diff options
67 files changed, 493 insertions, 199 deletions
diff --git a/arch/um/os-Linux/util.c b/arch/um/os-Linux/util.c index 6ea77979531..42827cafa6a 100644 --- a/arch/um/os-Linux/util.c +++ b/arch/um/os-Linux/util.c @@ -5,6 +5,7 @@ #include <stdio.h> #include <stdlib.h> +#include <unistd.h> #include <errno.h> #include <signal.h> #include <string.h> @@ -75,6 +76,26 @@ void setup_hostinfo(char *buf, int len) host.release, host.version, host.machine); } +/* + * We cannot use glibc's abort(). It makes use of tgkill() which + * has no effect within UML's kernel threads. + * After that glibc would execute an invalid instruction to kill + * the calling process and UML crashes with SIGSEGV. + */ +static inline void __attribute__ ((noreturn)) uml_abort(void) +{ + sigset_t sig; + + fflush(NULL); + + if (!sigemptyset(&sig) && !sigaddset(&sig, SIGABRT)) + sigprocmask(SIG_UNBLOCK, &sig, 0); + + for (;;) + if (kill(getpid(), SIGABRT) < 0) + exit(127); +} + void os_dump_core(void) { int pid; @@ -116,5 +137,5 @@ void os_dump_core(void) while ((pid = waitpid(-1, NULL, WNOHANG | __WALL)) > 0) os_kill_ptraced_process(pid, 0); - abort(); + uml_abort(); } diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h index d87988bacf3..34595d5e103 100644 --- a/arch/x86/include/asm/apicdef.h +++ b/arch/x86/include/asm/apicdef.h @@ -78,6 +78,7 @@ #define APIC_DEST_LOGICAL 0x00800 #define APIC_DEST_PHYSICAL 0x00000 #define APIC_DM_FIXED 0x00000 +#define APIC_DM_FIXED_MASK 0x00700 #define APIC_DM_LOWEST 0x00100 #define APIC_DM_SMI 0x00200 #define APIC_DM_REMRD 0x00300 diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h index 3e094af443c..130f1eeee5f 100644 --- a/arch/x86/include/asm/uv/uv_bau.h +++ b/arch/x86/include/asm/uv/uv_bau.h @@ -94,6 +94,8 @@ /* after this # consecutive successes, bump up the throttle if it was lowered */ #define COMPLETE_THRESHOLD 5 +#define UV_LB_SUBNODEID 0x10 + /* * number of entries in the destination side payload queue */ @@ -124,7 +126,7 @@ * The distribution specification (32 bytes) is interpreted as a 256-bit * distribution vector. Adjacent bits correspond to consecutive even numbered * nodeIDs. The result of adding the index of a given bit to the 15-bit - * 'base_dest_nodeid' field of the header corresponds to the + * 'base_dest_nasid' field of the header corresponds to the * destination nodeID associated with that specified bit. */ struct bau_target_uvhubmask { @@ -176,7 +178,7 @@ struct bau_msg_payload { struct bau_msg_header { unsigned int dest_subnodeid:6; /* must be 0x10, for the LB */ /* bits 5:0 */ - unsigned int base_dest_nodeid:15; /* nasid of the */ + unsigned int base_dest_nasid:15; /* nasid of the */ /* bits 20:6 */ /* first bit in uvhub map */ unsigned int command:8; /* message type */ /* bits 28:21 */ @@ -378,6 +380,10 @@ struct ptc_stats { unsigned long d_rcanceled; /* number of messages canceled by resets */ }; +struct hub_and_pnode { + short uvhub; + short pnode; +}; /* * one per-cpu; to locate the software tables */ @@ -399,10 +405,12 @@ struct bau_control { int baudisabled; int set_bau_off; short cpu; + short osnode; short uvhub_cpu; short uvhub; short cpus_in_socket; short cpus_in_uvhub; + short partition_base_pnode; unsigned short message_number; unsigned short uvhub_quiesce; short socket_acknowledge_count[DEST_Q_SIZE]; @@ -422,15 +430,16 @@ struct bau_control { int congested_period; cycles_t period_time; long period_requests; + struct hub_and_pnode *target_hub_and_pnode; }; static inline int bau_uvhub_isset(int uvhub, struct bau_target_uvhubmask *dstp) { return constant_test_bit(uvhub, &dstp->bits[0]); } -static inline void bau_uvhub_set(int uvhub, struct bau_target_uvhubmask *dstp) +static inline void bau_uvhub_set(int pnode, struct bau_target_uvhubmask *dstp) { - __set_bit(uvhub, &dstp->bits[0]); + __set_bit(pnode, &dstp->bits[0]); } static inline void bau_uvhubs_clear(struct bau_target_uvhubmask *dstp, int nbits) diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h index a501741c233..4298002d0c8 100644 --- a/arch/x86/include/asm/uv/uv_hub.h +++ b/arch/x86/include/asm/uv/uv_hub.h @@ -398,6 +398,8 @@ struct uv_blade_info { unsigned short nr_online_cpus; unsigned short pnode; short memory_nid; + spinlock_t nmi_lock; + unsigned long nmi_count; }; extern struct uv_blade_info *uv_blade_info; extern short *uv_node_to_blade; diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h index 20cafeac745..f5bb64a823d 100644 --- a/arch/x86/include/asm/uv/uv_mmrs.h +++ b/arch/x86/include/asm/uv/uv_mmrs.h @@ -5,7 +5,7 @@ * * SGI UV MMR definitions * - * Copyright (C) 2007-2010 Silicon Graphics, Inc. All rights reserved. + * Copyright (C) 2007-2011 Silicon Graphics, Inc. All rights reserved. */ #ifndef _ASM_X86_UV_UV_MMRS_H @@ -1099,5 +1099,19 @@ union uvh_rtc1_int_config_u { } s; }; +/* ========================================================================= */ +/* UVH_SCRATCH5 */ +/* ========================================================================= */ +#define UVH_SCRATCH5 0x2d0200UL +#define UVH_SCRATCH5_32 0x00778 + +#define UVH_SCRATCH5_SCRATCH5_SHFT 0 +#define UVH_SCRATCH5_SCRATCH5_MASK 0xffffffffffffffffUL +union uvh_scratch5_u { + unsigned long v; + struct uvh_scratch5_s { + unsigned long scratch5 : 64; /* RW, W1CS */ + } s; +}; #endif /* __ASM_UV_MMRS_X86_H__ */ diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 33b10a0fc09..7acd2d2ac96 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -37,6 +37,13 @@ #include <asm/smp.h> #include <asm/x86_init.h> #include <asm/emergency-restart.h> +#include <asm/nmi.h> + +/* BMC sets a bit this MMR non-zero before sending an NMI */ +#define UVH_NMI_MMR UVH_SCRATCH5 +#define UVH_NMI_MMR_CLEAR (UVH_NMI_MMR + 8) +#define UV_NMI_PENDING_MASK (1UL << 63) +DEFINE_PER_CPU(unsigned long, cpu_last_nmi_count); DEFINE_PER_CPU(int, x2apic_extra_bits); @@ -642,18 +649,46 @@ void __cpuinit uv_cpu_init(void) */ int uv_handle_nmi(struct notifier_block *self, unsigned long reason, void *data) { + unsigned long real_uv_nmi; + int bid; + if (reason != DIE_NMIUNKNOWN) return NOTIFY_OK; if (in_crash_kexec) /* do nothing if entering the crash kernel */ return NOTIFY_OK; + /* - * Use a lock so only one cpu prints at a time - * to prevent intermixed output. + * Each blade has an MMR that indicates when an NMI has been sent + * to cpus on the blade. If an NMI is detected, atomically + * clear the MMR and update a per-blade NMI count used to + * cause each cpu on the blade to notice a new NMI. + */ + bid = uv_numa_blade_id(); + real_uv_nmi = (uv_read_local_mmr(UVH_NMI_MMR) & UV_NMI_PENDING_MASK); + + if (unlikely(real_uv_nmi)) { + spin_lock(&uv_blade_info[bid].nmi_lock); + real_uv_nmi = (uv_read_local_mmr(UVH_NMI_MMR) & UV_NMI_PENDING_MASK); + if (real_uv_nmi) { + uv_blade_info[bid].nmi_count++; + uv_write_local_mmr(UVH_NMI_MMR_CLEAR, UV_NMI_PENDING_MASK); + } + spin_unlock(&uv_blade_info[bid].nmi_lock); + } + + if (likely(__get_cpu_var(cpu_last_nmi_count) == uv_blade_info[bid].nmi_count)) + return NOTIFY_DONE; + + __get_cpu_var(cpu_last_nmi_count) = uv_blade_info[bid].nmi_count; + + /* + * Use a lock so only one cpu prints at a time. + * This prevents intermixed output. */ spin_lock(&uv_nmi_lock); - pr_info("NMI stack dump cpu %u:\n", smp_processor_id()); + pr_info("UV NMI stack dump cpu %u:\n", smp_processor_id()); dump_stack(); spin_unlock(&uv_nmi_lock); @@ -661,7 +696,8 @@ int uv_handle_nmi(struct notifier_block *self, unsigned long reason, void *data) } static struct notifier_block uv_dump_stack_nmi_nb = { - .notifier_call = uv_handle_nmi + .notifier_call = uv_handle_nmi, + .priority = NMI_LOCAL_LOW_PRIOR - 1, }; void uv_register_nmi_notifier(void) @@ -720,8 +756,9 @@ void __init uv_system_init(void) printk(KERN_DEBUG "UV: Found %d blades\n", uv_num_possible_blades()); bytes = sizeof(struct uv_blade_info) * uv_num_possible_blades(); - uv_blade_info = kmalloc(bytes, GFP_KERNEL); + uv_blade_info = kzalloc(bytes, GFP_KERNEL); BUG_ON(!uv_blade_info); + for (blade = 0; blade < uv_num_possible_blades(); blade++) uv_blade_info[blade].memory_nid = -1; @@ -747,6 +784,7 @@ void __init uv_system_init(void) uv_blade_info[blade].pnode = pnode; uv_blade_info[blade].nr_possible_cpus = 0; uv_blade_info[blade].nr_online_cpus = 0; + spin_lock_init(&uv_blade_info[blade].nmi_lock); max_pnode = max(pnode, max_pnode); blade++; } diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index bb9eb29a52d..6f9d1f6063e 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -613,7 +613,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) #endif /* As a rule processors have APIC timer running in deep C states */ - if (c->x86 >= 0xf && !cpu_has_amd_erratum(amd_erratum_400)) + if (c->x86 > 0xf && !cpu_has_amd_erratum(amd_erratum_400)) set_cpu_cap(c, X86_FEATURE_ARAT); /* @@ -698,7 +698,7 @@ cpu_dev_register(amd_cpu_dev); */ const int amd_erratum_400[] = - AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0x0f, 0x4, 0x2, 0xff, 0xf), + AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0xf, 0x41, 0x2, 0xff, 0xf), AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0xff, 0xf)); EXPORT_SYMBOL_GPL(amd_erratum_400); diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 167f97b5596..bb0adad3514 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -509,6 +509,7 @@ recurse: out_free: if (b) { kobject_put(&b->kobj); + list_del(&b->miscj); kfree(b); } return err; diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 6f8c5e9da97..0f034460260 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -446,18 +446,20 @@ void intel_init_thermal(struct cpuinfo_x86 *c) */ rdmsr(MSR_IA32_MISC_ENABLE, l, h); + h = lvtthmr_init; /* * The initial value of thermal LVT entries on all APs always reads * 0x10000 because APs are woken up by BSP issuing INIT-SIPI-SIPI * sequence to them and LVT registers are reset to 0s except for * the mask bits which are set to 1s when APs receive INIT IPI. - * Always restore the value that BIOS has programmed on AP based on - * BSP's info we saved since BIOS is always setting the same value - * for all threads/cores + * If BIOS takes over the thermal interrupt and sets its interrupt + * delivery mode to SMI (not fixed), it restores the value that the + * BIOS has programmed on AP based on BSP's info we saved since BIOS + * is always setting the same value for all threads/cores. */ - apic_write(APIC_LVTTHMR, lvtthmr_init); + if ((h & APIC_DM_FIXED_MASK) != APIC_DM_FIXED) + apic_write(APIC_LVTTHMR, lvtthmr_init); - h = lvtthmr_init; if ((l & MSR_IA32_MISC_ENABLE_TM1) && (h & APIC_DM_SMI)) { printk(KERN_DEBUG diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index c969fd9d156..f1a6244d7d9 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -1183,12 +1183,13 @@ static void __kprobes optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs) { struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + unsigned long flags; /* This is possible if op is under delayed unoptimizing */ if (kprobe_disabled(&op->kp)) return; - preempt_disable(); + local_irq_save(flags); if (kprobe_running()) { kprobes_inc_nmissed_count(&op->kp); } else { @@ -1207,7 +1208,7 @@ static void __kprobes optimized_callback(struct optimized_kprobe *op, opt_pre_handler(&op->kp, regs); __this_cpu_write(current_kprobe, NULL); } - preempt_enable_no_resched(); + local_irq_restore(flags); } static int __kprobes copy_optimized_instructions(u8 *dest, u8 *src) diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index 7cb6424317f..c58e0ea39ef 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -699,16 +699,17 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, struct mm_struct *mm, unsigned long va, unsigned int cpu) { - int tcpu; - int uvhub; int locals = 0; int remotes = 0; int hubs = 0; + int tcpu; + int tpnode; struct bau_desc *bau_desc; struct cpumask *flush_mask; struct ptc_stats *stat; struct bau_control *bcp; struct bau_control *tbcp; + struct hub_and_pnode *hpp; /* kernel was booted 'nobau' */ if (nobau) @@ -750,11 +751,18 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, bau_desc += UV_ITEMS_PER_DESCRIPTOR * bcp->uvhub_cpu; bau_uvhubs_clear(&bau_desc->distribution, UV_DISTRIBUTION_SIZE); - /* cpu statistics */ for_each_cpu(tcpu, flush_mask) { - uvhub = uv_cpu_to_blade_id(tcpu); - bau_uvhub_set(uvhub, &bau_desc->distribution); - if (uvhub == bcp->uvhub) + /* + * The distribution vector is a bit map of pnodes, relative + * to the partition base pnode (and the partition base nasid + * in the header). + * Translate cpu to pnode and hub using an array stored + * in local memory. + */ + hpp = &bcp->socket_master->target_hub_and_pnode[tcpu]; + tpnode = hpp->pnode - bcp->partition_base_pnode; + bau_uvhub_set(tpnode, &bau_desc->distribution); + if (hpp->uvhub == bcp->uvhub) locals++; else remotes++; @@ -855,7 +863,7 @@ void uv_bau_message_interrupt(struct pt_regs *regs) * an interrupt, but causes an error message to be returned to * the sender. */ -static void uv_enable_timeouts(void) +static void __init uv_enable_timeouts(void) { int uvhub; int nuvhubs; @@ -1326,10 +1334,10 @@ static int __init uv_ptc_init(void) } /* - * initialize the sending side's sending buffers + * Initialize the sending side's sending buffers. */ static void -uv_activation_descriptor_init(int node, int pnode) +uv_activation_descriptor_init(int node, int pnode, int base_pnode) { int i; int cpu; @@ -1352,11 +1360,11 @@ uv_activation_descriptor_init(int node, int pnode) n = pa >> uv_nshift; m = pa & uv_mmask; + /* the 14-bit pnode */ uv_write_global_mmr64(pnode, UVH_LB_BAU_SB_DESCRIPTOR_BASE, (n << UV_DESC_BASE_PNODE_SHIFT | m)); - /* - * initializing all 8 (UV_ITEMS_PER_DESCRIPTOR) descriptors for each + * Initializing all 8 (UV_ITEMS_PER_DESCRIPTOR) descriptors for each * cpu even though we only use the first one; one descriptor can * describe a broadcast to 256 uv hubs. */ @@ -1365,12 +1373,13 @@ uv_activation_descriptor_init(int node, int pnode) memset(bd2, 0, sizeof(struct bau_desc)); bd2->header.sw_ack_flag = 1; /* - * base_dest_nodeid is the nasid of the first uvhub - * in the partition. The bit map will indicate uvhub numbers, - * which are 0-N in a partition. Pnodes are unique system-wide. + * The base_dest_nasid set in the message header is the nasid + * of the first uvhub in the partition. The bit map will + * indicate destination pnode numbers relative to that base. + * They may not be consecutive if nasid striding is being used. */ - bd2->header.base_dest_nodeid = UV_PNODE_TO_NASID(uv_partition_base_pnode); - bd2->header.dest_subnodeid = 0x10; /* the LB */ + bd2->header.base_dest_nasid = UV_PNODE_TO_NASID(base_pnode); + bd2->header.dest_subnodeid = UV_LB_SUBNODEID; bd2->header.command = UV_NET_ENDPOINT_INTD; bd2->header.int_both = 1; /* @@ -1442,7 +1451,7 @@ uv_payload_queue_init(int node, int pnode) /* * Initialization of each UV hub's structures */ -static void __init uv_init_uvhub(int uvhub, int vector) +static void __init uv_init_uvhub(int uvhub, int vector, int base_pnode) { int node; int pnode; @@ -1450,11 +1459,11 @@ static void __init uv_init_uvhub(int uvhub, int vector) node = uvhub_to_first_node(uvhub); pnode = uv_blade_to_pnode(uvhub); - uv_activation_descriptor_init(node, pnode); + uv_activation_descriptor_init(node, pnode, base_pnode); uv_payload_queue_init(node, pnode); /* - * the below initialization can't be in firmware because the - * messaging IRQ will be determined by the OS + * The below initialization can't be in firmware because the + * messaging IRQ will be determined by the OS. */ apicid = uvhub_to_first_apicid(uvhub) | uv_apicid_hibits; uv_write_global_mmr64(pnode, UVH_BAU_DATA_CONFIG, @@ -1491,10 +1500,11 @@ calculate_destination_timeout(void) /* * initialize the bau_control structure for each cpu */ -static int __init uv_init_per_cpu(int nuvhubs) +static int __init uv_init_per_cpu(int nuvhubs, int base_part_pnode) { int i; int cpu; + int tcpu; int pnode; int uvhub; int have_hmaster; @@ -1528,6 +1538,15 @@ static int __init uv_init_per_cpu(int nuvhubs) bcp = &per_cpu(bau_control, cpu); memset(bcp, 0, sizeof(struct bau_control)); pnode = uv_cpu_hub_info(cpu)->pnode; + if ((pnode - base_part_pnode) >= UV_DISTRIBUTION_SIZE) { + printk(KERN_EMERG + "cpu %d pnode %d-%d beyond %d; BAU disabled\n", + cpu, pnode, base_part_pnode, + UV_DISTRIBUTION_SIZE); + return 1; + } + bcp->osnode = cpu_to_node(cpu); + bcp->partition_base_pnode = uv_partition_base_pnode; uvhub = uv_cpu_hub_info(cpu)->numa_blade_id; *(uvhub_mask + (uvhub/8)) |= (1 << (uvhub%8)); bdp = &uvhub_descs[uvhub]; @@ -1536,7 +1555,7 @@ static int __init uv_init_per_cpu(int nuvhubs) bdp->pnode = pnode; /* kludge: 'assuming' one node per socket, and assuming that disabling a socket just leaves a gap in node numbers */ - socket = (cpu_to_node(cpu) & 1); + socket = bcp->osnode & 1; bdp->socket_mask |= (1 << socket); sdp = &bdp->socket[socket]; sdp->cpu_number[sdp->num_cpus] = cpu; @@ -1585,6 +1604,20 @@ static int __init uv_init_per_cpu(int nuvhubs) nextsocket: socket++; socket_mask = (socket_mask >> 1); + /* each socket gets a local array of pnodes/hubs */ + bcp = smaster; + bcp->target_hub_and_pnode = kmalloc_node( + sizeof(struct hub_and_pnode) * + num_possible_cpus(), GFP_KERNEL, bcp->osnode); + memset(bcp->target_hub_and_pnode, 0, + sizeof(struct hub_and_pnode) * + num_possible_cpus()); + for_each_present_cpu(tcpu) { + bcp->target_hub_and_pnode[tcpu].pnode = + uv_cpu_hub_info(tcpu)->pnode; + bcp->target_hub_and_pnode[tcpu].uvhub = + uv_cpu_hub_info(tcpu)->numa_blade_id; + } } } kfree(uvhub_descs); @@ -1637,21 +1670,22 @@ static int __init uv_bau_init(void) spin_lock_init(&disable_lock); congested_cycles = microsec_2_cycles(congested_response_us); - if (uv_init_per_cpu(nuvhubs)) { - nobau = 1; - return 0; - } - uv_partition_base_pnode = 0x7fffffff; - for (uvhub = 0; uvhub < nuvhubs; uvhub++) + for (uvhub = 0; uvhub < nuvhubs; uvhub++) { if (uv_blade_nr_possible_cpus(uvhub) && (uv_blade_to_pnode(uvhub) < uv_partition_base_pnode)) uv_partition_base_pnode = uv_blade_to_pnode(uvhub); + } + + if (uv_init_per_cpu(nuvhubs, uv_partition_base_pnode)) { + nobau = 1; + return 0; + } vector = UV_BAU_MESSAGE; for_each_possible_blade(uvhub) if (uv_blade_nr_possible_cpus(uvhub)) - uv_init_uvhub(uvhub, vector); + uv_init_uvhub(uvhub, vector, uv_partition_base_pnode); uv_enable_timeouts(); alloc_intr_gate(vector, uv_bau_message_intr1); diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index f0605ab2a76..471fdcc5df8 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -114,6 +114,13 @@ struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup) } EXPORT_SYMBOL_GPL(cgroup_to_blkio_cgroup); +struct blkio_cgroup *task_blkio_cgroup(struct task_struct *tsk) +{ + return container_of(task_subsys_state(tsk, blkio_subsys_id), + struct blkio_cgroup, css); +} +EXPORT_SYMBOL_GPL(task_blkio_cgroup); + static inline void blkio_update_group_weight(struct blkio_group *blkg, unsigned int weight) { diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h index 10919fae2d3..c774930cc20 100644 --- a/block/blk-cgroup.h +++ b/block/blk-cgroup.h @@ -291,6 +291,7 @@ static inline void blkiocg_set_start_empty_time(struct blkio_group *blkg) {} #if defined(CONFIG_BLK_CGROUP) || defined(CONFIG_BLK_CGROUP_MODULE) extern struct blkio_cgroup blkio_root_cgroup; extern struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup); +extern struct blkio_cgroup *task_blkio_cgroup(struct task_struct *tsk); extern void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg, struct blkio_group *blkg, void *key, dev_t dev, enum blkio_policy_id plid); @@ -314,6 +315,8 @@ void blkiocg_update_io_remove_stats(struct blkio_group *blkg, struct cgroup; static inline struct blkio_cgroup * cgroup_to_blkio_cgroup(struct cgroup *cgroup) { return NULL; } +static inline struct blkio_cgroup * +task_blkio_cgroup(struct task_struct *tsk) { return NULL; } static inline void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg, struct blkio_group *blkg, void *key, dev_t dev, diff --git a/block/blk-core.c b/block/blk-core.c index a2e58eeb354..3fe00a14822 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -316,8 +316,10 @@ EXPORT_SYMBOL(__blk_run_queue); */ void blk_run_queue_async(struct request_queue *q) { - if (likely(!blk_queue_stopped(q))) + if (likely(!blk_queue_stopped(q))) { + __cancel_delayed_work(&q->delay_work); queue_delayed_work(kblockd_workqueue, &q->delay_work, 0); + } } EXPORT_SYMBOL(blk_run_queue_async); diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 0475a22a420..252a81a306f 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -160,9 +160,8 @@ static void throtl_put_tg(struct throtl_grp *tg) } static struct throtl_grp * throtl_find_alloc_tg(struct throtl_data *td, - struct cgroup *cgroup) + struct blkio_cgroup *blkcg) { - struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup); struct throtl_grp *tg = NULL; void *key = td; struct backing_dev_info *bdi = &td->queue->backing_dev_info; @@ -229,12 +228,12 @@ done: static struct throtl_grp * throtl_get_tg(struct throtl_data *td) { - struct cgroup *cgroup; struct throtl_grp *tg = NULL; + struct blkio_cgroup *blkcg; rcu_read_lock(); - cgroup = task_cgroup(current, blkio_subsys_id); - tg = throtl_find_alloc_tg(td, cgroup); + blkcg = task_blkio_cgroup(current); + tg = throtl_find_alloc_tg(td, blkcg); if (!tg) tg = &td->root_tg; rcu_read_unlock(); diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 5b52011e3a4..ab7a9e6a9b1 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -1014,10 +1014,9 @@ void cfq_update_blkio_group_weight(void *key, struct blkio_group *blkg, cfqg->needs_update = true; } -static struct cfq_group * -cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create) +static struct cfq_group * cfq_find_alloc_cfqg(struct cfq_data *cfqd, + struct blkio_cgroup *blkcg, int create) { - struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup); struct cfq_group *cfqg = NULL; void *key = cfqd; int i, j; @@ -1079,12 +1078,12 @@ done: */ static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd, int create) { - struct cgroup *cgroup; + struct blkio_cgroup *blkcg; struct cfq_group *cfqg = NULL; rcu_read_lock(); - cgroup = task_cgroup(current, blkio_subsys_id); - cfqg = cfq_find_alloc_cfqg(cfqd, cgroup, create); + blkcg = task_blkio_cgroup(current); + cfqg = cfq_find_alloc_cfqg(cfqd, blkcg, create); if (!cfqg && create) cfqg = &cfqd->root_group; rcu_read_unlock(); diff --git a/drivers/block/DAC960.c b/drivers/block/DAC960.c index 8066d086578..e086fbbbe85 100644 --- a/drivers/block/DAC960.c +++ b/drivers/block/DAC960.c @@ -2547,7 +2547,6 @@ static bool DAC960_RegisterBlockDevice(DAC960_Controller_T *Controller) disk->major = MajorNumber; disk->first_minor = n << DAC960_MaxPartitionsBits; disk->fops = &DAC960_BlockDeviceOperations; - disk->events = DISK_EVENT_MEDIA_CHANGE; } /* Indicate the Block Device Registration completed successfully, diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c index 456c0cc90dc..8eba86bba59 100644 --- a/drivers/block/amiflop.c +++ b/drivers/block/amiflop.c @@ -1736,7 +1736,6 @@ static int __init fd_probe_drives(void) disk->major = FLOPPY_MAJOR; disk->first_minor = drive; disk->fops = &floppy_fops; - disk->events = DISK_EVENT_MEDIA_CHANGE; sprintf(disk->disk_name, "fd%d", drive); disk->private_data = &unit[drive]; set_capacity(disk, 880*2); diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c index c871eae1412..ede16c64ff0 100644 --- a/drivers/block/ataflop.c +++ b/drivers/block/ataflop.c @@ -1964,7 +1964,6 @@ static int __init atari_floppy_init (void) unit[i].disk->first_minor = i; sprintf(unit[i].disk->disk_name, "fd%d", i); unit[i].disk->fops = &floppy_fops; - unit[i].disk->events = DISK_EVENT_MEDIA_CHANGE; unit[i].disk->private_data = &unit[i]; unit[i].disk->queue = blk_init_queue(do_fd_request, &ataflop_lock); diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 301d7a9a41a..db8f88586c8 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -4205,7 +4205,6 @@ static int __init floppy_init(void) disks[dr]->major = FLOPPY_MAJOR; disks[dr]->first_minor = TOMINOR(dr); disks[dr]->fops = &floppy_fops; - disks[dr]->events = DISK_EVENT_MEDIA_CHANGE; sprintf(disks[dr]->disk_name, "fd%d", dr); init_timer(&motor_off_timer[dr]); diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c index 2f2ccf68625..8690e31d993 100644 --- a/drivers/block/paride/pcd.c +++ b/drivers/block/paride/pcd.c @@ -320,7 +320,6 @@ static void pcd_init_units(void) disk->first_minor = unit; strcpy(disk->disk_name, cd->name); /* umm... */ disk->fops = &pcd_bdops; - disk->events = DISK_EVENT_MEDIA_CHANGE; } } diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c index 21dfdb77686..869e7676d46 100644 --- a/drivers/block/paride/pd.c +++ b/drivers/block/paride/pd.c @@ -837,7 +837,6 @@ static void pd_probe_drive(struct pd_unit *disk) p->fops = &pd_fops; p->major = major; p->first_minor = (disk - pd) << PD_BITS; - p->events = DISK_EVENT_MEDIA_CHANGE; disk->gd = p; p->private_data = disk; p->queue = pd_queue; diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c index 7adeb1edbf4..f21b520ef41 100644 --- a/drivers/block/paride/pf.c +++ b/drivers/block/paride/pf.c @@ -294,7 +294,6 @@ static void __init pf_init_units(void) disk->first_minor = unit; strcpy(disk->disk_name, pf->name); disk->fops = &pf_fops; - disk->events = DISK_EVENT_MEDIA_CHANGE; if (!(*drives[unit])[D_PRT]) pf_drive_count++; } diff --git a/drivers/block/swim.c b/drivers/block/swim.c index 24a482f2fbd..fd5adcd5594 100644 --- a/drivers/block/swim.c +++ b/drivers/block/swim.c @@ -858,7 +858,6 @@ static int __devinit swim_floppy_init(struct swim_priv *swd) swd->unit[drive].disk->first_minor = drive; sprintf(swd->unit[drive].disk->disk_name, "fd%d", drive); swd->unit[drive].disk->fops = &floppy_fops; - swd->unit[drive].disk->events = DISK_EVENT_MEDIA_CHANGE; swd->unit[drive].disk->private_data = &swd->unit[drive]; swd->unit[drive].disk->queue = swd->queue; set_capacity(swd->unit[drive].disk, 2880); diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c index 4c10f56facb..773bfa79277 100644 --- a/drivers/block/swim3.c +++ b/drivers/block/swim3.c @@ -1163,7 +1163,6 @@ static int __devinit swim3_attach(struct macio_dev *mdev, const struct of_device disk->major = FLOPPY_MAJOR; disk->first_minor = i; disk->fops = &floppy_fops; - disk->events = DISK_EVENT_MEDIA_CHANGE; disk->private_data = &floppy_states[i]; disk->queue = swim3_queue; disk->flags |= GENHD_FL_REMOVABLE; diff --git a/drivers/block/ub.c b/drivers/block/ub.c index 68b9430c7cf..0e376d46bdd 100644 --- a/drivers/block/ub.c +++ b/drivers/block/ub.c @@ -2334,7 +2334,6 @@ static int ub_probe_lun(struct ub_dev *sc, int lnum) disk->major = UB_MAJOR; disk->first_minor = lun->id * UB_PARTS_PER_LUN; disk->fops = &ub_bd_fops; - disk->events = DISK_EVENT_MEDIA_CHANGE; disk->private_data = lun; disk->driverfs_dev = &sc->intf->dev; diff --git a/drivers/block/xsysace.c b/drivers/block/xsysace.c index 645ff765cd1..6c7fd7db6df 100644 --- a/drivers/block/xsysace.c +++ b/drivers/block/xsysace.c @@ -1005,7 +1005,6 @@ static int __devinit ace_setup(struct ace_device *ace) ace->gd->major = ace_major; ace->gd->first_minor = ace->id * ACE_NUM_MINORS; ace->gd->fops = &ace_fops; - ace->gd->events = DISK_EVENT_MEDIA_CHANGE; ace->gd->queue = ace->queue; ace->gd->private_data = ace; snprintf(ace->gd->disk_name, 32, "xs%c", ace->id + 'a'); diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index 514dd8efaf7..75fb965b8f7 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -986,6 +986,9 @@ int cdrom_open(struct cdrom_device_info *cdi, struct block_device *bdev, fmode_t cdinfo(CD_OPEN, "entering cdrom_open\n"); + /* open is event synchronization point, check events first */ + check_disk_change(bdev); + /* if this was a O_NONBLOCK open and we should honor the flags, * do a quick open without drive/disc integrity checks. */ cdi->use_count++; @@ -1012,9 +1015,6 @@ int cdrom_open(struct cdrom_device_info *cdi, struct block_device *bdev, fmode_t cdinfo(CD_OPEN, "Use count for \"/dev/%s\" now %d\n", cdi->name, cdi->use_count); - /* Do this on open. Don't wait for mount, because they might - not be mounting, but opening with O_NONBLOCK */ - check_disk_change(bdev); return 0; err_release: if (CDROM_CAN(CDC_LOCK) && cdi->options & CDO_LOCK) { diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c index b2b034fea34..3ceaf006e7f 100644 --- a/drivers/cdrom/gdrom.c +++ b/drivers/cdrom/gdrom.c @@ -803,7 +803,6 @@ static int __devinit probe_gdrom(struct platform_device *devptr) goto probe_fail_cdrom_register; } gd.disk->fops = &gdrom_bdops; - gd.disk->events = DISK_EVENT_MEDIA_CHANGE; /* latch on to the interrupt */ err = gdrom_set_interrupt_handlers(); if (err) diff --git a/drivers/cdrom/viocd.c b/drivers/cdrom/viocd.c index 4e874c5fa60..e427fbe4599 100644 --- a/drivers/cdrom/viocd.c +++ b/drivers/cdrom/viocd.c @@ -626,7 +626,6 @@ static int viocd_probe(struct vio_dev *vdev, const struct vio_device_id *id) gendisk->queue = q; gendisk->fops = &viocd_fops; gendisk->flags = GENHD_FL_CD|GENHD_FL_REMOVABLE; - gendisk->events = DISK_EVENT_MEDIA_CHANGE; set_capacity(gendisk, 0); gendisk->private_data = d; d->viocd_disk = gendisk; diff --git a/drivers/leds/leds-lm3530.c b/drivers/leds/leds-lm3530.c index e7089a1f6cb..b37e6186d0f 100644 --- a/drivers/leds/leds-lm3530.c +++ b/drivers/leds/leds-lm3530.c @@ -349,6 +349,7 @@ static const struct i2c_device_id lm3530_id[] = { {LM3530_NAME, 0}, {} }; +MODULE_DEVICE_TABLE(i2c, lm3530_id); static struct i2c_driver lm3530_i2c_driver = { .probe = lm3530_probe, diff --git a/drivers/media/video/cx88/cx88-input.c b/drivers/media/video/cx88/cx88-input.c index c820e2f5352..3f442003623 100644 --- a/drivers/media/video/cx88/cx88-input.c +++ b/drivers/media/video/cx88/cx88-input.c @@ -524,7 +524,7 @@ void cx88_ir_irq(struct cx88_core *core) for (todo = 32; todo > 0; todo -= bits) { ev.pulse = samples & 0x80000000 ? false : true; bits = min(todo, 32U - fls(ev.pulse ? samples : ~samples)); - ev.duration = (bits * NSEC_PER_SEC) / (1000 * ir_samplerate); + ev.duration = (bits * (NSEC_PER_SEC / 1000)) / ir_samplerate; ir_raw_event_store_with_filter(ir->dev, &ev); samples <<= bits; } diff --git a/drivers/media/video/soc_camera.c b/drivers/media/video/soc_camera.c index 3973f9a9475..ddb4c091ded 100644 --- a/drivers/media/video/soc_camera.c +++ b/drivers/media/video/soc_camera.c @@ -136,11 +136,50 @@ unsigned long soc_camera_apply_sensor_flags(struct soc_camera_link *icl, } EXPORT_SYMBOL(soc_camera_apply_sensor_flags); +#define pixfmtstr(x) (x) & 0xff, ((x) >> 8) & 0xff, ((x) >> 16) & 0xff, \ + ((x) >> 24) & 0xff + +static int soc_camera_try_fmt(struct soc_camera_device *icd, + struct v4l2_format *f) +{ + struct soc_camera_host *ici = to_soc_camera_host(icd->dev.parent); + struct v4l2_pix_format *pix = &f->fmt.pix; + int ret; + + dev_dbg(&icd->dev, "TRY_FMT(%c%c%c%c, %ux%u)\n", + pixfmtstr(pix->pixelformat), pix->width, pix->height); + + pix->bytesperline = 0; + pix->sizeimage = 0; + + ret = ici->ops->try_fmt(icd, f); + if (ret < 0) + return ret; + + if (!pix->sizeimage) { + if (!pix->bytesperline) { + const struct soc_camera_format_xlate *xlate; + + xlate = soc_camera_xlate_by_fourcc(icd, pix->pixelformat); + if (!xlate) + return -EINVAL; + + ret = soc_mbus_bytes_per_line(pix->width, + xlate->host_fmt); + if (ret > 0) + pix->bytesperline = ret; + } + if (pix->bytesperline) + pix->sizeimage = pix->bytesperline * pix->height; + } + + return 0; +} + static int soc_camera_try_fmt_vid_cap(struct file *file, void *priv, struct v4l2_format *f) { struct soc_camera_device *icd = file->private_data; - struct soc_camera_host *ici = to_soc_camera_host(icd->dev.parent); WARN_ON(priv != file->private_data); @@ -149,7 +188,7 @@ static int soc_camera_try_fmt_vid_cap(struct file *file, void *priv, return -EINVAL; /* limit format to hardware capabilities */ - return ici->ops->try_fmt(icd, f); + return soc_camera_try_fmt(icd, f); } static int soc_camera_enum_input(struct file *file, void *priv, @@ -362,9 +401,6 @@ static void soc_camera_free_user_formats(struct soc_camera_device *icd) icd->user_formats = NULL; } -#define pixfmtstr(x) (x) & 0xff, ((x) >> 8) & 0xff, ((x) >> 16) & 0xff, \ - ((x) >> 24) & 0xff - /* Called with .vb_lock held, or from the first open(2), see comment there */ static int soc_camera_set_fmt(struct soc_camera_device *icd, struct v4l2_format *f) @@ -377,7 +413,7 @@ static int soc_camera_set_fmt(struct soc_camera_device *icd, pixfmtstr(pix->pixelformat), pix->width, pix->height); /* We always call try_fmt() before set_fmt() or set_crop() */ - ret = ici->ops->try_fmt(icd, f); + ret = soc_camera_try_fmt(icd, f); if (ret < 0) return ret; diff --git a/drivers/media/video/v4l2-device.c b/drivers/media/video/v4l2-device.c index 5aeaf876ba9..4aae501f02d 100644 --- a/drivers/media/video/v4l2-device.c +++ b/drivers/media/video/v4l2-device.c @@ -155,8 +155,10 @@ int v4l2_device_register_subdev(struct v4l2_device *v4l2_dev, sd->v4l2_dev = v4l2_dev; if (sd->internal_ops && sd->internal_ops->registered) { err = sd->internal_ops->registered(sd); - if (err) + if (err) { + module_put(sd->owner); return err; + } } /* This just returns 0 if either of the two args is NULL */ @@ -164,6 +166,7 @@ int v4l2_device_register_subdev(struct v4l2_device *v4l2_dev, if (err) { if (sd->internal_ops && sd->internal_ops->unregistered) sd->internal_ops->unregistered(sd); + module_put(sd->owner); return err; } diff --git a/drivers/media/video/v4l2-subdev.c b/drivers/media/video/v4l2-subdev.c index 0b806449067..812729ebf09 100644 --- a/drivers/media/video/v4l2-subdev.c +++ b/drivers/media/video/v4l2-subdev.c @@ -155,25 +155,25 @@ static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg) switch (cmd) { case VIDIOC_QUERYCTRL: - return v4l2_subdev_queryctrl(sd, arg); + return v4l2_queryctrl(sd->ctrl_handler, arg); case VIDIOC_QUERYMENU: - return v4l2_subdev_querymenu(sd, arg); + return v4l2_querymenu(sd->ctrl_handler, arg); case VIDIOC_G_CTRL: - return v4l2_subdev_g_ctrl(sd, arg); + return v4l2_g_ctrl(sd->ctrl_handler, arg); case VIDIOC_S_CTRL: - return v4l2_subdev_s_ctrl(sd, arg); + return v4l2_s_ctrl(sd->ctrl_handler, arg); case VIDIOC_G_EXT_CTRLS: - return v4l2_subdev_g_ext_ctrls(sd, arg); + return v4l2_g_ext_ctrls(sd->ctrl_handler, arg); case VIDIOC_S_EXT_CTRLS: - return v4l2_subdev_s_ext_ctrls(sd, arg); + return v4l2_s_ext_ctrls(sd->ctrl_handler, arg); case VIDIOC_TRY_EXT_CTRLS: - return v4l2_subdev_try_ext_ctrls(sd, arg); + return v4l2_try_ext_ctrls(sd->ctrl_handler, arg); case VIDIOC_DQEVENT: if (!(sd->flags & V4L2_SUBDEV_FL_HAS_EVENTS)) diff --git a/drivers/message/i2o/i2o_block.c b/drivers/message/i2o/i2o_block.c index 643ad52e3ca..4796bbf0ae4 100644 --- a/drivers/message/i2o/i2o_block.c +++ b/drivers/message/i2o/i2o_block.c @@ -1000,7 +1000,6 @@ static struct i2o_block_device *i2o_block_device_alloc(void) gd->major = I2O_MAJOR; gd->queue = queue; gd->fops = &i2o_block_fops; - gd->events = DISK_EVENT_MEDIA_CHANGE; gd->private_data = dev; dev->gd = gd; diff --git a/drivers/rapidio/switches/idt_gen2.c b/drivers/rapidio/switches/idt_gen2.c index ac2701b22e7..043ee3136e4 100644 --- a/drivers/rapidio/switches/idt_gen2.c +++ b/drivers/rapidio/switches/idt_gen2.c @@ -95,6 +95,9 @@ idtg2_route_add_entry(struct rio_mport *mport, u16 destid, u8 hopcount, else table++; + if (route_port == RIO_INVALID_ROUTE) + route_port = IDT_DEFAULT_ROUTE; + rio_mport_write_config_32(mport, destid, hopcount, LOCAL_RTE_CONF_DESTID_SEL, table); @@ -411,6 +414,12 @@ static int idtg2_switch_init(struct rio_dev *rdev, int do_enum) rdev->rswitch->em_handle = idtg2_em_handler; rdev->rswitch->sw_sysfs = idtg2_sysfs; + if (do_enum) { + /* Ensure that default routing is disabled on startup */ + rio_write_config_32(rdev, + RIO_STD_RTE_DEFAULT_PORT, IDT_NO_ROUTE); + } + return 0; } diff --git a/drivers/rapidio/switches/idtcps.c b/drivers/rapidio/switches/idtcps.c index 3a971077e7b..d06ee2d44b4 100644 --- a/drivers/rapidio/switches/idtcps.c +++ b/drivers/rapidio/switches/idtcps.c @@ -26,6 +26,9 @@ idtcps_route_add_entry(struct rio_mport *mport, u16 destid, u8 hopcount, { u32 result; + if (route_port == RIO_INVALID_ROUTE) + route_port = CPS_DEFAULT_ROUTE; + if (table == RIO_GLOBAL_TABLE) { rio_mport_write_config_32(mport, destid, hopcount, RIO_STD_RTE_CONF_DESTID_SEL_CSR, route_destid); @@ -130,6 +133,9 @@ static int idtcps_switch_init(struct rio_dev *rdev, int do_enum) /* set TVAL = ~50us */ rio_write_config_32(rdev, rdev->phys_efptr + RIO_PORT_LINKTO_CTL_CSR, 0x8e << 8); + /* Ensure that default routing is disabled on startup */ + rio_write_config_32(rdev, + RIO_STD_RTE_DEFAULT_PORT, CPS_NO_ROUTE); } return 0; diff --git a/drivers/rapidio/switches/tsi57x.c b/drivers/rapidio/switches/tsi57x.c index 1a62934bfeb..db8b8028988 100644 --- a/drivers/rapidio/switches/tsi57x.c +++ b/drivers/rapidio/switches/tsi57x.c @@ -303,6 +303,12 @@ static int tsi57x_switch_init(struct rio_dev *rdev, int do_enum) rdev->rswitch->em_init = tsi57x_em_init; rdev->rswitch->em_handle = tsi57x_em_handler; + if (do_enum) { + /* Ensure that default routing is disabled on startup */ + rio_write_config_32(rdev, RIO_STD_RTE_DEFAULT_PORT, + RIO_INVALID_ROUTE); + } + return 0; } diff --git a/drivers/rtc/rtc-davinci.c b/drivers/rtc/rtc-davinci.c index 8d46838dff8..755e1fe914a 100644 --- a/drivers/rtc/rtc-davinci.c +++ b/drivers/rtc/rtc-davinci.c @@ -524,6 +524,8 @@ static int __init davinci_rtc_probe(struct platform_device *pdev) goto fail2; } + platform_set_drvdata(pdev, davinci_rtc); + davinci_rtc->rtc = rtc_device_register(pdev->name, &pdev->dev, &davinci_rtc_ops, THIS_MODULE); if (IS_ERR(davinci_rtc->rtc)) { @@ -553,8 +555,6 @@ static int __init davinci_rtc_probe(struct platform_device *pdev) rtcss_write(davinci_rtc, PRTCSS_RTC_CCTRL_CAEN, PRTCSS_RTC_CCTRL); - platform_set_drvdata(pdev, davinci_rtc); - device_init_wakeup(&pdev->dev, 0); return 0; @@ -562,6 +562,7 @@ static int __init davinci_rtc_probe(struct platform_device *pdev) fail4: rtc_device_unregister(davinci_rtc->rtc); fail3: + platform_set_drvdata(pdev, NULL); iounmap(davinci_rtc->base); fail2: release_mem_region(davinci_rtc->pbase, davinci_rtc->base_size); diff --git a/drivers/rtc/rtc-ds1286.c b/drivers/rtc/rtc-ds1286.c index 60ce6960082..47e681df31e 100644 --- a/drivers/rtc/rtc-ds1286.c +++ b/drivers/rtc/rtc-ds1286.c @@ -355,6 +355,7 @@ static int __devinit ds1286_probe(struct platform_device *pdev) goto out; } spin_lock_init(&priv->lock); + platform_set_drvdata(pdev, priv); rtc = rtc_device_register("ds1286", &pdev->dev, &ds1286_ops, THIS_MODULE); if (IS_ERR(rtc)) { @@ -362,7 +363,6 @@ static int __devinit ds1286_probe(struct platform_device *pdev) goto out; } priv->rtc = rtc; - platform_set_drvdata(pdev, priv); return 0; out: diff --git a/drivers/rtc/rtc-ep93xx.c b/drivers/rtc/rtc-ep93xx.c index 11ae64dcbf3..335551d333b 100644 --- a/drivers/rtc/rtc-ep93xx.c +++ b/drivers/rtc/rtc-ep93xx.c @@ -151,6 +151,7 @@ static int __init ep93xx_rtc_probe(struct platform_device *pdev) return -ENXIO; pdev->dev.platform_data = ep93xx_rtc; + platform_set_drvdata(pdev, rtc); rtc = rtc_device_register(pdev->name, &pdev->dev, &ep93xx_rtc_ops, THIS_MODULE); @@ -159,8 +160,6 @@ static int __init ep93xx_rtc_probe(struct platform_device *pdev) goto exit; } - platform_set_drvdata(pdev, rtc); - err = sysfs_create_group(&pdev->dev.kobj, &ep93xx_rtc_sysfs_files); if (err) goto fail; @@ -168,9 +167,9 @@ static int __init ep93xx_rtc_probe(struct platform_device *pdev) return 0; fail: - platform_set_drvdata(pdev, NULL); rtc_device_unregister(rtc); exit: + platform_set_drvdata(pdev, NULL); pdev->dev.platform_data = NULL; return err; } diff --git a/drivers/rtc/rtc-m41t80.c b/drivers/rtc/rtc-m41t80.c index 69fe664a222..eda128fc1d3 100644 --- a/drivers/rtc/rtc-m41t80.c +++ b/drivers/rtc/rtc-m41t80.c @@ -783,6 +783,9 @@ static int m41t80_probe(struct i2c_client *client, goto exit; } + clientdata->features = id->driver_data; + i2c_set_clientdata(client, clientdata); + rtc = rtc_device_register(client->name, &client->dev, &m41t80_rtc_ops, THIS_MODULE); if (IS_ERR(rtc)) { @@ -792,8 +795,6 @@ static int m41t80_probe(struct i2c_client *client, } clientdata->rtc = rtc; - clientdata->features = id->driver_data; - i2c_set_clientdata(client, clientdata); /* Make sure HT (Halt Update) bit is cleared */ rc = i2c_smbus_read_byte_data(client, M41T80_REG_ALARM_HOUR); diff --git a/drivers/rtc/rtc-max8925.c b/drivers/rtc/rtc-max8925.c index 20494b5edc3..3bc046f427e 100644 --- a/drivers/rtc/rtc-max8925.c +++ b/drivers/rtc/rtc-max8925.c @@ -258,6 +258,8 @@ static int __devinit max8925_rtc_probe(struct platform_device *pdev) } dev_set_drvdata(&pdev->dev, info); + /* XXX - isn't this redundant? */ + platform_set_drvdata(pdev, info); info->rtc_dev = rtc_device_register("max8925-rtc", &pdev->dev, &max8925_rtc_ops, THIS_MODULE); @@ -267,10 +269,9 @@ static int __devinit max8925_rtc_probe(struct platform_device *pdev) goto out_rtc; } - platform_set_drvdata(pdev, info); - return 0; out_rtc: + platform_set_drvdata(pdev, NULL); free_irq(chip->irq_base + MAX8925_IRQ_RTC_ALARM0, info); out_irq: kfree(info); diff --git a/drivers/rtc/rtc-max8998.c b/drivers/rtc/rtc-max8998.c index 3f7bc6b9fef..2e48aa60427 100644 --- a/drivers/rtc/rtc-max8998.c +++ b/drivers/rtc/rtc-max8998.c @@ -265,6 +265,8 @@ static int __devinit max8998_rtc_probe(struct platform_device *pdev) info->rtc = max8998->rtc; info->irq = max8998->irq_base + MAX8998_IRQ_ALARM0; + platform_set_drvdata(pdev, info); + info->rtc_dev = rtc_device_register("max8998-rtc", &pdev->dev, &max8998_rtc_ops, THIS_MODULE); @@ -274,8 +276,6 @@ static int __devinit max8998_rtc_probe(struct platform_device *pdev) goto out_rtc; } - platform_set_drvdata(pdev, info); - ret = request_threaded_irq(info->irq, NULL, max8998_rtc_alarm_irq, 0, "rtc-alarm0", info); @@ -293,6 +293,7 @@ static int __devinit max8998_rtc_probe(struct platform_device *pdev) return 0; out_rtc: + platform_set_drvdata(pdev, NULL); kfree(info); return ret; } diff --git a/drivers/rtc/rtc-mc13xxx.c b/drivers/rtc/rtc-mc13xxx.c index c5ac03793e7..a1a278bc340 100644 --- a/drivers/rtc/rtc-mc13xxx.c +++ b/drivers/rtc/rtc-mc13xxx.c @@ -349,11 +349,15 @@ static int __devinit mc13xxx_rtc_probe(struct platform_device *pdev) if (ret) goto err_alarm_irq_request; + mc13xxx_unlock(mc13xxx); + priv->rtc = rtc_device_register(pdev->name, &pdev->dev, &mc13xxx_rtc_ops, THIS_MODULE); if (IS_ERR(priv->rtc)) { ret = PTR_ERR(priv->rtc); + mc13xxx_lock(mc13xxx); + mc13xxx_irq_free(mc13xxx, MC13XXX_IRQ_TODA, priv); err_alarm_irq_request: @@ -365,12 +369,12 @@ err_reset_irq_status: mc13xxx_irq_free(mc13xxx, MC13XXX_IRQ_RTCRST, priv); err_reset_irq_request: + mc13xxx_unlock(mc13xxx); + platform_set_drvdata(pdev, NULL); kfree(priv); } - mc13xxx_unlock(mc13xxx); - return ret; } diff --git a/drivers/rtc/rtc-msm6242.c b/drivers/rtc/rtc-msm6242.c index 67820626e18..fcb113c1112 100644 --- a/drivers/rtc/rtc-msm6242.c +++ b/drivers/rtc/rtc-msm6242.c @@ -214,6 +214,7 @@ static int __init msm6242_rtc_probe(struct platform_device *dev) error = -ENOMEM; goto out_free_priv; } + platform_set_drvdata(dev, priv); rtc = rtc_device_register("rtc-msm6242", &dev->dev, &msm6242_rtc_ops, THIS_MODULE); @@ -223,10 +224,10 @@ static int __init msm6242_rtc_probe(struct platform_device *dev) } priv->rtc = rtc; - platform_set_drvdata(dev, priv); return 0; out_unmap: + platform_set_drvdata(dev, NULL); iounmap(priv->regs); out_free_priv: kfree(priv); diff --git a/drivers/rtc/rtc-mxc.c b/drivers/rtc/rtc-mxc.c index 826ab64a8fa..d814417bee8 100644 --- a/drivers/rtc/rtc-mxc.c +++ b/drivers/rtc/rtc-mxc.c @@ -418,14 +418,6 @@ static int __init mxc_rtc_probe(struct platform_device *pdev) goto exit_put_clk; } - rtc = rtc_device_register(pdev->name, &pdev->dev, &mxc_rtc_ops, - THIS_MODULE); - if (IS_ERR(rtc)) { - ret = PTR_ERR(rtc); - goto exit_put_clk; - } - - pdata->rtc = rtc; platform_set_drvdata(pdev, pdata); /* Configure and enable the RTC */ @@ -438,8 +430,19 @@ static int __init mxc_rtc_probe(struct platform_device *pdev) pdata->irq = -1; } + rtc = rtc_device_register(pdev->name, &pdev->dev, &mxc_rtc_ops, + THIS_MODULE); + if (IS_ERR(rtc)) { + ret = PTR_ERR(rtc); + goto exit_clr_drvdata; + } + + pdata->rtc = rtc; + return 0; +exit_clr_drvdata: + platform_set_drvdata(pdev, NULL); exit_put_clk: clk_disable(pdata->clk); clk_put(pdata->clk); diff --git a/drivers/rtc/rtc-pcap.c b/drivers/rtc/rtc-pcap.c index a633abc4289..cd4f198cc2e 100644 --- a/drivers/rtc/rtc-pcap.c +++ b/drivers/rtc/rtc-pcap.c @@ -151,6 +151,8 @@ static int __devinit pcap_rtc_probe(struct platform_device *pdev) pcap_rtc->pcap = dev_get_drvdata(pdev->dev.parent); + platform_set_drvdata(pdev, pcap_rtc); + pcap_rtc->rtc = rtc_device_register("pcap", &pdev->dev, &pcap_rtc_ops, THIS_MODULE); if (IS_ERR(pcap_rtc->rtc)) { @@ -158,7 +160,6 @@ static int __devinit pcap_rtc_probe(struct platform_device *pdev) goto fail_rtc; } - platform_set_drvdata(pdev, pcap_rtc); timer_irq = pcap_to_irq(pcap_rtc->pcap, PCAP_IRQ_1HZ); alarm_irq = pcap_to_irq(pcap_rtc->pcap, PCAP_IRQ_TODA); @@ -177,6 +178,7 @@ fail_alarm: fail_timer: rtc_device_unregister(pcap_rtc->rtc); fail_rtc: + platform_set_drvdata(pdev, NULL); kfree(pcap_rtc); return err; } diff --git a/drivers/rtc/rtc-rp5c01.c b/drivers/rtc/rtc-rp5c01.c index 694da39b6dd..359da6d020b 100644 --- a/drivers/rtc/rtc-rp5c01.c +++ b/drivers/rtc/rtc-rp5c01.c @@ -249,15 +249,15 @@ static int __init rp5c01_rtc_probe(struct platform_device *dev) spin_lock_init(&priv->lock); + platform_set_drvdata(dev, priv); + rtc = rtc_device_register("rtc-rp5c01", &dev->dev, &rp5c01_rtc_ops, THIS_MODULE); if (IS_ERR(rtc)) { error = PTR_ERR(rtc); goto out_unmap; } - priv->rtc = rtc; - platform_set_drvdata(dev, priv); error = sysfs_create_bin_file(&dev->dev.kobj, &priv->nvram_attr); if (error) @@ -268,6 +268,7 @@ static int __init rp5c01_rtc_probe(struct platform_device *dev) out_unregister: rtc_device_unregister(rtc); out_unmap: + platform_set_drvdata(dev, NULL); iounmap(priv->regs); out_free_priv: kfree(priv); diff --git a/drivers/s390/char/tape_block.c b/drivers/s390/char/tape_block.c index 83cea9a55e2..1b3924c2fff 100644 --- a/drivers/s390/char/tape_block.c +++ b/drivers/s390/char/tape_block.c @@ -236,7 +236,6 @@ tapeblock_setup_device(struct tape_device * device) disk->major = tapeblock_major; disk->first_minor = device->first_minor; disk->fops = &tapeblock_fops; - disk->events = DISK_EVENT_MEDIA_CHANGE; disk->private_data = tape_get_device(device); disk->queue = blkdat->request_queue; set_capacity(disk, 0); diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 0bac91e7237..ec1803a4872 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -74,8 +74,6 @@ struct kmem_cache *scsi_sdb_cache; */ #define SCSI_QUEUE_DELAY 3 -static void scsi_run_queue(struct request_queue *q); - /* * Function: scsi_unprep_request() * @@ -161,7 +159,7 @@ static int __scsi_queue_insert(struct scsi_cmnd *cmd, int reason, int unbusy) blk_requeue_request(q, cmd->request); spin_unlock_irqrestore(q->queue_lock, flags); - scsi_run_queue(q); + kblockd_schedule_work(q, &device->requeue_work); return 0; } @@ -438,7 +436,11 @@ static void scsi_run_queue(struct request_queue *q) continue; } - blk_run_queue_async(sdev->request_queue); + spin_unlock(shost->host_lock); + spin_lock(sdev->request_queue->queue_lock); + __blk_run_queue(sdev->request_queue); + spin_unlock(sdev->request_queue->queue_lock); + spin_lock(shost->host_lock); } /* put any unprocessed entries back */ list_splice(&starved_list, &shost->starved_list); @@ -447,6 +449,16 @@ static void scsi_run_queue(struct request_queue *q) blk_run_queue(q); } +void scsi_requeue_run_queue(struct work_struct *work) +{ + struct scsi_device *sdev; + struct request_queue *q; + + sdev = container_of(work, struct scsi_device, requeue_work); + q = sdev->request_queue; + scsi_run_queue(q); +} + /* * Function: scsi_requeue_command() * diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index 087821fac8f..58584dc0724 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -242,6 +242,7 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget, int display_failure_msg = 1, ret; struct Scsi_Host *shost = dev_to_shost(starget->dev.parent); extern void scsi_evt_thread(struct work_struct *work); + extern void scsi_requeue_run_queue(struct work_struct *work); sdev = kzalloc(sizeof(*sdev) + shost->transportt->device_size, GFP_ATOMIC); @@ -264,6 +265,7 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget, INIT_LIST_HEAD(&sdev->event_list); spin_lock_init(&sdev->list_lock); INIT_WORK(&sdev->event_work, scsi_evt_thread); + INIT_WORK(&sdev->requeue_work, scsi_requeue_run_queue); sdev->sdev_gendev.parent = get_device(&starget->dev); sdev->sdev_target = starget; diff --git a/fs/block_dev.c b/fs/block_dev.c index 5147bdd3b8e..257b00e9842 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1102,6 +1102,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) if (!bdev->bd_part) goto out_clear; + ret = 0; if (disk->fops->open) { ret = disk->fops->open(bdev, mode); if (ret == -ERESTARTSYS) { @@ -1118,9 +1119,18 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) put_disk(disk); goto restart; } - if (ret) - goto out_clear; } + /* + * If the device is invalidated, rescan partition + * if open succeeded or failed with -ENOMEDIUM. + * The latter is necessary to prevent ghost + * partitions on a removed medium. + */ + if (bdev->bd_invalidated && (!ret || ret == -ENOMEDIUM)) + rescan_partitions(disk, bdev); + if (ret) + goto out_clear; + if (!bdev->bd_openers) { bd_set_size(bdev,(loff_t)get_capacity(disk)<<9); bdi = blk_get_backing_dev_info(bdev); @@ -1128,8 +1138,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) bdi = &default_backing_dev_info; bdev_inode_switch_bdi(bdev->bd_inode, bdi); } - if (bdev->bd_invalidated) - rescan_partitions(disk, bdev); } else { struct block_device *whole; whole = bdget_disk(disk, 0); @@ -1153,13 +1161,14 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) } } else { if (bdev->bd_contains == bdev) { - if (bdev->bd_disk->fops->open) { + ret = 0; + if (bdev->bd_disk->fops->open) ret = bdev->bd_disk->fops->open(bdev, mode); - if (ret) - goto out_unlock_bdev; - } - if (bdev->bd_invalidated) + /* the same as first opener case, read comment there */ + if (bdev->bd_invalidated && (!ret || ret == -ENOMEDIUM)) rescan_partitions(bdev->bd_disk, bdev); + if (ret) + goto out_unlock_bdev; } /* only one opener holds refs to the module and disk */ module_put(disk->fops->owner); diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c index 23d43cde430..1b2e180b018 100644 --- a/fs/cifs/cifs_unicode.c +++ b/fs/cifs/cifs_unicode.c @@ -277,6 +277,7 @@ cifsConvertToUCS(__le16 *target, const char *source, int srclen, for (i = 0, j = 0; i < srclen; j++) { src_char = source[i]; + charlen = 1; switch (src_char) { case 0: put_unaligned(0, &target[j]); @@ -316,16 +317,13 @@ cifsConvertToUCS(__le16 *target, const char *source, int srclen, dst_char = cpu_to_le16(0x003f); charlen = 1; } - /* - * character may take more than one byte in the source - * string, but will take exactly two bytes in the - * target string - */ - i += charlen; - continue; } + /* + * character may take more than one byte in the source string, + * but will take exactly two bytes in the target string + */ + i += charlen; put_unaligned(dst_char, &target[j]); - i++; /* move to next char in source string */ } ctoUCS_out: diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 05f1dcf7d79..277262a8e82 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -2673,6 +2673,11 @@ is_path_accessible(int xid, struct cifsTconInfo *tcon, 0 /* not legacy */, cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); + + if (rc == -EOPNOTSUPP || rc == -EINVAL) + rc = SMBQueryInformation(xid, tcon, full_path, pfile_info, + cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & + CIFS_MOUNT_MAP_SPECIAL_CHR); kfree(pfile_info); return rc; } diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 838c1149251..eaf4350c0f9 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -208,6 +208,8 @@ static inline struct proc_dir_entry *proc_symlink(const char *name, struct proc_dir_entry *parent,const char *dest) {return NULL;} static inline struct proc_dir_entry *proc_mkdir(const char *name, struct proc_dir_entry *parent) {return NULL;} +static inline struct proc_dir_entry *proc_mkdir_mode(const char *name, + mode_t mode, struct proc_dir_entry *parent) { return NULL; } static inline struct proc_dir_entry *create_proc_read_entry(const char *name, mode_t mode, struct proc_dir_entry *base, diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 2d3ec509468..dd82e02ddde 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -169,6 +169,7 @@ struct scsi_device { sdev_dev; struct execute_work ew; /* used to get process context on put */ + struct work_struct requeue_work; struct scsi_dh_data *scsi_dh_data; enum scsi_device_state sdev_state; diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 6519cf62d9c..0e17c10f8a9 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -685,8 +685,8 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq) /* Add clocksource to the clcoksource list */ mutex_lock(&clocksource_mutex); clocksource_enqueue(cs); - clocksource_select(); clocksource_enqueue_watchdog(cs); + clocksource_select(); mutex_unlock(&clocksource_mutex); return 0; } @@ -706,8 +706,8 @@ int clocksource_register(struct clocksource *cs) mutex_lock(&clocksource_mutex); clocksource_enqueue(cs); - clocksource_select(); clocksource_enqueue_watchdog(cs); + clocksource_select(); mutex_unlock(&clocksource_mutex); return 0; } diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index da800ffa810..723c7637e55 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -522,10 +522,11 @@ static void tick_broadcast_init_next_event(struct cpumask *mask, */ void tick_broadcast_setup_oneshot(struct clock_event_device *bc) { + int cpu = smp_processor_id(); + /* Set it up only once ! */ if (bc->event_handler != tick_handle_oneshot_broadcast) { int was_periodic = bc->mode == CLOCK_EVT_MODE_PERIODIC; - int cpu = smp_processor_id(); bc->event_handler = tick_handle_oneshot_broadcast; clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT); @@ -551,6 +552,15 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc) tick_broadcast_set_event(tick_next_period, 1); } else bc->next_event.tv64 = KTIME_MAX; + } else { + /* + * The first cpu which switches to oneshot mode sets + * the bit for all other cpus which are in the general + * (periodic) broadcast mask. So the bit is set and + * would prevent the first broadcast enter after this + * to program the bc device. + */ + tick_broadcast_clear_oneshot(cpu); } } diff --git a/mm/vmscan.c b/mm/vmscan.c index f6b435c8007..8bfd45050a6 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -937,7 +937,7 @@ keep_lumpy: * back off and wait for congestion to clear because further reclaim * will encounter the same problem */ - if (nr_dirty == nr_congested && nr_dirty != 0) + if (nr_dirty && nr_dirty == nr_congested && scanning_global_lru(sc)) zone_set_flag(zone, ZONE_CONGESTED); free_page_list(&free_pages); diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 416538248a4..0974f957b8f 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -427,7 +427,7 @@ static void mmap_read_all(void) { int i; - for (i = 0; i < evsel_list->cpus->nr; i++) { + for (i = 0; i < evsel_list->nr_mmaps; i++) { if (evsel_list->mmap[i].base) mmap_read(&evsel_list->mmap[i]); } diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c index 11e3c845836..2f9a337b182 100644 --- a/tools/perf/builtin-test.c +++ b/tools/perf/builtin-test.c @@ -549,7 +549,7 @@ static int test__basic_mmap(void) ++foo; } - while ((event = perf_evlist__read_on_cpu(evlist, 0)) != NULL) { + while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) { struct perf_sample sample; if (event->header.type != PERF_RECORD_SAMPLE) { diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 7e3d6e310bf..ebfc7cf5f63 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -801,12 +801,12 @@ static void perf_event__process_sample(const union perf_event *event, } } -static void perf_session__mmap_read_cpu(struct perf_session *self, int cpu) +static void perf_session__mmap_read_idx(struct perf_session *self, int idx) { struct perf_sample sample; union perf_event *event; - while ((event = perf_evlist__read_on_cpu(top.evlist, cpu)) != NULL) { + while ((event = perf_evlist__mmap_read(top.evlist, idx)) != NULL) { perf_session__parse_sample(self, event, &sample); if (event->header.type == PERF_RECORD_SAMPLE) @@ -820,8 +820,8 @@ static void perf_session__mmap_read(struct perf_session *self) { int i; - for (i = 0; i < top.evlist->cpus->nr; i++) - perf_session__mmap_read_cpu(self, i); + for (i = 0; i < top.evlist->nr_mmaps; i++) + perf_session__mmap_read_idx(self, i); } static void start_counters(struct perf_evlist *evlist) diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 45da8d186b4..23eb22b05d2 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -166,11 +166,11 @@ struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id) return NULL; } -union perf_event *perf_evlist__read_on_cpu(struct perf_evlist *evlist, int cpu) +union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) { /* XXX Move this to perf.c, making it generally available */ unsigned int page_size = sysconf(_SC_PAGE_SIZE); - struct perf_mmap *md = &evlist->mmap[cpu]; + struct perf_mmap *md = &evlist->mmap[idx]; unsigned int head = perf_mmap__read_head(md); unsigned int old = md->prev; unsigned char *data = md->base + page_size; @@ -235,31 +235,37 @@ union perf_event *perf_evlist__read_on_cpu(struct perf_evlist *evlist, int cpu) void perf_evlist__munmap(struct perf_evlist *evlist) { - int cpu; + int i; - for (cpu = 0; cpu < evlist->cpus->nr; cpu++) { - if (evlist->mmap[cpu].base != NULL) { - munmap(evlist->mmap[cpu].base, evlist->mmap_len); - evlist->mmap[cpu].base = NULL; + for (i = 0; i < evlist->nr_mmaps; i++) { + if (evlist->mmap[i].base != NULL) { + munmap(evlist->mmap[i].base, evlist->mmap_len); + evlist->mmap[i].base = NULL; } } + + free(evlist->mmap); + evlist->mmap = NULL; } int perf_evlist__alloc_mmap(struct perf_evlist *evlist) { - evlist->mmap = zalloc(evlist->cpus->nr * sizeof(struct perf_mmap)); + evlist->nr_mmaps = evlist->cpus->nr; + if (evlist->cpus->map[0] == -1) + evlist->nr_mmaps = evlist->threads->nr; + evlist->mmap = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap)); return evlist->mmap != NULL ? 0 : -ENOMEM; } static int __perf_evlist__mmap(struct perf_evlist *evlist, struct perf_evsel *evsel, - int cpu, int prot, int mask, int fd) + int idx, int prot, int mask, int fd) { - evlist->mmap[cpu].prev = 0; - evlist->mmap[cpu].mask = mask; - evlist->mmap[cpu].base = mmap(NULL, evlist->mmap_len, prot, + evlist->mmap[idx].prev = 0; + evlist->mmap[idx].mask = mask; + evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, prot, MAP_SHARED, fd, 0); - if (evlist->mmap[cpu].base == MAP_FAILED) { - if (evlist->cpus->map[cpu] == -1 && evsel->attr.inherit) + if (evlist->mmap[idx].base == MAP_FAILED) { + if (evlist->cpus->map[idx] == -1 && evsel->attr.inherit) ui__warning("Inherit is not allowed on per-task " "events using mmap.\n"); return -1; @@ -269,6 +275,86 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, struct perf_evsel *ev return 0; } +static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int mask) +{ + struct perf_evsel *evsel; + int cpu, thread; + + for (cpu = 0; cpu < evlist->cpus->nr; cpu++) { + int output = -1; + + for (thread = 0; thread < evlist->threads->nr; thread++) { + list_for_each_entry(evsel, &evlist->entries, node) { + int fd = FD(evsel, cpu, thread); + + if (output == -1) { + output = fd; + if (__perf_evlist__mmap(evlist, evsel, cpu, + prot, mask, output) < 0) + goto out_unmap; + } else { + if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, output) != 0) + goto out_unmap; + } + + if ((evsel->attr.read_format & PERF_FORMAT_ID) && + perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0) + goto out_unmap; + } + } + } + + return 0; + +out_unmap: + for (cpu = 0; cpu < evlist->cpus->nr; cpu++) { + if (evlist->mmap[cpu].base != NULL) { + munmap(evlist->mmap[cpu].base, evlist->mmap_len); + evlist->mmap[cpu].base = NULL; + } + } + return -1; +} + +static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, int mask) +{ + struct perf_evsel *evsel; + int thread; + + for (thread = 0; thread < evlist->threads->nr; thread++) { + int output = -1; + + list_for_each_entry(evsel, &evlist->entries, node) { + int fd = FD(evsel, 0, thread); + + if (output == -1) { + output = fd; + if (__perf_evlist__mmap(evlist, evsel, thread, + prot, mask, output) < 0) + goto out_unmap; + } else { + if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, output) != 0) + goto out_unmap; + } + + if ((evsel->attr.read_format & PERF_FORMAT_ID) && + perf_evlist__id_add_fd(evlist, evsel, 0, thread, fd) < 0) + goto out_unmap; + } + } + + return 0; + +out_unmap: + for (thread = 0; thread < evlist->threads->nr; thread++) { + if (evlist->mmap[thread].base != NULL) { + munmap(evlist->mmap[thread].base, evlist->mmap_len); + evlist->mmap[thread].base = NULL; + } + } + return -1; +} + /** perf_evlist__mmap - Create per cpu maps to receive events * * @evlist - list of events @@ -287,11 +373,11 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, struct perf_evsel *ev int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite) { unsigned int page_size = sysconf(_SC_PAGE_SIZE); - int mask = pages * page_size - 1, cpu; - struct perf_evsel *first_evsel, *evsel; + int mask = pages * page_size - 1; + struct perf_evsel *evsel; const struct cpu_map *cpus = evlist->cpus; const struct thread_map *threads = evlist->threads; - int thread, prot = PROT_READ | (overwrite ? 0 : PROT_WRITE); + int prot = PROT_READ | (overwrite ? 0 : PROT_WRITE); if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0) return -ENOMEM; @@ -301,43 +387,18 @@ int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite) evlist->overwrite = overwrite; evlist->mmap_len = (pages + 1) * page_size; - first_evsel = list_entry(evlist->entries.next, struct perf_evsel, node); list_for_each_entry(evsel, &evlist->entries, node) { if ((evsel->attr.read_format & PERF_FORMAT_ID) && evsel->sample_id == NULL && perf_evsel__alloc_id(evsel, cpus->nr, threads->nr) < 0) return -ENOMEM; - - for (cpu = 0; cpu < cpus->nr; cpu++) { - for (thread = 0; thread < threads->nr; thread++) { - int fd = FD(evsel, cpu, thread); - - if (evsel->idx || thread) { - if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, - FD(first_evsel, cpu, 0)) != 0) - goto out_unmap; - } else if (__perf_evlist__mmap(evlist, evsel, cpu, - prot, mask, fd) < 0) - goto out_unmap; - - if ((evsel->attr.read_format & PERF_FORMAT_ID) && - perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0) - goto out_unmap; - } - } } - return 0; + if (evlist->cpus->map[0] == -1) + return perf_evlist__mmap_per_thread(evlist, prot, mask); -out_unmap: - for (cpu = 0; cpu < cpus->nr; cpu++) { - if (evlist->mmap[cpu].base != NULL) { - munmap(evlist->mmap[cpu].base, evlist->mmap_len); - evlist->mmap[cpu].base = NULL; - } - } - return -1; + return perf_evlist__mmap_per_cpu(evlist, prot, mask); } int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid, @@ -348,7 +409,7 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid, if (evlist->threads == NULL) return -1; - if (target_tid != -1) + if (cpu_list == NULL && target_tid != -1) evlist->cpus = cpu_map__dummy_new(); else evlist->cpus = cpu_map__new(cpu_list); diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 8b1cb7a4c5f..7109d7add14 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -17,6 +17,7 @@ struct perf_evlist { struct hlist_head heads[PERF_EVLIST__HLIST_SIZE]; int nr_entries; int nr_fds; + int nr_mmaps; int mmap_len; bool overwrite; union perf_event event_copy; @@ -46,7 +47,7 @@ void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd); struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id); -union perf_event *perf_evlist__read_on_cpu(struct perf_evlist *self, int cpu); +union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx); int perf_evlist__alloc_mmap(struct perf_evlist *evlist); int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite); diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index f5e38451fdc..99c722672f8 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -680,7 +680,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, &cpu, &sample_id_all)) return NULL; - event = perf_evlist__read_on_cpu(evlist, cpu); + event = perf_evlist__mmap_read(evlist, cpu); if (event != NULL) { struct perf_evsel *first; PyObject *pyevent = pyrf_event__new(event); |