diff options
69 files changed, 511 insertions, 331 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index 69c8a9c3289a..38df53f828e1 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8286,7 +8286,7 @@ F: include/linux/delayacct.h F: kernel/delayacct.c PERFORMANCE EVENTS SUBSYSTEM -M: Peter Zijlstra <[email protected]> +M: Peter Zijlstra <[email protected]> M: Ingo Molnar <[email protected]> M: Arnaldo Carvalho de Melo <[email protected]> diff --git a/arch/blackfin/kernel/perf_event.c b/arch/blackfin/kernel/perf_event.c index 1e9c8b0bf486..170d786807c4 100644 --- a/arch/blackfin/kernel/perf_event.c +++ b/arch/blackfin/kernel/perf_event.c @@ -14,7 +14,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <[email protected]> + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra * Copyright (C) 2009 Intel Corporation, <[email protected]> * * ppc: diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c index 7cfd7f153966..4dca18347ee9 100644 --- a/arch/sh/kernel/perf_event.c +++ b/arch/sh/kernel/perf_event.c @@ -10,7 +10,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <[email protected]> + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra * Copyright (C) 2009 Intel Corporation, <[email protected]> * * ppc: diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c index b0da5aedb336..3091267c5cc3 100644 --- a/arch/sparc/kernel/perf_event.c +++ b/arch/sparc/kernel/perf_event.c @@ -9,7 +9,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <[email protected]> + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra */ #include <linux/perf_event.h> diff --git a/arch/tile/kernel/perf_event.c b/arch/tile/kernel/perf_event.c index bb509cee3b59..8767060d70fb 100644 --- a/arch/tile/kernel/perf_event.c +++ b/arch/tile/kernel/perf_event.c @@ -21,7 +21,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <[email protected]> + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra * Copyright (C) 2009 Intel Corporation, <[email protected]> * Copyright (C) 2009 Google, Inc., Stephane Eranian */ diff --git a/arch/um/Makefile b/arch/um/Makefile index 25ed4098640e..e3abe6f3156d 100644 --- a/arch/um/Makefile +++ b/arch/um/Makefile @@ -131,7 +131,7 @@ export LDS_ELF_FORMAT := $(ELF_FORMAT) # The wrappers will select whether using "malloc" or the kernel allocator. LINK_WRAPS = -Wl,--wrap,malloc -Wl,--wrap,free -Wl,--wrap,calloc -LD_FLAGS_CMDLINE = $(foreach opt,$(LDFLAGS),-Wl,$(opt)) -lrt +LD_FLAGS_CMDLINE = $(foreach opt,$(LDFLAGS),-Wl,$(opt)) # Used by link-vmlinux.sh which has special support for um link export CFLAGS_vmlinux := $(LINK-y) $(LINK_WRAPS) $(LD_FLAGS_CMDLINE) diff --git a/arch/um/drivers/net_user.c b/arch/um/drivers/net_user.c index e697a4136707..e9f8445861dc 100644 --- a/arch/um/drivers/net_user.c +++ b/arch/um/drivers/net_user.c @@ -249,21 +249,23 @@ void close_addr(unsigned char *addr, unsigned char *netmask, void *arg) char *split_if_spec(char *str, ...) { - char **arg, *end; + char **arg, *end, *ret = NULL; va_list ap; va_start(ap, str); while ((arg = va_arg(ap, char **)) != NULL) { if (*str == '\0') - return NULL; + goto out; end = strchr(str, ','); if (end != str) *arg = str; if (end == NULL) - return NULL; + goto out; *end++ = '\0'; str = end; } + ret = str; +out: va_end(ap); - return str; + return ret; } diff --git a/arch/um/kernel/signal.c b/arch/um/kernel/signal.c index 57acbd67d85d..fc8be0e3a4ff 100644 --- a/arch/um/kernel/signal.c +++ b/arch/um/kernel/signal.c @@ -69,7 +69,7 @@ void do_signal(struct pt_regs *regs) struct ksignal ksig; int handled_sig = 0; - while (get_signal(&ksig)) { + if (get_signal(&ksig)) { handled_sig = 1; /* Whee! Actually deliver the signal. */ handle_signal(&ksig, regs); diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 4562cf070c27..2bf79d7c97df 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -5,7 +5,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <[email protected]> + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra * Copyright (C) 2009 Intel Corporation, <[email protected]> * Copyright (C) 2009 Google, Inc., Stephane Eranian * diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 499f533dd3cc..d0e35ebb2adb 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -5,7 +5,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <[email protected]> + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra * Copyright (C) 2009 Intel Corporation, <[email protected]> * Copyright (C) 2009 Google, Inc., Stephane Eranian * @@ -387,7 +387,7 @@ struct cpu_hw_events { /* Check flags and event code/umask, and set the HSW N/A flag */ #define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(code, n) \ __EVENT_CONSTRAINT(code, n, \ - INTEL_ARCH_EVENT_MASK|INTEL_ARCH_EVENT_MASK, \ + INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_NA_HSW) @@ -627,6 +627,7 @@ struct x86_perf_task_context { u64 lbr_from[MAX_LBR_ENTRIES]; u64 lbr_to[MAX_LBR_ENTRIES]; u64 lbr_info[MAX_LBR_ENTRIES]; + int tos; int lbr_callstack_users; int lbr_stack_state; }; diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index f63360be2238..e2a430021e46 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -232,7 +232,7 @@ static struct event_constraint intel_hsw_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ - INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.* */ + INTEL_UEVENT_CONSTRAINT(0x148, 0x4), /* L1D_PEND_MISS.PENDING */ INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */ INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */ /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c index 377e8f8ed391..a316ca96f1b6 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c +++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c @@ -298,7 +298,7 @@ static bool __match_event(struct perf_event *a, struct perf_event *b) static inline struct perf_cgroup *event_to_cgroup(struct perf_event *event) { if (event->attach_state & PERF_ATTACH_TASK) - return perf_cgroup_from_task(event->hw.target); + return perf_cgroup_from_task(event->hw.target, event->ctx); return event->cgrp; } diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index bfd0b717e944..659f01e165d5 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -239,7 +239,7 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx) } mask = x86_pmu.lbr_nr - 1; - tos = intel_pmu_lbr_tos(); + tos = task_ctx->tos; for (i = 0; i < tos; i++) { lbr_idx = (tos - i) & mask; wrmsrl(x86_pmu.lbr_from + lbr_idx, task_ctx->lbr_from[i]); @@ -247,6 +247,7 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx) if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO) wrmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]); } + wrmsrl(x86_pmu.lbr_tos, tos); task_ctx->lbr_stack_state = LBR_NONE; } @@ -270,6 +271,7 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx) if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO) rdmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]); } + task_ctx->tos = tos; task_ctx->lbr_stack_state = LBR_VALID; } diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c index dc5fa6a1e8d6..3512ba607361 100644 --- a/arch/x86/kernel/irq_work.c +++ b/arch/x86/kernel/irq_work.c @@ -1,7 +1,7 @@ /* * x86 specific code for irq_work * - * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra <[email protected]> + * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra */ #include <linux/kernel.h> diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c index 06934a8a4872..e5f854ce2d72 100644 --- a/arch/x86/um/signal.c +++ b/arch/x86/um/signal.c @@ -211,7 +211,7 @@ static int copy_sc_from_user(struct pt_regs *regs, if (err) return 1; - err = convert_fxsr_from_user(&fpx, sc.fpstate); + err = convert_fxsr_from_user(&fpx, (void *)sc.fpstate); if (err) return 1; @@ -227,7 +227,7 @@ static int copy_sc_from_user(struct pt_regs *regs, { struct user_i387_struct fp; - err = copy_from_user(&fp, sc.fpstate, + err = copy_from_user(&fp, (void *)sc.fpstate, sizeof(struct user_i387_struct)); if (err) return 1; @@ -291,7 +291,7 @@ static int copy_sc_to_user(struct sigcontext __user *to, #endif #undef PUTREG sc.oldmask = mask; - sc.fpstate = to_fp; + sc.fpstate = (unsigned long)to_fp; err = copy_to_user(to, &sc, sizeof(struct sigcontext)); if (err) @@ -468,12 +468,10 @@ long sys_sigreturn(void) struct sigframe __user *frame = (struct sigframe __user *)(sp - 8); sigset_t set; struct sigcontext __user *sc = &frame->sc; - unsigned long __user *oldmask = &sc->oldmask; - unsigned long __user *extramask = frame->extramask; int sig_size = (_NSIG_WORDS - 1) * sizeof(unsigned long); - if (copy_from_user(&set.sig[0], oldmask, sizeof(set.sig[0])) || - copy_from_user(&set.sig[1], extramask, sig_size)) + if (copy_from_user(&set.sig[0], (void *)sc->oldmask, sizeof(set.sig[0])) || + copy_from_user(&set.sig[1], frame->extramask, sig_size)) goto segfault; set_current_blocked(&set); @@ -505,6 +503,7 @@ int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig, { struct rt_sigframe __user *frame; int err = 0, sig = ksig->sig; + unsigned long fp_to; frame = (struct rt_sigframe __user *) round_down(stack_top - sizeof(struct rt_sigframe), 16); @@ -526,7 +525,10 @@ int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig, err |= __save_altstack(&frame->uc.uc_stack, PT_REGS_SP(regs)); err |= copy_sc_to_user(&frame->uc.uc_mcontext, &frame->fpstate, regs, set->sig[0]); - err |= __put_user(&frame->fpstate, &frame->uc.uc_mcontext.fpstate); + + fp_to = (unsigned long)&frame->fpstate; + + err |= __put_user(fp_to, &frame->uc.uc_mcontext.fpstate); if (sizeof(*set) == 16) { err |= __put_user(set->sig[0], &frame->uc.uc_sigmask.sig[0]); err |= __put_user(set->sig[1], &frame->uc.uc_sigmask.sig[1]); diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 5bcdfc10c23a..5a37188b559f 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1127,15 +1127,15 @@ void blkcg_exit_queue(struct request_queue *q) * of the main cic data structures. For now we allow a task to change * its cgroup only if it's the only owner of its ioc. */ -static int blkcg_can_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static int blkcg_can_attach(struct cgroup_taskset *tset) { struct task_struct *task; + struct cgroup_subsys_state *dst_css; struct io_context *ioc; int ret = 0; /* task_lock() is needed to avoid races with exit_io_context() */ - cgroup_taskset_for_each(task, tset) { + cgroup_taskset_for_each(task, dst_css, tset) { task_lock(task); ioc = task->io_context; if (ioc && atomic_read(&ioc->nr_tasks) > 1) diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index ff02bb4218fc..cdfbcc54821f 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -314,16 +314,6 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0x1f37), board_ahci_avn }, /* Avoton RAID */ { PCI_VDEVICE(INTEL, 0x1f3e), board_ahci_avn }, /* Avoton RAID */ { PCI_VDEVICE(INTEL, 0x1f3f), board_ahci_avn }, /* Avoton RAID */ - { PCI_VDEVICE(INTEL, 0xa182), board_ahci }, /* Lewisburg AHCI*/ - { PCI_VDEVICE(INTEL, 0xa202), board_ahci }, /* Lewisburg AHCI*/ - { PCI_VDEVICE(INTEL, 0xa184), board_ahci }, /* Lewisburg RAID*/ - { PCI_VDEVICE(INTEL, 0xa204), board_ahci }, /* Lewisburg RAID*/ - { PCI_VDEVICE(INTEL, 0xa186), board_ahci }, /* Lewisburg RAID*/ - { PCI_VDEVICE(INTEL, 0xa206), board_ahci }, /* Lewisburg RAID*/ - { PCI_VDEVICE(INTEL, 0x2822), board_ahci }, /* Lewisburg RAID*/ - { PCI_VDEVICE(INTEL, 0x2826), board_ahci }, /* Lewisburg RAID*/ - { PCI_VDEVICE(INTEL, 0xa18e), board_ahci }, /* Lewisburg RAID*/ - { PCI_VDEVICE(INTEL, 0xa20e), board_ahci }, /* Lewisburg RAID*/ { PCI_VDEVICE(INTEL, 0x2823), board_ahci }, /* Wellsburg RAID */ { PCI_VDEVICE(INTEL, 0x2827), board_ahci }, /* Wellsburg RAID */ { PCI_VDEVICE(INTEL, 0x8d02), board_ahci }, /* Wellsburg AHCI */ @@ -350,10 +340,22 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0x9d03), board_ahci }, /* Sunrise Point-LP AHCI */ { PCI_VDEVICE(INTEL, 0x9d05), board_ahci }, /* Sunrise Point-LP RAID */ { PCI_VDEVICE(INTEL, 0x9d07), board_ahci }, /* Sunrise Point-LP RAID */ + { PCI_VDEVICE(INTEL, 0xa102), board_ahci }, /* Sunrise Point-H AHCI */ { PCI_VDEVICE(INTEL, 0xa103), board_ahci }, /* Sunrise Point-H AHCI */ { PCI_VDEVICE(INTEL, 0xa105), board_ahci }, /* Sunrise Point-H RAID */ + { PCI_VDEVICE(INTEL, 0xa106), board_ahci }, /* Sunrise Point-H RAID */ { PCI_VDEVICE(INTEL, 0xa107), board_ahci }, /* Sunrise Point-H RAID */ { PCI_VDEVICE(INTEL, 0xa10f), board_ahci }, /* Sunrise Point-H RAID */ + { PCI_VDEVICE(INTEL, 0x2822), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0x2826), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0xa182), board_ahci }, /* Lewisburg AHCI*/ + { PCI_VDEVICE(INTEL, 0xa184), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0xa186), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0xa18e), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0xa202), board_ahci }, /* Lewisburg AHCI*/ + { PCI_VDEVICE(INTEL, 0xa204), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0xa206), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0xa20e), board_ahci }, /* Lewisburg RAID*/ /* JMicron 360/1/3/5/6, match class to avoid IDE function */ { PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, diff --git a/drivers/ata/ahci_mvebu.c b/drivers/ata/ahci_mvebu.c index 8490d37aee2a..f7a7fa81740e 100644 --- a/drivers/ata/ahci_mvebu.c +++ b/drivers/ata/ahci_mvebu.c @@ -62,6 +62,7 @@ static void ahci_mvebu_regret_option(struct ahci_host_priv *hpriv) writel(0x80, hpriv->mmio + AHCI_VENDOR_SPECIFIC_0_DATA); } +#ifdef CONFIG_PM_SLEEP static int ahci_mvebu_suspend(struct platform_device *pdev, pm_message_t state) { return ahci_platform_suspend_host(&pdev->dev); @@ -81,6 +82,10 @@ static int ahci_mvebu_resume(struct platform_device *pdev) return ahci_platform_resume_host(&pdev->dev); } +#else +#define ahci_mvebu_suspend NULL +#define ahci_mvebu_resume NULL +#endif static const struct ata_port_info ahci_mvebu_port_info = { .flags = AHCI_FLAG_COMMON, diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index 096064cd6c52..4665512dae44 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -1273,6 +1273,15 @@ static int ahci_exec_polled_cmd(struct ata_port *ap, int pmp, ata_tf_to_fis(tf, pmp, is_cmd, fis); ahci_fill_cmd_slot(pp, 0, cmd_fis_len | flags | (pmp << 12)); + /* set port value for softreset of Port Multiplier */ + if (pp->fbs_enabled && pp->fbs_last_dev != pmp) { + tmp = readl(port_mmio + PORT_FBS); + tmp &= ~(PORT_FBS_DEV_MASK | PORT_FBS_DEC); + tmp |= pmp << PORT_FBS_DEV_OFFSET; + writel(tmp, port_mmio + PORT_FBS); + pp->fbs_last_dev = pmp; + } + /* issue & wait */ writel(1, port_mmio + PORT_CMD_ISSUE); diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index cb0508af1459..961acc788f44 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -1505,12 +1505,20 @@ static const char *ata_err_string(unsigned int err_mask) unsigned int ata_read_log_page(struct ata_device *dev, u8 log, u8 page, void *buf, unsigned int sectors) { + unsigned long ap_flags = dev->link->ap->flags; struct ata_taskfile tf; unsigned int err_mask; bool dma = false; DPRINTK("read log page - log 0x%x, page 0x%x\n", log, page); + /* + * Return error without actually issuing the command on controllers + * which e.g. lockup on a read log page. + */ + if (ap_flags & ATA_FLAG_NO_LOG_PAGE) + return AC_ERR_DEV; + retry: ata_tf_init(dev, &tf); if (dev->dma_mode && ata_id_has_read_log_dma_ext(dev->id) && diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c index 5389579c5120..a723ae929783 100644 --- a/drivers/ata/sata_fsl.c +++ b/drivers/ata/sata_fsl.c @@ -45,7 +45,8 @@ enum { SATA_FSL_MAX_PRD_DIRECT = 16, /* Direct PRDT entries */ SATA_FSL_HOST_FLAGS = (ATA_FLAG_SATA | ATA_FLAG_PIO_DMA | - ATA_FLAG_PMP | ATA_FLAG_NCQ | ATA_FLAG_AN), + ATA_FLAG_PMP | ATA_FLAG_NCQ | + ATA_FLAG_AN | ATA_FLAG_NO_LOG_PAGE), SATA_FSL_MAX_CMDS = SATA_FSL_QUEUE_DEPTH, SATA_FSL_CMD_HDR_SIZE = 16, /* 4 DWORDS */ diff --git a/drivers/ata/sata_sil.c b/drivers/ata/sata_sil.c index dea6edcbf145..29bcff086bce 100644 --- a/drivers/ata/sata_sil.c +++ b/drivers/ata/sata_sil.c @@ -630,6 +630,9 @@ static void sil_dev_config(struct ata_device *dev) unsigned int n, quirks = 0; unsigned char model_num[ATA_ID_PROD_LEN + 1]; + /* This controller doesn't support trim */ + dev->horkage |= ATA_HORKAGE_NOTRIM; + ata_id_c_string(dev->id, model_num, ATA_ID_PROD, sizeof(model_num)); for (n = 0; sil_blacklist[n].product; n++) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index d8838dedb7a4..f94ab786088f 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -140,6 +140,12 @@ struct virtnet_info { /* CPU hot plug notifier */ struct notifier_block nb; + + /* Control VQ buffers: protected by the rtnl lock */ + struct virtio_net_ctrl_hdr ctrl_hdr; + virtio_net_ctrl_ack ctrl_status; + u8 ctrl_promisc; + u8 ctrl_allmulti; }; struct padded_vnet_hdr { @@ -976,31 +982,30 @@ static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd, struct scatterlist *out) { struct scatterlist *sgs[4], hdr, stat; - struct virtio_net_ctrl_hdr ctrl; - virtio_net_ctrl_ack status = ~0; unsigned out_num = 0, tmp; /* Caller should know better */ BUG_ON(!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ)); - ctrl.class = class; - ctrl.cmd = cmd; + vi->ctrl_status = ~0; + vi->ctrl_hdr.class = class; + vi->ctrl_hdr.cmd = cmd; /* Add header */ - sg_init_one(&hdr, &ctrl, sizeof(ctrl)); + sg_init_one(&hdr, &vi->ctrl_hdr, sizeof(vi->ctrl_hdr)); sgs[out_num++] = &hdr; if (out) sgs[out_num++] = out; /* Add return status. */ - sg_init_one(&stat, &status, sizeof(status)); + sg_init_one(&stat, &vi->ctrl_status, sizeof(vi->ctrl_status)); sgs[out_num] = &stat; BUG_ON(out_num + 1 > ARRAY_SIZE(sgs)); virtqueue_add_sgs(vi->cvq, sgs, out_num, 1, vi, GFP_ATOMIC); if (unlikely(!virtqueue_kick(vi->cvq))) - return status == VIRTIO_NET_OK; + return vi->ctrl_status == VIRTIO_NET_OK; /* Spin for a response, the kick causes an ioport write, trapping * into the hypervisor, so the request should be handled immediately. @@ -1009,7 +1014,7 @@ static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd, !virtqueue_is_broken(vi->cvq)) cpu_relax(); - return status == VIRTIO_NET_OK; + return vi->ctrl_status == VIRTIO_NET_OK; } static int virtnet_set_mac_address(struct net_device *dev, void *p) @@ -1151,7 +1156,6 @@ static void virtnet_set_rx_mode(struct net_device *dev) { struct virtnet_info *vi = netdev_priv(dev); struct scatterlist sg[2]; - u8 promisc, allmulti; struct virtio_net_ctrl_mac *mac_data; struct netdev_hw_addr *ha; int uc_count; @@ -1163,22 +1167,22 @@ static void virtnet_set_rx_mode(struct net_device *dev) if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_RX)) return; - promisc = ((dev->flags & IFF_PROMISC) != 0); - allmulti = ((dev->flags & IFF_ALLMULTI) != 0); + vi->ctrl_promisc = ((dev->flags & IFF_PROMISC) != 0); + vi->ctrl_allmulti = ((dev->flags & IFF_ALLMULTI) != 0); - sg_init_one(sg, &promisc, sizeof(promisc)); + sg_init_one(sg, &vi->ctrl_promisc, sizeof(vi->ctrl_promisc)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX, VIRTIO_NET_CTRL_RX_PROMISC, sg)) dev_warn(&dev->dev, "Failed to %sable promisc mode.\n", - promisc ? "en" : "dis"); + vi->ctrl_promisc ? "en" : "dis"); - sg_init_one(sg, &allmulti, sizeof(allmulti)); + sg_init_one(sg, &vi->ctrl_allmulti, sizeof(vi->ctrl_allmulti)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX, VIRTIO_NET_CTRL_RX_ALLMULTI, sg)) dev_warn(&dev->dev, "Failed to %sable allmulti mode.\n", - allmulti ? "en" : "dis"); + vi->ctrl_allmulti ? "en" : "dis"); uc_count = netdev_uc_count(dev); mc_count = netdev_mc_count(dev); diff --git a/drivers/pci/host/pcie-altera.c b/drivers/pci/host/pcie-altera.c index e5dda38bdde5..99da549d5d06 100644 --- a/drivers/pci/host/pcie-altera.c +++ b/drivers/pci/host/pcie-altera.c @@ -55,8 +55,10 @@ #define TLP_CFG_DW2(bus, devfn, offset) \ (((bus) << 24) | ((devfn) << 16) | (offset)) #define TLP_REQ_ID(bus, devfn) (((bus) << 8) | (devfn)) +#define TLP_COMP_STATUS(s) (((s) >> 12) & 7) #define TLP_HDR_SIZE 3 #define TLP_LOOP 500 +#define RP_DEVFN 0 #define INTX_NUM 4 @@ -166,34 +168,41 @@ static bool altera_pcie_valid_config(struct altera_pcie *pcie, static int tlp_read_packet(struct altera_pcie *pcie, u32 *value) { - u8 loop; + int i; bool sop = 0; u32 ctrl; u32 reg0, reg1; + u32 comp_status = 1; /* * Minimum 2 loops to read TLP headers and 1 loop to read data * payload. */ - for (loop = 0; loop < TLP_LOOP; loop++) { + for (i = 0; i < TLP_LOOP; i++) { ctrl = cra_readl(pcie, RP_RXCPL_STATUS); if ((ctrl & RP_RXCPL_SOP) || (ctrl & RP_RXCPL_EOP) || sop) { reg0 = cra_readl(pcie, RP_RXCPL_REG0); reg1 = cra_readl(pcie, RP_RXCPL_REG1); - if (ctrl & RP_RXCPL_SOP) + if (ctrl & RP_RXCPL_SOP) { sop = true; + comp_status = TLP_COMP_STATUS(reg1); + } if (ctrl & RP_RXCPL_EOP) { + if (comp_status) + return PCIBIOS_DEVICE_NOT_FOUND; + if (value) *value = reg0; + return PCIBIOS_SUCCESSFUL; } } udelay(5); } - return -ENOENT; + return PCIBIOS_DEVICE_NOT_FOUND; } static void tlp_write_packet(struct altera_pcie *pcie, u32 *headers, @@ -233,7 +242,7 @@ static int tlp_cfg_dword_read(struct altera_pcie *pcie, u8 bus, u32 devfn, else headers[0] = TLP_CFG_DW0(TLP_FMTTYPE_CFGRD1); - headers[1] = TLP_CFG_DW1(TLP_REQ_ID(pcie->root_bus_nr, devfn), + headers[1] = TLP_CFG_DW1(TLP_REQ_ID(pcie->root_bus_nr, RP_DEVFN), TLP_READ_TAG, byte_en); headers[2] = TLP_CFG_DW2(bus, devfn, where); @@ -253,7 +262,7 @@ static int tlp_cfg_dword_write(struct altera_pcie *pcie, u8 bus, u32 devfn, else headers[0] = TLP_CFG_DW0(TLP_FMTTYPE_CFGWR1); - headers[1] = TLP_CFG_DW1(TLP_REQ_ID(pcie->root_bus_nr, devfn), + headers[1] = TLP_CFG_DW1(TLP_REQ_ID(pcie->root_bus_nr, RP_DEVFN), TLP_WRITE_TAG, byte_en); headers[2] = TLP_CFG_DW2(bus, devfn, where); @@ -458,7 +467,7 @@ static int altera_pcie_init_irq_domain(struct altera_pcie *pcie) struct device_node *node = dev->of_node; /* Setup INTx */ - pcie->irq_domain = irq_domain_add_linear(node, INTX_NUM, + pcie->irq_domain = irq_domain_add_linear(node, INTX_NUM + 1, &intx_domain_ops, pcie); if (!pcie->irq_domain) { dev_err(dev, "Failed to get a INTx IRQ domain\n"); diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 53e463244bb7..7eaa4c87fec7 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -54,7 +54,7 @@ static int pci_msi_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) struct irq_domain *domain; domain = pci_msi_get_domain(dev); - if (domain) + if (domain && irq_domain_is_hierarchy(domain)) return pci_msi_domain_alloc_irqs(domain, dev, nvec, type); return arch_setup_msi_irqs(dev, nvec, type); @@ -65,7 +65,7 @@ static void pci_msi_teardown_msi_irqs(struct pci_dev *dev) struct irq_domain *domain; domain = pci_msi_get_domain(dev); - if (domain) + if (domain && irq_domain_is_hierarchy(domain)) pci_msi_domain_free_irqs(domain, dev); else arch_teardown_msi_irqs(dev); diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index eec2f11809ff..ad2146a9ab2d 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -819,7 +819,7 @@ long vhost_vring_ioctl(struct vhost_dev *d, int ioctl, void __user *argp) BUILD_BUG_ON(__alignof__ *vq->used > VRING_USED_ALIGN_SIZE); if ((a.avail_user_addr & (VRING_AVAIL_ALIGN_SIZE - 1)) || (a.used_user_addr & (VRING_USED_ALIGN_SIZE - 1)) || - (a.log_guest_addr & (sizeof(u64) - 1))) { + (a.log_guest_addr & (VRING_USED_ALIGN_SIZE - 1))) { r = -EINVAL; break; } @@ -1369,7 +1369,7 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq, /* Grab the next descriptor number they're advertising, and increment * the index we've seen. */ if (unlikely(__get_user(ring_head, - &vq->avail->ring[last_avail_idx % vq->num]))) { + &vq->avail->ring[last_avail_idx & (vq->num - 1)]))) { vq_err(vq, "Failed to read head: idx %d address %p\n", last_avail_idx, &vq->avail->ring[last_avail_idx % vq->num]); @@ -1489,7 +1489,7 @@ static int __vhost_add_used_n(struct vhost_virtqueue *vq, u16 old, new; int start; - start = vq->last_used_idx % vq->num; + start = vq->last_used_idx & (vq->num - 1); used = vq->used->ring + start; if (count == 1) { if (__put_user(heads[0].id, &used->id)) { @@ -1531,7 +1531,7 @@ int vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads, { int start, n, r; - start = vq->last_used_idx % vq->num; + start = vq->last_used_idx & (vq->num - 1); n = vq->num - start; if (n < count) { r = __vhost_add_used_n(vq, heads, n); diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index b1877d73fa56..7062bb0975a5 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -412,6 +412,7 @@ static int virtio_init(void) static void __exit virtio_exit(void) { bus_unregister(&virtio_bus); + ida_destroy(&virtio_index_ida); } core_initcall(virtio_init); module_exit(virtio_exit); diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 096b857e7b75..ee663c458b20 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -80,6 +80,12 @@ struct vring_virtqueue { /* Last used index we've seen. */ u16 last_used_idx; + /* Last written value to avail->flags */ + u16 avail_flags_shadow; + + /* Last written value to avail->idx in guest byte order */ + u16 avail_idx_shadow; + /* How to notify other side. FIXME: commonalize hcalls! */ bool (*notify)(struct virtqueue *vq); @@ -109,7 +115,7 @@ static struct vring_desc *alloc_indirect(struct virtqueue *_vq, * otherwise virt_to_phys will give us bogus addresses in the * virtqueue. */ - gfp &= ~(__GFP_HIGHMEM | __GFP_HIGH); + gfp &= ~__GFP_HIGHMEM; desc = kmalloc(total_sg * sizeof(struct vring_desc), gfp); if (!desc) @@ -235,13 +241,14 @@ static inline int virtqueue_add(struct virtqueue *_vq, /* Put entry in available array (but don't update avail->idx until they * do sync). */ - avail = virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx) & (vq->vring.num - 1); + avail = vq->avail_idx_shadow & (vq->vring.num - 1); vq->vring.avail->ring[avail] = cpu_to_virtio16(_vq->vdev, head); /* Descriptors and available array need to be set before we expose the * new available array entries. */ virtio_wmb(vq->weak_barriers); - vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx) + 1); + vq->avail_idx_shadow++; + vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, vq->avail_idx_shadow); vq->num_added++; pr_debug("Added buffer head %i to %p\n", head, vq); @@ -354,8 +361,8 @@ bool virtqueue_kick_prepare(struct virtqueue *_vq) * event. */ virtio_mb(vq->weak_barriers); - old = virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx) - vq->num_added; - new = virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx); + old = vq->avail_idx_shadow - vq->num_added; + new = vq->avail_idx_shadow; vq->num_added = 0; #ifdef DEBUG @@ -510,7 +517,7 @@ void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len) /* If we expect an interrupt for the next entry, tell host * by writing event index and flush out the write before * the read in the next get_buf call. */ - if (!(vq->vring.avail->flags & cpu_to_virtio16(_vq->vdev, VRING_AVAIL_F_NO_INTERRUPT))) { + if (!(vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT)) { vring_used_event(&vq->vring) = cpu_to_virtio16(_vq->vdev, vq->last_used_idx); virtio_mb(vq->weak_barriers); } @@ -537,7 +544,11 @@ void virtqueue_disable_cb(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); - vq->vring.avail->flags |= cpu_to_virtio16(_vq->vdev, VRING_AVAIL_F_NO_INTERRUPT); + if (!(vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT)) { + vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT; + vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow); + } + } EXPORT_SYMBOL_GPL(virtqueue_disable_cb); @@ -565,7 +576,10 @@ unsigned virtqueue_enable_cb_prepare(struct virtqueue *_vq) /* Depending on the VIRTIO_RING_F_EVENT_IDX feature, we need to * either clear the flags bit or point the event index at the next * entry. Always do both to keep code simple. */ - vq->vring.avail->flags &= cpu_to_virtio16(_vq->vdev, ~VRING_AVAIL_F_NO_INTERRUPT); + if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) { + vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT; + vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow); + } vring_used_event(&vq->vring) = cpu_to_virtio16(_vq->vdev, last_used_idx = vq->last_used_idx); END_USE(vq); return last_used_idx; @@ -633,9 +647,12 @@ bool virtqueue_enable_cb_delayed(struct virtqueue *_vq) /* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to * either clear the flags bit or point the event index at the next * entry. Always do both to keep code simple. */ - vq->vring.avail->flags &= cpu_to_virtio16(_vq->vdev, ~VRING_AVAIL_F_NO_INTERRUPT); + if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) { + vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT; + vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow); + } /* TODO: tune this threshold */ - bufs = (u16)(virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx) - vq->last_used_idx) * 3 / 4; + bufs = (u16)(vq->avail_idx_shadow - vq->last_used_idx) * 3 / 4; vring_used_event(&vq->vring) = cpu_to_virtio16(_vq->vdev, vq->last_used_idx + bufs); virtio_mb(vq->weak_barriers); if (unlikely((u16)(virtio16_to_cpu(_vq->vdev, vq->vring.used->idx) - vq->last_used_idx) > bufs)) { @@ -670,7 +687,8 @@ void *virtqueue_detach_unused_buf(struct virtqueue *_vq) /* detach_buf clears data, so grab it now. */ buf = vq->data[i]; detach_buf(vq, i); - vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx) - 1); + vq->avail_idx_shadow--; + vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, vq->avail_idx_shadow); END_USE(vq); return buf; } @@ -735,6 +753,8 @@ struct virtqueue *vring_new_virtqueue(unsigned int index, vq->weak_barriers = weak_barriers; vq->broken = false; vq->last_used_idx = 0; + vq->avail_flags_shadow = 0; + vq->avail_idx_shadow = 0; vq->num_added = 0; list_add_tail(&vq->vq.list, &vdev->vqs); #ifdef DEBUG @@ -746,8 +766,10 @@ struct virtqueue *vring_new_virtqueue(unsigned int index, vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX); /* No callback? Tell other side not to bother us. */ - if (!callback) - vq->vring.avail->flags |= cpu_to_virtio16(vdev, VRING_AVAIL_F_NO_INTERRUPT); + if (!callback) { + vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT; + vq->vring.avail->flags = cpu_to_virtio16(vdev, vq->avail_flags_shadow); + } /* Put everything in free lists. */ vq->free_head = 0; diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c index af06830bfc00..1a0835073663 100644 --- a/fs/ext4/crypto.c +++ b/fs/ext4/crypto.c @@ -389,7 +389,7 @@ int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex) struct ext4_crypto_ctx *ctx; struct page *ciphertext_page = NULL; struct bio *bio; - ext4_lblk_t lblk = ex->ee_block; + ext4_lblk_t lblk = le32_to_cpu(ex->ee_block); ext4_fsblk_t pblk = ext4_ext_pblock(ex); unsigned int len = ext4_ext_get_actual_len(ex); int ret, err = 0; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 750063f7a50c..cc7ca4e87144 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -26,6 +26,7 @@ #include <linux/seqlock.h> #include <linux/mutex.h> #include <linux/timer.h> +#include <linux/version.h> #include <linux/wait.h> #include <linux/blockgroup_lock.h> #include <linux/percpu_counter.h> @@ -727,19 +728,55 @@ struct move_extent { <= (EXT4_GOOD_OLD_INODE_SIZE + \ (einode)->i_extra_isize)) \ +/* + * We use an encoding that preserves the times for extra epoch "00": + * + * extra msb of adjust for signed + * epoch 32-bit 32-bit tv_sec to + * bits time decoded 64-bit tv_sec 64-bit tv_sec valid time range + * 0 0 1 -0x80000000..-0x00000001 0x000000000 1901-12-13..1969-12-31 + * 0 0 0 0x000000000..0x07fffffff 0x000000000 1970-01-01..2038-01-19 + * 0 1 1 0x080000000..0x0ffffffff 0x100000000 2038-01-19..2106-02-07 + * 0 1 0 0x100000000..0x17fffffff 0x100000000 2106-02-07..2174-02-25 + * 1 0 1 0x180000000..0x1ffffffff 0x200000000 2174-02-25..2242-03-16 + * 1 0 0 0x200000000..0x27fffffff 0x200000000 2242-03-16..2310-04-04 + * 1 1 1 0x280000000..0x2ffffffff 0x300000000 2310-04-04..2378-04-22 + * 1 1 0 0x300000000..0x37fffffff 0x300000000 2378-04-22..2446-05-10 + * + * Note that previous versions of the kernel on 64-bit systems would + * incorrectly use extra epoch bits 1,1 for dates between 1901 and + * 1970. e2fsck will correct this, assuming that it is run on the + * affected filesystem before 2242. + */ + static inline __le32 ext4_encode_extra_time(struct timespec *time) { - return cpu_to_le32((sizeof(time->tv_sec) > 4 ? - (time->tv_sec >> 32) & EXT4_EPOCH_MASK : 0) | - ((time->tv_nsec << EXT4_EPOCH_BITS) & EXT4_NSEC_MASK)); + u32 extra = sizeof(time->tv_sec) > 4 ? + ((time->tv_sec - (s32)time->tv_sec) >> 32) & EXT4_EPOCH_MASK : 0; + return cpu_to_le32(extra | (time->tv_nsec << EXT4_EPOCH_BITS)); } static inline void ext4_decode_extra_time(struct timespec *time, __le32 extra) { - if (sizeof(time->tv_sec) > 4) - time->tv_sec |= (__u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK) - << 32; - time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS; + if (unlikely(sizeof(time->tv_sec) > 4 && + (extra & cpu_to_le32(EXT4_EPOCH_MASK)))) { +#if LINUX_VERSION_CODE < KERNEL_VERSION(4,20,0) + /* Handle legacy encoding of pre-1970 dates with epoch + * bits 1,1. We assume that by kernel version 4.20, + * everyone will have run fsck over the affected + * filesystems to correct the problem. (This + * backwards compatibility may be removed before this + * time, at the discretion of the ext4 developers.) + */ + u64 extra_bits = le32_to_cpu(extra) & EXT4_EPOCH_MASK; + if (extra_bits == 3 && ((time->tv_sec) & 0x80000000) != 0) + extra_bits = 0; + time->tv_sec += extra_bits << 32; +#else + time->tv_sec += (u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK) << 32; +#endif + } + time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS; } #define EXT4_INODE_SET_XTIME(xtime, inode, raw_inode) \ diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c index abe2401ce405..e8e7af62ac95 100644 --- a/fs/ext4/symlink.c +++ b/fs/ext4/symlink.c @@ -52,7 +52,7 @@ static const char *ext4_encrypted_follow_link(struct dentry *dentry, void **cook /* Symlink is encrypted */ sd = (struct ext4_encrypted_symlink_data *)caddr; cstr.name = sd->encrypted_path; - cstr.len = le32_to_cpu(sd->len); + cstr.len = le16_to_cpu(sd->len); if ((cstr.len + sizeof(struct ext4_encrypted_symlink_data) - 1) > max_size) { diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index 1b57c72f4a00..1420a3c614af 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -358,7 +358,7 @@ static int name##_open(struct inode *inode, struct file *file) \ return single_open(file, ext4_seq_##name##_show, PDE_DATA(inode)); \ } \ \ -const struct file_operations ext4_seq_##name##_fops = { \ +static const struct file_operations ext4_seq_##name##_fops = { \ .owner = THIS_MODULE, \ .open = name##_open, \ .read = seq_read, \ diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 89463eee6791..ca181e81c765 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1009,7 +1009,8 @@ out: } /* Fast check whether buffer is already attached to the required transaction */ -static bool jbd2_write_access_granted(handle_t *handle, struct buffer_head *bh) +static bool jbd2_write_access_granted(handle_t *handle, struct buffer_head *bh, + bool undo) { struct journal_head *jh; bool ret = false; @@ -1036,6 +1037,9 @@ static bool jbd2_write_access_granted(handle_t *handle, struct buffer_head *bh) jh = READ_ONCE(bh->b_private); if (!jh) goto out; + /* For undo access buffer must have data copied */ + if (undo && !jh->b_committed_data) + goto out; if (jh->b_transaction != handle->h_transaction && jh->b_next_transaction != handle->h_transaction) goto out; @@ -1073,7 +1077,7 @@ int jbd2_journal_get_write_access(handle_t *handle, struct buffer_head *bh) struct journal_head *jh; int rc; - if (jbd2_write_access_granted(handle, bh)) + if (jbd2_write_access_granted(handle, bh, false)) return 0; jh = jbd2_journal_add_journal_head(bh); @@ -1210,7 +1214,7 @@ int jbd2_journal_get_undo_access(handle_t *handle, struct buffer_head *bh) char *committed_data = NULL; JBUFFER_TRACE(jh, "entry"); - if (jbd2_write_access_granted(handle, bh)) + if (jbd2_write_access_granted(handle, bh, true)) return 0; jh = jbd2_journal_add_journal_head(bh); @@ -2152,6 +2156,7 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh, if (!buffer_dirty(bh)) { /* bdflush has written it. We can drop it now */ + __jbd2_journal_remove_checkpoint(jh); goto zap_buffer; } @@ -2181,6 +2186,7 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh, /* The orphan record's transaction has * committed. We can cleanse this buffer */ clear_buffer_jbddirty(bh); + __jbd2_journal_remove_checkpoint(jh); goto zap_buffer; } } diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index db284bff29dc..9dbb739cafa0 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -5,7 +5,7 @@ * Copyright 2001 Red Hat, Inc. * Based on code from mm/memory.c Copyright Linus Torvalds and others. * - * Copyright 2011 Red Hat, Inc., Peter Zijlstra <[email protected]> + * Copyright 2011 Red Hat, Inc., Peter Zijlstra * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 60d44b26276d..06b77f9dd3f2 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -90,7 +90,6 @@ enum { */ struct cgroup_file { /* do not access any fields from outside cgroup core */ - struct list_head node; /* anchored at css->files */ struct kernfs_node *kn; }; @@ -134,9 +133,6 @@ struct cgroup_subsys_state { */ u64 serial_nr; - /* all cgroup_files associated with this css */ - struct list_head files; - /* percpu_ref killing and RCU release */ struct rcu_head rcu_head; struct work_struct destroy_work; @@ -426,12 +422,9 @@ struct cgroup_subsys { void (*css_reset)(struct cgroup_subsys_state *css); void (*css_e_css_changed)(struct cgroup_subsys_state *css); - int (*can_attach)(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset); - void (*cancel_attach)(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset); - void (*attach)(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset); + int (*can_attach)(struct cgroup_taskset *tset); + void (*cancel_attach)(struct cgroup_taskset *tset); + void (*attach)(struct cgroup_taskset *tset); int (*can_fork)(struct task_struct *task, void **priv_p); void (*cancel_fork)(struct task_struct *task, void *priv); void (*fork)(struct task_struct *task, void *priv); diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 22e3754f89c5..cb91b44f5f78 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -88,6 +88,7 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); int cgroup_rm_cftypes(struct cftype *cfts); +void cgroup_file_notify(struct cgroup_file *cfile); char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen); int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry); @@ -119,8 +120,10 @@ struct cgroup_subsys_state *css_rightmost_descendant(struct cgroup_subsys_state struct cgroup_subsys_state *css_next_descendant_post(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *css); -struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset); -struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset); +struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset, + struct cgroup_subsys_state **dst_cssp); +struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset, + struct cgroup_subsys_state **dst_cssp); void css_task_iter_start(struct cgroup_subsys_state *css, struct css_task_iter *it); @@ -235,30 +238,39 @@ void css_task_iter_end(struct css_task_iter *it); /** * cgroup_taskset_for_each - iterate cgroup_taskset * @task: the loop cursor + * @dst_css: the destination css * @tset: taskset to iterate * * @tset may contain multiple tasks and they may belong to multiple - * processes. When there are multiple tasks in @tset, if a task of a - * process is in @tset, all tasks of the process are in @tset. Also, all - * are guaranteed to share the same source and destination csses. + * processes. + * + * On the v2 hierarchy, there may be tasks from multiple processes and they + * may not share the source or destination csses. + * + * On traditional hierarchies, when there are multiple tasks in @tset, if a + * task of a process is in @tset, all tasks of the process are in @tset. + * Also, all are guaranteed to share the same source and destination csses. * * Iteration is not in any specific order. */ -#define cgroup_taskset_for_each(task, tset) \ - for ((task) = cgroup_taskset_first((tset)); (task); \ - (task) = cgroup_taskset_next((tset))) +#define cgroup_taskset_for_each(task, dst_css, tset) \ + for ((task) = cgroup_taskset_first((tset), &(dst_css)); \ + (task); \ + (task) = cgroup_taskset_next((tset), &(dst_css))) /** * cgroup_taskset_for_each_leader - iterate group leaders in a cgroup_taskset * @leader: the loop cursor + * @dst_css: the destination css * @tset: takset to iterate * * Iterate threadgroup leaders of @tset. For single-task migrations, @tset * may not contain any. */ -#define cgroup_taskset_for_each_leader(leader, tset) \ - for ((leader) = cgroup_taskset_first((tset)); (leader); \ - (leader) = cgroup_taskset_next((tset))) \ +#define cgroup_taskset_for_each_leader(leader, dst_css, tset) \ + for ((leader) = cgroup_taskset_first((tset), &(dst_css)); \ + (leader); \ + (leader) = cgroup_taskset_next((tset), &(dst_css))) \ if ((leader) != (leader)->group_leader) \ ; \ else @@ -516,19 +528,6 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp) pr_cont_kernfs_path(cgrp->kn); } -/** - * cgroup_file_notify - generate a file modified event for a cgroup_file - * @cfile: target cgroup_file - * - * @cfile must have been obtained by setting cftype->file_offset. - */ -static inline void cgroup_file_notify(struct cgroup_file *cfile) -{ - /* might not have been created due to one of the CFTYPE selector flags */ - if (cfile->kn) - kernfs_notify(cfile->kn); -} - #else /* !CONFIG_CGROUPS */ struct cgroup_subsys_state; diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 8dde55974f18..0536524bb9eb 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -5,7 +5,7 @@ * Jump label support * * Copyright (C) 2009-2012 Jason Baron <[email protected]> - * Copyright (C) 2011-2012 Peter Zijlstra <[email protected]> + * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra * * DEPRECATED API: * diff --git a/include/linux/libata.h b/include/linux/libata.h index 83577f8fd15b..600c1e0626a5 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -210,6 +210,7 @@ enum { ATA_FLAG_SLAVE_POSS = (1 << 0), /* host supports slave dev */ /* (doesn't imply presence) */ ATA_FLAG_SATA = (1 << 1), + ATA_FLAG_NO_LOG_PAGE = (1 << 5), /* do not issue log page read */ ATA_FLAG_NO_ATAPI = (1 << 6), /* No ATAPI support */ ATA_FLAG_PIO_DMA = (1 << 7), /* PIO cmds via DMA */ ATA_FLAG_PIO_LBA48 = (1 << 8), /* Host DMA engine is LBA28 only */ diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 70400dc7660f..c57e424d914b 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -2,7 +2,7 @@ * Runtime locking correctness validator * * Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar <[email protected]> - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <[email protected]> + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * see Documentation/locking/lockdep-design.txt for more details. */ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index d841d33bcdc9..f9828a48f16a 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -697,9 +697,11 @@ struct perf_cgroup { * if there is no cgroup event for the current CPU context. */ static inline struct perf_cgroup * -perf_cgroup_from_task(struct task_struct *task) +perf_cgroup_from_task(struct task_struct *task, struct perf_event_context *ctx) { - return container_of(task_css(task, perf_event_cgrp_id), + return container_of(task_css_check(task, perf_event_cgrp_id, + ctx ? lockdep_is_held(&ctx->lock) + : true), struct perf_cgroup, css); } #endif /* CONFIG_CGROUP_PERF */ diff --git a/include/linux/proportions.h b/include/linux/proportions.h index 5440f64d2942..21221338ad18 100644 --- a/include/linux/proportions.h +++ b/include/linux/proportions.h @@ -1,7 +1,7 @@ /* * FLoating proportions * - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <[email protected]> + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * This file contains the public data structure and API definitions. */ diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index 0bdc72f36905..4a29c75b146e 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -21,7 +21,7 @@ * Authors: * Srikar Dronamraju * Jim Keniston - * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra <[email protected]> + * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra */ #include <linux/errno.h> diff --git a/kernel/cgroup.c b/kernel/cgroup.c index f1603c153890..470f6536b9e8 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -98,6 +98,12 @@ static DEFINE_SPINLOCK(css_set_lock); static DEFINE_SPINLOCK(cgroup_idr_lock); /* + * Protects cgroup_file->kn for !self csses. It synchronizes notifications + * against file removal/re-creation across css hiding. + */ +static DEFINE_SPINLOCK(cgroup_file_kn_lock); + +/* * Protects cgroup_subsys->release_agent_path. Modifying it also requires * cgroup_mutex. Reading requires either cgroup_mutex or this spinlock. */ @@ -754,9 +760,11 @@ static void put_css_set_locked(struct css_set *cset) if (!atomic_dec_and_test(&cset->refcount)) return; - /* This css_set is dead. unlink it and release cgroup refcounts */ - for_each_subsys(ss, ssid) + /* This css_set is dead. unlink it and release cgroup and css refs */ + for_each_subsys(ss, ssid) { list_del(&cset->e_cset_node[ssid]); + css_put(cset->subsys[ssid]); + } hash_del(&cset->hlist); css_set_count--; @@ -1056,9 +1064,13 @@ static struct css_set *find_css_set(struct css_set *old_cset, key = css_set_hash(cset->subsys); hash_add(css_set_table, &cset->hlist, key); - for_each_subsys(ss, ssid) + for_each_subsys(ss, ssid) { + struct cgroup_subsys_state *css = cset->subsys[ssid]; + list_add_tail(&cset->e_cset_node[ssid], - &cset->subsys[ssid]->cgroup->e_csets[ssid]); + &css->cgroup->e_csets[ssid]); + css_get(css); + } spin_unlock_bh(&css_set_lock); @@ -1393,6 +1405,16 @@ static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft) char name[CGROUP_FILE_NAME_MAX]; lockdep_assert_held(&cgroup_mutex); + + if (cft->file_offset) { + struct cgroup_subsys_state *css = cgroup_css(cgrp, cft->ss); + struct cgroup_file *cfile = (void *)css + cft->file_offset; + + spin_lock_irq(&cgroup_file_kn_lock); + cfile->kn = NULL; + spin_unlock_irq(&cgroup_file_kn_lock); + } + kernfs_remove_by_name(cgrp->kn, cgroup_file_name(cgrp, cft, name)); } @@ -1856,7 +1878,6 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp) INIT_LIST_HEAD(&cgrp->self.sibling); INIT_LIST_HEAD(&cgrp->self.children); - INIT_LIST_HEAD(&cgrp->self.files); INIT_LIST_HEAD(&cgrp->cset_links); INIT_LIST_HEAD(&cgrp->pidlists); mutex_init(&cgrp->pidlist_mutex); @@ -2216,6 +2237,9 @@ struct cgroup_taskset { struct list_head src_csets; struct list_head dst_csets; + /* the subsys currently being processed */ + int ssid; + /* * Fields for cgroup_taskset_*() iteration. * @@ -2278,25 +2302,29 @@ static void cgroup_taskset_add(struct task_struct *task, /** * cgroup_taskset_first - reset taskset and return the first task * @tset: taskset of interest + * @dst_cssp: output variable for the destination css * * @tset iteration is initialized and the first task is returned. */ -struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset) +struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset, + struct cgroup_subsys_state **dst_cssp) { tset->cur_cset = list_first_entry(tset->csets, struct css_set, mg_node); tset->cur_task = NULL; - return cgroup_taskset_next(tset); + return cgroup_taskset_next(tset, dst_cssp); } /** * cgroup_taskset_next - iterate to the next task in taskset * @tset: taskset of interest + * @dst_cssp: output variable for the destination css * * Return the next task in @tset. Iteration must have been initialized * with cgroup_taskset_first(). */ -struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset) +struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset, + struct cgroup_subsys_state **dst_cssp) { struct css_set *cset = tset->cur_cset; struct task_struct *task = tset->cur_task; @@ -2311,6 +2339,18 @@ struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset) if (&task->cg_list != &cset->mg_tasks) { tset->cur_cset = cset; tset->cur_task = task; + + /* + * This function may be called both before and + * after cgroup_taskset_migrate(). The two cases + * can be distinguished by looking at whether @cset + * has its ->mg_dst_cset set. + */ + if (cset->mg_dst_cset) + *dst_cssp = cset->mg_dst_cset->subsys[tset->ssid]; + else + *dst_cssp = cset->subsys[tset->ssid]; + return task; } @@ -2346,7 +2386,8 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset, /* check that we can legitimately attach to the cgroup */ for_each_e_css(css, i, dst_cgrp) { if (css->ss->can_attach) { - ret = css->ss->can_attach(css, tset); + tset->ssid = i; + ret = css->ss->can_attach(tset); if (ret) { failed_css = css; goto out_cancel_attach; @@ -2379,9 +2420,12 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset, */ tset->csets = &tset->dst_csets; - for_each_e_css(css, i, dst_cgrp) - if (css->ss->attach) - css->ss->attach(css, tset); + for_each_e_css(css, i, dst_cgrp) { + if (css->ss->attach) { + tset->ssid = i; + css->ss->attach(tset); + } + } ret = 0; goto out_release_tset; @@ -2390,8 +2434,10 @@ out_cancel_attach: for_each_e_css(css, i, dst_cgrp) { if (css == failed_css) break; - if (css->ss->cancel_attach) - css->ss->cancel_attach(css, tset); + if (css->ss->cancel_attach) { + tset->ssid = i; + css->ss->cancel_attach(tset); + } } out_release_tset: spin_lock_bh(&css_set_lock); @@ -3313,9 +3359,9 @@ static int cgroup_add_file(struct cgroup_subsys_state *css, struct cgroup *cgrp, if (cft->file_offset) { struct cgroup_file *cfile = (void *)css + cft->file_offset; - kernfs_get(kn); + spin_lock_irq(&cgroup_file_kn_lock); cfile->kn = kn; - list_add(&cfile->node, &css->files); + spin_unlock_irq(&cgroup_file_kn_lock); } return 0; @@ -3553,6 +3599,22 @@ int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) } /** + * cgroup_file_notify - generate a file modified event for a cgroup_file + * @cfile: target cgroup_file + * + * @cfile must have been obtained by setting cftype->file_offset. + */ +void cgroup_file_notify(struct cgroup_file *cfile) +{ + unsigned long flags; + + spin_lock_irqsave(&cgroup_file_kn_lock, flags); + if (cfile->kn) + kernfs_notify(cfile->kn); + spin_unlock_irqrestore(&cgroup_file_kn_lock, flags); +} + +/** * cgroup_task_count - count the number of tasks in a cgroup. * @cgrp: the cgroup in question * @@ -4613,13 +4675,9 @@ static void css_free_work_fn(struct work_struct *work) container_of(work, struct cgroup_subsys_state, destroy_work); struct cgroup_subsys *ss = css->ss; struct cgroup *cgrp = css->cgroup; - struct cgroup_file *cfile; percpu_ref_exit(&css->refcnt); - list_for_each_entry(cfile, &css->files, node) - kernfs_put(cfile->kn); - if (ss) { /* css free path */ int id = css->id; @@ -4724,7 +4782,6 @@ static void init_and_link_css(struct cgroup_subsys_state *css, css->ss = ss; INIT_LIST_HEAD(&css->sibling); INIT_LIST_HEAD(&css->children); - INIT_LIST_HEAD(&css->files); css->serial_nr = css_serial_nr_next++; if (cgroup_parent(cgrp)) { diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index f1b30ad5dc6d..2d3df82c54f2 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -155,12 +155,10 @@ static void freezer_css_free(struct cgroup_subsys_state *css) * @freezer->lock. freezer_attach() makes the new tasks conform to the * current state and all following state changes can see the new tasks. */ -static void freezer_attach(struct cgroup_subsys_state *new_css, - struct cgroup_taskset *tset) +static void freezer_attach(struct cgroup_taskset *tset) { - struct freezer *freezer = css_freezer(new_css); struct task_struct *task; - bool clear_frozen = false; + struct cgroup_subsys_state *new_css; mutex_lock(&freezer_mutex); @@ -174,22 +172,21 @@ static void freezer_attach(struct cgroup_subsys_state *new_css, * current state before executing the following - !frozen tasks may * be visible in a FROZEN cgroup and frozen tasks in a THAWED one. */ - cgroup_taskset_for_each(task, tset) { + cgroup_taskset_for_each(task, new_css, tset) { + struct freezer *freezer = css_freezer(new_css); + if (!(freezer->state & CGROUP_FREEZING)) { __thaw_task(task); } else { freeze_task(task); - freezer->state &= ~CGROUP_FROZEN; - clear_frozen = true; + /* clear FROZEN and propagate upwards */ + while (freezer && (freezer->state & CGROUP_FROZEN)) { + freezer->state &= ~CGROUP_FROZEN; + freezer = parent_freezer(freezer); + } } } - /* propagate FROZEN clearing upwards */ - while (clear_frozen && (freezer = parent_freezer(freezer))) { - freezer->state &= ~CGROUP_FROZEN; - clear_frozen = freezer->state & CGROUP_FREEZING; - } - mutex_unlock(&freezer_mutex); } diff --git a/kernel/cgroup_pids.c b/kernel/cgroup_pids.c index cdd8df4e991c..b50d5a167fda 100644 --- a/kernel/cgroup_pids.c +++ b/kernel/cgroup_pids.c @@ -106,7 +106,7 @@ static void pids_uncharge(struct pids_cgroup *pids, int num) { struct pids_cgroup *p; - for (p = pids; p; p = parent_pids(p)) + for (p = pids; parent_pids(p); p = parent_pids(p)) pids_cancel(p, num); } @@ -123,7 +123,7 @@ static void pids_charge(struct pids_cgroup *pids, int num) { struct pids_cgroup *p; - for (p = pids; p; p = parent_pids(p)) + for (p = pids; parent_pids(p); p = parent_pids(p)) atomic64_add(num, &p->counter); } @@ -140,7 +140,7 @@ static int pids_try_charge(struct pids_cgroup *pids, int num) { struct pids_cgroup *p, *q; - for (p = pids; p; p = parent_pids(p)) { + for (p = pids; parent_pids(p); p = parent_pids(p)) { int64_t new = atomic64_add_return(num, &p->counter); /* @@ -162,13 +162,13 @@ revert: return -EAGAIN; } -static int pids_can_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static int pids_can_attach(struct cgroup_taskset *tset) { - struct pids_cgroup *pids = css_pids(css); struct task_struct *task; + struct cgroup_subsys_state *dst_css; - cgroup_taskset_for_each(task, tset) { + cgroup_taskset_for_each(task, dst_css, tset) { + struct pids_cgroup *pids = css_pids(dst_css); struct cgroup_subsys_state *old_css; struct pids_cgroup *old_pids; @@ -187,13 +187,13 @@ static int pids_can_attach(struct cgroup_subsys_state *css, return 0; } -static void pids_cancel_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void pids_cancel_attach(struct cgroup_taskset *tset) { - struct pids_cgroup *pids = css_pids(css); struct task_struct *task; + struct cgroup_subsys_state *dst_css; - cgroup_taskset_for_each(task, tset) { + cgroup_taskset_for_each(task, dst_css, tset) { + struct pids_cgroup *pids = css_pids(dst_css); struct cgroup_subsys_state *old_css; struct pids_cgroup *old_pids; @@ -205,65 +205,28 @@ static void pids_cancel_attach(struct cgroup_subsys_state *css, } } +/* + * task_css_check(true) in pids_can_fork() and pids_cancel_fork() relies + * on threadgroup_change_begin() held by the copy_process(). + */ static int pids_can_fork(struct task_struct *task, void **priv_p) { struct cgroup_subsys_state *css; struct pids_cgroup *pids; - int err; - /* - * Use the "current" task_css for the pids subsystem as the tentative - * css. It is possible we will charge the wrong hierarchy, in which - * case we will forcefully revert/reapply the charge on the right - * hierarchy after it is committed to the task proper. - */ - css = task_get_css(current, pids_cgrp_id); + css = task_css_check(current, pids_cgrp_id, true); pids = css_pids(css); - - err = pids_try_charge(pids, 1); - if (err) - goto err_css_put; - - *priv_p = css; - return 0; - -err_css_put: - css_put(css); - return err; + return pids_try_charge(pids, 1); } static void pids_cancel_fork(struct task_struct *task, void *priv) { - struct cgroup_subsys_state *css = priv; - struct pids_cgroup *pids = css_pids(css); - - pids_uncharge(pids, 1); - css_put(css); -} - -static void pids_fork(struct task_struct *task, void *priv) -{ struct cgroup_subsys_state *css; - struct cgroup_subsys_state *old_css = priv; struct pids_cgroup *pids; - struct pids_cgroup *old_pids = css_pids(old_css); - css = task_get_css(task, pids_cgrp_id); + css = task_css_check(current, pids_cgrp_id, true); pids = css_pids(css); - - /* - * If the association has changed, we have to revert and reapply the - * charge/uncharge on the wrong hierarchy to the current one. Since - * the association can only change due to an organisation event, its - * okay for us to ignore the limit in this case. - */ - if (pids != old_pids) { - pids_uncharge(old_pids, 1); - pids_charge(pids, 1); - } - - css_put(css); - css_put(old_css); + pids_uncharge(pids, 1); } static void pids_free(struct task_struct *task) @@ -335,6 +298,7 @@ static struct cftype pids_files[] = { { .name = "current", .read_s64 = pids_current_read, + .flags = CFTYPE_NOT_ON_ROOT, }, { } /* terminate */ }; @@ -346,7 +310,6 @@ struct cgroup_subsys pids_cgrp_subsys = { .cancel_attach = pids_cancel_attach, .can_fork = pids_can_fork, .cancel_fork = pids_cancel_fork, - .fork = pids_fork, .free = pids_free, .legacy_cftypes = pids_files, .dfl_cftypes = pids_files, diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 10ae73611d80..02a8ea5c9963 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1429,15 +1429,16 @@ static int fmeter_getrate(struct fmeter *fmp) static struct cpuset *cpuset_attach_old_cs; /* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */ -static int cpuset_can_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static int cpuset_can_attach(struct cgroup_taskset *tset) { - struct cpuset *cs = css_cs(css); + struct cgroup_subsys_state *css; + struct cpuset *cs; struct task_struct *task; int ret; /* used later by cpuset_attach() */ - cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset)); + cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset, &css)); + cs = css_cs(css); mutex_lock(&cpuset_mutex); @@ -1447,7 +1448,7 @@ static int cpuset_can_attach(struct cgroup_subsys_state *css, (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))) goto out_unlock; - cgroup_taskset_for_each(task, tset) { + cgroup_taskset_for_each(task, css, tset) { ret = task_can_attach(task, cs->cpus_allowed); if (ret) goto out_unlock; @@ -1467,9 +1468,14 @@ out_unlock: return ret; } -static void cpuset_cancel_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void cpuset_cancel_attach(struct cgroup_taskset *tset) { + struct cgroup_subsys_state *css; + struct cpuset *cs; + + cgroup_taskset_first(tset, &css); + cs = css_cs(css); + mutex_lock(&cpuset_mutex); css_cs(css)->attach_in_progress--; mutex_unlock(&cpuset_mutex); @@ -1482,16 +1488,19 @@ static void cpuset_cancel_attach(struct cgroup_subsys_state *css, */ static cpumask_var_t cpus_attach; -static void cpuset_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void cpuset_attach(struct cgroup_taskset *tset) { /* static buf protected by cpuset_mutex */ static nodemask_t cpuset_attach_nodemask_to; struct task_struct *task; struct task_struct *leader; - struct cpuset *cs = css_cs(css); + struct cgroup_subsys_state *css; + struct cpuset *cs; struct cpuset *oldcs = cpuset_attach_old_cs; + cgroup_taskset_first(tset, &css); + cs = css_cs(css); + mutex_lock(&cpuset_mutex); /* prepare for attach */ @@ -1502,7 +1511,7 @@ static void cpuset_attach(struct cgroup_subsys_state *css, guarantee_online_mems(cs, &cpuset_attach_nodemask_to); - cgroup_taskset_for_each(task, tset) { + cgroup_taskset_for_each(task, css, tset) { /* * can_attach beforehand should guarantee that this doesn't * fail. TODO: have a better way to handle failure here @@ -1518,7 +1527,7 @@ static void cpuset_attach(struct cgroup_subsys_state *css, * sleep and should be moved outside migration path proper. */ cpuset_attach_nodemask_to = cs->effective_mems; - cgroup_taskset_for_each_leader(leader, tset) { + cgroup_taskset_for_each_leader(leader, css, tset) { struct mm_struct *mm = get_task_mm(leader); if (mm) { diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c index d659487254d5..9c418002b8c1 100644 --- a/kernel/events/callchain.c +++ b/kernel/events/callchain.c @@ -3,7 +3,7 @@ * * Copyright (C) 2008 Thomas Gleixner <[email protected]> * Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar - * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra <[email protected]> + * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra * Copyright � 2009 Paul Mackerras, IBM Corp. <[email protected]> * * For licensing details see kernel-base/COPYING diff --git a/kernel/events/core.c b/kernel/events/core.c index 36babfd20648..ef2d6ea10736 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3,7 +3,7 @@ * * Copyright (C) 2008 Thomas Gleixner <[email protected]> * Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar - * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra <[email protected]> + * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra * Copyright © 2009 Paul Mackerras, IBM Corp. <[email protected]> * * For licensing details see kernel-base/COPYING @@ -435,7 +435,7 @@ static inline void update_cgrp_time_from_event(struct perf_event *event) if (!is_cgroup_event(event)) return; - cgrp = perf_cgroup_from_task(current); + cgrp = perf_cgroup_from_task(current, event->ctx); /* * Do not update time when cgroup is not active */ @@ -458,7 +458,7 @@ perf_cgroup_set_timestamp(struct task_struct *task, if (!task || !ctx->nr_cgroups) return; - cgrp = perf_cgroup_from_task(task); + cgrp = perf_cgroup_from_task(task, ctx); info = this_cpu_ptr(cgrp->info); info->timestamp = ctx->timestamp; } @@ -489,7 +489,6 @@ static void perf_cgroup_switch(struct task_struct *task, int mode) * we reschedule only in the presence of cgroup * constrained events. */ - rcu_read_lock(); list_for_each_entry_rcu(pmu, &pmus, entry) { cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); @@ -522,8 +521,10 @@ static void perf_cgroup_switch(struct task_struct *task, int mode) * set cgrp before ctxsw in to allow * event_filter_match() to not have to pass * task around + * we pass the cpuctx->ctx to perf_cgroup_from_task() + * because cgorup events are only per-cpu */ - cpuctx->cgrp = perf_cgroup_from_task(task); + cpuctx->cgrp = perf_cgroup_from_task(task, &cpuctx->ctx); cpu_ctx_sched_in(cpuctx, EVENT_ALL, task); } perf_pmu_enable(cpuctx->ctx.pmu); @@ -531,8 +532,6 @@ static void perf_cgroup_switch(struct task_struct *task, int mode) } } - rcu_read_unlock(); - local_irq_restore(flags); } @@ -542,17 +541,20 @@ static inline void perf_cgroup_sched_out(struct task_struct *task, struct perf_cgroup *cgrp1; struct perf_cgroup *cgrp2 = NULL; + rcu_read_lock(); /* * we come here when we know perf_cgroup_events > 0 + * we do not need to pass the ctx here because we know + * we are holding the rcu lock */ - cgrp1 = perf_cgroup_from_task(task); + cgrp1 = perf_cgroup_from_task(task, NULL); /* * next is NULL when called from perf_event_enable_on_exec() * that will systematically cause a cgroup_switch() */ if (next) - cgrp2 = perf_cgroup_from_task(next); + cgrp2 = perf_cgroup_from_task(next, NULL); /* * only schedule out current cgroup events if we know @@ -561,6 +563,8 @@ static inline void perf_cgroup_sched_out(struct task_struct *task, */ if (cgrp1 != cgrp2) perf_cgroup_switch(task, PERF_CGROUP_SWOUT); + + rcu_read_unlock(); } static inline void perf_cgroup_sched_in(struct task_struct *prev, @@ -569,13 +573,16 @@ static inline void perf_cgroup_sched_in(struct task_struct *prev, struct perf_cgroup *cgrp1; struct perf_cgroup *cgrp2 = NULL; + rcu_read_lock(); /* * we come here when we know perf_cgroup_events > 0 + * we do not need to pass the ctx here because we know + * we are holding the rcu lock */ - cgrp1 = perf_cgroup_from_task(task); + cgrp1 = perf_cgroup_from_task(task, NULL); /* prev can never be NULL */ - cgrp2 = perf_cgroup_from_task(prev); + cgrp2 = perf_cgroup_from_task(prev, NULL); /* * only need to schedule in cgroup events if we are changing @@ -584,6 +591,8 @@ static inline void perf_cgroup_sched_in(struct task_struct *prev, */ if (cgrp1 != cgrp2) perf_cgroup_switch(task, PERF_CGROUP_SWIN); + + rcu_read_unlock(); } static inline int perf_cgroup_connect(int fd, struct perf_event *event, @@ -4216,7 +4225,14 @@ retry: goto retry; } - __perf_event_period(&pe); + if (event->attr.freq) { + event->attr.sample_freq = value; + } else { + event->attr.sample_period = value; + event->hw.sample_period = value; + } + + local64_set(&event->hw.period_left, 0); raw_spin_unlock_irq(&ctx->lock); return 0; @@ -5667,6 +5683,17 @@ perf_event_aux_ctx(struct perf_event_context *ctx, } static void +perf_event_aux_task_ctx(perf_event_aux_output_cb output, void *data, + struct perf_event_context *task_ctx) +{ + rcu_read_lock(); + preempt_disable(); + perf_event_aux_ctx(task_ctx, output, data); + preempt_enable(); + rcu_read_unlock(); +} + +static void perf_event_aux(perf_event_aux_output_cb output, void *data, struct perf_event_context *task_ctx) { @@ -5675,14 +5702,23 @@ perf_event_aux(perf_event_aux_output_cb output, void *data, struct pmu *pmu; int ctxn; + /* + * If we have task_ctx != NULL we only notify + * the task context itself. The task_ctx is set + * only for EXIT events before releasing task + * context. + */ + if (task_ctx) { + perf_event_aux_task_ctx(output, data, task_ctx); + return; + } + rcu_read_lock(); list_for_each_entry_rcu(pmu, &pmus, entry) { cpuctx = get_cpu_ptr(pmu->pmu_cpu_context); if (cpuctx->unique_pmu != pmu) goto next; perf_event_aux_ctx(&cpuctx->ctx, output, data); - if (task_ctx) - goto next; ctxn = pmu->task_ctx_nr; if (ctxn < 0) goto next; @@ -5692,12 +5728,6 @@ perf_event_aux(perf_event_aux_output_cb output, void *data, next: put_cpu_ptr(pmu->pmu_cpu_context); } - - if (task_ctx) { - preempt_disable(); - perf_event_aux_ctx(task_ctx, output, data); - preempt_enable(); - } rcu_read_unlock(); } @@ -8787,10 +8817,8 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn) struct perf_event_context *child_ctx, *clone_ctx = NULL; unsigned long flags; - if (likely(!child->perf_event_ctxp[ctxn])) { - perf_event_task(child, NULL, 0); + if (likely(!child->perf_event_ctxp[ctxn])) return; - } local_irq_save(flags); /* @@ -8874,6 +8902,14 @@ void perf_event_exit_task(struct task_struct *child) for_each_task_context_nr(ctxn) perf_event_exit_task_context(child, ctxn); + + /* + * The perf_event_exit_task_context calls perf_event_task + * with child's task_ctx, which generates EXIT events for + * child contexts and sets child->perf_event_ctxp[] to NULL. + * At this point we need to send EXIT events to cpu contexts. + */ + perf_event_task(child, NULL, 0); } static void perf_free_event(struct perf_event *event, @@ -9452,16 +9488,18 @@ static void perf_cgroup_css_free(struct cgroup_subsys_state *css) static int __perf_cgroup_move(void *info) { struct task_struct *task = info; + rcu_read_lock(); perf_cgroup_switch(task, PERF_CGROUP_SWOUT | PERF_CGROUP_SWIN); + rcu_read_unlock(); return 0; } -static void perf_cgroup_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void perf_cgroup_attach(struct cgroup_taskset *tset) { struct task_struct *task; + struct cgroup_subsys_state *css; - cgroup_taskset_for_each(task, tset) + cgroup_taskset_for_each(task, css, tset) task_function_call(task, __perf_cgroup_move, task); } diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index b5d1ea79c595..adfdc0536117 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -3,7 +3,7 @@ * * Copyright (C) 2008 Thomas Gleixner <[email protected]> * Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar - * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra <[email protected]> + * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra * Copyright © 2009 Paul Mackerras, IBM Corp. <[email protected]> * * For licensing details see kernel-base/COPYING diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 4e5e9798aa0c..7dad84913abf 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -19,7 +19,7 @@ * Authors: * Srikar Dronamraju * Jim Keniston - * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra <[email protected]> + * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra */ #include <linux/kernel.h> diff --git a/kernel/fork.c b/kernel/fork.c index f97f2c449f5c..fce002ee3ddf 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1368,8 +1368,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->real_start_time = ktime_get_boot_ns(); p->io_context = NULL; p->audit_context = NULL; - if (clone_flags & CLONE_THREAD) - threadgroup_change_begin(current); + threadgroup_change_begin(current); cgroup_fork(p); #ifdef CONFIG_NUMA p->mempolicy = mpol_dup(p->mempolicy); @@ -1610,8 +1609,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, proc_fork_connector(p); cgroup_post_fork(p, cgrp_ss_priv); - if (clone_flags & CLONE_THREAD) - threadgroup_change_end(current); + threadgroup_change_end(current); perf_event_fork(p); trace_task_newtask(p, clone_flags); @@ -1652,8 +1650,7 @@ bad_fork_cleanup_policy: mpol_put(p->mempolicy); bad_fork_cleanup_threadgroup_lock: #endif - if (clone_flags & CLONE_THREAD) - threadgroup_change_end(current); + threadgroup_change_end(current); delayacct_tsk_free(p); bad_fork_cleanup_count: atomic_dec(&p->cred->user->processes); diff --git a/kernel/irq_work.c b/kernel/irq_work.c index cbf9fb899d92..bcf107ce0854 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra <[email protected]> + * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra * * Provides a framework for enqueueing and running callbacks from hardirq * context. The enqueueing is NMI-safe. diff --git a/kernel/jump_label.c b/kernel/jump_label.c index f7dd15d537f9..05254eeb4b4e 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -2,7 +2,7 @@ * jump label support * * Copyright (C) 2009 Jason Baron <[email protected]> - * Copyright (C) 2011 Peter Zijlstra <[email protected]> + * Copyright (C) 2011 Peter Zijlstra * */ #include <linux/memory.h> diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index deae3907ac1e..60ace56618f6 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -6,7 +6,7 @@ * Started by Ingo Molnar: * * Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar <[email protected]> - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <[email protected]> + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * this code maps all the lock dependencies as they occur in a live kernel * and will warn about the following classes of locking bugs: diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c index d83d798bef95..dbb61a302548 100644 --- a/kernel/locking/lockdep_proc.c +++ b/kernel/locking/lockdep_proc.c @@ -6,7 +6,7 @@ * Started by Ingo Molnar: * * Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar <[email protected]> - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <[email protected]> + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * Code for /proc/lockdep and /proc/lockdep_stats: * diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c index c0a205101c23..caf4041f5b0a 100644 --- a/kernel/sched/clock.c +++ b/kernel/sched/clock.c @@ -1,7 +1,7 @@ /* * sched_clock for unstable cpu clocks * - * Copyright (C) 2008 Red Hat, Inc., Peter Zijlstra <[email protected]> + * Copyright (C) 2008 Red Hat, Inc., Peter Zijlstra * * Updates and enhancements: * Copyright (C) 2008 Red Hat, Inc. Steven Rostedt <[email protected]> diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 7063c6a07440..732e993b564b 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -8241,12 +8241,12 @@ static void cpu_cgroup_fork(struct task_struct *task, void *private) sched_move_task(task); } -static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static int cpu_cgroup_can_attach(struct cgroup_taskset *tset) { struct task_struct *task; + struct cgroup_subsys_state *css; - cgroup_taskset_for_each(task, tset) { + cgroup_taskset_for_each(task, css, tset) { #ifdef CONFIG_RT_GROUP_SCHED if (!sched_rt_can_attach(css_tg(css), task)) return -EINVAL; @@ -8259,12 +8259,12 @@ static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css, return 0; } -static void cpu_cgroup_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void cpu_cgroup_attach(struct cgroup_taskset *tset) { struct task_struct *task; + struct cgroup_subsys_state *css; - cgroup_taskset_for_each(task, tset) + cgroup_taskset_for_each(task, css, tset) sched_move_task(task); } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index f04fda8f669c..90e26b11deaa 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -17,7 +17,7 @@ * Copyright (C) 2007, Thomas Gleixner <[email protected]> * * Adaptive scheduling granularity, math enhancements by Peter Zijlstra - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <[email protected]> + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra */ #include <linux/latencytop.h> diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index abfc903e741e..cc9f7a9319be 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -1,7 +1,7 @@ /* * trace event based perf event profiling/tracing * - * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra <[email protected]> + * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra * Copyright (C) 2009-2010 Frederic Weisbecker <[email protected]> */ diff --git a/lib/btree.c b/lib/btree.c index 4264871ea1a0..f93a945274af 100644 --- a/lib/btree.c +++ b/lib/btree.c @@ -5,7 +5,7 @@ * * Copyright (c) 2007-2008 Joern Engel <[email protected]> * Bits and pieces stolen from Peter Zijlstra's code, which is - * Copyright 2007, Red Hat Inc. Peter Zijlstra <[email protected]> + * Copyright 2007, Red Hat Inc. Peter Zijlstra * GPLv2 * * see http://programming.kicks-ass.net/kernel-patches/vma_lookup/btree.patch diff --git a/lib/proportions.c b/lib/proportions.c index 6f724298f67a..efa54f259ea9 100644 --- a/lib/proportions.c +++ b/lib/proportions.c @@ -1,7 +1,7 @@ /* * Floating proportions * - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <[email protected]> + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * Description: * diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 9acfb165eb52..c92a65b2b4ab 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4779,23 +4779,18 @@ static void mem_cgroup_clear_mc(void) spin_unlock(&mc.lock); } -static int mem_cgroup_can_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static int mem_cgroup_can_attach(struct cgroup_taskset *tset) { - struct mem_cgroup *memcg = mem_cgroup_from_css(css); + struct cgroup_subsys_state *css; + struct mem_cgroup *memcg; struct mem_cgroup *from; struct task_struct *leader, *p; struct mm_struct *mm; unsigned long move_flags; int ret = 0; - /* - * We are now commited to this value whatever it is. Changes in this - * tunable will only affect upcoming migrations, not the current one. - * So we need to save it, and keep it going. - */ - move_flags = READ_ONCE(memcg->move_charge_at_immigrate); - if (!move_flags) + /* charge immigration isn't supported on the default hierarchy */ + if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) return 0; /* @@ -4805,13 +4800,23 @@ static int mem_cgroup_can_attach(struct cgroup_subsys_state *css, * multiple. */ p = NULL; - cgroup_taskset_for_each_leader(leader, tset) { + cgroup_taskset_for_each_leader(leader, css, tset) { WARN_ON_ONCE(p); p = leader; + memcg = mem_cgroup_from_css(css); } if (!p) return 0; + /* + * We are now commited to this value whatever it is. Changes in this + * tunable will only affect upcoming migrations, not the current one. + * So we need to save it, and keep it going. + */ + move_flags = READ_ONCE(memcg->move_charge_at_immigrate); + if (!move_flags) + return 0; + from = mem_cgroup_from_task(p); VM_BUG_ON(from == memcg); @@ -4842,8 +4847,7 @@ static int mem_cgroup_can_attach(struct cgroup_subsys_state *css, return ret; } -static void mem_cgroup_cancel_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset) { if (mc.to) mem_cgroup_clear_mc(); @@ -4985,10 +4989,10 @@ retry: atomic_dec(&mc.from->moving_account); } -static void mem_cgroup_move_task(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void mem_cgroup_move_task(struct cgroup_taskset *tset) { - struct task_struct *p = cgroup_taskset_first(tset); + struct cgroup_subsys_state *css; + struct task_struct *p = cgroup_taskset_first(tset, &css); struct mm_struct *mm = get_task_mm(p); if (mm) { @@ -5000,17 +5004,14 @@ static void mem_cgroup_move_task(struct cgroup_subsys_state *css, mem_cgroup_clear_mc(); } #else /* !CONFIG_MMU */ -static int mem_cgroup_can_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static int mem_cgroup_can_attach(struct cgroup_taskset *tset) { return 0; } -static void mem_cgroup_cancel_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset) { } -static void mem_cgroup_move_task(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void mem_cgroup_move_task(struct cgroup_taskset *tset) { } #endif diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 3e4d65445fa7..d15d88c8efa1 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2,7 +2,7 @@ * mm/page-writeback.c * * Copyright (C) 2002, Linus Torvalds. - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <[email protected]> + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * Contains functions related to writing back dirty pages at the * address_space level. diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c index 2e4df84c34a1..d9ee8d08a3a6 100644 --- a/net/core/netclassid_cgroup.c +++ b/net/core/netclassid_cgroup.c @@ -81,9 +81,11 @@ static void update_classid(struct cgroup_subsys_state *css, void *v) css_task_iter_end(&it); } -static void cgrp_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void cgrp_attach(struct cgroup_taskset *tset) { + struct cgroup_subsys_state *css; + + cgroup_taskset_first(tset, &css); update_classid(css, (void *)(unsigned long)css_cls_state(css)->classid); } diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index cbd0a199bf52..40fd09fe06ae 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -218,13 +218,14 @@ static int update_netprio(const void *v, struct file *file, unsigned n) return 0; } -static void net_prio_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void net_prio_attach(struct cgroup_taskset *tset) { struct task_struct *p; - void *v = (void *)(unsigned long)css->cgroup->id; + struct cgroup_subsys_state *css; + + cgroup_taskset_for_each(p, css, tset) { + void *v = (void *)(unsigned long)css->cgroup->id; - cgroup_taskset_for_each(p, tset) { task_lock(p); iterate_fd(p->files, 0, update_netprio, v); task_unlock(p); diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 1a10d8ac8162..dacf71a43ad4 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -62,7 +62,7 @@ vmlinux_link() -Wl,--start-group \ ${KBUILD_VMLINUX_MAIN} \ -Wl,--end-group \ - -lutil ${1} + -lutil -lrt ${1} rm -f linux fi } diff --git a/tools/virtio/linux/kernel.h b/tools/virtio/linux/kernel.h index 0a3da64638ce..4db7d5691ba7 100644 --- a/tools/virtio/linux/kernel.h +++ b/tools/virtio/linux/kernel.h @@ -110,4 +110,10 @@ static inline void free_page(unsigned long addr) (void) (&_min1 == &_min2); \ _min1 < _min2 ? _min1 : _min2; }) +/* TODO: empty stubs for now. Broken but enough for virtio_ring.c */ +#define list_add_tail(a, b) do {} while (0) +#define list_del(a) do {} while (0) +#define list_for_each_entry(a, b, c) while (0) +/* end of stubs */ + #endif /* KERNEL_H */ diff --git a/tools/virtio/linux/virtio.h b/tools/virtio/linux/virtio.h index a3e07016a440..ee125e714053 100644 --- a/tools/virtio/linux/virtio.h +++ b/tools/virtio/linux/virtio.h @@ -3,12 +3,6 @@ #include <linux/scatterlist.h> #include <linux/kernel.h> -/* TODO: empty stubs for now. Broken but enough for virtio_ring.c */ -#define list_add_tail(a, b) do {} while (0) -#define list_del(a) do {} while (0) -#define list_for_each_entry(a, b, c) while (0) -/* end of stubs */ - struct virtio_device { void *dev; u64 features; diff --git a/tools/virtio/linux/virtio_config.h b/tools/virtio/linux/virtio_config.h index 806d683ab107..57a6964a1e35 100644 --- a/tools/virtio/linux/virtio_config.h +++ b/tools/virtio/linux/virtio_config.h @@ -40,33 +40,39 @@ static inline void __virtio_clear_bit(struct virtio_device *vdev, #define virtio_has_feature(dev, feature) \ (__virtio_test_bit((dev), feature)) +static inline bool virtio_is_little_endian(struct virtio_device *vdev) +{ + return virtio_has_feature(vdev, VIRTIO_F_VERSION_1) || + virtio_legacy_is_little_endian(); +} + +/* Memory accessors */ static inline u16 virtio16_to_cpu(struct virtio_device *vdev, __virtio16 val) { - return __virtio16_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); + return __virtio16_to_cpu(virtio_is_little_endian(vdev), val); } static inline __virtio16 cpu_to_virtio16(struct virtio_device *vdev, u16 val) { - return __cpu_to_virtio16(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); + return __cpu_to_virtio16(virtio_is_little_endian(vdev), val); } static inline u32 virtio32_to_cpu(struct virtio_device *vdev, __virtio32 val) { - return __virtio32_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); + return __virtio32_to_cpu(virtio_is_little_endian(vdev), val); } static inline __virtio32 cpu_to_virtio32(struct virtio_device *vdev, u32 val) { - return __cpu_to_virtio32(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); + return __cpu_to_virtio32(virtio_is_little_endian(vdev), val); } static inline u64 virtio64_to_cpu(struct virtio_device *vdev, __virtio64 val) { - return __virtio64_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); + return __virtio64_to_cpu(virtio_is_little_endian(vdev), val); } static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val) { - return __cpu_to_virtio64(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); + return __cpu_to_virtio64(virtio_is_little_endian(vdev), val); } - |