diff options
54 files changed, 803 insertions, 519 deletions
diff --git a/arch/x86/kernel/apic_32.c b/arch/x86/kernel/apic_32.c index d6c89835837..039a8d4aaf6 100644 --- a/arch/x86/kernel/apic_32.c +++ b/arch/x86/kernel/apic_32.c @@ -1720,15 +1720,19 @@ static int __init parse_lapic_timer_c2_ok(char *arg) } early_param("lapic_timer_c2_ok", parse_lapic_timer_c2_ok); -static int __init apic_set_verbosity(char *str) +static int __init apic_set_verbosity(char *arg) { - if (strcmp("debug", str) == 0) + if (!arg) + return -EINVAL; + + if (strcmp(arg, "debug") == 0) apic_verbosity = APIC_DEBUG; - else if (strcmp("verbose", str) == 0) + else if (strcmp(arg, "verbose") == 0) apic_verbosity = APIC_VERBOSE; - return 1; + + return 0; } -__setup("apic=", apic_set_verbosity); +early_param("apic", apic_set_verbosity); static int __init lapic_insert_resource(void) { diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index c9b58a806e8..c8e315f1aa8 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -50,6 +50,8 @@ static double __initdata y = 3145727.0; */ static void __init check_fpu(void) { + s32 fdiv_bug; + if (!boot_cpu_data.hard_math) { #ifndef CONFIG_MATH_EMULATION printk(KERN_EMERG "No coprocessor found and no math emulation present.\n"); @@ -74,8 +76,10 @@ static void __init check_fpu(void) "fistpl %0\n\t" "fwait\n\t" "fninit" - : "=m" (*&boot_cpu_data.fdiv_bug) + : "=m" (*&fdiv_bug) : "m" (*&x), "m" (*&y)); + + boot_cpu_data.fdiv_bug = fdiv_bug; if (boot_cpu_data.fdiv_bug) printk("Hmm, FPU with FDIV bug.\n"); } diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c index de9aa0e3a9c..09cddb57bec 100644 --- a/arch/x86/kernel/io_apic_32.c +++ b/arch/x86/kernel/io_apic_32.c @@ -57,7 +57,7 @@ atomic_t irq_mis_count; static struct { int pin, apic; } ioapic_i8259 = { -1, -1 }; static DEFINE_SPINLOCK(ioapic_lock); -static DEFINE_SPINLOCK(vector_lock); +DEFINE_SPINLOCK(vector_lock); int timer_through_8259 __initdata; @@ -1209,10 +1209,6 @@ static int assign_irq_vector(int irq) return vector; } -void setup_vector_irq(int cpu) -{ -} - static struct irq_chip ioapic_chip; #define IOAPIC_AUTO -1 diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c index 8269434d170..61a83b70c18 100644 --- a/arch/x86/kernel/io_apic_64.c +++ b/arch/x86/kernel/io_apic_64.c @@ -101,7 +101,7 @@ int timer_through_8259 __initdata; static struct { int pin, apic; } ioapic_i8259 = { -1, -1 }; static DEFINE_SPINLOCK(ioapic_lock); -DEFINE_SPINLOCK(vector_lock); +static DEFINE_SPINLOCK(vector_lock); /* * # of IRQ routing registers @@ -697,6 +697,19 @@ static int pin_2_irq(int idx, int apic, int pin) return irq; } +void lock_vector_lock(void) +{ + /* Used to the online set of cpus does not change + * during assign_irq_vector. + */ + spin_lock(&vector_lock); +} + +void unlock_vector_lock(void) +{ + spin_unlock(&vector_lock); +} + static int __assign_irq_vector(int irq, cpumask_t mask) { /* @@ -802,7 +815,7 @@ static void __clear_irq_vector(int irq) cpus_clear(cfg->domain); } -static void __setup_vector_irq(int cpu) +void __setup_vector_irq(int cpu) { /* Initialize vector_irq on a new cpu */ /* This function must be called with vector_lock held */ @@ -825,14 +838,6 @@ static void __setup_vector_irq(int cpu) } } -void setup_vector_irq(int cpu) -{ - spin_lock(&vector_lock); - __setup_vector_irq(smp_processor_id()); - spin_unlock(&vector_lock); -} - - static struct irq_chip ioapic_chip; static void ioapic_register_intr(int irq, unsigned long trigger) diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 6ae005ccaed..678090508a6 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -83,7 +83,7 @@ static void __init MP_bus_info(struct mpc_config_bus *m) if (x86_quirks->mpc_oem_bus_info) x86_quirks->mpc_oem_bus_info(m, str); else - printk(KERN_INFO "Bus #%d is %s\n", m->mpc_busid, str); + apic_printk(APIC_VERBOSE, "Bus #%d is %s\n", m->mpc_busid, str); #if MAX_MP_BUSSES < 256 if (m->mpc_busid >= MAX_MP_BUSSES) { @@ -154,7 +154,7 @@ static void __init MP_ioapic_info(struct mpc_config_ioapic *m) static void print_MP_intsrc_info(struct mpc_config_intsrc *m) { - printk(KERN_CONT "Int: type %d, pol %d, trig %d, bus %02x," + apic_printk(APIC_VERBOSE, "Int: type %d, pol %d, trig %d, bus %02x," " IRQ %02x, APIC ID %x, APIC INT %02x\n", m->mpc_irqtype, m->mpc_irqflag & 3, (m->mpc_irqflag >> 2) & 3, m->mpc_srcbus, @@ -163,7 +163,7 @@ static void print_MP_intsrc_info(struct mpc_config_intsrc *m) static void __init print_mp_irq_info(struct mp_config_intsrc *mp_irq) { - printk(KERN_CONT "Int: type %d, pol %d, trig %d, bus %02x," + apic_printk(APIC_VERBOSE, "Int: type %d, pol %d, trig %d, bus %02x," " IRQ %02x, APIC ID %x, APIC INT %02x\n", mp_irq->mp_irqtype, mp_irq->mp_irqflag & 3, (mp_irq->mp_irqflag >> 2) & 3, mp_irq->mp_srcbus, @@ -235,7 +235,7 @@ static void __init MP_intsrc_info(struct mpc_config_intsrc *m) static void __init MP_lintsrc_info(struct mpc_config_lintsrc *m) { - printk(KERN_INFO "Lint: type %d, pol %d, trig %d, bus %02x," + apic_printk(APIC_VERBOSE, "Lint: type %d, pol %d, trig %d, bus %02x," " IRQ %02x, APIC ID %x, APIC LINT %02x\n", m->mpc_irqtype, m->mpc_irqflag & 3, (m->mpc_irqflag >> 2) & 3, m->mpc_srcbusid, @@ -695,7 +695,8 @@ static int __init smp_scan_config(unsigned long base, unsigned long length, unsigned int *bp = phys_to_virt(base); struct intel_mp_floating *mpf; - printk(KERN_DEBUG "Scan SMP from %p for %ld bytes.\n", bp, length); + apic_printk(APIC_VERBOSE, "Scan SMP from %p for %ld bytes.\n", + bp, length); BUILD_BUG_ON(sizeof(*mpf) != 16); while (length > 0) { diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index b67a4b1d4ea..02d19328525 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -1350,7 +1350,7 @@ static void calgary_init_bitmap_from_tce_table(struct iommu_table *tbl) * Function for kdump case. Get the tce tables from first kernel * by reading the contents of the base adress register of calgary iommu */ -static void get_tce_space_from_tar() +static void get_tce_space_from_tar(void) { int bus; void __iomem *target; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 2d888586385..68b48e3fbcb 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -604,6 +604,14 @@ void __init setup_arch(char **cmdline_p) early_cpu_init(); early_ioremap_init(); +#if defined(CONFIG_VMI) && defined(CONFIG_X86_32) + /* + * Must be before kernel pagetables are setup + * or fixmap area is touched. + */ + vmi_init(); +#endif + ROOT_DEV = old_decode_dev(boot_params.hdr.root_dev); screen_info = boot_params.screen_info; edid_info = boot_params.edid_info; @@ -817,14 +825,6 @@ void __init setup_arch(char **cmdline_p) kvmclock_init(); #endif -#if defined(CONFIG_VMI) && defined(CONFIG_X86_32) - /* - * Must be after max_low_pfn is determined, and before kernel - * pagetables are setup. - */ - vmi_init(); -#endif - paravirt_pagetable_setup_start(swapper_pg_dir); paging_init(); paravirt_pagetable_setup_done(swapper_pg_dir); @@ -861,12 +861,6 @@ void __init setup_arch(char **cmdline_p) init_apic_mappings(); ioapic_init_mappings(); -#if defined(CONFIG_SMP) && defined(CONFIG_X86_PC) && defined(CONFIG_X86_32) - if (def_to_bigsmp) - printk(KERN_WARNING "More than 8 CPUs detected and " - "CONFIG_X86_PC cannot handle it.\nUse " - "CONFIG_X86_GENERICARCH or CONFIG_X86_BIGSMP.\n"); -#endif kvm_guest_init(); e820_reserve_resources(); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 332512767f4..91055d7fc1b 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -326,12 +326,16 @@ static void __cpuinit start_secondary(void *unused) * for which cpus receive the IPI. Holding this * lock helps us to not include this cpu in a currently in progress * smp_call_function(). + * + * We need to hold vector_lock so there the set of online cpus + * does not change while we are assigning vectors to cpus. Holding + * this lock ensures we don't half assign or remove an irq from a cpu. */ ipi_call_lock_irq(); -#ifdef CONFIG_X86_IO_APIC - setup_vector_irq(smp_processor_id()); -#endif + lock_vector_lock(); + __setup_vector_irq(smp_processor_id()); cpu_set(smp_processor_id(), cpu_online_map); + unlock_vector_lock(); ipi_call_unlock_irq(); per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE; @@ -990,7 +994,17 @@ int __cpuinit native_cpu_up(unsigned int cpu) flush_tlb_all(); low_mappings = 1; +#ifdef CONFIG_X86_PC + if (def_to_bigsmp && apicid > 8) { + printk(KERN_WARNING + "More than 8 CPUs detected - skipping them.\n" + "Use CONFIG_X86_GENERICARCH and CONFIG_X86_BIGSMP.\n"); + err = -1; + } else + err = do_boot_cpu(apicid, cpu); +#else err = do_boot_cpu(apicid, cpu); +#endif zap_low_mappings(); low_mappings = 0; @@ -1336,7 +1350,9 @@ int __cpu_disable(void) remove_siblinginfo(cpu); /* It's now safe to remove this processor from the online map */ + lock_vector_lock(); remove_cpu_from_maps(cpu); + unlock_vector_lock(); fixup_irqs(cpu_online_map); return 0; } diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c index 0a1b1a9d922..6ca515d6db5 100644 --- a/arch/x86/kernel/vmi_32.c +++ b/arch/x86/kernel/vmi_32.c @@ -37,6 +37,7 @@ #include <asm/timer.h> #include <asm/vmi_time.h> #include <asm/kmap_types.h> +#include <asm/setup.h> /* Convenient for calling VMI functions indirectly in the ROM */ typedef u32 __attribute__((regparm(1))) (VROMFUNC)(void); @@ -683,7 +684,7 @@ void vmi_bringup(void) { /* We must establish the lowmem mapping for MMU ops to work */ if (vmi_ops.set_linear_mapping) - vmi_ops.set_linear_mapping(0, (void *)__PAGE_OFFSET, max_low_pfn, 0); + vmi_ops.set_linear_mapping(0, (void *)__PAGE_OFFSET, MAXMEM_PFN, 0); } /* diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 557b2abceef..d50302774fe 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -207,6 +207,9 @@ static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[]) unsigned long addr; int i; + if (PREALLOCATED_PMDS == 0) /* Work around gcc-3.4.x bug */ + return; + pud = pud_offset(pgd, 0); for (addr = i = 0; i < PREALLOCATED_PMDS; diff --git a/drivers/char/agp/agp.h b/drivers/char/agp/agp.h index 81e14bea54b..4bada0e8b81 100644 --- a/drivers/char/agp/agp.h +++ b/drivers/char/agp/agp.h @@ -148,6 +148,9 @@ struct agp_bridge_data { char minor_version; struct list_head list; u32 apbase_config; + /* list of agp_memory mapped to the aperture */ + struct list_head mapped_list; + spinlock_t mapped_lock; }; #define KB(x) ((x) * 1024) diff --git a/drivers/char/agp/ali-agp.c b/drivers/char/agp/ali-agp.c index 1ffb381130c..31dcd9142d5 100644 --- a/drivers/char/agp/ali-agp.c +++ b/drivers/char/agp/ali-agp.c @@ -110,7 +110,8 @@ static int ali_configure(void) nlvm_addr+= agp_bridge->gart_bus_addr; nlvm_addr|=(agp_bridge->gart_bus_addr>>12); - printk(KERN_INFO PFX "nlvm top &base = %8x\n",nlvm_addr); + dev_info(&agp_bridge->dev->dev, "nlvm top &base = %8x\n", + nlvm_addr); } #endif @@ -315,8 +316,8 @@ static int __devinit agp_ali_probe(struct pci_dev *pdev, goto found; } - printk(KERN_ERR PFX "Unsupported ALi chipset (device id: %04x)\n", - pdev->device); + dev_err(&pdev->dev, "unsupported ALi chipset [%04x/%04x])\n", + pdev->vendor, pdev->device); return -ENODEV; @@ -361,8 +362,7 @@ found: bridge->driver = &ali_generic_bridge; } - printk(KERN_INFO PFX "Detected ALi %s chipset\n", - devs[j].chipset_name); + dev_info(&pdev->dev, "ALi %s chipset\n", devs[j].chipset_name); /* Fill in the mode register */ pci_read_config_dword(pdev, diff --git a/drivers/char/agp/amd-k7-agp.c b/drivers/char/agp/amd-k7-agp.c index 39a0718bc61..e280531843b 100644 --- a/drivers/char/agp/amd-k7-agp.c +++ b/drivers/char/agp/amd-k7-agp.c @@ -419,8 +419,8 @@ static int __devinit agp_amdk7_probe(struct pci_dev *pdev, return -ENODEV; j = ent - agp_amdk7_pci_table; - printk(KERN_INFO PFX "Detected AMD %s chipset\n", - amd_agp_device_ids[j].chipset_name); + dev_info(&pdev->dev, "AMD %s chipset\n", + amd_agp_device_ids[j].chipset_name); bridge = agp_alloc_bridge(); if (!bridge) @@ -442,7 +442,7 @@ static int __devinit agp_amdk7_probe(struct pci_dev *pdev, while (!cap_ptr) { gfxcard = pci_get_class(PCI_CLASS_DISPLAY_VGA<<8, gfxcard); if (!gfxcard) { - printk (KERN_INFO PFX "Couldn't find an AGP VGA controller.\n"); + dev_info(&pdev->dev, "no AGP VGA controller\n"); return -ENODEV; } cap_ptr = pci_find_capability(gfxcard, PCI_CAP_ID_AGP); @@ -453,7 +453,7 @@ static int __devinit agp_amdk7_probe(struct pci_dev *pdev, (if necessary at all). */ if (gfxcard->vendor == PCI_VENDOR_ID_NVIDIA) { agp_bridge->flags |= AGP_ERRATA_1X; - printk (KERN_INFO PFX "AMD 751 chipset with NVidia GeForce detected. Forcing to 1X due to errata.\n"); + dev_info(&pdev->dev, "AMD 751 chipset with NVidia GeForce; forcing 1X due to errata\n"); } pci_dev_put(gfxcard); } @@ -469,7 +469,7 @@ static int __devinit agp_amdk7_probe(struct pci_dev *pdev, agp_bridge->flags = AGP_ERRATA_FASTWRITES; agp_bridge->flags |= AGP_ERRATA_SBA; agp_bridge->flags |= AGP_ERRATA_1X; - printk (KERN_INFO PFX "AMD 761 chipset with errata detected - disabling AGP fast writes & SBA and forcing to 1X.\n"); + dev_info(&pdev->dev, "AMD 761 chipset with errata; disabling AGP fast writes & SBA and forcing to 1X\n"); } } diff --git a/drivers/char/agp/amd64-agp.c b/drivers/char/agp/amd64-agp.c index 481ffe87c71..7495c522d8e 100644 --- a/drivers/char/agp/amd64-agp.c +++ b/drivers/char/agp/amd64-agp.c @@ -34,6 +34,7 @@ static struct resource *aperture_resource; static int __initdata agp_try_unsupported = 1; +static int agp_bridges_found; static void amd64_tlbflush(struct agp_memory *temp) { @@ -293,12 +294,13 @@ static __devinit int fix_northbridge(struct pci_dev *nb, struct pci_dev *agp, * so let double check that order, and lets trust the AMD NB settings */ if (order >=0 && aper + (32ULL<<(20 + order)) > 0x100000000ULL) { - printk(KERN_INFO "Aperture size %u MB is not right, using settings from NB\n", - 32 << order); + dev_info(&agp->dev, "aperture size %u MB is not right, using settings from NB\n", + 32 << order); order = nb_order; } - printk(KERN_INFO PFX "Aperture from AGP @ %Lx size %u MB\n", aper, 32 << order); + dev_info(&agp->dev, "aperture from AGP @ %Lx size %u MB\n", + aper, 32 << order); if (order < 0 || !agp_aperture_valid(aper, (32*1024*1024)<<order)) return -1; @@ -319,10 +321,10 @@ static __devinit int cache_nbs (struct pci_dev *pdev, u32 cap_ptr) for (i = 0; i < num_k8_northbridges; i++) { struct pci_dev *dev = k8_northbridges[i]; if (fix_northbridge(dev, pdev, cap_ptr) < 0) { - printk(KERN_ERR PFX "No usable aperture found.\n"); + dev_err(&dev->dev, "no usable aperture found\n"); #ifdef __x86_64__ /* should port this to i386 */ - printk(KERN_ERR PFX "Consider rebooting with iommu=memaper=2 to get a good aperture.\n"); + dev_err(&dev->dev, "consider rebooting with iommu=memaper=2 to get a good aperture\n"); #endif return -1; } @@ -345,14 +347,14 @@ static void __devinit amd8151_init(struct pci_dev *pdev, struct agp_bridge_data default: revstring="??"; break; } - printk (KERN_INFO PFX "Detected AMD 8151 AGP Bridge rev %s\n", revstring); + dev_info(&pdev->dev, "AMD 8151 AGP Bridge rev %s\n", revstring); /* * Work around errata. * Chips before B2 stepping incorrectly reporting v3.5 */ if (pdev->revision < 0x13) { - printk (KERN_INFO PFX "Correcting AGP revision (reports 3.5, is really 3.0)\n"); + dev_info(&pdev->dev, "correcting AGP revision (reports 3.5, is really 3.0)\n"); bridge->major_version = 3; bridge->minor_version = 0; } @@ -375,11 +377,11 @@ static int __devinit uli_agp_init(struct pci_dev *pdev) struct pci_dev *dev1; int i; unsigned size = amd64_fetch_size(); - printk(KERN_INFO "Setting up ULi AGP.\n"); + + dev_info(&pdev->dev, "setting up ULi AGP\n"); dev1 = pci_get_slot (pdev->bus,PCI_DEVFN(0,0)); if (dev1 == NULL) { - printk(KERN_INFO PFX "Detected a ULi chipset, " - "but could not fine the secondary device.\n"); + dev_info(&pdev->dev, "can't find ULi secondary device\n"); return -ENODEV; } @@ -388,7 +390,7 @@ static int __devinit uli_agp_init(struct pci_dev *pdev) break; if (i == ARRAY_SIZE(uli_sizes)) { - printk(KERN_INFO PFX "No ULi size found for %d\n", size); + dev_info(&pdev->dev, "no ULi size found for %d\n", size); return -ENODEV; } @@ -433,13 +435,11 @@ static int nforce3_agp_init(struct pci_dev *pdev) int i; unsigned size = amd64_fetch_size(); - printk(KERN_INFO PFX "Setting up Nforce3 AGP.\n"); + dev_info(&pdev->dev, "setting up Nforce3 AGP\n"); dev1 = pci_get_slot(pdev->bus, PCI_DEVFN(11, 0)); if (dev1 == NULL) { - printk(KERN_INFO PFX "agpgart: Detected an NVIDIA " - "nForce3 chipset, but could not find " - "the secondary device.\n"); + dev_info(&pdev->dev, "can't find Nforce3 secondary device\n"); return -ENODEV; } @@ -448,7 +448,7 @@ static int nforce3_agp_init(struct pci_dev *pdev) break; if (i == ARRAY_SIZE(nforce3_sizes)) { - printk(KERN_INFO PFX "No NForce3 size found for %d\n", size); + dev_info(&pdev->dev, "no NForce3 size found for %d\n", size); return -ENODEV; } @@ -462,7 +462,7 @@ static int nforce3_agp_init(struct pci_dev *pdev) /* if x86-64 aperture base is beyond 4G, exit here */ if ( (apbase & 0x7fff) >> (32 - 25) ) { - printk(KERN_INFO PFX "aperture base > 4G\n"); + dev_info(&pdev->dev, "aperture base > 4G\n"); return -ENODEV; } @@ -489,6 +489,7 @@ static int __devinit agp_amd64_probe(struct pci_dev *pdev, { struct agp_bridge_data *bridge; u8 cap_ptr; + int err; cap_ptr = pci_find_capability(pdev, PCI_CAP_ID_AGP); if (!cap_ptr) @@ -504,7 +505,8 @@ static int __devinit agp_amd64_probe(struct pci_dev *pdev, pdev->device == PCI_DEVICE_ID_AMD_8151_0) { amd8151_init(pdev, bridge); } else { - printk(KERN_INFO PFX "Detected AGP bridge %x\n", pdev->devfn); + dev_info(&pdev->dev, "AGP bridge [%04x/%04x]\n", + pdev->vendor, pdev->device); } bridge->driver = &amd_8151_driver; @@ -536,7 +538,12 @@ static int __devinit agp_amd64_probe(struct pci_dev *pdev, } pci_set_drvdata(pdev, bridge); - return agp_add_bridge(bridge); + err = agp_add_bridge(bridge); + if (err < 0) + return err; + + agp_bridges_found++; + return 0; } static void __devexit agp_amd64_remove(struct pci_dev *pdev) @@ -713,7 +720,11 @@ int __init agp_amd64_init(void) if (agp_off) return -EINVAL; - if (pci_register_driver(&agp_amd64_pci_driver) < 0) { + err = pci_register_driver(&agp_amd64_pci_driver); + if (err < 0) + return err; + + if (agp_bridges_found == 0) { struct pci_dev *dev; if (!agp_try_unsupported && !agp_try_unsupported_boot) { printk(KERN_INFO PFX "No supported AGP bridge found.\n"); diff --git a/drivers/char/agp/ati-agp.c b/drivers/char/agp/ati-agp.c index 3a4566c0d84..6ecbcafb34b 100644 --- a/drivers/char/agp/ati-agp.c +++ b/drivers/char/agp/ati-agp.c @@ -486,8 +486,8 @@ static int __devinit agp_ati_probe(struct pci_dev *pdev, goto found; } - printk(KERN_ERR PFX - "Unsupported Ati chipset (device id: %04x)\n", pdev->device); + dev_err(&pdev->dev, "unsupported Ati chipset [%04x/%04x])\n", + pdev->vendor, pdev->device); return -ENODEV; found: @@ -500,8 +500,7 @@ found: bridge->driver = &ati_generic_bridge; - printk(KERN_INFO PFX "Detected Ati %s chipset\n", - devs[j].chipset_name); + dev_info(&pdev->dev, "Ati %s chipset\n", devs[j].chipset_name); /* Fill in the mode register */ pci_read_config_dword(pdev, diff --git a/drivers/char/agp/backend.c b/drivers/char/agp/backend.c index 1ec87104e68..3a3cc03d401 100644 --- a/drivers/char/agp/backend.c +++ b/drivers/char/agp/backend.c @@ -144,7 +144,8 @@ static int agp_backend_initialize(struct agp_bridge_data *bridge) void *addr = bridge->driver->agp_alloc_page(bridge); if (!addr) { - printk(KERN_ERR PFX "unable to get memory for scratch page.\n"); + dev_err(&bridge->dev->dev, + "can't get memory for scratch page\n"); return -ENOMEM; } @@ -155,13 +156,13 @@ static int agp_backend_initialize(struct agp_bridge_data *bridge) size_value = bridge->driver->fetch_size(); if (size_value == 0) { - printk(KERN_ERR PFX "unable to determine aperture size.\n"); + dev_err(&bridge->dev->dev, "can't determine aperture size\n"); rc = -EINVAL; goto err_out; } if (bridge->driver->create_gatt_table(bridge)) { - printk(KERN_ERR PFX - "unable to get memory for graphics translation table.\n"); + dev_err(&bridge->dev->dev, + "can't get memory for graphics translation table\n"); rc = -ENOMEM; goto err_out; } @@ -169,7 +170,8 @@ static int agp_backend_initialize(struct agp_bridge_data *bridge) bridge->key_list = vmalloc(PAGE_SIZE * 4); if (bridge->key_list == NULL) { - printk(KERN_ERR PFX "error allocating memory for key lists.\n"); + dev_err(&bridge->dev->dev, + "can't allocate memory for key lists\n"); rc = -ENOMEM; goto err_out; } @@ -179,10 +181,12 @@ static int agp_backend_initialize(struct agp_bridge_data *bridge) memset(bridge->key_list, 0, PAGE_SIZE * 4); if (bridge->driver->configure()) { - printk(KERN_ERR PFX "error configuring host chipset.\n"); + dev_err(&bridge->dev->dev, "error configuring host chipset\n"); rc = -EINVAL; goto err_out; } + INIT_LIST_HEAD(&bridge->mapped_list); + spin_lock_init(&bridge->mapped_lock); return 0; @@ -269,25 +273,27 @@ int agp_add_bridge(struct agp_bridge_data *bridge) /* Grab reference on the chipset driver. */ if (!try_module_get(bridge->driver->owner)) { - printk (KERN_INFO PFX "Couldn't lock chipset driver.\n"); + dev_info(&bridge->dev->dev, "can't lock chipset driver\n"); return -EINVAL; } error = agp_backend_initialize(bridge); if (error) { - printk (KERN_INFO PFX "agp_backend_initialize() failed.\n"); + dev_info(&bridge->dev->dev, + "agp_backend_initialize() failed\n"); goto err_out; } if (list_empty(&agp_bridges)) { error = agp_frontend_initialize(); if (error) { - printk (KERN_INFO PFX "agp_frontend_initialize() failed.\n"); + dev_info(&bridge->dev->dev, + "agp_frontend_initialize() failed\n"); goto frontend_err; } - printk(KERN_INFO PFX "AGP aperture is %dM @ 0x%lx\n", - bridge->driver->fetch_size(), bridge->gart_bus_addr); + dev_info(&bridge->dev->dev, "AGP aperture is %dM @ 0x%lx\n", + bridge->driver->fetch_size(), bridge->gart_bus_addr); } diff --git a/drivers/char/agp/generic.c b/drivers/char/agp/generic.c index eaa1a355bb3..118dbde25dc 100644 --- a/drivers/char/agp/generic.c +++ b/drivers/char/agp/generic.c @@ -429,6 +429,10 @@ int agp_bind_memory(struct agp_memory *curr, off_t pg_start) curr->is_bound = true; curr->pg_start = pg_start; + spin_lock(&agp_bridge->mapped_lock); + list_add(&curr->mapped_list, &agp_bridge->mapped_list); + spin_unlock(&agp_bridge->mapped_lock); + return 0; } EXPORT_SYMBOL(agp_bind_memory); @@ -461,10 +465,34 @@ int agp_unbind_memory(struct agp_memory *curr) curr->is_bound = false; curr->pg_start = 0; + spin_lock(&curr->bridge->mapped_lock); + list_del(&curr->mapped_list); + spin_unlock(&curr->bridge->mapped_lock); return 0; } EXPORT_SYMBOL(agp_unbind_memory); +/** + * agp_rebind_emmory - Rewrite the entire GATT, useful on resume + */ +int agp_rebind_memory(void) +{ + struct agp_memory *curr; + int ret_val = 0; + + spin_lock(&agp_bridge->mapped_lock); + list_for_each_entry(curr, &agp_bridge->mapped_list, mapped_list) { + ret_val = curr->bridge->driver->insert_memory(curr, + curr->pg_start, + curr->type); + if (ret_val != 0) + break; + } + spin_unlock(&agp_bridge->mapped_lock); + return ret_val; +} +EXPORT_SYMBOL(agp_rebind_memory); + /* End - Routines for handling swapping of agp_memory into the GATT */ @@ -771,8 +799,8 @@ void agp_device_command(u32 bridge_agpstat, bool agp_v3) if (!agp) continue; - printk(KERN_INFO PFX "Putting AGP V%d device at %s into %dx mode\n", - agp_v3 ? 3 : 2, pci_name(device), mode); + dev_info(&device->dev, "putting AGP V%d device into %dx mode\n", + agp_v3 ? 3 : 2, mode); pci_write_config_dword(device, agp + PCI_AGP_COMMAND, bridge_agpstat); } } @@ -800,10 +828,8 @@ void agp_generic_enable(struct agp_bridge_data *bridge, u32 requested_mode) get_agp_version(agp_bridge); - printk(KERN_INFO PFX "Found an AGP %d.%d compliant device at %s.\n", - agp_bridge->major_version, - agp_bridge->minor_version, - pci_name(agp_bridge->dev)); + dev_info(&agp_bridge->dev->dev, "AGP %d.%d bridge\n", + agp_bridge->major_version, agp_bridge->minor_version); pci_read_config_dword(agp_bridge->dev, agp_bridge->capndx + PCI_AGP_STATUS, &bridge_agpstat); @@ -832,8 +858,7 @@ void agp_generic_enable(struct agp_bridge_data *bridge, u32 requested_mode) pci_write_config_dword(bridge->dev, bridge->capndx+AGPCTRL, temp); - printk(KERN_INFO PFX "Device is in legacy mode," - " falling back to 2.x\n"); + dev_info(&bridge->dev->dev, "bridge is in legacy mode, falling back to 2.x\n"); } } diff --git a/drivers/char/agp/intel-agp.c b/drivers/char/agp/intel-agp.c index df702642ab8..016fdf0623a 100644 --- a/drivers/char/agp/intel-agp.c +++ b/drivers/char/agp/intel-agp.c @@ -32,8 +32,8 @@ #define PCI_DEVICE_ID_INTEL_Q35_IG 0x29B2 #define PCI_DEVICE_ID_INTEL_Q33_HB 0x29D0 #define PCI_DEVICE_ID_INTEL_Q33_IG 0x29D2 -#define PCI_DEVICE_ID_INTEL_IGD_HB 0x2A40 -#define PCI_DEVICE_ID_INTEL_IGD_IG 0x2A42 +#define PCI_DEVICE_ID_INTEL_GM45_HB 0x2A40 +#define PCI_DEVICE_ID_INTEL_GM45_IG 0x2A42 #define PCI_DEVICE_ID_INTEL_IGD_E_HB 0x2E00 #define PCI_DEVICE_ID_INTEL_IGD_E_IG 0x2E02 #define PCI_DEVICE_ID_INTEL_Q45_HB 0x2E10 @@ -55,7 +55,7 @@ agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_82965G_HB || \ agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_82965GM_HB || \ agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_82965GME_HB || \ - agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_IGD_HB) + agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_GM45_HB) #define IS_G33 (agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_G33_HB || \ agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_Q35_HB || \ @@ -161,7 +161,7 @@ static int intel_i810_fetch_size(void) values = A_SIZE_FIX(agp_bridge->driver->aperture_sizes); if ((smram_miscc & I810_GMS) == I810_GMS_DISABLE) { - printk(KERN_WARNING PFX "i810 is disabled\n"); + dev_warn(&agp_bridge->dev->dev, "i810 is disabled\n"); return 0; } if ((smram_miscc & I810_GFX_MEM_WIN_SIZE) == I810_GFX_MEM_WIN_32M) { @@ -193,7 +193,8 @@ static int intel_i810_configure(void) intel_private.registers = ioremap(temp, 128 * 4096); if (!intel_private.registers) { - printk(KERN_ERR PFX "Unable to remap memory.\n"); + dev_err(&intel_private.pcidev->dev, + "can't remap memory\n"); return -ENOMEM; } } @@ -201,7 +202,8 @@ static int intel_i810_configure(void) if ((readl(intel_private.registers+I810_DRAM_CTL) & I810_DRAM_ROW_0) == I810_DRAM_ROW_0_SDRAM) { /* This will need to be dynamically assigned */ - printk(KERN_INFO PFX "detected 4MB dedicated video ram.\n"); + dev_info(&intel_private.pcidev->dev, + "detected 4MB dedicated video ram\n"); intel_private.num_dcache_entries = 1024; } pci_read_config_dword(intel_private.pcidev, I810_GMADDR, &temp); @@ -500,8 +502,8 @@ static void intel_i830_init_gtt_entries(void) size = 1024 + 512; break; default: - printk(KERN_INFO PFX "Unknown page table size, " - "assuming 512KB\n"); + dev_info(&intel_private.pcidev->dev, + "unknown page table size, assuming 512KB\n"); size = 512; } size += 4; /* add in BIOS popup space */ @@ -515,8 +517,8 @@ static void intel_i830_init_gtt_entries(void) size = 2048; break; default: - printk(KERN_INFO PFX "Unknown page table size 0x%x, " - "assuming 512KB\n", + dev_info(&agp_bridge->dev->dev, + "unknown page table size 0x%x, assuming 512KB\n", (gmch_ctrl & G33_PGETBL_SIZE_MASK)); size = 512; } @@ -627,11 +629,11 @@ static void intel_i830_init_gtt_entries(void) } } if (gtt_entries > 0) - printk(KERN_INFO PFX "Detected %dK %s memory.\n", + dev_info(&agp_bridge->dev->dev, "detected %dK %s memory\n", gtt_entries / KB(1), local ? "local" : "stolen"); else - printk(KERN_INFO PFX - "No pre-allocated video memory detected.\n"); + dev_info(&agp_bridge->dev->dev, + "no pre-allocated video memory detected\n"); gtt_entries /= KB(4); intel_private.gtt_entries = gtt_entries; @@ -801,10 +803,12 @@ static int intel_i830_insert_entries(struct agp_memory *mem, off_t pg_start, num_entries = A_SIZE_FIX(temp)->num_entries; if (pg_start < intel_private.gtt_entries) { - printk(KERN_DEBUG PFX "pg_start == 0x%.8lx,intel_private.gtt_entries == 0x%.8x\n", - pg_start, intel_private.gtt_entries); + dev_printk(KERN_DEBUG, &intel_private.pcidev->dev, + "pg_start == 0x%.8lx, intel_private.gtt_entries == 0x%.8x\n", + pg_start, intel_private.gtt_entries); - printk(KERN_INFO PFX "Trying to insert into local/stolen memory\n"); + dev_info(&intel_private.pcidev->dev, + "trying to insert into local/stolen memory\n"); goto out_err; } @@ -851,7 +855,8 @@ static int intel_i830_remove_entries(struct agp_memory *mem, off_t pg_start, return 0; if (pg_start < intel_private.gtt_entries) { - printk(KERN_INFO PFX "Trying to disable local/stolen memory\n"); + dev_info(&intel_private.pcidev->dev, + "trying to disable local/stolen memory\n"); return -EINVAL; } @@ -957,7 +962,7 @@ static void intel_i9xx_setup_flush(void) if (intel_private.ifp_resource.start) { intel_private.i9xx_flush_page = ioremap_nocache(intel_private.ifp_resource.start, PAGE_SIZE); if (!intel_private.i9xx_flush_page) - printk(KERN_INFO "unable to ioremap flush page - no chipset flushing"); + dev_info(&intel_private.pcidev->dev, "can't ioremap flush page - no chipset flushing"); } } @@ -1028,10 +1033,12 @@ static int intel_i915_insert_entries(struct agp_memory *mem, off_t pg_start, num_entries = A_SIZE_FIX(temp)->num_entries; if (pg_start < intel_private.gtt_entries) { - printk(KERN_DEBUG PFX "pg_start == 0x%.8lx,intel_private.gtt_entries == 0x%.8x\n", - pg_start, intel_private.gtt_entries); + dev_printk(KERN_DEBUG, &intel_private.pcidev->dev, + "pg_start == 0x%.8lx, intel_private.gtt_entries == 0x%.8x\n", + pg_start, intel_private.gtt_entries); - printk(KERN_INFO PFX "Trying to insert into local/stolen memory\n"); + dev_info(&intel_private.pcidev->dev, + "trying to insert into local/stolen memory\n"); goto out_err; } @@ -1078,7 +1085,8 @@ static int intel_i915_remove_entries(struct agp_memory *mem, off_t pg_start, return 0; if (pg_start < intel_private.gtt_entries) { - printk(KERN_INFO PFX "Trying to disable local/stolen memory\n"); + dev_info(&intel_private.pcidev->dev, + "trying to disable local/stolen memory\n"); return -EINVAL; } @@ -1182,7 +1190,7 @@ static unsigned long intel_i965_mask_memory(struct agp_bridge_data *bridge, static void intel_i965_get_gtt_range(int *gtt_offset, int *gtt_size) { switch (agp_bridge->dev->device) { - case PCI_DEVICE_ID_INTEL_IGD_HB: + case PCI_DEVICE_ID_INTEL_GM45_HB: case PCI_DEVICE_ID_INTEL_IGD_E_HB: case PCI_DEVICE_ID_INTEL_Q45_HB: case PCI_DEVICE_ID_INTEL_G45_HB: @@ -1379,7 +1387,7 @@ static int intel_815_configure(void) /* the Intel 815 chipset spec. says that bits 29-31 in the * ATTBASE register are reserved -> try not to write them */ if (agp_bridge->gatt_bus_addr & INTEL_815_ATTBASE_MASK) { - printk(KERN_EMERG PFX "gatt bus addr too high"); + dev_emerg(&agp_bridge->dev->dev, "gatt bus addr too high"); return -EINVAL; } @@ -2117,8 +2125,8 @@ static const struct intel_driver_description { NULL, &intel_g33_driver }, { PCI_DEVICE_ID_INTEL_Q33_HB, PCI_DEVICE_ID_INTEL_Q33_IG, 0, "Q33", NULL, &intel_g33_driver }, - { PCI_DEVICE_ID_INTEL_IGD_HB, PCI_DEVICE_ID_INTEL_IGD_IG, 0, - "Intel Integrated Graphics Device", NULL, &intel_i965_driver }, + { PCI_DEVICE_ID_INTEL_GM45_HB, PCI_DEVICE_ID_INTEL_GM45_IG, 0, + "Mobile Intel? GM45 Express", NULL, &intel_i965_driver }, { PCI_DEVICE_ID_INTEL_IGD_E_HB, PCI_DEVICE_ID_INTEL_IGD_E_IG, 0, "Intel Integrated Graphics Device", NULL, &intel_i965_driver }, { PCI_DEVICE_ID_INTEL_Q45_HB, PCI_DEVICE_ID_INTEL_Q45_IG, 0, @@ -2163,8 +2171,8 @@ static int __devinit agp_intel_probe(struct pci_dev *pdev, if (intel_agp_chipsets[i].name == NULL) { if (cap_ptr) - printk(KERN_WARNING PFX "Unsupported Intel chipset" - "(device id: %04x)\n", pdev->device); + dev_warn(&pdev->dev, "unsupported Intel chipset [%04x/%04x]\n", + pdev->vendor, pdev->device); agp_put_bridge(bridge); return -ENODEV; } @@ -2172,9 +2180,8 @@ static int __devinit agp_intel_probe(struct pci_dev *pdev, if (bridge->driver == NULL) { /* bridge has no AGP and no IGD detected */ if (cap_ptr) - printk(KERN_WARNING PFX "Failed to find bridge device " - "(chip_id: %04x)\n", - intel_agp_chipsets[i].gmch_chip_id); + dev_warn(&pdev->dev, "can't find bridge device (chip_id: %04x)\n", + intel_agp_chipsets[i].gmch_chip_id); agp_put_bridge(bridge); return -ENODEV; } @@ -2183,8 +2190,7 @@ static int __devinit agp_intel_probe(struct pci_dev *pdev, bridge->capndx = cap_ptr; bridge->dev_private_data = &intel_private; - printk(KERN_INFO PFX "Detected an Intel %s Chipset.\n", - intel_agp_chipsets[i].name); + dev_info(&pdev->dev, "Intel %s Chipset\n", intel_agp_chipsets[i].name); /* * The following fixes the case where the BIOS has "forgotten" to @@ -2194,7 +2200,7 @@ static int __devinit agp_intel_probe(struct pci_dev *pdev, r = &pdev->resource[0]; if (!r->start && r->end) { if (pci_assign_resource(pdev, 0)) { - printk(KERN_ERR PFX "could not assign resource 0\n"); + dev_err(&pdev->dev, "can't assign resource 0\n"); agp_put_bridge(bridge); return -ENODEV; } @@ -2206,7 +2212,7 @@ static int __devinit agp_intel_probe(struct pci_dev *pdev, * 20030610 - hamish@zot.org */ if (pci_enable_device(pdev)) { - printk(KERN_ERR PFX "Unable to Enable PCI device\n"); + dev_err(&pdev->dev, "can't enable PCI device\n"); agp_put_bridge(bridge); return -ENODEV; } @@ -2238,6 +2244,7 @@ static void __devexit agp_intel_remove(struct pci_dev *pdev) static int agp_intel_resume(struct pci_dev *pdev) { struct agp_bridge_data *bridge = pci_get_drvdata(pdev); + int ret_val; pci_restore_state(pdev); @@ -2265,6 +2272,10 @@ static int agp_intel_resume(struct pci_dev *pdev) else if (bridge->driver == &intel_i965_driver) intel_i915_configure(); + ret_val = agp_rebind_memory(); + if (ret_val != 0) + return ret_val; + return 0; } #endif @@ -2315,7 +2326,7 @@ static struct pci_device_id agp_intel_pci_table[] = { ID(PCI_DEVICE_ID_INTEL_G33_HB), ID(PCI_DEVICE_ID_INTEL_Q35_HB), ID(PCI_DEVICE_ID_INTEL_Q33_HB), - ID(PCI_DEVICE_ID_INTEL_IGD_HB), + ID(PCI_DEVICE_ID_INTEL_GM45_HB), ID(PCI_DEVICE_ID_INTEL_IGD_E_HB), ID(PCI_DEVICE_ID_INTEL_Q45_HB), ID(PCI_DEVICE_ID_INTEL_G45_HB), diff --git a/drivers/char/agp/isoch.c b/drivers/char/agp/isoch.c index 3f9ccde6237..c73385cc4b8 100644 --- a/drivers/char/agp/isoch.c +++ b/drivers/char/agp/isoch.c @@ -153,7 +153,7 @@ static int agp_3_5_isochronous_node_enable(struct agp_bridge_data *bridge, /* Check if this configuration has any chance of working */ if (tot_bw > target.maxbw) { - printk(KERN_ERR PFX "isochronous bandwidth required " + dev_err(&td->dev, "isochronous bandwidth required " "by AGP 3.0 devices exceeds that which is supported by " "the AGP 3.0 bridge!\n"); ret = -ENODEV; @@ -188,7 +188,7 @@ static int agp_3_5_isochronous_node_enable(struct agp_bridge_data *bridge, /* Exit if the minimal ISOCH_N allocation among the masters is more * than the target can handle. */ if (tot_n > target.n) { - printk(KERN_ERR PFX "number of isochronous " + dev_err(&td->dev, "number of isochronous " "transactions per period required by AGP 3.0 devices " "exceeds that which is supported by the AGP 3.0 " "bridge!\n"); @@ -229,7 +229,7 @@ static int agp_3_5_isochronous_node_enable(struct agp_bridge_data *bridge, /* Exit if the minimal RQ needs of the masters exceeds what the target * can provide. */ if (tot_rq > rq_isoch) { - printk(KERN_ERR PFX "number of request queue slots " + dev_err(&td->dev, "number of request queue slots " "required by the isochronous bandwidth requested by " "AGP 3.0 devices exceeds the number provided by the " "AGP 3.0 bridge!\n"); @@ -359,8 +359,9 @@ int agp_3_5_enable(struct agp_bridge_data *bridge) case 0x0001: /* Unclassified device */ /* Don't know what this is, but log it for investigation. */ if (mcapndx != 0) { - printk (KERN_INFO PFX "Wacky, found unclassified AGP device. %x:%x\n", - dev->vendor, dev->device); + dev_info(&td->dev, "wacky, found unclassified AGP device %s [%04x/%04x]\n", + pci_name(dev), + dev->vendor, dev->device); } continue; @@ -407,17 +408,18 @@ int agp_3_5_enable(struct agp_bridge_data *bridge) } if (mcapndx == 0) { - printk(KERN_ERR PFX "woah! Non-AGP device " - "found on the secondary bus of an AGP 3.5 bridge!\n"); + dev_err(&td->dev, "woah! Non-AGP device %s on " + "secondary bus of AGP 3.5 bridge!\n", + pci_name(dev)); ret = -ENODEV; goto free_and_exit; } mmajor = (ncapid >> AGP_MAJOR_VERSION_SHIFT) & 0xf; if (mmajor < 3) { - printk(KERN_ERR PFX "woah! AGP 2.0 device " - "found on the secondary bus of an AGP 3.5 " - "bridge operating with AGP 3.0 electricals!\n"); + dev_err(&td->dev, "woah! AGP 2.0 device %s on " + "secondary bus of AGP 3.5 bridge operating " + "with AGP 3.0 electricals!\n", pci_name(dev)); ret = -ENODEV; goto free_and_exit; } @@ -427,10 +429,10 @@ int agp_3_5_enable(struct agp_bridge_data *bridge) pci_read_config_dword(dev, cur->capndx+AGPSTAT, &mstatus); if (((mstatus >> 3) & 0x1) == 0) { - printk(KERN_ERR PFX "woah! AGP 3.x device " - "not operating in AGP 3.x mode found on the " - "secondary bus of an AGP 3.5 bridge operating " - "with AGP 3.0 electricals!\n"); + dev_err(&td->dev, "woah! AGP 3.x device %s not " + "operating in AGP 3.x mode on secondary bus " + "of AGP 3.5 bridge operating with AGP 3.0 " + "electricals!\n", pci_name(dev)); ret = -ENODEV; goto free_and_exit; } @@ -444,9 +446,9 @@ int agp_3_5_enable(struct agp_bridge_data *bridge) if (isoch) { ret = agp_3_5_isochronous_node_enable(bridge, dev_list, ndevs); if (ret) { - printk(KERN_INFO PFX "Something bad happened setting " - "up isochronous xfers. Falling back to " - "non-isochronous xfer mode.\n"); + dev_info(&td->dev, "something bad happened setting " + "up isochronous xfers; falling back to " + "non-isochronous xfer mode\n"); } else { goto free_and_exit; } @@ -466,4 +468,3 @@ free_and_exit: get_out: return ret; } - diff --git a/drivers/char/agp/sis-agp.c b/drivers/char/agp/sis-agp.c index b6791846809..2587ef96a96 100644 --- a/drivers/char/agp/sis-agp.c +++ b/drivers/char/agp/sis-agp.c @@ -79,10 +79,8 @@ static void sis_delayed_enable(struct agp_bridge_data *bridge, u32 mode) u32 command; int rate; - printk(KERN_INFO PFX "Found an AGP %d.%d compliant device at %s.\n", - agp_bridge->major_version, - agp_bridge->minor_version, - pci_name(agp_bridge->dev)); + dev_info(&agp_bridge->dev->dev, "AGP %d.%d bridge\n", + agp_bridge->major_version, agp_bridge->minor_version); pci_read_config_dword(agp_bridge->dev, agp_bridge->capndx + PCI_AGP_STATUS, &command); command = agp_collect_device_status(bridge, mode, command); @@ -94,8 +92,8 @@ static void sis_delayed_enable(struct agp_bridge_data *bridge, u32 mode) if (!agp) continue; - printk(KERN_INFO PFX "Putting AGP V3 device at %s into %dx mode\n", - pci_name(device), rate); + dev_info(&agp_bridge->dev->dev, "putting AGP V3 device at %s into %dx mode\n", + pci_name(device), rate); pci_write_config_dword(device, agp + PCI_AGP_COMMAND, command); @@ -105,7 +103,7 @@ static void sis_delayed_enable(struct agp_bridge_data *bridge, u32 mode) * cannot be configured */ if (device->device == bridge->dev->device) { - printk(KERN_INFO PFX "SiS delay workaround: giving bridge time to recover.\n"); + dev_info(&agp_bridge->dev->dev, "SiS delay workaround: giving bridge time to recover\n"); msleep(10); } } @@ -190,7 +188,8 @@ static int __devinit agp_sis_probe(struct pci_dev *pdev, return -ENODEV; - printk(KERN_INFO PFX "Detected SiS chipset - id:%i\n", pdev->device); + dev_info(&pdev->dev, "SiS chipset [%04x/%04x]\n", + pdev->vendor, pdev->device); bridge = agp_alloc_bridge(); if (!bridge) return -ENOMEM; @@ -242,7 +241,7 @@ static struct pci_device_id agp_sis_pci_table[] = { .class = (PCI_CLASS_BRIDGE_HOST << 8), .class_mask = ~0, .vendor = PCI_VENDOR_ID_SI, - .device = PCI_DEVICE_ID_SI_5591_AGP, + .device = PCI_DEVICE_ID_SI_5591, .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, }, diff --git a/drivers/char/agp/sworks-agp.c b/drivers/char/agp/sworks-agp.c index 0e054c13449..2fb27fe4c10 100644 --- a/drivers/char/agp/sworks-agp.c +++ b/drivers/char/agp/sworks-agp.c @@ -241,7 +241,8 @@ static void serverworks_tlbflush(struct agp_memory *temp) while (readb(serverworks_private.registers+SVWRKS_POSTFLUSH) == 1) { cpu_relax(); if (time_after(jiffies, timeout)) { - printk(KERN_ERR PFX "TLB post flush took more than 3 seconds\n"); + dev_err(&serverworks_private.svrwrks_dev->dev, + "TLB post flush took more than 3 seconds\n"); break; } } @@ -251,7 +252,8 @@ static void serverworks_tlbflush(struct agp_memory *temp) while (readl(serverworks_private.registers+SVWRKS_DIRFLUSH) == 1) { cpu_relax(); if (time_after(jiffies, timeout)) { - printk(KERN_ERR PFX "TLB Dir flush took more than 3 seconds\n"); + dev_err(&serverworks_private.svrwrks_dev->dev, + "TLB Dir flush took more than 3 seconds\n"); break; } } @@ -271,7 +273,7 @@ static int serverworks_configure(void) temp = (temp & PCI_BASE_ADDRESS_MEM_MASK); serverworks_private.registers = (volatile u8 __iomem *) ioremap(temp, 4096); if (!serverworks_private.registers) { - printk (KERN_ERR PFX "Unable to ioremap() memory.\n"); + dev_err(&agp_bridge->dev->dev, "can't ioremap(%#x)\n", temp); return -ENOMEM; } @@ -451,7 +453,7 @@ static int __devinit agp_serverworks_probe(struct pci_dev *pdev, switch (pdev->device) { case 0x0006: - printk (KERN_ERR PFX "ServerWorks CNB20HE is unsupported due to lack of documentation.\n"); + dev_err(&pdev->dev, "ServerWorks CNB20HE is unsupported due to lack of documentation\n"); return -ENODEV; case PCI_DEVICE_ID_SERVERWORKS_HE: @@ -461,8 +463,8 @@ static int __devinit agp_serverworks_probe(struct pci_dev *pdev, default: if (cap_ptr) - printk(KERN_ERR PFX "Unsupported Serverworks chipset " - "(device id: %04x)\n", pdev->device); + dev_err(&pdev->dev, "unsupported Serverworks chipset " + "[%04x/%04x]\n", pdev->vendor, pdev->device); return -ENODEV; } @@ -470,8 +472,7 @@ static int __devinit agp_serverworks_probe(struct pci_dev *pdev, bridge_dev = pci_get_bus_and_slot((unsigned int)pdev->bus->number, PCI_DEVFN(0, 1)); if (!bridge_dev) { - printk(KERN_INFO PFX "Detected a Serverworks chipset " - "but could not find the secondary device.\n"); + dev_info(&pdev->dev, "can't find secondary device\n"); return -ENODEV; } @@ -482,8 +483,8 @@ static int __devinit agp_serverworks_probe(struct pci_dev *pdev, if (temp & PCI_BASE_ADDRESS_MEM_TYPE_64) { pci_read_config_dword(pdev, SVWRKS_APSIZE + 4, &temp2); if (temp2 != 0) { - printk(KERN_INFO PFX "Detected 64 bit aperture address, " - "but top bits are not zero. Disabling agp\n"); + dev_info(&pdev->dev, "64 bit aperture address, " + "but top bits are not zero; disabling AGP\n"); return -ENODEV; } serverworks_private.mm_addr_ofs = 0x18; @@ -495,8 +496,8 @@ static int __devinit agp_serverworks_probe(struct pci_dev *pdev, pci_read_config_dword(pdev, serverworks_private.mm_addr_ofs + 4, &temp2); if (temp2 != 0) { - printk(KERN_INFO PFX "Detected 64 bit MMIO address, " - "but top bits are not zero. Disabling agp\n"); + dev_info(&pdev->dev, "64 bit MMIO address, but top " + "bits are not zero; disabling AGP\n"); return -ENODEV; } } diff --git a/drivers/char/agp/uninorth-agp.c b/drivers/char/agp/uninorth-agp.c index d2fa3cfca02..eef72709ec5 100644 --- a/drivers/char/agp/uninorth-agp.c +++ b/drivers/char/agp/uninorth-agp.c @@ -46,8 +46,8 @@ static int uninorth_fetch_size(void) break; if (i == agp_bridge->driver->num_aperture_sizes) { - printk(KERN_ERR PFX "Invalid aperture size, using" - " default\n"); + dev_err(&agp_bridge->dev->dev, "invalid aperture size, " + "using default\n"); size = 0; aperture = NULL; } @@ -108,8 +108,8 @@ static int uninorth_configure(void) current_size = A_SIZE_32(agp_bridge->current_size); - printk(KERN_INFO PFX "configuring for size idx: %d\n", - current_size->size_value); + dev_info(&agp_bridge->dev->dev, "configuring for size idx: %d\n", + current_size->size_value); /* aperture size and gatt addr */ pci_write_config_dword(agp_bridge->dev, @@ -197,8 +197,9 @@ static int u3_insert_memory(struct agp_memory *mem, off_t pg_start, int type) gp = (u32 *) &agp_bridge->gatt_table[pg_start]; for (i = 0; i < mem->page_count; ++i) { if (gp[i]) { - printk("u3_insert_memory: entry 0x%x occupied (%x)\n", - i, gp[i]); + dev_info(&agp_bridge->dev->dev, + "u3_insert_memory: entry 0x%x occupied (%x)\n", + i, gp[i]); return -EBUSY; } } @@ -276,8 +277,8 @@ static void uninorth_agp_enable(struct agp_bridge_data *bridge, u32 mode) &scratch); } while ((scratch & PCI_AGP_COMMAND_AGP) == 0 && ++timeout < 1000); if ((scratch & PCI_AGP_COMMAND_AGP) == 0) - printk(KERN_ERR PFX "failed to write UniNorth AGP" - " command register\n"); + dev_err(&bridge->dev->dev, "can't write UniNorth AGP " + "command register\n"); if (uninorth_rev >= 0x30) { /* This is an AGP V3 */ @@ -330,8 +331,8 @@ static int agp_uninorth_suspend(struct pci_dev *pdev) pci_read_config_dword(device, agp + PCI_AGP_COMMAND, &cmd); if (!(cmd & PCI_AGP_COMMAND_AGP)) continue; - printk("uninorth-agp: disabling AGP on device %s\n", - pci_name(device)); + dev_info(&pdev->dev, "disabling AGP on device %s\n", + pci_name(device)); cmd &= ~PCI_AGP_COMMAND_AGP; pci_write_config_dword(device, agp + PCI_AGP_COMMAND, cmd); } @@ -341,8 +342,7 @@ static int agp_uninorth_suspend(struct pci_dev *pdev) pci_read_config_dword(pdev, agp + PCI_AGP_COMMAND, &cmd); bridge->dev_private_data = (void *)(long)cmd; if (cmd & PCI_AGP_COMMAND_AGP) { - printk("uninorth-agp: disabling AGP on bridge %s\n", - pci_name(pdev)); + dev_info(&pdev->dev, "disabling AGP on bridge\n"); cmd &= ~PCI_AGP_COMMAND_AGP; pci_write_config_dword(pdev, agp + PCI_AGP_COMMAND, cmd); } @@ -591,14 +591,14 @@ static int __devinit agp_uninorth_probe(struct pci_dev *pdev, /* probe for known chipsets */ for (j = 0; devs[j].chipset_name != NULL; ++j) { if (pdev->device == devs[j].device_id) { - printk(KERN_INFO PFX "Detected Apple %s chipset\n", - devs[j].chipset_name); + dev_info(&pdev->dev, "Apple %s chipset\n", + devs[j].chipset_name); goto found; } } - printk(KERN_ERR PFX "Unsupported Apple chipset (device id: %04x).\n", - pdev->device); + dev_err(&pdev->dev, "unsupported Apple chipset [%04x/%04x]\n", + pdev->vendor, pdev->device); return -ENODEV; found: diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c index fcdd73f2562..994da56fffe 100644 --- a/drivers/scsi/device_handler/scsi_dh_alua.c +++ b/drivers/scsi/device_handler/scsi_dh_alua.c @@ -680,7 +680,7 @@ static int alua_prep_fn(struct scsi_device *sdev, struct request *req) } -const struct scsi_dh_devlist alua_dev_list[] = { +static const struct scsi_dh_devlist alua_dev_list[] = { {"HP", "MSA VOLUME" }, {"HP", "HSV101" }, {"HP", "HSV111" }, diff --git a/drivers/scsi/device_handler/scsi_dh_emc.c b/drivers/scsi/device_handler/scsi_dh_emc.c index aa46b131b20..b9d23e9e9a4 100644 --- a/drivers/scsi/device_handler/scsi_dh_emc.c +++ b/drivers/scsi/device_handler/scsi_dh_emc.c @@ -562,7 +562,7 @@ done: return result; } -const struct scsi_dh_devlist clariion_dev_list[] = { +static const struct scsi_dh_devlist clariion_dev_list[] = { {"DGC", "RAID"}, {"DGC", "DISK"}, {"DGC", "VRAID"}, diff --git a/drivers/scsi/device_handler/scsi_dh_hp_sw.c b/drivers/scsi/device_handler/scsi_dh_hp_sw.c index 9c7a1f8ebb7..a6a4ef3ad51 100644 --- a/drivers/scsi/device_handler/scsi_dh_hp_sw.c +++ b/drivers/scsi/device_handler/scsi_dh_hp_sw.c @@ -282,7 +282,7 @@ static int hp_sw_activate(struct scsi_device *sdev) return ret; } -const struct scsi_dh_devlist hp_sw_dh_data_list[] = { +static const struct scsi_dh_devlist hp_sw_dh_data_list[] = { {"COMPAQ", "MSA1000 VOLUME"}, {"COMPAQ", "HSV110"}, {"HP", "HSV100"}, diff --git a/drivers/scsi/device_handler/scsi_dh_rdac.c b/drivers/scsi/device_handler/scsi_dh_rdac.c index b093a501f8a..e7c7b4ebc1f 100644 --- a/drivers/scsi/device_handler/scsi_dh_rdac.c +++ b/drivers/scsi/device_handler/scsi_dh_rdac.c @@ -574,7 +574,7 @@ static int rdac_check_sense(struct scsi_device *sdev, return SCSI_RETURN_NOT_HANDLED; } -const struct scsi_dh_devlist rdac_dev_list[] = { +static const struct scsi_dh_devlist rdac_dev_list[] = { {"IBM", "1722"}, {"IBM", "1724"}, {"IBM", "1726"}, diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c index 8dee3200750..0540ca27a44 100644 --- a/fs/jbd/transaction.c +++ b/fs/jbd/transaction.c @@ -291,7 +291,7 @@ handle_t *journal_start(journal_t *journal, int nblocks) goto out; } - lock_acquire(&handle->h_lockdep_map, 0, 0, 0, 2, _THIS_IP_); + lock_map_acquire(&handle->h_lockdep_map); out: return handle; @@ -1448,7 +1448,7 @@ int journal_stop(handle_t *handle) spin_unlock(&journal->j_state_lock); } - lock_release(&handle->h_lockdep_map, 1, _THIS_IP_); + lock_map_release(&handle->h_lockdep_map); jbd_free_handle(handle); return err; diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 4f7cadbb19f..e5d540588fa 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -301,7 +301,7 @@ handle_t *jbd2_journal_start(journal_t *journal, int nblocks) goto out; } - lock_acquire(&handle->h_lockdep_map, 0, 0, 0, 2, _THIS_IP_); + lock_map_acquire(&handle->h_lockdep_map); out: return handle; } @@ -1279,7 +1279,7 @@ int jbd2_journal_stop(handle_t *handle) spin_unlock(&journal->j_state_lock); } - lock_release(&handle->h_lockdep_map, 1, _THIS_IP_); + lock_map_release(&handle->h_lockdep_map); jbd2_free_handle(handle); return err; diff --git a/include/asm-x86/efi.h b/include/asm-x86/efi.h index 7ed2bd7a7f5..d4f2b0abe92 100644 --- a/include/asm-x86/efi.h +++ b/include/asm-x86/efi.h @@ -86,7 +86,7 @@ extern u64 efi_call6(void *fp, u64 arg1, u64 arg2, u64 arg3, efi_call6((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \ (u64)(a3), (u64)(a4), (u64)(a5), (u64)(a6)) -extern void *efi_ioremap(unsigned long addr, unsigned long size); +extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size); #endif /* CONFIG_X86_32 */ diff --git a/include/asm-x86/hw_irq.h b/include/asm-x86/hw_irq.h index 77ba51df566..edd0b95f14d 100644 --- a/include/asm-x86/hw_irq.h +++ b/include/asm-x86/hw_irq.h @@ -98,9 +98,17 @@ extern void (*const interrupt[NR_IRQS])(void); #else typedef int vector_irq_t[NR_VECTORS]; DECLARE_PER_CPU(vector_irq_t, vector_irq); -extern spinlock_t vector_lock; #endif -extern void setup_vector_irq(int cpu); + +#if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_X86_64) +extern void lock_vector_lock(void); +extern void unlock_vector_lock(void); +extern void __setup_vector_irq(int cpu); +#else +static inline void lock_vector_lock(void) {} +static inline void unlock_vector_lock(void) {} +static inline void __setup_vector_irq(int cpu) {} +#endif #endif /* !ASSEMBLY_ */ diff --git a/include/asm-x86/irq_vectors.h b/include/asm-x86/irq_vectors.h index 90b1d1f12f0..b95d167b7fb 100644 --- a/include/asm-x86/irq_vectors.h +++ b/include/asm-x86/irq_vectors.h @@ -109,7 +109,15 @@ #define LAST_VM86_IRQ 15 #define invalid_vm86_irq(irq) ((irq) < 3 || (irq) > 15) -#if !defined(CONFIG_X86_VOYAGER) +#ifdef CONFIG_X86_64 +# if NR_CPUS < MAX_IO_APICS +# define NR_IRQS (NR_VECTORS + (32 * NR_CPUS)) +# else +# define NR_IRQS (NR_VECTORS + (32 * MAX_IO_APICS)) +# endif +# define NR_IRQ_VECTORS NR_IRQS + +#elif !defined(CONFIG_X86_VOYAGER) # if defined(CONFIG_X86_IO_APIC) || defined(CONFIG_PARAVIRT) || defined(CONFIG_X86_VISWS) diff --git a/include/linux/agp_backend.h b/include/linux/agp_backend.h index 972b12bcfb3..2b8df8b420f 100644 --- a/include/linux/agp_backend.h +++ b/include/linux/agp_backend.h @@ -30,6 +30,8 @@ #ifndef _AGP_BACKEND_H #define _AGP_BACKEND_H 1 +#include <linux/list.h> + enum chipset_type { NOT_SUPPORTED, SUPPORTED, @@ -78,6 +80,8 @@ struct agp_memory { bool is_bound; bool is_flushed; bool vmalloc_flag; + /* list of agp_memory mapped to the aperture */ + struct list_head mapped_list; }; #define AGP_NORMAL_MEMORY 0 @@ -96,6 +100,7 @@ extern struct agp_memory *agp_allocate_memory(struct agp_bridge_data *, size_t, extern int agp_copy_info(struct agp_bridge_data *, struct agp_kern_info *); extern int agp_bind_memory(struct agp_memory *, off_t); extern int agp_unbind_memory(struct agp_memory *); +extern int agp_rebind_memory(void); extern void agp_enable(struct agp_bridge_data *, u32); extern struct agp_bridge_data *agp_backend_acquire(struct pci_dev *); extern void agp_backend_release(struct agp_bridge_data *); diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 2486eb4edbf..331e5f1c2d8 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -89,6 +89,7 @@ struct lock_class { struct lockdep_subclass_key *key; unsigned int subclass; + unsigned int dep_gen_id; /* * IRQ/softirq usage tracking bits: @@ -189,6 +190,14 @@ struct lock_chain { u64 chain_key; }; +#define MAX_LOCKDEP_KEYS_BITS 13 +/* + * Subtract one because we offset hlock->class_idx by 1 in order + * to make 0 mean no class. This avoids overflowing the class_idx + * bitfield and hitting the BUG in hlock_class(). + */ +#define MAX_LOCKDEP_KEYS ((1UL << MAX_LOCKDEP_KEYS_BITS) - 1) + struct held_lock { /* * One-way hash of the dependency chain up to this point. We @@ -205,14 +214,14 @@ struct held_lock { * with zero), here we store the previous hash value: */ u64 prev_chain_key; - struct lock_class *class; unsigned long acquire_ip; struct lockdep_map *instance; - + struct lockdep_map *nest_lock; #ifdef CONFIG_LOCK_STAT u64 waittime_stamp; u64 holdtime_stamp; #endif + unsigned int class_idx:MAX_LOCKDEP_KEYS_BITS; /* * The lock-stack is unified in that the lock chains of interrupt * contexts nest ontop of process context chains, but we 'separate' @@ -226,11 +235,11 @@ struct held_lock { * The following field is used to detect when we cross into an * interrupt context: */ - int irq_context; - int trylock; - int read; - int check; - int hardirqs_off; + unsigned int irq_context:2; /* bit 0 - soft, bit 1 - hard */ + unsigned int trylock:1; + unsigned int read:2; /* see lock_acquire() comment */ + unsigned int check:2; /* see lock_acquire() comment */ + unsigned int hardirqs_off:1; }; /* @@ -294,11 +303,15 @@ extern void lockdep_init_map(struct lockdep_map *lock, const char *name, * 2: full validation */ extern void lock_acquire(struct lockdep_map *lock, unsigned int subclass, - int trylock, int read, int check, unsigned long ip); + int trylock, int read, int check, + struct lockdep_map *nest_lock, unsigned long ip); extern void lock_release(struct lockdep_map *lock, int nested, unsigned long ip); +extern void lock_set_subclass(struct lockdep_map *lock, unsigned int subclass, + unsigned long ip); + # define INIT_LOCKDEP .lockdep_recursion = 0, #define lockdep_depth(tsk) (debug_locks ? (tsk)->lockdep_depth : 0) @@ -313,8 +326,9 @@ static inline void lockdep_on(void) { } -# define lock_acquire(l, s, t, r, c, i) do { } while (0) +# define lock_acquire(l, s, t, r, c, n, i) do { } while (0) # define lock_release(l, n, i) do { } while (0) +# define lock_set_subclass(l, s, i) do { } while (0) # define lockdep_init() do { } while (0) # define lockdep_info() do { } while (0) # define lockdep_init_map(lock, name, key, sub) do { (void)(key); } while (0) @@ -400,9 +414,11 @@ static inline void print_irqtrace_events(struct task_struct *curr) #ifdef CONFIG_DEBUG_LOCK_ALLOC # ifdef CONFIG_PROVE_LOCKING -# define spin_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 2, i) +# define spin_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 2, NULL, i) +# define spin_acquire_nest(l, s, t, n, i) lock_acquire(l, s, t, 0, 2, n, i) # else -# define spin_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 1, i) +# define spin_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 1, NULL, i) +# define spin_acquire_nest(l, s, t, n, i) lock_acquire(l, s, t, 0, 1, NULL, i) # endif # define spin_release(l, n, i) lock_release(l, n, i) #else @@ -412,11 +428,11 @@ static inline void print_irqtrace_events(struct task_struct *curr) #ifdef CONFIG_DEBUG_LOCK_ALLOC # ifdef CONFIG_PROVE_LOCKING -# define rwlock_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 2, i) -# define rwlock_acquire_read(l, s, t, i) lock_acquire(l, s, t, 2, 2, i) +# define rwlock_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 2, NULL, i) +# define rwlock_acquire_read(l, s, t, i) lock_acquire(l, s, t, 2, 2, NULL, i) # else -# define rwlock_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 1, i) -# define rwlock_acquire_read(l, s, t, i) lock_acquire(l, s, t, 2, 1, i) +# define rwlock_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 1, NULL, i) +# define rwlock_acquire_read(l, s, t, i) lock_acquire(l, s, t, 2, 1, NULL, i) # endif # define rwlock_release(l, n, i) lock_release(l, n, i) #else @@ -427,9 +443,9 @@ static inline void print_irqtrace_events(struct task_struct *curr) #ifdef CONFIG_DEBUG_LOCK_ALLOC # ifdef CONFIG_PROVE_LOCKING -# define mutex_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 2, i) +# define mutex_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 2, NULL, i) # else -# define mutex_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 1, i) +# define mutex_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 1, NULL, i) # endif # define mutex_release(l, n, i) lock_release(l, n, i) #else @@ -439,11 +455,11 @@ static inline void print_irqtrace_events(struct task_struct *curr) #ifdef CONFIG_DEBUG_LOCK_ALLOC # ifdef CONFIG_PROVE_LOCKING -# define rwsem_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 2, i) -# define rwsem_acquire_read(l, s, t, i) lock_acquire(l, s, t, 1, 2, i) +# define rwsem_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 2, NULL, i) +# define rwsem_acquire_read(l, s, t, i) lock_acquire(l, s, t, 1, 2, NULL, i) # else -# define rwsem_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 1, i) -# define rwsem_acquire_read(l, s, t, i) lock_acquire(l, s, t, 1, 1, i) +# define rwsem_acquire(l, s, t, i) lock_acquire(l, s, t, 0, 1, NULL, i) +# define rwsem_acquire_read(l, s, t, i) lock_acquire(l, s, t, 1, 1, NULL, i) # endif # define rwsem_release(l, n, i) lock_release(l, n, i) #else @@ -452,4 +468,16 @@ static inline void print_irqtrace_events(struct task_struct *curr) # define rwsem_release(l, n, i) do { } while (0) #endif +#ifdef CONFIG_DEBUG_LOCK_ALLOC +# ifdef CONFIG_PROVE_LOCKING +# define lock_map_acquire(l) lock_acquire(l, 0, 0, 0, 2, NULL, _THIS_IP_) +# else +# define lock_map_acquire(l) lock_acquire(l, 0, 0, 0, 1, NULL, _THIS_IP_) +# endif +# define lock_map_release(l) lock_release(l, 1, _THIS_IP_) +#else +# define lock_map_acquire(l) do { } while (0) +# define lock_map_release(l) do { } while (0) +#endif + #endif /* __LINUX_LOCKDEP_H */ diff --git a/include/linux/rcuclassic.h b/include/linux/rcuclassic.h index 8c774905dcf..4ab84362272 100644 --- a/include/linux/rcuclassic.h +++ b/include/linux/rcuclassic.h @@ -117,7 +117,7 @@ extern int rcu_needs_cpu(int cpu); #ifdef CONFIG_DEBUG_LOCK_ALLOC extern struct lockdep_map rcu_lock_map; # define rcu_read_acquire() \ - lock_acquire(&rcu_lock_map, 0, 0, 2, 1, _THIS_IP_) + lock_acquire(&rcu_lock_map, 0, 0, 2, 1, NULL, _THIS_IP_) # define rcu_read_release() lock_release(&rcu_lock_map, 1, _THIS_IP_) #else # define rcu_read_acquire() do { } while (0) diff --git a/include/linux/sched.h b/include/linux/sched.h index 5270d449ff9..5850bfb968a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1551,16 +1551,10 @@ static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask) extern unsigned long long sched_clock(void); -#ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK -static inline void sched_clock_init(void) -{ -} - -static inline u64 sched_clock_cpu(int cpu) -{ - return sched_clock(); -} +extern void sched_clock_init(void); +extern u64 sched_clock_cpu(int cpu); +#ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK static inline void sched_clock_tick(void) { } @@ -1572,28 +1566,11 @@ static inline void sched_clock_idle_sleep_event(void) static inline void sched_clock_idle_wakeup_event(u64 delta_ns) { } - -#ifdef CONFIG_NO_HZ -static inline void sched_clock_tick_stop(int cpu) -{ -} - -static inline void sched_clock_tick_start(int cpu) -{ -} -#endif - -#else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */ -extern void sched_clock_init(void); -extern u64 sched_clock_cpu(int cpu); +#else extern void sched_clock_tick(void); extern void sched_clock_idle_sleep_event(void); extern void sched_clock_idle_wakeup_event(u64 delta_ns); -#ifdef CONFIG_NO_HZ -extern void sched_clock_tick_stop(int cpu); -extern void sched_clock_tick_start(int cpu); #endif -#endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */ /* * For kernel-internal use: high-speed (but slightly incorrect) per-cpu diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 61e5610ad16..e0c0fccced4 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -183,8 +183,14 @@ do { \ #ifdef CONFIG_DEBUG_LOCK_ALLOC # define spin_lock_nested(lock, subclass) _spin_lock_nested(lock, subclass) +# define spin_lock_nest_lock(lock, nest_lock) \ + do { \ + typecheck(struct lockdep_map *, &(nest_lock)->dep_map);\ + _spin_lock_nest_lock(lock, &(nest_lock)->dep_map); \ + } while (0) #else # define spin_lock_nested(lock, subclass) _spin_lock(lock) +# define spin_lock_nest_lock(lock, nest_lock) _spin_lock(lock) #endif #define write_lock(lock) _write_lock(lock) diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h index 8a2307ce729..d79845d034b 100644 --- a/include/linux/spinlock_api_smp.h +++ b/include/linux/spinlock_api_smp.h @@ -22,6 +22,8 @@ int in_lock_functions(unsigned long addr); void __lockfunc _spin_lock(spinlock_t *lock) __acquires(lock); void __lockfunc _spin_lock_nested(spinlock_t *lock, int subclass) __acquires(lock); +void __lockfunc _spin_lock_nest_lock(spinlock_t *lock, struct lockdep_map *map) + __acquires(lock); void __lockfunc _read_lock(rwlock_t *lock) __acquires(lock); void __lockfunc _write_lock(rwlock_t *lock) __acquires(lock); void __lockfunc _spin_lock_bh(spinlock_t *lock) __acquires(lock); diff --git a/kernel/Kconfig.hz b/kernel/Kconfig.hz index 382dd5a8b2d..94fabd534b0 100644 --- a/kernel/Kconfig.hz +++ b/kernel/Kconfig.hz @@ -55,4 +55,4 @@ config HZ default 1000 if HZ_1000 config SCHED_HRTICK - def_bool HIGH_RES_TIMERS && USE_GENERIC_SMP_HELPERS + def_bool HIGH_RES_TIMERS && (!SMP || USE_GENERIC_SMP_HELPERS) diff --git a/kernel/cpu.c b/kernel/cpu.c index e202a68d1cc..c977c339f55 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -349,6 +349,8 @@ static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen) goto out_notify; BUG_ON(!cpu_online(cpu)); + cpu_set(cpu, cpu_active_map); + /* Now call notifier in preparation. */ raw_notifier_call_chain(&cpu_chain, CPU_ONLINE | mod, hcpu); @@ -383,9 +385,6 @@ int __cpuinit cpu_up(unsigned int cpu) err = _cpu_up(cpu, 0); - if (cpu_online(cpu)) - cpu_set(cpu, cpu_active_map); - out: cpu_maps_update_done(); return err; diff --git a/kernel/lockdep.c b/kernel/lockdep.c index d38a6436297..1aa91fd6b06 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -124,6 +124,15 @@ static struct lock_list list_entries[MAX_LOCKDEP_ENTRIES]; unsigned long nr_lock_classes; static struct lock_class lock_classes[MAX_LOCKDEP_KEYS]; +static inline struct lock_class *hlock_class(struct held_lock *hlock) +{ + if (!hlock->class_idx) { + DEBUG_LOCKS_WARN_ON(1); + return NULL; + } + return lock_classes + hlock->class_idx - 1; +} + #ifdef CONFIG_LOCK_STAT static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS], lock_stats); @@ -222,7 +231,7 @@ static void lock_release_holdtime(struct held_lock *hlock) holdtime = sched_clock() - hlock->holdtime_stamp; - stats = get_lock_stats(hlock->class); + stats = get_lock_stats(hlock_class(hlock)); if (hlock->read) lock_time_inc(&stats->read_holdtime, holdtime); else @@ -372,6 +381,19 @@ unsigned int nr_process_chains; unsigned int max_lockdep_depth; unsigned int max_recursion_depth; +static unsigned int lockdep_dependency_gen_id; + +static bool lockdep_dependency_visit(struct lock_class *source, + unsigned int depth) +{ + if (!depth) + lockdep_dependency_gen_id++; + if (source->dep_gen_id == lockdep_dependency_gen_id) + return true; + source->dep_gen_id = lockdep_dependency_gen_id; + return false; +} + #ifdef CONFIG_DEBUG_LOCKDEP /* * We cannot printk in early bootup code. Not even early_printk() @@ -505,7 +527,7 @@ static void print_lockdep_cache(struct lockdep_map *lock) static void print_lock(struct held_lock *hlock) { - print_lock_name(hlock->class); + print_lock_name(hlock_class(hlock)); printk(", at: "); print_ip_sym(hlock->acquire_ip); } @@ -558,6 +580,9 @@ static void print_lock_dependencies(struct lock_class *class, int depth) { struct lock_list *entry; + if (lockdep_dependency_visit(class, depth)) + return; + if (DEBUG_LOCKS_WARN_ON(depth >= 20)) return; @@ -932,7 +957,7 @@ static noinline int print_circular_bug_tail(void) if (debug_locks_silent) return 0; - this.class = check_source->class; + this.class = hlock_class(check_source); if (!save_trace(&this.trace)) return 0; @@ -959,6 +984,67 @@ static int noinline print_infinite_recursion_bug(void) return 0; } +unsigned long __lockdep_count_forward_deps(struct lock_class *class, + unsigned int depth) +{ + struct lock_list *entry; + unsigned long ret = 1; + + if (lockdep_dependency_visit(class, depth)) + return 0; + + /* + * Recurse this class's dependency list: + */ + list_for_each_entry(entry, &class->locks_after, entry) + ret += __lockdep_count_forward_deps(entry->class, depth + 1); + + return ret; +} + +unsigned long lockdep_count_forward_deps(struct lock_class *class) +{ + unsigned long ret, flags; + + local_irq_save(flags); + __raw_spin_lock(&lockdep_lock); + ret = __lockdep_count_forward_deps(class, 0); + __raw_spin_unlock(&lockdep_lock); + local_irq_restore(flags); + + return ret; +} + +unsigned long __lockdep_count_backward_deps(struct lock_class *class, + unsigned int depth) +{ + struct lock_list *entry; + unsigned long ret = 1; + + if (lockdep_dependency_visit(class, depth)) + return 0; + /* + * Recurse this class's dependency list: + */ + list_for_each_entry(entry, &class->locks_before, entry) + ret += __lockdep_count_backward_deps(entry->class, depth + 1); + + return ret; +} + +unsigned long lockdep_count_backward_deps(struct lock_class *class) +{ + unsigned long ret, flags; + + local_irq_save(flags); + __raw_spin_lock(&lockdep_lock); + ret = __lockdep_count_backward_deps(class, 0); + __raw_spin_unlock(&lockdep_lock); + local_irq_restore(flags); + + return ret; +} + /* * Prove that the dependency graph starting at <entry> can not * lead to <target>. Print an error and return 0 if it does. @@ -968,6 +1054,9 @@ check_noncircular(struct lock_class *source, unsigned int depth) { struct lock_list *entry; + if (lockdep_dependency_visit(source, depth)) + return 1; + debug_atomic_inc(&nr_cyclic_check_recursions); if (depth > max_recursion_depth) max_recursion_depth = depth; @@ -977,7 +1066,7 @@ check_noncircular(struct lock_class *source, unsigned int depth) * Check this lock's dependency list: */ list_for_each_entry(entry, &source->locks_after, entry) { - if (entry->class == check_target->class) + if (entry->class == hlock_class(check_target)) return print_circular_bug_header(entry, depth+1); debug_atomic_inc(&nr_cyclic_checks); if (!check_noncircular(entry->class, depth+1)) @@ -1011,6 +1100,9 @@ find_usage_forwards(struct lock_class *source, unsigned int depth) struct lock_list *entry; int ret; + if (lockdep_dependency_visit(source, depth)) + return 1; + if (depth > max_recursion_depth) max_recursion_depth = depth; if (depth >= RECURSION_LIMIT) @@ -1050,6 +1142,9 @@ find_usage_backwards(struct lock_class *source, unsigned int depth) struct lock_list *entry; int ret; + if (lockdep_dependency_visit(source, depth)) + return 1; + if (!__raw_spin_is_locked(&lockdep_lock)) return DEBUG_LOCKS_WARN_ON(1); @@ -1064,6 +1159,11 @@ find_usage_backwards(struct lock_class *source, unsigned int depth) return 2; } + if (!source && debug_locks_off_graph_unlock()) { + WARN_ON(1); + return 0; + } + /* * Check this lock's dependency list: */ @@ -1103,9 +1203,9 @@ print_bad_irq_dependency(struct task_struct *curr, printk("\nand this task is already holding:\n"); print_lock(prev); printk("which would create a new lock dependency:\n"); - print_lock_name(prev->class); + print_lock_name(hlock_class(prev)); printk(" ->"); - print_lock_name(next->class); + print_lock_name(hlock_class(next)); printk("\n"); printk("\nbut this new dependency connects a %s-irq-safe lock:\n", @@ -1146,12 +1246,12 @@ check_usage(struct task_struct *curr, struct held_lock *prev, find_usage_bit = bit_backwards; /* fills in <backwards_match> */ - ret = find_usage_backwards(prev->class, 0); + ret = find_usage_backwards(hlock_class(prev), 0); if (!ret || ret == 1) return ret; find_usage_bit = bit_forwards; - ret = find_usage_forwards(next->class, 0); + ret = find_usage_forwards(hlock_class(next), 0); if (!ret || ret == 1) return ret; /* ret == 2 */ @@ -1272,18 +1372,32 @@ check_deadlock(struct task_struct *curr, struct held_lock *next, struct lockdep_map *next_instance, int read) { struct held_lock *prev; + struct held_lock *nest = NULL; int i; for (i = 0; i < curr->lockdep_depth; i++) { prev = curr->held_locks + i; - if (prev->class != next->class) + + if (prev->instance == next->nest_lock) + nest = prev; + + if (hlock_class(prev) != hlock_class(next)) continue; + /* * Allow read-after-read recursion of the same * lock class (i.e. read_lock(lock)+read_lock(lock)): */ if ((read == 2) && prev->read) return 2; + + /* + * We're holding the nest_lock, which serializes this lock's + * nesting behaviour. + */ + if (nest) + return 2; + return print_deadlock_bug(curr, prev, next); } return 1; @@ -1329,7 +1443,7 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, */ check_source = next; check_target = prev; - if (!(check_noncircular(next->class, 0))) + if (!(check_noncircular(hlock_class(next), 0))) return print_circular_bug_tail(); if (!check_prev_add_irq(curr, prev, next)) @@ -1353,8 +1467,8 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, * chains - the second one will be new, but L1 already has * L2 added to its dependency list, due to the first chain.) */ - list_for_each_entry(entry, &prev->class->locks_after, entry) { - if (entry->class == next->class) { + list_for_each_entry(entry, &hlock_class(prev)->locks_after, entry) { + if (entry->class == hlock_class(next)) { if (distance == 1) entry->distance = 1; return 2; @@ -1365,26 +1479,28 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, * Ok, all validations passed, add the new lock * to the previous lock's dependency list: */ - ret = add_lock_to_list(prev->class, next->class, - &prev->class->locks_after, next->acquire_ip, distance); + ret = add_lock_to_list(hlock_class(prev), hlock_class(next), + &hlock_class(prev)->locks_after, + next->acquire_ip, distance); if (!ret) return 0; - ret = add_lock_to_list(next->class, prev->class, - &next->class->locks_before, next->acquire_ip, distance); + ret = add_lock_to_list(hlock_class(next), hlock_class(prev), + &hlock_class(next)->locks_before, + next->acquire_ip, distance); if (!ret) return 0; /* * Debugging printouts: */ - if (verbose(prev->class) || verbose(next->class)) { + if (verbose(hlock_class(prev)) || verbose(hlock_class(next))) { graph_unlock(); printk("\n new dependency: "); - print_lock_name(prev->class); + print_lock_name(hlock_class(prev)); printk(" => "); - print_lock_name(next->class); + print_lock_name(hlock_class(next)); printk("\n"); dump_stack(); return graph_lock(); @@ -1481,7 +1597,7 @@ static inline int lookup_chain_cache(struct task_struct *curr, struct held_lock *hlock, u64 chain_key) { - struct lock_class *class = hlock->class; + struct lock_class *class = hlock_class(hlock); struct list_head *hash_head = chainhashentry(chain_key); struct lock_chain *chain; struct held_lock *hlock_curr, *hlock_next; @@ -1554,7 +1670,7 @@ cache_hit: if (likely(cn + chain->depth <= MAX_LOCKDEP_CHAIN_HLOCKS)) { chain->base = cn; for (j = 0; j < chain->depth - 1; j++, i++) { - int lock_id = curr->held_locks[i].class - lock_classes; + int lock_id = curr->held_locks[i].class_idx - 1; chain_hlocks[chain->base + j] = lock_id; } chain_hlocks[chain->base + j] = class - lock_classes; @@ -1650,7 +1766,7 @@ static void check_chain_key(struct task_struct *curr) WARN_ON(1); return; } - id = hlock->class - lock_classes; + id = hlock->class_idx - 1; if (DEBUG_LOCKS_WARN_ON(id >= MAX_LOCKDEP_KEYS)) return; @@ -1695,7 +1811,7 @@ print_usage_bug(struct task_struct *curr, struct held_lock *this, print_lock(this); printk("{%s} state was registered at:\n", usage_str[prev_bit]); - print_stack_trace(this->class->usage_traces + prev_bit, 1); + print_stack_trace(hlock_class(this)->usage_traces + prev_bit, 1); print_irqtrace_events(curr); printk("\nother info that might help us debug this:\n"); @@ -1714,7 +1830,7 @@ static inline int valid_state(struct task_struct *curr, struct held_lock *this, enum lock_usage_bit new_bit, enum lock_usage_bit bad_bit) { - if (unlikely(this->class->usage_mask & (1 << bad_bit))) + if (unlikely(hlock_class(this)->usage_mask & (1 << bad_bit))) return print_usage_bug(curr, this, bad_bit, new_bit); return 1; } @@ -1753,7 +1869,7 @@ print_irq_inversion_bug(struct task_struct *curr, struct lock_class *other, lockdep_print_held_locks(curr); printk("\nthe first lock's dependencies:\n"); - print_lock_dependencies(this->class, 0); + print_lock_dependencies(hlock_class(this), 0); printk("\nthe second lock's dependencies:\n"); print_lock_dependencies(other, 0); @@ -1776,7 +1892,7 @@ check_usage_forwards(struct task_struct *curr, struct held_lock *this, find_usage_bit = bit; /* fills in <forwards_match> */ - ret = find_usage_forwards(this->class, 0); + ret = find_usage_forwards(hlock_class(this), 0); if (!ret || ret == 1) return ret; @@ -1795,7 +1911,7 @@ check_usage_backwards(struct task_struct *curr, struct held_lock *this, find_usage_bit = bit; /* fills in <backwards_match> */ - ret = find_usage_backwards(this->class, 0); + ret = find_usage_backwards(hlock_class(this), 0); if (!ret || ret == 1) return ret; @@ -1861,7 +1977,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this, LOCK_ENABLED_HARDIRQS_READ, "hard-read")) return 0; #endif - if (hardirq_verbose(this->class)) + if (hardirq_verbose(hlock_class(this))) ret = 2; break; case LOCK_USED_IN_SOFTIRQ: @@ -1886,7 +2002,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this, LOCK_ENABLED_SOFTIRQS_READ, "soft-read")) return 0; #endif - if (softirq_verbose(this->class)) + if (softirq_verbose(hlock_class(this))) ret = 2; break; case LOCK_USED_IN_HARDIRQ_READ: @@ -1899,7 +2015,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this, if (!check_usage_forwards(curr, this, LOCK_ENABLED_HARDIRQS, "hard")) return 0; - if (hardirq_verbose(this->class)) + if (hardirq_verbose(hlock_class(this))) ret = 2; break; case LOCK_USED_IN_SOFTIRQ_READ: @@ -1912,7 +2028,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this, if (!check_usage_forwards(curr, this, LOCK_ENABLED_SOFTIRQS, "soft")) return 0; - if (softirq_verbose(this->class)) + if (softirq_verbose(hlock_class(this))) ret = 2; break; case LOCK_ENABLED_HARDIRQS: @@ -1938,7 +2054,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this, LOCK_USED_IN_HARDIRQ_READ, "hard-read")) return 0; #endif - if (hardirq_verbose(this->class)) + if (hardirq_verbose(hlock_class(this))) ret = 2; break; case LOCK_ENABLED_SOFTIRQS: @@ -1964,7 +2080,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this, LOCK_USED_IN_SOFTIRQ_READ, "soft-read")) return 0; #endif - if (softirq_verbose(this->class)) + if (softirq_verbose(hlock_class(this))) ret = 2; break; case LOCK_ENABLED_HARDIRQS_READ: @@ -1979,7 +2095,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this, LOCK_USED_IN_HARDIRQ, "hard")) return 0; #endif - if (hardirq_verbose(this->class)) + if (hardirq_verbose(hlock_class(this))) ret = 2; break; case LOCK_ENABLED_SOFTIRQS_READ: @@ -1994,7 +2110,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this, LOCK_USED_IN_SOFTIRQ, "soft")) return 0; #endif - if (softirq_verbose(this->class)) + if (softirq_verbose(hlock_class(this))) ret = 2; break; default: @@ -2310,7 +2426,7 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this, * If already set then do not dirty the cacheline, * nor do any checks: */ - if (likely(this->class->usage_mask & new_mask)) + if (likely(hlock_class(this)->usage_mask & new_mask)) return 1; if (!graph_lock()) @@ -2318,14 +2434,14 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this, /* * Make sure we didnt race: */ - if (unlikely(this->class->usage_mask & new_mask)) { + if (unlikely(hlock_class(this)->usage_mask & new_mask)) { graph_unlock(); return 1; } - this->class->usage_mask |= new_mask; + hlock_class(this)->usage_mask |= new_mask; - if (!save_trace(this->class->usage_traces + new_bit)) + if (!save_trace(hlock_class(this)->usage_traces + new_bit)) return 0; switch (new_bit) { @@ -2405,7 +2521,7 @@ EXPORT_SYMBOL_GPL(lockdep_init_map); */ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, int trylock, int read, int check, int hardirqs_off, - unsigned long ip) + struct lockdep_map *nest_lock, unsigned long ip) { struct task_struct *curr = current; struct lock_class *class = NULL; @@ -2459,10 +2575,12 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, return 0; hlock = curr->held_locks + depth; - - hlock->class = class; + if (DEBUG_LOCKS_WARN_ON(!class)) + return 0; + hlock->class_idx = class - lock_classes + 1; hlock->acquire_ip = ip; hlock->instance = lock; + hlock->nest_lock = nest_lock; hlock->trylock = trylock; hlock->read = read; hlock->check = check; @@ -2574,6 +2692,55 @@ static int check_unlock(struct task_struct *curr, struct lockdep_map *lock, return 1; } +static int +__lock_set_subclass(struct lockdep_map *lock, + unsigned int subclass, unsigned long ip) +{ + struct task_struct *curr = current; + struct held_lock *hlock, *prev_hlock; + struct lock_class *class; + unsigned int depth; + int i; + + depth = curr->lockdep_depth; + if (DEBUG_LOCKS_WARN_ON(!depth)) + return 0; + + prev_hlock = NULL; + for (i = depth-1; i >= 0; i--) { + hlock = curr->held_locks + i; + /* + * We must not cross into another context: + */ + if (prev_hlock && prev_hlock->irq_context != hlock->irq_context) + break; + if (hlock->instance == lock) + goto found_it; + prev_hlock = hlock; + } + return print_unlock_inbalance_bug(curr, lock, ip); + +found_it: + class = register_lock_class(lock, subclass, 0); + hlock->class_idx = class - lock_classes + 1; + + curr->lockdep_depth = i; + curr->curr_chain_key = hlock->prev_chain_key; + + for (; i < depth; i++) { + hlock = curr->held_locks + i; + if (!__lock_acquire(hlock->instance, + hlock_class(hlock)->subclass, hlock->trylock, + hlock->read, hlock->check, hlock->hardirqs_off, + hlock->nest_lock, hlock->acquire_ip)) + return 0; + } + + if (DEBUG_LOCKS_WARN_ON(curr->lockdep_depth != depth)) + return 0; + return 1; +} + /* * Remove the lock to the list of currently held locks in a * potentially non-nested (out of order) manner. This is a @@ -2624,9 +2791,9 @@ found_it: for (i++; i < depth; i++) { hlock = curr->held_locks + i; if (!__lock_acquire(hlock->instance, - hlock->class->subclass, hlock->trylock, + hlock_class(hlock)->subclass, hlock->trylock, hlock->read, hlock->check, hlock->hardirqs_off, - hlock->acquire_ip)) + hlock->nest_lock, hlock->acquire_ip)) return 0; } @@ -2669,7 +2836,7 @@ static int lock_release_nested(struct task_struct *curr, #ifdef CONFIG_DEBUG_LOCKDEP hlock->prev_chain_key = 0; - hlock->class = NULL; + hlock->class_idx = 0; hlock->acquire_ip = 0; hlock->irq_context = 0; #endif @@ -2738,18 +2905,36 @@ static void check_flags(unsigned long flags) #endif } +void +lock_set_subclass(struct lockdep_map *lock, + unsigned int subclass, unsigned long ip) +{ + unsigned long flags; + + if (unlikely(current->lockdep_recursion)) + return; + + raw_local_irq_save(flags); + current->lockdep_recursion = 1; + check_flags(flags); + if (__lock_set_subclass(lock, subclass, ip)) + check_chain_key(current); + current->lockdep_recursion = 0; + raw_local_irq_restore(flags); +} + +EXPORT_SYMBOL_GPL(lock_set_subclass); + /* * We are not always called with irqs disabled - do that here, * and also avoid lockdep recursion: */ void lock_acquire(struct lockdep_map *lock, unsigned int subclass, - int trylock, int read, int check, unsigned long ip) + int trylock, int read, int check, + struct lockdep_map *nest_lock, unsigned long ip) { unsigned long flags; - if (unlikely(!lock_stat && !prove_locking)) - return; - if (unlikely(current->lockdep_recursion)) return; @@ -2758,7 +2943,7 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass, current->lockdep_recursion = 1; __lock_acquire(lock, subclass, trylock, read, check, - irqs_disabled_flags(flags), ip); + irqs_disabled_flags(flags), nest_lock, ip); current->lockdep_recursion = 0; raw_local_irq_restore(flags); } @@ -2770,9 +2955,6 @@ void lock_release(struct lockdep_map *lock, int nested, { unsigned long flags; - if (unlikely(!lock_stat && !prove_locking)) - return; - if (unlikely(current->lockdep_recursion)) return; @@ -2845,9 +3027,9 @@ __lock_contended(struct lockdep_map *lock, unsigned long ip) found_it: hlock->waittime_stamp = sched_clock(); - point = lock_contention_point(hlock->class, ip); + point = lock_contention_point(hlock_class(hlock), ip); - stats = get_lock_stats(hlock->class); + stats = get_lock_stats(hlock_class(hlock)); if (point < ARRAY_SIZE(stats->contention_point)) stats->contention_point[i]++; if (lock->cpu != smp_processor_id()) @@ -2893,7 +3075,7 @@ found_it: hlock->holdtime_stamp = now; } - stats = get_lock_stats(hlock->class); + stats = get_lock_stats(hlock_class(hlock)); if (waittime) { if (hlock->read) lock_time_inc(&stats->read_waittime, waittime); @@ -2988,6 +3170,7 @@ static void zap_class(struct lock_class *class) list_del_rcu(&class->hash_entry); list_del_rcu(&class->lock_entry); + class->key = NULL; } static inline int within(const void *addr, void *start, unsigned long size) diff --git a/kernel/lockdep_internals.h b/kernel/lockdep_internals.h index c3600a091a2..55db193d366 100644 --- a/kernel/lockdep_internals.h +++ b/kernel/lockdep_internals.h @@ -17,9 +17,6 @@ */ #define MAX_LOCKDEP_ENTRIES 8192UL -#define MAX_LOCKDEP_KEYS_BITS 11 -#define MAX_LOCKDEP_KEYS (1UL << MAX_LOCKDEP_KEYS_BITS) - #define MAX_LOCKDEP_CHAINS_BITS 14 #define MAX_LOCKDEP_CHAINS (1UL << MAX_LOCKDEP_CHAINS_BITS) @@ -53,6 +50,9 @@ extern unsigned int nr_process_chains; extern unsigned int max_lockdep_depth; extern unsigned int max_recursion_depth; +extern unsigned long lockdep_count_forward_deps(struct lock_class *); +extern unsigned long lockdep_count_backward_deps(struct lock_class *); + #ifdef CONFIG_DEBUG_LOCKDEP /* * Various lockdep statistics: diff --git a/kernel/lockdep_proc.c b/kernel/lockdep_proc.c index 9b0e940e254..fa19aee604c 100644 --- a/kernel/lockdep_proc.c +++ b/kernel/lockdep_proc.c @@ -63,34 +63,6 @@ static void l_stop(struct seq_file *m, void *v) { } -static unsigned long count_forward_deps(struct lock_class *class) -{ - struct lock_list *entry; - unsigned long ret = 1; - - /* - * Recurse this class's dependency list: - */ - list_for_each_entry(entry, &class->locks_after, entry) - ret += count_forward_deps(entry->class); - - return ret; -} - -static unsigned long count_backward_deps(struct lock_class *class) -{ - struct lock_list *entry; - unsigned long ret = 1; - - /* - * Recurse this class's dependency list: - */ - list_for_each_entry(entry, &class->locks_before, entry) - ret += count_backward_deps(entry->class); - - return ret; -} - static void print_name(struct seq_file *m, struct lock_class *class) { char str[128]; @@ -124,10 +96,10 @@ static int l_show(struct seq_file *m, void *v) #ifdef CONFIG_DEBUG_LOCKDEP seq_printf(m, " OPS:%8ld", class->ops); #endif - nr_forward_deps = count_forward_deps(class); + nr_forward_deps = lockdep_count_forward_deps(class); seq_printf(m, " FD:%5ld", nr_forward_deps); - nr_backward_deps = count_backward_deps(class); + nr_backward_deps = lockdep_count_backward_deps(class); seq_printf(m, " BD:%5ld", nr_backward_deps); get_usage_chars(class, &c1, &c2, &c3, &c4); @@ -229,6 +201,9 @@ static int lc_show(struct seq_file *m, void *v) for (i = 0; i < chain->depth; i++) { class = lock_chain_get_class(chain, i); + if (!class->key) + continue; + seq_printf(m, "[%p] ", class->key); print_name(m, class); seq_puts(m, "\n"); @@ -350,7 +325,7 @@ static int lockdep_stats_show(struct seq_file *m, void *v) if (class->usage_mask & LOCKF_ENABLED_HARDIRQS_READ) nr_hardirq_read_unsafe++; - sum_forward_deps += count_forward_deps(class); + sum_forward_deps += lockdep_count_forward_deps(class); } #ifdef CONFIG_DEBUG_LOCKDEP DEBUG_LOCKS_WARN_ON(debug_atomic_read(&nr_unused_locks) != nr_unused); diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index 9a21681aa80..e36d5798cbf 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -289,21 +289,29 @@ void do_schedule_next_timer(struct siginfo *info) else schedule_next_timer(timr); - info->si_overrun = timr->it_overrun_last; + info->si_overrun += timr->it_overrun_last; } if (timr) unlock_timer(timr, flags); } -int posix_timer_event(struct k_itimer *timr,int si_private) +int posix_timer_event(struct k_itimer *timr, int si_private) { - memset(&timr->sigq->info, 0, sizeof(siginfo_t)); + /* + * FIXME: if ->sigq is queued we can race with + * dequeue_signal()->do_schedule_next_timer(). + * + * If dequeue_signal() sees the "right" value of + * si_sys_private it calls do_schedule_next_timer(). + * We re-queue ->sigq and drop ->it_lock(). + * do_schedule_next_timer() locks the timer + * and re-schedules it while ->sigq is pending. + * Not really bad, but not that we want. + */ timr->sigq->info.si_sys_private = si_private; - /* Send signal to the process that owns this timer.*/ timr->sigq->info.si_signo = timr->it_sigev_signo; - timr->sigq->info.si_errno = 0; timr->sigq->info.si_code = SI_TIMER; timr->sigq->info.si_tid = timr->it_id; timr->sigq->info.si_value = timr->it_sigev_value; @@ -435,6 +443,7 @@ static struct k_itimer * alloc_posix_timer(void) kmem_cache_free(posix_timers_cache, tmr); tmr = NULL; } + memset(&tmr->sigq->info, 0, sizeof(siginfo_t)); return tmr; } diff --git a/kernel/sched.c b/kernel/sched.c index 04160d277e7..d601fb0406c 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -600,7 +600,6 @@ struct rq { /* BKL stats */ unsigned int bkl_count; #endif - struct lock_class_key rq_lock_key; }; static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); @@ -834,7 +833,7 @@ static inline u64 global_rt_period(void) static inline u64 global_rt_runtime(void) { - if (sysctl_sched_rt_period < 0) + if (sysctl_sched_rt_runtime < 0) return RUNTIME_INF; return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC; @@ -2759,10 +2758,10 @@ static void double_rq_lock(struct rq *rq1, struct rq *rq2) } else { if (rq1 < rq2) { spin_lock(&rq1->lock); - spin_lock(&rq2->lock); + spin_lock_nested(&rq2->lock, SINGLE_DEPTH_NESTING); } else { spin_lock(&rq2->lock); - spin_lock(&rq1->lock); + spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING); } } update_rq_clock(rq1); @@ -2805,14 +2804,21 @@ static int double_lock_balance(struct rq *this_rq, struct rq *busiest) if (busiest < this_rq) { spin_unlock(&this_rq->lock); spin_lock(&busiest->lock); - spin_lock(&this_rq->lock); + spin_lock_nested(&this_rq->lock, SINGLE_DEPTH_NESTING); ret = 1; } else - spin_lock(&busiest->lock); + spin_lock_nested(&busiest->lock, SINGLE_DEPTH_NESTING); } return ret; } +static void double_unlock_balance(struct rq *this_rq, struct rq *busiest) + __releases(busiest->lock) +{ + spin_unlock(&busiest->lock); + lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_); +} + /* * If dest_cpu is allowed for this process, migrate the task to it. * This is accomplished by forcing the cpu_allowed mask to only @@ -3637,7 +3643,7 @@ redo: ld_moved = move_tasks(this_rq, this_cpu, busiest, imbalance, sd, CPU_NEWLY_IDLE, &all_pinned); - spin_unlock(&busiest->lock); + double_unlock_balance(this_rq, busiest); if (unlikely(all_pinned)) { cpu_clear(cpu_of(busiest), *cpus); @@ -3752,7 +3758,7 @@ static void active_load_balance(struct rq *busiest_rq, int busiest_cpu) else schedstat_inc(sd, alb_failed); } - spin_unlock(&target_rq->lock); + double_unlock_balance(busiest_rq, target_rq); } #ifdef CONFIG_NO_HZ @@ -8000,7 +8006,6 @@ void __init sched_init(void) rq = cpu_rq(i); spin_lock_init(&rq->lock); - lockdep_set_class(&rq->lock, &rq->rq_lock_key); rq->nr_running = 0; init_cfs_rq(&rq->cfs, rq); init_rt_rq(&rq->rt, rq); diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c index 22ed55d1167..204991a0bfa 100644 --- a/kernel/sched_clock.c +++ b/kernel/sched_clock.c @@ -32,13 +32,19 @@ #include <linux/ktime.h> #include <linux/module.h> +/* + * Scheduler clock - returns current time in nanosec units. + * This is default implementation. + * Architectures and sub-architectures can override this. + */ +unsigned long long __attribute__((weak)) sched_clock(void) +{ + return (unsigned long long)jiffies * (NSEC_PER_SEC / HZ); +} -#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK +static __read_mostly int sched_clock_running; -#define MULTI_SHIFT 15 -/* Max is double, Min is 1/2 */ -#define MAX_MULTI (2LL << MULTI_SHIFT) -#define MIN_MULTI (1LL << (MULTI_SHIFT-1)) +#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK struct sched_clock_data { /* @@ -49,14 +55,9 @@ struct sched_clock_data { raw_spinlock_t lock; unsigned long tick_jiffies; - u64 prev_raw; u64 tick_raw; u64 tick_gtod; u64 clock; - s64 multi; -#ifdef CONFIG_NO_HZ - int check_max; -#endif }; static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data); @@ -71,8 +72,6 @@ static inline struct sched_clock_data *cpu_sdc(int cpu) return &per_cpu(sched_clock_data, cpu); } -static __read_mostly int sched_clock_running; - void sched_clock_init(void) { u64 ktime_now = ktime_to_ns(ktime_get()); @@ -84,90 +83,39 @@ void sched_clock_init(void) scd->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED; scd->tick_jiffies = now_jiffies; - scd->prev_raw = 0; scd->tick_raw = 0; scd->tick_gtod = ktime_now; scd->clock = ktime_now; - scd->multi = 1 << MULTI_SHIFT; -#ifdef CONFIG_NO_HZ - scd->check_max = 1; -#endif } sched_clock_running = 1; } -#ifdef CONFIG_NO_HZ -/* - * The dynamic ticks makes the delta jiffies inaccurate. This - * prevents us from checking the maximum time update. - * Disable the maximum check during stopped ticks. - */ -void sched_clock_tick_stop(int cpu) -{ - struct sched_clock_data *scd = cpu_sdc(cpu); - - scd->check_max = 0; -} - -void sched_clock_tick_start(int cpu) -{ - struct sched_clock_data *scd = cpu_sdc(cpu); - - scd->check_max = 1; -} - -static int check_max(struct sched_clock_data *scd) -{ - return scd->check_max; -} -#else -static int check_max(struct sched_clock_data *scd) -{ - return 1; -} -#endif /* CONFIG_NO_HZ */ - /* * update the percpu scd from the raw @now value * * - filter out backward motion * - use jiffies to generate a min,max window to clip the raw values */ -static void __update_sched_clock(struct sched_clock_data *scd, u64 now, u64 *time) +static u64 __update_sched_clock(struct sched_clock_data *scd, u64 now) { unsigned long now_jiffies = jiffies; long delta_jiffies = now_jiffies - scd->tick_jiffies; u64 clock = scd->clock; u64 min_clock, max_clock; - s64 delta = now - scd->prev_raw; + s64 delta = now - scd->tick_raw; WARN_ON_ONCE(!irqs_disabled()); - - /* - * At schedule tick the clock can be just under the gtod. We don't - * want to push it too prematurely. - */ - min_clock = scd->tick_gtod + (delta_jiffies * TICK_NSEC); - if (min_clock > TICK_NSEC) - min_clock -= TICK_NSEC / 2; + min_clock = scd->tick_gtod + delta_jiffies * TICK_NSEC; if (unlikely(delta < 0)) { clock++; goto out; } - /* - * The clock must stay within a jiffie of the gtod. - * But since we may be at the start of a jiffy or the end of one - * we add another jiffy buffer. - */ - max_clock = scd->tick_gtod + (2 + delta_jiffies) * TICK_NSEC; - - delta *= scd->multi; - delta >>= MULTI_SHIFT; + max_clock = min_clock + TICK_NSEC; - if (unlikely(clock + delta > max_clock) && check_max(scd)) { + if (unlikely(clock + delta > max_clock)) { if (clock < max_clock) clock = max_clock; else @@ -180,12 +128,10 @@ static void __update_sched_clock(struct sched_clock_data *scd, u64 now, u64 *tim if (unlikely(clock < min_clock)) clock = min_clock; - if (time) - *time = clock; - else { - scd->prev_raw = now; - scd->clock = clock; - } + scd->tick_jiffies = now_jiffies; + scd->clock = clock; + + return clock; } static void lock_double_clock(struct sched_clock_data *data1, @@ -203,7 +149,7 @@ static void lock_double_clock(struct sched_clock_data *data1, u64 sched_clock_cpu(int cpu) { struct sched_clock_data *scd = cpu_sdc(cpu); - u64 now, clock; + u64 now, clock, this_clock, remote_clock; if (unlikely(!sched_clock_running)) return 0ull; @@ -212,43 +158,44 @@ u64 sched_clock_cpu(int cpu) now = sched_clock(); if (cpu != raw_smp_processor_id()) { - /* - * in order to update a remote cpu's clock based on our - * unstable raw time rebase it against: - * tick_raw (offset between raw counters) - * tick_gotd (tick offset between cpus) - */ struct sched_clock_data *my_scd = this_scd(); lock_double_clock(scd, my_scd); - now -= my_scd->tick_raw; - now += scd->tick_raw; + this_clock = __update_sched_clock(my_scd, now); + remote_clock = scd->clock; - now += my_scd->tick_gtod; - now -= scd->tick_gtod; + /* + * Use the opportunity that we have both locks + * taken to couple the two clocks: we take the + * larger time as the latest time for both + * runqueues. (this creates monotonic movement) + */ + if (likely(remote_clock < this_clock)) { + clock = this_clock; + scd->clock = clock; + } else { + /* + * Should be rare, but possible: + */ + clock = remote_clock; + my_scd->clock = remote_clock; + } __raw_spin_unlock(&my_scd->lock); - - __update_sched_clock(scd, now, &clock); - - __raw_spin_unlock(&scd->lock); - } else { __raw_spin_lock(&scd->lock); - __update_sched_clock(scd, now, NULL); - clock = scd->clock; - __raw_spin_unlock(&scd->lock); + clock = __update_sched_clock(scd, now); } + __raw_spin_unlock(&scd->lock); + return clock; } void sched_clock_tick(void) { struct sched_clock_data *scd = this_scd(); - unsigned long now_jiffies = jiffies; - s64 mult, delta_gtod, delta_raw; u64 now, now_gtod; if (unlikely(!sched_clock_running)) @@ -260,29 +207,14 @@ void sched_clock_tick(void) now = sched_clock(); __raw_spin_lock(&scd->lock); - __update_sched_clock(scd, now, NULL); + __update_sched_clock(scd, now); /* * update tick_gtod after __update_sched_clock() because that will * already observe 1 new jiffy; adding a new tick_gtod to that would * increase the clock 2 jiffies. */ - delta_gtod = now_gtod - scd->tick_gtod; - delta_raw = now - scd->tick_raw; - - if ((long)delta_raw > 0) { - mult = delta_gtod << MULTI_SHIFT; - do_div(mult, delta_raw); - scd->multi = mult; - if (scd->multi > MAX_MULTI) - scd->multi = MAX_MULTI; - else if (scd->multi < MIN_MULTI) - scd->multi = MIN_MULTI; - } else - scd->multi = 1 << MULTI_SHIFT; - scd->tick_raw = now; scd->tick_gtod = now_gtod; - scd->tick_jiffies = now_jiffies; __raw_spin_unlock(&scd->lock); } @@ -301,7 +233,6 @@ EXPORT_SYMBOL_GPL(sched_clock_idle_sleep_event); void sched_clock_idle_wakeup_event(u64 delta_ns) { struct sched_clock_data *scd = this_scd(); - u64 now = sched_clock(); /* * Override the previous timestamp and ignore all @@ -310,27 +241,30 @@ void sched_clock_idle_wakeup_event(u64 delta_ns) * rq clock: */ __raw_spin_lock(&scd->lock); - scd->prev_raw = now; scd->clock += delta_ns; - scd->multi = 1 << MULTI_SHIFT; __raw_spin_unlock(&scd->lock); touch_softlockup_watchdog(); } EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event); -#endif +#else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */ -/* - * Scheduler clock - returns current time in nanosec units. - * This is default implementation. - * Architectures and sub-architectures can override this. - */ -unsigned long long __attribute__((weak)) sched_clock(void) +void sched_clock_init(void) { - return (unsigned long long)jiffies * (NSEC_PER_SEC / HZ); + sched_clock_running = 1; } +u64 sched_clock_cpu(int cpu) +{ + if (unlikely(!sched_clock_running)) + return 0; + + return sched_clock(); +} + +#endif + unsigned long long cpu_clock(int cpu) { unsigned long long clock; diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index cf2cd6ce4cb..fb8994c6d4b 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -899,7 +899,7 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p) * doesn't make sense. Rely on vruntime for fairness. */ if (rq->curr != p) - delta = max(10000LL, delta); + delta = max_t(s64, 10000LL, delta); hrtick_start(rq, delta); } @@ -1442,18 +1442,23 @@ __load_balance_iterator(struct cfs_rq *cfs_rq, struct list_head *next) struct task_struct *p = NULL; struct sched_entity *se; - while (next != &cfs_rq->tasks) { + if (next == &cfs_rq->tasks) + return NULL; + + /* Skip over entities that are not tasks */ + do { se = list_entry(next, struct sched_entity, group_node); next = next->next; + } while (next != &cfs_rq->tasks && !entity_is_task(se)); - /* Skip over entities that are not tasks */ - if (entity_is_task(se)) { - p = task_of(se); - break; - } - } + if (next == &cfs_rq->tasks) + return NULL; cfs_rq->balance_iterator = next; + + if (entity_is_task(se)) + p = task_of(se); + return p; } diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index 908c04f9dad..6163e4cf885 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -861,6 +861,8 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p) #define RT_MAX_TRIES 3 static int double_lock_balance(struct rq *this_rq, struct rq *busiest); +static void double_unlock_balance(struct rq *this_rq, struct rq *busiest); + static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep); static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu) @@ -1022,7 +1024,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq) break; /* try again */ - spin_unlock(&lowest_rq->lock); + double_unlock_balance(rq, lowest_rq); lowest_rq = NULL; } @@ -1091,7 +1093,7 @@ static int push_rt_task(struct rq *rq) resched_task(lowest_rq->curr); - spin_unlock(&lowest_rq->lock); + double_unlock_balance(rq, lowest_rq); ret = 1; out: @@ -1197,7 +1199,7 @@ static int pull_rt_task(struct rq *this_rq) } skip: - spin_unlock(&src_rq->lock); + double_unlock_balance(this_rq, src_rq); } return ret; diff --git a/kernel/signal.c b/kernel/signal.c index 954f77d7e3b..c539f60c6f4 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1304,6 +1304,7 @@ int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group) q->info.si_overrun++; goto out; } + q->info.si_overrun = 0; signalfd_notify(t, sig); pending = group ? &t->signal->shared_pending : &t->pending; diff --git a/kernel/smp.c b/kernel/smp.c index 96fc7c0edc5..e6084f6efb4 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -260,6 +260,41 @@ void __smp_call_function_single(int cpu, struct call_single_data *data) generic_exec_single(cpu, data); } +/* Dummy function */ +static void quiesce_dummy(void *unused) +{ +} + +/* + * Ensure stack based data used in call function mask is safe to free. + * + * This is needed by smp_call_function_mask when using on-stack data, because + * a single call function queue is shared by all CPUs, and any CPU may pick up + * the data item on the queue at any time before it is deleted. So we need to + * ensure that all CPUs have transitioned through a quiescent state after + * this call. + * + * This is a very slow function, implemented by sending synchronous IPIs to + * all possible CPUs. For this reason, we have to alloc data rather than use + * stack based data even in the case of synchronous calls. The stack based + * data is then just used for deadlock/oom fallback which will be very rare. + * + * If a faster scheme can be made, we could go back to preferring stack based + * data -- the data allocation/free is non-zero cost. + */ +static void smp_call_function_mask_quiesce_stack(cpumask_t mask) +{ + struct call_single_data data; + int cpu; + + data.func = quiesce_dummy; + data.info = NULL; + data.flags = CSD_FLAG_WAIT; + + for_each_cpu_mask(cpu, mask) + generic_exec_single(cpu, &data); +} + /** * smp_call_function_mask(): Run a function on a set of other CPUs. * @mask: The set of cpus to run on. @@ -285,6 +320,7 @@ int smp_call_function_mask(cpumask_t mask, void (*func)(void *), void *info, cpumask_t allbutself; unsigned long flags; int cpu, num_cpus; + int slowpath = 0; /* Can deadlock when called with interrupts disabled */ WARN_ON(irqs_disabled()); @@ -306,15 +342,16 @@ int smp_call_function_mask(cpumask_t mask, void (*func)(void *), void *info, return smp_call_function_single(cpu, func, info, wait); } - if (!wait) { - data = kmalloc(sizeof(*data), GFP_ATOMIC); - if (data) - data->csd.flags = CSD_FLAG_ALLOC; - } - if (!data) { + data = kmalloc(sizeof(*data), GFP_ATOMIC); + if (data) { + data->csd.flags = CSD_FLAG_ALLOC; + if (wait) + data->csd.flags |= CSD_FLAG_WAIT; + } else { data = &d; data->csd.flags = CSD_FLAG_WAIT; wait = 1; + slowpath = 1; } spin_lock_init(&data->lock); @@ -331,8 +368,11 @@ int smp_call_function_mask(cpumask_t mask, void (*func)(void *), void *info, arch_send_call_function_ipi(mask); /* optionally wait for the CPUs to complete */ - if (wait) + if (wait) { csd_flag_wait(&data->csd); + if (unlikely(slowpath)) + smp_call_function_mask_quiesce_stack(allbutself); + } return 0; } diff --git a/kernel/spinlock.c b/kernel/spinlock.c index a1fb54c93cd..44baeea94ab 100644 --- a/kernel/spinlock.c +++ b/kernel/spinlock.c @@ -292,6 +292,7 @@ void __lockfunc _spin_lock_nested(spinlock_t *lock, int subclass) } EXPORT_SYMBOL(_spin_lock_nested); + unsigned long __lockfunc _spin_lock_irqsave_nested(spinlock_t *lock, int subclass) { unsigned long flags; @@ -314,6 +315,16 @@ unsigned long __lockfunc _spin_lock_irqsave_nested(spinlock_t *lock, int subclas EXPORT_SYMBOL(_spin_lock_irqsave_nested); +void __lockfunc _spin_lock_nest_lock(spinlock_t *lock, + struct lockdep_map *nest_lock) +{ + preempt_disable(); + spin_acquire_nest(&lock->dep_map, 0, 0, nest_lock, _RET_IP_); + LOCK_CONTENDED(lock, _raw_spin_trylock, _raw_spin_lock); +} + +EXPORT_SYMBOL(_spin_lock_nest_lock); + #endif void __lockfunc _spin_unlock(spinlock_t *lock) diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 825b4c00fe4..f5da526424a 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -289,7 +289,6 @@ void tick_nohz_stop_sched_tick(int inidle) ts->tick_stopped = 1; ts->idle_jiffies = last_jiffies; rcu_enter_nohz(); - sched_clock_tick_stop(cpu); } /* @@ -392,7 +391,6 @@ void tick_nohz_restart_sched_tick(void) select_nohz_load_balancer(0); now = ktime_get(); tick_do_update_jiffies64(now); - sched_clock_tick_start(cpu); cpu_clear(cpu, nohz_cpu_mask); /* diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 4a26a1382df..4048e92aa04 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -290,11 +290,11 @@ static void run_workqueue(struct cpu_workqueue_struct *cwq) BUG_ON(get_wq_data(work) != cwq); work_clear_pending(work); - lock_acquire(&cwq->wq->lockdep_map, 0, 0, 0, 2, _THIS_IP_); - lock_acquire(&lockdep_map, 0, 0, 0, 2, _THIS_IP_); + lock_map_acquire(&cwq->wq->lockdep_map); + lock_map_acquire(&lockdep_map); f(work); - lock_release(&lockdep_map, 1, _THIS_IP_); - lock_release(&cwq->wq->lockdep_map, 1, _THIS_IP_); + lock_map_release(&lockdep_map); + lock_map_release(&cwq->wq->lockdep_map); if (unlikely(in_atomic() || lockdep_depth(current) > 0)) { printk(KERN_ERR "BUG: workqueue leaked lock or atomic: " @@ -413,8 +413,8 @@ void flush_workqueue(struct workqueue_struct *wq) int cpu; might_sleep(); - lock_acquire(&wq->lockdep_map, 0, 0, 0, 2, _THIS_IP_); - lock_release(&wq->lockdep_map, 1, _THIS_IP_); + lock_map_acquire(&wq->lockdep_map); + lock_map_release(&wq->lockdep_map); for_each_cpu_mask_nr(cpu, *cpu_map) flush_cpu_workqueue(per_cpu_ptr(wq->cpu_wq, cpu)); } @@ -441,8 +441,8 @@ int flush_work(struct work_struct *work) if (!cwq) return 0; - lock_acquire(&cwq->wq->lockdep_map, 0, 0, 0, 2, _THIS_IP_); - lock_release(&cwq->wq->lockdep_map, 1, _THIS_IP_); + lock_map_acquire(&cwq->wq->lockdep_map); + lock_map_release(&cwq->wq->lockdep_map); prev = NULL; spin_lock_irq(&cwq->lock); @@ -536,8 +536,8 @@ static void wait_on_work(struct work_struct *work) might_sleep(); - lock_acquire(&work->lockdep_map, 0, 0, 0, 2, _THIS_IP_); - lock_release(&work->lockdep_map, 1, _THIS_IP_); + lock_map_acquire(&work->lockdep_map); + lock_map_release(&work->lockdep_map); cwq = get_wq_data(work); if (!cwq) @@ -872,8 +872,8 @@ static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq) if (cwq->thread == NULL) return; - lock_acquire(&cwq->wq->lockdep_map, 0, 0, 0, 2, _THIS_IP_); - lock_release(&cwq->wq->lockdep_map, 1, _THIS_IP_); + lock_map_acquire(&cwq->wq->lockdep_map); + lock_map_release(&cwq->wq->lockdep_map); flush_cpu_workqueue(cwq); /* diff --git a/lib/debug_locks.c b/lib/debug_locks.c index 0ef01d14727..0218b4693dd 100644 --- a/lib/debug_locks.c +++ b/lib/debug_locks.c @@ -8,6 +8,7 @@ * * Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> */ +#include <linux/kernel.h> #include <linux/rwsem.h> #include <linux/mutex.h> #include <linux/module.h> @@ -37,6 +38,7 @@ int debug_locks_off(void) { if (xchg(&debug_locks, 0)) { if (!debug_locks_silent) { + oops_in_progress = 1; console_verbose(); return 1; } diff --git a/mm/mmap.c b/mm/mmap.c index 971d0eda754..339cf5c4d5d 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2273,14 +2273,14 @@ int install_special_mapping(struct mm_struct *mm, static DEFINE_MUTEX(mm_all_locks_mutex); -static void vm_lock_anon_vma(struct anon_vma *anon_vma) +static void vm_lock_anon_vma(struct mm_struct *mm, struct anon_vma *anon_vma) { if (!test_bit(0, (unsigned long *) &anon_vma->head.next)) { /* * The LSB of head.next can't change from under us * because we hold the mm_all_locks_mutex. */ - spin_lock(&anon_vma->lock); + spin_lock_nest_lock(&anon_vma->lock, &mm->mmap_sem); /* * We can safely modify head.next after taking the * anon_vma->lock. If some other vma in this mm shares @@ -2296,7 +2296,7 @@ static void vm_lock_anon_vma(struct anon_vma *anon_vma) } } -static void vm_lock_mapping(struct address_space *mapping) +static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping) { if (!test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) { /* @@ -2310,7 +2310,7 @@ static void vm_lock_mapping(struct address_space *mapping) */ if (test_and_set_bit(AS_MM_ALL_LOCKS, &mapping->flags)) BUG(); - spin_lock(&mapping->i_mmap_lock); + spin_lock_nest_lock(&mapping->i_mmap_lock, &mm->mmap_sem); } } @@ -2358,11 +2358,17 @@ int mm_take_all_locks(struct mm_struct *mm) for (vma = mm->mmap; vma; vma = vma->vm_next) { if (signal_pending(current)) goto out_unlock; - if (vma->anon_vma) - vm_lock_anon_vma(vma->anon_vma); if (vma->vm_file && vma->vm_file->f_mapping) - vm_lock_mapping(vma->vm_file->f_mapping); + vm_lock_mapping(mm, vma->vm_file->f_mapping); + } + + for (vma = mm->mmap; vma; vma = vma->vm_next) { + if (signal_pending(current)) + goto out_unlock; + if (vma->anon_vma) + vm_lock_anon_vma(mm, vma->anon_vma); } + ret = 0; out_unlock: |