diff options
49 files changed, 1622 insertions, 517 deletions
diff --git a/Documentation/devicetree/bindings/interrupt-controller/interrupts.txt b/Documentation/devicetree/bindings/interrupt-controller/interrupts.txt index 1486497a24c1..ce6a1a072028 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/interrupts.txt +++ b/Documentation/devicetree/bindings/interrupt-controller/interrupts.txt @@ -4,11 +4,13 @@ Specifying interrupt information for devices 1) Interrupt client nodes ------------------------- -Nodes that describe devices which generate interrupts must contain an either an -"interrupts" property or an "interrupts-extended" property. These properties -contain a list of interrupt specifiers, one per output interrupt. The format of -the interrupt specifier is determined by the interrupt controller to which the -interrupts are routed; see section 2 below for details. +Nodes that describe devices which generate interrupts must contain an +"interrupts" property, an "interrupts-extended" property, or both. If both are +present, the latter should take precedence; the former may be provided simply +for compatibility with software that does not recognize the latter. These +properties contain a list of interrupt specifiers, one per output interrupt. The +format of the interrupt specifier is determined by the interrupt controller to +which the interrupts are routed; see section 2 below for details. Example: interrupt-parent = <&intc1>; diff --git a/Documentation/devicetree/bindings/pci/designware-pcie.txt b/Documentation/devicetree/bindings/pci/designware-pcie.txt index d0d15ee42834..ed0d9b9fff2b 100644 --- a/Documentation/devicetree/bindings/pci/designware-pcie.txt +++ b/Documentation/devicetree/bindings/pci/designware-pcie.txt @@ -2,6 +2,10 @@ Required properties: - compatible: should contain "snps,dw-pcie" to identify the core. +- reg: Should contain the configuration address space. +- reg-names: Must be "config" for the PCIe configuration space. + (The old way of getting the configuration address space from "ranges" + is deprecated and should be avoided.) - #address-cells: set to <3> - #size-cells: set to <2> - device_type: set to "pci" diff --git a/Documentation/devicetree/bindings/pci/ti-pci.txt b/Documentation/devicetree/bindings/pci/ti-pci.txt new file mode 100644 index 000000000000..3d217911b313 --- /dev/null +++ b/Documentation/devicetree/bindings/pci/ti-pci.txt @@ -0,0 +1,59 @@ +TI PCI Controllers + +PCIe Designware Controller + - compatible: Should be "ti,dra7-pcie"" + - reg : Two register ranges as listed in the reg-names property + - reg-names : The first entry must be "ti-conf" for the TI specific registers + The second entry must be "rc-dbics" for the designware pcie + registers + The third entry must be "config" for the PCIe configuration space + - phys : list of PHY specifiers (used by generic PHY framework) + - phy-names : must be "pcie-phy0", "pcie-phy1", "pcie-phyN".. based on the + number of PHYs as specified in *phys* property. + - ti,hwmods : Name of the hwmod associated to the pcie, "pcie<X>", + where <X> is the instance number of the pcie from the HW spec. + - interrupts : Two interrupt entries must be specified. The first one is for + main interrupt line and the second for MSI interrupt line. + - #address-cells, + #size-cells, + #interrupt-cells, + device_type, + ranges, + num-lanes, + interrupt-map-mask, + interrupt-map : as specified in ../designware-pcie.txt + +Example: +axi { + compatible = "simple-bus"; + #size-cells = <1>; + #address-cells = <1>; + ranges = <0x51000000 0x51000000 0x3000 + 0x0 0x20000000 0x10000000>; + pcie@51000000 { + compatible = "ti,dra7-pcie"; + reg = <0x51000000 0x2000>, <0x51002000 0x14c>, <0x1000 0x2000>; + reg-names = "rc_dbics", "ti_conf", "config"; + interrupts = <0 232 0x4>, <0 233 0x4>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + ranges = <0x81000000 0 0 0x03000 0 0x00010000 + 0x82000000 0 0x20013000 0x13000 0 0xffed000>; + #interrupt-cells = <1>; + num-lanes = <1>; + ti,hwmods = "pcie1"; + phys = <&pcie1_phy>; + phy-names = "pcie-phy0"; + interrupt-map-mask = <0 0 0 7>; + interrupt-map = <0 0 0 1 &pcie_intc 1>, + <0 0 0 2 &pcie_intc 2>, + <0 0 0 3 &pcie_intc 3>, + <0 0 0 4 &pcie_intc 4>; + pcie_intc: interrupt-controller { + interrupt-controller; + #address-cells = <0>; + #interrupt-cells = <1>; + }; + }; +}; diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index b18dd1779029..f1997e9da61f 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -349,7 +349,11 @@ prototypes: locking rules: inode->i_lock may block fl_copy_lock: yes no -fl_release_private: maybe no +fl_release_private: maybe maybe[1] + +[1]: ->fl_release_private for flock or POSIX locks is currently allowed +to block. Leases however can still be freed while the i_lock is held and +so fl_release_private called on a lease should not block. ----------------------- lock_manager_operations --------------------------- prototypes: diff --git a/MAINTAINERS b/MAINTAINERS index aefa94841ff3..05dc39d66920 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6858,6 +6858,14 @@ S: Supported F: Documentation/devicetree/bindings/pci/nvidia,tegra20-pcie.txt F: drivers/pci/host/pci-tegra.c +PCI DRIVER FOR TI DRA7XX +M: Kishon Vijay Abraham I <kishon@ti.com> +L: linux-omap@vger.kernel.org +L: linux-pci@vger.kernel.org +S: Supported +F: Documentation/devicetree/bindings/pci/ti-pci.txt +F: drivers/pci/host/pci-dra7xx.c + PCI DRIVER FOR RENESAS R-CAR M: Simon Horman <horms@verge.net.au> L: linux-pci@vger.kernel.org @@ -1,7 +1,7 @@ VERSION = 3 -PATCHLEVEL = 16 +PATCHLEVEL = 17 SUBLEVEL = 0 -EXTRAVERSION = +EXTRAVERSION = -rc1 NAME = Shuffling Zombie Juror # *DOCUMENTATION* diff --git a/arch/frv/include/asm/processor.h b/arch/frv/include/asm/processor.h index a34f309e5801..6554e78893f2 100644 --- a/arch/frv/include/asm/processor.h +++ b/arch/frv/include/asm/processor.h @@ -129,7 +129,8 @@ unsigned long get_wchan(struct task_struct *p); #define KSTK_EIP(tsk) ((tsk)->thread.frame0->pc) #define KSTK_ESP(tsk) ((tsk)->thread.frame0->sp) -#define cpu_relax() barrier() +#define cpu_relax() barrier() +#define cpu_relax_lowlatency() cpu_relax() /* data cache prefetch */ #define ARCH_HAS_PREFETCH diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index 329d7fdd0a6a..b9615ba5b083 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -101,7 +101,7 @@ struct kvm_rma_info *kvm_alloc_rma() ri = kmalloc(sizeof(struct kvm_rma_info), GFP_KERNEL); if (!ri) return NULL; - page = cma_alloc(kvm_cma, kvm_rma_pages, get_order(kvm_rma_pages)); + page = cma_alloc(kvm_cma, kvm_rma_pages, order_base_2(kvm_rma_pages)); if (!page) goto err_out; atomic_set(&ri->use_count, 1); @@ -135,12 +135,12 @@ struct page *kvm_alloc_hpt(unsigned long nr_pages) { unsigned long align_pages = HPT_ALIGN_PAGES; - VM_BUG_ON(get_order(nr_pages) < KVM_CMA_CHUNK_ORDER - PAGE_SHIFT); + VM_BUG_ON(order_base_2(nr_pages) < KVM_CMA_CHUNK_ORDER - PAGE_SHIFT); /* Old CPUs require HPT aligned on a multiple of its size */ if (!cpu_has_feature(CPU_FTR_ARCH_206)) align_pages = nr_pages; - return cma_alloc(kvm_cma, nr_pages, get_order(align_pages)); + return cma_alloc(kvm_cma, nr_pages, order_base_2(align_pages)); } EXPORT_SYMBOL_GPL(kvm_alloc_hpt); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 572460175ba5..7c492ed9087b 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -95,7 +95,7 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level) #define KVM_REFILL_PAGES 25 #define KVM_MAX_CPUID_ENTRIES 80 #define KVM_NR_FIXED_MTRR_REGION 88 -#define KVM_NR_VAR_MTRR 10 +#define KVM_NR_VAR_MTRR 8 #define ASYNC_PF_PER_VCPU 64 diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h index eac9e92fe181..e21331ce368f 100644 --- a/arch/x86/include/uapi/asm/msr-index.h +++ b/arch/x86/include/uapi/asm/msr-index.h @@ -149,6 +149,9 @@ #define MSR_CORE_C1_RES 0x00000660 +#define MSR_CC6_DEMOTION_POLICY_CONFIG 0x00000668 +#define MSR_MC6_DEMOTION_POLICY_CONFIG 0x00000669 + #define MSR_AMD64_MC0_MASK 0xc0010044 #define MSR_IA32_MCx_CTL(x) (MSR_IA32_MC0_CTL + 4*(x)) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 56657b0bb3bb..03954f7900f5 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -1491,9 +1491,6 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt, goto exception; break; case VCPU_SREG_CS: - if (in_task_switch && rpl != dpl) - goto exception; - if (!(seg_desc.type & 8)) goto exception; @@ -4394,8 +4391,11 @@ done_prefixes: ctxt->execute = opcode.u.execute; + if (unlikely(ctxt->ud) && likely(!(ctxt->d & EmulateOnUD))) + return EMULATION_FAILED; + if (unlikely(ctxt->d & - (NotImpl|EmulateOnUD|Stack|Op3264|Sse|Mmx|Intercept|CheckPerm))) { + (NotImpl|Stack|Op3264|Sse|Mmx|Intercept|CheckPerm))) { /* * These are copied unconditionally here, and checked unconditionally * in x86_emulate_insn. @@ -4406,9 +4406,6 @@ done_prefixes: if (ctxt->d & NotImpl) return EMULATION_FAILED; - if (!(ctxt->d & EmulateOnUD) && ctxt->ud) - return EMULATION_FAILED; - if (mode == X86EMUL_MODE_PROT64 && (ctxt->d & Stack)) ctxt->op_bytes = 8; diff --git a/drivers/char/hw_random/virtio-rng.c b/drivers/char/hw_random/virtio-rng.c index 0027137daa56..2e3139eda93b 100644 --- a/drivers/char/hw_random/virtio-rng.c +++ b/drivers/char/hw_random/virtio-rng.c @@ -116,6 +116,7 @@ static int probe_common(struct virtio_device *vdev) .cleanup = virtio_cleanup, .priv = (unsigned long)vi, .name = vi->name, + .quality = 1000, }; vdev->priv = vi; diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 4d140bbbe100..9b7ee7e427df 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -89,6 +89,7 @@ struct idle_cpu { * Indicate which enable bits to clear here. */ unsigned long auto_demotion_disable_flags; + bool byt_auto_demotion_disable_flag; bool disable_promotion_to_c1e; }; @@ -442,6 +443,66 @@ static struct cpuidle_state hsw_cstates[] = { { .enter = NULL } }; +static struct cpuidle_state bdw_cstates[] = { + { + .name = "C1-BDW", + .desc = "MWAIT 0x00", + .flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID, + .exit_latency = 2, + .target_residency = 2, + .enter = &intel_idle }, + { + .name = "C1E-BDW", + .desc = "MWAIT 0x01", + .flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_TIME_VALID, + .exit_latency = 10, + .target_residency = 20, + .enter = &intel_idle }, + { + .name = "C3-BDW", + .desc = "MWAIT 0x10", + .flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED, + .exit_latency = 40, + .target_residency = 100, + .enter = &intel_idle }, + { + .name = "C6-BDW", + .desc = "MWAIT 0x20", + .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED, + .exit_latency = 133, + .target_residency = 400, + .enter = &intel_idle }, + { + .name = "C7s-BDW", + .desc = "MWAIT 0x32", + .flags = MWAIT2flg(0x32) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED, + .exit_latency = 166, + .target_residency = 500, + .enter = &intel_idle }, + { + .name = "C8-BDW", + .desc = "MWAIT 0x40", + .flags = MWAIT2flg(0x40) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED, + .exit_latency = 300, + .target_residency = 900, + .enter = &intel_idle }, + { + .name = "C9-BDW", + .desc = "MWAIT 0x50", + .flags = MWAIT2flg(0x50) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED, + .exit_latency = 600, + .target_residency = 1800, + .enter = &intel_idle }, + { + .name = "C10-BDW", + .desc = "MWAIT 0x60", + .flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED, + .exit_latency = 2600, + .target_residency = 7700, + .enter = &intel_idle }, + { + .enter = NULL } +}; static struct cpuidle_state atom_cstates[] = { { @@ -613,6 +674,7 @@ static const struct idle_cpu idle_cpu_snb = { static const struct idle_cpu idle_cpu_byt = { .state_table = byt_cstates, .disable_promotion_to_c1e = true, + .byt_auto_demotion_disable_flag = true, }; static const struct idle_cpu idle_cpu_ivb = { @@ -630,6 +692,11 @@ static const struct idle_cpu idle_cpu_hsw = { .disable_promotion_to_c1e = true, }; +static const struct idle_cpu idle_cpu_bdw = { + .state_table = bdw_cstates, + .disable_promotion_to_c1e = true, +}; + static const struct idle_cpu idle_cpu_avn = { .state_table = avn_cstates, .disable_promotion_to_c1e = true, @@ -658,7 +725,10 @@ static const struct x86_cpu_id intel_idle_ids[] = { ICPU(0x3f, idle_cpu_hsw), ICPU(0x45, idle_cpu_hsw), ICPU(0x46, idle_cpu_hsw), - ICPU(0x4D, idle_cpu_avn), + ICPU(0x4d, idle_cpu_avn), + ICPU(0x3d, idle_cpu_bdw), + ICPU(0x4f, idle_cpu_bdw), + ICPU(0x56, idle_cpu_bdw), {} }; MODULE_DEVICE_TABLE(x86cpu, intel_idle_ids); @@ -814,6 +884,11 @@ static int __init intel_idle_cpuidle_driver_init(void) if (icpu->auto_demotion_disable_flags) on_each_cpu(auto_demotion_disable, NULL, 1); + if (icpu->byt_auto_demotion_disable_flag) { + wrmsrl(MSR_CC6_DEMOTION_POLICY_CONFIG, 0); + wrmsrl(MSR_MC6_DEMOTION_POLICY_CONFIG, 0); + } + if (icpu->disable_promotion_to_c1e) /* each-cpu is redundant */ on_each_cpu(c1e_promotion_disable, NULL, 1); diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index b08c18871323..6703751d87d7 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -2953,6 +2953,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, */ if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) { end_reshape(conf); + close_sync(conf); return 0; } @@ -3081,6 +3082,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, } r10_bio = mempool_alloc(conf->r10buf_pool, GFP_NOIO); + r10_bio->state = 0; raise_barrier(conf, rb2 != NULL); atomic_set(&r10_bio->remaining, 0); @@ -3269,6 +3271,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, if (sync_blocks < max_sync) max_sync = sync_blocks; r10_bio = mempool_alloc(conf->r10buf_pool, GFP_NOIO); + r10_bio->state = 0; r10_bio->mddev = mddev; atomic_set(&r10_bio->remaining, 0); @@ -4384,6 +4387,7 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, read_more: /* Now schedule reads for blocks from sector_nr to last */ r10_bio = mempool_alloc(conf->r10buf_pool, GFP_NOIO); + r10_bio->state = 0; raise_barrier(conf, sectors_done != 0); atomic_set(&r10_bio->remaining, 0); r10_bio->mddev = mddev; @@ -4398,6 +4402,7 @@ read_more: * on all the target devices. */ // FIXME + mempool_free(r10_bio, conf->r10buf_pool); set_bit(MD_RECOVERY_INTR, &mddev->recovery); return sectors_done; } @@ -4410,7 +4415,7 @@ read_more: read_bio->bi_private = r10_bio; read_bio->bi_end_io = end_sync_read; read_bio->bi_rw = READ; - read_bio->bi_flags &= ~(BIO_POOL_MASK - 1); + read_bio->bi_flags &= (~0UL << BIO_RESET_BITS); read_bio->bi_flags |= 1 << BIO_UPTODATE; read_bio->bi_vcnt = 0; read_bio->bi_iter.bi_size = 0; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 6234b2e84587..183588b11fc1 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -2922,7 +2922,7 @@ static int fetch_block(struct stripe_head *sh, struct stripe_head_state *s, (!test_bit(R5_Insync, &dev->flags) || test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) && !test_bit(R5_OVERWRITE, &fdev[0]->flags)) || (sh->raid_conf->level == 6 && s->failed && s->to_write && - s->to_write < sh->raid_conf->raid_disks - 2 && + s->to_write - s->non_overwrite < sh->raid_conf->raid_disks - 2 && (!test_bit(R5_Insync, &dev->flags) || test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))))) { /* we would like to get this block, possibly by computing it, * otherwise read it if the backing disk is insync @@ -3817,6 +3817,8 @@ static void handle_stripe(struct stripe_head *sh) set_bit(R5_Wantwrite, &dev->flags); if (prexor) continue; + if (s.failed > 1) + continue; if (!test_bit(R5_Insync, &dev->flags) || ((i == sh->pd_idx || i == sh->qd_idx) && s.failed == 0)) diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index f46a24ffa3fe..79cb8313c7d8 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -453,7 +453,7 @@ static int __init __reserved_mem_reserve_reg(unsigned long node, base = dt_mem_next_cell(dt_root_addr_cells, &prop); size = dt_mem_next_cell(dt_root_size_cells, &prop); - if (base && size && + if (size && early_init_dt_reserve_memory_arch(base, size, nomap) == 0) pr_debug("Reserved memory: reserved region for node '%s': base %pa, size %ld MiB\n", uname, &base, (unsigned long)size / SZ_1M); diff --git a/drivers/of/irq.c b/drivers/of/irq.c index 3e06a699352d..1471e0a223a5 100644 --- a/drivers/of/irq.c +++ b/drivers/of/irq.c @@ -301,16 +301,17 @@ int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_ar /* Get the reg property (if any) */ addr = of_get_property(device, "reg", NULL); + /* Try the new-style interrupts-extended first */ + res = of_parse_phandle_with_args(device, "interrupts-extended", + "#interrupt-cells", index, out_irq); + if (!res) + return of_irq_parse_raw(addr, out_irq); + /* Get the interrupts property */ intspec = of_get_property(device, "interrupts", &intlen); - if (intspec == NULL) { - /* Try the new-style interrupts-extended */ - res = of_parse_phandle_with_args(device, "interrupts-extended", - "#interrupt-cells", index, out_irq); - if (res) - return -EINVAL; - return of_irq_parse_raw(addr, out_irq); - } + if (intspec == NULL) + return -EINVAL; + intlen /= sizeof(*intspec); pr_debug(" intspec=%d intlen=%d\n", be32_to_cpup(intspec), intlen); diff --git a/drivers/of/selftest.c b/drivers/of/selftest.c index d41002667833..a737cb5974de 100644 --- a/drivers/of/selftest.c +++ b/drivers/of/selftest.c @@ -27,6 +27,7 @@ static struct selftest_results { #define NO_OF_NODES 2 static struct device_node *nodes[NO_OF_NODES]; static int last_node_index; +static bool selftest_live_tree; #define selftest(result, fmt, ...) { \ if (!(result)) { \ @@ -630,13 +631,6 @@ static int attach_node_and_children(struct device_node *np) { struct device_node *next, *root = np, *dup; - if (!np) { - pr_warn("%s: No tree to attach; not running tests\n", - __func__); - return -ENODATA; - } - - /* skip root node */ np = np->child; /* storing a copy in temporary node */ @@ -672,12 +666,12 @@ static int attach_node_and_children(struct device_node *np) static int __init selftest_data_add(void) { void *selftest_data; - struct device_node *selftest_data_node; + struct device_node *selftest_data_node, *np; extern uint8_t __dtb_testcases_begin[]; extern uint8_t __dtb_testcases_end[]; const int size = __dtb_testcases_end - __dtb_testcases_begin; - if (!size || !of_allnodes) { + if (!size) { pr_warn("%s: No testcase data to attach; not running tests\n", __func__); return -ENODATA; @@ -692,6 +686,22 @@ static int __init selftest_data_add(void) return -ENOMEM; } of_fdt_unflatten_tree(selftest_data, &selftest_data_node); + if (!selftest_data_node) { + pr_warn("%s: No tree to attach; not running tests\n", __func__); + return -ENODATA; + } + + if (!of_allnodes) { + /* enabling flag for removing nodes */ + selftest_live_tree = true; + of_allnodes = selftest_data_node; + + for_each_of_allnodes(np) + __of_attach_node_sysfs(np); + of_aliases = of_find_node_by_path("/aliases"); + of_chosen = of_find_node_by_path("/chosen"); + return 0; + } /* attach the sub-tree to live tree */ return attach_node_and_children(selftest_data_node); @@ -723,6 +733,18 @@ static void selftest_data_remove(void) struct device_node *np; struct property *prop; + if (selftest_live_tree) { + of_node_put(of_aliases); + of_node_put(of_chosen); + of_aliases = NULL; + of_chosen = NULL; + for_each_child_of_node(of_allnodes, np) + detach_node_and_children(np); + __of_detach_node_sysfs(of_allnodes); + of_allnodes = NULL; + return; + } + while (last_node_index >= 0) { if (nodes[last_node_index]) { np = of_find_node_by_path(nodes[last_node_index]->full_name); diff --git a/drivers/pci/host/Kconfig b/drivers/pci/host/Kconfig index 2d8a4d05d78f..8922c376456a 100644 --- a/drivers/pci/host/Kconfig +++ b/drivers/pci/host/Kconfig @@ -1,9 +1,18 @@ menu "PCI host controller drivers" depends on PCI +config PCI_DRA7XX + bool "TI DRA7xx PCIe controller" + select PCIE_DW + depends on OF && HAS_IOMEM && TI_PIPE3 + help + Enables support for the PCIe controller in the DRA7xx SoC. There + are two instances of PCIe controller in DRA7xx. This controller can + act both as EP and RC. This reuses the Designware core. + config PCI_MVEBU bool "Marvell EBU PCIe controller" - depends on ARCH_MVEBU || ARCH_DOVE || ARCH_KIRKWOOD + depends on ARCH_MVEBU || ARCH_DOVE depends on OF config PCIE_DW diff --git a/drivers/pci/host/Makefile b/drivers/pci/host/Makefile index 0daec7941aba..d0e88f114ff9 100644 --- a/drivers/pci/host/Makefile +++ b/drivers/pci/host/Makefile @@ -1,4 +1,5 @@ obj-$(CONFIG_PCIE_DW) += pcie-designware.o +obj-$(CONFIG_PCI_DRA7XX) += pci-dra7xx.o obj-$(CONFIG_PCI_EXYNOS) += pci-exynos.o obj-$(CONFIG_PCI_IMX6) += pci-imx6.o obj-$(CONFIG_PCI_MVEBU) += pci-mvebu.o diff --git a/drivers/pci/host/pci-dra7xx.c b/drivers/pci/host/pci-dra7xx.c new file mode 100644 index 000000000000..52b34fee07fd --- /dev/null +++ b/drivers/pci/host/pci-dra7xx.c @@ -0,0 +1,458 @@ +/* + * pcie-dra7xx - PCIe controller driver for TI DRA7xx SoCs + * + * Copyright (C) 2013-2014 Texas Instruments Incorporated - http://www.ti.com + * + * Authors: Kishon Vijay Abraham I <kishon@ti.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/delay.h> +#include <linux/err.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/irqdomain.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/phy/phy.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> +#include <linux/resource.h> +#include <linux/types.h> + +#include "pcie-designware.h" + +/* PCIe controller wrapper DRA7XX configuration registers */ + +#define PCIECTRL_DRA7XX_CONF_IRQSTATUS_MAIN 0x0024 +#define PCIECTRL_DRA7XX_CONF_IRQENABLE_SET_MAIN 0x0028 +#define ERR_SYS BIT(0) +#define ERR_FATAL BIT(1) +#define ERR_NONFATAL BIT(2) +#define ERR_COR BIT(3) +#define ERR_AXI BIT(4) +#define ERR_ECRC BIT(5) +#define PME_TURN_OFF BIT(8) +#define PME_TO_ACK BIT(9) +#define PM_PME BIT(10) +#define LINK_REQ_RST BIT(11) +#define LINK_UP_EVT BIT(12) +#define CFG_BME_EVT BIT(13) +#define CFG_MSE_EVT BIT(14) +#define INTERRUPTS (ERR_SYS | ERR_FATAL | ERR_NONFATAL | ERR_COR | ERR_AXI | \ + ERR_ECRC | PME_TURN_OFF | PME_TO_ACK | PM_PME | \ + LINK_REQ_RST | LINK_UP_EVT | CFG_BME_EVT | CFG_MSE_EVT) + +#define PCIECTRL_DRA7XX_CONF_IRQSTATUS_MSI 0x0034 +#define PCIECTRL_DRA7XX_CONF_IRQENABLE_SET_MSI 0x0038 +#define INTA BIT(0) +#define INTB BIT(1) +#define INTC BIT(2) +#define INTD BIT(3) +#define MSI BIT(4) +#define LEG_EP_INTERRUPTS (INTA | INTB | INTC | INTD) + +#define PCIECTRL_DRA7XX_CONF_DEVICE_CMD 0x0104 +#define LTSSM_EN 0x1 + +#define PCIECTRL_DRA7XX_CONF_PHY_CS 0x010C +#define LINK_UP BIT(16) + +struct dra7xx_pcie { + void __iomem *base; + struct phy **phy; + int phy_count; + struct device *dev; + struct pcie_port pp; +}; + +#define to_dra7xx_pcie(x) container_of((x), struct dra7xx_pcie, pp) + +static inline u32 dra7xx_pcie_readl(struct dra7xx_pcie *pcie, u32 offset) +{ + return readl(pcie->base + offset); +} + +static inline void dra7xx_pcie_writel(struct dra7xx_pcie *pcie, u32 offset, + u32 value) +{ + writel(value, pcie->base + offset); +} + +static int dra7xx_pcie_link_up(struct pcie_port *pp) +{ + struct dra7xx_pcie *dra7xx = to_dra7xx_pcie(pp); + u32 reg = dra7xx_pcie_readl(dra7xx, PCIECTRL_DRA7XX_CONF_PHY_CS); + + return !!(reg & LINK_UP); +} + +static int dra7xx_pcie_establish_link(struct pcie_port *pp) +{ + u32 reg; + unsigned int retries = 1000; + struct dra7xx_pcie *dra7xx = to_dra7xx_pcie(pp); + + if (dw_pcie_link_up(pp)) { + dev_err(pp->dev, "link is already up\n"); + return 0; + } + + reg = dra7xx_pcie_readl(dra7xx, PCIECTRL_DRA7XX_CONF_DEVICE_CMD); + reg |= LTSSM_EN; + dra7xx_pcie_writel(dra7xx, PCIECTRL_DRA7XX_CONF_DEVICE_CMD, reg); + + while (retries--) { + reg = dra7xx_pcie_readl(dra7xx, PCIECTRL_DRA7XX_CONF_PHY_CS); + if (reg & LINK_UP) + break; + usleep_range(10, 20); + } + + if (retries == 0) { + dev_err(pp->dev, "link is not up\n"); + return -ETIMEDOUT; + } + + return 0; +} + +static void dra7xx_pcie_enable_interrupts(struct pcie_port *pp) +{ + struct dra7xx_pcie *dra7xx = to_dra7xx_pcie(pp); + + dra7xx_pcie_writel(dra7xx, PCIECTRL_DRA7XX_CONF_IRQSTATUS_MAIN, + ~INTERRUPTS); + dra7xx_pcie_writel(dra7xx, + PCIECTRL_DRA7XX_CONF_IRQENABLE_SET_MAIN, INTERRUPTS); + dra7xx_pcie_writel(dra7xx, PCIECTRL_DRA7XX_CONF_IRQSTATUS_MSI, + ~LEG_EP_INTERRUPTS & ~MSI); + + if (IS_ENABLED(CONFIG_PCI_MSI)) + dra7xx_pcie_writel(dra7xx, + PCIECTRL_DRA7XX_CONF_IRQENABLE_SET_MSI, MSI); + else + dra7xx_pcie_writel(dra7xx, + PCIECTRL_DRA7XX_CONF_IRQENABLE_SET_MSI, + LEG_EP_INTERRUPTS); +} + +static void dra7xx_pcie_host_init(struct pcie_port *pp) +{ + dw_pcie_setup_rc(pp); + dra7xx_pcie_establish_link(pp); + if (IS_ENABLED(CONFIG_PCI_MSI)) + dw_pcie_msi_init(pp); + dra7xx_pcie_enable_interrupts(pp); +} + +static struct pcie_host_ops dra7xx_pcie_host_ops = { + .link_up = dra7xx_pcie_link_up, + .host_init = dra7xx_pcie_host_init, +}; + +static int dra7xx_pcie_intx_map(struct irq_domain *domain, unsigned int irq, + irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler(irq, &dummy_irq_chip, handle_simple_irq); + irq_set_chip_data(irq, domain->host_data); + set_irq_flags(irq, IRQF_VALID); + + return 0; +} + +static const struct irq_domain_ops intx_domain_ops = { + .map = dra7xx_pcie_intx_map, +}; + +static int dra7xx_pcie_init_irq_domain(struct pcie_port *pp) +{ + struct device *dev = pp->dev; + struct device_node *node = dev->of_node; + struct device_node *pcie_intc_node = of_get_next_child(node, NULL); + + if (!pcie_intc_node) { + dev_err(dev, "No PCIe Intc node found\n"); + return PTR_ERR(pcie_intc_node); + } + + pp->irq_domain = irq_domain_add_linear(pcie_intc_node, 4, + &intx_domain_ops, pp); + if (!pp->irq_domain) { + dev_err(dev, "Failed to get a INTx IRQ domain\n"); + return PTR_ERR(pp->irq_domain); + } + + return 0; +} + +static irqreturn_t dra7xx_pcie_msi_irq_handler(int irq, void *arg) +{ + struct pcie_port *pp = arg; + struct dra7xx_pcie *dra7xx = to_dra7xx_pcie(pp); + u32 reg; + + reg = dra7xx_pcie_readl(dra7xx, PCIECTRL_DRA7XX_CONF_IRQSTATUS_MSI); + + switch (reg) { + case MSI: + dw_handle_msi_irq(pp); + break; + case INTA: + case INTB: + case INTC: + case INTD: + generic_handle_irq(irq_find_mapping(pp->irq_domain, ffs(reg))); + break; + } + + dra7xx_pcie_writel(dra7xx, PCIECTRL_DRA7XX_CONF_IRQSTATUS_MSI, reg); + + return IRQ_HANDLED; +} + + +static irqreturn_t dra7xx_pcie_irq_handler(int irq, void *arg) +{ + struct dra7xx_pcie *dra7xx = arg; + u32 reg; + + reg = dra7xx_pcie_readl(dra7xx, PCIECTRL_DRA7XX_CONF_IRQSTATUS_MAIN); + + if (reg & ERR_SYS) + dev_dbg(dra7xx->dev, "System Error\n"); + + if (reg & ERR_FATAL) + dev_dbg(dra7xx->dev, "Fatal Error\n"); + + if (reg & ERR_NONFATAL) + dev_dbg(dra7xx->dev, "Non Fatal Error\n"); + + if (reg & ERR_COR) + dev_dbg(dra7xx->dev, "Correctable Error\n"); + + if (reg & ERR_AXI) + dev_dbg(dra7xx->dev, "AXI tag lookup fatal Error\n"); + + if (reg & ERR_ECRC) + dev_dbg(dra7xx->dev, "ECRC Error\n"); + + if (reg & PME_TURN_OFF) + dev_dbg(dra7xx->dev, + "Power Management Event Turn-Off message received\n"); + + if (reg & PME_TO_ACK) + dev_dbg(dra7xx->dev, + "Power Management Turn-Off Ack message received\n"); + + if (reg & PM_PME) + dev_dbg(dra7xx->dev, + "PM Power Management Event message received\n"); + + if (reg & LINK_REQ_RST) + dev_dbg(dra7xx->dev, "Link Request Reset\n"); + + if (reg & LINK_UP_EVT) + dev_dbg(dra7xx->dev, "Link-up state change\n"); + + if (reg & CFG_BME_EVT) + dev_dbg(dra7xx->dev, "CFG 'Bus Master Enable' change\n"); + + if (reg & CFG_MSE_EVT) + dev_dbg(dra7xx->dev, "CFG 'Memory Space Enable' change\n"); + + dra7xx_pcie_writel(dra7xx, PCIECTRL_DRA7XX_CONF_IRQSTATUS_MAIN, reg); + + return IRQ_HANDLED; +} + +static int add_pcie_port(struct dra7xx_pcie *dra7xx, + struct platform_device *pdev) +{ + int ret; + struct pcie_port *pp; + struct resource *res; + struct device *dev = &pdev->dev; + + pp = &dra7xx->pp; + pp->dev = dev; + pp->ops = &dra7xx_pcie_host_ops; + + pp->irq = platform_get_irq(pdev, 1); + if (pp->irq < 0) { + dev_err(dev, "missing IRQ resource\n"); + return -EINVAL; + } + + ret = devm_request_irq(&pdev->dev, pp->irq, + dra7xx_pcie_msi_irq_handler, IRQF_SHARED, + "dra7-pcie-msi", pp); + if (ret) { + dev_err(&pdev->dev, "failed to request irq\n"); + return ret; + } + + if (!IS_ENABLED(CONFIG_PCI_MSI)) { + ret = dra7xx_pcie_init_irq_domain(pp); + if (ret < 0) + return ret; + } + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "rc_dbics"); + pp->dbi_base = devm_ioremap(dev, res->start, resource_size(res)); + if (!pp->dbi_base) + return -ENOMEM; + + ret = dw_pcie_host_init(pp); + if (ret) { + dev_err(dra7xx->dev, "failed to initialize host\n"); + return ret; + } + + return 0; +} + +static int __init dra7xx_pcie_probe(struct platform_device *pdev) +{ + u32 reg; + int ret; + int irq; + int i; + int phy_count; + struct phy **phy; + void __iomem *base; + struct resource *res; + struct dra7xx_pcie *dra7xx; + struct device *dev = &pdev->dev; + struct device_node *np = dev->of_node; + char name[10]; + + dra7xx = devm_kzalloc(dev, sizeof(*dra7xx), GFP_KERNEL); + if (!dra7xx) + return -ENOMEM; + + irq = platform_get_irq(pdev, 0); + if (irq < 0) { + dev_err(dev, "missing IRQ resource\n"); + return -EINVAL; + } + + ret = devm_request_irq(dev, irq, dra7xx_pcie_irq_handler, + IRQF_SHARED, "dra7xx-pcie-main", dra7xx); + if (ret) { + dev_err(dev, "failed to request irq\n"); + return ret; + } + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "ti_conf"); + base = devm_ioremap_nocache(dev, res->start, resource_size(res)); + if (!base) + return -ENOMEM; + + phy_count = of_property_count_strings(np, "phy-names"); + if (phy_count < 0) { + dev_err(dev, "unable to find the strings\n"); + return phy_count; + } + + phy = devm_kzalloc(dev, sizeof(*phy) * phy_count, GFP_KERNEL); + if (!phy) + return -ENOMEM; + + for (i = 0; i < phy_count; i++) { + snprintf(name, sizeof(name), "pcie-phy%d", i); + phy[i] = devm_phy_get(dev, name); + if (IS_ERR(phy[i])) + return PTR_ERR(phy[i]); + + ret = phy_init(phy[i]); + if (ret < 0) + goto err_phy; + + ret = phy_power_on(phy[i]); + if (ret < 0) { + phy_exit(phy[i]); + goto err_phy; + } + } + + dra7xx->base = base; + dra7xx->phy = phy; + dra7xx->dev = dev; + dra7xx->phy_count = phy_count; + + pm_runtime_enable(dev); + ret = pm_runtime_get_sync(dev); + if (IS_ERR_VALUE(ret)) { + dev_err(dev, "pm_runtime_get_sync failed\n"); + goto err_phy; + } + + reg = dra7xx_pcie_readl(dra7xx, PCIECTRL_DRA7XX_CONF_DEVICE_CMD); + reg &= ~LTSSM_EN; + dra7xx_pcie_writel(dra7xx, PCIECTRL_DRA7XX_CONF_DEVICE_CMD, reg); + + platform_set_drvdata(pdev, dra7xx); + + ret = add_pcie_port(dra7xx, pdev); + if (ret < 0) + goto err_add_port; + + return 0; + +err_add_port: + pm_runtime_put(dev); + pm_runtime_disable(dev); + +err_phy: + while (--i >= 0) { + phy_power_off(phy[i]); + phy_exit(phy[i]); + } + + return ret; +} + +static int __exit dra7xx_pcie_remove(struct platform_device *pdev) +{ + struct dra7xx_pcie *dra7xx = platform_get_drvdata(pdev); + struct pcie_port *pp = &dra7xx->pp; + struct device *dev = &pdev->dev; + int count = dra7xx->phy_count; + + if (pp->irq_domain) + irq_domain_remove(pp->irq_domain); + pm_runtime_put(dev); + pm_runtime_disable(dev); + while (count--) { + phy_power_off(dra7xx->phy[count]); + phy_exit(dra7xx->phy[count]); + } + + return 0; +} + +static const struct of_device_id of_dra7xx_pcie_match[] = { + { .compatible = "ti,dra7-pcie", }, + {}, +}; +MODULE_DEVICE_TABLE(of, of_dra7xx_pcie_match); + +static struct platform_driver dra7xx_pcie_driver = { + .remove = __exit_p(dra7xx_pcie_remove), + .driver = { + .name = "dra7-pcie", + .owner = THIS_MODULE, + .of_match_table = of_dra7xx_pcie_match, + }, +}; + +module_platform_driver_probe(dra7xx_pcie_driver, dra7xx_pcie_probe); + +MODULE_AUTHOR("Kishon Vijay Abraham I <kishon@ti.com>"); +MODULE_DESCRIPTION("TI PCIe controller driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/host/pci-tegra.c b/drivers/pci/host/pci-tegra.c index abd65784618d..0fb0fdb223d5 100644 --- a/drivers/pci/host/pci-tegra.c +++ b/drivers/pci/host/pci-tegra.c @@ -25,6 +25,7 @@ */ #include <linux/clk.h> +#include <linux/debugfs.h> #include <linux/delay.h> #include <linux/export.h> #include <linux/interrupt.h> @@ -276,6 +277,7 @@ struct tegra_pcie { unsigned int num_supplies; const struct tegra_pcie_soc_data *soc_data; + struct dentry *debugfs; }; struct tegra_pcie_port { @@ -1739,6 +1741,115 @@ static const struct of_device_id tegra_pcie_of_match[] = { }; MODULE_DEVICE_TABLE(of, tegra_pcie_of_match); +static void *tegra_pcie_ports_seq_start(struct seq_file *s, loff_t *pos) +{ + struct tegra_pcie *pcie = s->private; + + if (list_empty(&pcie->ports)) + return NULL; + + seq_printf(s, "Index Status\n"); + + return seq_list_start(&pcie->ports, *pos); +} + +static void *tegra_pcie_ports_seq_next(struct seq_file *s, void *v, loff_t *pos) +{ + struct tegra_pcie *pcie = s->private; + + return seq_list_next(v, &pcie->ports, pos); +} + +static void tegra_pcie_ports_seq_stop(struct seq_file *s, void *v) +{ +} + +static int tegra_pcie_ports_seq_show(struct seq_file *s, void *v) +{ + bool up = false, active = false; + struct tegra_pcie_port *port; + unsigned int value; + + port = list_entry(v, struct tegra_pcie_port, list); + + value = readl(port->base + RP_VEND_XP); + + if (value & RP_VEND_XP_DL_UP) + up = true; + + value = readl(port->base + RP_LINK_CONTROL_STATUS); + + if (value & RP_LINK_CONTROL_STATUS_DL_LINK_ACTIVE) + active = true; + + seq_printf(s, "%2u ", port->index); + + if (up) + seq_printf(s, "up"); + + if (active) { + if (up) + seq_printf(s, ", "); + + seq_printf(s, "active"); + } + + seq_printf(s, "\n"); + return 0; +} + +static const struct seq_operations tegra_pcie_ports_seq_ops = { + .start = tegra_pcie_ports_seq_start, + .next = tegra_pcie_ports_seq_next, + .stop = tegra_pcie_ports_seq_stop, + .show = tegra_pcie_ports_seq_show, +}; + +static int tegra_pcie_ports_open(struct inode *inode, struct file *file) +{ + struct tegra_pcie *pcie = inode->i_private; + struct seq_file *s; + int err; + + err = seq_open(file, &tegra_pcie_ports_seq_ops); + if (err) + return err; + + s = file->private_data; + s->private = pcie; + + return 0; +} + +static const struct file_operations tegra_pcie_ports_ops = { + .owner = THIS_MODULE, + .open = tegra_pcie_ports_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static int tegra_pcie_debugfs_init(struct tegra_pcie *pcie) +{ + struct dentry *file; + + pcie->debugfs = debugfs_create_dir("pcie", NULL); + if (!pcie->debugfs) + return -ENOMEM; + + file = debugfs_create_file("ports", S_IFREG | S_IRUGO, pcie->debugfs, + pcie, &tegra_pcie_ports_ops); + if (!file) + goto remove; + + return 0; + +remove: + debugfs_remove_recursive(pcie->debugfs); + pcie->debugfs = NULL; + return -ENOMEM; +} + static int tegra_pcie_probe(struct platform_device *pdev) { const struct of_device_id *match; @@ -1793,6 +1904,13 @@ static int tegra_pcie_probe(struct platform_device *pdev) goto disable_msi; } + if (IS_ENABLED(CONFIG_DEBUG_FS)) { + err = tegra_pcie_debugfs_init(pcie); + if (err < 0) + dev_err(&pdev->dev, "failed to setup debugfs: %d\n", + err); + } + platform_set_drvdata(pdev, pcie); return 0; diff --git a/drivers/pci/host/pcie-designware.c b/drivers/pci/host/pcie-designware.c index 1eaf4df3618a..52bd3a143563 100644 --- a/drivers/pci/host/pcie-designware.c +++ b/drivers/pci/host/pcie-designware.c @@ -20,6 +20,7 @@ #include <linux/of_pci.h> #include <linux/pci.h> #include <linux/pci_regs.h> +#include <linux/platform_device.h> #include <linux/types.h> #include "pcie-designware.h" @@ -217,27 +218,47 @@ static int find_valid_pos0(struct pcie_port *pp, int msgvec, int pos, int *pos0) return 0; } +static void dw_pcie_msi_clear_irq(struct pcie_port *pp, int irq) +{ + unsigned int res, bit, val; + + res = (irq / 32) * 12; + bit = irq % 32; + dw_pcie_rd_own_conf(pp, PCIE_MSI_INTR0_ENABLE + res, 4, &val); + val &= ~(1 << bit); + dw_pcie_wr_own_conf(pp, PCIE_MSI_INTR0_ENABLE + res, 4, val); +} + static void clear_irq_range(struct pcie_port *pp, unsigned int irq_base, unsigned int nvec, unsigned int pos) { - unsigned int i, res, bit, val; + unsigned int i; for (i = 0; i < nvec; i++) { irq_set_msi_desc_off(irq_base, i, NULL); clear_bit(pos + i, pp->msi_irq_in_use); /* Disable corresponding interrupt on MSI controller */ - res = ((pos + i) / 32) * 12; - bit = (pos + i) % 32; - dw_pcie_rd_own_conf(pp, PCIE_MSI_INTR0_ENABLE + res, 4, &val); - val &= ~(1 << bit); - dw_pcie_wr_own_conf(pp, PCIE_MSI_INTR0_ENABLE + res, 4, val); + if (pp->ops->msi_clear_irq) + pp->ops->msi_clear_irq(pp, pos + i); + else + dw_pcie_msi_clear_irq(pp, pos + i); } } +static void dw_pcie_msi_set_irq(struct pcie_port *pp, int irq) +{ + unsigned int res, bit, val; + + res = (irq / 32) * 12; + bit = irq % 32; + dw_pcie_rd_own_conf(pp, PCIE_MSI_INTR0_ENABLE + res, 4, &val); + val |= 1 << bit; + dw_pcie_wr_own_conf(pp, PCIE_MSI_INTR0_ENABLE + res, 4, val); +} + static int assign_irq(int no_irqs, struct msi_desc *desc, int *pos) { - int res, bit, irq, pos0, pos1, i; - u32 val; + int irq, pos0, pos1, i; struct pcie_port *pp = sys_to_pcie(desc->dev->bus->sysdata); if (!pp) { @@ -281,11 +302,10 @@ static int assign_irq(int no_irqs, struct msi_desc *desc, int *pos) } set_bit(pos0 + i, pp->msi_irq_in_use); /*Enable corresponding interrupt in MSI interrupt controller */ - res = ((pos0 + i) / 32) * 12; - bit = (pos0 + i) % 32; - dw_pcie_rd_own_conf(pp, PCIE_MSI_INTR0_ENABLE + res, 4, &val); - val |= 1 << bit; - dw_pcie_wr_own_conf(pp, PCIE_MSI_INTR0_ENABLE + res, 4, val); + if (pp->ops->msi_set_irq) + pp->ops->msi_set_irq(pp, pos0 + i); + else + dw_pcie_msi_set_irq(pp, pos0 + i); } *pos = pos0; @@ -353,7 +373,10 @@ static int dw_msi_setup_irq(struct msi_chip *chip, struct pci_dev *pdev, */ desc->msi_attrib.multiple = msgvec; - msg.address_lo = virt_to_phys((void *)pp->msi_data); + if (pp->ops->get_msi_data) + msg.address_lo = pp->ops->get_msi_data(pp); + else + msg.address_lo = virt_to_phys((void *)pp->msi_data); msg.address_hi = 0x0; msg.data = pos; write_msi_msg(irq, &msg); @@ -396,10 +419,35 @@ static const struct irq_domain_ops msi_domain_ops = { int __init dw_pcie_host_init(struct pcie_port *pp) { struct device_node *np = pp->dev->of_node; + struct platform_device *pdev = to_platform_device(pp->dev); struct of_pci_range range; struct of_pci_range_parser parser; - u32 val; - int i; + struct resource *cfg_res; + u32 val, na, ns; + const __be32 *addrp; + int i, index; + + /* Find the address cell size and the number of cells in order to get + * the untranslated address. + */ + of_property_read_u32(np, "#address-cells", &na); + ns = of_n_size_cells(np); + + cfg_res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "config"); + if (cfg_res) { + pp->config.cfg0_size = resource_size(cfg_res)/2; + pp->config.cfg1_size = resource_size(cfg_res)/2; + pp->cfg0_base = cfg_res->start; + pp->cfg1_base = cfg_res->start + pp->config.cfg0_size; + + /* Find the untranslated configuration space address */ + index = of_property_match_string(np, "reg-names", "config"); + addrp = of_get_address(np, index, false, false); + pp->cfg0_mod_base = of_read_number(addrp, ns); + pp->cfg1_mod_base = pp->cfg0_mod_base + pp->config.cfg0_size; + } else { + dev_err(pp->dev, "missing *config* reg space\n"); + } if (of_pci_range_parser_init(&parser, np)) { dev_err(pp->dev, "missing ranges property\n"); @@ -422,17 +470,33 @@ int __init dw_pcie_host_init(struct pcie_port *pp) pp->config.io_size = resource_size(&pp->io); pp->config.io_bus_addr = range.pci_addr; pp->io_base = range.cpu_addr; + + /* Find the untranslated IO space address */ + pp->io_mod_base = of_read_number(parser.range - + parser.np + na, ns); } if (restype == IORESOURCE_MEM) { of_pci_range_to_resource(&range, np, &pp->mem); pp->mem.name = "MEM"; pp->config.mem_size = resource_size(&pp->mem); pp->config.mem_bus_addr = range.pci_addr; + + /* Find the untranslated MEM space address */ + pp->mem_mod_base = of_read_number(parser.range - + parser.np + na, ns); } if (restype == 0) { of_pci_range_to_resource(&range, np, &pp->cfg); pp->config.cfg0_size = resource_size(&pp->cfg)/2; pp->config.cfg1_size = resource_size(&pp->cfg)/2; + pp->cfg0_base = pp->cfg.start; + pp->cfg1_base = pp->cfg.start + pp->config.cfg0_size; + + /* Find the untranslated configuration space address */ + pp->cfg0_mod_base = of_read_number(parser.range - + parser.np + na, ns); + pp->cfg1_mod_base = pp->cfg0_mod_base + + pp->config.cfg0_size; } } @@ -445,8 +509,6 @@ int __init dw_pcie_host_init(struct pcie_port *pp) } } - pp->cfg0_base = pp->cfg.start; - pp->cfg1_base = pp->cfg.start + pp->config.cfg0_size; pp->mem_base = pp->mem.start; pp->va_cfg0_base = devm_ioremap(pp->dev, pp->cfg0_base, @@ -509,9 +571,9 @@ static void dw_pcie_prog_viewport_cfg0(struct pcie_port *pp, u32 busdev) /* Program viewport 0 : OUTBOUND : CFG0 */ dw_pcie_writel_rc(pp, PCIE_ATU_REGION_OUTBOUND | PCIE_ATU_REGION_INDEX0, PCIE_ATU_VIEWPORT); - dw_pcie_writel_rc(pp, pp->cfg0_base, PCIE_ATU_LOWER_BASE); - dw_pcie_writel_rc(pp, (pp->cfg0_base >> 32), PCIE_ATU_UPPER_BASE); - dw_pcie_writel_rc(pp, pp->cfg0_base + pp->config.cfg0_size - 1, + dw_pcie_writel_rc(pp, pp->cfg0_mod_base, PCIE_ATU_LOWER_BASE); + dw_pcie_writel_rc(pp, (pp->cfg0_mod_base >> 32), PCIE_ATU_UPPER_BASE); + dw_pcie_writel_rc(pp, pp->cfg0_mod_base + pp->config.cfg0_size - 1, PCIE_ATU_LIMIT); dw_pcie_writel_rc(pp, busdev, PCIE_ATU_LOWER_TARGET); dw_pcie_writel_rc(pp, 0, PCIE_ATU_UPPER_TARGET); @@ -525,9 +587,9 @@ static void dw_pcie_prog_viewport_cfg1(struct pcie_port *pp, u32 busdev) dw_pcie_writel_rc(pp, PCIE_ATU_REGION_OUTBOUND | PCIE_ATU_REGION_INDEX1, PCIE_ATU_VIEWPORT); dw_pcie_writel_rc(pp, PCIE_ATU_TYPE_CFG1, PCIE_ATU_CR1); - dw_pcie_writel_rc(pp, pp->cfg1_base, PCIE_ATU_LOWER_BASE); - dw_pcie_writel_rc(pp, (pp->cfg1_base >> 32), PCIE_ATU_UPPER_BASE); - dw_pcie_writel_rc(pp, pp->cfg1_base + pp->config.cfg1_size - 1, + dw_pcie_writel_rc(pp, pp->cfg1_mod_base, PCIE_ATU_LOWER_BASE); + dw_pcie_writel_rc(pp, (pp->cfg1_mod_base >> 32), PCIE_ATU_UPPER_BASE); + dw_pcie_writel_rc(pp, pp->cfg1_mod_base + pp->config.cfg1_size - 1, PCIE_ATU_LIMIT); dw_pcie_writel_rc(pp, busdev, PCIE_ATU_LOWER_TARGET); dw_pcie_writel_rc(pp, 0, PCIE_ATU_UPPER_TARGET); @@ -540,9 +602,9 @@ static void dw_pcie_prog_viewport_mem_outbound(struct pcie_port *pp) dw_pcie_writel_rc(pp, PCIE_ATU_REGION_OUTBOUND | PCIE_ATU_REGION_INDEX0, PCIE_ATU_VIEWPORT); dw_pcie_writel_rc(pp, PCIE_ATU_TYPE_MEM, PCIE_ATU_CR1); - dw_pcie_writel_rc(pp, pp->mem_base, PCIE_ATU_LOWER_BASE); - dw_pcie_writel_rc(pp, (pp->mem_base >> 32), PCIE_ATU_UPPER_BASE); - dw_pcie_writel_rc(pp, pp->mem_base + pp->config.mem_size - 1, + dw_pcie_writel_rc(pp, pp->mem_mod_base, PCIE_ATU_LOWER_BASE); + dw_pcie_writel_rc(pp, (pp->mem_mod_base >> 32), PCIE_ATU_UPPER_BASE); + dw_pcie_writel_rc(pp, pp->mem_mod_base + pp->config.mem_size - 1, PCIE_ATU_LIMIT); dw_pcie_writel_rc(pp, pp->config.mem_bus_addr, PCIE_ATU_LOWER_TARGET); dw_pcie_writel_rc(pp, upper_32_bits(pp->config.mem_bus_addr), @@ -556,9 +618,9 @@ static void dw_pcie_prog_viewport_io_outbound(struct pcie_port *pp) dw_pcie_writel_rc(pp, PCIE_ATU_REGION_OUTBOUND | PCIE_ATU_REGION_INDEX1, PCIE_ATU_VIEWPORT); dw_pcie_writel_rc(pp, PCIE_ATU_TYPE_IO, PCIE_ATU_CR1); - dw_pcie_writel_rc(pp, pp->io_base, PCIE_ATU_LOWER_BASE); - dw_pcie_writel_rc(pp, (pp->io_base >> 32), PCIE_ATU_UPPER_BASE); - dw_pcie_writel_rc(pp, pp->io_base + pp->config.io_size - 1, + dw_pcie_writel_rc(pp, pp->io_mod_base, PCIE_ATU_LOWER_BASE); + dw_pcie_writel_rc(pp, (pp->io_mod_base >> 32), PCIE_ATU_UPPER_BASE); + dw_pcie_writel_rc(pp, pp->io_mod_base + pp->config.io_size - 1, PCIE_ATU_LIMIT); dw_pcie_writel_rc(pp, pp->config.io_bus_addr, PCIE_ATU_LOWER_TARGET); dw_pcie_writel_rc(pp, upper_32_bits(pp->config.io_bus_addr), @@ -656,7 +718,11 @@ static int dw_pcie_rd_conf(struct pci_bus *bus, u32 devfn, int where, } if (bus->number != pp->root_bus_nr) - ret = dw_pcie_rd_other_conf(pp, bus, devfn, + if (pp->ops->rd_other_conf) + ret = pp->ops->rd_other_conf(pp, bus, devfn, + where, size, val); + else + ret = dw_pcie_rd_other_conf(pp, bus, devfn, where, size, val); else ret = dw_pcie_rd_own_conf(pp, where, size, val); @@ -679,7 +745,11 @@ static int dw_pcie_wr_conf(struct pci_bus *bus, u32 devfn, return PCIBIOS_DEVICE_NOT_FOUND; if (bus->number != pp->root_bus_nr) - ret = dw_pcie_wr_other_conf(pp, bus, devfn, + if (pp->ops->wr_other_conf) + ret = pp->ops->wr_other_conf(pp, bus, devfn, + where, size, val); + else + ret = dw_pcie_wr_other_conf(pp, bus, devfn, where, size, val); else ret = dw_pcie_wr_own_conf(pp, where, size, val); diff --git a/drivers/pci/host/pcie-designware.h b/drivers/pci/host/pcie-designware.h index 77f592faa7bf..daf81f922cda 100644 --- a/drivers/pci/host/pcie-designware.h +++ b/drivers/pci/host/pcie-designware.h @@ -36,11 +36,15 @@ struct pcie_port { u8 root_bus_nr; void __iomem *dbi_base; u64 cfg0_base; + u64 cfg0_mod_base; void __iomem *va_cfg0_base; u64 cfg1_base; + u64 cfg1_mod_base; void __iomem *va_cfg1_base; u64 io_base; + u64 io_mod_base; u64 mem_base; + u64 mem_mod_base; struct resource cfg; struct resource io; struct resource mem; @@ -61,8 +65,15 @@ struct pcie_host_ops { u32 val, void __iomem *dbi_base); int (*rd_own_conf)(struct pcie_port *pp, int where, int size, u32 *val); int (*wr_own_conf)(struct pcie_port *pp, int where, int size, u32 val); + int (*rd_other_conf)(struct pcie_port *pp, struct pci_bus *bus, + unsigned int devfn, int where, int size, u32 *val); + int (*wr_other_conf)(struct pcie_port *pp, struct pci_bus *bus, + unsigned int devfn, int where, int size, u32 val); int (*link_up)(struct pcie_port *pp); void (*host_init)(struct pcie_port *pp); + void (*msi_set_irq)(struct pcie_port *pp, int irq); + void (*msi_clear_irq)(struct pcie_port *pp, int irq); + u32 (*get_msi_data)(struct pcie_port *pp); }; int dw_pcie_cfg_read(void __iomem *addr, int where, int size, u32 *val); diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c index df3306019a7e..d81f3cc43ff1 100644 --- a/drivers/scsi/scsi.c +++ b/drivers/scsi/scsi.c @@ -377,6 +377,10 @@ scsi_alloc_host_cmd_pool(struct Scsi_Host *shost) pool->slab_flags |= SLAB_CACHE_DMA; pool->gfp_mask = __GFP_DMA; } + + if (hostt->cmd_size) + hostt->cmd_pool = pool; + return pool; } @@ -421,8 +425,10 @@ out: out_free_slab: kmem_cache_destroy(pool->cmd_slab); out_free_pool: - if (hostt->cmd_size) + if (hostt->cmd_size) { scsi_free_host_cmd_pool(pool); + hostt->cmd_pool = NULL; + } goto out; } @@ -444,8 +450,10 @@ static void scsi_put_host_cmd_pool(struct Scsi_Host *shost) if (!--pool->users) { kmem_cache_destroy(pool->cmd_slab); kmem_cache_destroy(pool->sense_slab); - if (hostt->cmd_size) + if (hostt->cmd_size) { scsi_free_host_cmd_pool(pool); + hostt->cmd_pool = NULL; + } } mutex_unlock(&host_cmd_pool_mutex); } diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 9c44392b748f..ce62e8798cc8 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1774,7 +1774,7 @@ static void scsi_request_fn(struct request_queue *q) blk_requeue_request(q, req); atomic_dec(&sdev->device_busy); out_delay: - if (atomic_read(&sdev->device_busy) && !scsi_device_blocked(sdev)) + if (!atomic_read(&sdev->device_busy) && !scsi_device_blocked(sdev)) blk_delay_queue(q, SCSI_QUEUE_DELAY); } @@ -192,7 +192,6 @@ static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages) } file->f_flags = O_RDWR; - file->private_data = ctx; return file; } @@ -202,7 +201,7 @@ static struct dentry *aio_mount(struct file_system_type *fs_type, static const struct dentry_operations ops = { .d_dname = simple_dname, }; - return mount_pseudo(fs_type, "aio:", NULL, &ops, 0xa10a10a1); + return mount_pseudo(fs_type, "aio:", NULL, &ops, AIO_RING_MAGIC); } /* aio_setup @@ -556,8 +555,7 @@ static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm) struct aio_ring *ring; spin_lock(&mm->ioctx_lock); - rcu_read_lock(); - table = rcu_dereference(mm->ioctx_table); + table = rcu_dereference_raw(mm->ioctx_table); while (1) { if (table) @@ -565,7 +563,6 @@ static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm) if (!table->table[i]) { ctx->id = i; table->table[i] = ctx; - rcu_read_unlock(); spin_unlock(&mm->ioctx_lock); /* While kioctx setup is in progress, @@ -579,8 +576,6 @@ static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm) } new_nr = (table ? table->nr : 1) * 4; - - rcu_read_unlock(); spin_unlock(&mm->ioctx_lock); table = kzalloc(sizeof(*table) + sizeof(struct kioctx *) * @@ -591,8 +586,7 @@ static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm) table->nr = new_nr; spin_lock(&mm->ioctx_lock); - rcu_read_lock(); - old = rcu_dereference(mm->ioctx_table); + old = rcu_dereference_raw(mm->ioctx_table); if (!old) { rcu_assign_pointer(mm->ioctx_table, table); @@ -739,12 +733,9 @@ static int kill_ioctx(struct mm_struct *mm, struct kioctx *ctx, spin_lock(&mm->ioctx_lock); - rcu_read_lock(); - table = rcu_dereference(mm->ioctx_table); - + table = rcu_dereference_raw(mm->ioctx_table); WARN_ON(ctx != table->table[ctx->id]); table->table[ctx->id] = NULL; - rcu_read_unlock(); spin_unlock(&mm->ioctx_lock); /* percpu_ref_kill() will do the necessary call_rcu() */ @@ -793,40 +784,30 @@ EXPORT_SYMBOL(wait_on_sync_kiocb); */ void exit_aio(struct mm_struct *mm) { - struct kioctx_table *table; - struct kioctx *ctx; - unsigned i = 0; - - while (1) { - rcu_read_lock(); - table = rcu_dereference(mm->ioctx_table); - - do { - if (!table || i >= table->nr) { - rcu_read_unlock(); - rcu_assign_pointer(mm->ioctx_table, NULL); - if (table) - kfree(table); - return; - } + struct kioctx_table *table = rcu_dereference_raw(mm->ioctx_table); + int i; - ctx = table->table[i++]; - } while (!ctx); + if (!table) + return; - rcu_read_unlock(); + for (i = 0; i < table->nr; ++i) { + struct kioctx *ctx = table->table[i]; + if (!ctx) + continue; /* - * We don't need to bother with munmap() here - - * exit_mmap(mm) is coming and it'll unmap everything. - * Since aio_free_ring() uses non-zero ->mmap_size - * as indicator that it needs to unmap the area, - * just set it to 0; aio_free_ring() is the only - * place that uses ->mmap_size, so it's safe. + * We don't need to bother with munmap() here - exit_mmap(mm) + * is coming and it'll unmap everything. And we simply can't, + * this is not necessarily our ->mm. + * Since kill_ioctx() uses non-zero ->mmap_size as indicator + * that it needs to unmap the area, just set it to 0. */ ctx->mmap_size = 0; - kill_ioctx(mm, ctx, NULL); } + + RCU_INIT_POINTER(mm->ioctx_table, NULL); + kfree(table); } static void put_reqs_available(struct kioctx *ctx, unsigned nr) @@ -834,10 +815,8 @@ static void put_reqs_available(struct kioctx *ctx, unsigned nr) struct kioctx_cpu *kcpu; unsigned long flags; - preempt_disable(); - kcpu = this_cpu_ptr(ctx->cpu); - local_irq_save(flags); + kcpu = this_cpu_ptr(ctx->cpu); kcpu->reqs_available += nr; while (kcpu->reqs_available >= ctx->req_batch * 2) { @@ -846,7 +825,6 @@ static void put_reqs_available(struct kioctx *ctx, unsigned nr) } local_irq_restore(flags); - preempt_enable(); } static bool get_reqs_available(struct kioctx *ctx) @@ -855,10 +833,8 @@ static bool get_reqs_available(struct kioctx *ctx) bool ret = false; unsigned long flags; - preempt_disable(); - kcpu = this_cpu_ptr(ctx->cpu); - local_irq_save(flags); + kcpu = this_cpu_ptr(ctx->cpu); if (!kcpu->reqs_available) { int old, avail = atomic_read(&ctx->reqs_available); @@ -878,7 +854,6 @@ static bool get_reqs_available(struct kioctx *ctx) kcpu->reqs_available--; out: local_irq_restore(flags); - preempt_enable(); return ret; } @@ -1047,7 +1022,7 @@ void aio_complete(struct kiocb *iocb, long res, long res2) } EXPORT_SYMBOL(aio_complete); -/* aio_read_events +/* aio_read_events_ring * Pull an event off of the ioctx's event ring. Returns the number of * events fetched */ @@ -1270,12 +1245,12 @@ static ssize_t aio_setup_vectored_rw(struct kiocb *kiocb, if (compat) ret = compat_rw_copy_check_uvector(rw, (struct compat_iovec __user *)buf, - *nr_segs, 1, *iovec, iovec); + *nr_segs, UIO_FASTIOV, *iovec, iovec); else #endif ret = rw_copy_check_uvector(rw, (struct iovec __user *)buf, - *nr_segs, 1, *iovec, iovec); + *nr_segs, UIO_FASTIOV, *iovec, iovec); if (ret < 0) return ret; @@ -1299,9 +1274,8 @@ static ssize_t aio_setup_single_vector(struct kiocb *kiocb, } /* - * aio_setup_iocb: - * Performs the initial checks and aio retry method - * setup for the kiocb at the time of io submission. + * aio_run_iocb: + * Performs the initial checks and io submission. */ static ssize_t aio_run_iocb(struct kiocb *req, unsigned opcode, char __user *buf, bool compat) @@ -1313,7 +1287,7 @@ static ssize_t aio_run_iocb(struct kiocb *req, unsigned opcode, fmode_t mode; aio_rw_op *rw_op; rw_iter_op *iter_op; - struct iovec inline_vec, *iovec = &inline_vec; + struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; struct iov_iter iter; switch (opcode) { @@ -1348,7 +1322,7 @@ rw_common: if (!ret) ret = rw_verify_area(rw, file, &req->ki_pos, req->ki_nbytes); if (ret < 0) { - if (iovec != &inline_vec) + if (iovec != inline_vecs) kfree(iovec); return ret; } @@ -1395,7 +1369,7 @@ rw_common: return -EINVAL; } - if (iovec != &inline_vec) + if (iovec != inline_vecs) kfree(iovec); if (ret != -EIOCBQUEUED) { diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index e25564bfcb46..54a201dac7f9 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -276,9 +276,8 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path, } if (ret > 0) goto next; - ret = ulist_add_merge(parents, eb->start, - (uintptr_t)eie, - (u64 *)&old, GFP_NOFS); + ret = ulist_add_merge_ptr(parents, eb->start, + eie, (void **)&old, GFP_NOFS); if (ret < 0) break; if (!ret && extent_item_pos) { @@ -1001,16 +1000,19 @@ again: ret = -EIO; goto out; } + btrfs_tree_read_lock(eb); + btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); ret = find_extent_in_eb(eb, bytenr, *extent_item_pos, &eie); + btrfs_tree_read_unlock_blocking(eb); free_extent_buffer(eb); if (ret < 0) goto out; ref->inode_list = eie; } - ret = ulist_add_merge(refs, ref->parent, - (uintptr_t)ref->inode_list, - (u64 *)&eie, GFP_NOFS); + ret = ulist_add_merge_ptr(refs, ref->parent, + ref->inode_list, + (void **)&eie, GFP_NOFS); if (ret < 0) goto out; if (!ret && extent_item_pos) { diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index 4794923c410c..43527fd78825 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -84,12 +84,6 @@ struct btrfs_inode { */ struct list_head delalloc_inodes; - /* - * list for tracking inodes that must be sent to disk before a - * rename or truncate commit - */ - struct list_head ordered_operations; - /* node for the red-black tree that links inodes in subvolume root */ struct rb_node rb_node; diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index aeab453b8e24..44ee5d2e52a4 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -280,9 +280,9 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans, WARN_ON(btrfs_header_generation(buf) > trans->transid); if (new_root_objectid == BTRFS_TREE_RELOC_OBJECTID) - ret = btrfs_inc_ref(trans, root, cow, 1, 1); + ret = btrfs_inc_ref(trans, root, cow, 1); else - ret = btrfs_inc_ref(trans, root, cow, 0, 1); + ret = btrfs_inc_ref(trans, root, cow, 0); if (ret) return ret; @@ -1035,14 +1035,14 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, if ((owner == root->root_key.objectid || root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) && !(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF)) { - ret = btrfs_inc_ref(trans, root, buf, 1, 1); + ret = btrfs_inc_ref(trans, root, buf, 1); BUG_ON(ret); /* -ENOMEM */ if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) { - ret = btrfs_dec_ref(trans, root, buf, 0, 1); + ret = btrfs_dec_ref(trans, root, buf, 0); BUG_ON(ret); /* -ENOMEM */ - ret = btrfs_inc_ref(trans, root, cow, 1, 1); + ret = btrfs_inc_ref(trans, root, cow, 1); BUG_ON(ret); /* -ENOMEM */ } new_flags |= BTRFS_BLOCK_FLAG_FULL_BACKREF; @@ -1050,9 +1050,9 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) - ret = btrfs_inc_ref(trans, root, cow, 1, 1); + ret = btrfs_inc_ref(trans, root, cow, 1); else - ret = btrfs_inc_ref(trans, root, cow, 0, 1); + ret = btrfs_inc_ref(trans, root, cow, 0); BUG_ON(ret); /* -ENOMEM */ } if (new_flags != 0) { @@ -1069,11 +1069,11 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, if (flags & BTRFS_BLOCK_FLAG_FULL_BACKREF) { if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) - ret = btrfs_inc_ref(trans, root, cow, 1, 1); + ret = btrfs_inc_ref(trans, root, cow, 1); else - ret = btrfs_inc_ref(trans, root, cow, 0, 1); + ret = btrfs_inc_ref(trans, root, cow, 0); BUG_ON(ret); /* -ENOMEM */ - ret = btrfs_dec_ref(trans, root, buf, 1, 1); + ret = btrfs_dec_ref(trans, root, buf, 1); BUG_ON(ret); /* -ENOMEM */ } clean_tree_block(trans, root, buf); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index be91397f4e92..8e29b614fe93 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3326,9 +3326,9 @@ int btrfs_reserve_extent(struct btrfs_root *root, u64 num_bytes, u64 min_alloc_size, u64 empty_size, u64 hint_byte, struct btrfs_key *ins, int is_data, int delalloc); int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, - struct extent_buffer *buf, int full_backref, int no_quota); + struct extent_buffer *buf, int full_backref); int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, - struct extent_buffer *buf, int full_backref, int no_quota); + struct extent_buffer *buf, int full_backref); int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u64 num_bytes, u64 flags, diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 08e65e9cf2aa..d0ed9e664f7d 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -60,8 +60,6 @@ static void end_workqueue_fn(struct btrfs_work *work); static void free_fs_root(struct btrfs_root *root); static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info, int read_only); -static void btrfs_destroy_ordered_operations(struct btrfs_transaction *t, - struct btrfs_root *root); static void btrfs_destroy_ordered_extents(struct btrfs_root *root); static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, struct btrfs_root *root); @@ -3829,34 +3827,6 @@ static void btrfs_error_commit_super(struct btrfs_root *root) btrfs_cleanup_transaction(root); } -static void btrfs_destroy_ordered_operations(struct btrfs_transaction *t, - struct btrfs_root *root) -{ - struct btrfs_inode *btrfs_inode; - struct list_head splice; - - INIT_LIST_HEAD(&splice); - - mutex_lock(&root->fs_info->ordered_operations_mutex); - spin_lock(&root->fs_info->ordered_root_lock); - - list_splice_init(&t->ordered_operations, &splice); - while (!list_empty(&splice)) { - btrfs_inode = list_entry(splice.next, struct btrfs_inode, - ordered_operations); - - list_del_init(&btrfs_inode->ordered_operations); - spin_unlock(&root->fs_info->ordered_root_lock); - - btrfs_invalidate_inodes(btrfs_inode->root); - - spin_lock(&root->fs_info->ordered_root_lock); - } - - spin_unlock(&root->fs_info->ordered_root_lock); - mutex_unlock(&root->fs_info->ordered_operations_mutex); -} - static void btrfs_destroy_ordered_extents(struct btrfs_root *root) { struct btrfs_ordered_extent *ordered; @@ -4093,8 +4063,6 @@ again: void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, struct btrfs_root *root) { - btrfs_destroy_ordered_operations(cur_trans, root); - btrfs_destroy_delayed_refs(cur_trans, root); cur_trans->state = TRANS_STATE_COMMIT_START; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 813537f362f9..102ed3143976 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3057,7 +3057,7 @@ out: static int __btrfs_mod_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, - int full_backref, int inc, int no_quota) + int full_backref, int inc) { u64 bytenr; u64 num_bytes; @@ -3111,7 +3111,7 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans, key.offset -= btrfs_file_extent_offset(buf, fi); ret = process_func(trans, root, bytenr, num_bytes, parent, ref_root, key.objectid, - key.offset, no_quota); + key.offset, 1); if (ret) goto fail; } else { @@ -3119,7 +3119,7 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans, num_bytes = btrfs_level_size(root, level - 1); ret = process_func(trans, root, bytenr, num_bytes, parent, ref_root, level - 1, 0, - no_quota); + 1); if (ret) goto fail; } @@ -3130,15 +3130,15 @@ fail: } int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, - struct extent_buffer *buf, int full_backref, int no_quota) + struct extent_buffer *buf, int full_backref) { - return __btrfs_mod_ref(trans, root, buf, full_backref, 1, no_quota); + return __btrfs_mod_ref(trans, root, buf, full_backref, 1); } int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, - struct extent_buffer *buf, int full_backref, int no_quota) + struct extent_buffer *buf, int full_backref) { - return __btrfs_mod_ref(trans, root, buf, full_backref, 0, no_quota); + return __btrfs_mod_ref(trans, root, buf, full_backref, 0); } static int write_one_cache_group(struct btrfs_trans_handle *trans, @@ -7478,6 +7478,220 @@ reada: wc->reada_slot = slot; } +static int account_leaf_items(struct btrfs_trans_handle *trans, + struct btrfs_root *root, + struct extent_buffer *eb) +{ + int nr = btrfs_header_nritems(eb); + int i, extent_type, ret; + struct btrfs_key key; + struct btrfs_file_extent_item *fi; + u64 bytenr, num_bytes; + + for (i = 0; i < nr; i++) { + btrfs_item_key_to_cpu(eb, &key, i); + + if (key.type != BTRFS_EXTENT_DATA_KEY) + continue; + + fi = btrfs_item_ptr(eb, i, struct btrfs_file_extent_item); + /* filter out non qgroup-accountable extents */ + extent_type = btrfs_file_extent_type(eb, fi); + + if (extent_type == BTRFS_FILE_EXTENT_INLINE) + continue; + + bytenr = btrfs_file_extent_disk_bytenr(eb, fi); + if (!bytenr) + continue; + + num_bytes = btrfs_file_extent_disk_num_bytes(eb, fi); + + ret = btrfs_qgroup_record_ref(trans, root->fs_info, + root->objectid, + bytenr, num_bytes, + BTRFS_QGROUP_OPER_SUB_SUBTREE, 0); + if (ret) + return ret; + } + return 0; +} + +/* + * Walk up the tree from the bottom, freeing leaves and any interior + * nodes which have had all slots visited. If a node (leaf or + * interior) is freed, the node above it will have it's slot + * incremented. The root node will never be freed. + * + * At the end of this function, we should have a path which has all + * slots incremented to the next position for a search. If we need to + * read a new node it will be NULL and the node above it will have the + * correct slot selected for a later read. + * + * If we increment the root nodes slot counter past the number of + * elements, 1 is returned to signal completion of the search. + */ +static int adjust_slots_upwards(struct btrfs_root *root, + struct btrfs_path *path, int root_level) +{ + int level = 0; + int nr, slot; + struct extent_buffer *eb; + + if (root_level == 0) + return 1; + + while (level <= root_level) { + eb = path->nodes[level]; + nr = btrfs_header_nritems(eb); + path->slots[level]++; + slot = path->slots[level]; + if (slot >= nr || level == 0) { + /* + * Don't free the root - we will detect this + * condition after our loop and return a + * positive value for caller to stop walking the tree. + */ + if (level != root_level) { + btrfs_tree_unlock_rw(eb, path->locks[level]); + path->locks[level] = 0; + + free_extent_buffer(eb); + path->nodes[level] = NULL; + path->slots[level] = 0; + } + } else { + /* + * We have a valid slot to walk back down + * from. Stop here so caller can process these + * new nodes. + */ + break; + } + + level++; + } + + eb = path->nodes[root_level]; + if (path->slots[root_level] >= btrfs_header_nritems(eb)) + return 1; + + return 0; +} + +/* + * root_eb is the subtree root and is locked before this function is called. + */ +static int account_shared_subtree(struct btrfs_trans_handle *trans, + struct btrfs_root *root, + struct extent_buffer *root_eb, + u64 root_gen, + int root_level) +{ + int ret = 0; + int level; + struct extent_buffer *eb = root_eb; + struct btrfs_path *path = NULL; + + BUG_ON(root_level < 0 || root_level > BTRFS_MAX_LEVEL); + BUG_ON(root_eb == NULL); + + if (!root->fs_info->quota_enabled) + return 0; + + if (!extent_buffer_uptodate(root_eb)) { + ret = btrfs_read_buffer(root_eb, root_gen); + if (ret) + goto out; + } + + if (root_level == 0) { + ret = account_leaf_items(trans, root, root_eb); + goto out; + } + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + + /* + * Walk down the tree. Missing extent blocks are filled in as + * we go. Metadata is accounted every time we read a new + * extent block. + * + * When we reach a leaf, we account for file extent items in it, + * walk back up the tree (adjusting slot pointers as we go) + * and restart the search process. + */ + extent_buffer_get(root_eb); /* For path */ + path->nodes[root_level] = root_eb; + path->slots[root_level] = 0; + path->locks[root_level] = 0; /* so release_path doesn't try to unlock */ +walk_down: + level = root_level; + while (level >= 0) { + if (path->nodes[level] == NULL) { + int child_bsize = root->nodesize; + int parent_slot; + u64 child_gen; + u64 child_bytenr; + + /* We need to get child blockptr/gen from + * parent before we can read it. */ + eb = path->nodes[level + 1]; + parent_slot = path->slots[level + 1]; + child_bytenr = btrfs_node_blockptr(eb, parent_slot); + child_gen = btrfs_node_ptr_generation(eb, parent_slot); + + eb = read_tree_block(root, child_bytenr, child_bsize, + child_gen); + if (!eb || !extent_buffer_uptodate(eb)) { + ret = -EIO; + goto out; + } + + path->nodes[level] = eb; + path->slots[level] = 0; + + btrfs_tree_read_lock(eb); + btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); + path->locks[level] = BTRFS_READ_LOCK_BLOCKING; + + ret = btrfs_qgroup_record_ref(trans, root->fs_info, + root->objectid, + child_bytenr, + child_bsize, + BTRFS_QGROUP_OPER_SUB_SUBTREE, + 0); + if (ret) + goto out; + + } + + if (level == 0) { + ret = account_leaf_items(trans, root, path->nodes[level]); + if (ret) + goto out; + + /* Nonzero return here means we completed our search */ + ret = adjust_slots_upwards(root, path, root_level); + if (ret) + break; + + /* Restart search with new slots */ + goto walk_down; + } + + level--; + } + + ret = 0; +out: + btrfs_free_path(path); + + return ret; +} + /* * helper to process tree block while walking down the tree. * @@ -7532,9 +7746,9 @@ static noinline int walk_down_proc(struct btrfs_trans_handle *trans, /* wc->stage == UPDATE_BACKREF */ if (!(wc->flags[level] & flag)) { BUG_ON(!path->locks[level]); - ret = btrfs_inc_ref(trans, root, eb, 1, wc->for_reloc); + ret = btrfs_inc_ref(trans, root, eb, 1); BUG_ON(ret); /* -ENOMEM */ - ret = btrfs_dec_ref(trans, root, eb, 0, wc->for_reloc); + ret = btrfs_dec_ref(trans, root, eb, 0); BUG_ON(ret); /* -ENOMEM */ ret = btrfs_set_disk_extent_flags(trans, root, eb->start, eb->len, flag, @@ -7581,6 +7795,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans, int level = wc->level; int reada = 0; int ret = 0; + bool need_account = false; generation = btrfs_node_ptr_generation(path->nodes[level], path->slots[level]); @@ -7626,6 +7841,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans, if (wc->stage == DROP_REFERENCE) { if (wc->refs[level - 1] > 1) { + need_account = true; if (level == 1 && (wc->flags[0] & BTRFS_BLOCK_FLAG_FULL_BACKREF)) goto skip; @@ -7689,6 +7905,16 @@ skip: parent = 0; } + if (need_account) { + ret = account_shared_subtree(trans, root, next, + generation, level - 1); + if (ret) { + printk_ratelimited(KERN_ERR "BTRFS: %s Error " + "%d accounting shared subtree. Quota " + "is out of sync, rescan required.\n", + root->fs_info->sb->s_id, ret); + } + } ret = btrfs_free_extent(trans, root, bytenr, blocksize, parent, root->root_key.objectid, level - 1, 0, 0); BUG_ON(ret); /* -ENOMEM */ @@ -7769,12 +7995,17 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans, if (wc->refs[level] == 1) { if (level == 0) { if (wc->flags[level] & BTRFS_BLOCK_FLAG_FULL_BACKREF) - ret = btrfs_dec_ref(trans, root, eb, 1, - wc->for_reloc); + ret = btrfs_dec_ref(trans, root, eb, 1); else - ret = btrfs_dec_ref(trans, root, eb, 0, - wc->for_reloc); + ret = btrfs_dec_ref(trans, root, eb, 0); BUG_ON(ret); /* -ENOMEM */ + ret = account_leaf_items(trans, root, eb); + if (ret) { + printk_ratelimited(KERN_ERR "BTRFS: %s Error " + "%d accounting leaf items. Quota " + "is out of sync, rescan required.\n", + root->fs_info->sb->s_id, ret); + } } /* make block locked assertion in clean_tree_block happy */ if (!path->locks[level] && @@ -7900,6 +8131,8 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int level; bool root_dropped = false; + btrfs_debug(root->fs_info, "Drop subvolume %llu", root->objectid); + path = btrfs_alloc_path(); if (!path) { err = -ENOMEM; @@ -8025,6 +8258,24 @@ int btrfs_drop_snapshot(struct btrfs_root *root, goto out_end_trans; } + /* + * Qgroup update accounting is run from + * delayed ref handling. This usually works + * out because delayed refs are normally the + * only way qgroup updates are added. However, + * we may have added updates during our tree + * walk so run qgroups here to make sure we + * don't lose any updates. + */ + ret = btrfs_delayed_qgroup_accounting(trans, + root->fs_info); + if (ret) + printk_ratelimited(KERN_ERR "BTRFS: Failure %d " + "running qgroup updates " + "during snapshot delete. " + "Quota is out of sync, " + "rescan required.\n", ret); + btrfs_end_transaction_throttle(trans, tree_root); if (!for_reloc && btrfs_need_cleaner_sleep(root)) { pr_debug("BTRFS: drop snapshot early exit\n"); @@ -8078,6 +8329,14 @@ int btrfs_drop_snapshot(struct btrfs_root *root, } root_dropped = true; out_end_trans: + ret = btrfs_delayed_qgroup_accounting(trans, tree_root->fs_info); + if (ret) + printk_ratelimited(KERN_ERR "BTRFS: Failure %d " + "running qgroup updates " + "during snapshot delete. " + "Quota is out of sync, " + "rescan required.\n", ret); + btrfs_end_transaction_throttle(trans, tree_root); out_free: kfree(wc); diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index f46cfe45d686..54c84daec9b5 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -756,7 +756,7 @@ again: found_next = 1; if (ret != 0) goto insert; - slot = 0; + slot = path->slots[0]; } btrfs_item_key_to_cpu(path->nodes[0], &found_key, slot); if (found_key.objectid != BTRFS_EXTENT_CSUM_OBJECTID || diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 1f2b99cb55ea..d3afac292d67 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1838,33 +1838,9 @@ out: int btrfs_release_file(struct inode *inode, struct file *filp) { - /* - * ordered_data_close is set by settattr when we are about to truncate - * a file from a non-zero size to a zero size. This tries to - * flush down new bytes that may have been written if the - * application were using truncate to replace a file in place. - */ - if (test_and_clear_bit(BTRFS_INODE_ORDERED_DATA_CLOSE, - &BTRFS_I(inode)->runtime_flags)) { - struct btrfs_trans_handle *trans; - struct btrfs_root *root = BTRFS_I(inode)->root; - - /* - * We need to block on a committing transaction to keep us from - * throwing a ordered operation on to the list and causing - * something like sync to deadlock trying to flush out this - * inode. - */ - trans = btrfs_start_transaction(root, 0); - if (IS_ERR(trans)) - return PTR_ERR(trans); - btrfs_add_ordered_operation(trans, BTRFS_I(inode)->root, inode); - btrfs_end_transaction(trans, root); - if (inode->i_size > BTRFS_ORDERED_OPERATIONS_FLUSH_LIMIT) - filemap_flush(inode->i_mapping); - } if (filp->private_data) btrfs_ioctl_trans_end(filp); + filemap_flush(inode->i_mapping); return 0; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 3183742d6f0d..03708ef3deef 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -709,6 +709,18 @@ retry: unlock_extent(io_tree, async_extent->start, async_extent->start + async_extent->ram_size - 1); + + /* + * we need to redirty the pages if we decide to + * fallback to uncompressed IO, otherwise we + * will not submit these pages down to lower + * layers. + */ + extent_range_redirty_for_io(inode, + async_extent->start, + async_extent->start + + async_extent->ram_size - 1); + goto retry; } goto out_free; @@ -7939,27 +7951,6 @@ static int btrfs_truncate(struct inode *inode) BUG_ON(ret); /* - * setattr is responsible for setting the ordered_data_close flag, - * but that is only tested during the last file release. That - * could happen well after the next commit, leaving a great big - * window where new writes may get lost if someone chooses to write - * to this file after truncating to zero - * - * The inode doesn't have any dirty data here, and so if we commit - * this is a noop. If someone immediately starts writing to the inode - * it is very likely we'll catch some of their writes in this - * transaction, and the commit will find this file on the ordered - * data list with good things to send down. - * - * This is a best effort solution, there is still a window where - * using truncate to replace the contents of the file will - * end up with a zero length file after a crash. - */ - if (inode->i_size == 0 && test_bit(BTRFS_INODE_ORDERED_DATA_CLOSE, - &BTRFS_I(inode)->runtime_flags)) - btrfs_add_ordered_operation(trans, root, inode); - - /* * So if we truncate and then write and fsync we normally would just * write the extents that changed, which is a problem if we need to * first truncate that entire inode. So set this flag so we write out @@ -8106,7 +8097,6 @@ struct inode *btrfs_alloc_inode(struct super_block *sb) mutex_init(&ei->delalloc_mutex); btrfs_ordered_inode_tree_init(&ei->ordered_tree); INIT_LIST_HEAD(&ei->delalloc_inodes); - INIT_LIST_HEAD(&ei->ordered_operations); RB_CLEAR_NODE(&ei->rb_node); return inode; @@ -8146,17 +8136,6 @@ void btrfs_destroy_inode(struct inode *inode) if (!root) goto free; - /* - * Make sure we're properly removed from the ordered operation - * lists. - */ - smp_mb(); - if (!list_empty(&BTRFS_I(inode)->ordered_operations)) { - spin_lock(&root->fs_info->ordered_root_lock); - list_del_init(&BTRFS_I(inode)->ordered_operations); - spin_unlock(&root->fs_info->ordered_root_lock); - } - if (test_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, &BTRFS_I(inode)->runtime_flags)) { btrfs_info(root->fs_info, "inode %llu still on the orphan list", @@ -8338,12 +8317,10 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, ret = 0; /* - * we're using rename to replace one file with another. - * and the replacement file is large. Start IO on it now so - * we don't add too much work to the end of the transaction + * we're using rename to replace one file with another. Start IO on it + * now so we don't add too much work to the end of the transaction */ - if (new_inode && S_ISREG(old_inode->i_mode) && new_inode->i_size && - old_inode->i_size > BTRFS_ORDERED_OPERATIONS_FLUSH_LIMIT) + if (new_inode && S_ISREG(old_inode->i_mode) && new_inode->i_size) filemap_flush(old_inode->i_mapping); /* close the racy window with snapshot create/destroy ioctl */ @@ -8391,12 +8368,6 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, */ btrfs_pin_log_trans(root); } - /* - * make sure the inode gets flushed if it is replacing - * something. - */ - if (new_inode && new_inode->i_size && S_ISREG(old_inode->i_mode)) - btrfs_add_ordered_operation(trans, root, old_inode); inode_inc_iversion(old_dir); inode_inc_iversion(new_dir); diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 7187b14faa6c..963895c1f801 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -571,18 +571,6 @@ void btrfs_remove_ordered_extent(struct inode *inode, trace_btrfs_ordered_extent_remove(inode, entry); - /* - * we have no more ordered extents for this inode and - * no dirty pages. We can safely remove it from the - * list of ordered extents - */ - if (RB_EMPTY_ROOT(&tree->tree) && - !mapping_tagged(inode->i_mapping, PAGECACHE_TAG_DIRTY)) { - spin_lock(&root->fs_info->ordered_root_lock); - list_del_init(&BTRFS_I(inode)->ordered_operations); - spin_unlock(&root->fs_info->ordered_root_lock); - } - if (!root->nr_ordered_extents) { spin_lock(&root->fs_info->ordered_root_lock); BUG_ON(list_empty(&root->ordered_root)); @@ -687,81 +675,6 @@ void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr) } /* - * this is used during transaction commit to write all the inodes - * added to the ordered operation list. These files must be fully on - * disk before the transaction commits. - * - * we have two modes here, one is to just start the IO via filemap_flush - * and the other is to wait for all the io. When we wait, we have an - * extra check to make sure the ordered operation list really is empty - * before we return - */ -int btrfs_run_ordered_operations(struct btrfs_trans_handle *trans, - struct btrfs_root *root, int wait) -{ - struct btrfs_inode *btrfs_inode; - struct inode *inode; - struct btrfs_transaction *cur_trans = trans->transaction; - struct list_head splice; - struct list_head works; - struct btrfs_delalloc_work *work, *next; - int ret = 0; - - INIT_LIST_HEAD(&splice); - INIT_LIST_HEAD(&works); - - mutex_lock(&root->fs_info->ordered_extent_flush_mutex); - spin_lock(&root->fs_info->ordered_root_lock); - list_splice_init(&cur_trans->ordered_operations, &splice); - while (!list_empty(&splice)) { - btrfs_inode = list_entry(splice.next, struct btrfs_inode, - ordered_operations); - inode = &btrfs_inode->vfs_inode; - - list_del_init(&btrfs_inode->ordered_operations); - - /* - * the inode may be getting freed (in sys_unlink path). - */ - inode = igrab(inode); - if (!inode) - continue; - - if (!wait) - list_add_tail(&BTRFS_I(inode)->ordered_operations, - &cur_trans->ordered_operations); - spin_unlock(&root->fs_info->ordered_root_lock); - - work = btrfs_alloc_delalloc_work(inode, wait, 1); - if (!work) { - spin_lock(&root->fs_info->ordered_root_lock); - if (list_empty(&BTRFS_I(inode)->ordered_operations)) - list_add_tail(&btrfs_inode->ordered_operations, - &splice); - list_splice_tail(&splice, - &cur_trans->ordered_operations); - spin_unlock(&root->fs_info->ordered_root_lock); - ret = -ENOMEM; - goto out; - } - list_add_tail(&work->list, &works); - btrfs_queue_work(root->fs_info->flush_workers, - &work->work); - - cond_resched(); - spin_lock(&root->fs_info->ordered_root_lock); - } - spin_unlock(&root->fs_info->ordered_root_lock); -out: - list_for_each_entry_safe(work, next, &works, list) { - list_del_init(&work->list); - btrfs_wait_and_free_delalloc_work(work); - } - mutex_unlock(&root->fs_info->ordered_extent_flush_mutex); - return ret; -} - -/* * Used to start IO or wait for a given ordered extent to finish. * * If wait is one, this effectively waits on page writeback for all the pages @@ -1120,42 +1033,6 @@ out: return index; } - -/* - * add a given inode to the list of inodes that must be fully on - * disk before a transaction commit finishes. - * - * This basically gives us the ext3 style data=ordered mode, and it is mostly - * used to make sure renamed files are fully on disk. - * - * It is a noop if the inode is already fully on disk. - * - * If trans is not null, we'll do a friendly check for a transaction that - * is already flushing things and force the IO down ourselves. - */ -void btrfs_add_ordered_operation(struct btrfs_trans_handle *trans, - struct btrfs_root *root, struct inode *inode) -{ - struct btrfs_transaction *cur_trans = trans->transaction; - u64 last_mod; - - last_mod = max(BTRFS_I(inode)->generation, BTRFS_I(inode)->last_trans); - - /* - * if this file hasn't been changed since the last transaction - * commit, we can safely return without doing anything - */ - if (last_mod <= root->fs_info->last_trans_committed) - return; - - spin_lock(&root->fs_info->ordered_root_lock); - if (list_empty(&BTRFS_I(inode)->ordered_operations)) { - list_add_tail(&BTRFS_I(inode)->ordered_operations, - &cur_trans->ordered_operations); - } - spin_unlock(&root->fs_info->ordered_root_lock); -} - int __init ordered_data_init(void) { btrfs_ordered_extent_cache = kmem_cache_create("btrfs_ordered_extent", diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h index 246897058efb..d81a274d621e 100644 --- a/fs/btrfs/ordered-data.h +++ b/fs/btrfs/ordered-data.h @@ -190,11 +190,6 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset, struct btrfs_ordered_extent *ordered); int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr, u32 *sum, int len); -int btrfs_run_ordered_operations(struct btrfs_trans_handle *trans, - struct btrfs_root *root, int wait); -void btrfs_add_ordered_operation(struct btrfs_trans_handle *trans, - struct btrfs_root *root, - struct inode *inode); int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr); void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr); void btrfs_get_logged_extents(struct inode *inode, diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 98cb6b2630f9..b497498484be 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1201,6 +1201,50 @@ out: mutex_unlock(&fs_info->qgroup_ioctl_lock); return ret; } + +static int comp_oper_exist(struct btrfs_qgroup_operation *oper1, + struct btrfs_qgroup_operation *oper2) +{ + /* + * Ignore seq and type here, we're looking for any operation + * at all related to this extent on that root. + */ + if (oper1->bytenr < oper2->bytenr) + return -1; + if (oper1->bytenr > oper2->bytenr) + return 1; + if (oper1->ref_root < oper2->ref_root) + return -1; + if (oper1->ref_root > oper2->ref_root) + return 1; + return 0; +} + +static int qgroup_oper_exists(struct btrfs_fs_info *fs_info, + struct btrfs_qgroup_operation *oper) +{ + struct rb_node *n; + struct btrfs_qgroup_operation *cur; + int cmp; + + spin_lock(&fs_info->qgroup_op_lock); + n = fs_info->qgroup_op_tree.rb_node; + while (n) { + cur = rb_entry(n, struct btrfs_qgroup_operation, n); + cmp = comp_oper_exist(cur, oper); + if (cmp < 0) { + n = n->rb_right; + } else if (cmp) { + n = n->rb_left; + } else { + spin_unlock(&fs_info->qgroup_op_lock); + return -EEXIST; + } + } + spin_unlock(&fs_info->qgroup_op_lock); + return 0; +} + static int comp_oper(struct btrfs_qgroup_operation *oper1, struct btrfs_qgroup_operation *oper2) { @@ -1290,6 +1334,23 @@ int btrfs_qgroup_record_ref(struct btrfs_trans_handle *trans, oper->seq = atomic_inc_return(&fs_info->qgroup_op_seq); INIT_LIST_HEAD(&oper->elem.list); oper->elem.seq = 0; + + if (type == BTRFS_QGROUP_OPER_SUB_SUBTREE) { + /* + * If any operation for this bytenr/ref_root combo + * exists, then we know it's not exclusively owned and + * shouldn't be queued up. + * + * This also catches the case where we have a cloned + * extent that gets queued up multiple times during + * drop snapshot. + */ + if (qgroup_oper_exists(fs_info, oper)) { + kfree(oper); + return 0; + } + } + ret = insert_qgroup_oper(fs_info, oper); if (ret) { /* Shouldn't happen so have an assert for developers */ @@ -1884,6 +1945,111 @@ out: } /* + * Process a reference to a shared subtree. This type of operation is + * queued during snapshot removal when we encounter extents which are + * shared between more than one root. + */ +static int qgroup_subtree_accounting(struct btrfs_trans_handle *trans, + struct btrfs_fs_info *fs_info, + struct btrfs_qgroup_operation *oper) +{ + struct ulist *roots = NULL; + struct ulist_node *unode; + struct ulist_iterator uiter; + struct btrfs_qgroup_list *glist; + struct ulist *parents; + int ret = 0; + int err; + struct btrfs_qgroup *qg; + u64 root_obj = 0; + struct seq_list elem = {}; + + parents = ulist_alloc(GFP_NOFS); + if (!parents) + return -ENOMEM; + + btrfs_get_tree_mod_seq(fs_info, &elem); + ret = btrfs_find_all_roots(trans, fs_info, oper->bytenr, + elem.seq, &roots); + btrfs_put_tree_mod_seq(fs_info, &elem); + if (ret < 0) + return ret; + + if (roots->nnodes != 1) + goto out; + + ULIST_ITER_INIT(&uiter); + unode = ulist_next(roots, &uiter); /* Only want 1 so no need to loop */ + /* + * If we find our ref root then that means all refs + * this extent has to the root have not yet been + * deleted. In that case, we do nothing and let the + * last ref for this bytenr drive our update. + * + * This can happen for example if an extent is + * referenced multiple times in a snapshot (clone, + * etc). If we are in the middle of snapshot removal, + * queued updates for such an extent will find the + * root if we have not yet finished removing the + * snapshot. + */ + if (unode->val == oper->ref_root) + goto out; + + root_obj = unode->val; + BUG_ON(!root_obj); + + spin_lock(&fs_info->qgroup_lock); + qg = find_qgroup_rb(fs_info, root_obj); + if (!qg) + goto out_unlock; + + qg->excl += oper->num_bytes; + qg->excl_cmpr += oper->num_bytes; + qgroup_dirty(fs_info, qg); + + /* + * Adjust counts for parent groups. First we find all + * parents, then in the 2nd loop we do the adjustment + * while adding parents of the parents to our ulist. + */ + list_for_each_entry(glist, &qg->groups, next_group) { + err = ulist_add(parents, glist->group->qgroupid, + ptr_to_u64(glist->group), GFP_ATOMIC); + if (err < 0) { + ret = err; + goto out_unlock; + } + } + + ULIST_ITER_INIT(&uiter); + while ((unode = ulist_next(parents, &uiter))) { + qg = u64_to_ptr(unode->aux); + qg->excl += oper->num_bytes; + qg->excl_cmpr += oper->num_bytes; + qgroup_dirty(fs_info, qg); + + /* Add any parents of the parents */ + list_for_each_entry(glist, &qg->groups, next_group) { + err = ulist_add(parents, glist->group->qgroupid, + ptr_to_u64(glist->group), GFP_ATOMIC); + if (err < 0) { + ret = err; + goto out_unlock; + } + } + } + +out_unlock: + spin_unlock(&fs_info->qgroup_lock); + +out: + ulist_free(roots); + ulist_free(parents); + return ret; +} + +/* * btrfs_qgroup_account_ref is called for every ref that is added to or deleted * from the fs. First, all roots referencing the extent are searched, and * then the space is accounted accordingly to the different roots. The @@ -1920,6 +2086,9 @@ static int btrfs_qgroup_account(struct btrfs_trans_handle *trans, case BTRFS_QGROUP_OPER_SUB_SHARED: ret = qgroup_shared_accounting(trans, fs_info, oper); break; + case BTRFS_QGROUP_OPER_SUB_SUBTREE: + ret = qgroup_subtree_accounting(trans, fs_info, oper); + break; default: ASSERT(0); } diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index 5952ff1fbd7a..18cc68ca3090 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -44,6 +44,7 @@ enum btrfs_qgroup_operation_type { BTRFS_QGROUP_OPER_ADD_SHARED, BTRFS_QGROUP_OPER_SUB_EXCL, BTRFS_QGROUP_OPER_SUB_SHARED, + BTRFS_QGROUP_OPER_SUB_SUBTREE, }; struct btrfs_qgroup_operation { diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 67b48b9a03e0..c4124de4435b 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1665,6 +1665,21 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes) return 0; } +/* + * Calculate numbers for 'df', pessimistic in case of mixed raid profiles. + * + * If there's a redundant raid level at DATA block groups, use the respective + * multiplier to scale the sizes. + * + * Unused device space usage is based on simulating the chunk allocator + * algorithm that respects the device sizes, order of allocations and the + * 'alloc_start' value, this is a close approximation of the actual use but + * there are other factors that may change the result (like a new metadata + * chunk). + * + * FIXME: not accurate for mixed block groups, total and free/used are ok, + * available appears slightly larger. + */ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct btrfs_fs_info *fs_info = btrfs_sb(dentry->d_sb); @@ -1675,6 +1690,8 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) u64 total_free_data = 0; int bits = dentry->d_sb->s_blocksize_bits; __be32 *fsid = (__be32 *)fs_info->fsid; + unsigned factor = 1; + struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv; int ret; /* holding chunk_muext to avoid allocating new chunks */ @@ -1682,30 +1699,52 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) rcu_read_lock(); list_for_each_entry_rcu(found, head, list) { if (found->flags & BTRFS_BLOCK_GROUP_DATA) { + int i; + total_free_data += found->disk_total - found->disk_used; total_free_data -= btrfs_account_ro_block_groups_free_space(found); + + for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) { + if (!list_empty(&found->block_groups[i])) { + switch (i) { + case BTRFS_RAID_DUP: + case BTRFS_RAID_RAID1: + case BTRFS_RAID_RAID10: + factor = 2; + } + } + } } total_used += found->disk_used; } + rcu_read_unlock(); - buf->f_namelen = BTRFS_NAME_LEN; - buf->f_blocks = btrfs_super_total_bytes(disk_super) >> bits; - buf->f_bfree = buf->f_blocks - (total_used >> bits); - buf->f_bsize = dentry->d_sb->s_blocksize; - buf->f_type = BTRFS_SUPER_MAGIC; + buf->f_blocks = div_u64(btrfs_super_total_bytes(disk_super), factor); + buf->f_blocks >>= bits; + buf->f_bfree = buf->f_blocks - (div_u64(total_used, factor) >> bits); + + /* Account global block reserve as used, it's in logical size already */ + spin_lock(&block_rsv->lock); + buf->f_bfree -= block_rsv->size >> bits; + spin_unlock(&block_rsv->lock); + buf->f_bavail = total_free_data; ret = btrfs_calc_avail_data_space(fs_info->tree_root, &total_free_data); if (ret) { mutex_unlock(&fs_info->chunk_mutex); return ret; } - buf->f_bavail += total_free_data; + buf->f_bavail += div_u64(total_free_data, factor); buf->f_bavail = buf->f_bavail >> bits; mutex_unlock(&fs_info->chunk_mutex); + buf->f_type = BTRFS_SUPER_MAGIC; + buf->f_bsize = dentry->d_sb->s_blocksize; + buf->f_namelen = BTRFS_NAME_LEN; + /* We treat it as constant endianness (it doesn't matter _which_) because we want the fsid to come out the same whether mounted on a big-endian or little-endian host */ diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 5f379affdf23..d89c6d3542ca 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -218,7 +218,6 @@ loop: spin_lock_init(&cur_trans->delayed_refs.lock); INIT_LIST_HEAD(&cur_trans->pending_snapshots); - INIT_LIST_HEAD(&cur_trans->ordered_operations); INIT_LIST_HEAD(&cur_trans->pending_chunks); INIT_LIST_HEAD(&cur_trans->switch_commits); list_add_tail(&cur_trans->list, &fs_info->trans_list); @@ -1612,27 +1611,6 @@ static void cleanup_transaction(struct btrfs_trans_handle *trans, kmem_cache_free(btrfs_trans_handle_cachep, trans); } -static int btrfs_flush_all_pending_stuffs(struct btrfs_trans_handle *trans, - struct btrfs_root *root) -{ - int ret; - - ret = btrfs_run_delayed_items(trans, root); - if (ret) - return ret; - - /* - * rename don't use btrfs_join_transaction, so, once we - * set the transaction to blocked above, we aren't going - * to get any new ordered operations. We can safely run - * it here and no for sure that nothing new will be added - * to the list - */ - ret = btrfs_run_ordered_operations(trans, root, 1); - - return ret; -} - static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info) { if (btrfs_test_opt(fs_info->tree_root, FLUSHONCOMMIT)) @@ -1653,13 +1631,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, struct btrfs_transaction *prev_trans = NULL; int ret; - ret = btrfs_run_ordered_operations(trans, root, 0); - if (ret) { - btrfs_abort_transaction(trans, root, ret); - btrfs_end_transaction(trans, root); - return ret; - } - /* Stop the commit early if ->aborted is set */ if (unlikely(ACCESS_ONCE(cur_trans->aborted))) { ret = cur_trans->aborted; @@ -1740,7 +1711,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, if (ret) goto cleanup_transaction; - ret = btrfs_flush_all_pending_stuffs(trans, root); + ret = btrfs_run_delayed_items(trans, root); if (ret) goto cleanup_transaction; @@ -1748,7 +1719,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, extwriter_counter_read(cur_trans) == 0); /* some pending stuffs might be added after the previous flush. */ - ret = btrfs_flush_all_pending_stuffs(trans, root); + ret = btrfs_run_delayed_items(trans, root); if (ret) goto cleanup_transaction; diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 7dd558ed0716..579be51b27e5 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -55,7 +55,6 @@ struct btrfs_transaction { wait_queue_head_t writer_wait; wait_queue_head_t commit_wait; struct list_head pending_snapshots; - struct list_head ordered_operations; struct list_head pending_chunks; struct list_head switch_commits; struct btrfs_delayed_ref_root delayed_refs; diff --git a/fs/btrfs/ulist.h b/fs/btrfs/ulist.h index 7f78cbf5cf41..4c29db604bbe 100644 --- a/fs/btrfs/ulist.h +++ b/fs/btrfs/ulist.h @@ -57,6 +57,21 @@ void ulist_free(struct ulist *ulist); int ulist_add(struct ulist *ulist, u64 val, u64 aux, gfp_t gfp_mask); int ulist_add_merge(struct ulist *ulist, u64 val, u64 aux, u64 *old_aux, gfp_t gfp_mask); + +/* just like ulist_add_merge() but take a pointer for the aux data */ +static inline int ulist_add_merge_ptr(struct ulist *ulist, u64 val, void *aux, + void **old_aux, gfp_t gfp_mask) +{ +#if BITS_PER_LONG == 32 + u64 old64 = (uintptr_t)*old_aux; + int ret = ulist_add_merge(ulist, val, (uintptr_t)aux, &old64, gfp_mask); + *old_aux = (void *)((uintptr_t)old64); + return ret; +#else + return ulist_add_merge(ulist, val, (u64)aux, (u64 *)old_aux, gfp_mask); +#endif +} + struct ulist_node *ulist_next(struct ulist *ulist, struct ulist_iterator *uiter); diff --git a/fs/locks.c b/fs/locks.c index a6f54802d277..cb66fb05ad4a 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -247,6 +247,18 @@ void locks_free_lock(struct file_lock *fl) } EXPORT_SYMBOL(locks_free_lock); +static void +locks_dispose_list(struct list_head *dispose) +{ + struct file_lock *fl; + + while (!list_empty(dispose)) { + fl = list_first_entry(dispose, struct file_lock, fl_block); + list_del_init(&fl->fl_block); + locks_free_lock(fl); + } +} + void locks_init_lock(struct file_lock *fl) { memset(fl, 0, sizeof(struct file_lock)); @@ -285,7 +297,8 @@ EXPORT_SYMBOL(__locks_copy_lock); void locks_copy_lock(struct file_lock *new, struct file_lock *fl) { - locks_release_private(new); + /* "new" must be a freshly-initialized lock */ + WARN_ON_ONCE(new->fl_ops); __locks_copy_lock(new, fl); new->fl_file = fl->fl_file; @@ -650,12 +663,16 @@ static void locks_unlink_lock(struct file_lock **thisfl_p) * * Must be called with i_lock held! */ -static void locks_delete_lock(struct file_lock **thisfl_p) +static void locks_delete_lock(struct file_lock **thisfl_p, + struct list_head *dispose) { struct file_lock *fl = *thisfl_p; locks_unlink_lock(thisfl_p); - locks_free_lock(fl); + if (dispose) + list_add(&fl->fl_block, dispose); + else + locks_free_lock(fl); } /* Determine if lock sys_fl blocks lock caller_fl. Common functionality @@ -811,6 +828,7 @@ static int flock_lock_file(struct file *filp, struct file_lock *request) struct inode * inode = file_inode(filp); int error = 0; int found = 0; + LIST_HEAD(dispose); if (!(request->fl_flags & FL_ACCESS) && (request->fl_type != F_UNLCK)) { new_fl = locks_alloc_lock(); @@ -833,7 +851,7 @@ static int flock_lock_file(struct file *filp, struct file_lock *request) if (request->fl_type == fl->fl_type) goto out; found = 1; - locks_delete_lock(before); + locks_delete_lock(before, &dispose); break; } @@ -880,6 +898,7 @@ out: spin_unlock(&inode->i_lock); if (new_fl) locks_free_lock(new_fl); + locks_dispose_list(&dispose); return error; } @@ -893,6 +912,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str struct file_lock **before; int error; bool added = false; + LIST_HEAD(dispose); /* * We may need two file_lock structures for this operation, @@ -988,7 +1008,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str else request->fl_end = fl->fl_end; if (added) { - locks_delete_lock(before); + locks_delete_lock(before, &dispose); continue; } request = fl; @@ -1018,21 +1038,24 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str * one (This may happen several times). */ if (added) { - locks_delete_lock(before); + locks_delete_lock(before, &dispose); continue; } - /* Replace the old lock with the new one. - * Wake up anybody waiting for the old one, - * as the change in lock type might satisfy - * their needs. + /* + * Replace the old lock with new_fl, and + * remove the old one. It's safe to do the + * insert here since we know that we won't be + * using new_fl later, and that the lock is + * just replacing an existing lock. */ - locks_wake_up_blocks(fl); - fl->fl_start = request->fl_start; - fl->fl_end = request->fl_end; - fl->fl_type = request->fl_type; - locks_release_private(fl); - locks_copy_private(fl, request); - request = fl; + error = -ENOLCK; + if (!new_fl) + goto out; + locks_copy_lock(new_fl, request); + request = new_fl; + new_fl = NULL; + locks_delete_lock(before, &dispose); + locks_insert_lock(before, request); added = true; } } @@ -1093,6 +1116,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str locks_free_lock(new_fl); if (new_fl2) locks_free_lock(new_fl2); + locks_dispose_list(&dispose); return error; } @@ -1268,7 +1292,7 @@ int lease_modify(struct file_lock **before, int arg) printk(KERN_ERR "locks_delete_lock: fasync == %p\n", fl->fl_fasync); fl->fl_fasync = NULL; } - locks_delete_lock(before); + locks_delete_lock(before, NULL); } return 0; } @@ -1737,13 +1761,10 @@ static int do_fcntl_add_lease(unsigned int fd, struct file *filp, long arg) ret = fl; spin_lock(&inode->i_lock); error = __vfs_setlease(filp, arg, &ret); - if (error) { - spin_unlock(&inode->i_lock); - locks_free_lock(fl); - goto out_free_fasync; - } - if (ret != fl) - locks_free_lock(fl); + if (error) + goto out_unlock; + if (ret == fl) + fl = NULL; /* * fasync_insert_entry() returns the old entry if any. @@ -1755,9 +1776,10 @@ static int do_fcntl_add_lease(unsigned int fd, struct file *filp, long arg) new = NULL; error = __f_setown(filp, task_pid(current), PIDTYPE_PID, 0); +out_unlock: spin_unlock(&inode->i_lock); - -out_free_fasync: + if (fl) + locks_free_lock(fl); if (new) fasync_free(new); return error; @@ -2320,6 +2342,7 @@ void locks_remove_file(struct file *filp) struct inode * inode = file_inode(filp); struct file_lock *fl; struct file_lock **before; + LIST_HEAD(dispose); if (!inode->i_flock) return; @@ -2365,12 +2388,13 @@ void locks_remove_file(struct file *filp) fl->fl_type, fl->fl_flags, fl->fl_start, fl->fl_end); - locks_delete_lock(before); + locks_delete_lock(before, &dispose); continue; } before = &fl->fl_next; } spin_unlock(&inode->i_lock); + locks_dispose_list(&dispose); } /** @@ -2452,7 +2476,11 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl, seq_puts(f, "FLOCK ADVISORY "); } } else if (IS_LEASE(fl)) { - seq_puts(f, "LEASE "); + if (fl->fl_flags & FL_DELEG) + seq_puts(f, "DELEG "); + else + seq_puts(f, "LEASE "); + if (lease_breaking(fl)) seq_puts(f, "BREAKING "); else if (fl->fl_file) diff --git a/kernel/module.c b/kernel/module.c index 6f69463f0066..03214bd288e9 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -3304,6 +3304,11 @@ static int load_module(struct load_info *info, const char __user *uargs, mutex_lock(&module_mutex); module_bug_cleanup(mod); mutex_unlock(&module_mutex); + + /* we can't deallocate the module until we clear memory protection */ + unset_module_init_ro_nx(mod); + unset_module_core_ro_nx(mod); + ddebug_cleanup: dynamic_debug_remove(info->debug); synchronize_sched(); diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index d0396af99fa0..5b1b807265a1 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -267,90 +267,90 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr) /* * Example Format w/ field column widths: * - * Package Core CPU Avg_MHz Bzy_MHz TSC_MHz SMI %Busy CPU_%c1 CPU_%c3 CPU_%c6 CPU_%c7 CoreTmp PkgTmp Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 PkgWatt CorWatt GFXWatt - * 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 1234567 + * Package Core CPU Avg_MHz Bzy_MHz TSC_MHz SMI %Busy CPU_%c1 CPU_%c3 CPU_%c6 CPU_%c7 CoreTmp PkgTmp Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 PkgWatt CorWatt GFXWatt + * 123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678 */ void print_header(void) { if (show_pkg) - outp += sprintf(outp, "Package "); + outp += sprintf(outp, " Package"); if (show_core) - outp += sprintf(outp, " Core "); + outp += sprintf(outp, " Core"); if (show_cpu) - outp += sprintf(outp, " CPU "); + outp += sprintf(outp, " CPU"); if (has_aperf) - outp += sprintf(outp, "Avg_MHz "); + outp += sprintf(outp, " Avg_MHz"); if (do_nhm_cstates) - outp += sprintf(outp, " %%Busy "); + outp += sprintf(outp, " %%Busy"); if (has_aperf) - outp += sprintf(outp, "Bzy_MHz "); - outp += sprintf(outp, "TSC_MHz "); + outp += sprintf(outp, " Bzy_MHz"); + outp += sprintf(outp, " TSC_MHz"); if (do_smi) - outp += sprintf(outp, " SMI "); + outp += sprintf(outp, " SMI"); if (extra_delta_offset32) - outp += sprintf(outp, " count 0x%03X ", extra_delta_offset32); + outp += sprintf(outp, " count 0x%03X", extra_delta_offset32); if (extra_delta_offset64) - outp += sprintf(outp, " COUNT 0x%03X ", extra_delta_offset64); + outp += sprintf(outp, " COUNT 0x%03X", extra_delta_offset64); if (extra_msr_offset32) - outp += sprintf(outp, " MSR 0x%03X ", extra_msr_offset32); + outp += sprintf(outp, " MSR 0x%03X", extra_msr_offset32); if (extra_msr_offset64) - outp += sprintf(outp, " MSR 0x%03X ", extra_msr_offset64); + outp += sprintf(outp, " MSR 0x%03X", extra_msr_offset64); if (do_nhm_cstates) - outp += sprintf(outp, " CPU%%c1 "); + outp += sprintf(outp, " CPU%%c1"); if (do_nhm_cstates && !do_slm_cstates) - outp += sprintf(outp, " CPU%%c3 "); + outp += sprintf(outp, " CPU%%c3"); if (do_nhm_cstates) - outp += sprintf(outp, " CPU%%c6 "); + outp += sprintf(outp, " CPU%%c6"); if (do_snb_cstates) - outp += sprintf(outp, " CPU%%c7 "); + outp += sprintf(outp, " CPU%%c7"); if (do_dts) - outp += sprintf(outp, "CoreTmp "); + outp += sprintf(outp, " CoreTmp"); if (do_ptm) - outp += sprintf(outp, " PkgTmp "); + outp += sprintf(outp, " PkgTmp"); if (do_snb_cstates) - outp += sprintf(outp, "Pkg%%pc2 "); + outp += sprintf(outp, " Pkg%%pc2"); if (do_nhm_cstates && !do_slm_cstates) - outp += sprintf(outp, "Pkg%%pc3 "); + outp += sprintf(outp, " Pkg%%pc3"); if (do_nhm_cstates && !do_slm_cstates) - outp += sprintf(outp, "Pkg%%pc6 "); + outp += sprintf(outp, " Pkg%%pc6"); if (do_snb_cstates) - outp += sprintf(outp, "Pkg%%pc7 "); + outp += sprintf(outp, " Pkg%%pc7"); if (do_c8_c9_c10) { - outp += sprintf(outp, "Pkg%%pc8 "); - outp += sprintf(outp, "Pkg%%pc9 "); - outp += sprintf(outp, "Pk%%pc10 "); + outp += sprintf(outp, " Pkg%%pc8"); + outp += sprintf(outp, " Pkg%%pc9"); + outp += sprintf(outp, " Pk%%pc10"); } if (do_rapl && !rapl_joules) { if (do_rapl & RAPL_PKG) - outp += sprintf(outp, "PkgWatt "); + outp += sprintf(outp, " PkgWatt"); if (do_rapl & RAPL_CORES) - outp += sprintf(outp, "CorWatt "); + outp += sprintf(outp, " CorWatt"); if (do_rapl & RAPL_GFX) - outp += sprintf(outp, "GFXWatt "); + outp += sprintf(outp, " GFXWatt"); if (do_rapl & RAPL_DRAM) - outp += sprintf(outp, "RAMWatt "); + outp += sprintf(outp, " RAMWatt"); if (do_rapl & RAPL_PKG_PERF_STATUS) - outp += sprintf(outp, " PKG_%% "); + outp += sprintf(outp, " PKG_%%"); if (do_rapl & RAPL_DRAM_PERF_STATUS) - outp += sprintf(outp, " RAM_%% "); + outp += sprintf(outp, " RAM_%%"); } else { if (do_rapl & RAPL_PKG) - outp += sprintf(outp, " Pkg_J "); + outp += sprintf(outp, " Pkg_J"); if (do_rapl & RAPL_CORES) - outp += sprintf(outp, " Cor_J "); + outp += sprintf(outp, " Cor_J"); if (do_rapl & RAPL_GFX) - outp += sprintf(outp, " GFX_J "); + outp += sprintf(outp, " GFX_J"); if (do_rapl & RAPL_DRAM) - outp += sprintf(outp, " RAM_W "); + outp += sprintf(outp, " RAM_W"); if (do_rapl & RAPL_PKG_PERF_STATUS) - outp += sprintf(outp, " PKG_%% "); + outp += sprintf(outp, " PKG_%%"); if (do_rapl & RAPL_DRAM_PERF_STATUS) - outp += sprintf(outp, " RAM_%% "); - outp += sprintf(outp, " time "); + outp += sprintf(outp, " RAM_%%"); + outp += sprintf(outp, " time"); } outp += sprintf(outp, "\n"); diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c index bf06577fea51..5819a2708d7e 100644 --- a/virt/kvm/assigned-dev.c +++ b/virt/kvm/assigned-dev.c @@ -526,8 +526,10 @@ static int assign_guest_irq(struct kvm *kvm, dev->irq_requested_type |= guest_irq_type; if (dev->ack_notifier.gsi != -1) kvm_register_irq_ack_notifier(kvm, &dev->ack_notifier); - } else + } else { kvm_free_irq_source_id(kvm, dev->irq_source_id); + dev->irq_source_id = -1; + } return r; } diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c index 0df7d4b34dfe..714b94932312 100644 --- a/virt/kvm/iommu.c +++ b/virt/kvm/iommu.c @@ -61,6 +61,14 @@ static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn, return pfn; } +static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages) +{ + unsigned long i; + + for (i = 0; i < npages; ++i) + kvm_release_pfn_clean(pfn + i); +} + int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot) { gfn_t gfn, end_gfn; @@ -123,6 +131,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot) if (r) { printk(KERN_ERR "kvm_iommu_map_address:" "iommu failed to map pfn=%llx\n", pfn); + kvm_unpin_pages(kvm, pfn, page_size); goto unmap_pages; } @@ -134,7 +143,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot) return 0; unmap_pages: - kvm_iommu_put_pages(kvm, slot->base_gfn, gfn); + kvm_iommu_put_pages(kvm, slot->base_gfn, gfn - slot->base_gfn); return r; } @@ -266,14 +275,6 @@ out_unlock: return r; } -static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages) -{ - unsigned long i; - - for (i = 0; i < npages; ++i) - kvm_release_pfn_clean(pfn + i); -} - static void kvm_iommu_put_pages(struct kvm *kvm, gfn_t base_gfn, unsigned long npages) { |