well wait, if need be. - */ - mutex_lock(®istration->mutex); - - /* if !XPC_CHANNEL_REGISTERED(ch_number) */ - if (registration->func == NULL) { - mutex_unlock(®istration->mutex); - return; - } - - /* remove the connection registration for the specified channel */ - registration->func = NULL; - registration->key = NULL; - registration->nentries = 0; - registration->msg_size = 0; - registration->assigned_limit = 0; - registration->idle_limit = 0; - - xpc_interface.disconnect(ch_number); - - mutex_unlock(®istration->mutex); - - return; -} - - -int __init -xp_init(void) -{ - int ret, ch_number; - u64 func_addr = *(u64 *) xp_nofault_PIOR; - u64 err_func_addr = *(u64 *) xp_error_PIOR; - - - if (!ia64_platform_is("sn2")) { - return -ENODEV; - } - - /* - * Register a nofault code region which performs a cross-partition - * PIO read. If the PIO read times out, the MCA handler will consume - * the error and return to a kernel-provided instruction to indicate - * an error. This PIO read exists because it is guaranteed to timeout - * if the destination is down (AMO operations do not timeout on at - * least some CPUs on Shubs <= v1.2, which unfortunately we have to - * work around). - */ - if ((ret = sn_register_nofault_code(func_addr, err_func_addr, - err_func_addr, 1, 1)) != 0) { - printk(KERN_ERR "XP: can't register nofault code, error=%d\n", - ret); - } - /* - * Setup the nofault PIO read target. (There is no special reason why - * SH_IPI_ACCESS was selected.) - */ - if (is_shub2()) { - xp_nofault_PIOR_target = SH2_IPI_ACCESS0; - } else { - xp_nofault_PIOR_target = SH1_IPI_ACCESS; - } - - /* initialize the connection registration mutex */ - for (ch_number = 0; ch_number < XPC_NCHANNELS; ch_number++) { - mutex_init(&xpc_registrations[ch_number].mutex); - } - - return 0; -} -module_init(xp_init); - - -void __exit -xp_exit(void) -{ - u64 func_addr = *(u64 *) xp_nofault_PIOR; - u64 err_func_addr = *(u64 *) xp_error_PIOR; - - - /* unregister the PIO read nofault code region */ - (void) sn_register_nofault_code(func_addr, err_func_addr, - err_func_addr, 1, 0); -} -module_exit(xp_exit); - - -MODULE_AUTHOR("Silicon Graphics, Inc."); -MODULE_DESCRIPTION("Cross Partition (XP) base"); -MODULE_LICENSE("GPL"); - -EXPORT_SYMBOL(xp_nofault_PIOR); -EXPORT_SYMBOL(xp_nofault_PIOR_target); -EXPORT_SYMBOL(xpc_registrations); -EXPORT_SYMBOL(xpc_interface); -EXPORT_SYMBOL(xpc_clear_interface); -EXPORT_SYMBOL(xpc_set_interface); -EXPORT_SYMBOL(xpc_connect); -EXPORT_SYMBOL(xpc_disconnect); - diff --git a/arch/ia64/sn/kernel/xp_nofault.S b/arch/ia64/sn/kernel/xp_nofault.S deleted file mode 100644 index 98e7c7dbfdd..00000000000 --- a/arch/ia64/sn/kernel/xp_nofault.S +++ /dev/null @@ -1,36 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (c) 2004-2007 Silicon Graphics, Inc. All Rights Reserved. - */ - - -/* - * The xp_nofault_PIOR function takes a pointer to a remote PIO register - * and attempts to load and consume a value from it. This function - * will be registered as a nofault code block. In the event that the - * PIO read fails, the MCA handler will force the error to look - * corrected and vector to the xp_error_PIOR which will return an error. - * - * The definition of "consumption" and the time it takes for an MCA - * to surface is processor implementation specific. This code - * is sufficient on Itanium through the Montvale processor family. - * It may need to be adjusted for future processor implementations. - * - * extern int xp_nofault_PIOR(void *remote_register); - */ - - .global xp_nofault_PIOR -xp_nofault_PIOR: - mov r8=r0 // Stage a success return value - ld8.acq r9=[r32];; // PIO Read the specified register - adds r9=1,r9;; // Add to force consumption - srlz.i;; // Allow time for MCA to surface - br.ret.sptk.many b0;; // Return success - - .global xp_error_PIOR -xp_error_PIOR: - mov r8=1 // Return value of 1 - br.ret.sptk.many b0;; // Return failure diff --git a/arch/ia64/sn/kernel/xpc_channel.c b/arch/ia64/sn/kernel/xpc_channel.c deleted file mode 100644 index 44ccc0d789c..00000000000 --- a/arch/ia64/sn/kernel/xpc_channel.c +++ /dev/null @@ -1,2379 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (c) 2004-2006 Silicon Graphics, Inc. All Rights Reserved. - */ - - -/* - * Cross Partition Communication (XPC) channel support. - * - * This is the part of XPC that manages the channels and - * sends/receives messages across them to/from other partitions. - * - */ - - -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/sched.h> -#include <linux/cache.h> -#include <linux/interrupt.h> -#include <linux/mutex.h> -#include <linux/completion.h> -#include <asm/sn/bte.h> -#include <asm/sn/sn_sal.h> -#include <asm/sn/xpc.h> - - -/* - * Guarantee that the kzalloc'd memory is cacheline aligned. - */ -static void * -xpc_kzalloc_cacheline_aligned(size_t size, gfp_t flags, void **base) -{ - /* see if kzalloc will give us cachline aligned memory by default */ - *base = kzalloc(size, flags); - if (*base == NULL) { - return NULL; - } - if ((u64) *base == L1_CACHE_ALIGN((u64) *base)) { - return *base; - } - kfree(*base); - - /* nope, we'll have to do it ourselves */ - *base = kzalloc(size + L1_CACHE_BYTES, flags); - if (*base == NULL) { - return NULL; - } - return (void *) L1_CACHE_ALIGN((u64) *base); -} - - -/* - * Set up the initial values for the XPartition Communication channels. - */ -static void -xpc_initialize_channels(struct xpc_partition *part, partid_t partid) -{ - int ch_number; - struct xpc_channel *ch; - - - for (ch_number = 0; ch_number < part->nchannels; ch_number++) { - ch = &part->channels[ch_number]; - - ch->partid = partid; - ch->number = ch_number; - ch->flags = XPC_C_DISCONNECTED; - - ch->local_GP = &part->local_GPs[ch_number]; - ch->local_openclose_args = - &part->local_openclose_args[ch_number]; - - atomic_set(&ch->kthreads_assigned, 0); - atomic_set(&ch->kthreads_idle, 0); - atomic_set(&ch->kthreads_active, 0); - - atomic_set(&ch->references, 0); - atomic_set(&ch->n_to_notify, 0); - - spin_lock_init(&ch->lock); - mutex_init(&ch->msg_to_pull_mutex); - init_completion(&ch->wdisconnect_wait); - - atomic_set(&ch->n_on_msg_allocate_wq, 0); - init_waitqueue_head(&ch->msg_allocate_wq); - init_waitqueue_head(&ch->idle_wq); - } -} - - -/* - * Setup the infrastructure necessary to support XPartition Communication - * between the specified remote partition and the local one. - */ -enum xpc_retval -xpc_setup_infrastructure(struct xpc_partition *part) -{ - int ret, cpuid; - struct timer_list *timer; - partid_t partid = XPC_PARTID(part); - - - /* - * Zero out MOST of the entry for this partition. Only the fields - * starting with `nchannels' will be zeroed. The preceding fields must - * remain `viable' across partition ups and downs, since they may be - * referenced during this memset() operation. - */ - memset(&part->nchannels, 0, sizeof(struct xpc_partition) - - offsetof(struct xpc_partition, nchannels)); - - /* - * Allocate all of the channel structures as a contiguous chunk of - * memory. - */ - part->channels = kzalloc(sizeof(struct xpc_channel) * XPC_NCHANNELS, - GFP_KERNEL); - if (part->channels == NULL) { - dev_err(xpc_chan, "can't get memory for channels\n"); - return xpcNoMemory; - } - - part->nchannels = XPC_NCHANNELS; - - - /* allocate all the required GET/PUT values */ - - part->local_GPs = xpc_kzalloc_cacheline_aligned(XPC_GP_SIZE, - GFP_KERNEL, &part->local_GPs_base); - if (part->local_GPs == NULL) { - kfree(part->channels); - part->channels = NULL; - dev_err(xpc_chan, "can't get memory for local get/put " - "values\n"); - return xpcNoMemory; - } - - part->remote_GPs = xpc_kzalloc_cacheline_aligned(XPC_GP_SIZE, - GFP_KERNEL, &part->remote_GPs_base); - if (part->remote_GPs == NULL) { - dev_err(xpc_chan, "can't get memory for remote get/put " - "values\n"); - kfree(part->local_GPs_base); - part->local_GPs = NULL; - kfree(part->channels); - part->channels = NULL; - return xpcNoMemory; - } - - - /* allocate all the required open and close args */ - - part->local_openclose_args = xpc_kzalloc_cacheline_aligned( - XPC_OPENCLOSE_ARGS_SIZE, GFP_KERNEL, - &part->local_openclose_args_base); - if (part->local_openclose_args == NULL) { - dev_err(xpc_chan, "can't get memory for local connect args\n"); - kfree(part->remote_GPs_base); - part->remote_GPs = NULL; - kfree(part->local_GPs_base); - part->local_GPs = NULL; - kfree(part->channels); - part->channels = NULL; - return xpcNoMemory; - } - - part->remote_openclose_args = xpc_kzalloc_cacheline_aligned( - XPC_OPENCLOSE_ARGS_SIZE, GFP_KERNEL, - &part->remote_openclose_args_base); - if (part->remote_openclose_args == NULL) { - dev_err(xpc_chan, "can't get memory for remote connect args\n"); - kfree(part->local_openclose_args_base); - part->local_openclose_args = NULL; - kfree(part->remote_GPs_base); - part->remote_GPs = NULL; - kfree(part->local_GPs_base); - part->local_GPs = NULL; - kfree(part->channels); - part->channels = NULL; - return xpcNoMemory; - } - - - xpc_initialize_channels(part, partid); - - atomic_set(&part->nchannels_active, 0); - atomic_set(&part->nchannels_engaged, 0); - - - /* local_IPI_amo were set to 0 by an earlier memset() */ - - /* Initialize this partitions AMO_t structure */ - part->local_IPI_amo_va = xpc_IPI_init(partid); - - spin_lock_init(&part->IPI_lock); - - atomic_set(&part->channel_mgr_requests, 1); - init_waitqueue_head(&part->channel_mgr_wq); - - sprintf(part->IPI_owner, "xpc%02d", partid); - 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, " - "errno=%d\n", -ret); - kfree(part->remote_openclose_args_base); - part->remote_openclose_args = NULL; - kfree(part->local_openclose_args_base); - part->local_openclose_args = NULL; - kfree(part->remote_GPs_base); - part->remote_GPs = NULL; - kfree(part->local_GPs_base); - part->local_GPs = NULL; - kfree(part->channels); - part->channels = NULL; - return xpcLackOfResources; - } - - /* Setup a timer to check for dropped IPIs */ - timer = &part->dropped_IPI_timer; - init_timer(timer); - timer->function = (void (*)(unsigned long)) xpc_dropped_IPI_check; - timer->data = (unsigned long) part; - timer->expires = jiffies + XPC_P_DROPPED_IPI_WAIT; - add_timer(timer); - - /* - * With the setting of the partition setup_state to XPC_P_SETUP, we're - * declaring that this partition is ready to go. - */ - part->setup_state = XPC_P_SETUP; - - - /* - * Setup the per partition specific variables required by the - * remote partition to establish channel connections with us. - * - * The setting of the magic # indicates that these per partition - * specific variables are ready to be used. - */ - xpc_vars_part[partid].GPs_pa = __pa(part->local_GPs); - xpc_vars_part[partid].openclose_args_pa = - __pa(part->local_openclose_args); - xpc_vars_part[partid].IPI_amo_pa = __pa(part->local_IPI_amo_va); - cpuid = raw_smp_processor_id(); /* any CPU in this partition will do */ - xpc_vars_part[partid].IPI_nasid = cpuid_to_nasid(cpuid); - xpc_vars_part[partid].IPI_phys_cpuid = cpu_physical_id(cpuid); - xpc_vars_part[partid].nchannels = part->nchannels; - xpc_vars_part[partid].magic = XPC_VP_MAGIC1; - - return xpcSuccess; -} - - -/* - * Create a wrapper that hides the underlying mechanism for pulling a cacheline - * (or multiple cachelines) from a remote partition. - * - * src must be a cacheline aligned physical address on the remote partition. - * dst must be a cacheline aligned virtual address on this partition. - * cnt must be an cacheline sized - */ -static enum xpc_retval -xpc_pull_remote_cachelines(struct xpc_partition *part, void *dst, - const void *src, size_t cnt) -{ - bte_result_t bte_ret; - - - DBUG_ON((u64) src != L1_CACHE_ALIGN((u64) src)); - DBUG_ON((u64) dst != L1_CACHE_ALIGN((u64) dst)); - DBUG_ON(cnt != L1_CACHE_ALIGN(cnt)); - - if (part->act_state == XPC_P_DEACTIVATING) { - return part->reason; - } - - bte_ret = xp_bte_copy((u64) src, (u64) dst, (u64) cnt, - (BTE_NORMAL | BTE_WACQUIRE), NULL); - if (bte_ret == BTE_SUCCESS) { - return xpcSuccess; - } - - dev_dbg(xpc_chan, "xp_bte_copy() from partition %d failed, ret=%d\n", - XPC_PARTID(part), bte_ret); - - return xpc_map_bte_errors(bte_ret); -} - - -/* - * Pull the remote per partition specific variables from the specified - * partition. - */ -enum xpc_retval -xpc_pull_remote_vars_part(struct xpc_partition *part) -{ - u8 buffer[L1_CACHE_BYTES * 2]; - struct xpc_vars_part *pulled_entry_cacheline = - (struct xpc_vars_part *) L1_CACHE_ALIGN((u64) buffer); - struct xpc_vars_part *pulled_entry; - u64 remote_entry_cacheline_pa, remote_entry_pa; - partid_t partid = XPC_PARTID(part); - enum xpc_retval ret; - - - /* pull the cacheline that contains the variables we're interested in */ - - DBUG_ON(part->remote_vars_part_pa != - L1_CACHE_ALIGN(part->remote_vars_part_pa)); - DBUG_ON(sizeof(struct xpc_vars_part) != L1_CACHE_BYTES / 2); - - remote_entry_pa = part->remote_vars_part_pa + - sn_partition_id * sizeof(struct xpc_vars_part); - - remote_entry_cacheline_pa = (remote_entry_pa & ~(L1_CACHE_BYTES - 1)); - - pulled_entry = (struct xpc_vars_part *) ((u64) pulled_entry_cacheline + - (remote_entry_pa & (L1_CACHE_BYTES - 1))); - - ret = xpc_pull_remote_cachelines(part, pulled_entry_cacheline, - (void *) remote_entry_cacheline_pa, - L1_CACHE_BYTES); - if (ret != xpcSuccess) { - dev_dbg(xpc_chan, "failed to pull XPC vars_part from " - "partition %d, ret=%d\n", partid, ret); - return ret; - } - - - /* see if they've been set up yet */ - - if (pulled_entry->magic != XPC_VP_MAGIC1 && - pulled_entry->magic != XPC_VP_MAGIC2) { - - if (pulled_entry->magic != 0) { - dev_dbg(xpc_chan, "partition %d's XPC vars_part for " - "partition %d has bad magic value (=0x%lx)\n", - partid, sn_partition_id, pulled_entry->magic); - return xpcBadMagic; - } - - /* they've not been initialized yet */ - return xpcRetry; - } - - if (xpc_vars_part[partid].magic == XPC_VP_MAGIC1) { - - /* validate the variables */ - - if (pulled_entry->GPs_pa == 0 || - pulled_entry->openclose_args_pa == 0 || - pulled_entry->IPI_amo_pa == 0) { - - dev_err(xpc_chan, "partition %d's XPC vars_part for " - "partition %d are not valid\n", partid, - sn_partition_id); - return xpcInvalidAddress; - } - - /* the variables we imported look to be valid */ - - part->remote_GPs_pa = pulled_entry->GPs_pa; - part->remote_openclose_args_pa = - pulled_entry->openclose_args_pa; - part->remote_IPI_amo_va = - (AMO_t *) __va(pulled_entry->IPI_amo_pa); - part->remote_IPI_nasid = pulled_entry->IPI_nasid; - part->remote_IPI_phys_cpuid = pulled_entry->IPI_phys_cpuid; - - if (part->nchannels > pulled_entry->nchannels) { - part->nchannels = pulled_entry->nchannels; - } - - /* let the other side know that we've pulled their variables */ - - xpc_vars_part[partid].magic = XPC_VP_MAGIC2; - } - - if (pulled_entry->magic == XPC_VP_MAGIC1) { - return xpcRetry; - } - - return xpcSuccess; -} - - -/* - * Get the IPI flags and pull the openclose args and/or remote GPs as needed. - */ -static u64 -xpc_get_IPI_flags(struct xpc_partition *part) -{ - unsigned long irq_flags; - u64 IPI_amo; - enum xpc_retval ret; - - - /* - * See if there are any IPI flags to be handled. - */ - - spin_lock_irqsave(&part->IPI_lock, irq_flags); - if ((IPI_amo = part->local_IPI_amo) != 0) { - part->local_IPI_amo = 0; - } - spin_unlock_irqrestore(&part->IPI_lock, irq_flags); - - - if (XPC_ANY_OPENCLOSE_IPI_FLAGS_SET(IPI_amo)) { - ret = xpc_pull_remote_cachelines(part, - part->remote_openclose_args, - (void *) part->remote_openclose_args_pa, - XPC_OPENCLOSE_ARGS_SIZE); - if (ret != xpcSuccess) { - XPC_DEACTIVATE_PARTITION(part, ret); - - dev_dbg(xpc_chan, "failed to pull openclose args from " - "partition %d, ret=%d\n", XPC_PARTID(part), - ret); - - /* don't bother processing IPIs anymore */ - IPI_amo = 0; - } - } - - if (XPC_ANY_MSG_IPI_FLAGS_SET(IPI_amo)) { - ret = xpc_pull_remote_cachelines(part, part->remote_GPs, - (void *) part->remote_GPs_pa, - XPC_GP_SIZE); - if (ret != xpcSuccess) { - XPC_DEACTIVATE_PARTITION(part, ret); - - dev_dbg(xpc_chan, "failed to pull GPs from partition " - "%d, ret=%d\n", XPC_PARTID(part), ret); - - /* don't bother processing IPIs anymore */ - IPI_amo = 0; - } - } - - return IPI_amo; -} - - -/* - * Allocate the local message queue and the notify queue. - */ -static enum xpc_retval -xpc_allocate_local_msgqueue(struct xpc_channel *ch) -{ - unsigned long irq_flags; - int nentries; - size_t nbytes; - - - // >>> may want to check for ch->flags & XPC_C_DISCONNECTING between - // >>> iterations of the for-loop, bail if set? - - // >>> should we impose a minimum #of entries? like 4 or 8? - for (nentries = ch->local_nentries; nentries > 0; nentries--) { - - nbytes = nentries * ch->msg_size; - ch->local_msgqueue = xpc_kzalloc_cacheline_aligned(nbytes, - GFP_KERNEL, - &ch->local_msgqueue_base); - if (ch->local_msgqueue == NULL) { - continue; - } - - nbytes = nentries * sizeof(struct xpc_notify); - ch->notify_queue = kzalloc(nbytes, GFP_KERNEL); - if (ch->notify_queue == NULL) { - kfree(ch->local_msgqueue_base); - ch->local_msgqueue = NULL; - continue; - } - - spin_lock_irqsave(&ch->lock, irq_flags); - if (nentries < ch->local_nentries) { - dev_dbg(xpc_chan, "nentries=%d local_nentries=%d, " - "partid=%d, channel=%d\n", nentries, - ch->local_nentries, ch->partid, ch->number); - - ch->local_nentries = nentries; - } - spin_unlock_irqrestore(&ch->lock, irq_flags); - return xpcSuccess; - } - - dev_dbg(xpc_chan, "can't get memory for local message queue and notify " - "queue, partid=%d, channel=%d\n", ch->partid, ch->number); - return xpcNoMemory; -} - - -/* - * Allocate the cached remote message queue. - */ -static enum xpc_retval -xpc_allocate_remote_msgqueue(struct xpc_channel *ch) -{ - unsigned long irq_flags; - int nentries; - size_t nbytes; - - - DBUG_ON(ch->remote_nentries <= 0); - - // >>> may want to check for ch->flags & XPC_C_DISCONNECTING between - // >>> iterations of the for-loop, bail if set? - - // >>> should we impose a minimum #of entries? like 4 or 8? - for (nentries = ch->remote_nentries; nentries > 0; nentries--) { - - nbytes = nentries * ch->msg_size; - ch->remote_msgqueue = xpc_kzalloc_cacheline_aligned(nbytes, - GFP_KERNEL, - &ch->remote_msgqueue_base); - if (ch->remote_msgqueue == NULL) { - continue; - } - - spin_lock_irqsave(&ch->lock, irq_flags); - if (nentries < ch->remote_nentries) { - dev_dbg(xpc_chan, "nentries=%d remote_nentries=%d, " - "partid=%d, channel=%d\n", nentries, - ch->remote_nentries, ch->partid, ch->number); - - ch->remote_nentries = nentries; - } - spin_unlock_irqrestore(&ch->lock, irq_flags); - return xpcSuccess; - } - - dev_dbg(xpc_chan, "can't get memory for cached remote message queue, " - "partid=%d, channel=%d\n", ch->partid, ch->number); - return xpcNoMemory; -} - - -/* - * Allocate message queues and other stuff associated with a channel. - * - * Note: Assumes all of the channel sizes are filled in. - */ -static enum xpc_retval -xpc_allocate_msgqueues(struct xpc_channel *ch) -{ - unsigned long irq_flags; - enum xpc_retval ret; - - - DBUG_ON(ch->flags & XPC_C_SETUP); - - if ((ret = xpc_allocate_local_msgqueue(ch)) != xpcSuccess) { - return ret; - } - - if ((ret = xpc_allocate_remote_msgqueue(ch)) != xpcSuccess) { - kfree(ch->local_msgqueue_base); - ch->local_msgqueue = NULL; - kfree(ch->notify_queue); - ch->notify_queue = NULL; - return ret; - } - - spin_lock_irqsave(&ch->lock, irq_flags); - ch->flags |= XPC_C_SETUP; - spin_unlock_irqrestore(&ch->lock, irq_flags); - - return xpcSuccess; -} - - -/* - * Process a connect message from a remote partition. - * - * Note: xpc_process_connect() is expecting to be called with the - * spin_lock_irqsave held and will leave it locked upon return. - */ -static void -xpc_process_connect(struct xpc_channel *ch, unsigned long *irq_flags) -{ - enum xpc_retval ret; - - - DBUG_ON(!spin_is_locked(&ch->lock)); - - if (!(ch->flags & XPC_C_OPENREQUEST) || - !(ch->flags & XPC_C_ROPENREQUEST)) { - /* nothing more to do for now */ - return; - } - DBUG_ON(!(ch->flags & XPC_C_CONNECTING)); - - if (!(ch->flags & XPC_C_SETUP)) { - spin_unlock_irqrestore(&ch->lock, *irq_flags); - ret = xpc_allocate_msgqueues(ch); - spin_lock_irqsave(&ch->lock, *irq_flags); - - if (ret != xpcSuccess) { - XPC_DISCONNECT_CHANNEL(ch, ret, irq_flags); - } - if (ch->flags & (XPC_C_CONNECTED | XPC_C_DISCONNECTING)) { - return; - } - - DBUG_ON(!(ch->flags & XPC_C_SETUP)); - DBUG_ON(ch->local_msgqueue == NULL); - DBUG_ON(ch->remote_msgqueue == NULL); - } - - if (!(ch->flags & XPC_C_OPENREPLY)) { - ch->flags |= XPC_C_OPENREPLY; - xpc_IPI_send_openreply(ch, irq_flags); - } - - if (!(ch->flags & XPC_C_ROPENREPLY)) { - return; - } - - DBUG_ON(ch->remote_msgqueue_pa == 0); - - ch->flags = (XPC_C_CONNECTED | XPC_C_SETUP); /* clear all else */ - - dev_info(xpc_chan, "channel %d to partition %d connected\n", - ch->number, ch->partid); - - spin_unlock_irqrestore(&ch->lock, *irq_flags); - xpc_create_kthreads(ch, 1, 0); - spin_lock_irqsave(&ch->lock, *irq_flags); -} - - -/* - * Notify those who wanted to be notified upon delivery of their message. - */ -static void -xpc_notify_senders(struct xpc_channel *ch, enum xpc_retval reason, s64 put) -{ - struct xpc_notify *notify; - u8 notify_type; - s64 get = ch->w_remote_GP.get - 1; - - - while (++get < put && atomic_read(&ch->n_to_notify) > 0) { - - notify = &ch->notify_queue[get % ch->local_nentries]; - - /* - * See if the notify entry indicates it was associated with - * a message who's sender wants to be notified. It is possible - * that it is, but someone else is doing or has done the - * notification. - */ - notify_type = notify->type; - if (notify_type == 0 || - cmpxchg(¬ify->type, notify_type, 0) != - notify_type) { - continue; - } - - DBUG_ON(notify_type != XPC_N_CALL); - - atomic_dec(&ch->n_to_notify); - - if (notify->func != NULL) { - dev_dbg(xpc_chan, "notify->func() called, notify=0x%p, " - "msg_number=%ld, partid=%d, channel=%d\n", - (void *) notify, get, ch->partid, ch->number); - - notify->func(reason, ch->partid, ch->number, - notify->key); - - dev_dbg(xpc_chan, "notify->func() returned, " - "notify=0x%p, msg_number=%ld, partid=%d, " - "channel=%d\n", (void *) notify, get, - ch->partid, ch->number); - } - } -} - - -/* - * Free up message queues and other stuff that were allocated for the specified - * channel. - * - * Note: ch->reason and ch->reason_line are left set for debugging purposes, - * they're cleared when XPC_C_DISCONNECTED is cleared. - */ -static void -xpc_free_msgqueues(struct xpc_channel *ch) -{ - DBUG_ON(!spin_is_locked(&ch->lock)); - DBUG_ON(atomic_read(&ch->n_to_notify) != 0); - - ch->remote_msgqueue_pa = 0; - ch->func = NULL; - ch->key = NULL; - ch->msg_size = 0; - ch->local_nentries = 0; - ch->remote_nentries = 0; - ch->kthreads_assigned_limit = 0; - ch->kthreads_idle_limit = 0; - - ch->local_GP->get = 0; - ch->local_GP->put = 0; - ch->remote_GP.get = 0; - ch->remote_GP.put = 0; - ch->w_local_GP.get = 0; - ch->w_local_GP.put = 0; - ch->w_remote_GP.get = 0; - ch->w_remote_GP.put = 0; - ch->next_msg_to_pull = 0; - - if (ch->flags & XPC_C_SETUP) { - ch->flags &= ~XPC_C_SETUP; - - dev_dbg(xpc_chan, "ch->flags=0x%x, partid=%d, channel=%d\n", - ch->flags, ch->partid, ch->number); - - kfree(ch->local_msgqueue_base); - ch->local_msgqueue = NULL; - kfree(ch->remote_msgqueue_base); - ch->remote_msgqueue = NULL; - kfree(ch->notify_queue); - ch->notify_queue = NULL; - } -} - - -/* - * spin_lock_irqsave() is expected to be held on entry. - */ -static void -xpc_process_disconnect(struct xpc_channel *ch, unsigned long *irq_flags) -{ - struct xpc_partition *part = &xpc_partitions[ch->partid]; - u32 channel_was_connected = (ch->flags & XPC_C_WASCONNECTED); - - - DBUG_ON(!spin_is_locked(&ch->lock)); - - if (!(ch->flags & XPC_C_DISCONNECTING)) { - return; - } - - DBUG_ON(!(ch->flags & XPC_C_CLOSEREQUEST)); - - /* make sure all activity has settled down first */ - - if (atomic_read(&ch->kthreads_assigned) > 0 || - atomic_read(&ch->references) > 0) { - return; - } - DBUG_ON((ch->flags & XPC_C_CONNECTEDCALLOUT_MADE) && - !(ch->flags & XPC_C_DISCONNECTINGCALLOUT_MADE)); - - if (part->act_state == XPC_P_DEACTIVATING) { - /* can't proceed until the other side disengages from us */ - if (xpc_partition_engaged(1UL << ch->partid)) { - return; - } - - } else { - - /* as long as the other side is up do the full protocol */ - - if (!(ch->flags & XPC_C_RCLOSEREQUEST)) { - return; - } - - if (!(ch->flags & XPC_C_CLOSEREPLY)) { - ch->flags |= XPC_C_CLOSEREPLY; - xpc_IPI_send_closereply(ch, irq_flags); - } - - if (!(ch->flags & XPC_C_RCLOSEREPLY)) { - return; - } - } - - /* wake those waiting for notify completion */ - if (atomic_read(&ch->n_to_notify) > 0) { - /* >>> we do callout while holding ch->lock */ - xpc_notify_senders(ch, ch->reason, ch->w_local_GP.put); - } - - /* both sides are disconnected now */ - - if (ch->flags & XPC_C_DISCONNECTINGCALLOUT_MADE) { - spin_unlock_irqrestore(&ch->lock, *irq_flags); - xpc_disconnect_callout(ch, xpcDisconnected); - spin_lock_irqsave(&ch->lock, *irq_flags); - } - - /* it's now safe to free the channel's message queues */ - xpc_free_msgqueues(ch); - - /* mark disconnected, clear all other flags except XPC_C_WDISCONNECT */ - ch->flags = (XPC_C_DISCONNECTED | (ch->flags & XPC_C_WDISCONNECT)); - - atomic_dec(&part->nchannels_active); - - if (channel_was_connected) { - dev_info(xpc_chan, "channel %d to partition %d disconnected, " - "reason=%d\n", ch->number, ch->partid, ch->reason); - } - - if (ch->flags & XPC_C_WDISCONNECT) { - /* we won't lose the CPU since we're holding ch->lock */ - complete(&ch->wdisconnect_wait); - } else if (ch->delayed_IPI_flags) { - if (part->act_state != XPC_P_DEACTIVATING) { - /* time to take action on any delayed IPI flags */ - spin_lock(&part->IPI_lock); - XPC_SET_IPI_FLAGS(part->local_IPI_amo, ch->number, - ch->delayed_IPI_flags); - spin_unlock(&part->IPI_lock); - } - ch->delayed_IPI_flags = 0; - } -} - - -/* - * Process a change in the channel's remote connection state. - */ -static void -xpc_process_openclose_IPI(struct xpc_partition *part, int ch_number, - u8 IPI_flags) -{ - unsigned long irq_flags; - struct xpc_openclose_args *args = - &part->remote_openclose_args[ch_number]; - struct xpc_channel *ch = &part->channels[ch_number]; - enum xpc_retval reason; - - - - spin_lock_irqsave(&ch->lock, irq_flags); - -again: - - if ((ch->flags & XPC_C_DISCONNECTED) && - (ch->flags & XPC_C_WDISCONNECT)) { - /* - * Delay processing IPI flags until thread waiting disconnect - * has had a chance to see that the channel is disconnected. - */ - ch->delayed_IPI_flags |= IPI_flags; - spin_unlock_irqrestore(&ch->lock, irq_flags); - return; - } - - - if (IPI_flags & XPC_IPI_CLOSEREQUEST) { - - dev_dbg(xpc_chan, "XPC_IPI_CLOSEREQUEST (reason=%d) received " - "from partid=%d, channel=%d\n", args->reason, - ch->partid, ch->number); - - /* - * If RCLOSEREQUEST is set, we're probably waiting for - * RCLOSEREPLY. We should find it and a ROPENREQUEST packed - * with this RCLOSEREQUEST in the IPI_flags. - */ - - if (ch->flags & XPC_C_RCLOSEREQUEST) { - DBUG_ON(!(ch->flags & XPC_C_DISCONNECTING)); - DBUG_ON(!(ch->flags & XPC_C_CLOSEREQUEST)); - DBUG_ON(!(ch->flags & XPC_C_CLOSEREPLY)); - DBUG_ON(ch->flags & XPC_C_RCLOSEREPLY); - - DBUG_ON(!(IPI_flags & XPC_IPI_CLOSEREPLY)); - IPI_flags &= ~XPC_IPI_CLOSEREPLY; - ch->flags |= XPC_C_RCLOSEREPLY; - - /* both sides have finished disconnecting */ - xpc_process_disconnect(ch, &irq_flags); - DBUG_ON(!(ch->flags & XPC_C_DISCONNECTED)); - goto again; - } - - if (ch->flags & XPC_C_DISCONNECTED) { - if (!(IPI_flags & XPC_IPI_OPENREQUEST)) { - if ((XPC_GET_IPI_FLAGS(part->local_IPI_amo, - ch_number) & XPC_IPI_OPENREQUEST)) { - - DBUG_ON(ch->delayed_IPI_flags != 0); - spin_lock(&part->IPI_lock); - XPC_SET_IPI_FLAGS(part->local_IPI_amo, - ch_number, - XPC_IPI_CLOSEREQUEST); - spin_unlock(&part->IPI_lock); - } - spin_unlock_irqrestore(&ch->lock, irq_flags); - return; - } - - XPC_SET_REASON(ch, 0, 0); - ch->flags &= ~XPC_C_DISCONNECTED; - - atomic_inc(&part->nchannels_active); - ch->flags |= (XPC_C_CONNECTING | XPC_C_ROPENREQUEST); - } - - IPI_flags &= ~(XPC_IPI_OPENREQUEST | XPC_IPI_OPENREPLY); - - /* - * The meaningful CLOSEREQUEST connection state fields are: - * reason = reason connection is to be closed - */ - - ch->flags |= XPC_C_RCLOSEREQUEST; - - if (!(ch->flags & XPC_C_DISCONNECTING)) { - reason = args->reason; - if (reason <= xpcSuccess || reason > xpcUnknownReason) { - reason = xpcUnknownReason; - } else if (reason == xpcUnregistering) { - reason = xpcOtherUnregistering; - } - - XPC_DISCONNECT_CHANNEL(ch, reason, &irq_flags); - - DBUG_ON(IPI_flags & XPC_IPI_CLOSEREPLY); - spin_unlock_irqrestore(&ch->lock, irq_flags); - return; - } - - xpc_process_disconnect(ch, &irq_flags); - } - - - if (IPI_flags & XPC_IPI_CLOSEREPLY) { - - dev_dbg(xpc_chan, "XPC_IPI_CLOSEREPLY received from partid=%d," - " channel=%d\n", ch->partid, ch->number); - - if (ch->flags & XPC_C_DISCONNECTED) { - DBUG_ON(part->act_state != XPC_P_DEACTIVATING); - spin_unlock_irqrestore(&ch->lock, irq_flags); - return; - } - - DBUG_ON(!(ch->flags & XPC_C_CLOSEREQUEST)); - - if (!(ch->flags & XPC_C_RCLOSEREQUEST)) { - if ((XPC_GET_IPI_FLAGS(part->local_IPI_amo, ch_number) - & XPC_IPI_CLOSEREQUEST)) { - - DBUG_ON(ch->delayed_IPI_flags != 0); - spin_lock(&part->IPI_lock); - XPC_SET_IPI_FLAGS(part->local_IPI_amo, - ch_number, XPC_IPI_CLOSEREPLY); - spin_unlock(&part->IPI_lock); - } - spin_unlock_irqrestore(&ch->lock, irq_flags); - return; - } - - ch->flags |= XPC_C_RCLOSEREPLY; - - if (ch->flags & XPC_C_CLOSEREPLY) { - /* both sides have finished disconnecting */ - xpc_process_disconnect(ch, &irq_flags); - } - } - - - if (IPI_flags & XPC_IPI_OPENREQUEST) { - - dev_dbg(xpc_chan, "XPC_IPI_OPENREQUEST (msg_size=%d, " - "local_nentries=%d) received from partid=%d, " - "channel=%d\n", args->msg_size, args->local_nentries, - ch->partid, ch->number); - - if (part->act_state == XPC_P_DEACTIVATING || - (ch->flags & XPC_C_ROPENREQUEST)) { - spin_unlock_irqrestore(&ch->lock, irq_flags); - return; - } - - if (ch->flags & (XPC_C_DISCONNECTING | XPC_C_WDISCONNECT)) { - ch->delayed_IPI_flags |= XPC_IPI_OPENREQUEST; - spin_unlock_irqrestore(&ch->lock, irq_flags); - return; - } - DBUG_ON(!(ch->flags & (XPC_C_DISCONNECTED | - XPC_C_OPENREQUEST))); - DBUG_ON(ch->flags & (XPC_C_ROPENREQUEST | XPC_C_ROPENREPLY | - XPC_C_OPENREPLY | XPC_C_CONNECTED)); - - /* - * The meaningful OPENREQUEST connection state fields are: - * msg_size = size of channel's messages in bytes - * local_nentries = remote partition's local_nentries - */ - if (args->msg_size == 0 || args->local_nentries == 0) { - /* assume OPENREQUEST was delayed by mistake */ - spin_unlock_irqrestore(&ch->lock, irq_flags); - return; - } - - ch->flags |= (XPC_C_ROPENREQUEST | XPC_C_CONNECTING); - ch->remote_nentries = args->local_nentries; - - - if (ch->flags & XPC_C_OPENREQUEST) { - if (args->msg_size != ch->msg_size) { - XPC_DISCONNECT_CHANNEL(ch, xpcUnequalMsgSizes, - &irq_flags); - spin_unlock_irqrestore(&ch->lock, irq_flags); - return; - } - } else { - ch->msg_size = args->msg_size; - - XPC_SET_REASON(ch, 0, 0); - ch->flags &= ~XPC_C_DISCONNECTED; - - atomic_inc(&part->nchannels_active); - } - - xpc_process_connect(ch, &irq_flags); - } - - - if (IPI_flags & XPC_IPI_OPENREPLY) { - - dev_dbg(xpc_chan, "XPC_IPI_OPENREPLY (local_msgqueue_pa=0x%lx, " - "local_nentries=%d, remote_nentries=%d) received from " - "partid=%d, channel=%d\n", args->local_msgqueue_pa, - args->local_nentries, args->remote_nentries, - ch->partid, ch->number); - - if (ch->flags & (XPC_C_DISCONNECTING | XPC_C_DISCONNECTED)) { - spin_unlock_irqrestore(&ch->lock, irq_flags); - return; - } - if (!(ch->flags & XPC_C_OPENREQUEST)) { - XPC_DISCONNECT_CHANNEL(ch, xpcOpenCloseError, - &irq_flags); - spin_unlock_irqrestore(&ch->lock, irq_flags); - return; - } - - DBUG_ON(!(ch->flags & XPC_C_ROPENREQUEST)); - DBUG_ON(ch->flags & XPC_C_CONNECTED); - - /* - * The meaningful OPENREPLY connection state fields are: - * local_msgqueue_pa = physical address of remote - * partition's local_msgqueue - * local_nentries = remote partition's local_nentries - * remote_nentries = remote partition's remote_nentries - */ - DBUG_ON(args->local_msgqueue_pa == 0); - DBUG_ON(args->local_nentries == 0); - DBUG_ON(args->remote_nentries == 0); - - ch->flags |= XPC_C_ROPENREPLY; - ch->remote_msgqueue_pa = args->local_msgqueue_pa; - - if (args->local_nentries < ch->remote_nentries) { - dev_dbg(xpc_chan, "XPC_IPI_OPENREPLY: new " - "remote_nentries=%d, old remote_nentries=%d, " - "partid=%d, channel=%d\n", - args->local_nentries, ch->remote_nentries, - ch->partid, ch->number); - - ch->remote_nentries = args->local_nentries; - } - if (args->remote_nentries < ch->local_nentries) { - dev_dbg(xpc_chan, "XPC_IPI_OPENREPLY: new " - "local_nentries=%d, old local_nentries=%d, " - "partid=%d, channel=%d\n", - args->remote_nentries, ch->local_nentries, - ch->partid, ch->number); - - ch->local_nentries = args->remote_nentries; - } - - xpc_process_connect(ch, &irq_flags); - } - - spin_unlock_irqrestore(&ch->lock, irq_flags); -} - - -/* - * Attempt to establish a channel connection to a remote partition. - */ -static enum xpc_retval -xpc_connect_channel(struct xpc_channel *ch) -{ - unsigned long irq_flags; - struct xpc_registration *registration = &xpc_registrations[ch->number]; - - - if (mutex_trylock(®istration->mutex) == 0) { - return xpcRetry; - } - - if (!XPC_CHANNEL_REGISTERED(ch->number)) { - mutex_unlock(®istration->mutex); - return xpcUnregistered; - } - - spin_lock_irqsave(&ch->lock, irq_flags); - - DBUG_ON(ch->flags & XPC_C_CONNECTED); - DBUG_ON(ch->flags & XPC_C_OPENREQUEST); - - if (ch->flags & XPC_C_DISCONNECTING) { - spin_unlock_irqrestore(&ch->lock, irq_flags); - mutex_unlock(®istration->mutex); - return ch->reason; - } - - - /* add info from the channel connect registration to the channel */ - - ch->kthreads_assigned_limit = registration->assigned_limit; - ch->kthreads_idle_limit = registration->idle_limit; - DBUG_ON(atomic_read(&ch->kthreads_assigned) != 0); - DBUG_ON(atomic_read(&ch->kthreads_idle) != 0); - DBUG_ON(atomic_read(&ch->kthreads_active) != 0); - - ch->func = registration->func; - DBUG_ON(registration->func == NULL); - ch->key = registration->key; - - ch->local_nentries = registration->nentries; - - if (ch->flags & XPC_C_ROPENREQUEST) { - if (registration->msg_size != ch->msg_size) { - /* the local and remote sides aren't the same */ - - /* - * Because XPC_DISCONNECT_CHANNEL() can block we're - * forced to up the registration sema before we unlock - * the channel lock. But that's okay here because we're - * done with the part that required the registration - * sema. XPC_DISCONNECT_CHANNEL() requires that the - * channel lock be locked and will unlock and relock - * the channel lock as needed. - */ - mutex_unlock(®istration->mutex); - XPC_DISCONNECT_CHANNEL(ch, xpcUnequalMsgSizes, - &irq_flags); - spin_unlock_irqrestore(&ch->lock, irq_flags); - return xpcUnequalMsgSizes; - } - } else { - ch->msg_size = registration->msg_size; - - XPC_SET_REASON(ch, 0, 0); - ch->flags &= ~XPC_C_DISCONNECTED; - - atomic_inc(&xpc_partitions[ch->partid].nchannels_active); - } - - mutex_unlock(®istration->mutex); - - - /* initiate the connection */ - - ch->flags |= (XPC_C_OPENREQUEST | XPC_C_CONNECTING); - xpc_IPI_send_openrequest(ch, &irq_flags); - - xpc_process_connect(ch, &irq_flags); - - spin_unlock_irqrestore(&ch->lock, irq_flags); - - return xpcSuccess; -} - - -/* - * Clear some of the msg flags in the local message queue. - */ -static inline void -xpc_clear_local_msgqueue_flags(struct xpc_channel *ch) -{ - struct xpc_msg *msg; - s64 get; - - - get = ch->w_remote_GP.get; - do { - msg = (struct xpc_msg *) ((u64) ch->local_msgqueue + - (get % ch->local_nentries) * ch->msg_size); - msg->flags = 0; - } while (++get < (volatile s64) ch->remote_GP.get); -} - - -/* - * Clear some of the msg flags in the remote message queue. - */ -static inline void -xpc_clear_remote_msgqueue_flags(struct xpc_channel *ch) -{ - struct xpc_msg *msg; - s64 put; - - - put = ch->w_remote_GP.put; - do { - msg = (struct xpc_msg *) ((u64) ch->remote_msgqueue + - (put % ch->remote_nentries) * ch->msg_size); - msg->flags = 0; - } while (++put < (volatile s64) ch->remote_GP.put); -} - - -static void -xpc_process_msg_IPI(struct xpc_partition *part, int ch_number) -{ - struct xpc_channel *ch = &part->channels[ch_number]; - int nmsgs_sent; - - - ch->remote_GP = part->remote_GPs[ch_number]; - - - /* See what, if anything, has changed for each connected channel */ - - xpc_msgqueue_ref(ch); - - if (ch->w_remote_GP.get == ch->remote_GP.get && - ch->w_remote_GP.put == ch->remote_GP.put) { - /* nothing changed since GPs were last pulled */ - xpc_msgqueue_deref(ch); - return; - } - - if (!(ch->flags & XPC_C_CONNECTED)){ - xpc_msgqueue_deref(ch); - return; - } - - - /* - * First check to see if messages recently sent by us have been - * received by the other side. (The remote GET value will have - * changed since we last looked at it.) - */ - - if (ch->w_remote_GP.get != ch->remote_GP.get) { - - /* - * We need to notify any senders that want to be notified - * that their sent messages have been received by their - * intended recipients. We need to do this before updating - * w_remote_GP.get so that we don't allocate the same message - * queue entries prematurely (see xpc_allocate_msg()). - */ - if (atomic_read(&ch->n_to_notify) > 0) { - /* - * Notify senders that messages sent have been - * received and delivered by the other side. - */ - xpc_notify_senders(ch, xpcMsgDelivered, - ch->remote_GP.get); - } - - /* - * Clear msg->flags in previously sent messages, so that - * they're ready for xpc_allocate_msg(). - */ - xpc_clear_local_msgqueue_flags(ch); - - ch->w_remote_GP.get = ch->remote_GP.get; - - dev_dbg(xpc_chan, "w_remote_GP.get changed to %ld, partid=%d, " - "channel=%d\n", ch->w_remote_GP.get, ch->partid, - ch->number); - - /* - * If anyone was waiting for message queue entries to become - * available, wake them up. - */ - if (atomic_read(&ch->n_on_msg_allocate_wq) > 0) { - wake_up(&ch->msg_allocate_wq); - } - } - - - /* - * Now check for newly sent messages by the other side. (The remote - * PUT value will have changed since we last looked at it.) - */ - - if (ch->w_remote_GP.put != ch->remote_GP.put) { - /* - * Clear msg->flags in previously received messages, so that - * they're ready for xpc_get_deliverable_msg(). - */ - xpc_clear_remote_msgqueue_flags(ch); - - ch->w_remote_GP.put = ch->remote_GP.put; - - dev_dbg(xpc_chan, "w_remote_GP.put changed to %ld, partid=%d, " - "channel=%d\n", ch->w_remote_GP.put, ch->partid, - ch->number); - - nmsgs_sent = ch->w_remote_GP.put - ch->w_local_GP.get; - if (nmsgs_sent > 0) { - dev_dbg(xpc_chan, "msgs waiting to be copied and " - "delivered=%d, partid=%d, channel=%d\n", - nmsgs_sent, ch->partid, ch->number); - - if (ch->flags & XPC_C_CONNECTEDCALLOUT_MADE) { - xpc_activate_kthreads(ch, nmsgs_sent); - } - } - } - - xpc_msgqueue_deref(ch); -} - - -void -xpc_process_channel_activity(struct xpc_partition *part) -{ - unsigned long irq_flags; - u64 IPI_amo, IPI_flags; - struct xpc_channel *ch; - int ch_number; - u32 ch_flags; - - - IPI_amo = xpc_get_IPI_flags(part); - - /* - * Initiate channel connections for registered channels. - * - * For each connected channel that has pending messages activate idle - * kthreads and/or create new kthreads as needed. - */ - - for (ch_number = 0; ch_number < part->nchannels; ch_number++) { - ch = &part->channels[ch_number]; - - - /* - * Process any open or close related IPI flags, and then deal - * with connecting or disconnecting the channel as required. - */ - - IPI_flags = XPC_GET_IPI_FLAGS(IPI_amo, ch_number); - - if (XPC_ANY_OPENCLOSE_IPI_FLAGS_SET(IPI_flags)) { - xpc_process_openclose_IPI(part, ch_number, IPI_flags); - } - - ch_flags = ch->flags; /* need an atomic snapshot of flags */ - - if (ch_flags & XPC_C_DISCONNECTING) { - spin_lock_irqsave(&ch->lock, irq_flags); - xpc_process_disconnect(ch, &irq_flags); - spin_unlock_irqrestore(&ch->lock, irq_flags); - continue; - } - - if (part->act_state == XPC_P_DEACTIVATING) { - continue; - } - - if (!(ch_flags & XPC_C_CONNECTED)) { - if (!(ch_flags & XPC_C_OPENREQUEST)) { - DBUG_ON(ch_flags & XPC_C_SETUP); - (void) xpc_connect_channel(ch); - } else { - spin_lock_irqsave(&ch->lock, irq_flags); - xpc_process_connect(ch, &irq_flags); - spin_unlock_irqrestore(&ch->lock, irq_flags); - } - continue; - } - - - /* - * Process any message related IPI flags, this may involve the - * activation of kthreads to deliver any pending messages sent - * from the other partition. - */ - - if (XPC_ANY_MSG_IPI_FLAGS_SET(IPI_flags)) { - xpc_process_msg_IPI(part, ch_number); - } - } -} - - -/* - * XPC's heartbeat code calls this function to inform XPC that a partition is - * going down. XPC responds by tearing down the XPartition Communication - * infrastructure used for the just downed partition. - * - * XPC's heartbeat code will never call this function and xpc_partition_up() - * at the same time. Nor will it ever make multiple calls to either function - * at the same time. - */ -void -xpc_partition_going_down(struct xpc_partition *part, enum xpc_retval reason) -{ - unsigned long irq_flags; - int ch_number; - struct xpc_channel *ch; - - - dev_dbg(xpc_chan, "deactivating partition %d, reason=%d\n", - XPC_PARTID(part), reason); - - if (!xpc_part_ref(part)) { - /* infrastructure for this partition isn't currently set up */ - return; - } - - - /* disconnect channels associated with the partition going down */ - - for (ch_number = 0; ch_number < part->nchannels; ch_number++) { - ch = &part->channels[ch_number]; - - xpc_msgqueue_ref(ch); - spin_lock_irqsave(&ch->lock, irq_flags); - - XPC_DISCONNECT_CHANNEL(ch, reason, &irq_flags); - - spin_unlock_irqrestore(&ch->lock, irq_flags); - xpc_msgqueue_deref(ch); - } - - xpc_wakeup_channel_mgr(part); - - xpc_part_deref(part); -} - - -/* - * Teardown the infrastructure necessary to support XPartition Communication - * between the specified remote partition and the local one. - */ -void -xpc_teardown_infrastructure(struct xpc_partition *part) -{ - partid_t partid = XPC_PARTID(part); - - - /* - * We start off by making this partition inaccessible to local - * processes by marking it as no longer setup. Then we make it - * inaccessible to remote processes by clearing the XPC per partition - * specific variable's magic # (which indicates that these variables - * are no longer valid) and by ignoring all XPC notify IPIs sent to - * this partition. - */ - - DBUG_ON(atomic_read(&part->nchannels_engaged) != 0); - DBUG_ON(atomic_read(&part->nchannels_active) != 0); - DBUG_ON(part->setup_state != XPC_P_SETUP); - part->setup_state = XPC_P_WTEARDOWN; - - xpc_vars_part[partid].magic = 0; - - - free_irq(SGI_XPC_NOTIFY, (void *) (u64) partid); - - - /* - * Before proceeding with the teardown we have to wait until all - * existing references cease. - */ - wait_event(part->teardown_wq, (atomic_read(&part->references) == 0)); - - - /* now we can begin tearing down the infrastructure */ - - part->setup_state = XPC_P_TORNDOWN; - - /* in case we've still got outstanding timers registered... */ - del_timer_sync(&part->dropped_IPI_timer); - - kfree(part->remote_openclose_args_base); - part->remote_openclose_args = NULL; - kfree(part->local_openclose_args_base); - part->local_openclose_args = NULL; - kfree(part->remote_GPs_base); - part->remote_GPs = NULL; - kfree(part->local_GPs_base); - part->local_GPs = NULL; - kfree(part->channels); - part->channels = NULL; - part->local_IPI_amo_va = NULL; -} - - -/* - * Called by XP at the time of channel connection registration to cause - * XPC to establish connections to all currently active partitions. - */ -void -xpc_initiate_connect(int ch_number) -{ - partid_t partid; - struct xpc_partition *part; - struct xpc_channel *ch; - - - DBUG_ON(ch_number < 0 || ch_number >= XPC_NCHANNELS); - - for (partid = 1; partid < XP_MAX_PARTITIONS; partid++) { - part = &xpc_partitions[partid]; - - if (xpc_part_ref(part)) { - ch = &part->channels[ch_number]; - - /* - * Initiate the establishment of a connection on the - * newly registered channel to the remote partition. - */ - xpc_wakeup_channel_mgr(part); - xpc_part_deref(part); - } - } -} - - -void -xpc_connected_callout(struct xpc_channel *ch) -{ - /* let the registerer know that a connection has been established */ - - if (ch->func != NULL) { - dev_dbg(xpc_chan, "ch->func() called, reason=xpcConnected, " - "partid=%d, channel=%d\n", ch->partid, ch->number); - - ch->func(xpcConnected, ch->partid, ch->number, - (void *) (u64) ch->local_nentries, ch->key); - - dev_dbg(xpc_chan, "ch->func() returned, reason=xpcConnected, " - "partid=%d, channel=%d\n", ch->partid, ch->number); - } -} - - -/* - * Called by XP at the time of channel connection unregistration to cause - * XPC to teardown all current connections for the specified channel. - * - * Before returning xpc_initiate_disconnect() will wait until all connections - * on the specified channel have been closed/torndown. So the caller can be - * assured that they will not be receiving any more callouts from XPC to the - * function they registered via xpc_connect(). - * - * Arguments: - * - * ch_number - channel # to unregister. - */ -void -xpc_initiate_disconnect(int ch_number) -{ - unsigned long irq_flags; - partid_t partid; - struct xpc_partition *part; - struct xpc_channel *ch; - - - DBUG_ON(ch_number < 0 || ch_number >= XPC_NCHANNELS); - - /* initiate the channel disconnect for every active partition */ - for (partid = 1; partid < XP_MAX_PARTITIONS; partid++) { - part = &xpc_partitions[partid]; - - if (xpc_part_ref(part)) { - ch = &part->channels[ch_number]; - xpc_msgqueue_ref(ch); - - spin_lock_irqsave(&ch->lock, irq_flags); - - if (!(ch->flags & XPC_C_DISCONNECTED)) { - ch->flags |= XPC_C_WDISCONNECT; - - XPC_DISCONNECT_CHANNEL(ch, xpcUnregistering, - &irq_flags); - } - - spin_unlock_irqrestore(&ch->lock, irq_flags); - - xpc_msgqueue_deref(ch); - xpc_part_deref(part); - } - } - - xpc_disconnect_wait(ch_number); -} - - -/* - * To disconnect a channel, and reflect it back to all who may be waiting. - * - * An OPEN is not allowed until XPC_C_DISCONNECTING is cleared by - * xpc_process_disconnect(), and if set, XPC_C_WDISCONNECT is cleared by - * xpc_disconnect_wait(). - * - * THE CHANNEL IS TO BE LOCKED BY THE CALLER AND WILL REMAIN LOCKED UPON RETURN. - */ -void -xpc_disconnect_channel(const int line, struct xpc_channel *ch, - enum xpc_retval reason, unsigned long *irq_flags) -{ - u32 channel_was_connected = (ch->flags & XPC_C_CONNECTED); - - - DBUG_ON(!spin_is_locked(&ch->lock)); - - if (ch->flags & (XPC_C_DISCONNECTING | XPC_C_DISCONNECTED)) { - return; - } - DBUG_ON(!(ch->flags & (XPC_C_CONNECTING | XPC_C_CONNECTED))); - - dev_dbg(xpc_chan, "reason=%d, line=%d, partid=%d, channel=%d\n", - reason, line, ch->partid, ch->number); - - XPC_SET_REASON(ch, reason, line); - - ch->flags |= (XPC_C_CLOSEREQUEST | XPC_C_DISCONNECTING); - /* some of these may not have been set */ - ch->flags &= ~(XPC_C_OPENREQUEST | XPC_C_OPENREPLY | - XPC_C_ROPENREQUEST | XPC_C_ROPENREPLY | - XPC_C_CONNECTING | XPC_C_CONNECTED); - - xpc_IPI_send_closerequest(ch, irq_flags); - - if (channel_was_connected) { - ch->flags |= XPC_C_WASCONNECTED; - } - - spin_unlock_irqrestore(&ch->lock, *irq_flags); - - /* wake all idle kthreads so they can exit */ - if (atomic_read(&ch->kthreads_idle) > 0) { - wake_up_all(&ch->idle_wq); - - } else if ((ch->flags & XPC_C_CONNECTEDCALLOUT_MADE) && - !(ch->flags & XPC_C_DISCONNECTINGCALLOUT)) { - /* start a kthread that will do the xpcDisconnecting callout */ - xpc_create_kthreads(ch, 1, 1); - } - - /* wake those waiting to allocate an entry from the local msg queue */ - if (atomic_read(&ch->n_on_msg_allocate_wq) > 0) { - wake_up(&ch->msg_allocate_wq); - } - - spin_lock_irqsave(&ch->lock, *irq_flags); -} - - -void -xpc_disconnect_callout(struct xpc_channel *ch, enum xpc_retval reason) -{ - /* - * Let the channel's registerer know that the channel is being - * disconnected. We don't want to do this if the registerer was never - * informed of a connection being made. - */ - - if (ch->func != NULL) { - dev_dbg(xpc_chan, "ch->func() called, reason=%d, partid=%d, " - "channel=%d\n", reason, ch->partid, ch->number); - - ch->func(reason, ch->partid, ch->number, NULL, ch->key); - - dev_dbg(xpc_chan, "ch->func() returned, reason=%d, partid=%d, " - "channel=%d\n", reason, ch->partid, ch->number); - } -} - - -/* - * Wait for a message entry to become available for the specified channel, - * but don't wait any longer than 1 jiffy. - */ -static enum xpc_retval -xpc_allocate_msg_wait(struct xpc_channel *ch) -{ - enum xpc_retval ret; - - - if (ch->flags & XPC_C_DISCONNECTING) { - DBUG_ON(ch->reason == xpcInterrupted); // >>> Is this true? - return ch->reason; - } - - atomic_inc(&ch->n_on_msg_allocate_wq); - ret = interruptible_sleep_on_timeout(&ch->msg_allocate_wq, 1); - atomic_dec(&ch->n_on_msg_allocate_wq); - - if (ch->flags & XPC_C_DISCONNECTING) { - ret = ch->reason; - DBUG_ON(ch->reason == xpcInterrupted); // >>> Is this true? - } else if (ret == 0) { - ret = xpcTimeout; - } else { - ret = xpcInterrupted; - } - - return ret; -} - - -/* - * Allocate an entry for a message from the message queue associated with the - * specified channel. - */ -static enum xpc_retval -xpc_allocate_msg(struct xpc_channel *ch, u32 flags, - struct xpc_msg **address_of_msg) -{ - struct xpc_msg *msg; - enum xpc_retval ret; - s64 put; - - - /* this reference will be dropped in xpc_send_msg() */ - xpc_msgqueue_ref(ch); - - if (ch->flags & XPC_C_DISCONNECTING) { - xpc_msgqueue_deref(ch); - return ch->reason; - } - if (!(ch->flags & XPC_C_CONNECTED)) { - xpc_msgqueue_deref(ch); - return xpcNotConnected; - } - - - /* - * Get the next available message entry from the local message queue. - * If none are available, we'll make sure that we grab the latest - * GP values. - */ - ret = xpcTimeout; - - while (1) { - - put = (volatile s64) ch->w_local_GP.put; - if (put - (volatile s64) ch->w_remote_GP.get < - ch->local_nentries) { - - /* There are available message entries. We need to try - * to secure one for ourselves. We'll do this by trying - * to increment w_local_GP.put as long as someone else - * doesn't beat us to it. If they do, we'll have to - * try again. - */ - if (cmpxchg(&ch->w_local_GP.put, put, put + 1) == - put) { - /* we got the entry referenced by put */ - break; - } - continue; /* try again */ - } - - - /* - * There aren't any available msg entries at this time. - * - * In waiting for a message entry to become available, - * we set a timeout in case the other side is not - * sending completion IPIs. This lets us fake an IPI - * that will cause the IPI handler to fetch the latest - * GP values as if an IPI was sent by the other side. - */ - if (ret == xpcTimeout) { - xpc_IPI_send_local_msgrequest(ch); - } - - if (flags & XPC_NOWAIT) { - xpc_msgqueue_deref(ch); - return xpcNoWait; - } - - ret = xpc_allocate_msg_wait(ch); - if (ret != xpcInterrupted && ret != xpcTimeout) { - xpc_msgqueue_deref(ch); - return ret; - } - } - - - /* get the message's address and initialize it */ - msg = (struct xpc_msg *) ((u64) ch->local_msgqueue + - (put % ch->local_nentries) * ch->msg_size); - - - DBUG_ON(msg->flags != 0); - msg->number = put; - - dev_dbg(xpc_chan, "w_local_GP.put changed to %ld; msg=0x%p, " - "msg_number=%ld, partid=%d, channel=%d\n", put + 1, - (void *) msg, msg->number, ch->partid, ch->number); - - *address_of_msg = msg; - - return xpcSuccess; -} - - -/* - * Allocate an entry for a message from the message queue associated with the - * specified channel. NOTE that this routine can sleep waiting for a message - * entry to become available. To not sleep, pass in the XPC_NOWAIT flag. - * - * Arguments: - * - * partid - ID of partition to which the channel is connected. - * ch_number - channel #. - * flags - see xpc.h for valid flags. - * payload - address of the allocated payload area pointer (filled in on - * return) in which the user-defined message is constructed. - */ -enum xpc_retval -xpc_initiate_allocate(partid_t partid, int ch_number, u32 flags, void **payload) -{ - struct xpc_partition *part = &xpc_partitions[partid]; - enum xpc_retval ret = xpcUnknownReason; - struct xpc_msg *msg = NULL; - - - DBUG_ON(partid <= 0 || partid >= XP_MAX_PARTITIONS); - DBUG_ON(ch_number < 0 || ch_number >= part->nchannels); - - *payload = NULL; - - if (xpc_part_ref(part)) { - ret = xpc_allocate_msg(&part->channels[ch_number], flags, &msg); - xpc_part_deref(part); - - if (msg != NULL) { - *payload = &msg->payload; - } - } - - return ret; -} - - -/* - * Now we actually send the messages that are ready to be sent by advancing - * the local message queue's Put value and then send an IPI to the recipient - * partition. - */ -static void -xpc_send_msgs(struct xpc_channel *ch, s64 initial_put) -{ - struct xpc_msg *msg; - s64 put = initial_put + 1; - int send_IPI = 0; - - - while (1) { - - while (1) { - if (put == (volatile s64) ch->w_local_GP.put) { - break; - } - - msg = (struct xpc_msg *) ((u64) ch->local_msgqueue + - (put % ch->local_nentries) * ch->msg_size); - - if (!(msg->flags & XPC_M_READY)) { - break; - } - - put++; - } - - if (put == initial_put) { - /* nothing's changed */ - break; - } - - if (cmpxchg_rel(&ch->local_GP->put, initial_put, put) != - initial_put) { - /* someone else beat us to it */ - DBUG_ON((volatile s64) ch->local_GP->put < initial_put); - break; - } - - /* we just set the new value of local_GP->put */ - - dev_dbg(xpc_chan, "local_GP->put changed to %ld, partid=%d, " - "channel=%d\n", put, ch->partid, ch->number); - - send_IPI = 1; - - /* - * We need to ensure that the message referenced by - * local_GP->put is not XPC_M_READY or that local_GP->put - * equals w_local_GP.put, so we'll go have a look. - */ - initial_put = put; - } - - if (send_IPI) { - xpc_IPI_send_msgrequest(ch); - } -} - - -/* - * Common code that does the actual sending of the message by advancing the - * local message queue's Put value and sends an IPI to the partition the - * message is being sent to. - */ -static enum xpc_retval -xpc_send_msg(struct xpc_channel *ch, struct xpc_msg *msg, u8 notify_type, - xpc_notify_func func, void *key) -{ - enum xpc_retval ret = xpcSuccess; - struct xpc_notify *notify = notify; - s64 put, msg_number = msg->number; - - - DBUG_ON(notify_type == XPC_N_CALL && func == NULL); - DBUG_ON((((u64) msg - (u64) ch->local_msgqueue) / ch->msg_size) != - msg_number % ch->local_nentries); - DBUG_ON(msg->flags & XPC_M_READY); - - if (ch->flags & XPC_C_DISCONNECTING) { - /* drop the reference grabbed in xpc_allocate_msg() */ - xpc_msgqueue_deref(ch); - return ch->reason; - } - - if (notify_type != 0) { - /* - * Tell the remote side to send an ACK interrupt when the - * message has been delivered. - */ - msg->flags |= XPC_M_INTERRUPT; - - atomic_inc(&ch->n_to_notify); - - notify = &ch->notify_queue[msg_number % ch->local_nentries]; - notify->func = func; - notify->key = key; - notify->type = notify_type; - - // >>> is a mb() needed here? - - if (ch->flags & XPC_C_DISCONNECTING) { - /* - * An error occurred between our last error check and - * this one. We will try to clear the type field from - * the notify entry. If we succeed then - * xpc_disconnect_channel() didn't already process - * the notify entry. - */ - if (cmpxchg(¬ify->type, notify_type, 0) == - notify_type) { - atomic_dec(&ch->n_to_notify); - ret = ch->reason; - } - - /* drop the reference grabbed in xpc_allocate_msg() */ - xpc_msgqueue_deref(ch); - return ret; - } - } - - msg->flags |= XPC_M_READY; - - /* - * The preceding store of msg->flags must occur before the following - * load of ch->local_GP->put. - */ - mb(); - - /* see if the message is next in line to be sent, if so send it */ - - put = ch->local_GP->put; - if (put == msg_number) { - xpc_send_msgs(ch, put); - } - - /* drop the reference grabbed in xpc_allocate_msg() */ - xpc_msgqueue_deref(ch); - return ret; -} - - -/* - * Send a message previously allocated using xpc_initiate_allocate() on the - * specified channel connected to the specified partition. - * - * This routine will not wait for the message to be received, nor will - * notification be given when it does happen. Once this routine has returned - * the message entry allocated via xpc_initiate_allocate() is no longer - * accessable to the caller. - * - * This routine, although called by users, does not call xpc_part_ref() to - * ensure that the partition infrastructure is in place. It relies on the - * fact that we called xpc_msgqueue_ref() in xpc_allocate_msg(). - * - * Arguments: - * - * partid - ID of partition to which the channel is connected. - * ch_number - channel # to send message on. - * payload - pointer to the payload area allocated via - * xpc_initiate_allocate(). - */ -enum xpc_retval -xpc_initiate_send(partid_t partid, int ch_number, void *payload) -{ - struct xpc_partition *part = &xpc_partitions[partid]; - struct xpc_msg *msg = XPC_MSG_ADDRESS(payload); - enum xpc_retval ret; - - - dev_dbg(xpc_chan, "msg=0x%p, partid=%d, channel=%d\n", (void *) msg, - partid, ch_number); - - DBUG_ON(partid <= 0 || partid >= XP_MAX_PARTITIONS); - DBUG_ON(ch_number < 0 || ch_number >= part->nchannels); - DBUG_ON(msg == NULL); - - ret = xpc_send_msg(&part->channels[ch_number], msg, 0, NULL, NULL); - - return ret; -} - - -/* - * Send a message previously allocated using xpc_initiate_allocate on the - * specified channel connected to the specified partition. - * - * This routine will not wait for the message to be sent. Once this routine - * has returned the message entry allocated via xpc_initiate_allocate() is no - * longer accessable to the caller. - * - * Once the remote end of the channel has received the message, the function - * passed as an argument to xpc_initiate_send_notify() will be called. This - * allows the sender to free up or re-use any buffers referenced by the - * message, but does NOT mean the message has been processed at the remote - * end by a receiver. - * - * If this routine returns an error, the caller's function will NOT be called. - * - * This routine, although called by users, does not call xpc_part_ref() to - * ensure that the partition infrastructure is in place. It relies on the - * fact that we called xpc_msgqueue_ref() in xpc_allocate_msg(). - * - * Arguments: - * - * partid - ID of partition to which the channel is connected. - * ch_number - channel # to send message on. - * payload - pointer to the payload area allocated via - * xpc_initiate_allocate(). - * func - function to call with asynchronous notification of message - * receipt. THIS FUNCTION MUST BE NON-BLOCKING. - * key - user-defined key to be passed to the function when it's called. - */ -enum xpc_retval -xpc_initiate_send_notify(partid_t partid, int ch_number, void *payload, - xpc_notify_func func, void *key) -{ - struct xpc_partition *part = &xpc_partitions[partid]; - struct xpc_msg *msg = XPC_MSG_ADDRESS(payload); - enum xpc_retval ret; - - - dev_dbg(xpc_chan, "msg=0x%p, partid=%d, channel=%d\n", (void *) msg, - partid, ch_number); - - DBUG_ON(partid <= 0 || partid >= XP_MAX_PARTITIONS); - DBUG_ON(ch_number < 0 || ch_number >= part->nchannels); - DBUG_ON(msg == NULL); - DBUG_ON(func == NULL); - - ret = xpc_send_msg(&part->channels[ch_number], msg, XPC_N_CALL, - func, key); - return ret; -} - - -static struct xpc_msg * -xpc_pull_remote_msg(struct xpc_channel *ch, s64 get) -{ - struct xpc_partition *part = &xpc_partitions[ch->partid]; - struct xpc_msg *remote_msg, *msg; - u32 msg_index, nmsgs; - u64 msg_offset; - enum xpc_retval ret; - - - if (mutex_lock_interruptible(&ch->msg_to_pull_mutex) != 0) { - /* we were interrupted by a signal */ - return NULL; - } - - while (get >= ch->next_msg_to_pull) { - - /* pull as many messages as are ready and able to be pulled */ - - msg_index = ch->next_msg_to_pull % ch->remote_nentries; - - DBUG_ON(ch->next_msg_to_pull >= - (volatile s64) ch->w_remote_GP.put); - nmsgs = (volatile s64) ch->w_remote_GP.put - - ch->next_msg_to_pull; - if (msg_index + nmsgs > ch->remote_nentries) { - /* ignore the ones that wrap the msg queue for now */ - nmsgs = ch->remote_nentries - msg_index; - } - - msg_offset = msg_index * ch->msg_size; - msg = (struct xpc_msg *) ((u64) ch->remote_msgqueue + - msg_offset); - remote_msg = (struct xpc_msg *) (ch->remote_msgqueue_pa + - msg_offset); - - if ((ret = xpc_pull_remote_cachelines(part, msg, remote_msg, - nmsgs * ch->msg_size)) != xpcSuccess) { - - dev_dbg(xpc_chan, "failed to pull %d msgs starting with" - " msg %ld from partition %d, channel=%d, " - "ret=%d\n", nmsgs, ch->next_msg_to_pull, - ch->partid, ch->number, ret); - - XPC_DEACTIVATE_PARTITION(part, ret); - - mutex_unlock(&ch->msg_to_pull_mutex); - return NULL; - } - - mb(); /* >>> this may not be needed, we're not sure */ - - ch->next_msg_to_pull += nmsgs; - } - - mutex_unlock(&ch->msg_to_pull_mutex); - - /* return the message we were looking for */ - msg_offset = (get % ch->remote_nentries) * ch->msg_size; - msg = (struct xpc_msg *) ((u64) ch->remote_msgqueue + msg_offset); - - return msg; -} - - -/* - * Get a message to be delivered. - */ -static struct xpc_msg * -xpc_get_deliverable_msg(struct xpc_channel *ch) -{ - struct xpc_msg *msg = NULL; - s64 get; - - - do { - if ((volatile u32) ch->flags & XPC_C_DISCONNECTING) { - break; - } - - get = (volatile s64) ch->w_local_GP.get; - if (get == (volatile s64) ch->w_remote_GP.put) { - break; - } - - /* There are messages waiting to be pulled and delivered. - * We need to try to secure one for ourselves. We'll do this - * by trying to increment w_local_GP.get and hope that no one - * else beats us to it. If they do, we'll we'll simply have - * to try again for the next one. - */ - - if (cmpxchg(&ch->w_local_GP.get, get, get + 1) == get) { - /* we got the entry referenced by get */ - - dev_dbg(xpc_chan, "w_local_GP.get changed to %ld, " - "partid=%d, channel=%d\n", get + 1, - ch->partid, ch->number); - - /* pull the message from the remote partition */ - - msg = xpc_pull_remote_msg(ch, get); - - DBUG_ON(msg != NULL && msg->number != get); - DBUG_ON(msg != NULL && (msg->flags & XPC_M_DONE)); - DBUG_ON(msg != NULL && !(msg->flags & XPC_M_READY)); - - break; - } - - } while (1); - - return msg; -} - - -/* - * Deliver a message to its intended recipient. - */ -void -xpc_deliver_msg(struct xpc_channel *ch) -{ - struct xpc_msg *msg; - - - if ((msg = xpc_get_deliverable_msg(ch)) != NULL) { - - /* - * This ref is taken to protect the payload itself from being - * freed before the user is finished with it, which the user - * indicates by calling xpc_initiate_received(). - */ - xpc_msgqueue_ref(ch); - - atomic_inc(&ch->kthreads_active); - - if (ch->func != NULL) { - dev_dbg(xpc_chan, "ch->func() called, msg=0x%p, " - "msg_number=%ld, partid=%d, channel=%d\n", - (void *) msg, msg->number, ch->partid, - ch->number); - - /* deliver the message to its intended recipient */ - ch->func(xpcMsgReceived, ch->partid, ch->number, - &msg->payload, ch->key); - - dev_dbg(xpc_chan, "ch->func() returned, msg=0x%p, " - "msg_number=%ld, partid=%d, channel=%d\n", - (void *) msg, msg->number, ch->partid, - ch->number); - } - - atomic_dec(&ch->kthreads_active); - } -} - - -/* - * Now we actually acknowledge the messages that have been delivered and ack'd - * by advancing the cached remote message queue's Get value and if requested - * send an IPI to the message sender's partition. - */ -static void -xpc_acknowledge_msgs(struct xpc_channel *ch, s64 initial_get, u8 msg_flags) -{ - struct xpc_msg *msg; - s64 get = initial_get + 1; - int send_IPI = 0; - - - while (1) { - - while (1) { - if (get == (volatile s64) ch->w_local_GP.get) { - break; - } - - msg = (struct xpc_msg *) ((u64) ch->remote_msgqueue + - (get % ch->remote_nentries) * ch->msg_size); - - if (!(msg->flags & XPC_M_DONE)) { - break; - } - - msg_flags |= msg->flags; - get++; - } - - if (get == initial_get) { - /* nothing's changed */ - break; - } - - if (cmpxchg_rel(&ch->local_GP->get, initial_get, get) != - initial_get) { - /* someone else beat us to it */ - DBUG_ON((volatile s64) ch->local_GP->get <= - initial_get); - break; - } - - /* we just set the new value of local_GP->get */ - - dev_dbg(xpc_chan, "local_GP->get changed to %ld, partid=%d, " - "channel=%d\n", get, ch->partid, ch->number); - - send_IPI = (msg_flags & XPC_M_INTERRUPT); - - /* - * We need to ensure that the message referenced by - * local_GP->get is not XPC_M_DONE or that local_GP->get - * equals w_local_GP.get, so we'll go have a look. - */ - initial_get = get; - } - - if (send_IPI) { - xpc_IPI_send_msgrequest(ch); - } -} - - -/* - * Acknowledge receipt of a delivered message. - * - * If a message has XPC_M_INTERRUPT set, send an interrupt to the partition - * that sent the message. - * - * This function, although called by users, does not call xpc_part_ref() to - * ensure that the partition infrastructure is in place. It relies on the - * fact that we called xpc_msgqueue_ref() in xpc_deliver_msg(). - * - * Arguments: - * - * partid - ID of partition to which the channel is connected. - * ch_number - channel # message received on. - * payload - pointer to the payload area allocated via - * xpc_initiate_allocate(). - */ -void -xpc_initiate_received(partid_t partid, int ch_number, void *payload) -{ - struct xpc_partition *part = &xpc_partitions[partid]; - struct xpc_channel *ch; - struct xpc_msg *msg = XPC_MSG_ADDRESS(payload); - s64 get, msg_number = msg->number; - - - DBUG_ON(partid <= 0 || partid >= XP_MAX_PARTITIONS); - DBUG_ON(ch_number < 0 || ch_number >= part->nchannels); - - ch = &part->channels[ch_number]; - - dev_dbg(xpc_chan, "msg=0x%p, msg_number=%ld, partid=%d, channel=%d\n", - (void *) msg, msg_number, ch->partid, ch->number); - - DBUG_ON((((u64) msg - (u64) ch->remote_msgqueue) / ch->msg_size) != - msg_number % ch->remote_nentries); - DBUG_ON(msg->flags & XPC_M_DONE); - - msg->flags |= XPC_M_DONE; - - /* - * The preceding store of msg->flags must occur before the following - * load of ch->local_GP->get. - */ - mb(); - - /* - * See if this message is next in line to be acknowledged as having - * been delivered. - */ - get = ch->local_GP->get; - if (get == msg_number) { - xpc_acknowledge_msgs(ch, get, msg->flags); - } - - /* the call to xpc_msgqueue_ref() was done by xpc_deliver_msg() */ - xpc_msgqueue_deref(ch); -} - diff --git a/arch/ia64/sn/kernel/xpc_main.c b/arch/ia64/sn/kernel/xpc_main.c deleted file mode 100644 index 9e0b164da9c..00000000000 --- a/arch/ia64/sn/kernel/xpc_main.c +++ /dev/null @@ -1,1431 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (c) 2004-2007 Silicon Graphics, Inc. All Rights Reserved. - */ - - -/* - * Cross Partition Communication (XPC) support - standard version. - * - * XPC provides a message passing capability that crosses partition - * boundaries. This module is made up of two parts: - * - * partition This part detects the presence/absence of other - * partitions. It provides a heartbeat and monitors - * the heartbeats of other partitions. - * - * channel This part manages the channels and sends/receives - * messages across them to/from other partitions. - * - * There are a couple of additional functions residing in XP, which - * provide an interface to XPC for its users. - * - * - * Caveats: - * - * . We currently have no way to determine which nasid an IPI came - * from. Thus, xpc_IPI_send() does a remote AMO write followed by - * an IPI. The AMO indicates where data is to be pulled from, so - * after the IPI arrives, the remote partition checks the AMO word. - * The IPI can actually arrive before the AMO however, so other code - * must periodically check for this case. Also, remote AMO operations - * do not reliably time out. Thus we do a remote PIO read solely to - * know whether the remote partition is down and whether we should - * stop sending IPIs to it. This remote PIO read operation is set up - * in a special nofault region so SAL knows to ignore (and cleanup) - * any errors due to the remote AMO write, PIO read, and/or PIO - * write operations. - * - * If/when new hardware solves this IPI problem, we should abandon - * the current approach. - * - */ - - -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/init.h> -#include <linux/sched.h> -#include <linux/syscalls.h> -#include <linux/cache.h> -#include <linux/interrupt.h> -#include <linux/delay.h> -#include <linux/reboot.h> -#include <linux/completion.h> -#include <linux/kdebug.h> -#include <asm/sn/intr.h> -#include <asm/sn/sn_sal.h> -#include <asm/uaccess.h> -#include <asm/sn/xpc.h> - - -/* define two XPC debug device structures to be used with dev_dbg() et al */ - -struct device_driver xpc_dbg_name = { - .name = "xpc" -}; - -struct device xpc_part_dbg_subname = { - .bus_id = {0}, /* set to "part" at xpc_init() time */ - .driver = &xpc_dbg_name -}; - -struct device xpc_chan_dbg_subname = { - .bus_id = {0}, /* set to "chan" at xpc_init() time */ - .driver = &xpc_dbg_name -}; - -struct device *xpc_part = &xpc_part_dbg_subname; -struct device *xpc_chan = &xpc_chan_dbg_subname; - - -static int xpc_kdebug_ignore; - - -/* systune related variables for /proc/sys directories */ - -static int xpc_hb_interval = XPC_HB_DEFAULT_INTERVAL; -static int xpc_hb_min_interval = 1; -static int xpc_hb_max_interval = 10; - -static int xpc_hb_check_interval = XPC_HB_CHECK_DEFAULT_INTERVAL; -static int xpc_hb_check_min_interval = 10; -static int xpc_hb_check_max_interval = 120; - -int xpc_disengage_request_timelimit = XPC_DISENGAGE_REQUEST_DEFAULT_TIMELIMIT; -static int xpc_disengage_request_min_timelimit = 0; -static int xpc_disengage_request_max_timelimit = 120; - -static ctl_table xpc_sys_xpc_hb_dir[] = { - { - .ctl_name = CTL_UNNUMBERED, - .procname = "hb_interval", - .data = &xpc_hb_interval, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, - .extra1 = &xpc_hb_min_interval, - .extra2 = &xpc_hb_max_interval - }, - { - .ctl_name = CTL_UNNUMBERED, - .procname = "hb_check_interval", - .data = &xpc_hb_check_interval, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, - .extra1 = &xpc_hb_check_min_interval, - .extra2 = &xpc_hb_check_max_interval - }, - {} -}; -static ctl_table xpc_sys_xpc_dir[] = { - { - .ctl_name = CTL_UNNUMBERED, - .procname = "hb", - .mode = 0555, - .child = xpc_sys_xpc_hb_dir - }, - { - .ctl_name = CTL_UNNUMBERED, - .procname = "disengage_request_timelimit", - .data = &xpc_disengage_request_timelimit, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, - .extra1 = &xpc_disengage_request_min_timelimit, - .extra2 = &xpc_disengage_request_max_timelimit - }, - {} -}; -static ctl_table xpc_sys_dir[] = { - { - .ctl_name = CTL_UNNUMBERED, - .procname = "xpc", - .mode = 0555, - .child = xpc_sys_xpc_dir - }, - {} -}; -static struct ctl_table_header *xpc_sysctl; - -/* non-zero if any remote partition disengage request was timed out */ -int xpc_disengage_request_timedout; - -/* #of IRQs received */ -static atomic_t xpc_act_IRQ_rcvd; - -/* IRQ handler notifies this wait queue on receipt of an IRQ */ -static DECLARE_WAIT_QUEUE_HEAD(xpc_act_IRQ_wq); - -static unsigned long xpc_hb_check_timeout; - -/* notification that the xpc_hb_checker thread has exited */ -static DECLARE_COMPLETION(xpc_hb_checker_exited); - -/* notification that the xpc_discovery thread has exited */ -static DECLARE_COMPLETION(xpc_discovery_exited); - - -static struct timer_list xpc_hb_timer; - - -static void xpc_kthread_waitmsgs(struct xpc_partition *, struct xpc_channel *); - - -static int xpc_system_reboot(struct notifier_block *, unsigned long, void *); -static struct notifier_block xpc_reboot_notifier = { - .notifier_call = xpc_system_reboot, -}; - -static int xpc_system_die(struct notifier_block *, unsigned long, void *); -static struct notifier_block xpc_die_notifier = { - .notifier_call = xpc_system_die, -}; - - -/* - * Timer function to enforce the timelimit on the partition disengage request. - */ -static void -xpc_timeout_partition_disengage_request(unsigned long data) -{ - struct xpc_partition *part = (struct xpc_partition *) data; - - - DBUG_ON(time_before(jiffies, part->disengage_request_timeout)); - - (void) xpc_partition_disengaged(part); - - DBUG_ON(part->disengage_request_timeout != 0); - DBUG_ON(xpc_partition_engaged(1UL << XPC_PARTID(part)) != 0); -} - - -/* - * Notify the heartbeat check thread that an IRQ has been received. - */ -static irqreturn_t -xpc_act_IRQ_handler(int irq, void *dev_id) -{ - atomic_inc(&xpc_act_IRQ_rcvd); - wake_up_interruptible(&xpc_act_IRQ_wq); - return IRQ_HANDLED; -} - - -/* - * Timer to produce the heartbeat. The timer structures function is - * already set when this is initially called. A tunable is used to - * specify when the next timeout should occur. - */ -static void -xpc_hb_beater(unsigned long dummy) -{ - xpc_vars->heartbeat++; - - if (time_after_eq(jiffies, xpc_hb_check_timeout)) { - wake_up_interruptible(&xpc_act_IRQ_wq); - } - - xpc_hb_timer.expires = jiffies + (xpc_hb_interval * HZ); - add_timer(&xpc_hb_timer); -} - - -/* - * This thread is responsible for nearly all of the partition - * activation/deactivation. - */ -static int -xpc_hb_checker(void *ignore) -{ - int last_IRQ_count = 0; - int new_IRQ_count; - int force_IRQ=0; - - - /* this thread was marked active by xpc_hb_init() */ - - daemonize(XPC_HB_CHECK_THREAD_NAME); - - set_cpus_allowed(current, cpumask_of_cpu(XPC_HB_CHECK_CPU)); - - /* set our heartbeating to other partitions into motion */ - xpc_hb_check_timeout = jiffies + (xpc_hb_check_interval * HZ); - xpc_hb_beater(0); - - while (!(volatile int) xpc_exiting) { - - dev_dbg(xpc_part, "woke up with %d ticks rem; %d IRQs have " - "been received\n", - (int) (xpc_hb_check_timeout - jiffies), - atomic_read(&xpc_act_IRQ_rcvd) - last_IRQ_count); - - - /* checking of remote heartbeats is skewed by IRQ handling */ - if (time_after_eq(jiffies, xpc_hb_check_timeout)) { - dev_dbg(xpc_part, "checking remote heartbeats\n"); - xpc_check_remote_hb(); - - /* - * We need to periodically recheck to ensure no - * IPI/AMO pairs have been missed. That check - * must always reset xpc_hb_check_timeout. - */ - force_IRQ = 1; - } - - - /* check for outstanding IRQs */ - new_IRQ_count = atomic_read(&xpc_act_IRQ_rcvd); - if (last_IRQ_count < new_IRQ_count || force_IRQ != 0) { - force_IRQ = 0; - - dev_dbg(xpc_part, "found an IRQ to process; will be " - "resetting xpc_hb_check_timeout\n"); - - last_IRQ_count += xpc_identify_act_IRQ_sender(); - if (last_IRQ_count < new_IRQ_count) { - /* retry once to help avoid missing AMO */ - (void) xpc_identify_act_IRQ_sender(); - } - last_IRQ_count = new_IRQ_count; - - xpc_hb_check_timeout = jiffies + - (xpc_hb_check_interval * HZ); - } - - /* wait for IRQ or timeout */ - (void) wait_event_interruptible(xpc_act_IRQ_wq, - (last_IRQ_count < atomic_read(&xpc_act_IRQ_rcvd) || - time_after_eq(jiffies, xpc_hb_check_timeout) || - (volatile int) xpc_exiting)); - } - - dev_dbg(xpc_part, "heartbeat checker is exiting\n"); - - - /* mark this thread as having exited */ - complete(&xpc_hb_checker_exited); - return 0; -} - - -/* - * This thread will attempt to discover other partitions to activate - * based on info provided by SAL. This new thread is short lived and - * will exit once discovery is complete. - */ -static int -xpc_initiate_discovery(void *ignore) -{ - daemonize(XPC_DISCOVERY_THREAD_NAME); - - xpc_discovery(); - - dev_dbg(xpc_part, "discovery thread is exiting\n"); - - /* mark this thread as having exited */ - complete(&xpc_discovery_exited); - return 0; -} - - -/* - * Establish first contact with the remote partititon. This involves pulling - * the XPC per partition variables from the remote partition and waiting for - * the remote partition to pull ours. - */ -static enum xpc_retval -xpc_make_first_contact(struct xpc_partition *part) -{ - enum xpc_retval ret; - - - while ((ret = xpc_pull_remote_vars_part(part)) != xpcSuccess) { - if (ret != xpcRetry) { - XPC_DEACTIVATE_PARTITION(part, ret); - return ret; - } - - dev_dbg(xpc_chan, "waiting to make first contact with " - "partition %d\n", XPC_PARTID(part)); - - /* wait a 1/4 of a second or so */ - (void) msleep_interruptible(250); - - if (part->act_state == XPC_P_DEACTIVATING) { - return part->reason; - } - } - - return xpc_mark_partition_active(part); -} - - -/* - * The first kthread assigned to a newly activated partition is the one - * created by XPC HB with which it calls xpc_partition_up(). XPC hangs on to - * that kthread until the partition is brought down, at which time that kthread - * returns back to XPC HB. (The return of that kthread will signify to XPC HB - * that XPC has dismantled all communication infrastructure for the associated - * partition.) This kthread becomes the channel manager for that partition. - * - * Each active partition has a channel manager, who, besides connecting and - * disconnecting channels, will ensure that each of the partition's connected - * channels has the required number of assigned kthreads to get the work done. - */ -static void -xpc_channel_mgr(struct xpc_partition *part) -{ - while (part->act_state != XPC_P_DEACTIVATING || - atomic_read(&part->nchannels_active) > 0 || - !xpc_partition_disengaged(part)) { - - xpc_process_channel_activity(part); - - - /* - * Wait until we've been requested to activate kthreads or - * all of the channel's message queues have been torn down or - * a signal is pending. - * - * The channel_mgr_requests is set to 1 after being awakened, - * This is done to prevent the channel mgr from making one pass - * through the loop for each request, since he will - * be servicing all the requests in one pass. The reason it's - * set to 1 instead of 0 is so that other kthreads will know - * that the channel mgr is running and won't bother trying to - * wake him up. - */ - atomic_dec(&part->channel_mgr_requests); - (void) wait_event_interruptible(part->channel_mgr_wq, - (atomic_read(&part->channel_mgr_requests) > 0 || - (volatile u64) part->local_IPI_amo != 0 || - ((volatile u8) part->act_state == - XPC_P_DEACTIVATING && - atomic_read(&part->nchannels_active) == 0 && - xpc_partition_disengaged(part)))); - atomic_set(&part->channel_mgr_requests, 1); - - // >>> Does it need to wakeup periodically as well? In case we - // >>> miscalculated the #of kthreads to wakeup or create? - } -} - - -/* - * When XPC HB determines that a partition has come up, it will create a new - * kthread and that kthread will call this function to attempt to set up the - * basic infrastructure used for Cross Partition Communication with the newly - * upped partition. - * - * The kthread that was created by XPC HB and which setup the XPC - * infrastructure will remain assigned to the partition until the partition - * goes down. At which time the kthread will teardown the XPC infrastructure - * and then exit. - * - * XPC HB will put the remote partition's XPC per partition specific variables - * physical address into xpc_partitions[partid].remote_vars_part_pa prior to - * calling xpc_partition_up(). - */ -static void -xpc_partition_up(struct xpc_partition *part) -{ - DBUG_ON(part->channels != NULL); - - dev_dbg(xpc_chan, "activating partition %d\n", XPC_PARTID(part)); - - if (xpc_setup_infrastructure(part) != xpcSuccess) { - return; - } - - /* - * The kthread that XPC HB called us with will become the - * channel manager for this partition. It will not return - * back to XPC HB until the partition's XPC infrastructure - * has been dismantled. - */ - - (void) xpc_part_ref(part); /* this will always succeed */ - - if (xpc_make_first_contact(part) == xpcSuccess) { - xpc_channel_mgr(part); - } - - xpc_part_deref(part); - - xpc_teardown_infrastructure(part); -} - - -static int -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 }; - int ret; - - - DBUG_ON(partid <= 0 || partid >= XP_MAX_PARTITIONS); - - spin_lock_irqsave(&part->act_lock, irq_flags); - - if (part->act_state == XPC_P_DEACTIVATING) { - part->act_state = XPC_P_INACTIVE; - spin_unlock_irqrestore(&part->act_lock, irq_flags); - part->remote_rp_pa = 0; - return 0; - } - - /* indicate the thread is activating */ - DBUG_ON(part->act_state != XPC_P_ACTIVATION_REQ); - part->act_state = XPC_P_ACTIVATING; - - XPC_SET_REASON(part, 0, 0); - spin_unlock_irqrestore(&part->act_lock, irq_flags); - - dev_dbg(xpc_part, "bringing partition %d up\n", partid); - - daemonize("xpc%02d", partid); - - /* - * This thread needs to run at a realtime priority to prevent a - * significant performance degradation. - */ - ret = sched_setscheduler(current, SCHED_FIFO, ¶m); - if (ret != 0) { - dev_warn(xpc_part, "unable to set pid %d to a realtime " - "priority, ret=%d\n", current->pid, ret); - } - - /* allow this thread and its children to run on any CPU */ - set_cpus_allowed(current, CPU_MASK_ALL); - - /* - * Register the remote partition's AMOs with SAL so it can handle - * and cleanup errors within that address range should the remote - * partition go down. We don't unregister this range because it is - * difficult to tell when outstanding writes to the remote partition - * are finished and thus when it is safe to unregister. This should - * not result in wasted space in the SAL xp_addr_region table because - * we should get the same page for remote_amos_page_pa after module - * reloads and system reboots. - */ - if (sn_register_xp_addr_region(part->remote_amos_page_pa, - PAGE_SIZE, 1) < 0) { - dev_warn(xpc_part, "xpc_partition_up(%d) failed to register " - "xp_addr region\n", partid); - - spin_lock_irqsave(&part->act_lock, irq_flags); - part->act_state = XPC_P_INACTIVE; - XPC_SET_REASON(part, xpcPhysAddrRegFailed, __LINE__); - spin_unlock_irqrestore(&part->act_lock, irq_flags); - part->remote_rp_pa = 0; - return 0; - } - - xpc_allow_hb(partid, xpc_vars); - xpc_IPI_send_activated(part); - - - /* - * xpc_partition_up() holds this thread and marks this partition as - * XPC_P_ACTIVE by calling xpc_hb_mark_active(). - */ - (void) xpc_partition_up(part); - - xpc_disallow_hb(partid, xpc_vars); - xpc_mark_partition_inactive(part); - - if (part->reason == xpcReactivating) { - /* interrupting ourselves results in activating partition */ - xpc_IPI_send_reactivate(part); - } - - return 0; -} - - -void -xpc_activate_partition(struct xpc_partition *part) -{ - partid_t partid = XPC_PARTID(part); - unsigned long irq_flags; - pid_t pid; - - - spin_lock_irqsave(&part->act_lock, irq_flags); - - DBUG_ON(part->act_state != XPC_P_INACTIVE); - - part->act_state = XPC_P_ACTIVATION_REQ; - XPC_SET_REASON(part, xpcCloneKThread, __LINE__); - - spin_unlock_irqrestore(&part->act_lock, irq_flags); - - pid = kernel_thread(xpc_activating, (void *) ((u64) partid), 0); - - if (unlikely(pid <= 0)) { - spin_lock_irqsave(&part->act_lock, irq_flags); - part->act_state = XPC_P_INACTIVE; - XPC_SET_REASON(part, xpcCloneKThreadFailed, __LINE__); - spin_unlock_irqrestore(&part->act_lock, irq_flags); - } -} - - -/* - * Handle the receipt of a SGI_XPC_NOTIFY IRQ by seeing whether the specified - * partition actually sent it. Since SGI_XPC_NOTIFY IRQs may be shared by more - * than one partition, we use an AMO_t structure per partition to indicate - * whether a partition has sent an IPI or not. >>> If it has, then wake up the - * associated kthread to handle it. - * - * All SGI_XPC_NOTIFY IRQs received by XPC are the result of IPIs sent by XPC - * running on other partitions. - * - * Noteworthy Arguments: - * - * irq - Interrupt ReQuest number. NOT USED. - * - * dev_id - partid of IPI's potential sender. - */ -irqreturn_t -xpc_notify_IRQ_handler(int irq, void *dev_id) -{ - partid_t partid = (partid_t) (u64) dev_id; - struct xpc_partition *part = &xpc_partitions[partid]; - - - DBUG_ON(partid <= 0 || partid >= XP_MAX_PARTITIONS); - - if (xpc_part_ref(part)) { - xpc_check_for_channel_activity(part); - - xpc_part_deref(part); - } - return IRQ_HANDLED; -} - - -/* - * Check to see if xpc_notify_IRQ_handler() dropped any IPIs on the floor - * because the write to their associated IPI amo completed after the IRQ/IPI - * was received. - */ -void -xpc_dropped_IPI_check(struct xpc_partition *part) -{ - if (xpc_part_ref(part)) { - xpc_check_for_channel_activity(part); - - part->dropped_IPI_timer.expires = jiffies + - XPC_P_DROPPED_IPI_WAIT; - add_timer(&part->dropped_IPI_timer); - xpc_part_deref(part); - } -} - - -void -xpc_activate_kthreads(struct xpc_channel *ch, int needed) -{ - int idle = atomic_read(&ch->kthreads_idle); - int assigned = atomic_read(&ch->kthreads_assigned); - int wakeup; - - - DBUG_ON(needed <= 0); - - if (idle > 0) { - wakeup = (needed > idle) ? idle : needed; - needed -= wakeup; - - dev_dbg(xpc_chan, "wakeup %d idle kthreads, partid=%d, " - "channel=%d\n", wakeup, ch->partid, ch->number); - - /* only wakeup the requested number of kthreads */ - wake_up_nr(&ch->idle_wq, wakeup); - } - - if (needed <= 0) { - return; - } - - if (needed + assigned > ch->kthreads_assigned_limit) { - needed = ch->kthreads_assigned_limit - assigned; - // >>>should never be less than 0 - if (needed <= 0) { - return; - } - } - - dev_dbg(xpc_chan, "create %d new kthreads, partid=%d, channel=%d\n", - needed, ch->partid, ch->number); - - xpc_create_kthreads(ch, needed, 0); -} - - -/* - * This function is where XPC's kthreads wait for messages to deliver. - */ -static void -xpc_kthread_waitmsgs(struct xpc_partition *part, struct xpc_channel *ch) -{ - do { - /* deliver messages to their intended recipients */ - - while ((volatile s64) ch->w_local_GP.get < - (volatile s64) ch->w_remote_GP.put && - !((volatile u32) ch->flags & - XPC_C_DISCONNECTING)) { - xpc_deliver_msg(ch); - } - - if (atomic_inc_return(&ch->kthreads_idle) > - ch->kthreads_idle_limit) { - /* too many idle kthreads on this channel */ - atomic_dec(&ch->kthreads_idle); - break; - } - - dev_dbg(xpc_chan, "idle kthread calling " - "wait_event_interruptible_exclusive()\n"); - - (void) wait_event_interruptible_exclusive(ch->idle_wq, - ((volatile s64) ch->w_local_GP.get < - (volatile s64) ch->w_remote_GP.put || - ((volatile u32) ch->flags & - XPC_C_DISCONNECTING))); - - atomic_dec(&ch->kthreads_idle); - - } while (!((volatile u32) ch->flags & XPC_C_DISCONNECTING)); -} - - -static int -xpc_daemonize_kthread(void *args) -{ - partid_t partid = XPC_UNPACK_ARG1(args); - u16 ch_number = XPC_UNPACK_ARG2(args); - struct xpc_partition *part = &xpc_partitions[partid]; - struct xpc_channel *ch; - int n_needed; - unsigned long irq_flags; - - - daemonize("xpc%02dc%d", partid, ch_number); - - dev_dbg(xpc_chan, "kthread starting, partid=%d, channel=%d\n", - partid, ch_number); - - ch = &part->channels[ch_number]; - - if (!(ch->flags & XPC_C_DISCONNECTING)) { - - /* let registerer know that connection has been established */ - - spin_lock_irqsave(&ch->lock, irq_flags); - if (!(ch->flags & XPC_C_CONNECTEDCALLOUT)) { - ch->flags |= XPC_C_CONNECTEDCALLOUT; - spin_unlock_irqrestore(&ch->lock, irq_flags); - - xpc_connected_callout(ch); - - spin_lock_irqsave(&ch->lock, irq_flags); - ch->flags |= XPC_C_CONNECTEDCALLOUT_MADE; - spin_unlock_irqrestore(&ch->lock, irq_flags); - - /* - * It is possible that while the callout was being - * made that the remote partition sent some messages. - * If that is the case, we may need to activate - * additional kthreads to help deliver them. We only - * need one less than total #of messages to deliver. - */ - n_needed = ch->w_remote_GP.put - ch->w_local_GP.get - 1; - if (n_needed > 0 && - !(ch->flags & XPC_C_DISCONNECTING)) { - xpc_activate_kthreads(ch, n_needed); - } - } else { - spin_unlock_irqrestore(&ch->lock, irq_flags); - } - - xpc_kthread_waitmsgs(part, ch); - } - - /* let registerer know that connection is disconnecting */ - - spin_lock_irqsave(&ch->lock, irq_flags); - if ((ch->flags & XPC_C_CONNECTEDCALLOUT_MADE) && - !(ch->flags & XPC_C_DISCONNECTINGCALLOUT)) { - ch->flags |= XPC_C_DISCONNECTINGCALLOUT; - spin_unlock_irqrestore(&ch->lock, irq_flags); - - xpc_disconnect_callout(ch, xpcDisconnecting); - - spin_lock_irqsave(&ch->lock, irq_flags); - ch->flags |= XPC_C_DISCONNECTINGCALLOUT_MADE; - } - spin_unlock_irqrestore(&ch->lock, irq_flags); - - if (atomic_dec_return(&ch->kthreads_assigned) == 0) { - if (atomic_dec_return(&part->nchannels_engaged) == 0) { - xpc_mark_partition_disengaged(part); - xpc_IPI_send_disengage(part); - } - } - - xpc_msgqueue_deref(ch); - - dev_dbg(xpc_chan, "kthread exiting, partid=%d, channel=%d\n", - partid, ch_number); - - xpc_part_deref(part); - return 0; -} - - -/* - * For each partition that XPC has established communications with, there is - * a minimum of one kernel thread assigned to perform any operation that - * may potentially sleep or block (basically the callouts to the asynchronous - * functions registered via xpc_connect()). - * - * Additional kthreads are created and destroyed by XPC as the workload - * demands. - * - * A kthread is assigned to one of the active channels that exists for a given - * partition. - */ -void -xpc_create_kthreads(struct xpc_channel *ch, int needed, - int ignore_disconnecting) -{ - unsigned long irq_flags; - pid_t pid; - u64 args = XPC_PACK_ARGS(ch->partid, ch->number); - struct xpc_partition *part = &xpc_partitions[ch->partid]; - - - while (needed-- > 0) { - - /* - * The following is done on behalf of the newly created - * kthread. That kthread is responsible for doing the - * counterpart to the following before it exits. - */ - if (ignore_disconnecting) { - if (!atomic_inc_not_zero(&ch->kthreads_assigned)) { - /* kthreads assigned had gone to zero */ - BUG_ON(!(ch->flags & - XPC_C_DISCONNECTINGCALLOUT_MADE)); - break; - } - - } else if (ch->flags & XPC_C_DISCONNECTING) { - break; - - } else if (atomic_inc_return(&ch->kthreads_assigned) == 1) { - if (atomic_inc_return(&part->nchannels_engaged) == 1) - xpc_mark_partition_engaged(part); - } - (void) xpc_part_ref(part); - xpc_msgqueue_ref(ch); - - pid = kernel_thread(xpc_daemonize_kthread, (void *) args, 0); - if (pid < 0) { - /* the fork failed */ - - /* - * NOTE: if (ignore_disconnecting && - * !(ch->flags & XPC_C_DISCONNECTINGCALLOUT)) is true, - * then we'll deadlock if all other kthreads assigned - * to this channel are blocked in the channel's - * registerer, because the only thing that will unblock - * them is the xpcDisconnecting callout that this - * failed kernel_thread would have made. - */ - - if (atomic_dec_return(&ch->kthreads_assigned) == 0 && - atomic_dec_return(&part->nchannels_engaged) == 0) { - xpc_mark_partition_disengaged(part); - xpc_IPI_send_disengage(part); - } - xpc_msgqueue_deref(ch); - xpc_part_deref(part); - - if (atomic_read(&ch->kthreads_assigned) < - ch->kthreads_idle_limit) { - /* - * Flag this as an error only if we have an - * insufficient #of kthreads for the channel - * to function. - */ - spin_lock_irqsave(&ch->lock, irq_flags); - XPC_DISCONNECT_CHANNEL(ch, xpcLackOfResources, - &irq_flags); - spin_unlock_irqrestore(&ch->lock, irq_flags); - } - break; - } - - ch->kthreads_created++; // >>> temporary debug only!!! - } -} - - -void -xpc_disconnect_wait(int ch_number) -{ - unsigned long irq_flags; - partid_t partid; - struct xpc_partition *part; - struct xpc_channel *ch; - int wakeup_channel_mgr; - - - /* now wait for all callouts to the caller's function to cease */ - for (partid = 1; partid < XP_MAX_PARTITIONS; partid++) { - part = &xpc_partitions[partid]; - - if (!xpc_part_ref(part)) { - continue; - } - - ch = &part->channels[ch_number]; - - if (!(ch->flags & XPC_C_WDISCONNECT)) { - xpc_part_deref(part); - continue; - } - - wait_for_completion(&ch->wdisconnect_wait); - - spin_lock_irqsave(&ch->lock, irq_flags); - DBUG_ON(!(ch->flags & XPC_C_DISCONNECTED)); - wakeup_channel_mgr = 0; - - if (ch->delayed_IPI_flags) { - if (part->act_state != XPC_P_DEACTIVATING) { - spin_lock(&part->IPI_lock); - XPC_SET_IPI_FLAGS(part->local_IPI_amo, - ch->number, ch->delayed_IPI_flags); - spin_unlock(&part->IPI_lock); - wakeup_channel_mgr = 1; - } - ch->delayed_IPI_flags = 0; - } - - ch->flags &= ~XPC_C_WDISCONNECT; - spin_unlock_irqrestore(&ch->lock, irq_flags); - - if (wakeup_channel_mgr) { - xpc_wakeup_channel_mgr(part); - } - - xpc_part_deref(part); - } -} - - -static void -xpc_do_exit(enum xpc_retval reason) -{ - partid_t partid; - int active_part_count, printed_waiting_msg = 0; - struct xpc_partition *part; - unsigned long printmsg_time, disengage_request_timeout = 0; - - - /* a 'rmmod XPC' and a 'reboot' cannot both end up here together */ - DBUG_ON(xpc_exiting == 1); - - /* - * Let the heartbeat checker thread and the discovery thread - * (if one is running) know that they should exit. Also wake up - * the heartbeat checker thread in case it's sleeping. - */ - xpc_exiting = 1; - wake_up_interruptible(&xpc_act_IRQ_wq); - - /* ignore all incoming interrupts */ - free_irq(SGI_XPC_ACTIVATE, NULL); - - /* wait for the discovery thread to exit */ - wait_for_completion(&xpc_discovery_exited); - - /* wait for the heartbeat checker thread to exit */ - wait_for_completion(&xpc_hb_checker_exited); - - - /* sleep for a 1/3 of a second or so */ - (void) msleep_interruptible(300); - - - /* wait for all partitions to become inactive */ - - printmsg_time = jiffies + (XPC_DISENGAGE_PRINTMSG_INTERVAL * HZ); - xpc_disengage_request_timedout = 0; - - do { - active_part_count = 0; - - for (partid = 1; partid < XP_MAX_PARTITIONS; partid++) { - part = &xpc_partitions[partid]; - - if (xpc_partition_disengaged(part) && - part->act_state == XPC_P_INACTIVE) { - continue; - } - - active_part_count++; - - XPC_DEACTIVATE_PARTITION(part, reason); - - if (part->disengage_request_timeout > - disengage_request_timeout) { - disengage_request_timeout = - part->disengage_request_timeout; - } - } - - if (xpc_partition_engaged(-1UL)) { - if (time_after(jiffies, printmsg_time)) { - dev_info(xpc_part, "waiting for remote " - "partitions to disengage, timeout in " - "%ld seconds\n", - (disengage_request_timeout - jiffies) - / HZ); - printmsg_time = jiffies + - (XPC_DISENGAGE_PRINTMSG_INTERVAL * HZ); - printed_waiting_msg = 1; - } - - } else if (active_part_count > 0) { - if (printed_waiting_msg) { - dev_info(xpc_part, "waiting for local partition" - " to disengage\n"); - printed_waiting_msg = 0; - } - - } else { - if (!xpc_disengage_request_timedout) { - dev_info(xpc_part, "all partitions have " - "disengaged\n"); - } - break; - } - - /* sleep for a 1/3 of a second or so */ - (void) msleep_interruptible(300); - - } while (1); - - DBUG_ON(xpc_partition_engaged(-1UL)); - - - /* indicate to others that our reserved page is uninitialized */ - xpc_rsvd_page->vars_pa = 0; - - /* now it's time to eliminate our heartbeat */ - del_timer_sync(&xpc_hb_timer); - DBUG_ON(xpc_vars->heartbeating_to_mask != 0); - - if (reason == xpcUnloading) { - /* take ourselves off of the reboot_notifier_list */ - (void) unregister_reboot_notifier(&xpc_reboot_notifier); - - /* take ourselves off of the die_notifier list */ - (void) unregister_die_notifier(&xpc_die_notifier); - } - - /* close down protections for IPI operations */ - xpc_restrict_IPI_ops(); - - - /* clear the interface to XPC's functions */ - xpc_clear_interface(); - - if (xpc_sysctl) { - unregister_sysctl_table(xpc_sysctl); - } - - kfree(xpc_remote_copy_buffer_base); -} - - -/* - * This function is called when the system is being rebooted. - */ -static int -xpc_system_reboot(struct notifier_block *nb, unsigned long event, void *unused) -{ - enum xpc_retval reason; - - - switch (event) { - case SYS_RESTART: - reason = xpcSystemReboot; - break; - case SYS_HALT: - reason = xpcSystemHalt; - break; - case SYS_POWER_OFF: - reason = xpcSystemPoweroff; - break; - default: - reason = xpcSystemGoingDown; - } - - xpc_do_exit(reason); - return NOTIFY_DONE; -} - - -/* - * Notify other partitions to disengage from all references to our memory. - */ -static void -xpc_die_disengage(void) -{ - struct xpc_partition *part; - partid_t partid; - unsigned long engaged; - long time, printmsg_time, disengage_request_timeout; - - - /* keep xpc_hb_checker thread from doing anything (just in case) */ - xpc_exiting = 1; - - xpc_vars->heartbeating_to_mask = 0; /* indicate we're deactivated */ - - for (partid = 1; partid < XP_MAX_PARTITIONS; partid++) { - part = &xpc_partitions[partid]; - - if (!XPC_SUPPORTS_DISENGAGE_REQUEST(part-> - remote_vars_version)) { - - /* just in case it was left set by an earlier XPC */ - xpc_clear_partition_engaged(1UL << partid); - continue; - } - - if (xpc_partition_engaged(1UL << partid) || - part->act_state != XPC_P_INACTIVE) { - xpc_request_partition_disengage(part); - xpc_mark_partition_disengaged(part); - xpc_IPI_send_disengage(part); - } - } - - time = rtc_time(); - printmsg_time = time + - (XPC_DISENGAGE_PRINTMSG_INTERVAL * sn_rtc_cycles_per_second); - disengage_request_timeout = time + - (xpc_disengage_request_timelimit * sn_rtc_cycles_per_second); - - /* wait for all other partitions to disengage from us */ - - while (1) { - engaged = xpc_partition_engaged(-1UL); - if (!engaged) { - dev_info(xpc_part, "all partitions have disengaged\n"); - break; - } - - time = rtc_time(); - if (time >= disengage_request_timeout) { - for (partid = 1; partid < XP_MAX_PARTITIONS; partid++) { - if (engaged & (1UL << partid)) { - dev_info(xpc_part, "disengage from " - "remote partition %d timed " - "out\n", partid); - } - } - break; - } - - if (time >= printmsg_time) { - dev_info(xpc_part, "waiting for remote partitions to " - "disengage, timeout in %ld seconds\n", - (disengage_request_timeout - time) / - sn_rtc_cycles_per_second); - printmsg_time = time + - (XPC_DISENGAGE_PRINTMSG_INTERVAL * - sn_rtc_cycles_per_second); - } - } -} - - -/* - * This function is called when the system is being restarted or halted due - * to some sort of system failure. If this is the case we need to notify the - * other partitions to disengage from all references to our memory. - * This function can also be called when our heartbeater could be offlined - * for a time. In this case we need to notify other partitions to not worry - * about the lack of a heartbeat. - */ -static int -xpc_system_die(struct notifier_block *nb, unsigned long event, void *unused) -{ - switch (event) { - case DIE_MACHINE_RESTART: - case DIE_MACHINE_HALT: - xpc_die_disengage(); - break; - - case DIE_KDEBUG_ENTER: - /* Should lack of heartbeat be ignored by other partitions? */ - if (!xpc_kdebug_ignore) { - break; - } - /* fall through */ - case DIE_MCA_MONARCH_ENTER: - case DIE_INIT_MONARCH_ENTER: - xpc_vars->heartbeat++; - xpc_vars->heartbeat_offline = 1; - break; - - case DIE_KDEBUG_LEAVE: - /* Is lack of heartbeat being ignored by other partitions? */ - if (!xpc_kdebug_ignore) { - break; - } - /* fall through */ - case DIE_MCA_MONARCH_LEAVE: - case DIE_INIT_MONARCH_LEAVE: - xpc_vars->heartbeat++; - xpc_vars->heartbeat_offline = 0; - break; - } - - return NOTIFY_DONE; -} - - -int __init -xpc_init(void) -{ - int ret; - partid_t partid; - struct xpc_partition *part; - pid_t pid; - size_t buf_size; - - - if (!ia64_platform_is("sn2")) { - return -ENODEV; - } - - - 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"); - - xpc_sysctl = register_sysctl_table(xpc_sys_dir); - - /* - * The first few fields of each entry of xpc_partitions[] need to - * be initialized now so that calls to xpc_connect() and - * xpc_disconnect() can be made prior to the activation of any remote - * partition. NOTE THAT NONE OF THE OTHER FIELDS BELONGING TO THESE - * ENTRIES ARE MEANINGFUL UNTIL AFTER AN ENTRY'S CORRESPONDING - * PARTITION HAS BEEN ACTIVATED. - */ - for (partid = 1; partid < XP_MAX_PARTITIONS; partid++) { - part = &xpc_partitions[partid]; - - DBUG_ON((u64) part != L1_CACHE_ALIGN((u64) part)); - - part->act_IRQ_rcvd = 0; - spin_lock_init(&part->act_lock); - part->act_state = XPC_P_INACTIVE; - XPC_SET_REASON(part, 0, 0); - - init_timer(&part->disengage_request_timer); - part->disengage_request_timer.function = - xpc_timeout_partition_disengage_request; - part->disengage_request_timer.data = (unsigned long) part; - - part->setup_state = XPC_P_UNSET; - init_waitqueue_head(&part->teardown_wq); - atomic_set(&part->references, 0); - } - - /* - * Open up protections for IPI operations (and AMO operations on - * Shub 1.1 systems). - */ - xpc_allow_IPI_ops(); - - /* - * Interrupts being processed will increment this atomic variable and - * awaken the heartbeat thread which will process the interrupts. - */ - atomic_set(&xpc_act_IRQ_rcvd, 0); - - /* - * This is safe to do before the xpc_hb_checker thread has started - * because the handler releases a wait queue. If an interrupt is - * received before the thread is waiting, it will not go to sleep, - * but rather immediately process the interrupt. - */ - ret = request_irq(SGI_XPC_ACTIVATE, xpc_act_IRQ_handler, 0, - "xpc hb", NULL); - if (ret != 0) { - dev_err(xpc_part, "can't register ACTIVATE IRQ handler, " - "errno=%d\n", -ret); - - xpc_restrict_IPI_ops(); - - if (xpc_sysctl) { - unregister_sysctl_table(xpc_sysctl); - } - - kfree(xpc_remote_copy_buffer_base); - return -EBUSY; - } - - /* - * Fill the partition reserved page with the information needed by - * other partitions to discover we are alive and establish initial - * communications. - */ - xpc_rsvd_page = xpc_rsvd_page_init(); - if (xpc_rsvd_page == NULL) { - dev_err(xpc_part, "could not setup our reserved page\n"); - - free_irq(SGI_XPC_ACTIVATE, NULL); - xpc_restrict_IPI_ops(); - - if (xpc_sysctl) { - unregister_sysctl_table(xpc_sysctl); - } - - kfree(xpc_remote_copy_buffer_base); - return -EBUSY; - } - - - /* add ourselves to the reboot_notifier_list */ - ret = register_reboot_notifier(&xpc_reboot_notifier); - if (ret != 0) { - dev_warn(xpc_part, "can't register reboot notifier\n"); - } - - /* add ourselves to the die_notifier list */ - ret = register_die_notifier(&xpc_die_notifier); - if (ret != 0) { - dev_warn(xpc_part, "can't register die notifier\n"); - } - - init_timer(&xpc_hb_timer); - xpc_hb_timer.function = xpc_hb_beater; - - /* - * The real work-horse behind xpc. This processes incoming - * interrupts and monitors remote heartbeats. - */ - pid = kernel_thread(xpc_hb_checker, NULL, 0); - if (pid < 0) { - dev_err(xpc_part, "failed while forking hb check thread\n"); - - /* indicate to others that our reserved page is uninitialized */ - xpc_rsvd_page->vars_pa = 0; - - /* take ourselves off of the reboot_notifier_list */ - (void) unregister_reboot_notifier(&xpc_reboot_notifier); - - /* take ourselves off of the die_notifier list */ - (void) unregister_die_notifier(&xpc_die_notifier); - - del_timer_sync(&xpc_hb_timer); - free_irq(SGI_XPC_ACTIVATE, NULL); - xpc_restrict_IPI_ops(); - - if (xpc_sysctl) { - unregister_sysctl_table(xpc_sysctl); - } - - kfree(xpc_remote_copy_buffer_base); - return -EBUSY; - } - - - /* - * Startup a thread that will attempt to discover other partitions to - * activate based on info provided by SAL. This new thread is short - * lived and will exit once discovery is complete. - */ - pid = kernel_thread(xpc_initiate_discovery, NULL, 0); - if (pid < 0) { - dev_err(xpc_part, "failed while forking discovery thread\n"); - - /* mark this new thread as a non-starter */ - complete(&xpc_discovery_exited); - - xpc_do_exit(xpcUnloading); - return -EBUSY; - } - - - /* set the interface to point at XPC's functions */ - xpc_set_interface(xpc_initiate_connect, xpc_initiate_disconnect, - xpc_initiate_allocate, xpc_initiate_send, - xpc_initiate_send_notify, xpc_initiate_received, - xpc_initiate_partid_to_nasids); - - return 0; -} -module_init(xpc_init); - - -void __exit -xpc_exit(void) -{ - xpc_do_exit(xpcUnloading); -} -module_exit(xpc_exit); - - -MODULE_AUTHOR("Silicon Graphics, Inc."); -MODULE_DESCRIPTION("Cross Partition Communication (XPC) support"); -MODULE_LICENSE("GPL"); - -module_param(xpc_hb_interval, int, 0); -MODULE_PARM_DESC(xpc_hb_interval, "Number of seconds between " - "heartbeat increments."); - -module_param(xpc_hb_check_interval, int, 0); -MODULE_PARM_DESC(xpc_hb_check_interval, "Number of seconds between " - "heartbeat checks."); - -module_param(xpc_disengage_request_timelimit, int, 0); -MODULE_PARM_DESC(xpc_disengage_request_timelimit, "Number of seconds to wait " - "for disengage request to complete."); - -module_param(xpc_kdebug_ignore, int, 0); -MODULE_PARM_DESC(xpc_kdebug_ignore, "Should lack of heartbeat be ignored by " - "other partitions when dropping into kdebug."); - diff --git a/arch/ia64/sn/kernel/xpc_partition.c b/arch/ia64/sn/kernel/xpc_partition.c deleted file mode 100644 index 9e97c268483..00000000000 --- a/arch/ia64/sn/kernel/xpc_partition.c +++ /dev/null @@ -1,1239 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (c) 2004-2006 Silicon Graphics, Inc. All Rights Reserved. - */ - - -/* - * Cross Partition Communication (XPC) partition support. - * - * This is the part of XPC that detects the presence/absence of - * other partitions. It provides a heartbeat and monitors the - * heartbeats of other partitions. - * - */ - - -#include <linux/kernel.h> -#include <linux/sysctl.h> -#include <linux/cache.h> -#include <linux/mmzone.h> -#include <linux/nodemask.h> -#include <asm/uncached.h> -#include <asm/sn/bte.h> -#include <asm/sn/intr.h> -#include <asm/sn/sn_sal.h> -#include <asm/sn/nodepda.h> -#include <asm/sn/addrs.h> -#include <asm/sn/xpc.h> - - -/* XPC is exiting flag */ -int xpc_exiting; - - -/* SH_IPI_ACCESS shub register value on startup */ -static u64 xpc_sh1_IPI_access; -static u64 xpc_sh2_IPI_access0; -static u64 xpc_sh2_IPI_access1; -static u64 xpc_sh2_IPI_access2; -static u64 xpc_sh2_IPI_access3; - - -/* original protection values for each node */ -u64 xpc_prot_vec[MAX_NUMNODES]; - - -/* this partition's reserved page pointers */ -struct xpc_rsvd_page *xpc_rsvd_page; -static u64 *xpc_part_nasids; -static u64 *xpc_mach_nasids; -struct xpc_vars *xpc_vars; -struct xpc_vars_part *xpc_vars_part; - -static int xp_nasid_mask_bytes; /* actual size in bytes of nasid mask */ -static int xp_nasid_mask_words; /* actual size in words of nasid mask */ - - -/* - * For performance reasons, each entry of xpc_partitions[] is cacheline - * aligned. And xpc_partitions[] is padded with an additional entry at the - * end so that the last legitimate entry doesn't share its cacheline with - * another variable. - */ -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). - */ -char *xpc_remote_copy_buffer; -void *xpc_remote_copy_buffer_base; - - -/* - * Guarantee that the kmalloc'd memory is cacheline aligned. - */ -void * -xpc_kmalloc_cacheline_aligned(size_t size, gfp_t flags, void **base) -{ - /* see if kmalloc will give us cachline aligned memory by default */ - *base = kmalloc(size, flags); - if (*base == NULL) { - return NULL; - } - if ((u64) *base == L1_CACHE_ALIGN((u64) *base)) { - return *base; - } - kfree(*base); - - /* nope, we'll have to do it ourselves */ - *base = kmalloc(size + L1_CACHE_BYTES, flags); - if (*base == NULL) { - return NULL; - } - return (void *) L1_CACHE_ALIGN((u64) *base); -} - - -/* - * Given a nasid, get the physical address of the partition's reserved page - * for that nasid. This function returns 0 on any error. - */ -static u64 -xpc_get_rsvd_page_pa(int nasid) -{ - bte_result_t bte_res; - s64 status; - u64 cookie = 0; - u64 rp_pa = nasid; /* seed with nasid */ - u64 len = 0; - u64 buf = buf; - u64 buf_len = 0; - void *buf_base = NULL; - - - while (1) { - - status = sn_partition_reserved_page_pa(buf, &cookie, &rp_pa, - &len); - - dev_dbg(xpc_part, "SAL returned with status=%li, cookie=" - "0x%016lx, address=0x%016lx, len=0x%016lx\n", - status, cookie, rp_pa, len); - - if (status != SALRET_MORE_PASSES) { - break; - } - - if (L1_CACHE_ALIGN(len) > buf_len) { - kfree(buf_base); - buf_len = L1_CACHE_ALIGN(len); - buf = (u64) xpc_kmalloc_cacheline_aligned(buf_len, - GFP_KERNEL, &buf_base); - if (buf_base == NULL) { - dev_err(xpc_part, "unable to kmalloc " - "len=0x%016lx\n", buf_len); - status = SALRET_ERROR; - break; - } - } - - 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); - status = SALRET_ERROR; - break; - } - } - - kfree(buf_base); - - if (status != SALRET_OK) { - rp_pa = 0; - } - dev_dbg(xpc_part, "reserved page at phys address 0x%016lx\n", rp_pa); - return rp_pa; -} - - -/* - * Fill the partition reserved page with the information needed by - * other partitions to discover we are alive and establish initial - * communications. - */ -struct xpc_rsvd_page * -xpc_rsvd_page_init(void) -{ - struct xpc_rsvd_page *rp; - AMO_t *amos_page; - u64 rp_pa, nasid_array = 0; - int i, ret; - - - /* get the local reserved page's address */ - - preempt_disable(); - rp_pa = xpc_get_rsvd_page_pa(cpuid_to_nasid(smp_processor_id())); - preempt_enable(); - if (rp_pa == 0) { - dev_err(xpc_part, "SAL failed to locate the reserved page\n"); - return NULL; - } - rp = (struct xpc_rsvd_page *) __va(rp_pa); - - if (rp->partid != sn_partition_id) { - dev_err(xpc_part, "the reserved page's partid of %d should be " - "%d\n", rp->partid, sn_partition_id); - return NULL; - } - - rp->version = XPC_RP_VERSION; - - /* establish the actual sizes of the nasid masks */ - if (rp->SAL_version == 1) { - /* SAL_version 1 didn't set the nasids_size field */ - rp->nasids_size = 128; - } - xp_nasid_mask_bytes = rp->nasids_size; - xp_nasid_mask_words = xp_nasid_mask_bytes / 8; - - /* setup the pointers to the various items in the reserved page */ - xpc_part_nasids = XPC_RP_PART_NASIDS(rp); - xpc_mach_nasids = XPC_RP_MACH_NASIDS(rp); - xpc_vars = XPC_RP_VARS(rp); - xpc_vars_part = XPC_RP_VARS_PART(rp); - - /* - * Before clearing xpc_vars, see if a page of AMOs had been previously - * allocated. If not we'll need to allocate one and set permissions - * so that cross-partition AMOs are allowed. - * - * The allocated AMO page needs MCA reporting to remain disabled after - * XPC has unloaded. To make this work, we keep a copy of the pointer - * to this page (i.e., amos_page) in the struct xpc_vars structure, - * which is pointed to by the reserved page, and re-use that saved copy - * on subsequent loads of XPC. This AMO page is never freed, and its - * memory protections are never restricted. - */ - if ((amos_page = xpc_vars->amos_page) == NULL) { - amos_page = (AMO_t *) TO_AMO(uncached_alloc_page(0)); - if (amos_page == NULL) { - dev_err(xpc_part, "can't allocate page of AMOs\n"); - return NULL; - } - - /* - * Open up AMO-R/W to cpu. This is done for Shub 1.1 systems - * when xpc_allow_IPI_ops() is called via xpc_hb_init(). - */ - if (!enable_shub_wars_1_1()) { - ret = sn_change_memprotect(ia64_tpa((u64) amos_page), - PAGE_SIZE, SN_MEMPROT_ACCESS_CLASS_1, - &nasid_array); - if (ret != 0) { - dev_err(xpc_part, "can't change memory " - "protections\n"); - uncached_free_page(__IA64_UNCACHED_OFFSET | - TO_PHYS((u64) amos_page)); - return NULL; - } - } - } else if (!IS_AMO_ADDRESS((u64) amos_page)) { - /* - * EFI's XPBOOT can also set amos_page in the reserved page, - * but it happens to leave it as an uncached physical address - * and we need it to be an uncached virtual, so we'll have to - * convert it. - */ - if (!IS_AMO_PHYS_ADDRESS((u64) amos_page)) { - dev_err(xpc_part, "previously used amos_page address " - "is bad = 0x%p\n", (void *) amos_page); - return NULL; - } - amos_page = (AMO_t *) TO_AMO((u64) amos_page); - } - - /* clear xpc_vars */ - memset(xpc_vars, 0, sizeof(struct xpc_vars)); - - xpc_vars->version = XPC_V_VERSION; - xpc_vars->act_nasid = cpuid_to_nasid(0); - xpc_vars->act_phys_cpuid = cpu_physical_id(0); - xpc_vars->vars_part_pa = __pa(xpc_vars_part); - xpc_vars->amos_page_pa = ia64_tpa((u64) amos_page); - xpc_vars->amos_page = amos_page; /* save for next load of XPC */ - - - /* clear xpc_vars_part */ - memset((u64 *) xpc_vars_part, 0, sizeof(struct xpc_vars_part) * - XP_MAX_PARTITIONS); - - /* initialize the activate IRQ related AMO variables */ - for (i = 0; i < xp_nasid_mask_words; i++) { - (void) xpc_IPI_init(XPC_ACTIVATE_IRQ_AMOS + i); - } - - /* initialize the engaged remote partitions related AMO variables */ - (void) xpc_IPI_init(XPC_ENGAGED_PARTITIONS_AMO); - (void) xpc_IPI_init(XPC_DISENGAGE_REQUEST_AMO); - - /* timestamp of when reserved page was setup by XPC */ - rp->stamp = CURRENT_TIME; - - /* - * This signifies to the remote partition that our reserved - * page is initialized. - */ - rp->vars_pa = __pa(xpc_vars); - - return rp; -} - - -/* - * Change protections to allow IPI operations (and AMO operations on - * Shub 1.1 systems). - */ -void -xpc_allow_IPI_ops(void) -{ - int node; - int nasid; - - - // >>> Change SH_IPI_ACCESS code to use SAL call once it is available. - - if (is_shub2()) { - xpc_sh2_IPI_access0 = - (u64) HUB_L((u64 *) LOCAL_MMR_ADDR(SH2_IPI_ACCESS0)); - xpc_sh2_IPI_access1 = - (u64) HUB_L((u64 *) LOCAL_MMR_ADDR(SH2_IPI_ACCESS1)); - xpc_sh2_IPI_access2 = - (u64) HUB_L((u64 *) LOCAL_MMR_ADDR(SH2_IPI_ACCESS2)); - xpc_sh2_IPI_access3 = - (u64) HUB_L((u64 *) LOCAL_MMR_ADDR(SH2_IPI_ACCESS3)); - - for_each_online_node(node) { - nasid = cnodeid_to_nasid(node); - HUB_S((u64 *) GLOBAL_MMR_ADDR(nasid, SH2_IPI_ACCESS0), - -1UL); - HUB_S((u64 *) GLOBAL_MMR_ADDR(nasid, SH2_IPI_ACCESS1), - -1UL); - HUB_S((u64 *) GLOBAL_MMR_ADDR(nasid, SH2_IPI_ACCESS2), - -1UL); - HUB_S((u64 *) GLOBAL_MMR_ADDR(nasid, SH2_IPI_ACCESS3), - -1UL); - } - - } else { - xpc_sh1_IPI_access = - (u64) HUB_L((u64 *) LOCAL_MMR_ADDR(SH1_IPI_ACCESS)); - - for_each_online_node(node) { - nasid = cnodeid_to_nasid(node); - HUB_S((u64 *) GLOBAL_MMR_ADDR(nasid, SH1_IPI_ACCESS), - -1UL); - - /* - * Since the BIST collides with memory operations on - * SHUB 1.1 sn_change_memprotect() cannot be used. - */ - if (enable_shub_wars_1_1()) { - /* open up everything */ - xpc_prot_vec[node] = (u64) HUB_L((u64 *) - GLOBAL_MMR_ADDR(nasid, - SH1_MD_DQLP_MMR_DIR_PRIVEC0)); - HUB_S((u64 *) GLOBAL_MMR_ADDR(nasid, - SH1_MD_DQLP_MMR_DIR_PRIVEC0), - -1UL); - HUB_S((u64 *) GLOBAL_MMR_ADDR(nasid, - SH1_MD_DQRP_MMR_DIR_PRIVEC0), - -1UL); - } - } - } -} - - -/* - * Restrict protections to disallow IPI operations (and AMO operations on - * Shub 1.1 systems). - */ -void -xpc_restrict_IPI_ops(void) -{ - int node; - int nasid; - - - // >>> Change SH_IPI_ACCESS code to use SAL call once it is available. - - if (is_shub2()) { - - for_each_online_node(node) { - nasid = cnodeid_to_nasid(node); - HUB_S((u64 *) GLOBAL_MMR_ADDR(nasid, SH2_IPI_ACCESS0), - xpc_sh2_IPI_access0); - HUB_S((u64 *) GLOBAL_MMR_ADDR(nasid, SH2_IPI_ACCESS1), - xpc_sh2_IPI_access1); - HUB_S((u64 *) GLOBAL_MMR_ADDR(nasid, SH2_IPI_ACCESS2), - xpc_sh2_IPI_access2); - HUB_S((u64 *) GLOBAL_MMR_ADDR(nasid, SH2_IPI_ACCESS3), - xpc_sh2_IPI_access3); - } - - } else { - - for_each_online_node(node) { - nasid = cnodeid_to_nasid(node); - HUB_S((u64 *) GLOBAL_MMR_ADDR(nasid, SH1_IPI_ACCESS), - xpc_sh1_IPI_access); - - if (enable_shub_wars_1_1()) { - HUB_S((u64 *) GLOBAL_MMR_ADDR(nasid, - SH1_MD_DQLP_MMR_DIR_PRIVEC0), - xpc_prot_vec[node]); - HUB_S((u64 *) GLOBAL_MMR_ADDR(nasid, - SH1_MD_DQRP_MMR_DIR_PRIVEC0), - xpc_prot_vec[node]); - } - } - } -} - - -/* - * At periodic intervals, scan through all active partitions and ensure - * their heartbeat is still active. If not, the partition is deactivated. - */ -void -xpc_check_remote_hb(void) -{ - struct xpc_vars *remote_vars; - struct xpc_partition *part; - partid_t partid; - bte_result_t bres; - - - remote_vars = (struct xpc_vars *) xpc_remote_copy_buffer; - - for (partid = 1; partid < XP_MAX_PARTITIONS; partid++) { - - if (xpc_exiting) { - break; - } - - if (partid == sn_partition_id) { - continue; - } - - part = &xpc_partitions[partid]; - - if (part->act_state == XPC_P_INACTIVE || - part->act_state == XPC_P_DEACTIVATING) { - continue; - } - - /* pull the remote_hb cache line */ - bres = xp_bte_copy(part->remote_vars_pa, - (u64) remote_vars, - XPC_RP_VARS_SIZE, - (BTE_NOTIFY | BTE_WACQUIRE), NULL); - if (bres != BTE_SUCCESS) { - XPC_DEACTIVATE_PARTITION(part, - xpc_map_bte_errors(bres)); - continue; - } - - dev_dbg(xpc_part, "partid = %d, heartbeat = %ld, last_heartbeat" - " = %ld, heartbeat_offline = %ld, HB_mask = 0x%lx\n", - partid, remote_vars->heartbeat, part->last_heartbeat, - remote_vars->heartbeat_offline, - remote_vars->heartbeating_to_mask); - - if (((remote_vars->heartbeat == part->last_heartbeat) && - (remote_vars->heartbeat_offline == 0)) || - !xpc_hb_allowed(sn_partition_id, remote_vars)) { - - XPC_DEACTIVATE_PARTITION(part, xpcNoHeartbeat); - continue; - } - - part->last_heartbeat = remote_vars->heartbeat; - } -} - - -/* - * Get a copy of a portion of the remote partition's rsvd page. - * - * remote_rp points to a buffer that is cacheline aligned for BTE copies and - * is large enough to contain a copy of their reserved page header and - * part_nasids mask. - */ -static enum xpc_retval -xpc_get_remote_rp(int nasid, u64 *discovered_nasids, - struct xpc_rsvd_page *remote_rp, u64 *remote_rp_pa) -{ - int bres, i; - - - /* get the reserved page's physical address */ - - *remote_rp_pa = xpc_get_rsvd_page_pa(nasid); - if (*remote_rp_pa == 0) { - return xpcNoRsvdPageAddr; - } - - - /* pull over the reserved page header and part_nasids mask */ - 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) { - return xpc_map_bte_errors(bres); - } - - - if (discovered_nasids != NULL) { - u64 *remote_part_nasids = XPC_RP_PART_NASIDS(remote_rp); - - - for (i = 0; i < xp_nasid_mask_words; i++) { - discovered_nasids[i] |= remote_part_nasids[i]; - } - } - - - /* check that the partid is for another partition */ - - if (remote_rp->partid < 1 || - remote_rp->partid > (XP_MAX_PARTITIONS - 1)) { - return xpcInvalidPartid; - } - - if (remote_rp->partid == sn_partition_id) { - return xpcLocalPartid; - } - - - if (XPC_VERSION_MAJOR(remote_rp->version) != - XPC_VERSION_MAJOR(XPC_RP_VERSION)) { - return xpcBadVersion; - } - - return xpcSuccess; -} - - -/* - * Get a copy of the remote partition's XPC variables from the reserved page. - * - * remote_vars points to a buffer that is cacheline aligned for BTE copies and - * assumed to be of size XPC_RP_VARS_SIZE. - */ -static enum xpc_retval -xpc_get_remote_vars(u64 remote_vars_pa, struct xpc_vars *remote_vars) -{ - int bres; - - - if (remote_vars_pa == 0) { - return xpcVarsNotSet; - } - - /* pull over the cross partition variables */ - 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); - } - - if (XPC_VERSION_MAJOR(remote_vars->version) != - XPC_VERSION_MAJOR(XPC_V_VERSION)) { - return xpcBadVersion; - } - - return xpcSuccess; -} - - -/* - * Update the remote partition's info. - */ -static void -xpc_update_partition_info(struct xpc_partition *part, u8 remote_rp_version, - struct timespec *remote_rp_stamp, u64 remote_rp_pa, - u64 remote_vars_pa, struct xpc_vars *remote_vars) -{ - part->remote_rp_version = remote_rp_version; - dev_dbg(xpc_part, " remote_rp_version = 0x%016x\n", - part->remote_rp_version); - - part->remote_rp_stamp = *remote_rp_stamp; - dev_dbg(xpc_part, " remote_rp_stamp (tv_sec = 0x%lx tv_nsec = 0x%lx\n", - part->remote_rp_stamp.tv_sec, part->remote_rp_stamp.tv_nsec); - - part->remote_rp_pa = remote_rp_pa; - dev_dbg(xpc_part, " remote_rp_pa = 0x%016lx\n", part->remote_rp_pa); - - part->remote_vars_pa = remote_vars_pa; - dev_dbg(xpc_part, " remote_vars_pa = 0x%016lx\n", - part->remote_vars_pa); - - part->last_heartbeat = remote_vars->heartbeat; - dev_dbg(xpc_part, " last_heartbeat = 0x%016lx\n", - part->last_heartbeat); - - part->remote_vars_part_pa = remote_vars->vars_part_pa; - dev_dbg(xpc_part, " remote_vars_part_pa = 0x%016lx\n", - part->remote_vars_part_pa); - - part->remote_act_nasid = remote_vars->act_nasid; - dev_dbg(xpc_part, " remote_act_nasid = 0x%x\n", - part->remote_act_nasid); - - part->remote_act_phys_cpuid = remote_vars->act_phys_cpuid; - dev_dbg(xpc_part, " remote_act_phys_cpuid = 0x%x\n", - part->remote_act_phys_cpuid); - - part->remote_amos_page_pa = remote_vars->amos_page_pa; - dev_dbg(xpc_part, " remote_amos_page_pa = 0x%lx\n", - part->remote_amos_page_pa); - - part->remote_vars_version = remote_vars->version; - dev_dbg(xpc_part, " remote_vars_version = 0x%x\n", - part->remote_vars_version); -} - - -/* - * Prior code has determined the nasid which generated an IPI. Inspect - * that nasid to determine if its partition needs to be activated or - * deactivated. - * - * A partition is consider "awaiting activation" if our partition - * flags indicate it is not active and it has a heartbeat. A - * partition is considered "awaiting deactivation" if our partition - * flags indicate it is active but it has no heartbeat or it is not - * sending its heartbeat to us. - * - * To determine the heartbeat, the remote nasid must have a properly - * initialized reserved page. - */ -static void -xpc_identify_act_IRQ_req(int nasid) -{ - struct xpc_rsvd_page *remote_rp; - struct xpc_vars *remote_vars; - u64 remote_rp_pa; - u64 remote_vars_pa; - int remote_rp_version; - int reactivate = 0; - int stamp_diff; - struct timespec remote_rp_stamp = { 0, 0 }; - partid_t partid; - struct xpc_partition *part; - enum xpc_retval ret; - - - /* pull over the reserved page structure */ - - remote_rp = (struct xpc_rsvd_page *) xpc_remote_copy_buffer; - - ret = xpc_get_remote_rp(nasid, NULL, remote_rp, &remote_rp_pa); - if (ret != xpcSuccess) { - dev_warn(xpc_part, "unable to get reserved page from nasid %d, " - "which sent interrupt, reason=%d\n", nasid, ret); - return; - } - - remote_vars_pa = remote_rp->vars_pa; - remote_rp_version = remote_rp->version; - if (XPC_SUPPORTS_RP_STAMP(remote_rp_version)) { - remote_rp_stamp = remote_rp->stamp; - } - partid = remote_rp->partid; - part = &xpc_partitions[partid]; - - - /* pull over the cross partition variables */ - - remote_vars = (struct xpc_vars *) xpc_remote_copy_buffer; - - ret = xpc_get_remote_vars(remote_vars_pa, remote_vars); - if (ret != xpcSuccess) { - - dev_warn(xpc_part, "unable to get XPC variables from nasid %d, " - "which sent interrupt, reason=%d\n", nasid, ret); - - XPC_DEACTIVATE_PARTITION(part, ret); - return; - } - - - part->act_IRQ_rcvd++; - - dev_dbg(xpc_part, "partid for nasid %d is %d; IRQs = %d; HB = " - "%ld:0x%lx\n", (int) nasid, (int) partid, part->act_IRQ_rcvd, - remote_vars->heartbeat, remote_vars->heartbeating_to_mask); - - if (xpc_partition_disengaged(part) && - part->act_state == XPC_P_INACTIVE) { - - xpc_update_partition_info(part, remote_rp_version, - &remote_rp_stamp, remote_rp_pa, - remote_vars_pa, remote_vars); - - if (XPC_SUPPORTS_DISENGAGE_REQUEST(part->remote_vars_version)) { - if (xpc_partition_disengage_requested(1UL << partid)) { - /* - * Other side is waiting on us to disengage, - * even though we already have. - */ - return; - } - } else { - /* other side doesn't support disengage requests */ - xpc_clear_partition_disengage_request(1UL << partid); - } - - xpc_activate_partition(part); - return; - } - - DBUG_ON(part->remote_rp_version == 0); - DBUG_ON(part->remote_vars_version == 0); - - if (!XPC_SUPPORTS_RP_STAMP(part->remote_rp_version)) { - DBUG_ON(XPC_SUPPORTS_DISENGAGE_REQUEST(part-> - remote_vars_version)); - - if (!XPC_SUPPORTS_RP_STAMP(remote_rp_version)) { - DBUG_ON(XPC_SUPPORTS_DISENGAGE_REQUEST(remote_vars-> - version)); - /* see if the other side rebooted */ - if (part->remote_amos_page_pa == - remote_vars->amos_page_pa && - xpc_hb_allowed(sn_partition_id, - remote_vars)) { - /* doesn't look that way, so ignore the IPI */ - return; - } - } - - /* - * Other side rebooted and previous XPC didn't support the - * disengage request, so we don't need to do anything special. - */ - - xpc_update_partition_info(part, remote_rp_version, - &remote_rp_stamp, remote_rp_pa, - remote_vars_pa, remote_vars); - part->reactivate_nasid = nasid; - XPC_DEACTIVATE_PARTITION(part, xpcReactivating); - return; - } - - DBUG_ON(!XPC_SUPPORTS_DISENGAGE_REQUEST(part->remote_vars_version)); - - if (!XPC_SUPPORTS_RP_STAMP(remote_rp_version)) { - DBUG_ON(!XPC_SUPPORTS_DISENGAGE_REQUEST(remote_vars->version)); - - /* - * Other side rebooted and previous XPC did support the - * disengage request, but the new one doesn't. - */ - - xpc_clear_partition_engaged(1UL << partid); - xpc_clear_partition_disengage_request(1UL << partid); - - xpc_update_partition_info(part, remote_rp_version, - &remote_rp_stamp, remote_rp_pa, - remote_vars_pa, remote_vars); - reactivate = 1; - - } else { - DBUG_ON(!XPC_SUPPORTS_DISENGAGE_REQUEST(remote_vars->version)); - - stamp_diff = xpc_compare_stamps(&part->remote_rp_stamp, - &remote_rp_stamp); - if (stamp_diff != 0) { - DBUG_ON(stamp_diff >= 0); - - /* - * Other side rebooted and the previous XPC did support - * the disengage request, as does the new one. - */ - - DBUG_ON(xpc_partition_engaged(1UL << partid)); - DBUG_ON(xpc_partition_disengage_requested(1UL << - partid)); - - xpc_update_partition_info(part, remote_rp_version, - &remote_rp_stamp, remote_rp_pa, - remote_vars_pa, remote_vars); - reactivate = 1; - } - } - - if (part->disengage_request_timeout > 0 && - !xpc_partition_disengaged(part)) { - /* still waiting on other side to disengage from us */ - return; - } - - if (reactivate) { - part->reactivate_nasid = nasid; - XPC_DEACTIVATE_PARTITION(part, xpcReactivating); - - } else if (XPC_SUPPORTS_DISENGAGE_REQUEST(part->remote_vars_version) && - xpc_partition_disengage_requested(1UL << partid)) { - XPC_DEACTIVATE_PARTITION(part, xpcOtherGoingDown); - } -} - - -/* - * Loop through the activation AMO variables and process any bits - * which are set. Each bit indicates a nasid sending a partition - * activation or deactivation request. - * - * Return #of IRQs detected. - */ -int -xpc_identify_act_IRQ_sender(void) -{ - int word, bit; - u64 nasid_mask; - u64 nasid; /* remote nasid */ - int n_IRQs_detected = 0; - AMO_t *act_amos; - - - act_amos = xpc_vars->amos_page + XPC_ACTIVATE_IRQ_AMOS; - - - /* scan through act AMO variable looking for non-zero entries */ - for (word = 0; word < xp_nasid_mask_words; word++) { - - if (xpc_exiting) { - break; - } - - nasid_mask = xpc_IPI_receive(&act_amos[word]); - if (nasid_mask == 0) { - /* no IRQs from nasids in this variable */ - continue; - } - - dev_dbg(xpc_part, "AMO[%d] gave back 0x%lx\n", word, - nasid_mask); - - - /* - * If this nasid has been added to the machine since - * our partition was reset, this will retain the - * remote nasid in our reserved pages machine mask. - * This is used in the event of module reload. - */ - xpc_mach_nasids[word] |= nasid_mask; - - - /* locate the nasid(s) which sent interrupts */ - - for (bit = 0; bit < (8 * sizeof(u64)); bit++) { - if (nasid_mask & (1UL << bit)) { - n_IRQs_detected++; - nasid = XPC_NASID_FROM_W_B(word, bit); - dev_dbg(xpc_part, "interrupt from nasid %ld\n", - nasid); - xpc_identify_act_IRQ_req(nasid); - } - } - } - return n_IRQs_detected; -} - - -/* - * See if the other side has responded to a partition disengage request - * from us. - */ -int -xpc_partition_disengaged(struct xpc_partition *part) -{ - partid_t partid = XPC_PARTID(part); - int disengaged; - - - disengaged = (xpc_partition_engaged(1UL << partid) == 0); - if (part->disengage_request_timeout) { - if (!disengaged) { - if (time_before(jiffies, part->disengage_request_timeout)) { - /* timelimit hasn't been reached yet */ - return 0; - } - - /* - * Other side hasn't responded to our disengage - * request in a timely fashion, so assume it's dead. - */ - - dev_info(xpc_part, "disengage from remote partition %d " - "timed out\n", partid); - xpc_disengage_request_timedout = 1; - xpc_clear_partition_engaged(1UL << partid); - disengaged = 1; - } - part->disengage_request_timeout = 0; - - /* cancel the timer function, provided it's not us */ - if (!in_interrupt()) { - del_singleshot_timer_sync(&part-> - disengage_request_timer); - } - - DBUG_ON(part->act_state != XPC_P_DEACTIVATING && - part->act_state != XPC_P_INACTIVE); - if (part->act_state != XPC_P_INACTIVE) { - xpc_wakeup_channel_mgr(part); - } - - if (XPC_SUPPORTS_DISENGAGE_REQUEST(part->remote_vars_version)) { - xpc_cancel_partition_disengage_request(part); - } - } - return disengaged; -} - - -/* - * Mark specified partition as active. - */ -enum xpc_retval -xpc_mark_partition_active(struct xpc_partition *part) -{ - unsigned long irq_flags; - enum xpc_retval ret; - - - dev_dbg(xpc_part, "setting partition %d to ACTIVE\n", XPC_PARTID(part)); - - spin_lock_irqsave(&part->act_lock, irq_flags); - if (part->act_state == XPC_P_ACTIVATING) { - part->act_state = XPC_P_ACTIVE; - ret = xpcSuccess; - } else { - DBUG_ON(part->reason == xpcSuccess); - ret = part->reason; - } - spin_unlock_irqrestore(&part->act_lock, irq_flags); - - return ret; -} - - -/* - * Notify XPC that the partition is down. - */ -void -xpc_deactivate_partition(const int line, struct xpc_partition *part, - enum xpc_retval reason) -{ - unsigned long irq_flags; - - - spin_lock_irqsave(&part->act_lock, irq_flags); - - if (part->act_state == XPC_P_INACTIVE) { - XPC_SET_REASON(part, reason, line); - spin_unlock_irqrestore(&part->act_lock, irq_flags); - if (reason == xpcReactivating) { - /* we interrupt ourselves to reactivate partition */ - xpc_IPI_send_reactivate(part); - } - return; - } - if (part->act_state == XPC_P_DEACTIVATING) { - if ((part->reason == xpcUnloading && reason != xpcUnloading) || - reason == xpcReactivating) { - XPC_SET_REASON(part, reason, line); - } - spin_unlock_irqrestore(&part->act_lock, irq_flags); - return; - } - - part->act_state = XPC_P_DEACTIVATING; - XPC_SET_REASON(part, reason, line); - - spin_unlock_irqrestore(&part->act_lock, irq_flags); - - if (XPC_SUPPORTS_DISENGAGE_REQUEST(part->remote_vars_version)) { - xpc_request_partition_disengage(part); - xpc_IPI_send_disengage(part); - - /* set a timelimit on the disengage request */ - part->disengage_request_timeout = jiffies + - (xpc_disengage_request_timelimit * HZ); - part->disengage_request_timer.expires = - part->disengage_request_timeout; - add_timer(&part->disengage_request_timer); - } - - dev_dbg(xpc_part, "bringing partition %d down, reason = %d\n", - XPC_PARTID(part), reason); - - xpc_partition_going_down(part, reason); -} - - -/* - * Mark specified partition as inactive. - */ -void -xpc_mark_partition_inactive(struct xpc_partition *part) -{ - unsigned long irq_flags; - - - dev_dbg(xpc_part, "setting partition %d to INACTIVE\n", - XPC_PARTID(part)); - - spin_lock_irqsave(&part->act_lock, irq_flags); - part->act_state = XPC_P_INACTIVE; - spin_unlock_irqrestore(&part->act_lock, irq_flags); - part->remote_rp_pa = 0; -} - - -/* - * SAL has provided a partition and machine mask. The partition mask - * contains a bit for each even nasid in our partition. The machine - * mask contains a bit for each even nasid in the entire machine. - * - * Using those two bit arrays, we can determine which nasids are - * known in the machine. Each should also have a reserved page - * initialized if they are available for partitioning. - */ -void -xpc_discovery(void) -{ - void *remote_rp_base; - struct xpc_rsvd_page *remote_rp; - struct xpc_vars *remote_vars; - u64 remote_rp_pa; - u64 remote_vars_pa; - int region; - int region_size; - int max_regions; - int nasid; - struct xpc_rsvd_page *rp; - partid_t partid; - struct xpc_partition *part; - u64 *discovered_nasids; - enum xpc_retval ret; - - - remote_rp = xpc_kmalloc_cacheline_aligned(XPC_RP_HEADER_SIZE + - xp_nasid_mask_bytes, - GFP_KERNEL, &remote_rp_base); - if (remote_rp == NULL) { - return; - } - remote_vars = (struct xpc_vars *) remote_rp; - - - discovered_nasids = kzalloc(sizeof(u64) * xp_nasid_mask_words, - GFP_KERNEL); - if (discovered_nasids == NULL) { - kfree(remote_rp_base); - return; - } - - rp = (struct xpc_rsvd_page *) xpc_rsvd_page; - - /* - * The term 'region' in this context refers to the minimum number of - * nodes that can comprise an access protection grouping. The access - * protection is in regards to memory, IOI and IPI. - */ - max_regions = 64; - region_size = sn_region_size; - - switch (region_size) { - case 128: - max_regions *= 2; - case 64: - max_regions *= 2; - case 32: - max_regions *= 2; - region_size = 16; - DBUG_ON(!is_shub2()); - } - - for (region = 0; region < max_regions; region++) { - - if ((volatile int) xpc_exiting) { - break; - } - - dev_dbg(xpc_part, "searching region %d\n", region); - - for (nasid = (region * region_size * 2); - nasid < ((region + 1) * region_size * 2); - nasid += 2) { - - if ((volatile int) xpc_exiting) { - break; - } - - dev_dbg(xpc_part, "checking nasid %d\n", nasid); - - - if (XPC_NASID_IN_ARRAY(nasid, xpc_part_nasids)) { - dev_dbg(xpc_part, "PROM indicates Nasid %d is " - "part of the local partition; skipping " - "region\n", nasid); - break; - } - - if (!(XPC_NASID_IN_ARRAY(nasid, xpc_mach_nasids))) { - dev_dbg(xpc_part, "PROM indicates Nasid %d was " - "not on Numa-Link network at reset\n", - nasid); - continue; - } - - if (XPC_NASID_IN_ARRAY(nasid, discovered_nasids)) { - dev_dbg(xpc_part, "Nasid %d is part of a " - "partition which was previously " - "discovered\n", nasid); - continue; - } - - - /* pull over the reserved page structure */ - - ret = xpc_get_remote_rp(nasid, discovered_nasids, - remote_rp, &remote_rp_pa); - if (ret != xpcSuccess) { - dev_dbg(xpc_part, "unable to get reserved page " - "from nasid %d, reason=%d\n", nasid, - ret); - - if (ret == xpcLocalPartid) { - break; - } - continue; - } - - remote_vars_pa = remote_rp->vars_pa; - - partid = remote_rp->partid; - part = &xpc_partitions[partid]; - - - /* pull over the cross partition variables */ - - ret = xpc_get_remote_vars(remote_vars_pa, remote_vars); - if (ret != xpcSuccess) { - dev_dbg(xpc_part, "unable to get XPC variables " - "from nasid %d, reason=%d\n", nasid, - ret); - - XPC_DEACTIVATE_PARTITION(part, ret); - continue; - } - - if (part->act_state != XPC_P_INACTIVE) { - dev_dbg(xpc_part, "partition %d on nasid %d is " - "already activating\n", partid, nasid); - break; - } - - /* - * Register the remote partition's AMOs with SAL so it - * can handle and cleanup errors within that address - * range should the remote partition go down. We don't - * unregister this range because it is difficult to - * tell when outstanding writes to the remote partition - * are finished and thus when it is thus safe to - * unregister. This should not result in wasted space - * in the SAL xp_addr_region table because we should - * get the same page for remote_act_amos_pa after - * module reloads and system reboots. - */ - if (sn_register_xp_addr_region( - remote_vars->amos_page_pa, - PAGE_SIZE, 1) < 0) { - dev_dbg(xpc_part, "partition %d failed to " - "register xp_addr region 0x%016lx\n", - partid, remote_vars->amos_page_pa); - - XPC_SET_REASON(part, xpcPhysAddrRegFailed, - __LINE__); - break; - } - - /* - * The remote nasid is valid and available. - * Send an interrupt to that nasid to notify - * it that we are ready to begin activation. - */ - dev_dbg(xpc_part, "sending an interrupt to AMO 0x%lx, " - "nasid %d, phys_cpuid 0x%x\n", - remote_vars->amos_page_pa, - remote_vars->act_nasid, - remote_vars->act_phys_cpuid); - - if (XPC_SUPPORTS_DISENGAGE_REQUEST(remote_vars-> - version)) { - part->remote_amos_page_pa = - remote_vars->amos_page_pa; - xpc_mark_partition_disengaged(part); - xpc_cancel_partition_disengage_request(part); - } - xpc_IPI_send_activate(remote_vars); - } - } - - kfree(discovered_nasids); - kfree(remote_rp_base); -} - - -/* - * Given a partid, get the nasids owned by that partition from the - * remote partition's reserved page. - */ -enum xpc_retval -xpc_initiate_partid_to_nasids(partid_t partid, void *nasid_mask) -{ - struct xpc_partition *part; - u64 part_nasid_pa; - int bte_res; - - - part = &xpc_partitions[partid]; - if (part->remote_rp_pa == 0) { - return xpcPartitionDown; - } - - memset(nasid_mask, 0, XP_NASID_MASK_BYTES); - - part_nasid_pa = (u64) XPC_RP_PART_NASIDS(part->remote_rp_pa); - - 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 deleted file mode 100644 index a5df672d839..00000000000 --- a/arch/ia64/sn/kernel/xpnet.c +++ /dev/null @@ -1,718 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 1999,2001-2005 Silicon Graphics, Inc. All rights reserved. - */ - - -/* - * Cross Partition Network Interface (XPNET) support - * - * XPNET provides a virtual network layered on top of the Cross - * Partition communication layer. - * - * XPNET provides direct point-to-point and broadcast-like support - * for an ethernet-like device. The ethernet broadcast medium is - * replaced with a point-to-point message structure which passes - * pointers to a DMA-capable block that a remote partition should - * retrieve and pass to the upper level networking layer. - * - */ - - -#include <linux/module.h> -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/ioport.h> -#include <linux/netdevice.h> -#include <linux/etherdevice.h> -#include <linux/delay.h> -#include <linux/ethtool.h> -#include <linux/mii.h> -#include <linux/smp.h> -#include <linux/string.h> -#include <asm/sn/bte.h> -#include <asm/sn/io.h> -#include <asm/sn/sn_sal.h> -#include <asm/types.h> -#include <asm/atomic.h> -#include <asm/sn/xp.h> - - -/* - * The message payload transferred by XPC. - * - * buf_pa is the physical address where the DMA should pull from. - * - * NOTE: for performance reasons, buf_pa should _ALWAYS_ begin on a - * cacheline boundary. To accomplish this, we record the number of - * bytes from the beginning of the first cacheline to the first useful - * byte of the skb (leadin_ignore) and the number of bytes from the - * last useful byte of the skb to the end of the last cacheline - * (tailout_ignore). - * - * size is the number of bytes to transfer which includes the skb->len - * (useful bytes of the senders skb) plus the leadin and tailout - */ -struct xpnet_message { - u16 version; /* Version for this message */ - u16 embedded_bytes; /* #of bytes embedded in XPC message */ - u32 magic; /* Special number indicating this is xpnet */ - u64 buf_pa; /* phys address of buffer to retrieve */ - u32 size; /* #of bytes in buffer */ - u8 leadin_ignore; /* #of bytes to ignore at the beginning */ - u8 tailout_ignore; /* #of bytes to ignore at the end */ - unsigned char data; /* body of small packets */ -}; - -/* - * Determine the size of our message, the cacheline aligned size, - * and then the number of message will request from XPC. - * - * XPC expects each message to exist in an individual cacheline. - */ -#define XPNET_MSG_SIZE (L1_CACHE_BYTES - XPC_MSG_PAYLOAD_OFFSET) -#define XPNET_MSG_DATA_MAX \ - (XPNET_MSG_SIZE - (u64)(&((struct xpnet_message *)0)->data)) -#define XPNET_MSG_ALIGNED_SIZE (L1_CACHE_ALIGN(XPNET_MSG_SIZE)) -#define XPNET_MSG_NENTRIES (PAGE_SIZE / XPNET_MSG_ALIGNED_SIZE) - - -#define XPNET_MAX_KTHREADS (XPNET_MSG_NENTRIES + 1) -#define XPNET_MAX_IDLE_KTHREADS (XPNET_MSG_NENTRIES + 1) - -/* - * Version number of XPNET implementation. XPNET can always talk to versions - * with same major #, and never talk to versions with a different version. - */ -#define _XPNET_VERSION(_major, _minor) (((_major) << 4) | (_minor)) -#define XPNET_VERSION_MAJOR(_v) ((_v) >> 4) -#define XPNET_VERSION_MINOR(_v) ((_v) & 0xf) - -#define XPNET_VERSION _XPNET_VERSION(1,0) /* version 1.0 */ -#define XPNET_VERSION_EMBED _XPNET_VERSION(1,1) /* version 1.1 */ -#define XPNET_MAGIC 0x88786984 /* "XNET" */ - -#define XPNET_VALID_MSG(_m) \ - ((XPNET_VERSION_MAJOR(_m->version) == XPNET_VERSION_MAJOR(XPNET_VERSION)) \ - && (msg->magic == XPNET_MAGIC)) - -#define XPNET_DEVICE_NAME "xp0" - - -/* - * When messages are queued with xpc_send_notify, a kmalloc'd buffer - * of the following type is passed as a notification cookie. When the - * notification function is called, we use the cookie to decide - * whether all outstanding message sends have completed. The skb can - * then be released. - */ -struct xpnet_pending_msg { - struct list_head free_list; - struct sk_buff *skb; - atomic_t use_count; -}; - -/* driver specific structure pointed to by the device structure */ -struct xpnet_dev_private { - struct net_device_stats stats; -}; - -struct net_device *xpnet_device; - -/* - * When we are notified of other partitions activating, we add them to - * our bitmask of partitions to which we broadcast. - */ -static u64 xpnet_broadcast_partitions; -/* protect above */ -static DEFINE_SPINLOCK(xpnet_broadcast_lock); - -/* - * Since the Block Transfer Engine (BTE) is being used for the transfer - * and it relies upon cache-line size transfers, we need to reserve at - * least one cache-line for head and tail alignment. The BTE is - * limited to 8MB transfers. - * - * Testing has shown that changing MTU to greater than 64KB has no effect - * on TCP as the two sides negotiate a Max Segment Size that is limited - * to 64K. Other protocols May use packets greater than this, but for - * now, the default is 64KB. - */ -#define XPNET_MAX_MTU (0x800000UL - L1_CACHE_BYTES) -/* 32KB has been determined to be the ideal */ -#define XPNET_DEF_MTU (0x8000UL) - - -/* - * The partition id is encapsulated in the MAC address. The following - * define locates the octet the partid is in. - */ -#define XPNET_PARTID_OCTET 1 -#define XPNET_LICENSE_OCTET 2 - - -/* - * Define the XPNET debug device structure that is to be used with dev_dbg(), - * dev_err(), dev_warn(), and dev_info(). - */ -struct device_driver xpnet_dbg_name = { - .name = "xpnet" -}; - -struct device xpnet_dbg_subname = { - .bus_id = {0}, /* set to "" */ - .driver = &xpnet_dbg_name -}; - -struct device *xpnet = &xpnet_dbg_subname; - -/* - * Packet was recevied by XPC and forwarded to us. - */ -static void -xpnet_receive(partid_t partid, int channel, struct xpnet_message *msg) -{ - struct sk_buff *skb; - bte_result_t bret; - struct xpnet_dev_private *priv = - (struct xpnet_dev_private *) xpnet_device->priv; - - - if (!XPNET_VALID_MSG(msg)) { - /* - * Packet with a different XPC version. Ignore. - */ - xpc_received(partid, channel, (void *) msg); - - priv->stats.rx_errors++; - - return; - } - dev_dbg(xpnet, "received 0x%lx, %d, %d, %d\n", msg->buf_pa, msg->size, - msg->leadin_ignore, msg->tailout_ignore); - - - /* reserve an extra cache line */ - skb = dev_alloc_skb(msg->size + L1_CACHE_BYTES); - if (!skb) { - dev_err(xpnet, "failed on dev_alloc_skb(%d)\n", - msg->size + L1_CACHE_BYTES); - - xpc_received(partid, channel, (void *) msg); - - priv->stats.rx_errors++; - - return; - } - - /* - * The allocated skb has some reserved space. - * In order to use bte_copy, we need to get the - * skb->data pointer moved forward. - */ - skb_reserve(skb, (L1_CACHE_BYTES - ((u64)skb->data & - (L1_CACHE_BYTES - 1)) + - msg->leadin_ignore)); - - /* - * Update the tail pointer to indicate data actually - * transferred. - */ - skb_put(skb, (msg->size - msg->leadin_ignore - msg->tailout_ignore)); - - /* - * Move the data over from the other side. - */ - if ((XPNET_VERSION_MINOR(msg->version) == 1) && - (msg->embedded_bytes != 0)) { - dev_dbg(xpnet, "copying embedded message. memcpy(0x%p, 0x%p, " - "%lu)\n", skb->data, &msg->data, - (size_t) msg->embedded_bytes); - - skb_copy_to_linear_data(skb, &msg->data, (size_t)msg->embedded_bytes); - } else { - dev_dbg(xpnet, "transferring buffer to the skb->data area;\n\t" - "bte_copy(0x%p, 0x%p, %hu)\n", (void *)msg->buf_pa, - (void *)__pa((u64)skb->data & ~(L1_CACHE_BYTES - 1)), - msg->size); - - bret = bte_copy(msg->buf_pa, - __pa((u64)skb->data & ~(L1_CACHE_BYTES - 1)), - msg->size, (BTE_NOTIFY | BTE_WACQUIRE), NULL); - - if (bret != BTE_SUCCESS) { - // >>> Need better way of cleaning skb. Currently skb - // >>> appears in_use and we can't just call - // >>> dev_kfree_skb. - dev_err(xpnet, "bte_copy(0x%p, 0x%p, 0x%hx) returned " - "error=0x%x\n", (void *)msg->buf_pa, - (void *)__pa((u64)skb->data & - ~(L1_CACHE_BYTES - 1)), - msg->size, bret); - - xpc_received(partid, channel, (void *) msg); - - priv->stats.rx_errors++; - - return; - } - } - - dev_dbg(xpnet, "<skb->head=0x%p skb->data=0x%p skb->tail=0x%p " - "skb->end=0x%p skb->len=%d\n", (void *) skb->head, - (void *)skb->data, skb_tail_pointer(skb), skb_end_pointer(skb), - skb->len); - - skb->protocol = eth_type_trans(skb, xpnet_device); - skb->ip_summed = CHECKSUM_UNNECESSARY; - - dev_dbg(xpnet, "passing skb to network layer\n" - KERN_DEBUG "\tskb->head=0x%p skb->data=0x%p skb->tail=0x%p " - "skb->end=0x%p skb->len=%d\n", - (void *)skb->head, (void *)skb->data, skb_tail_pointer(skb), - skb_end_pointer(skb), skb->len); - - - xpnet_device->last_rx = jiffies; - priv->stats.rx_packets++; - priv->stats.rx_bytes += skb->len + ETH_HLEN; - - netif_rx_ni(skb); - xpc_received(partid, channel, (void *) msg); -} - - -/* - * This is the handler which XPC calls during any sort of change in - * state or message reception on a connection. - */ -static void -xpnet_connection_activity(enum xpc_retval reason, partid_t partid, int channel, - void *data, void *key) -{ - long bp; - - - DBUG_ON(partid <= 0 || partid >= XP_MAX_PARTITIONS); - DBUG_ON(channel != XPC_NET_CHANNEL); - - switch(reason) { - case xpcMsgReceived: /* message received */ - DBUG_ON(data == NULL); - - xpnet_receive(partid, channel, (struct xpnet_message *) data); - break; - - case xpcConnected: /* connection completed to a partition */ - spin_lock_bh(&xpnet_broadcast_lock); - xpnet_broadcast_partitions |= 1UL << (partid -1 ); - bp = xpnet_broadcast_partitions; - spin_unlock_bh(&xpnet_broadcast_lock); - - netif_carrier_on(xpnet_device); - - dev_dbg(xpnet, "%s connection created to partition %d; " - "xpnet_broadcast_partitions=0x%lx\n", - xpnet_device->name, partid, bp); - break; - - default: - spin_lock_bh(&xpnet_broadcast_lock); - xpnet_broadcast_partitions &= ~(1UL << (partid -1 )); - bp = xpnet_broadcast_partitions; - spin_unlock_bh(&xpnet_broadcast_lock); - - if (bp == 0) { - netif_carrier_off(xpnet_device); - } - - dev_dbg(xpnet, "%s disconnected from partition %d; " - "xpnet_broadcast_partitions=0x%lx\n", - xpnet_device->name, partid, bp); - break; - - } -} - - -static int -xpnet_dev_open(struct net_device *dev) -{ - enum xpc_retval ret; - - - dev_dbg(xpnet, "calling xpc_connect(%d, 0x%p, NULL, %ld, %ld, %ld, " - "%ld)\n", XPC_NET_CHANNEL, xpnet_connection_activity, - XPNET_MSG_SIZE, XPNET_MSG_NENTRIES, XPNET_MAX_KTHREADS, - XPNET_MAX_IDLE_KTHREADS); - - ret = xpc_connect(XPC_NET_CHANNEL, xpnet_connection_activity, NULL, - XPNET_MSG_SIZE, XPNET_MSG_NENTRIES, - XPNET_MAX_KTHREADS, XPNET_MAX_IDLE_KTHREADS); - if (ret != xpcSuccess) { - dev_err(xpnet, "ifconfig up of %s failed on XPC connect, " - "ret=%d\n", dev->name, ret); - - return -ENOMEM; - } - - dev_dbg(xpnet, "ifconfig up of %s; XPC connected\n", dev->name); - - return 0; -} - - -static int -xpnet_dev_stop(struct net_device *dev) -{ - xpc_disconnect(XPC_NET_CHANNEL); - - dev_dbg(xpnet, "ifconfig down of %s; XPC disconnected\n", dev->name); - - return 0; -} - - -static int -xpnet_dev_change_mtu(struct net_device *dev, int new_mtu) -{ - /* 68 comes from min TCP+IP+MAC header */ - if ((new_mtu < 68) || (new_mtu > XPNET_MAX_MTU)) { - dev_err(xpnet, "ifconfig %s mtu %d failed; value must be " - "between 68 and %ld\n", dev->name, new_mtu, - XPNET_MAX_MTU); - return -EINVAL; - } - - dev->mtu = new_mtu; - dev_dbg(xpnet, "ifconfig %s mtu set to %d\n", dev->name, new_mtu); - return 0; -} - - -/* - * Required for the net_device structure. - */ -static int -xpnet_dev_set_config(struct net_device *dev, struct ifmap *new_map) -{ - return 0; -} - - -/* - * Return statistics to the caller. - */ -static struct net_device_stats * -xpnet_dev_get_stats(struct net_device *dev) -{ - struct xpnet_dev_private *priv; - - - priv = (struct xpnet_dev_private *) dev->priv; - - return &priv->stats; -} - - -/* - * Notification that the other end has received the message and - * DMA'd the skb information. At this point, they are done with - * our side. When all recipients are done processing, we - * release the skb and then release our pending message structure. - */ -static void -xpnet_send_completed(enum xpc_retval reason, partid_t partid, int channel, - void *__qm) -{ - struct xpnet_pending_msg *queued_msg = - (struct xpnet_pending_msg *) __qm; - - - DBUG_ON(queued_msg == NULL); - - dev_dbg(xpnet, "message to %d notified with reason %d\n", - partid, reason); - - if (atomic_dec_return(&queued_msg->use_count) == 0) { - dev_dbg(xpnet, "all acks for skb->head=-x%p\n", - (void *) queued_msg->skb->head); - - dev_kfree_skb_any(queued_msg->skb); - kfree(queued_msg); - } -} - - -/* - * Network layer has formatted a packet (skb) and is ready to place it - * "on the wire". Prepare and send an xpnet_message to all partitions - * which have connected with us and are targets of this packet. - * - * MAC-NOTE: For the XPNET driver, the MAC address contains the - * destination partition_id. If the destination partition id word - * is 0xff, this packet is to broadcast to all partitions. - */ -static int -xpnet_dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) -{ - struct xpnet_pending_msg *queued_msg; - enum xpc_retval ret; - struct xpnet_message *msg; - u64 start_addr, end_addr; - long dp; - u8 second_mac_octet; - partid_t dest_partid; - struct xpnet_dev_private *priv; - u16 embedded_bytes; - - - priv = (struct xpnet_dev_private *) dev->priv; - - - dev_dbg(xpnet, ">skb->head=0x%p skb->data=0x%p skb->tail=0x%p " - "skb->end=0x%p skb->len=%d\n", (void *) skb->head, - (void *)skb->data, skb_tail_pointer(skb), skb_end_pointer(skb), - skb->len); - - - /* - * The xpnet_pending_msg tracks how many outstanding - * xpc_send_notifies are relying on this skb. When none - * remain, release the skb. - */ - queued_msg = kmalloc(sizeof(struct xpnet_pending_msg), GFP_ATOMIC); - if (queued_msg == NULL) { - dev_warn(xpnet, "failed to kmalloc %ld bytes; dropping " - "packet\n", sizeof(struct xpnet_pending_msg)); - - priv->stats.tx_errors++; - - return -ENOMEM; - } - - - /* get the beginning of the first cacheline and end of last */ - start_addr = ((u64) skb->data & ~(L1_CACHE_BYTES - 1)); - end_addr = L1_CACHE_ALIGN((u64)skb_tail_pointer(skb)); - - /* calculate how many bytes to embed in the XPC message */ - embedded_bytes = 0; - if (unlikely(skb->len <= XPNET_MSG_DATA_MAX)) { - /* skb->data does fit so embed */ - embedded_bytes = skb->len; - } - - - /* - * Since the send occurs asynchronously, we set the count to one - * and begin sending. Any sends that happen to complete before - * we are done sending will not free the skb. We will be left - * with that task during exit. This also handles the case of - * a packet destined for a partition which is no longer up. - */ - atomic_set(&queued_msg->use_count, 1); - queued_msg->skb = skb; - - - second_mac_octet = skb->data[XPNET_PARTID_OCTET]; - if (second_mac_octet == 0xff) { - /* we are being asked to broadcast to all partitions */ - dp = xpnet_broadcast_partitions; - } else if (second_mac_octet != 0) { - dp = xpnet_broadcast_partitions & - (1UL << (second_mac_octet - 1)); - } else { - /* 0 is an invalid partid. Ignore */ - dp = 0; - } - dev_dbg(xpnet, "destination Partitions mask (dp) = 0x%lx\n", dp); - - /* - * If we wanted to allow promiscuous mode to work like an - * unswitched network, this would be a good point to OR in a - * mask of partitions which should be receiving all packets. - */ - - /* - * Main send loop. - */ - for (dest_partid = 1; dp && dest_partid < XP_MAX_PARTITIONS; - dest_partid++) { - - - if (!(dp & (1UL << (dest_partid - 1)))) { - /* not destined for this partition */ - continue; - } - - /* remove this partition from the destinations mask */ - dp &= ~(1UL << (dest_partid - 1)); - - - /* found a partition to send to */ - - ret = xpc_allocate(dest_partid, XPC_NET_CHANNEL, - XPC_NOWAIT, (void **)&msg); - if (unlikely(ret != xpcSuccess)) { - continue; - } - - msg->embedded_bytes = embedded_bytes; - if (unlikely(embedded_bytes != 0)) { - msg->version = XPNET_VERSION_EMBED; - dev_dbg(xpnet, "calling memcpy(0x%p, 0x%p, 0x%lx)\n", - &msg->data, skb->data, (size_t) embedded_bytes); - skb_copy_from_linear_data(skb, &msg->data, - (size_t)embedded_bytes); - } else { - msg->version = XPNET_VERSION; - } - msg->magic = XPNET_MAGIC; - msg->size = end_addr - start_addr; - msg->leadin_ignore = (u64) skb->data - start_addr; - msg->tailout_ignore = end_addr - (u64)skb_tail_pointer(skb); - msg->buf_pa = __pa(start_addr); - - dev_dbg(xpnet, "sending XPC message to %d:%d\n" - KERN_DEBUG "msg->buf_pa=0x%lx, msg->size=%u, " - "msg->leadin_ignore=%u, msg->tailout_ignore=%u\n", - dest_partid, XPC_NET_CHANNEL, msg->buf_pa, msg->size, - msg->leadin_ignore, msg->tailout_ignore); - - - atomic_inc(&queued_msg->use_count); - - ret = xpc_send_notify(dest_partid, XPC_NET_CHANNEL, msg, - xpnet_send_completed, queued_msg); - if (unlikely(ret != xpcSuccess)) { - atomic_dec(&queued_msg->use_count); - continue; - } - - } - - if (atomic_dec_return(&queued_msg->use_count) == 0) { - dev_dbg(xpnet, "no partitions to receive packet destined for " - "%d\n", dest_partid); - - - dev_kfree_skb(skb); - kfree(queued_msg); - } - - priv->stats.tx_packets++; - priv->stats.tx_bytes += skb->len; - - return 0; -} - - -/* - * Deal with transmit timeouts coming from the network layer. - */ -static void -xpnet_dev_tx_timeout (struct net_device *dev) -{ - struct xpnet_dev_private *priv; - - - priv = (struct xpnet_dev_private *) dev->priv; - - priv->stats.tx_errors++; - return; -} - - -static int __init -xpnet_init(void) -{ - int i; - u32 license_num; - int result = -ENOMEM; - - - if (!ia64_platform_is("sn2")) { - return -ENODEV; - } - - dev_info(xpnet, "registering network device %s\n", XPNET_DEVICE_NAME); - - /* - * use ether_setup() to init the majority of our device - * structure and then override the necessary pieces. - */ - xpnet_device = alloc_netdev(sizeof(struct xpnet_dev_private), - XPNET_DEVICE_NAME, ether_setup); - if (xpnet_device == NULL) { - return -ENOMEM; - } - - netif_carrier_off(xpnet_device); - - xpnet_device->mtu = XPNET_DEF_MTU; - xpnet_device->change_mtu = xpnet_dev_change_mtu; - xpnet_device->open = xpnet_dev_open; - xpnet_device->get_stats = xpnet_dev_get_stats; - xpnet_device->stop = xpnet_dev_stop; - xpnet_device->hard_start_xmit = xpnet_dev_hard_start_xmit; - xpnet_device->tx_timeout = xpnet_dev_tx_timeout; - xpnet_device->set_config = xpnet_dev_set_config; - - /* - * Multicast assumes the LSB of the first octet is set for multicast - * MAC addresses. We chose the first octet of the MAC to be unlikely - * to collide with any vendor's officially issued MAC. - */ - xpnet_device->dev_addr[0] = 0xfe; - xpnet_device->dev_addr[XPNET_PARTID_OCTET] = sn_partition_id; - license_num = sn_partition_serial_number_val(); - for (i = 3; i >= 0; i--) { - xpnet_device->dev_addr[XPNET_LICENSE_OCTET + i] = - license_num & 0xff; - license_num = license_num >> 8; - } - - /* - * ether_setup() sets this to a multicast device. We are - * really not supporting multicast at this time. - */ - xpnet_device->flags &= ~IFF_MULTICAST; - - /* - * No need to checksum as it is a DMA transfer. The BTE will - * report an error if the data is not retrievable and the - * packet will be dropped. - */ - xpnet_device->features = NETIF_F_NO_CSUM; - - result = register_netdev(xpnet_device); - if (result != 0) { - free_netdev(xpnet_device); - } - - return result; -} -module_init(xpnet_init); - - -static void __exit -xpnet_exit(void) -{ - dev_info(xpnet, "unregistering network device %s\n", - xpnet_device[0].name); - - unregister_netdev(xpnet_device); - - free_netdev(xpnet_device); -} -module_exit(xpnet_exit); - - -MODULE_AUTHOR("Silicon Graphics, Inc."); -MODULE_DESCRIPTION("Cross Partition Network adapter (XPNET)"); -MODULE_LICENSE("GPL"); - diff --git a/arch/ia64/sn/pci/tioce_provider.c b/arch/ia64/sn/pci/tioce_provider.c index 9b3c1137302..94e584527f4 100644 --- a/arch/ia64/sn/pci/tioce_provider.c +++ b/arch/ia64/sn/pci/tioce_provider.c @@ -655,7 +655,8 @@ tioce_dma(struct pci_dev *pdev, u64 paddr, size_t byte_count, int dma_flags) * * Simply call tioce_do_dma_map() to create a map with the barrier bit set * in the address. - */ static u64 + */ +static u64 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, dma_flags); @@ -668,7 +669,8 @@ tioce_dma_consistent(struct pci_dev *pdev, u64 paddr, size_t byte_count, int dma * * Handle a CE error interrupt. Simply a wrapper around a SAL call which * defers processing to the SGI prom. - */ static irqreturn_t + */ +static irqreturn_t tioce_error_intr_handler(int irq, void *arg) { struct tioce_common *soft = arg; diff --git a/arch/sparc/kernel/entry.S b/arch/sparc/kernel/entry.S index 135644f8add..484c83d23ee 100644 --- a/arch/sparc/kernel/entry.S +++ b/arch/sparc/kernel/entry.S @@ -1409,7 +1409,6 @@ syscall_is_too_hard: st %o0, [%sp + STACKFRAME_SZ + PT_I0] - .globl ret_sys_call ret_sys_call: ld [%curptr + TI_FLAGS], %l6 cmp %o0, -ERESTART_RESTARTBLOCK diff --git a/arch/sparc/kernel/signal.c b/arch/sparc/kernel/signal.c index 1f730619a24..3e849e8e348 100644 --- a/arch/sparc/kernel/signal.c +++ b/arch/sparc/kernel/signal.c @@ -105,11 +105,6 @@ static int _sigpause_common(old_sigset_t set) return -ERESTARTNOHAND; } -asmlinkage int sys_sigpause(unsigned int set) -{ - return _sigpause_common(set); -} - asmlinkage int sys_sigsuspend(old_sigset_t set) { return _sigpause_common(set); diff --git a/arch/sparc64/Kconfig b/arch/sparc64/Kconfig index df3eacb5ca1..8acc5cc3862 100644 --- a/arch/sparc64/Kconfig +++ b/arch/sparc64/Kconfig @@ -250,6 +250,26 @@ endchoice endmenu +config NUMA + bool "NUMA support" + +config NODES_SHIFT + int + default "4" + depends on NEED_MULTIPLE_NODES + +# Some NUMA nodes have memory ranges that span +# other nodes. Even though a pfn is valid and +# between a node's start and end pfns, it may not +# reside on that node. See memmap_init_zone() +# for details. +config NODES_SPAN_OTHER_NODES + def_bool y + depends on NEED_MULTIPLE_NODES + +config ARCH_POPULATES_NODE_MAP + def_bool y + config ARCH_SELECT_MEMORY_MODEL def_bool y diff --git a/arch/sparc64/defconfig b/arch/sparc64/defconfig index e1835868ad3..92f79680f70 100644 --- a/arch/sparc64/defconfig +++ b/arch/sparc64/defconfig @@ -1,7 +1,7 @@ # # Automatically generated make config: don't edit -# Linux kernel version: 2.6.25 -# Sun Apr 20 01:33:21 2008 +# Linux kernel version: 2.6.25-numa +# Wed Apr 23 04:49:08 2008 # CONFIG_SPARC=y CONFIG_SPARC64=y @@ -152,6 +152,8 @@ CONFIG_GENERIC_CALIBRATE_DELAY=y CONFIG_HUGETLB_PAGE_SIZE_4MB=y # CONFIG_HUGETLB_PAGE_SIZE_512K is not set # CONFIG_HUGETLB_PAGE_SIZE_64K is not set +# CONFIG_NUMA is not set +CONFIG_ARCH_POPULATES_NODE_MAP=y CONFIG_ARCH_SELECT_MEMORY_MODEL=y CONFIG_ARCH_SPARSEMEM_ENABLE=y CONFIG_ARCH_SPARSEMEM_DEFAULT=y @@ -787,7 +789,6 @@ CONFIG_I2C_ALGOBIT=y # CONFIG_SENSORS_PCF8574 is not set # CONFIG_PCF8575 is not set # CONFIG_SENSORS_PCF8591 is not set -# CONFIG_TPS65010 is not set # CONFIG_SENSORS_MAX6875 is not set # CONFIG_SENSORS_TSL2550 is not set # CONFIG_I2C_DEBUG_CORE is not set @@ -869,6 +870,7 @@ CONFIG_SSB_POSSIBLE=y # Multifunction device drivers # # CONFIG_MFD_SM501 is not set +# CONFIG_HTC_PASIC3 is not set # # Multimedia devices @@ -1219,10 +1221,6 @@ CONFIG_USB_STORAGE=m # CONFIG_NEW_LEDS is not set # CONFIG_INFINIBAND is not set # CONFIG_RTC_CLASS is not set - -# -# Userspace I/O -# # CONFIG_UIO is not set # @@ -1399,6 +1397,7 @@ CONFIG_SCHEDSTATS=y CONFIG_DEBUG_BUGVERBOSE=y # CONFIG_DEBUG_INFO is not set # CONFIG_DEBUG_VM is not set +# CONFIG_DEBUG_WRITECOUNT is not set # CONFIG_DEBUG_LIST is not set # CONFIG_DEBUG_SG is not set # CONFIG_BOOT_PRINTK_DELAY is not set @@ -1425,53 +1424,82 @@ CONFIG_ASYNC_CORE=m CONFIG_ASYNC_MEMCPY=m CONFIG_ASYNC_XOR=m CONFIG_CRYPTO=y + +# +# Crypto core or helper +# CONFIG_CRYPTO_ALGAPI=y CONFIG_CRYPTO_AEAD=y CONFIG_CRYPTO_BLKCIPHER=y -# CONFIG_CRYPTO_SEQIV is not set CONFIG_CRYPTO_HASH=y CONFIG_CRYPTO_MANAGER=y +CONFIG_CRYPTO_GF128MUL=m +CONFIG_CRYPTO_NULL=m +# CONFIG_CRYPTO_CRYPTD is not set +CONFIG_CRYPTO_AUTHENC=y +CONFIG_CRYPTO_TEST=m + +# +# Authenticated Encryption with Associated Data +# +# CONFIG_CRYPTO_CCM is not set +# CONFIG_CRYPTO_GCM is not set +# CONFIG_CRYPTO_SEQIV is not set + +# +# Block modes +# +CONFIG_CRYPTO_CBC=y +# CONFIG_CRYPTO_CTR is not set +# CONFIG_CRYPTO_CTS is not set +CONFIG_CRYPTO_ECB=m +CONFIG_CRYPTO_LRW=m +CONFIG_CRYPTO_PCBC=m +CONFIG_CRYPTO_XTS=m + +# +# Hash modes +# CONFIG_CRYPTO_HMAC=y CONFIG_CRYPTO_XCBC=y -CONFIG_CRYPTO_NULL=m + +# +# Digest +# +CONFIG_CRYPTO_CRC32C=m CONFIG_CRYPTO_MD4=y CONFIG_CRYPTO_MD5=y +CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_SHA1=y CONFIG_CRYPTO_SHA256=m CONFIG_CRYPTO_SHA512=m -CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_TGR192=m -CONFIG_CRYPTO_GF128MUL=m -CONFIG_CRYPTO_ECB=m -CONFIG_CRYPTO_CBC=y -CONFIG_CRYPTO_PCBC=m -CONFIG_CRYPTO_LRW=m -CONFIG_CRYPTO_XTS=m -# CONFIG_CRYPTO_CTR is not set -# CONFIG_CRYPTO_GCM is not set -# CONFIG_CRYPTO_CCM is not set -# CONFIG_CRYPTO_CRYPTD is not set -CONFIG_CRYPTO_DES=y -CONFIG_CRYPTO_FCRYPT=m -CONFIG_CRYPTO_BLOWFISH=m -CONFIG_CRYPTO_TWOFISH=m -CONFIG_CRYPTO_TWOFISH_COMMON=m -CONFIG_CRYPTO_SERPENT=m +CONFIG_CRYPTO_WP512=m + +# +# Ciphers +# CONFIG_CRYPTO_AES=m +CONFIG_CRYPTO_ANUBIS=m +CONFIG_CRYPTO_ARC4=m +CONFIG_CRYPTO_BLOWFISH=m +CONFIG_CRYPTO_CAMELLIA=m CONFIG_CRYPTO_CAST5=m CONFIG_CRYPTO_CAST6=m -CONFIG_CRYPTO_TEA=m -CONFIG_CRYPTO_ARC4=m +CONFIG_CRYPTO_DES=y +CONFIG_CRYPTO_FCRYPT=m CONFIG_CRYPTO_KHAZAD=m -CONFIG_CRYPTO_ANUBIS=m -CONFIG_CRYPTO_SEED=m # CONFIG_CRYPTO_SALSA20 is not set +CONFIG_CRYPTO_SEED=m +CONFIG_CRYPTO_SERPENT=m +CONFIG_CRYPTO_TEA=m +CONFIG_CRYPTO_TWOFISH=m +CONFIG_CRYPTO_TWOFISH_COMMON=m + +# +# Compression +# CONFIG_CRYPTO_DEFLATE=y -CONFIG_CRYPTO_MICHAEL_MIC=m -CONFIG_CRYPTO_CRC32C=m -CONFIG_CRYPTO_CAMELLIA=m -CONFIG_CRYPTO_TEST=m -CONFIG_CRYPTO_AUTHENC=y # CONFIG_CRYPTO_LZO is not set CONFIG_CRYPTO_HW=y # CONFIG_CRYPTO_DEV_HIFN_795X is not set @@ -1492,3 +1520,4 @@ CONFIG_PLIST=y CONFIG_HAS_IOMEM=y CONFIG_HAS_IOPORT=y CONFIG_HAS_DMA=y +CONFIG_HAVE_LMB=y diff --git a/arch/sparc64/kernel/ebus.c b/arch/sparc64/kernel/ebus.c index 04ab81cb4f4..bc263227484 100644 --- a/arch/sparc64/kernel/ebus.c +++ b/arch/sparc64/kernel/ebus.c @@ -396,6 +396,7 @@ static void __init fill_ebus_device(struct device_node *dp, struct linux_ebus_de sd->op = &dev->ofdev; sd->iommu = dev->bus->ofdev.dev.parent->archdata.iommu; sd->stc = dev->bus->ofdev.dev.parent->archdata.stc; + sd->numa_node = dev->bus->ofdev.dev.parent->archdata.numa_node; dev->ofdev.node = dp; dev->ofdev.dev.parent = &dev->bus->ofdev.dev; diff --git a/arch/sparc64/kernel/entry.S b/arch/sparc64/kernel/entry.S index fb43c76bdc2..fd06e937ae1 100644 --- a/arch/sparc64/kernel/entry.S +++ b/arch/sparc64/kernel/entry.S @@ -47,7 +47,7 @@ do_fpdis: ba,pt %xcc, etrap 109: or %g7, %lo(109b), %g7 add %g0, %g0, %g0 - ba,a,pt %xcc, rtrap_clr_l6 + ba,a,pt %xcc, rtrap 1: TRAP_LOAD_THREAD_REG(%g6, %g1) ldub [%g6 + TI_FPSAVED], %g5 @@ -226,7 +226,7 @@ fp_other_bounce: call do_fpother add %sp, PTREGS_OFF, %o0 ba,pt %xcc, rtrap - clr %l6 + nop .globl do_fpother_check_fitos .align 32 @@ -489,7 +489,7 @@ utrap_trap: /* %g3=handler,%g4=level */ call bad_trap add %sp, PTREGS_OFF, %o0 ba,pt %xcc, rtrap - clr %l6 + nop invoke_utrap: sllx %g3, 3, %g3 @@ -607,7 +607,7 @@ __spitfire_cee_trap_continue: call spitfire_access_error add %sp, PTREGS_OFF, %o0 ba,pt %xcc, rtrap - clr %l6 + nop /* This is the trap handler entry point for ECC correctable * errors. They are corrected, but we listen for the trap @@ -686,7 +686,7 @@ __spitfire_data_access_exception_tl1: call spitfire_data_access_exception_tl1 add %sp, PTREGS_OFF, %o0 ba,pt %xcc, rtrap - clr %l6 + nop __spitfire_data_access_exception: rdpr %pstate, %g4 @@ -705,7 +705,7 @@ __spitfire_data_access_exception: call spitfire_data_access_exception add %sp, PTREGS_OFF, %o0 ba,pt %xcc, rtrap - clr %l6 + nop .globl __spitfire_insn_access_exception .globl __spitfire_insn_access_exception_tl1 @@ -725,7 +725,7 @@ __spitfire_insn_access_exception_tl1: call spitfire_insn_access_exception_tl1 add %sp, PTREGS_OFF, %o0 ba,pt %xcc, rtrap - clr %l6 + nop __spitfire_insn_access_exception: rdpr %pstate, %g4 @@ -743,7 +743,7 @@ __spitfire_insn_access_exception: call spitfire_insn_access_exception add %sp, PTREGS_OFF, %o0 ba,pt %xcc, rtrap - clr %l6 + nop /* These get patched into the trap table at boot time * once we know we have a cheetah processor. @@ -937,7 +937,7 @@ do_dcpe_tl1_fatal: call cheetah_plus_parity_error add %sp, PTREGS_OFF, %o1 ba,pt %xcc, rtrap - clr %l6 + nop do_icpe_tl1: rdpr %tl, %g1 ! Save original trap level @@ -979,7 +979,7 @@ do_icpe_tl1_fatal: call cheetah_plus_parity_error add %sp, PTREGS_OFF, %o1 ba,pt %xcc, rtrap - clr %l6 + nop dcpe_icpe_tl1_common: /* Flush D-cache, re-enable D/I caches in DCU and finally @@ -1281,7 +1281,7 @@ __do_privact: call do_privact add %sp, PTREGS_OFF, %o0 ba,pt %xcc, rtrap - clr %l6 + nop .globl do_mna do_mna: @@ -1308,7 +1308,7 @@ do_mna: call mem_address_unaligned add %sp, PTREGS_OFF, %o0 ba,pt %xcc, rtrap - clr %l6 + nop .globl do_lddfmna do_lddfmna: @@ -1326,7 +1326,7 @@ do_lddfmna: call handle_lddfmna add %sp, PTREGS_OFF, %o0 ba,pt %xcc, rtrap - clr %l6 + nop .globl do_stdfmna do_stdfmna: @@ -1344,7 +1344,7 @@ do_stdfmna: call handle_stdfmna add %sp, PTREGS_OFF, %o0 ba,pt %xcc, rtrap - clr %l6 + nop .globl breakpoint_trap breakpoint_trap: @@ -1424,13 +1424,13 @@ sys32_rt_sigreturn: 1: ldx [%curptr + TI_FLAGS], %l5 andcc %l5, (_TIF_SYSCALL_TRACE|_TIF_SECCOMP|_TIF_SYSCALL_AUDIT), %g0 be,pt %icc, rtrap - clr %l6 + nop add %sp, PTREGS_OFF, %o0 call syscall_trace mov 1, %o1 ba,pt %xcc, rtrap - clr %l6 + nop /* This is how fork() was meant to be done, 8 instruction entry. * @@ -1559,7 +1559,7 @@ linux_sparc_syscall32: /* Linux native system calls enter here... */ .align 32 - .globl linux_sparc_syscall, ret_sys_call + .globl linux_sparc_syscall linux_sparc_syscall: /* Direct access to user regs, much faster. */ cmp %g1, NR_SYSCALLS ! IEU1 Group @@ -1605,7 +1605,7 @@ ret_sys_call: bne,pn %icc, linux_syscall_trace2 add %l1, 0x4, %l2 ! npc = npc+4 stx %l1, [%sp + PTREGS_OFF + PT_V9_TPC] - ba,pt %xcc, rtrap_clr_l6 + ba,pt %xcc, rtrap stx %l2, [%sp + PTREGS_OFF + PT_V9_TNPC] 1: @@ -1616,7 +1616,6 @@ ret_sys_call: sub %g0, %o0, %o0 or %g3, %g2, %g3 stx %o0, [%sp + PTREGS_OFF + PT_V9_I0] - mov 1, %l6 stx %g3, [%sp + PTREGS_OFF + PT_V9_TSTATE] bne,pn %icc, linux_syscall_trace2 add %l1, 0x4, %l2 ! npc = npc+4 diff --git a/arch/sparc64/kernel/entry.h b/arch/sparc64/kernel/entry.h index 4a91e9c6d31..32fbab62085 100644 --- a/arch/sparc64/kernel/entry.h +++ b/arch/sparc64/kernel/entry.h @@ -20,7 +20,6 @@ extern void timer_interrupt(int irq, struct pt_regs *regs); extern void do_notify_resume(struct pt_regs *regs, unsigned long orig_i0, - int restart_syscall, unsigned long thread_info_flags); extern asmlinkage void syscall_trace(struct pt_regs *regs, diff --git a/arch/sparc64/kernel/etrap.S b/arch/sparc64/kernel/etrap.S index 4b2bf9eb447..b49d3b60bc0 100644 --- a/arch/sparc64/kernel/etrap.S +++ b/arch/sparc64/kernel/etrap.S @@ -53,7 +53,11 @@ etrap_irq: stx %g3, [%g2 + STACKFRAME_SZ + PT_V9_TPC] rd %y, %g3 stx %g1, [%g2 + STACKFRAME_SZ + PT_V9_TNPC] + rdpr %tt, %g1 st %g3, [%g2 + STACKFRAME_SZ + PT_V9_Y] + sethi %hi(PT_REGS_MAGIC), %g3 + or %g3, %g1, %g1 + st %g1, [%g2 + STACKFRAME_SZ + PT_V9_MAGIC] rdpr %cansave, %g1 brnz,pt %g1, etrap_save diff --git a/arch/sparc64/kernel/iommu.c b/arch/sparc64/kernel/iommu.c index 756fa24eeef..2a37a6ca2a1 100644 --- a/arch/sparc64/kernel/iommu.c +++ b/arch/sparc64/kernel/iommu.c @@ -173,9 +173,11 @@ void iommu_range_free(struct iommu *iommu, dma_addr_t dma_addr, unsigned long np } int iommu_table_init(struct iommu *iommu, int tsbsize, - u32 dma_offset, u32 dma_addr_mask) + u32 dma_offset, u32 dma_addr_mask, + int numa_node) { - unsigned long i, tsbbase, order, sz, num_tsb_entries; + unsigned long i, order, sz, num_tsb_entries; + struct page *page; num_tsb_entries = tsbsize / sizeof(iopte_t); @@ -188,11 +190,12 @@ int iommu_table_init(struct iommu *iommu, int tsbsize, /* Allocate and initialize the free area map. */ sz = num_tsb_entries / 8; sz = (sz + 7UL) & ~7UL; - iommu->arena.map = kzalloc(sz, GFP_KERNEL); + iommu->arena.map = kmalloc_node(sz, GFP_KERNEL, numa_node); if (!iommu->arena.map) { printk(KERN_ERR "IOMMU: Error, kmalloc(arena.map) failed.\n"); return -ENOMEM; } + memset(iommu->arena.map, 0, sz); iommu->arena.limit = num_tsb_entries; if (tlb_type != hypervisor) @@ -201,21 +204,23 @@ int iommu_table_init(struct iommu *iommu, int tsbsize, /* Allocate and initialize the dummy page which we * set inactive IO PTEs to point to. */ - iommu->dummy_page = get_zeroed_page(GFP_KERNEL); - if (!iommu->dummy_page) { + page = alloc_pages_node(numa_node, GFP_KERNEL, 0); + if (!page) { printk(KERN_ERR "IOMMU: Error, gfp(dummy_page) failed.\n"); goto out_free_map; } + iommu->dummy_page = (unsigned long) page_address(page); + memset((void *)iommu->dummy_page, 0, PAGE_SIZE); iommu->dummy_page_pa = (unsigned long) __pa(iommu->dummy_page); /* Now allocate and setup the IOMMU page table itself. */ order = get_order(tsbsize); - tsbbase = __get_free_pages(GFP_KERNEL, order); - if (!tsbbase) { + page = alloc_pages_node(numa_node, GFP_KERNEL, order); + if (!page) { printk(KERN_ERR "IOMMU: Error, gfp(tsb) failed.\n"); goto out_free_dummy_page; } - iommu->page_table = (iopte_t *)tsbbase; + iommu->page_table = (iopte_t *)page_address(page); for (i = 0; i < num_tsb_entries; i++) iopte_make_dummy(iommu, &iommu->page_table[i]); @@ -276,20 +281,24 @@ static inline void iommu_free_ctx(struct iommu *iommu, int ctx) static void *dma_4u_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addrp, gfp_t gfp) { + unsigned long flags, order, first_page; struct iommu *iommu; + struct page *page; + int npages, nid; iopte_t *iopte; - unsigned long flags, order, first_page; void *ret; - int npages; size = IO_PAGE_ALIGN(size); order = get_order(size); if (order >= 10) return NULL; - first_page = __get_free_pages(gfp, order); - if (first_page == 0UL) + nid = dev->archdata.numa_node; + page = alloc_pages_node(nid, gfp, order); + if (unlikely(!page)) return NULL; + + first_page = (unsigned long) page_address(page); memset((char *)first_page, 0, PAGE_SIZE << order); iommu = dev->archdata.iommu; diff --git a/arch/sparc64/kernel/isa.c b/arch/sparc64/kernel/isa.c index b5f7b354084..a2af5ed784c 100644 --- a/arch/sparc64/kernel/isa.c +++ b/arch/sparc64/kernel/isa.c @@ -92,6 +92,7 @@ static void __init isa_fill_devices(struct sparc_isa_bridge *isa_br) sd->op = &isa_dev->ofdev; sd->iommu = isa_br->ofdev.dev.parent->archdata.iommu; sd->stc = isa_br->ofdev.dev.parent->archdata.stc; + sd->numa_node = isa_br->ofdev.dev.parent->archdata.numa_node; isa_dev->ofdev.node = dp; isa_dev->ofdev.dev.parent = &isa_br->ofdev.dev; diff --git a/arch/sparc64/kernel/mdesc.c b/arch/sparc64/kernel/mdesc.c index 91008358956..dde52bcf5c6 100644 --- a/arch/sparc64/kernel/mdesc.c +++ b/arch/sparc64/kernel/mdesc.c @@ -1,10 +1,10 @@ /* mdesc.c: Sun4V machine description handling. * - * Copyright (C) 2007 David S. Miller <davem@davemloft.net> + * Copyright (C) 2007, 2008 David S. Miller <davem@davemloft.net> */ #include <linux/kernel.h> #include <linux/types.h> -#include <linux/bootmem.h> +#include <linux/lmb.h> #include <linux/log2.h> #include <linux/list.h> #include <linux/slab.h> @@ -84,24 +84,28 @@ static void mdesc_handle_init(struct mdesc_handle *hp, hp->handle_size = handle_size; } -static struct mdesc_handle * __init mdesc_bootmem_alloc(unsigned int mdesc_size) +static struct mdesc_handle * __init mdesc_lmb_alloc(unsigned int mdesc_size) { - struct mdesc_handle *hp; unsigned int handle_size, alloc_size; + struct mdesc_handle *hp; + unsigned long paddr; handle_size = (sizeof(struct mdesc_handle) - sizeof(struct mdesc_hdr) + mdesc_size); alloc_size = PAGE_ALIGN(handle_size); - hp = __alloc_bootmem(alloc_size, PAGE_SIZE, 0UL); - if (hp) - mdesc_handle_init(hp, handle_size, hp); + paddr = lmb_alloc(alloc_size, PAGE_SIZE); + hp = NULL; + if (paddr) { + hp = __va(paddr); + mdesc_handle_init(hp, handle_size, hp); + } return hp; } -static void mdesc_bootmem_free(struct mdesc_handle *hp) +static void mdesc_lmb_free(struct mdesc_handle *hp) { unsigned int alloc_size, handle_size = hp->handle_size; unsigned long start, end; @@ -124,9 +128,9 @@ static void mdesc_bootmem_free(struct mdesc_handle *hp) } } -static struct mdesc_mem_ops bootmem_mdesc_ops = { - .alloc = mdesc_bootmem_alloc, - .free = mdesc_bootmem_free, +static struct mdesc_mem_ops lmb_mdesc_ops = { + .alloc = mdesc_lmb_alloc, + .free = mdesc_lmb_free, }; static struct mdesc_handle *mdesc_kmalloc(unsigned int mdesc_size) @@ -888,7 +892,7 @@ void __init sun4v_mdesc_init(void) printk("MDESC: Size is %lu bytes.\n", len); - hp = mdesc_alloc(len, &bootmem_mdesc_ops); + hp = mdesc_alloc(len, &lmb_mdesc_ops); if (hp == NULL) { prom_printf("MDESC: alloc of %lu bytes failed.\n", len); prom_halt(); diff --git a/arch/sparc64/kernel/of_device.c b/arch/sparc64/kernel/of_device.c index 0fd9db95b89..9e58e8cba1c 100644 --- a/arch/sparc64/kernel/of_device.c +++ b/arch/sparc64/kernel/of_device.c @@ -6,6 +6,7 @@ #include <linux/mod_devicetable.h> #include <linux/slab.h> #include <linux/errno.h> +#include <linux/irq.h> #include <linux/of_device.h> #include <linux/of_platform.h> @@ -660,6 +661,7 @@ static unsigned int __init build_one_device_irq(struct of_device *op, struct device_node *dp = op->node; struct device_node *pp, *ip; unsigned int orig_irq = irq; + int nid; if (irq == 0xffffffff) return irq; @@ -672,7 +674,7 @@ static unsigned int __init build_one_device_irq(struct of_device *op, printk("%s: direct translate %x --> %x\n", dp->full_name, orig_irq, irq); - return irq; + goto out; } /* Something more complicated. Walk up to the root, applying @@ -744,6 +746,14 @@ static unsigned int __init build_one_device_irq(struct of_device *op, printk("%s: Apply IRQ trans [%s] %x --> %x\n", op->node->full_name, ip->full_name, orig_irq, irq); +out: + nid = of_node_to_nid(dp); + if (nid != -1) { + cpumask_t numa_mask = node_to_cpumask(nid); + + irq_set_affinity(irq, numa_mask); + } + return irq; } diff --git a/arch/sparc64/kernel/pci.c b/arch/sparc64/kernel/pci.c index 545356b00e2..49f91276651 100644 --- a/arch/sparc64/kernel/pci.c +++ b/arch/sparc64/kernel/pci.c @@ -369,10 +369,12 @@ struct pci_dev *of_create_pci_dev(struct pci_pbm_info *pbm, sd->host_controller = pbm; sd->prom_node = node; sd->op = of_find_device_by_node(node); + sd->numa_node = pbm->numa_node; sd = &sd->op->dev.archdata; sd->iommu = pbm->iommu; sd->stc = &pbm->stc; + sd->numa_node = pbm->numa_node; type = of_get_property(node, "device_type", NULL); if (type == NULL) @@ -1159,6 +1161,16 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, return 0; } +#ifdef CONFIG_NUMA +int pcibus_to_node(struct pci_bus *pbus) +{ + struct pci_pbm_info *pbm = pbus->sysdata; + + return pbm->numa_node; +} +EXPORT_SYMBOL(pcibus_to_node); +#endif + /* Return the domain nuber for this pci bus */ int pci_domain_nr(struct pci_bus *pbus) diff --git a/arch/sparc64/kernel/pci_fire.c b/arch/sparc64/kernel/pci_fire.c index 7571ed56314..d23bb6f53cd 100644 --- a/arch/sparc64/kernel/pci_fire.c +++ b/arch/sparc64/kernel/pci_fire.c @@ -71,7 +71,8 @@ static int pci_fire_pbm_iommu_init(struct pci_pbm_info *pbm) */ fire_write(iommu->iommu_flushinv, ~(u64)0); - err = iommu_table_init(iommu, tsbsize * 8 * 1024, vdma[0], dma_mask); + err = iommu_table_init(iommu, tsbsize * 8 * 1024, vdma[0], dma_mask, + pbm->numa_node); if (err) return err; @@ -449,6 +450,8 @@ static int __init pci_fire_pbm_init(struct pci_controller_info *p, pbm->next = pci_pbm_root; pci_pbm_root = pbm; + pbm->numa_node = -1; + pbm->scan_bus = pci_fire_scan_bus; pbm->pci_ops = &sun4u_pci_ops; pbm->config_space_reg_bits = 12; diff --git a/arch/sparc64/kernel/pci_impl.h b/arch/sparc64/kernel/pci_impl.h index 4a50da13ce4..218bac4ff79 100644 --- a/arch/sparc64/kernel/pci_impl.h +++ b/arch/sparc64/kernel/pci_impl.h @@ -148,6 +148,8 @@ struct pci_pbm_info { struct pci_bus *pci_bus; void (*scan_bus)(struct pci_pbm_info *); struct pci_ops *pci_ops; + + int numa_node; }; struct pci_controller_info { @@ -161,8 +163,6 @@ extern struct pci_pbm_info *pci_pbm_root; extern int pci_num_pbms; /* PCI bus scanning and fixup support. */ -extern void pci_iommu_table_init(struct iommu *iommu, int tsbsize, - u32 dma_offset, u32 dma_addr_mask); extern void pci_get_pbm_props(struct pci_pbm_info *pbm); extern struct pci_bus *pci_scan_one_pbm(struct pci_pbm_info *pbm); extern void pci_determine_mem_io_space(struct pci_pbm_info *pbm); diff --git a/arch/sparc64/kernel/pci_msi.c b/arch/sparc64/kernel/pci_msi.c index d6d64b44af6..db5e8fd8f67 100644 --- a/arch/sparc64/kernel/pci_msi.c +++ b/arch/sparc64/kernel/pci_msi.c @@ -279,11 +279,17 @@ static int bringup_one_msi_queue(struct pci_pbm_info *pbm, unsigned long devino) { int irq = ops->msiq_build_irq(pbm, msiqid, devino); - int err; + int err, nid; if (irq < 0) return irq; + nid = pbm->numa_node; + if (nid != -1) { + cpumask_t numa_mask = node_to_cpumask(nid); + + irq_set_affinity(irq, numa_mask); + } err = request_irq(irq, sparc64_msiq_interrupt, 0, "MSIQ", &pbm->msiq_irq_cookies[msiqid - pbm->msiq_first]); diff --git a/arch/sparc64/kernel/pci_psycho.c b/arch/sparc64/kernel/pci_psycho.c index 0bad96e5d18..994dbe0603d 100644 --- a/arch/sparc64/kernel/pci_psycho.c +++ b/arch/sparc64/kernel/pci_psycho.c @@ -848,7 +848,8 @@ static int psycho_iommu_init(struct pci_pbm_info *pbm) /* Leave diag mode enabled for full-flushing done * in pci_iommu.c */ - err = iommu_table_init(iommu, IO_TSB_SIZE, 0xc0000000, 0xffffffff); + err = iommu_table_init(iommu, IO_TSB_SIZE, 0xc0000000, 0xffffffff, + pbm->numa_node); if (err) return err; @@ -979,6 +980,8 @@ static void __init psycho_pbm_init(struct pci_controller_info *p, pbm->next = pci_pbm_root; pci_pbm_root = pbm; + pbm->numa_node = -1; + pbm->scan_bus = psycho_scan_bus; pbm->pci_ops = &sun4u_pci_ops; pbm->config_space_reg_bits = 8; diff --git a/arch/sparc64/kernel/pci_sabre.c b/arch/sparc64/kernel/pci_sabre.c index 1c5f5fa2339..4c34195baf3 100644 --- a/arch/sparc64/kernel/pci_sabre.c +++ b/arch/sparc64/kernel/pci_sabre.c @@ -704,7 +704,7 @@ static int sabre_iommu_init(struct pci_pbm_info *pbm, * in pci_iommu.c */ err = iommu_table_init(iommu, tsbsize * 1024 * 8, - dvma_offset, dma_mask); + dvma_offset, dma_mask, pbm->numa_node); if (err) return err; @@ -737,6 +737,8 @@ static void __init sabre_pbm_init(struct pci_controller_info *p, pbm->name = dp->full_name; printk("%s: SABRE PCI Bus Module\n", pbm->name); + pbm->numa_node = -1; + pbm->scan_bus = sabre_scan_bus; pbm->pci_ops = &sun4u_pci_ops; pbm->config_space_reg_bits = 8; diff --git a/arch/sparc64/kernel/pci_schizo.c b/arch/sparc64/kernel/pci_schizo.c index e3060936232..615edd9c8e2 100644 --- a/arch/sparc64/kernel/pci_schizo.c +++ b/arch/sparc64/kernel/pci_schizo.c @@ -1220,7 +1220,8 @@ static int schizo_pbm_iommu_init(struct pci_pbm_info *pbm) /* Leave diag mode enabled for full-flushing done * in pci_iommu.c */ - err = iommu_table_init(iommu, tsbsize * 8 * 1024, vdma[0], dma_mask); + err = iommu_table_init(iommu, tsbsize * 8 * 1024, vdma[0], dma_mask, + pbm->numa_node); if (err) return err; @@ -1379,6 +1380,8 @@ static int __init schizo_pbm_init(struct pci_controller_info *p, pbm->next = pci_pbm_root; pci_pbm_root = pbm; + pbm->numa_node = -1; + pbm->scan_bus = schizo_scan_bus; pbm->pci_ops = &sun4u_pci_ops; pbm->config_space_reg_bits = 8; diff --git a/arch/sparc64/kernel/pci_sun4v.c b/arch/sparc64/kernel/pci_sun4v.c index 01839706bd5..e2bb9790039 100644 --- a/arch/sparc64/kernel/pci_sun4v.c +++ b/arch/sparc64/kernel/pci_sun4v.c @@ -127,10 +127,12 @@ static inline long iommu_batch_end(void) static void *dma_4v_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addrp, gfp_t gfp) { - struct iommu *iommu; unsigned long flags, order, first_page, npages, n; + struct iommu *iommu; + struct page *page; void *ret; long entry; + int nid; size = IO_PAGE_ALIGN(size); order = get_order(size); @@ -139,10 +141,12 @@ static void *dma_4v_alloc_coherent(struct device *dev, size_t size, npages = size >> IO_PAGE_SHIFT; - first_page = __get_free_pages(gfp, order); - if (unlikely(first_page == 0UL)) + nid = dev->archdata.numa_node; + page = alloc_pages_node(nid, gfp, order); + if (unlikely(!page)) return NULL; + first_page = (unsigned long) page_address(page); memset((char *)first_page, 0, PAGE_SIZE << order); iommu = dev->archdata.iommu; @@ -899,6 +903,8 @@ static void __init pci_sun4v_pbm_init(struct pci_controller_info *p, pbm->next = pci_pbm_root; pci_pbm_root = pbm; + pbm->numa_node = of_node_to_nid(dp); + pbm->scan_bus = pci_sun4v_scan_bus; pbm->pci_ops = &sun4v_pci_ops; pbm->config_space_reg_bits = 12; @@ -913,6 +919,7 @@ static void __init pci_sun4v_pbm_init(struct pci_controller_info *p, pbm->name = dp->full_name; printk("%s: SUN4V PCI Bus Module\n", pbm->name); + printk("%s: On NUMA node %d\n", pbm->name, pbm->numa_node); pci_determine_mem_io_space(pbm); diff --git a/arch/sparc64/kernel/prom.c b/arch/sparc64/kernel/prom.c index 68964ddcde1..ed03a18d3b3 100644 --- a/arch/sparc64/kernel/prom.c +++ b/arch/sparc64/kernel/prom.c @@ -19,8 +19,8 @@ #include <linux/types.h> #include <linux/string.h> #include <linux/mm.h> -#include <linux/bootmem.h> #include <linux/module.h> +#include <linux/lmb.h> #include <asm/prom.h> #include <asm/of_device.h> @@ -122,16 +122,20 @@ int of_find_in_proplist(const char *list, const char *match, int len) } EXPORT_SYMBOL(of_find_in_proplist); -static unsigned int prom_early_allocated; +static unsigned int prom_early_allocated __initdata; static void * __init prom_early_alloc(unsigned long size) { + unsigned long paddr = lmb_alloc(size, SMP_CACHE_BYTES); void *ret; - ret = __alloc_bootmem(size, SMP_CACHE_BYTES, 0UL); - if (ret != NULL) - memset(ret, 0, size); + if (!paddr) { + prom_printf("prom_early_alloc(%lu) failed\n"); + prom_halt(); + } + ret = __va(paddr); + memset(ret, 0, size); prom_early_allocated += size; return ret; diff --git a/arch/sparc64/kernel/rtrap.S b/arch/sparc64/kernel/rtrap.S index 079d18a11d2..ecf6753b204 100644 --- a/arch/sparc64/kernel/rtrap.S +++ b/arch/sparc64/kernel/rtrap.S @@ -18,12 +18,6 @@ #define RTRAP_PSTATE_IRQOFF (PSTATE_RMO|PSTATE_PEF|PSTATE_PRIV) #define RTRAP_PSTATE_AG_IRQOFF (PSTATE_RMO|PSTATE_PEF|PSTATE_PRIV|PSTATE_AG) - /* Register %l6 keeps track of whether we are returning - * from a system call or not. It is cleared if we call - * do_notify_resume, and it must not be otherwise modified - * until we fully commit to returning to userspace. - */ - .text .align 32 __handle_softirq: @@ -56,14 +50,12 @@ __handle_user_windows: be,pt %xcc, __handle_user_windows_continue nop mov %l5, %o1 - mov %l6, %o2 add %sp, PTREGS_OFF, %o0 - mov %l0, %o3 + mov %l0, %o2 call do_notify_resume wrpr %g0, RTRAP_PSTATE, %pstate wrpr %g0, RTRAP_PSTATE_IRQOFF, %pstate - clr %l6 /* Signal delivery can modify pt_regs tstate, so we must * reload it. */ @@ -99,14 +91,12 @@ __handle_perfctrs: be,pt %xcc, __handle_perfctrs_continue sethi %hi(TSTATE_PEF), %o0 mov %l5, %o1 - mov %l6, %o2 add %sp, PTREGS_OFF, %o0 - mov %l0, %o3 + mov %l0, %o2 call do_notify_resume wrpr %g0, RTRAP_PSTATE, %pstate wrpr %g0, RTRAP_PSTATE_IRQOFF, %pstate - clr %l6 /* Signal delivery can modify pt_regs tstate, so we must * reload it. */ @@ -127,13 +117,11 @@ __handle_userfpu: __handle_signal: mov %l5, %o1 - mov %l6, %o2 add %sp, PTREGS_OFF, %o0 - mov %l0, %o3 + mov %l0, %o2 call do_notify_resume wrpr %g0, RTRAP_PSTATE, %pstate wrpr %g0, RTRAP_PSTATE_IRQOFF, %pstate - clr %l6 /* Signal delivery can modify pt_regs tstate, so we must * reload it. @@ -145,9 +133,8 @@ __handle_signal: andn %l1, %l4, %l1 .align 64 - .globl rtrap_irq, rtrap_clr_l6, rtrap, irqsz_patchme, rtrap_xcall + .globl rtrap_irq, rtrap, irqsz_patchme, rtrap_xcall rtrap_irq: -rtrap_clr_l6: clr %l6 rtrap: #ifndef CONFIG_SMP sethi %hi(per_cpu____cpu_data), %l0 diff --git a/arch/sparc64/kernel/sbus.c b/arch/sparc64/kernel/sbus.c index d1fb13ba02b..fa2827c4a3a 100644 --- a/arch/sparc64/kernel/sbus.c +++ b/arch/sparc64/kernel/sbus.c @@ -544,6 +544,7 @@ static void __init sbus_iommu_init(int __node, struct sbus_bus *sbus) sbus->ofdev.dev.archdata.iommu = iommu; sbus->ofdev.dev.archdata.stc = strbuf; + sbus->ofdev.dev.archdata.numa_node = -1; reg_base = regs + SYSIO_IOMMUREG_BASE; iommu->iommu_control = reg_base + IOMMU_CONTROL; @@ -575,7 +576,7 @@ static void __init sbus_iommu_init(int __node, struct sbus_bus *sbus) sbus->portid, regs); /* Setup for TSB_SIZE=7, TBW_SIZE=0, MMU_DE=1, MMU_EN=1 */ - if (iommu_table_init(iommu, IO_TSB_SIZE, MAP_BASE, 0xffffffff)) + if (iommu_table_init(iommu, IO_TSB_SIZE, MAP_BASE, 0xffffffff, -1)) goto fatal_memory_error; control = upa_readq(iommu->iommu_control); diff --git a/arch/sparc64/kernel/setup.c b/arch/sparc64/kernel/setup.c index 6acb4c51cfe..da5e6ee0c66 100644 --- a/arch/sparc64/kernel/setup.c +++ b/arch/sparc64/kernel/setup.c @@ -82,7 +82,7 @@ unsigned long cmdline_memory_size = 0; static struct console prom_early_console = { .name = "earlyprom", .write = prom_console_write, - .flags = CON_PRINTBUFFER | CON_BOOT, + .flags = CON_PRINTBUFFER | CON_BOOT | CON_ANYTIME, .index = -1, }; @@ -281,6 +281,7 @@ void __init setup_arch(char **cmdline_p) /* Initialize PROM console and command line. */ *cmdline_p = prom_getbootargs(); strcpy(boot_command_line, *cmdline_p); + parse_early_param(); boot_flags_init(*cmdline_p); register_console(&prom_early_console); diff --git a/arch/sparc64/kernel/signal.c b/arch/sparc64/kernel/signal.c index 1c47009eb5e..77a3e8592cb 100644 --- a/arch/sparc64/kernel/signal.c +++ b/arch/sparc64/kernel/signal.c @@ -510,15 +510,20 @@ static inline void syscall_restart(unsigned long orig_i0, struct pt_regs *regs, * want to handle. Thus you cannot kill init even with a SIGKILL even by * mistake. */ -static void do_signal(struct pt_regs *regs, unsigned long orig_i0, int restart_syscall) +static void do_signal(struct pt_regs *regs, unsigned long orig_i0) { - siginfo_t info; struct signal_deliver_cookie cookie; struct k_sigaction ka; - int signr; sigset_t *oldset; + siginfo_t info; + int signr, tt; - cookie.restart_syscall = restart_syscall; + tt = regs->magic & 0x1ff; + if (tt == 0x110 || tt == 0x111 || tt == 0x16d) { + regs->magic &= ~0x1ff; + cookie.restart_syscall = 1; + } else + cookie.restart_syscall = 0; cookie.orig_i0 = orig_i0; if (test_thread_flag(TIF_RESTORE_SIGMASK)) @@ -529,9 +534,8 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0, int restart_s #ifdef CONFIG_SPARC32_COMPAT if (test_thread_flag(TIF_32BIT)) { extern void do_signal32(sigset_t *, struct pt_regs *, - unsigned long, int); - do_signal32(oldset, regs, orig_i0, - cookie.restart_syscall); + struct signal_deliver_cookie *); + do_signal32(oldset, regs, &cookie); return; } #endif @@ -539,7 +543,7 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0, int restart_s signr = get_signal_to_deliver(&info, &ka, regs, &cookie); if (signr > 0) { if (cookie.restart_syscall) - syscall_restart(orig_i0, regs, &ka.sa); + syscall_restart(cookie.orig_i0, regs, &ka.sa); handle_signal(signr, &ka, &info, oldset, regs); /* a signal was successfully delivered; the saved @@ -576,11 +580,10 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0, int restart_s } } -void do_notify_resume(struct pt_regs *regs, unsigned long orig_i0, int restart_syscall, - unsigned long thread_info_flags) +void do_notify_resume(struct pt_regs *regs, unsigned long orig_i0, unsigned long thread_info_flags) { if (thread_info_flags & (_TIF_SIGPENDING | _TIF_RESTORE_SIGMASK)) - do_signal(regs, orig_i0, restart_syscall); + do_signal(regs, orig_i0); } void ptrace_signal_deliver(struct pt_regs *regs, void *cookie) diff --git a/arch/sparc64/kernel/signal32.c b/arch/sparc64/kernel/signal32.c index 74e0512f135..43cdec64d9c 100644 --- a/arch/sparc64/kernel/signal32.c +++ b/arch/sparc64/kernel/signal32.c @@ -982,20 +982,16 @@ static inline void syscall_restart32(unsigned long orig_i0, struct pt_regs *regs * mistake. */ void do_signal32(sigset_t *oldset, struct pt_regs * regs, - unsigned long orig_i0, int restart_syscall) + struct signal_deliver_cookie *cookie) { - siginfo_t info; - struct signal_deliver_cookie cookie; struct k_sigaction ka; + siginfo_t info; int signr; - cookie.restart_syscall = restart_syscall; - cookie.orig_i0 = orig_i0; - - signr = get_signal_to_deliver(&info, &ka, regs, &cookie); + signr = get_signal_to_deliver(&info, &ka, regs, cookie); if (signr > 0) { - if (cookie.restart_syscall) - syscall_restart32(orig_i0, regs, &ka.sa); + if (cookie->restart_syscall) + syscall_restart32(cookie->orig_i0, regs, &ka.sa); handle_signal32(signr, &ka, &info, oldset, regs); /* a signal was successfully delivered; the saved @@ -1007,16 +1003,16 @@ void do_signal32(sigset_t *oldset, struct pt_regs * regs, clear_thread_flag(TIF_RESTORE_SIGMASK); return; } - if (cookie.restart_syscall && + if (cookie->restart_syscall && (regs->u_regs[UREG_I0] == ERESTARTNOHAND || regs->u_regs[UREG_I0] == ERESTARTSYS || regs->u_regs[UREG_I0] == ERESTARTNOINTR)) { /* replay the system call when we are done */ - regs->u_regs[UREG_I0] = cookie.orig_i0; + regs->u_regs[UREG_I0] = cookie->orig_i0; regs->tpc -= 4; regs->tnpc -= 4; } - if (cookie.restart_syscall && + if (cookie->restart_syscall && regs->u_regs[UREG_I0] == ERESTART_RESTARTBLOCK) { regs->u_regs[UREG_G1] = __NR_restart_syscall; regs->tpc -= 4; diff --git a/arch/sparc64/kernel/smp.c b/arch/sparc64/kernel/smp.c index 59f020d69d4..524b8892094 100644 --- a/arch/sparc64/kernel/smp.c +++ b/arch/sparc64/kernel/smp.c @@ -20,7 +20,7 @@ #include <linux/cache.h> #include <linux/jiffies.h> #include <linux/profile.h> -#include <linux/bootmem.h> +#include <linux/lmb.h> #include <asm/head.h> #include <asm/ptrace.h> @@ -1431,7 +1431,7 @@ EXPORT_SYMBOL(__per_cpu_shift); void __init real_setup_per_cpu_areas(void) { - unsigned long goal, size, i; + unsigned long paddr, goal, size, i; char *ptr; /* Copy section for each CPU (we discard the original) */ @@ -1441,8 +1441,13 @@ void __init real_setup_per_cpu_areas(void) for (size = PAGE_SIZE; size < goal; size <<= 1UL) __per_cpu_shift++; - ptr = alloc_bootmem_pages(size * NR_CPUS); + paddr = lmb_alloc(size * NR_CPUS, PAGE_SIZE); + if (!paddr) { + prom_printf("Cannot allocate per-cpu memory.\n"); + prom_halt(); + } + ptr = __va(paddr); __per_cpu_base = ptr - __per_cpu_start; for (i = 0; i < NR_CPUS; i++, ptr += size) diff --git a/arch/sparc64/kernel/sparc64_ksyms.c b/arch/sparc64/kernel/sparc64_ksyms.c index 38736460b8d..66336590e83 100644 --- a/arch/sparc64/kernel/sparc64_ksyms.c +++ b/arch/sparc64/kernel/sparc64_ksyms.c @@ -68,8 +68,6 @@ extern void *__memscan_zero(void *, size_t); extern void *__memscan_generic(void *, int, size_t); extern int __memcmp(const void *, const void *, __kernel_size_t); extern __kernel_size_t strlen(const char *); -extern void linux_sparc_syscall(void); -extern void rtrap(void); extern void show_regs(struct pt_regs *); extern void syscall_trace(struct pt_regs *, int); extern void sys_sigsuspend(void); diff --git a/arch/sparc64/kernel/stacktrace.c b/arch/sparc64/kernel/stacktrace.c index 84d39e873e8..01b52f561af 100644 --- a/arch/sparc64/kernel/stacktrace.c +++ b/arch/sparc64/kernel/stacktrace.c @@ -20,6 +20,8 @@ void save_stack_trace(struct stack_trace *trace) thread_base = (unsigned long) tp; do { struct reg_window *rw; + struct pt_regs *regs; + unsigned long pc; /* Bogus frame pointer? */ if (fp < (thread_base + sizeof(struct thread_info)) || @@ -27,11 +29,19 @@ void save_stack_trace(struct stack_trace *trace) break; rw = (struct reg_window *) fp; + regs = (struct pt_regs *) (rw + 1); + + if ((regs->magic & ~0x1ff) == PT_REGS_MAGIC) { + pc = regs->tpc; + fp = regs->u_regs[UREG_I6] + STACK_BIAS; + } else { + pc = rw->ins[7]; + fp = rw->ins[6] + STACK_BIAS; + } + if (trace->skip > 0) trace->skip--; else - trace->entries[trace->nr_entries++] = rw->ins[7]; - - fp = rw->ins[6] + STACK_BIAS; + trace->entries[trace->nr_entries++] = pc; } while (trace->nr_entries < trace->max_entries); } diff --git a/arch/sparc64/kernel/sun4v_tlb_miss.S b/arch/sparc64/kernel/sun4v_tlb_miss.S index fd9430562e0..e1fbf8c7578 100644 --- a/arch/sparc64/kernel/sun4v_tlb_miss.S +++ b/arch/sparc64/kernel/sun4v_tlb_miss.S @@ -262,7 +262,7 @@ sun4v_iacc: mov %l5, %o2 call sun4v_insn_access_exception add %sp, PTREGS_OFF, %o0 - ba,a,pt %xcc, rtrap_clr_l6 + ba,a,pt %xcc, rtrap /* Instruction Access Exception, tl1. */ sun4v_iacc_tl1: @@ -278,7 +278,7 @@ sun4v_iacc_tl1: mov %l5, %o2 call sun4v_insn_access_exception_tl1 add %sp, PTREGS_OFF, %o0 - ba,a,pt %xcc, rtrap_clr_l6 + ba,a,pt %xcc, rtrap /* Data Access Exception, tl0. */ sun4v_dacc: @@ -294,7 +294,7 @@ sun4v_dacc: mov %l5, %o2 call sun4v_data_access_exception add %sp, PTREGS_OFF, %o0 - ba,a,pt %xcc, rtrap_clr_l6 + ba,a,pt %xcc, rtrap /* Data Access Exception, tl1. */ sun4v_dacc_tl1: @@ -310,7 +310,7 @@ sun4v_dacc_tl1: mov %l5, %o2 call sun4v_data_access_exception_tl1 add %sp, PTREGS_OFF, %o0 - ba,a,pt %xcc, rtrap_clr_l6 + ba,a,pt %xcc, rtrap /* Memory Address Unaligned. */ sun4v_mna: @@ -344,7 +344,7 @@ sun4v_mna: mov %l5, %o2 call sun4v_do_mna add %sp, PTREGS_OFF, %o0 - ba,a,pt %xcc, rtrap_clr_l6 + ba,a,pt %xcc, rtrap /* Privileged Action. */ sun4v_privact: @@ -352,7 +352,7 @@ sun4v_privact: rd %pc, %g7 call do_privact add %sp, PTREGS_OFF, %o0 - ba,a,pt %xcc, rtrap_clr_l6 + ba,a,pt %xcc, rtrap /* Unaligned ldd float, tl0. */ sun4v_lddfmna: @@ -368,7 +368,7 @@ sun4v_lddfmna: mov %l5, %o2 call handle_lddfmna add %sp, PTREGS_OFF, %o0 - ba,a,pt %xcc, rtrap_clr_l6 + ba,a,pt %xcc, rtrap /* Unaligned std float, tl0. */ sun4v_stdfmna: @@ -384,7 +384,7 @@ sun4v_stdfmna: mov %l5, %o2 call handle_stdfmna add %sp, PTREGS_OFF, %o0 - ba,a,pt %xcc, rtrap_clr_l6 + ba,a,pt %xcc, rtrap #define BRANCH_ALWAYS 0x10680000 #define NOP 0x01000000 diff --git a/arch/sparc64/kernel/sysfs.c b/arch/sparc64/kernel/sysfs.c index 52816c7be0b..e885034a6b7 100644 --- a/arch/sparc64/kernel/sysfs.c +++ b/arch/sparc64/kernel/sysfs.c @@ -273,10 +273,22 @@ static void __init check_mmu_stats(void) mmu_stats_supported = 1; } +static void register_nodes(void) +{ +#ifdef CONFIG_NUMA + int i; + + for (i = 0; i < MAX_NUMNODES; i++) + register_one_node(i); +#endif +} + static int __init topology_init(void) { int cpu; + register_nodes(); + check_mmu_stats(); register_cpu_notifier(&sysfs_cpu_nb); diff --git a/arch/sparc64/kernel/traps.c b/arch/sparc64/kernel/traps.c index 96da847023f..d9b8d46707d 100644 --- a/arch/sparc64/kernel/traps.c +++ b/arch/sparc64/kernel/traps.c @@ -2091,9 +2091,8 @@ static void user_instruction_dump(unsigned int __user *pc) void show_stack(struct task_struct *tsk, unsigned long *_ksp) { - unsigned long pc, fp, thread_base, ksp; + unsigned long fp, thread_base, ksp; struct thread_info *tp; - struct reg_window *rw; int count = 0; ksp = (unsigned long) _ksp; @@ -2117,15 +2116,27 @@ void show_stack(struct task_struct *tsk, unsigned long *_ksp) printk("\n"); #endif do { + struct reg_window *rw; + struct pt_regs *regs; + unsigned long pc; + /* Bogus frame pointer? */ if (fp < (thread_base + sizeof(struct thread_info)) || fp >= (thread_base + THREAD_SIZE)) break; rw = (struct reg_window *)fp; - pc = rw->ins[7]; + regs = (struct pt_regs *) (rw + 1); + + if ((regs->magic & ~0x1ff) == PT_REGS_MAGIC) { + pc = regs->tpc; + fp = regs->u_regs[UREG_I6] + STACK_BIAS; + } else { + pc = rw->ins[7]; + fp = rw->ins[6] + STACK_BIAS; + } + printk(" [%016lx] ", pc); print_symbol("%s\n", pc); - fp = rw->ins[6] + STACK_BIAS; } while (++count < 16); #ifndef CONFIG_KALLSYMS printk("\n"); diff --git a/arch/sparc64/kernel/tsb.S b/arch/sparc64/kernel/tsb.S index 10adb2fb8ff..c499214b501 100644 --- a/arch/sparc64/kernel/tsb.S +++ b/arch/sparc64/kernel/tsb.S @@ -275,7 +275,7 @@ sparc64_realfault_common: stx %l5, [%g6 + TI_FAULT_ADDR] ! Save fault address call do_sparc64_fault ! Call fault handler add %sp, PTREGS_OFF, %o0 ! Compute pt_regs arg - ba,pt %xcc, rtrap_clr_l6 ! Restore cpu state + ba,pt %xcc, rtrap ! Restore cpu state nop ! Delay slot (fill me) winfix_trampoline: diff --git a/arch/sparc64/kernel/winfixup.S b/arch/sparc64/kernel/winfixup.S index c4aa110a10e..a6b0863c27d 100644 --- a/arch/sparc64/kernel/winfixup.S +++ b/arch/sparc64/kernel/winfixup.S @@ -32,7 +32,7 @@ fill_fixup: rd %pc, %g7 call do_sparc64_fault add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap_clr_l6 + ba,pt %xcc, rtrap nop /* Be very careful about usage of the trap globals here. @@ -100,7 +100,7 @@ spill_fixup_dax: rd %pc, %g7 call do_sparc64_fault add %sp, PTREGS_OFF, %o0 - ba,a,pt %xcc, rtrap_clr_l6 + ba,a,pt %xcc, rtrap winfix_mna: andn %g3, 0x7f, %g3 @@ -122,12 +122,12 @@ fill_fixup_mna: mov %l4, %o2 call sun4v_do_mna mov %l5, %o1 - ba,a,pt %xcc, rtrap_clr_l6 + ba,a,pt %xcc, rtrap 1: mov %l4, %o1 mov %l5, %o2 call mem_address_unaligned nop - ba,a,pt %xcc, rtrap_clr_l6 + ba,a,pt %xcc, rtrap winfix_dax: andn %g3, 0x7f, %g3 @@ -150,7 +150,7 @@ fill_fixup_dax: add %sp, PTREGS_OFF, %o0 call sun4v_data_access_exception nop - ba,a,pt %xcc, rtrap_clr_l6 + ba,a,pt %xcc, rtrap 1: call spitfire_data_access_exception nop - ba,a,pt %xcc, rtrap_clr_l6 + ba,a,pt %xcc, rtrap diff --git a/arch/sparc64/mm/init.c b/arch/sparc64/mm/init.c index f37078d9640..177d8aaeec4 100644 --- a/arch/sparc64/mm/init.c +++ b/arch/sparc64/mm/init.c @@ -24,6 +24,8 @@ #include <linux/cache.h> #include <linux/sort.h> #include <linux/percpu.h> +#include <linux/lmb.h> +#include <linux/mmzone.h> #include <asm/head.h> #include <asm/system.h> @@ -72,9 +74,7 @@ extern struct tsb swapper_4m_tsb[KERNEL_TSB4M_NENTRIES]; #define MAX_BANKS 32 static struct linux_prom64_registers pavail[MAX_BANKS] __initdata; -static struct linux_prom64_registers pavail_rescan[MAX_BANKS] __initdata; static int pavail_ents __initdata; -static int pavail_rescan_ents __initdata; static int cmp_p64(const void *a, const void *b) { @@ -715,285 +715,684 @@ out: smp_new_mmu_context_version(); } -/* Find a free area for the bootmem map, avoiding the kernel image - * and the initial ramdisk. - */ -static unsigned long __init choose_bootmap_pfn(unsigned long start_pfn, - unsigned long end_pfn) +static int numa_enabled = 1; +static int numa_debug; + +static int __init early_numa(char *p) { - unsigned long avoid_start, avoid_end, bootmap_size; - int i; + if (!p) + return 0; + + if (strstr(p, "off")) + numa_enabled = 0; + + if (strstr(p, "debug")) + numa_debug = 1; + + return 0; +} +early_param("numa", early_numa); - bootmap_size = bootmem_bootmap_pages(end_pfn - start_pfn); - bootmap_size <<= PAGE_SHIFT; +#define numadbg(f, a...) \ +do { if (numa_debug) \ + printk(KERN_INFO f, ## a); \ +} while (0) - avoid_start = avoid_end = 0; +static void __init find_ramdisk(unsigned long phys_base) +{ #ifdef CONFIG_BLK_DEV_INITRD - avoid_start = initrd_start; - avoid_end = PAGE_ALIGN(initrd_end); + if (sparc_ramdisk_image || sparc_ramdisk_image64) { + unsigned long ramdisk_image; + + /* Older versions of the bootloader only supported a + * 32-bit physical address for the ramdisk image + * location, stored at sparc_ramdisk_image. Newer + * SILO versions set sparc_ramdisk_image to zero and + * provide a full 64-bit physical address at + * sparc_ramdisk_image64. + */ + ramdisk_image = sparc_ramdisk_image; + if (!ramdisk_image) + ramdisk_image = sparc_ramdisk_image64; + + /* Another bootloader quirk. The bootloader normalizes + * the physical address to KERNBASE, so we have to + * factor that back out and add in the lowest valid + * physical page address to get the true physical address. + */ + ramdisk_image -= KERNBASE; + ramdisk_image += phys_base; + + numadbg("Found ramdisk at physical address 0x%lx, size %u\n", + ramdisk_image, sparc_ramdisk_size); + + initrd_start = ramdisk_image; + initrd_end = ramdisk_image + sparc_ramdisk_size; + + lmb_reserve(initrd_start, initrd_end); + } #endif +} - for (i = 0; i < pavail_ents; i++) { - unsigned long start, end; +struct node_mem_mask { + unsigned long mask; + unsigned long val; + unsigned long bootmem_paddr; +}; +static struct node_mem_mask node_masks[MAX_NUMNODES]; +static int num_node_masks; - start = pavail[i].phys_addr; - end = start + pavail[i].reg_size; +int numa_cpu_lookup_table[NR_CPUS]; +cpumask_t numa_cpumask_lookup_table[MAX_NUMNODES]; - while (start < end) { - if (start >= kern_base && - start < PAGE_ALIGN(kern_base + kern_size)) { - start = PAGE_ALIGN(kern_base + kern_size); - continue; - } - if (start >= avoid_start && start < avoid_end) { - start = avoid_end; - continue; - } +#ifdef CONFIG_NEED_MULTIPLE_NODES +static bootmem_data_t plat_node_bdata[MAX_NUMNODES]; - if ((end - start) < bootmap_size) - break; +struct mdesc_mblock { + u64 base; + u64 size; + u64 offset; /* RA-to-PA */ +}; +static struct mdesc_mblock *mblocks; +static int num_mblocks; - if (start < kern_base && - (start + bootmap_size) > kern_base) { - start = PAGE_ALIGN(kern_base + kern_size); - continue; - } +static unsigned long ra_to_pa(unsigned long addr) +{ + int i; - if (start < avoid_start && - (start + bootmap_size) > avoid_start) { - start = avoid_end; - continue; - } + for (i = 0; i < num_mblocks; i++) { + struct mdesc_mblock *m = &mblocks[i]; - /* OK, it doesn't overlap anything, use it. */ - return start >> PAGE_SHIFT; + if (addr >= m->base && + addr < (m->base + m->size)) { + addr += m->offset; + break; } } - - prom_printf("Cannot find free area for bootmap, aborting.\n"); - prom_halt(); + return addr; } -static void __init trim_pavail(unsigned long *cur_size_p, - unsigned long *end_of_phys_p) +static int find_node(unsigned long addr) { - unsigned long to_trim = *cur_size_p - cmdline_memory_size; - unsigned long avoid_start, avoid_end; int i; - to_trim = PAGE_ALIGN(to_trim); + addr = ra_to_pa(addr); + for (i = 0; i < num_node_masks; i++) { + struct node_mem_mask *p = &node_masks[i]; - avoid_start = avoid_end = 0; -#ifdef CONFIG_BLK_DEV_INITRD - avoid_start = initrd_start; - avoid_end = PAGE_ALIGN(initrd_end); + if ((addr & p->mask) == p->val) + return i; + } + return -1; +} + +static unsigned long nid_range(unsigned long start, unsigned long end, + int *nid) +{ + *nid = find_node(start); + start += PAGE_SIZE; + while (start < end) { + int n = find_node(start); + + if (n != *nid) + break; + start += PAGE_SIZE; + } + + return start; +} +#else +static unsigned long nid_range(unsigned long start, unsigned long end, + int *nid) +{ + *nid = 0; + return end; +} #endif - /* Trim some pavail[] entries in order to satisfy the - * requested "mem=xxx" kernel command line specification. - * - * We must not trim off the kernel image area nor the - * initial ramdisk range (if any). Also, we must not trim - * any pavail[] entry down to zero in order to preserve - * the invariant that all pavail[] entries have a non-zero - * size which is assumed by all of the code in here. - */ - for (i = 0; i < pavail_ents; i++) { - unsigned long start, end, kern_end; - unsigned long trim_low, trim_high, n; +/* This must be invoked after performing all of the necessary + * add_active_range() calls for 'nid'. We need to be able to get + * correct data from get_pfn_range_for_nid(). + */ +static void __init allocate_node_data(int nid) +{ + unsigned long paddr, num_pages, start_pfn, end_pfn; + struct pglist_data *p; + +#ifdef CONFIG_NEED_MULTIPLE_NODES + paddr = lmb_alloc_nid(sizeof(struct pglist_data), + SMP_CACHE_BYTES, nid, nid_range); + if (!paddr) { + prom_printf("Cannot allocate pglist_data for nid[%d]\n", nid); + prom_halt(); + } + NODE_DATA(nid) = __va(paddr); + memset(NODE_DATA(nid), 0, sizeof(struct pglist_data)); - kern_end = PAGE_ALIGN(kern_base + kern_size); + NODE_DATA(nid)->bdata = &plat_node_bdata[nid]; +#endif - trim_low = start = pavail[i].phys_addr; - trim_high = end = start + pavail[i].reg_size; + p = NODE_DATA(nid); - if (kern_base >= start && - kern_base < end) { - trim_low = kern_base; - if (kern_end >= end) - continue; - } - if (kern_end >= start && - kern_end < end) { - trim_high = kern_end; - } - if (avoid_start && - avoid_start >= start && - avoid_start < end) { - if (trim_low > avoid_start) - trim_low = avoid_start; - if (avoid_end >= end) - continue; - } - if (avoid_end && - avoid_end >= start && - avoid_end < end) { - if (trim_high < avoid_end) - trim_high = avoid_end; + get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); + p->node_start_pfn = start_pfn; + p->node_spanned_pages = end_pfn - start_pfn; + + if (p->node_spanned_pages) { + num_pages = bootmem_bootmap_pages(p->node_spanned_pages); + + paddr = lmb_alloc_nid(num_pages << PAGE_SHIFT, PAGE_SIZE, nid, + nid_range); + if (!paddr) { + prom_printf("Cannot allocate bootmap for nid[%d]\n", + nid); + prom_halt(); } + node_masks[nid].bootmem_paddr = paddr; + } +} + +static void init_node_masks_nonnuma(void) +{ + int i; + + numadbg("Initializing tables for non-numa.\n"); + + node_masks[0].mask = node_masks[0].val = 0; + num_node_masks = 1; + + for (i = 0; i < NR_CPUS; i++) + numa_cpu_lookup_table[i] = 0; + + numa_cpumask_lookup_table[0] = CPU_MASK_ALL; +} + +#ifdef CONFIG_NEED_MULTIPLE_NODES +struct pglist_data *node_data[MAX_NUMNODES]; + +EXPORT_SYMBOL(numa_cpu_lookup_table); +EXPORT_SYMBOL(numa_cpumask_lookup_table); +EXPORT_SYMBOL(node_data); + +struct mdesc_mlgroup { + u64 node; + u64 latency; + u64 match; + u64 mask; +}; +static struct mdesc_mlgroup *mlgroups; +static int num_mlgroups; + +static int scan_pio_for_cfg_handle(struct mdesc_handle *md, u64 pio, + u32 cfg_handle) +{ + u64 arc; - if (trim_high <= trim_low) + mdesc_for_each_arc(arc, md, pio, MDESC_ARC_TYPE_FWD) { + u64 target = mdesc_arc_target(md, arc); + const u64 *val; + + val = mdesc_get_property(md, target, + "cfg-handle", NULL); + if (val && *val == cfg_handle) + return 0; + } + return -ENODEV; +} + +static int scan_arcs_for_cfg_handle(struct mdesc_handle *md, u64 grp, + u32 cfg_handle) +{ + u64 arc, candidate, best_latency = ~(u64)0; + + candidate = MDESC_NODE_NULL; + mdesc_for_each_arc(arc, md, grp, MDESC_ARC_TYPE_FWD) { + u64 target = mdesc_arc_target(md, arc); + const char *name = mdesc_node_name(md, target); + const u64 *val; + + if (strcmp(name, "pio-latency-group")) continue; - if (trim_low == start && trim_high == end) { - /* Whole chunk is available for trimming. - * Trim all except one page, in order to keep - * entry non-empty. - */ - n = (end - start) - PAGE_SIZE; - if (n > to_trim) - n = to_trim; - - if (n) { - pavail[i].phys_addr += n; - pavail[i].reg_size -= n; - to_trim -= n; - } - } else { - n = (trim_low - start); - if (n > to_trim) - n = to_trim; - - if (n) { - pavail[i].phys_addr += n; - pavail[i].reg_size -= n; - to_trim -= n; - } - if (to_trim) { - n = end - trim_high; - if (n > to_trim) - n = to_trim; - if (n) { - pavail[i].reg_size -= n; - to_trim -= n; - } - } + val = mdesc_get_property(md, target, "latency", NULL); + if (!val) + continue; + + if (*val < best_latency) { + candidate = target; + best_latency = *val; } + } + + if (candidate == MDESC_NODE_NULL) + return -ENODEV; + + return scan_pio_for_cfg_handle(md, candidate, cfg_handle); +} + +int of_node_to_nid(struct device_node *dp) +{ + const struct linux_prom64_registers *regs; + struct mdesc_handle *md; + u32 cfg_handle; + int count, nid; + u64 grp; - if (!to_trim) + if (!mlgroups) + return -1; + + regs = of_get_property(dp, "reg", NULL); + if (!regs) + return -1; + + cfg_handle = (regs->phys_addr >> 32UL) & 0x0fffffff; + + md = mdesc_grab(); + + count = 0; + nid = -1; + mdesc_for_each_node_by_name(md, grp, "group") { + if (!scan_arcs_for_cfg_handle(md, grp, cfg_handle)) { + nid = count; break; + } + count++; } - /* Recalculate. */ - *cur_size_p = 0UL; - for (i = 0; i < pavail_ents; i++) { - *end_of_phys_p = pavail[i].phys_addr + - pavail[i].reg_size; - *cur_size_p += pavail[i].reg_size; - } + mdesc_release(md); + + return nid; } -/* About pages_avail, this is the value we will use to calculate - * the zholes_size[] argument given to free_area_init_node(). The - * page allocator uses this to calculate nr_kernel_pages, - * nr_all_pages and zone->present_pages. On NUMA it is used - * to calculate zone->min_unmapped_pages and zone->min_slab_pages. - * - * So this number should really be set to what the page allocator - * actually ends up with. This means: - * 1) It should include bootmem map pages, we'll release those. - * 2) It should not include the kernel image, except for the - * __init sections which we will also release. - * 3) It should include the initrd image, since we'll release - * that too. - */ -static unsigned long __init bootmem_init(unsigned long *pages_avail, - unsigned long phys_base) +static void add_node_ranges(void) { - unsigned long bootmap_size, end_pfn; - unsigned long end_of_phys_memory = 0UL; - unsigned long bootmap_pfn, bytes_avail, size; int i; - bytes_avail = 0UL; - for (i = 0; i < pavail_ents; i++) { - end_of_phys_memory = pavail[i].phys_addr + - pavail[i].reg_size; - bytes_avail += pavail[i].reg_size; + for (i = 0; i < lmb.memory.cnt; i++) { + unsigned long size = lmb_size_bytes(&lmb.memory, i); + unsigned long start, end; + + start = lmb.memory.region[i].base; + end = start + size; + while (start < end) { + unsigned long this_end; + int nid; + + this_end = nid_range(start, end, &nid); + + numadbg("Adding active range nid[%d] " + "start[%lx] end[%lx]\n", + nid, start, this_end); + + add_active_range(nid, + start >> PAGE_SHIFT, + this_end >> PAGE_SHIFT); + + start = this_end; + } } +} - /* Determine the location of the initial ramdisk before trying - * to honor the "mem=xxx" command line argument. We must know - * where the kernel image and the ramdisk image are so that we - * do not trim those two areas from the physical memory map. - */ +static int __init grab_mlgroups(struct mdesc_handle *md) +{ + unsigned long paddr; + int count = 0; + u64 node; + + mdesc_for_each_node_by_name(md, node, "memory-latency-group") + count++; + if (!count) + return -ENOENT; + + paddr = lmb_alloc(count * sizeof(struct mdesc_mlgroup), + SMP_CACHE_BYTES); + if (!paddr) + return -ENOMEM; + + mlgroups = __va(paddr); + num_mlgroups = count; + + count = 0; + mdesc_for_each_node_by_name(md, node, "memory-latency-group") { + struct mdesc_mlgroup *m = &mlgroups[count++]; + const u64 *val; + + m->node = node; + + val = mdesc_get_property(md, node, "latency", NULL); + m->latency = *val; + val = mdesc_get_property(md, node, "address-match", NULL); + m->match = *val; + val = mdesc_get_property(md, node, "address-mask", NULL); + m->mask = *val; + + numadbg("MLGROUP[%d]: node[%lx] latency[%lx] " + "match[%lx] mask[%lx]\n", + count - 1, m->node, m->latency, m->match, m->mask); + } -#ifdef CONFIG_BLK_DEV_INITRD - /* Now have to check initial ramdisk, so that bootmap does not overwrite it */ - if (sparc_ramdisk_image || sparc_ramdisk_image64) { - unsigned long ramdisk_image = sparc_ramdisk_image ? - sparc_ramdisk_image : sparc_ramdisk_image64; - ramdisk_image -= KERNBASE; - initrd_start = ramdisk_image + phys_base; - initrd_end = initrd_start + sparc_ramdisk_size; - if (initrd_end > end_of_phys_memory) { - printk(KERN_CRIT "initrd extends beyond end of memory " - "(0x%016lx > 0x%016lx)\ndisabling initrd\n", - initrd_end, end_of_phys_memory); - initrd_start = 0; - initrd_end = 0; + return 0; +} + +static int __init grab_mblocks(struct mdesc_handle *md) +{ + unsigned long paddr; + int count = 0; + u64 node; + + mdesc_for_each_node_by_name(md, node, "mblock") + count++; + if (!count) + return -ENOENT; + + paddr = lmb_alloc(count * sizeof(struct mdesc_mblock), + SMP_CACHE_BYTES); + if (!paddr) + return -ENOMEM; + + mblocks = __va(paddr); + num_mblocks = count; + + count = 0; + mdesc_for_each_node_by_name(md, node, "mblock") { + struct mdesc_mblock *m = &mblocks[count++]; + const u64 *val; + + val = mdesc_get_property(md, node, "base", NULL); + m->base = *val; + val = mdesc_get_property(md, node, "size", NULL); + m->size = *val; + val = mdesc_get_property(md, node, + "address-congruence-offset", NULL); + m->offset = *val; + + numadbg("MBLOCK[%d]: base[%lx] size[%lx] offset[%lx]\n", + count - 1, m->base, m->size, m->offset); + } + + return 0; +} + +static void __init numa_parse_mdesc_group_cpus(struct mdesc_handle *md, + u64 grp, cpumask_t *mask) +{ + u64 arc; + + cpus_clear(*mask); + + mdesc_for_each_arc(arc, md, grp, MDESC_ARC_TYPE_BACK) { + u64 target = mdesc_arc_target(md, arc); + const char *name = mdesc_node_name(md, target); + const u64 *id; + + if (strcmp(name, "cpu")) + continue; + id = mdesc_get_property(md, target, "id", NULL); + if (*id < NR_CPUS) + cpu_set(*id, *mask); + } +} + +static struct mdesc_mlgroup * __init find_mlgroup(u64 node) +{ + int i; + + for (i = 0; i < num_mlgroups; i++) { + struct mdesc_mlgroup *m = &mlgroups[i]; + if (m->node == node) + return m; + } + return NULL; +} + +static int __init numa_attach_mlgroup(struct mdesc_handle *md, u64 grp, + int index) +{ + struct mdesc_mlgroup *candidate = NULL; + u64 arc, best_latency = ~(u64)0; + struct node_mem_mask *n; + + mdesc_for_each_arc(arc, md, grp, MDESC_ARC_TYPE_FWD) { + u64 target = mdesc_arc_target(md, arc); + struct mdesc_mlgroup *m = find_mlgroup(target); + if (!m) + continue; + if (m->latency < best_latency) { + candidate = m; + best_latency = m->latency; } } -#endif + if (!candidate) + return -ENOENT; + + if (num_node_masks != index) { + printk(KERN_ERR "Inconsistent NUMA state, " + "index[%d] != num_node_masks[%d]\n", + index, num_node_masks); + return -EINVAL; + } - if (cmdline_memory_size && - bytes_avail > cmdline_memory_size) - trim_pavail(&bytes_avail, - &end_of_phys_memory); + n = &node_masks[num_node_masks++]; - *pages_avail = bytes_avail >> PAGE_SHIFT; + n->mask = candidate->mask; + n->val = candidate->match; - end_pfn = end_of_phys_memory >> PAGE_SHIFT; + numadbg("NUMA NODE[%d]: mask[%lx] val[%lx] (latency[%lx])\n", + index, n->mask, n->val, candidate->latency); - /* Initialize the boot-time allocator. */ - max_pfn = max_low_pfn = end_pfn; - min_low_pfn = (phys_base >> PAGE_SHIFT); + return 0; +} + +static int __init numa_parse_mdesc_group(struct mdesc_handle *md, u64 grp, + int index) +{ + cpumask_t mask; + int cpu; - bootmap_pfn = choose_bootmap_pfn(min_low_pfn, end_pfn); + numa_parse_mdesc_group_cpus(md, grp, &mask); - bootmap_size = init_bootmem_node(NODE_DATA(0), bootmap_pfn, - min_low_pfn, end_pfn); + for_each_cpu_mask(cpu, mask) + numa_cpu_lookup_table[cpu] = index; + numa_cpumask_lookup_table[index] = mask; - /* Now register the available physical memory with the - * allocator. - */ - for (i = 0; i < pavail_ents; i++) - free_bootmem(pavail[i].phys_addr, pavail[i].reg_size); + if (numa_debug) { + printk(KERN_INFO "NUMA GROUP[%d]: cpus [ ", index); + for_each_cpu_mask(cpu, mask) + printk("%d ", cpu); + printk("]\n"); + } -#ifdef CONFIG_BLK_DEV_INITRD - if (initrd_start) { - size = initrd_end - initrd_start; + return numa_attach_mlgroup(md, grp, index); +} + +static int __init numa_parse_mdesc(void) +{ + struct mdesc_handle *md = mdesc_grab(); + int i, err, count; + u64 node; + + node = mdesc_node_by_name(md, MDESC_NODE_NULL, "latency-groups"); + if (node == MDESC_NODE_NULL) { + mdesc_release(md); + return -ENOENT; + } + + err = grab_mblocks(md); + if (err < 0) + goto out; + + err = grab_mlgroups(md); + if (err < 0) + goto out; + + count = 0; + mdesc_for_each_node_by_name(md, node, "group") { + err = numa_parse_mdesc_group(md, node, count); + if (err < 0) + break; + count++; + } + + add_node_ranges(); + + for (i = 0; i < num_node_masks; i++) { + allocate_node_data(i); + node_set_online(i); + } + + err = 0; +out: + mdesc_release(md); + return err; +} + +static int __init numa_parse_sun4u(void) +{ + return -1; +} - /* Reserve the initrd image area. */ - reserve_bootmem(initrd_start, size, BOOTMEM_DEFAULT); +static int __init bootmem_init_numa(void) +{ + int err = -1; - initrd_start += PAGE_OFFSET; - initrd_end += PAGE_OFFSET; + numadbg("bootmem_init_numa()\n"); + + if (numa_enabled) { + if (tlb_type == hypervisor) + err = numa_parse_mdesc(); + else + err = numa_parse_sun4u(); } + return err; +} + +#else + +static int bootmem_init_numa(void) +{ + return -1; +} + #endif - /* Reserve the kernel text/data/bss. */ - reserve_bootmem(kern_base, kern_size, BOOTMEM_DEFAULT); - *pages_avail -= PAGE_ALIGN(kern_size) >> PAGE_SHIFT; - - /* Add back in the initmem pages. */ - size = ((unsigned long)(__init_end) & PAGE_MASK) - - PAGE_ALIGN((unsigned long)__init_begin); - *pages_avail += size >> PAGE_SHIFT; - - /* Reserve the bootmem map. We do not account for it - * in pages_avail because we will release that memory - * in free_all_bootmem. - */ - size = bootmap_size; - reserve_bootmem((bootmap_pfn << PAGE_SHIFT), size, BOOTMEM_DEFAULT); - for (i = 0; i < pavail_ents; i++) { +static void __init bootmem_init_nonnuma(void) +{ + unsigned long top_of_ram = lmb_end_of_DRAM(); + unsigned long total_ram = lmb_phys_mem_size(); + unsigned int i; + + numadbg("bootmem_init_nonnuma()\n"); + + printk(KERN_INFO "Top of RAM: 0x%lx, Total RAM: 0x%lx\n", + top_of_ram, total_ram); + printk(KERN_INFO "Memory hole size: %ldMB\n", + (top_of_ram - total_ram) >> 20); + + init_node_masks_nonnuma(); + + for (i = 0; i < lmb.memory.cnt; i++) { + unsigned long size = lmb_size_bytes(&lmb.memory, i); unsigned long start_pfn, end_pfn; - start_pfn = pavail[i].phys_addr >> PAGE_SHIFT; - end_pfn = (start_pfn + (pavail[i].reg_size >> PAGE_SHIFT)); - memory_present(0, start_pfn, end_pfn); + if (!size) + continue; + + start_pfn = lmb.memory.region[i].base >> PAGE_SHIFT; + end_pfn = start_pfn + lmb_size_pages(&lmb.memory, i); + add_active_range(0, start_pfn, end_pfn); + } + + allocate_node_data(0); + + node_set_online(0); +} + +static void __init reserve_range_in_node(int nid, unsigned long start, + unsigned long end) +{ + numadbg(" reserve_range_in_node(nid[%d],start[%lx],end[%lx]\n", + nid, start, end); + while (start < end) { + unsigned long this_end; + int n; + + this_end = nid_range(start, end, &n); + if (n == nid) { + numadbg(" MATCH reserving range [%lx:%lx]\n", + start, this_end); + reserve_bootmem_node(NODE_DATA(nid), start, + (this_end - start), BOOTMEM_DEFAULT); + } else + numadbg(" NO MATCH, advancing start to %lx\n", + this_end); + + start = this_end; + } +} + +static void __init trim_reserved_in_node(int nid) +{ + int i; + + numadbg(" trim_reserved_in_node(%d)\n", nid); + + for (i = 0; i < lmb.reserved.cnt; i++) { + unsigned long start = lmb.reserved.region[i].base; + unsigned long size = lmb_size_bytes(&lmb.reserved, i); + unsigned long end = start + size; + + reserve_range_in_node(nid, start, end); + } +} + +static void __init bootmem_init_one_node(int nid) +{ + struct pglist_data *p; + + numadbg("bootmem_init_one_node(%d)\n", nid); + + p = NODE_DATA(nid); + + if (p->node_spanned_pages) { + unsigned long paddr = node_masks[nid].bootmem_paddr; + unsigned long end_pfn; + + end_pfn = p->node_start_pfn + p->node_spanned_pages; + + numadbg(" init_bootmem_node(%d, %lx, %lx, %lx)\n", + nid, paddr >> PAGE_SHIFT, p->node_start_pfn, end_pfn); + + init_bootmem_node(p, paddr >> PAGE_SHIFT, + p->node_start_pfn, end_pfn); + + numadbg(" free_bootmem_with_active_regions(%d, %lx)\n", + nid, end_pfn); + free_bootmem_with_active_regions(nid, end_pfn); + + trim_reserved_in_node(nid); + + numadbg(" sparse_memory_present_with_active_regions(%d)\n", + nid); + sparse_memory_present_with_active_regions(nid); } +} + +static unsigned long __init bootmem_init(unsigned long phys_base) +{ + unsigned long end_pfn; + int nid; + + end_pfn = lmb_end_of_DRAM() >> PAGE_SHIFT; + max_pfn = max_low_pfn = end_pfn; + min_low_pfn = (phys_base >> PAGE_SHIFT); + + if (bootmem_init_numa() < 0) + bootmem_init_nonnuma(); + + /* XXX cpu notifier XXX */ + + for_each_online_node(nid) + bootmem_init_one_node(nid); sparse_init(); @@ -1289,7 +1688,7 @@ void __init setup_per_cpu_areas(void) void __init paging_init(void) { - unsigned long end_pfn, pages_avail, shift, phys_base; + unsigned long end_pfn, shift, phys_base; unsigned long real_end, i; /* These build time checkes make sure that the dcache_dirty_cpu() @@ -1330,12 +1729,26 @@ void __init paging_init(void) sun4v_ktsb_init(); } + lmb_init(); + /* Find available physical memory... */ read_obp_memory("available", &pavail[0], &pavail_ents); phys_base = 0xffffffffffffffffUL; - for (i = 0; i < pavail_ents; i++) + for (i = 0; i < pavail_ents; i++) { phys_base = min(phys_base, pavail[i].phys_addr); + lmb_add(pavail[i].phys_addr, pavail[i].reg_size); + } + + lmb_reserve(kern_base, kern_size); + + find_ramdisk(phys_base); + + if (cmdline_memory_size) + lmb_enforce_memory_limit(phys_base + cmdline_memory_size); + + lmb_analyze(); + lmb_dump_all(); set_bit(0, mmu_context_bmap); @@ -1371,14 +1784,10 @@ void __init paging_init(void) if (tlb_type == hypervisor) sun4v_ktsb_register(); - /* Setup bootmem... */ - pages_avail = 0; - last_valid_pfn = end_pfn = bootmem_init(&pages_avail, phys_base); - - max_mapnr = last_valid_pfn; - - kernel_physical_mapping_init(); - + /* We must setup the per-cpu areas before we pull in the + * PROM and the MDESC. The code there fills in cpu and + * other information into per-cpu data structures. + */ real_setup_per_cpu_areas(); prom_build_devicetree(); @@ -1386,20 +1795,22 @@ void __init paging_init(void) if (tlb_type == hypervisor) sun4v_mdesc_init(); + /* Setup bootmem... */ + last_valid_pfn = end_pfn = bootmem_init(phys_base); + +#ifndef CONFIG_NEED_MULTIPLE_NODES + max_mapnr = last_valid_pfn; +#endif + kernel_physical_mapping_init(); + { - unsigned long zones_size[MAX_NR_ZONES]; - unsigned long zholes_size[MAX_NR_ZONES]; - int znum; + unsigned long max_zone_pfns[MAX_NR_ZONES]; - for (znum = 0; znum < MAX_NR_ZONES; znum++) - zones_size[znum] = zholes_size[znum] = 0; + memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); - zones_size[ZONE_NORMAL] = end_pfn; - zholes_size[ZONE_NORMAL] = end_pfn - pages_avail; + max_zone_pfns[ZONE_NORMAL] = end_pfn; - free_area_init_node(0, &contig_page_data, zones_size, - __pa(PAGE_OFFSET) >> PAGE_SHIFT, - zholes_size); + free_area_init_nodes(max_zone_pfns); } printk("Booting Linux...\n"); @@ -1408,21 +1819,52 @@ void __init paging_init(void) cpu_probe(); } -static void __init taint_real_pages(void) +int __init page_in_phys_avail(unsigned long paddr) +{ + int i; + + paddr &= PAGE_MASK; + + for (i = 0; i < pavail_ents; i++) { + unsigned long start, end; + + start = pavail[i].phys_addr; + end = start + pavail[i].reg_size; + + if (paddr >= start && paddr < end) + return 1; + } + if (paddr >= kern_base && paddr < (kern_base + kern_size)) + return 1; +#ifdef CONFIG_BLK_DEV_INITRD + if (paddr >= __pa(initrd_start) && + paddr < __pa(PAGE_ALIGN(initrd_end))) + return 1; +#endif + + return 0; +} + +static struct linux_prom64_registers pavail_rescan[MAX_BANKS] __initdata; +static int pavail_rescan_ents __initdata; + +/* Certain OBP calls, such as fetching "available" properties, can + * claim physical memory. So, along with initializing the valid + * address bitmap, what we do here is refetch the physical available + * memory list again, and make sure it provides at least as much + * memory as 'pavail' does. + */ +static void setup_valid_addr_bitmap_from_pavail(void) { int i; read_obp_memory("available", &pavail_rescan[0], &pavail_rescan_ents); - /* Find changes discovered in the physmem available rescan and - * reserve the lost portions in the bootmem maps. - */ for (i = 0; i < pavail_ents; i++) { unsigned long old_start, old_end; old_start = pavail[i].phys_addr; - old_end = old_start + - pavail[i].reg_size; + old_end = old_start + pavail[i].reg_size; while (old_start < old_end) { int n; @@ -1440,7 +1882,16 @@ static void __init taint_real_pages(void) goto do_next_page; } } - reserve_bootmem(old_start, PAGE_SIZE, BOOTMEM_DEFAULT); + + prom_printf("mem_init: Lost memory in pavail\n"); + prom_printf("mem_init: OLD start[%lx] size[%lx]\n", + pavail[i].phys_addr, + pavail[i].reg_size); + prom_printf("mem_init: NEW start[%lx] size[%lx]\n", + pavail_rescan[i].phys_addr, + pavail_rescan[i].reg_size); + prom_printf("mem_init: Cannot continue, aborting.\n"); + prom_halt(); do_next_page: old_start += PAGE_SIZE; @@ -1448,32 +1899,6 @@ static void __init taint_real_pages(void) } } -int __init page_in_phys_avail(unsigned long paddr) -{ - int i; - - paddr &= PAGE_MASK; - - for (i = 0; i < pavail_rescan_ents; i++) { - unsigned long start, end; - - start = pavail_rescan[i].phys_addr; - end = start + pavail_rescan[i].reg_size; - - if (paddr >= start && paddr < end) - return 1; - } - if (paddr >= kern_base && paddr < (kern_base + kern_size)) - return 1; -#ifdef CONFIG_BLK_DEV_INITRD - if (paddr >= __pa(initrd_start) && - paddr < __pa(PAGE_ALIGN(initrd_end))) - return 1; -#endif - - return 0; -} - void __init mem_init(void) { unsigned long codepages, datapages, initpages; @@ -1496,14 +1921,26 @@ void __init mem_init(void) addr += PAGE_SIZE; } - taint_real_pages(); + setup_valid_addr_bitmap_from_pavail(); high_memory = __va(last_valid_pfn << PAGE_SHIFT); +#ifdef CONFIG_NEED_MULTIPLE_NODES + for_each_online_node(i) { + if (NODE_DATA(i)->node_spanned_pages != 0) { + totalram_pages += + free_all_bootmem_node(NODE_DATA(i)); + } + } +#else + totalram_pages = free_all_bootmem(); +#endif + /* We subtract one to account for the mem_map_zero page * allocated below. */ - totalram_pages = num_physpages = free_all_bootmem() - 1; + totalram_pages -= 1; + num_physpages = totalram_pages; /* * Set up the zero page, mark it reserved, so that page count diff --git a/arch/sparc64/mm/tsb.c b/arch/sparc64/mm/tsb.c index a3e6e4b635b..fe70c8a557b 100644 --- a/arch/sparc64/mm/tsb.c +++ b/arch/sparc64/mm/tsb.c @@ -321,7 +321,8 @@ retry_tsb_alloc: if (new_size > (PAGE_SIZE * 2)) gfp_flags = __GFP_NOWARN | __GFP_NORETRY; - new_tsb = kmem_cache_alloc(tsb_caches[new_cache_index], gfp_flags); + new_tsb = kmem_cache_alloc_node(tsb_caches[new_cache_index], + gfp_flags, numa_node_id()); if (unlikely(!new_tsb)) { /* Not being able to fork due to a high-order TSB * allocation failure is very bad behavior. Just back diff --git a/arch/sparc64/mm/ultra.S b/arch/sparc64/mm/ultra.S index 2865c105b6a..e686a67561a 100644 --- a/arch/sparc64/mm/ultra.S +++ b/arch/sparc64/mm/ultra.S @@ -476,7 +476,6 @@ xcall_sync_tick: #endif call smp_synchronize_tick_client nop - clr %l6 b rtrap_xcall ldx [%sp + PTREGS_OFF + PT_V9_TSTATE], %l1 @@ -511,7 +510,6 @@ xcall_report_regs: #endif call __show_regs add %sp, PTREGS_OFF, %o0 - clr %l6 /* Has to be a non-v9 branch due to the large distance. */ b rtrap_xcall ldx [%sp + PTREGS_OFF + PT_V9_TSTATE], %l1 @@ -576,7 +574,7 @@ __hypervisor_tlb_xcall_error: mov %l4, %o0 call hypervisor_tlbop_error_xcall mov %l5, %o1 - ba,a,pt %xcc, rtrap_clr_l6 + ba,a,pt %xcc, rtrap .globl __hypervisor_xcall_flush_tlb_mm __hypervisor_xcall_flush_tlb_mm: /* 21 insns */ |