diff options
112 files changed, 1366 insertions, 785 deletions
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index f48178024067..db3b1aba32a3 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -843,6 +843,7 @@ Provides counts of softirq handlers serviced since boot time, for each cpu. TASKLET: 0 0 0 290 SCHED: 27035 26983 26971 26746 HRTIMER: 0 0 0 0 + RCU: 1678 1769 2178 2250 1.3 IDE devices in /proc/ide diff --git a/MAINTAINERS b/MAINTAINERS index 502f2dd761eb..f0358cd91de3 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2291,8 +2291,7 @@ F: drivers/scsi/eata_pio.* EBTABLES M: Bart De Schuymer <bart.de.schuymer@pandora.be> -L: ebtables-user@lists.sourceforge.net -L: ebtables-devel@lists.sourceforge.net +L: netfilter-devel@vger.kernel.org W: http://ebtables.sourceforge.net/ S: Maintained F: include/linux/netfilter_bridge/ebt_*.h @@ -7007,6 +7006,13 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/mjg59/platform-drivers-x86. S: Maintained F: drivers/platform/x86 +X86 MCE INFRASTRUCTURE +M: Tony Luck <tony.luck@intel.com> +M: Borislav Petkov <bp@amd64.org> +L: linux-edac@vger.kernel.org +S: Maintained +F: arch/x86/kernel/cpu/mcheck/* + XEN HYPERVISOR INTERFACE M: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com> M: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> diff --git a/arch/arm/mach-msm/timer.c b/arch/arm/mach-msm/timer.c index 38b95e949d13..63621f152c98 100644 --- a/arch/arm/mach-msm/timer.c +++ b/arch/arm/mach-msm/timer.c @@ -23,6 +23,8 @@ #include <linux/io.h> #include <asm/mach/time.h> +#include <asm/hardware/gic.h> + #include <mach/msm_iomap.h> #include <mach/cpu.h> @@ -55,10 +57,12 @@ enum timer_location { #if defined(CONFIG_ARCH_QSD8X50) #define DGT_HZ (19200000 / 4) /* 19.2 MHz / 4 by default */ #define MSM_DGT_SHIFT (0) -#elif defined(CONFIG_ARCH_MSM7X30) || defined(CONFIG_ARCH_MSM8X60) || \ - defined(CONFIG_ARCH_MSM8960) +#elif defined(CONFIG_ARCH_MSM7X30) #define DGT_HZ (24576000 / 4) /* 24.576 MHz (LPXO) / 4 by default */ #define MSM_DGT_SHIFT (0) +#elif defined(CONFIG_ARCH_MSM8X60) || defined(CONFIG_ARCH_MSM8960) +#define DGT_HZ (27000000 / 4) /* 27 MHz (PXO) / 4 by default */ +#define MSM_DGT_SHIFT (0) #else #define DGT_HZ 19200000 /* 19.2 MHz or 600 KHz after shift */ #define MSM_DGT_SHIFT (5) @@ -100,7 +104,11 @@ static cycle_t msm_read_timer_count(struct clocksource *cs) { struct msm_clock *clk = container_of(cs, struct msm_clock, clocksource); - return readl(clk->global_counter); + /* + * Shift timer count down by a constant due to unreliable lower bits + * on some targets. + */ + return readl(clk->global_counter) >> clk->shift; } static struct msm_clock *clockevent_to_clock(struct clock_event_device *evt) diff --git a/arch/x86/include/asm/memblock.h b/arch/x86/include/asm/memblock.h index 19ae14ba6978..0cd3800f33b9 100644 --- a/arch/x86/include/asm/memblock.h +++ b/arch/x86/include/asm/memblock.h @@ -4,7 +4,6 @@ #define ARCH_DISCARD_MEMBLOCK u64 memblock_x86_find_in_range_size(u64 start, u64 *sizep, u64 align); -void memblock_x86_to_bootmem(u64 start, u64 end); void memblock_x86_reserve_range(u64 start, u64 end, char *name); void memblock_x86_free_range(u64 start, u64 end); @@ -19,5 +18,6 @@ u64 memblock_x86_hole_size(u64 start, u64 end); u64 memblock_x86_find_in_range_node(int nid, u64 start, u64 end, u64 size, u64 align); u64 memblock_x86_free_memory_in_range(u64 addr, u64 limit); u64 memblock_x86_memory_in_range(u64 addr, u64 limit); +bool memblock_x86_check_reserved_size(u64 *addrp, u64 *sizep, u64 align); #endif diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index 31d84acc1512..a518c0a45044 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -22,6 +22,8 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift) u64 product; #ifdef __i386__ u32 tmp1, tmp2; +#else + ulong tmp; #endif if (shift < 0) @@ -42,8 +44,11 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift) : "a" ((u32)delta), "1" ((u32)(delta >> 32)), "2" (mul_frac) ); #elif defined(__x86_64__) __asm__ ( - "mul %%rdx ; shrd $32,%%rdx,%%rax" - : "=a" (product) : "0" (delta), "d" ((u64)mul_frac) ); + "mul %[mul_frac] ; shrd $32, %[hi], %[lo]" + : [lo]"=a"(product), + [hi]"=d"(tmp) + : "0"(delta), + [mul_frac]"rm"((u64)mul_frac)); #else #error implement me! #endif diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index bd14bb4c8594..aee38623b768 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -565,7 +565,7 @@ gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn, static bool mapping_level_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t large_gfn) { - return gfn_to_memslot_dirty_bitmap(vcpu, large_gfn, true); + return !gfn_to_memslot_dirty_bitmap(vcpu, large_gfn, true); } static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn) diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 6c4dc010c4cb..9d03ad4dd5ec 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -121,7 +121,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker, gva_t addr, u32 access) { pt_element_t pte; - pt_element_t __user *ptep_user; + pt_element_t __user *uninitialized_var(ptep_user); gfn_t table_gfn; unsigned index, pt_access, uninitialized_var(pte_access); gpa_t pte_gpa; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 4c3fa0f67469..d48ec60ea421 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2047,7 +2047,8 @@ static void ept_update_paging_mode_cr0(unsigned long *hw_cr0, unsigned long cr0, struct kvm_vcpu *vcpu) { - vmx_decache_cr3(vcpu); + if (!test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail)) + vmx_decache_cr3(vcpu); if (!(cr0 & X86_CR0_PG)) { /* From paging/starting to nonpaging */ vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, diff --git a/arch/x86/mm/memblock.c b/arch/x86/mm/memblock.c index aa1169392b83..992da5ec5a64 100644 --- a/arch/x86/mm/memblock.c +++ b/arch/x86/mm/memblock.c @@ -8,7 +8,7 @@ #include <linux/range.h> /* Check for already reserved areas */ -static bool __init check_with_memblock_reserved_size(u64 *addrp, u64 *sizep, u64 align) +bool __init memblock_x86_check_reserved_size(u64 *addrp, u64 *sizep, u64 align) { struct memblock_region *r; u64 addr = *addrp, last; @@ -59,7 +59,7 @@ u64 __init memblock_x86_find_in_range_size(u64 start, u64 *sizep, u64 align) if (addr >= ei_last) continue; *sizep = ei_last - addr; - while (check_with_memblock_reserved_size(&addr, sizep, align)) + while (memblock_x86_check_reserved_size(&addr, sizep, align)) ; if (*sizep) diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 0d3a4fa34560..474356b98ede 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -310,14 +310,31 @@ void __init efi_reserve_boot_services(void) for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { efi_memory_desc_t *md = p; - unsigned long long start = md->phys_addr; - unsigned long long size = md->num_pages << EFI_PAGE_SHIFT; + u64 start = md->phys_addr; + u64 size = md->num_pages << EFI_PAGE_SHIFT; if (md->type != EFI_BOOT_SERVICES_CODE && md->type != EFI_BOOT_SERVICES_DATA) continue; - - memblock_x86_reserve_range(start, start + size, "EFI Boot"); + /* Only reserve where possible: + * - Not within any already allocated areas + * - Not over any memory area (really needed, if above?) + * - Not within any part of the kernel + * - Not the bios reserved area + */ + if ((start+size >= virt_to_phys(_text) + && start <= virt_to_phys(_end)) || + !e820_all_mapped(start, start+size, E820_RAM) || + memblock_x86_check_reserved_size(&start, &size, + 1<<EFI_PAGE_SHIFT)) { + /* Could not reserve, skip it */ + md->num_pages = 0; + memblock_dbg(PFX "Could not reserve boot range " + "[0x%010llx-0x%010llx]\n", + start, start+size-1); + } else + memblock_x86_reserve_range(start, start+size, + "EFI Boot"); } } @@ -334,6 +351,10 @@ static void __init efi_free_boot_services(void) md->type != EFI_BOOT_SERVICES_DATA) continue; + /* Could not reserve boot area */ + if (!size) + continue; + free_bootmem_late(start, size); } } diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index dd7b88f2ec7a..5525163a0398 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1033,6 +1033,13 @@ static void xen_machine_halt(void) xen_reboot(SHUTDOWN_poweroff); } +static void xen_machine_power_off(void) +{ + if (pm_power_off) + pm_power_off(); + xen_reboot(SHUTDOWN_poweroff); +} + static void xen_crash_shutdown(struct pt_regs *regs) { xen_reboot(SHUTDOWN_crash); @@ -1058,7 +1065,7 @@ int xen_panic_handler_init(void) static const struct machine_ops xen_machine_ops __initconst = { .restart = xen_restart, .halt = xen_machine_halt, - .power_off = xen_machine_halt, + .power_off = xen_machine_power_off, .shutdown = xen_machine_halt, .crash_shutdown = xen_crash_shutdown, .emergency_restart = xen_emergency_restart, diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index dc708dcc62f1..673e968df3cf 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -59,6 +59,7 @@ #include <asm/page.h> #include <asm/init.h> #include <asm/pat.h> +#include <asm/smp.h> #include <asm/xen/hypercall.h> #include <asm/xen/hypervisor.h> @@ -1231,7 +1232,7 @@ static void xen_flush_tlb_others(const struct cpumask *cpus, { struct { struct mmuext_op op; - DECLARE_BITMAP(mask, NR_CPUS); + DECLARE_BITMAP(mask, num_processors); } *args; struct multicall_space mcs; @@ -1599,6 +1600,11 @@ static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn) for (pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) { pte_t pte; +#ifdef CONFIG_X86_32 + if (pfn > max_pfn_mapped) + max_pfn_mapped = pfn; +#endif + if (!pte_none(pte_page[pteidx])) continue; @@ -1766,7 +1772,9 @@ pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd, initial_kernel_pmd = extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE); - max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->mfn_list)); + max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->pt_base) + + xen_start_info->nr_pt_frames * PAGE_SIZE + + 512*1024); kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd); memcpy(initial_kernel_pmd, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD); diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index be1a464f6d66..60aeeb56948f 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -227,11 +227,7 @@ char * __init xen_memory_setup(void) memcpy(map_raw, map, sizeof(map)); e820.nr_map = 0; -#ifdef CONFIG_X86_32 xen_extra_mem_start = mem_end; -#else - xen_extra_mem_start = max((1ULL << 32), mem_end); -#endif for (i = 0; i < memmap.nr_entries; i++) { unsigned long long end; @@ -266,6 +262,12 @@ char * __init xen_memory_setup(void) if (map[i].size > 0) e820_add_region(map[i].addr, map[i].size, map[i].type); } + /* Align the balloon area so that max_low_pfn does not get set + * to be at the _end_ of the PCI gap at the far end (fee01000). + * Note that xen_extra_mem_start gets set in the loop above to be + * past the last E820 region. */ + if (xen_initial_domain() && (xen_extra_mem_start < (1ULL<<32))) + xen_extra_mem_start = (1ULL<<32); /* * In domU, the ISA region is normal, usable memory, but we diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 41038c01de40..b4533a86d7e4 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -205,11 +205,18 @@ static void __init xen_smp_prepare_boot_cpu(void) static void __init xen_smp_prepare_cpus(unsigned int max_cpus) { unsigned cpu; + unsigned int i; xen_init_lock_cpu(0); smp_store_cpu_info(0); cpu_data(0).x86_max_cores = 1; + + for_each_possible_cpu(i) { + zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL); + zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL); + zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL); + } set_cpu_sibling_map(0); if (xen_smp_intr_init(0)) diff --git a/drivers/bluetooth/btmrvl_debugfs.c b/drivers/bluetooth/btmrvl_debugfs.c index fd6305bf953e..8ecf4c6c2874 100644 --- a/drivers/bluetooth/btmrvl_debugfs.c +++ b/drivers/bluetooth/btmrvl_debugfs.c @@ -64,6 +64,8 @@ static ssize_t btmrvl_hscfgcmd_write(struct file *file, return -EFAULT; ret = strict_strtol(buf, 10, &result); + if (ret) + return ret; priv->btmrvl_dev.hscfgcmd = result; @@ -108,6 +110,8 @@ static ssize_t btmrvl_psmode_write(struct file *file, const char __user *ubuf, return -EFAULT; ret = strict_strtol(buf, 10, &result); + if (ret) + return ret; priv->btmrvl_dev.psmode = result; @@ -147,6 +151,8 @@ static ssize_t btmrvl_pscmd_write(struct file *file, const char __user *ubuf, return -EFAULT; ret = strict_strtol(buf, 10, &result); + if (ret) + return ret; priv->btmrvl_dev.pscmd = result; @@ -191,6 +197,8 @@ static ssize_t btmrvl_gpiogap_write(struct file *file, const char __user *ubuf, return -EFAULT; ret = strict_strtol(buf, 16, &result); + if (ret) + return ret; priv->btmrvl_dev.gpio_gap = result; @@ -230,6 +238,8 @@ static ssize_t btmrvl_hscmd_write(struct file *file, const char __user *ubuf, return -EFAULT; ret = strict_strtol(buf, 10, &result); + if (ret) + return ret; priv->btmrvl_dev.hscmd = result; if (priv->btmrvl_dev.hscmd) { @@ -272,6 +282,8 @@ static ssize_t btmrvl_hsmode_write(struct file *file, const char __user *ubuf, return -EFAULT; ret = strict_strtol(buf, 10, &result); + if (ret) + return ret; priv->btmrvl_dev.hsmode = result; diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c index be0921ef6b52..4cf25347b015 100644 --- a/drivers/input/evdev.c +++ b/drivers/input/evdev.c @@ -111,7 +111,8 @@ static void evdev_event(struct input_handle *handle, rcu_read_unlock(); - wake_up_interruptible(&evdev->wait); + if (type == EV_SYN && code == SYN_REPORT) + wake_up_interruptible(&evdev->wait); } static int evdev_fasync(int fd, struct file *file, int on) diff --git a/drivers/input/input.c b/drivers/input/input.c index 75e11c7b70fd..da38d97a51b1 100644 --- a/drivers/input/input.c +++ b/drivers/input/input.c @@ -1756,7 +1756,7 @@ static unsigned int input_estimate_events_per_packet(struct input_dev *dev) } else if (test_bit(ABS_MT_TRACKING_ID, dev->absbit)) { mt_slots = dev->absinfo[ABS_MT_TRACKING_ID].maximum - dev->absinfo[ABS_MT_TRACKING_ID].minimum + 1, - clamp(mt_slots, 2, 32); + mt_slots = clamp(mt_slots, 2, 32); } else if (test_bit(ABS_MT_POSITION_X, dev->absbit)) { mt_slots = 2; } else { diff --git a/drivers/input/keyboard/omap-keypad.c b/drivers/input/keyboard/omap-keypad.c index f23a743817db..33d0bdc837c0 100644 --- a/drivers/input/keyboard/omap-keypad.c +++ b/drivers/input/keyboard/omap-keypad.c @@ -209,6 +209,7 @@ static void omap_kp_tasklet(unsigned long data) #endif } } + input_sync(omap_kp_data->input); memcpy(keypad_state, new_state, sizeof(keypad_state)); if (key_down) { diff --git a/drivers/input/keyboard/sh_keysc.c b/drivers/input/keyboard/sh_keysc.c index 834cf98e7efb..6876700a4469 100644 --- a/drivers/input/keyboard/sh_keysc.c +++ b/drivers/input/keyboard/sh_keysc.c @@ -32,7 +32,7 @@ static const struct { [SH_KEYSC_MODE_3] = { 2, 4, 7 }, [SH_KEYSC_MODE_4] = { 3, 6, 6 }, [SH_KEYSC_MODE_5] = { 4, 6, 7 }, - [SH_KEYSC_MODE_6] = { 5, 7, 7 }, + [SH_KEYSC_MODE_6] = { 5, 8, 8 }, }; struct sh_keysc_priv { diff --git a/drivers/input/mousedev.c b/drivers/input/mousedev.c index 257e033986e4..0110b5a3a167 100644 --- a/drivers/input/mousedev.c +++ b/drivers/input/mousedev.c @@ -187,7 +187,7 @@ static void mousedev_abs_event(struct input_dev *dev, struct mousedev *mousedev, if (size == 0) size = xres ? : 1; - clamp(value, min, max); + value = clamp(value, min, max); mousedev->packet.x = ((value - min) * xres) / size; mousedev->packet.abs_event = 1; @@ -201,7 +201,7 @@ static void mousedev_abs_event(struct input_dev *dev, struct mousedev *mousedev, if (size == 0) size = yres ? : 1; - clamp(value, min, max); + value = clamp(value, min, max); mousedev->packet.y = yres - ((value - min) * yres) / size; mousedev->packet.abs_event = 1; diff --git a/drivers/isdn/gigaset/interface.c b/drivers/isdn/gigaset/interface.c index 59de638225fe..e35058bcd7b9 100644 --- a/drivers/isdn/gigaset/interface.c +++ b/drivers/isdn/gigaset/interface.c @@ -156,8 +156,10 @@ static int if_open(struct tty_struct *tty, struct file *filp) if (!cs || !try_module_get(cs->driver->owner)) return -ENODEV; - if (mutex_lock_interruptible(&cs->mutex)) + if (mutex_lock_interruptible(&cs->mutex)) { + module_put(cs->driver->owner); return -ERESTARTSYS; + } tty->driver_data = cs; ++cs->open_count; diff --git a/drivers/misc/sgi-xp/xpnet.c b/drivers/misc/sgi-xp/xpnet.c index ee5109a3cd98..42f067347bc7 100644 --- a/drivers/misc/sgi-xp/xpnet.c +++ b/drivers/misc/sgi-xp/xpnet.c @@ -495,14 +495,14 @@ xpnet_dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) } } + dev->stats.tx_packets++; + dev->stats.tx_bytes += skb->len; + if (atomic_dec_return(&queued_msg->use_count) == 0) { dev_kfree_skb(skb); kfree(queued_msg); } - dev->stats.tx_packets++; - dev->stats.tx_bytes += skb->len; - return NETDEV_TX_OK; } diff --git a/drivers/net/3c503.c b/drivers/net/3c503.c index d84f6e8903a5..5b732988d493 100644 --- a/drivers/net/3c503.c +++ b/drivers/net/3c503.c @@ -412,7 +412,7 @@ el2_open(struct net_device *dev) outb_p(0x04 << ((*irqp == 9) ? 2 : *irqp), E33G_IDCFR); outb_p(0x00, E33G_IDCFR); msleep(1); - free_irq(*irqp, el2_probe_interrupt); + free_irq(*irqp, &seen); if (!seen) continue; @@ -422,6 +422,7 @@ el2_open(struct net_device *dev) continue; if (retval < 0) goto err_disable; + break; } while (*++irqp); if (*irqp == 0) { diff --git a/drivers/net/bfin_mac.c b/drivers/net/bfin_mac.c index 68d45ba2d9b9..6c019e148546 100644 --- a/drivers/net/bfin_mac.c +++ b/drivers/net/bfin_mac.c @@ -52,13 +52,13 @@ MODULE_DESCRIPTION(DRV_DESC); MODULE_ALIAS("platform:bfin_mac"); #if defined(CONFIG_BFIN_MAC_USE_L1) -# define bfin_mac_alloc(dma_handle, size) l1_data_sram_zalloc(size) -# define bfin_mac_free(dma_handle, ptr) l1_data_sram_free(ptr) +# define bfin_mac_alloc(dma_handle, size, num) l1_data_sram_zalloc(size*num) +# define bfin_mac_free(dma_handle, ptr, num) l1_data_sram_free(ptr) #else -# define bfin_mac_alloc(dma_handle, size) \ - dma_alloc_coherent(NULL, size, dma_handle, GFP_KERNEL) -# define bfin_mac_free(dma_handle, ptr) \ - dma_free_coherent(NULL, sizeof(*ptr), ptr, dma_handle) +# define bfin_mac_alloc(dma_handle, size, num) \ + dma_alloc_coherent(NULL, size*num, dma_handle, GFP_KERNEL) +# define bfin_mac_free(dma_handle, ptr, num) \ + dma_free_coherent(NULL, sizeof(*ptr)*num, ptr, dma_handle) #endif #define PKT_BUF_SZ 1580 @@ -95,7 +95,7 @@ static void desc_list_free(void) t = t->next; } } - bfin_mac_free(dma_handle, tx_desc); + bfin_mac_free(dma_handle, tx_desc, CONFIG_BFIN_TX_DESC_NUM); } if (rx_desc) { @@ -109,7 +109,7 @@ static void desc_list_free(void) r = r->next; } } - bfin_mac_free(dma_handle, rx_desc); + bfin_mac_free(dma_handle, rx_desc, CONFIG_BFIN_RX_DESC_NUM); } } @@ -126,13 +126,13 @@ static int desc_list_init(void) #endif tx_desc = bfin_mac_alloc(&dma_handle, - sizeof(struct net_dma_desc_tx) * + sizeof(struct net_dma_desc_tx), CONFIG_BFIN_TX_DESC_NUM); if (tx_desc == NULL) goto init_error; rx_desc = bfin_mac_alloc(&dma_handle, - sizeof(struct net_dma_desc_rx) * + sizeof(struct net_dma_desc_rx), CONFIG_BFIN_RX_DESC_NUM); if (rx_desc == NULL) goto init_error; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 652b30e525d0..eafe44a528ac 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1297,6 +1297,7 @@ static inline int slave_enable_netpoll(struct slave *slave) goto out; np->dev = slave->dev; + strlcpy(np->dev_name, slave->dev->name, IFNAMSIZ); err = __netpoll_setup(np); if (err) { kfree(np); diff --git a/drivers/net/fs_enet/mac-fcc.c b/drivers/net/fs_enet/mac-fcc.c index 7a84e45487e8..7583a9572bcc 100644 --- a/drivers/net/fs_enet/mac-fcc.c +++ b/drivers/net/fs_enet/mac-fcc.c @@ -105,7 +105,7 @@ static int do_pd_setup(struct fs_enet_private *fep) goto out_ep; fep->fcc.mem = (void __iomem *)cpm2_immr; - fpi->dpram_offset = cpm_dpalloc(128, 8); + fpi->dpram_offset = cpm_dpalloc(128, 32); if (IS_ERR_VALUE(fpi->dpram_offset)) { ret = fpi->dpram_offset; goto out_fcccp; diff --git a/drivers/net/hp100.c b/drivers/net/hp100.c index 8e10d2f6a5ad..c3ecb118c1df 100644 --- a/drivers/net/hp100.c +++ b/drivers/net/hp100.c @@ -1580,12 +1580,12 @@ static netdev_tx_t hp100_start_xmit_bm(struct sk_buff *skb, hp100_outl(ringptr->pdl_paddr, TX_PDA_L); /* Low Prio. Queue */ lp->txrcommit++; - spin_unlock_irqrestore(&lp->lock, flags); - /* Update statistics */ dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; + spin_unlock_irqrestore(&lp->lock, flags); + return NETDEV_TX_OK; drop: diff --git a/drivers/net/hplance.c b/drivers/net/hplance.c index b6060f7538df..a900d5bf2948 100644 --- a/drivers/net/hplance.c +++ b/drivers/net/hplance.c @@ -135,7 +135,7 @@ static void __devexit hplance_remove_one(struct dio_dev *d) } /* Initialise a single lance board at the given DIO device */ -static void __init hplance_init(struct net_device *dev, struct dio_dev *d) +static void __devinit hplance_init(struct net_device *dev, struct dio_dev *d) { unsigned long va = (d->resource.start + DIO_VIRADDRBASE); struct hplance_private *lp; diff --git a/drivers/net/netxen/netxen_nic_main.c b/drivers/net/netxen/netxen_nic_main.c index b644383017f9..c0788a31ff0f 100644 --- a/drivers/net/netxen/netxen_nic_main.c +++ b/drivers/net/netxen/netxen_nic_main.c @@ -1965,11 +1965,11 @@ netxen_nic_xmit_frame(struct sk_buff *skb, struct net_device *netdev) netxen_tso_check(netdev, tx_ring, first_desc, skb); - netxen_nic_update_cmd_producer(adapter, tx_ring); - adapter->stats.txbytes += skb->len; adapter->stats.xmitcalled++; + netxen_nic_update_cmd_producer(adapter, tx_ring); + return NETDEV_TX_OK; drop_packet: diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 392a6c4b72e5..a70244306c94 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -58,6 +58,7 @@ config BROADCOM_PHY config BCM63XX_PHY tristate "Drivers for Broadcom 63xx SOCs internal PHY" + depends on BCM63XX ---help--- Currently supports the 6348 and 6358 PHYs. diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index b0c9522bb535..2cd8dc5847b4 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -543,11 +543,20 @@ static void recalibrate(struct dp83640_clock *clock) /* time stamping methods */ -static void decode_evnt(struct dp83640_private *dp83640, - struct phy_txts *phy_txts, u16 ests) +static int decode_evnt(struct dp83640_private *dp83640, + void *data, u16 ests) { + struct phy_txts *phy_txts; struct ptp_clock_event event; int words = (ests >> EVNT_TS_LEN_SHIFT) & EVNT_TS_LEN_MASK; + u16 ext_status = 0; + + if (ests & MULT_EVNT) { + ext_status = *(u16 *) data; + data += sizeof(ext_status); + } + + phy_txts = data; switch (words) { /* fall through in every case */ case 3: @@ -565,6 +574,9 @@ static void decode_evnt(struct dp83640_private *dp83640, event.timestamp = phy2txts(&dp83640->edata); ptp_clock_event(dp83640->clock->ptp_clock, &event); + + words = ext_status ? words + 2 : words + 1; + return words * sizeof(u16); } static void decode_rxts(struct dp83640_private *dp83640, @@ -643,9 +655,7 @@ static void decode_status_frame(struct dp83640_private *dp83640, } else if (PSF_EVNT == type && len >= sizeof(*phy_txts)) { - phy_txts = (struct phy_txts *) ptr; - decode_evnt(dp83640, phy_txts, ests); - size = sizeof(*phy_txts); + size = decode_evnt(dp83640, ptr, ests); } else { size = 0; @@ -1034,8 +1044,8 @@ static bool dp83640_rxtstamp(struct phy_device *phydev, if (is_status_frame(skb, type)) { decode_status_frame(dp83640, skb); - /* Let the stack drop this frame. */ - return false; + kfree_skb(skb); + return true; } SKB_PTP_TYPE(skb) = type; diff --git a/drivers/net/ppp_async.c b/drivers/net/ppp_async.c index a1b82c9c67d2..c554a397e558 100644 --- a/drivers/net/ppp_async.c +++ b/drivers/net/ppp_async.c @@ -523,7 +523,7 @@ static void ppp_async_process(unsigned long arg) #define PUT_BYTE(ap, buf, c, islcp) do { \ if ((islcp && c < 0x20) || (ap->xaccm[c >> 5] & (1 << (c & 0x1f)))) {\ *buf++ = PPP_ESCAPE; \ - *buf++ = c ^ 0x20; \ + *buf++ = c ^ PPP_TRANS; \ } else \ *buf++ = c; \ } while (0) @@ -896,7 +896,7 @@ ppp_async_input(struct asyncppp *ap, const unsigned char *buf, sp = skb_put(skb, n); memcpy(sp, buf, n); if (ap->state & SC_ESCAPE) { - sp[0] ^= 0x20; + sp[0] ^= PPP_TRANS; ap->state &= ~SC_ESCAPE; } } diff --git a/drivers/net/pxa168_eth.c b/drivers/net/pxa168_eth.c index 89f7540d90f9..5f597ca592bb 100644 --- a/drivers/net/pxa168_eth.c +++ b/drivers/net/pxa168_eth.c @@ -1273,7 +1273,7 @@ static int pxa168_eth_start_xmit(struct sk_buff *skb, struct net_device *dev) wmb(); wrl(pep, SDMA_CMD, SDMA_CMD_TXDH | SDMA_CMD_ERD); - stats->tx_bytes += skb->len; + stats->tx_bytes += length; stats->tx_packets++; dev->trans_start = jiffies; if (pep->tx_ring_size - pep->tx_desc_count <= 1) { diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c index ef1ce2ebeb4a..05d81780d1fd 100644 --- a/drivers/net/r8169.c +++ b/drivers/net/r8169.c @@ -1621,7 +1621,7 @@ static void rtl8169_get_mac_version(struct rtl8169_private *tp, * * (RTL_R32(TxConfig) & 0x700000) == 0x200000 ? 8101Eb : 8101Ec */ - static const struct { + static const struct rtl_mac_info { u32 mask; u32 val; int mac_version; @@ -1689,7 +1689,8 @@ static void rtl8169_get_mac_version(struct rtl8169_private *tp, /* Catch-all */ { 0x00000000, 0x00000000, RTL_GIGA_MAC_NONE } - }, *p = mac_info; + }; + const struct rtl_mac_info *p = mac_info; u32 reg; reg = RTL_R32(TxConfig); @@ -3681,7 +3682,7 @@ static void rtl_set_rx_max_size(void __iomem *ioaddr, unsigned int rx_buf_sz) static void rtl8169_set_magic_reg(void __iomem *ioaddr, unsigned mac_version) { - static const struct { + static const struct rtl_cfg2_info { u32 mac_version; u32 clk; u32 val; @@ -3690,7 +3691,8 @@ static void rtl8169_set_magic_reg(void __iomem *ioaddr, unsigned mac_version) { RTL_GIGA_MAC_VER_05, PCI_Clock_66MHz, 0x000fffff }, { RTL_GIGA_MAC_VER_06, PCI_Clock_33MHz, 0x00ffff00 }, // 8110SCe { RTL_GIGA_MAC_VER_06, PCI_Clock_66MHz, 0x00ffffff } - }, *p = cfg2_info; + }; + const struct rtl_cfg2_info *p = cfg2_info; unsigned int i; u32 clk; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 74e94054ab1a..5235f48be1be 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -460,7 +460,23 @@ static u32 tun_net_fix_features(struct net_device *dev, u32 features) return (features & tun->set_features) | (features & ~TUN_USER_FEATURES); } - +#ifdef CONFIG_NET_POLL_CONTROLLER +static void tun_poll_controller(struct net_device *dev) +{ + /* + * Tun only receives frames when: + * 1) the char device endpoint gets data from user space + * 2) the tun socket gets a sendmsg call from user space + * Since both of those are syncronous operations, we are guaranteed + * never to have pending data when we poll for it + * so theres nothing to do here but return. + * We need this though so netpoll recognizes us as an interface that + * supports polling, which enables bridge devices in virt setups to + * still use netconsole + */ + return; +} +#endif static const struct net_device_ops tun_netdev_ops = { .ndo_uninit = tun_net_uninit, .ndo_open = tun_net_open, @@ -468,6 +484,9 @@ static const struct net_device_ops tun_netdev_ops = { .ndo_start_xmit = tun_net_xmit, .ndo_change_mtu = tun_net_change_mtu, .ndo_fix_features = tun_net_fix_features, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = tun_poll_controller, +#endif }; static const struct net_device_ops tap_netdev_ops = { @@ -480,6 +499,9 @@ static const struct net_device_ops tap_netdev_ops = { .ndo_set_multicast_list = tun_net_mclist, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = tun_poll_controller, +#endif }; /* Initialize net device. */ diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig index 9d4f9117260f..84d4608153c9 100644 --- a/drivers/net/usb/Kconfig +++ b/drivers/net/usb/Kconfig @@ -385,6 +385,16 @@ config USB_NET_CX82310_ETH router with USB ethernet port. This driver is for routers only, it will not work with ADSL modems (use cxacru driver instead). +config USB_NET_KALMIA + tristate "Samsung Kalmia based LTE USB modem" + depends on USB_USBNET + help + Choose this option if you have a Samsung Kalmia based USB modem + as Samsung GT-B3730. + + To compile this driver as a module, choose M here: the + module will be called kalmia. + config USB_HSO tristate "Option USB High Speed Mobile Devices" depends on USB && RFKILL diff --git a/drivers/net/usb/Makefile b/drivers/net/usb/Makefile index c7ec8a5f0a90..c203fa21f6b1 100644 --- a/drivers/net/usb/Makefile +++ b/drivers/net/usb/Makefile @@ -23,6 +23,7 @@ obj-$(CONFIG_USB_NET_MCS7830) += mcs7830.o obj-$(CONFIG_USB_USBNET) += usbnet.o obj-$(CONFIG_USB_NET_INT51X1) += int51x1.o obj-$(CONFIG_USB_CDC_PHONET) += cdc-phonet.o +obj-$(CONFIG_USB_NET_KALMIA) += kalmia.o obj-$(CONFIG_USB_IPHETH) += ipheth.o obj-$(CONFIG_USB_SIERRA_NET) += sierra_net.o obj-$(CONFIG_USB_NET_CX82310_ETH) += cx82310_eth.o diff --git a/drivers/net/usb/kalmia.c b/drivers/net/usb/kalmia.c new file mode 100644 index 000000000000..d965fb1e013e --- /dev/null +++ b/drivers/net/usb/kalmia.c @@ -0,0 +1,384 @@ +/* + * USB network interface driver for Samsung Kalmia based LTE USB modem like the + * Samsung GT-B3730 and GT-B3710. + * + * Copyright (C) 2011 Marius Bjoernstad Kotsbak <marius@kotsbak.com> + * + * Sponsored by Quicklink Video Distribution Services Ltd. + * + * Based on the cdc_eem module. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <linux/ctype.h> +#include <linux/ethtool.h> +#include <linux/workqueue.h> +#include <linux/mii.h> +#include <linux/usb.h> +#include <linux/crc32.h> +#include <linux/usb/cdc.h> +#include <linux/usb/usbnet.h> +#include <linux/gfp.h> + +/* + * The Samsung Kalmia based LTE USB modems have a CDC ACM port for modem control + * handled by the "option" module and an ethernet data port handled by this + * module. + * + * The stick must first be switched into modem mode by usb_modeswitch + * or similar tool. Then the modem gets sent two initialization packets by + * this module, which gives the MAC address of the device. User space can then + * connect the modem using AT commands through the ACM port and then use + * DHCP on the network interface exposed by this module. Network packets are + * sent to and from the modem in a proprietary format discovered after watching + * the behavior of the windows driver for the modem. + * + * More information about the use of the modem is available in usb_modeswitch + * forum and the project page: + * + * http://www.draisberghof.de/usb_modeswitch/bb/viewtopic.php?t=465 + * https://github.com/mkotsbak/Samsung-GT-B3730-linux-driver + */ + +/* #define DEBUG */ +/* #define VERBOSE */ + +#define KALMIA_HEADER_LENGTH 6 +#define KALMIA_ALIGN_SIZE 4 +#define KALMIA_USB_TIMEOUT 10000 + +/*-------------------------------------------------------------------------*/ + +static int +kalmia_send_init_packet(struct usbnet *dev, u8 *init_msg, u8 init_msg_len, + u8 *buffer, u8 expected_len) +{ + int act_len; + int status; + + netdev_dbg(dev->net, "Sending init packet"); + + status = usb_bulk_msg(dev->udev, usb_sndbulkpipe(dev->udev, 0x02), + init_msg, init_msg_len, &act_len, KALMIA_USB_TIMEOUT); + if (status != 0) { + netdev_err(dev->net, + "Error sending init packet. Status %i, length %i\n", + status, act_len); + return status; + } + else if (act_len != init_msg_len) { + netdev_err(dev->net, + "Did not send all of init packet. Bytes sent: %i", + act_len); + } + else { + netdev_dbg(dev->net, "Successfully sent init packet."); + } + + status = usb_bulk_msg(dev->udev, usb_rcvbulkpipe(dev->udev, 0x81), + buffer, expected_len, &act_len, KALMIA_USB_TIMEOUT); + + if (status != 0) + netdev_err(dev->net, + "Error receiving init result. Status %i, length %i\n", + status, act_len); + else if (act_len != expected_len) + netdev_err(dev->net, "Unexpected init result length: %i\n", + act_len); + + return status; +} + +static int +kalmia_init_and_get_ethernet_addr(struct usbnet *dev, u8 *ethernet_addr) +{ + char init_msg_1[] = + { 0x57, 0x50, 0x04, 0x00, 0x00, 0x00, 0x00, 0x20, 0x00, 0x00, + 0x00, 0x00 }; + char init_msg_2[] = + { 0x57, 0x50, 0x04, 0x00, 0x00, 0x00, 0x00, 0x02, 0x00, 0xf4, + 0x00, 0x00 }; + char receive_buf[28]; + int status; + + status = kalmia_send_init_packet(dev, init_msg_1, sizeof(init_msg_1) + / sizeof(init_msg_1[0]), receive_buf, 24); + if (status != 0) + return status; + + status = kalmia_send_init_packet(dev, init_msg_2, sizeof(init_msg_2) + / sizeof(init_msg_2[0]), receive_buf, 28); + if (status != 0) + return status; + + memcpy(ethernet_addr, receive_buf + 10, ETH_ALEN); + + return status; +} + +static int +kalmia_bind(struct usbnet *dev, struct usb_interface *intf) +{ + u8 status; + u8 ethernet_addr[ETH_ALEN]; + + /* Don't bind to AT command interface */ + if (intf->cur_altsetting->desc.bInterfaceClass != USB_CLASS_VENDOR_SPEC) + return -EINVAL; + + dev->in = usb_rcvbulkpipe(dev->udev, 0x81 & USB_ENDPOINT_NUMBER_MASK); + dev->out = usb_sndbulkpipe(dev->udev, 0x02 & USB_ENDPOINT_NUMBER_MASK); + dev->status = NULL; + + dev->net->hard_header_len += KALMIA_HEADER_LENGTH; + dev->hard_mtu = 1400; + dev->rx_urb_size = dev->hard_mtu * 10; // Found as optimal after testing + + status = kalmia_init_and_get_ethernet_addr(dev, ethernet_addr); + + if (status < 0) { + usb_set_intfdata(intf, NULL); + usb_driver_release_interface(driver_of(intf), intf); + return status; + } + + memcpy(dev->net->dev_addr, ethernet_addr, ETH_ALEN); + memcpy(dev->net->perm_addr, ethernet_addr, ETH_ALEN); + + return status; +} + +static struct sk_buff * +kalmia_tx_fixup(struct usbnet *dev, struct sk_buff *skb, gfp_t flags) +{ + struct sk_buff *skb2 = NULL; + u16 content_len; + unsigned char *header_start; + unsigned char ether_type_1, ether_type_2; + u8 remainder, padlen = 0; + + if (!skb_cloned(skb)) { + int headroom = skb_headroom(skb); + int tailroom = skb_tailroom(skb); + + if ((tailroom >= KALMIA_ALIGN_SIZE) && (headroom + >= KALMIA_HEADER_LENGTH)) + goto done; + + if ((headroom + tailroom) > (KALMIA_HEADER_LENGTH + + KALMIA_ALIGN_SIZE)) { + skb->data = memmove(skb->head + KALMIA_HEADER_LENGTH, + skb->data, skb->len); + skb_set_tail_pointer(skb, skb->len); + goto done; + } + } + + skb2 = skb_copy_expand(skb, KALMIA_HEADER_LENGTH, + KALMIA_ALIGN_SIZE, flags); + if (!skb2) + return NULL; + + dev_kfree_skb_any(skb); + skb = skb2; + + done: header_start = skb_push(skb, KALMIA_HEADER_LENGTH); + ether_type_1 = header_start[KALMIA_HEADER_LENGTH + 12]; + ether_type_2 = header_start[KALMIA_HEADER_LENGTH + 13]; + + netdev_dbg(dev->net, "Sending etherType: %02x%02x", ether_type_1, + ether_type_2); + + /* According to empiric data for data packages */ + header_start[0] = 0x57; + header_start[1] = 0x44; + content_len = skb->len - KALMIA_HEADER_LENGTH; + header_start[2] = (content_len & 0xff); /* low byte */ + header_start[3] = (content_len >> 8); /* high byte */ + + header_start[4] = ether_type_1; + header_start[5] = ether_type_2; + + /* Align to 4 bytes by padding with zeros */ + remainder = skb->len % KALMIA_ALIGN_SIZE; + if (remainder > 0) { + padlen = KALMIA_ALIGN_SIZE - remainder; + memset(skb_put(skb, padlen), 0, padlen); + } + + netdev_dbg( + dev->net, + "Sending package with length %i and padding %i. Header: %02x:%02x:%02x:%02x:%02x:%02x.", + content_len, padlen, header_start[0], header_start[1], + header_start[2], header_start[3], header_start[4], + header_start[5]); + + return skb; +} + +static int +kalmia_rx_fixup(struct usbnet *dev, struct sk_buff *skb) +{ + /* + * Our task here is to strip off framing, leaving skb with one + * data frame for the usbnet framework code to process. + */ + const u8 HEADER_END_OF_USB_PACKET[] = + { 0x57, 0x5a, 0x00, 0x00, 0x08, 0x00 }; + const u8 EXPECTED_UNKNOWN_HEADER_1[] = + { 0x57, 0x43, 0x1e, 0x00, 0x15, 0x02 }; + const u8 EXPECTED_UNKNOWN_HEADER_2[] = + { 0x57, 0x50, 0x0e, 0x00, 0x00, 0x00 }; + u8 i = 0; + + /* incomplete header? */ + if (skb->len < KALMIA_HEADER_LENGTH) + return 0; + + do { + struct sk_buff *skb2 = NULL; + u8 *header_start; + u16 usb_packet_length, ether_packet_length; + int is_last; + + header_start = skb->data; + + if (unlikely(header_start[0] != 0x57 || header_start[1] != 0x44)) { + if (!memcmp(header_start, EXPECTED_UNKNOWN_HEADER_1, + sizeof(EXPECTED_UNKNOWN_HEADER_1)) || !memcmp( + header_start, EXPECTED_UNKNOWN_HEADER_2, + sizeof(EXPECTED_UNKNOWN_HEADER_2))) { + netdev_dbg( + dev->net, + "Received expected unknown frame header: %02x:%02x:%02x:%02x:%02x:%02x. Package length: %i\n", + header_start[0], header_start[1], + header_start[2], header_start[3], + header_start[4], header_start[5], + skb->len - KALMIA_HEADER_LENGTH); + } + else { + netdev_err( + dev->net, + "Received unknown frame header: %02x:%02x:%02x:%02x:%02x:%02x. Package length: %i\n", + header_start[0], header_start[1], + header_start[2], header_start[3], + header_start[4], header_start[5], + skb->len - KALMIA_HEADER_LENGTH); + return 0; + } + } + else + netdev_dbg( + dev->net, + "Received header: %02x:%02x:%02x:%02x:%02x:%02x. Package length: %i\n", + header_start[0], header_start[1], header_start[2], + header_start[3], header_start[4], header_start[5], + skb->len - KALMIA_HEADER_LENGTH); + + /* subtract start header and end header */ + usb_packet_length = skb->len - (2 * KALMIA_HEADER_LENGTH); + ether_packet_length = header_start[2] + (header_start[3] << 8); + skb_pull(skb, KALMIA_HEADER_LENGTH); + + /* Some small packets misses end marker */ + if (usb_packet_length < ether_packet_length) { + ether_packet_length = usb_packet_length + + KALMIA_HEADER_LENGTH; + is_last = true; + } + else { + netdev_dbg(dev->net, "Correct package length #%i", i + + 1); + + is_last = (memcmp(skb->data + ether_packet_length, + HEADER_END_OF_USB_PACKET, + sizeof(HEADER_END_OF_USB_PACKET)) == 0); + if (!is_last) { + header_start = skb->data + ether_packet_length; + netdev_dbg( + dev->net, + "End header: %02x:%02x:%02x:%02x:%02x:%02x. Package length: %i\n", + header_start[0], header_start[1], + header_start[2], header_start[3], + header_start[4], header_start[5], + skb->len - KALMIA_HEADER_LENGTH); + } + } + + if (is_last) { + skb2 = skb; + } + else { + skb2 = skb_clone(skb, GFP_ATOMIC); + if (unlikely(!skb2)) + return 0; + } + + skb_trim(skb2, ether_packet_length); + + if (is_last) { + return 1; + } + else { + usbnet_skb_return(dev, skb2); + skb_pull(skb, ether_packet_length); + } + + i++; + } + while (skb->len); + + return 1; +} + +static const struct driver_info kalmia_info = { + .description = "Samsung Kalmia LTE USB dongle", + .flags = FLAG_WWAN, + .bind = kalmia_bind, + .rx_fixup = kalmia_rx_fixup, + .tx_fixup = kalmia_tx_fixup +}; + +/*-------------------------------------------------------------------------*/ + +static const struct usb_device_id products[] = { + /* The unswitched USB ID, to get the module auto loaded: */ + { USB_DEVICE(0x04e8, 0x689a) }, + /* The stick swithed into modem (by e.g. usb_modeswitch): */ + { USB_DEVICE(0x04e8, 0x6889), + .driver_info = (unsigned long) &kalmia_info, }, + { /* EMPTY == end of list */} }; +MODULE_DEVICE_TABLE( usb, products); + +static struct usb_driver kalmia_driver = { + .name = "kalmia", + .id_table = products, + .probe = usbnet_probe, + .disconnect = usbnet_disconnect, + .suspend = usbnet_suspend, + .resume = usbnet_resume +}; + +static int __init kalmia_init(void) +{ + return usb_register(&kalmia_driver); +} +module_init( kalmia_init); + +static void __exit kalmia_exit(void) +{ + usb_deregister(&kalmia_driver); +} +module_exit( kalmia_exit); + +MODULE_AUTHOR("Marius Bjoernstad Kotsbak <marius@kotsbak.com>"); +MODULE_DESCRIPTION("Samsung Kalmia USB network driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/wan/farsync.c b/drivers/net/wan/farsync.c index e050bd65e037..777d1a4e81b2 100644 --- a/drivers/net/wan/farsync.c +++ b/drivers/net/wan/farsync.c @@ -2203,8 +2203,10 @@ fst_open(struct net_device *dev) if (port->mode != FST_RAW) { err = hdlc_open(dev); - if (err) + if (err) { + module_put(THIS_MODULE); return err; + } } fst_openport(port); diff --git a/drivers/net/wireless/mwifiex/cfg80211.c b/drivers/net/wireless/mwifiex/cfg80211.c index 660831ce293c..687c1f223497 100644 --- a/drivers/net/wireless/mwifiex/cfg80211.c +++ b/drivers/net/wireless/mwifiex/cfg80211.c @@ -1288,6 +1288,8 @@ int mwifiex_register_cfg80211(struct net_device *dev, u8 *mac, *(unsigned long *) wdev_priv = (unsigned long) priv; + set_wiphy_dev(wdev->wiphy, (struct device *) priv->adapter->dev); + ret = wiphy_register(wdev->wiphy); if (ret < 0) { dev_err(priv->adapter->dev, "%s: registering cfg80211 device\n", diff --git a/drivers/net/wireless/mwl8k.c b/drivers/net/wireless/mwl8k.c index 32261189bcef..aeac3cc4dbe4 100644 --- a/drivers/net/wireless/mwl8k.c +++ b/drivers/net/wireless/mwl8k.c @@ -2474,6 +2474,7 @@ struct mwl8k_cmd_set_hw_spec { * faster client. */ #define MWL8K_SET_HW_SPEC_FLAG_ENABLE_LIFE_TIME_EXPIRY 0x00000400 +#define MWL8K_SET_HW_SPEC_FLAG_GENERATE_CCMP_HDR 0x00000200 #define MWL8K_SET_HW_SPEC_FLAG_HOST_DECR_MGMT 0x00000080 #define MWL8K_SET_HW_SPEC_FLAG_HOSTFORM_PROBERESP 0x00000020 #define MWL8K_SET_HW_SPEC_FLAG_HOSTFORM_BEACON 0x00000010 @@ -2510,7 +2511,8 @@ static int mwl8k_cmd_set_hw_spec(struct ieee80211_hw *hw) cmd->flags = cpu_to_le32(MWL8K_SET_HW_SPEC_FLAG_HOST_DECR_MGMT | MWL8K_SET_HW_SPEC_FLAG_HOSTFORM_PROBERESP | MWL8K_SET_HW_SPEC_FLAG_HOSTFORM_BEACON | - MWL8K_SET_HW_SPEC_FLAG_ENABLE_LIFE_TIME_EXPIRY); + MWL8K_SET_HW_SPEC_FLAG_ENABLE_LIFE_TIME_EXPIRY | + MWL8K_SET_HW_SPEC_FLAG_GENERATE_CCMP_HDR); cmd->num_tx_desc_per_queue = cpu_to_le32(MWL8K_TX_DESCS); cmd->total_rxd = cpu_to_le32(MWL8K_RX_DESCS); diff --git a/drivers/xen/events.c b/drivers/xen/events.c index 553da68bd510..30df85d8fca8 100644 --- a/drivers/xen/events.c +++ b/drivers/xen/events.c @@ -395,9 +395,9 @@ static void unmask_evtchn(int port) static void xen_irq_init(unsigned irq) { struct irq_info *info; +#ifdef CONFIG_SMP struct irq_desc *desc = irq_to_desc(irq); -#ifdef CONFIG_SMP /* By default all event channels notify CPU#0. */ cpumask_copy(desc->irq_data.affinity, cpumask_of(0)); #endif diff --git a/fs/bad_inode.c b/fs/bad_inode.c index 9ad2369d9e35..bfcb18feb1df 100644 --- a/fs/bad_inode.c +++ b/fs/bad_inode.c @@ -231,9 +231,6 @@ static int bad_inode_readlink(struct dentry *dentry, char __user *buffer, static int bad_inode_permission(struct inode *inode, int mask, unsigned int flags) { - if (flags & IPERM_FLAG_RCU) - return -ECHILD; - return -EIO; } diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 378b5b4443f3..300628795fdb 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -967,6 +967,12 @@ struct btrfs_fs_info { struct srcu_struct subvol_srcu; spinlock_t trans_lock; + /* + * the reloc mutex goes with the trans lock, it is taken + * during commit to protect us from the relocation code + */ + struct mutex reloc_mutex; + struct list_head trans_list; struct list_head hashers; struct list_head dead_roots; @@ -1172,6 +1178,14 @@ struct btrfs_root { u32 type; u64 highest_objectid; + + /* btrfs_record_root_in_trans is a multi-step process, + * and it can race with the balancing code. But the + * race is very small, and only the first time the root + * is added to each transaction. So in_trans_setup + * is used to tell us when more checks are required + */ + unsigned long in_trans_setup; int ref_cows; int track_dirty; int in_radix; @@ -1181,7 +1195,6 @@ struct btrfs_root { struct btrfs_key defrag_max; int defrag_running; char *name; - int in_sysfs; /* the dirty list is only used by non-reference counted roots */ struct list_head dirty_list; diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 6462c29d2d37..f1cbd028f7b3 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -297,7 +297,6 @@ struct btrfs_delayed_item *btrfs_alloc_delayed_item(u32 data_len) item->data_len = data_len; item->ins_or_del = 0; item->bytes_reserved = 0; - item->block_rsv = NULL; item->delayed_node = NULL; atomic_set(&item->refs, 1); } @@ -593,10 +592,8 @@ static int btrfs_delayed_item_reserve_metadata(struct btrfs_trans_handle *trans, num_bytes = btrfs_calc_trans_metadata_size(root, 1); ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes); - if (!ret) { + if (!ret) item->bytes_reserved = num_bytes; - item->block_rsv = dst_rsv; - } return ret; } @@ -604,10 +601,13 @@ static int btrfs_delayed_item_reserve_metadata(struct btrfs_trans_handle *trans, static void btrfs_delayed_item_release_metadata(struct btrfs_root *root, struct btrfs_delayed_item *item) { + struct btrfs_block_rsv *rsv; + if (!item->bytes_reserved) return; - btrfs_block_rsv_release(root, item->block_rsv, + rsv = &root->fs_info->global_block_rsv; + btrfs_block_rsv_release(root, rsv, item->bytes_reserved); } @@ -1014,6 +1014,7 @@ int btrfs_run_delayed_items(struct btrfs_trans_handle *trans, struct btrfs_delayed_root *delayed_root; struct btrfs_delayed_node *curr_node, *prev_node; struct btrfs_path *path; + struct btrfs_block_rsv *block_rsv; int ret = 0; path = btrfs_alloc_path(); @@ -1021,6 +1022,9 @@ int btrfs_run_delayed_items(struct btrfs_trans_handle *trans, return -ENOMEM; path->leave_spinning = 1; + block_rsv = trans->block_rsv; + trans->block_rsv = &root->fs_info->global_block_rsv; + delayed_root = btrfs_get_delayed_root(root); curr_node = btrfs_first_delayed_node(delayed_root); @@ -1045,6 +1049,7 @@ int btrfs_run_delayed_items(struct btrfs_trans_handle *trans, } btrfs_free_path(path); + trans->block_rsv = block_rsv; return ret; } @@ -1052,6 +1057,7 @@ static int __btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans, struct btrfs_delayed_node *node) { struct btrfs_path *path; + struct btrfs_block_rsv *block_rsv; int ret; path = btrfs_alloc_path(); @@ -1059,6 +1065,9 @@ static int __btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans, return -ENOMEM; path->leave_spinning = 1; + block_rsv = trans->block_rsv; + trans->block_rsv = &node->root->fs_info->global_block_rsv; + ret = btrfs_insert_delayed_items(trans, path, node->root, node); if (!ret) ret = btrfs_delete_delayed_items(trans, path, node->root, node); @@ -1066,6 +1075,7 @@ static int __btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans, ret = btrfs_update_delayed_inode(trans, node->root, path, node); btrfs_free_path(path); + trans->block_rsv = block_rsv; return ret; } @@ -1116,6 +1126,7 @@ static void btrfs_async_run_delayed_node_done(struct btrfs_work *work) struct btrfs_path *path; struct btrfs_delayed_node *delayed_node = NULL; struct btrfs_root *root; + struct btrfs_block_rsv *block_rsv; unsigned long nr = 0; int need_requeue = 0; int ret; @@ -1134,6 +1145,9 @@ static void btrfs_async_run_delayed_node_done(struct btrfs_work *work) if (IS_ERR(trans)) goto free_path; + block_rsv = trans->block_rsv; + trans->block_rsv = &root->fs_info->global_block_rsv; + ret = btrfs_insert_delayed_items(trans, path, root, delayed_node); if (!ret) ret = btrfs_delete_delayed_items(trans, path, root, @@ -1176,6 +1190,7 @@ static void btrfs_async_run_delayed_node_done(struct btrfs_work *work) nr = trans->blocks_used; + trans->block_rsv = block_rsv; btrfs_end_transaction_dmeta(trans, root); __btrfs_btree_balance_dirty(root, nr); free_path: @@ -1222,6 +1237,13 @@ again: return 0; } +void btrfs_assert_delayed_root_empty(struct btrfs_root *root) +{ + struct btrfs_delayed_root *delayed_root; + delayed_root = btrfs_get_delayed_root(root); + WARN_ON(btrfs_first_delayed_node(delayed_root)); +} + void btrfs_balance_delayed_items(struct btrfs_root *root) { struct btrfs_delayed_root *delayed_root; diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h index eb7d240aa648..d1a6a2915c66 100644 --- a/fs/btrfs/delayed-inode.h +++ b/fs/btrfs/delayed-inode.h @@ -75,7 +75,6 @@ struct btrfs_delayed_item { struct list_head tree_list; /* used for batch insert/delete items */ struct list_head readdir_list; /* used for readdir items */ u64 bytes_reserved; - struct btrfs_block_rsv *block_rsv; struct btrfs_delayed_node *delayed_node; atomic_t refs; int ins_or_del; @@ -138,4 +137,8 @@ int btrfs_readdir_delayed_dir_index(struct file *filp, void *dirent, /* for init */ int __init btrfs_delayed_inode_init(void); void btrfs_delayed_inode_exit(void); + +/* for debugging */ +void btrfs_assert_delayed_root_empty(struct btrfs_root *root); + #endif diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 9f68c6898653..1ac8db5dc0a3 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1044,7 +1044,6 @@ static int __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize, root->last_trans = 0; root->highest_objectid = 0; root->name = NULL; - root->in_sysfs = 0; root->inode_tree = RB_ROOT; INIT_RADIX_TREE(&root->delayed_nodes_tree, GFP_ATOMIC); root->block_rsv = NULL; @@ -1300,19 +1299,21 @@ again: return root; root->free_ino_ctl = kzalloc(sizeof(*root->free_ino_ctl), GFP_NOFS); - if (!root->free_ino_ctl) - goto fail; root->free_ino_pinned = kzalloc(sizeof(*root->free_ino_pinned), GFP_NOFS); - if (!root->free_ino_pinned) + if (!root->free_ino_pinned || !root->free_ino_ctl) { + ret = -ENOMEM; goto fail; + } btrfs_init_free_ino_ctl(root); mutex_init(&root->fs_commit_mutex); spin_lock_init(&root->cache_lock); init_waitqueue_head(&root->cache_wait); - set_anon_super(&root->anon_super, NULL); + ret = set_anon_super(&root->anon_super, NULL); + if (ret) + goto fail; if (btrfs_root_refs(&root->root_item) == 0) { ret = -ENOENT; @@ -1618,6 +1619,7 @@ struct btrfs_root *open_ctree(struct super_block *sb, spin_lock_init(&fs_info->fs_roots_radix_lock); spin_lock_init(&fs_info->delayed_iput_lock); spin_lock_init(&fs_info->defrag_inodes_lock); + mutex_init(&fs_info->reloc_mutex); init_completion(&fs_info->kobj_unregister); fs_info->tree_root = tree_root; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index b42efc2ded51..1f61bf5b4960 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3314,10 +3314,6 @@ static int shrink_delalloc(struct btrfs_trans_handle *trans, if (reserved == 0) return 0; - /* nothing to shrink - nothing to reclaim */ - if (root->fs_info->delalloc_bytes == 0) - return 0; - max_reclaim = min(reserved, to_reclaim); while (loops < 1024) { diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 751ddf8fc58a..0a9b10c5b0a7 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3076,6 +3076,7 @@ int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, ret = btrfs_update_inode(trans, root, dir); BUG_ON(ret); + btrfs_free_path(path); return 0; } diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index b793d112d1f6..a3c4751e07db 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -482,8 +482,10 @@ static int create_snapshot(struct btrfs_root *root, struct dentry *dentry, ret = btrfs_snap_reserve_metadata(trans, pending_snapshot); BUG_ON(ret); + spin_lock(&root->fs_info->trans_lock); list_add(&pending_snapshot->list, &trans->transaction->pending_snapshots); + spin_unlock(&root->fs_info->trans_lock); if (async_transid) { *async_transid = trans->transid; ret = btrfs_commit_transaction_async(trans, diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index b1ef27cc673b..5e0a3dc79a45 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -1368,7 +1368,7 @@ int btrfs_update_reloc_root(struct btrfs_trans_handle *trans, int ret; if (!root->reloc_root) - return 0; + goto out; reloc_root = root->reloc_root; root_item = &reloc_root->root_item; @@ -1390,6 +1390,8 @@ int btrfs_update_reloc_root(struct btrfs_trans_handle *trans, ret = btrfs_update_root(trans, root->fs_info->tree_root, &reloc_root->root_key, root_item); BUG_ON(ret); + +out: return 0; } @@ -2142,10 +2144,11 @@ int prepare_to_merge(struct reloc_control *rc, int err) u64 num_bytes = 0; int ret; - spin_lock(&root->fs_info->trans_lock); + mutex_lock(&root->fs_info->reloc_mutex); rc->merging_rsv_size += root->nodesize * (BTRFS_MAX_LEVEL - 1) * 2; rc->merging_rsv_size += rc->nodes_relocated * 2; - spin_unlock(&root->fs_info->trans_lock); + mutex_unlock(&root->fs_info->reloc_mutex); + again: if (!err) { num_bytes = rc->merging_rsv_size; @@ -2214,9 +2217,16 @@ int merge_reloc_roots(struct reloc_control *rc) int ret; again: root = rc->extent_root; - spin_lock(&root->fs_info->trans_lock); + + /* + * this serializes us with btrfs_record_root_in_transaction, + * we have to make sure nobody is in the middle of + * adding their roots to the list while we are + * doing this splice + */ + mutex_lock(&root->fs_info->reloc_mutex); list_splice_init(&rc->reloc_roots, &reloc_roots); - spin_unlock(&root->fs_info->trans_lock); + mutex_unlock(&root->fs_info->reloc_mutex); while (!list_empty(&reloc_roots)) { found = 1; @@ -3590,17 +3600,19 @@ next: static void set_reloc_control(struct reloc_control *rc) { struct btrfs_fs_info *fs_info = rc->extent_root->fs_info; - spin_lock(&fs_info->trans_lock); + + mutex_lock(&fs_info->reloc_mutex); fs_info->reloc_ctl = rc; - spin_unlock(&fs_info->trans_lock); + mutex_unlock(&fs_info->reloc_mutex); } static void unset_reloc_control(struct reloc_control *rc) { struct btrfs_fs_info *fs_info = rc->extent_root->fs_info; - spin_lock(&fs_info->trans_lock); + + mutex_lock(&fs_info->reloc_mutex); fs_info->reloc_ctl = NULL; - spin_unlock(&fs_info->trans_lock); + mutex_unlock(&fs_info->reloc_mutex); } static int check_extent_flags(u64 flags) diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index c3c223ae6691..daac9ae6d731 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -28,152 +28,6 @@ #include "disk-io.h" #include "transaction.h" -static ssize_t root_blocks_used_show(struct btrfs_root *root, char *buf) -{ - return snprintf(buf, PAGE_SIZE, "%llu\n", - (unsigned long long)btrfs_root_used(&root->root_item)); -} - -static ssize_t root_block_limit_show(struct btrfs_root *root, char *buf) -{ - return snprintf(buf, PAGE_SIZE, "%llu\n", - (unsigned long long)btrfs_root_limit(&root->root_item)); -} - -static ssize_t super_blocks_used_show(struct btrfs_fs_info *fs, char *buf) -{ - - return snprintf(buf, PAGE_SIZE, "%llu\n", - (unsigned long long)btrfs_super_bytes_used(&fs->super_copy)); -} - -static ssize_t super_total_blocks_show(struct btrfs_fs_info *fs, char *buf) -{ - return snprintf(buf, PAGE_SIZE, "%llu\n", - (unsigned long long)btrfs_super_total_bytes(&fs->super_copy)); -} - -static ssize_t super_blocksize_show(struct btrfs_fs_info *fs, char *buf) -{ - return snprintf(buf, PAGE_SIZE, "%llu\n", - (unsigned long long)btrfs_super_sectorsize(&fs->super_copy)); -} - -/* this is for root attrs (subvols/snapshots) */ -struct btrfs_root_attr { - struct attribute attr; - ssize_t (*show)(struct btrfs_root *, char *); - ssize_t (*store)(struct btrfs_root *, const char *, size_t); -}; - -#define ROOT_ATTR(name, mode, show, store) \ -static struct btrfs_root_attr btrfs_root_attr_##name = __ATTR(name, mode, \ - show, store) - -ROOT_ATTR(blocks_used, 0444, root_blocks_used_show, NULL); -ROOT_ATTR(block_limit, 0644, root_block_limit_show, NULL); - -static struct attribute *btrfs_root_attrs[] = { - &btrfs_root_attr_blocks_used.attr, - &btrfs_root_attr_block_limit.attr, - NULL, -}; - -/* this is for super attrs (actual full fs) */ -struct btrfs_super_attr { - struct attribute attr; - ssize_t (*show)(struct btrfs_fs_info *, char *); - ssize_t (*store)(struct btrfs_fs_info *, const char *, size_t); -}; - -#define SUPER_ATTR(name, mode, show, store) \ -static struct btrfs_super_attr btrfs_super_attr_##name = __ATTR(name, mode, \ - show, store) - -SUPER_ATTR(blocks_used, 0444, super_blocks_used_show, NULL); -SUPER_ATTR(total_blocks, 0444, super_total_blocks_show, NULL); -SUPER_ATTR(blocksize, 0444, super_blocksize_show, NULL); - -static struct attribute *btrfs_super_attrs[] = { - &btrfs_super_attr_blocks_used.attr, - &btrfs_super_attr_total_blocks.attr, - &btrfs_super_attr_blocksize.attr, - NULL, -}; - -static ssize_t btrfs_super_attr_show(struct kobject *kobj, - struct attribute *attr, char *buf) -{ - struct btrfs_fs_info *fs = container_of(kobj, struct btrfs_fs_info, - super_kobj); - struct btrfs_super_attr *a = container_of(attr, - struct btrfs_super_attr, - attr); - - return a->show ? a->show(fs, buf) : 0; -} - -static ssize_t btrfs_super_attr_store(struct kobject *kobj, - struct attribute *attr, - const char *buf, size_t len) -{ - struct btrfs_fs_info *fs = container_of(kobj, struct btrfs_fs_info, - super_kobj); - struct btrfs_super_attr *a = container_of(attr, - struct btrfs_super_attr, - attr); - - return a->store ? a->store(fs, buf, len) : 0; -} - -static ssize_t btrfs_root_attr_show(struct kobject *kobj, - struct attribute *attr, char *buf) -{ - struct btrfs_root *root = container_of(kobj, struct btrfs_root, - root_kobj); - struct btrfs_root_attr *a = container_of(attr, - struct btrfs_root_attr, - attr); - - return a->show ? a->show(root, buf) : 0; -} - -static ssize_t btrfs_root_attr_store(struct kobject *kobj, - struct attribute *attr, - const char *buf, size_t len) -{ - struct btrfs_root *root = container_of(kobj, struct btrfs_root, - root_kobj); - struct btrfs_root_attr *a = container_of(attr, - struct btrfs_root_attr, - attr); - return a->store ? a->store(root, buf, len) : 0; -} - -static void btrfs_super_release(struct kobject *kobj) -{ - struct btrfs_fs_info *fs = container_of(kobj, struct btrfs_fs_info, - super_kobj); - complete(&fs->kobj_unregister); -} - -static void btrfs_root_release(struct kobject *kobj) -{ - struct btrfs_root *root = container_of(kobj, struct btrfs_root, - root_kobj); - complete(&root->kobj_unregister); -} - -static const struct sysfs_ops btrfs_super_attr_ops = { - .show = btrfs_super_attr_show, - .store = btrfs_super_attr_store, -}; - -static const struct sysfs_ops btrfs_root_attr_ops = { - .show = btrfs_root_attr_show, - .store = btrfs_root_attr_store, -}; - /* /sys/fs/btrfs/ entry */ static struct kset *btrfs_kset; diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 2b3590b9fe98..51dcec86757f 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -126,28 +126,85 @@ static noinline int join_transaction(struct btrfs_root *root, int nofail) * to make sure the old root from before we joined the transaction is deleted * when the transaction commits */ -int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans, +static int record_root_in_trans(struct btrfs_trans_handle *trans, struct btrfs_root *root) { if (root->ref_cows && root->last_trans < trans->transid) { WARN_ON(root == root->fs_info->extent_root); WARN_ON(root->commit_root != root->node); + /* + * see below for in_trans_setup usage rules + * we have the reloc mutex held now, so there + * is only one writer in this function + */ + root->in_trans_setup = 1; + + /* make sure readers find in_trans_setup before + * they find our root->last_trans update + */ + smp_wmb(); + spin_lock(&root->fs_info->fs_roots_radix_lock); if (root->last_trans == trans->transid) { spin_unlock(&root->fs_info->fs_roots_radix_lock); return 0; } - root->last_trans = trans->transid; radix_tree_tag_set(&root->fs_info->fs_roots_radix, (unsigned long)root->root_key.objectid, BTRFS_ROOT_TRANS_TAG); spin_unlock(&root->fs_info->fs_roots_radix_lock); + root->last_trans = trans->transid; + + /* this is pretty tricky. We don't want to + * take the relocation lock in btrfs_record_root_in_trans + * unless we're really doing the first setup for this root in + * this transaction. + * + * Normally we'd use root->last_trans as a flag to decide + * if we want to take the expensive mutex. + * + * But, we have to set root->last_trans before we + * init the relocation root, otherwise, we trip over warnings + * in ctree.c. The solution used here is to flag ourselves + * with root->in_trans_setup. When this is 1, we're still + * fixing up the reloc trees and everyone must wait. + * + * When this is zero, they can trust root->last_trans and fly + * through btrfs_record_root_in_trans without having to take the + * lock. smp_wmb() makes sure that all the writes above are + * done before we pop in the zero below + */ btrfs_init_reloc_root(trans, root); + smp_wmb(); + root->in_trans_setup = 0; } return 0; } + +int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans, + struct btrfs_root *root) +{ + if (!root->ref_cows) + return 0; + + /* + * see record_root_in_trans for comments about in_trans_setup usage + * and barriers + */ + smp_rmb(); + if (root->last_trans == trans->transid && + !root->in_trans_setup) + return 0; + + mutex_lock(&root->fs_info->reloc_mutex); + record_root_in_trans(trans, root); + mutex_unlock(&root->fs_info->reloc_mutex); + + return 0; +} + /* wait for commit against the current transaction to become unblocked * when this is done, it is safe to start a new transaction, but the current * transaction might not be fully on disk. @@ -882,7 +939,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, parent = dget_parent(dentry); parent_inode = parent->d_inode; parent_root = BTRFS_I(parent_inode)->root; - btrfs_record_root_in_trans(trans, parent_root); + record_root_in_trans(trans, parent_root); /* * insert the directory item @@ -900,7 +957,16 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, ret = btrfs_update_inode(trans, parent_root, parent_inode); BUG_ON(ret); - btrfs_record_root_in_trans(trans, root); + /* + * pull in the delayed directory update + * and the delayed inode item + * otherwise we corrupt the FS during + * snapshot + */ + ret = btrfs_run_delayed_items(trans, root); + BUG_ON(ret); + + record_root_in_trans(trans, root); btrfs_set_root_last_snapshot(&root->root_item, trans->transid); memcpy(new_root_item, &root->root_item, sizeof(*new_root_item)); btrfs_check_and_init_root_item(new_root_item); @@ -961,14 +1027,6 @@ static noinline int create_pending_snapshots(struct btrfs_trans_handle *trans, int ret; list_for_each_entry(pending, head, list) { - /* - * We must deal with the delayed items before creating - * snapshots, or we will create a snapthot with inconsistent - * information. - */ - ret = btrfs_run_delayed_items(trans, fs_info->fs_root); - BUG_ON(ret); - ret = create_pending_snapshot(trans, fs_info, pending); BUG_ON(ret); } @@ -1241,21 +1299,42 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, schedule_timeout(1); finish_wait(&cur_trans->writer_wait, &wait); - spin_lock(&root->fs_info->trans_lock); - root->fs_info->trans_no_join = 1; - spin_unlock(&root->fs_info->trans_lock); } while (atomic_read(&cur_trans->num_writers) > 1 || (should_grow && cur_trans->num_joined != joined)); - ret = create_pending_snapshots(trans, root->fs_info); - BUG_ON(ret); + /* + * Ok now we need to make sure to block out any other joins while we + * commit the transaction. We could have started a join before setting + * no_join so make sure to wait for num_writers to == 1 again. + */ + spin_lock(&root->fs_info->trans_lock); + root->fs_info->trans_no_join = 1; + spin_unlock(&root->fs_info->trans_lock); + wait_event(cur_trans->writer_wait, + atomic_read(&cur_trans->num_writers) == 1); + + /* + * the reloc mutex makes sure that we stop + * the balancing code from coming in and moving + * extents around in the middle of the commit + */ + mutex_lock(&root->fs_info->reloc_mutex); ret = btrfs_run_delayed_items(trans, root); BUG_ON(ret); + ret = create_pending_snapshots(trans, root->fs_info); + BUG_ON(ret); + ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1); BUG_ON(ret); + /* + * make sure none of the code above managed to slip in a + * delayed item + */ + btrfs_assert_delayed_root_empty(root); + WARN_ON(cur_trans != trans->transaction); btrfs_scrub_pause(root); @@ -1312,6 +1391,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, root->fs_info->running_transaction = NULL; root->fs_info->trans_no_join = 0; spin_unlock(&root->fs_info->trans_lock); + mutex_unlock(&root->fs_info->reloc_mutex); wake_up(&root->fs_info->transaction_wait); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 592396c6dc47..4ce8a9f41d1e 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3177,7 +3177,7 @@ again: tmp_key.offset = (u64)-1; wc.replay_dest = btrfs_read_fs_root_no_name(fs_info, &tmp_key); - BUG_ON(!wc.replay_dest); + BUG_ON(IS_ERR_OR_NULL(wc.replay_dest)); wc.replay_dest->log_root = log; btrfs_record_root_in_trans(trans, wc.replay_dest); diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index e9def996e383..2f0c58646c10 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -257,9 +257,6 @@ static int cifs_permission(struct inode *inode, int mask, unsigned int flags) { struct cifs_sb_info *cifs_sb; - if (flags & IPERM_FLAG_RCU) - return -ECHILD; - cifs_sb = CIFS_SB(inode->i_sb); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM) { diff --git a/fs/coda/pioctl.c b/fs/coda/pioctl.c index 6cbb3afb36dc..cb140ef293e4 100644 --- a/fs/coda/pioctl.c +++ b/fs/coda/pioctl.c @@ -43,8 +43,6 @@ const struct file_operations coda_ioctl_operations = { /* the coda pioctl inode ops */ static int coda_ioctl_permission(struct inode *inode, int mask, unsigned int flags) { - if (flags & IPERM_FLAG_RCU) - return -ECHILD; return (mask & MAY_EXEC) ? -EACCES : 0; } diff --git a/fs/logfs/dir.c b/fs/logfs/dir.c index 9ed89d1663f8..1afae26cf236 100644 --- a/fs/logfs/dir.c +++ b/fs/logfs/dir.c @@ -555,13 +555,6 @@ static int logfs_symlink(struct inode *dir, struct dentry *dentry, return __logfs_create(dir, dentry, inode, target, destlen); } -static int logfs_permission(struct inode *inode, int mask, unsigned int flags) -{ - if (flags & IPERM_FLAG_RCU) - return -ECHILD; - return generic_permission(inode, mask, flags, NULL); -} - static int logfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { @@ -820,7 +813,6 @@ const struct inode_operations logfs_dir_iops = { .mknod = logfs_mknod, .rename = logfs_rename, .rmdir = logfs_rmdir, - .permission = logfs_permission, .symlink = logfs_symlink, .unlink = logfs_unlink, }; diff --git a/fs/namei.c b/fs/namei.c index 9e425e7e6c8f..0223c41fb114 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -238,7 +238,8 @@ int generic_permission(struct inode *inode, int mask, unsigned int flags, /* * Read/write DACs are always overridable. - * Executable DACs are overridable if at least one exec bit is set. + * Executable DACs are overridable for all directories and + * for non-directories that have least one exec bit set. */ if (!(mask & MAY_EXEC) || execute_ok(inode)) if (ns_capable(inode_userns(inode), CAP_DAC_OVERRIDE)) @@ -1011,9 +1012,6 @@ failed: * Follow down to the covering mount currently visible to userspace. At each * point, the filesystem owning that dentry may be queried as to whether the * caller is permitted to proceed or not. - * - * Care must be taken as namespace_sem may be held (indicated by mounting_here - * being true). */ int follow_down(struct path *path) { diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig index 18b3e8975fe0..fbb2a5ef5817 100644 --- a/fs/nfsd/Kconfig +++ b/fs/nfsd/Kconfig @@ -82,6 +82,7 @@ config NFSD_V4 select NFSD_V3 select FS_POSIX_ACL select SUNRPC_GSS + select CRYPTO help This option enables support in your system's NFS server for version 4 of the NFS protocol (RFC 3530). diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 1f5eae40f34e..2b1449dd2f49 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -13,6 +13,7 @@ #include <linux/lockd/lockd.h> #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/gss_api.h> +#include <linux/sunrpc/gss_krb5_enctypes.h> #include "idmap.h" #include "nfsd.h" @@ -189,18 +190,10 @@ static struct file_operations export_features_operations = { .release = single_release, }; -#ifdef CONFIG_SUNRPC_GSS +#if defined(CONFIG_SUNRPC_GSS) || defined(CONFIG_SUNRPC_GSS_MODULE) static int supported_enctypes_show(struct seq_file *m, void *v) { - struct gss_api_mech *k5mech; - - k5mech = gss_mech_get_by_name("krb5"); - if (k5mech == NULL) - goto out; - if (k5mech->gm_upcall_enctypes != NULL) - seq_printf(m, k5mech->gm_upcall_enctypes); - gss_mech_put(k5mech); -out: + seq_printf(m, KRB5_SUPPORTED_ENCTYPES); return 0; } @@ -215,7 +208,7 @@ static struct file_operations supported_enctypes_ops = { .llseek = seq_lseek, .release = single_release, }; -#endif /* CONFIG_SUNRPC_GSS */ +#endif /* CONFIG_SUNRPC_GSS or CONFIG_SUNRPC_GSS_MODULE */ extern int nfsd_pool_stats_open(struct inode *inode, struct file *file); extern int nfsd_pool_stats_release(struct inode *inode, struct file *file); @@ -1427,9 +1420,9 @@ static int nfsd_fill_super(struct super_block * sb, void * data, int silent) [NFSD_Versions] = {"versions", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_Ports] = {"portlist", &transaction_ops, S_IWUSR|S_IRUGO}, [NFSD_MaxBlkSize] = {"max_block_size", &transaction_ops, S_IWUSR|S_IRUGO}, -#ifdef CONFIG_SUNRPC_GSS +#if defined(CONFIG_SUNRPC_GSS) || defined(CONFIG_SUNRPC_GSS_MODULE) [NFSD_SupportedEnctypes] = {"supported_krb5_enctypes", &supported_enctypes_ops, S_IRUGO}, -#endif /* CONFIG_SUNRPC_GSS */ +#endif /* CONFIG_SUNRPC_GSS or CONFIG_SUNRPC_GSS_MODULE */ #ifdef CONFIG_NFSD_V4 [NFSD_Leasetime] = {"nfsv4leasetime", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_Gracetime] = {"nfsv4gracetime", &transaction_ops, S_IWUSR|S_IRUSR}, diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index d5718273bb32..fd0acca5370a 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -696,7 +696,15 @@ nfsd_access(struct svc_rqst *rqstp, struct svc_fh *fhp, u32 *access, u32 *suppor } #endif /* CONFIG_NFSD_V3 */ +static int nfsd_open_break_lease(struct inode *inode, int access) +{ + unsigned int mode; + if (access & NFSD_MAY_NOT_BREAK_LEASE) + return 0; + mode = (access & NFSD_MAY_WRITE) ? O_WRONLY : O_RDONLY; + return break_lease(inode, mode | O_NONBLOCK); +} /* * Open an existing file or directory. @@ -744,12 +752,7 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, if (!inode->i_fop) goto out; - /* - * Check to see if there are any leases on this file. - * This may block while leases are broken. - */ - if (!(access & NFSD_MAY_NOT_BREAK_LEASE)) - host_err = break_lease(inode, O_NONBLOCK | ((access & NFSD_MAY_WRITE) ? O_WRONLY : 0)); + host_err = nfsd_open_break_lease(inode, access); if (host_err) /* NOMEM or WOULDBLOCK */ goto out_nfserr; @@ -1660,8 +1663,10 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp, if (!dold->d_inode) goto out_drop_write; host_err = nfsd_break_lease(dold->d_inode); - if (host_err) + if (host_err) { + err = nfserrno(host_err); goto out_drop_write; + } host_err = vfs_link(dold, dirp, dnew); if (!host_err) { err = nfserrno(commit_metadata(ffhp)); diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index b954878ad6ce..b9b45fc2903e 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -801,12 +801,7 @@ out_err: int nilfs_permission(struct inode *inode, int mask, unsigned int flags) { - struct nilfs_root *root; - - if (flags & IPERM_FLAG_RCU) - return -ECHILD; - - root = NILFS_I(inode)->i_root; + struct nilfs_root *root = NILFS_I(inode)->i_root; if ((mask & MAY_WRITE) && root && root->cno != NILFS_CPTREE_CURRENT_CNO) return -EROFS; /* snapshot is not writable */ diff --git a/fs/proc/base.c b/fs/proc/base.c index 14def991d9dd..8a84210ca080 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2169,11 +2169,7 @@ static const struct file_operations proc_fd_operations = { */ static int proc_fd_permission(struct inode *inode, int mask, unsigned int flags) { - int rv; - - if (flags & IPERM_FLAG_RCU) - return -ECHILD; - rv = generic_permission(inode, mask, flags, NULL); + int rv = generic_permission(inode, mask, flags, NULL); if (rv == 0) return 0; if (task_pid(current) == proc_pid(inode)) diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index f50133c11c24..d167de365a8d 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -304,9 +304,6 @@ static int proc_sys_permission(struct inode *inode, int mask,unsigned int flags) struct ctl_table *table; int error; - if (flags & IPERM_FLAG_RCU) - return -ECHILD; - /* Executable files are not allowed under /proc/sys/ */ if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode)) return -EACCES; diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index e8a62f41b458..d78089690965 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -954,8 +954,6 @@ static int xattr_mount_check(struct super_block *s) int reiserfs_permission(struct inode *inode, int mask, unsigned int flags) { - if (flags & IPERM_FLAG_RCU) - return -ECHILD; /* * We don't do permission checks on the internal objects. * Permissions are determined by the "owning" object. diff --git a/fs/timerfd.c b/fs/timerfd.c index f67acbdda5e8..dffeb3795af1 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -61,7 +61,9 @@ static enum hrtimer_restart timerfd_tmrproc(struct hrtimer *htmr) /* * Called when the clock was set to cancel the timers in the cancel - * list. + * list. This will wake up processes waiting on these timers. The + * wake-up requires ctx->ticks to be non zero, therefore we increment + * it before calling wake_up_locked(). */ void timerfd_clock_was_set(void) { @@ -76,6 +78,7 @@ void timerfd_clock_was_set(void) spin_lock_irqsave(&ctx->wqh.lock, flags); if (ctx->moffs.tv64 != moffs.tv64) { ctx->moffs.tv64 = KTIME_MAX; + ctx->ticks++; wake_up_locked(&ctx->wqh); } spin_unlock_irqrestore(&ctx->wqh.lock, flags); diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 8c892c2d5300..529be0582029 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -2146,6 +2146,7 @@ static struct dentry *ubifs_mount(struct file_system_type *fs_type, int flags, if (IS_ERR(sb)) { err = PTR_ERR(sb); kfree(c); + goto out_close; } if (sb->s_root) { diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index d4646b48dc4a..18a1baf31f2d 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -188,6 +188,7 @@ struct clocksource { #ifdef CONFIG_CLOCKSOURCE_WATCHDOG /* Watchdog related data, used by the framework */ struct list_head wd_list; + cycle_t cs_last; cycle_t wd_last; #endif } ____cacheline_aligned; diff --git a/include/linux/device_cgroup.h b/include/linux/device_cgroup.h index 0b0d9c39ed67..7aad1f440867 100644 --- a/include/linux/device_cgroup.h +++ b/include/linux/device_cgroup.h @@ -2,8 +2,16 @@ #include <linux/fs.h> #ifdef CONFIG_CGROUP_DEVICE -extern int devcgroup_inode_permission(struct inode *inode, int mask); +extern int __devcgroup_inode_permission(struct inode *inode, int mask); extern int devcgroup_inode_mknod(int mode, dev_t dev); +static inline int devcgroup_inode_permission(struct inode *inode, int mask) +{ + if (likely(!inode->i_rdev)) + return 0; + if (!S_ISBLK(inode->i_mode) && !S_ISCHR(inode->i_mode)) + return 0; + return __devcgroup_inode_permission(inode, mask); +} #else static inline int devcgroup_inode_permission(struct inode *inode, int mask) { return 0; } diff --git a/include/linux/input/sh_keysc.h b/include/linux/input/sh_keysc.h index 649dc7f12925..5d253cd93691 100644 --- a/include/linux/input/sh_keysc.h +++ b/include/linux/input/sh_keysc.h @@ -1,7 +1,7 @@ #ifndef __SH_KEYSC_H__ #define __SH_KEYSC_H__ -#define SH_KEYSC_MAXKEYS 49 +#define SH_KEYSC_MAXKEYS 64 struct sh_keysc_info { enum { SH_KEYSC_MODE_1, SH_KEYSC_MODE_2, SH_KEYSC_MODE_3, diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 6c12989839d9..f6efed0039ed 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -414,6 +414,7 @@ enum TASKLET_SOFTIRQ, SCHED_SOFTIRQ, HRTIMER_SOFTIRQ, + RCU_SOFTIRQ, /* Preferable RCU should always be the last softirq */ NR_SOFTIRQS }; diff --git a/include/linux/smp.h b/include/linux/smp.h index 7ad824d510a2..8cc38d3bab0c 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -85,12 +85,15 @@ int smp_call_function_any(const struct cpumask *mask, * Generic and arch helpers */ #ifdef CONFIG_USE_GENERIC_SMP_HELPERS +void __init call_function_init(void); void generic_smp_call_function_single_interrupt(void); void generic_smp_call_function_interrupt(void); void ipi_call_lock(void); void ipi_call_unlock(void); void ipi_call_lock_irq(void); void ipi_call_unlock_irq(void); +#else +static inline void call_function_init(void) { } #endif /* @@ -134,7 +137,7 @@ static inline void smp_send_reschedule(int cpu) { } #define smp_prepare_boot_cpu() do {} while (0) #define smp_call_function_many(mask, func, info, wait) \ (up_smp_call_function(func, info)) -static inline void init_call_single_data(void) { } +static inline void call_function_init(void) { } static inline int smp_call_function_any(const struct cpumask *mask, smp_call_func_t func, diff --git a/include/linux/sunrpc/gss_krb5_enctypes.h b/include/linux/sunrpc/gss_krb5_enctypes.h new file mode 100644 index 000000000000..ec6234eee89c --- /dev/null +++ b/include/linux/sunrpc/gss_krb5_enctypes.h @@ -0,0 +1,4 @@ +/* + * Dumb way to share this static piece of information with nfsd + */ +#define KRB5_SUPPORTED_ENCTYPES "18,17,16,23,3,1,2" diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index c7c42e7acc31..5d4f8e586e32 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -307,6 +307,12 @@ static inline int nf_ct_is_untracked(const struct nf_conn *ct) return test_bit(IPS_UNTRACKED_BIT, &ct->status); } +/* Packet is received from loopback */ +static inline bool nf_is_loopback_packet(const struct sk_buff *skb) +{ + return skb->dev && skb->skb_iif && skb->dev->flags & IFF_LOOPBACK; +} + extern int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp); extern unsigned int nf_conntrack_htable_size; extern unsigned int nf_conntrack_max; diff --git a/include/trace/events/irq.h b/include/trace/events/irq.h index ae045ca7d356..1c09820df585 100644 --- a/include/trace/events/irq.h +++ b/include/trace/events/irq.h @@ -20,7 +20,8 @@ struct softirq_action; softirq_name(BLOCK_IOPOLL), \ softirq_name(TASKLET), \ softirq_name(SCHED), \ - softirq_name(HRTIMER)) + softirq_name(HRTIMER), \ + softirq_name(RCU)) /** * irq_handler_entry - called immediately before the irq action handler diff --git a/init/main.c b/init/main.c index cafba67c13bf..d7211faed2ad 100644 --- a/init/main.c +++ b/init/main.c @@ -542,6 +542,7 @@ asmlinkage void __init start_kernel(void) timekeeping_init(); time_init(); profile_init(); + call_function_init(); if (!irqs_disabled()) printk(KERN_CRIT "start_kernel(): bug: interrupts were " "enabled early\n"); diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 89419ff92e99..7e59ffb3d0ba 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -87,6 +87,8 @@ static struct rcu_state *rcu_state; int rcu_scheduler_active __read_mostly; EXPORT_SYMBOL_GPL(rcu_scheduler_active); +#ifdef CONFIG_RCU_BOOST + /* * Control variables for per-CPU and per-rcu_node kthreads. These * handle all flavors of RCU. @@ -98,8 +100,11 @@ DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); DEFINE_PER_CPU(char, rcu_cpu_has_work); static char rcu_kthreads_spawnable; +#endif /* #ifdef CONFIG_RCU_BOOST */ + static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu); -static void invoke_rcu_cpu_kthread(void); +static void invoke_rcu_core(void); +static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp); #define RCU_KTHREAD_PRIO 1 /* RT priority for per-CPU kthreads. */ @@ -1088,14 +1093,8 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp) int need_report = 0; struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); struct rcu_node *rnp; - struct task_struct *t; - /* Stop the CPU's kthread. */ - t = per_cpu(rcu_cpu_kthread_task, cpu); - if (t != NULL) { - per_cpu(rcu_cpu_kthread_task, cpu) = NULL; - kthread_stop(t); - } + rcu_stop_cpu_kthread(cpu); /* Exclude any attempts to start a new grace period. */ raw_spin_lock_irqsave(&rsp->onofflock, flags); @@ -1231,7 +1230,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) /* Re-raise the RCU softirq if there are callbacks remaining. */ if (cpu_has_callbacks_ready_to_invoke(rdp)) - invoke_rcu_cpu_kthread(); + invoke_rcu_core(); } /* @@ -1277,7 +1276,7 @@ void rcu_check_callbacks(int cpu, int user) } rcu_preempt_check_callbacks(cpu); if (rcu_pending(cpu)) - invoke_rcu_cpu_kthread(); + invoke_rcu_core(); } #ifdef CONFIG_SMP @@ -1442,13 +1441,14 @@ __rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp) } /* If there are callbacks ready, invoke them. */ - rcu_do_batch(rsp, rdp); + if (cpu_has_callbacks_ready_to_invoke(rdp)) + invoke_rcu_callbacks(rsp, rdp); } /* * Do softirq processing for the current CPU. */ -static void rcu_process_callbacks(void) +static void rcu_process_callbacks(struct softirq_action *unused) { __rcu_process_callbacks(&rcu_sched_state, &__get_cpu_var(rcu_sched_data)); @@ -1465,342 +1465,20 @@ static void rcu_process_callbacks(void) * the current CPU with interrupts disabled, the rcu_cpu_kthread_task * cannot disappear out from under us. */ -static void invoke_rcu_cpu_kthread(void) -{ - unsigned long flags; - - local_irq_save(flags); - __this_cpu_write(rcu_cpu_has_work, 1); - if (__this_cpu_read(rcu_cpu_kthread_task) == NULL) { - local_irq_restore(flags); - return; - } - wake_up_process(__this_cpu_read(rcu_cpu_kthread_task)); - local_irq_restore(flags); -} - -/* - * Wake up the specified per-rcu_node-structure kthread. - * Because the per-rcu_node kthreads are immortal, we don't need - * to do anything to keep them alive. - */ -static void invoke_rcu_node_kthread(struct rcu_node *rnp) -{ - struct task_struct *t; - - t = rnp->node_kthread_task; - if (t != NULL) - wake_up_process(t); -} - -/* - * Set the specified CPU's kthread to run RT or not, as specified by - * the to_rt argument. The CPU-hotplug locks are held, so the task - * is not going away. - */ -static void rcu_cpu_kthread_setrt(int cpu, int to_rt) -{ - int policy; - struct sched_param sp; - struct task_struct *t; - - t = per_cpu(rcu_cpu_kthread_task, cpu); - if (t == NULL) - return; - if (to_rt) { - policy = SCHED_FIFO; - sp.sched_priority = RCU_KTHREAD_PRIO; - } else { - policy = SCHED_NORMAL; - sp.sched_priority = 0; - } - sched_setscheduler_nocheck(t, policy, &sp); -} - -/* - * Timer handler to initiate the waking up of per-CPU kthreads that - * have yielded the CPU due to excess numbers of RCU callbacks. - * We wake up the per-rcu_node kthread, which in turn will wake up - * the booster kthread. - */ -static void rcu_cpu_kthread_timer(unsigned long arg) -{ - struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, arg); - struct rcu_node *rnp = rdp->mynode; - - atomic_or(rdp->grpmask, &rnp->wakemask); - invoke_rcu_node_kthread(rnp); -} - -/* - * Drop to non-real-time priority and yield, but only after posting a - * timer that will cause us to regain our real-time priority if we - * remain preempted. Either way, we restore our real-time priority - * before returning. - */ -static void rcu_yield(void (*f)(unsigned long), unsigned long arg) -{ - struct sched_param sp; - struct timer_list yield_timer; - - setup_timer_on_stack(&yield_timer, f, arg); - mod_timer(&yield_timer, jiffies + 2); - sp.sched_priority = 0; - sched_setscheduler_nocheck(current, SCHED_NORMAL, &sp); - set_user_nice(current, 19); - schedule(); - sp.sched_priority = RCU_KTHREAD_PRIO; - sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); - del_timer(&yield_timer); -} - -/* - * Handle cases where the rcu_cpu_kthread() ends up on the wrong CPU. - * This can happen while the corresponding CPU is either coming online - * or going offline. We cannot wait until the CPU is fully online - * before starting the kthread, because the various notifier functions - * can wait for RCU grace periods. So we park rcu_cpu_kthread() until - * the corresponding CPU is online. - * - * Return 1 if the kthread needs to stop, 0 otherwise. - * - * Caller must disable bh. This function can momentarily enable it. - */ -static int rcu_cpu_kthread_should_stop(int cpu) -{ - while (cpu_is_offline(cpu) || - !cpumask_equal(¤t->cpus_allowed, cpumask_of(cpu)) || - smp_processor_id() != cpu) { - if (kthread_should_stop()) - return 1; - per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU; - per_cpu(rcu_cpu_kthread_cpu, cpu) = raw_smp_processor_id(); - local_bh_enable(); - schedule_timeout_uninterruptible(1); - if (!cpumask_equal(¤t->cpus_allowed, cpumask_of(cpu))) - set_cpus_allowed_ptr(current, cpumask_of(cpu)); - local_bh_disable(); - } - per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu; - return 0; -} - -/* - * Per-CPU kernel thread that invokes RCU callbacks. This replaces the - * earlier RCU softirq. - */ -static int rcu_cpu_kthread(void *arg) -{ - int cpu = (int)(long)arg; - unsigned long flags; - int spincnt = 0; - unsigned int *statusp = &per_cpu(rcu_cpu_kthread_status, cpu); - char work; - char *workp = &per_cpu(rcu_cpu_has_work, cpu); - - for (;;) { - *statusp = RCU_KTHREAD_WAITING; - rcu_wait(*workp != 0 || kthread_should_stop()); - local_bh_disable(); - if (rcu_cpu_kthread_should_stop(cpu)) { - local_bh_enable(); - break; - } - *statusp = RCU_KTHREAD_RUNNING; - per_cpu(rcu_cpu_kthread_loops, cpu)++; - local_irq_save(flags); - work = *workp; - *workp = 0; - local_irq_restore(flags); - if (work) - rcu_process_callbacks(); - local_bh_enable(); - if (*workp != 0) - spincnt++; - else - spincnt = 0; - if (spincnt > 10) { - *statusp = RCU_KTHREAD_YIELDING; - rcu_yield(rcu_cpu_kthread_timer, (unsigned long)cpu); - spincnt = 0; - } - } - *statusp = RCU_KTHREAD_STOPPED; - return 0; -} - -/* - * Spawn a per-CPU kthread, setting up affinity and priority. - * Because the CPU hotplug lock is held, no other CPU will be attempting - * to manipulate rcu_cpu_kthread_task. There might be another CPU - * attempting to access it during boot, but the locking in kthread_bind() - * will enforce sufficient ordering. - */ -static int __cpuinit rcu_spawn_one_cpu_kthread(int cpu) +static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp) { - struct sched_param sp; - struct task_struct *t; - - if (!rcu_kthreads_spawnable || - per_cpu(rcu_cpu_kthread_task, cpu) != NULL) - return 0; - t = kthread_create(rcu_cpu_kthread, (void *)(long)cpu, "rcuc%d", cpu); - if (IS_ERR(t)) - return PTR_ERR(t); - kthread_bind(t, cpu); - per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu; - WARN_ON_ONCE(per_cpu(rcu_cpu_kthread_task, cpu) != NULL); - per_cpu(rcu_cpu_kthread_task, cpu) = t; - sp.sched_priority = RCU_KTHREAD_PRIO; - sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); - return 0; -} - -/* - * Per-rcu_node kthread, which is in charge of waking up the per-CPU - * kthreads when needed. We ignore requests to wake up kthreads - * for offline CPUs, which is OK because force_quiescent_state() - * takes care of this case. - */ -static int rcu_node_kthread(void *arg) -{ - int cpu; - unsigned long flags; - unsigned long mask; - struct rcu_node *rnp = (struct rcu_node *)arg; - struct sched_param sp; - struct task_struct *t; - - for (;;) { - rnp->node_kthread_status = RCU_KTHREAD_WAITING; - rcu_wait(atomic_read(&rnp->wakemask) != 0); - rnp->node_kthread_status = RCU_KTHREAD_RUNNING; - raw_spin_lock_irqsave(&rnp->lock, flags); - mask = atomic_xchg(&rnp->wakemask, 0); - rcu_initiate_boost(rnp, flags); /* releases rnp->lock. */ - for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1) { - if ((mask & 0x1) == 0) - continue; - preempt_disable(); - t = per_cpu(rcu_cpu_kthread_task, cpu); - if (!cpu_online(cpu) || t == NULL) { - preempt_enable(); - continue; - } - per_cpu(rcu_cpu_has_work, cpu) = 1; - sp.sched_priority = RCU_KTHREAD_PRIO; - sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); - preempt_enable(); - } - } - /* NOTREACHED */ - rnp->node_kthread_status = RCU_KTHREAD_STOPPED; - return 0; -} - -/* - * Set the per-rcu_node kthread's affinity to cover all CPUs that are - * served by the rcu_node in question. The CPU hotplug lock is still - * held, so the value of rnp->qsmaskinit will be stable. - * - * We don't include outgoingcpu in the affinity set, use -1 if there is - * no outgoing CPU. If there are no CPUs left in the affinity set, - * this function allows the kthread to execute on any CPU. - */ -static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) -{ - cpumask_var_t cm; - int cpu; - unsigned long mask = rnp->qsmaskinit; - - if (rnp->node_kthread_task == NULL) - return; - if (!alloc_cpumask_var(&cm, GFP_KERNEL)) + if (likely(!rsp->boost)) { + rcu_do_batch(rsp, rdp); return; - cpumask_clear(cm); - for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1) - if ((mask & 0x1) && cpu != outgoingcpu) - cpumask_set_cpu(cpu, cm); - if (cpumask_weight(cm) == 0) { - cpumask_setall(cm); - for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++) - cpumask_clear_cpu(cpu, cm); - WARN_ON_ONCE(cpumask_weight(cm) == 0); } - set_cpus_allowed_ptr(rnp->node_kthread_task, cm); - rcu_boost_kthread_setaffinity(rnp, cm); - free_cpumask_var(cm); + invoke_rcu_callbacks_kthread(); } -/* - * Spawn a per-rcu_node kthread, setting priority and affinity. - * Called during boot before online/offline can happen, or, if - * during runtime, with the main CPU-hotplug locks held. So only - * one of these can be executing at a time. - */ -static int __cpuinit rcu_spawn_one_node_kthread(struct rcu_state *rsp, - struct rcu_node *rnp) +static void invoke_rcu_core(void) { - unsigned long flags; - int rnp_index = rnp - &rsp->node[0]; - struct sched_param sp; - struct task_struct *t; - - if (!rcu_kthreads_spawnable || - rnp->qsmaskinit == 0) - return 0; - if (rnp->node_kthread_task == NULL) { - t = kthread_create(rcu_node_kthread, (void *)rnp, - "rcun%d", rnp_index); - if (IS_ERR(t)) - return PTR_ERR(t); - raw_spin_lock_irqsave(&rnp->lock, flags); - rnp->node_kthread_task = t; - raw_spin_unlock_irqrestore(&rnp->lock, flags); - sp.sched_priority = 99; - sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); - } - return rcu_spawn_one_boost_kthread(rsp, rnp, rnp_index); + raise_softirq(RCU_SOFTIRQ); } -static void rcu_wake_one_boost_kthread(struct rcu_node *rnp); - -/* - * Spawn all kthreads -- called as soon as the scheduler is running. - */ -static int __init rcu_spawn_kthreads(void) -{ - int cpu; - struct rcu_node *rnp; - struct task_struct *t; - - rcu_kthreads_spawnable = 1; - for_each_possible_cpu(cpu) { - per_cpu(rcu_cpu_has_work, cpu) = 0; - if (cpu_online(cpu)) { - (void)rcu_spawn_one_cpu_kthread(cpu); - t = per_cpu(rcu_cpu_kthread_task, cpu); - if (t) - wake_up_process(t); - } - } - rnp = rcu_get_root(rcu_state); - (void)rcu_spawn_one_node_kthread(rcu_state, rnp); - if (rnp->node_kthread_task) - wake_up_process(rnp->node_kthread_task); - if (NUM_RCU_NODES > 1) { - rcu_for_each_leaf_node(rcu_state, rnp) { - (void)rcu_spawn_one_node_kthread(rcu_state, rnp); - t = rnp->node_kthread_task; - if (t) - wake_up_process(t); - rcu_wake_one_boost_kthread(rnp); - } - } - return 0; -} -early_initcall(rcu_spawn_kthreads); - static void __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), struct rcu_state *rsp) @@ -2207,44 +1885,6 @@ static void __cpuinit rcu_prepare_cpu(int cpu) rcu_preempt_init_percpu_data(cpu); } -static void __cpuinit rcu_prepare_kthreads(int cpu) -{ - struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu); - struct rcu_node *rnp = rdp->mynode; - - /* Fire up the incoming CPU's kthread and leaf rcu_node kthread. */ - if (rcu_kthreads_spawnable) { - (void)rcu_spawn_one_cpu_kthread(cpu); - if (rnp->node_kthread_task == NULL) - (void)rcu_spawn_one_node_kthread(rcu_state, rnp); - } -} - -/* - * kthread_create() creates threads in TASK_UNINTERRUPTIBLE state, - * but the RCU threads are woken on demand, and if demand is low this - * could be a while triggering the hung task watchdog. - * - * In order to avoid this, poke all tasks once the CPU is fully - * up and running. - */ -static void __cpuinit rcu_online_kthreads(int cpu) -{ - struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu); - struct rcu_node *rnp = rdp->mynode; - struct task_struct *t; - - t = per_cpu(rcu_cpu_kthread_task, cpu); - if (t) - wake_up_process(t); - - t = rnp->node_kthread_task; - if (t) - wake_up_process(t); - - rcu_wake_one_boost_kthread(rnp); -} - /* * Handle CPU online/offline notification events. */ @@ -2262,7 +1902,6 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self, rcu_prepare_kthreads(cpu); break; case CPU_ONLINE: - rcu_online_kthreads(cpu); case CPU_DOWN_FAILED: rcu_node_kthread_setaffinity(rnp, -1); rcu_cpu_kthread_setrt(cpu, 1); @@ -2410,6 +2049,7 @@ void __init rcu_init(void) rcu_init_one(&rcu_sched_state, &rcu_sched_data); rcu_init_one(&rcu_bh_state, &rcu_bh_data); __rcu_init_preempt(); + open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); /* * We don't need protection against CPU-hotplug here because diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 7b9a08b4aaea..01b2ccda26fb 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -369,6 +369,7 @@ struct rcu_state { /* period because */ /* force_quiescent_state() */ /* was running. */ + u8 boost; /* Subject to priority boost. */ unsigned long gpnum; /* Current gp number. */ unsigned long completed; /* # of last completed gp. */ @@ -426,6 +427,7 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp); #ifdef CONFIG_HOTPLUG_CPU static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags); +static void rcu_stop_cpu_kthread(int cpu); #endif /* #ifdef CONFIG_HOTPLUG_CPU */ static void rcu_print_detail_task_stall(struct rcu_state *rsp); static void rcu_print_task_stall(struct rcu_node *rnp); @@ -450,11 +452,19 @@ static void rcu_preempt_send_cbs_to_online(void); static void __init __rcu_init_preempt(void); static void rcu_needs_cpu_flush(void); static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags); +static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); +static void invoke_rcu_callbacks_kthread(void); +#ifdef CONFIG_RCU_BOOST +static void rcu_preempt_do_callbacks(void); static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, cpumask_var_t cm); -static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp, struct rcu_node *rnp, int rnp_index); +static void invoke_rcu_node_kthread(struct rcu_node *rnp); +static void rcu_yield(void (*f)(unsigned long), unsigned long arg); +#endif /* #ifdef CONFIG_RCU_BOOST */ +static void rcu_cpu_kthread_setrt(int cpu, int to_rt); +static void __cpuinit rcu_prepare_kthreads(int cpu); #endif /* #ifndef RCU_TREE_NONCORE */ diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index c8bff3099a89..14dc7dd00902 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -602,6 +602,15 @@ static void rcu_preempt_process_callbacks(void) &__get_cpu_var(rcu_preempt_data)); } +#ifdef CONFIG_RCU_BOOST + +static void rcu_preempt_do_callbacks(void) +{ + rcu_do_batch(&rcu_preempt_state, &__get_cpu_var(rcu_preempt_data)); +} + +#endif /* #ifdef CONFIG_RCU_BOOST */ + /* * Queue a preemptible-RCU callback for invocation after a grace period. */ @@ -1249,6 +1258,23 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) } /* + * Wake up the per-CPU kthread to invoke RCU callbacks. + */ +static void invoke_rcu_callbacks_kthread(void) +{ + unsigned long flags; + + local_irq_save(flags); + __this_cpu_write(rcu_cpu_has_work, 1); + if (__this_cpu_read(rcu_cpu_kthread_task) == NULL) { + local_irq_restore(flags); + return; + } + wake_up_process(__this_cpu_read(rcu_cpu_kthread_task)); + local_irq_restore(flags); +} + +/* * Set the affinity of the boost kthread. The CPU-hotplug locks are * held, so no one should be messing with the existence of the boost * kthread. @@ -1288,6 +1314,7 @@ static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp, if (&rcu_preempt_state != rsp) return 0; + rsp->boost = 1; if (rnp->boost_kthread_task != NULL) return 0; t = kthread_create(rcu_boost_kthread, (void *)rnp, @@ -1299,13 +1326,372 @@ static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp, raw_spin_unlock_irqrestore(&rnp->lock, flags); sp.sched_priority = RCU_KTHREAD_PRIO; sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); + wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */ return 0; } -static void __cpuinit rcu_wake_one_boost_kthread(struct rcu_node *rnp) +#ifdef CONFIG_HOTPLUG_CPU + +/* + * Stop the RCU's per-CPU kthread when its CPU goes offline,. + */ +static void rcu_stop_cpu_kthread(int cpu) { - if (rnp->boost_kthread_task) - wake_up_process(rnp->boost_kthread_task); + struct task_struct *t; + + /* Stop the CPU's kthread. */ + t = per_cpu(rcu_cpu_kthread_task, cpu); + if (t != NULL) { + per_cpu(rcu_cpu_kthread_task, cpu) = NULL; + kthread_stop(t); + } +} + +#endif /* #ifdef CONFIG_HOTPLUG_CPU */ + +static void rcu_kthread_do_work(void) +{ + rcu_do_batch(&rcu_sched_state, &__get_cpu_var(rcu_sched_data)); + rcu_do_batch(&rcu_bh_state, &__get_cpu_var(rcu_bh_data)); + rcu_preempt_do_callbacks(); +} + +/* + * Wake up the specified per-rcu_node-structure kthread. + * Because the per-rcu_node kthreads are immortal, we don't need + * to do anything to keep them alive. + */ +static void invoke_rcu_node_kthread(struct rcu_node *rnp) +{ + struct task_struct *t; + + t = rnp->node_kthread_task; + if (t != NULL) + wake_up_process(t); +} + +/* + * Set the specified CPU's kthread to run RT or not, as specified by + * the to_rt argument. The CPU-hotplug locks are held, so the task + * is not going away. + */ +static void rcu_cpu_kthread_setrt(int cpu, int to_rt) +{ + int policy; + struct sched_param sp; + struct task_struct *t; + + t = per_cpu(rcu_cpu_kthread_task, cpu); + if (t == NULL) + return; + if (to_rt) { + policy = SCHED_FIFO; + sp.sched_priority = RCU_KTHREAD_PRIO; + } else { + policy = SCHED_NORMAL; + sp.sched_priority = 0; + } + sched_setscheduler_nocheck(t, policy, &sp); +} + +/* + * Timer handler to initiate the waking up of per-CPU kthreads that + * have yielded the CPU due to excess numbers of RCU callbacks. + * We wake up the per-rcu_node kthread, which in turn will wake up + * the booster kthread. + */ +static void rcu_cpu_kthread_timer(unsigned long arg) +{ + struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, arg); + struct rcu_node *rnp = rdp->mynode; + + atomic_or(rdp->grpmask, &rnp->wakemask); + invoke_rcu_node_kthread(rnp); +} + +/* + * Drop to non-real-time priority and yield, but only after posting a + * timer that will cause us to regain our real-time priority if we + * remain preempted. Either way, we restore our real-time priority + * before returning. + */ +static void rcu_yield(void (*f)(unsigned long), unsigned long arg) +{ + struct sched_param sp; + struct timer_list yield_timer; + + setup_timer_on_stack(&yield_timer, f, arg); + mod_timer(&yield_timer, jiffies + 2); + sp.sched_priority = 0; + sched_setscheduler_nocheck(current, SCHED_NORMAL, &sp); + set_user_nice(current, 19); + schedule(); + sp.sched_priority = RCU_KTHREAD_PRIO; + sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); + del_timer(&yield_timer); +} + +/* + * Handle cases where the rcu_cpu_kthread() ends up on the wrong CPU. + * This can happen while the corresponding CPU is either coming online + * or going offline. We cannot wait until the CPU is fully online + * before starting the kthread, because the various notifier functions + * can wait for RCU grace periods. So we park rcu_cpu_kthread() until + * the corresponding CPU is online. + * + * Return 1 if the kthread needs to stop, 0 otherwise. + * + * Caller must disable bh. This function can momentarily enable it. + */ +static int rcu_cpu_kthread_should_stop(int cpu) +{ + while (cpu_is_offline(cpu) || + !cpumask_equal(¤t->cpus_allowed, cpumask_of(cpu)) || + smp_processor_id() != cpu) { + if (kthread_should_stop()) + return 1; + per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU; + per_cpu(rcu_cpu_kthread_cpu, cpu) = raw_smp_processor_id(); + local_bh_enable(); + schedule_timeout_uninterruptible(1); + if (!cpumask_equal(¤t->cpus_allowed, cpumask_of(cpu))) + set_cpus_allowed_ptr(current, cpumask_of(cpu)); + local_bh_disable(); + } + per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu; + return 0; +} + +/* + * Per-CPU kernel thread that invokes RCU callbacks. This replaces the + * earlier RCU softirq. + */ +static int rcu_cpu_kthread(void *arg) +{ + int cpu = (int)(long)arg; + unsigned long flags; + int spincnt = 0; + unsigned int *statusp = &per_cpu(rcu_cpu_kthread_status, cpu); + char work; + char *workp = &per_cpu(rcu_cpu_has_work, cpu); + + for (;;) { + *statusp = RCU_KTHREAD_WAITING; + rcu_wait(*workp != 0 || kthread_should_stop()); + local_bh_disable(); + if (rcu_cpu_kthread_should_stop(cpu)) { + local_bh_enable(); + break; + } + *statusp = RCU_KTHREAD_RUNNING; + per_cpu(rcu_cpu_kthread_loops, cpu)++; + local_irq_save(flags); + work = *workp; + *workp = 0; + local_irq_restore(flags); + if (work) + rcu_kthread_do_work(); + local_bh_enable(); + if (*workp != 0) + spincnt++; + else + spincnt = 0; + if (spincnt > 10) { + *statusp = RCU_KTHREAD_YIELDING; + rcu_yield(rcu_cpu_kthread_timer, (unsigned long)cpu); + spincnt = 0; + } + } + *statusp = RCU_KTHREAD_STOPPED; + return 0; +} + +/* + * Spawn a per-CPU kthread, setting up affinity and priority. + * Because the CPU hotplug lock is held, no other CPU will be attempting + * to manipulate rcu_cpu_kthread_task. There might be another CPU + * attempting to access it during boot, but the locking in kthread_bind() + * will enforce sufficient ordering. + * + * Please note that we cannot simply refuse to wake up the per-CPU + * kthread because kthreads are created in TASK_UNINTERRUPTIBLE state, + * which can result in softlockup complaints if the task ends up being + * idle for more than a couple of minutes. + * + * However, please note also that we cannot bind the per-CPU kthread to its + * CPU until that CPU is fully online. We also cannot wait until the + * CPU is fully online before we create its per-CPU kthread, as this would + * deadlock the system when CPU notifiers tried waiting for grace + * periods. So we bind the per-CPU kthread to its CPU only if the CPU + * is online. If its CPU is not yet fully online, then the code in + * rcu_cpu_kthread() will wait until it is fully online, and then do + * the binding. + */ +static int __cpuinit rcu_spawn_one_cpu_kthread(int cpu) +{ + struct sched_param sp; + struct task_struct *t; + + if (!rcu_kthreads_spawnable || + per_cpu(rcu_cpu_kthread_task, cpu) != NULL) + return 0; + t = kthread_create(rcu_cpu_kthread, (void *)(long)cpu, "rcuc%d", cpu); + if (IS_ERR(t)) + return PTR_ERR(t); + if (cpu_online(cpu)) + kthread_bind(t, cpu); + per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu; + WARN_ON_ONCE(per_cpu(rcu_cpu_kthread_task, cpu) != NULL); + sp.sched_priority = RCU_KTHREAD_PRIO; + sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); + per_cpu(rcu_cpu_kthread_task, cpu) = t; + wake_up_process(t); /* Get to TASK_INTERRUPTIBLE quickly. */ + return 0; +} + +/* + * Per-rcu_node kthread, which is in charge of waking up the per-CPU + * kthreads when needed. We ignore requests to wake up kthreads + * for offline CPUs, which is OK because force_quiescent_state() + * takes care of this case. + */ +static int rcu_node_kthread(void *arg) +{ + int cpu; + unsigned long flags; + unsigned long mask; + struct rcu_node *rnp = (struct rcu_node *)arg; + struct sched_param sp; + struct task_struct *t; + + for (;;) { + rnp->node_kthread_status = RCU_KTHREAD_WAITING; + rcu_wait(atomic_read(&rnp->wakemask) != 0); + rnp->node_kthread_status = RCU_KTHREAD_RUNNING; + raw_spin_lock_irqsave(&rnp->lock, flags); + mask = atomic_xchg(&rnp->wakemask, 0); + rcu_initiate_boost(rnp, flags); /* releases rnp->lock. */ + for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1) { + if ((mask & 0x1) == 0) + continue; + preempt_disable(); + t = per_cpu(rcu_cpu_kthread_task, cpu); + if (!cpu_online(cpu) || t == NULL) { + preempt_enable(); + continue; + } + per_cpu(rcu_cpu_has_work, cpu) = 1; + sp.sched_priority = RCU_KTHREAD_PRIO; + sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); + preempt_enable(); + } + } + /* NOTREACHED */ + rnp->node_kthread_status = RCU_KTHREAD_STOPPED; + return 0; +} + +/* + * Set the per-rcu_node kthread's affinity to cover all CPUs that are + * served by the rcu_node in question. The CPU hotplug lock is still + * held, so the value of rnp->qsmaskinit will be stable. + * + * We don't include outgoingcpu in the affinity set, use -1 if there is + * no outgoing CPU. If there are no CPUs left in the affinity set, + * this function allows the kthread to execute on any CPU. + */ +static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) +{ + cpumask_var_t cm; + int cpu; + unsigned long mask = rnp->qsmaskinit; + + if (rnp->node_kthread_task == NULL) + return; + if (!alloc_cpumask_var(&cm, GFP_KERNEL)) + return; + cpumask_clear(cm); + for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1) + if ((mask & 0x1) && cpu != outgoingcpu) + cpumask_set_cpu(cpu, cm); + if (cpumask_weight(cm) == 0) { + cpumask_setall(cm); + for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++) + cpumask_clear_cpu(cpu, cm); + WARN_ON_ONCE(cpumask_weight(cm) == 0); + } + set_cpus_allowed_ptr(rnp->node_kthread_task, cm); + rcu_boost_kthread_setaffinity(rnp, cm); + free_cpumask_var(cm); +} + +/* + * Spawn a per-rcu_node kthread, setting priority and affinity. + * Called during boot before online/offline can happen, or, if + * during runtime, with the main CPU-hotplug locks held. So only + * one of these can be executing at a time. + */ +static int __cpuinit rcu_spawn_one_node_kthread(struct rcu_state *rsp, + struct rcu_node *rnp) +{ + unsigned long flags; + int rnp_index = rnp - &rsp->node[0]; + struct sched_param sp; + struct task_struct *t; + + if (!rcu_kthreads_spawnable || + rnp->qsmaskinit == 0) + return 0; + if (rnp->node_kthread_task == NULL) { + t = kthread_create(rcu_node_kthread, (void *)rnp, + "rcun%d", rnp_index); + if (IS_ERR(t)) + return PTR_ERR(t); + raw_spin_lock_irqsave(&rnp->lock, flags); + rnp->node_kthread_task = t; + raw_spin_unlock_irqrestore(&rnp->lock, flags); + sp.sched_priority = 99; + sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); + wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */ + } + return rcu_spawn_one_boost_kthread(rsp, rnp, rnp_index); +} + +/* + * Spawn all kthreads -- called as soon as the scheduler is running. + */ +static int __init rcu_spawn_kthreads(void) +{ + int cpu; + struct rcu_node *rnp; + + rcu_kthreads_spawnable = 1; + for_each_possible_cpu(cpu) { + per_cpu(rcu_cpu_has_work, cpu) = 0; + if (cpu_online(cpu)) + (void)rcu_spawn_one_cpu_kthread(cpu); + } + rnp = rcu_get_root(rcu_state); + (void)rcu_spawn_one_node_kthread(rcu_state, rnp); + if (NUM_RCU_NODES > 1) { + rcu_for_each_leaf_node(rcu_state, rnp) + (void)rcu_spawn_one_node_kthread(rcu_state, rnp); + } + return 0; +} +early_initcall(rcu_spawn_kthreads); + +static void __cpuinit rcu_prepare_kthreads(int cpu) +{ + struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu); + struct rcu_node *rnp = rdp->mynode; + + /* Fire up the incoming CPU's kthread and leaf rcu_node kthread. */ + if (rcu_kthreads_spawnable) { + (void)rcu_spawn_one_cpu_kthread(cpu); + if (rnp->node_kthread_task == NULL) + (void)rcu_spawn_one_node_kthread(rcu_state, rnp); + } } #else /* #ifdef CONFIG_RCU_BOOST */ @@ -1315,23 +1701,32 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) raw_spin_unlock_irqrestore(&rnp->lock, flags); } -static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, - cpumask_var_t cm) +static void invoke_rcu_callbacks_kthread(void) { + WARN_ON_ONCE(1); } static void rcu_preempt_boost_start_gp(struct rcu_node *rnp) { } -static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp, - struct rcu_node *rnp, - int rnp_index) +#ifdef CONFIG_HOTPLUG_CPU + +static void rcu_stop_cpu_kthread(int cpu) +{ +} + +#endif /* #ifdef CONFIG_HOTPLUG_CPU */ + +static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) +{ +} + +static void rcu_cpu_kthread_setrt(int cpu, int to_rt) { - return 0; } -static void __cpuinit rcu_wake_one_boost_kthread(struct rcu_node *rnp) +static void __cpuinit rcu_prepare_kthreads(int cpu) { } @@ -1509,7 +1904,7 @@ static DEFINE_PER_CPU(unsigned long, rcu_dyntick_holdoff); * * Because it is not legal to invoke rcu_process_callbacks() with irqs * disabled, we do one pass of force_quiescent_state(), then do a - * invoke_rcu_cpu_kthread() to cause rcu_process_callbacks() to be invoked + * invoke_rcu_core() to cause rcu_process_callbacks() to be invoked * later. The per-cpu rcu_dyntick_drain variable controls the sequencing. */ int rcu_needs_cpu(int cpu) @@ -1560,7 +1955,7 @@ int rcu_needs_cpu(int cpu) /* If RCU callbacks are still pending, RCU still needs this CPU. */ if (c) - invoke_rcu_cpu_kthread(); + invoke_rcu_core(); return c; } diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c index 9678cc3650f5..4e144876dc68 100644 --- a/kernel/rcutree_trace.c +++ b/kernel/rcutree_trace.c @@ -46,6 +46,8 @@ #define RCU_TREE_NONCORE #include "rcutree.h" +#ifdef CONFIG_RCU_BOOST + DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status); DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_cpu); DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); @@ -58,6 +60,8 @@ static char convert_kthread_status(unsigned int kthread_status) return "SRWOY"[kthread_status]; } +#endif /* #ifdef CONFIG_RCU_BOOST */ + static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) { if (!rdp->beenonline) @@ -76,7 +80,7 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) rdp->dynticks_fqs); #endif /* #ifdef CONFIG_NO_HZ */ seq_printf(m, " of=%lu ri=%lu", rdp->offline_fqs, rdp->resched_ipi); - seq_printf(m, " ql=%ld qs=%c%c%c%c kt=%d/%c/%d ktl=%x b=%ld", + seq_printf(m, " ql=%ld qs=%c%c%c%c", rdp->qlen, ".N"[rdp->nxttail[RCU_NEXT_READY_TAIL] != rdp->nxttail[RCU_NEXT_TAIL]], @@ -84,13 +88,16 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) rdp->nxttail[RCU_NEXT_READY_TAIL]], ".W"[rdp->nxttail[RCU_DONE_TAIL] != rdp->nxttail[RCU_WAIT_TAIL]], - ".D"[&rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL]], + ".D"[&rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL]]); +#ifdef CONFIG_RCU_BOOST + seq_printf(m, " kt=%d/%c/%d ktl=%x", per_cpu(rcu_cpu_has_work, rdp->cpu), convert_kthread_status(per_cpu(rcu_cpu_kthread_status, rdp->cpu)), per_cpu(rcu_cpu_kthread_cpu, rdp->cpu), - per_cpu(rcu_cpu_kthread_loops, rdp->cpu) & 0xffff, - rdp->blimit); + per_cpu(rcu_cpu_kthread_loops, rdp->cpu) & 0xffff); +#endif /* #ifdef CONFIG_RCU_BOOST */ + seq_printf(m, " b=%ld", rdp->blimit); seq_printf(m, " ci=%lu co=%lu ca=%lu\n", rdp->n_cbs_invoked, rdp->n_cbs_orphaned, rdp->n_cbs_adopted); } @@ -147,18 +154,21 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp) rdp->dynticks_fqs); #endif /* #ifdef CONFIG_NO_HZ */ seq_printf(m, ",%lu,%lu", rdp->offline_fqs, rdp->resched_ipi); - seq_printf(m, ",%ld,\"%c%c%c%c\",%d,\"%c\",%ld", rdp->qlen, + seq_printf(m, ",%ld,\"%c%c%c%c\"", rdp->qlen, ".N"[rdp->nxttail[RCU_NEXT_READY_TAIL] != rdp->nxttail[RCU_NEXT_TAIL]], ".R"[rdp->nxttail[RCU_WAIT_TAIL] != rdp->nxttail[RCU_NEXT_READY_TAIL]], ".W"[rdp->nxttail[RCU_DONE_TAIL] != rdp->nxttail[RCU_WAIT_TAIL]], - ".D"[&rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL]], + ".D"[&rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL]]); +#ifdef CONFIG_RCU_BOOST + seq_printf(m, ",%d,\"%c\"", per_cpu(rcu_cpu_has_work, rdp->cpu), convert_kthread_status(per_cpu(rcu_cpu_kthread_status, - rdp->cpu)), - rdp->blimit); + rdp->cpu))); +#endif /* #ifdef CONFIG_RCU_BOOST */ + seq_printf(m, ",%ld", rdp->blimit); seq_printf(m, ",%lu,%lu,%lu\n", rdp->n_cbs_invoked, rdp->n_cbs_orphaned, rdp->n_cbs_adopted); } @@ -169,7 +179,11 @@ static int show_rcudata_csv(struct seq_file *m, void *unused) #ifdef CONFIG_NO_HZ seq_puts(m, "\"dt\",\"dt nesting\",\"dt NMI nesting\",\"df\","); #endif /* #ifdef CONFIG_NO_HZ */ - seq_puts(m, "\"of\",\"ri\",\"ql\",\"b\",\"ci\",\"co\",\"ca\"\n"); + seq_puts(m, "\"of\",\"ri\",\"ql\",\"qs\""); +#ifdef CONFIG_RCU_BOOST + seq_puts(m, "\"kt\",\"ktl\""); +#endif /* #ifdef CONFIG_RCU_BOOST */ + seq_puts(m, ",\"b\",\"ci\",\"co\",\"ca\"\n"); #ifdef CONFIG_TREE_PREEMPT_RCU seq_puts(m, "\"rcu_preempt:\"\n"); PRINT_RCU_DATA(rcu_preempt_data, print_one_rcu_data_csv, m); diff --git a/kernel/smp.c b/kernel/smp.c index 73a195193558..fb67dfa8394e 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -74,7 +74,7 @@ static struct notifier_block __cpuinitdata hotplug_cfd_notifier = { .notifier_call = hotplug_cfd, }; -static int __cpuinit init_call_single_data(void) +void __init call_function_init(void) { void *cpu = (void *)(long)smp_processor_id(); int i; @@ -88,10 +88,7 @@ static int __cpuinit init_call_single_data(void) hotplug_cfd(&hotplug_cfd_notifier, CPU_UP_PREPARE, cpu); register_cpu_notifier(&hotplug_cfd_notifier); - - return 0; } -early_initcall(init_call_single_data); /* * csd_lock/csd_unlock used to serialize access to per-cpu csd resources diff --git a/kernel/softirq.c b/kernel/softirq.c index 13960170cad4..40cf63ddd4b3 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -58,7 +58,7 @@ DEFINE_PER_CPU(struct task_struct *, ksoftirqd); char *softirq_to_name[NR_SOFTIRQS] = { "HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "BLOCK_IOPOLL", - "TASKLET", "SCHED", "HRTIMER" + "TASKLET", "SCHED", "HRTIMER", "RCU" }; /* diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 1c95fd677328..e0980f0d9a0a 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -185,7 +185,6 @@ static struct clocksource *watchdog; static struct timer_list watchdog_timer; static DECLARE_WORK(watchdog_work, clocksource_watchdog_work); static DEFINE_SPINLOCK(watchdog_lock); -static cycle_t watchdog_last; static int watchdog_running; static int clocksource_watchdog_kthread(void *data); @@ -254,11 +253,6 @@ static void clocksource_watchdog(unsigned long data) if (!watchdog_running) goto out; - wdnow = watchdog->read(watchdog); - wd_nsec = clocksource_cyc2ns((wdnow - watchdog_last) & watchdog->mask, - watchdog->mult, watchdog->shift); - watchdog_last = wdnow; - list_for_each_entry(cs, &watchdog_list, wd_list) { /* Clocksource already marked unstable? */ @@ -268,19 +262,28 @@ static void clocksource_watchdog(unsigned long data) continue; } + local_irq_disable(); csnow = cs->read(cs); + wdnow = watchdog->read(watchdog); + local_irq_enable(); /* Clocksource initialized ? */ if (!(cs->flags & CLOCK_SOURCE_WATCHDOG)) { cs->flags |= CLOCK_SOURCE_WATCHDOG; - cs->wd_last = csnow; + cs->wd_last = wdnow; + cs->cs_last = csnow; continue; } - /* Check the deviation from the watchdog clocksource. */ - cs_nsec = clocksource_cyc2ns((csnow - cs->wd_last) & + wd_nsec = clocksource_cyc2ns((wdnow - cs->wd_last) & watchdog->mask, + watchdog->mult, watchdog->shift); + + cs_nsec = clocksource_cyc2ns((csnow - cs->cs_last) & cs->mask, cs->mult, cs->shift); - cs->wd_last = csnow; + cs->cs_last = csnow; + cs->wd_last = wdnow; + + /* Check the deviation from the watchdog clocksource. */ if (abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD) { clocksource_unstable(cs, cs_nsec - wd_nsec); continue; @@ -318,7 +321,6 @@ static inline void clocksource_start_watchdog(void) return; init_timer(&watchdog_timer); watchdog_timer.function = clocksource_watchdog; - watchdog_last = watchdog->read(watchdog); watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL; add_timer_on(&watchdog_timer, cpumask_first(cpu_online_mask)); watchdog_running = 1; diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c index dff763b7baf1..1f06468a10d7 100644 --- a/kernel/trace/trace_printk.c +++ b/kernel/trace/trace_printk.c @@ -240,13 +240,10 @@ static const char **find_next(void *v, loff_t *pos) const char **fmt = v; int start_index; - if (!fmt) - fmt = __start___trace_bprintk_fmt + *pos; - start_index = __stop___trace_bprintk_fmt - __start___trace_bprintk_fmt; if (*pos < start_index) - return fmt; + return __start___trace_bprintk_fmt + *pos; return find_next_mod_format(start_index, v, fmt, pos); } diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index c7a581a96894..917ecb93ea28 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -205,7 +205,7 @@ int register_vlan_dev(struct net_device *dev) grp->nr_vlans++; if (ngrp) { - if (ops->ndo_vlan_rx_register) + if (ops->ndo_vlan_rx_register && (real_dev->features & NETIF_F_HW_VLAN_RX)) ops->ndo_vlan_rx_register(real_dev, ngrp); rcu_assign_pointer(real_dev->vlgrp, ngrp); } diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index f13ddbf858ba..77930aa522e3 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -477,14 +477,16 @@ static void hci_setup_event_mask(struct hci_dev *hdev) * command otherwise */ u8 events[8] = { 0xff, 0xff, 0xfb, 0xff, 0x00, 0x00, 0x00, 0x00 }; - /* Events for 1.2 and newer controllers */ - if (hdev->lmp_ver > 1) { - events[4] |= 0x01; /* Flow Specification Complete */ - events[4] |= 0x02; /* Inquiry Result with RSSI */ - events[4] |= 0x04; /* Read Remote Extended Features Complete */ - events[5] |= 0x08; /* Synchronous Connection Complete */ - events[5] |= 0x10; /* Synchronous Connection Changed */ - } + /* CSR 1.1 dongles does not accept any bitfield so don't try to set + * any event mask for pre 1.2 devices */ + if (hdev->lmp_ver <= 1) + return; + + events[4] |= 0x01; /* Flow Specification Complete */ + events[4] |= 0x02; /* Inquiry Result with RSSI */ + events[4] |= 0x04; /* Read Remote Extended Features Complete */ + events[5] |= 0x08; /* Synchronous Connection Complete */ + events[5] |= 0x10; /* Synchronous Connection Changed */ if (hdev->features[3] & LMP_RSSI_INQ) events[4] |= 0x04; /* Inquiry Result with RSSI */ diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 18dc9888d8c2..8248303f44e8 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -413,6 +413,7 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, char __us break; } + memset(&cinfo, 0, sizeof(cinfo)); cinfo.hci_handle = chan->conn->hcon->handle; memcpy(cinfo.dev_class, chan->conn->hcon->dev_class, 3); diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 386cfaffd4b7..1b10727ce523 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -788,6 +788,7 @@ static int rfcomm_sock_getsockopt_old(struct socket *sock, int optname, char __u l2cap_sk = rfcomm_pi(sk)->dlc->session->sock->sk; + memset(&cinfo, 0, sizeof(cinfo)); cinfo.hci_handle = conn->hcon->handle; memcpy(cinfo.dev_class, conn->hcon->dev_class, 3); diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 42fdffd1d76c..cb4fb7837e5c 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -369,6 +369,15 @@ static void __sco_sock_close(struct sock *sk) case BT_CONNECTED: case BT_CONFIG: + if (sco_pi(sk)->conn) { + sk->sk_state = BT_DISCONN; + sco_sock_set_timer(sk, SCO_DISCONN_TIMEOUT); + hci_conn_put(sco_pi(sk)->conn->hcon); + sco_pi(sk)->conn->hcon = NULL; + } else + sco_chan_del(sk, ECONNRESET); + break; + case BT_CONNECT: case BT_DISCONN: sco_chan_del(sk, ECONNRESET); @@ -819,7 +828,9 @@ static void sco_chan_del(struct sock *sk, int err) conn->sk = NULL; sco_pi(sk)->conn = NULL; sco_conn_unlock(conn); - hci_conn_put(conn->hcon); + + if (conn->hcon) + hci_conn_put(conn->hcon); } sk->sk_state = BT_CLOSED; diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index a6b2f86378c7..c188c803c09c 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -243,6 +243,7 @@ int br_netpoll_enable(struct net_bridge_port *p) goto out; np->dev = p->dev; + strlcpy(np->dev_name, p->dev->name, IFNAMSIZ); err = __netpoll_setup(np); if (err) { diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 2f14eafdeeab..29b9812c8da0 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1424,7 +1424,7 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, switch (ih->type) { case IGMP_HOST_MEMBERSHIP_REPORT: case IGMPV2_HOST_MEMBERSHIP_REPORT: - BR_INPUT_SKB_CB(skb2)->mrouters_only = 1; + BR_INPUT_SKB_CB(skb)->mrouters_only = 1; err = br_ip4_multicast_add_group(br, port, ih->group); break; case IGMPV3_HOST_MEMBERSHIP_REPORT: @@ -1543,7 +1543,7 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, goto out; } mld = (struct mld_msg *)skb_transport_header(skb2); - BR_INPUT_SKB_CB(skb2)->mrouters_only = 1; + BR_INPUT_SKB_CB(skb)->mrouters_only = 1; err = br_ip6_multicast_add_group(br, port, &mld->mld_mca); break; } diff --git a/net/caif/cfmuxl.c b/net/caif/cfmuxl.c index 3a66b8c10e09..c23979e79dfa 100644 --- a/net/caif/cfmuxl.c +++ b/net/caif/cfmuxl.c @@ -255,7 +255,7 @@ static void cfmuxl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl, if (cfsrvl_phyid_match(layer, phyid) && layer->ctrlcmd) { - if ((ctrl == _CAIF_CTRLCMD_PHYIF_FLOW_OFF_IND || + if ((ctrl == _CAIF_CTRLCMD_PHYIF_DOWN_IND || ctrl == CAIF_CTRLCMD_REMOTE_SHUTDOWN_IND) && layer->id != 0) { diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c index ed0eab39f531..02548b292b53 100644 --- a/net/ieee802154/nl-phy.c +++ b/net/ieee802154/nl-phy.c @@ -44,7 +44,7 @@ static int ieee802154_nl_fill_phy(struct sk_buff *msg, u32 pid, pr_debug("%s\n", __func__); if (!buf) - goto out; + return -EMSGSIZE; hdr = genlmsg_put(msg, 0, seq, &nl802154_family, flags, IEEE802154_LIST_PHY); @@ -65,6 +65,7 @@ static int ieee802154_nl_fill_phy(struct sk_buff *msg, u32 pid, pages * sizeof(uint32_t), buf); mutex_unlock(&phy->pib_lock); + kfree(buf); return genlmsg_end(msg, hdr); nla_put_failure: diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 9c1926027a26..eae1f676f870 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -676,6 +676,7 @@ int inet_accept(struct socket *sock, struct socket *newsock, int flags) lock_sock(sk2); + sock_rps_record_flow(sk2); WARN_ON(!((1 << sk2->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT | TCPF_CLOSE))); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 6ffe94ca5bc9..3267d3898437 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -437,7 +437,7 @@ static int valid_cc(const void *bc, int len, int cc) return 0; if (cc == len) return 1; - if (op->yes < 4) + if (op->yes < 4 || op->yes & 3) return 0; len -= op->yes; bc += op->yes; @@ -447,11 +447,11 @@ static int valid_cc(const void *bc, int len, int cc) static int inet_diag_bc_audit(const void *bytecode, int bytecode_len) { - const unsigned char *bc = bytecode; + const void *bc = bytecode; int len = bytecode_len; while (len > 0) { - struct inet_diag_bc_op *op = (struct inet_diag_bc_op *)bc; + const struct inet_diag_bc_op *op = bc; //printk("BC: %d %d %d {%d} / %d\n", op->code, op->yes, op->no, op[1].no, len); switch (op->code) { @@ -462,22 +462,20 @@ static int inet_diag_bc_audit(const void *bytecode, int bytecode_len) case INET_DIAG_BC_S_LE: case INET_DIAG_BC_D_GE: case INET_DIAG_BC_D_LE: - if (op->yes < 4 || op->yes > len + 4) - return -EINVAL; case INET_DIAG_BC_JMP: - if (op->no < 4 || op->no > len + 4) + if (op->no < 4 || op->no > len + 4 || op->no & 3) return -EINVAL; if (op->no < len && !valid_cc(bytecode, bytecode_len, len - op->no)) return -EINVAL; break; case INET_DIAG_BC_NOP: - if (op->yes < 4 || op->yes > len + 4) - return -EINVAL; break; default: return -EINVAL; } + if (op->yes < 4 || op->yes > len + 4 || op->yes & 3) + return -EINVAL; bc += op->yes; len -= op->yes; } diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c index f7f9bd7ba12d..5c9b9d963918 100644 --- a/net/ipv4/netfilter/ip_queue.c +++ b/net/ipv4/netfilter/ip_queue.c @@ -203,7 +203,8 @@ ipq_build_packet_message(struct nf_queue_entry *entry, int *errp) else pmsg->outdev_name[0] = '\0'; - if (entry->indev && entry->skb->dev) { + if (entry->indev && entry->skb->dev && + entry->skb->mac_header != entry->skb->network_header) { pmsg->hw_type = entry->skb->dev->type; pmsg->hw_addrlen = dev_parse_header(entry->skb, pmsg->hw_addr); diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 764743843503..24e556e83a3b 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -566,7 +566,7 @@ check_entry(const struct ipt_entry *e, const char *name) const struct xt_entry_target *t; if (!ip_checkentry(&e->ip)) { - duprintf("ip check failed %p %s.\n", e, par->match->name); + duprintf("ip check failed %p %s.\n", e, name); return -EINVAL; } diff --git a/net/ipv4/netfilter/ipt_ecn.c b/net/ipv4/netfilter/ipt_ecn.c index af6e9c778345..2b57e52c746c 100644 --- a/net/ipv4/netfilter/ipt_ecn.c +++ b/net/ipv4/netfilter/ipt_ecn.c @@ -25,7 +25,8 @@ MODULE_LICENSE("GPL"); static inline bool match_ip(const struct sk_buff *skb, const struct ipt_ecn_info *einfo) { - return (ip_hdr(skb)->tos & IPT_ECN_IP_MASK) == einfo->ip_ect; + return ((ip_hdr(skb)->tos & IPT_ECN_IP_MASK) == einfo->ip_ect) ^ + !!(einfo->invert & IPT_ECN_OP_MATCH_IP); } static inline bool match_tcp(const struct sk_buff *skb, @@ -76,8 +77,6 @@ static bool ecn_mt(const struct sk_buff *skb, struct xt_action_param *par) return false; if (info->operation & (IPT_ECN_OP_MATCH_ECE|IPT_ECN_OP_MATCH_CWR)) { - if (ip_hdr(skb)->protocol != IPPROTO_TCP) - return false; if (!match_tcp(skb, info, &par->hotdrop)) return false; } @@ -97,7 +96,7 @@ static int ecn_mt_check(const struct xt_mtchk_param *par) return -EINVAL; if (info->operation & (IPT_ECN_OP_MATCH_ECE|IPT_ECN_OP_MATCH_CWR) && - ip->proto != IPPROTO_TCP) { + (ip->proto != IPPROTO_TCP || ip->invflags & IPT_INV_PROTO)) { pr_info("cannot match TCP bits in rule for non-tcp packets\n"); return -EINVAL; } diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index db10075dd88e..de9da21113a1 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -121,7 +121,9 @@ static unsigned int ipv4_confirm(unsigned int hooknum, return ret; } - if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status)) { + /* adjust seqs for loopback traffic only in outgoing direction */ + if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && + !nf_is_loopback_packet(skb)) { typeof(nf_nat_seq_adjust_hook) seq_adjust; seq_adjust = rcu_dereference(nf_nat_seq_adjust_hook); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 9aaa67165f42..39b403f854c6 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -41,7 +41,6 @@ #include <linux/proc_fs.h> #include <net/sock.h> #include <net/ping.h> -#include <net/icmp.h> #include <net/udp.h> #include <net/route.h> #include <net/inet_common.h> diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 045f0ec6a4a0..aa13ef105110 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1902,9 +1902,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, hash = rt_hash(daddr, saddr, dev->ifindex, rt_genid(dev_net(dev))); rth = rt_intern_hash(hash, rth, skb, dev->ifindex); - err = 0; - if (IS_ERR(rth)) - err = PTR_ERR(rth); + return IS_ERR(rth) ? PTR_ERR(rth) : 0; e_nobufs: return -ENOBUFS; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a7d6671e33b8..708dc203b034 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1589,6 +1589,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) goto discard; if (nsk != sk) { + sock_rps_save_rxhash(nsk, skb->rxhash); if (tcp_child_process(sk, nsk, skb)) { rsk = nsk; goto reset; diff --git a/net/ipv6/netfilter/ip6_queue.c b/net/ipv6/netfilter/ip6_queue.c index 065fe405fb58..249394863284 100644 --- a/net/ipv6/netfilter/ip6_queue.c +++ b/net/ipv6/netfilter/ip6_queue.c @@ -204,7 +204,8 @@ ipq_build_packet_message(struct nf_queue_entry *entry, int *errp) else pmsg->outdev_name[0] = '\0'; - if (entry->indev && entry->skb->dev) { + if (entry->indev && entry->skb->dev && + entry->skb->mac_header != entry->skb->network_header) { pmsg->hw_type = entry->skb->dev->type; pmsg->hw_addrlen = dev_parse_header(entry->skb, pmsg->hw_addr); } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index d1fd28711ba5..87551ca568cd 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1644,6 +1644,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) * the new socket.. */ if(nsk != sk) { + sock_rps_save_rxhash(nsk, skb->rxhash); if (tcp_child_process(sk, nsk, skb)) goto reset; if (opt_skb) diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index bf28ac2fc99b..782db275ac53 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -776,8 +776,16 @@ static void ip_vs_conn_expire(unsigned long data) if (cp->control) ip_vs_control_del(cp); - if (cp->flags & IP_VS_CONN_F_NFCT) + if (cp->flags & IP_VS_CONN_F_NFCT) { ip_vs_conn_drop_conntrack(cp); + /* Do not access conntracks during subsys cleanup + * because nf_conntrack_find_get can not be used after + * conntrack cleanup for the net. + */ + smp_rmb(); + if (ipvs->enable) + ip_vs_conn_drop_conntrack(cp); + } ip_vs_pe_put(cp->pe); kfree(cp->pe_data); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 55af2242bccd..24c28d238dcb 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1945,6 +1945,7 @@ static void __net_exit __ip_vs_dev_cleanup(struct net *net) { EnterFunction(2); net_ipvs(net)->enable = 0; /* Disable packet reception */ + smp_wmb(); __ip_vs_sync_cleanup(net); LeaveFunction(2); } diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index e0ee010935e7..2e7ccbb43ddb 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -456,7 +456,8 @@ __build_packet_message(struct nfulnl_instance *inst, if (skb->mark) NLA_PUT_BE32(inst->skb, NFULA_MARK, htonl(skb->mark)); - if (indev && skb->dev) { + if (indev && skb->dev && + skb->mac_header != skb->network_header) { struct nfulnl_msg_packet_hw phw; int len = dev_parse_header(skb, phw.hw_addr); if (len > 0) { diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index b83123f12b42..fdd2fafe0a14 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -335,7 +335,8 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, if (entskb->mark) NLA_PUT_BE32(skb, NFQA_MARK, htonl(entskb->mark)); - if (indev && entskb->dev) { + if (indev && entskb->dev && + entskb->mac_header != entskb->network_header) { struct nfqnl_msg_packet_hw phw; int len = dev_parse_header(entskb, phw.hw_addr); if (len) { diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index 0a9a2ec2e469..c3b75333b821 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -43,6 +43,7 @@ #include <linux/sunrpc/gss_krb5.h> #include <linux/sunrpc/xdr.h> #include <linux/crypto.h> +#include <linux/sunrpc/gss_krb5_enctypes.h> #ifdef RPC_DEBUG # define RPCDBG_FACILITY RPCDBG_AUTH @@ -750,7 +751,7 @@ static struct gss_api_mech gss_kerberos_mech = { .gm_ops = &gss_kerberos_ops, .gm_pf_num = ARRAY_SIZE(gss_kerberos_pfs), .gm_pfs = gss_kerberos_pfs, - .gm_upcall_enctypes = "18,17,16,23,3,1,2", + .gm_upcall_enctypes = KRB5_SUPPORTED_ENCTYPES, }; static int __init init_kerberos_module(void) diff --git a/security/device_cgroup.c b/security/device_cgroup.c index cd1f779fa51d..1be68269e1c2 100644 --- a/security/device_cgroup.c +++ b/security/device_cgroup.c @@ -474,17 +474,11 @@ struct cgroup_subsys devices_subsys = { .subsys_id = devices_subsys_id, }; -int devcgroup_inode_permission(struct inode *inode, int mask) +int __devcgroup_inode_permission(struct inode *inode, int mask) { struct dev_cgroup *dev_cgroup; struct dev_whitelist_item *wh; - dev_t device = inode->i_rdev; - if (!device) - return 0; - if (!S_ISBLK(inode->i_mode) && !S_ISCHR(inode->i_mode)) - return 0; - rcu_read_lock(); dev_cgroup = task_devcgroup(current); diff --git a/tools/perf/Makefile b/tools/perf/Makefile index 032ba6398a5c..940257b5774e 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -633,7 +633,7 @@ prefix_SQ = $(subst ','\'',$(prefix)) SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH)) -LIBS = -Wl,--whole-archive $(PERFLIBS) -Wl,--no-whole-archive $(EXTLIBS) +LIBS = -Wl,--whole-archive $(PERFLIBS) -Wl,--no-whole-archive -Wl,--start-group $(EXTLIBS) -Wl,--end-group ALL_CFLAGS += $(BASIC_CFLAGS) ALL_CFLAGS += $(ARCH_CFLAGS) diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index 1e88485c16a0..0a7ed5b5e281 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -2187,6 +2187,7 @@ static const struct flag flags[] = { { "TASKLET_SOFTIRQ", 6 }, { "SCHED_SOFTIRQ", 7 }, { "HRTIMER_SOFTIRQ", 8 }, + { "RCU_SOFTIRQ", 9 }, { "HRTIMER_NORESTART", 0 }, { "HRTIMER_RESTART", 1 }, |